diff options
1056 files changed, 22232 insertions, 8943 deletions
@@ -70,6 +70,7 @@ Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Brian Avery <b.avery@hp.com> Brian King <brking@us.ibm.com> +Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com> Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> Chao Yu <chao@kernel.org> <chao2.yu@samsung.com> @@ -79,6 +80,9 @@ Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org> Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com> Christian Borntraeger <borntraeger@linux.ibm.com> <cborntra@de.ibm.com> Christian Borntraeger <borntraeger@linux.ibm.com> <borntrae@de.ibm.com> +Christian Brauner <brauner@kernel.org> <christian@brauner.io> +Christian Brauner <brauner@kernel.org> <christian.brauner@canonical.com> +Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com> Christophe Ricard <christophe.ricard@gmail.com> Christoph Hellwig <hch@lst.de> Colin Ian King <colin.king@intel.com> <colin.king@canonical.com> diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst index f2b3439edcc2..860fe651d645 100644 --- a/Documentation/accounting/psi.rst +++ b/Documentation/accounting/psi.rst @@ -92,7 +92,8 @@ Triggers can be set on more than one psi metric and more than one trigger for the same psi metric can be specified. However for each trigger a separate file descriptor is required to be able to poll it separately from others, therefore for each trigger a separate open() syscall should be made even -when opening the same psi interface file. +when opening the same psi interface file. Write operations to a file descriptor +with an already existing psi trigger will fail with EBUSY. Monitors activate only when system enters stall state for the monitored psi metric and deactivates upon exit from the stall state. While system is diff --git a/Documentation/admin-guide/gpio/index.rst b/Documentation/admin-guide/gpio/index.rst index 7db367572f30..f6861ca16ffe 100644 --- a/Documentation/admin-guide/gpio/index.rst +++ b/Documentation/admin-guide/gpio/index.rst @@ -10,6 +10,7 @@ gpio gpio-aggregator sysfs gpio-mockup + gpio-sim .. only:: subproject and html diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 4150f74c521a..f86b5e1623c6 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -365,6 +365,15 @@ new netns has been created. Default : 0 (for compatibility reasons) +txrehash +-------- + +Controls default hash rethink behaviour on listening socket when SO_TXREHASH +option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). + +If set to 1 (default), hash rethink is performed on listening socket. +If set to 0, hash rethink is not performed. + 2. /proc/sys/net/unix - Parameters for Unix domain sockets ---------------------------------------------------------- diff --git a/Documentation/arm/marvell.rst b/Documentation/arm/marvell.rst index 9485a5a2e2e9..2f41caa0096c 100644 --- a/Documentation/arm/marvell.rst +++ b/Documentation/arm/marvell.rst @@ -266,10 +266,12 @@ Avanta family ------------- Flavors: + - 88F6500 - 88F6510 - 88F6530P - 88F6550 - 88F6560 + - 88F6601 Homepage: https://web.archive.org/web/20181005145041/http://www.marvell.com/broadband/ diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 5342e895fb60..0ec7b7f1524b 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -52,6 +52,12 @@ stable kernels. | Allwinner | A64/R18 | UNKNOWN1 | SUN50I_ERRATUM_UNKNOWN1 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2064142 | ARM64_ERRATUM_2064142 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2038923 | ARM64_ERRATUM_2038923 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #1902691 | ARM64_ERRATUM_1902691 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #826319 | ARM64_ERRATUM_826319 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A53 | #827319 | ARM64_ERRATUM_827319 | @@ -92,12 +98,18 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2051678 | ARM64_ERRATUM_2051678 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2054223 | ARM64_ERRATUM_2054223 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 1ebf4c5c7ddc..ab08852e53ae 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -565,18 +565,15 @@ A map can be created with ``btf_fd`` and specified key/value type id.:: In libbpf, the map can be defined with extra annotation like below: :: - struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, - }; - BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); + struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct ipv_counts); + __uint(max_entries, 4); + } btf_map SEC(".maps"); -Here, the parameters for macro BPF_ANNOTATE_KV_PAIR are map name, key and -value types for the map. During ELF parsing, libbpf is able to extract -key/value type_id's and assign them to BPF_MAP_CREATE attributes -automatically. +During ELF parsing, libbpf is able to extract key/value type_id's and assign +them to BPF_MAP_CREATE attributes automatically. .. _BPF_Prog_Load: @@ -824,13 +821,12 @@ structure has bitfields. For example, for the following map,:: ___A b1:4; enum A b2:4; }; - struct bpf_map_def SEC("maps") tmpmap = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(struct tmp_t), - .max_entries = 1, - }; - BPF_ANNOTATE_KV_PAIR(tmpmap, int, struct tmp_t); + struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct tmp_t); + __uint(max_entries, 1); + } tmpmap SEC(".maps"); bpftool is able to pretty print like below: :: diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst index dcefee707ccd..a833ecf12fbc 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -7,6 +7,14 @@ directory. These are intended to be small tests to exercise individual code paths in the kernel. Tests are intended to be run after building, installing and booting a kernel. +Kselftest from mainline can be run on older stable kernels. Running tests +from mainline offers the best coverage. Several test rings run mainline +kselftest suite on stable releases. The reason is that when a new test +gets added to test existing code to regression test a bug, we should be +able to run that test on an older kernel. Hence, it is important to keep +code that can still test an older kernel and make sure it skips the test +gracefully on newer releases. + You can find additional information on Kselftest framework, how to write new tests using the framework on Kselftest wiki: diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml index 79d0358e2f61..620f01775e42 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml @@ -36,6 +36,7 @@ properties: - renesas,intc-ex-r8a77980 # R-Car V3H - renesas,intc-ex-r8a77990 # R-Car E3 - renesas,intc-ex-r8a77995 # R-Car D3 + - renesas,intc-ex-r8a779a0 # R-Car V3U - const: renesas,irqc '#interrupt-cells': diff --git a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml index 28b6b17fe4b2..0dfa6b26e099 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml @@ -62,6 +62,7 @@ properties: interrupts-extended: minItems: 1 + maxItems: 15872 description: Specifies which contexts are connected to the PLIC, with "-1" specifying that a context is not present. Each node pointed to should be a @@ -90,12 +91,11 @@ examples: #interrupt-cells = <1>; compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; interrupt-controller; - interrupts-extended = < - &cpu0_intc 11 - &cpu1_intc 11 &cpu1_intc 9 - &cpu2_intc 11 &cpu2_intc 9 - &cpu3_intc 11 &cpu3_intc 9 - &cpu4_intc 11 &cpu4_intc 9>; + interrupts-extended = <&cpu0_intc 11>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>; reg = <0xc000000 0x4000000>; riscv,ndev = <10>; }; diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt index 0968b40aef1e..e3501bfa22e9 100644 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -31,7 +31,7 @@ tcan4x5x: tcan4x5x@0 { #address-cells = <1>; #size-cells = <1>; spi-max-frequency = <10000000>; - bosch,mram-cfg = <0x0 0 0 32 0 0 1 1>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; interrupt-parent = <&gpio1>; interrupts = <14 IRQ_TYPE_LEVEL_LOW>; device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; diff --git a/Documentation/devicetree/bindings/net/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index 8dd06db34169..6cd3d853dcba 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -81,6 +81,25 @@ properties: phy-handle: true + phys: + maxItems: 1 + + phy-names: + const: sgmii-phy + description: + Required with ZynqMP SoC when in SGMII mode. + Should reference PS-GTR generic PHY device for this controller + instance. See ZynqMP example. + + resets: + maxItems: 1 + description: + Recommended with ZynqMP, specify reset control for this + controller instance with zynqmp-reset driver. + + reset-names: + maxItems: 1 + fixed-link: true iommus: @@ -157,3 +176,40 @@ examples: reset-gpios = <&pioE 6 1>; }; }; + + - | + #include <dt-bindings/clock/xlnx-zynqmp-clk.h> + #include <dt-bindings/power/xlnx-zynqmp-power.h> + #include <dt-bindings/reset/xlnx-zynqmp-resets.h> + #include <dt-bindings/phy/phy.h> + + bus { + #address-cells = <2>; + #size-cells = <2>; + gem1: ethernet@ff0c0000 { + compatible = "cdns,zynqmp-gem", "cdns,gem"; + interrupt-parent = <&gic>; + interrupts = <0 59 4>, <0 59 4>; + reg = <0x0 0xff0c0000 0x0 0x1000>; + clocks = <&zynqmp_clk LPD_LSBUS>, <&zynqmp_clk GEM1_REF>, + <&zynqmp_clk GEM1_TX>, <&zynqmp_clk GEM1_RX>, + <&zynqmp_clk GEM_TSU>; + clock-names = "pclk", "hclk", "tx_clk", "rx_clk", "tsu_clk"; + #address-cells = <1>; + #size-cells = <0>; + #stream-id-cells = <1>; + iommus = <&smmu 0x875>; + power-domains = <&zynqmp_firmware PD_ETH_1>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>; + reset-names = "gem1_rst"; + status = "okay"; + phy-mode = "sgmii"; + phy-names = "sgmii-phy"; + phys = <&psgtr 1 PHY_TYPE_SGMII 1 1>; + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 84985f53bffd..184152087b60 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -42,6 +42,12 @@ properties: description: Set if the output SYNCLKO frequency should be set to 125MHz instead of 25MHz. + microchip,synclko-disable: + $ref: /schemas/types.yaml#/definitions/flag + description: + Set if the output SYNCLKO clock should be disabled. Do not mix with + microchip,synclko-125. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt index 020337f3c05f..801efc7d6818 100644 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ b/Documentation/devicetree/bindings/net/fsl-fman.txt @@ -388,14 +388,24 @@ PROPERTIES Value type: <prop-encoded-array> Definition: A standard property. -- bus-frequency +- clocks + Usage: optional + Value type: <phandle> + Definition: A reference to the input clock of the controller + from which the MDC frequency is derived. + +- clock-frequency Usage: optional Value type: <u32> - Definition: Specifies the external MDIO bus clock speed to - be used, if different from the standard 2.5 MHz. - This may be due to the standard speed being unsupported (e.g. - due to a hardware problem), or to advertise that all relevant - components in the system support a faster speed. + Definition: Specifies the external MDC frequency, in Hertz, to + be used. Requires that the input clock is specified in the + "clocks" property. See also: mdio.yaml. + +- suppress-preamble + Usage: optional + Value type: <boolean> + Definition: Disable generation of preamble bits. See also: + mdio.yaml. - interrupts Usage: required for external MDIO diff --git a/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml b/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml index e79e4e166ad8..13812768b923 100644 --- a/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml +++ b/Documentation/devicetree/bindings/net/microchip,lan966x-switch.yaml @@ -38,6 +38,7 @@ properties: - description: register based extraction - description: frame dma based extraction - description: analyzer interrupt + - description: ptp interrupt interrupt-names: minItems: 1 @@ -45,6 +46,7 @@ properties: - const: xtr - const: fdma - const: ana + - const: ptp resets: items: diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml index b86edf67ce62..58ecc62adfaa 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml @@ -107,6 +107,10 @@ properties: - const: imem - const: config + qcom,qmp: + $ref: /schemas/types.yaml#/definitions/phandle + description: phandle to the AOSS side-channel message RAM + qcom,smem-states: $ref: /schemas/types.yaml#/definitions/phandle-array description: State bits used in by the AP to signal the modem. @@ -222,6 +226,8 @@ examples: "imem", "config"; + qcom,qmp = <&aoss_qmp>; + qcom,smem-states = <&ipa_smp2p_out 0>, <&ipa_smp2p_out 1>; qcom,smem-state-names = "ipa-clock-enabled-valid", diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml index 5dd209206e88..3ec2d7b83775 100644 --- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml @@ -23,8 +23,9 @@ properties: minItems: 1 maxItems: 256 items: - minimum: 0 - maximum: 256 + items: + - minimum: 0 + maximum: 256 description: Chip select used by the device. diff --git a/Documentation/index.rst b/Documentation/index.rst index 2b4de3926858..b58692d687f6 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -166,6 +166,7 @@ to ReStructured Text format, or are simply too old. .. toctree:: :maxdepth: 2 + tools/index staging/index watch_queue diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst index e6cd40663ea5..4cbd50edf277 100644 --- a/Documentation/kernel-hacking/locking.rst +++ b/Documentation/kernel-hacking/locking.rst @@ -295,7 +295,7 @@ Pete Zaitcev gives the following summary: - If you are in a process context (any syscall) and want to lock other process out, use a mutex. You can take a mutex and sleep - (``copy_from_user*(`` or ``kmalloc(x,GFP_KERNEL)``). + (``copy_from_user()`` or ``kmalloc(x,GFP_KERNEL)``). - Otherwise (== data can be touched in an interrupt), use spin_lock_irqsave() and diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 9d98e0511249..cae28af7a476 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -860,8 +860,16 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ==================================== ====== =========================== +``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with +page-flipping TCP zero-copy receive (``getsockopt(TCP_ZEROCOPY_RECEIVE)``). +If enabled the device is configured to place frame headers and data into +separate buffers. The device configuration must make it possible to receive +full memory pages of data, for example because MTU is high enough or through +HW-GRO. + RINGS_SET ========= diff --git a/Documentation/tools/index.rst b/Documentation/tools/index.rst new file mode 100644 index 000000000000..0bb1e61bdcc0 --- /dev/null +++ b/Documentation/tools/index.rst @@ -0,0 +1,20 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +Kernel tools +============ + +This book covers user-space tools that are shipped with the kernel source; +more additions are needed here: + +.. toctree:: + :maxdepth: 1 + + rtla/index + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/tools/rtla/index.rst b/Documentation/tools/rtla/index.rst new file mode 100644 index 000000000000..840f0bf3e803 --- /dev/null +++ b/Documentation/tools/rtla/index.rst @@ -0,0 +1,26 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================ +The realtime Linux analysis tool +================================ + +RTLA provides a set of tools for the analysis of the kernel's realtime +behavior on specific hardware. + +.. toctree:: + :maxdepth: 1 + + rtla + rtla-osnoise + rtla-osnoise-hist + rtla-osnoise-top + rtla-timerlat + rtla-timerlat-hist + rtla-timerlat-top + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index bb8cfddbb22d..a4267104db50 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -3268,6 +3268,7 @@ number. :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device (no set) :Type: device ioctl, vm ioctl, vcpu ioctl :Parameters: struct kvm_device_attr :Returns: 0 on success, -1 on error @@ -3302,7 +3303,8 @@ transferred is defined by the particular attribute. ------------------------ :Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device, - KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_VCPU_ATTRIBUTES for vcpu device + KVM_CAP_SYS_ATTRIBUTES for system (/dev/kvm) device :Type: device ioctl, vm ioctl, vcpu ioctl :Parameters: struct kvm_device_attr :Returns: 0 on success, -1 on error diff --git a/Documentation/vm/page_table_check.rst b/Documentation/vm/page_table_check.rst index 81f521ff7ea7..1a09472f10a3 100644 --- a/Documentation/vm/page_table_check.rst +++ b/Documentation/vm/page_table_check.rst @@ -9,7 +9,7 @@ Page Table Check Introduction ============ -Page table check allows to hardern the kernel by ensuring that some types of +Page table check allows to harden the kernel by ensuring that some types of the memory corruptions are prevented. Page table check performs extra verifications at the time when new pages become diff --git a/MAINTAINERS b/MAINTAINERS index ea3e6c914384..c7169da15ab4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -190,8 +190,9 @@ M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git +Q: https://patchwork.kernel.org/project/linux-wireless/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git F: Documentation/driver-api/80211/cfg80211.rst F: Documentation/networking/regulatory.rst F: include/linux/ieee80211.h @@ -4156,9 +4157,8 @@ N: csky K: csky CA8210 IEEE-802.15.4 RADIO DRIVER -M: Harry Morris <h.morris@cascoda.com> L: linux-wpan@vger.kernel.org -S: Maintained +S: Orphan W: https://github.com/Cascoda/ca8210-linux.git F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c @@ -7208,8 +7208,10 @@ F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ F: include/dt-bindings/net/qca-ar803x.h +F: include/linux/linkmode.h F: include/linux/*mdio*.h F: include/linux/mdio/*.h +F: include/linux/mii.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h @@ -11366,8 +11368,9 @@ M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git +Q: https://patchwork.kernel.org/project/linux-wireless/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git F: Documentation/networking/mac80211-injection.rst F: Documentation/networking/mac80211_hwsim/mac80211_hwsim.rst F: drivers/net/wireless/mac80211_hwsim.[ch] @@ -13374,9 +13377,10 @@ NETWORKING DRIVERS (WIRELESS) M: Kalle Valo <kvalo@kernel.org> L: linux-wireless@vger.kernel.org S: Maintained -Q: http://patchwork.kernel.org/project/linux-wireless/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next.git +W: https://wireless.wiki.kernel.org/ +Q: https://patchwork.kernel.org/project/linux-wireless/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git F: Documentation/devicetree/bindings/net/wireless/ F: drivers/net/wireless/ @@ -13449,7 +13453,11 @@ L: netdev@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git F: arch/x86/net/* +F: include/linux/ip.h +F: include/linux/ipv6* +F: include/net/fib* F: include/net/ip* +F: include/net/route.h F: net/ipv4/ F: net/ipv6/ @@ -13510,10 +13518,6 @@ F: include/net/tls.h F: include/uapi/linux/tls.h F: net/tls/* -NETWORKING [WIRELESS] -L: linux-wireless@vger.kernel.org -Q: http://patchwork.kernel.org/project/linux-wireless/list/ - NETXEN (1/10) GbE SUPPORT M: Manish Chopra <manishc@marvell.com> M: Rahul Verma <rahulv@marvell.com> @@ -16347,8 +16351,7 @@ REALTEK RTL83xx SMI DSA ROUTER CHIPS M: Linus Walleij <linus.walleij@linaro.org> S: Maintained F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt -F: drivers/net/dsa/realtek-smi* -F: drivers/net/dsa/rtl83* +F: drivers/net/dsa/realtek/* REALTEK WIRELESS DRIVER (rtlwifi family) M: Ping-Ke Shih <pkshih@realtek.com> @@ -16532,8 +16535,9 @@ M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git +Q: https://patchwork.kernel.org/project/linux-wireless/list/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git F: Documentation/ABI/stable/sysfs-class-rfkill F: Documentation/driver-api/rfkill.rst F: include/linux/rfkill.h @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Gobble Gobble # *DOCUMENTATION* diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 284d28755b8d..7d81535893af 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -133,6 +133,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fabe39169b12..4c97cb40eebb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -83,6 +83,7 @@ config ARM select HAVE_EBPF_JIT if !CPU_ENDIAN_BE32 select HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT + select HAVE_BUILDTIME_MCOUNT_SORT select HAVE_DEBUG_KMEMLEAK if !XIP_KERNEL select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 7d23d4bb2168..6fe67963ba5a 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -288,6 +288,7 @@ */ #define ALT_UP(instr...) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ 9997: instr ;\ .if . - 9997b == 2 ;\ @@ -299,6 +300,7 @@ .popsection #define ALT_UP_B(label) \ .pushsection ".alt.smp.init", "a" ;\ + .align 2 ;\ .long 9998b - . ;\ W(b) . + (label - 9998b) ;\ .popsection diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 6af68edfa53a..bdc35c0e8dfb 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -96,6 +96,7 @@ unsigned long __get_wchan(struct task_struct *p); #define __ALT_SMP_ASM(smp, up) \ "9998: " smp "\n" \ " .pushsection \".alt.smp.init\", \"a\"\n" \ + " .align 2\n" \ " .long 9998b - .\n" \ " " up "\n" \ " .popsection\n" diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 36fbc3329252..32dbfd81f42a 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -11,6 +11,7 @@ #include <linux/string.h> #include <asm/memory.h> #include <asm/domain.h> +#include <asm/unaligned.h> #include <asm/unified.h> #include <asm/compiler.h> @@ -497,7 +498,10 @@ do { \ } \ default: __err = __get_user_bad(); break; \ } \ - *(type *)(dst) = __val; \ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) \ + put_unaligned(__val, (type *)(dst)); \ + else \ + *(type *)(dst) = __val; /* aligned by caller */ \ if (__err) \ goto err_label; \ } while (0) @@ -507,7 +511,9 @@ do { \ const type *__pk_ptr = (dst); \ unsigned long __dst = (unsigned long)__pk_ptr; \ int __err = 0; \ - type __val = *(type *)src; \ + type __val = IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \ + ? get_unaligned((type *)(src)) \ + : *(type *)(src); /* aligned by caller */ \ switch (sizeof(type)) { \ case 1: __put_user_asm_byte(__val, __dst, __err, ""); break; \ case 2: __put_user_asm_half(__val, __dst, __err, ""); break; \ diff --git a/arch/arm/probes/kprobes/Makefile b/arch/arm/probes/kprobes/Makefile index 14db56f49f0a..6159010dac4a 100644 --- a/arch/arm/probes/kprobes/Makefile +++ b/arch/arm/probes/kprobes/Makefile @@ -1,4 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 +KASAN_SANITIZE_actions-common.o := n +KASAN_SANITIZE_actions-arm.o := n +KASAN_SANITIZE_actions-thumb.o := n obj-$(CONFIG_KPROBES) += core.o actions-common.o checkers-common.o obj-$(CONFIG_ARM_KPROBES_TEST) += test-kprobes.o test-kprobes-objs := test-core.o diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6978140edfa4..f2b5a4abef21 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -670,15 +670,25 @@ config ARM64_ERRATUM_1508412 config ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE bool +config ARM64_ERRATUM_2051678 + bool "Cortex-A510: 2051678: disable Hardware Update of the page table dirty bit" + help + This options adds the workaround for ARM Cortex-A510 erratum ARM64_ERRATUM_2051678. + Affected Coretex-A510 might not respect the ordering rules for + hardware update of the page table's dirty bit. The workaround + is to not enable the feature on affected CPUs. + + If unsure, say Y. + config ARM64_ERRATUM_2119858 - bool "Cortex-A710: 2119858: workaround TRBE overwriting trace data in FILL mode" + bool "Cortex-A710/X2: 2119858: workaround TRBE overwriting trace data in FILL mode" default y depends on CORESIGHT_TRBE select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE help - This option adds the workaround for ARM Cortex-A710 erratum 2119858. + This option adds the workaround for ARM Cortex-A710/X2 erratum 2119858. - Affected Cortex-A710 cores could overwrite up to 3 cache lines of trace + Affected Cortex-A710/X2 cores could overwrite up to 3 cache lines of trace data at the base of the buffer (pointed to by TRBASER_EL1) in FILL mode in the event of a WRAP event. @@ -761,14 +771,14 @@ config ARM64_ERRATUM_2253138 If unsure, say Y. config ARM64_ERRATUM_2224489 - bool "Cortex-A710: 2224489: workaround TRBE writing to address out-of-range" + bool "Cortex-A710/X2: 2224489: workaround TRBE writing to address out-of-range" depends on CORESIGHT_TRBE default y select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE help - This option adds the workaround for ARM Cortex-A710 erratum 2224489. + This option adds the workaround for ARM Cortex-A710/X2 erratum 2224489. - Affected Cortex-A710 cores might write to an out-of-range address, not reserved + Affected Cortex-A710/X2 cores might write to an out-of-range address, not reserved for TRBE. Under some conditions, the TRBE might generate a write to the next virtually addressed page following the last page of the TRBE address space (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base. @@ -778,6 +788,65 @@ config ARM64_ERRATUM_2224489 If unsure, say Y. +config ARM64_ERRATUM_2064142 + bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2064142. + + Affected Cortex-A510 core might fail to write into system registers after the + TRBE has been disabled. Under some conditions after the TRBE has been disabled + writes into TRBE registers TRBLIMITR_EL1, TRBPTR_EL1, TRBBASER_EL1, TRBSR_EL1, + and TRBTRG_EL1 will be ignored and will not be effected. + + Work around this in the driver by executing TSB CSYNC and DSB after collection + is stopped and before performing a system register write to one of the affected + registers. + + If unsure, say Y. + +config ARM64_ERRATUM_2038923 + bool "Cortex-A510: 2038923: workaround TRBE corruption with enable" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 2038923. + + Affected Cortex-A510 core might cause an inconsistent view on whether trace is + prohibited within the CPU. As a result, the trace buffer or trace buffer state + might be corrupted. This happens after TRBE buffer has been enabled by setting + TRBLIMITR_EL1.E, followed by just a single context synchronization event before + execution changes from a context, in which trace is prohibited to one where it + isn't, or vice versa. In these mentioned conditions, the view of whether trace + is prohibited is inconsistent between parts of the CPU, and the trace buffer or + the trace buffer state might be corrupted. + + Work around this in the driver by preventing an inconsistent view of whether the + trace is prohibited or not based on TRBLIMITR_EL1.E by immediately following a + change to TRBLIMITR_EL1.E with at least one ISB instruction before an ERET, or + two ISB instructions if no ERET is to take place. + + If unsure, say Y. + +config ARM64_ERRATUM_1902691 + bool "Cortex-A510: 1902691: workaround TRBE trace corruption" + depends on COMPILE_TEST # Until the CoreSight TRBE driver changes are in + default y + help + This option adds the workaround for ARM Cortex-A510 erratum 1902691. + + Affected Cortex-A510 core might cause trace data corruption, when being written + into the memory. Effectively TRBE is broken and hence cannot be used to capture + trace data. + + Work around this problem in the driver by just preventing TRBE initialization on + affected cpus. The firmware must have disabled the access to TRBE for the kernel + on such implementations. This will cover the kernel for any firmware that doesn't + do this already. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 74e66443e4ce..9bec3ba20c69 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -512,6 +512,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x874>; power-domains = <&zynqmp_firmware PD_ETH_0>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM0>; + reset-names = "gem0_rst"; }; gem1: ethernet@ff0c0000 { @@ -526,6 +528,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x875>; power-domains = <&zynqmp_firmware PD_ETH_1>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM1>; + reset-names = "gem1_rst"; }; gem2: ethernet@ff0d0000 { @@ -540,6 +544,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x876>; power-domains = <&zynqmp_firmware PD_ETH_2>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM2>; + reset-names = "gem2_rst"; }; gem3: ethernet@ff0e0000 { @@ -554,6 +560,8 @@ #stream-id-cells = <1>; iommus = <&smmu 0x877>; power-domains = <&zynqmp_firmware PD_ETH_3>; + resets = <&zynqmp_reset ZYNQMP_RESET_GEM3>; + reset-names = "gem3_rst"; }; gpio: gpio@ff0a0000 { diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 19b8441aa8f2..999b9149f856 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -73,7 +73,9 @@ #define ARM_CPU_PART_CORTEX_A76 0xD0B #define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define APM_CPU_PART_POTENZA 0x000 @@ -115,7 +117,9 @@ #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 9e1c1aef9ebd..066098198c24 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -347,6 +347,7 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_2119858 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_RANGE(MIDR_CORTEX_X2, 0, 0, 2, 0), #endif {}, }; @@ -371,6 +372,7 @@ static struct midr_range trbe_write_out_of_range_cpus[] = { #endif #ifdef CONFIG_ARM64_ERRATUM_2224489 MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_RANGE(MIDR_CORTEX_X2, 0, 0, 2, 0), #endif {}, }; @@ -598,6 +600,33 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2064142 + { + .desc = "ARM erratum 2064142", + .capability = ARM64_WORKAROUND_2064142, + + /* Cortex-A510 r0p0 - r0p2 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_2038923 + { + .desc = "ARM erratum 2038923", + .capability = ARM64_WORKAROUND_2038923, + + /* Cortex-A510 r0p0 - r0p2 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2) + }, +#endif +#ifdef CONFIG_ARM64_ERRATUM_1902691 + { + .desc = "ARM erratum 1902691", + .capability = ARM64_WORKAROUND_1902691, + + /* Cortex-A510 r0p0 - r0p1 */ + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 1) + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a46ab3b1c4d5..e5f23dab1c8d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1646,6 +1646,9 @@ static bool cpu_has_broken_dbm(void) /* Kryo4xx Silver (rdpe => r1p0) */ MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif +#ifdef CONFIG_ARM64_ERRATUM_2051678 + MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2), +#endif {}, }; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 0fb58fed54cb..e4103e085681 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -33,8 +33,8 @@ */ -static void start_backtrace(struct stackframe *frame, unsigned long fp, - unsigned long pc) +static notrace void start_backtrace(struct stackframe *frame, unsigned long fp, + unsigned long pc) { frame->fp = fp; frame->pc = pc; @@ -55,6 +55,7 @@ static void start_backtrace(struct stackframe *frame, unsigned long fp, frame->prev_fp = 0; frame->prev_type = STACK_TYPE_UNKNOWN; } +NOKPROBE_SYMBOL(start_backtrace); /* * Unwind from one frame record (A) to the next frame record (B). diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 60813497a381..172452f79e46 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -29,8 +29,11 @@ ldflags-y := -shared -soname=linux-vdso.so.1 --hash-style=sysv \ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO +# -Wmissing-prototypes and -Wmissing-declarations are removed from +# the CFLAGS of vgettimeofday.c to make possible to build the +# kernel with CONFIG_WERROR enabled. CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) \ - $(CC_FLAGS_LTO) + $(CC_FLAGS_LTO) -Wmissing-prototypes -Wmissing-declarations KASAN_SANITIZE := n KCSAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 0418399e0a20..c5d009715402 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -38,7 +38,10 @@ static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, u64 val) { - write_sysreg_el1(val, SYS_SPSR); + if (has_vhe()) + write_sysreg_el1(val, SYS_SPSR); + else + __vcpu_sys_reg(vcpu, SPSR_EL1) = val; } static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 844a6f003fd5..2cb3867eb7c2 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -983,13 +983,9 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, */ stage2_put_pte(ptep, mmu, addr, level, mm_ops); - if (need_flush) { - kvm_pte_t *pte_follow = kvm_pte_follow(pte, mm_ops); - - dcache_clean_inval_poc((unsigned long)pte_follow, - (unsigned long)pte_follow + - kvm_granule_size(level)); - } + if (need_flush && mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), + kvm_granule_size(level)); if (childp) mm_ops->put_page(childp); @@ -1151,15 +1147,13 @@ static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, struct kvm_pgtable *pgt = arg; struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; kvm_pte_t pte = *ptep; - kvm_pte_t *pte_follow; if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte)) return 0; - pte_follow = kvm_pte_follow(pte, mm_ops); - dcache_clean_inval_poc((unsigned long)pte_follow, - (unsigned long)pte_follow + - kvm_granule_size(level)); + if (mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(pte, mm_ops), + kvm_granule_size(level)); return 0; } diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 20db2f281cf2..4fb419f7b8b6 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -983,6 +983,9 @@ static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; /* IDbits */ val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; + /* SEIS */ + if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) + val |= BIT(ICC_CTLR_EL1_SEIS_SHIFT); /* A3V */ val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; /* EOImode */ diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index a33d4366b326..b549af8b1dc2 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -609,6 +609,18 @@ static int __init early_gicv4_enable(char *buf) } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); +static const struct midr_range broken_seis[] = { + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), + MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), + {}, +}; + +static bool vgic_v3_broken_seis(void) +{ + return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && + is_midr_in_range_list(read_cpuid_id(), broken_seis)); +} + /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description @@ -676,9 +688,10 @@ int vgic_v3_probe(const struct gic_kvm_info *info) group1_trap = true; } - if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) { - kvm_info("GICv3 with locally generated SEI\n"); + if (vgic_v3_broken_seis()) { + kvm_info("GICv3 with broken locally generated SEI\n"); + kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) diff --git a/arch/arm64/mm/extable.c b/arch/arm64/mm/extable.c index c0181e60cc98..489455309695 100644 --- a/arch/arm64/mm/extable.c +++ b/arch/arm64/mm/extable.c @@ -40,8 +40,8 @@ static bool ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex, struct pt_regs *regs) { - int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->type); - int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->type); + int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data); + int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); unsigned long data, addr, offset; addr = pt_regs_read_reg(regs, reg_addr); diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 870c39537dd0..e7719e8f18de 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -55,6 +55,9 @@ WORKAROUND_1418040 WORKAROUND_1463225 WORKAROUND_1508412 WORKAROUND_1542419 +WORKAROUND_2064142 +WORKAROUND_2038923 +WORKAROUND_1902691 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 703952819e10..a7e01573abd8 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -318,7 +318,7 @@ config ARCH_PROC_KCORE_TEXT depends on PROC_KCORE config IA64_MCA_RECOVERY - tristate "MCA recovery from errors other than TLB." + bool "MCA recovery from errors other than TLB." config IA64_PALINFO tristate "/proc/pal support" diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c index acb55a41260d..2bcdd7d3a1ad 100644 --- a/arch/ia64/pci/fixup.c +++ b/arch/ia64/pci/fixup.c @@ -76,5 +76,5 @@ static void pci_fixup_video(struct pci_dev *pdev) } } } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S index 0a515cde1c18..25860fba6218 100644 --- a/arch/mips/cavium-octeon/octeon-memcpy.S +++ b/arch/mips/cavium-octeon/octeon-memcpy.S @@ -74,7 +74,7 @@ #define EXC(inst_reg,addr,handler) \ 9: inst_reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* diff --git a/arch/mips/include/asm/asm.h b/arch/mips/include/asm/asm.h index 6ffdd4b5e1d0..336ac9b65235 100644 --- a/arch/mips/include/asm/asm.h +++ b/arch/mips/include/asm/asm.h @@ -285,7 +285,7 @@ symbol = value #define PTR_SCALESHIFT 2 -#define PTR .word +#define PTR_WD .word #define PTRSIZE 4 #define PTRLOG 2 #endif @@ -310,7 +310,7 @@ symbol = value #define PTR_SCALESHIFT 3 -#define PTR .dword +#define PTR_WD .dword #define PTRSIZE 8 #define PTRLOG 3 #endif diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h index b463f2aa5a61..db497a8167da 100644 --- a/arch/mips/include/asm/ftrace.h +++ b/arch/mips/include/asm/ftrace.h @@ -32,7 +32,7 @@ do { \ ".previous\n" \ \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR) "\t1b, 3b\n\t" \ + STR(PTR_WD) "\t1b, 3b\n\t" \ ".previous\n" \ \ : [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\ @@ -54,7 +54,7 @@ do { \ ".previous\n" \ \ ".section\t__ex_table,\"a\"\n\t"\ - STR(PTR) "\t1b, 3b\n\t" \ + STR(PTR_WD) "\t1b, 3b\n\t" \ ".previous\n" \ \ : [tmp_err] "=r" (error) \ diff --git a/arch/mips/include/asm/r4kcache.h b/arch/mips/include/asm/r4kcache.h index af3788589ee6..431a1c9d53fc 100644 --- a/arch/mips/include/asm/r4kcache.h +++ b/arch/mips/include/asm/r4kcache.h @@ -119,7 +119,7 @@ static inline void flush_scache_line(unsigned long addr) " j 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ - " "STR(PTR)" 1b, 3b \n" \ + " "STR(PTR_WD)" 1b, 3b \n" \ " .previous" \ : "+r" (__err) \ : "i" (op), "r" (addr), "i" (-EFAULT)); \ @@ -142,7 +142,7 @@ static inline void flush_scache_line(unsigned long addr) " j 2b \n" \ " .previous \n" \ " .section __ex_table,\"a\" \n" \ - " "STR(PTR)" 1b, 3b \n" \ + " "STR(PTR_WD)" 1b, 3b \n" \ " .previous" \ : "+r" (__err) \ : "i" (op), "r" (addr), "i" (-EFAULT)); \ diff --git a/arch/mips/include/asm/unaligned-emul.h b/arch/mips/include/asm/unaligned-emul.h index 2022b18944b9..9af0f4d3d288 100644 --- a/arch/mips/include/asm/unaligned-emul.h +++ b/arch/mips/include/asm/unaligned-emul.h @@ -20,8 +20,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -41,8 +41,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -74,10 +74,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -102,8 +102,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -125,8 +125,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -145,8 +145,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -178,10 +178,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -223,14 +223,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -255,8 +255,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT));\ @@ -276,8 +276,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -296,8 +296,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -325,10 +325,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -365,14 +365,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -398,8 +398,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -419,8 +419,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -452,10 +452,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -481,8 +481,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -504,8 +504,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -524,8 +524,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -557,10 +557,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -602,14 +602,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (value), "=r" (res) \ : "r" (addr), "i" (-EFAULT)); \ @@ -632,8 +632,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT));\ @@ -653,8 +653,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -673,8 +673,8 @@ do { \ "j\t3b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 4b\n\t" \ - STR(PTR)"\t2b, 4b\n\t" \ + STR(PTR_WD)"\t1b, 4b\n\t" \ + STR(PTR_WD)"\t2b, 4b\n\t" \ ".previous" \ : "=r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT)); \ @@ -703,10 +703,10 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ @@ -743,14 +743,14 @@ do { \ "j\t10b\n\t" \ ".previous\n\t" \ ".section\t__ex_table,\"a\"\n\t" \ - STR(PTR)"\t1b, 11b\n\t" \ - STR(PTR)"\t2b, 11b\n\t" \ - STR(PTR)"\t3b, 11b\n\t" \ - STR(PTR)"\t4b, 11b\n\t" \ - STR(PTR)"\t5b, 11b\n\t" \ - STR(PTR)"\t6b, 11b\n\t" \ - STR(PTR)"\t7b, 11b\n\t" \ - STR(PTR)"\t8b, 11b\n\t" \ + STR(PTR_WD)"\t1b, 11b\n\t" \ + STR(PTR_WD)"\t2b, 11b\n\t" \ + STR(PTR_WD)"\t3b, 11b\n\t" \ + STR(PTR_WD)"\t4b, 11b\n\t" \ + STR(PTR_WD)"\t5b, 11b\n\t" \ + STR(PTR_WD)"\t6b, 11b\n\t" \ + STR(PTR_WD)"\t7b, 11b\n\t" \ + STR(PTR_WD)"\t8b, 11b\n\t" \ ".previous" \ : "=&r" (res) \ : "r" (value), "r" (addr), "i" (-EFAULT) \ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 24e0efb360f6..1d55e57b8466 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -144,6 +144,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index a39ec755e4c2..750fe569862b 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -1258,10 +1258,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1333,10 +1333,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1404,10 +1404,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1474,10 +1474,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1589,14 +1589,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1708,14 +1708,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1827,14 +1827,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1945,14 +1945,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - STR(PTR) " 1b,8b\n" - STR(PTR) " 2b,8b\n" - STR(PTR) " 3b,8b\n" - STR(PTR) " 4b,8b\n" - STR(PTR) " 5b,8b\n" - STR(PTR) " 6b,8b\n" - STR(PTR) " 7b,8b\n" - STR(PTR) " 0b,8b\n" + STR(PTR_WD) " 1b,8b\n" + STR(PTR_WD) " 2b,8b\n" + STR(PTR_WD) " 3b,8b\n" + STR(PTR_WD) " 4b,8b\n" + STR(PTR_WD) " 5b,8b\n" + STR(PTR_WD) " 6b,8b\n" + STR(PTR_WD) " 7b,8b\n" + STR(PTR_WD) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -2007,7 +2007,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2065,7 +2065,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); @@ -2126,7 +2126,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2189,7 +2189,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - STR(PTR) " 1b,3b\n" + STR(PTR_WD) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); diff --git a/arch/mips/kernel/r2300_fpu.S b/arch/mips/kernel/r2300_fpu.S index cbf6db98cfb3..2748c55820c2 100644 --- a/arch/mips/kernel/r2300_fpu.S +++ b/arch/mips/kernel/r2300_fpu.S @@ -23,14 +23,14 @@ #define EX(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ - PTR 9b,fault; \ + PTR_WD 9b,fault; \ .previous #define EX2(a,b) \ 9: a,##b; \ .section __ex_table,"a"; \ - PTR 9b,fault; \ - PTR 9b+4,fault; \ + PTR_WD 9b,fault; \ + PTR_WD 9b+4,fault; \ .previous .set mips1 diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index b91e91106475..2e687c60bc4f 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -31,7 +31,7 @@ .ex\@: \insn \reg, \src .set pop .section __ex_table,"a" - PTR .ex\@, fault + PTR_WD .ex\@, fault .previous .endm diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S index f3c908abdbb8..cfde14b48fd8 100644 --- a/arch/mips/kernel/relocate_kernel.S +++ b/arch/mips/kernel/relocate_kernel.S @@ -147,10 +147,10 @@ LEAF(kexec_smp_wait) kexec_args: EXPORT(kexec_args) -arg0: PTR 0x0 -arg1: PTR 0x0 -arg2: PTR 0x0 -arg3: PTR 0x0 +arg0: PTR_WD 0x0 +arg1: PTR_WD 0x0 +arg2: PTR_WD 0x0 +arg3: PTR_WD 0x0 .size kexec_args,PTRSIZE*4 #ifdef CONFIG_SMP @@ -161,10 +161,10 @@ arg3: PTR 0x0 */ secondary_kexec_args: EXPORT(secondary_kexec_args) -s_arg0: PTR 0x0 -s_arg1: PTR 0x0 -s_arg2: PTR 0x0 -s_arg3: PTR 0x0 +s_arg0: PTR_WD 0x0 +s_arg1: PTR_WD 0x0 +s_arg2: PTR_WD 0x0 +s_arg3: PTR_WD 0x0 .size secondary_kexec_args,PTRSIZE*4 kexec_flag: LONG 0x1 @@ -173,17 +173,17 @@ kexec_flag: kexec_start_address: EXPORT(kexec_start_address) - PTR 0x0 + PTR_WD 0x0 .size kexec_start_address, PTRSIZE kexec_indirection_page: EXPORT(kexec_indirection_page) - PTR 0 + PTR_WD 0 .size kexec_indirection_page, PTRSIZE relocate_new_kernel_end: relocate_new_kernel_size: EXPORT(relocate_new_kernel_size) - PTR relocate_new_kernel_end - relocate_new_kernel + PTR_WD relocate_new_kernel_end - relocate_new_kernel .size relocate_new_kernel_size, PTRSIZE diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index b1b2e106f711..9bfce5f75f60 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -72,10 +72,10 @@ loads_done: .set pop .section __ex_table,"a" - PTR load_a4, bad_stack_a4 - PTR load_a5, bad_stack_a5 - PTR load_a6, bad_stack_a6 - PTR load_a7, bad_stack_a7 + PTR_WD load_a4, bad_stack_a4 + PTR_WD load_a5, bad_stack_a5 + PTR_WD load_a6, bad_stack_a6 + PTR_WD load_a7, bad_stack_a7 .previous lw t0, TI_FLAGS($28) # syscall tracing enabled? @@ -216,7 +216,7 @@ einval: li v0, -ENOSYS #endif /* CONFIG_MIPS_MT_FPAFF */ #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 2 .type sys_call_table, @object EXPORT(sys_call_table) diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index f650c55a17dc..97456b2ca7dc 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -101,7 +101,7 @@ not_n32_scall: END(handle_sysn32) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .type sysn32_call_table, @object EXPORT(sysn32_call_table) #include <asm/syscall_table_n32.h> diff --git a/arch/mips/kernel/scall64-n64.S b/arch/mips/kernel/scall64-n64.S index 5d7bfc65e4d0..5f6ed4b4c399 100644 --- a/arch/mips/kernel/scall64-n64.S +++ b/arch/mips/kernel/scall64-n64.S @@ -109,7 +109,7 @@ illegal_syscall: j n64_syscall_exit END(handle_sys64) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 3 .type sys_call_table, @object EXPORT(sys_call_table) diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index cedc8bd88804..d3c2616cba22 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -73,10 +73,10 @@ load_a7: lw a7, 28(t0) # argument #8 from usp loads_done: .section __ex_table,"a" - PTR load_a4, bad_stack_a4 - PTR load_a5, bad_stack_a5 - PTR load_a6, bad_stack_a6 - PTR load_a7, bad_stack_a7 + PTR_WD load_a4, bad_stack_a4 + PTR_WD load_a5, bad_stack_a5 + PTR_WD load_a6, bad_stack_a6 + PTR_WD load_a7, bad_stack_a7 .previous li t1, _TIF_WORK_SYSCALL_ENTRY @@ -214,7 +214,7 @@ einval: li v0, -ENOSYS END(sys32_syscall) #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) -#define __SYSCALL(nr, entry) PTR entry +#define __SYSCALL(nr, entry) PTR_WD entry .align 3 .type sys32_call_table,@object EXPORT(sys32_call_table) diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 5512cd586e6e..ae93a607ddf7 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -122,8 +122,8 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 4b \n" - " "STR(PTR)" 2b, 4b \n" + " "STR(PTR_WD)" 1b, 4b \n" + " "STR(PTR_WD)" 2b, 4b \n" " .previous \n" " .set pop \n" : [old] "=&r" (old), @@ -152,8 +152,8 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) " j 3b \n" " .previous \n" " .section __ex_table,\"a\" \n" - " "STR(PTR)" 1b, 5b \n" - " "STR(PTR)" 2b, 5b \n" + " "STR(PTR_WD)" 1b, 5b \n" + " "STR(PTR_WD)" 2b, 5b \n" " .previous \n" " .set pop \n" : [old] "=&r" (old), diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 4adca5abbc72..c706f5890a05 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -458,8 +458,8 @@ void kvm_vz_acquire_htimer(struct kvm_vcpu *vcpu) /** * _kvm_vz_save_htimer() - Switch to software emulation of guest timer. * @vcpu: Virtual CPU. - * @compare: Pointer to write compare value to. - * @cause: Pointer to write cause value to. + * @out_compare: Pointer to write compare value to. + * @out_cause: Pointer to write cause value to. * * Save VZ guest timer state and switch to software emulation of guest CP0 * timer. The hard timer must already be in use, so preemption should be @@ -1541,11 +1541,14 @@ static int kvm_trap_vz_handle_guest_exit(struct kvm_vcpu *vcpu) } /** - * kvm_trap_vz_handle_cop_unusuable() - Guest used unusable coprocessor. + * kvm_trap_vz_handle_cop_unusable() - Guest used unusable coprocessor. * @vcpu: Virtual CPU context. * * Handle when the guest attempts to use a coprocessor which hasn't been allowed * by the root context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) { @@ -1592,6 +1595,9 @@ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) * * Handle when the guest attempts to use MSA when it is disabled in the root * context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_msa_disabled(struct kvm_vcpu *vcpu) { diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S index a46db0807195..7767137c3e49 100644 --- a/arch/mips/lib/csum_partial.S +++ b/arch/mips/lib/csum_partial.S @@ -347,7 +347,7 @@ EXPORT_SYMBOL(csum_partial) .if \mode == LEGACY_MODE; \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, .L_exc; \ + PTR_WD 9b, .L_exc; \ .previous; \ /* This is enabled in EVA mode */ \ .else; \ @@ -356,7 +356,7 @@ EXPORT_SYMBOL(csum_partial) ((\to == USEROP) && (type == ST_INSN)); \ 9: __BUILD_EVA_INSN(insn##e, reg, addr); \ .section __ex_table,"a"; \ - PTR 9b, .L_exc; \ + PTR_WD 9b, .L_exc; \ .previous; \ .else; \ /* EVA without exception */ \ diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S index 277c32296636..18a43f2e29c8 100644 --- a/arch/mips/lib/memcpy.S +++ b/arch/mips/lib/memcpy.S @@ -116,7 +116,7 @@ .if \mode == LEGACY_MODE; \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous; \ /* This is assembled in EVA mode */ \ .else; \ @@ -125,7 +125,7 @@ ((\to == USEROP) && (type == ST_INSN)); \ 9: __BUILD_EVA_INSN(insn##e, reg, addr); \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous; \ .else; \ /* \ diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S index b0baa3c79fad..0b342bae9a98 100644 --- a/arch/mips/lib/memset.S +++ b/arch/mips/lib/memset.S @@ -52,7 +52,7 @@ 9: ___BUILD_EVA_INSN(insn, reg, addr); \ .endif; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous .macro f_fill64 dst, offset, val, fixup, mode diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S index 556acf684d7b..13aaa9927ad1 100644 --- a/arch/mips/lib/strncpy_user.S +++ b/arch/mips/lib/strncpy_user.S @@ -15,7 +15,7 @@ #define EX(insn,reg,addr,handler) \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* @@ -59,7 +59,7 @@ LEAF(__strncpy_from_user_asm) jr ra .section __ex_table,"a" - PTR 1b, .Lfault + PTR_WD 1b, .Lfault .previous EXPORT_SYMBOL(__strncpy_from_user_asm) diff --git a/arch/mips/lib/strnlen_user.S b/arch/mips/lib/strnlen_user.S index 92b63f20ec05..6de31b616f9c 100644 --- a/arch/mips/lib/strnlen_user.S +++ b/arch/mips/lib/strnlen_user.S @@ -14,7 +14,7 @@ #define EX(insn,reg,addr,handler) \ 9: insn reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* diff --git a/arch/mips/loongson64/vbios_quirk.c b/arch/mips/loongson64/vbios_quirk.c index 9a29e94d3db1..3115d4de982c 100644 --- a/arch/mips/loongson64/vbios_quirk.c +++ b/arch/mips/loongson64/vbios_quirk.c @@ -3,7 +3,7 @@ #include <linux/pci.h> #include <loongson.h> -static void pci_fixup_radeon(struct pci_dev *pdev) +static void pci_fixup_video(struct pci_dev *pdev) { struct resource *res = &pdev->resource[PCI_ROM_RESOURCE]; @@ -22,8 +22,7 @@ static void pci_fixup_radeon(struct pci_dev *pdev) res->flags = IORESOURCE_MEM | IORESOURCE_ROM_SHADOW | IORESOURCE_PCI_FIXED; - dev_info(&pdev->dev, "BAR %d: assigned %pR for Radeon ROM\n", - PCI_ROM_RESOURCE, res); + dev_info(&pdev->dev, "Video device with shadowed ROM at %pR\n", res); } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, 0x9615, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_radeon); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_ATI, 0x9615, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 845ddc63c882..654061e0964e 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -125,6 +125,8 @@ #define SO_RESERVE_MEM 0x4047 +#define SO_TXREHASH 0x4048 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index 7be27862329f..78c6a5fde1d6 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -223,6 +223,8 @@ static __always_inline void update_user_segments(u32 val) update_user_segment(15, val); } +int __init find_free_bat(void); +unsigned int bat_block_size(unsigned long base, unsigned long top); #endif /* !__ASSEMBLY__ */ /* We happily ignore the smaller BATs on 601, we don't actually use diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 609c80f67194..f8b94f78403f 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -178,6 +178,7 @@ static inline bool pte_user(pte_t pte) #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 33e073d6b0c4..875730d5af40 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1082,6 +1082,8 @@ static inline int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t p return hash__map_kernel_page(ea, pa, prot); } +void unmap_kernel_page(unsigned long va); + static inline int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys) diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 947b5b9c4424..a832aeafe560 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -111,8 +111,10 @@ static inline void __set_fixmap(enum fixed_addresses idx, BUILD_BUG_ON(idx >= __end_of_fixed_addresses); else if (WARN_ON(idx >= __end_of_fixed_addresses)) return; - - map_kernel_page(__fix_to_virt(idx), phys, flags); + if (pgprot_val(flags)) + map_kernel_page(__fix_to_virt(idx), phys, flags); + else + unmap_kernel_page(__fix_to_virt(idx)); } #define __early_set_fixmap __set_fixmap diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index a58fb4aa6c81..674e5aaafcbd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -473,7 +473,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(void) { return false; } diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index fe07558173ef..827038a33064 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -39,7 +39,6 @@ struct kvm_nested_guest { pgd_t *shadow_pgtable; /* our page table for this guest */ u64 l1_gr_to_hr; /* L1's addr of part'n-scoped table */ u64 process_table; /* process table entry for this guest */ - u64 hfscr; /* HFSCR that the L1 requested for this nested guest */ long refcnt; /* number of pointers to this struct */ struct mutex tlb_lock; /* serialize page faults and tlbies */ struct kvm_nested_guest *next; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index a770443cd6e0..d9bf60bf0816 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -818,6 +818,7 @@ struct kvm_vcpu_arch { /* For support of nested guests */ struct kvm_nested_guest *nested; + u64 nested_hfscr; /* HFSCR that the L1 requested for the nested guest */ u32 nested_vcpu_id; gpa_t nested_io_gpr; #endif diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b67742e2a9b2..d959c2a73fbf 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -64,6 +64,7 @@ extern int icache_44x_need_flush; #ifndef __ASSEMBLY__ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index a3313e853e5e..2816d158280a 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -308,6 +308,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __swp_entry_to_pte(x) __pte((x).val) int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot); +void unmap_kernel_page(unsigned long va); extern int __meminit vmemmap_create_mapping(unsigned long start, unsigned long page_size, unsigned long phys); diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index efad07081cc0..9675303b724e 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -500,6 +500,7 @@ #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index 52d05b465e3e..25fc8ad9a27a 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -90,7 +90,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long val, mask = -1UL; unsigned int n = 6; - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) mask = 0xffffffff; while (n--) { @@ -105,7 +105,7 @@ static inline void syscall_get_arguments(struct task_struct *task, static inline int syscall_get_arch(struct task_struct *task) { - if (is_32bit_task()) + if (is_tsk_32bit_task(task)) return AUDIT_ARCH_PPC; else if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) return AUDIT_ARCH_PPC64LE; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 5725029aaa29..d6e649b3c70b 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -168,8 +168,10 @@ static inline bool test_thread_local_flags(unsigned int flags) #ifdef CONFIG_COMPAT #define is_32bit_task() (test_thread_flag(TIF_32BIT)) +#define is_tsk_32bit_task(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT)) #else #define is_32bit_task() (IS_ENABLED(CONFIG_PPC32)) +#define is_tsk_32bit_task(tsk) (IS_ENABLED(CONFIG_PPC32)) #endif #if defined(CONFIG_PPC64) diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S index 92088f848266..7bab2d7de372 100644 --- a/arch/powerpc/kernel/interrupt_64.S +++ b/arch/powerpc/kernel/interrupt_64.S @@ -30,6 +30,7 @@ COMPAT_SYS_CALL_TABLE: .ifc \srr,srr mfspr r11,SPRN_SRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) @@ -40,6 +41,7 @@ COMPAT_SYS_CALL_TABLE: .else mfspr r11,SPRN_HSRR0 ld r12,_NIP(r1) + clrrdi r11,r11,2 clrrdi r12,r12,2 100: tdne r11,r12 EMIT_WARN_ENTRY 100b,__FILE__,__LINE__,(BUGFLAG_WARNING | BUGFLAG_ONCE) diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 62361cc7281c..cd0b8b71ecdd 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -649,8 +649,9 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec_or_work(now); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); __this_cpu_inc(irq_stat.timer_irqs_others); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index d1817cd9a691..84c89f08ae9a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1816,7 +1816,6 @@ static int kvmppc_handle_exit_hv(struct kvm_vcpu *vcpu, static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) { - struct kvm_nested_guest *nested = vcpu->arch.nested; int r; int srcu_idx; @@ -1922,7 +1921,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu) * it into a HEAI. */ if (!(vcpu->arch.hfscr_permitted & (1UL << cause)) || - (nested->hfscr & (1UL << cause))) { + (vcpu->arch.nested_hfscr & (1UL << cause))) { vcpu->arch.trap = BOOK3S_INTERRUPT_H_EMUL_ASSIST; /* diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 8f8daaeeb3b7..9d373f8963ee 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -363,7 +363,7 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* set L1 state to L2 state */ vcpu->arch.nested = l2; vcpu->arch.nested_vcpu_id = l2_hv.vcpu_token; - l2->hfscr = l2_hv.hfscr; + vcpu->arch.nested_hfscr = l2_hv.hfscr; vcpu->arch.regs = l2_regs; /* Guest must always run with ME enabled, HV disabled. */ diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 94045b265b6b..203735caf691 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -76,7 +76,7 @@ unsigned long p_block_mapped(phys_addr_t pa) return 0; } -static int __init find_free_bat(void) +int __init find_free_bat(void) { int b; int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; @@ -100,7 +100,7 @@ static int __init find_free_bat(void) * - block size has to be a power of two. This is calculated by finding the * highest bit set to 1. */ -static unsigned int block_size(unsigned long base, unsigned long top) +unsigned int bat_block_size(unsigned long base, unsigned long top) { unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; @@ -145,7 +145,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to int idx; while ((idx = find_free_bat()) != -1 && base != top) { - unsigned int size = block_size(base, top); + unsigned int size = bat_block_size(base, top); if (size < 128 << 10) break; @@ -201,12 +201,12 @@ void mmu_mark_initmem_nx(void) unsigned long size; for (i = 0; i < nb - 1 && base < top;) { - size = block_size(base, top); + size = bat_block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; } if (base < top) { - size = block_size(base, top); + size = bat_block_size(base, top); if ((top - base) > size) { size <<= 1; if (strict_kernel_rwx_enabled() && base + size > border) diff --git a/arch/powerpc/mm/kasan/book3s_32.c b/arch/powerpc/mm/kasan/book3s_32.c index 35b287b0a8da..450a67ef0bbe 100644 --- a/arch/powerpc/mm/kasan/book3s_32.c +++ b/arch/powerpc/mm/kasan/book3s_32.c @@ -10,48 +10,51 @@ int __init kasan_init_region(void *start, size_t size) { unsigned long k_start = (unsigned long)kasan_mem_to_shadow(start); unsigned long k_end = (unsigned long)kasan_mem_to_shadow(start + size); - unsigned long k_cur = k_start; - int k_size = k_end - k_start; - int k_size_base = 1 << (ffs(k_size) - 1); + unsigned long k_nobat = k_start; + unsigned long k_cur; + phys_addr_t phys; int ret; - void *block; - block = memblock_alloc(k_size, k_size_base); - - if (block && k_size_base >= SZ_128K && k_start == ALIGN(k_start, k_size_base)) { - int shift = ffs(k_size - k_size_base); - int k_size_more = shift ? 1 << (shift - 1) : 0; - - setbat(-1, k_start, __pa(block), k_size_base, PAGE_KERNEL); - if (k_size_more >= SZ_128K) - setbat(-1, k_start + k_size_base, __pa(block) + k_size_base, - k_size_more, PAGE_KERNEL); - if (v_block_mapped(k_start)) - k_cur = k_start + k_size_base; - if (v_block_mapped(k_start + k_size_base)) - k_cur = k_start + k_size_base + k_size_more; - - update_bats(); + while (k_nobat < k_end) { + unsigned int k_size = bat_block_size(k_nobat, k_end); + int idx = find_free_bat(); + + if (idx == -1) + break; + if (k_size < SZ_128K) + break; + phys = memblock_phys_alloc_range(k_size, k_size, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + break; + + setbat(idx, k_nobat, phys, k_size, PAGE_KERNEL); + k_nobat += k_size; } + if (k_nobat != k_start) + update_bats(); - if (!block) - block = memblock_alloc(k_size, PAGE_SIZE); - if (!block) - return -ENOMEM; + if (k_nobat < k_end) { + phys = memblock_phys_alloc_range(k_end - k_nobat, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_ANYWHERE); + if (!phys) + return -ENOMEM; + } ret = kasan_init_shadow_page_tables(k_start, k_end); if (ret) return ret; - kasan_update_early_region(k_start, k_cur, __pte(0)); + kasan_update_early_region(k_start, k_nobat, __pte(0)); - for (; k_cur < k_end; k_cur += PAGE_SIZE) { + for (k_cur = k_nobat; k_cur < k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_off_k(k_cur); - void *va = block + k_cur - k_start; - pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL); + pte_t pte = pfn_pte(PHYS_PFN(phys + k_cur - k_nobat), PAGE_KERNEL); __set_pte_at(&init_mm, k_cur, pte_offset_kernel(pmd, k_cur), pte, 0); } flush_tlb_kernel_range(k_start, k_end); + memset(kasan_mem_to_shadow(start), 0, k_end - k_start); + return 0; } diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index abb3198bd277..6ec5a7dd7913 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -206,6 +206,15 @@ void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, __set_pte_at(mm, addr, ptep, pte, 0); } +void unmap_kernel_page(unsigned long va) +{ + pmd_t *pmdp = pmd_off_k(va); + pte_t *ptep = pte_offset_kernel(pmdp, va); + + pte_clear(&init_mm, va, ptep); + flush_tlb_kernel_range(va, va + PAGE_SIZE); +} + /* * This is called when relaxing access to a PTE. It's also called in the page * fault path when we don't hit any of the major fault cases, ie, a minor diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index d6ffdd0f2309..56dd1f4e3e44 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -23,15 +23,15 @@ static void bpf_jit_fill_ill_insns(void *area, unsigned int size) memset32(area, BREAKPOINT_INSTRUCTION, size / 4); } -/* Fix the branch target addresses for subprog calls */ -static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, - struct codegen_context *ctx, u32 *addrs) +/* Fix updated addresses (for subprog calls, ldimm64, et al) during extra pass */ +static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, + struct codegen_context *ctx, u32 *addrs) { const struct bpf_insn *insn = fp->insnsi; bool func_addr_fixed; u64 func_addr; u32 tmp_idx; - int i, ret; + int i, j, ret; for (i = 0; i < fp->len; i++) { /* @@ -66,6 +66,23 @@ static int bpf_jit_fixup_subprog_calls(struct bpf_prog *fp, u32 *image, * of the JITed sequence remains unchanged. */ ctx->idx = tmp_idx; + } else if (insn[i].code == (BPF_LD | BPF_IMM | BPF_DW)) { + tmp_idx = ctx->idx; + ctx->idx = addrs[i] / 4; +#ifdef CONFIG_PPC32 + PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm); + PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm); + for (j = ctx->idx - addrs[i] / 4; j < 4; j++) + EMIT(PPC_RAW_NOP()); +#else + func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32); + PPC_LI64(b2p[insn[i].dst_reg], func_addr); + /* overwrite rest with nops */ + for (j = ctx->idx - addrs[i] / 4; j < 5; j++) + EMIT(PPC_RAW_NOP()); +#endif + ctx->idx = tmp_idx; + i++; } } @@ -200,13 +217,13 @@ skip_init_ctx: /* * Do not touch the prologue and epilogue as they will remain * unchanged. Only fix the branch target address for subprog - * calls in the body. + * calls in the body, and ldimm64 instructions. * * This does not change the offsets and lengths of the subprog * call instruction sequences and hence, the size of the JITed * image as well. */ - bpf_jit_fixup_subprog_calls(fp, code_base, &cgctx, addrs); + bpf_jit_fixup_addresses(fp, code_base, &cgctx, addrs); /* There is no need to perform the usual passes. */ goto skip_codegen_passes; diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index faaebd446cad..cf8dd8aea386 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -191,6 +191,9 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun if (image && rel < 0x2000000 && rel >= -0x2000000) { PPC_BL_ABS(func); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); } else { /* Load function address into r0 */ EMIT(PPC_RAW_LIS(_R0, IMM_H(func))); @@ -290,6 +293,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * bool func_addr_fixed; u64 func_addr; u32 true_cond; + u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -905,8 +910,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * 16 byte instruction that uses two 'struct bpf_insn' */ case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ + tmp_idx = ctx->idx; PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm); PPC_LI32(dst_reg, (u32)insn[i].imm); + /* padding to allow full 4 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 4; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; break; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 9eae8d8ed340..e1e8c934308a 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -319,6 +319,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * u64 imm64; u32 true_cond; u32 tmp_idx; + int j; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -633,17 +634,21 @@ bpf_alu32_trunc: EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 64: - /* - * Way easier and faster(?) to store the value - * into stack and then use ldbrx - * - * ctx->seen will be reliable in pass2, but - * the instructions generated will remain the - * same across all passes - */ + /* Store the value to stack and then use byte-reverse loads */ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); - EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + } else { + EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); + EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); + } break; } break; @@ -848,9 +853,13 @@ emit_clear: case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */ imm64 = ((u64)(u32) insn[i].imm) | (((u64)(u32) insn[i+1].imm) << 32); + tmp_idx = ctx->idx; + PPC_LI64(dst_reg, imm64); + /* padding to allow full 5 instructions for later patching */ + for (j = ctx->idx - tmp_idx; j < 5; j++) + EMIT(PPC_RAW_NOP()); /* Adjust for two bpf instructions */ addrs[++i] = ctx->idx * 4; - PPC_LI64(dst_reg, imm64); break; /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a684901b6965..b5b42cf0a703 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -776,6 +776,34 @@ static void pmao_restore_workaround(bool ebb) mtspr(SPRN_PMC6, pmcs[5]); } +/* + * If the perf subsystem wants performance monitor interrupts as soon as + * possible (e.g., to sample the instruction address and stack chain), + * this should return true. The IRQ masking code can then enable MSR[EE] + * in some places (e.g., interrupt handlers) that allows PMI interrupts + * through to improve accuracy of profiles, at the cost of some performance. + * + * The PMU counters can be enabled by other means (e.g., sysfs raw SPR + * access), but in that case there is no need for prompt PMI handling. + * + * This currently returns true if any perf counter is being used. It + * could possibly return false if only events are being counted rather than + * samples being taken, but for now this is good enough. + */ +bool power_pmu_wants_prompt_pmi(void) +{ + struct cpu_hw_events *cpuhw; + + /* + * This could simply test local_paca->pmcregs_in_use if that were not + * under ifdef KVM. + */ + if (!ppmu) + return false; + + cpuhw = this_cpu_ptr(&cpu_hw_events); + return cpuhw->n_events; +} #endif /* CONFIG_PPC64 */ static void perf_event_interrupt(struct pt_regs *regs); @@ -1327,9 +1355,20 @@ static void power_pmu_disable(struct pmu *pmu) * Otherwise provide a warning if there is PMI pending, but * no counter is found overflown. */ - if (any_pmc_overflown(cpuhw)) - clear_pmi_irq_pending(); - else + if (any_pmc_overflown(cpuhw)) { + /* + * Since power_pmu_disable runs under local_irq_save, it + * could happen that code hits a PMC overflow without PMI + * pending in paca. Hence only clear PMI pending if it was + * set. + * + * If a PMI is pending, then MSR[EE] must be disabled (because + * the masked PMI handler disabling EE). So it is safe to + * call clear_pmi_irq_pending(). + */ + if (pmi_irq_pending()) + clear_pmi_irq_pending(); + } else WARN_ON(pmi_irq_pending()); val = mmcra = cpuhw->mmcr.mmcra; @@ -2438,36 +2477,6 @@ static void perf_event_interrupt(struct pt_regs *regs) perf_sample_event_took(sched_clock() - start_clock); } -/* - * If the perf subsystem wants performance monitor interrupts as soon as - * possible (e.g., to sample the instruction address and stack chain), - * this should return true. The IRQ masking code can then enable MSR[EE] - * in some places (e.g., interrupt handlers) that allows PMI interrupts - * though to improve accuracy of profiles, at the cost of some performance. - * - * The PMU counters can be enabled by other means (e.g., sysfs raw SPR - * access), but in that case there is no need for prompt PMI handling. - * - * This currently returns true if any perf counter is being used. It - * could possibly return false if only events are being counted rather than - * samples being taken, but for now this is good enough. - */ -bool power_pmu_wants_prompt_pmi(void) -{ - struct cpu_hw_events *cpuhw; - - /* - * This could simply test local_paca->pmcregs_in_use if that were not - * under ifdef KVM. - */ - - if (!ppmu) - return false; - - cpuhw = this_cpu_ptr(&cpu_hw_events); - return cpuhw->n_events; -} - static int power_pmu_prepare_cpu(unsigned int cpu) { struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9750f92380f5..be9f39fd06df 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -945,6 +945,9 @@ config S390_GUEST endmenu +config S390_MODULES_SANITY_TEST_HELPERS + def_bool n + menu "Selftests" config S390_UNWIND_SELFTEST @@ -971,4 +974,16 @@ config S390_KPROBES_SANITY_TEST Say N if you are unsure. +config S390_MODULES_SANITY_TEST + def_tristate n + depends on KUNIT + default KUNIT_ALL_TESTS + prompt "Enable s390 specific modules tests" + select S390_MODULES_SANITY_TEST_HELPERS + help + This option enables an s390 specific modules test. This option is + not useful for distributions or general kernels, but only for + kernel developers working on architecture code. + + Say N if you are unsure. endmenu diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 7fe8975b49ec..498bed9b261b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -63,6 +63,7 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m +CONFIG_S390_MODULES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y @@ -96,7 +97,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y @@ -109,6 +109,7 @@ CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PERCPU_STATS=y CONFIG_GUP_TEST=y +CONFIG_ANON_VMA_NAME=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -116,7 +117,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -185,7 +185,6 @@ CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_NFT_CT=m -CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m @@ -391,6 +390,7 @@ CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m +CONFIG_NET_SWITCHDEV=y CONFIG_CGROUP_NET_PRIO=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y @@ -400,6 +400,7 @@ CONFIG_PCI_IOV=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -501,6 +502,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set @@ -511,7 +513,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -542,6 +543,7 @@ CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set @@ -592,6 +594,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -756,9 +759,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -774,6 +774,8 @@ CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m CONFIG_CRC7=m @@ -807,7 +809,6 @@ CONFIG_SLUB_DEBUG_ON=y CONFIG_SLUB_STATS=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_VM=y -CONFIG_DEBUG_VM_VMACACHE=y CONFIG_DEBUG_VM_PGFLAGS=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m @@ -819,12 +820,11 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y CONFIG_TEST_LOCKUP=m -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y +CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 466780c465f5..61e36b999f67 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -61,6 +61,7 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_S390_UNWIND_SELFTEST=m CONFIG_S390_KPROBES_SANITY_TEST=m +CONFIG_S390_MODULES_SANITY_TEST=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y # CONFIG_GCC_PLUGINS is not set @@ -91,7 +92,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_FRONTSWAP=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y @@ -101,6 +101,7 @@ CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PERCPU_STATS=y +CONFIG_ANON_VMA_NAME=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -108,7 +109,6 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m -CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -177,7 +177,6 @@ CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y CONFIG_NFT_CT=m -CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m @@ -382,6 +381,7 @@ CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m +CONFIG_NET_SWITCHDEV=y CONFIG_CGROUP_NET_PRIO=y CONFIG_NET_PKTGEN=m CONFIG_PCI=y @@ -391,6 +391,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m @@ -492,6 +493,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set +# CONFIG_NET_VENDOR_ENGLEDER is not set # CONFIG_NET_VENDOR_EZCHIP is not set # CONFIG_NET_VENDOR_GOOGLE is not set # CONFIG_NET_VENDOR_HUAWEI is not set @@ -502,7 +504,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -533,6 +534,7 @@ CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_SYNOPSYS is not set # CONFIG_NET_VENDOR_TEHUTI is not set # CONFIG_NET_VENDOR_TI is not set +# CONFIG_NET_VENDOR_VERTEXCOM is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_NET_VENDOR_XILINX is not set @@ -582,6 +584,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -743,9 +746,6 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y -CONFIG_CRYPTO_LIB_BLAKE2S=m -CONFIG_CRYPTO_LIB_CURVE25519=m -CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -762,6 +762,8 @@ CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index eed3b9acfa71..c55c668dc3c7 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -1,6 +1,7 @@ # CONFIG_SWAP is not set CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y # CONFIG_CPU_ISOLATION is not set # CONFIG_UTS_NS is not set # CONFIG_TIME_NS is not set @@ -34,6 +35,7 @@ CONFIG_NET=y # CONFIG_PCPU_DEV_REFCNT is not set # CONFIG_ETHTOOL_NETLINK is not set CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_SAFE=y CONFIG_BLK_DEV_RAM=y # CONFIG_DCSSBLK is not set # CONFIG_DASD is not set @@ -58,6 +60,7 @@ CONFIG_ZFCP=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set +# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c index 33f973ff9744..e8f15dbb89d0 100644 --- a/arch/s390/hypfs/hypfs_vm.c +++ b/arch/s390/hypfs/hypfs_vm.c @@ -20,6 +20,7 @@ static char local_guest[] = " "; static char all_guests[] = "* "; +static char *all_groups = all_guests; static char *guest_query; struct diag2fc_data { @@ -62,10 +63,11 @@ static int diag2fc(int size, char* query, void *addr) memcpy(parm_list.userid, query, NAME_LEN); ASCEBC(parm_list.userid, NAME_LEN); - parm_list.addr = (unsigned long) addr ; + memcpy(parm_list.aci_grp, all_groups, NAME_LEN); + ASCEBC(parm_list.aci_grp, NAME_LEN); + parm_list.addr = (unsigned long)addr; parm_list.size = size; parm_list.fmt = 0x02; - memset(parm_list.aci_grp, 0x40, NAME_LEN); rc = -1; diag_stat_inc(DIAG_STAT_X2FC); diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 147cb3534ce4..d74e26b48604 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -47,8 +47,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); int __put_user_bad(void) __attribute__((noreturn)); int __get_user_bad(void) __attribute__((noreturn)); -#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES - union oac { unsigned int val; struct { @@ -71,6 +69,8 @@ union oac { }; }; +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + #define __put_get_user_asm(to, from, size, oac_spec) \ ({ \ int __rc; \ diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index d52d85367bf7..b032e556eeb7 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -33,7 +33,7 @@ #define DEBUGP(fmt , ...) #endif -#define PLT_ENTRY_SIZE 20 +#define PLT_ENTRY_SIZE 22 void *module_alloc(unsigned long size) { @@ -341,27 +341,26 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, case R_390_PLTOFF32: /* 32 bit offset from GOT to PLT. */ case R_390_PLTOFF64: /* 16 bit offset from GOT to PLT. */ if (info->plt_initialized == 0) { - unsigned int insn[5]; - unsigned int *ip = me->core_layout.base + - me->arch.plt_offset + - info->plt_offset; - - insn[0] = 0x0d10e310; /* basr 1,0 */ - insn[1] = 0x100a0004; /* lg 1,10(1) */ + unsigned char insn[PLT_ENTRY_SIZE]; + char *plt_base; + char *ip; + + plt_base = me->core_layout.base + me->arch.plt_offset; + ip = plt_base + info->plt_offset; + *(int *)insn = 0x0d10e310; /* basr 1,0 */ + *(int *)&insn[4] = 0x100c0004; /* lg 1,12(1) */ if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) { - unsigned int *ij; - ij = me->core_layout.base + - me->arch.plt_offset + - me->arch.plt_size - PLT_ENTRY_SIZE; - insn[2] = 0xa7f40000 + /* j __jump_r1 */ - (unsigned int)(u16) - (((unsigned long) ij - 8 - - (unsigned long) ip) / 2); + char *jump_r1; + + jump_r1 = plt_base + me->arch.plt_size - + PLT_ENTRY_SIZE; + /* brcl 0xf,__jump_r1 */ + *(short *)&insn[8] = 0xc0f4; + *(int *)&insn[10] = (jump_r1 - (ip + 8)) / 2; } else { - insn[2] = 0x07f10000; /* br %r1 */ + *(int *)&insn[8] = 0x07f10000; /* br %r1 */ } - insn[3] = (unsigned int) (val >> 32); - insn[4] = (unsigned int) val; + *(long *)&insn[14] = val; write(ip, insn, sizeof(insn)); info->plt_initialized = 1; diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 0c9e894913dc..651a51914e34 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -264,7 +264,14 @@ static int notrace s390_validate_registers(union mci mci, int umode) /* Validate vector registers */ union ctlreg0 cr0; - if (!mci.vr) { + /* + * The vector validity must only be checked if not running a + * KVM guest. For KVM guests the machine check is forwarded by + * KVM and it is the responsibility of the guest to take + * appropriate actions. The host vector or FPU values have been + * saved by KVM and will be restored by KVM. + */ + if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) { /* * Vector registers can't be restored. If the kernel * currently uses vector registers the system is @@ -307,11 +314,21 @@ static int notrace s390_validate_registers(union mci mci, int umode) if (cr2.gse) { if (!mci.gs) { /* - * Guarded storage register can't be restored and - * the current processes uses guarded storage. - * It has to be terminated. + * 2 cases: + * - machine check in kernel or userspace + * - machine check while running SIE (KVM guest) + * For kernel or userspace the userspace values of + * guarded storage control can not be recreated, the + * process must be terminated. + * For SIE the guest values of guarded storage can not + * be recreated. This is either due to a bug or due to + * GS being disabled in the guest. The guest will be + * notified by KVM code and the guests machine check + * handling must take care of this. The host values + * are saved by KVM and are not affected. */ - kill_task = 1; + if (!test_cpu_flag(CIF_MCCK_GUEST)) + kill_task = 1; } else { load_gs_cb((struct gs_cb *)mcesa->guarded_storage_save_area); } diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 707cd4622c13..69feb8ed3312 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -17,4 +17,7 @@ KASAN_SANITIZE_uaccess.o := n obj-$(CONFIG_S390_UNWIND_SELFTEST) += test_unwind.o CFLAGS_test_unwind.o += -fno-optimize-sibling-calls +obj-$(CONFIG_S390_MODULES_SANITY_TEST) += test_modules.o +obj-$(CONFIG_S390_MODULES_SANITY_TEST_HELPERS) += test_modules_helpers.o + lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/s390/lib/test_modules.c b/arch/s390/lib/test_modules.c new file mode 100644 index 000000000000..d056baa8fbb0 --- /dev/null +++ b/arch/s390/lib/test_modules.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <kunit/test.h> +#include <linux/module.h> + +#include "test_modules.h" + +#define DECLARE_RETURN(i) int test_modules_return_ ## i(void) +REPEAT_10000(DECLARE_RETURN); + +/* + * Test that modules with many relocations are loaded properly. + */ +static void test_modules_many_vmlinux_relocs(struct kunit *test) +{ + int result = 0; + +#define CALL_RETURN(i) result += test_modules_return_ ## i() + REPEAT_10000(CALL_RETURN); + KUNIT_ASSERT_EQ(test, result, 49995000); +} + +static struct kunit_case modules_testcases[] = { + KUNIT_CASE(test_modules_many_vmlinux_relocs), + {} +}; + +static struct kunit_suite modules_test_suite = { + .name = "modules_test_s390", + .test_cases = modules_testcases, +}; + +kunit_test_suites(&modules_test_suite); + +MODULE_LICENSE("GPL"); diff --git a/arch/s390/lib/test_modules.h b/arch/s390/lib/test_modules.h new file mode 100644 index 000000000000..43b5e4b4af3e --- /dev/null +++ b/arch/s390/lib/test_modules.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef TEST_MODULES_H +#define TEST_MODULES_H + +#define __REPEAT_10000_3(f, x) \ + f(x ## 0); \ + f(x ## 1); \ + f(x ## 2); \ + f(x ## 3); \ + f(x ## 4); \ + f(x ## 5); \ + f(x ## 6); \ + f(x ## 7); \ + f(x ## 8); \ + f(x ## 9) +#define __REPEAT_10000_2(f, x) \ + __REPEAT_10000_3(f, x ## 0); \ + __REPEAT_10000_3(f, x ## 1); \ + __REPEAT_10000_3(f, x ## 2); \ + __REPEAT_10000_3(f, x ## 3); \ + __REPEAT_10000_3(f, x ## 4); \ + __REPEAT_10000_3(f, x ## 5); \ + __REPEAT_10000_3(f, x ## 6); \ + __REPEAT_10000_3(f, x ## 7); \ + __REPEAT_10000_3(f, x ## 8); \ + __REPEAT_10000_3(f, x ## 9) +#define __REPEAT_10000_1(f, x) \ + __REPEAT_10000_2(f, x ## 0); \ + __REPEAT_10000_2(f, x ## 1); \ + __REPEAT_10000_2(f, x ## 2); \ + __REPEAT_10000_2(f, x ## 3); \ + __REPEAT_10000_2(f, x ## 4); \ + __REPEAT_10000_2(f, x ## 5); \ + __REPEAT_10000_2(f, x ## 6); \ + __REPEAT_10000_2(f, x ## 7); \ + __REPEAT_10000_2(f, x ## 8); \ + __REPEAT_10000_2(f, x ## 9) +#define REPEAT_10000(f) \ + __REPEAT_10000_1(f, 0); \ + __REPEAT_10000_1(f, 1); \ + __REPEAT_10000_1(f, 2); \ + __REPEAT_10000_1(f, 3); \ + __REPEAT_10000_1(f, 4); \ + __REPEAT_10000_1(f, 5); \ + __REPEAT_10000_1(f, 6); \ + __REPEAT_10000_1(f, 7); \ + __REPEAT_10000_1(f, 8); \ + __REPEAT_10000_1(f, 9) + +#endif diff --git a/arch/s390/lib/test_modules_helpers.c b/arch/s390/lib/test_modules_helpers.c new file mode 100644 index 000000000000..1670349a03eb --- /dev/null +++ b/arch/s390/lib/test_modules_helpers.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/export.h> + +#include "test_modules.h" + +#define DEFINE_RETURN(i) \ + int test_modules_return_ ## i(void) \ + { \ + return 1 ## i - 10000; \ + } \ + EXPORT_SYMBOL_GPL(test_modules_return_ ## i) +REPEAT_10000(DEFINE_RETURN); diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2672dd03faf3..666f81e617ea 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -126,6 +126,8 @@ #define SO_RESERVE_MEM 0x0052 +#define SO_TXREHASH 0x0053 + #if !defined(__KERNEL__) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ebe8fc76949a..9f5bd41bf660 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -186,6 +186,7 @@ config X86 select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT select HAVE_OBJTOOL_MCOUNT if STACK_VALIDATION + select HAVE_BUILDTIME_MCOUNT_SORT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fd9f908debe5..c91434056c29 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6236,6 +6236,19 @@ __init int intel_pmu_init(void) pmu->num_counters = x86_pmu.num_counters; pmu->num_counters_fixed = x86_pmu.num_counters_fixed; } + + /* + * Quirk: For some Alder Lake machine, when all E-cores are disabled in + * a BIOS, the leaf 0xA will enumerate all counters of P-cores. However, + * the X86_FEATURE_HYBRID_CPU is still set. The above codes will + * mistakenly add extra counters for P-cores. Correct the number of + * counters here. + */ + if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) { + pmu->num_counters = x86_pmu.num_counters; + pmu->num_counters_fixed = x86_pmu.num_counters_fixed; + } + pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters); pmu->unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, @@ -6340,6 +6353,8 @@ __init int intel_pmu_init(void) } if (x86_pmu.lbr_nr) { + intel_pmu_lbr_init(); + pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); /* only support branch_stack snapshot for perfmon >= v2 */ diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 8043213b75a5..669c2be14784 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -8,14 +8,6 @@ #include "../perf_event.h" -static const enum { - LBR_EIP_FLAGS = 1, - LBR_TSX = 2, -} lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { - [LBR_FORMAT_EIP_FLAGS] = LBR_EIP_FLAGS, - [LBR_FORMAT_EIP_FLAGS2] = LBR_EIP_FLAGS | LBR_TSX, -}; - /* * Intel LBR_SELECT bits * Intel Vol3a, April 2011, Section 16.7 Table 16-10 @@ -243,7 +235,7 @@ void intel_pmu_lbr_reset_64(void) for (i = 0; i < x86_pmu.lbr_nr; i++) { wrmsrl(x86_pmu.lbr_from + i, 0); wrmsrl(x86_pmu.lbr_to + i, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (x86_pmu.lbr_has_info) wrmsrl(x86_pmu.lbr_info + i, 0); } } @@ -305,11 +297,10 @@ enum { */ static inline bool lbr_from_signext_quirk_needed(void) { - int lbr_format = x86_pmu.intel_cap.lbr_format; bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM); - return !tsx_support && (lbr_desc[lbr_format] & LBR_TSX); + return !tsx_support && x86_pmu.lbr_has_tsx; } static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key); @@ -427,12 +418,12 @@ rdlbr_all(struct lbr_entry *lbr, unsigned int idx, bool need_info) void intel_pmu_lbr_restore(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; - int i; - unsigned lbr_idx, mask; + bool need_info = x86_pmu.lbr_has_info; u64 tos = task_ctx->tos; + unsigned lbr_idx, mask; + int i; mask = x86_pmu.lbr_nr - 1; for (i = 0; i < task_ctx->valid_lbrs; i++) { @@ -444,7 +435,7 @@ void intel_pmu_lbr_restore(void *ctx) lbr_idx = (tos - i) & mask; wrlbr_from(lbr_idx, 0); wrlbr_to(lbr_idx, 0); - if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + if (need_info) wrlbr_info(lbr_idx, 0); } @@ -519,9 +510,9 @@ static void __intel_pmu_lbr_restore(void *ctx) void intel_pmu_lbr_save(void *ctx) { - bool need_info = x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx = ctx; + bool need_info = x86_pmu.lbr_has_info; unsigned lbr_idx, mask; u64 tos; int i; @@ -816,7 +807,6 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { bool need_info = false, call_stack = false; unsigned long mask = x86_pmu.lbr_nr - 1; - int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; @@ -831,9 +821,7 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; - int skip = 0; u16 cycles = 0; - int lbr_flags = lbr_desc[lbr_format]; from = rdlbr_from(lbr_idx, NULL); to = rdlbr_to(lbr_idx, NULL); @@ -845,37 +833,39 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) if (call_stack && !from) break; - if (lbr_format == LBR_FORMAT_INFO && need_info) { - u64 info; - - info = rdlbr_info(lbr_idx, NULL); - mis = !!(info & LBR_INFO_MISPRED); - pred = !mis; - in_tx = !!(info & LBR_INFO_IN_TX); - abort = !!(info & LBR_INFO_ABORT); - cycles = (info & LBR_INFO_CYCLES); - } - - if (lbr_format == LBR_FORMAT_TIME) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - cycles = ((to >> 48) & LBR_INFO_CYCLES); - - to = (u64)((((s64)to) << 16) >> 16); - } - - if (lbr_flags & LBR_EIP_FLAGS) { - mis = !!(from & LBR_FROM_FLAG_MISPRED); - pred = !mis; - skip = 1; - } - if (lbr_flags & LBR_TSX) { - in_tx = !!(from & LBR_FROM_FLAG_IN_TX); - abort = !!(from & LBR_FROM_FLAG_ABORT); - skip = 3; + if (x86_pmu.lbr_has_info) { + if (need_info) { + u64 info; + + info = rdlbr_info(lbr_idx, NULL); + mis = !!(info & LBR_INFO_MISPRED); + pred = !mis; + cycles = (info & LBR_INFO_CYCLES); + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(info & LBR_INFO_IN_TX); + abort = !!(info & LBR_INFO_ABORT); + } + } + } else { + int skip = 0; + + if (x86_pmu.lbr_from_flags) { + mis = !!(from & LBR_FROM_FLAG_MISPRED); + pred = !mis; + skip = 1; + } + if (x86_pmu.lbr_has_tsx) { + in_tx = !!(from & LBR_FROM_FLAG_IN_TX); + abort = !!(from & LBR_FROM_FLAG_ABORT); + skip = 3; + } + from = (u64)((((s64)from) << skip) >> skip); + + if (x86_pmu.lbr_to_cycles) { + cycles = ((to >> 48) & LBR_INFO_CYCLES); + to = (u64)((((s64)to) << 16) >> 16); + } } - from = (u64)((((s64)from) << skip) >> skip); /* * Some CPUs report duplicated abort records, @@ -903,37 +893,40 @@ void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_stack.hw_idx = tos; } +static DEFINE_STATIC_KEY_FALSE(x86_lbr_mispred); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_cycles); +static DEFINE_STATIC_KEY_FALSE(x86_lbr_type); + static __always_inline int get_lbr_br_type(u64 info) { - if (!static_cpu_has(X86_FEATURE_ARCH_LBR) || !x86_pmu.lbr_br_type) - return 0; + int type = 0; - return (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + if (static_branch_likely(&x86_lbr_type)) + type = (info & LBR_INFO_BR_TYPE) >> LBR_INFO_BR_TYPE_OFFSET; + + return type; } static __always_inline bool get_lbr_mispred(u64 info) { - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; + bool mispred = 0; - return !!(info & LBR_INFO_MISPRED); -} + if (static_branch_likely(&x86_lbr_mispred)) + mispred = !!(info & LBR_INFO_MISPRED); -static __always_inline bool get_lbr_predicted(u64 info) -{ - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && !x86_pmu.lbr_mispred) - return 0; - - return !(info & LBR_INFO_MISPRED); + return mispred; } static __always_inline u16 get_lbr_cycles(u64 info) { + u16 cycles = info & LBR_INFO_CYCLES; + if (static_cpu_has(X86_FEATURE_ARCH_LBR) && - !(x86_pmu.lbr_timed_lbr && info & LBR_INFO_CYC_CNT_VALID)) - return 0; + (!static_branch_likely(&x86_lbr_cycles) || + !(info & LBR_INFO_CYC_CNT_VALID))) + cycles = 0; - return info & LBR_INFO_CYCLES; + return cycles; } static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, @@ -961,7 +954,7 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->from = from; e->to = to; e->mispred = get_lbr_mispred(info); - e->predicted = get_lbr_predicted(info); + e->predicted = !e->mispred; e->in_tx = !!(info & LBR_INFO_IN_TX); e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); @@ -1120,7 +1113,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && - (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + x86_pmu.lbr_has_info) reg->config |= LBR_NO_INFO; return 0; @@ -1706,6 +1699,38 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } +void intel_pmu_lbr_init(void) +{ + switch (x86_pmu.intel_cap.lbr_format) { + case LBR_FORMAT_EIP_FLAGS2: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_EIP_FLAGS: + x86_pmu.lbr_from_flags = 1; + break; + + case LBR_FORMAT_INFO: + x86_pmu.lbr_has_tsx = 1; + fallthrough; + case LBR_FORMAT_INFO2: + x86_pmu.lbr_has_info = 1; + break; + + case LBR_FORMAT_TIME: + x86_pmu.lbr_from_flags = 1; + x86_pmu.lbr_to_cycles = 1; + break; + } + + if (x86_pmu.lbr_has_info) { + /* + * Only used in combination with baseline pebs. + */ + static_branch_enable(&x86_lbr_mispred); + static_branch_enable(&x86_lbr_cycles); + } +} + /* * LBR state size is variable based on the max number of registers. * This calculates the expected state size, which should match @@ -1726,6 +1751,9 @@ static bool is_arch_lbr_xsave_available(void) * Check the LBR state with the corresponding software structure. * Disable LBR XSAVES support if the size doesn't match. */ + if (xfeature_size(XFEATURE_LBR) == 0) + return false; + if (WARN_ON(xfeature_size(XFEATURE_LBR) != get_lbr_state_size())) return false; @@ -1765,6 +1793,12 @@ void __init intel_pmu_arch_lbr_init(void) x86_pmu.lbr_br_type = ecx.split.lbr_br_type; x86_pmu.lbr_nr = lbr_nr; + if (x86_pmu.lbr_mispred) + static_branch_enable(&x86_lbr_mispred); + if (x86_pmu.lbr_timed_lbr) + static_branch_enable(&x86_lbr_cycles); + if (x86_pmu.lbr_br_type) + static_branch_enable(&x86_lbr_type); arch_lbr_xsave = is_arch_lbr_xsave_available(); if (arch_lbr_xsave) { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index f1ba6ab2e97e..e497da9bf427 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1762,7 +1762,7 @@ static const struct intel_uncore_init_fun rkl_uncore_init __initconst = { static const struct intel_uncore_init_fun adl_uncore_init __initconst = { .cpu_init = adl_uncore_cpu_init, - .mmio_init = tgl_uncore_mmio_init, + .mmio_init = adl_uncore_mmio_init, }; static const struct intel_uncore_init_fun icx_uncore_init __initconst = { diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index b9687980aab6..2adeaf4de4df 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -584,10 +584,11 @@ void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); void skl_uncore_cpu_init(void); void icl_uncore_cpu_init(void); -void adl_uncore_cpu_init(void); void tgl_uncore_cpu_init(void); +void adl_uncore_cpu_init(void); void tgl_uncore_mmio_init(void); void tgl_l_uncore_mmio_init(void); +void adl_uncore_mmio_init(void); int snb_pci2phy_map_init(int devid); /* uncore_snbep.c */ diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index 3049c646fa20..6ddadb482f68 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -494,8 +494,8 @@ void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box) writel(0, box->io_addr); } -static void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, - struct perf_event *event) +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 6d735611c281..cfaf558bdb6b 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -139,6 +139,8 @@ void intel_generic_uncore_mmio_disable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_enable_box(struct intel_uncore_box *box); void intel_generic_uncore_mmio_disable_event(struct intel_uncore_box *box, struct perf_event *event); +void intel_generic_uncore_mmio_enable_event(struct intel_uncore_box *box, + struct perf_event *event); void intel_generic_uncore_pci_init_box(struct intel_uncore_box *box); void intel_generic_uncore_pci_disable_box(struct intel_uncore_box *box); diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 0f63706cdadf..f698a55bde81 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */ #include "uncore.h" +#include "uncore_discovery.h" /* Uncore IMC PCI IDs */ #define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 @@ -64,6 +65,20 @@ #define PCI_DEVICE_ID_INTEL_RKL_2_IMC 0x4c53 #define PCI_DEVICE_ID_INTEL_ADL_1_IMC 0x4660 #define PCI_DEVICE_ID_INTEL_ADL_2_IMC 0x4641 +#define PCI_DEVICE_ID_INTEL_ADL_3_IMC 0x4601 +#define PCI_DEVICE_ID_INTEL_ADL_4_IMC 0x4602 +#define PCI_DEVICE_ID_INTEL_ADL_5_IMC 0x4609 +#define PCI_DEVICE_ID_INTEL_ADL_6_IMC 0x460a +#define PCI_DEVICE_ID_INTEL_ADL_7_IMC 0x4621 +#define PCI_DEVICE_ID_INTEL_ADL_8_IMC 0x4623 +#define PCI_DEVICE_ID_INTEL_ADL_9_IMC 0x4629 +#define PCI_DEVICE_ID_INTEL_ADL_10_IMC 0x4637 +#define PCI_DEVICE_ID_INTEL_ADL_11_IMC 0x463b +#define PCI_DEVICE_ID_INTEL_ADL_12_IMC 0x4648 +#define PCI_DEVICE_ID_INTEL_ADL_13_IMC 0x4649 +#define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 +#define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 +#define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -155,6 +170,7 @@ DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(chmask, chmask, "config:8-11"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28"); @@ -1334,6 +1350,62 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_2_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_5_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_6_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_7_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_8_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_9_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_10_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_11_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_12_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_13_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_14_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_15_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; @@ -1390,7 +1462,8 @@ static struct pci_dev *tgl_uncore_get_mc_dev(void) #define TGL_UNCORE_MMIO_IMC_MEM_OFFSET 0x10000 #define TGL_UNCORE_PCI_IMC_MAP_SIZE 0xe000 -static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +static void __uncore_imc_init_box(struct intel_uncore_box *box, + unsigned int base_offset) { struct pci_dev *pdev = tgl_uncore_get_mc_dev(); struct intel_uncore_pmu *pmu = box->pmu; @@ -1417,11 +1490,17 @@ static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) addr |= ((resource_size_t)mch_bar << 32); #endif + addr += base_offset; box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); } +static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, 0); +} + static struct intel_uncore_ops tgl_uncore_imc_freerunning_ops = { .init_box = tgl_uncore_imc_freerunning_init_box, .exit_box = uncore_mmio_exit_box, @@ -1469,3 +1548,136 @@ void tgl_uncore_mmio_init(void) } /* end of Tiger Lake MMIO uncore support */ + +/* Alder Lake MMIO uncore support */ +#define ADL_UNCORE_IMC_BASE 0xd900 +#define ADL_UNCORE_IMC_MAP_SIZE 0x200 +#define ADL_UNCORE_IMC_CTR 0xe8 +#define ADL_UNCORE_IMC_CTRL 0xd0 +#define ADL_UNCORE_IMC_GLOBAL_CTL 0xc0 +#define ADL_UNCORE_IMC_BOX_CTL 0xc4 +#define ADL_UNCORE_IMC_FREERUNNING_BASE 0xd800 +#define ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE 0x100 + +#define ADL_UNCORE_IMC_CTL_FRZ (1 << 0) +#define ADL_UNCORE_IMC_CTL_RST_CTRL (1 << 1) +#define ADL_UNCORE_IMC_CTL_RST_CTRS (1 << 2) +#define ADL_UNCORE_IMC_CTL_INT (ADL_UNCORE_IMC_CTL_RST_CTRL | \ + ADL_UNCORE_IMC_CTL_RST_CTRS) + +static void adl_uncore_imc_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_BASE); + + /* The global control in MC1 can control both MCs. */ + if (box->io_addr && (box->pmu->pmu_idx == 1)) + writel(ADL_UNCORE_IMC_CTL_INT, box->io_addr + ADL_UNCORE_IMC_GLOBAL_CTL); +} + +static void adl_uncore_mmio_disable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(ADL_UNCORE_IMC_CTL_FRZ, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static void adl_uncore_mmio_enable_box(struct intel_uncore_box *box) +{ + if (!box->io_addr) + return; + + writel(0, box->io_addr + uncore_mmio_box_ctl(box)); +} + +static struct intel_uncore_ops adl_uncore_mmio_ops = { + .init_box = adl_uncore_imc_init_box, + .exit_box = uncore_mmio_exit_box, + .disable_box = adl_uncore_mmio_disable_box, + .enable_box = adl_uncore_mmio_enable_box, + .disable_event = intel_generic_uncore_mmio_disable_event, + .enable_event = intel_generic_uncore_mmio_enable_event, + .read_counter = uncore_mmio_read_counter, +}; + +#define ADL_UNC_CTL_CHMASK_MASK 0x00000f00 +#define ADL_UNC_IMC_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \ + ADL_UNC_CTL_CHMASK_MASK | \ + SNB_UNC_CTL_EDGE_DET) + +static struct attribute *adl_uncore_imc_formats_attr[] = { + &format_attr_event.attr, + &format_attr_chmask.attr, + &format_attr_edge.attr, + NULL, +}; + +static const struct attribute_group adl_uncore_imc_format_group = { + .name = "format", + .attrs = adl_uncore_imc_formats_attr, +}; + +static struct intel_uncore_type adl_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 64, + .perf_ctr = ADL_UNCORE_IMC_CTR, + .event_ctl = ADL_UNCORE_IMC_CTRL, + .event_mask = ADL_UNC_IMC_EVENT_MASK, + .box_ctl = ADL_UNCORE_IMC_BOX_CTL, + .mmio_offset = 0, + .mmio_map_size = ADL_UNCORE_IMC_MAP_SIZE, + .ops = &adl_uncore_mmio_ops, + .format_group = &adl_uncore_imc_format_group, +}; + +enum perf_adl_uncore_imc_freerunning_types { + ADL_MMIO_UNCORE_IMC_DATA_TOTAL, + ADL_MMIO_UNCORE_IMC_DATA_READ, + ADL_MMIO_UNCORE_IMC_DATA_WRITE, + ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX +}; + +static struct freerunning_counters adl_uncore_imc_freerunning[] = { + [ADL_MMIO_UNCORE_IMC_DATA_TOTAL] = { 0x40, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_READ] = { 0x58, 0x0, 0x0, 1, 64 }, + [ADL_MMIO_UNCORE_IMC_DATA_WRITE] = { 0xA0, 0x0, 0x0, 1, 64 }, +}; + +static void adl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) +{ + __uncore_imc_init_box(box, ADL_UNCORE_IMC_FREERUNNING_BASE); +} + +static struct intel_uncore_ops adl_uncore_imc_freerunning_ops = { + .init_box = adl_uncore_imc_freerunning_init_box, + .exit_box = uncore_mmio_exit_box, + .read_counter = uncore_mmio_read_counter, + .hw_config = uncore_freerunning_hw_config, +}; + +static struct intel_uncore_type adl_uncore_imc_free_running = { + .name = "imc_free_running", + .num_counters = 3, + .num_boxes = 2, + .num_freerunning_types = ADL_MMIO_UNCORE_IMC_FREERUNNING_TYPE_MAX, + .mmio_map_size = ADL_UNCORE_IMC_FREERUNNING_MAP_SIZE, + .freerunning = adl_uncore_imc_freerunning, + .ops = &adl_uncore_imc_freerunning_ops, + .event_descs = tgl_uncore_imc_events, + .format_group = &tgl_uncore_imc_format_group, +}; + +static struct intel_uncore_type *adl_mmio_uncores[] = { + &adl_uncore_imc, + &adl_uncore_imc_free_running, + NULL +}; + +void adl_uncore_mmio_init(void) +{ + uncore_mmio_uncores = adl_mmio_uncores; +} + +/* end of Alder Lake MMIO uncore support */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 3660f698fb2a..ed869443efb2 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -5482,7 +5482,7 @@ static struct intel_uncore_type icx_uncore_imc = { .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, - .event_descs = hswep_uncore_imc_events, + .event_descs = snr_uncore_imc_events, .perf_ctr = SNR_IMC_MMIO_PMON_CTR0, .event_ctl = SNR_IMC_MMIO_PMON_CTL0, .event_mask = SNBEP_PMON_RAW_EVENT_MASK, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 9d376e528dfc..150261d929b9 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -215,7 +215,8 @@ enum { LBR_FORMAT_EIP_FLAGS2 = 0x04, LBR_FORMAT_INFO = 0x05, LBR_FORMAT_TIME = 0x06, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, + LBR_FORMAT_INFO2 = 0x07, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO2, }; enum { @@ -840,6 +841,11 @@ struct x86_pmu { bool lbr_double_abort; /* duplicated lbr aborts */ bool lbr_pt_coexist; /* (LBR|BTS) may coexist with PT */ + unsigned int lbr_has_info:1; + unsigned int lbr_has_tsx:1; + unsigned int lbr_from_flags:1; + unsigned int lbr_to_cycles:1; + /* * Intel Architectural LBR CPUID Enumeration */ @@ -1392,6 +1398,8 @@ void intel_pmu_lbr_init_skl(void); void intel_pmu_lbr_init_knl(void); +void intel_pmu_lbr_init(void); + void intel_pmu_arch_lbr_init(void); void intel_pmu_pebs_data_source_nhm(void); diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 85feafacc445..77e3a47af5ad 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -536,11 +536,14 @@ static struct perf_msr intel_rapl_spr_msrs[] = { * - perf_msr_probe(PERF_RAPL_MAX) * - want to use same event codes across both architectures */ -static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = { - [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr }, +static struct perf_msr amd_rapl_msrs[] = { + [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 }, + [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, + [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 }, + [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 }, + [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 }, }; - static int rapl_cpu_offline(unsigned int cpu) { struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1384517d7709..6e7c545bc7ee 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1483,7 +1483,8 @@ struct kvm_x86_ops { int (*get_msr_feature)(struct kvm_msr_entry *entry); - bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, void *insn, int insn_len); + bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); @@ -1496,6 +1497,7 @@ struct kvm_x86_ops { }; struct kvm_x86_nested_ops { + void (*leave_nested)(struct kvm_vcpu *vcpu); int (*check_events)(struct kvm_vcpu *vcpu); bool (*hv_timer_pending)(struct kvm_vcpu *vcpu); void (*triple_fault)(struct kvm_vcpu *vcpu); @@ -1861,7 +1863,6 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 2da3316bb559..bf6e96011dfe 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -452,6 +452,9 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 +/* attributes for system fd (group 0) */ +#define KVM_X86_XCOMP_GUEST_SUPP 0 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index a1e2f41796dc..9f4b508886dd 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -423,7 +423,7 @@ static void threshold_restart_bank(void *_tr) u32 hi, lo; /* sysfs write might race against an offline operation */ - if (this_cpu_read(threshold_banks)) + if (!this_cpu_read(threshold_banks) && !tr->set_lvt_off) return; rdmsr(tr->b->address, lo, hi); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index bb9a46a804bf..baafbb37be67 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -486,6 +486,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c) case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_ICELAKE_D: case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_XEON_PHI_KNL: case INTEL_FAM6_XEON_PHI_KNM: diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3902c28fb6cb..28be02adc669 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -133,6 +133,7 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 orig = &vcpu->arch.cpuid_entries[i]; if (e2[i].function != orig->function || e2[i].index != orig->index || + e2[i].flags != orig->flags || e2[i].eax != orig->eax || e2[i].ebx != orig->ebx || e2[i].ecx != orig->ecx || e2[i].edx != orig->edx) return -EINVAL; @@ -196,10 +197,26 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) vcpu->arch.pv_cpuid.features = best->eax; } +/* + * Calculate guest's supported XCR0 taking into account guest CPUID data and + * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0). + */ +static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) +{ + struct kvm_cpuid_entry2 *best; + + best = cpuid_entry2_find(entries, nent, 0xd, 0); + if (!best) + return 0; + + return (best->eax | ((u64)best->edx << 32)) & supported_xcr0; +} + static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); best = cpuid_entry2_find(entries, nent, 1, 0); if (best) { @@ -238,6 +255,21 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e vcpu->arch.ia32_misc_enable_msr & MSR_IA32_MISC_ENABLE_MWAIT); } + + /* + * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate + * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's + * requested XCR0 value. The enclave's XFRM must be a subset of XCRO + * at the time of EENTER, thus adjust the allowed XFRM by the guest's + * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to + * '1' even on CPUs that don't support XSAVE. + */ + best = cpuid_entry2_find(entries, nent, 0x12, 0x1); + if (best) { + best->ecx &= guest_supported_xcr0 & 0xffffffff; + best->edx &= guest_supported_xcr0 >> 32; + best->ecx |= XFEATURE_MASK_FPSSE; + } } void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) @@ -261,27 +293,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - best = kvm_find_cpuid_entry(vcpu, 0xD, 0); - if (!best) - vcpu->arch.guest_supported_xcr0 = 0; - else - vcpu->arch.guest_supported_xcr0 = - (best->eax | ((u64)best->edx << 32)) & supported_xcr0; - - /* - * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate - * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's - * requested XCR0 value. The enclave's XFRM must be a subset of XCRO - * at the time of EENTER, thus adjust the allowed XFRM by the guest's - * supported XCR0. Similar to XCR0 handling, FP and SSE are forced to - * '1' even on CPUs that don't support XSAVE. - */ - best = kvm_find_cpuid_entry(vcpu, 0x12, 0x1); - if (best) { - best->ecx &= vcpu->arch.guest_supported_xcr0 & 0xffffffff; - best->edx &= vcpu->arch.guest_supported_xcr0 >> 32; - best->ecx |= XFEATURE_MASK_FPSSE; - } + vcpu->arch.guest_supported_xcr0 = + cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); kvm_update_pv_runtime(vcpu); @@ -346,8 +359,14 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ - if (vcpu->arch.last_vmentry_cpu != -1) - return kvm_cpuid_check_equal(vcpu, e2, nent); + if (vcpu->arch.last_vmentry_cpu != -1) { + r = kvm_cpuid_check_equal(vcpu, e2, nent); + if (r) + return r; + + kvfree(e2); + return 0; + } r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -887,13 +906,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case 0xd: { - u64 guest_perm = xstate_get_guest_group_perm(); + u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xss = supported_xss; - entry->eax &= supported_xcr0 & guest_perm; - entry->ebx = xstate_required_size(supported_xcr0, false); + entry->eax &= permitted_xcr0; + entry->ebx = xstate_required_size(permitted_xcr0, false); entry->ecx = entry->ebx; - entry->edx &= (supported_xcr0 & guest_perm) >> 32; - if (!supported_xcr0) + entry->edx &= permitted_xcr0 >> 32; + if (!permitted_xcr0) break; entry = do_host_cpuid(array, function, 1); @@ -902,20 +922,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) cpuid_entry_override(entry, CPUID_D_1_EAX); if (entry->eax & (F(XSAVES)|F(XSAVEC))) - entry->ebx = xstate_required_size(supported_xcr0 | supported_xss, + entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { - WARN_ON_ONCE(supported_xss != 0); + WARN_ON_ONCE(permitted_xss != 0); entry->ebx = 0; } - entry->ecx &= supported_xss; - entry->edx &= supported_xss >> 32; + entry->ecx &= permitted_xss; + entry->edx &= permitted_xss >> 32; for (i = 2; i < 64; ++i) { bool s_state; - if (supported_xcr0 & BIT_ULL(i)) + if (permitted_xcr0 & BIT_ULL(i)) s_state = false; - else if (supported_xss & BIT_ULL(i)) + else if (permitted_xss & BIT_ULL(i)) s_state = true; else continue; @@ -929,7 +949,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * invalid sub-leafs. Only valid sub-leafs should * reach this point, and they should have a non-zero * save state size. Furthermore, check whether the - * processor agrees with supported_xcr0/supported_xss + * processor agrees with permitted_xcr0/permitted_xss * on whether this is an XCR0- or IA32_XSS-managed area. */ if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index baca9fa37a91..4662469240bc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2629,7 +2629,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_set_version(vcpu); apic_update_ppr(apic); - hrtimer_cancel(&apic->lapic_timer.timer); + cancel_apic_timer(apic); apic->lapic_timer.expired_tscdeadline = 0; apic_update_lvtt(apic); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index cf206855ebf0..1218b5a342fc 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -983,9 +983,9 @@ void svm_free_nested(struct vcpu_svm *svm) /* * Forcibly leave nested mode in order to be able to reset the VCPU later on. */ -void svm_leave_nested(struct vcpu_svm *svm) +void svm_leave_nested(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *vcpu = &svm->vcpu; + struct vcpu_svm *svm = to_svm(vcpu); if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; @@ -1411,7 +1411,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; } @@ -1478,7 +1478,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (is_guest_mode(vcpu)) - svm_leave_nested(svm); + svm_leave_nested(vcpu); else svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; @@ -1532,6 +1532,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) } struct kvm_x86_nested_ops svm_nested_ops = { + .leave_nested = svm_leave_nested, .check_events = svm_check_nested_events, .triple_fault = nested_svm_triple_fault, .get_nested_state_pages = svm_get_nested_state_pages, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6a22798eaaee..17b53457d866 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2100,8 +2100,13 @@ void __init sev_hardware_setup(void) if (!sev_enabled || !npt_enabled) goto out; - /* Does the CPU support SEV? */ - if (!boot_cpu_has(X86_FEATURE_SEV)) + /* + * SEV must obviously be supported in hardware. Sanity check that the + * CPU supports decode assists, which is mandatory for SEV guests to + * support instruction emulation. + */ + if (!boot_cpu_has(X86_FEATURE_SEV) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) goto out; /* Retrieve SEV CPUID information */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2c99b18d76c0..6d97629655e3 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -290,7 +290,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) { if (!(efer & EFER_SVME)) { - svm_leave_nested(svm); + svm_leave_nested(vcpu); svm_set_gif(svm, true); /* #GP intercept is still needed for vmware backdoor */ if (!enable_vmware_backdoor) @@ -312,7 +312,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return ret; } - if (svm_gp_erratum_intercept) + /* + * Never intercept #GP for SEV guests, KVM can't + * decrypt guest memory to workaround the erratum. + */ + if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); } } @@ -1010,9 +1014,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu) * Guest access to VMware backdoor ports could legitimately * trigger #GP because of TSS I/O permission bitmap. * We intercept those #GP and allow access to them anyway - * as VMware does. + * as VMware does. Don't intercept #GP for SEV guests as KVM can't + * decrypt guest memory to decode the faulting instruction. */ - if (enable_vmware_backdoor) + if (enable_vmware_backdoor && !sev_guest(vcpu->kvm)) set_exception_intercept(svm, GP_VECTOR); svm_set_intercept(svm, INTERCEPT_INTR); @@ -2091,10 +2096,6 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (error_code) goto reinject; - /* All SVM instructions expect page aligned RAX */ - if (svm->vmcb->save.rax & ~PAGE_MASK) - goto reinject; - /* Decode the instruction for usage later */ if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK) goto reinject; @@ -2112,8 +2113,13 @@ static int gp_interception(struct kvm_vcpu *vcpu) if (!is_guest_mode(vcpu)) return kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE); - } else + } else { + /* All SVM instructions expect page aligned RAX */ + if (svm->vmcb->save.rax & ~PAGE_MASK) + goto reinject; + return emulate_svm_instr(vcpu, opcode); + } reinject: kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); @@ -4252,79 +4258,140 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; unsigned long cr4; + u64 error_code; + + /* Emulation is always possible when KVM has access to all guest state. */ + if (!sev_guest(vcpu->kvm)) + return true; + + /* #UD and #GP should never be intercepted for SEV guests. */ + WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | + EMULTYPE_TRAP_UD_FORCED | + EMULTYPE_VMWARE_GP)); /* - * When the guest is an SEV-ES guest, emulation is not possible. + * Emulation is impossible for SEV-ES guests as KVM doesn't have access + * to guest register state. */ if (sev_es_guest(vcpu->kvm)) return false; /* + * Emulation is possible if the instruction is already decoded, e.g. + * when completing I/O after returning from userspace. + */ + if (emul_type & EMULTYPE_NO_DECODE) + return true; + + /* + * Emulation is possible for SEV guests if and only if a prefilled + * buffer containing the bytes of the intercepted instruction is + * available. SEV guest memory is encrypted with a guest specific key + * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * decode garbage. + * + * Inject #UD if KVM reached this point without an instruction buffer. + * In practice, this path should never be hit by a well-behaved guest, + * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path + * is still theoretically reachable, e.g. via unaccelerated fault-like + * AVIC access, and needs to be handled by KVM to avoid putting the + * guest into an infinite loop. Injecting #UD is somewhat arbitrary, + * but its the least awful option given lack of insight into the guest. + */ + if (unlikely(!insn)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return false; + } + + /* + * Emulate for SEV guests if the insn buffer is not empty. The buffer + * will be empty if the DecodeAssist microcode cannot fetch bytes for + * the faulting instruction because the code fetch itself faulted, e.g. + * the guest attempted to fetch from emulated MMIO or a guest page + * table used to translate CS:RIP resides in emulated MMIO. + */ + if (likely(insn_len)) + return true; + + /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. * * Errata: - * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is - * possible that CPU microcode implementing DecodeAssist will fail - * to read bytes of instruction which caused #NPF. In this case, - * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly - * return 0 instead of the correct guest instruction bytes. - * - * This happens because CPU microcode reading instruction bytes - * uses a special opcode which attempts to read data using CPL=0 - * privileges. The microcode reads CS:RIP and if it hits a SMAP - * fault, it gives up and returns no instruction bytes. + * When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is + * possible that CPU microcode implementing DecodeAssist will fail to + * read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly + * be '0'. This happens because microcode reads CS:RIP using a _data_ + * loap uop with CPL=0 privileges. If the load hits a SMAP #PF, ucode + * gives up and does not fill the instruction bytes buffer. * - * Detection: - * We reach here in case CPU supports DecodeAssist, raised #NPF and - * returned 0 in GuestIntrBytes field of the VMCB. - * First, errata can only be triggered in case vCPU CR4.SMAP=1. - * Second, if vCPU CR4.SMEP=1, errata could only be triggered - * in case vCPU CPL==3 (Because otherwise guest would have triggered - * a SMEP fault instead of #NPF). - * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL. - * As most guests enable SMAP if they have also enabled SMEP, use above - * logic in order to attempt minimize false-positive of detecting errata - * while still preserving all cases semantic correctness. + * As above, KVM reaches this point iff the VM is an SEV guest, the CPU + * supports DecodeAssist, a #NPF was raised, KVM's page fault handler + * triggered emulation (e.g. for MMIO), and the CPU returned 0 in the + * GuestIntrBytes field of the VMCB. * - * Workaround: - * To determine what instruction the guest was executing, the hypervisor - * will have to decode the instruction at the instruction pointer. + * This does _not_ mean that the erratum has been encountered, as the + * DecodeAssist will also fail if the load for CS:RIP hits a legitimate + * #PF, e.g. if the guest attempt to execute from emulated MMIO and + * encountered a reserved/not-present #PF. * - * In non SEV guest, hypervisor will be able to read the guest - * memory to decode the instruction pointer when insn_len is zero - * so we return true to indicate that decoding is possible. + * To hit the erratum, the following conditions must be true: + * 1. CR4.SMAP=1 (obviously). + * 2. CR4.SMEP=0 || CPL=3. If SMEP=1 and CPL<3, the erratum cannot + * have been hit as the guest would have encountered a SMEP + * violation #PF, not a #NPF. + * 3. The #NPF is not due to a code fetch, in which case failure to + * retrieve the instruction bytes is legitimate (see abvoe). * - * But in the SEV guest, the guest memory is encrypted with the - * guest specific key and hypervisor will not be able to decode the - * instruction pointer so we will not able to workaround it. Lets - * print the error and request to kill the guest. + * In addition, don't apply the erratum workaround if the #NPF occurred + * while translating guest page tables (see below). */ - if (likely(!insn || insn_len)) - return true; - - /* - * If RIP is invalid, go ahead with emulation which will cause an - * internal error exit. - */ - if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT)) - return true; + error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) + goto resume_guest; cr4 = kvm_read_cr4(vcpu); smep = cr4 & X86_CR4_SMEP; smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - if (!sev_guest(vcpu->kvm)) - return true; - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); - kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + + /* + * If the fault occurred in userspace, arbitrarily inject #GP + * to avoid killing the guest and to hopefully avoid confusing + * the guest kernel too much, e.g. injecting #PF would not be + * coherent with respect to the guest's page tables. Request + * triple fault if the fault occurred in the kernel as there's + * no fault that KVM can inject without confusing the guest. + * In practice, the triple fault is moot as no sane SEV kernel + * will execute from user memory while also running with SMAP=1. + */ + if (is_user) + kvm_inject_gp(vcpu, 0); + else + kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); } +resume_guest: + /* + * If the erratum was not hit, simply resume the guest and let it fault + * again. While awful, e.g. the vCPU may get stuck in an infinite loop + * if the fault is at CPL=0, it's the lesser of all evils. Exiting to + * userspace will kill the guest, and letting the emulator read garbage + * will yield random behavior and potentially corrupt the guest. + * + * Simply resuming the guest is technically not a violation of the SEV + * architecture. AMD's APM states that all code fetches and page table + * accesses for SEV guest are encrypted, regardless of the C-Bit. The + * APM also states that encrypted accesses to MMIO are "ignored", but + * doesn't explicitly define "ignored", i.e. doing nothing and letting + * the guest spin is technically "ignoring" the access. + */ return false; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 47ef8f4a9358..73525353e424 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -304,11 +304,6 @@ static inline void vmcb_mark_all_clean(struct vmcb *vmcb) & ~VMCB_ALWAYS_DIRTY_MASK; } -static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit) -{ - return (vmcb->control.clean & (1 << bit)); -} - static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit) { vmcb->control.clean &= ~(1 << bit); @@ -525,7 +520,7 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm) int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun); -void svm_leave_nested(struct vcpu_svm *svm); +void svm_leave_nested(struct kvm_vcpu *vcpu); void svm_free_nested(struct vcpu_svm *svm); int svm_allocate_nested(struct vcpu_svm *svm); int nested_svm_vmrun(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index c53b8bf8d013..489ca56212c6 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -46,6 +46,9 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb) if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) hve->hv_enlightenments_control.enlightened_npt_tlb = 1; + + if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP) + hve->hv_enlightenments_control.msr_bitmap = 1; } static inline void svm_hv_hardware_setup(void) @@ -83,14 +86,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( struct hv_enlightenments *hve = (struct hv_enlightenments *)vmcb->control.reserved_sw; - /* - * vmcb can be NULL if called during early vcpu init. - * And its okay not to mark vmcb dirty during vcpu init - * as we mark it dirty unconditionally towards end of vcpu - * init phase. - */ - if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) && - hve->hv_enlightenments_control.msr_bitmap) + if (hve->hv_enlightenments_control.msr_bitmap) vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 959b59d13b5a..3f430e218375 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -54,7 +54,6 @@ struct nested_vmx_msrs { struct vmcs_config { int size; - int order; u32 basic_cap; u32 revision_id; u32 pin_based_exec_ctrl; diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index ba6f99f584ac..87e3dc10edf4 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -12,8 +12,6 @@ DEFINE_STATIC_KEY_FALSE(enable_evmcs); -#if IS_ENABLED(CONFIG_HYPERV) - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -296,6 +294,7 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); +#if IS_ENABLED(CONFIG_HYPERV) __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) { vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; @@ -362,6 +361,7 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata) case MSR_IA32_VMX_PROCBASED_CTLS2: ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC; break; + case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; break; diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index 16731d2cf231..8d70f9aea94b 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -59,12 +59,12 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); SECONDARY_EXEC_SHADOW_VMCS | \ SECONDARY_EXEC_TSC_SCALING | \ SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) +#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) #define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) -#if IS_ENABLED(CONFIG_HYPERV) - struct evmcs_field { u16 offset; u16 clean_field; @@ -73,26 +73,56 @@ struct evmcs_field { extern const struct evmcs_field vmcs_field_to_evmcs_1[]; extern const unsigned int nr_evmcs_1_fields; -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) { unsigned int index = ROL16(field, 6); const struct evmcs_field *evmcs_field; - if (unlikely(index >= nr_evmcs_1_fields)) { - WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n", - field); + if (unlikely(index >= nr_evmcs_1_fields)) return -ENOENT; - } evmcs_field = &vmcs_field_to_evmcs_1[index]; + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + if (clean_field) *clean_field = evmcs_field->clean_field; return evmcs_field->offset; } +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#if IS_ENABLED(CONFIG_HYPERV) + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", + field); + + return offset; +} + static __always_inline void evmcs_write64(unsigned long field, u64 value) { u16 clean_field; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f235f77cbc03..ba34e94049c7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,6 +7,7 @@ #include <asm/mmu_context.h> #include "cpuid.h" +#include "evmcs.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" @@ -4851,18 +4852,20 @@ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu) struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs; /* - * We should allocate a shadow vmcs for vmcs01 only when L1 - * executes VMXON and free it when L1 executes VMXOFF. - * As it is invalid to execute VMXON twice, we shouldn't reach - * here when vmcs01 already have an allocated shadow vmcs. + * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it + * when L1 executes VMXOFF or the vCPU is forced out of nested + * operation. VMXON faults if the CPU is already post-VMXON, so it + * should be impossible to already have an allocated shadow VMCS. KVM + * doesn't support virtualization of VMCS shadowing, so vmcs01 should + * always be the loaded VMCS. */ - WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs); + if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs)) + return loaded_vmcs->shadow_vmcs; + + loaded_vmcs->shadow_vmcs = alloc_vmcs(true); + if (loaded_vmcs->shadow_vmcs) + vmcs_clear(loaded_vmcs->shadow_vmcs); - if (!loaded_vmcs->shadow_vmcs) { - loaded_vmcs->shadow_vmcs = alloc_vmcs(true); - if (loaded_vmcs->shadow_vmcs) - vmcs_clear(loaded_vmcs->shadow_vmcs); - } return loaded_vmcs->shadow_vmcs; } @@ -5099,27 +5102,49 @@ static int handle_vmread(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - /* - * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, - * any VMREAD sets the ALU flags for VMfailInvalid. - */ - if (vmx->nested.current_vmptr == INVALID_GPA || - (is_guest_mode(vcpu) && - get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) - return nested_vmx_failInvalid(vcpu); - /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); - if (offset < 0) - return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + /* + * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, + * any VMREAD sets the ALU flags for VMfailInvalid. + */ + if (vmx->nested.current_vmptr == INVALID_GPA || + (is_guest_mode(vcpu) && + get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA)) + return nested_vmx_failInvalid(vcpu); - if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) - copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); + offset = get_vmcs12_field_offset(field); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field)) + copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - /* Read the field, zero-extended to a u64 value */ - value = vmcs12_read_any(vmcs12, field, offset); + /* Read the field, zero-extended to a u64 value */ + value = vmcs12_read_any(vmcs12, field, offset); + } else { + /* + * Hyper-V TLFS (as of 6.0b) explicitly states, that while an + * enlightened VMCS is active VMREAD/VMWRITE instructions are + * unsupported. Unfortunately, certain versions of Windows 11 + * don't comply with this requirement which is not enforced in + * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a + * workaround, as misbehaving guests will panic on VM-Fail. + * Note, enlightened VMCS is incompatible with shadow VMCS so + * all VMREADs from L2 should go to L1. + */ + if (WARN_ON_ONCE(is_guest_mode(vcpu))) + return nested_vmx_failInvalid(vcpu); + + offset = evmcs_field_offset(field, NULL); + if (offset < 0) + return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); + + /* Read the field, zero-extended to a u64 value */ + value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset); + } /* * Now copy part of this value to register or memory, as requested. @@ -5214,7 +5239,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - offset = vmcs_field_to_offset(field); + offset = get_vmcs12_field_offset(field); if (offset < 0) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); @@ -6462,7 +6487,7 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) max_idx = 0; for (i = 0; i < nr_vmcs12_fields; i++) { /* The vmcs12 table is very, very sparsely populated. */ - if (!vmcs_field_to_offset_table[i]) + if (!vmcs12_field_offsets[i]) continue; idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i)); @@ -6771,6 +6796,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *)) } struct kvm_x86_nested_ops vmx_nested_ops = { + .leave_nested = vmx_leave_nested, .check_events = vmx_check_nested_events, .hv_timer_pending = nested_vmx_preemption_timer_pending, .triple_fault = nested_vmx_triple_fault, diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index cab6ba7a5005..2251b60920f8 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -8,7 +8,7 @@ FIELD(number, name), \ [ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32) -const unsigned short vmcs_field_to_offset_table[] = { +const unsigned short vmcs12_field_offsets[] = { FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id), FIELD(POSTED_INTR_NV, posted_intr_nv), FIELD(GUEST_ES_SELECTOR, guest_es_selector), @@ -151,4 +151,4 @@ const unsigned short vmcs_field_to_offset_table[] = { FIELD(HOST_RSP, host_rsp), FIELD(HOST_RIP, host_rip), }; -const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs_field_to_offset_table); +const unsigned int nr_vmcs12_fields = ARRAY_SIZE(vmcs12_field_offsets); diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 2a45f026ee11..746129ddd5ae 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -361,10 +361,10 @@ static inline void vmx_check_vmcs12_offsets(void) CHECK_OFFSET(guest_pml_index, 996); } -extern const unsigned short vmcs_field_to_offset_table[]; +extern const unsigned short vmcs12_field_offsets[]; extern const unsigned int nr_vmcs12_fields; -static inline short vmcs_field_to_offset(unsigned long field) +static inline short get_vmcs12_field_offset(unsigned long field) { unsigned short offset; unsigned int index; @@ -377,7 +377,7 @@ static inline short vmcs_field_to_offset(unsigned long field) return -ENOENT; index = array_index_nospec(index, nr_vmcs12_fields); - offset = vmcs_field_to_offset_table[index]; + offset = vmcs12_field_offsets[index]; if (offset == 0) return -ENOENT; return offset; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4ac676066d60..aca3ae2a02f3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1487,11 +1487,12 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len) +static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does - * not point tthe failing instruction, and even if it did, the code + * not point at the failing instruction, and even if it did, the code * stream is inaccessible. Inject #UD instead of exiting to userspace * so that guest userspace can't DoS the guest simply by triggering * emulation (enclaves are CPL3 only). @@ -2603,7 +2604,6 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, return -EIO; vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_conf->size); vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff; vmcs_conf->revision_id = vmx_msr_low; @@ -2628,7 +2628,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) struct page *pages; struct vmcs *vmcs; - pages = __alloc_pages_node(node, flags, vmcs_config.order); + pages = __alloc_pages_node(node, flags, 0); if (!pages) return NULL; vmcs = page_address(pages); @@ -2647,7 +2647,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) void free_vmcs(struct vmcs *vmcs) { - free_pages((unsigned long)vmcs, vmcs_config.order); + free_page((unsigned long)vmcs); } /* @@ -4094,10 +4094,14 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) vmcs_write32(HOST_IA32_SYSENTER_CS, low32); /* - * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites - * HOST_IA32_SYSENTER_ESP. + * SYSENTER is used for 32-bit system calls on either 32-bit or + * 64-bit kernels. It is always zero If neither is allowed, otherwise + * vmx_vcpu_load_vmcs loads it with the per-CPU entry stack (and may + * have already done so!). */ - vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32)) + vmcs_writel(HOST_IA32_SYSENTER_ESP, 0); + rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl); vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */ @@ -4901,8 +4905,33 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) dr6 = vmx_get_exit_qual(vcpu); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + /* + * If the #DB was due to ICEBP, a.k.a. INT1, skip the + * instruction. ICEBP generates a trap-like #DB, but + * despite its interception control being tied to #DB, + * is an instruction intercept, i.e. the VM-Exit occurs + * on the ICEBP itself. Note, skipping ICEBP also + * clears STI and MOVSS blocking. + * + * For all other #DBs, set vmcs.PENDING_DBG_EXCEPTIONS.BS + * if single-step is enabled in RFLAGS and STI or MOVSS + * blocking is active, as the CPU doesn't set the bit + * on VM-Exit due to #DB interception. VM-Entry has a + * consistency check that a single-step #DB is pending + * in this scenario as the previous instruction cannot + * have toggled RFLAGS.TF 0=>1 (because STI and POP/MOV + * don't modify RFLAGS), therefore the one instruction + * delay when activating single-step breakpoints must + * have already expired. Note, the CPU sets/clears BS + * as appropriate for all other VM-Exits types. + */ if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); + else if ((vmx_get_rflags(vcpu) & X86_EFLAGS_TF) && + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS))) + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS) | DR6_BS); kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; @@ -5397,7 +5426,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, NULL, 0)) + if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9e43d756312f..74b53a16f38a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3535,6 +3535,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~supported_xss) return 1; vcpu->arch.ia32_xss = data; + kvm_update_cpuid_runtime(vcpu); break; case MSR_SMI_COUNT: if (!msr_info->host_initiated) @@ -4229,6 +4230,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SREGS2: case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: + case KVM_CAP_SYS_ATTRIBUTES: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4331,7 +4333,49 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; } return r; +} + +static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) +{ + void __user *uaddr = (void __user*)(unsigned long)attr->addr; + if ((u64)(unsigned long)uaddr != attr->addr) + return ERR_PTR(-EFAULT); + return uaddr; +} + +static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) +{ + u64 __user *uaddr = kvm_get_attr_addr(attr); + + if (attr->group) + return -ENXIO; + + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + if (put_user(supported_xcr0, uaddr)) + return -EFAULT; + return 0; + default: + return -ENXIO; + break; + } +} + +static int kvm_x86_dev_has_attr(struct kvm_device_attr *attr) +{ + if (attr->group) + return -ENXIO; + + switch (attr->attr) { + case KVM_X86_XCOMP_GUEST_SUPP: + return 0; + default: + return -ENXIO; + } } long kvm_arch_dev_ioctl(struct file *filp, @@ -4422,6 +4466,22 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; + case KVM_GET_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_get_attr(&attr); + break; + } + case KVM_HAS_DEVICE_ATTR: { + struct kvm_device_attr attr; + r = -EFAULT; + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + break; + r = kvm_x86_dev_has_attr(&attr); + break; + } default: r = -EINVAL; break; @@ -4860,8 +4920,10 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { - if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) + if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { + kvm_x86_ops.nested_ops->leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); + } vcpu->arch.smi_pending = events->smi.pending; @@ -5022,11 +5084,11 @@ static int kvm_arch_tsc_has_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: @@ -5045,12 +5107,12 @@ static int kvm_arch_tsc_get_attr(struct kvm_vcpu *vcpu, static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { - u64 __user *uaddr = (u64 __user *)(unsigned long)attr->addr; + u64 __user *uaddr = kvm_get_attr_addr(attr); struct kvm *kvm = vcpu->kvm; int r; - if ((u64)(unsigned long)uaddr != attr->addr) - return -EFAULT; + if (IS_ERR(uaddr)) + return PTR_ERR(uaddr); switch (attr->attr) { case KVM_VCPU_TSC_OFFSET: { @@ -6810,6 +6872,13 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); +static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) +{ + return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, + insn, insn_len); +} + int handle_ud(struct kvm_vcpu *vcpu) { static const char kvm_emulate_prefix[] = { __KVM_EMULATE_PREFIX }; @@ -6817,7 +6886,7 @@ int handle_ud(struct kvm_vcpu *vcpu) char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) return 1; if (force_emulation_prefix && @@ -8193,7 +8262,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) + if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -9706,7 +9775,7 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); } -void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) +static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) return; @@ -11209,7 +11278,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.msr_misc_features_enables = 0; - vcpu->arch.xcr0 = XFEATURE_MASK_FP; + __kvm_set_xcr(vcpu, 0, XFEATURE_MASK_FP); + __kvm_set_msr(vcpu, MSR_IA32_XSS, 0, true); } /* All GPRs except RDX (handled below) are zeroed on RESET/INIT. */ @@ -11226,8 +11296,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1, 0); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); - vcpu->arch.ia32_xss = 0; - static_call(kvm_x86_vcpu_reset)(vcpu, init_event); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 0e3f7d6e9fd7..bad57535fad0 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -316,10 +316,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotq %0\n" "\t" LOCK_PREFIX "andq %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) @@ -335,10 +332,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) "\tnotl %0\n" "\t" LOCK_PREFIX "andl %0, %2\n" "2:\n" - "\t.section .fixup,\"ax\"\n" - "3:\tjmp\t2b\n" - "\t.previous\n" - _ASM_EXTABLE_UA(1b, 3b) + _ASM_EXTABLE_UA(1b, 2b) : "=r" (evtchn_pending_sel32), "+m" (vi->evtchn_pending_sel), "+m" (v->arch.xen.evtchn_pending_sel) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 2edd86649468..615a76d70019 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -353,8 +353,8 @@ static void pci_fixup_video(struct pci_dev *pdev) } } } -DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_DISPLAY_VGA, 8, pci_fixup_video); static const struct dmi_system_id msi_k8t_dmi_table[] = { diff --git a/block/blk-core.c b/block/blk-core.c index 97f8bc8d3a79..d93e3bb9a769 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1061,20 +1061,32 @@ again: } static unsigned long __part_start_io_acct(struct block_device *part, - unsigned int sectors, unsigned int op) + unsigned int sectors, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); - unsigned long now = READ_ONCE(jiffies); part_stat_lock(); - update_io_ticks(part, now, false); + update_io_ticks(part, start_time, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); - return now; + return start_time; +} + +/** + * bio_start_io_acct_time - start I/O accounting for bio based drivers + * @bio: bio to start account for + * @start_time: start time that should be passed back to bio_end_io_acct(). + */ +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time) +{ + __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), start_time); } +EXPORT_SYMBOL_GPL(bio_start_io_acct_time); /** * bio_start_io_acct - start I/O accounting for bio based drivers @@ -1084,14 +1096,15 @@ static unsigned long __part_start_io_acct(struct block_device *part, */ unsigned long bio_start_io_acct(struct bio *bio) { - return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio)); + return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(disk->part0, sectors, op); + return __part_start_io_acct(disk->part0, sectors, op, jiffies); } EXPORT_SYMBOL(disk_start_io_acct); diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index b925f3db3ab7..18c68d8b9138 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -144,7 +144,7 @@ int disk_register_independent_access_ranges(struct gendisk *disk, &q->kobj, "%s", "independent_access_ranges"); if (ret) { q->ia_ranges = NULL; - kfree(iars); + kobject_put(&iars->kobj); return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index f3bf3358a3bb..1adfe4824ef5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2922,6 +2922,8 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * */ blk_mq_run_dispatch_ops(rq->q, ret = blk_mq_request_issue_directly(rq, true)); + if (ret) + blk_account_io_done(rq, ktime_get_ns()); return ret; } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c index 028329428b75..87c7c90676ca 100644 --- a/drivers/ata/pata_platform.c +++ b/drivers/ata/pata_platform.c @@ -128,6 +128,8 @@ int __pata_platform_probe(struct device *dev, struct resource *io_res, ap = host->ports[0]; ap->ops = devm_kzalloc(dev, sizeof(*ap->ops), GFP_KERNEL); + if (!ap->ops) + return -ENOMEM; ap->ops->inherits = &ata_sff_port_ops; ap->ops->cable_detect = ata_cable_unknown; ap->ops->set_mode = pata_platform_set_mode; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 1a4f8b227eac..06514ed66022 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2428,10 +2428,15 @@ static int btintel_setup_combined(struct hci_dev *hdev) /* Apply the device specific HCI quirks * - * WBS for SdP - SdP and Stp have a same hw_varaint but - * different fw_variant + * WBS for SdP - For the Legacy ROM products, only SdP + * supports the WBS. But the version information is not + * enough to use here because the StP2 and SdP have same + * hw_variant and fw_variant. So, this flag is set by + * the transport driver (btusb) based on the HW info + * (idProduct) */ - if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22) + if (!btintel_test_flag(hdev, + INTEL_ROM_LEGACY_NO_WBS_SUPPORT)) set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index c9b24e9299e2..e0060e58573c 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -152,6 +152,7 @@ enum { INTEL_BROKEN_INITIAL_NCMD, INTEL_BROKEN_SHUTDOWN_LED, INTEL_ROM_LEGACY, + INTEL_ROM_LEGACY_NO_WBS_SUPPORT, __INTEL_NUM_FLAGS, }; diff --git a/drivers/bluetooth/btmrvl_debugfs.c b/drivers/bluetooth/btmrvl_debugfs.c index c4867576be00..db35b917aecf 100644 --- a/drivers/bluetooth/btmrvl_debugfs.c +++ b/drivers/bluetooth/btmrvl_debugfs.c @@ -1,4 +1,4 @@ -/** +/* * Marvell Bluetooth driver: debugfs related functions * * Copyright (C) 2009, Marvell International Ltd. diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 68378b42ea7f..b8ef66f89fc1 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -1,4 +1,4 @@ -/** +/* * Marvell BT-over-SDIO driver: SDIO interface related functions. * * Copyright (C) 2009, Marvell International Ltd. diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 6e7b0c7567c0..fb76d9765ce0 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -7,8 +7,12 @@ #define HCI_WMT_MAX_EVENT_SIZE 64 +#define BTMTK_WMT_REG_WRITE 0x1 #define BTMTK_WMT_REG_READ 0x2 +#define MT7921_PINMUX_0 0x70005050 +#define MT7921_PINMUX_1 0x70005054 + enum { BTMTK_WMT_PATCH_DWNLD = 0x1, BTMTK_WMT_TEST = 0x2, @@ -68,6 +72,37 @@ struct btmtk_tci_sleep { u8 time_compensation; } __packed; +struct btmtk_wakeon { + u8 mode; + u8 gpo; + u8 active_high; + __le16 enable_delay; + __le16 wakeup_delay; +} __packed; + +struct btmtk_sco { + u8 clock_config; + u8 transmit_format_config; + u8 channel_format_config; + u8 channel_select_config; +} __packed; + +struct reg_read_cmd { + u8 type; + u8 rsv; + u8 num; + __le32 addr; +} __packed; + +struct reg_write_cmd { + u8 type; + u8 rsv; + u8 num; + __le32 addr; + __le32 data; + __le32 mask; +} __packed; + struct btmtk_hci_wmt_params { u8 op; u8 flag; diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index b5ea8d3bffaa..8be763ab3bf4 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -31,28 +31,32 @@ #define VERSION "0.1" -#define MTKBTSDIO_AUTOSUSPEND_DELAY 8000 +#define MTKBTSDIO_AUTOSUSPEND_DELAY 1000 -static bool enable_autosuspend; +static bool enable_autosuspend = true; struct btmtksdio_data { const char *fwname; u16 chipid; + bool lp_mbox_supported; }; static const struct btmtksdio_data mt7663_data = { .fwname = FIRMWARE_MT7663, .chipid = 0x7663, + .lp_mbox_supported = false, }; static const struct btmtksdio_data mt7668_data = { .fwname = FIRMWARE_MT7668, .chipid = 0x7668, + .lp_mbox_supported = false, }; static const struct btmtksdio_data mt7921_data = { .fwname = FIRMWARE_MT7961, .chipid = 0x7921, + .lp_mbox_supported = true, }; static const struct sdio_device_id btmtksdio_table[] = { @@ -87,8 +91,17 @@ MODULE_DEVICE_TABLE(sdio, btmtksdio_table); #define RX_DONE_INT BIT(1) #define TX_EMPTY BIT(2) #define TX_FIFO_OVERFLOW BIT(8) +#define FW_MAILBOX_INT BIT(15) +#define INT_MASK GENMASK(15, 0) #define RX_PKT_LEN GENMASK(31, 16) +#define MTK_REG_CSICR 0xc0 +#define CSICR_CLR_MBOX_ACK BIT(0) +#define MTK_REG_PH2DSM0R 0xc4 +#define PH2DSM0R_DRIVER_OWN BIT(0) +#define MTK_REG_PD2HRM0R 0xdc +#define PD2HRM0R_DRV_OWN BIT(0) + #define MTK_REG_CTDR 0x18 #define MTK_REG_CRDR 0x1c @@ -100,6 +113,7 @@ MODULE_DEVICE_TABLE(sdio, btmtksdio_table); #define BTMTKSDIO_TX_WAIT_VND_EVT 1 #define BTMTKSDIO_HW_TX_READY 2 #define BTMTKSDIO_FUNC_ENABLED 3 +#define BTMTKSDIO_PATCH_ENABLED 4 struct mtkbtsdio_hdr { __le16 len; @@ -278,6 +292,78 @@ static u32 btmtksdio_drv_own_query(struct btmtksdio_dev *bdev) return sdio_readl(bdev->func, MTK_REG_CHLPCR, NULL); } +static u32 btmtksdio_drv_own_query_79xx(struct btmtksdio_dev *bdev) +{ + return sdio_readl(bdev->func, MTK_REG_PD2HRM0R, NULL); +} + +static int btmtksdio_fw_pmctrl(struct btmtksdio_dev *bdev) +{ + u32 status; + int err; + + sdio_claim_host(bdev->func); + + if (bdev->data->lp_mbox_supported && + test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state)) { + sdio_writel(bdev->func, CSICR_CLR_MBOX_ACK, MTK_REG_CSICR, + &err); + err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev, + status, !(status & PD2HRM0R_DRV_OWN), + 2000, 1000000); + if (err < 0) { + bt_dev_err(bdev->hdev, "mailbox ACK not cleared"); + goto out; + } + } + + /* Return ownership to the device */ + sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err); + if (err < 0) + goto out; + + err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, + !(status & C_COM_DRV_OWN), 2000, 1000000); + +out: + sdio_release_host(bdev->func); + + if (err < 0) + bt_dev_err(bdev->hdev, "Cannot return ownership to device"); + + return err; +} + +static int btmtksdio_drv_pmctrl(struct btmtksdio_dev *bdev) +{ + u32 status; + int err; + + sdio_claim_host(bdev->func); + + /* Get ownership from the device */ + sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); + if (err < 0) + goto out; + + err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, + status & C_COM_DRV_OWN, 2000, 1000000); + + if (!err && bdev->data->lp_mbox_supported && + test_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state)) + err = readx_poll_timeout(btmtksdio_drv_own_query_79xx, bdev, + status, status & PD2HRM0R_DRV_OWN, + 2000, 1000000); + +out: + sdio_release_host(bdev->func); + + if (err < 0) + bt_dev_err(bdev->hdev, "Cannot get ownership from device"); + + return err; +} + static int btmtksdio_recv_event(struct hci_dev *hdev, struct sk_buff *skb) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); @@ -480,6 +566,13 @@ static void btmtksdio_txrx_work(struct work_struct *work) * FIFO. */ sdio_writel(bdev->func, int_status, MTK_REG_CHISR, NULL); + int_status &= INT_MASK; + + if ((int_status & FW_MAILBOX_INT) && + bdev->data->chipid == 0x7921) { + sdio_writel(bdev->func, PH2DSM0R_DRIVER_OWN, + MTK_REG_PH2DSM0R, 0); + } if (int_status & FW_OWN_BACK_INT) bt_dev_dbg(bdev->hdev, "Get fw own back"); @@ -531,7 +624,7 @@ static void btmtksdio_interrupt(struct sdio_func *func) static int btmtksdio_open(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); - u32 status, val; + u32 val; int err; sdio_claim_host(bdev->func); @@ -542,18 +635,10 @@ static int btmtksdio_open(struct hci_dev *hdev) set_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state); - /* Get ownership from the device */ - sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); + err = btmtksdio_drv_pmctrl(bdev); if (err < 0) goto err_disable_func; - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - status & C_COM_DRV_OWN, 2000, 1000000); - if (err < 0) { - bt_dev_err(bdev->hdev, "Cannot get ownership from device"); - goto err_disable_func; - } - /* Disable interrupt & mask out all interrupt sources */ sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, &err); if (err < 0) @@ -623,8 +708,6 @@ err_release_host: static int btmtksdio_close(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); - u32 status; - int err; sdio_claim_host(bdev->func); @@ -635,13 +718,7 @@ static int btmtksdio_close(struct hci_dev *hdev) cancel_work_sync(&bdev->txrx_work); - /* Return ownership to the device */ - sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, NULL); - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - !(status & C_COM_DRV_OWN), 2000, 1000000); - if (err < 0) - bt_dev_err(bdev->hdev, "Cannot return ownership to device"); + btmtksdio_fw_pmctrl(bdev); clear_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state); sdio_disable_func(bdev->func); @@ -686,6 +763,7 @@ static int btmtksdio_func_query(struct hci_dev *hdev) static int mt76xx_setup(struct hci_dev *hdev, const char *fwname) { + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); struct btmtk_hci_wmt_params wmt_params; struct btmtk_tci_sleep tci_sleep; struct sk_buff *skb; @@ -746,6 +824,8 @@ ignore_setup_fw: return err; } + set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state); + ignore_func_on: /* Apply the low power environment setup */ tci_sleep.mode = 0x5; @@ -768,6 +848,7 @@ ignore_func_on: static int mt79xx_setup(struct hci_dev *hdev, const char *fwname) { + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); struct btmtk_hci_wmt_params wmt_params; u8 param = 0x1; int err; @@ -793,19 +874,15 @@ static int mt79xx_setup(struct hci_dev *hdev, const char *fwname) hci_set_msft_opcode(hdev, 0xFD30); hci_set_aosp_capable(hdev); + set_bit(BTMTKSDIO_PATCH_ENABLED, &bdev->tx_state); return err; } -static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) +static int btmtksdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) { struct btmtk_hci_wmt_params wmt_params; - struct reg_read_cmd { - u8 type; - u8 rsv; - u8 num; - __le32 addr; - } __packed reg_read = { + struct reg_read_cmd reg_read = { .type = 1, .num = 1, }; @@ -821,7 +898,7 @@ static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) err = mtk_hci_wmt_sync(hdev, &wmt_params); if (err < 0) { - bt_dev_err(hdev, "Failed to read reg(%d)", err); + bt_dev_err(hdev, "Failed to read reg (%d)", err); return err; } @@ -830,6 +907,66 @@ static int btsdio_mtk_reg_read(struct hci_dev *hdev, u32 reg, u32 *val) return err; } +static int btmtksdio_mtk_reg_write(struct hci_dev *hdev, u32 reg, u32 val, u32 mask) +{ + struct btmtk_hci_wmt_params wmt_params; + const struct reg_write_cmd reg_write = { + .type = 1, + .num = 1, + .addr = cpu_to_le32(reg), + .data = cpu_to_le32(val), + .mask = cpu_to_le32(mask), + }; + int err, status; + + wmt_params.op = BTMTK_WMT_REGISTER; + wmt_params.flag = BTMTK_WMT_REG_WRITE; + wmt_params.dlen = sizeof(reg_write); + wmt_params.data = ®_write; + wmt_params.status = &status; + + err = mtk_hci_wmt_sync(hdev, &wmt_params); + if (err < 0) + bt_dev_err(hdev, "Failed to write reg (%d)", err); + + return err; +} + +static int btmtksdio_sco_setting(struct hci_dev *hdev) +{ + const struct btmtk_sco sco_setting = { + .clock_config = 0x49, + .channel_format_config = 0x80, + }; + struct sk_buff *skb; + u32 val; + int err; + + /* Enable SCO over I2S/PCM for MediaTek chipset */ + skb = __hci_cmd_sync(hdev, 0xfc72, sizeof(sco_setting), + &sco_setting, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + kfree_skb(skb); + + err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_0, &val); + if (err < 0) + return err; + + val |= 0x11000000; + err = btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_0, val, ~0); + if (err < 0) + return err; + + err = btmtksdio_mtk_reg_read(hdev, MT7921_PINMUX_1, &val); + if (err < 0) + return err; + + val |= 0x00000101; + return btmtksdio_mtk_reg_write(hdev, MT7921_PINMUX_1, val, ~0); +} + static int btmtksdio_setup(struct hci_dev *hdev) { struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); @@ -844,13 +981,13 @@ static int btmtksdio_setup(struct hci_dev *hdev) switch (bdev->data->chipid) { case 0x7921: - err = btsdio_mtk_reg_read(hdev, 0x70010200, &dev_id); + err = btmtksdio_mtk_reg_read(hdev, 0x70010200, &dev_id); if (err < 0) { bt_dev_err(hdev, "Failed to get device id (%d)", err); return err; } - err = btsdio_mtk_reg_read(hdev, 0x80021004, &fw_version); + err = btmtksdio_mtk_reg_read(hdev, 0x80021004, &fw_version); if (err < 0) { bt_dev_err(hdev, "Failed to get fw version (%d)", err); return err; @@ -862,6 +999,22 @@ static int btmtksdio_setup(struct hci_dev *hdev) err = mt79xx_setup(hdev, fwname); if (err < 0) return err; + + err = btmtksdio_fw_pmctrl(bdev); + if (err < 0) + return err; + + err = btmtksdio_drv_pmctrl(bdev); + if (err < 0) + return err; + + /* Enable SCO over I2S/PCM */ + err = btmtksdio_sco_setting(hdev); + if (err < 0) { + bt_dev_err(hdev, "Failed to enable SCO setting (%d)", err); + return err; + } + break; case 0x7663: case 0x7668: @@ -958,6 +1111,32 @@ static int btmtksdio_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } +static bool btmtksdio_sdio_wakeup(struct hci_dev *hdev) +{ + struct btmtksdio_dev *bdev = hci_get_drvdata(hdev); + bool may_wakeup = device_may_wakeup(bdev->dev); + const struct btmtk_wakeon bt_awake = { + .mode = 0x1, + .gpo = 0, + .active_high = 0x1, + .enable_delay = cpu_to_le16(0xc80), + .wakeup_delay = cpu_to_le16(0x20), + }; + + if (may_wakeup && bdev->data->chipid == 0x7921) { + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, 0xfc27, sizeof(bt_awake), + &bt_awake, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) + may_wakeup = false; + + kfree_skb(skb); + } + + return may_wakeup; +} + static int btmtksdio_probe(struct sdio_func *func, const struct sdio_device_id *id) { @@ -997,6 +1176,7 @@ static int btmtksdio_probe(struct sdio_func *func, hdev->setup = btmtksdio_setup; hdev->shutdown = btmtksdio_shutdown; hdev->send = btmtksdio_send_frame; + hdev->wakeup = btmtksdio_sdio_wakeup; hdev->set_bdaddr = btmtk_set_bdaddr; SET_HCIDEV_DEV(hdev, &func->dev); @@ -1032,7 +1212,11 @@ static int btmtksdio_probe(struct sdio_func *func, */ pm_runtime_put_noidle(bdev->dev); - return 0; + err = device_init_wakeup(bdev->dev, true); + if (err) + bt_dev_err(hdev, "failed to initialize device wakeup"); + + return err; } static void btmtksdio_remove(struct sdio_func *func) @@ -1058,7 +1242,6 @@ static int btmtksdio_runtime_suspend(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); struct btmtksdio_dev *bdev; - u32 status; int err; bdev = sdio_get_drvdata(func); @@ -1070,18 +1253,9 @@ static int btmtksdio_runtime_suspend(struct device *dev) sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER); - sdio_claim_host(bdev->func); + err = btmtksdio_fw_pmctrl(bdev); - sdio_writel(bdev->func, C_FW_OWN_REQ_SET, MTK_REG_CHLPCR, &err); - if (err < 0) - goto out; - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - !(status & C_COM_DRV_OWN), 2000, 1000000); -out: - bt_dev_info(bdev->hdev, "status (%d) return ownership to device", err); - - sdio_release_host(bdev->func); + bt_dev_dbg(bdev->hdev, "status (%d) return ownership to device", err); return err; } @@ -1090,7 +1264,6 @@ static int btmtksdio_runtime_resume(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); struct btmtksdio_dev *bdev; - u32 status; int err; bdev = sdio_get_drvdata(func); @@ -1100,18 +1273,9 @@ static int btmtksdio_runtime_resume(struct device *dev) if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state)) return 0; - sdio_claim_host(bdev->func); + err = btmtksdio_drv_pmctrl(bdev); - sdio_writel(bdev->func, C_FW_OWN_REQ_CLR, MTK_REG_CHLPCR, &err); - if (err < 0) - goto out; - - err = readx_poll_timeout(btmtksdio_drv_own_query, bdev, status, - status & C_COM_DRV_OWN, 2000, 1000000); -out: - bt_dev_info(bdev->hdev, "status (%d) get ownership from device", err); - - sdio_release_host(bdev->func); + bt_dev_dbg(bdev->hdev, "status (%d) get ownership from device", err); return err; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index c2bdd1e6060e..c2030f7e25b4 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -149,6 +149,14 @@ static const struct id_table ic_id_table[] = { .cfg_name = "rtl_bt/rtl8761bu_config" }, /* 8822C with UART interface */ + { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0x8, HCI_UART), + .config_needed = true, + .has_rom_version = true, + .has_msft_ext = true, + .fw_name = "rtl_bt/rtl8822cs_fw.bin", + .cfg_name = "rtl_bt/rtl8822cs_config" }, + + /* 8822C with UART interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART), .config_needed = true, .has_rom_version = true, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c30d131da784..aefa0ee293f3 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -62,6 +62,7 @@ static struct usb_driver btusb_driver; #define BTUSB_QCA_WCN6855 0x1000000 #define BTUSB_INTEL_BROKEN_SHUTDOWN_LED 0x2000000 #define BTUSB_INTEL_BROKEN_INITIAL_NCMD 0x4000000 +#define BTUSB_INTEL_NO_WBS_SUPPORT 0x8000000 static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -385,9 +386,11 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED | + BTUSB_INTEL_NO_WBS_SUPPORT | BTUSB_INTEL_BROKEN_INITIAL_NCMD | BTUSB_INTEL_BROKEN_SHUTDOWN_LED }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL_COMBINED | + BTUSB_INTEL_NO_WBS_SUPPORT | BTUSB_INTEL_BROKEN_SHUTDOWN_LED }, { USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0aa7), .driver_info = BTUSB_INTEL_COMBINED | @@ -405,6 +408,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852AE Bluetooth devices */ + { USB_DEVICE(0x0bda, 0x2852), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0xc852), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x385a), .driver_info = BTUSB_REALTEK | @@ -2057,10 +2062,10 @@ static int btusb_setup_csr(struct hci_dev *hdev) * These controllers are really messed-up. * * 1. Their bulk RX endpoint will never report any data unless - * the device was suspended at least once (yes, really). + * the device was suspended at least once (yes, really). * 2. They will not wakeup when autosuspended and receiving data - * on their bulk RX endpoint from e.g. a keyboard or mouse - * (IOW remote-wakeup support is broken for the bulk endpoint). + * on their bulk RX endpoint from e.g. a keyboard or mouse + * (IOW remote-wakeup support is broken for the bulk endpoint). * * To fix 1. enable runtime-suspend, force-suspend the * HCI and then wake-it up by disabling runtime-suspend. @@ -3737,6 +3742,9 @@ static int btusb_probe(struct usb_interface *intf, hdev->send = btusb_send_frame_intel; hdev->cmd_timeout = btusb_intel_cmd_timeout; + if (id->driver_info & BTUSB_INTEL_NO_WBS_SUPPORT) + btintel_set_flag(hdev, INTEL_ROM_LEGACY_NO_WBS_SUPPORT); + if (id->driver_info & BTUSB_INTEL_BROKEN_INITIAL_NCMD) btintel_set_flag(hdev, INTEL_BROKEN_INITIAL_NCMD); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 34286ffe0568..fdf504b0d265 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -966,6 +966,11 @@ static void h5_btrtl_open(struct h5 *h5) pm_runtime_enable(&h5->hu->serdev->dev); } + /* The controller needs reset to startup */ + gpiod_set_value_cansleep(h5->enable_gpio, 0); + gpiod_set_value_cansleep(h5->device_wake_gpio, 0); + msleep(100); + /* The controller needs up to 500ms to wakeup */ gpiod_set_value_cansleep(h5->enable_gpio, 1); gpiod_set_value_cansleep(h5->device_wake_gpio, 1); diff --git a/drivers/bluetooth/hci_ll.c b/drivers/bluetooth/hci_ll.c index eb1e736efeeb..4eb420a9ed04 100644 --- a/drivers/bluetooth/hci_ll.c +++ b/drivers/bluetooth/hci_ll.c @@ -509,7 +509,7 @@ static int send_command_from_firmware(struct ll_device *lldev, return 0; } -/** +/* * download_firmware - * internal function which parses through the .bts firmware * script file intreprets SEND, DELAY actions only as of now diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 3b00d82d36cf..4cda890ce647 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -305,6 +305,8 @@ int hci_uart_register_device(struct hci_uart *hu, if (err) return err; + percpu_init_rwsem(&hu->proto_lock); + err = p->open(hu); if (err) goto err_open; @@ -327,7 +329,6 @@ int hci_uart_register_device(struct hci_uart *hu, INIT_WORK(&hu->init_ready, hci_uart_init_work); INIT_WORK(&hu->write_work, hci_uart_write_work); - percpu_init_rwsem(&hu->proto_lock); /* Only when vendor specific setup callback is provided, consider * the manufacturer information valid. This avoids filling in the diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 646ad385e490..ccac1c453080 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -358,7 +358,7 @@ static void cn_proc_mcast_ctl(struct cn_msg *msg, * other namespaces. */ if ((current_user_ns() != &init_user_ns) || - (task_active_pid_ns(current) != &init_pid_ns)) + !task_is_in_init_pid_ns(current)) return; /* Can only change if privileged. */ diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 7e0957eea094..869894b74741 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -90,10 +90,8 @@ struct counter_device *counter_alloc(size_t sizeof_priv) int err; ch = kzalloc(sizeof(*ch) + sizeof_priv, GFP_KERNEL); - if (!ch) { - err = -ENOMEM; - goto err_alloc_ch; - } + if (!ch) + return NULL; counter = &ch->counter; dev = &counter->dev; @@ -123,9 +121,8 @@ err_chrdev_add: err_ida_alloc: kfree(ch); -err_alloc_ch: - return ERR_PTR(err); + return NULL; } EXPORT_SYMBOL_GPL(counter_alloc); @@ -208,12 +205,12 @@ struct counter_device *devm_counter_alloc(struct device *dev, size_t sizeof_priv int err; counter = counter_alloc(sizeof_priv); - if (IS_ERR(counter)) - return counter; + if (!counter) + return NULL; err = devm_add_action_or_reset(dev, devm_counter_put, counter); if (err < 0) - return ERR_PTR(err); + return NULL; return counter; } diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index ae79c3300129..7de3f5b6e8d0 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -722,6 +722,13 @@ void __init efi_systab_report_header(const efi_table_hdr_t *systab_hdr, systab_hdr->revision >> 16, systab_hdr->revision & 0xffff, vendor); + + if (IS_ENABLED(CONFIG_X86_64) && + systab_hdr->revision > EFI_1_10_SYSTEM_TABLE_REVISION && + !strcmp(vendor, "Apple")) { + pr_info("Apple Mac detected, using EFI v1.10 runtime services only\n"); + efi.runtime_version = EFI_1_10_SYSTEM_TABLE_REVISION; + } } static __initdata char memory_type_name[][13] = { diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 2363fee9211c..9cc556013d08 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -119,9 +119,9 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (image->image_base != _text) efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n"); - if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) - efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", - EFI_KIMG_ALIGN >> 10); + if (!IS_ALIGNED((u64)_text, SEGMENT_ALIGN)) + efi_err("FIRMWARE BUG: kernel image not aligned on %dk boundary\n", + SEGMENT_ALIGN >> 10); kernel_size = _edata - _text; kernel_memsize = kernel_size + (_end - _edata); diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 838bbfed11d3..04b137eca8da 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -816,7 +816,7 @@ gpio_sim_make_bank_swnode(struct gpio_sim_bank *bank, properties[prop_idx++] = PROPERTY_ENTRY_U32("ngpios", bank->num_lines); - if (bank->label) + if (bank->label && (strlen(bank->label) > 0)) properties[prop_idx++] = PROPERTY_ENTRY_STRING("gpio-sim,label", bank->label); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b21bcdc97460..4c83f1db8a24 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1525,6 +1525,87 @@ static const u16 amdgpu_unsupported_pciidlist[] = { 0x99A0, 0x99A2, 0x99A4, + /* radeon secondary ids */ + 0x3171, + 0x3e70, + 0x4164, + 0x4165, + 0x4166, + 0x4168, + 0x4170, + 0x4171, + 0x4172, + 0x4173, + 0x496e, + 0x4a69, + 0x4a6a, + 0x4a6b, + 0x4a70, + 0x4a74, + 0x4b69, + 0x4b6b, + 0x4b6c, + 0x4c6e, + 0x4e64, + 0x4e65, + 0x4e66, + 0x4e67, + 0x4e68, + 0x4e69, + 0x4e6a, + 0x4e71, + 0x4f73, + 0x5569, + 0x556b, + 0x556d, + 0x556f, + 0x5571, + 0x5854, + 0x5874, + 0x5940, + 0x5941, + 0x5b72, + 0x5b73, + 0x5b74, + 0x5b75, + 0x5d44, + 0x5d45, + 0x5d6d, + 0x5d6f, + 0x5d72, + 0x5d77, + 0x5e6b, + 0x5e6d, + 0x7120, + 0x7124, + 0x7129, + 0x712e, + 0x712f, + 0x7162, + 0x7163, + 0x7166, + 0x7167, + 0x7172, + 0x7173, + 0x71a0, + 0x71a1, + 0x71a3, + 0x71a7, + 0x71bb, + 0x71e0, + 0x71e1, + 0x71e2, + 0x71e6, + 0x71e7, + 0x71f2, + 0x7269, + 0x726b, + 0x726e, + 0x72a0, + 0x72a8, + 0x72b1, + 0x72b3, + 0x793f, }; static const struct pci_device_id pciidlist[] = { diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c index ff5bb152ef49..e6ef36de0825 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c @@ -2033,10 +2033,10 @@ static void calculate_bandwidth( kfree(surface_type); free_tiling_mode: kfree(tiling_mode); -free_yclk: - kfree(yclk); free_sclk: kfree(sclk); +free_yclk: + kfree(yclk); } /******************************************************************************* diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c index ec19678a0702..e447c74be713 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c @@ -503,7 +503,6 @@ static void dcn_bw_calc_rq_dlg_ttu( //input[in_idx].dout.output_standard; /*todo: soc->sr_enter_plus_exit_time??*/ - dlg_sys_param->t_srx_delay_us = dc->dcn_ip->dcfclk_cstate_latency / v->dcf_clk_deep_sleep; dml1_rq_dlg_get_rq_params(dml, rq_param, &input->pipe.src); dml1_extract_rq_regs(dml, rq_regs, rq_param); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 01c8849b9db2..6f5528d34093 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1404,20 +1404,34 @@ static void program_timing_sync( status->timing_sync_info.master = false; } - /* remove any other unblanked pipes as they have already been synced */ - for (j = j + 1; j < group_size; j++) { - bool is_blanked; - if (pipe_set[j]->stream_res.opp->funcs->dpg_is_blanked) - is_blanked = - pipe_set[j]->stream_res.opp->funcs->dpg_is_blanked(pipe_set[j]->stream_res.opp); - else - is_blanked = - pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg); - if (!is_blanked) { - group_size--; - pipe_set[j] = pipe_set[group_size]; - j--; + /* remove any other pipes that are already been synced */ + if (dc->config.use_pipe_ctx_sync_logic) { + /* check pipe's syncd to decide which pipe to be removed */ + for (j = 1; j < group_size; j++) { + if (pipe_set[j]->pipe_idx_syncd == pipe_set[0]->pipe_idx_syncd) { + group_size--; + pipe_set[j] = pipe_set[group_size]; + j--; + } else + /* link slave pipe's syncd with master pipe */ + pipe_set[j]->pipe_idx_syncd = pipe_set[0]->pipe_idx_syncd; + } + } else { + for (j = j + 1; j < group_size; j++) { + bool is_blanked; + + if (pipe_set[j]->stream_res.opp->funcs->dpg_is_blanked) + is_blanked = + pipe_set[j]->stream_res.opp->funcs->dpg_is_blanked(pipe_set[j]->stream_res.opp); + else + is_blanked = + pipe_set[j]->stream_res.tg->funcs->is_blanked(pipe_set[j]->stream_res.tg); + if (!is_blanked) { + group_size--; + pipe_set[j] = pipe_set[group_size]; + j--; + } } } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 05e216524370..4c3ab2575e4b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -202,7 +202,7 @@ void dp_wait_for_training_aux_rd_interval( uint32_t wait_in_micro_secs) { #if defined(CONFIG_DRM_AMD_DC_DCN) - if (wait_in_micro_secs > 16000) + if (wait_in_micro_secs > 1000) msleep(wait_in_micro_secs/1000); else udelay(wait_in_micro_secs); @@ -6935,7 +6935,7 @@ bool dpcd_write_128b_132b_sst_payload_allocation_table( } } retries++; - udelay(5000); + msleep(5); } if (!result && retries == max_retries) { @@ -6987,7 +6987,7 @@ bool dpcd_poll_for_allocation_change_trigger(struct dc_link *link) break; } - udelay(5000); + msleep(5); } if (result == ACT_FAILED) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index d4ff6cc6b8d9..b3912ff9dc91 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -3217,6 +3217,60 @@ struct hpo_dp_link_encoder *resource_get_hpo_dp_link_enc_for_det_lt( } #endif +void reset_syncd_pipes_from_disabled_pipes(struct dc *dc, + struct dc_state *context) +{ + int i, j; + struct pipe_ctx *pipe_ctx_old, *pipe_ctx, *pipe_ctx_syncd; + + /* If pipe backend is reset, need to reset pipe syncd status */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe_ctx_old = &dc->current_state->res_ctx.pipe_ctx[i]; + pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (!pipe_ctx_old->stream) + continue; + + if (pipe_ctx_old->top_pipe || pipe_ctx_old->prev_odm_pipe) + continue; + + if (!pipe_ctx->stream || + pipe_need_reprogram(pipe_ctx_old, pipe_ctx)) { + + /* Reset all the syncd pipes from the disabled pipe */ + for (j = 0; j < dc->res_pool->pipe_count; j++) { + pipe_ctx_syncd = &context->res_ctx.pipe_ctx[j]; + if ((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx_syncd) == pipe_ctx_old->pipe_idx) || + !IS_PIPE_SYNCD_VALID(pipe_ctx_syncd)) + SET_PIPE_SYNCD_TO_PIPE(pipe_ctx_syncd, j); + } + } + } +} + +void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, + struct dc_state *context, + uint8_t disabled_master_pipe_idx) +{ + int i; + struct pipe_ctx *pipe_ctx, *pipe_ctx_check; + + pipe_ctx = &context->res_ctx.pipe_ctx[disabled_master_pipe_idx]; + if ((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx) != disabled_master_pipe_idx) || + !IS_PIPE_SYNCD_VALID(pipe_ctx)) + SET_PIPE_SYNCD_TO_PIPE(pipe_ctx, disabled_master_pipe_idx); + + /* for the pipe disabled, check if any slave pipe exists and assert */ + for (i = 0; i < dc->res_pool->pipe_count; i++) { + pipe_ctx_check = &context->res_ctx.pipe_ctx[i]; + + if ((GET_PIPE_SYNCD_FROM_PIPE(pipe_ctx_check) == disabled_master_pipe_idx) && + IS_PIPE_SYNCD_VALID(pipe_ctx_check) && (i != disabled_master_pipe_idx)) + DC_ERR("DC: Failure: pipe_idx[%d] syncd with disabled master pipe_idx[%d]\n", + i, disabled_master_pipe_idx); + } +} + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter) { /* TODO - get transmitter to phy idx mapping from DMUB */ diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index da2c78ce14d6..288e7b01f561 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -344,6 +344,7 @@ struct dc_config { uint8_t vblank_alignment_max_frame_time_diff; bool is_asymmetric_memory; bool is_single_rank_dimm; + bool use_pipe_ctx_sync_logic; }; enum visual_confirm { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 78192ecba102..f3ff141b706a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1566,6 +1566,10 @@ static enum dc_status apply_single_controller_ctx_to_hw( &pipe_ctx->stream->audio_info); } + /* make sure no pipes syncd to the pipe being enabled */ + if (!pipe_ctx->stream->apply_seamless_boot_optimization && dc->config.use_pipe_ctx_sync_logic) + check_syncd_pipes_for_disabled_master_pipe(dc, context, pipe_ctx->pipe_idx); + #if defined(CONFIG_DRM_AMD_DC_DCN) /* DCN3.1 FPGA Workaround * Need to enable HPO DP Stream Encoder before setting OTG master enable. @@ -1604,7 +1608,7 @@ static enum dc_status apply_single_controller_ctx_to_hw( pipe_ctx->stream_res.stream_enc, pipe_ctx->stream_res.tg->inst); - if (dc_is_dp_signal(pipe_ctx->stream->signal) && + if (dc_is_embedded_signal(pipe_ctx->stream->signal) && pipe_ctx->stream_res.stream_enc->funcs->reset_fifo) pipe_ctx->stream_res.stream_enc->funcs->reset_fifo( pipe_ctx->stream_res.stream_enc); @@ -2297,6 +2301,10 @@ enum dc_status dce110_apply_ctx_to_hw( enum dc_status status; int i; + /* reset syncd pipes from disabled pipes */ + if (dc->config.use_pipe_ctx_sync_logic) + reset_syncd_pipes_from_disabled_pipes(dc, context); + /* Reset old context */ /* look up the targets that have been removed since last commit */ hws->funcs.reset_hw_ctx_wrap(dc, context); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 602ec9a08549..8ca26383b568 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -1878,7 +1878,6 @@ noinline bool dcn30_internal_validate_bw( dc->res_pool->funcs->update_soc_for_wm_a(dc, context); pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); - DC_FP_START(); if (!pipe_cnt) { out = true; goto validate_out; @@ -2104,7 +2103,6 @@ validate_fail: out = false; validate_out: - DC_FP_END(); return out; } @@ -2306,7 +2304,9 @@ bool dcn30_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); if (pipe_cnt == 0) goto validate_out; diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c index c1c6e602b06c..5d9637b07429 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c @@ -686,7 +686,7 @@ static const struct dc_debug_options debug_defaults_drv = { .disable_clock_gate = true, .disable_pplib_clock_request = true, .disable_pplib_wm_range = true, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, @@ -1380,6 +1380,17 @@ static void set_wm_ranges( pp_smu->nv_funcs.set_wm_ranges(&pp_smu->nv_funcs.pp_smu, &ranges); } +static void dcn301_calculate_wm_and_dlg( + struct dc *dc, struct dc_state *context, + display_e2e_pipe_params_st *pipes, + int pipe_cnt, + int vlevel) +{ + DC_FP_START(); + dcn301_calculate_wm_and_dlg_fp(dc, context, pipes, pipe_cnt, vlevel); + DC_FP_END(); +} + static struct resource_funcs dcn301_res_pool_funcs = { .destroy = dcn301_destroy_resource_pool, .link_enc_create = dcn301_link_encoder_create, diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 42ed47e8133d..8d64187478e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2260,6 +2260,9 @@ static bool dcn31_resource_construct( dc->caps.color.mpc.ogam_rom_caps.hlg = 0; dc->caps.color.mpc.ocsc = 1; + /* Use pipe context based otg sync logic */ + dc->config.use_pipe_ctx_sync_logic = true; + /* read VBIOS LTTPR caps */ { if (ctx->dc_bios->funcs->get_lttpr_caps) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c index 246071c72f6b..548cdef8a8ad 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c @@ -1576,8 +1576,6 @@ void dml20_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, dlg_sys_param.total_flip_bytes = get_total_immediate_flip_bytes(mode_lib, e2e_pipe_param, num_pipes); - dlg_sys_param.t_srx_delay_us = mode_lib->ip.dcfclk_cstate_latency - / dlg_sys_param.deepsleep_dcfclk_mhz; // TODO: Deprecated print__dlg_sys_params_st(mode_lib, &dlg_sys_param); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 015e7f2c0b16..0fc9f3e3ffae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -1577,8 +1577,6 @@ void dml20v2_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, dlg_sys_param.total_flip_bytes = get_total_immediate_flip_bytes(mode_lib, e2e_pipe_param, num_pipes); - dlg_sys_param.t_srx_delay_us = mode_lib->ip.dcfclk_cstate_latency - / dlg_sys_param.deepsleep_dcfclk_mhz; // TODO: Deprecated print__dlg_sys_params_st(mode_lib, &dlg_sys_param); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index 8bc27de4c104..618f4b682ab1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -1688,8 +1688,6 @@ void dml21_rq_dlg_get_dlg_reg( mode_lib, e2e_pipe_param, num_pipes); - dlg_sys_param.t_srx_delay_us = mode_lib->ip.dcfclk_cstate_latency - / dlg_sys_param.deepsleep_dcfclk_mhz; // TODO: Deprecated print__dlg_sys_params_st(mode_lib, &dlg_sys_param); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c index aef854270054..747167083dea 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_rq_dlg_calc_30.c @@ -1858,8 +1858,6 @@ void dml30_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, dlg_sys_param.total_flip_bytes = get_total_immediate_flip_bytes(mode_lib, e2e_pipe_param, num_pipes); - dlg_sys_param.t_srx_delay_us = mode_lib->ip.dcfclk_cstate_latency - / dlg_sys_param.deepsleep_dcfclk_mhz; // TODO: Deprecated print__dlg_sys_params_st(mode_lib, &dlg_sys_param); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c index 94c32832a0e7..0a7a33864973 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.c @@ -327,7 +327,7 @@ void dcn301_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info) dcn3_01_soc.sr_exit_time_us = bb_info.dram_sr_exit_latency_100ns * 10; } -void dcn301_calculate_wm_and_dlg(struct dc *dc, +void dcn301_calculate_wm_and_dlg_fp(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h index fc7065d17842..774b0fdfc80b 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn301/dcn301_fpu.h @@ -34,7 +34,7 @@ void dcn301_fpu_set_wm_ranges(int i, void dcn301_fpu_init_soc_bounding_box(struct bp_soc_bb_info bb_info); -void dcn301_calculate_wm_and_dlg(struct dc *dc, +void dcn301_calculate_wm_and_dlg_fp(struct dc *dc, struct dc_state *context, display_e2e_pipe_params_st *pipes, int pipe_cnt, diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index d46a2733024c..8f9f1d607f7c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -546,7 +546,6 @@ struct _vcs_dpi_display_dlg_sys_params_st { double t_sr_wm_us; double t_extra_us; double mem_trip_us; - double t_srx_delay_us; double deepsleep_dcfclk_mhz; double total_flip_bw; unsigned int total_flip_bytes; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c index 71ea503cb32f..412e75eb4704 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_rq_dlg_helpers.c @@ -142,9 +142,6 @@ void print__dlg_sys_params_st(struct display_mode_lib *mode_lib, const struct _v dml_print("DML_RQ_DLG_CALC: t_sr_wm_us = %3.2f\n", dlg_sys_param->t_sr_wm_us); dml_print("DML_RQ_DLG_CALC: t_extra_us = %3.2f\n", dlg_sys_param->t_extra_us); dml_print( - "DML_RQ_DLG_CALC: t_srx_delay_us = %3.2f\n", - dlg_sys_param->t_srx_delay_us); - dml_print( "DML_RQ_DLG_CALC: deepsleep_dcfclk_mhz = %3.2f\n", dlg_sys_param->deepsleep_dcfclk_mhz); dml_print( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c index 59dc2c5b58dd..3df559c591f8 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c @@ -1331,10 +1331,6 @@ void dml1_rq_dlg_get_dlg_params( if (dual_plane) DTRACE("DLG: %s: swath_height_c = %d", __func__, swath_height_c); - DTRACE( - "DLG: %s: t_srx_delay_us = %3.2f", - __func__, - (double) dlg_sys_param->t_srx_delay_us); DTRACE("DLG: %s: line_time_in_us = %3.2f", __func__, (double) line_time_in_us); DTRACE("DLG: %s: vupdate_offset = %d", __func__, vupdate_offset); DTRACE("DLG: %s: vupdate_width = %d", __func__, vupdate_width); diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 890280026e69..943240e2809e 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -382,6 +382,7 @@ struct pipe_ctx { struct pll_settings pll_settings; uint8_t pipe_idx; + uint8_t pipe_idx_syncd; struct pipe_ctx *top_pipe; struct pipe_ctx *bottom_pipe; diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 4249bf306e09..dbfe6690ded8 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -34,6 +34,10 @@ #define MEMORY_TYPE_HBM 2 +#define IS_PIPE_SYNCD_VALID(pipe) ((((pipe)->pipe_idx_syncd) & 0x80)?1:0) +#define GET_PIPE_SYNCD_FROM_PIPE(pipe) ((pipe)->pipe_idx_syncd & 0x7F) +#define SET_PIPE_SYNCD_TO_PIPE(pipe, pipe_syncd) ((pipe)->pipe_idx_syncd = (0x80 | pipe_syncd)) + enum dce_version resource_parse_asic_id( struct hw_asic_id asic_id); @@ -208,6 +212,13 @@ struct hpo_dp_link_encoder *resource_get_hpo_dp_link_enc_for_det_lt( const struct dc_link *link); #endif +void reset_syncd_pipes_from_disabled_pipes(struct dc *dc, + struct dc_state *context); + +void check_syncd_pipes_for_disabled_master_pipe(struct dc *dc, + struct dc_state *context, + uint8_t disabled_master_pipe_idx); + uint8_t resource_transmitter_to_phy_idx(const struct dc *dc, enum transmitter transmitter); #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_RESOURCE_H_ */ diff --git a/drivers/gpu/drm/ast/ast_tables.h b/drivers/gpu/drm/ast/ast_tables.h index d9eb353a4bf0..dbe1cc620f6e 100644 --- a/drivers/gpu/drm/ast/ast_tables.h +++ b/drivers/gpu/drm/ast/ast_tables.h @@ -282,8 +282,6 @@ static const struct ast_vbios_enhtable res_1360x768[] = { }; static const struct ast_vbios_enhtable res_1600x900[] = { - {1800, 1600, 24, 80, 1000, 900, 1, 3, VCLK108, /* 60Hz */ - (SyncPP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo), 60, 3, 0x3A }, {1760, 1600, 48, 32, 926, 900, 3, 5, VCLK97_75, /* 60Hz CVT RB */ (SyncNP | Charx8Dot | LineCompareOff | WideScreenMode | NewModeInfo | AST2500PreCatchCRT), 60, 1, 0x3A }, diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 21174efd91be..88cd992df356 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1327,8 +1327,10 @@ int drm_atomic_check_only(struct drm_atomic_state *state) drm_dbg_atomic(dev, "checking %p\n", state); - for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) - requested_crtc |= drm_crtc_mask(crtc); + for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { + if (new_crtc_state->enable) + requested_crtc |= drm_crtc_mask(crtc); + } for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { ret = drm_atomic_plane_check(old_plane_state, new_plane_state); @@ -1377,8 +1379,10 @@ int drm_atomic_check_only(struct drm_atomic_state *state) } } - for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) - affected_crtc |= drm_crtc_mask(crtc); + for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { + if (new_crtc_state->enable) + affected_crtc |= drm_crtc_mask(crtc); + } /* * For commits that allow modesets drivers can add other CRTCs to the diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 042bb80383c9..b910978d3e48 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -115,6 +115,12 @@ static const struct drm_dmi_panel_orientation_data lcd1280x1920_rightside_up = { .orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP, }; +static const struct drm_dmi_panel_orientation_data lcd1600x2560_leftside_up = { + .width = 1600, + .height = 2560, + .orientation = DRM_MODE_PANEL_ORIENTATION_LEFT_UP, +}; + static const struct dmi_system_id orientation_data[] = { { /* Acer One 10 (S1003) */ .matches = { @@ -275,6 +281,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Default string"), }, .driver_data = (void *)&onegx1_pro, + }, { /* OneXPlayer */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ONE-NETBOOK TECHNOLOGY CO., LTD."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"), + }, + .driver_data = (void *)&lcd1600x2560_leftside_up, }, { /* Samsung GalaxyBook 10.6 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), diff --git a/drivers/gpu/drm/drm_privacy_screen_x86.c b/drivers/gpu/drm/drm_privacy_screen_x86.c index a2cafb294ca6..e7aa74ad0b24 100644 --- a/drivers/gpu/drm/drm_privacy_screen_x86.c +++ b/drivers/gpu/drm/drm_privacy_screen_x86.c @@ -33,6 +33,9 @@ static bool __init detect_thinkpad_privacy_screen(void) unsigned long long output; acpi_status status; + if (acpi_disabled) + return false; + /* Get embedded-controller handle */ status = acpi_get_devices("PNP0C09", acpi_set_handle, NULL, &ec_handle); if (ACPI_FAILURE(status) || !ec_handle) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index b03c20c14ca1..a17313282e8b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -469,8 +469,8 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, return -EINVAL; } - if (args->stream_size > SZ_64K || args->nr_relocs > SZ_64K || - args->nr_bos > SZ_64K || args->nr_pmrs > 128) { + if (args->stream_size > SZ_128K || args->nr_relocs > SZ_128K || + args->nr_bos > SZ_128K || args->nr_pmrs > 128) { DRM_ERROR("submit arguments out of size limits\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 4b4829eb16c2..0dd107dcecc2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -311,6 +311,7 @@ struct drm_i915_gem_object { #define I915_BO_READONLY BIT(6) #define I915_TILING_QUIRK_BIT 7 /* unknown swizzling; do not release! */ #define I915_BO_PROTECTED BIT(8) +#define I915_BO_WAS_BOUND_BIT 9 /** * @mem_flags - Mutable placement-related flags * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 9f429ed6e78a..a50f884973bc 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -10,6 +10,8 @@ #include "i915_gem_lmem.h" #include "i915_gem_mman.h" +#include "gt/intel_gt.h" + void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, struct sg_table *pages, unsigned int sg_page_sizes) @@ -221,6 +223,14 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) __i915_gem_object_reset_page_iter(obj); obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0; + if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) { + struct drm_i915_private *i915 = to_i915(obj->base.dev); + intel_wakeref_t wakeref; + + with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref) + intel_gt_invalidate_tlbs(to_gt(i915)); + } + return pages; } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f98f0fb21efb..35d0fcd3a86c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -29,6 +29,8 @@ void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) { spin_lock_init(>->irq_lock); + mutex_init(>->tlb_invalidate_lock); + INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -912,3 +914,109 @@ void intel_gt_info_print(const struct intel_gt_info *info, intel_sseu_dump(&info->sseu, p); } + +struct reg_and_bit { + i915_reg_t reg; + u32 bit; +}; + +static struct reg_and_bit +get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, + const i915_reg_t *regs, const unsigned int num) +{ + const unsigned int class = engine->class; + struct reg_and_bit rb = { }; + + if (drm_WARN_ON_ONCE(&engine->i915->drm, + class >= num || !regs[class].reg)) + return rb; + + rb.reg = regs[class]; + if (gen8 && class == VIDEO_DECODE_CLASS) + rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */ + else + rb.bit = engine->instance; + + rb.bit = BIT(rb.bit); + + return rb; +} + +void intel_gt_invalidate_tlbs(struct intel_gt *gt) +{ + static const i915_reg_t gen8_regs[] = { + [RENDER_CLASS] = GEN8_RTCR, + [VIDEO_DECODE_CLASS] = GEN8_M1TCR, /* , GEN8_M2TCR */ + [VIDEO_ENHANCEMENT_CLASS] = GEN8_VTCR, + [COPY_ENGINE_CLASS] = GEN8_BTCR, + }; + static const i915_reg_t gen12_regs[] = { + [RENDER_CLASS] = GEN12_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS] = GEN12_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS] = GEN12_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR, + }; + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct intel_engine_cs *engine; + enum intel_engine_id id; + const i915_reg_t *regs; + unsigned int num = 0; + + if (I915_SELFTEST_ONLY(gt->awake == -ENODEV)) + return; + + if (GRAPHICS_VER(i915) == 12) { + regs = gen12_regs; + num = ARRAY_SIZE(gen12_regs); + } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { + regs = gen8_regs; + num = ARRAY_SIZE(gen8_regs); + } else if (GRAPHICS_VER(i915) < 8) { + return; + } + + if (drm_WARN_ONCE(&i915->drm, !num, + "Platform does not implement TLB invalidation!")) + return; + + GEM_TRACE("\n"); + + assert_rpm_wakelock_held(&i915->runtime_pm); + + mutex_lock(>->tlb_invalidate_lock); + intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); + + for_each_engine(engine, gt, id) { + /* + * HW architecture suggest typical invalidation time at 40us, + * with pessimistic cases up to 100us and a recommendation to + * cap at 1ms. We go a bit higher just in case. + */ + const unsigned int timeout_us = 100; + const unsigned int timeout_ms = 4; + struct reg_and_bit rb; + + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); + if (!i915_mmio_reg_offset(rb.reg)) + continue; + + intel_uncore_write_fw(uncore, rb.reg, rb.bit); + if (__intel_wait_for_register_fw(uncore, + rb.reg, rb.bit, 0, + timeout_us, timeout_ms, + NULL)) + drm_err_ratelimited(>->i915->drm, + "%s TLB invalidation did not complete in %ums!\n", + engine->name, timeout_ms); + } + + /* + * Use delayed put since a) we mostly expect a flurry of TLB + * invalidations so it is good to avoid paying the forcewake cost and + * b) it works around a bug in Icelake which cannot cope with too rapid + * transitions. + */ + intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL); + mutex_unlock(>->tlb_invalidate_lock); +} diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 3ace129eb2af..a913fb6ffec3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -91,4 +91,6 @@ void intel_gt_info_print(const struct intel_gt_info *info, void intel_gt_watchdog_work(struct work_struct *work); +void intel_gt_invalidate_tlbs(struct intel_gt *gt); + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 14216cc471b1..f20687796490 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -73,6 +73,8 @@ struct intel_gt { struct intel_uc uc; + struct mutex tlb_invalidate_lock; + struct i915_wa_list wa_list; struct intel_gt_timelines { diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 971d601fe751..c32420cb8ed5 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2721,6 +2721,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING (1 << 28) #define GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT (1 << 24) +#define GEN8_RTCR _MMIO(0x4260) +#define GEN8_M1TCR _MMIO(0x4264) +#define GEN8_M2TCR _MMIO(0x4268) +#define GEN8_BTCR _MMIO(0x426c) +#define GEN8_VTCR _MMIO(0x4270) + #if 0 #define PRB0_TAIL _MMIO(0x2030) #define PRB0_HEAD _MMIO(0x2034) @@ -2819,6 +2825,11 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define FAULT_VA_HIGH_BITS (0xf << 0) #define FAULT_GTT_SEL (1 << 4) +#define GEN12_GFX_TLB_INV_CR _MMIO(0xced8) +#define GEN12_VD_TLB_INV_CR _MMIO(0xcedc) +#define GEN12_VE_TLB_INV_CR _MMIO(0xcee0) +#define GEN12_BLT_TLB_INV_CR _MMIO(0xcee4) + #define GEN12_AUX_ERR_DBG _MMIO(0x43f4) #define FPGA_DBG _MMIO(0x42300) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 29a858c53bdd..c0d6d5526abe 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -457,6 +457,9 @@ int i915_vma_bind(struct i915_vma *vma, vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); } + if (vma->obj) + set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags); + atomic_or(bind_flags, &vma->flags); return 0; } diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index fc25ebf1a593..778da3179b3c 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -724,7 +724,8 @@ void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore, } static void __intel_uncore_forcewake_put(struct intel_uncore *uncore, - enum forcewake_domains fw_domains) + enum forcewake_domains fw_domains, + bool delayed) { struct intel_uncore_forcewake_domain *domain; unsigned int tmp; @@ -739,7 +740,11 @@ static void __intel_uncore_forcewake_put(struct intel_uncore *uncore, continue; } - fw_domains_put(uncore, domain->mask); + if (delayed && + !(domain->uncore->fw_domains_timer & domain->mask)) + fw_domain_arm_timer(domain); + else + fw_domains_put(uncore, domain->mask); } } @@ -760,7 +765,20 @@ void intel_uncore_forcewake_put(struct intel_uncore *uncore, return; spin_lock_irqsave(&uncore->lock, irqflags); - __intel_uncore_forcewake_put(uncore, fw_domains); + __intel_uncore_forcewake_put(uncore, fw_domains, false); + spin_unlock_irqrestore(&uncore->lock, irqflags); +} + +void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore, + enum forcewake_domains fw_domains) +{ + unsigned long irqflags; + + if (!uncore->fw_get_funcs) + return; + + spin_lock_irqsave(&uncore->lock, irqflags); + __intel_uncore_forcewake_put(uncore, fw_domains, true); spin_unlock_irqrestore(&uncore->lock, irqflags); } @@ -802,7 +820,7 @@ void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore, if (!uncore->fw_get_funcs) return; - __intel_uncore_forcewake_put(uncore, fw_domains); + __intel_uncore_forcewake_put(uncore, fw_domains, false); } void assert_forcewakes_inactive(struct intel_uncore *uncore) diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 210fe2a71612..2a15b2b2e2fc 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -246,6 +246,8 @@ void intel_uncore_forcewake_get(struct intel_uncore *uncore, enum forcewake_domains domains); void intel_uncore_forcewake_put(struct intel_uncore *uncore, enum forcewake_domains domains); +void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore, + enum forcewake_domains domains); void intel_uncore_forcewake_flush(struct intel_uncore *uncore, enum forcewake_domains fw_domains); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 51b83776951b..17cfad6424db 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1560,6 +1560,8 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) for (i = 0; i < gpu->nr_rings; i++) a6xx_gpu->shadow[i] = 0; + gpu->suspend_count++; + return 0; } diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 93005839b5da..fb261930ad1c 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -608,9 +608,27 @@ static int adreno_resume(struct device *dev) return gpu->funcs->pm_resume(gpu); } +static int active_submits(struct msm_gpu *gpu) +{ + int active_submits; + mutex_lock(&gpu->active_lock); + active_submits = gpu->active_submits; + mutex_unlock(&gpu->active_lock); + return active_submits; +} + static int adreno_suspend(struct device *dev) { struct msm_gpu *gpu = dev_to_gpu(dev); + int remaining; + + remaining = wait_event_timeout(gpu->retire_event, + active_submits(gpu) == 0, + msecs_to_jiffies(1000)); + if (remaining == 0) { + dev_err(dev, "Timeout waiting for GPU to suspend\n"); + return -EBUSY; + } return gpu->funcs->pm_suspend(gpu); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index a98e964c3b6f..355894a3b48c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -26,9 +26,16 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, struct dpu_hw_pcc_cfg *cfg) { - u32 base = ctx->cap->sblk->pcc.base; + u32 base; - if (!ctx || !base) { + if (!ctx) { + DRM_ERROR("invalid ctx %pK\n", ctx); + return; + } + + base = ctx->cap->sblk->pcc.base; + + if (!base) { DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index 052548883d27..0fe02529b5e7 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -40,7 +40,12 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi) of_node_put(phy_node); - if (!phy_pdev || !msm_dsi->phy) { + if (!phy_pdev) { + DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); + return -EPROBE_DEFER; + } + if (!msm_dsi->phy) { + put_device(&phy_pdev->dev); DRM_DEV_ERROR(&pdev->dev, "%s: phy driver is not ready\n", __func__); return -EPROBE_DEFER; } diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index c2ed177717c7..2027b38617ab 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -808,12 +808,14 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, struct msm_dsi_phy_clk_request *clk_req, struct msm_dsi_phy_shared_timings *shared_timings) { - struct device *dev = &phy->pdev->dev; + struct device *dev; int ret; if (!phy || !phy->cfg->ops.enable) return -EINVAL; + dev = &phy->pdev->dev; + ret = dsi_phy_enable_resource(phy); if (ret) { DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 3acdeae25caf..719720709e9e 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -97,10 +97,15 @@ static int msm_hdmi_get_phy(struct hdmi *hdmi) of_node_put(phy_node); - if (!phy_pdev || !hdmi->phy) { + if (!phy_pdev) { DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); return -EPROBE_DEFER; } + if (!hdmi->phy) { + DRM_DEV_ERROR(&pdev->dev, "phy driver is not ready\n"); + put_device(&phy_pdev->dev); + return -EPROBE_DEFER; + } hdmi->phy_dev = get_device(&phy_pdev->dev); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ad35a5d94053..555666e3f960 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -461,7 +461,7 @@ static int msm_init_vram(struct drm_device *dev) of_node_put(node); if (ret) return ret; - size = r.end - r.start; + size = r.end - r.start + 1; DRM_INFO("using VRAM carveout: %lx@%pa\n", size, &r.start); /* if we have no IOMMU, then we need to use carveout allocator. @@ -510,7 +510,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) struct msm_drm_private *priv = dev_get_drvdata(dev); struct drm_device *ddev; struct msm_kms *kms; - struct msm_mdss *mdss; int ret, i; ddev = drm_dev_alloc(drv, dev); @@ -521,8 +520,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) ddev->dev_private = priv; priv->dev = ddev; - mdss = priv->mdss; - priv->wq = alloc_ordered_workqueue("msm", 0); priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 0f78c2615272..2c1049c0ea14 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -703,6 +703,8 @@ static void retire_submits(struct msm_gpu *gpu) } } } + + wake_up_all(&gpu->retire_event); } static void retire_worker(struct kthread_work *work) @@ -848,6 +850,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, INIT_LIST_HEAD(&gpu->active_list); mutex_init(&gpu->active_lock); mutex_init(&gpu->lock); + init_waitqueue_head(&gpu->retire_event); kthread_init_work(&gpu->retire_work, retire_worker); kthread_init_work(&gpu->recover_work, recover_worker); kthread_init_work(&gpu->fault_work, fault_worker); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 445c6bfd4b6b..92aa1e9196c6 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -230,6 +230,9 @@ struct msm_gpu { /* work for handling GPU recovery: */ struct kthread_work recover_work; + /** retire_event: notified when submits are retired: */ + wait_queue_head_t retire_event; + /* work for handling active-list retiring: */ struct kthread_work retire_work; diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 62405e980925..9bf319be11f6 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -133,6 +133,18 @@ void msm_devfreq_init(struct msm_gpu *gpu) CLOCK_MONOTONIC, HRTIMER_MODE_REL); } +static void cancel_idle_work(struct msm_gpu_devfreq *df) +{ + hrtimer_cancel(&df->idle_work.timer); + kthread_cancel_work_sync(&df->idle_work.work); +} + +static void cancel_boost_work(struct msm_gpu_devfreq *df) +{ + hrtimer_cancel(&df->boost_work.timer); + kthread_cancel_work_sync(&df->boost_work.work); +} + void msm_devfreq_cleanup(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; @@ -152,7 +164,12 @@ void msm_devfreq_resume(struct msm_gpu *gpu) void msm_devfreq_suspend(struct msm_gpu *gpu) { - devfreq_suspend_device(gpu->devfreq.devfreq); + struct msm_gpu_devfreq *df = &gpu->devfreq; + + devfreq_suspend_device(df->devfreq); + + cancel_idle_work(df); + cancel_boost_work(df); } static void msm_devfreq_boost_work(struct kthread_work *work) @@ -196,7 +213,7 @@ void msm_devfreq_active(struct msm_gpu *gpu) /* * Cancel any pending transition to idle frequency: */ - hrtimer_cancel(&df->idle_work.timer); + cancel_idle_work(df); idle_time = ktime_to_ms(ktime_sub(ktime_get(), df->idle_time)); diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c index a229da58962a..9300d3354c51 100644 --- a/drivers/gpu/drm/vc4/vc4_dsi.c +++ b/drivers/gpu/drm/vc4/vc4_dsi.c @@ -1262,7 +1262,6 @@ static int vc4_dsi_host_attach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { struct vc4_dsi *dsi = host_to_dsi(host); - int ret; dsi->lanes = device->lanes; dsi->channel = device->channel; @@ -1297,18 +1296,15 @@ static int vc4_dsi_host_attach(struct mipi_dsi_host *host, return 0; } - ret = component_add(&dsi->pdev->dev, &vc4_dsi_ops); - if (ret) { - mipi_dsi_host_unregister(&dsi->dsi_host); - return ret; - } - - return 0; + return component_add(&dsi->pdev->dev, &vc4_dsi_ops); } static int vc4_dsi_host_detach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { + struct vc4_dsi *dsi = host_to_dsi(host); + + component_del(&dsi->pdev->dev, &vc4_dsi_ops); return 0; } @@ -1686,9 +1682,7 @@ static int vc4_dsi_dev_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; struct vc4_dsi *dsi = dev_get_drvdata(dev); - component_del(&pdev->dev, &vc4_dsi_ops); mipi_dsi_host_unregister(&dsi->dsi_host); - return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index d6b66636a19b..ea3ecdda561d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1140,15 +1140,14 @@ extern int vmw_execbuf_fence_commands(struct drm_file *file_priv, struct vmw_private *dev_priv, struct vmw_fence_obj **p_fence, uint32_t *p_handle); -extern void vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv, +extern int vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv, struct vmw_fpriv *vmw_fp, int ret, struct drm_vmw_fence_rep __user *user_fence_rep, struct vmw_fence_obj *fence, uint32_t fence_handle, - int32_t out_fence_fd, - struct sync_file *sync_file); + int32_t out_fence_fd); bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd); /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 44ca23b0ea4e..dd2ff441068e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3879,17 +3879,17 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv, * Also if copying fails, user-space will be unable to signal the fence object * so we wait for it immediately, and then unreference the user-space reference. */ -void +int vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv, struct vmw_fpriv *vmw_fp, int ret, struct drm_vmw_fence_rep __user *user_fence_rep, struct vmw_fence_obj *fence, uint32_t fence_handle, - int32_t out_fence_fd, struct sync_file *sync_file) + int32_t out_fence_fd) { struct drm_vmw_fence_rep fence_rep; if (user_fence_rep == NULL) - return; + return 0; memset(&fence_rep, 0, sizeof(fence_rep)); @@ -3917,19 +3917,13 @@ vmw_execbuf_copy_fence_user(struct vmw_private *dev_priv, * handle. */ if (unlikely(ret != 0) && (fence_rep.error == 0)) { - if (sync_file) - fput(sync_file->file); - - if (fence_rep.fd != -1) { - put_unused_fd(fence_rep.fd); - fence_rep.fd = -1; - } - ttm_ref_object_base_unref(vmw_fp->tfile, fence_handle); VMW_DEBUG_USER("Fence copy error. Syncing.\n"); (void) vmw_fence_obj_wait(fence, false, false, VMW_FENCE_WAIT_TIMEOUT); } + + return ret ? -EFAULT : 0; } /** @@ -4266,16 +4260,23 @@ int vmw_execbuf_process(struct drm_file *file_priv, (void) vmw_fence_obj_wait(fence, false, false, VMW_FENCE_WAIT_TIMEOUT); + } + } + + ret = vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv), ret, + user_fence_rep, fence, handle, out_fence_fd); + + if (sync_file) { + if (ret) { + /* usercopy of fence failed, put the file object */ + fput(sync_file->file); + put_unused_fd(out_fence_fd); } else { /* Link the fence with the FD created earlier */ fd_install(out_fence_fd, sync_file->file); } } - vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv), ret, - user_fence_rep, fence, handle, out_fence_fd, - sync_file); - /* Don't unreference when handing fence out */ if (unlikely(out_fence != NULL)) { *out_fence = fence; @@ -4293,7 +4294,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, */ vmw_validation_unref_lists(&val_ctx); - return 0; + return ret; out_unlock_binding: mutex_unlock(&dev_priv->binding_mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index c60d395f9e2e..5001b87aebe8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -1128,7 +1128,7 @@ int vmw_fence_event_ioctl(struct drm_device *dev, void *data, } vmw_execbuf_copy_fence_user(dev_priv, vmw_fp, 0, user_fence_rep, fence, - handle, -1, NULL); + handle, -1); vmw_fence_obj_unreference(&fence); return 0; out_no_create: diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 4e693e8de2c3..bbd2f4ec08ec 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -2501,7 +2501,7 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, if (file_priv) vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv), ret, user_fence_rep, fence, - handle, -1, NULL); + handle, -1); if (out_fence) *out_fence = fence; else diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index ca873a3b98db..f2d05bff4245 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1660,6 +1660,13 @@ static int balloon_connect_vsp(struct hv_device *dev) unsigned long t; int ret; + /* + * max_pkt_size should be large enough for one vmbus packet header plus + * our receive buffer size. Hyper-V sends messages up to + * HV_HYP_PAGE_SIZE bytes long on balloon channel. + */ + dev->channel->max_pkt_size = HV_HYP_PAGE_SIZE * 2; + ret = vmbus_open(dev->channel, dm_ring_size, dm_ring_size, NULL, 0, balloon_onchannelcallback, dev); if (ret) diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c index d519aca4a9d6..fb6d14d213a1 100644 --- a/drivers/hwmon/adt7470.c +++ b/drivers/hwmon/adt7470.c @@ -662,6 +662,9 @@ static int adt7470_fan_write(struct device *dev, u32 attr, int channel, long val struct adt7470_data *data = dev_get_drvdata(dev); int err; + if (val <= 0) + return -EINVAL; + val = FAN_RPM_TO_PERIOD(val); val = clamp_val(val, 1, 65534); diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c index 74019dff2550..1c9493c70813 100644 --- a/drivers/hwmon/lm90.c +++ b/drivers/hwmon/lm90.c @@ -373,7 +373,7 @@ static const struct lm90_params lm90_params[] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT | LM90_HAVE_BROKEN_ALERT | LM90_HAVE_CRIT, .alert_alarms = 0x7c, - .max_convrate = 8, + .max_convrate = 7, }, [lm86] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_REM_LIMIT_EXT @@ -394,12 +394,13 @@ static const struct lm90_params lm90_params[] = { .max_convrate = 9, }, [max6646] = { - .flags = LM90_HAVE_CRIT, + .flags = LM90_HAVE_CRIT | LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 6, .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, }, [max6654] = { + .flags = LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 7, .reg_local_ext = MAX6657_REG_R_LOCAL_TEMPL, @@ -418,7 +419,7 @@ static const struct lm90_params lm90_params[] = { }, [max6680] = { .flags = LM90_HAVE_OFFSET | LM90_HAVE_CRIT - | LM90_HAVE_CRIT_ALRM_SWP, + | LM90_HAVE_CRIT_ALRM_SWP | LM90_HAVE_BROKEN_ALERT, .alert_alarms = 0x7c, .max_convrate = 7, }, @@ -848,7 +849,7 @@ static int lm90_update_device(struct device *dev) * Re-enable ALERT# output if it was originally enabled and * relevant alarms are all clear */ - if (!(data->config_orig & 0x80) && + if ((client->irq || !(data->config_orig & 0x80)) && !(data->alarms & data->alert_alarms)) { if (data->config & 0x80) { dev_dbg(&client->dev, "Re-enabling ALERT#\n"); @@ -1807,22 +1808,22 @@ static bool lm90_is_tripped(struct i2c_client *client, u16 *status) if (st & LM90_STATUS_LLOW) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_min, 0); + hwmon_temp_min_alarm, 0); if (st & LM90_STATUS_RLOW) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_min, 1); + hwmon_temp_min_alarm, 1); if (st2 & MAX6696_STATUS2_R2LOW) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_min, 2); + hwmon_temp_min_alarm, 2); if (st & LM90_STATUS_LHIGH) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_max, 0); + hwmon_temp_max_alarm, 0); if (st & LM90_STATUS_RHIGH) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_max, 1); + hwmon_temp_max_alarm, 1); if (st2 & MAX6696_STATUS2_R2HIGH) hwmon_notify_event(data->hwmon_dev, hwmon_temp, - hwmon_temp_max, 2); + hwmon_temp_max_alarm, 2); return true; } diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index fd3f91cb01c6..098d12b9ecda 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -1175,7 +1175,7 @@ static inline u8 in_to_reg(u32 val, u8 nr) struct nct6775_data { int addr; /* IO base of hw monitor block */ - int sioreg; /* SIO register address */ + struct nct6775_sio_data *sio_data; enum kinds kind; const char *name; @@ -3559,7 +3559,7 @@ clear_caseopen(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct nct6775_data *data = dev_get_drvdata(dev); - struct nct6775_sio_data *sio_data = dev_get_platdata(dev); + struct nct6775_sio_data *sio_data = data->sio_data; int nr = to_sensor_dev_attr(attr)->index - INTRUSION_ALARM_BASE; unsigned long val; u8 reg; @@ -3967,7 +3967,7 @@ static int nct6775_probe(struct platform_device *pdev) return -ENOMEM; data->kind = sio_data->kind; - data->sioreg = sio_data->sioreg; + data->sio_data = sio_data; if (sio_data->access == access_direct) { data->addr = res->start; diff --git a/drivers/hwmon/pmbus/ir38064.c b/drivers/hwmon/pmbus/ir38064.c index 0ea7e1c18bdc..09276e397194 100644 --- a/drivers/hwmon/pmbus/ir38064.c +++ b/drivers/hwmon/pmbus/ir38064.c @@ -62,7 +62,7 @@ static const struct i2c_device_id ir38064_id[] = { MODULE_DEVICE_TABLE(i2c, ir38064_id); -static const struct of_device_id ir38064_of_match[] = { +static const struct of_device_id __maybe_unused ir38064_of_match[] = { { .compatible = "infineon,ir38060" }, { .compatible = "infineon,ir38064" }, { .compatible = "infineon,ir38164" }, diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 2543ef65825b..38091ebb9403 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -178,7 +178,6 @@ struct aic_irq_chip { struct irq_domain *hw_domain; struct irq_domain *ipi_domain; int nr_hw; - int ipi_hwirq; }; static DEFINE_PER_CPU(uint32_t, aic_fiq_unmasked); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d25b7a864bbb..9e93ff2b6375 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4856,6 +4856,38 @@ static struct syscore_ops its_syscore_ops = { .resume = its_restore_enable, }; +static void __init __iomem *its_map_one(struct resource *res, int *err) +{ + void __iomem *its_base; + u32 val; + + its_base = ioremap(res->start, SZ_64K); + if (!its_base) { + pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start); + *err = -ENOMEM; + return NULL; + } + + val = readl_relaxed(its_base + GITS_PIDR2) & GIC_PIDR2_ARCH_MASK; + if (val != 0x30 && val != 0x40) { + pr_warn("ITS@%pa: No ITS detected, giving up\n", &res->start); + *err = -ENODEV; + goto out_unmap; + } + + *err = its_force_quiescent(its_base); + if (*err) { + pr_warn("ITS@%pa: Failed to quiesce, giving up\n", &res->start); + goto out_unmap; + } + + return its_base; + +out_unmap: + iounmap(its_base); + return NULL; +} + static int its_init_domain(struct fwnode_handle *handle, struct its_node *its) { struct irq_domain *inner_domain; @@ -4963,29 +4995,14 @@ static int __init its_probe_one(struct resource *res, { struct its_node *its; void __iomem *its_base; - u32 val, ctlr; u64 baser, tmp, typer; struct page *page; + u32 ctlr; int err; - its_base = ioremap(res->start, SZ_64K); - if (!its_base) { - pr_warn("ITS@%pa: Unable to map ITS registers\n", &res->start); - return -ENOMEM; - } - - val = readl_relaxed(its_base + GITS_PIDR2) & GIC_PIDR2_ARCH_MASK; - if (val != 0x30 && val != 0x40) { - pr_warn("ITS@%pa: No ITS detected, giving up\n", &res->start); - err = -ENODEV; - goto out_unmap; - } - - err = its_force_quiescent(its_base); - if (err) { - pr_warn("ITS@%pa: Failed to quiesce, giving up\n", &res->start); - goto out_unmap; - } + its_base = its_map_one(res, &err); + if (!its_base) + return err; pr_info("ITS %pR\n", res); @@ -5241,13 +5258,31 @@ static int its_cpu_memreserve_lpi(unsigned int cpu) out: /* Last CPU being brought up gets to issue the cleanup */ - if (cpumask_equal(&cpus_booted_once_mask, cpu_possible_mask)) + if (!IS_ENABLED(CONFIG_SMP) || + cpumask_equal(&cpus_booted_once_mask, cpu_possible_mask)) schedule_work(&rdist_memreserve_cpuhp_cleanup_work); gic_data_rdist()->flags |= RD_LOCAL_MEMRESERVE_DONE; return ret; } +/* Mark all the BASER registers as invalid before they get reprogrammed */ +static int __init its_reset_one(struct resource *res) +{ + void __iomem *its_base; + int err, i; + + its_base = its_map_one(res, &err); + if (!its_base) + return err; + + for (i = 0; i < GITS_BASER_NR_REGS; i++) + gits_write_baser(0, its_base + GITS_BASER + (i << 3)); + + iounmap(its_base); + return 0; +} + static const struct of_device_id its_device_id[] = { { .compatible = "arm,gic-v3-its", }, {}, @@ -5258,6 +5293,26 @@ static int __init its_of_probe(struct device_node *node) struct device_node *np; struct resource res; + /* + * Make sure *all* the ITS are reset before we probe any, as + * they may be sharing memory. If any of the ITS fails to + * reset, don't even try to go any further, as this could + * result in something even worse. + */ + for (np = of_find_matching_node(node, its_device_id); np; + np = of_find_matching_node(np, its_device_id)) { + int err; + + if (!of_device_is_available(np) || + !of_property_read_bool(np, "msi-controller") || + of_address_to_resource(np, 0, &res)) + continue; + + err = its_reset_one(&res); + if (err) + return err; + } + for (np = of_find_matching_node(node, its_device_id); np; np = of_find_matching_node(np, its_device_id)) { if (!of_device_is_available(np)) @@ -5420,11 +5475,35 @@ dom_err: return err; } +static int __init its_acpi_reset(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_generic_translator *its_entry; + struct resource res; + + its_entry = (struct acpi_madt_generic_translator *)header; + res = (struct resource) { + .start = its_entry->base_address, + .end = its_entry->base_address + ACPI_GICV3_ITS_MEM_SIZE - 1, + .flags = IORESOURCE_MEM, + }; + + return its_reset_one(&res); +} + static void __init its_acpi_probe(void) { acpi_table_parse_srat_its(); - acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR, - gic_acpi_parse_madt_its, 0); + /* + * Make sure *all* the ITS are reset before we probe any, as + * they may be sharing memory. If any of the ITS fails to + * reset, don't even try to go any further, as this could + * result in something even worse. + */ + if (acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR, + its_acpi_reset, 0) > 0) + acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR, + gic_acpi_parse_madt_its, 0); acpi_its_srat_maps_free(); } #else diff --git a/drivers/irqchip/irq-loongson-pch-msi.c b/drivers/irqchip/irq-loongson-pch-msi.c index 32562b7e681b..e3801c4a77ed 100644 --- a/drivers/irqchip/irq-loongson-pch-msi.c +++ b/drivers/irqchip/irq-loongson-pch-msi.c @@ -241,7 +241,7 @@ static int pch_msi_init(struct device_node *node, return 0; err_map: - kfree(priv->msi_map); + bitmap_free(priv->msi_map); err_priv: kfree(priv); return ret; diff --git a/drivers/irqchip/irq-realtek-rtl.c b/drivers/irqchip/irq-realtek-rtl.c index fd9f275592d2..50a56820c99b 100644 --- a/drivers/irqchip/irq-realtek-rtl.c +++ b/drivers/irqchip/irq-realtek-rtl.c @@ -62,7 +62,7 @@ static struct irq_chip realtek_ictl_irq = { static int intc_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { - irq_set_chip_and_handler(hw, &realtek_ictl_irq, handle_level_irq); + irq_set_chip_and_handler(irq, &realtek_ictl_irq, handle_level_irq); return 0; } @@ -76,16 +76,20 @@ static void realtek_irq_dispatch(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct irq_domain *domain; - unsigned int pending; + unsigned long pending; + unsigned int soc_int; chained_irq_enter(chip, desc); pending = readl(REG(RTL_ICTL_GIMR)) & readl(REG(RTL_ICTL_GISR)); + if (unlikely(!pending)) { spurious_interrupt(); goto out; } + domain = irq_desc_get_handler_data(desc); - generic_handle_domain_irq(domain, __ffs(pending)); + for_each_set_bit(soc_int, &pending, 32) + generic_handle_domain_irq(domain, soc_int); out: chained_irq_exit(chip, desc); @@ -95,7 +99,8 @@ out: * SoC interrupts are cascaded to MIPS CPU interrupts according to the * interrupt-map in the device tree. Each SoC interrupt gets 4 bits for * the CPU interrupt in an Interrupt Routing Register. Max 32 SoC interrupts - * thus go into 4 IRRs. + * thus go into 4 IRRs. A routing value of '0' means the interrupt is left + * disconnected. Routing values {1..15} connect to output lines {0..14}. */ static int __init map_interrupts(struct device_node *node, struct irq_domain *domain) { @@ -134,7 +139,7 @@ static int __init map_interrupts(struct device_node *node, struct irq_domain *do of_node_put(cpu_ictl); cpu_int = be32_to_cpup(imap + 2); - if (cpu_int > 7) + if (cpu_int > 7 || cpu_int < 2) return -EINVAL; if (!(mips_irqs_set & BIT(cpu_int))) { @@ -143,7 +148,8 @@ static int __init map_interrupts(struct device_node *node, struct irq_domain *do mips_irqs_set |= BIT(cpu_int); } - regs[(soc_int * 4) / 32] |= cpu_int << (soc_int * 4) % 32; + /* Use routing values (1..6) for CPU interrupts (2..7) */ + regs[(soc_int * 4) / 32] |= (cpu_int - 1) << (soc_int * 4) % 32; imap += 3; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c0ae8087c602..dcbd6d201619 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -489,7 +489,7 @@ static void start_io_acct(struct dm_io *io) struct mapped_device *md = io->md; struct bio *bio = io->orig_bio; - io->start_time = bio_start_io_acct(bio); + bio_start_io_acct_time(bio, io->start_time); if (unlikely(dm_stats_used(&md->stats))) dm_stats_account_io(&md->stats, bio_data_dir(bio), bio->bi_iter.bi_sector, bio_sectors(bio), @@ -535,7 +535,7 @@ static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio) io->md = md; spin_lock_init(&io->endio_lock); - start_io_acct(io); + io->start_time = jiffies; return io; } @@ -1442,9 +1442,6 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md, ci->sector = bio->bi_iter.bi_sector; } -#define __dm_part_stat_sub(part, field, subnd) \ - (part_stat_get(part, field) -= (subnd)) - /* * Entry point to split a bio into clones and submit them to the targets. */ @@ -1480,23 +1477,12 @@ static void __split_and_process_bio(struct mapped_device *md, GFP_NOIO, &md->queue->bio_split); ci.io->orig_bio = b; - /* - * Adjust IO stats for each split, otherwise upon queue - * reentry there will be redundant IO accounting. - * NOTE: this is a stop-gap fix, a proper fix involves - * significant refactoring of DM core's bio splitting - * (by eliminating DM's splitting and just using bio_split) - */ - part_stat_lock(); - __dm_part_stat_sub(dm_disk(md)->part0, - sectors[op_stat_group(bio_op(bio))], ci.sector_count); - part_stat_unlock(); - bio_chain(b, bio); trace_block_split(b, bio->bi_iter.bi_sector); submit_bio_noacct(bio); } } + start_io_acct(ci.io); /* drop the extra reference count */ dm_io_dec_pending(ci.io, errno_to_blk_status(error)); diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index c3305bdda69c..bee727ed98db 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -440,6 +440,10 @@ static int at25_probe(struct spi_device *spi) return -ENXIO; } + at25 = devm_kzalloc(&spi->dev, sizeof(*at25), GFP_KERNEL); + if (!at25) + return -ENOMEM; + mutex_init(&at25->lock); at25->spi = spi; spi_set_drvdata(spi, at25); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 533e476988f2..303c8d32d451 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -19,6 +19,7 @@ #include <linux/in.h> #include <net/arp.h> #include <net/ipv6.h> +#include <net/ndisc.h> #include <asm/byteorder.h> #include <net/bonding.h> #include <net/bond_alb.h> @@ -1269,6 +1270,27 @@ unwind: return res; } +/* determine if the packet is NA or NS */ +static bool alb_determine_nd(struct sk_buff *skb, struct bonding *bond) +{ + struct ipv6hdr *ip6hdr; + struct icmp6hdr *hdr; + + if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) + return true; + + ip6hdr = ipv6_hdr(skb); + if (ip6hdr->nexthdr != IPPROTO_ICMPV6) + return false; + + if (!pskb_network_may_pull(skb, sizeof(*ip6hdr) + sizeof(*hdr))) + return true; + + hdr = icmp6_hdr(skb); + return hdr->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT || + hdr->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION; +} + /************************ exported alb functions ************************/ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) @@ -1348,8 +1370,11 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, /* Do not TX balance any multicast or broadcast */ if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { - case htons(ETH_P_IP): case htons(ETH_P_IPV6): + if (alb_determine_nd(skb, bond)) + break; + fallthrough; + case htons(ETH_P_IP): hash_index = bond_xmit_hash(bond, skb); if (bond->params.tlb_dynamic_lb) { tx_slave = tlb_choose_channel(bond, @@ -1432,10 +1457,12 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, break; } - if (!pskb_network_may_pull(skb, sizeof(*ip6hdr))) { + if (alb_determine_nd(skb, bond)) { do_tx_balance = false; break; } + + /* The IPv6 header is pulled by alb_determine_nd */ /* Additionally, DAD probes should not be tx-balanced as that * will lead to false positives for duplicate addresses and * prevent address configuration from working. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ec498ce70f35..238b56d77c36 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4133,9 +4133,7 @@ static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cm fallthrough; case SIOCGHWTSTAMP: - rcu_read_lock(); real_dev = bond_option_active_slave_get_rcu(bond); - rcu_read_unlock(); if (!real_dev) return -EOPNOTSUPP; @@ -5382,9 +5380,7 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev, struct net_device *real_dev; struct phy_device *phydev; - rcu_read_lock(); real_dev = bond_option_active_slave_get_rcu(bond); - rcu_read_unlock(); if (real_dev) { ops = real_dev->ethtool_ops; phydev = real_dev->phydev; diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 0bff1884d5cc..74d7fcbfd065 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -296,6 +296,7 @@ static_assert(sizeof(struct flexcan_regs) == 0x4 * 18 + 0xfb8); static const struct flexcan_devtype_data fsl_mcf5441x_devtype_data = { .quirks = FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_NR_IRQ_3 | FLEXCAN_QUIRK_NR_MB_16 | + FLEXCAN_QUIRK_SUPPPORT_RX_MAILBOX | FLEXCAN_QUIRK_SUPPPORT_RX_FIFO, }; diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h index fccdff8b1f0f..23fc09a7e10f 100644 --- a/drivers/net/can/flexcan/flexcan.h +++ b/drivers/net/can/flexcan/flexcan.h @@ -21,7 +21,7 @@ * Below is some version info we got: * SOC Version IP-Version Glitch- [TR]WRN_INT IRQ Err Memory err RTR rece- FD Mode MB * Filter? connected? Passive detection ption in MB Supported? - * MCF5441X FlexCAN2 ? no yes no no yes no 16 + * MCF5441X FlexCAN2 ? no yes no no no no 16 * MX25 FlexCAN2 03.00.00.00 no no no no no no 64 * MX28 FlexCAN2 03.00.04.00 yes yes no no no no 64 * MX35 FlexCAN2 03.00.00.00 no no no no no no 64 diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 5b47cd867783..1a4b56f6fa8c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -336,6 +336,9 @@ m_can_fifo_read(struct m_can_classdev *cdev, u32 addr_offset = cdev->mcfg[MRAM_RXF0].off + fgi * RXF0_ELEMENT_SIZE + offset; + if (val_count == 0) + return 0; + return cdev->ops->read_fifo(cdev, addr_offset, val, val_count); } @@ -346,6 +349,9 @@ m_can_fifo_write(struct m_can_classdev *cdev, u32 addr_offset = cdev->mcfg[MRAM_TXB].off + fpi * TXB_ELEMENT_SIZE + offset; + if (val_count == 0) + return 0; + return cdev->ops->write_fifo(cdev, addr_offset, val, val_count); } diff --git a/drivers/net/can/m_can/tcan4x5x-regmap.c b/drivers/net/can/m_can/tcan4x5x-regmap.c index ca80dbaf7a3f..26e212b8ca7a 100644 --- a/drivers/net/can/m_can/tcan4x5x-regmap.c +++ b/drivers/net/can/m_can/tcan4x5x-regmap.c @@ -12,7 +12,7 @@ #define TCAN4X5X_SPI_INSTRUCTION_WRITE (0x61 << 24) #define TCAN4X5X_SPI_INSTRUCTION_READ (0x41 << 24) -#define TCAN4X5X_MAX_REGISTER 0x8ffc +#define TCAN4X5X_MAX_REGISTER 0x87fc static int tcan4x5x_regmap_gather_write(void *context, const void *reg, size_t reg_len, diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 7b1457a6e327..8d51c1019dcd 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -36,6 +36,7 @@ config NET_DSA_LANTIQ_GSWIP config NET_DSA_MT7530 tristate "MediaTek MT753x and MT7621 Ethernet switch support" select NET_DSA_TAG_MTK + select MEDIATEK_GE_PHY help This enables support for the MediaTek MT7530, MT7531, and MT7621 Ethernet switch chips. @@ -67,17 +68,7 @@ config NET_DSA_QCA8K This enables support for the Qualcomm Atheros QCA8K Ethernet switch chips. -config NET_DSA_REALTEK_SMI - tristate "Realtek SMI Ethernet switch family support" - select NET_DSA_TAG_RTL4_A - select NET_DSA_TAG_RTL8_4 - select FIXED_PHY - select IRQ_DOMAIN - select REALTEK_PHY - select REGMAP - help - This enables support for the Realtek SMI-based switch - chips, currently only RTL8366RB. +source "drivers/net/dsa/realtek/Kconfig" config NET_DSA_SMSC_LAN9303 tristate diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 8da1569a34e6..e73838c12256 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -9,8 +9,6 @@ obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o -obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o -realtek-smi-objs := realtek-smi-core.o rtl8366.o rtl8366rb.o rtl8365mb.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o @@ -23,5 +21,6 @@ obj-y += microchip/ obj-y += mv88e6xxx/ obj-y += ocelot/ obj-y += qca/ +obj-y += realtek/ obj-y += sja1105/ obj-y += xrs700x/ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 3867f3d4545f..a3b98992f180 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2186,7 +2186,7 @@ int b53_eee_init(struct dsa_switch *ds, int port, struct phy_device *phy) { int ret; - ret = phy_init_eee(phy, 0); + ret = phy_init_eee(phy, false); if (ret) return 0; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 33499fcd8848..9161ce4ca352 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -709,49 +709,25 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) PHY_BRCM_IDDQ_SUSPEND; } -static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void bcm_sf2_sw_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { + unsigned long *interfaces = config->supported_interfaces; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - - if (!phy_interface_mode_is_rgmii(state->interface) && - state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_REVMII && - state->interface != PHY_INTERFACE_MODE_GMII && - state->interface != PHY_INTERFACE_MODE_INTERNAL && - state->interface != PHY_INTERFACE_MODE_MOCA) { - linkmode_zero(supported); - if (port != core_readl(priv, CORE_IMP0_PRT_ID)) - dev_err(ds->dev, - "Unsupported interface: %d for port %d\n", - state->interface, port); - return; - } - - /* Allow all the expected bits */ - phylink_set(mask, Autoneg); - phylink_set_port_modes(mask); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - /* With the exclusion of MII and Reverse MII, we support Gigabit, - * including Half duplex - */ - if (state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_REVMII) { - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseT_Half); + if (priv->int_phy_mask & BIT(port)) { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, interfaces); + } else if (priv->moca_port == port) { + __set_bit(PHY_INTERFACE_MODE_MOCA, interfaces); + } else { + __set_bit(PHY_INTERFACE_MODE_MII, interfaces); + __set_bit(PHY_INTERFACE_MODE_REVMII, interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, interfaces); + phy_interface_set_rgmii(interfaces); } - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; } static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port, @@ -1218,7 +1194,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .get_sset_count = bcm_sf2_sw_get_sset_count, .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .get_phy_flags = bcm_sf2_sw_get_phy_flags, - .phylink_validate = bcm_sf2_sw_validate, + .phylink_get_caps = bcm_sf2_sw_get_caps, .phylink_mac_config = bcm_sf2_sw_mac_config, .phylink_mac_link_down = bcm_sf2_sw_mac_link_down, .phylink_mac_link_up = bcm_sf2_sw_mac_link_up, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 991b9c6b6ce7..5dc9899bc0a6 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1461,27 +1461,22 @@ static int ksz8_setup(struct dsa_switch *ds) return 0; } -static void ksz8_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void ksz8_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; struct ksz_device *dev = ds->priv; if (port == dev->cpu_port) { - if (state->interface != PHY_INTERFACE_MODE_RMII && - state->interface != PHY_INTERFACE_MODE_MII && - state->interface != PHY_INTERFACE_MODE_NA) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_MII, + config->supported_interfaces); } else { - if (state->interface != PHY_INTERFACE_MODE_INTERNAL && - state->interface != PHY_INTERFACE_MODE_NA) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); } - /* Allow all the expected bits */ - phylink_set_port_modes(mask); - phylink_set(mask, Autoneg); + config->mac_capabilities = MAC_10 | MAC_100; /* Silicon Errata Sheet (DS80000830A): * "Port 1 does not respond to received flow control PAUSE frames" @@ -1489,27 +1484,11 @@ static void ksz8_validate(struct dsa_switch *ds, int port, * switches. */ if (!ksz_is_ksz88x3(dev) || port) - phylink_set(mask, Pause); + config->mac_capabilities |= MAC_SYM_PAUSE; /* Asym pause is not supported on KSZ8863 and KSZ8873 */ if (!ksz_is_ksz88x3(dev)) - phylink_set(mask, Asym_Pause); - - /* 10M and 100M are only supported */ - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); - - return; - -unsupported: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported interface: %s, port: %d\n", - phy_modes(state->interface), port); + config->mac_capabilities |= MAC_ASYM_PAUSE; } static const struct dsa_switch_ops ksz8_switch_ops = { @@ -1518,7 +1497,7 @@ static const struct dsa_switch_ops ksz8_switch_ops = { .setup = ksz8_setup, .phy_read = ksz_phy_read16, .phy_write = ksz_phy_write16, - .phylink_validate = ksz8_validate, + .phylink_get_caps = ksz8_get_caps, .phylink_mac_link_down = ksz_mac_link_down, .port_enable = ksz_enable_port, .get_strings = ksz8_get_strings, diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 353b5f981740..a85d990896b0 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -222,9 +222,12 @@ static int ksz9477_reset_switch(struct ksz_device *dev) (BROADCAST_STORM_VALUE * BROADCAST_STORM_PROT_RATE) / 100); - if (dev->synclko_125) - ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1, - SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ); + data8 = SW_ENABLE_REFCLKO; + if (dev->synclko_disable) + data8 = 0; + else if (dev->synclko_125) + data8 = SW_ENABLE_REFCLKO | SW_REFCLKO_IS_125MHZ; + ksz_write8(dev, REG_SW_GLOBAL_OUTPUT_CTRL__1, data8); return 0; } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 55dbda04ea62..7e33ec73f803 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -434,6 +434,12 @@ int ksz_switch_register(struct ksz_device *dev, } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); + dev->synclko_disable = of_property_read_bool(dev->dev->of_node, + "microchip,synclko-disable"); + if (dev->synclko_125 && dev->synclko_disable) { + dev_err(dev->dev, "inconsistent synclko settings\n"); + return -EINVAL; + } } ret = dsa_register_switch(dev->ds); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index df8ae59c8525..3db63f62f0a1 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -75,6 +75,7 @@ struct ksz_device { u32 regs_size; bool phy_errata_9477; bool synclko_125; + bool synclko_disable; struct vlan_table *vlan_cache; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index b82512e5b33b..bc77a26c825a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2846,7 +2846,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, mcr |= PMCR_RX_FC_EN; } - if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, 0) >= 0) { + if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) { switch (speed) { case SPEED_1000: mcr |= PMCR_FORCE_EEE1G; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 58ca684d73f7..c54649c4c3a0 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -86,12 +86,16 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val) int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask, u16 val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - /* There's no bus specific operation to wait for a mask */ - for (i = 0; i < 16; i++) { + /* There's no bus specific operation to wait for a mask. Even + * if the initial poll takes longer than 50ms, always do at + * least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_read(chip, addr, reg, &data); if (err) return err; @@ -99,7 +103,10 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, if ((data & mask) == val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } dev_err(chip->dev, "Timeout while waiting for switch\n"); @@ -563,133 +570,249 @@ static int mv88e6xxx_serdes_pcs_link_up(struct mv88e6xxx_chip *chip, int port, return 0; } -static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static const u8 mv88e6185_phy_interface_modes[] = { + [MV88E6185_PORT_STS_CMODE_GMII_FD] = PHY_INTERFACE_MODE_GMII, + [MV88E6185_PORT_STS_CMODE_MII_100_FD_PS] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_MII_100] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_MII_10] = PHY_INTERFACE_MODE_MII, + [MV88E6185_PORT_STS_CMODE_SERDES] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6185_PORT_STS_CMODE_1000BASE_X] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6185_PORT_STS_CMODE_PHY] = PHY_INTERFACE_MODE_SGMII, +}; + +static void mv88e6185_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (!phy_interface_mode_is_8023z(state->interface)) { - /* 10M and 100M are only supported in non-802.3z mode */ - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - } + u8 cmode = chip->ports[port].cmode; + + if (cmode < ARRAY_SIZE(mv88e6185_phy_interface_modes) && + mv88e6185_phy_interface_modes[cmode]) + __set_bit(mv88e6185_phy_interface_modes[cmode], + config->supported_interfaces); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; } -static void mv88e6185_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) -{ - /* FIXME: if the port is in 1000Base-X mode, then it only supports - * 1000M FD speeds. In this case, CMODE will indicate 5. +static const u8 mv88e6xxx_phy_interface_modes[] = { + [MV88E6XXX_PORT_STS_CMODE_MII_PHY] = PHY_INTERFACE_MODE_MII, + [MV88E6XXX_PORT_STS_CMODE_MII] = PHY_INTERFACE_MODE_MII, + [MV88E6XXX_PORT_STS_CMODE_GMII] = PHY_INTERFACE_MODE_GMII, + [MV88E6XXX_PORT_STS_CMODE_RMII_PHY] = PHY_INTERFACE_MODE_RMII, + [MV88E6XXX_PORT_STS_CMODE_RMII] = PHY_INTERFACE_MODE_RMII, + [MV88E6XXX_PORT_STS_CMODE_100BASEX] = PHY_INTERFACE_MODE_100BASEX, + [MV88E6XXX_PORT_STS_CMODE_1000BASEX] = PHY_INTERFACE_MODE_1000BASEX, + [MV88E6XXX_PORT_STS_CMODE_SGMII] = PHY_INTERFACE_MODE_SGMII, + /* higher interface modes are not needed here, since ports supporting + * them are writable, and so the supported interfaces are filled in the + * corresponding .phylink_set_interfaces() implementation below */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); +}; - mv88e6065_phylink_validate(chip, port, mask, state); +static void mv88e6xxx_translate_cmode(u8 cmode, unsigned long *supported) +{ + if (cmode < ARRAY_SIZE(mv88e6xxx_phy_interface_modes) && + mv88e6xxx_phy_interface_modes[cmode]) + __set_bit(mv88e6xxx_phy_interface_modes[cmode], supported); + else if (cmode == MV88E6XXX_PORT_STS_CMODE_RGMII) + phy_interface_set_rgmii(supported); } -static void mv88e6341_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 5) - phylink_set(mask, 2500baseX_Full); + unsigned long *supported = config->supported_interfaces; - /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); - mv88e6065_phylink_validate(chip, port, mask, state); + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; } -static void mv88e6352_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip) { - /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + u16 reg, val; + int err; + + err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, ®); + if (err) + return err; + + /* If PHY_DETECT is zero, then we are not in auto-media mode */ + if (!(reg & MV88E6XXX_PORT_STS_PHY_DETECT)) + return 0xf; + + val = reg & ~MV88E6XXX_PORT_STS_PHY_DETECT; + err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, val); + if (err) + return err; + + err = mv88e6xxx_port_read(chip, 4, MV88E6XXX_PORT_STS, &val); + if (err) + return err; + + /* Restore PHY_DETECT value */ + err = mv88e6xxx_port_write(chip, 4, MV88E6XXX_PORT_STS, reg); + if (err) + return err; - mv88e6065_phylink_validate(chip, port, mask, state); + return val & MV88E6XXX_PORT_STS_CMODE_MASK; } -static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6352_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 9) { - phylink_set(mask, 2500baseX_Full); - phylink_set(mask, 2500baseT_Full); + unsigned long *supported = config->supported_interfaces; + int err, cmode; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; + + /* Port 4 supports automedia if the serdes is associated with it. */ + if (port == 4) { + mv88e6xxx_reg_lock(chip); + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err < 0) + dev_err(chip->dev, "p%d: failed to read scratch\n", + port); + if (err <= 0) + goto unlock; + + cmode = mv88e6352_get_port4_serdes_cmode(chip); + if (cmode < 0) + dev_err(chip->dev, "p%d: failed to read serdes cmode\n", + port); + else + mv88e6xxx_translate_cmode(cmode, supported); +unlock: + mv88e6xxx_reg_unlock(chip); } +} + +static void mv88e6341_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); /* No ethtool bits for 200Mbps */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; + + /* The C_Mode field is programmable on port 5 */ + if (port == 5) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); - mv88e6065_phylink_validate(chip, port, mask, state); + config->mac_capabilities |= MAC_2500FD; + } } -static void mv88e6390x_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6390_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { - if (port >= 9) { - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseKR_Full); + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + /* No ethtool bits for 200Mbps */ + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; + + /* The C_Mode field is programmable on ports 9 and 10 */ + if (port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + + config->mac_capabilities |= MAC_2500FD; } +} + +static void mv88e6390x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; - mv88e6390_phylink_validate(chip, port, mask, state); + mv88e6390_phylink_get_caps(chip, port, config); + + /* For the 6x90X, ports 2-7 can be in automedia mode. + * (Note that 6x90 doesn't support RXAUI nor XAUI). + * + * Port 2 can also support 1000BASE-X in automedia mode if port 9 is + * configured for 1000BASE-X, SGMII or 2500BASE-X. + * Port 3-4 can also support 1000BASE-X in automedia mode if port 9 is + * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X. + * + * Port 5 can also support 1000BASE-X in automedia mode if port 10 is + * configured for 1000BASE-X, SGMII or 2500BASE-X. + * Port 6-7 can also support 1000BASE-X in automedia mode if port 10 is + * configured for RXAUI, 1000BASE-X, SGMII or 2500BASE-X. + * + * For now, be permissive (as the old code was) and allow 1000BASE-X + * on ports 2..7. + */ + if (port >= 2 && port <= 7) + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); + + /* The C_Mode field can also be programmed for 10G speeds */ + if (port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_XAUI, supported); + __set_bit(PHY_INTERFACE_MODE_RXAUI, supported); + + config->mac_capabilities |= MAC_10000FD; + } } -static void mv88e6393x_phylink_validate(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state) +static void mv88e6393x_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) { + unsigned long *supported = config->supported_interfaces; bool is_6191x = chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6191X; - if (((port == 0 || port == 9) && !is_6191x) || port == 10) { - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseKR_Full); - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); - phylink_set(mask, 5000baseT_Full); - phylink_set(mask, 2500baseX_Full); - phylink_set(mask, 2500baseT_Full); - } + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + /* The C_Mode field can be programmed for ports 0, 9 and 10 */ + if (port == 0 || port == 9 || port == 10) { + __set_bit(PHY_INTERFACE_MODE_SGMII, supported); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, supported); - mv88e6065_phylink_validate(chip, port, mask, state); + /* 6191X supports >1G modes only on port 10 */ + if (!is_6191x || port == 10) { + __set_bit(PHY_INTERFACE_MODE_2500BASEX, supported); + __set_bit(PHY_INTERFACE_MODE_5GBASER, supported); + __set_bit(PHY_INTERFACE_MODE_10GBASER, supported); + /* FIXME: USXGMII is not supported yet */ + /* __set_bit(PHY_INTERFACE_MODE_USXGMII, supported); */ + + config->mac_capabilities |= MAC_2500FD | MAC_5000FD | + MAC_10000FD; + } + } } -static void mv88e6xxx_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; struct mv88e6xxx_chip *chip = ds->priv; - /* Allow all the expected bits */ - phylink_set(mask, Autoneg); - phylink_set(mask, Pause); - phylink_set_port_modes(mask); + chip->info->ops->phylink_get_caps(chip, port, config); - if (chip->info->ops->phylink_validate) - chip->info->ops->phylink_validate(chip, port, mask, state); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); - - /* We can only operate at 2500BaseX or 1000BaseX. If requested - * to advertise both, only report advertising at 2500BaseX. - */ - phylink_helper_basex_speed(state); + /* Internal ports need GMII for PHYLIB */ + if (mv88e6xxx_phy_is_internal(ds, port)) + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); } static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, @@ -1283,8 +1406,15 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) pvlan = 0; - /* Frames from user ports can egress any local DSA links and CPU ports, - * as well as any local member of their bridge group. + /* Frames from standalone user ports can only egress on the + * upstream port. + */ + if (!dsa_port_bridge_dev_get(dp)) + return BIT(dsa_switch_upstream_port(ds)); + + /* Frames from bridged user ports can egress any local DSA + * links and CPU ports, as well as any local member of their + * bridge group. */ dsa_switch_for_each_port(other_dp, ds) if (other_dp->type == DSA_PORT_TYPE_CPU || @@ -1616,21 +1746,11 @@ static int mv88e6xxx_fid_map_vlan(struct mv88e6xxx_chip *chip, int mv88e6xxx_fid_map(struct mv88e6xxx_chip *chip, unsigned long *fid_bitmap) { - int i, err; - u16 fid; - bitmap_zero(fid_bitmap, MV88E6XXX_N_FID); - /* Set every FID bit used by the (un)bridged ports */ - for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { - err = mv88e6xxx_port_get_fid(chip, i, &fid); - if (err) - return err; - - set_bit(fid, fid_bitmap); - } - - /* Set every FID bit used by the VLAN entries */ + /* Every FID has an associated VID, so walking the VTU + * will discover the full set of FIDs in use. + */ return mv88e6xxx_vtu_walk(chip, mv88e6xxx_fid_map_vlan, fid_bitmap); } @@ -1643,10 +1763,7 @@ static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) if (err) return err; - /* The reset value 0x000 is used to indicate that multiple address - * databases are not needed. Return the next positive available. - */ - *fid = find_next_zero_bit(fid_bitmap, MV88E6XXX_N_FID, 1); + *fid = find_first_zero_bit(fid_bitmap, MV88E6XXX_N_FID); if (unlikely(*fid >= mv88e6xxx_num_databases(chip))) return -ENOSPC; @@ -2138,6 +2255,9 @@ static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, if (!vlan.valid) { memset(&vlan, 0, sizeof(vlan)); + if (vid == MV88E6XXX_VID_STANDALONE) + vlan.policy = true; + err = mv88e6xxx_atu_new(chip, &vlan.fid); if (err) return err; @@ -2480,6 +2600,10 @@ static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, if (err) goto unlock; + err = mv88e6xxx_port_set_map_da(chip, port, true); + if (err) + goto unlock; + err = mv88e6xxx_port_commit_pvid(chip, port); if (err) goto unlock; @@ -2514,6 +2638,12 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); + err = mv88e6xxx_port_set_map_da(chip, port, false); + if (err) + dev_err(ds->dev, + "port %d failed to restore map-DA: %pe\n", + port, ERR_PTR(err)); + err = mv88e6xxx_port_commit_pvid(chip, port); if (err) dev_err(ds->dev, @@ -2911,12 +3041,13 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) return err; /* Port Control 2: don't force a good FCS, set the MTU size to - * 10222 bytes, disable 802.1q tags checking, don't discard tagged or - * untagged frames on this port, do a destination address lookup on all - * received packets as usual, disable ARP mirroring and don't send a - * copy of all transmitted/received frames on this port to the CPU. + * 10222 bytes, disable 802.1q tags checking, don't discard + * tagged or untagged frames on this port, skip destination + * address lookup on user ports, disable ARP mirroring and don't + * send a copy of all transmitted/received frames on this port + * to the CPU. */ - err = mv88e6xxx_port_set_map_da(chip, port); + err = mv88e6xxx_port_set_map_da(chip, port, !dsa_is_user_port(ds, port)); if (err) return err; @@ -2924,8 +3055,44 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) if (err) return err; + /* On chips that support it, set all downstream DSA ports' + * VLAN policy to TRAP. In combination with loading + * MV88E6XXX_VID_STANDALONE as a policy entry in the VTU, this + * provides a better isolation barrier between standalone + * ports, as the ATU is bypassed on any intermediate switches + * between the incoming port and the CPU. + */ + if (dsa_is_downstream_port(ds, port) && + chip->info->ops->port_set_policy) { + err = chip->info->ops->port_set_policy(chip, port, + MV88E6XXX_POLICY_MAPPING_VTU, + MV88E6XXX_POLICY_ACTION_TRAP); + if (err) + return err; + } + + /* User ports start out in standalone mode and 802.1Q is + * therefore disabled. On DSA ports, all valid VIDs are always + * loaded in the VTU - therefore, enable 802.1Q in order to take + * advantage of VLAN policy on chips that supports it. + */ err = mv88e6xxx_port_set_8021q_mode(chip, port, - MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED); + dsa_is_user_port(ds, port) ? + MV88E6XXX_PORT_CTL2_8021Q_MODE_DISABLED : + MV88E6XXX_PORT_CTL2_8021Q_MODE_SECURE); + if (err) + return err; + + /* Bind MV88E6XXX_VID_STANDALONE to MV88E6XXX_FID_STANDALONE by + * virtue of the fact that mv88e6xxx_atu_new() will pick it as + * the first free FID. This will be used as the private PVID for + * unbridged ports. Shared (DSA and CPU) ports must also be + * members of this VID, in order to trap all frames assigned to + * it to the CPU. + */ + err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_STANDALONE, + MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED, + false); if (err) return err; @@ -2938,7 +3105,7 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port) * relying on their port default FID. */ err = mv88e6xxx_port_vlan_join(chip, port, MV88E6XXX_VID_BRIDGED, - MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNTAGGED, + MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_UNMODIFIED, false); if (err) return err; @@ -3577,7 +3744,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3611,7 +3778,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3627,6 +3794,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .port_sync_link = mv88e6185_port_sync_link, .port_set_speed_duplex = mv88e6185_port_set_speed_duplex, .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_policy = mv88e6352_port_set_policy, .port_set_frame_mode = mv88e6351_port_set_frame_mode, .port_set_ucast_flood = mv88e6352_port_set_ucast_flood, .port_set_mcast_flood = mv88e6352_port_set_mcast_flood, @@ -3657,7 +3825,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3694,7 +3862,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3735,7 +3903,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6141_ops = { @@ -3799,7 +3967,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6341_phylink_validate, + .phylink_get_caps = mv88e6341_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6161_ops = { @@ -3841,7 +4009,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -3877,7 +4045,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6165_avb_ops, .ptp_ops = &mv88e6165_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6171_ops = { @@ -3919,7 +4087,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6172_ops = { @@ -3974,7 +4142,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6175_ops = { @@ -4016,7 +4184,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -4074,7 +4242,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6185_ops = { @@ -4113,7 +4281,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, .set_max_frame_size = mv88e6185_g1_set_max_frame_size, }; @@ -4175,7 +4343,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6190x_ops = { @@ -4236,7 +4404,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, - .phylink_validate = mv88e6390x_phylink_validate, + .phylink_get_caps = mv88e6390x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6191_ops = { @@ -4296,7 +4464,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_get_regs = mv88e6390_serdes_get_regs, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6240_ops = { @@ -4356,7 +4524,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6250_ops = { @@ -4396,7 +4564,7 @@ static const struct mv88e6xxx_ops mv88e6250_ops = { .vtu_loadpurge = mv88e6185_g1_vtu_loadpurge, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6250_ptp_ops, - .phylink_validate = mv88e6065_phylink_validate, + .phylink_get_caps = mv88e6250_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6290_ops = { @@ -4458,7 +4626,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6320_ops = { @@ -4502,7 +4670,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6321_ops = { @@ -4544,7 +4712,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6341_ops = { @@ -4610,7 +4778,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6341_phylink_validate, + .phylink_get_caps = mv88e6341_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6350_ops = { @@ -4652,7 +4820,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .atu_set_hash = mv88e6165_g1_atu_set_hash, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6351_ops = { @@ -4696,7 +4864,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6185_phylink_validate, + .phylink_get_caps = mv88e6185_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6352_ops = { @@ -4759,7 +4927,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .serdes_get_stats = mv88e6352_serdes_get_stats, .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, .serdes_get_regs = mv88e6352_serdes_get_regs, - .phylink_validate = mv88e6352_phylink_validate, + .phylink_get_caps = mv88e6352_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6390_ops = { @@ -4824,7 +4992,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, + .phylink_get_caps = mv88e6390_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6390x_ops = { @@ -4888,7 +5056,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6390x_phylink_validate, + .phylink_get_caps = mv88e6390x_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6393x_ops = { @@ -4952,7 +5120,7 @@ static const struct mv88e6xxx_ops mv88e6393x_ops = { .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_validate = mv88e6393x_phylink_validate, + .phylink_get_caps = mv88e6393x_phylink_get_caps, }; static const struct mv88e6xxx_info mv88e6xxx_table[] = { @@ -6221,7 +6389,7 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .teardown = mv88e6xxx_teardown, .port_setup = mv88e6xxx_port_setup, .port_teardown = mv88e6xxx_port_teardown, - .phylink_validate = mv88e6xxx_validate, + .phylink_get_caps = mv88e6xxx_get_caps, .phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state, .phylink_mac_config = mv88e6xxx_mac_config, .phylink_mac_an_restart = mv88e6xxx_serdes_pcs_an_restart, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 8271b8aa7b71..12aa637779f5 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -179,6 +179,7 @@ struct mv88e6xxx_vtu_entry { u16 fid; u8 sid; bool valid; + bool policy; u8 member[DSA_MAX_PORTS]; u8 state[DSA_MAX_PORTS]; }; @@ -392,6 +393,7 @@ struct mv88e6xxx_chip { struct mv88e6xxx_bus_ops { int (*read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int (*write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); + int (*init)(struct mv88e6xxx_chip *chip); }; struct mv88e6xxx_mdio_bus { @@ -609,9 +611,8 @@ struct mv88e6xxx_ops { const struct mv88e6xxx_ptp_ops *ptp_ops; /* Phylink */ - void (*phylink_validate)(struct mv88e6xxx_chip *chip, int port, - unsigned long *mask, - struct phylink_link_state *state); + void (*phylink_get_caps)(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config); /* Max Frame Size */ int (*set_max_frame_size)(struct mv88e6xxx_chip *chip, int mtu); diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 4f3dbb015f77..2c1607c858a1 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -46,6 +46,7 @@ /* Offset 0x02: VTU FID Register */ #define MV88E6352_G1_VTU_FID 0x02 +#define MV88E6352_G1_VTU_FID_VID_POLICY 0x1000 #define MV88E6352_G1_VTU_FID_MASK 0x0fff /* Offset 0x03: VTU SID Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_vtu.c b/drivers/net/dsa/mv88e6xxx/global1_vtu.c index ae12c981923e..b1bd9274a562 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_vtu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_vtu.c @@ -27,7 +27,7 @@ static int mv88e6xxx_g1_vtu_fid_read(struct mv88e6xxx_chip *chip, return err; entry->fid = val & MV88E6352_G1_VTU_FID_MASK; - + entry->policy = !!(val & MV88E6352_G1_VTU_FID_VID_POLICY); return 0; } @@ -36,6 +36,9 @@ static int mv88e6xxx_g1_vtu_fid_write(struct mv88e6xxx_chip *chip, { u16 val = entry->fid & MV88E6352_G1_VTU_FID_MASK; + if (entry->policy) + val |= MV88E6352_G1_VTU_FID_VID_POLICY; + return mv88e6xxx_g1_write(chip, MV88E6352_G1_VTU_FID, val); } diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index f3e27573a386..807aeaad9830 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -299,6 +299,8 @@ #define MV88E6352_G2_SCRATCH_CONFIG_DATA1_NO_CPU BIT(2) #define MV88E6352_G2_SCRATCH_CONFIG_DATA2 0x72 #define MV88E6352_G2_SCRATCH_CONFIG_DATA2_P0_MODE_MASK 0x3 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA3 0x73 +#define MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL BIT(1) #define MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO 0 #define MV88E6352_G2_SCRATCH_GPIO_PCTL_TRIG 1 @@ -370,6 +372,7 @@ extern const struct mv88e6xxx_gpio_ops mv88e6352_gpio_ops; int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, bool external); +int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port); int mv88e6xxx_g2_atu_stats_set(struct mv88e6xxx_chip *chip, u16 kind, u16 bin); int mv88e6xxx_g2_atu_stats_get(struct mv88e6xxx_chip *chip, u16 *stats); diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c index eda710062933..a9d6e40321a2 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -289,3 +289,31 @@ int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_scratch_write(chip, misc_cfg, val); } + +/** + * mv88e6352_g2_scratch_port_has_serdes - indicate if a port can have a serdes + * @chip: chip private data + * @port: port number to check for serdes + * + * Indicates whether the port may have a serdes attached according to the + * pin strapping. Returns negative error number, 0 if the port is not + * configured to have a serdes, and 1 if the port is configured to have a + * serdes attached. + */ +int mv88e6352_g2_scratch_port_has_serdes(struct mv88e6xxx_chip *chip, int port) +{ + u8 config3, p; + int err; + + err = mv88e6xxx_g2_scratch_read(chip, MV88E6352_G2_SCRATCH_CONFIG_DATA3, + &config3); + if (err) + return err; + + if (config3 & MV88E6352_G2_SCRATCH_CONFIG_DATA3_S_SEL) + p = 5; + else + p = 4; + + return port == p; +} diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index ab41619a809b..ceb450113f88 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -1278,7 +1278,7 @@ int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, new); } -int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port) +int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map) { u16 reg; int err; @@ -1287,7 +1287,10 @@ int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port) if (err) return err; - reg |= MV88E6XXX_PORT_CTL2_MAP_DA; + if (map) + reg |= MV88E6XXX_PORT_CTL2_MAP_DA; + else + reg &= ~MV88E6XXX_PORT_CTL2_MAP_DA; return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_CTL2, reg); } diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index 03382b66f800..3a13db2ec27b 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -42,6 +42,11 @@ #define MV88E6XXX_PORT_STS_TX_PAUSED 0x0020 #define MV88E6XXX_PORT_STS_FLOW_CTL 0x0010 #define MV88E6XXX_PORT_STS_CMODE_MASK 0x000f +#define MV88E6XXX_PORT_STS_CMODE_MII_PHY 0x0001 +#define MV88E6XXX_PORT_STS_CMODE_MII 0x0002 +#define MV88E6XXX_PORT_STS_CMODE_GMII 0x0003 +#define MV88E6XXX_PORT_STS_CMODE_RMII_PHY 0x0004 +#define MV88E6XXX_PORT_STS_CMODE_RMII 0x0005 #define MV88E6XXX_PORT_STS_CMODE_RGMII 0x0007 #define MV88E6XXX_PORT_STS_CMODE_100BASEX 0x0008 #define MV88E6XXX_PORT_STS_CMODE_1000BASEX 0x0009 @@ -425,7 +430,7 @@ int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); int mv88e6xxx_port_drop_untagged(struct mv88e6xxx_chip *chip, int port, bool drop_untagged); -int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); +int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port, bool map); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); int mv88e6xxx_port_set_mirror(struct mv88e6xxx_chip *chip, int port, diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 2b05ead515cd..6a177bf654ee 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -272,14 +272,6 @@ int mv88e6352_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) return lane; } -static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port) -{ - if (mv88e6xxx_serdes_get_lane(chip, port) >= 0) - return true; - - return false; -} - struct mv88e6352_serdes_hw_stat { char string[ETH_GSTRING_LEN]; int sizeof_stat; @@ -293,20 +285,24 @@ static struct mv88e6352_serdes_hw_stat mv88e6352_serdes_hw_stats[] = { int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port) { - if (mv88e6352_port_has_serdes(chip, port)) - return ARRAY_SIZE(mv88e6352_serdes_hw_stats); + int err; - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; + + return ARRAY_SIZE(mv88e6352_serdes_hw_stats); } int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip, int port, uint8_t *data) { struct mv88e6352_serdes_hw_stat *stat; - int i; + int err, i; - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; for (i = 0; i < ARRAY_SIZE(mv88e6352_serdes_hw_stats); i++) { stat = &mv88e6352_serdes_hw_stats[i]; @@ -348,11 +344,12 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, { struct mv88e6xxx_port *mv88e6xxx_port = &chip->ports[port]; struct mv88e6352_serdes_hw_stat *stat; + int i, err; u64 value; - int i; - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) + return err; BUILD_BUG_ON(ARRAY_SIZE(mv88e6352_serdes_hw_stats) > ARRAY_SIZE(mv88e6xxx_port->serdes_stats)); @@ -419,8 +416,13 @@ unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port) int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port) { - if (!mv88e6352_port_has_serdes(chip, port)) - return 0; + int err; + + mv88e6xxx_reg_lock(chip); + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + mv88e6xxx_reg_unlock(chip); + if (err <= 0) + return err; return 32 * sizeof(u16); } @@ -432,7 +434,8 @@ void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) int err; int i; - if (!mv88e6352_port_has_serdes(chip, port)) + err = mv88e6352_g2_scratch_port_has_serdes(chip, port); + if (err <= 0) return; for (i = 0 ; i < 32; i++) { diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 282fe08db050..a990271b7482 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -55,11 +55,15 @@ static int mv88e6xxx_smi_direct_write(struct mv88e6xxx_chip *chip, static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, int dev, int reg, int bit, int val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - for (i = 0; i < 16; i++) { + /* Even if the initial poll takes longer than 50ms, always do + * at least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_smi_direct_read(chip, dev, reg, &data); if (err) return err; @@ -67,7 +71,10 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, if (!!(data & BIT(bit)) == !!val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } return -ETIMEDOUT; @@ -104,11 +111,6 @@ static int mv88e6xxx_smi_indirect_read(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_CMD, MV88E6XXX_SMI_CMD_BUSY | @@ -132,11 +134,6 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_DATA, data); if (err) @@ -155,9 +152,20 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, MV88E6XXX_SMI_CMD, 15, 0); } +static int mv88e6xxx_smi_indirect_init(struct mv88e6xxx_chip *chip) +{ + /* Ensure that the chip starts out in the ready state. As both + * reads and writes always ensure this on return, they can + * safely depend on the chip not being busy on entry. + */ + return mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, + MV88E6XXX_SMI_CMD, 15, 0); +} + static const struct mv88e6xxx_bus_ops mv88e6xxx_smi_indirect_ops = { .read = mv88e6xxx_smi_indirect_read, .write = mv88e6xxx_smi_indirect_write, + .init = mv88e6xxx_smi_indirect_init, }; int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, @@ -175,5 +183,8 @@ int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, chip->bus = bus; chip->sw_addr = sw_addr; + if (chip->smi_ops->init) + return chip->smi_ops->init(chip); + return 0; } diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index da0d7e68643a..3bda7015f0c1 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -499,52 +499,27 @@ static enum dsa_tag_protocol ar9331_sw_get_tag_protocol(struct dsa_switch *ds, return DSA_TAG_PROTO_AR9331; } -static void ar9331_sw_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void ar9331_sw_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; switch (port) { case 0: - if (state->interface != PHY_INTERFACE_MODE_GMII) - goto unsupported; - - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseT_Half); + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + config->mac_capabilities |= MAC_1000; break; case 1: case 2: case 3: case 4: case 5: - if (state->interface != PHY_INTERFACE_MODE_INTERNAL) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); break; - default: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported port: %i\n", port); - return; } - - phylink_set_port_modes(mask); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); - - return; - -unsupported: - linkmode_zero(supported); - dev_err(ds->dev, "Unsupported interface: %d, port: %d\n", - state->interface, port); } static void ar9331_sw_phylink_mac_config(struct dsa_switch *ds, int port, @@ -697,7 +672,7 @@ static const struct dsa_switch_ops ar9331_sw_ops = { .get_tag_protocol = ar9331_sw_get_tag_protocol, .setup = ar9331_sw_setup, .port_disable = ar9331_sw_port_disable, - .phylink_validate = ar9331_sw_phylink_validate, + .phylink_get_caps = ar9331_sw_phylink_get_caps, .phylink_mac_config = ar9331_sw_phylink_mac_config, .phylink_mac_link_down = ar9331_sw_phylink_mac_link_down, .phylink_mac_link_up = ar9331_sw_phylink_mac_link_up, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 039694518788..bb2fbb6826ac 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -20,6 +20,7 @@ #include <linux/phylink.h> #include <linux/gpio/consumer.h> #include <linux/etherdevice.h> +#include <linux/dsa/tag_qca.h> #include "qca8k.h" @@ -74,12 +75,6 @@ static const struct qca8k_mib_desc ar8327_mib[] = { MIB_DESC(1, 0xac, "TXUnicast"), }; -/* The 32bit switch registers are accessed indirectly. To achieve this we need - * to set the page of the register. Track the last page that was set to reduce - * mdio writes - */ -static u16 qca8k_current_page = 0xffff; - static void qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page) { @@ -94,6 +89,44 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page) } static int +qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo) +{ + u16 *cached_lo = &priv->mdio_cache.lo; + struct mii_bus *bus = priv->bus; + int ret; + + if (lo == *cached_lo) + return 0; + + ret = bus->write(bus, phy_id, regnum, lo); + if (ret < 0) + dev_err_ratelimited(&bus->dev, + "failed to write qca8k 32bit lo register\n"); + + *cached_lo = lo; + return 0; +} + +static int +qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi) +{ + u16 *cached_hi = &priv->mdio_cache.hi; + struct mii_bus *bus = priv->bus; + int ret; + + if (hi == *cached_hi) + return 0; + + ret = bus->write(bus, phy_id, regnum, hi); + if (ret < 0) + dev_err_ratelimited(&bus->dev, + "failed to write qca8k 32bit hi register\n"); + + *cached_hi = hi; + return 0; +} + +static int qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val) { int ret; @@ -116,7 +149,7 @@ qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val) } static void -qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val) +qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val) { u16 lo, hi; int ret; @@ -124,20 +157,19 @@ qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val) lo = val & 0xffff; hi = (u16)(val >> 16); - ret = bus->write(bus, phy_id, regnum, lo); + ret = qca8k_set_lo(priv, phy_id, regnum, lo); if (ret >= 0) - ret = bus->write(bus, phy_id, regnum + 1, hi); - if (ret < 0) - dev_err_ratelimited(&bus->dev, - "failed to write qca8k 32bit register\n"); + ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi); } static int -qca8k_set_page(struct mii_bus *bus, u16 page) +qca8k_set_page(struct qca8k_priv *priv, u16 page) { + u16 *cached_page = &priv->mdio_cache.page; + struct mii_bus *bus = priv->bus; int ret; - if (page == qca8k_current_page) + if (page == *cached_page) return 0; ret = bus->write(bus, 0x18, 0, page); @@ -147,7 +179,7 @@ qca8k_set_page(struct mii_bus *bus, u16 page) return ret; } - qca8k_current_page = page; + *cached_page = page; usleep_range(1000, 2000); return 0; } @@ -170,6 +202,252 @@ qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val) return regmap_update_bits(priv->regmap, reg, mask, write_val); } +static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data; + struct qca8k_priv *priv = ds->priv; + struct qca_mgmt_ethhdr *mgmt_ethhdr; + u8 len, cmd; + + mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb); + mgmt_eth_data = &priv->mgmt_eth_data; + + cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command); + len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command); + + /* Make sure the seq match the requested packet */ + if (mgmt_ethhdr->seq == mgmt_eth_data->seq) + mgmt_eth_data->ack = true; + + if (cmd == MDIO_READ) { + mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data; + + /* Get the rest of the 12 byte of data. + * The read/write function will extract the requested data. + */ + if (len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(mgmt_eth_data->data + 1, skb->data, + QCA_HDR_MGMT_DATA2_LEN); + } + + complete(&mgmt_eth_data->rw_done); +} + +static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 *val, + int priority, unsigned int len) +{ + struct qca_mgmt_ethhdr *mgmt_ethhdr; + unsigned int real_len; + struct sk_buff *skb; + u32 *data2; + u16 hdr; + + skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN); + if (!skb) + return NULL; + + /* Max value for len reg is 15 (0xf) but the switch actually return 16 byte + * Actually for some reason the steps are: + * 0: nothing + * 1-4: first 4 byte + * 5-6: first 12 byte + * 7-15: all 16 byte + */ + if (len == 16) + real_len = 15; + else + real_len = len; + + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb->len); + + mgmt_ethhdr = skb_push(skb, QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN); + + hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION); + hdr |= FIELD_PREP(QCA_HDR_XMIT_PRIORITY, priority); + hdr |= QCA_HDR_XMIT_FROM_CPU; + hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0)); + hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG); + + mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); + mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, + QCA_HDR_MGMT_CHECK_CODE_VAL); + + if (cmd == MDIO_WRITE) + mgmt_ethhdr->mdio_data = *val; + + mgmt_ethhdr->hdr = htons(hdr); + + data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN); + if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN); + + return skb; +} + +static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num) +{ + struct qca_mgmt_ethhdr *mgmt_ethhdr; + + mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data; + mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); +} + +static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data; + struct sk_buff *skb; + bool ack; + int ret; + + skb = qca8k_alloc_mdio_header(MDIO_READ, reg, NULL, + QCA8K_ETHERNET_MDIO_PRIORITY, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&mgmt_eth_data->mutex); + + /* Check mgmt_master if is operational */ + if (!priv->mgmt_master) { + kfree_skb(skb); + mutex_unlock(&mgmt_eth_data->mutex); + return -EINVAL; + } + + skb->dev = priv->mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the mdio pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + + *val = mgmt_eth_data->data[0]; + if (len > QCA_HDR_MGMT_DATA1_LEN) + memcpy(val + 1, mgmt_eth_data->data + 1, len - QCA_HDR_MGMT_DATA1_LEN); + + ack = mgmt_eth_data->ack; + + mutex_unlock(&mgmt_eth_data->mutex); + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + return 0; +} + +static int qca8k_write_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + struct qca8k_mgmt_eth_data *mgmt_eth_data = &priv->mgmt_eth_data; + struct sk_buff *skb; + bool ack; + int ret; + + skb = qca8k_alloc_mdio_header(MDIO_WRITE, reg, val, + QCA8K_ETHERNET_MDIO_PRIORITY, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&mgmt_eth_data->mutex); + + /* Check mgmt_master if is operational */ + if (!priv->mgmt_master) { + kfree_skb(skb); + mutex_unlock(&mgmt_eth_data->mutex); + return -EINVAL; + } + + skb->dev = priv->mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the mdio pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + msecs_to_jiffies(QCA8K_ETHERNET_TIMEOUT)); + + ack = mgmt_eth_data->ack; + + mutex_unlock(&mgmt_eth_data->mutex); + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + return 0; +} + +static int +qca8k_regmap_update_bits_eth(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val) +{ + u32 val = 0; + int ret; + + ret = qca8k_read_eth(priv, reg, &val, sizeof(val)); + if (ret) + return ret; + + val &= ~mask; + val |= write_val; + + return qca8k_write_eth(priv, reg, &val, sizeof(val)); +} + +static int +qca8k_bulk_read(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + int i, count = len / sizeof(u32), ret; + + if (priv->mgmt_master && !qca8k_read_eth(priv, reg, val, len)) + return 0; + + for (i = 0; i < count; i++) { + ret = regmap_read(priv->regmap, reg + (i * 4), val + i); + if (ret < 0) + return ret; + } + + return 0; +} + +static int +qca8k_bulk_write(struct qca8k_priv *priv, u32 reg, u32 *val, int len) +{ + int i, count = len / sizeof(u32), ret; + u32 tmp; + + if (priv->mgmt_master && !qca8k_write_eth(priv, reg, val, len)) + return 0; + + for (i = 0; i < count; i++) { + tmp = val[i]; + + ret = regmap_write(priv->regmap, reg + (i * 4), tmp); + if (ret < 0) + return ret; + } + + return 0; +} + static int qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val) { @@ -178,11 +456,14 @@ qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val) u16 r1, r2, page; int ret; + if (!qca8k_read_eth(priv, reg, val, sizeof(val))) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; @@ -201,15 +482,18 @@ qca8k_regmap_write(void *ctx, uint32_t reg, uint32_t val) u16 r1, r2, page; int ret; + if (!qca8k_write_eth(priv, reg, &val, sizeof(val))) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); exit: mutex_unlock(&bus->mdio_lock); @@ -225,11 +509,14 @@ qca8k_regmap_update_bits(void *ctx, uint32_t reg, uint32_t mask, uint32_t write_ u32 val; int ret; + if (!qca8k_regmap_update_bits_eth(priv, reg, mask, write_val)) + return 0; + qca8k_split_addr(reg, &r1, &r2, &page); mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret < 0) goto exit; @@ -239,7 +526,7 @@ qca8k_regmap_update_bits(void *ctx, uint32_t reg, uint32_t mask, uint32_t write_ val &= ~mask; val |= write_val; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); exit: mutex_unlock(&bus->mdio_lock); @@ -296,17 +583,13 @@ qca8k_busy_wait(struct qca8k_priv *priv, u32 reg, u32 mask) static int qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb) { - u32 reg[4], val; - int i, ret; + u32 reg[3]; + int ret; /* load the ARL table into an array */ - for (i = 0; i < 4; i++) { - ret = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4), &val); - if (ret < 0) - return ret; - - reg[i] = val; - } + ret = qca8k_bulk_read(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg)); + if (ret) + return ret; /* vid - 83:72 */ fdb->vid = FIELD_GET(QCA8K_ATU_VID_MASK, reg[2]); @@ -330,7 +613,6 @@ qca8k_fdb_write(struct qca8k_priv *priv, u16 vid, u8 port_mask, const u8 *mac, u8 aging) { u32 reg[3] = { 0 }; - int i; /* vid - 83:72 */ reg[2] = FIELD_PREP(QCA8K_ATU_VID_MASK, vid); @@ -347,8 +629,7 @@ qca8k_fdb_write(struct qca8k_priv *priv, u16 vid, u8 port_mask, const u8 *mac, reg[0] |= FIELD_PREP(QCA8K_ATU_ADDR5_MASK, mac[5]); /* load the array into the ARL table */ - for (i = 0; i < 3; i++) - qca8k_write(priv, QCA8K_REG_ATU_DATA0 + (i * 4), reg[i]); + qca8k_bulk_write(priv, QCA8K_REG_ATU_DATA0, reg, sizeof(reg)); } static int @@ -632,7 +913,10 @@ qca8k_mib_init(struct qca8k_priv *priv) int ret; mutex_lock(&priv->reg_mutex); - ret = regmap_set_bits(priv->regmap, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY); + ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB, + QCA8K_MIB_FUNC | QCA8K_MIB_BUSY, + FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_FLUSH) | + QCA8K_MIB_BUSY); if (ret) goto exit; @@ -666,6 +950,199 @@ qca8k_port_set_status(struct qca8k_priv *priv, int port, int enable) regmap_clear_bits(priv->regmap, QCA8K_REG_PORT_STATUS(port), mask); } +static int +qca8k_phy_eth_busy_wait(struct qca8k_mgmt_eth_data *mgmt_eth_data, + struct sk_buff *read_skb, u32 *val) +{ + struct sk_buff *skb = skb_copy(read_skb, GFP_KERNEL); + bool ack; + int ret; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the copy pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) + return -ETIMEDOUT; + + if (!ack) + return -EINVAL; + + *val = mgmt_eth_data->data[0]; + + return 0; +} + +static int +qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy, + int regnum, u16 data) +{ + struct sk_buff *write_skb, *clear_skb, *read_skb; + struct qca8k_mgmt_eth_data *mgmt_eth_data; + u32 write_val, clear_val = 0, val; + struct net_device *mgmt_master; + int ret, ret1; + bool ack; + + if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) + return -EINVAL; + + mgmt_eth_data = &priv->mgmt_eth_data; + + write_val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | + QCA8K_MDIO_MASTER_PHY_ADDR(phy) | + QCA8K_MDIO_MASTER_REG_ADDR(regnum); + + if (read) { + write_val |= QCA8K_MDIO_MASTER_READ; + } else { + write_val |= QCA8K_MDIO_MASTER_WRITE; + write_val |= QCA8K_MDIO_MASTER_DATA(data); + } + + /* Prealloc all the needed skb before the lock */ + write_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &write_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(write_val)); + if (!write_skb) + return -ENOMEM; + + clear_skb = qca8k_alloc_mdio_header(MDIO_WRITE, QCA8K_MDIO_MASTER_CTRL, &clear_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val)); + if (!clear_skb) { + ret = -ENOMEM; + goto err_clear_skb; + } + + read_skb = qca8k_alloc_mdio_header(MDIO_READ, QCA8K_MDIO_MASTER_CTRL, &clear_val, + QCA8K_ETHERNET_PHY_PRIORITY, sizeof(clear_val)); + if (!read_skb) { + ret = -ENOMEM; + goto err_read_skb; + } + + /* Actually start the request: + * 1. Send mdio master packet + * 2. Busy Wait for mdio master command + * 3. Get the data if we are reading + * 4. Reset the mdio master (even with error) + */ + mutex_lock(&mgmt_eth_data->mutex); + + /* Check if mgmt_master is operational */ + mgmt_master = priv->mgmt_master; + if (!mgmt_master) { + mutex_unlock(&mgmt_eth_data->mutex); + ret = -EINVAL; + goto err_mgmt_master; + } + + read_skb->dev = mgmt_master; + clear_skb->dev = mgmt_master; + write_skb->dev = mgmt_master; + + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the write pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(write_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(write_skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) { + ret = -ETIMEDOUT; + kfree_skb(read_skb); + goto exit; + } + + if (!ack) { + ret = -EINVAL; + kfree_skb(read_skb); + goto exit; + } + + ret = read_poll_timeout(qca8k_phy_eth_busy_wait, ret1, + !(val & QCA8K_MDIO_MASTER_BUSY), 0, + QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false, + mgmt_eth_data, read_skb, &val); + + if (ret < 0 && ret1 < 0) { + ret = ret1; + goto exit; + } + + if (read) { + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the read pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(read_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(read_skb); + + ret = wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + ack = mgmt_eth_data->ack; + + if (ret <= 0) { + ret = -ETIMEDOUT; + goto exit; + } + + if (!ack) { + ret = -EINVAL; + goto exit; + } + + ret = mgmt_eth_data->data[0] & QCA8K_MDIO_MASTER_DATA_MASK; + } else { + kfree_skb(read_skb); + } +exit: + reinit_completion(&mgmt_eth_data->rw_done); + + /* Increment seq_num and set it in the clear pkt */ + mgmt_eth_data->seq++; + qca8k_mdio_header_fill_seq_num(clear_skb, mgmt_eth_data->seq); + mgmt_eth_data->ack = false; + + dev_queue_xmit(clear_skb); + + wait_for_completion_timeout(&mgmt_eth_data->rw_done, + QCA8K_ETHERNET_TIMEOUT); + + mutex_unlock(&mgmt_eth_data->mutex); + + return ret; + + /* Error handling before lock */ +err_mgmt_master: + kfree_skb(read_skb); +err_read_skb: + kfree_skb(clear_skb); +err_clear_skb: + kfree_skb(write_skb); + + return ret; +} + static u32 qca8k_port_to_phy(int port) { @@ -704,8 +1181,9 @@ qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask) } static int -qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) +qca8k_mdio_write(struct qca8k_priv *priv, int phy, int regnum, u16 data) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -722,18 +1200,18 @@ qca8k_mdio_write(struct mii_bus *bus, int phy, int regnum, u16 data) mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, QCA8K_MDIO_MASTER_BUSY); exit: /* even if the busy_wait timeouts try to clear the MASTER_EN */ - qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + qca8k_mii_write32(priv, 0x10 | r2, r1, 0); mutex_unlock(&bus->mdio_lock); @@ -741,8 +1219,9 @@ exit: } static int -qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) +qca8k_mdio_read(struct qca8k_priv *priv, int phy, int regnum) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; u32 val; int ret; @@ -758,11 +1237,11 @@ qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - ret = qca8k_set_page(bus, page); + ret = qca8k_set_page(priv, page); if (ret) goto exit; - qca8k_mii_write32(bus, 0x10 | r2, r1, val); + qca8k_mii_write32(priv, 0x10 | r2, r1, val); ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, QCA8K_MDIO_MASTER_BUSY); @@ -773,7 +1252,7 @@ qca8k_mdio_read(struct mii_bus *bus, int phy, int regnum) exit: /* even if the busy_wait timeouts try to clear the MASTER_EN */ - qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + qca8k_mii_write32(priv, 0x10 | r2, r1, 0); mutex_unlock(&bus->mdio_lock); @@ -787,24 +1266,35 @@ static int qca8k_internal_mdio_write(struct mii_bus *slave_bus, int phy, int regnum, u16 data) { struct qca8k_priv *priv = slave_bus->priv; - struct mii_bus *bus = priv->bus; + int ret; - return qca8k_mdio_write(bus, phy, regnum, data); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, false, phy, regnum, data); + if (!ret) + return 0; + + return qca8k_mdio_write(priv, phy, regnum, data); } static int qca8k_internal_mdio_read(struct mii_bus *slave_bus, int phy, int regnum) { struct qca8k_priv *priv = slave_bus->priv; - struct mii_bus *bus = priv->bus; + int ret; - return qca8k_mdio_read(bus, phy, regnum); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, true, phy, regnum, 0); + if (ret >= 0) + return ret; + + return qca8k_mdio_read(priv, phy, regnum); } static int qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) { struct qca8k_priv *priv = ds->priv; + int ret; /* Check if the legacy mapping should be used and the * port is not correctly mapped to the right PHY in the @@ -813,7 +1303,12 @@ qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) if (priv->legacy_phy_port_mapping) port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; - return qca8k_mdio_write(priv->bus, port, regnum, data); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, false, port, regnum, 0); + if (!ret) + return ret; + + return qca8k_mdio_write(priv, port, regnum, data); } static int @@ -829,7 +1324,12 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum) if (priv->legacy_phy_port_mapping) port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; - ret = qca8k_mdio_read(priv->bus, port, regnum); + /* Use mdio Ethernet when available, fallback to legacy one on error */ + ret = qca8k_phy_eth_command(priv, true, port, regnum, 0); + if (ret >= 0) + return ret; + + ret = qca8k_mdio_read(priv, port, regnum); if (ret < 0) return 0xffff; @@ -1531,67 +2031,39 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, } } -static void -qca8k_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void qca8k_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - switch (port) { case 0: /* 1st CPU port */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_RGMII && - state->interface != PHY_INTERFACE_MODE_RGMII_ID && - state->interface != PHY_INTERFACE_MODE_RGMII_TXID && - state->interface != PHY_INTERFACE_MODE_RGMII_RXID && - state->interface != PHY_INTERFACE_MODE_SGMII) - goto unsupported; + phy_interface_set_rgmii(config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); break; + case 1: case 2: case 3: case 4: case 5: /* Internal PHY */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_GMII && - state->interface != PHY_INTERFACE_MODE_INTERNAL) - goto unsupported; + __set_bit(PHY_INTERFACE_MODE_GMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); break; + case 6: /* 2nd CPU port / external PHY */ - if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_RGMII && - state->interface != PHY_INTERFACE_MODE_RGMII_ID && - state->interface != PHY_INTERFACE_MODE_RGMII_TXID && - state->interface != PHY_INTERFACE_MODE_RGMII_RXID && - state->interface != PHY_INTERFACE_MODE_SGMII && - state->interface != PHY_INTERFACE_MODE_1000BASEX) - goto unsupported; + phy_interface_set_rgmii(config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + config->supported_interfaces); break; - default: -unsupported: - linkmode_zero(supported); - return; } - phylink_set_port_modes(mask); - phylink_set(mask, Autoneg); - - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - - if (state->interface == PHY_INTERFACE_MODE_1000BASEX) - phylink_set(mask, 1000baseX_Full); - - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000FD; } static int @@ -1703,6 +2175,97 @@ qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) ETH_GSTRING_LEN); } +static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *skb) +{ + const struct qca8k_match_data *match_data; + struct qca8k_mib_eth_data *mib_eth_data; + struct qca8k_priv *priv = ds->priv; + const struct qca8k_mib_desc *mib; + struct mib_ethhdr *mib_ethhdr; + int i, mib_len, offset = 0; + u64 *data; + u8 port; + + mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb); + mib_eth_data = &priv->mib_eth_data; + + /* The switch autocast every port. Ignore other packet and + * parse only the requested one. + */ + port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, ntohs(mib_ethhdr->hdr)); + if (port != mib_eth_data->req_port) + goto exit; + + match_data = device_get_match_data(priv->dev); + data = mib_eth_data->data; + + for (i = 0; i < match_data->mib_count; i++) { + mib = &ar8327_mib[i]; + + /* First 3 mib are present in the skb head */ + if (i < 3) { + data[i] = mib_ethhdr->data[i]; + continue; + } + + mib_len = sizeof(uint32_t); + + /* Some mib are 64 bit wide */ + if (mib->size == 2) + mib_len = sizeof(uint64_t); + + /* Copy the mib value from packet to the */ + memcpy(data + i, skb->data + offset, mib_len); + + /* Set the offset for the next mib */ + offset += mib_len; + } + +exit: + /* Complete on receiving all the mib packet */ + if (refcount_dec_and_test(&mib_eth_data->port_parsed)) + complete(&mib_eth_data->rw_done); +} + +static int +qca8k_get_ethtool_stats_eth(struct dsa_switch *ds, int port, u64 *data) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct qca8k_mib_eth_data *mib_eth_data; + struct qca8k_priv *priv = ds->priv; + int ret; + + mib_eth_data = &priv->mib_eth_data; + + mutex_lock(&mib_eth_data->mutex); + + reinit_completion(&mib_eth_data->rw_done); + + mib_eth_data->req_port = dp->index; + mib_eth_data->data = data; + refcount_set(&mib_eth_data->port_parsed, QCA8K_NUM_PORTS); + + mutex_lock(&priv->reg_mutex); + + /* Send mib autocast request */ + ret = regmap_update_bits(priv->regmap, QCA8K_REG_MIB, + QCA8K_MIB_FUNC | QCA8K_MIB_BUSY, + FIELD_PREP(QCA8K_MIB_FUNC, QCA8K_MIB_CAST) | + QCA8K_MIB_BUSY); + + mutex_unlock(&priv->reg_mutex); + + if (ret) + goto exit; + + ret = wait_for_completion_timeout(&mib_eth_data->rw_done, QCA8K_ETHERNET_TIMEOUT); + +exit: + mutex_unlock(&mib_eth_data->mutex); + + return ret; +} + static void qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) @@ -1714,6 +2277,10 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, u32 hi = 0; int ret; + if (priv->mgmt_master && + qca8k_get_ethtool_stats_eth(ds, port, data) > 0) + return; + match_data = of_device_get_match_data(priv->dev); for (i = 0; i < match_data->mib_count; i++) { @@ -2383,6 +2950,46 @@ qca8k_port_lag_leave(struct dsa_switch *ds, int port, return qca8k_lag_refresh_portmap(ds, port, lag, true); } +static void +qca8k_master_change(struct dsa_switch *ds, const struct net_device *master, + bool operational) +{ + struct dsa_port *dp = master->dsa_ptr; + struct qca8k_priv *priv = ds->priv; + + /* Ethernet MIB/MDIO is only supported for CPU port 0 */ + if (dp->index != 0) + return; + + mutex_lock(&priv->mgmt_eth_data.mutex); + mutex_lock(&priv->mib_eth_data.mutex); + + priv->mgmt_master = operational ? (struct net_device *)master : NULL; + + mutex_unlock(&priv->mib_eth_data.mutex); + mutex_unlock(&priv->mgmt_eth_data.mutex); +} + +static int qca8k_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) +{ + struct qca_tagger_data *tagger_data; + + switch (proto) { + case DSA_TAG_PROTO_QCA: + tagger_data = ds->tagger_data; + + tagger_data->rw_reg_ack_handler = qca8k_rw_reg_ack_handler; + tagger_data->mib_autocast_handler = qca8k_mib_autocast_handler; + + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + static const struct dsa_switch_ops qca8k_switch_ops = { .get_tag_protocol = qca8k_get_tag_protocol, .setup = qca8k_setup, @@ -2410,7 +3017,7 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .port_vlan_filtering = qca8k_port_vlan_filtering, .port_vlan_add = qca8k_port_vlan_add, .port_vlan_del = qca8k_port_vlan_del, - .phylink_validate = qca8k_phylink_validate, + .phylink_get_caps = qca8k_phylink_get_caps, .phylink_mac_link_state = qca8k_phylink_mac_link_state, .phylink_mac_config = qca8k_phylink_mac_config, .phylink_mac_link_down = qca8k_phylink_mac_link_down, @@ -2418,6 +3025,8 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .get_phy_flags = qca8k_get_phy_flags, .port_lag_join = qca8k_port_lag_join, .port_lag_leave = qca8k_port_lag_leave, + .master_state_change = qca8k_master_change, + .connect_tag_protocol = qca8k_connect_tag_protocol, }; static int qca8k_read_switch_id(struct qca8k_priv *priv) @@ -2488,6 +3097,10 @@ qca8k_sw_probe(struct mdio_device *mdiodev) return PTR_ERR(priv->regmap); } + priv->mdio_cache.page = 0xffff; + priv->mdio_cache.lo = 0xffff; + priv->mdio_cache.hi = 0xffff; + /* Check the detected switch id */ ret = qca8k_read_switch_id(priv); if (ret) @@ -2497,6 +3110,12 @@ qca8k_sw_probe(struct mdio_device *mdiodev) if (!priv->ds) return -ENOMEM; + mutex_init(&priv->mgmt_eth_data.mutex); + init_completion(&priv->mgmt_eth_data.rw_done); + + mutex_init(&priv->mib_eth_data.mutex); + init_completion(&priv->mib_eth_data.rw_done); + priv->ds->dev = &mdiodev->dev; priv->ds->num_ports = QCA8K_NUM_PORTS; priv->ds->priv = priv; diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index ab4a417b25a9..c3d3c2269b1d 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -11,6 +11,11 @@ #include <linux/delay.h> #include <linux/regmap.h> #include <linux/gpio.h> +#include <linux/dsa/tag_qca.h> + +#define QCA8K_ETHERNET_MDIO_PRIORITY 7 +#define QCA8K_ETHERNET_PHY_PRIORITY 6 +#define QCA8K_ETHERNET_TIMEOUT 100 #define QCA8K_NUM_PORTS 7 #define QCA8K_NUM_CPU_PORTS 2 @@ -63,7 +68,7 @@ #define QCA8K_REG_MODULE_EN 0x030 #define QCA8K_MODULE_EN_MIB BIT(0) #define QCA8K_REG_MIB 0x034 -#define QCA8K_MIB_FLUSH BIT(24) +#define QCA8K_MIB_FUNC GENMASK(26, 24) #define QCA8K_MIB_CPU_KEEP BIT(20) #define QCA8K_MIB_BUSY BIT(17) #define QCA8K_MDIO_MASTER_CTRL 0x3c @@ -313,6 +318,12 @@ enum qca8k_vlan_cmd { QCA8K_VLAN_READ = 6, }; +enum qca8k_mid_cmd { + QCA8K_MIB_FLUSH = 1, + QCA8K_MIB_FLUSH_PORT = 2, + QCA8K_MIB_CAST = 3, +}; + struct ar8xxx_port_status { int enabled; }; @@ -328,6 +339,22 @@ enum { QCA8K_CPU_PORT6, }; +struct qca8k_mgmt_eth_data { + struct completion rw_done; + struct mutex mutex; /* Enforce one mdio read/write at time */ + bool ack; + u32 seq; + u32 data[4]; +}; + +struct qca8k_mib_eth_data { + struct completion rw_done; + struct mutex mutex; /* Process one command at time */ + refcount_t port_parsed; /* Counter to track parsed port */ + u8 req_port; + u64 *data; /* pointer to ethtool data */ +}; + struct qca8k_ports_config { bool sgmii_rx_clk_falling_edge; bool sgmii_tx_clk_falling_edge; @@ -336,6 +363,19 @@ struct qca8k_ports_config { u8 rgmii_tx_delay[QCA8K_NUM_CPU_PORTS]; /* 0: CPU port0, 1: CPU port6 */ }; +struct qca8k_mdio_cache { +/* The 32bit switch registers are accessed indirectly. To achieve this we need + * to set the page of the register. Track the last page that was set to reduce + * mdio writes + */ + u16 page; +/* lo and hi can also be cached and from Documentation we can skip one + * extra mdio write if lo or hi is didn't change. + */ + u16 lo; + u16 hi; +}; + struct qca8k_priv { u8 switch_id; u8 switch_revision; @@ -353,6 +393,10 @@ struct qca8k_priv { struct dsa_switch_ops ops; struct gpio_desc *reset_gpio; unsigned int port_mtu[QCA8K_NUM_PORTS]; + struct net_device *mgmt_master; /* Track if mdio/mib Ethernet is available */ + struct qca8k_mgmt_eth_data mgmt_eth_data; + struct qca8k_mib_eth_data mib_eth_data; + struct qca8k_mdio_cache mdio_cache; }; struct qca8k_mib_desc { diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c deleted file mode 100644 index aae46ada8d83..000000000000 --- a/drivers/net/dsa/realtek-smi-core.c +++ /dev/null @@ -1,523 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* Realtek Simple Management Interface (SMI) driver - * It can be discussed how "simple" this interface is. - * - * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels - * but the protocol is not MDIO at all. Instead it is a Realtek - * pecularity that need to bit-bang the lines in a special way to - * communicate with the switch. - * - * ASICs we intend to support with this driver: - * - * RTL8366 - The original version, apparently - * RTL8369 - Similar enough to have the same datsheet as RTL8366 - * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite - * different register layout from the other two - * RTL8366S - Is this "RTL8366 super"? - * RTL8367 - Has an OpenWRT driver as well - * RTL8368S - Seems to be an alternative name for RTL8366RB - * RTL8370 - Also uses SMI - * - * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> - * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> - * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> - * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> - * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/device.h> -#include <linux/spinlock.h> -#include <linux/skbuff.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_mdio.h> -#include <linux/delay.h> -#include <linux/gpio/consumer.h> -#include <linux/platform_device.h> -#include <linux/regmap.h> -#include <linux/bitops.h> -#include <linux/if_bridge.h> - -#include "realtek-smi-core.h" - -#define REALTEK_SMI_ACK_RETRY_COUNT 5 -#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */ -#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */ - -static inline void realtek_smi_clk_delay(struct realtek_smi *smi) -{ - ndelay(smi->clk_delay); -} - -static void realtek_smi_start(struct realtek_smi *smi) -{ - /* Set GPIO pins to output mode, with initial state: - * SCK = 0, SDA = 1 - */ - gpiod_direction_output(smi->mdc, 0); - gpiod_direction_output(smi->mdio, 1); - realtek_smi_clk_delay(smi); - - /* CLK 1: 0 -> 1, 1 -> 0 */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - - /* CLK 2: */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 1); -} - -static void realtek_smi_stop(struct realtek_smi *smi) -{ - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 0); - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdio, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - - /* Add a click */ - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 1); - - /* Set GPIO pins to input mode */ - gpiod_direction_input(smi->mdio); - gpiod_direction_input(smi->mdc); -} - -static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len) -{ - for (; len > 0; len--) { - realtek_smi_clk_delay(smi); - - /* Prepare data */ - gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1)))); - realtek_smi_clk_delay(smi); - - /* Clocking */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - gpiod_set_value(smi->mdc, 0); - } -} - -static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data) -{ - gpiod_direction_input(smi->mdio); - - for (*data = 0; len > 0; len--) { - u32 u; - - realtek_smi_clk_delay(smi); - - /* Clocking */ - gpiod_set_value(smi->mdc, 1); - realtek_smi_clk_delay(smi); - u = !!gpiod_get_value(smi->mdio); - gpiod_set_value(smi->mdc, 0); - - *data |= (u << (len - 1)); - } - - gpiod_direction_output(smi->mdio, 0); -} - -static int realtek_smi_wait_for_ack(struct realtek_smi *smi) -{ - int retry_cnt; - - retry_cnt = 0; - do { - u32 ack; - - realtek_smi_read_bits(smi, 1, &ack); - if (ack == 0) - break; - - if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) { - dev_err(smi->dev, "ACK timeout\n"); - return -ETIMEDOUT; - } - } while (1); - - return 0; -} - -static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data) -{ - realtek_smi_write_bits(smi, data, 8); - return realtek_smi_wait_for_ack(smi); -} - -static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data) -{ - realtek_smi_write_bits(smi, data, 8); - return 0; -} - -static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data) -{ - u32 t; - - /* Read data */ - realtek_smi_read_bits(smi, 8, &t); - *data = (t & 0xff); - - /* Send an ACK */ - realtek_smi_write_bits(smi, 0x00, 1); - - return 0; -} - -static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data) -{ - u32 t; - - /* Read data */ - realtek_smi_read_bits(smi, 8, &t); - *data = (t & 0xff); - - /* Send an ACK */ - realtek_smi_write_bits(smi, 0x01, 1); - - return 0; -} - -static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data) -{ - unsigned long flags; - u8 lo = 0; - u8 hi = 0; - int ret; - - spin_lock_irqsave(&smi->lock, flags); - - realtek_smi_start(smi); - - /* Send READ command */ - ret = realtek_smi_write_byte(smi, smi->cmd_read); - if (ret) - goto out; - - /* Set ADDR[7:0] */ - ret = realtek_smi_write_byte(smi, addr & 0xff); - if (ret) - goto out; - - /* Set ADDR[15:8] */ - ret = realtek_smi_write_byte(smi, addr >> 8); - if (ret) - goto out; - - /* Read DATA[7:0] */ - realtek_smi_read_byte0(smi, &lo); - /* Read DATA[15:8] */ - realtek_smi_read_byte1(smi, &hi); - - *data = ((u32)lo) | (((u32)hi) << 8); - - ret = 0; - - out: - realtek_smi_stop(smi); - spin_unlock_irqrestore(&smi->lock, flags); - - return ret; -} - -static int realtek_smi_write_reg(struct realtek_smi *smi, - u32 addr, u32 data, bool ack) -{ - unsigned long flags; - int ret; - - spin_lock_irqsave(&smi->lock, flags); - - realtek_smi_start(smi); - - /* Send WRITE command */ - ret = realtek_smi_write_byte(smi, smi->cmd_write); - if (ret) - goto out; - - /* Set ADDR[7:0] */ - ret = realtek_smi_write_byte(smi, addr & 0xff); - if (ret) - goto out; - - /* Set ADDR[15:8] */ - ret = realtek_smi_write_byte(smi, addr >> 8); - if (ret) - goto out; - - /* Write DATA[7:0] */ - ret = realtek_smi_write_byte(smi, data & 0xff); - if (ret) - goto out; - - /* Write DATA[15:8] */ - if (ack) - ret = realtek_smi_write_byte(smi, data >> 8); - else - ret = realtek_smi_write_byte_noack(smi, data >> 8); - if (ret) - goto out; - - ret = 0; - - out: - realtek_smi_stop(smi); - spin_unlock_irqrestore(&smi->lock, flags); - - return ret; -} - -/* There is one single case when we need to use this accessor and that - * is when issueing soft reset. Since the device reset as soon as we write - * that bit, no ACK will come back for natural reasons. - */ -int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr, - u32 data) -{ - return realtek_smi_write_reg(smi, addr, data, false); -} -EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack); - -/* Regmap accessors */ - -static int realtek_smi_write(void *ctx, u32 reg, u32 val) -{ - struct realtek_smi *smi = ctx; - - return realtek_smi_write_reg(smi, reg, val, true); -} - -static int realtek_smi_read(void *ctx, u32 reg, u32 *val) -{ - struct realtek_smi *smi = ctx; - - return realtek_smi_read_reg(smi, reg, val); -} - -static const struct regmap_config realtek_smi_mdio_regmap_config = { - .reg_bits = 10, /* A4..A0 R4..R0 */ - .val_bits = 16, - .reg_stride = 1, - /* PHY regs are at 0x8000 */ - .max_register = 0xffff, - .reg_format_endian = REGMAP_ENDIAN_BIG, - .reg_read = realtek_smi_read, - .reg_write = realtek_smi_write, - .cache_type = REGCACHE_NONE, -}; - -static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum) -{ - struct realtek_smi *smi = bus->priv; - - return smi->ops->phy_read(smi, addr, regnum); -} - -static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum, - u16 val) -{ - struct realtek_smi *smi = bus->priv; - - return smi->ops->phy_write(smi, addr, regnum, val); -} - -int realtek_smi_setup_mdio(struct realtek_smi *smi) -{ - struct device_node *mdio_np; - int ret; - - mdio_np = of_get_compatible_child(smi->dev->of_node, "realtek,smi-mdio"); - if (!mdio_np) { - dev_err(smi->dev, "no MDIO bus node\n"); - return -ENODEV; - } - - smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev); - if (!smi->slave_mii_bus) { - ret = -ENOMEM; - goto err_put_node; - } - smi->slave_mii_bus->priv = smi; - smi->slave_mii_bus->name = "SMI slave MII"; - smi->slave_mii_bus->read = realtek_smi_mdio_read; - smi->slave_mii_bus->write = realtek_smi_mdio_write; - snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", - smi->ds->index); - smi->slave_mii_bus->dev.of_node = mdio_np; - smi->slave_mii_bus->parent = smi->dev; - smi->ds->slave_mii_bus = smi->slave_mii_bus; - - ret = devm_of_mdiobus_register(smi->dev, smi->slave_mii_bus, mdio_np); - if (ret) { - dev_err(smi->dev, "unable to register MDIO bus %s\n", - smi->slave_mii_bus->id); - goto err_put_node; - } - - return 0; - -err_put_node: - of_node_put(mdio_np); - - return ret; -} - -static int realtek_smi_probe(struct platform_device *pdev) -{ - const struct realtek_smi_variant *var; - struct device *dev = &pdev->dev; - struct realtek_smi *smi; - struct device_node *np; - int ret; - - var = of_device_get_match_data(dev); - np = dev->of_node; - - smi = devm_kzalloc(dev, sizeof(*smi) + var->chip_data_sz, GFP_KERNEL); - if (!smi) - return -ENOMEM; - smi->chip_data = (void *)smi + sizeof(*smi); - smi->map = devm_regmap_init(dev, NULL, smi, - &realtek_smi_mdio_regmap_config); - if (IS_ERR(smi->map)) { - ret = PTR_ERR(smi->map); - dev_err(dev, "regmap init failed: %d\n", ret); - return ret; - } - - /* Link forward and backward */ - smi->dev = dev; - smi->clk_delay = var->clk_delay; - smi->cmd_read = var->cmd_read; - smi->cmd_write = var->cmd_write; - smi->ops = var->ops; - - dev_set_drvdata(dev, smi); - spin_lock_init(&smi->lock); - - /* TODO: if power is software controlled, set up any regulators here */ - - /* Assert then deassert RESET */ - smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(smi->reset)) { - dev_err(dev, "failed to get RESET GPIO\n"); - return PTR_ERR(smi->reset); - } - msleep(REALTEK_SMI_HW_STOP_DELAY); - gpiod_set_value(smi->reset, 0); - msleep(REALTEK_SMI_HW_START_DELAY); - dev_info(dev, "deasserted RESET\n"); - - /* Fetch MDIO pins */ - smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW); - if (IS_ERR(smi->mdc)) - return PTR_ERR(smi->mdc); - smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW); - if (IS_ERR(smi->mdio)) - return PTR_ERR(smi->mdio); - - smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); - - ret = smi->ops->detect(smi); - if (ret) { - dev_err(dev, "unable to detect switch\n"); - return ret; - } - - smi->ds = devm_kzalloc(dev, sizeof(*smi->ds), GFP_KERNEL); - if (!smi->ds) - return -ENOMEM; - - smi->ds->dev = dev; - smi->ds->num_ports = smi->num_ports; - smi->ds->priv = smi; - - smi->ds->ops = var->ds_ops; - ret = dsa_register_switch(smi->ds); - if (ret) { - dev_err_probe(dev, ret, "unable to register switch\n"); - return ret; - } - return 0; -} - -static int realtek_smi_remove(struct platform_device *pdev) -{ - struct realtek_smi *smi = platform_get_drvdata(pdev); - - if (!smi) - return 0; - - dsa_unregister_switch(smi->ds); - if (smi->slave_mii_bus) - of_node_put(smi->slave_mii_bus->dev.of_node); - gpiod_set_value(smi->reset, 1); - - platform_set_drvdata(pdev, NULL); - - return 0; -} - -static void realtek_smi_shutdown(struct platform_device *pdev) -{ - struct realtek_smi *smi = platform_get_drvdata(pdev); - - if (!smi) - return; - - dsa_switch_shutdown(smi->ds); - - platform_set_drvdata(pdev, NULL); -} - -static const struct of_device_id realtek_smi_of_match[] = { - { - .compatible = "realtek,rtl8366rb", - .data = &rtl8366rb_variant, - }, - { - /* FIXME: add support for RTL8366S and more */ - .compatible = "realtek,rtl8366s", - .data = NULL, - }, - { - .compatible = "realtek,rtl8365mb", - .data = &rtl8365mb_variant, - }, - { /* sentinel */ }, -}; -MODULE_DEVICE_TABLE(of, realtek_smi_of_match); - -static struct platform_driver realtek_smi_driver = { - .driver = { - .name = "realtek-smi", - .of_match_table = of_match_ptr(realtek_smi_of_match), - }, - .probe = realtek_smi_probe, - .remove = realtek_smi_remove, - .shutdown = realtek_smi_shutdown, -}; -module_platform_driver(realtek_smi_driver); - -MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig new file mode 100644 index 000000000000..b7427a8292b2 --- /dev/null +++ b/drivers/net/dsa/realtek/Kconfig @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0-only +menuconfig NET_DSA_REALTEK + tristate "Realtek Ethernet switch family support" + depends on NET_DSA + select FIXED_PHY + select IRQ_DOMAIN + select REALTEK_PHY + select REGMAP + help + Select to enable support for Realtek Ethernet switch chips. + +config NET_DSA_REALTEK_MDIO + tristate "Realtek MDIO connected switch driver" + depends on NET_DSA_REALTEK + help + Select to enable support for registering switches configured + through MDIO. + +config NET_DSA_REALTEK_SMI + tristate "Realtek SMI connected switch driver" + depends on NET_DSA_REALTEK + help + Select to enable support for registering switches connected + through SMI. + +config NET_DSA_REALTEK_RTL8365MB + tristate "Realtek RTL8365MB switch subdriver" + depends on NET_DSA_REALTEK + depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + select NET_DSA_TAG_RTL8_4 + help + Select to enable support for Realtek RTL8365MB-VC and RTL8367S. + +config NET_DSA_REALTEK_RTL8366RB + tristate "Realtek RTL8366RB switch subdriver" + depends on NET_DSA_REALTEK + depends on NET_DSA_REALTEK_SMI || NET_DSA_REALTEK_MDIO + select NET_DSA_TAG_RTL4_A + help + Select to enable support for Realtek RTL8366RB diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile new file mode 100644 index 000000000000..0aab57252a7c --- /dev/null +++ b/drivers/net/dsa/realtek/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_NET_DSA_REALTEK_MDIO) += realtek-mdio.o +obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek-smi.o +obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o +rtl8366-objs := rtl8366-core.o rtl8366rb.o +obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o diff --git a/drivers/net/dsa/realtek/realtek-mdio.c b/drivers/net/dsa/realtek/realtek-mdio.c new file mode 100644 index 000000000000..0c5f2bdced9d --- /dev/null +++ b/drivers/net/dsa/realtek/realtek-mdio.c @@ -0,0 +1,229 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Realtek MDIO interface driver + * + * ASICs we intend to support with this driver: + * + * RTL8366 - The original version, apparently + * RTL8369 - Similar enough to have the same datsheet as RTL8366 + * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite + * different register layout from the other two + * RTL8366S - Is this "RTL8366 super"? + * RTL8367 - Has an OpenWRT driver as well + * RTL8368S - Seems to be an alternative name for RTL8366RB + * RTL8370 - Also uses SMI + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> + * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> + * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> + * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> + */ + +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> + +#include "realtek.h" + +/* Read/write via mdiobus */ +#define REALTEK_MDIO_CTRL0_REG 31 +#define REALTEK_MDIO_START_REG 29 +#define REALTEK_MDIO_CTRL1_REG 21 +#define REALTEK_MDIO_ADDRESS_REG 23 +#define REALTEK_MDIO_DATA_WRITE_REG 24 +#define REALTEK_MDIO_DATA_READ_REG 25 + +#define REALTEK_MDIO_START_OP 0xFFFF +#define REALTEK_MDIO_ADDR_OP 0x000E +#define REALTEK_MDIO_READ_OP 0x0001 +#define REALTEK_MDIO_WRITE_OP 0x0003 + +static int realtek_mdio_write(void *ctx, u32 reg, u32 val) +{ + struct realtek_priv *priv = ctx; + struct mii_bus *bus = priv->bus; + int ret; + + mutex_lock(&bus->mdio_lock); + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_DATA_WRITE_REG, val); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_WRITE_OP); + +out_unlock: + mutex_unlock(&bus->mdio_lock); + + return ret; +} + +static int realtek_mdio_read(void *ctx, u32 reg, u32 *val) +{ + struct realtek_priv *priv = ctx; + struct mii_bus *bus = priv->bus; + int ret; + + mutex_lock(&bus->mdio_lock); + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL0_REG, REALTEK_MDIO_ADDR_OP); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_ADDRESS_REG, reg); + if (ret) + goto out_unlock; + + ret = bus->write(bus, priv->mdio_addr, REALTEK_MDIO_CTRL1_REG, REALTEK_MDIO_READ_OP); + if (ret) + goto out_unlock; + + ret = bus->read(bus, priv->mdio_addr, REALTEK_MDIO_DATA_READ_REG); + if (ret >= 0) { + *val = ret; + ret = 0; + } + +out_unlock: + mutex_unlock(&bus->mdio_lock); + + return ret; +} + +static const struct regmap_config realtek_mdio_regmap_config = { + .reg_bits = 10, /* A4..A0 R4..R0 */ + .val_bits = 16, + .reg_stride = 1, + /* PHY regs are at 0x8000 */ + .max_register = 0xffff, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .reg_read = realtek_mdio_read, + .reg_write = realtek_mdio_write, + .cache_type = REGCACHE_NONE, +}; + +static int realtek_mdio_probe(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv; + struct device *dev = &mdiodev->dev; + const struct realtek_variant *var; + int ret; + struct device_node *np; + + var = of_device_get_match_data(dev); + if (!var) + return -EINVAL; + + priv = devm_kzalloc(&mdiodev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->map = devm_regmap_init(dev, NULL, priv, &realtek_mdio_regmap_config); + if (IS_ERR(priv->map)) { + ret = PTR_ERR(priv->map); + dev_err(dev, "regmap init failed: %d\n", ret); + return ret; + } + + priv->mdio_addr = mdiodev->addr; + priv->bus = mdiodev->bus; + priv->dev = &mdiodev->dev; + priv->chip_data = (void *)priv + sizeof(*priv); + + priv->clk_delay = var->clk_delay; + priv->cmd_read = var->cmd_read; + priv->cmd_write = var->cmd_write; + priv->ops = var->ops; + + priv->write_reg_noack = realtek_mdio_write; + + np = dev->of_node; + + dev_set_drvdata(dev, priv); + + /* TODO: if power is software controlled, set up any regulators here */ + priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); + + ret = priv->ops->detect(priv); + if (ret) { + dev_err(dev, "unable to detect switch\n"); + return ret; + } + + priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL); + if (!priv->ds) + return -ENOMEM; + + priv->ds->dev = dev; + priv->ds->num_ports = priv->num_ports; + priv->ds->priv = priv; + priv->ds->ops = var->ds_ops_mdio; + + ret = dsa_register_switch(priv->ds); + if (ret) { + dev_err(priv->dev, "unable to register switch ret = %d\n", ret); + return ret; + } + + return 0; +} + +static void realtek_mdio_remove(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_unregister_switch(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void realtek_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct realtek_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static const struct of_device_id realtek_mdio_of_match[] = { +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB) + { .compatible = "realtek,rtl8366rb", .data = &rtl8366rb_variant, }, +#endif +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) + { .compatible = "realtek,rtl8365mb", .data = &rtl8365mb_variant, }, + { .compatible = "realtek,rtl8367s", .data = &rtl8365mb_variant, }, +#endif + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, realtek_mdio_of_match); + +static struct mdio_driver realtek_mdio_driver = { + .mdiodrv.driver = { + .name = "realtek-mdio", + .of_match_table = of_match_ptr(realtek_mdio_of_match), + }, + .probe = realtek_mdio_probe, + .remove = realtek_mdio_remove, + .shutdown = realtek_mdio_shutdown, +}; + +mdio_module_driver(realtek_mdio_driver); + +MODULE_AUTHOR("Luiz Angelo Daros de Luca <luizluca@gmail.com>"); +MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via MDIO interface"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c new file mode 100644 index 000000000000..946fbbd70153 --- /dev/null +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -0,0 +1,535 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Realtek Simple Management Interface (SMI) driver + * It can be discussed how "simple" this interface is. + * + * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels + * but the protocol is not MDIO at all. Instead it is a Realtek + * pecularity that need to bit-bang the lines in a special way to + * communicate with the switch. + * + * ASICs we intend to support with this driver: + * + * RTL8366 - The original version, apparently + * RTL8369 - Similar enough to have the same datsheet as RTL8366 + * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite + * different register layout from the other two + * RTL8366S - Is this "RTL8366 super"? + * RTL8367 - Has an OpenWRT driver as well + * RTL8368S - Seems to be an alternative name for RTL8366RB + * RTL8370 - Also uses SMI + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com> + * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv> + * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com> + * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/spinlock.h> +#include <linux/skbuff.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_mdio.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/bitops.h> +#include <linux/if_bridge.h> + +#include "realtek.h" + +#define REALTEK_SMI_ACK_RETRY_COUNT 5 +#define REALTEK_SMI_HW_STOP_DELAY 25 /* msecs */ +#define REALTEK_SMI_HW_START_DELAY 100 /* msecs */ + +static inline void realtek_smi_clk_delay(struct realtek_priv *priv) +{ + ndelay(priv->clk_delay); +} + +static void realtek_smi_start(struct realtek_priv *priv) +{ + /* Set GPIO pins to output mode, with initial state: + * SCK = 0, SDA = 1 + */ + gpiod_direction_output(priv->mdc, 0); + gpiod_direction_output(priv->mdio, 1); + realtek_smi_clk_delay(priv); + + /* CLK 1: 0 -> 1, 1 -> 0 */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + + /* CLK 2: */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 1); +} + +static void realtek_smi_stop(struct realtek_priv *priv) +{ + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 0); + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdio, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + + /* Add a click */ + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 1); + + /* Set GPIO pins to input mode */ + gpiod_direction_input(priv->mdio); + gpiod_direction_input(priv->mdc); +} + +static void realtek_smi_write_bits(struct realtek_priv *priv, u32 data, u32 len) +{ + for (; len > 0; len--) { + realtek_smi_clk_delay(priv); + + /* Prepare data */ + gpiod_set_value(priv->mdio, !!(data & (1 << (len - 1)))); + realtek_smi_clk_delay(priv); + + /* Clocking */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + gpiod_set_value(priv->mdc, 0); + } +} + +static void realtek_smi_read_bits(struct realtek_priv *priv, u32 len, u32 *data) +{ + gpiod_direction_input(priv->mdio); + + for (*data = 0; len > 0; len--) { + u32 u; + + realtek_smi_clk_delay(priv); + + /* Clocking */ + gpiod_set_value(priv->mdc, 1); + realtek_smi_clk_delay(priv); + u = !!gpiod_get_value(priv->mdio); + gpiod_set_value(priv->mdc, 0); + + *data |= (u << (len - 1)); + } + + gpiod_direction_output(priv->mdio, 0); +} + +static int realtek_smi_wait_for_ack(struct realtek_priv *priv) +{ + int retry_cnt; + + retry_cnt = 0; + do { + u32 ack; + + realtek_smi_read_bits(priv, 1, &ack); + if (ack == 0) + break; + + if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) { + dev_err(priv->dev, "ACK timeout\n"); + return -ETIMEDOUT; + } + } while (1); + + return 0; +} + +static int realtek_smi_write_byte(struct realtek_priv *priv, u8 data) +{ + realtek_smi_write_bits(priv, data, 8); + return realtek_smi_wait_for_ack(priv); +} + +static int realtek_smi_write_byte_noack(struct realtek_priv *priv, u8 data) +{ + realtek_smi_write_bits(priv, data, 8); + return 0; +} + +static int realtek_smi_read_byte0(struct realtek_priv *priv, u8 *data) +{ + u32 t; + + /* Read data */ + realtek_smi_read_bits(priv, 8, &t); + *data = (t & 0xff); + + /* Send an ACK */ + realtek_smi_write_bits(priv, 0x00, 1); + + return 0; +} + +static int realtek_smi_read_byte1(struct realtek_priv *priv, u8 *data) +{ + u32 t; + + /* Read data */ + realtek_smi_read_bits(priv, 8, &t); + *data = (t & 0xff); + + /* Send an ACK */ + realtek_smi_write_bits(priv, 0x01, 1); + + return 0; +} + +static int realtek_smi_read_reg(struct realtek_priv *priv, u32 addr, u32 *data) +{ + unsigned long flags; + u8 lo = 0; + u8 hi = 0; + int ret; + + spin_lock_irqsave(&priv->lock, flags); + + realtek_smi_start(priv); + + /* Send READ command */ + ret = realtek_smi_write_byte(priv, priv->cmd_read); + if (ret) + goto out; + + /* Set ADDR[7:0] */ + ret = realtek_smi_write_byte(priv, addr & 0xff); + if (ret) + goto out; + + /* Set ADDR[15:8] */ + ret = realtek_smi_write_byte(priv, addr >> 8); + if (ret) + goto out; + + /* Read DATA[7:0] */ + realtek_smi_read_byte0(priv, &lo); + /* Read DATA[15:8] */ + realtek_smi_read_byte1(priv, &hi); + + *data = ((u32)lo) | (((u32)hi) << 8); + + ret = 0; + + out: + realtek_smi_stop(priv); + spin_unlock_irqrestore(&priv->lock, flags); + + return ret; +} + +static int realtek_smi_write_reg(struct realtek_priv *priv, + u32 addr, u32 data, bool ack) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&priv->lock, flags); + + realtek_smi_start(priv); + + /* Send WRITE command */ + ret = realtek_smi_write_byte(priv, priv->cmd_write); + if (ret) + goto out; + + /* Set ADDR[7:0] */ + ret = realtek_smi_write_byte(priv, addr & 0xff); + if (ret) + goto out; + + /* Set ADDR[15:8] */ + ret = realtek_smi_write_byte(priv, addr >> 8); + if (ret) + goto out; + + /* Write DATA[7:0] */ + ret = realtek_smi_write_byte(priv, data & 0xff); + if (ret) + goto out; + + /* Write DATA[15:8] */ + if (ack) + ret = realtek_smi_write_byte(priv, data >> 8); + else + ret = realtek_smi_write_byte_noack(priv, data >> 8); + if (ret) + goto out; + + ret = 0; + + out: + realtek_smi_stop(priv); + spin_unlock_irqrestore(&priv->lock, flags); + + return ret; +} + +/* There is one single case when we need to use this accessor and that + * is when issueing soft reset. Since the device reset as soon as we write + * that bit, no ACK will come back for natural reasons. + */ +static int realtek_smi_write_reg_noack(void *ctx, u32 reg, u32 val) +{ + return realtek_smi_write_reg(ctx, reg, val, false); +} + +/* Regmap accessors */ + +static int realtek_smi_write(void *ctx, u32 reg, u32 val) +{ + struct realtek_priv *priv = ctx; + + return realtek_smi_write_reg(priv, reg, val, true); +} + +static int realtek_smi_read(void *ctx, u32 reg, u32 *val) +{ + struct realtek_priv *priv = ctx; + + return realtek_smi_read_reg(priv, reg, val); +} + +static const struct regmap_config realtek_smi_mdio_regmap_config = { + .reg_bits = 10, /* A4..A0 R4..R0 */ + .val_bits = 16, + .reg_stride = 1, + /* PHY regs are at 0x8000 */ + .max_register = 0xffff, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .reg_read = realtek_smi_read, + .reg_write = realtek_smi_write, + .cache_type = REGCACHE_NONE, +}; + +static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum) +{ + struct realtek_priv *priv = bus->priv; + + return priv->ops->phy_read(priv, addr, regnum); +} + +static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct realtek_priv *priv = bus->priv; + + return priv->ops->phy_write(priv, addr, regnum, val); +} + +static int realtek_smi_setup_mdio(struct dsa_switch *ds) +{ + struct realtek_priv *priv = ds->priv; + struct device_node *mdio_np; + int ret; + + mdio_np = of_get_compatible_child(priv->dev->of_node, "realtek,smi-mdio"); + if (!mdio_np) { + dev_err(priv->dev, "no MDIO bus node\n"); + return -ENODEV; + } + + priv->slave_mii_bus = devm_mdiobus_alloc(priv->dev); + if (!priv->slave_mii_bus) { + ret = -ENOMEM; + goto err_put_node; + } + priv->slave_mii_bus->priv = priv; + priv->slave_mii_bus->name = "SMI slave MII"; + priv->slave_mii_bus->read = realtek_smi_mdio_read; + priv->slave_mii_bus->write = realtek_smi_mdio_write; + snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", + ds->index); + priv->slave_mii_bus->dev.of_node = mdio_np; + priv->slave_mii_bus->parent = priv->dev; + ds->slave_mii_bus = priv->slave_mii_bus; + + ret = devm_of_mdiobus_register(priv->dev, priv->slave_mii_bus, mdio_np); + if (ret) { + dev_err(priv->dev, "unable to register MDIO bus %s\n", + priv->slave_mii_bus->id); + goto err_put_node; + } + + return 0; + +err_put_node: + of_node_put(mdio_np); + + return ret; +} + +static int realtek_smi_probe(struct platform_device *pdev) +{ + const struct realtek_variant *var; + struct device *dev = &pdev->dev; + struct realtek_priv *priv; + struct device_node *np; + int ret; + + var = of_device_get_match_data(dev); + np = dev->of_node; + + priv = devm_kzalloc(dev, sizeof(*priv) + var->chip_data_sz, GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->chip_data = (void *)priv + sizeof(*priv); + priv->map = devm_regmap_init(dev, NULL, priv, + &realtek_smi_mdio_regmap_config); + if (IS_ERR(priv->map)) { + ret = PTR_ERR(priv->map); + dev_err(dev, "regmap init failed: %d\n", ret); + return ret; + } + + /* Link forward and backward */ + priv->dev = dev; + priv->clk_delay = var->clk_delay; + priv->cmd_read = var->cmd_read; + priv->cmd_write = var->cmd_write; + priv->ops = var->ops; + + priv->setup_interface = realtek_smi_setup_mdio; + priv->write_reg_noack = realtek_smi_write_reg_noack; + + dev_set_drvdata(dev, priv); + spin_lock_init(&priv->lock); + + /* TODO: if power is software controlled, set up any regulators here */ + + /* Assert then deassert RESET */ + priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(priv->reset)) { + dev_err(dev, "failed to get RESET GPIO\n"); + return PTR_ERR(priv->reset); + } + msleep(REALTEK_SMI_HW_STOP_DELAY); + gpiod_set_value(priv->reset, 0); + msleep(REALTEK_SMI_HW_START_DELAY); + dev_info(dev, "deasserted RESET\n"); + + /* Fetch MDIO pins */ + priv->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW); + if (IS_ERR(priv->mdc)) + return PTR_ERR(priv->mdc); + priv->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW); + if (IS_ERR(priv->mdio)) + return PTR_ERR(priv->mdio); + + priv->leds_disabled = of_property_read_bool(np, "realtek,disable-leds"); + + ret = priv->ops->detect(priv); + if (ret) { + dev_err(dev, "unable to detect switch\n"); + return ret; + } + + priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL); + if (!priv->ds) + return -ENOMEM; + + priv->ds->dev = dev; + priv->ds->num_ports = priv->num_ports; + priv->ds->priv = priv; + + priv->ds->ops = var->ds_ops_smi; + ret = dsa_register_switch(priv->ds); + if (ret) { + dev_err_probe(dev, ret, "unable to register switch\n"); + return ret; + } + return 0; +} + +static int realtek_smi_remove(struct platform_device *pdev) +{ + struct realtek_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return 0; + + dsa_unregister_switch(priv->ds); + if (priv->slave_mii_bus) + of_node_put(priv->slave_mii_bus->dev.of_node); + gpiod_set_value(priv->reset, 1); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static void realtek_smi_shutdown(struct platform_device *pdev) +{ + struct realtek_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + platform_set_drvdata(pdev, NULL); +} + +static const struct of_device_id realtek_smi_of_match[] = { +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB) + { + .compatible = "realtek,rtl8366rb", + .data = &rtl8366rb_variant, + }, +#endif + { + /* FIXME: add support for RTL8366S and more */ + .compatible = "realtek,rtl8366s", + .data = NULL, + }, +#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8365MB) + { + .compatible = "realtek,rtl8365mb", + .data = &rtl8365mb_variant, + }, + { + .compatible = "realtek,rtl8367s", + .data = &rtl8365mb_variant, + }, +#endif + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, realtek_smi_of_match); + +static struct platform_driver realtek_smi_driver = { + .driver = { + .name = "realtek-smi", + .of_match_table = of_match_ptr(realtek_smi_of_match), + }, + .probe = realtek_smi_probe, + .remove = realtek_smi_remove, + .shutdown = realtek_smi_shutdown, +}; +module_platform_driver(realtek_smi_driver); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Driver for Realtek ethernet switch connected via SMI interface"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek/realtek.h index 5bfa53e2480a..ed5abf6cb3d6 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek/realtek.h @@ -13,7 +13,7 @@ #include <linux/gpio/consumer.h> #include <net/dsa.h> -struct realtek_smi_ops; +struct realtek_ops; struct dentry; struct inode; struct file; @@ -25,7 +25,7 @@ struct rtl8366_mib_counter { const char *name; }; -/** +/* * struct rtl8366_vlan_mc - Virtual LAN member configuration */ struct rtl8366_vlan_mc { @@ -43,13 +43,15 @@ struct rtl8366_vlan_4k { u8 fid; }; -struct realtek_smi { +struct realtek_priv { struct device *dev; struct gpio_desc *reset; struct gpio_desc *mdc; struct gpio_desc *mdio; struct regmap *map; struct mii_bus *slave_mii_bus; + struct mii_bus *bus; + int mdio_addr; unsigned int clk_delay; u8 cmd_read; @@ -65,7 +67,9 @@ struct realtek_smi { unsigned int num_mib_counters; struct rtl8366_mib_counter *mib_counters; - const struct realtek_smi_ops *ops; + const struct realtek_ops *ops; + int (*setup_interface)(struct dsa_switch *ds); + int (*write_reg_noack)(void *ctx, u32 addr, u32 data); int vlan_enabled; int vlan4k_enabled; @@ -74,61 +78,57 @@ struct realtek_smi { void *chip_data; /* Per-chip extra variant data */ }; -/** - * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations +/* + * struct realtek_ops - vtable for the per-SMI-chiptype operations * @detect: detects the chiptype */ -struct realtek_smi_ops { - int (*detect)(struct realtek_smi *smi); - int (*reset_chip)(struct realtek_smi *smi); - int (*setup)(struct realtek_smi *smi); - void (*cleanup)(struct realtek_smi *smi); - int (*get_mib_counter)(struct realtek_smi *smi, +struct realtek_ops { + int (*detect)(struct realtek_priv *priv); + int (*reset_chip)(struct realtek_priv *priv); + int (*setup)(struct realtek_priv *priv); + void (*cleanup)(struct realtek_priv *priv); + int (*get_mib_counter)(struct realtek_priv *priv, int port, struct rtl8366_mib_counter *mib, u64 *mibvalue); - int (*get_vlan_mc)(struct realtek_smi *smi, u32 index, + int (*get_vlan_mc)(struct realtek_priv *priv, u32 index, struct rtl8366_vlan_mc *vlanmc); - int (*set_vlan_mc)(struct realtek_smi *smi, u32 index, + int (*set_vlan_mc)(struct realtek_priv *priv, u32 index, const struct rtl8366_vlan_mc *vlanmc); - int (*get_vlan_4k)(struct realtek_smi *smi, u32 vid, + int (*get_vlan_4k)(struct realtek_priv *priv, u32 vid, struct rtl8366_vlan_4k *vlan4k); - int (*set_vlan_4k)(struct realtek_smi *smi, + int (*set_vlan_4k)(struct realtek_priv *priv, const struct rtl8366_vlan_4k *vlan4k); - int (*get_mc_index)(struct realtek_smi *smi, int port, int *val); - int (*set_mc_index)(struct realtek_smi *smi, int port, int index); - bool (*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan); - int (*enable_vlan)(struct realtek_smi *smi, bool enable); - int (*enable_vlan4k)(struct realtek_smi *smi, bool enable); - int (*enable_port)(struct realtek_smi *smi, int port, bool enable); - int (*phy_read)(struct realtek_smi *smi, int phy, int regnum); - int (*phy_write)(struct realtek_smi *smi, int phy, int regnum, + int (*get_mc_index)(struct realtek_priv *priv, int port, int *val); + int (*set_mc_index)(struct realtek_priv *priv, int port, int index); + bool (*is_vlan_valid)(struct realtek_priv *priv, unsigned int vlan); + int (*enable_vlan)(struct realtek_priv *priv, bool enable); + int (*enable_vlan4k)(struct realtek_priv *priv, bool enable); + int (*enable_port)(struct realtek_priv *priv, int port, bool enable); + int (*phy_read)(struct realtek_priv *priv, int phy, int regnum); + int (*phy_write)(struct realtek_priv *priv, int phy, int regnum, u16 val); }; -struct realtek_smi_variant { - const struct dsa_switch_ops *ds_ops; - const struct realtek_smi_ops *ops; +struct realtek_variant { + const struct dsa_switch_ops *ds_ops_smi; + const struct dsa_switch_ops *ds_ops_mdio; + const struct realtek_ops *ops; unsigned int clk_delay; u8 cmd_read; u8 cmd_write; size_t chip_data_sz; }; -/* SMI core calls */ -int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr, - u32 data); -int realtek_smi_setup_mdio(struct realtek_smi *smi); - /* RTL8366 library helpers */ -int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used); -int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, +int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used); +int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member, u32 untag, u32 fid); -int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, +int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port, unsigned int vid); -int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable); -int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable); -int rtl8366_reset_vlan(struct realtek_smi *smi); +int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable); +int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable); +int rtl8366_reset_vlan(struct realtek_priv *priv); int rtl8366_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); @@ -139,7 +139,7 @@ void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset, int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); -extern const struct realtek_smi_variant rtl8366rb_variant; -extern const struct realtek_smi_variant rtl8365mb_variant; +extern const struct realtek_variant rtl8366rb_variant; +extern const struct realtek_variant rtl8365mb_variant; #endif /* _REALTEK_SMI_H */ diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index 3b729544798b..2ed592147c20 100644 --- a/drivers/net/dsa/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -99,18 +99,28 @@ #include <linux/regmap.h> #include <linux/if_bridge.h> -#include "realtek-smi-core.h" +#include "realtek.h" /* Chip-specific data and limits */ -#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 -#define RTL8365MB_CPU_PORT_NUM_8365MB_VC 6 -#define RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC 2112 +#define RTL8365MB_CHIP_ID_8365MB_VC 0x6367 +#define RTL8365MB_CHIP_VER_8365MB_VC 0x0040 + +#define RTL8365MB_CHIP_ID_8367S 0x6367 +#define RTL8365MB_CHIP_VER_8367S 0x00A0 + +#define RTL8365MB_CHIP_ID_8367RB 0x6367 +#define RTL8365MB_CHIP_VER_8367RB 0x0020 /* Family-specific data and limits */ -#define RTL8365MB_PHYADDRMAX 7 -#define RTL8365MB_NUM_PHYREGS 32 -#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) -#define RTL8365MB_MAX_NUM_PORTS (RTL8365MB_CPU_PORT_NUM_8365MB_VC + 1) +#define RTL8365MB_PHYADDRMAX 7 +#define RTL8365MB_NUM_PHYREGS 32 +#define RTL8365MB_PHYREGMAX (RTL8365MB_NUM_PHYREGS - 1) +/* RTL8370MB and RTL8310SR, possibly suportable by this driver, have 10 ports */ +#define RTL8365MB_MAX_NUM_PORTS 10 +#define RTL8365MB_LEARN_LIMIT_MAX 2112 + +/* valid for all 6-port or less variants */ +static const int rtl8365mb_extint_port_map[] = { -1, -1, -1, -1, -1, -1, 1, 2, -1, -1}; /* Chip identification registers */ #define RTL8365MB_CHIP_ID_REG 0x1300 @@ -191,7 +201,7 @@ /* The PHY OCP addresses of PHY registers 0~31 start here */ #define RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE 0xA400 -/* EXT port interface mode values - used in DIGITAL_INTERFACE_SELECT */ +/* EXT interface port mode values - used in DIGITAL_INTERFACE_SELECT */ #define RTL8365MB_EXT_PORT_MODE_DISABLE 0 #define RTL8365MB_EXT_PORT_MODE_RGMII 1 #define RTL8365MB_EXT_PORT_MODE_MII_MAC 2 @@ -207,39 +217,56 @@ #define RTL8365MB_EXT_PORT_MODE_1000X 12 #define RTL8365MB_EXT_PORT_MODE_100FX 13 -/* EXT port interface mode configuration registers 0~1 */ -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extport) \ - (RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 + \ - ((_extport) >> 1) * (0x13C3 - 0x1305)) -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extport) \ - (0xF << (((_extport) % 2))) -#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extport) \ - (((_extport) % 2) * 4) - -/* EXT port RGMII TX/RX delay configuration registers 1~2 */ -#define RTL8365MB_EXT_RGMXF_REG1 0x1307 -#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 -#define RTL8365MB_EXT_RGMXF_REG(_extport) \ - (RTL8365MB_EXT_RGMXF_REG1 + \ - (((_extport) >> 1) * (0x13C5 - 0x1307))) +/* Realtek docs and driver uses logic number as EXT_PORT0=16, EXT_PORT1=17, + * EXT_PORT2=18, to interact with switch ports. That logic number is internally + * converted to either a physical port number (0..9) or an external interface id (0..2), + * depending on which function was called. The external interface id is calculated as + * (ext_id=logic_port-15), while the logical to physical map depends on the chip id/version. + * + * EXT_PORT0 mentioned in datasheets and rtl8367c driver is used in this driver + * as extid==1, EXT_PORT2, mentioned in Realtek rtl8367c driver for 10-port switches, + * would have an ext_id of 3 (out of range for most extint macros) and ext_id 0 does + * not seem to be used as well for this family. + */ + +/* EXT interface mode configuration registers 0~1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 0x1305 /* EXT1 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 0x13C3 /* EXT2 */ +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(_extint) \ + ((_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG0 : \ + (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_SELECT_REG1 : \ + 0x0) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(_extint) \ + (0xF << (((_extint) % 2))) +#define RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET(_extint) \ + (((_extint) % 2) * 4) + +/* EXT interface RGMII TX/RX delay configuration registers 0~2 */ +#define RTL8365MB_EXT_RGMXF_REG0 0x1306 /* EXT0 */ +#define RTL8365MB_EXT_RGMXF_REG1 0x1307 /* EXT1 */ +#define RTL8365MB_EXT_RGMXF_REG2 0x13C5 /* EXT2 */ +#define RTL8365MB_EXT_RGMXF_REG(_extint) \ + ((_extint) == 0 ? RTL8365MB_EXT_RGMXF_REG0 : \ + (_extint) == 1 ? RTL8365MB_EXT_RGMXF_REG1 : \ + (_extint) == 2 ? RTL8365MB_EXT_RGMXF_REG2 : \ + 0x0) #define RTL8365MB_EXT_RGMXF_RXDELAY_MASK 0x0007 #define RTL8365MB_EXT_RGMXF_TXDELAY_MASK 0x0008 -/* External port speed values - used in DIGITAL_INTERFACE_FORCE */ +/* External interface port speed values - used in DIGITAL_INTERFACE_FORCE */ #define RTL8365MB_PORT_SPEED_10M 0 #define RTL8365MB_PORT_SPEED_100M 1 #define RTL8365MB_PORT_SPEED_1000M 2 -/* EXT port force configuration registers 0~2 */ -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 -#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extport) \ - (RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 + \ - ((_extport) & 0x1) + \ - ((((_extport) >> 1) & 0x1) * (0x13C4 - 0x1310))) +/* EXT interface force configuration registers 0~2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 0x1310 /* EXT0 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 0x1311 /* EXT1 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 0x13C4 /* EXT2 */ +#define RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(_extint) \ + ((_extint) == 0 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG0 : \ + (_extint) == 1 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG1 : \ + (_extint) == 2 ? RTL8365MB_DIGITAL_INTERFACE_FORCE_REG2 : \ + 0x0) #define RTL8365MB_DIGITAL_INTERFACE_FORCE_EN_MASK 0x1000 #define RTL8365MB_DIGITAL_INTERFACE_FORCE_NWAY_MASK 0x0080 #define RTL8365MB_DIGITAL_INTERFACE_FORCE_TXPAUSE_MASK 0x0040 @@ -516,7 +543,7 @@ struct rtl8365mb_cpu { /** * struct rtl8365mb_port - private per-port data - * @smi: pointer to parent realtek_smi data + * @priv: pointer to parent realtek_priv data * @index: DSA port index, same as dsa_port::index * @stats: link statistics populated by rtl8365mb_stats_poll, ready for atomic * access via rtl8365mb_get_stats64 @@ -524,7 +551,7 @@ struct rtl8365mb_cpu { * @mib_work: delayed work for polling MIB counters */ struct rtl8365mb_port { - struct realtek_smi *smi; + struct realtek_priv *priv; unsigned int index; struct rtnl_link_stats64 stats; spinlock_t stats_lock; @@ -533,13 +560,12 @@ struct rtl8365mb_port { /** * struct rtl8365mb - private chip-specific driver data - * @smi: pointer to parent realtek_smi data + * @priv: pointer to parent realtek_priv data * @irq: registered IRQ or zero * @chip_id: chip identifier * @chip_ver: chip silicon revision * @port_mask: mask of all ports * @learn_limit_max: maximum number of L2 addresses the chip can learn - * @cpu: CPU tagging and CPU port configuration for this chip * @mib_lock: prevent concurrent reads of MIB counters * @ports: per-port data * @jam_table: chip-specific initialization jam table @@ -548,29 +574,28 @@ struct rtl8365mb_port { * Private data for this driver. */ struct rtl8365mb { - struct realtek_smi *smi; + struct realtek_priv *priv; int irq; u32 chip_id; u32 chip_ver; u32 port_mask; u32 learn_limit_max; - struct rtl8365mb_cpu cpu; struct mutex mib_lock; struct rtl8365mb_port ports[RTL8365MB_MAX_NUM_PORTS]; const struct rtl8365mb_jam_tbl_entry *jam_table; size_t jam_size; }; -static int rtl8365mb_phy_poll_busy(struct realtek_smi *smi) +static int rtl8365mb_phy_poll_busy(struct realtek_priv *priv) { u32 val; - return regmap_read_poll_timeout(smi->map, + return regmap_read_poll_timeout(priv->map, RTL8365MB_INDIRECT_ACCESS_STATUS_REG, val, !val, 10, 100); } -static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_prepare(struct realtek_priv *priv, int phy, u32 ocp_addr) { u32 val; @@ -579,7 +604,7 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, /* Set OCP prefix */ val = FIELD_GET(RTL8365MB_PHY_OCP_ADDR_PREFIX_MASK, ocp_addr); ret = regmap_update_bits( - smi->map, RTL8365MB_GPHY_OCP_MSB_0_REG, + priv->map, RTL8365MB_GPHY_OCP_MSB_0_REG, RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, FIELD_PREP(RTL8365MB_GPHY_OCP_MSB_0_CFG_CPU_OCPADR_MASK, val)); if (ret) @@ -592,7 +617,7 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, ocp_addr >> 1); val |= FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_ADDRESS_OCPADR_9_6_MASK, ocp_addr >> 6); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_ADDRESS_REG, val); if (ret) return ret; @@ -600,17 +625,17 @@ static int rtl8365mb_phy_ocp_prepare(struct realtek_smi *smi, int phy, return 0; } -static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_read(struct realtek_priv *priv, int phy, u32 ocp_addr, u16 *data) { u32 val; int ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; - ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr); if (ret) return ret; @@ -619,16 +644,16 @@ static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, RTL8365MB_INDIRECT_ACCESS_CTRL_RW_READ); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); if (ret) return ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; /* Get PHY register data */ - ret = regmap_read(smi->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, + ret = regmap_read(priv->map, RTL8365MB_INDIRECT_ACCESS_READ_DATA_REG, &val); if (ret) return ret; @@ -638,22 +663,22 @@ static int rtl8365mb_phy_ocp_read(struct realtek_smi *smi, int phy, return 0; } -static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, +static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, u32 ocp_addr, u16 data) { u32 val; int ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; - ret = rtl8365mb_phy_ocp_prepare(smi, phy, ocp_addr); + ret = rtl8365mb_phy_ocp_prepare(priv, phy, ocp_addr); if (ret) return ret; /* Set PHY register data */ - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_WRITE_DATA_REG, data); if (ret) return ret; @@ -663,18 +688,18 @@ static int rtl8365mb_phy_ocp_write(struct realtek_smi *smi, int phy, RTL8365MB_INDIRECT_ACCESS_CTRL_CMD_VALUE) | FIELD_PREP(RTL8365MB_INDIRECT_ACCESS_CTRL_RW_MASK, RTL8365MB_INDIRECT_ACCESS_CTRL_RW_WRITE); - ret = regmap_write(smi->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); + ret = regmap_write(priv->map, RTL8365MB_INDIRECT_ACCESS_CTRL_REG, val); if (ret) return ret; - ret = rtl8365mb_phy_poll_busy(smi); + ret = rtl8365mb_phy_poll_busy(priv); if (ret) return ret; return 0; } -static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) +static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum) { u32 ocp_addr; u16 val; @@ -688,21 +713,21 @@ static int rtl8365mb_phy_read(struct realtek_smi *smi, int phy, int regnum) ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; - ret = rtl8365mb_phy_ocp_read(smi, phy, ocp_addr, &val); + ret = rtl8365mb_phy_ocp_read(priv, phy, ocp_addr, &val); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to read PHY%d reg %02x @ %04x, ret %d\n", phy, regnum, ocp_addr, ret); return ret; } - dev_dbg(smi->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", + dev_dbg(priv->dev, "read PHY%d register 0x%02x @ %04x, val <- %04x\n", phy, regnum, ocp_addr, val); return val; } -static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, +static int rtl8365mb_phy_write(struct realtek_priv *priv, int phy, int regnum, u16 val) { u32 ocp_addr; @@ -716,20 +741,31 @@ static int rtl8365mb_phy_write(struct realtek_smi *smi, int phy, int regnum, ocp_addr = RTL8365MB_PHY_OCP_ADDR_PHYREG_BASE + regnum * 2; - ret = rtl8365mb_phy_ocp_write(smi, phy, ocp_addr, val); + ret = rtl8365mb_phy_ocp_write(priv, phy, ocp_addr, val); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to write PHY%d reg %02x @ %04x, ret %d\n", phy, regnum, ocp_addr, ret); return ret; } - dev_dbg(smi->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", + dev_dbg(priv->dev, "write PHY%d register 0x%02x @ %04x, val -> %04x\n", phy, regnum, ocp_addr, val); return 0; } +static int rtl8365mb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum) +{ + return rtl8365mb_phy_read(ds->priv, phy, regnum); +} + +static int rtl8365mb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum, + u16 val) +{ + return rtl8365mb_phy_write(ds->priv, phy, regnum, val); +} + static enum dsa_tag_protocol rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -737,25 +773,25 @@ rtl8365mb_get_tag_protocol(struct dsa_switch *ds, int port, return DSA_TAG_PROTO_RTL8_4; } -static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, +static int rtl8365mb_ext_config_rgmii(struct realtek_priv *priv, int port, phy_interface_t interface) { struct device_node *dn; struct dsa_port *dp; int tx_delay = 0; int rx_delay = 0; - int ext_port; + int ext_int; u32 val; int ret; - if (port == smi->cpu_port) { - ext_port = 1; - } else { - dev_err(smi->dev, "only one EXT port is currently supported\n"); + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int <= 0) { + dev_err(priv->dev, "Port %d is not an external interface port\n", port); return -EINVAL; } - dp = dsa_to_port(smi->ds, port); + dp = dsa_to_port(priv->ds, port); dn = dp->dn; /* Set the RGMII TX/RX delay @@ -786,8 +822,8 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, if (val == 0 || val == 2) tx_delay = val / 2; else - dev_warn(smi->dev, - "EXT port TX delay must be 0 or 2 ns\n"); + dev_warn(priv->dev, + "EXT interface TX delay must be 0 or 2 ns\n"); } if (!of_property_read_u32(dn, "rx-internal-delay-ps", &val)) { @@ -796,12 +832,12 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, if (val <= 7) rx_delay = val; else - dev_warn(smi->dev, - "EXT port RX delay must be 0 to 2.1 ns\n"); + dev_warn(priv->dev, + "EXT interface RX delay must be 0 to 2.1 ns\n"); } ret = regmap_update_bits( - smi->map, RTL8365MB_EXT_RGMXF_REG(ext_port), + priv->map, RTL8365MB_EXT_RGMXF_REG(ext_int), RTL8365MB_EXT_RGMXF_TXDELAY_MASK | RTL8365MB_EXT_RGMXF_RXDELAY_MASK, FIELD_PREP(RTL8365MB_EXT_RGMXF_TXDELAY_MASK, tx_delay) | @@ -810,18 +846,18 @@ static int rtl8365mb_ext_config_rgmii(struct realtek_smi *smi, int port, return ret; ret = regmap_update_bits( - smi->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_port), - RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_port), + priv->map, RTL8365MB_DIGITAL_INTERFACE_SELECT_REG(ext_int), + RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_MASK(ext_int), RTL8365MB_EXT_PORT_MODE_RGMII << RTL8365MB_DIGITAL_INTERFACE_SELECT_MODE_OFFSET( - ext_port)); + ext_int)); if (ret) return ret; return 0; } -static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, +static int rtl8365mb_ext_config_forcemode(struct realtek_priv *priv, int port, bool link, int speed, int duplex, bool tx_pause, bool rx_pause) { @@ -830,14 +866,14 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, u32 r_duplex; u32 r_speed; u32 r_link; - int ext_port; + int ext_int; int val; int ret; - if (port == smi->cpu_port) { - ext_port = 1; - } else { - dev_err(smi->dev, "only one EXT port is currently supported\n"); + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int <= 0) { + dev_err(priv->dev, "Port %d is not an external interface port\n", port); return -EINVAL; } @@ -854,7 +890,7 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, } else if (speed == SPEED_10) { r_speed = RTL8365MB_PORT_SPEED_10M; } else { - dev_err(smi->dev, "unsupported port speed %s\n", + dev_err(priv->dev, "unsupported port speed %s\n", phy_speed_to_str(speed)); return -EINVAL; } @@ -864,7 +900,7 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, } else if (duplex == DUPLEX_HALF) { r_duplex = 0; } else { - dev_err(smi->dev, "unsupported duplex %s\n", + dev_err(priv->dev, "unsupported duplex %s\n", phy_duplex_to_str(duplex)); return -EINVAL; } @@ -886,8 +922,8 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_DUPLEX_MASK, r_duplex) | FIELD_PREP(RTL8365MB_DIGITAL_INTERFACE_FORCE_SPEED_MASK, r_speed); - ret = regmap_write(smi->map, - RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_port), + ret = regmap_write(priv->map, + RTL8365MB_DIGITAL_INTERFACE_FORCE_REG(ext_int), val); if (ret) return ret; @@ -898,13 +934,17 @@ static int rtl8365mb_ext_config_forcemode(struct realtek_smi *smi, int port, static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, phy_interface_t interface) { - if (dsa_is_user_port(ds, port) && + int ext_int; + + ext_int = rtl8365mb_extint_port_map[port]; + + if (ext_int < 0 && (interface == PHY_INTERFACE_MODE_NA || interface == PHY_INTERFACE_MODE_INTERNAL || interface == PHY_INTERFACE_MODE_GMII)) /* Internal PHY */ return true; - else if (dsa_is_cpu_port(ds, port) && + else if ((ext_int >= 1) && phy_interface_mode_is_rgmii(interface)) /* Extension MAC */ return true; @@ -912,65 +952,43 @@ static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, return false; } -static void rtl8365mb_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void rtl8365mb_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - struct realtek_smi *smi = ds->priv; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0 }; - - /* include/linux/phylink.h says: - * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink - * expects the MAC driver to return all supported link modes. - */ - if (state->interface != PHY_INTERFACE_MODE_NA && - !rtl8365mb_phy_mode_supported(ds, port, state->interface)) { - dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", - phy_modes(state->interface), port); - linkmode_zero(supported); - return; - } - - phylink_set_port_modes(mask); - - phylink_set(mask, Autoneg); - phylink_set(mask, Pause); - phylink_set(mask, Asym_Pause); - - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 100baseT_Full); - phylink_set(mask, 1000baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + if (dsa_is_user_port(ds, port)) + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + else if (dsa_is_cpu_port(ds, port)) + phy_interface_set_rgmii(config->supported_interfaces); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000FD; } static void rtl8365mb_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; if (!rtl8365mb_phy_mode_supported(ds, port, state->interface)) { - dev_err(smi->dev, "phy mode %s is unsupported on port %d\n", + dev_err(priv->dev, "phy mode %s is unsupported on port %d\n", phy_modes(state->interface), port); return; } if (mode != MLO_AN_PHY && mode != MLO_AN_FIXED) { - dev_err(smi->dev, + dev_err(priv->dev, "port %d supports only conventional PHY or fixed-link\n", port); return; } if (phy_interface_mode_is_rgmii(state->interface)) { - ret = rtl8365mb_ext_config_rgmii(smi, port, state->interface); + ret = rtl8365mb_ext_config_rgmii(priv, port, state->interface); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to configure RGMII mode on port %d: %d\n", port, ret); return; @@ -985,20 +1003,20 @@ static void rtl8365mb_phylink_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; int ret; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; cancel_delayed_work_sync(&p->mib_work); if (phy_interface_mode_is_rgmii(interface)) { - ret = rtl8365mb_ext_config_forcemode(smi, port, false, 0, 0, + ret = rtl8365mb_ext_config_forcemode(priv, port, false, 0, 0, false, false); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to reset forced mode on port %d: %d\n", port, ret); @@ -1013,21 +1031,21 @@ static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, int duplex, bool tx_pause, bool rx_pause) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; int ret; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; schedule_delayed_work(&p->mib_work, 0); if (phy_interface_mode_is_rgmii(interface)) { - ret = rtl8365mb_ext_config_forcemode(smi, port, true, speed, + ret = rtl8365mb_ext_config_forcemode(priv, port, true, speed, duplex, tx_pause, rx_pause); if (ret) - dev_err(smi->dev, + dev_err(priv->dev, "failed to force mode on port %d: %d\n", port, ret); @@ -1038,7 +1056,7 @@ static void rtl8365mb_phylink_mac_link_up(struct dsa_switch *ds, int port, static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; enum rtl8365mb_stp_state val; int msti = 0; @@ -1057,36 +1075,36 @@ static void rtl8365mb_port_stp_state_set(struct dsa_switch *ds, int port, val = RTL8365MB_STP_STATE_FORWARDING; break; default: - dev_err(smi->dev, "invalid STP state: %u\n", state); + dev_err(priv->dev, "invalid STP state: %u\n", state); return; } - regmap_update_bits(smi->map, RTL8365MB_MSTI_CTRL_REG(msti, port), + regmap_update_bits(priv->map, RTL8365MB_MSTI_CTRL_REG(msti, port), RTL8365MB_MSTI_CTRL_PORT_STATE_MASK(port), val << RTL8365MB_MSTI_CTRL_PORT_STATE_OFFSET(port)); } -static int rtl8365mb_port_set_learning(struct realtek_smi *smi, int port, +static int rtl8365mb_port_set_learning(struct realtek_priv *priv, int port, bool enable) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; /* Enable/disable learning by limiting the number of L2 addresses the * port can learn. Realtek documentation states that a limit of zero * disables learning. When enabling learning, set it to the chip's * maximum. */ - return regmap_write(smi->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), + return regmap_write(priv->map, RTL8365MB_LUT_PORT_LEARN_LIMIT_REG(port), enable ? mb->learn_limit_max : 0); } -static int rtl8365mb_port_set_isolation(struct realtek_smi *smi, int port, +static int rtl8365mb_port_set_isolation(struct realtek_priv *priv, int port, u32 mask) { - return regmap_write(smi->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); + return regmap_write(priv->map, RTL8365MB_PORT_ISOLATION_REG(port), mask); } -static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, +static int rtl8365mb_mib_counter_read(struct realtek_priv *priv, int port, u32 offset, u32 length, u64 *mibvalue) { u64 tmpvalue = 0; @@ -1098,13 +1116,13 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, * and then poll the control register before reading the value from some * counter registers. */ - ret = regmap_write(smi->map, RTL8365MB_MIB_ADDRESS_REG, + ret = regmap_write(priv->map, RTL8365MB_MIB_ADDRESS_REG, RTL8365MB_MIB_ADDRESS(port, offset)); if (ret) return ret; /* Poll for completion */ - ret = regmap_read_poll_timeout(smi->map, RTL8365MB_MIB_CTRL0_REG, val, + ret = regmap_read_poll_timeout(priv->map, RTL8365MB_MIB_CTRL0_REG, val, !(val & RTL8365MB_MIB_CTRL0_BUSY_MASK), 10, 100); if (ret) @@ -1126,7 +1144,7 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, /* Read the MIB counter 16 bits at a time */ for (i = 0; i < length; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8365MB_MIB_COUNTER_REG(offset - i), &val); if (ret) return ret; @@ -1142,21 +1160,21 @@ static int rtl8365mb_mib_counter_read(struct realtek_smi *smi, int port, static void rtl8365mb_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; mutex_lock(&mb->mib_lock); for (i = 0; i < RTL8365MB_MIB_END; i++) { struct rtl8365mb_mib_counter *mib = &rtl8365mb_mib_counters[i]; - ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + ret = rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &data[i]); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to read port %d counters: %d\n", port, ret); break; @@ -1190,15 +1208,15 @@ static int rtl8365mb_get_sset_count(struct dsa_switch *ds, int port, int sset) static void rtl8365mb_get_phy_stats(struct dsa_switch *ds, int port, struct ethtool_eth_phy_stats *phy_stats) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_mib_counter *mib; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3StatsSymbolErrors]; mutex_lock(&mb->mib_lock); - rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &phy_stats->SymbolErrorDuringCarrier); mutex_unlock(&mb->mib_lock); } @@ -1226,12 +1244,12 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, [RTL8365MB_MIB_dot3StatsExcessiveCollisions] = 1, }; - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; mutex_lock(&mb->mib_lock); for (i = 0; i < RTL8365MB_MIB_END; i++) { @@ -1241,7 +1259,7 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, if (!cnt[i]) continue; - ret = rtl8365mb_mib_counter_read(smi, port, mib->offset, + ret = rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &cnt[i]); if (ret) break; @@ -1291,20 +1309,20 @@ static void rtl8365mb_get_mac_stats(struct dsa_switch *ds, int port, static void rtl8365mb_get_ctrl_stats(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_mib_counter *mib; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; mib = &rtl8365mb_mib_counters[RTL8365MB_MIB_dot3ControlInUnknownOpcodes]; mutex_lock(&mb->mib_lock); - rtl8365mb_mib_counter_read(smi, port, mib->offset, mib->length, + rtl8365mb_mib_counter_read(priv, port, mib->offset, mib->length, &ctrl_stats->UnsupportedOpcodesReceived); mutex_unlock(&mb->mib_lock); } -static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) +static void rtl8365mb_stats_update(struct realtek_priv *priv, int port) { u64 cnt[RTL8365MB_MIB_END] = { [RTL8365MB_MIB_ifOutOctets] = 1, @@ -1323,7 +1341,7 @@ static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) [RTL8365MB_MIB_dot3StatsFCSErrors] = 1, [RTL8365MB_MIB_dot3StatsLateCollisions] = 1, }; - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; struct rtnl_link_stats64 *stats; int ret; int i; @@ -1338,7 +1356,7 @@ static void rtl8365mb_stats_update(struct realtek_smi *smi, int port) if (!cnt[i]) continue; - ret = rtl8365mb_mib_counter_read(smi, port, c->offset, + ret = rtl8365mb_mib_counter_read(priv, port, c->offset, c->length, &cnt[i]); if (ret) break; @@ -1388,9 +1406,9 @@ static void rtl8365mb_stats_poll(struct work_struct *work) struct rtl8365mb_port *p = container_of(to_delayed_work(work), struct rtl8365mb_port, mib_work); - struct realtek_smi *smi = p->smi; + struct realtek_priv *priv = p->priv; - rtl8365mb_stats_update(smi, p->index); + rtl8365mb_stats_update(priv, p->index); schedule_delayed_work(&p->mib_work, RTL8365MB_STATS_INTERVAL_JIFFIES); } @@ -1398,11 +1416,11 @@ static void rtl8365mb_stats_poll(struct work_struct *work) static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8365mb_port *p; struct rtl8365mb *mb; - mb = smi->chip_data; + mb = priv->chip_data; p = &mb->ports[port]; spin_lock(&p->stats_lock); @@ -1410,9 +1428,9 @@ static void rtl8365mb_get_stats64(struct dsa_switch *ds, int port, spin_unlock(&p->stats_lock); } -static void rtl8365mb_stats_setup(struct realtek_smi *smi) +static void rtl8365mb_stats_setup(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int i; /* Per-chip global mutex to protect MIB counter access, since doing @@ -1420,10 +1438,10 @@ static void rtl8365mb_stats_setup(struct realtek_smi *smi) */ mutex_init(&mb->mib_lock); - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; /* Per-port spinlock to protect the stats64 data */ @@ -1436,45 +1454,45 @@ static void rtl8365mb_stats_setup(struct realtek_smi *smi) } } -static void rtl8365mb_stats_teardown(struct realtek_smi *smi) +static void rtl8365mb_stats_teardown(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int i; - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; cancel_delayed_work_sync(&p->mib_work); } } -static int rtl8365mb_get_and_clear_status_reg(struct realtek_smi *smi, u32 reg, +static int rtl8365mb_get_and_clear_status_reg(struct realtek_priv *priv, u32 reg, u32 *val) { int ret; - ret = regmap_read(smi->map, reg, val); + ret = regmap_read(priv->map, reg, val); if (ret) return ret; - return regmap_write(smi->map, reg, *val); + return regmap_write(priv->map, reg, *val); } static irqreturn_t rtl8365mb_irq(int irq, void *data) { - struct realtek_smi *smi = data; + struct realtek_priv *priv = data; unsigned long line_changes = 0; struct rtl8365mb *mb; u32 stat; int line; int ret; - mb = smi->chip_data; + mb = priv->chip_data; - ret = rtl8365mb_get_and_clear_status_reg(smi, RTL8365MB_INTR_STATUS_REG, + ret = rtl8365mb_get_and_clear_status_reg(priv, RTL8365MB_INTR_STATUS_REG, &stat); if (ret) goto out_error; @@ -1485,14 +1503,14 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) u32 val; ret = rtl8365mb_get_and_clear_status_reg( - smi, RTL8365MB_PORT_LINKUP_IND_REG, &val); + priv, RTL8365MB_PORT_LINKUP_IND_REG, &val); if (ret) goto out_error; linkup_ind = FIELD_GET(RTL8365MB_PORT_LINKUP_IND_MASK, val); ret = rtl8365mb_get_and_clear_status_reg( - smi, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); + priv, RTL8365MB_PORT_LINKDOWN_IND_REG, &val); if (ret) goto out_error; @@ -1504,8 +1522,8 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) if (!line_changes) goto out_none; - for_each_set_bit(line, &line_changes, smi->num_ports) { - int child_irq = irq_find_mapping(smi->irqdomain, line); + for_each_set_bit(line, &line_changes, priv->num_ports) { + int child_irq = irq_find_mapping(priv->irqdomain, line); handle_nested_irq(child_irq); } @@ -1513,7 +1531,7 @@ static irqreturn_t rtl8365mb_irq(int irq, void *data) return IRQ_HANDLED; out_error: - dev_err(smi->dev, "failed to read interrupt status: %d\n", ret); + dev_err(priv->dev, "failed to read interrupt status: %d\n", ret); out_none: return IRQ_NONE; @@ -1548,27 +1566,27 @@ static const struct irq_domain_ops rtl8365mb_irqdomain_ops = { .xlate = irq_domain_xlate_onecell, }; -static int rtl8365mb_set_irq_enable(struct realtek_smi *smi, bool enable) +static int rtl8365mb_set_irq_enable(struct realtek_priv *priv, bool enable) { - return regmap_update_bits(smi->map, RTL8365MB_INTR_CTRL_REG, + return regmap_update_bits(priv->map, RTL8365MB_INTR_CTRL_REG, RTL8365MB_INTR_LINK_CHANGE_MASK, FIELD_PREP(RTL8365MB_INTR_LINK_CHANGE_MASK, enable ? 1 : 0)); } -static int rtl8365mb_irq_enable(struct realtek_smi *smi) +static int rtl8365mb_irq_enable(struct realtek_priv *priv) { - return rtl8365mb_set_irq_enable(smi, true); + return rtl8365mb_set_irq_enable(priv, true); } -static int rtl8365mb_irq_disable(struct realtek_smi *smi) +static int rtl8365mb_irq_disable(struct realtek_priv *priv) { - return rtl8365mb_set_irq_enable(smi, false); + return rtl8365mb_set_irq_enable(priv, false); } -static int rtl8365mb_irq_setup(struct realtek_smi *smi) +static int rtl8365mb_irq_setup(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; struct device_node *intc; u32 irq_trig; int virq; @@ -1577,9 +1595,9 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) int ret; int i; - intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller"); if (!intc) { - dev_err(smi->dev, "missing child interrupt-controller node\n"); + dev_err(priv->dev, "missing child interrupt-controller node\n"); return -EINVAL; } @@ -1587,24 +1605,24 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) irq = of_irq_get(intc, 0); if (irq <= 0) { if (irq != -EPROBE_DEFER) - dev_err(smi->dev, "failed to get parent irq: %d\n", + dev_err(priv->dev, "failed to get parent irq: %d\n", irq); ret = irq ? irq : -EINVAL; goto out_put_node; } - smi->irqdomain = irq_domain_add_linear(intc, smi->num_ports, - &rtl8365mb_irqdomain_ops, smi); - if (!smi->irqdomain) { - dev_err(smi->dev, "failed to add irq domain\n"); + priv->irqdomain = irq_domain_add_linear(intc, priv->num_ports, + &rtl8365mb_irqdomain_ops, priv); + if (!priv->irqdomain) { + dev_err(priv->dev, "failed to add irq domain\n"); ret = -ENOMEM; goto out_put_node; } - for (i = 0; i < smi->num_ports; i++) { - virq = irq_create_mapping(smi->irqdomain, i); + for (i = 0; i < priv->num_ports; i++) { + virq = irq_create_mapping(priv->irqdomain, i); if (!virq) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to create irq domain mapping\n"); ret = -EINVAL; goto out_remove_irqdomain; @@ -1625,40 +1643,40 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) val = RTL8365MB_INTR_POLARITY_LOW; break; default: - dev_err(smi->dev, "unsupported irq trigger type %u\n", + dev_err(priv->dev, "unsupported irq trigger type %u\n", irq_trig); ret = -EINVAL; goto out_remove_irqdomain; } - ret = regmap_update_bits(smi->map, RTL8365MB_INTR_POLARITY_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_INTR_POLARITY_REG, RTL8365MB_INTR_POLARITY_MASK, FIELD_PREP(RTL8365MB_INTR_POLARITY_MASK, val)); if (ret) goto out_remove_irqdomain; /* Disable the interrupt in case the chip has it enabled on reset */ - ret = rtl8365mb_irq_disable(smi); + ret = rtl8365mb_irq_disable(priv); if (ret) goto out_remove_irqdomain; /* Clear the interrupt status register */ - ret = regmap_write(smi->map, RTL8365MB_INTR_STATUS_REG, + ret = regmap_write(priv->map, RTL8365MB_INTR_STATUS_REG, RTL8365MB_INTR_ALL_MASK); if (ret) goto out_remove_irqdomain; ret = request_threaded_irq(irq, NULL, rtl8365mb_irq, IRQF_ONESHOT, - "rtl8365mb", smi); + "rtl8365mb", priv); if (ret) { - dev_err(smi->dev, "failed to request irq: %d\n", ret); + dev_err(priv->dev, "failed to request irq: %d\n", ret); goto out_remove_irqdomain; } /* Store the irq so that we know to free it during teardown */ mb->irq = irq; - ret = rtl8365mb_irq_enable(smi); + ret = rtl8365mb_irq_enable(priv); if (ret) goto out_free_irq; @@ -1667,17 +1685,17 @@ static int rtl8365mb_irq_setup(struct realtek_smi *smi) return 0; out_free_irq: - free_irq(mb->irq, smi); + free_irq(mb->irq, priv); mb->irq = 0; out_remove_irqdomain: - for (i = 0; i < smi->num_ports; i++) { - virq = irq_find_mapping(smi->irqdomain, i); + for (i = 0; i < priv->num_ports; i++) { + virq = irq_find_mapping(priv->irqdomain, i); irq_dispose_mapping(virq); } - irq_domain_remove(smi->irqdomain); - smi->irqdomain = NULL; + irq_domain_remove(priv->irqdomain); + priv->irqdomain = NULL; out_put_node: of_node_put(intc); @@ -1685,36 +1703,34 @@ out_put_node: return ret; } -static void rtl8365mb_irq_teardown(struct realtek_smi *smi) +static void rtl8365mb_irq_teardown(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int virq; int i; if (mb->irq) { - free_irq(mb->irq, smi); + free_irq(mb->irq, priv); mb->irq = 0; } - if (smi->irqdomain) { - for (i = 0; i < smi->num_ports; i++) { - virq = irq_find_mapping(smi->irqdomain, i); + if (priv->irqdomain) { + for (i = 0; i < priv->num_ports; i++) { + virq = irq_find_mapping(priv->irqdomain, i); irq_dispose_mapping(virq); } - irq_domain_remove(smi->irqdomain); - smi->irqdomain = NULL; + irq_domain_remove(priv->irqdomain); + priv->irqdomain = NULL; } } -static int rtl8365mb_cpu_config(struct realtek_smi *smi) +static int rtl8365mb_cpu_config(struct realtek_priv *priv, const struct rtl8365mb_cpu *cpu) { - struct rtl8365mb *mb = smi->chip_data; - struct rtl8365mb_cpu *cpu = &mb->cpu; u32 val; int ret; - ret = regmap_update_bits(smi->map, RTL8365MB_CPU_PORT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_CPU_PORT_MASK_REG, RTL8365MB_CPU_PORT_MASK_MASK, FIELD_PREP(RTL8365MB_CPU_PORT_MASK_MASK, cpu->mask)); @@ -1726,26 +1742,26 @@ static int rtl8365mb_cpu_config(struct realtek_smi *smi) FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_POSITION_MASK, cpu->position) | FIELD_PREP(RTL8365MB_CPU_CTRL_RXBYTECOUNT_MASK, cpu->rx_length) | FIELD_PREP(RTL8365MB_CPU_CTRL_TAG_FORMAT_MASK, cpu->format) | - FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port) | + FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_MASK, cpu->trap_port & 0x7) | FIELD_PREP(RTL8365MB_CPU_CTRL_TRAP_PORT_EXT_MASK, - cpu->trap_port >> 3); - ret = regmap_write(smi->map, RTL8365MB_CPU_CTRL_REG, val); + cpu->trap_port >> 3 & 0x1); + ret = regmap_write(priv->map, RTL8365MB_CPU_CTRL_REG, val); if (ret) return ret; return 0; } -static int rtl8365mb_switch_init(struct realtek_smi *smi) +static int rtl8365mb_switch_init(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; int ret; int i; /* Do any chip-specific init jam before getting to the common stuff */ if (mb->jam_table) { for (i = 0; i < mb->jam_size; i++) { - ret = regmap_write(smi->map, mb->jam_table[i].reg, + ret = regmap_write(priv->map, mb->jam_table[i].reg, mb->jam_table[i].val); if (ret) return ret; @@ -1754,7 +1770,7 @@ static int rtl8365mb_switch_init(struct realtek_smi *smi) /* Common init jam */ for (i = 0; i < ARRAY_SIZE(rtl8365mb_init_jam_common); i++) { - ret = regmap_write(smi->map, rtl8365mb_init_jam_common[i].reg, + ret = regmap_write(priv->map, rtl8365mb_init_jam_common[i].reg, rtl8365mb_init_jam_common[i].val); if (ret) return ret; @@ -1763,75 +1779,86 @@ static int rtl8365mb_switch_init(struct realtek_smi *smi) return 0; } -static int rtl8365mb_reset_chip(struct realtek_smi *smi) +static int rtl8365mb_reset_chip(struct realtek_priv *priv) { u32 val; - realtek_smi_write_reg_noack(smi, RTL8365MB_CHIP_RESET_REG, - FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, - 1)); + priv->write_reg_noack(priv, RTL8365MB_CHIP_RESET_REG, + FIELD_PREP(RTL8365MB_CHIP_RESET_HW_MASK, 1)); /* Realtek documentation says the chip needs 1 second to reset. Sleep * for 100 ms before accessing any registers to prevent ACK timeouts. */ msleep(100); - return regmap_read_poll_timeout(smi->map, RTL8365MB_CHIP_RESET_REG, val, + return regmap_read_poll_timeout(priv->map, RTL8365MB_CHIP_RESET_REG, val, !(val & RTL8365MB_CHIP_RESET_HW_MASK), 20000, 1e6); } static int rtl8365mb_setup(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; + struct rtl8365mb_cpu cpu = {0}; + struct dsa_port *cpu_dp; struct rtl8365mb *mb; int ret; int i; - mb = smi->chip_data; + mb = priv->chip_data; - ret = rtl8365mb_reset_chip(smi); + ret = rtl8365mb_reset_chip(priv); if (ret) { - dev_err(smi->dev, "failed to reset chip: %d\n", ret); + dev_err(priv->dev, "failed to reset chip: %d\n", ret); goto out_error; } /* Configure switch to vendor-defined initial state */ - ret = rtl8365mb_switch_init(smi); + ret = rtl8365mb_switch_init(priv); if (ret) { - dev_err(smi->dev, "failed to initialize switch: %d\n", ret); + dev_err(priv->dev, "failed to initialize switch: %d\n", ret); goto out_error; } /* Set up cascading IRQs */ - ret = rtl8365mb_irq_setup(smi); + ret = rtl8365mb_irq_setup(priv); if (ret == -EPROBE_DEFER) return ret; else if (ret) - dev_info(smi->dev, "no interrupt support\n"); + dev_info(priv->dev, "no interrupt support\n"); /* Configure CPU tagging */ - ret = rtl8365mb_cpu_config(smi); + cpu.trap_port = RTL8365MB_MAX_NUM_PORTS; + dsa_switch_for_each_cpu_port(cpu_dp, priv->ds) { + cpu.mask |= BIT(cpu_dp->index); + + if (cpu.trap_port == RTL8365MB_MAX_NUM_PORTS) + cpu.trap_port = cpu_dp->index; + } + + cpu.enable = cpu.mask > 0; + cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; + cpu.position = RTL8365MB_CPU_POS_AFTER_SA; + cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; + cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; + + ret = rtl8365mb_cpu_config(priv, &cpu); if (ret) goto out_teardown_irq; /* Configure ports */ - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { struct rtl8365mb_port *p = &mb->ports[i]; - if (dsa_is_unused_port(smi->ds, i)) + if (dsa_is_unused_port(priv->ds, i)) continue; - /* Set up per-port private data */ - p->smi = smi; - p->index = i; - /* Forward only to the CPU */ - ret = rtl8365mb_port_set_isolation(smi, i, BIT(smi->cpu_port)); + ret = rtl8365mb_port_set_isolation(priv, i, cpu.mask); if (ret) goto out_teardown_irq; /* Disable learning */ - ret = rtl8365mb_port_set_learning(smi, i, false); + ret = rtl8365mb_port_set_learning(priv, i, false); if (ret) goto out_teardown_irq; @@ -1839,29 +1866,35 @@ static int rtl8365mb_setup(struct dsa_switch *ds) * ports will still forward frames to the CPU despite being * administratively down by default. */ - rtl8365mb_port_stp_state_set(smi->ds, i, BR_STATE_DISABLED); + rtl8365mb_port_stp_state_set(priv->ds, i, BR_STATE_DISABLED); + + /* Set up per-port private data */ + p->priv = priv; + p->index = i; } /* Set maximum packet length to 1536 bytes */ - ret = regmap_update_bits(smi->map, RTL8365MB_CFG0_MAX_LEN_REG, + ret = regmap_update_bits(priv->map, RTL8365MB_CFG0_MAX_LEN_REG, RTL8365MB_CFG0_MAX_LEN_MASK, FIELD_PREP(RTL8365MB_CFG0_MAX_LEN_MASK, 1536)); if (ret) goto out_teardown_irq; - ret = realtek_smi_setup_mdio(smi); - if (ret) { - dev_err(smi->dev, "could not set up MDIO bus\n"); - goto out_teardown_irq; + if (priv->setup_interface) { + ret = priv->setup_interface(ds); + if (ret) { + dev_err(priv->dev, "could not set up MDIO bus\n"); + goto out_teardown_irq; + } } /* Start statistics counter polling */ - rtl8365mb_stats_setup(smi); + rtl8365mb_stats_setup(priv); return 0; out_teardown_irq: - rtl8365mb_irq_teardown(smi); + rtl8365mb_irq_teardown(priv); out_error: return ret; @@ -1869,10 +1902,10 @@ out_error: static void rtl8365mb_teardown(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; - rtl8365mb_stats_teardown(smi); - rtl8365mb_irq_teardown(smi); + rtl8365mb_stats_teardown(priv); + rtl8365mb_irq_teardown(priv); } static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) @@ -1902,48 +1935,57 @@ static int rtl8365mb_get_chip_id_and_ver(struct regmap *map, u32 *id, u32 *ver) return 0; } -static int rtl8365mb_detect(struct realtek_smi *smi) +static int rtl8365mb_detect(struct realtek_priv *priv) { - struct rtl8365mb *mb = smi->chip_data; + struct rtl8365mb *mb = priv->chip_data; u32 chip_id; u32 chip_ver; int ret; - ret = rtl8365mb_get_chip_id_and_ver(smi->map, &chip_id, &chip_ver); + ret = rtl8365mb_get_chip_id_and_ver(priv->map, &chip_id, &chip_ver); if (ret) { - dev_err(smi->dev, "failed to read chip id and version: %d\n", + dev_err(priv->dev, "failed to read chip id and version: %d\n", ret); return ret; } switch (chip_id) { case RTL8365MB_CHIP_ID_8365MB_VC: - dev_info(smi->dev, - "found an RTL8365MB-VC switch (ver=0x%04x)\n", - chip_ver); + switch (chip_ver) { + case RTL8365MB_CHIP_VER_8365MB_VC: + dev_info(priv->dev, + "found an RTL8365MB-VC switch (ver=0x%04x)\n", + chip_ver); + break; + case RTL8365MB_CHIP_VER_8367RB: + dev_info(priv->dev, + "found an RTL8367RB-VB switch (ver=0x%04x)\n", + chip_ver); + break; + case RTL8365MB_CHIP_VER_8367S: + dev_info(priv->dev, + "found an RTL8367S switch (ver=0x%04x)\n", + chip_ver); + break; + default: + dev_err(priv->dev, "unrecognized switch version (ver=0x%04x)", + chip_ver); + return -ENODEV; + } - smi->cpu_port = RTL8365MB_CPU_PORT_NUM_8365MB_VC; - smi->num_ports = smi->cpu_port + 1; + priv->num_ports = RTL8365MB_MAX_NUM_PORTS; - mb->smi = smi; + mb->priv = priv; mb->chip_id = chip_id; mb->chip_ver = chip_ver; - mb->port_mask = BIT(smi->num_ports) - 1; - mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX_8365MB_VC; + mb->port_mask = GENMASK(priv->num_ports - 1, 0); + mb->learn_limit_max = RTL8365MB_LEARN_LIMIT_MAX; mb->jam_table = rtl8365mb_init_jam_8365mb_vc; mb->jam_size = ARRAY_SIZE(rtl8365mb_init_jam_8365mb_vc); - mb->cpu.enable = 1; - mb->cpu.mask = BIT(smi->cpu_port); - mb->cpu.trap_port = smi->cpu_port; - mb->cpu.insert = RTL8365MB_CPU_INSERT_TO_ALL; - mb->cpu.position = RTL8365MB_CPU_POS_AFTER_SA; - mb->cpu.rx_length = RTL8365MB_CPU_RXLEN_64BYTES; - mb->cpu.format = RTL8365MB_CPU_FORMAT_8BYTES; - break; default: - dev_err(smi->dev, + dev_err(priv->dev, "found an unknown Realtek switch (id=0x%04x, ver=0x%04x)\n", chip_id, chip_ver); return -ENODEV; @@ -1952,14 +1994,34 @@ static int rtl8365mb_detect(struct realtek_smi *smi) return 0; } -static const struct dsa_switch_ops rtl8365mb_switch_ops = { +static const struct dsa_switch_ops rtl8365mb_switch_ops_smi = { + .get_tag_protocol = rtl8365mb_get_tag_protocol, + .setup = rtl8365mb_setup, + .teardown = rtl8365mb_teardown, + .phylink_get_caps = rtl8365mb_phylink_get_caps, + .phylink_mac_config = rtl8365mb_phylink_mac_config, + .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, + .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .port_stp_state_set = rtl8365mb_port_stp_state_set, + .get_strings = rtl8365mb_get_strings, + .get_ethtool_stats = rtl8365mb_get_ethtool_stats, + .get_sset_count = rtl8365mb_get_sset_count, + .get_eth_phy_stats = rtl8365mb_get_phy_stats, + .get_eth_mac_stats = rtl8365mb_get_mac_stats, + .get_eth_ctrl_stats = rtl8365mb_get_ctrl_stats, + .get_stats64 = rtl8365mb_get_stats64, +}; + +static const struct dsa_switch_ops rtl8365mb_switch_ops_mdio = { .get_tag_protocol = rtl8365mb_get_tag_protocol, .setup = rtl8365mb_setup, .teardown = rtl8365mb_teardown, - .phylink_validate = rtl8365mb_phylink_validate, + .phylink_get_caps = rtl8365mb_phylink_get_caps, .phylink_mac_config = rtl8365mb_phylink_mac_config, .phylink_mac_link_down = rtl8365mb_phylink_mac_link_down, .phylink_mac_link_up = rtl8365mb_phylink_mac_link_up, + .phy_read = rtl8365mb_dsa_phy_read, + .phy_write = rtl8365mb_dsa_phy_write, .port_stp_state_set = rtl8365mb_port_stp_state_set, .get_strings = rtl8365mb_get_strings, .get_ethtool_stats = rtl8365mb_get_ethtool_stats, @@ -1970,18 +2032,23 @@ static const struct dsa_switch_ops rtl8365mb_switch_ops = { .get_stats64 = rtl8365mb_get_stats64, }; -static const struct realtek_smi_ops rtl8365mb_smi_ops = { +static const struct realtek_ops rtl8365mb_ops = { .detect = rtl8365mb_detect, .phy_read = rtl8365mb_phy_read, .phy_write = rtl8365mb_phy_write, }; -const struct realtek_smi_variant rtl8365mb_variant = { - .ds_ops = &rtl8365mb_switch_ops, - .ops = &rtl8365mb_smi_ops, +const struct realtek_variant rtl8365mb_variant = { + .ds_ops_smi = &rtl8365mb_switch_ops_smi, + .ds_ops_mdio = &rtl8365mb_switch_ops_mdio, + .ops = &rtl8365mb_ops, .clk_delay = 10, .cmd_read = 0xb9, .cmd_write = 0xb8, .chip_data_sz = sizeof(struct rtl8365mb), }; EXPORT_SYMBOL_GPL(rtl8365mb_variant); + +MODULE_AUTHOR("Alvin Å ipraga <alsi@bang-olufsen.dk>"); +MODULE_DESCRIPTION("Driver for RTL8365MB-VC ethernet switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/realtek/rtl8366-core.c index bdb8d8d34880..dc5f75be3017 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/realtek/rtl8366-core.c @@ -11,18 +11,18 @@ #include <linux/if_bridge.h> #include <net/dsa.h> -#include "realtek-smi-core.h" +#include "realtek.h" -int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used) +int rtl8366_mc_is_used(struct realtek_priv *priv, int mc_index, int *used) { int ret; int i; *used = 0; - for (i = 0; i < smi->num_ports; i++) { + for (i = 0; i < priv->num_ports; i++) { int index = 0; - ret = smi->ops->get_mc_index(smi, i, &index); + ret = priv->ops->get_mc_index(priv, i, &index); if (ret) return ret; @@ -38,13 +38,13 @@ EXPORT_SYMBOL_GPL(rtl8366_mc_is_used); /** * rtl8366_obtain_mc() - retrieve or allocate a VLAN member configuration - * @smi: the Realtek SMI device instance + * @priv: the Realtek SMI device instance * @vid: the VLAN ID to look up or allocate * @vlanmc: the pointer will be assigned to a pointer to a valid member config * if successful * @return: index of a new member config or negative error number */ -static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, +static int rtl8366_obtain_mc(struct realtek_priv *priv, int vid, struct rtl8366_vlan_mc *vlanmc) { struct rtl8366_vlan_4k vlan4k; @@ -52,10 +52,10 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, int i; /* Try to find an existing member config entry for this VID */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->get_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n", i, vid); return ret; } @@ -65,19 +65,19 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, } /* We have no MC entry for this VID, try to find an empty one */ - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->get_vlan_mc(smi, i, vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->get_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "error searching for VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error searching for VLAN MC %d for VID %d\n", i, vid); return ret; } if (vlanmc->vid == 0 && vlanmc->member == 0) { /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) { - dev_err(smi->dev, "error looking for 4K VLAN MC %d for VID %d\n", + dev_err(priv->dev, "error looking for 4K VLAN MC %d for VID %d\n", i, vid); return ret; } @@ -86,30 +86,30 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, vlanmc->member = vlan4k.member; vlanmc->untag = vlan4k.untag; vlanmc->fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n", i, vid); return ret; } - dev_dbg(smi->dev, "created new MC at index %d for VID %d\n", + dev_dbg(priv->dev, "created new MC at index %d for VID %d\n", i, vid); return i; } } /* MC table is full, try to find an unused entry and replace it */ - for (i = 0; i < smi->num_vlan_mc; i++) { + for (i = 0; i < priv->num_vlan_mc; i++) { int used; - ret = rtl8366_mc_is_used(smi, i, &used); + ret = rtl8366_mc_is_used(priv, i, &used); if (ret) return ret; if (!used) { /* Update the entry from the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) return ret; @@ -117,23 +117,23 @@ static int rtl8366_obtain_mc(struct realtek_smi *smi, int vid, vlanmc->member = vlan4k.member; vlanmc->untag = vlan4k.untag; vlanmc->fid = vlan4k.fid; - ret = smi->ops->set_vlan_mc(smi, i, vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, vlanmc); if (ret) { - dev_err(smi->dev, "unable to set/update VLAN MC %d for VID %d\n", + dev_err(priv->dev, "unable to set/update VLAN MC %d for VID %d\n", i, vid); return ret; } - dev_dbg(smi->dev, "recycled MC at index %i for VID %d\n", + dev_dbg(priv->dev, "recycled MC at index %i for VID %d\n", i, vid); return i; } } - dev_err(smi->dev, "all VLAN member configurations are in use\n"); + dev_err(priv->dev, "all VLAN member configurations are in use\n"); return -ENOSPC; } -int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, +int rtl8366_set_vlan(struct realtek_priv *priv, int vid, u32 member, u32 untag, u32 fid) { struct rtl8366_vlan_mc vlanmc; @@ -141,31 +141,31 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, int mc; int ret; - if (!smi->ops->is_vlan_valid(smi, vid)) + if (!priv->ops->is_vlan_valid(priv, vid)) return -EINVAL; - dev_dbg(smi->dev, + dev_dbg(priv->dev, "setting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, member, untag); /* Update the 4K table */ - ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k); + ret = priv->ops->get_vlan_4k(priv, vid, &vlan4k); if (ret) return ret; vlan4k.member |= member; vlan4k.untag |= untag; vlan4k.fid = fid; - ret = smi->ops->set_vlan_4k(smi, &vlan4k); + ret = priv->ops->set_vlan_4k(priv, &vlan4k); if (ret) return ret; - dev_dbg(smi->dev, + dev_dbg(priv->dev, "resulting VLAN%d 4k members: 0x%02x, untagged: 0x%02x\n", vid, vlan4k.member, vlan4k.untag); /* Find or allocate a member config for this VID */ - ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + ret = rtl8366_obtain_mc(priv, vid, &vlanmc); if (ret < 0) return ret; mc = ret; @@ -176,12 +176,12 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, vlanmc.fid = fid; /* Commit updates to the MC entry */ - ret = smi->ops->set_vlan_mc(smi, mc, &vlanmc); + ret = priv->ops->set_vlan_mc(priv, mc, &vlanmc); if (ret) - dev_err(smi->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", + dev_err(priv->dev, "failed to commit changes to VLAN MC index %d for VID %d\n", mc, vid); else - dev_dbg(smi->dev, + dev_dbg(priv->dev, "resulting VLAN%d MC members: 0x%02x, untagged: 0x%02x\n", vid, vlanmc.member, vlanmc.untag); @@ -189,37 +189,37 @@ int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member, } EXPORT_SYMBOL_GPL(rtl8366_set_vlan); -int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, +int rtl8366_set_pvid(struct realtek_priv *priv, unsigned int port, unsigned int vid) { struct rtl8366_vlan_mc vlanmc; int mc; int ret; - if (!smi->ops->is_vlan_valid(smi, vid)) + if (!priv->ops->is_vlan_valid(priv, vid)) return -EINVAL; /* Find or allocate a member config for this VID */ - ret = rtl8366_obtain_mc(smi, vid, &vlanmc); + ret = rtl8366_obtain_mc(priv, vid, &vlanmc); if (ret < 0) return ret; mc = ret; - ret = smi->ops->set_mc_index(smi, port, mc); + ret = priv->ops->set_mc_index(priv, port, mc); if (ret) { - dev_err(smi->dev, "set PVID: failed to set MC index %d for port %d\n", + dev_err(priv->dev, "set PVID: failed to set MC index %d for port %d\n", mc, port); return ret; } - dev_dbg(smi->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", + dev_dbg(priv->dev, "set PVID: the PVID for port %d set to %d using existing MC index %d\n", port, vid, mc); return 0; } EXPORT_SYMBOL_GPL(rtl8366_set_pvid); -int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable) +int rtl8366_enable_vlan4k(struct realtek_priv *priv, bool enable) { int ret; @@ -229,52 +229,52 @@ int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable) */ if (enable) { /* Make sure VLAN is ON */ - ret = smi->ops->enable_vlan(smi, true); + ret = priv->ops->enable_vlan(priv, true); if (ret) return ret; - smi->vlan_enabled = true; + priv->vlan_enabled = true; } - ret = smi->ops->enable_vlan4k(smi, enable); + ret = priv->ops->enable_vlan4k(priv, enable); if (ret) return ret; - smi->vlan4k_enabled = enable; + priv->vlan4k_enabled = enable; return 0; } EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k); -int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable) +int rtl8366_enable_vlan(struct realtek_priv *priv, bool enable) { int ret; - ret = smi->ops->enable_vlan(smi, enable); + ret = priv->ops->enable_vlan(priv, enable); if (ret) return ret; - smi->vlan_enabled = enable; + priv->vlan_enabled = enable; /* If we turn VLAN off, make sure that we turn off * 4k VLAN as well, if that happened to be on. */ if (!enable) { - smi->vlan4k_enabled = false; - ret = smi->ops->enable_vlan4k(smi, false); + priv->vlan4k_enabled = false; + ret = priv->ops->enable_vlan4k(priv, false); } return ret; } EXPORT_SYMBOL_GPL(rtl8366_enable_vlan); -int rtl8366_reset_vlan(struct realtek_smi *smi) +int rtl8366_reset_vlan(struct realtek_priv *priv) { struct rtl8366_vlan_mc vlanmc; int ret; int i; - rtl8366_enable_vlan(smi, false); - rtl8366_enable_vlan4k(smi, false); + rtl8366_enable_vlan(priv, false); + rtl8366_enable_vlan4k(priv, false); /* Clear the 16 VLAN member configurations */ vlanmc.vid = 0; @@ -282,8 +282,8 @@ int rtl8366_reset_vlan(struct realtek_smi *smi) vlanmc.member = 0; vlanmc.untag = 0; vlanmc.fid = 0; - for (i = 0; i < smi->num_vlan_mc; i++) { - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + for (i = 0; i < priv->num_vlan_mc; i++) { + ret = priv->ops->set_vlan_mc(priv, i, &vlanmc); if (ret) return ret; } @@ -298,12 +298,12 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, { bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID); - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; u32 member = 0; u32 untag = 0; int ret; - if (!smi->ops->is_vlan_valid(smi, vlan->vid)) { + if (!priv->ops->is_vlan_valid(priv, vlan->vid)) { NL_SET_ERR_MSG_MOD(extack, "VLAN ID not valid"); return -EINVAL; } @@ -312,13 +312,13 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, * FIXME: what's with this 4k business? * Just rtl8366_enable_vlan() seems inconclusive. */ - ret = rtl8366_enable_vlan4k(smi, true); + ret = rtl8366_enable_vlan4k(priv, true); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to enable VLAN 4K"); return ret; } - dev_dbg(smi->dev, "add VLAN %d on port %d, %s, %s\n", + dev_dbg(priv->dev, "add VLAN %d on port %d, %s, %s\n", vlan->vid, port, untagged ? "untagged" : "tagged", pvid ? "PVID" : "no PVID"); @@ -327,18 +327,18 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, if (untagged) untag |= BIT(port); - ret = rtl8366_set_vlan(smi, vlan->vid, member, untag, 0); + ret = rtl8366_set_vlan(priv, vlan->vid, member, untag, 0); if (ret) { - dev_err(smi->dev, "failed to set up VLAN %04x", vlan->vid); + dev_err(priv->dev, "failed to set up VLAN %04x", vlan->vid); return ret; } if (!pvid) return 0; - ret = rtl8366_set_pvid(smi, port, vlan->vid); + ret = rtl8366_set_pvid(priv, port, vlan->vid); if (ret) { - dev_err(smi->dev, "failed to set PVID on port %d to VLAN %04x", + dev_err(priv->dev, "failed to set PVID on port %d to VLAN %04x", port, vlan->vid); return ret; } @@ -350,15 +350,15 @@ EXPORT_SYMBOL_GPL(rtl8366_vlan_add); int rtl8366_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret, i; - dev_dbg(smi->dev, "del VLAN %d on port %d\n", vlan->vid, port); + dev_dbg(priv->dev, "del VLAN %d on port %d\n", vlan->vid, port); - for (i = 0; i < smi->num_vlan_mc; i++) { + for (i = 0; i < priv->num_vlan_mc; i++) { struct rtl8366_vlan_mc vlanmc; - ret = smi->ops->get_vlan_mc(smi, i, &vlanmc); + ret = priv->ops->get_vlan_mc(priv, i, &vlanmc); if (ret) return ret; @@ -376,9 +376,9 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, vlanmc.priority = 0; vlanmc.fid = 0; } - ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); + ret = priv->ops->set_vlan_mc(priv, i, &vlanmc); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to remove VLAN %04x\n", vlan->vid); return ret; @@ -394,15 +394,15 @@ EXPORT_SYMBOL_GPL(rtl8366_vlan_del); void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366_mib_counter *mib; int i; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return; - for (i = 0; i < smi->num_mib_counters; i++) { - mib = &smi->mib_counters[i]; + for (i = 0; i < priv->num_mib_counters; i++) { + mib = &priv->mib_counters[i]; strncpy(data + i * ETH_GSTRING_LEN, mib->name, ETH_GSTRING_LEN); } @@ -411,35 +411,35 @@ EXPORT_SYMBOL_GPL(rtl8366_get_strings); int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; /* We only support SS_STATS */ if (sset != ETH_SS_STATS) return 0; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return -EINVAL; - return smi->num_mib_counters; + return priv->num_mib_counters; } EXPORT_SYMBOL_GPL(rtl8366_get_sset_count); void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int i; int ret; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return; - for (i = 0; i < smi->num_mib_counters; i++) { + for (i = 0; i < priv->num_mib_counters; i++) { struct rtl8366_mib_counter *mib; u64 mibvalue = 0; - mib = &smi->mib_counters[i]; - ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue); + mib = &priv->mib_counters[i]; + ret = priv->ops->get_mib_counter(priv, port, mib, &mibvalue); if (ret) { - dev_err(smi->dev, "error reading MIB counter %s\n", + dev_err(priv->dev, "error reading MIB counter %s\n", mib->name); } data[i] = mibvalue; diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index ecc19bd5115f..fb6565e68401 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -21,7 +21,7 @@ #include <linux/of_irq.h> #include <linux/regmap.h> -#include "realtek-smi-core.h" +#include "realtek.h" #define RTL8366RB_PORT_NUM_CPU 5 #define RTL8366RB_NUM_PORTS 6 @@ -396,7 +396,7 @@ static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = { { 0, 70, 2, "IfOutBroadcastPkts" }, }; -static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, +static int rtl8366rb_get_mib_counter(struct realtek_priv *priv, int port, struct rtl8366_mib_counter *mib, u64 *mibvalue) @@ -412,12 +412,12 @@ static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, /* Writing access counter address first * then ASIC will prepare 64bits counter wait for being retrived */ - ret = regmap_write(smi->map, addr, 0); /* Write whatever */ + ret = regmap_write(priv->map, addr, 0); /* Write whatever */ if (ret) return ret; /* Read MIB control register */ - ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_MIB_CTRL_REG, &val); if (ret) return -EIO; @@ -430,7 +430,7 @@ static int rtl8366rb_get_mib_counter(struct realtek_smi *smi, /* Read each individual MIB 16 bits at the time */ *mibvalue = 0; for (i = mib->length; i > 0; i--) { - ret = regmap_read(smi->map, addr + (i - 1), &val); + ret = regmap_read(priv->map, addr + (i - 1), &val); if (ret) return ret; *mibvalue = (*mibvalue << 16) | (val & 0xFFFF); @@ -455,38 +455,38 @@ static u32 rtl8366rb_get_irqmask(struct irq_data *d) static void rtl8366rb_mask_irq(struct irq_data *d) { - struct realtek_smi *smi = irq_data_get_irq_chip_data(d); + struct realtek_priv *priv = irq_data_get_irq_chip_data(d); int ret; - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG, rtl8366rb_get_irqmask(d), 0); if (ret) - dev_err(smi->dev, "could not mask IRQ\n"); + dev_err(priv->dev, "could not mask IRQ\n"); } static void rtl8366rb_unmask_irq(struct irq_data *d) { - struct realtek_smi *smi = irq_data_get_irq_chip_data(d); + struct realtek_priv *priv = irq_data_get_irq_chip_data(d); int ret; - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_MASK_REG, rtl8366rb_get_irqmask(d), rtl8366rb_get_irqmask(d)); if (ret) - dev_err(smi->dev, "could not unmask IRQ\n"); + dev_err(priv->dev, "could not unmask IRQ\n"); } static irqreturn_t rtl8366rb_irq(int irq, void *data) { - struct realtek_smi *smi = data; + struct realtek_priv *priv = data; u32 stat; int ret; /* This clears the IRQ status register */ - ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG, + ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG, &stat); if (ret) { - dev_err(smi->dev, "can't read interrupt status\n"); + dev_err(priv->dev, "can't read interrupt status\n"); return IRQ_NONE; } stat &= RTL8366RB_INTERRUPT_VALID; @@ -502,7 +502,7 @@ static irqreturn_t rtl8366rb_irq(int irq, void *data) */ if (line < 12 && line > 5) line -= 5; - child_irq = irq_find_mapping(smi->irqdomain, line); + child_irq = irq_find_mapping(priv->irqdomain, line); handle_nested_irq(child_irq); } return IRQ_HANDLED; @@ -538,7 +538,7 @@ static const struct irq_domain_ops rtl8366rb_irqdomain_ops = { .xlate = irq_domain_xlate_onecell, }; -static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) +static int rtl8366rb_setup_cascaded_irq(struct realtek_priv *priv) { struct device_node *intc; unsigned long irq_trig; @@ -547,24 +547,24 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) u32 val; int i; - intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller"); + intc = of_get_child_by_name(priv->dev->of_node, "interrupt-controller"); if (!intc) { - dev_err(smi->dev, "missing child interrupt-controller node\n"); + dev_err(priv->dev, "missing child interrupt-controller node\n"); return -EINVAL; } /* RB8366RB IRQs cascade off this one */ irq = of_irq_get(intc, 0); if (irq <= 0) { - dev_err(smi->dev, "failed to get parent IRQ\n"); + dev_err(priv->dev, "failed to get parent IRQ\n"); ret = irq ? irq : -EINVAL; goto out_put_node; } /* This clears the IRQ status register */ - ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG, + ret = regmap_read(priv->map, RTL8366RB_INTERRUPT_STATUS_REG, &val); if (ret) { - dev_err(smi->dev, "can't read interrupt status\n"); + dev_err(priv->dev, "can't read interrupt status\n"); goto out_put_node; } @@ -573,48 +573,48 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi) switch (irq_trig) { case IRQF_TRIGGER_RISING: case IRQF_TRIGGER_HIGH: - dev_info(smi->dev, "active high/rising IRQ\n"); + dev_info(priv->dev, "active high/rising IRQ\n"); val = 0; break; case IRQF_TRIGGER_FALLING: case IRQF_TRIGGER_LOW: - dev_info(smi->dev, "active low/falling IRQ\n"); + dev_info(priv->dev, "active low/falling IRQ\n"); val = RTL8366RB_INTERRUPT_POLARITY; break; } - ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_INTERRUPT_POLARITY, val); if (ret) { - dev_err(smi->dev, "could not configure IRQ polarity\n"); + dev_err(priv->dev, "could not configure IRQ polarity\n"); goto out_put_node; } - ret = devm_request_threaded_irq(smi->dev, irq, NULL, + ret = devm_request_threaded_irq(priv->dev, irq, NULL, rtl8366rb_irq, IRQF_ONESHOT, - "RTL8366RB", smi); + "RTL8366RB", priv); if (ret) { - dev_err(smi->dev, "unable to request irq: %d\n", ret); + dev_err(priv->dev, "unable to request irq: %d\n", ret); goto out_put_node; } - smi->irqdomain = irq_domain_add_linear(intc, - RTL8366RB_NUM_INTERRUPT, - &rtl8366rb_irqdomain_ops, - smi); - if (!smi->irqdomain) { - dev_err(smi->dev, "failed to create IRQ domain\n"); + priv->irqdomain = irq_domain_add_linear(intc, + RTL8366RB_NUM_INTERRUPT, + &rtl8366rb_irqdomain_ops, + priv); + if (!priv->irqdomain) { + dev_err(priv->dev, "failed to create IRQ domain\n"); ret = -EINVAL; goto out_put_node; } - for (i = 0; i < smi->num_ports; i++) - irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq); + for (i = 0; i < priv->num_ports; i++) + irq_set_parent(irq_create_mapping(priv->irqdomain, i), irq); out_put_node: of_node_put(intc); return ret; } -static int rtl8366rb_set_addr(struct realtek_smi *smi) +static int rtl8366rb_set_addr(struct realtek_priv *priv) { u8 addr[ETH_ALEN]; u16 val; @@ -622,18 +622,18 @@ static int rtl8366rb_set_addr(struct realtek_smi *smi) eth_random_addr(addr); - dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", + dev_info(priv->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n", addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); val = addr[0] << 8 | addr[1]; - ret = regmap_write(smi->map, RTL8366RB_SMAR0, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR0, val); if (ret) return ret; val = addr[2] << 8 | addr[3]; - ret = regmap_write(smi->map, RTL8366RB_SMAR1, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR1, val); if (ret) return ret; val = addr[4] << 8 | addr[5]; - ret = regmap_write(smi->map, RTL8366RB_SMAR2, val); + ret = regmap_write(priv->map, RTL8366RB_SMAR2, val); if (ret) return ret; @@ -765,7 +765,7 @@ static const struct rtl8366rb_jam_tbl_entry rtl8366rb_green_jam[] = { /* Function that jams the tables in the proper registers */ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, - int jam_size, struct realtek_smi *smi, + int jam_size, struct realtek_priv *priv, bool write_dbg) { u32 val; @@ -774,24 +774,24 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, for (i = 0; i < jam_size; i++) { if ((jam_table[i].reg & 0xBE00) == 0xBE00) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_PHY_ACCESS_BUSY_REG, &val); if (ret) return ret; if (!(val & RTL8366RB_PHY_INT_BUSY)) { - ret = regmap_write(smi->map, - RTL8366RB_PHY_ACCESS_CTRL_REG, - RTL8366RB_PHY_CTRL_WRITE); + ret = regmap_write(priv->map, + RTL8366RB_PHY_ACCESS_CTRL_REG, + RTL8366RB_PHY_CTRL_WRITE); if (ret) return ret; } } if (write_dbg) - dev_dbg(smi->dev, "jam %04x into register %04x\n", + dev_dbg(priv->dev, "jam %04x into register %04x\n", jam_table[i].val, jam_table[i].reg); - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, jam_table[i].reg, jam_table[i].val); if (ret) @@ -802,7 +802,7 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table, static int rtl8366rb_setup(struct dsa_switch *ds) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; const struct rtl8366rb_jam_tbl_entry *jam_table; struct rtl8366rb *rb; u32 chip_ver = 0; @@ -812,11 +812,11 @@ static int rtl8366rb_setup(struct dsa_switch *ds) int ret; int i; - rb = smi->chip_data; + rb = priv->chip_data; - ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id); + ret = regmap_read(priv->map, RTL8366RB_CHIP_ID_REG, &chip_id); if (ret) { - dev_err(smi->dev, "unable to read chip id\n"); + dev_err(priv->dev, "unable to read chip id\n"); return ret; } @@ -824,18 +824,18 @@ static int rtl8366rb_setup(struct dsa_switch *ds) case RTL8366RB_CHIP_ID_8366: break; default: - dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id); + dev_err(priv->dev, "unknown chip id (%04x)\n", chip_id); return -ENODEV; } - ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG, + ret = regmap_read(priv->map, RTL8366RB_CHIP_VERSION_CTRL_REG, &chip_ver); if (ret) { - dev_err(smi->dev, "unable to read chip version\n"); + dev_err(priv->dev, "unable to read chip version\n"); return ret; } - dev_info(smi->dev, "RTL%04x ver %u chip found\n", + dev_info(priv->dev, "RTL%04x ver %u chip found\n", chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK); /* Do the init dance using the right jam table */ @@ -872,20 +872,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds) jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500); } - ret = rtl8366rb_jam_table(jam_table, jam_size, smi, true); + ret = rtl8366rb_jam_table(jam_table, jam_size, priv, true); if (ret) return ret; /* Isolate all user ports so they can only send packets to itself and the CPU port */ for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { - ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) | RTL8366RB_PORT_ISO_EN); if (ret) return ret; } /* CPU port can send packets to all ports */ - ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), + ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) | RTL8366RB_PORT_ISO_EN); if (ret) @@ -893,26 +893,26 @@ static int rtl8366rb_setup(struct dsa_switch *ds) /* Set up the "green ethernet" feature */ ret = rtl8366rb_jam_table(rtl8366rb_green_jam, - ARRAY_SIZE(rtl8366rb_green_jam), smi, false); + ARRAY_SIZE(rtl8366rb_green_jam), priv, false); if (ret) return ret; - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_GREEN_FEATURE_REG, (chip_ver == 1) ? 0x0007 : 0x0003); if (ret) return ret; /* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */ - ret = regmap_write(smi->map, 0x0c, 0x240); + ret = regmap_write(priv->map, 0x0c, 0x240); if (ret) return ret; - ret = regmap_write(smi->map, 0x0d, 0x240); + ret = regmap_write(priv->map, 0x0d, 0x240); if (ret) return ret; /* Set some random MAC address */ - ret = rtl8366rb_set_addr(smi); + ret = rtl8366rb_set_addr(priv); if (ret) return ret; @@ -921,21 +921,21 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * If you set RTL8368RB_CPU_NO_TAG (bit 15) in this registers * the custom tag is turned off. */ - ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG, + ret = regmap_update_bits(priv->map, RTL8368RB_CPU_CTRL_REG, 0xFFFF, - BIT(smi->cpu_port)); + BIT(priv->cpu_port)); if (ret) return ret; /* Make sure we default-enable the fixed CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, - BIT(smi->cpu_port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, + BIT(priv->cpu_port), 0); if (ret) return ret; /* Set maximum packet length to 1536 bytes */ - ret = regmap_update_bits(smi->map, RTL8366RB_SGCR, + ret = regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_MAX_LENGTH_MASK, RTL8366RB_SGCR_MAX_LENGTH_1536); if (ret) @@ -945,13 +945,13 @@ static int rtl8366rb_setup(struct dsa_switch *ds) rb->max_mtu[i] = 1532; /* Disable learning for all ports */ - ret = regmap_write(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL, + ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, RTL8366RB_PORT_ALL); if (ret) return ret; /* Enable auto ageing for all ports */ - ret = regmap_write(smi->map, RTL8366RB_SECURITY_CTRL, 0); + ret = regmap_write(priv->map, RTL8366RB_SECURITY_CTRL, 0); if (ret) return ret; @@ -962,30 +962,30 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * connected to something exotic such as fiber, then this might * be worth experimenting with. */ - ret = regmap_update_bits(smi->map, RTL8366RB_PMC0, + ret = regmap_update_bits(priv->map, RTL8366RB_PMC0, RTL8366RB_PMC0_P4_IOMODE_MASK, 0 << RTL8366RB_PMC0_P4_IOMODE_SHIFT); if (ret) return ret; /* Accept all packets by default, we enable filtering on-demand */ - ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, 0); if (ret) return ret; - ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, + ret = regmap_write(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, 0); if (ret) return ret; /* Don't drop packets whose DA has not been learned */ - ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2, + ret = regmap_update_bits(priv->map, RTL8366RB_SSCR2, RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0); if (ret) return ret; /* Set blinking, TODO: make this configurable */ - ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_BLINKRATE_REG, RTL8366RB_LED_BLINKRATE_MASK, RTL8366RB_LED_BLINKRATE_56MS); if (ret) @@ -996,15 +996,15 @@ static int rtl8366rb_setup(struct dsa_switch *ds) * behaviour (no individual config) but we can set up each * LED separately. */ - if (smi->leds_disabled) { + if (priv->leds_disabled) { /* Turn everything off */ - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x0FFF, 0); - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x0FFF, 0); - regmap_update_bits(smi->map, + regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_P4_RGMII_LED, 0); @@ -1014,7 +1014,7 @@ static int rtl8366rb_setup(struct dsa_switch *ds) val = RTL8366RB_LED_FORCE; } for (i = 0; i < 4; i++) { - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_CTRL_REG, 0xf << (i * 4), val << (i * 4)); @@ -1022,18 +1022,20 @@ static int rtl8366rb_setup(struct dsa_switch *ds) return ret; } - ret = rtl8366_reset_vlan(smi); + ret = rtl8366_reset_vlan(priv); if (ret) return ret; - ret = rtl8366rb_setup_cascaded_irq(smi); + ret = rtl8366rb_setup_cascaded_irq(priv); if (ret) - dev_info(smi->dev, "no interrupt support\n"); + dev_info(priv->dev, "no interrupt support\n"); - ret = realtek_smi_setup_mdio(smi); - if (ret) { - dev_info(smi->dev, "could not set up MDIO bus\n"); - return -ENODEV; + if (priv->setup_interface) { + ret = priv->setup_interface(ds); + if (ret) { + dev_err(priv->dev, "could not set up MDIO bus\n"); + return -ENODEV; + } } return 0; @@ -1052,35 +1054,35 @@ rtl8366rb_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, struct phy_device *phydev, int speed, int duplex, bool tx_pause, bool rx_pause) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - if (port != smi->cpu_port) + if (port != priv->cpu_port) return; - dev_dbg(smi->dev, "MAC link up on CPU port (%d)\n", port); + dev_dbg(priv->dev, "MAC link up on CPU port (%d)\n", port); /* Force the fixed CPU port into 1Gbit mode, no autonegotiation */ - ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_MAC_FORCE_CTRL_REG, BIT(port), BIT(port)); if (ret) { - dev_err(smi->dev, "failed to force 1Gbit on CPU port\n"); + dev_err(priv->dev, "failed to force 1Gbit on CPU port\n"); return; } - ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2, + ret = regmap_update_bits(priv->map, RTL8366RB_PAACR2, 0xFF00U, RTL8366RB_PAACR_CPU_PORT << 8); if (ret) { - dev_err(smi->dev, "failed to set PAACR on CPU port\n"); + dev_err(priv->dev, "failed to set PAACR on CPU port\n"); return; } /* Enable the CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), 0); if (ret) { - dev_err(smi->dev, "failed to enable the CPU port\n"); + dev_err(priv->dev, "failed to enable the CPU port\n"); return; } } @@ -1089,99 +1091,99 @@ static void rtl8366rb_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - if (port != smi->cpu_port) + if (port != priv->cpu_port) return; - dev_dbg(smi->dev, "MAC link down on CPU port (%d)\n", port); + dev_dbg(priv->dev, "MAC link down on CPU port (%d)\n", port); /* Disable the CPU port */ - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), BIT(port)); if (ret) { - dev_err(smi->dev, "failed to disable the CPU port\n"); + dev_err(priv->dev, "failed to disable the CPU port\n"); return; } } -static void rb8366rb_set_port_led(struct realtek_smi *smi, +static void rb8366rb_set_port_led(struct realtek_priv *priv, int port, bool enable) { u16 val = enable ? 0x3f : 0; int ret; - if (smi->leds_disabled) + if (priv->leds_disabled) return; switch (port) { case 0: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x3F, val); break; case 1: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_0_1_CTRL_REG, 0x3F << RTL8366RB_LED_1_OFFSET, val << RTL8366RB_LED_1_OFFSET); break; case 2: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x3F, val); break; case 3: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_LED_2_3_CTRL_REG, 0x3F << RTL8366RB_LED_3_OFFSET, val << RTL8366RB_LED_3_OFFSET); break; case 4: - ret = regmap_update_bits(smi->map, + ret = regmap_update_bits(priv->map, RTL8366RB_INTERRUPT_CONTROL_REG, RTL8366RB_P4_RGMII_LED, enable ? RTL8366RB_P4_RGMII_LED : 0); break; default: - dev_err(smi->dev, "no LED for port %d\n", port); + dev_err(priv->dev, "no LED for port %d\n", port); return; } if (ret) - dev_err(smi->dev, "error updating LED on port %d\n", port); + dev_err(priv->dev, "error updating LED on port %d\n", port); } static int rtl8366rb_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - dev_dbg(smi->dev, "enable port %d\n", port); - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + dev_dbg(priv->dev, "enable port %d\n", port); + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), 0); if (ret) return ret; - rb8366rb_set_port_led(smi, port, true); + rb8366rb_set_port_led(priv, port, true); return 0; } static void rtl8366rb_port_disable(struct dsa_switch *ds, int port) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; - dev_dbg(smi->dev, "disable port %d\n", port); - ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port), + dev_dbg(priv->dev, "disable port %d\n", port); + ret = regmap_update_bits(priv->map, RTL8366RB_PECR, BIT(port), BIT(port)); if (ret) return; - rb8366rb_set_port_led(smi, port, false); + rb8366rb_set_port_led(priv, port, false); } static int @@ -1189,7 +1191,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, bool *tx_fwd_offload) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; unsigned int port_bitmap = 0; int ret, i; @@ -1202,17 +1204,17 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Join this port to each other port on the bridge */ - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(port)), RTL8366RB_PORT_ISO_PORTS(BIT(port))); if (ret) - dev_err(smi->dev, "failed to join port %d\n", port); + dev_err(priv->dev, "failed to join port %d\n", port); port_bitmap |= BIT(i); } /* Set the bits for the ports we can access */ - return regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), RTL8366RB_PORT_ISO_PORTS(port_bitmap), RTL8366RB_PORT_ISO_PORTS(port_bitmap)); } @@ -1221,7 +1223,7 @@ static void rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; unsigned int port_bitmap = 0; int ret, i; @@ -1234,28 +1236,30 @@ rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port from any other port on the bridge */ - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0); if (ret) - dev_err(smi->dev, "failed to leave port %d\n", port); + dev_err(priv->dev, "failed to leave port %d\n", port); port_bitmap |= BIT(i); } /* Clear the bits for the ports we can not access, leave ourselves */ - regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0); } /** * rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames - * @smi: SMI state container + * @priv: SMI state container * @port: the port to drop untagged and C-tagged frames on * @drop: whether to drop or pass untagged and C-tagged frames + * + * Return: zero for success, a negative number on error. */ -static int rtl8366rb_drop_untagged(struct realtek_smi *smi, int port, bool drop) +static int rtl8366rb_drop_untagged(struct realtek_priv *priv, int port, bool drop) { - return regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + return regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port), drop ? RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port) : 0); } @@ -1264,17 +1268,17 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366rb *rb; int ret; - rb = smi->chip_data; + rb = priv->chip_data; - dev_dbg(smi->dev, "port %d: %s VLAN filtering\n", port, + dev_dbg(priv->dev, "port %d: %s VLAN filtering\n", port, vlan_filtering ? "enable" : "disable"); /* If the port is not in the member set, the frame will be dropped */ - ret = regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, + ret = regmap_update_bits(priv->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, BIT(port), vlan_filtering ? BIT(port) : 0); if (ret) return ret; @@ -1284,9 +1288,9 @@ static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, * filtering on a port, we need to accept any frames. */ if (vlan_filtering) - ret = rtl8366rb_drop_untagged(smi, port, !rb->pvid_enabled[port]); + ret = rtl8366rb_drop_untagged(priv, port, !rb->pvid_enabled[port]); else - ret = rtl8366rb_drop_untagged(smi, port, false); + ret = rtl8366rb_drop_untagged(priv, port, false); return ret; } @@ -1308,11 +1312,11 @@ rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; int ret; if (flags.mask & BR_LEARNING) { - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_LEARNDIS_CTRL, + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, BIT(port), (flags.val & BR_LEARNING) ? 0 : BIT(port)); if (ret) @@ -1325,7 +1329,7 @@ rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port, static void rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; u32 val; int i; @@ -1344,13 +1348,13 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) val = RTL8366RB_STP_STATE_FORWARDING; break; default: - dev_err(smi->dev, "unknown bridge state requested\n"); + dev_err(priv->dev, "unknown bridge state requested\n"); return; } /* Set the same status for the port on all the FIDs */ for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { - regmap_update_bits(smi->map, RTL8366RB_STP_STATE_BASE + i, + regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i, RTL8366RB_STP_STATE_MASK(port), RTL8366RB_STP_STATE(port, val)); } @@ -1359,26 +1363,26 @@ rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) static void rtl8366rb_port_fast_age(struct dsa_switch *ds, int port) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; /* This will age out any learned L2 entries */ - regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL, + regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL, BIT(port), BIT(port)); /* Restore the normal state of things */ - regmap_update_bits(smi->map, RTL8366RB_SECURITY_CTRL, + regmap_update_bits(priv->map, RTL8366RB_SECURITY_CTRL, BIT(port), 0); } static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) { - struct realtek_smi *smi = ds->priv; + struct realtek_priv *priv = ds->priv; struct rtl8366rb *rb; unsigned int max_mtu; u32 len; int i; /* Cache the per-port MTU setting */ - rb = smi->chip_data; + rb = priv->chip_data; rb->max_mtu[port] = new_mtu; /* Roof out the MTU for the entire switch to the greatest @@ -1406,7 +1410,7 @@ static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) else len = RTL8366RB_SGCR_MAX_LENGTH_16000; - return regmap_update_bits(smi->map, RTL8366RB_SGCR, + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_MAX_LENGTH_MASK, len); } @@ -1419,7 +1423,7 @@ static int rtl8366rb_max_mtu(struct dsa_switch *ds, int port) return 15996; } -static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, +static int rtl8366rb_get_vlan_4k(struct realtek_priv *priv, u32 vid, struct rtl8366_vlan_4k *vlan4k) { u32 data[3]; @@ -1432,19 +1436,19 @@ static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, return -EINVAL; /* write VID */ - ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE, + ret = regmap_write(priv->map, RTL8366RB_VLAN_TABLE_WRITE_BASE, vid & RTL8366RB_VLAN_VID_MASK); if (ret) return ret; /* write table access control word */ - ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, RTL8366RB_TABLE_VLAN_READ_CTRL); if (ret) return ret; for (i = 0; i < 3; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_VLAN_TABLE_READ_BASE + i, &data[i]); if (ret) @@ -1460,7 +1464,7 @@ static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid, return 0; } -static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, +static int rtl8366rb_set_vlan_4k(struct realtek_priv *priv, const struct rtl8366_vlan_4k *vlan4k) { u32 data[3]; @@ -1480,7 +1484,7 @@ static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK; for (i = 0; i < 3; i++) { - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_VLAN_TABLE_WRITE_BASE + i, data[i]); if (ret) @@ -1488,13 +1492,13 @@ static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi, } /* write table access control word */ - ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_TABLE_ACCESS_CTRL_REG, RTL8366RB_TABLE_VLAN_WRITE_CTRL); return ret; } -static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, +static int rtl8366rb_get_vlan_mc(struct realtek_priv *priv, u32 index, struct rtl8366_vlan_mc *vlanmc) { u32 data[3]; @@ -1507,7 +1511,7 @@ static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, return -EINVAL; for (i = 0; i < 3; i++) { - ret = regmap_read(smi->map, + ret = regmap_read(priv->map, RTL8366RB_VLAN_MC_BASE(index) + i, &data[i]); if (ret) @@ -1525,7 +1529,7 @@ static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index, return 0; } -static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, +static int rtl8366rb_set_vlan_mc(struct realtek_priv *priv, u32 index, const struct rtl8366_vlan_mc *vlanmc) { u32 data[3]; @@ -1549,7 +1553,7 @@ static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK; for (i = 0; i < 3; i++) { - ret = regmap_write(smi->map, + ret = regmap_write(priv->map, RTL8366RB_VLAN_MC_BASE(index) + i, data[i]); if (ret) @@ -1559,15 +1563,15 @@ static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index, return 0; } -static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val) +static int rtl8366rb_get_mc_index(struct realtek_priv *priv, int port, int *val) { u32 data; int ret; - if (port >= smi->num_ports) + if (port >= priv->num_ports) return -EINVAL; - ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), + ret = regmap_read(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), &data); if (ret) return ret; @@ -1578,22 +1582,22 @@ static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val) return 0; } -static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index) +static int rtl8366rb_set_mc_index(struct realtek_priv *priv, int port, int index) { struct rtl8366rb *rb; bool pvid_enabled; int ret; - rb = smi->chip_data; + rb = priv->chip_data; pvid_enabled = !!index; - if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS) + if (port >= priv->num_ports || index >= RTL8366RB_NUM_VLANS) return -EINVAL; - ret = regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), - RTL8366RB_PORT_VLAN_CTRL_MASK << + ret = regmap_update_bits(priv->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), + RTL8366RB_PORT_VLAN_CTRL_MASK << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port), - (index & RTL8366RB_PORT_VLAN_CTRL_MASK) << + (index & RTL8366RB_PORT_VLAN_CTRL_MASK) << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)); if (ret) return ret; @@ -1604,17 +1608,17 @@ static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index) * not drop any untagged or C-tagged frames. Make sure to update the * filtering setting. */ - if (dsa_port_is_vlan_filtering(dsa_to_port(smi->ds, port))) - ret = rtl8366rb_drop_untagged(smi, port, !pvid_enabled); + if (dsa_port_is_vlan_filtering(dsa_to_port(priv->ds, port))) + ret = rtl8366rb_drop_untagged(priv, port, !pvid_enabled); return ret; } -static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) +static bool rtl8366rb_is_vlan_valid(struct realtek_priv *priv, unsigned int vlan) { unsigned int max = RTL8366RB_NUM_VLANS - 1; - if (smi->vlan4k_enabled) + if (priv->vlan4k_enabled) max = RTL8366RB_NUM_VIDS - 1; if (vlan > max) @@ -1623,23 +1627,23 @@ static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) return true; } -static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable) +static int rtl8366rb_enable_vlan(struct realtek_priv *priv, bool enable) { - dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable"); - return regmap_update_bits(smi->map, + dev_dbg(priv->dev, "%s VLAN\n", enable ? "enable" : "disable"); + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN, enable ? RTL8366RB_SGCR_EN_VLAN : 0); } -static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable) +static int rtl8366rb_enable_vlan4k(struct realtek_priv *priv, bool enable) { - dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable"); - return regmap_update_bits(smi->map, RTL8366RB_SGCR, + dev_dbg(priv->dev, "%s VLAN 4k\n", enable ? "enable" : "disable"); + return regmap_update_bits(priv->map, RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN_4KTB, enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0); } -static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum) +static int rtl8366rb_phy_read(struct realtek_priv *priv, int phy, int regnum) { u32 val; u32 reg; @@ -1648,32 +1652,32 @@ static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum) if (phy > RTL8366RB_PHY_NO_MAX) return -EINVAL; - ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG, RTL8366RB_PHY_CTRL_READ); if (ret) return ret; reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum; - ret = regmap_write(smi->map, reg, 0); + ret = regmap_write(priv->map, reg, 0); if (ret) { - dev_err(smi->dev, + dev_err(priv->dev, "failed to write PHY%d reg %04x @ %04x, ret %d\n", phy, regnum, reg, ret); return ret; } - ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val); if (ret) return ret; - dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n", + dev_dbg(priv->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n", phy, regnum, reg, val); return val; } -static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum, +static int rtl8366rb_phy_write(struct realtek_priv *priv, int phy, int regnum, u16 val) { u32 reg; @@ -1682,34 +1686,45 @@ static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum, if (phy > RTL8366RB_PHY_NO_MAX) return -EINVAL; - ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG, + ret = regmap_write(priv->map, RTL8366RB_PHY_ACCESS_CTRL_REG, RTL8366RB_PHY_CTRL_WRITE); if (ret) return ret; reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum; - dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n", + dev_dbg(priv->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n", phy, regnum, reg, val); - ret = regmap_write(smi->map, reg, val); + ret = regmap_write(priv->map, reg, val); if (ret) return ret; return 0; } -static int rtl8366rb_reset_chip(struct realtek_smi *smi) +static int rtl8366rb_dsa_phy_read(struct dsa_switch *ds, int phy, int regnum) +{ + return rtl8366rb_phy_read(ds->priv, phy, regnum); +} + +static int rtl8366rb_dsa_phy_write(struct dsa_switch *ds, int phy, int regnum, + u16 val) +{ + return rtl8366rb_phy_write(ds->priv, phy, regnum, val); +} + +static int rtl8366rb_reset_chip(struct realtek_priv *priv) { int timeout = 10; u32 val; int ret; - realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG, - RTL8366RB_CHIP_CTRL_RESET_HW); + priv->write_reg_noack(priv, RTL8366RB_RESET_CTRL_REG, + RTL8366RB_CHIP_CTRL_RESET_HW); do { usleep_range(20000, 25000); - ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val); + ret = regmap_read(priv->map, RTL8366RB_RESET_CTRL_REG, &val); if (ret) return ret; @@ -1718,21 +1733,21 @@ static int rtl8366rb_reset_chip(struct realtek_smi *smi) } while (--timeout); if (!timeout) { - dev_err(smi->dev, "timeout waiting for the switch to reset\n"); + dev_err(priv->dev, "timeout waiting for the switch to reset\n"); return -EIO; } return 0; } -static int rtl8366rb_detect(struct realtek_smi *smi) +static int rtl8366rb_detect(struct realtek_priv *priv) { - struct device *dev = smi->dev; + struct device *dev = priv->dev; int ret; u32 val; /* Detect device */ - ret = regmap_read(smi->map, 0x5c, &val); + ret = regmap_read(priv->map, 0x5c, &val); if (ret) { dev_err(dev, "can't get chip ID (%d)\n", ret); return ret; @@ -1745,11 +1760,11 @@ static int rtl8366rb_detect(struct realtek_smi *smi) return -ENODEV; case 0x5937: dev_info(dev, "found an RTL8366RB switch\n"); - smi->cpu_port = RTL8366RB_PORT_NUM_CPU; - smi->num_ports = RTL8366RB_NUM_PORTS; - smi->num_vlan_mc = RTL8366RB_NUM_VLANS; - smi->mib_counters = rtl8366rb_mib_counters; - smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters); + priv->cpu_port = RTL8366RB_PORT_NUM_CPU; + priv->num_ports = RTL8366RB_NUM_PORTS; + priv->num_vlan_mc = RTL8366RB_NUM_VLANS; + priv->mib_counters = rtl8366rb_mib_counters; + priv->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters); break; default: dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n", @@ -1757,14 +1772,14 @@ static int rtl8366rb_detect(struct realtek_smi *smi) break; } - ret = rtl8366rb_reset_chip(smi); + ret = rtl8366rb_reset_chip(priv); if (ret) return ret; return 0; } -static const struct dsa_switch_ops rtl8366rb_switch_ops = { +static const struct dsa_switch_ops rtl8366rb_switch_ops_smi = { .get_tag_protocol = rtl8366_get_tag_protocol, .setup = rtl8366rb_setup, .phylink_mac_link_up = rtl8366rb_mac_link_up, @@ -1787,7 +1802,32 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = { .port_max_mtu = rtl8366rb_max_mtu, }; -static const struct realtek_smi_ops rtl8366rb_smi_ops = { +static const struct dsa_switch_ops rtl8366rb_switch_ops_mdio = { + .get_tag_protocol = rtl8366_get_tag_protocol, + .setup = rtl8366rb_setup, + .phy_read = rtl8366rb_dsa_phy_read, + .phy_write = rtl8366rb_dsa_phy_write, + .phylink_mac_link_up = rtl8366rb_mac_link_up, + .phylink_mac_link_down = rtl8366rb_mac_link_down, + .get_strings = rtl8366_get_strings, + .get_ethtool_stats = rtl8366_get_ethtool_stats, + .get_sset_count = rtl8366_get_sset_count, + .port_bridge_join = rtl8366rb_port_bridge_join, + .port_bridge_leave = rtl8366rb_port_bridge_leave, + .port_vlan_filtering = rtl8366rb_vlan_filtering, + .port_vlan_add = rtl8366_vlan_add, + .port_vlan_del = rtl8366_vlan_del, + .port_enable = rtl8366rb_port_enable, + .port_disable = rtl8366rb_port_disable, + .port_pre_bridge_flags = rtl8366rb_port_pre_bridge_flags, + .port_bridge_flags = rtl8366rb_port_bridge_flags, + .port_stp_state_set = rtl8366rb_port_stp_state_set, + .port_fast_age = rtl8366rb_port_fast_age, + .port_change_mtu = rtl8366rb_change_mtu, + .port_max_mtu = rtl8366rb_max_mtu, +}; + +static const struct realtek_ops rtl8366rb_ops = { .detect = rtl8366rb_detect, .get_vlan_mc = rtl8366rb_get_vlan_mc, .set_vlan_mc = rtl8366rb_set_vlan_mc, @@ -1803,12 +1843,17 @@ static const struct realtek_smi_ops rtl8366rb_smi_ops = { .phy_write = rtl8366rb_phy_write, }; -const struct realtek_smi_variant rtl8366rb_variant = { - .ds_ops = &rtl8366rb_switch_ops, - .ops = &rtl8366rb_smi_ops, +const struct realtek_variant rtl8366rb_variant = { + .ds_ops_smi = &rtl8366rb_switch_ops_smi, + .ds_ops_mdio = &rtl8366rb_switch_ops_mdio, + .ops = &rtl8366rb_ops, .clk_delay = 10, .cmd_read = 0xa9, .cmd_write = 0xa8, .chip_data_sz = sizeof(struct rtl8366rb), }; EXPORT_SYMBOL_GPL(rtl8366rb_variant); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Driver for RTL8366RB ethernet switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 0730352cdd57..bc06fe6bac6b 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -442,34 +442,27 @@ static void xrs700x_teardown(struct dsa_switch *ds) cancel_delayed_work_sync(&priv->mib_work); } -static void xrs700x_phylink_validate(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state) +static void xrs700x_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - switch (port) { case 0: + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + config->mac_capabilities = MAC_10FD | MAC_100FD; break; + case 1: case 2: case 3: - phylink_set(mask, 1000baseT_Full); + phy_interface_set_rgmii(config->supported_interfaces); + config->mac_capabilities = MAC_10FD | MAC_100FD | MAC_1000FD; break; + default: - linkmode_zero(supported); dev_err(ds->dev, "Unsupported port: %i\n", port); - return; + break; } - - phylink_set_port_modes(mask); - - /* The switch only supports full duplex. */ - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Full); - - linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); } static void xrs700x_mac_link_up(struct dsa_switch *ds, int port, @@ -703,7 +696,7 @@ static const struct dsa_switch_ops xrs700x_ops = { .setup = xrs700x_setup, .teardown = xrs700x_teardown, .port_stp_state_set = xrs700x_port_stp_state_set, - .phylink_validate = xrs700x_phylink_validate, + .phylink_get_caps = xrs700x_phylink_get_caps, .phylink_mac_link_up = xrs700x_mac_link_up, .get_strings = xrs700x_get_strings, .get_sset_count = xrs700x_get_sset_count, diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 481f1df3106c..ad57209007e1 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -138,11 +138,6 @@ MODULE_PARM_DESC(use_mmio, "Use MMIO (1) or PIO(0) to access the NIC. " module_param(rx_copybreak, int, 0); module_param(use_mmio, int, 0); -#if defined(NETIF_F_TSO) && MAX_SKB_FRAGS > 32 -#warning Typhoon only supports 32 entries in its SG list for TSO, disabling TSO -#undef NETIF_F_TSO -#endif - #if TXLO_ENTRIES <= (2 * MAX_SKB_FRAGS) #error TX ring too small! #endif @@ -2261,9 +2256,28 @@ out: return mode; } +#if MAX_SKB_FRAGS > 32 + +#include <net/vxlan.h> + +static netdev_features_t typhoon_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->nr_frags > 32 && skb_is_gso(skb)) + features &= ~NETIF_F_GSO_MASK; + + features = vlan_features_check(skb, features); + return vxlan_features_check(skb, features); +} +#endif + static const struct net_device_ops typhoon_netdev_ops = { .ndo_open = typhoon_open, .ndo_stop = typhoon_close, +#if MAX_SKB_FRAGS > 32 + .ndo_features_check = typhoon_features_check, +#endif .ndo_start_xmit = typhoon_start_tx, .ndo_set_rx_mode = typhoon_set_rx_mode, .ndo_tx_timeout = typhoon_tx_timeout, @@ -2278,6 +2292,7 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *dev; struct typhoon *tp; int card_id = (int) ent->driver_data; + u8 addr[ETH_ALEN] __aligned(4); void __iomem *ioaddr; void *shared; dma_addr_t shared_dma; @@ -2409,8 +2424,9 @@ typhoon_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto error_out_reset; } - *(__be16 *)&dev->dev_addr[0] = htons(le16_to_cpu(xp_resp[0].parm1)); - *(__be32 *)&dev->dev_addr[2] = htonl(le32_to_cpu(xp_resp[0].parm2)); + *(__be16 *)&addr[0] = htons(le16_to_cpu(xp_resp[0].parm1)); + *(__be32 *)&addr[2] = htonl(le32_to_cpu(xp_resp[0].parm2)); + eth_hw_addr_set(dev, addr); if (!is_valid_ether_addr(dev->dev_addr)) { err_msg = "Could not obtain valid ethernet address, aborting"; diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index bd22a534b1c0..e7b879123bb1 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -655,6 +655,7 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) struct ei_device *ei_local; struct net_device *dev; struct etherh_priv *eh; + u8 addr[ETH_ALEN]; int ret; ret = ecard_request_resources(ec); @@ -724,12 +725,13 @@ etherh_probe(struct expansion_card *ec, const struct ecard_id *id) spin_lock_init(&ei_local->page_lock); if (ec->cid.product == PROD_ANT_ETHERM) { - etherm_addr(dev->dev_addr); + etherm_addr(addr); ei_local->reg_offset = etherm_regoffsets; } else { - etherh_addr(dev->dev_addr, ec); + etherh_addr(addr, ec); ei_local->reg_offset = etherh_regoffsets; } + eth_hw_addr_set(dev, addr); ei_local->name = dev->name; ei_local->word16 = 1; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 53080fd143dc..07444aead3fd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -1400,10 +1400,9 @@ static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, void *first_frag) struct sk_buff *skb; if (!first_frag) - skb = netdev_alloc_skb_ip_align(rx_ring->netdev, - rx_ring->rx_copybreak); + skb = napi_alloc_skb(rx_ring->napi, rx_ring->rx_copybreak); else - skb = build_skb(first_frag, ENA_PAGE_SIZE); + skb = napi_build_skb(first_frag, ENA_PAGE_SIZE); if (unlikely(!skb)) { ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1, diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 493b0cefcc2a..ec8df05e7bf6 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -1032,6 +1032,7 @@ static int dec_lance_probe(struct device *bdev, const int type) int i, ret; unsigned long esar_base; unsigned char *esar; + u8 addr[ETH_ALEN]; const char *desc; if (dec_lance_debug && version_printed++ == 0) @@ -1228,7 +1229,8 @@ static int dec_lance_probe(struct device *bdev, const int type) break; } for (i = 0; i < 6; i++) - dev->dev_addr[i] = esar[i * 4]; + addr[i] = esar[i * 4]; + eth_hw_addr_set(dev, addr); printk("%s: %s, addr = %pM, irq = %d\n", name, desc, dev->dev_addr, dev->irq); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 492ac383f16d..a3593290886f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -721,7 +721,9 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata) if (!channel->tx_ring) break; + /* Deactivate the Tx timer */ del_timer_sync(&channel->tx_timer); + channel->tx_timer_active = 0; } } @@ -2550,6 +2552,14 @@ read_again: buf2_len = xgbe_rx_buf2_len(rdata, packet, len); len += buf2_len; + if (buf2_len > rdata->rx.buf.dma_len) { + /* Hardware inconsistency within the descriptors + * that has resulted in a length underflow. + */ + error = 1; + goto skip_data; + } + if (!skb) { skb = xgbe_create_skb(pdata, napi, rdata, buf1_len); @@ -2579,8 +2589,10 @@ skip_data: if (!last || context_next) goto read_again; - if (!skb) + if (!skb || error) { + dev_kfree_skb(skb); goto next_packet; + } /* Be sure we don't exceed the configured MTU */ max_len = netdev->mtu + ETH_HLEN; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 1bc4d33a0ce5..30a573db02bb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -826,7 +826,6 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic) struct aq_hw_s *aq_hw = aq_nic->aq_hw; int hweight = 0; int err = 0; - int i; if (unlikely(!aq_hw_ops->hw_filter_vlan_set)) return -EOPNOTSUPP; @@ -837,8 +836,7 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic) aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans); if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) { - for (i = 0; i < BITS_TO_LONGS(VLAN_N_VID); i++) - hweight += hweight_long(aq_nic->active_vlans[i]); + hweight = bitmap_weight(aq_nic->active_vlans, VLAN_N_VID); err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false); if (err) @@ -871,7 +869,7 @@ int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic) struct aq_hw_s *aq_hw = aq_nic->aq_hw; int err = 0; - memset(aq_nic->active_vlans, 0, sizeof(aq_nic->active_vlans)); + bitmap_zero(aq_nic->active_vlans, VLAN_N_VID); aq_fvlan_rebuild(aq_nic, aq_nic->active_vlans, aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index a19dd6797070..447a75ea0cc1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1271,7 +1271,7 @@ struct bnx2x_fw_stats_data { struct per_port_stats port; struct per_pf_stats pf; struct fcoe_statistics_params fcoe; - struct per_queue_stats queue_stats[1]; + struct per_queue_stats queue_stats[]; }; /* Public slow path states */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4f94136a011a..c313221348c5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -233,6 +233,7 @@ static const u16 bnxt_async_events_arr[] = { ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST, ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP, ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT, + ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE, }; static struct workqueue_struct *bnxt_pf_wq; @@ -2079,6 +2080,16 @@ static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) (BNXT_EVENT_RING_TYPE(data2) == \ ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX) +#define BNXT_EVENT_PHC_EVENT_TYPE(data1) \ + (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK) >>\ + ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT) + +#define BNXT_EVENT_PHC_RTC_UPDATE(data1) \ + (((data1) & ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK) >>\ + ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT) + +#define BNXT_PHC_BITS 48 + static int bnxt_async_event_process(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl) { @@ -2258,6 +2269,24 @@ static int bnxt_async_event_process(struct bnxt *bp, bnxt_event_error_report(bp, data1, data2); goto async_event_process_exit; } + case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: { + switch (BNXT_EVENT_PHC_EVENT_TYPE(data1)) { + case ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE: + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u64 ns; + + spin_lock_bh(&ptp->ptp_lock); + bnxt_ptp_update_current_time(bp); + ns = (((u64)BNXT_EVENT_PHC_RTC_UPDATE(data1) << + BNXT_PHC_BITS) | ptp->current_time); + bnxt_ptp_rtc_timecounter_init(ptp, ns); + spin_unlock_bh(&ptp->ptp_lock); + } + break; + } + goto async_event_process_exit; + } case ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE: { u16 seq_id = le32_to_cpu(cmpl->event_data2) & 0xffff; @@ -7414,6 +7443,7 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) struct hwrm_port_mac_ptp_qcfg_output *resp; struct hwrm_port_mac_ptp_qcfg_input *req; struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + bool phc_cfg; u8 flags; int rc; @@ -7456,7 +7486,8 @@ static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) rc = -ENODEV; goto exit; } - rc = bnxt_ptp_init(bp); + phc_cfg = (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED) != 0; + rc = bnxt_ptp_init(bp, phc_cfg); if (rc) netdev_warn(bp->dev, "PTP initialization failed.\n"); exit: @@ -7514,6 +7545,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_PTP_PPS; + if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_PTP_RTC; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT)) bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED)) @@ -10288,6 +10321,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* VF-reps may need to be re-opened after the PF is re-opened */ if (BNXT_PF(bp)) bnxt_vf_reps_open(bp); + bnxt_ptp_init_rtc(bp, true); return 0; open_err_irq: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 440dfeb4948b..4b023e35c765 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1957,6 +1957,7 @@ struct bnxt { #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_FW_CAP_HOT_RESET 0x00200000 + #define BNXT_FW_CAP_PTP_RTC 0x00400000 #define BNXT_FW_CAP_VLAN_RX_STRIP 0x01000000 #define BNXT_FW_CAP_VLAN_TX_INSERT 0x02000000 #define BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED 0x04000000 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 003330e8cd58..5edbee92f5c4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -11,6 +11,7 @@ #include <linux/ctype.h> #include <linux/stringify.h> #include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> #include <linux/linkmode.h> #include <linux/interrupt.h> #include <linux/pci.h> @@ -802,9 +803,11 @@ static void bnxt_get_ringparam(struct net_device *dev, if (bp->flags & BNXT_FLAG_AGG_RINGS) { ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT_JUM_ENA; ering->rx_jumbo_max_pending = BNXT_MAX_RX_JUM_DESC_CNT; + kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } else { ering->rx_max_pending = BNXT_MAX_RX_DESC_CNT; ering->rx_jumbo_max_pending = 0; + kernel_ering->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED; } ering->tx_max_pending = BNXT_MAX_TX_DESC_CNT; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index ea86c54247c7..b7100edbd6dd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -369,6 +369,12 @@ struct cmd_nums { #define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL #define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL #define HWRM_FUNC_KEY_CTX_ALLOC 0x1a2UL + #define HWRM_FUNC_BACKING_STORE_CFG_V2 0x1a3UL + #define HWRM_FUNC_BACKING_STORE_QCFG_V2 0x1a4UL + #define HWRM_FUNC_DBR_PACING_CFG 0x1a5UL + #define HWRM_FUNC_DBR_PACING_QCFG 0x1a6UL + #define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT 0x1a7UL + #define HWRM_FUNC_BACKING_STORE_QCAPS_V2 0x1a8UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -390,6 +396,9 @@ struct cmd_nums { #define HWRM_MFG_PRVSN_IMPORT_CERT 0x212UL #define HWRM_MFG_PRVSN_GET_STATE 0x213UL #define HWRM_MFG_GET_NVM_MEASUREMENT 0x214UL + #define HWRM_MFG_PSOC_QSTATUS 0x215UL + #define HWRM_MFG_SELFTEST_QLIST 0x216UL + #define HWRM_MFG_SELFTEST_EXEC 0x217UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -532,8 +541,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 63 -#define HWRM_VERSION_STR "1.10.2.63" +#define HWRM_VERSION_RSVD 73 +#define HWRM_VERSION_STR "1.10.2.73" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -757,10 +766,11 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE 0x40UL #define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE 0x41UL #define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST 0x42UL - #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_MASTER 0x43UL + #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE 0x43UL #define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP 0x44UL #define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT 0x45UL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x46UL + #define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD 0x46UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x47UL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1112,34 +1122,37 @@ struct hwrm_async_event_cmpl_echo_request { __le32 event_data1; }; -/* hwrm_async_event_cmpl_phc_master (size:128b/16B) */ -struct hwrm_async_event_cmpl_phc_master { +/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */ +struct hwrm_async_event_cmpl_phc_update { __le16 type; - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_MASK 0x3fUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT 0x2eUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_LAST ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT __le16 event_id; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER 0x43UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE __le32 event_data2; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_SFT 16 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT 16 u8 opaque_v; - #define ASYNC_EVENT_CMPL_PHC_MASTER_V 0x1UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_MASK 0xfeUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_SFT 1 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_V 0x1UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1 u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_MASK 0xfUL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_SFT 0 - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL - #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK 0xfUL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE 0x4UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK 0xffff0UL + #define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT 4 }; /* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */ @@ -1330,6 +1343,30 @@ struct hwrm_async_event_cmpl_error_report_nvm { #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE }; +/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD +}; + /* hwrm_func_reset_input (size:192b/24B) */ struct hwrm_func_reset_input { __le16 req_type; @@ -1589,6 +1626,10 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL 0x800000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED 0x1000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP 0x2000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED 0x4000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED 0x8000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED 0x10000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED 0x20000000UL u8 max_schqs; u8 mpc_chnls_cap; #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE 0x1UL @@ -2455,7 +2496,7 @@ struct hwrm_func_backing_store_qcaps_output { __le16 rkc_entry_size; __le32 tkc_max_entries; __le32 rkc_max_entries; - u8 rsvd[7]; + u8 rsvd1[7]; u8 valid; }; @@ -3164,7 +3205,7 @@ struct hwrm_func_ptp_pin_cfg_output { u8 valid; }; -/* hwrm_func_ptp_cfg_input (size:320b/40B) */ +/* hwrm_func_ptp_cfg_input (size:384b/48B) */ struct hwrm_func_ptp_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -3178,6 +3219,7 @@ struct hwrm_func_ptp_cfg_input { #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD 0x8UL #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP 0x10UL #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE 0x20UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME 0x40UL u8 ptp_pps_event; #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL 0x1UL #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL 0x2UL @@ -3204,6 +3246,7 @@ struct hwrm_func_ptp_cfg_input { __le32 ptp_freq_adj_ext_up; __le32 ptp_freq_adj_ext_phase_lower; __le32 ptp_freq_adj_ext_phase_upper; + __le64 ptp_set_time; }; /* hwrm_func_ptp_cfg_output (size:128b/16B) */ @@ -3243,6 +3286,308 @@ struct hwrm_func_ptp_ts_query_output { u8 valid; }; +/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */ +struct hwrm_func_ptp_ext_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 enables; + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID 0x1UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID 0x2UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE 0x4UL + #define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER 0x8UL + __le16 phc_master_fid; + __le16 phc_sec_fid; + u8 phc_sec_mode; + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH 0x0UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL 0x1UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL + #define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY + u8 unused_0; + __le32 failover_timer; + u8 unused_1[4]; +}; + +/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */ +struct hwrm_func_ptp_ext_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */ +struct hwrm_func_ptp_ext_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 unused_0[8]; +}; + +/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */ +struct hwrm_func_ptp_ext_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 phc_master_fid; + __le16 phc_sec_fid; + __le16 phc_active_fid0; + __le16 phc_active_fid1; + __le32 last_failover_event; + __le16 from_fid; + __le16 to_fid; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_backing_store_cfg_v2_input (size:448b/56B) */ +struct hwrm_func_backing_store_cfg_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID + __le16 instance; + __le32 flags; + #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL + __le64 page_dir; + __le32 num_entries; + __le16 entry_size; + u8 page_size_pbl_level; + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT 0 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G + u8 subtype_valid_cnt; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; +}; + +/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */ +struct hwrm_func_backing_store_cfg_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 rsvd0[7]; + u8 valid; +}; + +/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */ +struct hwrm_func_backing_store_qcfg_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID + __le16 instance; + u8 rsvd[4]; +}; + +/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */ +struct hwrm_func_backing_store_qcfg_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 type; + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID + __le16 instance; + __le32 flags; + __le64 page_dir; + __le32 num_entries; + u8 page_size_pbl_level; + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT 0 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT 4 + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G + u8 subtype_valid_cnt; + u8 rsvd[2]; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; + u8 rsvd2[7]; + u8 valid; +}; + +/* qpc_split_entries (size:128b/16B) */ +struct qpc_split_entries { + __le32 qp_num_l2_entries; + __le32 qp_num_qp1_entries; + __le32 rsvd[2]; +}; + +/* srq_split_entries (size:128b/16B) */ +struct srq_split_entries { + __le32 srq_num_l2_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* cq_split_entries (size:128b/16B) */ +struct cq_split_entries { + __le32 cq_num_l2_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* vnic_split_entries (size:128b/16B) */ +struct vnic_split_entries { + __le32 vnic_num_vnic_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* mrav_split_entries (size:128b/16B) */ +struct mrav_split_entries { + __le32 mrav_num_av_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + +/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */ +struct hwrm_func_backing_store_qcaps_v2_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 type; + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID + u8 rsvd[6]; +}; + +/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */ +struct hwrm_func_backing_store_qcaps_v2_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 type; + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TKC 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RKC 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID + __le16 entry_size; + __le32 flags; + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID 0x2UL + __le32 instance_bit_map; + u8 ctx_init_value; + u8 ctx_init_offset; + u8 entry_multiple; + u8 rsvd; + __le32 max_num_entries; + __le32 min_num_entries; + __le16 next_valid_type; + u8 subtype_valid_cnt; + u8 rsvd2; + __le32 split_entry_0; + __le32 split_entry_1; + __le32 split_entry_2; + __le32 split_entry_3; + u8 rsvd3[3]; + u8 valid; +}; + /* hwrm_func_drv_if_change_input (size:192b/24B) */ struct hwrm_func_drv_if_change_input { __le16 req_type; @@ -3741,7 +4086,7 @@ struct hwrm_port_phy_qcfg_output { u8 valid; }; -/* hwrm_port_mac_cfg_input (size:384b/48B) */ +/* hwrm_port_mac_cfg_input (size:448b/56B) */ struct hwrm_port_mac_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -3807,7 +4152,8 @@ struct hwrm_port_mac_cfg_input { #define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT 5 u8 unused_0[3]; __le32 ptp_freq_adj_ppb; - __le32 ptp_adj_phase; + u8 unused_1[4]; + __le64 ptp_adj_phase; }; /* hwrm_port_mac_cfg_output (size:128b/16B) */ @@ -3850,6 +4196,7 @@ struct hwrm_port_mac_ptp_qcfg_output { #define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS 0x4UL #define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x8UL #define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK 0x10UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED 0x20UL u8 unused_0[3]; __le32 rx_ts_reg_off_lower; __le32 rx_ts_reg_off_upper; @@ -4339,7 +4686,8 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_PORT_CNT_2 0x2UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_3 0x3UL #define PORT_PHY_QCAPS_RESP_PORT_CNT_4 0x4UL - #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_4 + #define PORT_PHY_QCAPS_RESP_PORT_CNT_12 0xcUL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST PORT_PHY_QCAPS_RESP_PORT_CNT_12 __le16 supported_speeds_force_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL @@ -4399,7 +4747,7 @@ struct hwrm_port_phy_qcaps_output { __le16 flags2; #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL - u8 unused_0[1]; + u8 internal_port_cnt; u8 valid; }; @@ -6221,12 +6569,13 @@ struct hwrm_vnic_rss_cfg_input { __le16 target_id; __le64 resp_addr; __le32 hash_type; - #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL - #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 0x1UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 0x2UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 0x4UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 0x8UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6 0x10UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL 0x40UL __le16 vnic_id; u8 ring_table_pair_index; u8 hash_mode_flags; @@ -7898,6 +8247,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output { u8 valid; }; +/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */ struct hwrm_tunnel_dst_port_query_input { __le16 req_type; __le16 cmpl_ring; @@ -8909,6 +9259,50 @@ struct hwrm_dbg_qcfg_output { u8 valid; }; +/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */ +struct hwrm_dbg_crashdump_medium_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 output_dest_flags; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR 0x1UL + __le16 pg_size_lvl; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK 0x3UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT 0 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0 0x0UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1 0x1UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2 0x2UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK 0x1cUL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT 2 + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K (0x0UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K (0x1UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K (0x2UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M (0x3UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M (0x4UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G (0x5UL << 2) + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT 5 + __le32 size; + __le32 coredump_component_disable_flags; + #define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM 0x1UL + __le32 unused_0; + __le64 pbl; +}; + +/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */ +struct hwrm_dbg_crashdump_medium_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_1[7]; + u8 valid; +}; + /* coredump_segment_record (size:128b/16B) */ struct coredump_segment_record { __le16 component_id; @@ -9372,8 +9766,35 @@ struct hwrm_nvm_install_update_output { __le16 resp_len; __le64 installed_items; u8 result; - #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL - #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS + #define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS 0x0UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE 0xffUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE 0xfdUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER 0xfbUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER 0xf3UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE 0xf2UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER 0xecUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE 0xebUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM 0xeaUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH 0xe9UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST 0xe8UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER 0xe7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM 0xe6UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM 0xe5UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH 0xe4UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE 0xe1UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV 0xceUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID 0xcdUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR 0xccUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID 0xcbUL + #define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM 0xc5UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM 0xc4UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM 0xc3UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR 0xb9UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR 0xb8UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND 0xb0UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED 0xa7UL + #define NVM_INSTALL_UPDATE_RESP_RESULT_LAST NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED u8 problem_item; #define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE 0x0UL #define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 48520967746f..a0b321a19361 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -19,6 +19,20 @@ #include "bnxt_hwrm.h" #include "bnxt_ptp.h" +static int bnxt_ptp_cfg_settime(struct bnxt *bp, u64 time) +{ + struct hwrm_func_ptp_cfg_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_FUNC_PTP_CFG); + if (rc) + return rc; + + req->enables = cpu_to_le16(FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME); + req->ptp_set_time = cpu_to_le64(time); + return hwrm_req_send(bp, req); +} + int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off) { unsigned int ptp_class; @@ -48,6 +62,9 @@ static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info, ptp_info); u64 ns = timespec64_to_ns(ts); + if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + return bnxt_ptp_cfg_settime(ptp->bp, ns); + spin_lock_bh(&ptp->ptp_lock); timecounter_init(&ptp->tc, &ptp->cc, ns); spin_unlock_bh(&ptp->ptp_lock); @@ -131,11 +148,47 @@ static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info, return 0; } +/* Caller holds ptp_lock */ +void bnxt_ptp_update_current_time(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + bnxt_refclk_read(ptp->bp, NULL, &ptp->current_time); + WRITE_ONCE(ptp->old_time, ptp->current_time); +} + +static int bnxt_ptp_adjphc(struct bnxt_ptp_cfg *ptp, s64 delta) +{ + struct hwrm_port_mac_cfg_input *req; + int rc; + + rc = hwrm_req_init(ptp->bp, req, HWRM_PORT_MAC_CFG); + if (rc) + return rc; + + req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE); + req->ptp_adj_phase = cpu_to_le64(delta); + + rc = hwrm_req_send(ptp->bp, req); + if (rc) { + netdev_err(ptp->bp->dev, "ptp adjphc failed. rc = %x\n", rc); + } else { + spin_lock_bh(&ptp->ptp_lock); + bnxt_ptp_update_current_time(ptp->bp); + spin_unlock_bh(&ptp->ptp_lock); + } + + return rc; +} + static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) { struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, ptp_info); + if (ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + return bnxt_ptp_adjphc(ptp, delta); + spin_lock_bh(&ptp->ptp_lock); timecounter_adjtime(&ptp->tc, delta); spin_unlock_bh(&ptp->ptp_lock); @@ -714,7 +767,70 @@ static bool bnxt_pps_config_ok(struct bnxt *bp) return !(bp->fw_cap & BNXT_FW_CAP_PTP_PPS) == !ptp->ptp_info.pin_config; } -int bnxt_ptp_init(struct bnxt *bp) +static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (!ptp->ptp_clock) { + memset(&ptp->cc, 0, sizeof(ptp->cc)); + ptp->cc.read = bnxt_cc_read; + ptp->cc.mask = CYCLECOUNTER_MASK(48); + ptp->cc.shift = 0; + ptp->cc.mult = 1; + ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; + } + if (init_tc) + timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); +} + +/* Caller holds ptp_lock */ +void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns) +{ + timecounter_init(&ptp->tc, &ptp->cc, ns); + /* For RTC, cycle_last must be in sync with the timecounter value. */ + ptp->tc.cycle_last = ns & ptp->cc.mask; +} + +int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg) +{ + struct timespec64 tsp; + u64 ns; + int rc; + + if (!bp->ptp_cfg || !(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + return -ENODEV; + + if (!phc_cfg) { + ktime_get_real_ts64(&tsp); + ns = timespec64_to_ns(&tsp); + rc = bnxt_ptp_cfg_settime(bp, ns); + if (rc) + return rc; + } else { + rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME, &ns); + if (rc) + return rc; + } + spin_lock_bh(&bp->ptp_cfg->ptp_lock); + bnxt_ptp_rtc_timecounter_init(bp->ptp_cfg, ns); + spin_unlock_bh(&bp->ptp_cfg->ptp_lock); + + return 0; +} + +static void bnxt_ptp_free(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (ptp->ptp_clock) { + ptp_clock_unregister(ptp->ptp_clock); + ptp->ptp_clock = NULL; + kfree(ptp->ptp_info.pin_config); + ptp->ptp_info.pin_config = NULL; + } +} + +int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg) { struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; int rc; @@ -726,26 +842,23 @@ int bnxt_ptp_init(struct bnxt *bp) if (rc) return rc; + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) { + bnxt_ptp_timecounter_init(bp, false); + rc = bnxt_ptp_init_rtc(bp, phc_cfg); + if (rc) + goto out; + } + if (ptp->ptp_clock && bnxt_pps_config_ok(bp)) return 0; - if (ptp->ptp_clock) { - ptp_clock_unregister(ptp->ptp_clock); - ptp->ptp_clock = NULL; - kfree(ptp->ptp_info.pin_config); - ptp->ptp_info.pin_config = NULL; - } + bnxt_ptp_free(bp); + atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS); spin_lock_init(&ptp->ptp_lock); - memset(&ptp->cc, 0, sizeof(ptp->cc)); - ptp->cc.read = bnxt_cc_read; - ptp->cc.mask = CYCLECOUNTER_MASK(48); - ptp->cc.shift = 0; - ptp->cc.mult = 1; - - ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; - timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + if (!(bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) + bnxt_ptp_timecounter_init(bp, true); ptp->ptp_info = bnxt_ptp_caps; if ((bp->fw_cap & BNXT_FW_CAP_PTP_PPS)) { @@ -757,8 +870,8 @@ int bnxt_ptp_init(struct bnxt *bp) int err = PTR_ERR(ptp->ptp_clock); ptp->ptp_clock = NULL; - bnxt_unmap_ptp_regs(bp); - return err; + rc = err; + goto out; } if (bp->flags & BNXT_FLAG_CHIP_P5) { spin_lock_bh(&ptp->ptp_lock); @@ -768,6 +881,11 @@ int bnxt_ptp_init(struct bnxt *bp) ptp_schedule_worker(ptp->ptp_clock, 0); } return 0; + +out: + bnxt_ptp_free(bp); + bnxt_unmap_ptp_regs(bp); + return rc; } void bnxt_ptp_clear(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 7c528e1f8713..373baf45884b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -131,12 +131,15 @@ do { \ #endif int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id, u16 *hdr_off); +void bnxt_ptp_update_current_time(struct bnxt *bp); void bnxt_ptp_pps_event(struct bnxt *bp, u32 data1, u32 data2); void bnxt_ptp_reapply_pps(struct bnxt *bp); int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts); -int bnxt_ptp_init(struct bnxt *bp); +void bnxt_ptp_rtc_timecounter_init(struct bnxt_ptp_cfg *ptp, u64 ns); +int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg); +int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg); void bnxt_ptp_clear(struct bnxt *bp); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 87f1056e29ff..cfe09117fe6c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1368,7 +1368,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_eee *e) if (!p->eee_enabled) { bcmgenet_eee_enable_set(dev, false); } else { - ret = phy_init_eee(dev->phydev, 0); + ret = phy_init_eee(dev->phydev, false); if (ret) { netif_err(priv, hw, dev, "EEE initialization failed\n"); return ret; diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index f38f40eb966e..a1a38456c9a3 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -2183,9 +2183,7 @@ static int sbmac_init(struct platform_device *pldev, long long base) ea_reg >>= 8; } - for (i = 0; i < 6; i++) { - dev->dev_addr[i] = eaddr[i]; - } + eth_hw_addr_set(dev, eaddr); /* * Initialize context (get pointers to registers and stuff), then diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 9ddbee7de72b..f0a7d8396a4a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -12,6 +12,7 @@ #include <linux/ptp_clock_kernel.h> #include <linux/net_tstamp.h> #include <linux/interrupt.h> +#include <linux/phy/phy.h> #if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP) #define MACB_EXT_DESC @@ -1291,6 +1292,9 @@ struct macb { u32 wol; struct macb_ptp_info *ptp_info; /* macb-ptp interface */ + + struct phy *sgmii_phy; /* for ZynqMP SGMII mode */ + #ifdef MACB_EXT_DESC uint8_t hw_dma_cap; #endif diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index a363da928e8b..1ce20bf52f72 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -34,7 +34,9 @@ #include <linux/udp.h> #include <linux/tcp.h> #include <linux/iopoll.h> +#include <linux/phy/phy.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include "macb.h" /* This structure is only used for MACB on SiFive FU540 devices */ @@ -2739,10 +2741,14 @@ static int macb_open(struct net_device *dev) macb_init_hw(bp); - err = macb_phylink_connect(bp); + err = phy_power_on(bp->sgmii_phy); if (err) goto reset_hw; + err = macb_phylink_connect(bp); + if (err) + goto phy_off; + netif_tx_start_all_queues(dev); if (bp->ptp_info) @@ -2750,6 +2756,9 @@ static int macb_open(struct net_device *dev) return 0; +phy_off: + phy_power_off(bp->sgmii_phy); + reset_hw: macb_reset_hw(bp); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) @@ -2775,6 +2784,8 @@ static int macb_close(struct net_device *dev) phylink_stop(bp->phylink); phylink_disconnect_phy(bp->phylink); + phy_power_off(bp->sgmii_phy); + spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); netif_carrier_off(dev); @@ -4544,13 +4555,55 @@ static const struct macb_config np4_config = { .usrio = &macb_default_usrio, }; +static int zynqmp_init(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + struct macb *bp = netdev_priv(dev); + int ret; + + if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) { + /* Ensure PS-GTR PHY device used in SGMII mode is ready */ + bp->sgmii_phy = devm_phy_get(&pdev->dev, "sgmii-phy"); + + if (IS_ERR(bp->sgmii_phy)) { + ret = PTR_ERR(bp->sgmii_phy); + dev_err_probe(&pdev->dev, ret, + "failed to get PS-GTR PHY\n"); + return ret; + } + + ret = phy_init(bp->sgmii_phy); + if (ret) { + dev_err(&pdev->dev, "failed to init PS-GTR PHY: %d\n", + ret); + return ret; + } + } + + /* Fully reset GEM controller at hardware level using zynqmp-reset driver, + * if mapped in device tree. + */ + ret = device_reset_optional(&pdev->dev); + if (ret) { + dev_err_probe(&pdev->dev, ret, "failed to reset controller"); + phy_exit(bp->sgmii_phy); + return ret; + } + + ret = macb_init(pdev); + if (ret) + phy_exit(bp->sgmii_phy); + + return ret; +} + static const struct macb_config zynqmp_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH, .dma_burst_length = 16, .clk_init = macb_clk_init, - .init = macb_init, + .init = zynqmp_init, .jumbo_max_len = 10240, .usrio = &macb_default_usrio, }; @@ -4767,7 +4820,7 @@ static int macb_probe(struct platform_device *pdev) err = macb_mii_init(bp); if (err) - goto err_out_free_netdev; + goto err_out_phy_exit; netif_carrier_off(dev); @@ -4792,6 +4845,9 @@ err_out_unregister_mdio: mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); +err_out_phy_exit: + phy_exit(bp->sgmii_phy); + err_out_free_netdev: free_netdev(dev); @@ -4813,6 +4869,7 @@ static int macb_remove(struct platform_device *pdev) if (dev) { bp = netdev_priv(dev); + phy_exit(bp->sgmii_phy); mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 574a32f23f96..2f6484dc186a 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1409,7 +1409,8 @@ static acpi_status bgx_acpi_register_phy(acpi_handle handle, struct device *dev = &bgx->pdev->dev; struct acpi_device *adev; - if (acpi_bus_get_device(handle, &adev)) + adev = acpi_fetch_acpi_dev(handle); + if (!adev) goto out; acpi_get_mac_address(dev, adev, bgx->lmac[bgx->acpi_lmac_idx].mac); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index c78b99a497df..8014eb33937c 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2363,11 +2363,13 @@ static void gemini_port_save_mac_addr(struct gemini_ethernet_port *port) static int gemini_ethernet_port_probe(struct platform_device *pdev) { char *port_names[2] = { "ethernet0", "ethernet1" }; + struct device_node *np = pdev->dev.of_node; struct gemini_ethernet_port *port; struct device *dev = &pdev->dev; struct gemini_ethernet *geth; struct net_device *netdev; struct device *parent; + u8 mac[ETH_ALEN]; unsigned int id; int irq; int ret; @@ -2473,6 +2475,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) netif_napi_add(netdev, &port->napi, gmac_napi_poll, DEFAULT_NAPI_WEIGHT); + ret = of_get_mac_address(np, mac); + if (!ret) { + dev_info(dev, "Setting macaddr from DT %pM\n", mac); + memcpy(port->mac_addr, mac, ETH_ALEN); + } + if (is_valid_ether_addr((void *)port->mac_addr)) { eth_hw_addr_set(netdev, (u8 *)port->mac_addr); } else { diff --git a/drivers/net/ethernet/dec/tulip/pnic.c b/drivers/net/ethernet/dec/tulip/pnic.c index 3fb39e32e1b4..653bde48ef44 100644 --- a/drivers/net/ethernet/dec/tulip/pnic.c +++ b/drivers/net/ethernet/dec/tulip/pnic.c @@ -21,7 +21,7 @@ void pnic_do_nway(struct net_device *dev) struct tulip_private *tp = netdev_priv(dev); void __iomem *ioaddr = tp->base_addr; u32 phy_reg = ioread32(ioaddr + 0xB8); - u32 new_csr6 = tp->csr6 & ~0x40C40200; + u32 new_csr6; if (phy_reg & 0x78000000) { /* Ignore baseT4 */ if (phy_reg & 0x20000000) dev->if_port = 5; diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index c710dc17be90..8dd7bf9014ec 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -340,7 +340,7 @@ enum wake_event_bits { struct netdev_desc { __le32 next_desc; __le32 status; - struct desc_frag { __le32 addr, length; } frag[1]; + struct desc_frag { __le32 addr, length; } frag; }; /* Bits in netdev_desc.status */ @@ -980,8 +980,8 @@ static void tx_timeout(struct net_device *dev, unsigned int txqueue) le32_to_cpu(np->tx_ring[i].next_desc), le32_to_cpu(np->tx_ring[i].status), (le32_to_cpu(np->tx_ring[i].status) >> 2) & 0xff, - le32_to_cpu(np->tx_ring[i].frag[0].addr), - le32_to_cpu(np->tx_ring[i].frag[0].length)); + le32_to_cpu(np->tx_ring[i].frag.addr), + le32_to_cpu(np->tx_ring[i].frag.length)); } printk(KERN_DEBUG "TxListPtr=%08x netif_queue_stopped=%d\n", ioread32(np->base + TxListPtr), @@ -1027,7 +1027,7 @@ static void init_ring(struct net_device *dev) np->rx_ring[i].next_desc = cpu_to_le32(np->rx_ring_dma + ((i+1)%RX_RING_SIZE)*sizeof(*np->rx_ring)); np->rx_ring[i].status = 0; - np->rx_ring[i].frag[0].length = 0; + np->rx_ring[i].frag.length = 0; np->rx_skbuff[i] = NULL; } @@ -1039,16 +1039,16 @@ static void init_ring(struct net_device *dev) if (skb == NULL) break; skb_reserve(skb, 2); /* 16 byte align the IP header. */ - np->rx_ring[i].frag[0].addr = cpu_to_le32( + np->rx_ring[i].frag.addr = cpu_to_le32( dma_map_single(&np->pci_dev->dev, skb->data, np->rx_buf_sz, DMA_FROM_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - np->rx_ring[i].frag[0].addr)) { + np->rx_ring[i].frag.addr)) { dev_kfree_skb(skb); np->rx_skbuff[i] = NULL; break; } - np->rx_ring[i].frag[0].length = cpu_to_le32(np->rx_buf_sz | LastFrag); + np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); } np->dirty_rx = (unsigned int)(i - RX_RING_SIZE); @@ -1097,12 +1097,12 @@ start_tx (struct sk_buff *skb, struct net_device *dev) txdesc->next_desc = 0; txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign); - txdesc->frag[0].addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev, + txdesc->frag.addr = cpu_to_le32(dma_map_single(&np->pci_dev->dev, skb->data, skb->len, DMA_TO_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - txdesc->frag[0].addr)) + txdesc->frag.addr)) goto drop_frame; - txdesc->frag[0].length = cpu_to_le32 (skb->len | LastFrag); + txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag); /* Increment cur_tx before tasklet_schedule() */ np->cur_tx++; @@ -1151,7 +1151,7 @@ reset_tx (struct net_device *dev) skb = np->tx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[i].frag[0].addr), + le32_to_cpu(np->tx_ring[i].frag.addr), skb->len, DMA_TO_DEVICE); dev_kfree_skb_any(skb); np->tx_skbuff[i] = NULL; @@ -1271,12 +1271,12 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) skb = np->tx_skbuff[entry]; /* Free the original skb. */ dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[entry].frag[0].addr), + le32_to_cpu(np->tx_ring[entry].frag.addr), skb->len, DMA_TO_DEVICE); dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; - np->tx_ring[entry].frag[0].addr = 0; - np->tx_ring[entry].frag[0].length = 0; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; } spin_unlock(&np->lock); } else { @@ -1290,12 +1290,12 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) skb = np->tx_skbuff[entry]; /* Free the original skb. */ dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[entry].frag[0].addr), + le32_to_cpu(np->tx_ring[entry].frag.addr), skb->len, DMA_TO_DEVICE); dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; - np->tx_ring[entry].frag[0].addr = 0; - np->tx_ring[entry].frag[0].length = 0; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; } spin_unlock(&np->lock); } @@ -1372,16 +1372,16 @@ static void rx_poll(struct tasklet_struct *t) (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { skb_reserve(skb, 2); /* 16 byte align the IP header */ dma_sync_single_for_cpu(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len); dma_sync_single_for_device(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb, pkt_len); } else { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(desc->frag[0].addr), + le32_to_cpu(desc->frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); skb_put(skb = np->rx_skbuff[entry], pkt_len); np->rx_skbuff[entry] = NULL; @@ -1427,18 +1427,18 @@ static void refill_rx (struct net_device *dev) if (skb == NULL) break; /* Better luck next round. */ skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ - np->rx_ring[entry].frag[0].addr = cpu_to_le32( + np->rx_ring[entry].frag.addr = cpu_to_le32( dma_map_single(&np->pci_dev->dev, skb->data, np->rx_buf_sz, DMA_FROM_DEVICE)); if (dma_mapping_error(&np->pci_dev->dev, - np->rx_ring[entry].frag[0].addr)) { + np->rx_ring[entry].frag.addr)) { dev_kfree_skb_irq(skb); np->rx_skbuff[entry] = NULL; break; } } /* Perhaps we need not reset this field. */ - np->rx_ring[entry].frag[0].length = + np->rx_ring[entry].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); np->rx_ring[entry].status = 0; cnt++; @@ -1870,14 +1870,14 @@ static int netdev_close(struct net_device *dev) (int)(np->tx_ring_dma)); for (i = 0; i < TX_RING_SIZE; i++) printk(KERN_DEBUG " #%d desc. %4.4x %8.8x %8.8x.\n", - i, np->tx_ring[i].status, np->tx_ring[i].frag[0].addr, - np->tx_ring[i].frag[0].length); + i, np->tx_ring[i].status, np->tx_ring[i].frag.addr, + np->tx_ring[i].frag.length); printk(KERN_DEBUG " Rx ring %8.8x:\n", (int)(np->rx_ring_dma)); for (i = 0; i < /*RX_RING_SIZE*/4 ; i++) { printk(KERN_DEBUG " #%d desc. %4.4x %4.4x %8.8x\n", - i, np->rx_ring[i].status, np->rx_ring[i].frag[0].addr, - np->rx_ring[i].frag[0].length); + i, np->rx_ring[i].status, np->rx_ring[i].frag.addr, + np->rx_ring[i].frag.length); } } #endif /* __i386__ debugging only */ @@ -1892,19 +1892,19 @@ static int netdev_close(struct net_device *dev) skb = np->rx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->rx_ring[i].frag[0].addr), + le32_to_cpu(np->rx_ring[i].frag.addr), np->rx_buf_sz, DMA_FROM_DEVICE); dev_kfree_skb(skb); np->rx_skbuff[i] = NULL; } - np->rx_ring[i].frag[0].addr = cpu_to_le32(0xBADF00D0); /* poison */ + np->rx_ring[i].frag.addr = cpu_to_le32(0xBADF00D0); /* poison */ } for (i = 0; i < TX_RING_SIZE; i++) { np->tx_ring[i].next_desc = 0; skb = np->tx_skbuff[i]; if (skb) { dma_unmap_single(&np->pci_dev->dev, - le32_to_cpu(np->tx_ring[i].frag[0].addr), + le32_to_cpu(np->tx_ring[i].frag.addr), skb->len, DMA_TO_DEVICE); dev_kfree_skb(skb); np->tx_skbuff[i] = NULL; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 623d113b6581..521f036d1c00 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -100,6 +100,14 @@ static int dpaa2_mac_get_if_mode(struct fwnode_handle *dpmac_node, return err; } +static struct phylink_pcs *dpaa2_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct dpaa2_mac *mac = phylink_to_dpaa2_mac(config); + + return mac->pcs; +} + static void dpaa2_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -172,6 +180,7 @@ static void dpaa2_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = dpaa2_mac_select_pcs, .mac_config = dpaa2_mac_config, .mac_link_up = dpaa2_mac_link_up, .mac_link_down = dpaa2_mac_link_down, @@ -303,9 +312,6 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) } mac->phylink = phylink; - if (mac->pcs) - phylink_set_pcs(mac->phylink, mac->pcs); - err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); if (err) { netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index ed16a5ac9ad0..a0c75c717073 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -934,18 +934,21 @@ static void enetc_mdiobus_destroy(struct enetc_pf *pf) enetc_imdio_remove(pf); } +static struct phylink_pcs * +enetc_pl_mac_select_pcs(struct phylink_config *config, phy_interface_t iface) +{ + struct enetc_pf *pf = phylink_to_enetc_pf(config); + + return pf->pcs; +} + static void enetc_pl_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { struct enetc_pf *pf = phylink_to_enetc_pf(config); - struct enetc_ndev_priv *priv; enetc_mac_config(&pf->si->hw, state->interface); - - priv = netdev_priv(pf->si->ndev); - if (pf->pcs) - phylink_set_pcs(priv->phylink, pf->pcs); } static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex) @@ -1062,6 +1065,7 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, static const struct phylink_mac_ops enetc_mac_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = enetc_pl_mac_select_pcs, .mac_config = enetc_pl_mac_config, .mac_link_up = enetc_pl_mac_link_up, .mac_link_down = enetc_pl_mac_link_down, diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 796133de527e..11227f51404c 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2797,7 +2797,7 @@ static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) int ret = 0; if (enable) { - ret = phy_init_eee(ndev->phydev, 0); + ret = phy_init_eee(ndev->phydev, false); if (ret) return ret; diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index bbbde9f701c2..be0bd4b44926 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -99,13 +99,13 @@ static void mpc52xx_fec_tx_timeout(struct net_device *dev, unsigned int txqueue) netif_wake_queue(dev); } -static void mpc52xx_fec_set_paddr(struct net_device *dev, u8 *mac) +static void mpc52xx_fec_set_paddr(struct net_device *dev, const u8 *mac) { struct mpc52xx_fec_priv *priv = netdev_priv(dev); struct mpc52xx_fec __iomem *fec = priv->fec; - out_be32(&fec->paddr1, *(u32 *)(&mac[0])); - out_be32(&fec->paddr2, (*(u16 *)(&mac[4]) << 16) | FEC_PADDR2_TYPE); + out_be32(&fec->paddr1, *(const u32 *)(&mac[0])); + out_be32(&fec->paddr2, (*(const u16 *)(&mac[4]) << 16) | FEC_PADDR2_TYPE); } static int mpc52xx_fec_set_mac_address(struct net_device *dev, void *addr) @@ -893,13 +893,15 @@ static int mpc52xx_fec_probe(struct platform_device *op) rv = of_get_ethdev_address(np, ndev); if (rv) { struct mpc52xx_fec __iomem *fec = priv->fec; + u8 addr[ETH_ALEN] __aligned(4); /* * If the MAC addresse is not provided via DT then read * it back from the controller regs */ - *(u32 *)(&ndev->dev_addr[0]) = in_be32(&fec->paddr1); - *(u16 *)(&ndev->dev_addr[4]) = in_be32(&fec->paddr2) >> 16; + *(u32 *)(&addr[0]) = in_be32(&fec->paddr1); + *(u16 *)(&addr[4]) = in_be32(&fec->paddr2) >> 16; + eth_hw_addr_set(ndev, addr); } /* diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index af99017a5453..7d49c28215f3 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -101,7 +101,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) u32 val, tempval; struct timespec64 ts; u64 ns; - val = 0; if (fep->pps_enable == enable) return 0; diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 266e562bd67a..ef8058a17188 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/acpi_mdio.h> +#include <linux/clk.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/mdio.h> @@ -36,9 +37,10 @@ struct tgec_mdio_controller { } __packed; #define MDIO_STAT_ENC BIT(6) -#define MDIO_STAT_CLKDIV(x) (((x>>1) & 0xff) << 8) +#define MDIO_STAT_CLKDIV(x) (((x) & 0x1ff) << 7) #define MDIO_STAT_BSY BIT(0) #define MDIO_STAT_RD_ER BIT(1) +#define MDIO_STAT_PRE_DIS BIT(5) #define MDIO_CTL_DEV_ADDR(x) (x & 0x1f) #define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5) #define MDIO_CTL_PRE_DIS BIT(10) @@ -50,6 +52,8 @@ struct tgec_mdio_controller { struct mdio_fsl_priv { struct tgec_mdio_controller __iomem *mdio_base; + struct clk *enet_clk; + u32 mdc_freq; bool is_little_endian; bool has_a009885; bool has_a011043; @@ -254,6 +258,50 @@ irq_restore: return ret; } +static int xgmac_mdio_set_mdc_freq(struct mii_bus *bus) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + struct device *dev = bus->parent; + u32 mdio_stat, div; + + if (device_property_read_u32(dev, "clock-frequency", &priv->mdc_freq)) + return 0; + + priv->enet_clk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->enet_clk)) { + dev_err(dev, "Input clock unknown, not changing MDC frequency"); + return PTR_ERR(priv->enet_clk); + } + + div = ((clk_get_rate(priv->enet_clk) / priv->mdc_freq) - 1) / 2; + if (div < 5 || div > 0x1ff) { + dev_err(dev, "Requested MDC frequency is out of range, ignoring"); + return -EINVAL; + } + + mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian); + mdio_stat &= ~MDIO_STAT_CLKDIV(0x1ff); + mdio_stat |= MDIO_STAT_CLKDIV(div); + xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian); + return 0; +} + +static void xgmac_mdio_set_suppress_preamble(struct mii_bus *bus) +{ + struct mdio_fsl_priv *priv = (struct mdio_fsl_priv *)bus->priv; + struct tgec_mdio_controller __iomem *regs = priv->mdio_base; + struct device *dev = bus->parent; + u32 mdio_stat; + + if (!device_property_read_bool(dev, "suppress-preamble")) + return; + + mdio_stat = xgmac_read32(®s->mdio_stat, priv->is_little_endian); + mdio_stat |= MDIO_STAT_PRE_DIS; + xgmac_write32(mdio_stat, ®s->mdio_stat, priv->is_little_endian); +} + static int xgmac_mdio_probe(struct platform_device *pdev) { struct fwnode_handle *fwnode; @@ -273,7 +321,7 @@ static int xgmac_mdio_probe(struct platform_device *pdev) return -EINVAL; } - bus = mdiobus_alloc_size(sizeof(struct mdio_fsl_priv)); + bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(struct mdio_fsl_priv)); if (!bus) return -ENOMEM; @@ -284,13 +332,11 @@ static int xgmac_mdio_probe(struct platform_device *pdev) bus->probe_capabilities = MDIOBUS_C22_C45; snprintf(bus->id, MII_BUS_ID_SIZE, "%pa", &res->start); - /* Set the PHY base address */ priv = bus->priv; - priv->mdio_base = ioremap(res->start, resource_size(res)); - if (!priv->mdio_base) { - ret = -ENOMEM; - goto err_ioremap; - } + priv->mdio_base = devm_ioremap(&pdev->dev, res->start, + resource_size(res)); + if (!priv->mdio_base) + return -ENOMEM; /* For both ACPI and DT cases, endianness of MDIO controller * needs to be specified using "little-endian" property. @@ -303,6 +349,12 @@ static int xgmac_mdio_probe(struct platform_device *pdev) priv->has_a011043 = device_property_read_bool(&pdev->dev, "fsl,erratum-a011043"); + xgmac_mdio_set_suppress_preamble(bus); + + ret = xgmac_mdio_set_mdc_freq(bus); + if (ret) + return ret; + fwnode = pdev->dev.fwnode; if (is_of_node(fwnode)) ret = of_mdiobus_register(bus, to_of_node(fwnode)); @@ -312,32 +364,12 @@ static int xgmac_mdio_probe(struct platform_device *pdev) ret = -EINVAL; if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); - goto err_registration; + return ret; } platform_set_drvdata(pdev, bus); return 0; - -err_registration: - iounmap(priv->mdio_base); - -err_ioremap: - mdiobus_free(bus); - - return ret; -} - -static int xgmac_mdio_remove(struct platform_device *pdev) -{ - struct mii_bus *bus = platform_get_drvdata(pdev); - struct mdio_fsl_priv *priv = bus->priv; - - mdiobus_unregister(bus); - iounmap(priv->mdio_base); - mdiobus_free(bus); - - return 0; } static const struct of_device_id xgmac_mdio_match[] = { @@ -364,7 +396,6 @@ static struct platform_driver xgmac_mdio_driver = { .acpi_match_table = xgmac_acpi_match, }, .probe = xgmac_mdio_probe, - .remove = xgmac_mdio_remove, }; module_platform_driver(xgmac_mdio_driver); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 5f5d4f7aa813..160735484465 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -843,7 +843,7 @@ static inline bool gve_is_gqi(struct gve_priv *priv) /* buffers */ int gve_alloc_page(struct gve_priv *priv, struct device *dev, struct page **page, dma_addr_t *dma, - enum dma_data_direction); + enum dma_data_direction, gfp_t gfp_flags); void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma, enum dma_data_direction); /* tx handling */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 2ad7f57f7e5b..f7621ab672b9 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -301,7 +301,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) */ static int gve_adminq_kick_and_wait(struct gve_priv *priv) { - u32 tail, head; + int tail, head; int i; tail = ioread32be(&priv->reg_bar0->adminq_event_counter); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index f7f65c4bf993..54e51c8221b8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -766,9 +766,9 @@ static void gve_free_rings(struct gve_priv *priv) int gve_alloc_page(struct gve_priv *priv, struct device *dev, struct page **page, dma_addr_t *dma, - enum dma_data_direction dir) + enum dma_data_direction dir, gfp_t gfp_flags) { - *page = alloc_page(GFP_KERNEL); + *page = alloc_page(gfp_flags); if (!*page) { priv->page_alloc_fail++; return -ENOMEM; @@ -811,7 +811,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id, for (i = 0; i < pages; i++) { err = gve_alloc_page(priv, &priv->pdev->dev, &qpl->pages[i], &qpl->page_buses[i], - gve_qpl_dma_dir(priv, id)); + gve_qpl_dma_dir(priv, id), GFP_KERNEL); /* caller handles clean up */ if (err) return -ENOMEM; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 9ddcc497f48e..2068199445bd 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -86,7 +86,8 @@ static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev, dma_addr_t dma; int err; - err = gve_alloc_page(priv, dev, &page, &dma, DMA_FROM_DEVICE); + err = gve_alloc_page(priv, dev, &page, &dma, DMA_FROM_DEVICE, + GFP_ATOMIC); if (err) return err; diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index beb8bb079023..8c939628e2d8 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -157,7 +157,7 @@ static int gve_alloc_page_dqo(struct gve_priv *priv, int err; err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page, - &buf_state->addr, DMA_FROM_DEVICE); + &buf_state->addr, DMA_FROM_DEVICE, GFP_KERNEL); if (err) return err; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 9298fbecb31a..6f18c9a03231 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -167,6 +167,7 @@ struct hnae3_handle; struct hnae3_queue { void __iomem *io_base; + void __iomem *mem_base; struct hnae3_ae_algo *ae_algo; struct hnae3_handle *handle; int tqp_index; /* index in a handle */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index babc5d7a3b52..0b8a73c40b12 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2028,9 +2028,73 @@ static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring, return bd_num; } +static void hns3_tx_push_bd(struct hns3_enet_ring *ring, int num) +{ +#define HNS3_BYTES_PER_64BIT 8 + + struct hns3_desc desc[HNS3_MAX_PUSH_BD_NUM] = {}; + int offset = 0; + + /* make sure everything is visible to device before + * excuting tx push or updating doorbell + */ + dma_wmb(); + + do { + int idx = (ring->next_to_use - num + ring->desc_num) % + ring->desc_num; + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_push++; + u64_stats_update_end(&ring->syncp); + memcpy(&desc[offset], &ring->desc[idx], + sizeof(struct hns3_desc)); + offset++; + } while (--num); + + __iowrite64_copy(ring->tqp->mem_base, desc, + (sizeof(struct hns3_desc) * HNS3_MAX_PUSH_BD_NUM) / + HNS3_BYTES_PER_64BIT); + + io_stop_wc(); +} + +static void hns3_tx_mem_doorbell(struct hns3_enet_ring *ring) +{ +#define HNS3_MEM_DOORBELL_OFFSET 64 + + __le64 bd_num = cpu_to_le64((u64)ring->pending_buf); + + /* make sure everything is visible to device before + * excuting tx push or updating doorbell + */ + dma_wmb(); + + __iowrite64_copy(ring->tqp->mem_base + HNS3_MEM_DOORBELL_OFFSET, + &bd_num, 1); + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_mem_doorbell += ring->pending_buf; + u64_stats_update_end(&ring->syncp); + + io_stop_wc(); +} + static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, bool doorbell) { + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); + + /* when tx push is enabled, the packet whose number of BD below + * HNS3_MAX_PUSH_BD_NUM can be pushed directly. + */ + if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num && + !ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) { + hns3_tx_push_bd(ring, num); + WRITE_ONCE(ring->last_to_use, ring->next_to_use); + return; + } + ring->pending_buf += num; if (!doorbell) { @@ -2038,11 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, return; } - if (!ring->pending_buf) - return; + if (ring->tqp->mem_base) + hns3_tx_mem_doorbell(ring); + else + writel(ring->pending_buf, + ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); - writel(ring->pending_buf, - ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); ring->pending_buf = 0; WRITE_ONCE(ring->last_to_use, ring->next_to_use); } @@ -2732,6 +2797,9 @@ static void hns3_dump_queue_stats(struct net_device *ndev, "seg_pkt_cnt: %llu, tx_more: %llu, restart_queue: %llu, tx_busy: %llu\n", tx_ring->stats.seg_pkt_cnt, tx_ring->stats.tx_more, tx_ring->stats.restart_queue, tx_ring->stats.tx_busy); + + netdev_info(ndev, "tx_push: %llu, tx_mem_doorbell: %llu\n", + tx_ring->stats.tx_push, tx_ring->stats.tx_mem_doorbell); } static void hns3_dump_queue_reg(struct net_device *ndev, @@ -5094,6 +5162,9 @@ static void hns3_state_init(struct hnae3_handle *handle) set_bit(HNS3_NIC_STATE_INITED, &priv->state); + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state); + if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->supported_pflags); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index a05a0c7423ce..4a3253692dcc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -7,6 +7,7 @@ #include <linux/dim.h> #include <linux/if_vlan.h> #include <net/page_pool.h> +#include <asm/barrier.h> #include "hnae3.h" @@ -25,9 +26,12 @@ enum hns3_nic_state { HNS3_NIC_STATE2_RESET_REQUESTED, HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, + HNS3_NIC_STATE_TX_PUSH_ENABLE, HNS3_NIC_STATE_MAX }; +#define HNS3_MAX_PUSH_BD_NUM 2 + #define HNS3_RING_RX_RING_BASEADDR_L_REG 0x00000 #define HNS3_RING_RX_RING_BASEADDR_H_REG 0x00004 #define HNS3_RING_RX_RING_BD_NUM_REG 0x00008 @@ -410,6 +414,8 @@ struct ring_stats { u64 tx_pkts; u64 tx_bytes; u64 tx_more; + u64 tx_push; + u64 tx_mem_doorbell; u64 restart_queue; u64 tx_busy; u64 tx_copy; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c06c39ece80d..6469238ae090 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -23,6 +23,8 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("packets", tx_pkts), HNS3_TQP_STAT("bytes", tx_bytes), HNS3_TQP_STAT("more", tx_more), + HNS3_TQP_STAT("push", tx_push), + HNS3_TQP_STAT("mem_doorbell", tx_mem_doorbell), HNS3_TQP_STAT("wake", restart_queue), HNS3_TQP_STAT("busy", tx_busy), HNS3_TQP_STAT("copy", tx_copy), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 24f7afacae02..78d0498bdabc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1643,6 +1643,7 @@ static int hclge_config_gro(struct hclge_dev *hdev) static int hclge_alloc_tqps(struct hclge_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hclge_comm_tqp *tqp; int i; @@ -1676,6 +1677,14 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev) (i - HCLGE_TQP_MAX_SIZE_DEV_V2) * HCLGE_TQP_REG_SIZE; + /* when device supports tx push and has device memory, + * the queue can execute push mode or doorbell mode on + * device memory. + */ + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + tqp->q.mem_base = hdev->hw.hw.mem_base + + HCLGE_TQP_MEM_OFFSET(hdev, i); + tqp++; } @@ -11008,8 +11017,6 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, static int hclge_dev_mem_map(struct hclge_dev *hdev) { -#define HCLGE_MEM_BAR 4 - struct pci_dev *pdev = hdev->pdev; struct hclge_hw *hw = &hdev->hw; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index adfb26e79262..f7f5a4b09068 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -169,6 +169,14 @@ enum HLCGE_PORT_TYPE { #define HCLGE_VECTOR0_ALL_MSIX_ERR_B 6U #define HCLGE_TRIGGER_IMP_RESET_B 7U +#define HCLGE_TQP_MEM_SIZE 0x10000 +#define HCLGE_MEM_BAR 4 +/* in the bar4, the first half is for roce, and the second half is for nic */ +#define HCLGE_NIC_MEM_OFFSET(hdev) \ + (pci_resource_len((hdev)->pdev, HCLGE_MEM_BAR) >> 1) +#define HCLGE_TQP_MEM_OFFSET(hdev, i) \ + (HCLGE_NIC_MEM_OFFSET(hdev) + HCLGE_TQP_MEM_SIZE * (i)) + #define HCLGE_MAC_DEFAULT_FRAME \ (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN) #define HCLGE_MAC_MIN_FRAME 64 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 7df87610ad96..93389bec8d89 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -321,6 +321,7 @@ static int hclgevf_get_pf_media_type(struct hclgevf_dev *hdev) static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hclge_comm_tqp *tqp; int i; @@ -354,6 +355,14 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev) (i - HCLGEVF_TQP_MAX_SIZE_DEV_V2) * HCLGEVF_TQP_REG_SIZE; + /* when device supports tx push and has device memory, + * the queue can execute push mode or doorbell mode on + * device memory. + */ + if (test_bit(HNAE3_DEV_SUPPORT_TX_PUSH_B, ae_dev->caps)) + tqp->q.mem_base = hdev->hw.hw.mem_base + + HCLGEVF_TQP_MEM_OFFSET(hdev, i); + tqp++; } @@ -2043,8 +2052,7 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) break; } - if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) - hclgevf_enable_vector(&hdev->misc_vector, true); + hclgevf_enable_vector(&hdev->misc_vector, true); return IRQ_HANDLED; } @@ -2547,8 +2555,6 @@ static void hclgevf_uninit_client_instance(struct hnae3_client *client, static int hclgevf_dev_mem_map(struct hclgevf_dev *hdev) { -#define HCLGEVF_MEM_BAR 4 - struct pci_dev *pdev = hdev->pdev; struct hclgevf_hw *hw = &hdev->hw; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 502ca1ce1a90..4b00fd44f118 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -96,6 +96,14 @@ #define HCLGEVF_RSS_IND_TBL_SIZE 512 +#define HCLGEVF_TQP_MEM_SIZE 0x10000 +#define HCLGEVF_MEM_BAR 4 +/* in the bar4, the first half is for roce, and the second half is for nic */ +#define HCLGEVF_NIC_MEM_OFFSET(hdev) \ + (pci_resource_len((hdev)->pdev, HCLGEVF_MEM_BAR) >> 1) +#define HCLGEVF_TQP_MEM_OFFSET(hdev, i) \ + (HCLGEVF_NIC_MEM_OFFSET(hdev) + HCLGEVF_TQP_MEM_SIZE * (i)) + #define HCLGEVF_MAC_MAX_FRAME 9728 #define HCLGEVF_STATS_TIMER_INTERVAL 36U diff --git a/drivers/net/ethernet/i825xx/ether1.c b/drivers/net/ethernet/i825xx/ether1.c index c612ef526d16..3e7d7c4bafdc 100644 --- a/drivers/net/ethernet/i825xx/ether1.c +++ b/drivers/net/ethernet/i825xx/ether1.c @@ -986,6 +986,7 @@ static int ether1_probe(struct expansion_card *ec, const struct ecard_id *id) { struct net_device *dev; + u8 addr[ETH_ALEN]; int i, ret = 0; ether1_banner(); @@ -1015,7 +1016,8 @@ ether1_probe(struct expansion_card *ec, const struct ecard_id *id) } for (i = 0; i < 6; i++) - dev->dev_addr[i] = readb(IDPROM_ADDRESS + (i << 2)); + addr[i] = readb(IDPROM_ADDRESS + (i << 2)); + eth_hw_addr_set(dev, addr); if (ether1_init_2(dev)) { ret = -ENODEV; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 59536bd5cab1..bda7a2a9d211 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2602,6 +2602,7 @@ static void __ibmvnic_reset(struct work_struct *work) struct ibmvnic_rwi *rwi; unsigned long flags; u32 reset_state; + int num_fails = 0; int rc = 0; adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset); @@ -2655,11 +2656,23 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } - if (rc) { - /* give backing device time to settle down */ + if (rc) + num_fails++; + else + num_fails = 0; + + /* If auto-priority-failover is enabled we can get + * back to back failovers during resets, resulting + * in at least two failed resets (from high-priority + * backing device to low-priority one and then back) + * If resets continue to fail beyond that, give the + * adapter some time to settle down before retrying. + */ + if (num_fails >= 3) { netdev_dbg(adapter->netdev, - "[S:%s] Hard reset failed, waiting 60 secs\n", - adapter_state_to_string(adapter->state)); + "[S:%s] Hard reset failed %d times, waiting 60 secs\n", + adapter_state_to_string(adapter->state), + num_fails); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(60 * HZ); } @@ -3844,11 +3857,25 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) struct device *dev = &adapter->vdev->dev; union ibmvnic_crq crq; int max_entries; + int cap_reqs; + + /* We send out 6 or 7 REQUEST_CAPABILITY CRQs below (depending on + * the PROMISC flag). Initialize this count upfront. When the tasklet + * receives a response to all of these, it will send the next protocol + * message (QUERY_IP_OFFLOAD). + */ + if (!(adapter->netdev->flags & IFF_PROMISC) || + adapter->promisc_supported) + cap_reqs = 7; + else + cap_reqs = 6; if (!retry) { /* Sub-CRQ entries are 32 byte long */ int entries_page = 4 * PAGE_SIZE / (sizeof(u64) * 4); + atomic_set(&adapter->running_cap_crqs, cap_reqs); + if (adapter->min_tx_entries_per_subcrq > entries_page || adapter->min_rx_add_entries_per_subcrq > entries_page) { dev_err(dev, "Fatal, invalid entries per sub-crq\n"); @@ -3909,44 +3936,45 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) adapter->opt_rx_comp_queues; adapter->req_rx_add_queues = adapter->max_rx_add_queues; + } else { + atomic_add(cap_reqs, &adapter->running_cap_crqs); } - memset(&crq, 0, sizeof(crq)); crq.request_capability.first = IBMVNIC_CRQ_CMD; crq.request_capability.cmd = REQUEST_CAPABILITY; crq.request_capability.capability = cpu_to_be16(REQ_TX_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_tx_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_rx_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_QUEUES); crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_queues); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_TX_ENTRIES_PER_SUBCRQ); crq.request_capability.number = cpu_to_be64(adapter->req_tx_entries_per_subcrq); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_RX_ADD_ENTRIES_PER_SUBCRQ); crq.request_capability.number = cpu_to_be64(adapter->req_rx_add_entries_per_subcrq); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); crq.request_capability.capability = cpu_to_be16(REQ_MTU); crq.request_capability.number = cpu_to_be64(adapter->req_mtu); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); if (adapter->netdev->flags & IFF_PROMISC) { @@ -3954,16 +3982,21 @@ static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); crq.request_capability.number = cpu_to_be64(1); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); } } else { crq.request_capability.capability = cpu_to_be16(PROMISC_REQUESTED); crq.request_capability.number = cpu_to_be64(0); - atomic_inc(&adapter->running_cap_crqs); + cap_reqs--; ibmvnic_send_crq(adapter, &crq); } + + /* Keep at end to catch any discrepancy between expected and actual + * CRQs sent. + */ + WARN_ON(cap_reqs != 0); } static int pending_scrq(struct ibmvnic_adapter *adapter, @@ -4357,118 +4390,132 @@ static void send_query_map(struct ibmvnic_adapter *adapter) static void send_query_cap(struct ibmvnic_adapter *adapter) { union ibmvnic_crq crq; + int cap_reqs; + + /* We send out 25 QUERY_CAPABILITY CRQs below. Initialize this count + * upfront. When the tasklet receives a response to all of these, it + * can send out the next protocol messaage (REQUEST_CAPABILITY). + */ + cap_reqs = 25; + + atomic_set(&adapter->running_cap_crqs, cap_reqs); - atomic_set(&adapter->running_cap_crqs, 0); memset(&crq, 0, sizeof(crq)); crq.query_capability.first = IBMVNIC_CRQ_CMD; crq.query_capability.cmd = QUERY_CAPABILITY; crq.query_capability.capability = cpu_to_be16(MIN_TX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MIN_RX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_TX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_RX_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MIN_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MIN_RX_ADD_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_RX_ADD_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(TCP_IP_OFFLOAD); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(PROMISC_SUPPORTED); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MIN_MTU); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_MTU); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_MULTICAST_FILTERS); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(VLAN_HEADER_INSERTION); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(RX_VLAN_HEADER_INSERTION); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(MAX_TX_SG_ENTRIES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(RX_SG_SUPPORTED); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(OPT_TX_COMP_SUB_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(OPT_RX_COMP_QUEUES); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(OPT_RX_BUFADD_Q_PER_RX_COMP_Q); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(OPT_TX_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(OPT_RXBA_ENTRIES_PER_SUBCRQ); - atomic_inc(&adapter->running_cap_crqs); ibmvnic_send_crq(adapter, &crq); + cap_reqs--; crq.query_capability.capability = cpu_to_be16(TX_RX_DESC_REQ); - atomic_inc(&adapter->running_cap_crqs); + ibmvnic_send_crq(adapter, &crq); + cap_reqs--; + + /* Keep at end to catch any discrepancy between expected and actual + * CRQs sent. + */ + WARN_ON(cap_reqs != 0); } static void send_query_ip_offload(struct ibmvnic_adapter *adapter) @@ -4772,6 +4819,8 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, char *name; atomic_dec(&adapter->running_cap_crqs); + netdev_dbg(adapter->netdev, "Outstanding request-caps: %d\n", + atomic_read(&adapter->running_cap_crqs)); switch (be16_to_cpu(crq->request_capability_rsp.capability)) { case REQ_TX_QUEUES: req_value = &adapter->req_tx_queues; @@ -4835,10 +4884,8 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq, } /* Done receiving requested capabilities, query IP offload support */ - if (atomic_read(&adapter->running_cap_crqs) == 0) { - adapter->wait_capability = false; + if (atomic_read(&adapter->running_cap_crqs) == 0) send_query_ip_offload(adapter); - } } static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, @@ -5136,10 +5183,8 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq, } out: - if (atomic_read(&adapter->running_cap_crqs) == 0) { - adapter->wait_capability = false; + if (atomic_read(&adapter->running_cap_crqs) == 0) send_request_cap(adapter, 0); - } } static int send_query_phys_parms(struct ibmvnic_adapter *adapter) @@ -5435,33 +5480,21 @@ static void ibmvnic_tasklet(struct tasklet_struct *t) struct ibmvnic_crq_queue *queue = &adapter->crq; union ibmvnic_crq *crq; unsigned long flags; - bool done = false; spin_lock_irqsave(&queue->lock, flags); - while (!done) { - /* Pull all the valid messages off the CRQ */ - while ((crq = ibmvnic_next_crq(adapter)) != NULL) { - /* This barrier makes sure ibmvnic_next_crq()'s - * crq->generic.first & IBMVNIC_CRQ_CMD_RSP is loaded - * before ibmvnic_handle_crq()'s - * switch(gen_crq->first) and switch(gen_crq->cmd). - */ - dma_rmb(); - ibmvnic_handle_crq(crq, adapter); - crq->generic.first = 0; - } - /* remain in tasklet until all - * capabilities responses are received + /* Pull all the valid messages off the CRQ */ + while ((crq = ibmvnic_next_crq(adapter)) != NULL) { + /* This barrier makes sure ibmvnic_next_crq()'s + * crq->generic.first & IBMVNIC_CRQ_CMD_RSP is loaded + * before ibmvnic_handle_crq()'s + * switch(gen_crq->first) and switch(gen_crq->cmd). */ - if (!adapter->wait_capability) - done = true; + dma_rmb(); + ibmvnic_handle_crq(crq, adapter); + crq->generic.first = 0; } - /* if capabilities CRQ's were sent in this tasklet, the following - * tasklet must wait until all responses are received - */ - if (atomic_read(&adapter->running_cap_crqs) != 0) - adapter->wait_capability = true; + spin_unlock_irqrestore(&queue->lock, flags); } diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 4a8f36e0ab07..4a7a56ff74ce 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -919,7 +919,6 @@ struct ibmvnic_adapter { int login_rsp_buf_sz; atomic_t running_cap_crqs; - bool wait_capability; struct ibmvnic_sub_crq_queue **tx_scrq ____cacheline_aligned; struct ibmvnic_sub_crq_queue **rx_scrq ____cacheline_aligned; diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index c3def0ee7788..8d06c9d8ff8b 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -115,7 +115,8 @@ enum e1000_boards { board_pch_lpt, board_pch_spt, board_pch_cnp, - board_pch_tgp + board_pch_tgp, + board_pch_adp }; struct e1000_ps_page { @@ -502,6 +503,7 @@ extern const struct e1000_info e1000_pch_lpt_info; extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; +extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 5e4fc9b4e2ad..c908c84b86d2 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -6021,3 +6021,23 @@ const struct e1000_info e1000_pch_tgp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_adp_info = { + .mac = e1000_pch_adp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 635a95927e93..6fb3437f68e0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -52,6 +52,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_spt] = &e1000_pch_spt_info, [board_pch_cnp] = &e1000_pch_cnp_info, [board_pch_tgp] = &e1000_pch_tgp_info, + [board_pch_adp] = &e1000_pch_adp_info, }; struct e1000_reg_info { @@ -6341,7 +6342,8 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) u32 mac_data; u16 phy_data; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME configure the device for S0ix */ mac_data = er32(H2ME); mac_data |= E1000_H2ME_START_DPG; @@ -6490,7 +6492,8 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) u16 phy_data; u32 i = 0; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME unconfigure the device from S0ix */ mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; @@ -7385,9 +7388,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) resource_size_t flash_start, flash_len; static int cards_found; u16 aspm_disable_flag = 0; - int bars, i, err, pci_using_dac; u16 eeprom_data = 0; u16 eeprom_apme_mask = E1000_EEPROM_APME; + int bars, i, err; s32 ret_val = 0; if (ei->flags2 & FLAG2_DISABLE_ASPM_L0S) @@ -7401,17 +7404,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } bars = pci_select_bars(pdev, IORESOURCE_MEM); @@ -7547,10 +7544,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_UNICAST_FLT; - if (pci_using_dac) { - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - } + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA; /* MTU range: 68 - max_hw_frame_size */ netdev->min_mtu = ETH_MIN_MTU; @@ -7898,22 +7893,22 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4d939af0a626..80c5cecaf2b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -144,6 +144,7 @@ enum i40e_state_t { __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ + __I40E_IN_REMOVE, __I40E_VFS_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, @@ -174,7 +175,6 @@ enum i40e_interrupt_policy { struct i40e_lump_tracking { u16 num_entries; - u16 search_hint; u16 list[0]; #define I40E_PILE_VALID_BIT 0x8000 #define I40E_IWARP_IRQ_PILE_ID (I40E_PILE_VALID_BIT - 2) @@ -848,12 +848,12 @@ struct i40e_vsi { struct rtnl_link_stats64 net_stats_offsets; struct i40e_eth_stats eth_stats; struct i40e_eth_stats eth_stats_offsets; - u32 tx_restart; - u32 tx_busy; + u64 tx_restart; + u64 tx_busy; u64 tx_linearize; u64 tx_force_wb; - u32 rx_buf_failed; - u32 rx_page_failed; + u64 rx_buf_failed; + u64 rx_page_failed; /* These are containers of ring pointers, allocated at run-time */ struct i40e_ring **rx_rings; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 7abef88801fb..42439f725aa4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -769,7 +769,7 @@ static bool i40e_asq_done(struct i40e_hw *hw) } /** - * i40e_asq_send_command_atomic - send command to Admin Queue + * i40e_asq_send_command_atomic_exec - send command to Admin Queue * @hw: pointer to the hw struct * @desc: prefilled descriptor describing the command (non DMA mem) * @buff: buffer to use for indirect commands @@ -780,11 +780,13 @@ static bool i40e_asq_done(struct i40e_hw *hw) * This is the main send command driver routine for the Admin Queue send * queue. It runs the queue, cleans the queue, etc **/ -i40e_status -i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ u16 buff_size, - struct i40e_asq_cmd_details *cmd_details, - bool is_atomic_context) +static i40e_status +i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context) { i40e_status status = 0; struct i40e_dma_mem *dma_buff = NULL; @@ -794,8 +796,6 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, u16 retval = 0; u32 val = 0; - mutex_lock(&hw->aq.asq_mutex); - if (hw->aq.asq.count == 0) { i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: Admin queue not initialized.\n"); @@ -969,6 +969,36 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, } asq_send_command_error: + return status; +} + +/** + * i40e_asq_send_command_atomic - send command to Admin Queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor describing the command (non DMA mem) + * @buff: buffer to use for indirect commands + * @buff_size: size of buffer for indirect commands + * @cmd_details: pointer to command details structure + * @is_atomic_context: is the function called in an atomic context? + * + * Acquires the lock and calls the main send command execution + * routine. + **/ +i40e_status +i40e_asq_send_command_atomic(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context) +{ + i40e_status status; + + mutex_lock(&hw->aq.asq_mutex); + status = i40e_asq_send_command_atomic_exec(hw, desc, buff, buff_size, + cmd_details, + is_atomic_context); + mutex_unlock(&hw->aq.asq_mutex); return status; } @@ -983,6 +1013,52 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, } /** + * i40e_asq_send_command_atomic_v2 - send command to Admin Queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor describing the command (non DMA mem) + * @buff: buffer to use for indirect commands + * @buff_size: size of buffer for indirect commands + * @cmd_details: pointer to command details structure + * @is_atomic_context: is the function called in an atomic context? + * @aq_status: pointer to Admin Queue status return value + * + * Acquires the lock and calls the main send command execution + * routine. Returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + **/ +i40e_status +i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context, + enum i40e_admin_queue_err *aq_status) +{ + i40e_status status; + + mutex_lock(&hw->aq.asq_mutex); + status = i40e_asq_send_command_atomic_exec(hw, desc, buff, + buff_size, + cmd_details, + is_atomic_context); + if (aq_status) + *aq_status = hw->aq.asq_last_status; + mutex_unlock(&hw->aq.asq_mutex); + return status; +} + +i40e_status +i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + return i40e_asq_send_command_atomic_v2(hw, desc, buff, buff_size, + cmd_details, true, aq_status); +} + +/** * i40e_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) * @opcode: the opcode can be used to decide which flags to turn off or on diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 9ddeb015eb7e..6aefffd83615 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1899,8 +1899,9 @@ i40e_status i40e_aq_add_vsi(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); - status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info, - sizeof(vsi_ctx->info), cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info, + sizeof(vsi_ctx->info), + cmd_details, true); if (status) goto aq_add_vsi_exit; @@ -2287,8 +2288,9 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); - status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info, - sizeof(vsi_ctx->info), cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info, + sizeof(vsi_ctx->info), + cmd_details, true); vsi_ctx->vsis_allocated = le16_to_cpu(resp->vsi_used); vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); @@ -2632,33 +2634,28 @@ get_veb_exit: } /** - * i40e_aq_add_macvlan - * @hw: pointer to the hw struct - * @seid: VSI for the mac address + * i40e_prepare_add_macvlan * @mv_list: list of macvlans to be added + * @desc: pointer to AQ descriptor structure * @count: length of the list - * @cmd_details: pointer to command details structure or NULL + * @seid: VSI for the mac address * - * Add MAC/VLAN addresses to the HW filtering + * Internal helper function that prepares the add macvlan request + * and returns the buffer size. **/ -i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, - struct i40e_aqc_add_macvlan_element_data *mv_list, - u16 count, struct i40e_asq_cmd_details *cmd_details) +static u16 +i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list, + struct i40e_aq_desc *desc, u16 count, u16 seid) { - struct i40e_aq_desc desc; struct i40e_aqc_macvlan *cmd = - (struct i40e_aqc_macvlan *)&desc.params.raw; - i40e_status status; + (struct i40e_aqc_macvlan *)&desc->params.raw; u16 buf_size; int i; - if (count == 0 || !mv_list || !hw) - return I40E_ERR_PARAM; - buf_size = count * sizeof(*mv_list); /* prep the rest of the request */ - i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_macvlan); + i40e_fill_default_direct_cmd_desc(desc, i40e_aqc_opc_add_macvlan); cmd->num_addresses = cpu_to_le16(count); cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid); cmd->seid[1] = 0; @@ -2669,14 +2666,71 @@ i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, mv_list[i].flags |= cpu_to_le16(I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC); - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + desc->flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); if (buf_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - status = i40e_asq_send_command(hw, &desc, mv_list, buf_size, - cmd_details); + return buf_size; +} - return status; +/** + * i40e_aq_add_macvlan + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be added + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * + * Add MAC/VLAN addresses to the HW filtering + **/ +i40e_status +i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); + + return i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size, + cmd_details, true); +} + +/** + * i40e_aq_add_macvlan_v2 + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be added + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * @aq_status: pointer to Admin Queue status return value + * + * Add MAC/VLAN addresses to the HW filtering. + * The _v2 version returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + * It also calls _v2 versions of asq_send_command functions to + * get the aq_status on the stack. + **/ +i40e_status +i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = i40e_prepare_add_macvlan(mv_list, &desc, count, seid); + + return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size, + cmd_details, true, aq_status); } /** @@ -2715,13 +2769,59 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, if (buf_size > I40E_AQ_LARGE_BUF) desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - status = i40e_asq_send_command(hw, &desc, mv_list, buf_size, - cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size, + cmd_details, true); return status; } /** + * i40e_aq_remove_macvlan_v2 + * @hw: pointer to the hw struct + * @seid: VSI for the mac address + * @mv_list: list of macvlans to be removed + * @count: length of the list + * @cmd_details: pointer to command details structure or NULL + * @aq_status: pointer to Admin Queue status return value + * + * Remove MAC/VLAN addresses from the HW filtering. + * The _v2 version returns the last Admin Queue status in aq_status + * to avoid race conditions in access to hw->aq.asq_last_status. + * It also calls _v2 versions of asq_send_command functions to + * get the aq_status on the stack. + **/ +i40e_status +i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status) +{ + struct i40e_aqc_macvlan *cmd; + struct i40e_aq_desc desc; + u16 buf_size; + + if (count == 0 || !mv_list || !hw) + return I40E_ERR_PARAM; + + buf_size = count * sizeof(*mv_list); + + /* prep the rest of the request */ + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan); + cmd = (struct i40e_aqc_macvlan *)&desc.params.raw; + cmd->num_addresses = cpu_to_le16(count); + cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid); + cmd->seid[1] = 0; + cmd->seid[2] = 0; + + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD)); + if (buf_size > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + + return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size, + cmd_details, true, aq_status); +} + +/** * i40e_mirrorrule_op - Internal helper function to add/delete mirror rule * @hw: pointer to the hw struct * @opcode: AQ opcode for add or delete mirror rule @@ -3868,7 +3968,8 @@ i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, cmd->seid = cpu_to_le16(seid); - status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + status = i40e_asq_send_command_atomic(hw, &desc, NULL, 0, + cmd_details, true); return status; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 2c1b1da1220e..90fff05fbd2b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -240,7 +240,7 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) (unsigned long int)vsi->net_stats_offsets.rx_compressed, (unsigned long int)vsi->net_stats_offsets.tx_compressed); dev_info(&pf->pdev->dev, - " tx_restart = %d, tx_busy = %d, rx_buf_failed = %d, rx_page_failed = %d\n", + " tx_restart = %llu, tx_busy = %llu, rx_buf_failed = %llu, rx_page_failed = %llu\n", vsi->tx_restart, vsi->tx_busy, vsi->rx_buf_failed, vsi->rx_page_failed); rcu_read_lock(); @@ -275,9 +275,8 @@ static void i40e_dbg_dump_vsi_seid(struct i40e_pf *pf, int seid) rx_ring->rx_stats.alloc_page_failed, rx_ring->rx_stats.alloc_buff_failed); dev_info(&pf->pdev->dev, - " rx_rings[%i]: rx_stats: realloc_count = %lld, page_reuse_count = %lld\n", + " rx_rings[%i]: rx_stats: realloc_count = 0, page_reuse_count = %lld\n", i, - rx_ring->rx_stats.realloc_count, rx_ring->rx_stats.page_reuse_count); dev_info(&pf->pdev->dev, " rx_rings[%i]: size = %i\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2a3d8aef7f4e..a95609d847ca 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -196,10 +196,6 @@ int i40e_free_virt_mem_d(struct i40e_hw *hw, struct i40e_virt_mem *mem) * @id: an owner id to stick on the items assigned * * Returns the base item index of the lump, or negative for error - * - * The search_hint trick and lack of advanced fit-finding only work - * because we're highly likely to have all the same size lump requests. - * Linear search time and any fragmentation should be minimal. **/ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, u16 needed, u16 id) @@ -214,8 +210,21 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, return -EINVAL; } - /* start the linear search with an imperfect hint */ - i = pile->search_hint; + /* Allocate last queue in the pile for FDIR VSI queue + * so it doesn't fragment the qp_pile + */ + if (pile == pf->qp_pile && pf->vsi[id]->type == I40E_VSI_FDIR) { + if (pile->list[pile->num_entries - 1] & I40E_PILE_VALID_BIT) { + dev_err(&pf->pdev->dev, + "Cannot allocate queue %d for I40E_VSI_FDIR\n", + pile->num_entries - 1); + return -ENOMEM; + } + pile->list[pile->num_entries - 1] = id | I40E_PILE_VALID_BIT; + return pile->num_entries - 1; + } + + i = 0; while (i < pile->num_entries) { /* skip already allocated entries */ if (pile->list[i] & I40E_PILE_VALID_BIT) { @@ -234,7 +243,6 @@ static int i40e_get_lump(struct i40e_pf *pf, struct i40e_lump_tracking *pile, for (j = 0; j < needed; j++) pile->list[i+j] = id | I40E_PILE_VALID_BIT; ret = i; - pile->search_hint = i + j; break; } @@ -257,7 +265,7 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) { int valid_id = (id | I40E_PILE_VALID_BIT); int count = 0; - int i; + u16 i; if (!pile || index >= pile->num_entries) return -EINVAL; @@ -269,8 +277,6 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) count++; } - if (count && index < pile->search_hint) - pile->search_hint = index; return count; } @@ -772,9 +778,9 @@ static void i40e_update_vsi_stats(struct i40e_vsi *vsi) struct rtnl_link_stats64 *ns; /* netdev stats */ struct i40e_eth_stats *oes; struct i40e_eth_stats *es; /* device's eth stats */ - u32 tx_restart, tx_busy; + u64 tx_restart, tx_busy; struct i40e_ring *p; - u32 rx_page, rx_buf; + u64 rx_page, rx_buf; u64 bytes, packets; unsigned int start; u64 tx_linearize; @@ -2137,19 +2143,19 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_del, int *retval) { struct i40e_hw *hw = &vsi->back->hw; + enum i40e_admin_queue_err aq_status; i40e_status aq_ret; - int aq_err; - aq_ret = i40e_aq_remove_macvlan(hw, vsi->seid, list, num_del, NULL); - aq_err = hw->aq.asq_last_status; + aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL, + &aq_status); /* Explicitly ignore and do not report when firmware returns ENOENT */ - if (aq_ret && !(aq_err == I40E_AQ_RC_ENOENT)) { + if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) { *retval = -EIO; dev_info(&vsi->back->pdev->dev, "ignoring delete macvlan error on %s, err %s, aq_err %s\n", vsi_name, i40e_stat_str(hw, aq_ret), - i40e_aq_str(hw, aq_err)); + i40e_aq_str(hw, aq_status)); } } @@ -2172,10 +2178,10 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, int num_add) { struct i40e_hw *hw = &vsi->back->hw; - int aq_err, fcnt; + enum i40e_admin_queue_err aq_status; + int fcnt; - i40e_aq_add_macvlan(hw, vsi->seid, list, num_add, NULL); - aq_err = hw->aq.asq_last_status; + i40e_aq_add_macvlan_v2(hw, vsi->seid, list, num_add, NULL, &aq_status); fcnt = i40e_update_filter_state(num_add, list, add_head); if (fcnt != num_add) { @@ -2183,17 +2189,19 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, promiscuous mode forced on\n", - i40e_aq_str(hw, aq_err), vsi_name); + i40e_aq_str(hw, aq_status), vsi_name); } else if (vsi->type == I40E_VSI_SRIOV || vsi->type == I40E_VSI_VMDQ1 || vsi->type == I40E_VSI_VMDQ2) { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi_name); + i40e_aq_str(hw, aq_status), vsi_name, + vsi_name); } else { dev_warn(&vsi->back->pdev->dev, "Error %s adding RX filters on %s, incorrect VSI type: %i.\n", - i40e_aq_str(hw, aq_err), vsi_name, vsi->type); + i40e_aq_str(hw, aq_status), vsi_name, + vsi->type); } } } @@ -5366,7 +5374,15 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { + + if (!vsi->mqprio_qopt.qopt.hw) { + if (pf->flags & I40E_FLAG_DCB_ENABLED) + goto skip_reset; + + if (IS_ENABLED(CONFIG_I40E_DCB) && + i40e_dcb_hw_get_num_tc(&pf->hw) == 1) + goto skip_reset; + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5374,6 +5390,8 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } + +skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) @@ -10574,15 +10592,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } i40e_get_oem_version(&pf->hw); - if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) && - ((hw->aq.fw_maj_ver == 4 && hw->aq.fw_min_ver <= 33) || - hw->aq.fw_maj_ver < 4) && hw->mac.type == I40E_MAC_XL710) { - /* The following delay is necessary for 4.33 firmware and older - * to recover after EMP reset. 200 ms should suffice but we - * put here 300 ms to be sure that FW is ready to operate - * after reset. - */ - mdelay(300); + if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state)) { + /* The following delay is necessary for firmware update. */ + mdelay(1000); } /* re-verify the eeprom if we just had an EMP reset */ @@ -10853,6 +10865,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { int ret; + + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; /* Now we wait for GRST to settle out. * We don't have to delete the VEBs or VSIs from the hw switch * because the reset will make them disappear. @@ -11792,7 +11807,6 @@ static int i40e_init_interrupt_scheme(struct i40e_pf *pf) return -ENOMEM; pf->irq_pile->num_entries = vectors; - pf->irq_pile->search_hint = 0; /* track first vector for misc interrupts, ignore return */ (void)i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT - 1); @@ -12213,6 +12227,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) vsi->req_queue_pairs = queue_count; i40e_prep_for_reset(pf); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return pf->alloc_rss_size; pf->alloc_rss_size = new_rss_size; @@ -12595,7 +12611,6 @@ static int i40e_sw_init(struct i40e_pf *pf) goto sw_init_done; } pf->qp_pile->num_entries = pf->hw.func_caps.num_tx_qp; - pf->qp_pile->search_hint = 0; pf->tx_timeout_recovery_level = 1; @@ -12709,7 +12724,8 @@ static int i40e_set_features(struct net_device *netdev, else i40e_vlan_stripping_disable(vsi); - if (!(features & NETIF_F_HW_TC) && pf->num_cloud_filters) { + if (!(features & NETIF_F_HW_TC) && + (netdev->features & NETIF_F_HW_TC) && pf->num_cloud_filters) { dev_err(&pf->pdev->dev, "Offloaded tc filters active, can't turn hw_tc_offload off"); return -EINVAL; @@ -13040,6 +13056,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, if (need_reset) i40e_prep_for_reset(pf); + /* VSI shall be deleted in a moment, just return EINVAL */ + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; + old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { @@ -13461,6 +13481,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + netdev->features &= ~NETIF_F_HW_TC; + if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, hw->mac.perm_addr); @@ -15324,12 +15346,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } /* set up pci connections */ @@ -15930,8 +15949,13 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); - while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE + * flags, once they are set, i40e_rebuild should not be called as + * i40e_prep_for_reset always returns early. + */ + while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) usleep_range(1000, 2000); + set_bit(__I40E_IN_REMOVE, pf->state); if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { set_bit(__I40E_VF_RESETS_DISABLED, pf->state); @@ -16130,6 +16154,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; + i40e_reset_and_rebuild(pf, false, false); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 9241b6005ad3..ebdcde6f1aeb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -27,10 +27,25 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details); i40e_status +i40e_asq_send_command_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); +i40e_status i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, bool is_atomic_context); +i40e_status +i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, + struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details, + bool is_atomic_context, + enum i40e_admin_queue_err *aq_status); /* debug function for adminq */ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, @@ -150,9 +165,19 @@ i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw, i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details); +i40e_status +i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_add_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details); +i40e_status +i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details, + enum i40e_admin_queue_err *aq_status); i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, struct i40e_asq_cmd_details *cmd_details, diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 8d0588a27a05..1908eed4fa5e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -413,6 +413,9 @@ #define I40E_VFINT_DYN_CTLN(_INTVF) (0x00024800 + ((_INTVF) * 4)) /* _i=0...511 */ /* Reset: VFR */ #define I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT 1 #define I40E_VFINT_DYN_CTLN_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN_CLEARPBA_SHIFT) +#define I40E_VFINT_ICR0_ADMINQ_SHIFT 30 +#define I40E_VFINT_ICR0_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ADMINQ_SHIFT) +#define I40E_VFINT_ICR0_ENA(_VF) (0x0002C000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ #define I40E_VPINT_AEQCTL(_VF) (0x0002B800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ #define I40E_VPINT_AEQCTL_MSIX_INDX_SHIFT 0 #define I40E_VPINT_AEQCTL_ITR_INDX_SHIFT 11 diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index bfc2845c99d1..88387a644cc3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -298,7 +298,6 @@ struct i40e_rx_queue_stats { u64 alloc_page_failed; u64 alloc_buff_failed; u64 page_reuse_count; - u64 realloc_count; }; enum i40e_ring_state_t { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b785d09c19f8..dfdb6e786461 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1377,6 +1377,32 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, } /** + * i40e_sync_vfr_reset + * @hw: pointer to hw struct + * @vf_id: VF identifier + * + * Before trigger hardware reset, we need to know if no other process has + * reserved the hardware for any reset operations. This check is done by + * examining the status of the RSTAT1 register used to signal the reset. + **/ +static int i40e_sync_vfr_reset(struct i40e_hw *hw, int vf_id) +{ + u32 reg; + int i; + + for (i = 0; i < I40E_VFR_WAIT_COUNT; i++) { + reg = rd32(hw, I40E_VFINT_ICR0_ENA(vf_id)) & + I40E_VFINT_ICR0_ADMINQ_MASK; + if (reg) + return 0; + + usleep_range(100, 200); + } + + return -EAGAIN; +} + +/** * i40e_trigger_vf_reset * @vf: pointer to the VF structure * @flr: VFLR was issued or not @@ -1390,9 +1416,11 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; u32 reg, reg_idx, bit_idx; + bool vf_active; + u32 radq; /* warn the VF */ - clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); + vf_active = test_and_clear_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states); /* Disable VF's configuration API during reset. The flag is re-enabled * in i40e_alloc_vf_res(), when it's safe again to access VF's VSI. @@ -1406,7 +1434,19 @@ static void i40e_trigger_vf_reset(struct i40e_vf *vf, bool flr) * just need to clean up, so don't hit the VFRTRIG register. */ if (!flr) { - /* reset VF using VPGEN_VFRTRIG reg */ + /* Sync VFR reset before trigger next one */ + radq = rd32(hw, I40E_VFINT_ICR0_ENA(vf->vf_id)) & + I40E_VFINT_ICR0_ADMINQ_MASK; + if (vf_active && !radq) + /* waiting for finish reset by virtual driver */ + if (i40e_sync_vfr_reset(hw, vf->vf_id)) + dev_info(&pf->pdev->dev, + "Reset VF %d never finished\n", + vf->vf_id); + + /* Reset VF using VPGEN_VFRTRIG reg. It is also setting + * in progress state in rstat1 register. + */ reg = rd32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id)); reg |= I40E_VPGEN_VFRTRIG_VFSWR_MASK; wr32(hw, I40E_VPGEN_VFRTRIG(vf->vf_id), reg); @@ -2618,6 +2658,59 @@ error_param: } /** + * i40e_check_enough_queue - find big enough queue number + * @vf: pointer to the VF info + * @needed: the number of items needed + * + * Returns the base item index of the queue, or negative for error + **/ +static int i40e_check_enough_queue(struct i40e_vf *vf, u16 needed) +{ + unsigned int i, cur_queues, more, pool_size; + struct i40e_lump_tracking *pile; + struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi; + + vsi = pf->vsi[vf->lan_vsi_idx]; + cur_queues = vsi->alloc_queue_pairs; + + /* if current allocated queues are enough for need */ + if (cur_queues >= needed) + return vsi->base_queue; + + pile = pf->qp_pile; + if (cur_queues > 0) { + /* if the allocated queues are not zero + * just check if there are enough queues for more + * behind the allocated queues. + */ + more = needed - cur_queues; + for (i = vsi->base_queue + cur_queues; + i < pile->num_entries; i++) { + if (pile->list[i] & I40E_PILE_VALID_BIT) + break; + + if (more-- == 1) + /* there is enough */ + return vsi->base_queue; + } + } + + pool_size = 0; + for (i = 0; i < pile->num_entries; i++) { + if (pile->list[i] & I40E_PILE_VALID_BIT) { + pool_size = 0; + continue; + } + if (needed <= ++pool_size) + /* there is enough */ + return i; + } + + return -ENOMEM; +} + +/** * i40e_vc_request_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2651,6 +2744,12 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) req_pairs - cur_pairs, pf->queues_left); vfres->num_queue_pairs = pf->queues_left + cur_pairs; + } else if (i40e_check_enough_queue(vf, req_pairs) < 0) { + dev_warn(&pf->pdev->dev, + "VF %d requested %d more queues, but there is not enough for it.\n", + vf->vf_id, + req_pairs - cur_pairs); + vfres->num_queue_pairs = cur_pairs; } else { /* successful request */ vf->num_req_queues = req_pairs; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 49575a640a84..03c42fd0fea1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -19,6 +19,7 @@ #define I40E_MAX_VF_PROMISC_FLAGS 3 #define I40E_VF_STATE_WAIT_COUNT 20 +#define I40E_VFR_WAIT_COUNT 100 /* Various queue ctrls */ enum i40e_queue_ctrl { diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 945b1bb9c6f4..67e9844e2076 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -241,21 +241,25 @@ bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) goto out; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } out: xsk_buff_free(xdp); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8125b9120615..b0bd95c85480 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4368,12 +4368,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } err = pci_request_regions(pdev, iavf_driver_name); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 30814435f779..f46af3b34074 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4459,8 +4459,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) /* set up for high or low DMA */ err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (err) { dev_err(dev, "DMA configuration failed: 0x%x\n", err); return err; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 3e38695f1c9d..c2258bee8ecb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -983,15 +983,17 @@ static struct sk_buff * ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, struct xdp_buff *xdp) { + unsigned int metasize = xdp->data - xdp->data_meta; unsigned int size = xdp->data_end - xdp->data; unsigned int headlen; struct sk_buff *skb; /* prefetch first cache line of first page */ - net_prefetch(xdp->data); + net_prefetch(xdp->data_meta); /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + ICE_RX_HDR_SIZE + metasize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -1003,8 +1005,13 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, - sizeof(long))); + memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta, + ALIGN(headlen + metasize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } /* if we exhaust the linear part then add what is left as a frag */ size -= headlen; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 2388837d6d6c..feb874bde171 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -428,20 +428,24 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring) static struct sk_buff * ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { - unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start; + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; struct sk_buff *skb; - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data - xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } xsk_buff_free(xdp); return skb; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 38ba92022cd4..bfa321e4003f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3164,8 +3164,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) s32 ret_val; static int global_quad_port_a; /* global quad port a indication */ const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; - int err, pci_using_dac; u8 part_str[E1000_PBANUM_LENGTH]; + int err; /* Catch broken hardware that put the wrong VF device ID in * the PCIe SR-IOV capability. @@ -3180,17 +3180,11 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, igb_driver_name); @@ -3306,8 +3300,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->mac.type >= e1000_i350) netdev->hw_features |= NETIF_F_NTUPLE; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index b78407289741..43ced78c3a2e 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2684,25 +2684,18 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct igbvf_adapter *adapter; struct e1000_hw *hw; const struct igbvf_info *ei = igbvf_info_tbl[ent->driver_data]; - static int cards_found; - int err, pci_using_dac; + int err; err = pci_enable_device_mem(pdev); if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_regions(pdev, igbvf_driver_name); @@ -2783,10 +2776,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_GSO_PARTIAL | IGBVF_GSO_PARTIAL_FEATURES; - netdev->features = netdev->hw_features; - - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features = netdev->hw_features | NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2f17f36e94fd..b965fb809d84 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2446,19 +2446,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, struct xdp_buff *xdp) { + unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; - unsigned int datasize = xdp->data_end - xdp->data; - unsigned int totalsize = metasize + datasize; struct sk_buff *skb; - skb = __napi_alloc_skb(&ring->q_vector->napi, - xdp->data_end - xdp->data_hard_start, + net_prefetch(xdp->data_meta); + + skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); - memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize); + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + if (metasize) { skb_metadata_set(skb, metasize); __skb_pull(skb, metasize); @@ -6251,23 +6252,17 @@ static int igc_probe(struct pci_dev *pdev, struct net_device *netdev; struct igc_hw *hw; const struct igc_info *ei = igc_info_tbl[ent->driver_data]; - int err, pci_using_dac; + int err; err = pci_enable_device_mem(pdev); if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, igc_driver_name); @@ -6367,8 +6362,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= netdev->features; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 99d481904ce6..affdefcca7e3 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -361,7 +361,6 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev = NULL; struct ixgb_adapter *adapter; static int cards_found = 0; - int pci_using_dac; u8 addr[ETH_ALEN]; int i; int err; @@ -370,16 +369,10 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - pci_using_dac = 0; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - pr_err("No usable DMA configuration, aborting\n"); - goto err_dma_mask; - } + if (err) { + pr_err("No usable DMA configuration, aborting\n"); + goto err_dma_mask; } err = pci_request_regions(pdev, ixgb_driver_name); @@ -444,10 +437,8 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_FILTER; netdev->hw_features |= NETIF_F_RXCSUM; - if (pci_using_dac) { - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - } + netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= NETIF_F_HIGHDMA; /* MTU range: 68 - 16114 */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 89b467006291..2c8a4a06f56a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10632,9 +10632,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgbe_adapter *adapter = NULL; struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; - int i, err, pci_using_dac, expected_gts; unsigned int indices = MAX_TX_QUEUES; u8 part_str[IXGBE_PBANUM_LENGTH]; + int i, err, expected_gts; bool disable_dev = false; #ifdef IXGBE_FCOE u16 device_caps; @@ -10654,16 +10654,11 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) return err; - if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } - pci_using_dac = 0; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_mem_regions(pdev, ixgbe_driver_name); @@ -10861,8 +10856,7 @@ skip_sriov: netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->hw_enc_features |= netdev->vlan_features; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index b3fd8e5cd85b..ee28929b9c5f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -207,26 +207,28 @@ bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) } static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, - struct ixgbe_rx_buffer *bi) + const struct xdp_buff *xdp) { - unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; - unsigned int datasize = bi->xdp->data_end - bi->xdp->data; + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; + net_prefetch(xdp->data_meta); + /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - bi->xdp->data_end - bi->xdp->data_hard_start, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, totalsize, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; - skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); - memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); - if (metasize) + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } - xsk_buff_free(bi->xdp); - bi->xdp = NULL; return skb; } @@ -317,12 +319,15 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, } /* XDP_PASS path */ - skb = ixgbe_construct_skb_zc(rx_ring, bi); + skb = ixgbe_construct_skb_zc(rx_ring, bi->xdp); if (!skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; break; } + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + cleaned_count++; ixgbe_inc_ntc(rx_ring); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0015fcf1df2b..7c33be9074e9 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4511,22 +4511,17 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgbevf_adapter *adapter = NULL; struct ixgbe_hw *hw = NULL; const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data]; - int err, pci_using_dac; bool disable_dev = false; + int err; err = pci_enable_device(pdev); if (err) return err; - if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { - pci_using_dac = 1; - } else { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); - goto err_dma; - } - pci_using_dac = 0; + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); + goto err_dma; } err = pci_request_regions(pdev, ixgbevf_driver_name); @@ -4606,10 +4601,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->hw_features |= NETIF_F_GSO_PARTIAL | IXGBEVF_GSO_PARTIAL_FEATURES; - netdev->features = netdev->hw_features; - - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; + netdev->features = netdev->hw_features | NETIF_F_HIGHDMA; netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; netdev->mpls_features |= NETIF_F_SG | diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 83c8908f0cc7..f1335a1ed695 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1884,8 +1884,8 @@ static void mvneta_txq_bufs_free(struct mvneta_port *pp, bytes_compl += buf->skb->len; pkts_compl++; dev_kfree_skb_any(buf->skb); - } else if (buf->type == MVNETA_TYPE_XDP_TX || - buf->type == MVNETA_TYPE_XDP_NDO) { + } else if ((buf->type == MVNETA_TYPE_XDP_TX || + buf->type == MVNETA_TYPE_XDP_NDO) && buf->xdpf) { if (napi && buf->type == MVNETA_TYPE_XDP_TX) xdp_return_frame_rx_napi(buf->xdpf); else @@ -2060,61 +2060,104 @@ int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) static void mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, - struct xdp_buff *xdp, struct skb_shared_info *sinfo, - int sync_len) + struct xdp_buff *xdp, int sync_len) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + for (i = 0; i < sinfo->nr_frags; i++) page_pool_put_full_page(rxq->page_pool, skb_frag_page(&sinfo->frags[i]), true); + +out: page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), sync_len, true); } static int mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq, - struct xdp_frame *xdpf, bool dma_map) + struct xdp_frame *xdpf, int *nxmit_byte, bool dma_map) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); + struct device *dev = pp->dev->dev.parent; struct mvneta_tx_desc *tx_desc; - struct mvneta_tx_buf *buf; - dma_addr_t dma_addr; + int i, num_frames = 1; + struct page *page; - if (txq->count >= txq->tx_stop_threshold) + if (unlikely(xdp_frame_has_frags(xdpf))) + num_frames += sinfo->nr_frags; + + if (txq->count + num_frames >= txq->size) return MVNETA_XDP_DROPPED; - tx_desc = mvneta_txq_next_desc_get(txq); + for (i = 0; i < num_frames; i++) { + struct mvneta_tx_buf *buf = &txq->buf[txq->txq_put_index]; + skb_frag_t *frag = NULL; + int len = xdpf->len; + dma_addr_t dma_addr; - buf = &txq->buf[txq->txq_put_index]; - if (dma_map) { - /* ndo_xdp_xmit */ - dma_addr = dma_map_single(pp->dev->dev.parent, xdpf->data, - xdpf->len, DMA_TO_DEVICE); - if (dma_mapping_error(pp->dev->dev.parent, dma_addr)) { - mvneta_txq_desc_put(txq); - return MVNETA_XDP_DROPPED; + if (unlikely(i)) { /* paged area */ + frag = &sinfo->frags[i - 1]; + len = skb_frag_size(frag); } - buf->type = MVNETA_TYPE_XDP_NDO; - } else { - struct page *page = virt_to_page(xdpf->data); - dma_addr = page_pool_get_dma_addr(page) + - sizeof(*xdpf) + xdpf->headroom; - dma_sync_single_for_device(pp->dev->dev.parent, dma_addr, - xdpf->len, DMA_BIDIRECTIONAL); - buf->type = MVNETA_TYPE_XDP_TX; - } - buf->xdpf = xdpf; + tx_desc = mvneta_txq_next_desc_get(txq); + if (dma_map) { + /* ndo_xdp_xmit */ + void *data; + + data = unlikely(frag) ? skb_frag_address(frag) + : xdpf->data; + dma_addr = dma_map_single(dev, data, len, + DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + mvneta_txq_desc_put(txq); + goto unmap; + } + + buf->type = MVNETA_TYPE_XDP_NDO; + } else { + page = unlikely(frag) ? skb_frag_page(frag) + : virt_to_page(xdpf->data); + dma_addr = page_pool_get_dma_addr(page); + if (unlikely(frag)) + dma_addr += skb_frag_off(frag); + else + dma_addr += sizeof(*xdpf) + xdpf->headroom; + dma_sync_single_for_device(dev, dma_addr, len, + DMA_BIDIRECTIONAL); + buf->type = MVNETA_TYPE_XDP_TX; + } + buf->xdpf = unlikely(i) ? NULL : xdpf; - tx_desc->command = MVNETA_TXD_FLZ_DESC; - tx_desc->buf_phys_addr = dma_addr; - tx_desc->data_size = xdpf->len; + tx_desc->command = unlikely(i) ? 0 : MVNETA_TXD_F_DESC; + tx_desc->buf_phys_addr = dma_addr; + tx_desc->data_size = len; + *nxmit_byte += len; - mvneta_txq_inc_put(txq); - txq->pending++; - txq->count++; + mvneta_txq_inc_put(txq); + } + /*last descriptor */ + tx_desc->command |= MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD; + + txq->pending += num_frames; + txq->count += num_frames; return MVNETA_XDP_TX; + +unmap: + for (i--; i >= 0; i--) { + mvneta_txq_desc_put(txq); + tx_desc = txq->descs + txq->next_desc_to_proc; + dma_unmap_single(dev, tx_desc->buf_phys_addr, + tx_desc->data_size, + DMA_TO_DEVICE); + } + + return MVNETA_XDP_DROPPED; } static int @@ -2123,8 +2166,8 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); struct mvneta_tx_queue *txq; struct netdev_queue *nq; + int cpu, nxmit_byte = 0; struct xdp_frame *xdpf; - int cpu; u32 ret; xdpf = xdp_convert_buff_to_frame(xdp); @@ -2136,10 +2179,10 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) nq = netdev_get_tx_queue(pp->dev, txq->id); __netif_tx_lock(nq, cpu); - ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false); + ret = mvneta_xdp_submit_frame(pp, txq, xdpf, &nxmit_byte, false); if (ret == MVNETA_XDP_TX) { u64_stats_update_begin(&stats->syncp); - stats->es.ps.tx_bytes += xdpf->len; + stats->es.ps.tx_bytes += nxmit_byte; stats->es.ps.tx_packets++; stats->es.ps.xdp_tx++; u64_stats_update_end(&stats->syncp); @@ -2178,11 +2221,11 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, __netif_tx_lock(nq, cpu); for (i = 0; i < num_frame; i++) { - ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true); + ret = mvneta_xdp_submit_frame(pp, txq, frames[i], &nxmit_byte, + true); if (ret != MVNETA_XDP_TX) break; - nxmit_byte += frames[i]->len; nxmit++; } @@ -2205,7 +2248,6 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct bpf_prog *prog, struct xdp_buff *xdp, u32 frame_sz, struct mvneta_stats *stats) { - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); unsigned int len, data_len, sync; u32 ret, act; @@ -2226,7 +2268,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, err = xdp_do_redirect(pp->dev, xdp, prog); if (unlikely(err)) { - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); ret = MVNETA_XDP_DROPPED; } else { ret = MVNETA_XDP_REDIR; @@ -2237,7 +2279,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, case XDP_TX: ret = mvneta_xdp_xmit_back(pp, xdp); if (ret != MVNETA_XDP_TX) - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); break; default: bpf_warn_invalid_xdp_action(pp->dev, prog, act); @@ -2246,7 +2288,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, trace_xdp_exception(pp->dev, prog, act); fallthrough; case XDP_DROP: - mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); + mvneta_xdp_put_buff(pp, rxq, xdp, sync); ret = MVNETA_XDP_DROPPED; stats->xdp_drop++; break; @@ -2269,7 +2311,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, int data_len = -MVNETA_MH_SIZE, len; struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; - struct skb_shared_info *sinfo; if (*size > MVNETA_MAX_RX_BUF_SIZE) { len = MVNETA_MAX_RX_BUF_SIZE; @@ -2289,11 +2330,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, /* Prefetch header */ prefetch(data); + xdp_buff_clear_frags_flag(xdp); xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE, data_len, false); - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = 0; } static void @@ -2301,9 +2340,9 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, struct mvneta_rx_desc *rx_desc, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, int *size, - struct skb_shared_info *xdp_sinfo, struct page *page) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; int data_len, len; @@ -2321,25 +2360,25 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, len, dma_dir); rx_desc->buf_phys_addr = 0; - if (data_len > 0 && xdp_sinfo->nr_frags < MAX_SKB_FRAGS) { - skb_frag_t *frag = &xdp_sinfo->frags[xdp_sinfo->nr_frags++]; + if (!xdp_buff_has_frags(xdp)) + sinfo->nr_frags = 0; + + if (data_len > 0 && sinfo->nr_frags < MAX_SKB_FRAGS) { + skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags++]; skb_frag_off_set(frag, pp->rx_offset_correction); skb_frag_size_set(frag, data_len); __skb_frag_set_page(frag, page); + + if (!xdp_buff_has_frags(xdp)) { + sinfo->xdp_frags_size = *size; + xdp_buff_set_frags_flag(xdp); + } + if (page_is_pfmemalloc(page)) + xdp_buff_set_frag_pfmemalloc(xdp); } else { page_pool_put_full_page(rxq->page_pool, page, true); } - - /* last fragment */ - if (len == *size) { - struct skb_shared_info *sinfo; - - sinfo = xdp_get_shared_info_from_buff(xdp); - sinfo->nr_frags = xdp_sinfo->nr_frags; - memcpy(sinfo->frags, xdp_sinfo->frags, - sinfo->nr_frags * sizeof(skb_frag_t)); - } *size -= len; } @@ -2348,8 +2387,11 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, struct xdp_buff *xdp, u32 desc_status) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - int i, num_frags = sinfo->nr_frags; struct sk_buff *skb; + u8 num_frags; + + if (unlikely(xdp_buff_has_frags(xdp))) + num_frags = sinfo->nr_frags; skb = build_skb(xdp->data_hard_start, PAGE_SIZE); if (!skb) @@ -2361,13 +2403,11 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, skb_put(skb, xdp->data_end - xdp->data); skb->ip_summed = mvneta_rx_csum(pp, desc_status); - for (i = 0; i < num_frags; i++) { - skb_frag_t *frag = &sinfo->frags[i]; - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - skb_frag_page(frag), skb_frag_off(frag), - skb_frag_size(frag), PAGE_SIZE); - } + if (unlikely(xdp_buff_has_frags(xdp))) + xdp_update_skb_shared_info(skb, num_frags, + sinfo->xdp_frags_size, + num_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } @@ -2379,7 +2419,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, { int rx_proc = 0, rx_todo, refill, size = 0; struct net_device *dev = pp->dev; - struct skb_shared_info sinfo; struct mvneta_stats ps = {}; struct bpf_prog *xdp_prog; u32 desc_status, frame_sz; @@ -2388,8 +2427,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, xdp_init_buff(&xdp_buf, PAGE_SIZE, &rxq->xdp_rxq); xdp_buf.data_hard_start = NULL; - sinfo.nr_frags = 0; - /* Get number of received packets */ rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); @@ -2431,7 +2468,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, } mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf, - &size, &sinfo, page); + &size, page); } /* Middle or Last descriptor */ if (!(rx_status & MVNETA_RXD_LAST_DESC)) @@ -2439,7 +2476,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, continue; if (size) { - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); goto next; } @@ -2451,7 +2488,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, if (IS_ERR(skb)) { struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); u64_stats_update_begin(&stats->syncp); stats->es.skb_alloc_error++; @@ -2468,11 +2505,10 @@ static int mvneta_rx_swbm(struct napi_struct *napi, napi_gro_receive(napi, skb); next: xdp_buf.data_hard_start = NULL; - sinfo.nr_frags = 0; } if (xdp_buf.data_hard_start) - mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); + mvneta_xdp_put_buff(pp, rxq, &xdp_buf, -1); if (ps.xdp_redirect) xdp_do_flush_map(); @@ -3260,7 +3296,8 @@ static int mvneta_create_page_pool(struct mvneta_port *pp, return err; } - err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0); + err = __xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0, + PAGE_SIZE); if (err < 0) goto err_free_pp; @@ -3740,6 +3777,7 @@ static void mvneta_percpu_disable(void *arg) static int mvneta_change_mtu(struct net_device *dev, int mtu) { struct mvneta_port *pp = netdev_priv(dev); + struct bpf_prog *prog = pp->xdp_prog; int ret; if (!IS_ALIGNED(MVNETA_RX_PKT_SIZE(mtu), 8)) { @@ -3748,8 +3786,11 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVNETA_RX_PKT_SIZE(mtu), 8); } - if (pp->xdp_prog && mtu > MVNETA_MAX_RX_BUF_SIZE) { - netdev_info(dev, "Illegal MTU value %d for XDP mode\n", mtu); + if (prog && !prog->aux->xdp_has_frags && + mtu > MVNETA_MAX_RX_BUF_SIZE) { + netdev_info(dev, "Illegal MTU %d for XDP prog without frags\n", + mtu); + return -EINVAL; } @@ -3969,6 +4010,15 @@ static const struct phylink_pcs_ops mvneta_phylink_pcs_ops = { .pcs_an_restart = mvneta_pcs_an_restart, }; +static struct phylink_pcs *mvneta_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct mvneta_port *pp = netdev_priv(ndev); + + return &pp->phylink_pcs; +} + static int mvneta_mac_prepare(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -4169,13 +4219,14 @@ static void mvneta_mac_link_up(struct phylink_config *config, mvneta_port_up(pp); if (phy && pp->eee_enabled) { - pp->eee_active = phy_init_eee(phy, 0) >= 0; + pp->eee_active = phy_init_eee(phy, false) >= 0; mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled); } } static const struct phylink_mac_ops mvneta_phylink_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = mvneta_mac_select_pcs, .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, .mac_finish = mvneta_mac_finish, @@ -4490,8 +4541,9 @@ static int mvneta_xdp_setup(struct net_device *dev, struct bpf_prog *prog, struct mvneta_port *pp = netdev_priv(dev); struct bpf_prog *old_prog; - if (prog && dev->mtu > MVNETA_MAX_RX_BUF_SIZE) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large for XDP"); + if (prog && !prog->aux->xdp_has_frags && + dev->mtu > MVNETA_MAX_RX_BUF_SIZE) { + NL_SET_ERR_MSG_MOD(extack, "prog does not support XDP frags"); return -EOPNOTSUPP; } @@ -5321,26 +5373,62 @@ static int mvneta_probe(struct platform_device *pdev) if (!dev) return -ENOMEM; - dev->irq = irq_of_parse_and_map(dn, 0); - if (dev->irq == 0) - return -EINVAL; + dev->tx_queue_len = MVNETA_MAX_TXD; + dev->watchdog_timeo = 5 * HZ; + dev->netdev_ops = &mvneta_netdev_ops; + dev->ethtool_ops = &mvneta_eth_tool_ops; + + pp = netdev_priv(dev); + spin_lock_init(&pp->lock); + pp->dn = dn; + + pp->rxq_def = rxq_def; + pp->indir[0] = rxq_def; err = of_get_phy_mode(dn, &phy_mode); if (err) { dev_err(&pdev->dev, "incorrect phy-mode\n"); - goto err_free_irq; + return err; } + pp->phy_interface = phy_mode; + comphy = devm_of_phy_get(&pdev->dev, dn, NULL); - if (comphy == ERR_PTR(-EPROBE_DEFER)) { - err = -EPROBE_DEFER; - goto err_free_irq; - } else if (IS_ERR(comphy)) { + if (comphy == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + if (IS_ERR(comphy)) comphy = NULL; + + pp->comphy = comphy; + + pp->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pp->base)) + return PTR_ERR(pp->base); + + /* Get special SoC configurations */ + if (of_device_is_compatible(dn, "marvell,armada-3700-neta")) + pp->neta_armada3700 = true; + + dev->irq = irq_of_parse_and_map(dn, 0); + if (dev->irq == 0) + return -EINVAL; + + pp->clk = devm_clk_get(&pdev->dev, "core"); + if (IS_ERR(pp->clk)) + pp->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(pp->clk)) { + err = PTR_ERR(pp->clk); + goto err_free_irq; } - pp = netdev_priv(dev); - spin_lock_init(&pp->lock); + clk_prepare_enable(pp->clk); + + pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); + if (!IS_ERR(pp->clk_bus)) + clk_prepare_enable(pp->clk_bus); + + pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; pp->phylink_config.dev = &dev->dev; pp->phylink_config.type = PHYLINK_NETDEV; @@ -5377,55 +5465,16 @@ static int mvneta_probe(struct platform_device *pdev) phy_mode, &mvneta_phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); - goto err_free_irq; - } - - dev->tx_queue_len = MVNETA_MAX_TXD; - dev->watchdog_timeo = 5 * HZ; - dev->netdev_ops = &mvneta_netdev_ops; - - dev->ethtool_ops = &mvneta_eth_tool_ops; - - pp->phylink = phylink; - pp->comphy = comphy; - pp->phy_interface = phy_mode; - pp->dn = dn; - - pp->rxq_def = rxq_def; - pp->indir[0] = rxq_def; - - /* Get special SoC configurations */ - if (of_device_is_compatible(dn, "marvell,armada-3700-neta")) - pp->neta_armada3700 = true; - - pp->clk = devm_clk_get(&pdev->dev, "core"); - if (IS_ERR(pp->clk)) - pp->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(pp->clk)) { - err = PTR_ERR(pp->clk); - goto err_free_phylink; - } - - clk_prepare_enable(pp->clk); - - pp->clk_bus = devm_clk_get(&pdev->dev, "bus"); - if (!IS_ERR(pp->clk_bus)) - clk_prepare_enable(pp->clk_bus); - - pp->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(pp->base)) { - err = PTR_ERR(pp->base); goto err_clk; } - pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; - phylink_set_pcs(phylink, &pp->phylink_pcs); + pp->phylink = phylink; /* Alloc per-cpu port structure */ pp->ports = alloc_percpu(struct mvneta_pcpu_port); if (!pp->ports) { err = -ENOMEM; - goto err_clk; + goto err_free_phylink; } /* Alloc per-cpu stats */ @@ -5569,12 +5618,12 @@ err_netdev: free_percpu(pp->stats); err_free_ports: free_percpu(pp->ports); -err_clk: - clk_disable_unprepare(pp->clk_bus); - clk_disable_unprepare(pp->clk); err_free_phylink: if (pp->phylink) phylink_destroy(pp->phylink); +err_clk: + clk_disable_unprepare(pp->clk_bus); + clk_disable_unprepare(pp->clk); err_free_irq: irq_dispose_mapping(dev->irq); return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 186d00a9ab35..3631d612aaca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1570,6 +1570,8 @@ static struct mac_ops cgx_mac_ops = { .mac_enadis_pause_frm = cgx_lmac_enadis_pause_frm, .mac_pause_frm_config = cgx_lmac_pause_frm_config, .mac_enadis_ptp_config = cgx_lmac_ptp_config, + .mac_rx_tx_enable = cgx_lmac_rx_tx_enable, + .mac_tx_enable = cgx_lmac_tx_enable, }; static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index fc6e7423cbd8..b33e7d1d0851 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -107,6 +107,9 @@ struct mac_ops { void (*mac_enadis_ptp_config)(void *cgxd, int lmac_id, bool enable); + + int (*mac_rx_tx_enable)(void *cgxd, int lmac_id, bool enable); + int (*mac_tx_enable)(void *cgxd, int lmac_id, bool enable); }; struct cgx { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 4e79e918a161..58e2aeebc14f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -732,6 +732,7 @@ enum nix_af_status { NIX_AF_ERR_BANDPROF_INVAL_REQ = -428, NIX_AF_ERR_CQ_CTX_WRITE_ERR = -429, NIX_AF_ERR_AQ_CTX_RETRY_WRITE = -430, + NIX_AF_ERR_LINK_CREDITS = -431, }; /* For NIX RX vtag action */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index 0fe7ad35e36f..4180376fa676 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -185,7 +185,6 @@ enum npc_kpu_parser_state { NPC_S_KPU2_QINQ, NPC_S_KPU2_ETAG, NPC_S_KPU2_EXDSA, - NPC_S_KPU2_NGIO, NPC_S_KPU2_CPT_CTAG, NPC_S_KPU2_CPT_QINQ, NPC_S_KPU3_CTAG, @@ -212,6 +211,7 @@ enum npc_kpu_parser_state { NPC_S_KPU5_NSH, NPC_S_KPU5_CPT_IP, NPC_S_KPU5_CPT_IP6, + NPC_S_KPU5_NGIO, NPC_S_KPU6_IP6_EXT, NPC_S_KPU6_IP6_HOP_DEST, NPC_S_KPU6_IP6_ROUT, @@ -1124,15 +1124,6 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { NPC_S_KPU1_ETHER, 0xff, NPC_ETYPE_CTAG, 0xffff, - NPC_ETYPE_NGIO, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_ETHER, 0xff, - NPC_ETYPE_CTAG, - 0xffff, NPC_ETYPE_CTAG, 0xffff, 0x0000, @@ -1968,6 +1959,15 @@ static struct npc_kpu_profile_cam kpu2_cam_entries[] = { }, { NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_NGIO, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, NPC_ETYPE_PPPOE, 0xffff, 0x0000, @@ -2750,15 +2750,6 @@ static struct npc_kpu_profile_cam kpu2_cam_entries[] = { 0x0000, }, { - NPC_S_KPU2_NGIO, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { NPC_S_KPU2_CPT_CTAG, 0xff, NPC_ETYPE_IP, 0xffff, @@ -5090,6 +5081,15 @@ static struct npc_kpu_profile_cam kpu5_cam_entries[] = { 0x0000, }, { + NPC_S_KPU5_NGIO, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { NPC_S_NA, 0X00, 0x0000, 0x0000, @@ -8425,14 +8425,6 @@ static struct npc_kpu_profile_action kpu1_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 12, 0, 0, 0, - NPC_S_KPU2_NGIO, 12, 1, - NPC_LID_LA, NPC_LT_LA_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 12, 0, 0, 0, NPC_S_KPU2_CTAG2, 12, 1, NPC_LID_LA, NPC_LT_LA_ETHER, NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, @@ -9196,6 +9188,14 @@ static struct npc_kpu_profile_action kpu2_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU5_NGIO, 6, 1, + NPC_LID_LB, NPC_LT_LB_CTAG, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 2, 0, NPC_S_KPU5_IP, 14, 1, NPC_LID_LB, NPC_LT_LB_PPPOE, @@ -9892,14 +9892,6 @@ static struct npc_kpu_profile_action kpu2_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 1, - NPC_LID_LC, NPC_LT_LC_NGIO, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 2, 0, NPC_S_KPU5_CPT_IP, 6, 1, NPC_LID_LB, NPC_LT_LB_CTAG, @@ -11974,6 +11966,14 @@ static struct npc_kpu_profile_action kpu5_action_entries[] = { 0, 0, 0, 0, }, { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_NGIO, + 0, + 0, 0, 0, 0, + }, + { NPC_ERRLEV_LC, NPC_EC_UNK, 0, 0, 0, 0, 1, NPC_S_NA, 0, 0, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index e695fa0e82a9..9ea2f6ac38ec 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -30,6 +30,8 @@ static struct mac_ops rpm_mac_ops = { .mac_enadis_pause_frm = rpm_lmac_enadis_pause_frm, .mac_pause_frm_config = rpm_lmac_pause_frm_config, .mac_enadis_ptp_config = rpm_lmac_ptp_config, + .mac_rx_tx_enable = rpm_lmac_rx_tx_enable, + .mac_tx_enable = rpm_lmac_tx_enable, }; struct mac_ops *rpm_get_mac_ops(void) @@ -54,6 +56,43 @@ int rpm_get_nr_lmacs(void *rpmd) return hweight8(rpm_read(rpm, 0, CGXX_CMRX_RX_LMACS) & 0xFULL); } +int rpm_lmac_tx_enable(void *rpmd, int lmac_id, bool enable) +{ + rpm_t *rpm = rpmd; + u64 cfg, last; + + if (!is_lmac_valid(rpm, lmac_id)) + return -ENODEV; + + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + last = cfg; + if (enable) + cfg |= RPM_TX_EN; + else + cfg &= ~(RPM_TX_EN); + + if (cfg != last) + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + return !!(last & RPM_TX_EN); +} + +int rpm_lmac_rx_tx_enable(void *rpmd, int lmac_id, bool enable) +{ + rpm_t *rpm = rpmd; + u64 cfg; + + if (!is_lmac_valid(rpm, lmac_id)) + return -ENODEV; + + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + if (enable) + cfg |= RPM_RX_EN | RPM_TX_EN; + else + cfg &= ~(RPM_RX_EN | RPM_TX_EN); + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + return 0; +} + void rpm_lmac_enadis_rx_pause_fwding(void *rpmd, int lmac_id, bool enable) { rpm_t *rpm = rpmd; @@ -252,23 +291,20 @@ int rpm_lmac_internal_loopback(void *rpmd, int lmac_id, bool enable) if (!rpm || lmac_id >= rpm->lmac_count) return -ENODEV; lmac_type = rpm->mac_ops->get_lmac_type(rpm, lmac_id); - if (lmac_type == LMAC_MODE_100G_R) { - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_PCS100X_CONTROL1); - - if (enable) - cfg |= RPMX_MTI_PCS_LBK; - else - cfg &= ~RPMX_MTI_PCS_LBK; - rpm_write(rpm, lmac_id, RPMX_MTI_PCS100X_CONTROL1, cfg); - } else { - cfg = rpm_read(rpm, lmac_id, RPMX_MTI_LPCSX_CONTROL1); - if (enable) - cfg |= RPMX_MTI_PCS_LBK; - else - cfg &= ~RPMX_MTI_PCS_LBK; - rpm_write(rpm, lmac_id, RPMX_MTI_LPCSX_CONTROL1, cfg); + + if (lmac_type == LMAC_MODE_QSGMII || lmac_type == LMAC_MODE_SGMII) { + dev_err(&rpm->pdev->dev, "loopback not supported for LPC mode\n"); + return 0; } + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_PCS100X_CONTROL1); + + if (enable) + cfg |= RPMX_MTI_PCS_LBK; + else + cfg &= ~RPMX_MTI_PCS_LBK; + rpm_write(rpm, lmac_id, RPMX_MTI_PCS100X_CONTROL1, cfg); + return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h index 57c8a687b488..ff580311edd0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h @@ -43,6 +43,8 @@ #define RPMX_MTI_STAT_DATA_HI_CDC 0x10038 #define RPM_LMAC_FWI 0xa +#define RPM_TX_EN BIT_ULL(0) +#define RPM_RX_EN BIT_ULL(1) /* Function Declarations */ int rpm_get_nr_lmacs(void *rpmd); @@ -57,4 +59,6 @@ int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, int rpm_get_tx_stats(void *rpmd, int lmac_id, int idx, u64 *tx_stat); int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat); void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable); +int rpm_lmac_rx_tx_enable(void *rpmd, int lmac_id, bool enable); +int rpm_lmac_tx_enable(void *rpmd, int lmac_id, bool enable); #endif /* RPM_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 3ca6b942ebe2..54e1b27a7dfe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -520,8 +520,11 @@ static void rvu_block_reset(struct rvu *rvu, int blkaddr, u64 rst_reg) rvu_write64(rvu, blkaddr, rst_reg, BIT_ULL(0)); err = rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true); - if (err) - dev_err(rvu->dev, "HW block:%d reset failed\n", blkaddr); + if (err) { + dev_err(rvu->dev, "HW block:%d reset timeout retrying again\n", blkaddr); + while (rvu_poll_reg(rvu, blkaddr, rst_reg, BIT_ULL(63), true) == -EBUSY) + ; + } } static void rvu_reset_all_blocks(struct rvu *rvu) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 66e45d733824..5ed94cfb47d2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -806,6 +806,7 @@ bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); +int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 2ca182a4ce82..8a7ac5a8b821 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -441,16 +441,26 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable) int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) { int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; u8 cgx_id, lmac_id; + void *cgxd; if (!is_cgx_config_permitted(rvu, pcifunc)) return LMAC_AF_ERR_PERM_DENIED; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start); +} - cgx_lmac_rx_tx_enable(rvu_cgx_pdata(cgx_id, rvu), lmac_id, start); +int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) +{ + struct mac_ops *mac_ops; - return 0; + mac_ops = get_mac_ops(cgxd); + return mac_ops->mac_tx_enable(cgxd, lmac_id, enable); } void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index a09a507369ac..d1eddb769a41 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1224,6 +1224,8 @@ static void print_nix_cn10k_sq_ctx(struct seq_file *m, seq_printf(m, "W3: head_offset\t\t\t%d\nW3: smenq_next_sqb_vld\t\t%d\n\n", sq_ctx->head_offset, sq_ctx->smenq_next_sqb_vld); + seq_printf(m, "W3: smq_next_sq_vld\t\t%d\nW3: smq_pend\t\t\t%d\n", + sq_ctx->smq_next_sq_vld, sq_ctx->smq_pend); seq_printf(m, "W4: next_sqb \t\t\t%llx\n\n", sq_ctx->next_sqb); seq_printf(m, "W5: tail_sqb \t\t\t%llx\n\n", sq_ctx->tail_sqb); seq_printf(m, "W6: smenq_sqb \t\t\t%llx\n\n", sq_ctx->smenq_sqb); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d8b1948aaa0a..97fb61915379 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -512,11 +512,11 @@ static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST); lmac_chan_cnt = cfg & 0xFF; - cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST1); - sdp_chan_cnt = cfg & 0xFFF; - cgx_bpid_cnt = hw->cgx_links * lmac_chan_cnt; lbk_bpid_cnt = hw->lbk_links * ((cfg >> 16) & 0xFF); + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST1); + sdp_chan_cnt = cfg & 0xFFF; sdp_bpid_cnt = hw->sdp_links * sdp_chan_cnt; pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); @@ -2068,8 +2068,8 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, /* enable cgx tx if disabled */ if (is_pf_cgxmapped(rvu, pf)) { rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), - lmac_id, true); + restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), + lmac_id, true); } cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq)); @@ -2092,7 +2092,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr, rvu_cgx_enadis_rx_bp(rvu, pf, true); /* restore cgx tx state */ if (restore_tx_en) - cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); + rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); return err; } @@ -3878,7 +3878,7 @@ nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, /* Enable cgx tx if disabled for credits to be back */ if (is_pf_cgxmapped(rvu, pf)) { rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), + restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, true); } @@ -3891,8 +3891,8 @@ nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0)); } - rc = -EBUSY; - poll_tmo = jiffies + usecs_to_jiffies(10000); + rc = NIX_AF_ERR_LINK_CREDITS; + poll_tmo = jiffies + usecs_to_jiffies(200000); /* Wait for credits to return */ do { if (time_after(jiffies, poll_tmo)) @@ -3918,7 +3918,7 @@ exit: /* Restore state of cgx tx */ if (restore_tx_en) - cgx_lmac_tx_enable(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); + rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); mutex_unlock(&rvu->rsrc_lock); return rc; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index c0005a1feee6..91f86d77cd41 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -402,6 +402,7 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, int index, struct mcam_entry *entry, bool *enable) { + struct rvu_npc_mcam_rule *rule; u16 owner, target_func; struct rvu_pfvf *pfvf; u64 rx_action; @@ -423,6 +424,12 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, test_bit(NIXLF_INITIALIZED, &pfvf->flags))) *enable = false; + /* fix up not needed for the rules added by user(ntuple filters) */ + list_for_each_entry(rule, &mcam->mcam_rules, list) { + if (rule->entry == index) + return; + } + /* copy VF default entry action to the VF mcam entry */ rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, target_func); @@ -489,8 +496,8 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, } /* PF installing VF rule */ - if (intf == NIX_INTF_RX && actindex < mcam->bmap_entries) - npc_fixup_vf_rule(rvu, mcam, blkaddr, index, entry, &enable); + if (is_npc_intf_rx(intf) && actindex < mcam->bmap_entries) + npc_fixup_vf_rule(rvu, mcam, blkaddr, actindex, entry, &enable); /* Set 'action' */ rvu_write64(rvu, blkaddr, @@ -916,7 +923,8 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 pcifunc, u64 rx_action) { int actindex, index, bank, entry; - bool enable; + struct rvu_npc_mcam_rule *rule; + bool enable, update; if (!(pcifunc & RVU_PFVF_FUNC_MASK)) return; @@ -924,6 +932,14 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam, mutex_lock(&mcam->lock); for (index = 0; index < mcam->bmap_entries; index++) { if (mcam->entry2target_pffunc[index] == pcifunc) { + update = true; + /* update not needed for the rules added via ntuple filters */ + list_for_each_entry(rule, &mcam->mcam_rules, list) { + if (rule->entry == index) + update = false; + } + if (!update) + continue; bank = npc_get_bank(mcam, index); actindex = index; entry = index & (mcam->banksize - 1); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index ff2b21999f36..19c53e591d0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -1098,14 +1098,6 @@ find_rule: write_req.cntr = rule->cntr; } - err = rvu_mbox_handler_npc_mcam_write_entry(rvu, &write_req, - &write_rsp); - if (err) { - rvu_mcam_remove_counter_from_rule(rvu, owner, rule); - if (new) - kfree(rule); - return err; - } /* update rule */ memcpy(&rule->packet, &dummy.packet, sizeof(rule->packet)); memcpy(&rule->mask, &dummy.mask, sizeof(rule->mask)); @@ -1132,6 +1124,18 @@ find_rule: if (req->default_rule) pfvf->def_ucast_rule = rule; + /* write to mcam entry registers */ + err = rvu_mbox_handler_npc_mcam_write_entry(rvu, &write_req, + &write_rsp); + if (err) { + rvu_mcam_remove_counter_from_rule(rvu, owner, rule); + if (new) { + list_del(&rule->list); + kfree(rule); + } + return err; + } + /* VF's MAC address is being changed via PF */ if (pf_set_vfs_mac) { ether_addr_copy(pfvf->default_mac, req->packet.dmac); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 66da31f30d3e..92c0ddb602ca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -222,8 +222,11 @@ EXPORT_SYMBOL(otx2_set_mac_address); int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) { struct nix_frs_cfg *req; + u16 maxlen; int err; + maxlen = otx2_get_max_mtu(pfvf) + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_nix_set_hw_frs(&pfvf->mbox); if (!req) { @@ -233,6 +236,10 @@ int otx2_hw_set_mtu(struct otx2_nic *pfvf, int mtu) req->maxlen = pfvf->netdev->mtu + OTX2_ETH_HLEN + OTX2_HW_TIMESTAMP_LEN; + /* Use max receive length supported by hardware for loopback devices */ + if (is_otx2_lbkvf(pfvf->pdev)) + req->maxlen = maxlen; + err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); return err; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 61e52812983f..56be20053931 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -178,6 +178,9 @@ struct otx2_hw { u16 rqpool_cnt; u16 sqpool_cnt; +#define OTX2_DEFAULT_RBUF_LEN 2048 + u16 rbuf_len; + /* NPA */ u32 stack_pg_ptrs; /* No of ptrs per stack page */ u32 stack_pg_bytes; /* Size of stack page */ @@ -603,6 +606,7 @@ static inline void __cn10k_aura_freeptr(struct otx2_nic *pfvf, u64 aura, size++; tar_addr |= ((size - 1) & 0x7) << 4; } + dma_wmb(); memcpy((u64 *)lmt_info->lmt_addr, ptrs, sizeof(u64) * num_ptrs); /* Perform LMTST flush */ cn10k_lmt_flush(val, tar_addr); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index d85db90632d6..abe5267210ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -371,6 +371,7 @@ static void otx2_get_ringparam(struct net_device *netdev, ring->rx_pending = qs->rqe_cnt ? qs->rqe_cnt : Q_COUNT(Q_SIZE_256); ring->tx_max_pending = Q_COUNT(Q_SIZE_MAX); ring->tx_pending = qs->sqe_cnt ? qs->sqe_cnt : Q_COUNT(Q_SIZE_4K); + kernel_ring->rx_buf_len = pfvf->hw.rbuf_len; } static int otx2_set_ringparam(struct net_device *netdev, @@ -379,6 +380,8 @@ static int otx2_set_ringparam(struct net_device *netdev, struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); + u32 rx_buf_len = kernel_ring->rx_buf_len; + u32 old_rx_buf_len = pfvf->hw.rbuf_len; bool if_up = netif_running(netdev); struct otx2_qset *qs = &pfvf->qset; u32 rx_count, tx_count; @@ -386,6 +389,15 @@ static int otx2_set_ringparam(struct net_device *netdev, if (ring->rx_mini_pending || ring->rx_jumbo_pending) return -EINVAL; + /* Hardware supports max size of 32k for a receive buffer + * and 1536 is typical ethernet frame size. + */ + if (rx_buf_len && (rx_buf_len < 1536 || rx_buf_len > 32768)) { + netdev_err(netdev, + "Receive buffer range is 1536 - 32768"); + return -EINVAL; + } + /* Permitted lengths are 16 64 256 1K 4K 16K 64K 256K 1M */ rx_count = ring->rx_pending; /* On some silicon variants a skid or reserved CQEs are @@ -403,7 +415,8 @@ static int otx2_set_ringparam(struct net_device *netdev, Q_COUNT(Q_SIZE_4K), Q_COUNT(Q_SIZE_MAX)); tx_count = Q_COUNT(Q_SIZE(tx_count, 3)); - if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt) + if (tx_count == qs->sqe_cnt && rx_count == qs->rqe_cnt && + rx_buf_len == old_rx_buf_len) return 0; if (if_up) @@ -413,6 +426,8 @@ static int otx2_set_ringparam(struct net_device *netdev, qs->sqe_cnt = tx_count; qs->rqe_cnt = rx_count; + pfvf->hw.rbuf_len = rx_buf_len; + if (if_up) return netdev->netdev_ops->ndo_open(netdev); @@ -1207,6 +1222,7 @@ end: static const struct ethtool_ops otx2_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, + .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN, .get_link = otx2_get_link, .get_drvinfo = otx2_get_drvinfo, .get_strings = otx2_get_strings, @@ -1326,6 +1342,7 @@ static int otx2vf_get_link_ksettings(struct net_device *netdev, static const struct ethtool_ops otx2vf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, + .supported_ring_params = ETHTOOL_RING_USE_RX_BUF_LEN, .get_link = otx2_get_link, .get_drvinfo = otx2vf_get_drvinfo, .get_strings = otx2vf_get_strings, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 6080ebd9bd94..86c1c2f77bd7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -394,7 +394,12 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf, dst_mdev->msg_size = mbox_hdr->msg_size; dst_mdev->num_msgs = num_msgs; err = otx2_sync_mbox_msg(dst_mbox); - if (err) { + /* Error code -EIO indicate there is a communication failure + * to the AF. Rest of the error codes indicate that AF processed + * VF messages and set the error codes in response messages + * (if any) so simply forward responses to VF. + */ + if (err == -EIO) { dev_warn(pf->dev, "AF not responding to VF%d messages\n", vf); /* restore PF mbase and exit */ @@ -1306,6 +1311,9 @@ static int otx2_get_rbuf_size(struct otx2_nic *pf, int mtu) int total_size; int rbuf_size; + if (pf->hw.rbuf_len) + return ALIGN(pf->hw.rbuf_len, OTX2_ALIGN) + OTX2_HEAD_ROOM; + /* The data transferred by NIX to memory consists of actual packet * plus additional data which has timestamp and/or EDSA/HIGIG2 * headers if interface is configured in corresponding modes. @@ -2620,6 +2628,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->tx_queues = qcount; hw->tot_tx_queues = qcount; hw->max_queues = qcount; + hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; num_vec = pci_msix_vec_count(pdev); hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 925b74ebb8b0..d96c8903c67e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -586,6 +586,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->tx_queues = qcount; hw->max_queues = qcount; hw->tot_tx_queues = qcount; + hw->rbuf_len = OTX2_DEFAULT_RBUF_LEN; hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, GFP_KERNEL); diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 89ca7960b225..4cd0747edaff 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1556,6 +1556,7 @@ static int mtk_star_probe(struct platform_device *pdev) return devm_register_netdev(dev, ndev); } +#ifdef CONFIG_OF static const struct of_device_id mtk_star_of_match[] = { { .compatible = "mediatek,mt8516-eth", }, { .compatible = "mediatek,mt8518-eth", }, @@ -1563,6 +1564,7 @@ static const struct of_device_id mtk_star_of_match[] = { { } }; MODULE_DEVICE_TABLE(of, mtk_star_of_match); +#endif static SIMPLE_DEV_PM_OPS(mtk_star_pm_ops, mtk_star_suspend, mtk_star_resume); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 812e6810cb3b..c14e06ca64d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -224,7 +224,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -241,8 +241,8 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; union { - struct mlx5_mtt inline_mtts[0]; - struct mlx5_klm inline_klms[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); + DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms); }; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 00449df98a5e..c1e07496c89c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -570,7 +570,8 @@ static int mlx5e_htb_convert_rate(struct mlx5e_priv *priv, u64 rate, static void mlx5e_htb_convert_ceil(struct mlx5e_priv *priv, u64 ceil, u32 *max_average_bw) { - *max_average_bw = div_u64(ceil, BYTES_IN_MBIT); + /* Hardware treats 0 as "unlimited", set at least 1. */ + *max_average_bw = max_t(u32, div_u64(ceil, BYTES_IN_MBIT), 1); qos_dbg(priv->mdev, "Convert: ceil %llu -> max_average_bw %u\n", ceil, *max_average_bw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 9c076aa20306..b6f5c1bcdbcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,18 +183,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *priv; - - /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) - return false; - - priv = netdev_priv(netdev); - rpriv = priv->ppriv; - - /* Egress acl forward to vport is supported only non-uplink representor */ - return rpriv->rep->vport != MLX5_VPORT_UPLINK; + return netif_is_lag_port(netdev) && mlx5e_eswitch_vf_rep(netdev); } static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr) @@ -210,9 +199,6 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt u16 fwd_vport_num; int err; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - info = ptr; lag_info = info->lower_state_info; /* This is not an event of a representor becoming active slave */ @@ -266,9 +252,6 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr) struct net_device *lag_dev; struct mlx5e_priv *priv; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - priv = netdev_priv(netdev); rpriv = priv->ppriv; lag_dev = info->upper_dev; @@ -293,6 +276,19 @@ static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_bond *bond; + struct mlx5e_priv *priv; + + if (!mlx5e_rep_is_lag_netdev(netdev)) + return NOTIFY_DONE; + + bond = container_of(nb, struct mlx5e_rep_bond, nb); + priv = netdev_priv(netdev); + rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH); + /* Verify VF representor is on the same device of the bond handling the netevent. */ + if (rpriv->uplink_priv.bond != bond) + return NOTIFY_DONE; switch (event) { case NETDEV_CHANGELOWERSTATE: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index c6d2f8c78db7..48dc121b2cb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -491,7 +491,7 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) } br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event; - err = register_netdevice_notifier(&br_offloads->netdev_nb); + err = register_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); if (err) { esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n", err); @@ -509,7 +509,9 @@ err_register_swdev_blk: err_register_swdev: destroy_workqueue(br_offloads->wq); err_alloc_wq: + rtnl_lock(); mlx5_esw_bridge_cleanup(esw); + rtnl_unlock(); } void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) @@ -524,7 +526,7 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) return; cancel_delayed_work_sync(&br_offloads->update_work); - unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); destroy_workqueue(br_offloads->wq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c index b0de6b999675..2b53738938a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_accept(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -20,7 +21,7 @@ tc_act_parse_accept(struct mlx5e_tc_act_parse_state *parse_state, { attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT; + attr->flags |= MLX5_ATTR_FLAG_ACCEPT; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 26efa33de56f..bfbc91c116a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -16,12 +16,12 @@ struct mlx5e_tc_act_parse_state { unsigned int num_actions; struct mlx5e_tc_flow *flow; struct netlink_ext_ack *extack; + bool ct; bool encap; bool decap; bool mpls_push; bool ptype_host; const struct ip_tunnel_info *tun_info; - struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; int if_count; struct mlx5_tc_ct_priv *ct_priv; @@ -30,7 +30,8 @@ struct mlx5e_tc_act_parse_state { struct mlx5e_tc_act { bool (*can_offload)(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index); + int act_index, + struct mlx5_flow_attr *attr); int (*parse_action)(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c index 29920ef0180a..c0f08ae6a57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c @@ -38,11 +38,12 @@ csum_offload_supported(struct mlx5e_priv *priv, static bool tc_act_can_offload_csum(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct mlx5e_tc_flow *flow = parse_state->flow; - return csum_offload_supported(flow->priv, flow->attr->action, + return csum_offload_supported(flow->priv, attr->action, act->csum_flags, parse_state->extack); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index 06ec30cdb269..85f0cb88127f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -8,8 +8,10 @@ static bool tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; struct netlink_ext_ack *extack = parse_state->extack; if (flow_flag_test(parse_state->flow, SAMPLE)) { @@ -18,6 +20,11 @@ tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state, return false; } + if (parse_state->ct && !clear_action) { + NL_SET_ERR_MSG_MOD(extack, "Multiple CT actions are not supoported"); + return false; + } + return true; } @@ -27,6 +34,7 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; int err; err = mlx5_tc_ct_parse_action(parse_state->ct_priv, attr, @@ -35,11 +43,16 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (err) return err; - flow_flag_set(parse_state->flow, CT); if (mlx5e_is_eswitch_flow(parse_state->flow)) attr->esw_attr->split_count = attr->esw_attr->out_count; + if (!clear_action) { + attr->flags |= MLX5_ATTR_FLAG_CT; + flow_flag_set(parse_state->flow, CT); + parse_state->ct = true; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c index 2e29a23bed12..3d5f23636a02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_drop(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c index f44515061228..fb1be822ad25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c @@ -8,6 +8,7 @@ static int validate_goto_chain(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { @@ -32,7 +33,7 @@ validate_goto_chain(struct mlx5e_priv *priv, } if (!mlx5_chains_backwards_supported(chains) && - dest_chain <= flow->attr->chain) { + dest_chain <= attr->chain) { NL_SET_ERR_MSG_MOD(extack, "Goto lower numbered chain isn't supported"); return -EOPNOTSUPP; } @@ -43,8 +44,8 @@ validate_goto_chain(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (flow->attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | - MLX5_FLOW_CONTEXT_ACTION_DECAP) && + if (attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_DECAP) && !reformat_and_fwd) { NL_SET_ERR_MSG_MOD(extack, "Goto chain is not allowed if action has reformat or decap"); @@ -57,12 +58,13 @@ validate_goto_chain(struct mlx5e_priv *priv, static bool tc_act_can_offload_goto(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; - if (validate_goto_chain(flow->priv, flow, act, extack)) + if (validate_goto_chain(flow->priv, flow, attr, act, extack)) return false; return true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c index d775c3d9edf3..e8d227595b3e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_mark(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { if (act->mark & ~MLX5E_TC_FLOW_ID_MASK) { NL_SET_ERR_MSG_MOD(parse_state->extack, "Bad flow mark, only 16 bit supported"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index c614fc7fdc9c..99fb98b3e71b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -99,7 +99,8 @@ get_fdb_out_dev(struct net_device *uplink_dev, struct net_device *out_dev) static bool tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; @@ -108,8 +109,8 @@ tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv = flow->priv; struct mlx5_esw_flow_attr *esw_attr; - parse_attr = flow->attr->parse_attr; - esw_attr = flow->attr->esw_attr; + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; if (!out_dev) { /* out_dev is NULL when filters with diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c index 2c74567b6d25..16681cf6e93e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_tc_flow *flow = parse_state->flow; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c index 784fc4f68b1e..40332949509a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c @@ -8,7 +8,8 @@ static bool tc_act_can_offload_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; struct mlx5e_priv *priv = parse_state->flow->priv; @@ -36,13 +37,13 @@ tc_act_parse_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, static bool tc_act_can_offload_mpls_pop(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; - struct mlx5e_tc_flow *flow = parse_state->flow; struct net_device *filter_dev; - filter_dev = flow->attr->parse_attr->filter_dev; + filter_dev = attr->parse_attr->filter_dev; /* we only support mpls pop if it is the first action * and the filter net device is bareudp. Subsequent diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c index 79addbbef087..39f8f71bed9e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c @@ -46,9 +46,9 @@ static int parse_pedit_to_modify_hdr(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) { + struct pedit_headers_action *hdrs = parse_attr->hdrs; u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; u8 htype = act->mangle.htype; int err = -EOPNOTSUPP; @@ -110,20 +110,20 @@ int mlx5e_tc_act_pedit_parse_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 mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) return parse_pedit_to_reformat(act, parse_attr, extack); - return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack); + return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, extack); } static bool tc_act_can_offload_pedit(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -141,8 +141,7 @@ tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state, ns_type = mlx5e_get_flow_namespace(flow); - err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, - attr->parse_attr, parse_state->hdrs, + err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, attr->parse_attr, flow, parse_state->extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h index da8ab03af58f..258f030a2dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h @@ -25,7 +25,6 @@ int mlx5e_tc_act_pedit_parse_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 mlx5e_tc_flow *flow, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c index 0819110193dc..6454b031ff7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_ptype(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c index 1c32e24e528d..9dd244147385 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c @@ -7,16 +7,16 @@ static bool tc_act_can_offload_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; - struct mlx5e_tc_flow *flow = parse_state->flow; struct mlx5e_tc_flow_parse_attr *parse_attr; struct net_device *out_dev = act->dev; struct mlx5_esw_flow_attr *esw_attr; - parse_attr = flow->attr->parse_attr; - esw_attr = flow->attr->esw_attr; + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; if (!out_dev) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c index 6699bdf5cf01..539fea13ce9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c @@ -8,7 +8,8 @@ static bool tc_act_can_offload_sample(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; @@ -27,11 +28,7 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { - struct mlx5e_sample_attr *sample_attr; - - sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); - if (!sample_attr) - return -ENOMEM; + struct mlx5e_sample_attr *sample_attr = &attr->sample_attr; sample_attr->rate = act->sample.rate; sample_attr->group_num = act->sample.psample_group->group_num; @@ -39,7 +36,7 @@ tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state, if (act->sample.truncate) sample_attr->trunc_size = act->sample.trunc_size; - attr->sample_attr = sample_attr; + attr->flags |= MLX5_ATTR_FLAG_SAMPLE; flow_flag_set(parse_state->flow, SAMPLE); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c index 046b64c2cec4..9ea293fdc434 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c @@ -7,7 +7,8 @@ static bool tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { struct netlink_ext_ack *extack = parse_state->extack; @@ -27,7 +28,7 @@ tc_act_parse_trap(struct mlx5e_tc_act_parse_state *parse_state, { attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c index 6f4a2cf46afd..b4fa2de9711d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c @@ -8,7 +8,8 @@ static bool tc_act_can_offload_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { if (!act->tunnel) { NL_SET_ERR_MSG_MOD(parse_state->extack, @@ -34,7 +35,8 @@ tc_act_parse_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, static bool tc_act_can_offload_tun_decap(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c index 70fc0c2d8813..6378b7558ba2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -9,7 +9,6 @@ static int add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack) { const struct flow_action_entry prio_tag_act = { @@ -26,7 +25,7 @@ add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, }; return mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, - &prio_tag_act, parse_attr, hdrs, action, + &prio_tag_act, parse_attr, action, extack); } @@ -151,7 +150,8 @@ mlx5e_tc_act_vlan_add_pop_action(struct mlx5e_priv *priv, static bool tc_act_can_offload_vlan(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -170,8 +170,8 @@ tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, /* Replace vlan pop+push with vlan modify */ attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; err = mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, act, - attr->parse_attr, parse_state->hdrs, - &attr->action, parse_state->extack); + attr->parse_attr, &attr->action, + parse_state->extack); } else { err = parse_tc_vlan_action(priv, act, esw_attr, &attr->action, parse_state->extack); @@ -191,7 +191,6 @@ tc_act_post_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *attr) { struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; - struct pedit_headers_action *hdrs = parse_state->hdrs; struct netlink_ext_ack *extack = parse_state->extack; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int err; @@ -202,7 +201,7 @@ tc_act_post_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, * tag rewrite. */ attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs, + err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, &attr->action, extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h index 3d62f13ab61f..2fa58c6f44eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h @@ -24,7 +24,6 @@ int mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack); #endif /* __MLX5_EN_TC_ACT_VLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c index 63e36e7f53e3..28444d4ffd73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c @@ -12,7 +12,6 @@ int mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, u32 *action, struct netlink_ext_ack *extack) { u16 mask16 = VLAN_VID_MASK; @@ -44,7 +43,7 @@ mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, return -EOPNOTSUPP; } - err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, hdrs, + err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, NULL, extack); *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; @@ -54,7 +53,8 @@ mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, static bool tc_act_can_offload_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, - int act_index) + int act_index, + struct mlx5_flow_attr *attr) { return true; } @@ -69,8 +69,7 @@ tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, int err; ns_type = mlx5e_get_flow_namespace(parse_state->flow); - err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, - attr->parse_attr, parse_state->hdrs, + err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, attr->parse_attr, &attr->action, parse_state->extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 31b4e39be2d3..9e0e229cf164 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -101,6 +101,7 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *at post_attr->inner_match_level = MLX5_MATCH_NONE; post_attr->outer_match_level = MLX5_MATCH_NONE; post_attr->action &= ~(MLX5_FLOW_CONTEXT_ACTION_DECAP); + post_attr->flags &= ~MLX5_ATTR_FLAG_SAMPLE; handle->ns_type = post_act->ns_type; /* Splits were handled before post action */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index ff4b4f8a5a9d..32230e677029 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -403,7 +403,7 @@ add_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, post_attr->chain = 0; post_attr->prio = 0; post_attr->ft = default_tbl; - post_attr->flags = MLX5_ESW_ATTR_FLAG_NO_IN_PORT; + post_attr->flags = MLX5_ATTR_FLAG_NO_IN_PORT; /* When offloading sample and encap action, if there is no valid * neigh data struct, a slow path rule is offloaded first. Source @@ -492,8 +492,7 @@ del_post_rule(struct mlx5_eswitch *esw, struct mlx5e_sample_flow *sample_flow, struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id) + struct mlx5_flow_attr *attr) { struct mlx5e_post_act_handle *post_act_handle = NULL; struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; @@ -502,6 +501,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_flow *sample_flow; struct mlx5e_sample_attr *sample_attr; struct mlx5_flow_attr *pre_attr; + u32 tunnel_id = attr->tunnel_id; struct mlx5_eswitch *esw; u32 default_tbl_id; u32 obj_id; @@ -513,7 +513,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL); if (!sample_flow) return ERR_PTR(-ENOMEM); - sample_attr = attr->sample_attr; + sample_attr = &attr->sample_attr; sample_attr->sample_flow = sample_flow; /* For NICs with reg_c_preserve support or decap action, use @@ -546,6 +546,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, err = PTR_ERR(sample_flow->sampler); goto err_sampler; } + sample_attr->sampler_id = sample_flow->sampler->sampler_id; /* Create an id mapping reg_c0 value to sample object. */ restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE; @@ -580,13 +581,12 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, if (tunnel_id) pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; pre_attr->modify_hdr = sample_flow->restore->modify_hdr; - pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE; + pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE; pre_attr->inner_match_level = attr->inner_match_level; pre_attr->outer_match_level = attr->outer_match_level; pre_attr->chain = attr->chain; pre_attr->prio = attr->prio; - pre_attr->sample_attr = attr->sample_attr; - sample_attr->sampler_id = sample_flow->sampler->sampler_id; + pre_attr->sample_attr = *sample_attr; pre_esw_attr = pre_attr->esw_attr; pre_esw_attr->in_mdev = esw_attr->in_mdev; pre_esw_attr->in_rep = esw_attr->in_rep; @@ -633,11 +633,11 @@ mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, * will hit fw syndromes. */ esw = tc_psample->esw; - sample_flow = attr->sample_attr->sample_flow; + sample_flow = attr->sample_attr.sample_flow; mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, sample_flow->pre_attr); sample_restore_put(tc_psample, sample_flow->restore); - mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr->restore_obj_id); + mapping_remove(esw->offloads.reg_c0_obj_pool, attr->sample_attr.restore_obj_id); sampler_put(tc_psample, sample_flow->sampler); if (sample_flow->post_act_handle) mlx5e_tc_post_act_del(tc_psample->post_act, sample_flow->post_act_handle); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h index 9ef8a49d7801..a569367eae4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h @@ -26,8 +26,7 @@ void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *sample_priv, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id); + struct mlx5_flow_attr *attr); void mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *sample_priv, @@ -45,8 +44,7 @@ mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample); static inline struct mlx5_flow_handle * mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5_flow_spec *spec, - struct mlx5_flow_attr *attr, - u32 tunnel_id) + struct mlx5_flow_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 4a0d38d219ed..0f4d3b9dd979 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -809,7 +809,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, attr->ft = nat ? ct_priv->ct_nat : ct_priv->ct; attr->outer_match_level = MLX5_MATCH_L4; attr->counter = entry->counter->counter; - attr->flags |= MLX5_ESW_ATTR_FLAG_NO_IN_PORT; + attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT; if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) attr->esw_attr->in_mdev = priv->mdev; @@ -1787,7 +1787,6 @@ mlx5_tc_ct_del_ft_cb(struct mlx5_tc_ct_priv *ct_priv, struct mlx5_ct_ft *ft) */ static struct mlx5_flow_handle * __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *orig_spec, struct mlx5_flow_attr *attr) { @@ -1871,12 +1870,10 @@ __mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *ct_priv, */ if ((pre_ct_attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) && attr->chain == 0) { - u32 tun_id = mlx5e_tc_get_flow_tun_id(flow); - err = mlx5e_tc_match_to_reg_set(priv->mdev, &pre_mod_acts, ct_priv->ns_type, TUNNEL_TO_REG, - tun_id); + attr->tunnel_id); if (err) { ct_dbg("Failed to set tunnel register mapping"); goto err_mapping; @@ -1926,87 +1923,19 @@ err_ft: return ERR_PTR(err); } -static struct mlx5_flow_handle * -__mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5_flow_spec *orig_spec, - struct mlx5_flow_attr *attr, - struct mlx5e_tc_mod_hdr_acts *mod_acts) -{ - struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); - u32 attr_sz = ns_to_attr_sz(ct_priv->ns_type); - struct mlx5_flow_attr *pre_ct_attr; - struct mlx5_modify_hdr *mod_hdr; - struct mlx5_flow_handle *rule; - struct mlx5_ct_flow *ct_flow; - int err; - - ct_flow = kzalloc(sizeof(*ct_flow), GFP_KERNEL); - if (!ct_flow) - return ERR_PTR(-ENOMEM); - - /* Base esw attributes on original rule attribute */ - pre_ct_attr = mlx5_alloc_flow_attr(ct_priv->ns_type); - if (!pre_ct_attr) { - err = -ENOMEM; - goto err_attr; - } - - memcpy(pre_ct_attr, attr, attr_sz); - - mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, - mod_acts->num_actions, - mod_acts->actions); - if (IS_ERR(mod_hdr)) { - err = PTR_ERR(mod_hdr); - ct_dbg("Failed to add create ct clear mod hdr"); - goto err_mod_hdr; - } - - pre_ct_attr->modify_hdr = mod_hdr; - - rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - ct_dbg("Failed to add ct clear rule"); - goto err_insert; - } - - attr->ct_attr.ct_flow = ct_flow; - ct_flow->pre_ct_attr = pre_ct_attr; - ct_flow->pre_ct_rule = rule; - return rule; - -err_insert: - mlx5_modify_header_dealloc(priv->mdev, mod_hdr); -err_mod_hdr: - netdev_warn(priv->netdev, - "Failed to offload ct clear flow, err %d\n", err); - kfree(pre_ct_attr); -err_attr: - kfree(ct_flow); - - return ERR_PTR(err); -} - struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts) { - bool clear_action = attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR; struct mlx5_flow_handle *rule; if (!priv) return ERR_PTR(-EOPNOTSUPP); mutex_lock(&priv->control_lock); - - if (clear_action) - rule = __mlx5_tc_ct_flow_offload_clear(priv, spec, attr, mod_hdr_acts); - else - rule = __mlx5_tc_ct_flow_offload(priv, flow, spec, attr); + rule = __mlx5_tc_ct_flow_offload(priv, spec, attr); mutex_unlock(&priv->control_lock); return rule; @@ -2014,14 +1943,13 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, static void __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv, - struct mlx5e_tc_flow *flow, - struct mlx5_ct_flow *ct_flow) + struct mlx5_ct_flow *ct_flow, + struct mlx5_flow_attr *attr) { struct mlx5_flow_attr *pre_ct_attr = ct_flow->pre_ct_attr; struct mlx5e_priv *priv = netdev_priv(ct_priv->netdev); - mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, - pre_ct_attr); + mlx5_tc_rule_delete(priv, ct_flow->pre_ct_rule, pre_ct_attr); mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr); if (ct_flow->post_act_handle) { @@ -2036,7 +1964,6 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv, void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_ct_flow *ct_flow = attr->ct_attr.ct_flow; @@ -2048,7 +1975,7 @@ mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, return; mutex_lock(&priv->control_lock); - __mlx5_tc_ct_delete_flow(priv, flow, ct_flow); + __mlx5_tc_ct_delete_flow(priv, ct_flow, attr); mutex_unlock(&priv->control_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 99662af1e41a..2b21c7b97a52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -116,13 +116,11 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts); void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr); bool @@ -183,7 +181,6 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, static inline struct mlx5_flow_handle * mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts) @@ -193,7 +190,6 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, static inline void mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv, - struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index f832c26ff2c3..9ffba584b982 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -37,6 +37,7 @@ struct mlx5e_tc_flow_parse_attr { const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS]; struct net_device *filter_dev; struct mlx5_flow_spec spec; + struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; struct mlx5e_tc_mod_hdr_acts mod_hdr_acts; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; struct ethhdr eth; @@ -107,10 +108,19 @@ struct mlx5e_tc_flow { struct rcu_head rcu_head; struct completion init_done; struct completion del_hw_done; - int tunnel_id; /* the mapped tunnel id of this flow */ struct mlx5_flow_attr *attr; }; +struct mlx5_flow_handle * +mlx5e_tc_rule_offload(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr); + +void +mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr); + u8 mlx5e_tc_get_ip_version(struct mlx5_flow_spec *spec, bool outer); struct mlx5_flow_handle * @@ -173,6 +183,7 @@ struct mlx5_flow_handle * mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_spec *spec); + void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 9918ed8c059b..1f8d339ff0c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -488,12 +488,14 @@ static void mlx5e_detach_encap_route(struct mlx5e_priv *priv, int out_index); void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index) + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + int out_index) { struct mlx5e_encap_entry *e = flow->encaps[out_index].e; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - if (flow->attr->esw_attr->dests[out_index].flags & + if (attr->esw_attr->dests[out_index].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) mlx5e_detach_encap_route(priv, flow, out_index); @@ -733,6 +735,7 @@ static unsigned int mlx5e_route_tbl_get_last_update(struct mlx5e_priv *priv) static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct mlx5e_encap_entry *e, bool new_encap_entry, unsigned long tbl_time_before, @@ -740,6 +743,7 @@ static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, @@ -748,7 +752,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; unsigned long tbl_time_before = 0; struct mlx5e_encap_entry *e; @@ -834,8 +837,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, e->compl_result = 1; attach_flow: - err = mlx5e_attach_encap_route(priv, flow, e, entry_created, tbl_time_before, - out_index); + err = mlx5e_attach_encap_route(priv, flow, attr, e, entry_created, + tbl_time_before, out_index); if (err) goto out_err; @@ -1198,6 +1201,7 @@ out: static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct mlx5e_encap_entry *e, bool new_encap_entry, unsigned long tbl_time_before, @@ -1206,7 +1210,6 @@ static int mlx5e_attach_encap_route(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; unsigned long tbl_time_after = tbl_time_before; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; struct mlx5_esw_flow_attr *esw_attr; struct mlx5e_route_entry *r; @@ -1377,7 +1380,7 @@ static void mlx5e_reoffload_encap(struct mlx5e_priv *priv, continue; } - err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow); + err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); if (err) { mlx5_core_warn(priv->mdev, "Failed to update flow mod_hdr err=%d", err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index 3391504d9a08..d542b8476491 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -7,15 +7,19 @@ #include "tc_priv.h" void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index); + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + int out_index); int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, struct net_device **encap_dev, bool *encap_valid); + int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 4cdf8e5b24c2..b789af07829c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1); +} + struct mlx5e_shampo_umr { u16 len; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 338d65e2c9ce..56e10c84a706 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 2db9573a3fe6..b56fea142c24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -157,11 +157,20 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, /* Tunnel mode */ if (mode == XFRM_MODE_TUNNEL) { eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; if (xo->proto == IPPROTO_IPV6) eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP) + + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | IP | [TCP | UDP] */ + eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index b98db50c3418..428881e0adcb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -131,14 +131,17 @@ static inline bool mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - struct xfrm_offload *xo = xfrm_offload(skb); + u8 inner_ipproto; if (!mlx5e_ipsec_eseg_meta(eseg)) return false; eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (xo->inner_ipproto) { - eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM; + inner_ipproto = xfrm_offload(skb)->inner_ipproto; + if (inner_ipproto) { + eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; + if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP) + eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM; } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial_inner++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index e86ccc22fb82..ee0a8f5206e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct tcphdr *skb_tcp_hd) { - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); struct tcphdr *last_tcp_hd; void *last_hd_addr; @@ -1871,7 +1871,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } -static void +static struct sk_buff * mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { @@ -1895,7 +1895,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); if (unlikely(!skb)) - return; + return NULL; /* queue up for recycling/reuse */ page_ref_inc(head->page); @@ -1907,7 +1907,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, ALIGN(head_size, sizeof(long))); if (unlikely(!skb)) { rq->stats->buff_alloc_err++; - return; + return NULL; } prefetchw(skb->data); @@ -1918,9 +1918,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb->tail += head_size; skb->len += head_size; } - rq->hw_gro_data->skb = skb; - NAPI_GRO_CB(skb)->count = 1; - skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size; + return skb; } static void @@ -1973,13 +1971,14 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size; - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset); u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); u32 data_offset = wqe_offset & (PAGE_SIZE - 1); u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe); u16 wqe_id = be16_to_cpu(cqe->wqe_id); u32 page_idx = wqe_offset >> PAGE_SHIFT; + u16 head_size = cqe->shampo.header_size; struct sk_buff **skb = &rq->hw_gro_data->skb; bool flush = cqe->shampo.flush; bool match = cqe->shampo.match; @@ -2011,9 +2010,16 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } if (!*skb) { - mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + if (likely(head_size)) + *skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + else + *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset, + page_idx); if (unlikely(!*skb)) goto free_hd_entry; + + NAPI_GRO_CB(*skb)->count = 1; + skb_shinfo(*skb)->gso_size = cqe_bcnt - head_size; } else { NAPI_GRO_CB(*skb)->count++; if (NAPI_GRO_CB(*skb)->count == 2 && @@ -2027,8 +2033,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } } - di = &wi->umr.dma_info[page_idx]; - mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + if (likely(head_size)) { + di = &wi->umr.dma_info[page_idx]; + mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + } mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb); if (flush) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3d908a7e1406..099d4ce16049 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -295,13 +295,62 @@ mlx5_tc_rule_delete(struct mlx5e_priv *priv, if (is_mdev_switchdev_mode(priv->mdev)) { mlx5_eswitch_del_offloaded_rule(esw, rule, attr); - return; } mlx5e_del_offloaded_nic_rule(priv, rule, attr); } +struct mlx5_flow_handle * +mlx5e_tc_rule_offload(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (attr->flags & MLX5_ATTR_FLAG_CT) { + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = + &attr->parse_attr->mod_hdr_acts; + + return mlx5_tc_ct_flow_offload(get_ct_priv(priv), + spec, attr, + mod_hdr_acts); + } + + if (!is_mdev_switchdev_mode(priv->mdev)) + return mlx5e_add_offloaded_nic_rule(priv, spec, attr); + + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) + return mlx5e_tc_sample_offload(get_sample_priv(priv), spec, attr); + + return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); +} + +void +mlx5e_tc_rule_unoffload(struct mlx5e_priv *priv, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (attr->flags & MLX5_ATTR_FLAG_CT) { + mlx5_tc_ct_delete_flow(get_ct_priv(priv), attr); + return; + } + + if (!is_mdev_switchdev_mode(priv->mdev)) { + mlx5e_del_offloaded_nic_rule(priv, rule, attr); + return; + } + + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE) { + mlx5e_tc_sample_unoffload(get_sample_priv(priv), rule, attr); + return; + } + + mlx5_eswitch_del_offloaded_rule(esw, rule, attr); +} + int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev, struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts, @@ -1039,6 +1088,21 @@ err_ft_get: } static int +alloc_flow_attr_counter(struct mlx5_core_dev *counter_dev, + struct mlx5_flow_attr *attr) + +{ + struct mlx5_fc *counter; + + counter = mlx5_fc_create(counter_dev, true); + if (IS_ERR(counter)) + return PTR_ERR(counter); + + attr->counter = counter; + return 0; +} + +static int mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -1046,7 +1110,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_core_dev *dev = priv->mdev; - struct mlx5_fc *counter; int err; parse_attr = attr->parse_attr; @@ -1058,11 +1121,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - counter = mlx5_fc_create(dev, true); - if (IS_ERR(counter)) - return PTR_ERR(counter); - - attr->counter = counter; + err = alloc_flow_attr_counter(dev, attr); + if (err) + return err; } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { @@ -1072,8 +1133,8 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, return err; } - if (flow_flag_test(flow, CT)) - flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), flow, &parse_attr->spec, + if (attr->flags & MLX5_ATTR_FLAG_CT) + flow->rule[0] = mlx5_tc_ct_flow_offload(get_ct_priv(priv), &parse_attr->spec, attr, &parse_attr->mod_hdr_acts); else flow->rule[0] = mlx5e_add_offloaded_nic_rule(priv, &parse_attr->spec, @@ -1107,8 +1168,8 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, flow_flag_clear(flow, OFFLOADED); - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); + if (attr->flags & MLX5_ATTR_FLAG_CT) + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); else if (!IS_ERR_OR_NULL(flow->rule[0])) mlx5e_del_offloaded_nic_rule(priv, flow->rule[0], attr); @@ -1142,40 +1203,27 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) { - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts; struct mlx5_flow_handle *rule; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) + if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - if (flow_flag_test(flow, CT)) { - mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; - - rule = mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv), - flow, spec, attr, - mod_hdr_acts); - } else if (flow_flag_test(flow, SAMPLE)) { - rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, - mlx5e_tc_get_flow_tun_id(flow)); - } else { - rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); - } + rule = mlx5e_tc_rule_offload(flow->priv, spec, attr); if (IS_ERR(rule)) return rule; if (attr->esw_attr->split_count) { flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr); - if (IS_ERR(flow->rule[1])) { - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); - else - mlx5_eswitch_del_offloaded_rule(esw, rule, attr); - return flow->rule[1]; - } + if (IS_ERR(flow->rule[1])) + goto err_rule1; } return rule; + +err_rule1: + mlx5e_tc_rule_unoffload(flow->priv, rule, attr); + return flow->rule[1]; } void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, @@ -1184,19 +1232,13 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, { flow_flag_clear(flow, OFFLOADED); - if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) - goto offload_rule_0; + if (attr->flags & MLX5_ATTR_FLAG_SLOW_PATH) + return mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); - if (flow_flag_test(flow, CT)) - mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), flow, attr); - else if (flow_flag_test(flow, SAMPLE)) - mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); - else -offload_rule_0: - mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); + mlx5e_tc_rule_unoffload(flow->priv, flow->rule[0], attr); } struct mlx5_flow_handle * @@ -1214,7 +1256,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) @@ -1239,7 +1281,7 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, memcpy(slow_attr, flow->attr, ESW_FLOW_ATTR_SZ); slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; slow_attr->esw_attr->split_count = 0; - slow_attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); flow_flag_clear(flow, SLOW); kfree(slow_attr); @@ -1348,10 +1390,10 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro } int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow) + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr) { - struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &parse_attr->mod_hdr_acts; + struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts = &attr->parse_attr->mod_hdr_acts; struct mlx5_modify_hdr *mod_hdr; mod_hdr = mlx5_modify_header_alloc(priv->mdev, @@ -1361,13 +1403,101 @@ int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, if (IS_ERR(mod_hdr)) return PTR_ERR(mod_hdr); - WARN_ON(flow->attr->modify_hdr); - flow->attr->modify_hdr = mod_hdr; + WARN_ON(attr->modify_hdr); + attr->modify_hdr = mod_hdr; return 0; } static int +set_encap_dests(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack, + bool *encap_valid, + bool *vf_tun) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct mlx5_esw_flow_attr *esw_attr; + struct net_device *encap_dev = NULL; + struct mlx5e_rep_priv *rpriv; + struct mlx5e_priv *out_priv; + int out_index; + int err = 0; + + parse_attr = attr->parse_attr; + esw_attr = attr->esw_attr; + *vf_tun = false; + *encap_valid = true; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + struct net_device *out_dev; + int mirred_ifindex; + + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + mirred_ifindex = parse_attr->mirred_ifindex[out_index]; + out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); + if (!out_dev) { + NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); + err = -ENODEV; + goto out; + } + err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, + extack, &encap_dev, encap_valid); + dev_put(out_dev); + if (err) + goto out; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + out_priv = netdev_priv(encap_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].mdev = out_priv->mdev; + } + + if (*vf_tun && esw_attr->out_count > 1) { + NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); + err = -EOPNOTSUPP; + goto out; + } + +out: + return err; +} + +static void +clean_encap_dests(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, + bool *vf_tun) +{ + struct mlx5_esw_flow_attr *esw_attr; + int out_index; + + esw_attr = attr->esw_attr; + *vf_tun = false; + + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { + if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) + continue; + + if (esw_attr->dests[out_index].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && + !esw_attr->dest_int_port) + *vf_tun = true; + + mlx5e_detach_encap(priv, flow, attr, out_index); + kfree(attr->parse_attr->tun_info[out_index]); + } +} + +static int mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -1375,15 +1505,10 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; - bool vf_tun = false, encap_valid = true; - struct net_device *encap_dev = NULL; struct mlx5_esw_flow_attr *esw_attr; - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *out_priv; - struct mlx5_fc *counter; + bool vf_tun, encap_valid; u32 max_prio, max_chain; int err = 0; - int out_index; parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; @@ -1414,7 +1539,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_out; - if (!attr->chain && esw_attr->int_port) { + if (!attr->chain && esw_attr->int_port && + attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { /* If decap route device is internal port, change the * source vport value in reg_c0 back to uplink just in * case the rule performs goto chain > 0. If we have a miss @@ -1471,50 +1597,17 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - struct net_device *out_dev; - int mirred_ifindex; - - if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)) - continue; - - mirred_ifindex = parse_attr->mirred_ifindex[out_index]; - out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex); - if (!out_dev) { - NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found"); - err = -ENODEV; - goto err_out; - } - err = mlx5e_attach_encap(priv, flow, out_dev, out_index, - extack, &encap_dev, &encap_valid); - dev_put(out_dev); - if (err) - goto err_out; - - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - vf_tun = true; - out_priv = netdev_priv(encap_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; - esw_attr->dests[out_index].mdev = out_priv->mdev; - } - - if (vf_tun && esw_attr->out_count > 1) { - NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported"); - err = -EOPNOTSUPP; + err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + if (err) goto err_out; - } err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) goto err_out; - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && - !(attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR)) { + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { if (vf_tun) { - err = mlx5e_tc_add_flow_mod_hdr(priv, parse_attr, flow); + err = mlx5e_tc_add_flow_mod_hdr(priv, flow, attr); if (err) goto err_out; } else { @@ -1525,13 +1618,9 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { - counter = mlx5_fc_create(esw_attr->counter_dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); + err = alloc_flow_attr_counter(esw_attr->counter_dev, attr); + if (err) goto err_out; - } - - attr->counter = counter; } /* we get here if one of the following takes place: @@ -1575,8 +1664,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun = false; - int out_index; + bool vf_tun; esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); @@ -1600,16 +1688,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow->decap_route) mlx5e_detach_decap_route(priv, flow); - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { - if (esw_attr->dests[out_index].flags & - MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE && - !esw_attr->dest_int_port) - vf_tun = true; - if (esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) { - mlx5e_detach_encap(priv, flow, out_index); - kfree(attr->parse_attr->tun_info[out_index]); - } - } + clean_encap_dests(priv, flow, attr, &vf_tun); mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); @@ -1633,7 +1712,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); - kfree(attr->sample_attr); kvfree(attr->esw_attr->rx_tun_attr); kvfree(attr->parse_attr); kfree(flow->attr); @@ -1853,7 +1931,7 @@ static int mlx5e_get_flow_tunnel_id(struct mlx5e_priv *priv, attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; } - flow->tunnel_id = value; + flow->attr->tunnel_id = value; return 0; err_set: @@ -1867,8 +1945,8 @@ err_enc_opts: static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow) { - u32 enc_opts_id = flow->tunnel_id & ENC_OPTS_BITS_MASK; - u32 tun_id = flow->tunnel_id >> ENC_OPTS_BITS; + u32 enc_opts_id = flow->attr->tunnel_id & ENC_OPTS_BITS_MASK; + u32 tun_id = flow->attr->tunnel_id >> ENC_OPTS_BITS; struct mlx5_rep_uplink_priv *uplink_priv; struct mlx5e_rep_priv *uplink_rpriv; struct mlx5_eswitch *esw; @@ -1884,11 +1962,6 @@ static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow) enc_opts_id); } -u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow) -{ - return flow->tunnel_id; -} - void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, struct flow_match_basic *match, bool outer, void *headers_c, void *headers_v) @@ -2810,14 +2883,15 @@ static unsigned long mask_to_le(unsigned long mask, int size) return mask; } + static int offload_pedit_fields(struct mlx5e_priv *priv, int namespace, - struct pedit_headers_action *hdrs, struct mlx5e_tc_flow_parse_attr *parse_attr, u32 *action_flags, struct netlink_ext_ack *extack) { struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; + struct pedit_headers_action *hdrs = parse_attr->hdrs; void *headers_c, *headers_v, *action, *vals_p; u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; @@ -2943,35 +3017,43 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, static const struct pedit_headers zero_masks = {}; -static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - u32 *action_flags, - struct netlink_ext_ack *extack) +static int verify_offload_pedit_fields(struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) { struct pedit_headers *cmd_masks; - int err; u8 cmd; - err = offload_pedit_fields(priv, namespace, hdrs, parse_attr, - action_flags, extack); - if (err < 0) - goto out_dealloc_parsed_actions; - for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { - cmd_masks = &hdrs[cmd].masks; + cmd_masks = &parse_attr->hdrs[cmd].masks; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { - NL_SET_ERR_MSG_MOD(extack, - "attempt to offload an unsupported field"); + NL_SET_ERR_MSG_MOD(extack, "attempt to offload an unsupported field"); netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd); print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS, 16, 1, cmd_masks, sizeof(zero_masks), true); - err = -EOPNOTSUPP; - goto out_dealloc_parsed_actions; + return -EOPNOTSUPP; } } return 0; +} + +static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + u32 *action_flags, + struct netlink_ext_ack *extack) +{ + int err; + + err = offload_pedit_fields(priv, namespace, parse_attr, action_flags, extack); + if (err) + goto out_dealloc_parsed_actions; + + err = verify_offload_pedit_fields(priv, parse_attr, extack); + if (err) + goto out_dealloc_parsed_actions; + + return 0; out_dealloc_parsed_actions: mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts); @@ -3191,6 +3273,18 @@ actions_match_supported(struct mlx5e_priv *priv, return false; } + if (!(~actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); + return false; + } + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); + return false; + } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, ct_flow, ct_clear, extack)) @@ -3244,7 +3338,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, return -EOPNOTSUPP; } - if (!tc_act->can_offload(parse_state, act, i)) + if (!tc_act->can_offload(parse_state, act, i, attr)) return -EOPNOTSUPP; err = tc_act->parse_action(parse_state, act, priv, attr); @@ -3255,7 +3349,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, flow_action_for_each(i, act, flow_action) { tc_act = mlx5e_tc_act_get(act->id, ns_type); if (!tc_act || !tc_act->post_parse || - !tc_act->can_offload(parse_state, act, i)) + !tc_act->can_offload(parse_state, act, i, attr)) continue; err = tc_act->post_parse(parse_state, priv, attr); @@ -3270,10 +3364,10 @@ static int actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, - struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct pedit_headers_action *hdrs = parse_attr->hdrs; enum mlx5_flow_namespace_type ns_type; int err; @@ -3283,8 +3377,7 @@ actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, ns_type = mlx5e_get_flow_namespace(flow); - err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs, - &attr->action, extack); + err = alloc_tc_pedit_action(priv, ns_type, parse_attr, &attr->action, extack); if (err) return err; @@ -3332,7 +3425,6 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, struct mlx5e_tc_act_parse_state *parse_state; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; - struct pedit_headers_action *hdrs; int err; err = flow_action_supported(flow_action, extack); @@ -3344,13 +3436,12 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, parse_state = &parse_attr->parse_state; mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); parse_state->ct_priv = get_ct_priv(priv); - hdrs = parse_state->hdrs; err = parse_tc_actions(parse_state, flow_action); if (err) return err; - err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack); if (err) return err; @@ -3455,7 +3546,6 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - struct pedit_headers_action *hdrs; int err; err = flow_action_supported(flow_action, extack); @@ -3467,7 +3557,6 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, parse_state = &parse_attr->parse_state; mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); parse_state->ct_priv = get_ct_priv(priv); - hdrs = parse_state->hdrs; err = parse_tc_actions(parse_state, flow_action); if (err) @@ -3481,7 +3570,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); + err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 5ffae9b13066..c6221728b767 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -71,7 +71,7 @@ struct mlx5_flow_attr { struct mlx5_fc *counter; struct mlx5_modify_hdr *modify_hdr; struct mlx5_ct_attr ct_attr; - struct mlx5e_sample_attr *sample_attr; + struct mlx5e_sample_attr sample_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; u32 chain; u16 prio; @@ -82,6 +82,7 @@ struct mlx5_flow_attr { u8 outer_match_level; u8 ip_version; u8 tun_ip_version; + int tunnel_id; /* mapped tunnel id */ u32 flags; union { struct mlx5_esw_flow_attr esw_attr[0]; @@ -89,6 +90,23 @@ struct mlx5_flow_attr { }; }; +enum { + MLX5_ATTR_FLAG_VLAN_HANDLED = BIT(0), + MLX5_ATTR_FLAG_SLOW_PATH = BIT(1), + MLX5_ATTR_FLAG_NO_IN_PORT = BIT(2), + MLX5_ATTR_FLAG_SRC_REWRITE = BIT(3), + MLX5_ATTR_FLAG_SAMPLE = BIT(4), + MLX5_ATTR_FLAG_ACCEPT = BIT(5), + MLX5_ATTR_FLAG_CT = BIT(6), +}; + +/* Returns true if any of the flags that require skipping further TC/NF processing are set. */ +static inline bool +mlx5e_tc_attr_flags_skip(u32 attr_flags) +{ + return attr_flags & (MLX5_ATTR_FLAG_SLOW_PATH | MLX5_ATTR_FLAG_ACCEPT); +} + struct mlx5_rx_tun_attr { u16 decap_vport; union { @@ -243,11 +261,8 @@ int mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, u32 data); int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct mlx5e_tc_flow *flow); - -struct mlx5e_tc_flow; -u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow); + struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr); void mlx5e_tc_set_ethertype(struct mlx5_core_dev *mdev, struct flow_match_basic *match, bool outer, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 7fd33b356cc8..ee7ecb88adc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - memcpy(vhdr, skb->data, cpy1_sz); + memcpy(&vhdr->addrs, skb->data, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index f690f430f40f..05e08cec5a8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1574,6 +1574,8 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads; + ASSERT_RTNL(); + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); if (!br_offloads) return ERR_PTR(-ENOMEM); @@ -1590,6 +1592,8 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + ASSERT_RTNL(); + if (!br_offloads) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h index 3401188e0a60..51ac24e6ec3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template, __field(unsigned int, used) ), TP_fast_assign( - strncpy(__entry->dev_name, + strscpy(__entry->dev_name, netdev_name(fdb->dev), IFNAMSIZ); memcpy(__entry->addr, fdb->key.addr, ETH_ALEN); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c index c275fe028b6d..0abef71cb839 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -86,7 +86,7 @@ mlx5_esw_indir_table_needed(struct mlx5_eswitch *esw, mlx5_eswitch_is_vf_vport(esw, vport_num) && esw->dev == dest_mdev && attr->ip_version && - attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE; + attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE; } u16 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index ead5e8acc8be..44321cdfe928 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -448,22 +448,6 @@ enum { MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE = BIT(2), }; -enum { - MLX5_ESW_ATTR_FLAG_VLAN_HANDLED = BIT(0), - MLX5_ESW_ATTR_FLAG_SLOW_PATH = BIT(1), - MLX5_ESW_ATTR_FLAG_NO_IN_PORT = BIT(2), - MLX5_ESW_ATTR_FLAG_SRC_REWRITE = BIT(3), - MLX5_ESW_ATTR_FLAG_SAMPLE = BIT(4), - MLX5_ESW_ATTR_FLAG_ACCEPT = BIT(5), -}; - -/* Returns true if any of the flags that require skipping further TC/NF processing are set. */ -static inline bool -mlx5_esw_attr_flags_skip(u32 attr_flags) -{ - return attr_flags & (MLX5_ESW_ATTR_FLAG_SLOW_PATH | MLX5_ESW_ATTR_FLAG_ACCEPT); -} - struct mlx5_esw_flow_attr { struct mlx5_eswitch_rep *in_rep; struct mlx5_core_dev *in_mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9a7b25692505..2b31d8bbd1b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -180,7 +180,7 @@ esw_setup_decap_indir(struct mlx5_eswitch *esw, { struct mlx5_flow_table *ft; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; ft = mlx5_esw_indir_table_get(esw, attr, spec, @@ -201,12 +201,12 @@ esw_cleanup_decap_indir(struct mlx5_eswitch *esw, static int esw_setup_sampler_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, - struct mlx5_flow_attr *attr, + u32 sampler_id, int i) { flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER; - dest[i].sampler_id = attr->sample_attr->sampler_id; + dest[i].sampler_id = sampler_id; return 0; } @@ -297,7 +297,7 @@ esw_setup_chain_src_port_rewrite(struct mlx5_flow_destination *dest, struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; int err; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; /* flow steering cannot handle more than one dest with the same ft @@ -364,7 +364,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; int j, err; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SRC_REWRITE)) + if (!(attr->flags & MLX5_ATTR_FLAG_SRC_REWRITE)) return -EOPNOTSUPP; for (j = esw_attr->split_count; j < esw_attr->out_count; j++, (*i)++) { @@ -463,15 +463,16 @@ esw_setup_dests(struct mlx5_flow_destination *dest, if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) && esw_src_port_rewrite_supported(esw)) - attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE; + attr->flags |= MLX5_ATTR_FLAG_SRC_REWRITE; - if (attr->flags & MLX5_ESW_ATTR_FLAG_SAMPLE) { - esw_setup_sampler_dest(dest, flow_act, attr, *i); + if (attr->flags & MLX5_ATTR_FLAG_SAMPLE && + !(attr->flags & MLX5_ATTR_FLAG_SLOW_PATH)) { + esw_setup_sampler_dest(dest, flow_act, attr->sample_attr.sampler_id, *i); (*i)++; } else if (attr->dest_ft) { esw_setup_ft_dest(dest, flow_act, esw, attr, spec, *i); (*i)++; - } else if (mlx5_esw_attr_flags_skip(attr->flags)) { + } else if (mlx5e_tc_attr_flags_skip(attr->flags)) { esw_setup_slow_path_dest(dest, flow_act, chains, *i); (*i)++; } else if (attr->dest_chain) { @@ -498,7 +499,7 @@ esw_cleanup_dests(struct mlx5_eswitch *esw, if (attr->dest_ft) { esw_cleanup_decap_indir(esw, attr); - } else if (!mlx5_esw_attr_flags_skip(attr->flags)) { + } else if (!mlx5e_tc_attr_flags_skip(attr->flags)) { if (attr->dest_chain) esw_cleanup_chain_dest(chains, attr->dest_chain, 1, 0); else if (esw_is_indir_table(esw, attr)) @@ -589,7 +590,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, else fdb = attr->ft; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_NO_IN_PORT)) + if (!(attr->flags & MLX5_ATTR_FLAG_NO_IN_PORT)) mlx5_eswitch_set_rule_source_port(esw, spec, attr, esw_attr->in_mdev->priv.eswitch, esw_attr->in_rep->vport); @@ -721,7 +722,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_del_flow_rules(rule); - if (!mlx5_esw_attr_flags_skip(attr->flags)) { + if (!mlx5e_tc_attr_flags_skip(attr->flags)) { /* unref the term table */ for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) { if (esw_attr->dests[i].termtbl) @@ -863,7 +864,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (err) goto unlock; - attr->flags &= ~MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED; vport = esw_vlan_action_get_vport(esw_attr, push, pop); @@ -871,7 +872,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, /* tracks VF --> wire rules without vlan push action */ if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { vport->vlan_refcount++; - attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; } goto unlock; @@ -902,7 +903,7 @@ skip_set_push: } out: if (!err) - attr->flags |= MLX5_ESW_ATTR_FLAG_VLAN_HANDLED; + attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; unlock: mutex_unlock(&esw->state_lock); return err; @@ -921,7 +922,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) return 0; - if (!(attr->flags & MLX5_ESW_ATTR_FLAG_VLAN_HANDLED)) + if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED)) return 0; push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); 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 182306bbefaa..ee568bf34ae2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -219,12 +219,14 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level) || - mlx5_esw_attr_flags_skip(attr->flags) || + mlx5e_tc_attr_flags_skip(attr->flags) || (!mlx5_eswitch_offload_is_uplink_port(esw, spec) && !esw_attr->int_port)) return false; /* push vlan on RX */ - if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) + if (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH && + !(mlx5_fs_get_capabilities(esw->dev, MLX5_FLOW_NAMESPACE_FDB) & + MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX)) return true; /* hairpin */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index dafe341358c7..a0ac17c3f12f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -152,6 +152,12 @@ static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns) return 0; } +static u32 mlx5_cmd_stub_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + return 0; +} + static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, struct mlx5_core_dev *slave, bool ft_id_valid, @@ -971,6 +977,12 @@ static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns, return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); } +static u32 mlx5_cmd_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + return 0; +} + static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, .destroy_flow_table = mlx5_cmd_destroy_flow_table, @@ -990,6 +1002,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, + .get_capabilities = mlx5_cmd_get_capabilities, }; static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { @@ -1011,6 +1024,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, + .get_capabilities = mlx5_cmd_stub_get_capabilities, }; const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 220ec632d35a..274004e80f03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -101,6 +101,9 @@ struct mlx5_flow_cmds { u16 format_id, u32 *match_mask); int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns, int definer_id); + + u32 (*get_capabilities)(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b628917e38e4..42f878e21fea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3040,6 +3040,22 @@ void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev) steering->esw_ingress_root_ns = NULL; } +u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_namespace *ns; + + ns = mlx5_get_flow_namespace(dev, type); + if (!ns) + return 0; + + root = find_root(&ns->node); + if (!root) + return 0; + + return root->cmds->get_capabilities(root, root->table_type); +} + static int init_egress_root_ns(struct mlx5_flow_steering *steering) { int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 5469b08d635f..c488a7c5b07e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -120,6 +120,11 @@ enum mlx5_flow_steering_mode { MLX5_FLOW_STEERING_MODE_SMFS }; +enum mlx5_flow_steering_capabilty { + MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0, + MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1, +}; + struct mlx5_flow_steering { struct mlx5_core_dev *dev; enum mlx5_flow_steering_mode mode; @@ -301,6 +306,8 @@ void mlx5_fs_egress_acls_cleanup(struct mlx5_core_dev *dev); int mlx5_fs_ingress_acls_init(struct mlx5_core_dev *dev, int total_vports); void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev); +u32 mlx5_fs_get_capabilities(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); + struct mlx5_flow_root_namespace *find_root(struct fs_node *node); #define fs_get_obj(v, _node) {v = container_of((_node), typeof(*v), node); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 0b0234f9d694..84dbe46d5ede 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -132,7 +132,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; - del_timer(&fw_reset->timer); + del_timer_sync(&fw_reset->timer); } static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index d5e47630e284..df58cba37930 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -121,12 +121,13 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains) u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains) { - if (!mlx5_chains_prios_supported(chains)) - return 1; - if (mlx5_chains_ignore_flow_level_supported(chains)) return UINT_MAX; + if (!chains->dev->priv.eswitch || + chains->dev->priv.eswitch->mode != MLX5_ESWITCH_OFFLOADS) + return 1; + /* We should get here only for eswitch case */ return FDB_TC_MAX_PRIO; } @@ -211,7 +212,7 @@ static int create_chain_restore(struct fs_chain *chain) { struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch; - char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)]; + u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_fs_chains *chains = chain->chains; enum mlx5e_tc_attr_to_reg chain_to_reg; struct mlx5_modify_hdr *mod_hdr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1ef2b6a848c1..7b16a1188aab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -406,23 +406,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, switch (module_id) { case MLX5_MODULE_ID_SFP: - mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; case MLX5_MODULE_ID_QSFP: case MLX5_MODULE_ID_QSFP_PLUS: case MLX5_MODULE_ID_QSFP28: - mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; default: mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); return -EINVAL; } - if (query.offset + size > MLX5_EEPROM_PAGE_LENGTH) + if (offset + size > MLX5_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ - size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; + size = MLX5_EEPROM_PAGE_LENGTH - offset; query.size = size; + query.offset = offset; return mlx5_query_mcia(dev, &query, data); } 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 a476da2424f8..033757bfdf64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -735,6 +735,16 @@ static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns) return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain); } +static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + if (ft_type != FS_FT_FDB || + MLX5_CAP_GEN(ns->dev, steering_format_version) != MLX5_STEERING_FORMAT_CONNECTX_6DX) + return 0; + + return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX; +} + bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) { return mlx5dr_is_supported(dev); @@ -759,6 +769,7 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { .set_peer = mlx5_cmd_dr_set_peer, .create_ns = mlx5_cmd_dr_create_ns, .destroy_ns = mlx5_cmd_dr_destroy_ns, + .get_capabilities = mlx5_cmd_dr_get_capabilities, }; const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 866b9357939b..f45df5fbdcc0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -212,6 +212,29 @@ struct mlxsw_event_listener_item { void *priv; }; +static const u8 mlxsw_core_trap_groups[] = { + MLXSW_REG_HTGT_TRAP_GROUP_EMAD, + MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT, +}; + +static int mlxsw_core_trap_groups_set(struct mlxsw_core *mlxsw_core) +{ + char htgt_pl[MLXSW_REG_HTGT_LEN]; + int err; + int i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_core_trap_groups); i++) { + mlxsw_reg_htgt_pack(htgt_pl, mlxsw_core_trap_groups[i], + MLXSW_REG_HTGT_INVALID_POLICER, + MLXSW_REG_HTGT_DEFAULT_PRIORITY, + MLXSW_REG_HTGT_DEFAULT_TC); + err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); + if (err) + return err; + } + return 0; +} + /****************** * EMAD processing ******************/ @@ -777,16 +800,10 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core) if (err) goto err_trap_register; - err = mlxsw_core->driver->basic_trap_groups_set(mlxsw_core); - if (err) - goto err_emad_trap_set; mlxsw_core->emad.use_emad = true; return 0; -err_emad_trap_set: - mlxsw_core_trap_unregister(mlxsw_core, &mlxsw_emad_rx_listener, - mlxsw_core); err_trap_register: destroy_workqueue(mlxsw_core->emad_wq); return err; @@ -1706,7 +1723,7 @@ static void mlxsw_core_health_listener_func(const struct mlxsw_reg_info *reg, } static const struct mlxsw_listener mlxsw_core_health_listener = - MLXSW_EVENTL(mlxsw_core_health_listener_func, MFDE, MFDE); + MLXSW_CORE_EVENTL(mlxsw_core_health_listener_func, MFDE); static int mlxsw_core_health_fw_fatal_dump_fatal_cause(const char *mfde_pl, @@ -2122,6 +2139,10 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, } } + err = mlxsw_core_trap_groups_set(mlxsw_core); + if (err) + goto err_trap_groups_set; + err = mlxsw_emad_init(mlxsw_core); if (err) goto err_emad_init; @@ -2181,6 +2202,7 @@ err_fw_rev_validate: err_register_params: mlxsw_emad_fini(mlxsw_core); err_emad_init: +err_trap_groups_set: kfree(mlxsw_core->lag.mapping); err_alloc_lag_mapping: mlxsw_ports_fini(mlxsw_core, reload); @@ -2540,6 +2562,45 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_trap_unregister); +int mlxsw_core_traps_register(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv) +{ + int i, err; + + for (i = 0; i < listeners_count; i++) { + err = mlxsw_core_trap_register(mlxsw_core, + &listeners[i], + priv); + if (err) + goto err_listener_register; + } + return 0; + +err_listener_register: + for (i--; i >= 0; i--) { + mlxsw_core_trap_unregister(mlxsw_core, + &listeners[i], + priv); + } + return err; +} +EXPORT_SYMBOL(mlxsw_core_traps_register); + +void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv) +{ + int i; + + for (i = 0; i < listeners_count; i++) { + mlxsw_core_trap_unregister(mlxsw_core, + &listeners[i], + priv); + } +} +EXPORT_SYMBOL(mlxsw_core_traps_unregister); + int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, bool enabled) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index f30bb8614e69..6d304092f4e7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -163,6 +163,9 @@ struct mlxsw_listener { .enabled_on_register = true, \ } +#define MLXSW_CORE_EVENTL(_func, _trap_id) \ + MLXSW_EVENTL(_func, _trap_id, CORE_EVENT) + int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, void *priv, bool enabled); @@ -181,6 +184,12 @@ 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_traps_register(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv); +void mlxsw_core_traps_unregister(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listeners, + size_t listeners_count, void *priv); int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, bool enabled); @@ -315,7 +324,6 @@ struct mlxsw_driver { const struct mlxsw_bus_info *mlxsw_bus_info, struct netlink_ext_ack *extack); void (*fini)(struct mlxsw_core *mlxsw_core); - int (*basic_trap_groups_set)(struct mlxsw_core *mlxsw_core); int (*port_type_set)(struct mlxsw_core *mlxsw_core, u16 local_port, enum devlink_port_type new_type); int (*port_split)(struct mlxsw_core *mlxsw_core, u16 local_port, 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 77e82e6cf6e8..fa33caecc91d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -1957,6 +1957,83 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, } EXPORT_SYMBOL(mlxsw_afa_block_append_mcrouter); +/* SIP DIP Action + * -------------- + * The SIP_DIP_ACTION is used for modifying the SIP and DIP fields of the + * packet, e.g. for NAT. The L3 checksum is updated. Also, if the L4 is TCP or + * if the L4 is UDP and the checksum field is not zero, then the L4 checksum is + * updated. + */ + +#define MLXSW_AFA_IP_CODE 0x11 +#define MLXSW_AFA_IP_SIZE 2 + +enum mlxsw_afa_ip_s_d { + /* ip refers to dip */ + MLXSW_AFA_IP_S_D_DIP, + /* ip refers to sip */ + MLXSW_AFA_IP_S_D_SIP, +}; + +/* afa_ip_s_d + * Source or destination. + */ +MLXSW_ITEM32(afa, ip, s_d, 0x00, 31, 1); + +enum mlxsw_afa_ip_m_l { + /* LSB: ip[63:0] refers to ip[63:0] */ + MLXSW_AFA_IP_M_L_LSB, + /* MSB: ip[63:0] refers to ip[127:64] */ + MLXSW_AFA_IP_M_L_MSB, +}; + +/* afa_ip_m_l + * MSB or LSB. + */ +MLXSW_ITEM32(afa, ip, m_l, 0x00, 30, 1); + +/* afa_ip_ip_63_32 + * Bits [63:32] in the IP address to change to. + */ +MLXSW_ITEM32(afa, ip, ip_63_32, 0x08, 0, 32); + +/* afa_ip_ip_31_0 + * Bits [31:0] in the IP address to change to. + */ +MLXSW_ITEM32(afa, ip, ip_31_0, 0x0C, 0, 32); + +static void mlxsw_afa_ip_pack(char *payload, enum mlxsw_afa_ip_s_d s_d, + enum mlxsw_afa_ip_m_l m_l, u32 ip_31_0, + u32 ip_63_32) +{ + mlxsw_afa_ip_s_d_set(payload, s_d); + mlxsw_afa_ip_m_l_set(payload, m_l); + mlxsw_afa_ip_ip_31_0_set(payload, ip_31_0); + mlxsw_afa_ip_ip_63_32_set(payload, ip_63_32); +} + +int mlxsw_afa_block_append_ip(struct mlxsw_afa_block *block, bool is_dip, + bool is_lsb, u32 val_31_0, u32 val_63_32, + struct netlink_ext_ack *extack) +{ + enum mlxsw_afa_ip_s_d s_d = is_dip ? MLXSW_AFA_IP_S_D_DIP : + MLXSW_AFA_IP_S_D_SIP; + enum mlxsw_afa_ip_m_l m_l = is_lsb ? MLXSW_AFA_IP_M_L_LSB : + MLXSW_AFA_IP_M_L_MSB; + char *act = mlxsw_afa_block_append_action(block, + MLXSW_AFA_IP_CODE, + MLXSW_AFA_IP_SIZE); + + if (IS_ERR(act)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot append IP action"); + return PTR_ERR(act); + } + + mlxsw_afa_ip_pack(act, s_d, m_l, val_31_0, val_63_32); + return 0; +} +EXPORT_SYMBOL(mlxsw_afa_block_append_ip); + /* L4 Port Action * -------------- * The L4_PORT_ACTION is used for modifying the sport and dport fields of the packet, e.g. for NAT. 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 16cbd6acbb01..db58037be46e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -92,6 +92,9 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid, int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, u16 expected_irif, u16 min_mtu, bool rmid_valid, u32 kvdl_index); +int mlxsw_afa_block_append_ip(struct mlxsw_afa_block *block, bool is_dip, + bool is_lsb, u32 val_31_0, u32 val_63_32, + struct netlink_ext_ack *extack); int mlxsw_afa_block_append_l4port(struct mlxsw_afa_block *block, bool is_dport, u16 l4_port, struct netlink_ext_ack *extack); int mlxsw_afa_block_append_police(struct mlxsw_afa_block *block, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 6dd4ae2f45f4..6ea4bf87be0b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -18,6 +18,7 @@ struct mlxsw_env_module_info { int num_ports_mapped; int num_ports_up; enum ethtool_module_power_mode_policy power_mode_policy; + enum mlxsw_reg_pmtm_module_type type; }; struct mlxsw_env { @@ -27,14 +28,47 @@ struct mlxsw_env { struct mlxsw_env_module_info module_info[]; }; -static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, - bool *qsfp, bool *cmis) +static int __mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(core); + int err; + + switch (mlxsw_env->module_info[module].type) { + case MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR: + err = -EINVAL; + break; + default: + err = 0; + } + + return err; +} + +static int mlxsw_env_validate_module_type(struct mlxsw_core *core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(core); + int err; + + mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(core, module); + mutex_unlock(&mlxsw_env->module_info_lock); + + return err; +} + +static int +mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, bool *qsfp, + bool *cmis) { char mcia_pl[MLXSW_REG_MCIA_LEN]; char *eeprom_tmp; u8 ident; int err; + err = mlxsw_env_validate_module_type(core, id); + if (err) + return err; + mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1, MLXSW_REG_MCIA_I2C_ADDR_LOW); err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); @@ -206,7 +240,8 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, return 0; } -int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, +int mlxsw_env_get_module_info(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, int module, struct ethtool_modinfo *modinfo) { u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE]; @@ -215,6 +250,13 @@ int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, unsigned int read_size; int err; + err = mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + netdev_err(netdev, + "EEPROM is not equipped on port module type"); + return err; + } + err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset, module_info, false, &read_size); if (err) @@ -356,6 +398,13 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, { u32 bytes_read = 0; u16 device_addr; + int err; + + err = mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "EEPROM is not equipped on port module type"); + return err; + } /* Offset cannot be larger than 2 * ETH_MODULE_EEPROM_PAGE_LEN */ device_addr = page->offset; @@ -364,7 +413,6 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, char mcia_pl[MLXSW_REG_MCIA_LEN]; char *eeprom_tmp; u8 size; - int err; size = min_t(u8, page->length - bytes_read, MLXSW_REG_MCIA_EEPROM_SIZE); @@ -419,6 +467,12 @@ int mlxsw_env_reset_module(struct net_device *netdev, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + netdev_err(netdev, "Reset module is not supported on port module type\n"); + goto out; + } + if (mlxsw_env->module_info[module].num_ports_up) { netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n"); err = -EINVAL; @@ -461,6 +515,12 @@ mlxsw_env_get_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Power mode is not supported on port module type"); + goto out; + } + params->policy = mlxsw_env->module_info[module].power_mode_policy; mlxsw_reg_mcion_pack(mcion_pl, module); @@ -571,6 +631,13 @@ mlxsw_env_set_module_power_mode(struct mlxsw_core *mlxsw_core, u8 module, mutex_lock(&mlxsw_env->module_info_lock); + err = __mlxsw_env_validate_module_type(mlxsw_core, module); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Power mode set is not supported on port module type"); + goto out; + } + if (mlxsw_env->module_info[module].power_mode_policy == policy) goto out; @@ -661,13 +728,12 @@ static int mlxsw_env_temp_event_set(struct mlxsw_core *mlxsw_core, return mlxsw_reg_write(mlxsw_core, MLXSW_REG(mtmp), mtmp_pl); } -static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core, - u8 module_count) +static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core) { int i, err, sensor_index; bool has_temp_sensor; - for (i = 0; i < module_count; i++) { + for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) { err = mlxsw_env_module_has_temp_sensor(mlxsw_core, i, &has_temp_sensor); if (err) @@ -759,7 +825,7 @@ mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl, } static const struct mlxsw_listener mlxsw_env_temp_warn_listener = - MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE); + MLXSW_CORE_EVENTL(mlxsw_env_mtwe_listener_func, MTWE); static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core) { @@ -849,7 +915,7 @@ mlxsw_env_pmpe_listener_func(const struct mlxsw_reg_info *reg, char *pmpe_pl, } static const struct mlxsw_listener mlxsw_env_module_plug_listener = - MLXSW_EVENTL(mlxsw_env_pmpe_listener_func, PMPE, PMPE); + MLXSW_CORE_EVENTL(mlxsw_env_pmpe_listener_func, PMPE); static int mlxsw_env_module_plug_event_register(struct mlxsw_core *mlxsw_core) @@ -876,12 +942,11 @@ mlxsw_env_module_plug_event_unregister(struct mlxsw_env *mlxsw_env) } static int -mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core, - u8 module_count) +mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core) { int i, err; - for (i = 0; i < module_count; i++) { + for (i = 0; i < mlxsw_core_env(mlxsw_core)->module_count; i++) { char pmaos_pl[MLXSW_REG_PMAOS_LEN]; mlxsw_reg_pmaos_pack(pmaos_pl, i); @@ -999,6 +1064,28 @@ out_unlock: } EXPORT_SYMBOL(mlxsw_env_module_port_down); +static int +mlxsw_env_module_type_set(struct mlxsw_core *mlxsw_core) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + int i; + + for (i = 0; i < mlxsw_env->module_count; i++) { + char pmtm_pl[MLXSW_REG_PMTM_LEN]; + int err; + + mlxsw_reg_pmtm_pack(pmtm_pl, 0, i); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl); + if (err) + return err; + + mlxsw_env->module_info[i].type = + mlxsw_reg_pmtm_module_type_get(pmtm_pl); + } + + return 0; +} + int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) { char mgpir_pl[MLXSW_REG_MGPIR_LEN]; @@ -1037,17 +1124,21 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) if (err) goto err_module_plug_event_register; - err = mlxsw_env_module_oper_state_event_enable(mlxsw_core, - env->module_count); + err = mlxsw_env_module_oper_state_event_enable(mlxsw_core); if (err) goto err_oper_state_event_enable; - err = mlxsw_env_module_temp_event_enable(mlxsw_core, env->module_count); + err = mlxsw_env_module_temp_event_enable(mlxsw_core); if (err) goto err_temp_event_enable; + err = mlxsw_env_module_type_set(mlxsw_core); + if (err) + goto err_type_set; + return 0; +err_type_set: err_temp_event_enable: err_oper_state_event_enable: mlxsw_env_module_plug_event_unregister(env); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index da121b1a84b4..ec6564e5d2ee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -12,7 +12,8 @@ struct ethtool_eeprom; int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, int off, int *temp); -int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module, +int mlxsw_env_get_module_info(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, int module, struct ethtool_modinfo *modinfo); int mlxsw_env_get_module_eeprom(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 10d13f5f9c7d..9ac8ce01c061 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -110,7 +110,8 @@ static int mlxsw_m_get_module_info(struct net_device *netdev, struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; - return mlxsw_env_get_module_info(core, mlxsw_m_port->module, modinfo); + return mlxsw_env_get_module_info(netdev, core, mlxsw_m_port->module, + modinfo); } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 24cc65018b41..eebd0479b2bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4482,6 +4482,8 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22) #define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23) +#define MLXSW_REG_PTYS_ETH_SPEED_100BASE_T BIT(24) +#define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T BIT(25) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28) #define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29) @@ -6062,6 +6064,58 @@ static inline void mlxsw_reg_pllp_unpack(char *payload, u8 *label_port, *slot_index = mlxsw_reg_pllp_slot_index_get(payload); } +/* PMTM - Port Module Type Mapping Register + * ---------------------------------------- + * The PMTM register allows query or configuration of module types. + * The register can only be set when the module is disabled by PMAOS register + */ +#define MLXSW_REG_PMTM_ID 0x5067 +#define MLXSW_REG_PMTM_LEN 0x10 + +MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN); + +/* reg_pmtm_slot_index + * Slot index. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtm, slot_index, 0x00, 24, 4); + +/* reg_pmtm_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8); + +enum mlxsw_reg_pmtm_module_type { + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_4_LANES = 0, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP = 1, + MLXSW_REG_PMTM_MODULE_TYPE_SFP = 2, + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_SINGLE_LANE = 4, + MLXSW_REG_PMTM_MODULE_TYPE_BACKPLANE_2_LANES = 8, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP4X = 10, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP2X = 11, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP1X = 12, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, + MLXSW_REG_PMTM_MODULE_TYPE_OSFP = 15, + MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD = 16, + MLXSW_REG_PMTM_MODULE_TYPE_DSFP = 17, + MLXSW_REG_PMTM_MODULE_TYPE_CHIP2CHIP8X = 18, + MLXSW_REG_PMTM_MODULE_TYPE_TWISTED_PAIR = 19, +}; + +/* reg_pmtm_module_type + * Module type. + * Access: RW + */ +MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 5); + +static inline void mlxsw_reg_pmtm_pack(char *payload, u8 slot_index, u8 module) +{ + MLXSW_REG_ZERO(pmtm, payload); + mlxsw_reg_pmtm_slot_index_set(payload, slot_index); + mlxsw_reg_pmtm_module_set(payload, module); +} + /* HTGT - Host Trap Group Table * ---------------------------- * Configures the properties for forwarding to CPU. @@ -6087,9 +6141,7 @@ MLXSW_ITEM32(reg, htgt, type, 0x00, 8, 4); enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_TRAP_GROUP_MFDE, - MLXSW_REG_HTGT_TRAP_GROUP_MTWE, - MLXSW_REG_HTGT_TRAP_GROUP_PMPE, + MLXSW_REG_HTGT_TRAP_GROUP_CORE_EVENT, MLXSW_REG_HTGT_TRAP_GROUP_SP_STP, MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP, MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP, @@ -12568,6 +12620,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(pddr), MLXSW_REG(pmmp), MLXSW_REG(pllp), + MLXSW_REG(pmtm), MLXSW_REG(htgt), MLXSW_REG(hpkt), MLXSW_REG(rgcr), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index c7fc650608eb..daacf6291253 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -33,6 +33,7 @@ enum mlxsw_res_id { MLXSW_RES_ID_ACL_MAX_REGIONS, MLXSW_RES_ID_ACL_MAX_GROUPS, MLXSW_RES_ID_ACL_MAX_GROUP_SIZE, + MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS, MLXSW_RES_ID_ACL_FLEX_KEYS, MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE, MLXSW_RES_ID_ACL_ACTIONS_PER_SET, @@ -90,6 +91,7 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903, [MLXSW_RES_ID_ACL_MAX_GROUPS] = 0x2904, [MLXSW_RES_ID_ACL_MAX_GROUP_SIZE] = 0x2905, + [MLXSW_RES_ID_ACL_MAX_DEFAULT_ACTIONS] = 0x2908, [MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910, [MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911, [MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index aa411dec62f0..a4b94eecea98 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2148,13 +2148,11 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_port *mlxsw_sp_port; enum mlxsw_reg_pude_oper_status status; - unsigned int max_ports; u16 local_port; - max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); - if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) @@ -2393,45 +2391,6 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) return 0; } -static int mlxsw_sp_traps_register(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_listener listeners[], - size_t listeners_count) -{ - int i; - int err; - - for (i = 0; i < listeners_count; i++) { - err = mlxsw_core_trap_register(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - if (err) - goto err_listener_register; - - } - return 0; - -err_listener_register: - for (i--; i >= 0; i--) { - mlxsw_core_trap_unregister(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - } - return err; -} - -static void mlxsw_sp_traps_unregister(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_listener listeners[], - size_t listeners_count) -{ - int i; - - for (i = 0; i < listeners_count; i++) { - mlxsw_core_trap_unregister(mlxsw_sp->core, - &listeners[i], - mlxsw_sp); - } -} - static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_trap *trap; @@ -2456,21 +2415,23 @@ static int mlxsw_sp_traps_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_trap_groups_set; - err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), + mlxsw_sp); if (err) goto err_traps_register; - err = mlxsw_sp_traps_register(mlxsw_sp, mlxsw_sp->listeners, - mlxsw_sp->listeners_count); + err = mlxsw_core_traps_register(mlxsw_sp->core, mlxsw_sp->listeners, + mlxsw_sp->listeners_count, mlxsw_sp); if (err) goto err_extra_traps_init; return 0; err_extra_traps_init: - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), + mlxsw_sp); err_traps_register: err_trap_groups_set: err_cpu_policers_set: @@ -2480,10 +2441,11 @@ err_cpu_policers_set: static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) { - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp->listeners, - mlxsw_sp->listeners_count); - mlxsw_sp_traps_unregister(mlxsw_sp, mlxsw_sp_listener, - ARRAY_SIZE(mlxsw_sp_listener)); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp->listeners, + mlxsw_sp->listeners_count, + mlxsw_sp); + mlxsw_core_traps_unregister(mlxsw_sp->core, mlxsw_sp_listener, + ARRAY_SIZE(mlxsw_sp_listener), mlxsw_sp); kfree(mlxsw_sp->trap); } @@ -2528,42 +2490,6 @@ static void mlxsw_sp_lag_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->lags); } -static int mlxsw_sp_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) -{ - char htgt_pl[MLXSW_REG_HTGT_LEN]; - int err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MFDE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_MTWE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_PMPE, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); -} - static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = { .clock_init = mlxsw_sp1_ptp_clock_init, .clock_fini = mlxsw_sp1_ptp_clock_fini, @@ -3677,7 +3603,6 @@ static struct mlxsw_driver mlxsw_sp1_driver = { .fw_filename = MLXSW_SP1_FW_FILENAME, .init = mlxsw_sp1_init, .fini = mlxsw_sp_fini, - .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, .port_split = mlxsw_sp_port_split, .port_unsplit = mlxsw_sp_port_unsplit, .sb_pool_get = mlxsw_sp_sb_pool_get, @@ -3717,7 +3642,6 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .fw_filename = MLXSW_SP2_FW_FILENAME, .init = mlxsw_sp2_init, .fini = mlxsw_sp_fini, - .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, .port_split = mlxsw_sp_port_split, .port_unsplit = mlxsw_sp_port_unsplit, .sb_pool_get = mlxsw_sp_sb_pool_get, @@ -3758,7 +3682,6 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .fw_filename = MLXSW_SP3_FW_FILENAME, .init = mlxsw_sp3_init, .fini = mlxsw_sp_fini, - .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, .port_split = mlxsw_sp_port_split, .port_unsplit = mlxsw_sp_port_unsplit, .sb_pool_get = mlxsw_sp_sb_pool_get, @@ -3797,7 +3720,6 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .priv_size = sizeof(struct mlxsw_sp), .init = mlxsw_sp4_init, .fini = mlxsw_sp_fini, - .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, .port_split = mlxsw_sp_port_split, .port_unsplit = mlxsw_sp_port_unsplit, .sb_pool_get = mlxsw_sp_sb_pool_get, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bb2442e1f705..20588e699588 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -481,6 +481,13 @@ int mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_8021ad_tagged, bool is_8021q_tagged); +static inline bool +mlxsw_sp_local_port_is_valid(struct mlxsw_sp *mlxsw_sp, u16 local_port) +{ + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); + + return local_port < max_ports && local_port; +} /* spectrum_buffers.c */ struct mlxsw_sp_hdroom_prio { @@ -813,6 +820,24 @@ int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core); /* spectrum2_kvdl.c */ extern const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops; +enum mlxsw_sp_acl_mangle_field { + MLXSW_SP_ACL_MANGLE_FIELD_IP_DSFIELD, + MLXSW_SP_ACL_MANGLE_FIELD_IP_DSCP, + MLXSW_SP_ACL_MANGLE_FIELD_IP_ECN, + MLXSW_SP_ACL_MANGLE_FIELD_IP_SPORT, + MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT, + MLXSW_SP_ACL_MANGLE_FIELD_IP4_SIP, + MLXSW_SP_ACL_MANGLE_FIELD_IP4_DIP, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_2, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_4, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_2, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3, + MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_4, +}; + struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; @@ -821,9 +846,14 @@ struct mlxsw_sp_acl_rule_info { ingress_bind_blocker:1, egress_bind_blocker:1, counter_valid:1, - policer_index_valid:1; + policer_index_valid:1, + ipv6_valid:1; unsigned int counter_index; u16 policer_index; + struct { + u32 prev_val; + enum mlxsw_sp_acl_mangle_field prev_field; + } ipv6; }; /* spectrum_flow.c */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c index a9fff8adc75e..d20e794e01ca 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c @@ -213,7 +213,6 @@ mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp1_kvdl_part *part; bool need_update = true; unsigned int nr_entries; - size_t usage_size; u64 resource_size; int err; @@ -225,8 +224,8 @@ mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp, } nr_entries = div_u64(resource_size, info->alloc_size); - usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long); - part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL); + part = kzalloc(struct_size(part, usage, BITS_TO_LONGS(nr_entries)), + GFP_KERNEL); if (!part) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index ad69913f19c1..5b0210862655 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -77,7 +77,14 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, int i; int err; + /* Some TCAM regions are not exposed to the host and used internally + * by the device. Allocate KVDL entries for the default actions of + * these regions to avoid the host from overwriting them. + */ tcam->kvdl_count = _tcam->max_regions; + if (MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_DEFAULT_ACTIONS)) + tcam->kvdl_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_DEFAULT_ACTIONS); err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET, tcam->kvdl_count, &tcam->kvdl_index); if (err) @@ -97,7 +104,10 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv, goto err_afa_block_continue; enc_actions = mlxsw_afa_block_cur_set(afa_block); - for (i = 0; i < tcam->kvdl_count; i++) { + /* Only write to KVDL entries used by TCAM regions exposed to the + * host. + */ + for (i = 0; i < _tcam->max_regions; i++) { mlxsw_reg_pefa_pack(pefa_pl, tcam->kvdl_index + i, true, enc_actions); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 70c11bfac08f..6c5af018546f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -505,14 +505,6 @@ int mlxsw_sp_acl_rulei_act_priority(struct mlxsw_sp *mlxsw_sp, extack); } -enum mlxsw_sp_acl_mangle_field { - MLXSW_SP_ACL_MANGLE_FIELD_IP_DSFIELD, - MLXSW_SP_ACL_MANGLE_FIELD_IP_DSCP, - MLXSW_SP_ACL_MANGLE_FIELD_IP_ECN, - MLXSW_SP_ACL_MANGLE_FIELD_IP_SPORT, - MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT, -}; - struct mlxsw_sp_acl_mangle_action { enum flow_action_mangle_base htype; /* Offset is u32-aligned. */ @@ -561,6 +553,18 @@ static struct mlxsw_sp_acl_mangle_action mlxsw_sp_acl_mangle_actions[] = { MLXSW_SP_ACL_MANGLE_ACTION_UDP(0, 0x0000ffff, 16, IP_SPORT), MLXSW_SP_ACL_MANGLE_ACTION_UDP(0, 0xffff0000, 0, IP_DPORT), + + MLXSW_SP_ACL_MANGLE_ACTION_IP4(12, 0x00000000, 0, IP4_SIP), + MLXSW_SP_ACL_MANGLE_ACTION_IP4(16, 0x00000000, 0, IP4_DIP), + + MLXSW_SP_ACL_MANGLE_ACTION_IP6(8, 0x00000000, 0, IP6_SIP_1), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(12, 0x00000000, 0, IP6_SIP_2), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(16, 0x00000000, 0, IP6_SIP_3), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(20, 0x00000000, 0, IP6_SIP_4), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(24, 0x00000000, 0, IP6_DIP_1), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(28, 0x00000000, 0, IP6_DIP_2), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(32, 0x00000000, 0, IP6_DIP_3), + MLXSW_SP_ACL_MANGLE_ACTION_IP6(36, 0x00000000, 0, IP6_DIP_4), }; static int @@ -599,6 +603,22 @@ static int mlxsw_sp1_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, return err; } +static int +mlxsw_sp2_acl_rulei_act_mangle_field_ip_odd(struct mlxsw_sp_acl_rule_info *rulei, + enum mlxsw_sp_acl_mangle_field field, + u32 val, struct netlink_ext_ack *extack) +{ + if (!rulei->ipv6_valid) { + rulei->ipv6.prev_val = val; + rulei->ipv6_valid = true; + rulei->ipv6.prev_field = field; + return 0; + } + + NL_SET_ERR_MSG_MOD(extack, "Unsupported mangle field order"); + return -EOPNOTSUPP; +} + static int mlxsw_sp2_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct mlxsw_sp_acl_mangle_action *mact, @@ -615,6 +635,61 @@ static int mlxsw_sp2_acl_rulei_act_mangle_field(struct mlxsw_sp *mlxsw_sp, return mlxsw_afa_block_append_l4port(rulei->act_block, false, val, extack); case MLXSW_SP_ACL_MANGLE_FIELD_IP_DPORT: return mlxsw_afa_block_append_l4port(rulei->act_block, true, val, extack); + /* IPv4 fields */ + case MLXSW_SP_ACL_MANGLE_FIELD_IP4_SIP: + return mlxsw_afa_block_append_ip(rulei->act_block, false, + true, val, 0, extack); + case MLXSW_SP_ACL_MANGLE_FIELD_IP4_DIP: + return mlxsw_afa_block_append_ip(rulei->act_block, true, + true, val, 0, extack); + /* IPv6 fields */ + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1: + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3: + return mlxsw_sp2_acl_rulei_act_mangle_field_ip_odd(rulei, + mact->field, + val, extack); + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_2: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_1) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + false, false, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_4: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_SIP_3) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + false, true, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_2: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_1) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + true, false, val, + rulei->ipv6.prev_val, + extack); + } + break; + case MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_4: + if (rulei->ipv6_valid && + rulei->ipv6.prev_field == MLXSW_SP_ACL_MANGLE_FIELD_IP6_DIP_3) { + rulei->ipv6_valid = false; + return mlxsw_afa_block_append_ip(rulei->act_block, + true, true, val, + rulei->ipv6.prev_val, + extack); + } + break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 20530712eadb..8b5d7f83b9b0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1034,13 +1034,10 @@ static int mlxsw_sp_get_module_info(struct net_device *netdev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - int err; - - err = mlxsw_env_get_module_info(mlxsw_sp->core, - mlxsw_sp_port->mapping.module, - modinfo); - return err; + return mlxsw_env_get_module_info(netdev, mlxsw_sp->core, + mlxsw_sp_port->mapping.module, + modinfo); } static int mlxsw_sp_get_module_eeprom(struct net_device *netdev, @@ -1048,13 +1045,10 @@ static int mlxsw_sp_get_module_eeprom(struct net_device *netdev, { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - int err; - - err = mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core, - mlxsw_sp_port->mapping.module, ee, - data); - return err; + return mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core, + mlxsw_sp_port->mapping.module, ee, + data); } static int @@ -1273,12 +1267,22 @@ struct mlxsw_sp1_port_link_mode { static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { { + .mask = MLXSW_REG_PTYS_ETH_SPEED_100BASE_T, + .mask_ethtool = ETHTOOL_LINK_MODE_100baseT_Full_BIT, + .speed = SPEED_100, + }, + { .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, .mask_ethtool = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, .speed = SPEED_1000, }, { + .mask = MLXSW_REG_PTYS_ETH_SPEED_1000BASE_T, + .mask_ethtool = ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + .speed = SPEED_1000, + }, + { .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, .mask_ethtool = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index bb417db773b9..f54af3d9a03b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -233,6 +233,12 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return -EOPNOTSUPP; } } + + if (rulei->ipv6_valid) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported mangle field"); + return -EOPNOTSUPP; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 0ff163fbc775..35422e64d89f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -568,12 +568,11 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress, u8 domain_number, u16 sequence_id, u64 timestamp) { - unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port *mlxsw_sp_port; struct mlxsw_sp1_ptp_key key; u8 types; - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 65c1724c63b0..bffdb41fc4ed 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2616,7 +2616,6 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, char *sfn_pl, int rec_index, bool adding) { - unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; struct mlxsw_sp_bridge_device *bridge_device; struct mlxsw_sp_bridge_port *bridge_port; @@ -2630,7 +2629,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port); - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!mlxsw_sp_local_port_is_valid(mlxsw_sp, local_port))) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 91a755efe2e6..5f1e7b8bad4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -750,7 +750,7 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev, } if (eee->eee_enabled) { - ret = phy_init_eee(phydev, 0); + ret = phy_init_eee(phydev, false); if (ret) { netif_err(adapter, drv, adapter->netdev, "EEE initialization failed\n"); diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 040cfff9f577..a9ffc719aa0e 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -7,4 +7,5 @@ obj-$(CONFIG_LAN966X_SWITCH) += lan966x-switch.o lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_mac.o lan966x_ethtool.o lan966x_switchdev.o \ - lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o + lan966x_vlan.o lan966x_fdb.o lan966x_mdb.o \ + lan966x_ptp.o diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c index 614f12c2fe6a..e58a27fd8b50 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c @@ -545,6 +545,39 @@ static int lan966x_set_pauseparam(struct net_device *dev, return phylink_ethtool_set_pauseparam(port->phylink, pause); } +static int lan966x_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + struct lan966x_phc *phc; + + if (!lan966x->ptp) + return ethtool_op_get_ts_info(dev, info); + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + + info->phc_index = phc->clock ? ptp_clock_index(phc->clock) : -1; + if (info->phc_index == -1) { + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + return 0; + } + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | + BIT(HWTSTAMP_TX_ONESTEP_SYNC); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + const struct ethtool_ops lan966x_ethtool_ops = { .get_link_ksettings = lan966x_get_link_ksettings, .set_link_ksettings = lan966x_set_link_ksettings, @@ -556,6 +589,7 @@ const struct ethtool_ops lan966x_ethtool_ops = { .get_eth_mac_stats = lan966x_get_eth_mac_stats, .get_rmon_stats = lan966x_get_eth_rmon_stats, .get_link = ethtool_op_get_link, + .get_ts_info = lan966x_get_ts_info, }; static void lan966x_check_stats_work(struct work_struct *work) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c index ca5f1177963d..ce5970bdcc6a 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mac.c @@ -40,11 +40,12 @@ static int lan966x_mac_wait_for_completion(struct lan966x *lan966x) { u32 val; - return readx_poll_timeout(lan966x_mac_get_status, - lan966x, val, - (ANA_MACACCESS_MAC_TABLE_CMD_GET(val)) == - MACACCESS_CMD_IDLE, - TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US); + return readx_poll_timeout_atomic(lan966x_mac_get_status, + lan966x, val, + (ANA_MACACCESS_MAC_TABLE_CMD_GET(val)) == + MACACCESS_CMD_IDLE, + TABLE_UPDATE_SLEEP_US, + TABLE_UPDATE_TIMEOUT_US); } static void lan966x_mac_select(struct lan966x *lan966x, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 2cb70da63db3..d62484f14564 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -4,11 +4,13 @@ #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/iopoll.h> +#include <linux/ip.h> #include <linux/of_platform.h> #include <linux/of_net.h> #include <linux/packing.h> #include <linux/phy/phy.h> #include <linux/reset.h> +#include <net/addrconf.h> #include "lan966x_main.h" @@ -44,6 +46,7 @@ static const struct lan966x_main_io_resource lan966x_main_iomap[] = { { TARGET_ORG, 0, 1 }, /* 0xe2000000 */ { TARGET_GCB, 0x4000, 1 }, /* 0xe2004000 */ { TARGET_QS, 0x8000, 1 }, /* 0xe2008000 */ + { TARGET_PTP, 0xc000, 1 }, /* 0xe200c000 */ { TARGET_CHIP_TOP, 0x10000, 1 }, /* 0xe2010000 */ { TARGET_REW, 0x14000, 1 }, /* 0xe2014000 */ { TARGET_SYS, 0x28000, 1 }, /* 0xe2028000 */ @@ -182,9 +185,9 @@ static int lan966x_port_inj_ready(struct lan966x *lan966x, u8 grp) { u32 val; - return readx_poll_timeout(lan966x_port_inj_status, lan966x, val, - QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp), - READL_SLEEP_US, READL_TIMEOUT_US); + return readx_poll_timeout_atomic(lan966x_port_inj_status, lan966x, val, + QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp), + READL_SLEEP_US, READL_TIMEOUT_US); } static int lan966x_port_ifh_xmit(struct sk_buff *skb, @@ -201,7 +204,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, val = lan_rd(lan966x, QS_INJ_STATUS); if (!(QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp)) || (QS_INJ_STATUS_WMARK_REACHED_GET(val) & BIT(grp))) - return NETDEV_TX_BUSY; + goto err; /* Write start of frame */ lan_wr(QS_INJ_CTRL_GAP_SIZE_SET(1) | @@ -213,7 +216,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr((__force u32)ifh[i], lan966x, QS_INJ_WR(grp)); } @@ -225,7 +228,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr(((u32 *)skb->data)[i], lan966x, QS_INJ_WR(grp)); } @@ -235,7 +238,7 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, /* Wait until the fifo is ready */ err = lan966x_port_inj_ready(lan966x, grp); if (err) - return NETDEV_TX_BUSY; + goto err; lan_wr(0, lan966x, QS_INJ_WR(grp)); ++i; @@ -255,8 +258,19 @@ static int lan966x_port_ifh_xmit(struct sk_buff *skb, dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + return NETDEV_TX_OK; + dev_consume_skb_any(skb); return NETDEV_TX_OK; + +err: + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + lan966x_ptp_txtstamp_release(port, skb); + + return NETDEV_TX_BUSY; } static void lan966x_ifh_set_bypass(void *ifh, u64 bypass) @@ -289,10 +303,23 @@ static void lan966x_ifh_set_vid(void *ifh, u64 vid) IFH_POS_TCI, IFH_LEN * 4, PACK, 0); } +static void lan966x_ifh_set_rew_op(void *ifh, u64 rew_op) +{ + packing(ifh, &rew_op, IFH_POS_REW_CMD + IFH_WID_REW_CMD - 1, + IFH_POS_REW_CMD, IFH_LEN * 4, PACK, 0); +} + +static void lan966x_ifh_set_timestamp(void *ifh, u64 timestamp) +{ + packing(ifh, ×tamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1, + IFH_POS_TIMESTAMP, IFH_LEN * 4, PACK, 0); +} + static int lan966x_port_xmit(struct sk_buff *skb, struct net_device *dev) { struct lan966x_port *port = netdev_priv(dev); __be32 ifh[IFH_LEN]; + int err; memset(ifh, 0x0, sizeof(__be32) * IFH_LEN); @@ -302,6 +329,15 @@ static int lan966x_port_xmit(struct sk_buff *skb, struct net_device *dev) lan966x_ifh_set_ipv(ifh, skb->priority >= 7 ? 0x7 : skb->priority); lan966x_ifh_set_vid(ifh, skb_vlan_tag_get(skb)); + if (port->lan966x->ptp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + err = lan966x_ptp_txtstamp_request(port, skb); + if (err) + return err; + + lan966x_ifh_set_rew_op(ifh, LAN966X_SKB_CB(skb)->rew_op); + lan966x_ifh_set_timestamp(ifh, LAN966X_SKB_CB(skb)->ts_id); + } + return lan966x_port_ifh_xmit(skb, ifh, dev); } @@ -350,6 +386,23 @@ static int lan966x_port_get_parent_id(struct net_device *dev, return 0; } +static int lan966x_port_ioctl(struct net_device *dev, struct ifreq *ifr, + int cmd) +{ + struct lan966x_port *port = netdev_priv(dev); + + if (!phy_has_hwtstamp(dev->phydev) && port->lan966x->ptp) { + switch (cmd) { + case SIOCSHWTSTAMP: + return lan966x_ptp_hwtstamp_set(port, ifr); + case SIOCGHWTSTAMP: + return lan966x_ptp_hwtstamp_get(port, ifr); + } + } + + return phy_mii_ioctl(dev->phydev, ifr, cmd); +} + static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_open = lan966x_port_open, .ndo_stop = lan966x_port_stop, @@ -360,6 +413,7 @@ static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_get_stats64 = lan966x_stats_get, .ndo_set_mac_address = lan966x_port_set_mac_address, .ndo_get_port_parent_id = lan966x_port_get_parent_id, + .ndo_eth_ioctl = lan966x_port_ioctl, }; bool lan966x_netdevice_check(const struct net_device *dev) @@ -367,6 +421,32 @@ bool lan966x_netdevice_check(const struct net_device *dev) return dev->netdev_ops == &lan966x_port_netdev_ops; } +static bool lan966x_hw_offload(struct lan966x *lan966x, u32 port, + struct sk_buff *skb) +{ + u32 val; + + /* The IGMP and MLD frames are not forward by the HW if + * multicast snooping is enabled, therefor don't mark as + * offload to allow the SW to forward the frames accordingly. + */ + val = lan_rd(lan966x, ANA_CPU_FWD_CFG(port)); + if (!(val & (ANA_CPU_FWD_CFG_IGMP_REDIR_ENA | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA))) + return true; + + if (skb->protocol == htons(ETH_P_IP) && + ip_hdr(skb)->protocol == IPPROTO_IGMP) + return false; + + if (skb->protocol == htons(ETH_P_IPV6) && + ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && + !ipv6_mc_check_mld(skb)) + return false; + + return true; +} + static int lan966x_port_xtr_status(struct lan966x *lan966x, u8 grp) { return lan_rd(lan966x, QS_XTR_RD(grp)); @@ -434,6 +514,12 @@ static void lan966x_ifh_get_len(void *ifh, u64 *len) IFH_POS_LEN, IFH_LEN * 4, UNPACK, 0); } +static void lan966x_ifh_get_timestamp(void *ifh, u64 *timestamp) +{ + packing(ifh, timestamp, IFH_POS_TIMESTAMP + IFH_WID_TIMESTAMP - 1, + IFH_POS_TIMESTAMP, IFH_LEN * 4, UNPACK, 0); +} + static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) { struct lan966x *lan966x = args; @@ -443,10 +529,10 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) return IRQ_NONE; do { + u64 src_port, len, timestamp; struct net_device *dev; struct sk_buff *skb; int sz = 0, buf_len; - u64 src_port, len; u32 ifh[IFH_LEN]; u32 *buf; u32 val; @@ -461,6 +547,7 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) lan966x_ifh_get_src_port(ifh, &src_port); lan966x_ifh_get_len(ifh, &len); + lan966x_ifh_get_timestamp(ifh, ×tamp); WARN_ON(src_port >= lan966x->num_phys_ports); @@ -501,11 +588,17 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) *buf = val; } + lan966x_ptp_rxtstamp(lan966x, skb, timestamp); skb->protocol = eth_type_trans(skb, dev); - if (lan966x->bridge_mask & BIT(src_port)) + if (lan966x->bridge_mask & BIT(src_port)) { skb->offload_fwd_mark = 1; + skb_reset_network_header(skb); + if (!lan966x_hw_offload(lan966x, src_port, skb)) + skb->offload_fwd_mark = 0; + } + netif_rx_ni(skb); dev->stats.rx_bytes += len; dev->stats.rx_packets++; @@ -628,7 +721,6 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, } port->phylink = phylink; - phylink_set_pcs(phylink, &port->phylink_pcs); err = register_netdev(dev); if (err) { @@ -708,7 +800,7 @@ static void lan966x_init(struct lan966x *lan966x) /* Setup flooding PGIDs */ lan_wr(ANA_FLOODING_IPMC_FLD_MC4_DATA_SET(PGID_MCIPV4) | ANA_FLOODING_IPMC_FLD_MC4_CTRL_SET(PGID_MC) | - ANA_FLOODING_IPMC_FLD_MC6_DATA_SET(PGID_MC) | + ANA_FLOODING_IPMC_FLD_MC6_DATA_SET(PGID_MCIPV6) | ANA_FLOODING_IPMC_FLD_MC6_CTRL_SET(PGID_MC), lan966x, ANA_FLOODING_IPMC); @@ -770,6 +862,10 @@ static void lan966x_init(struct lan966x *lan966x) ANA_PGID_PGID, lan966x, ANA_PGID(PGID_MCIPV4)); + lan_rmw(GENMASK(lan966x->num_phys_ports - 1, 0), + ANA_PGID_PGID, + lan966x, ANA_PGID(PGID_MCIPV6)); + /* Unicast to all other ports */ lan_rmw(GENMASK(lan966x->num_phys_ports - 1, 0), ANA_PGID_PGID, @@ -897,6 +993,17 @@ static int lan966x_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, err, "Unable to use ana irq"); } + lan966x->ptp_irq = platform_get_irq_byname(pdev, "ptp"); + if (lan966x->ptp_irq > 0) { + err = devm_request_threaded_irq(&pdev->dev, lan966x->ptp_irq, NULL, + lan966x_ptp_irq_handler, IRQF_ONESHOT, + "ptp irq", lan966x); + if (err) + return dev_err_probe(&pdev->dev, err, "Unable to use ptp irq"); + + lan966x->ptp = 1; + } + /* init switch */ lan966x_init(lan966x); lan966x_stats_init(lan966x); @@ -931,8 +1038,15 @@ static int lan966x_probe(struct platform_device *pdev) if (err) goto cleanup_ports; + err = lan966x_ptp_init(lan966x); + if (err) + goto cleanup_fdb; + return 0; +cleanup_fdb: + lan966x_fdb_deinit(lan966x); + cleanup_ports: fwnode_handle_put(portnp); @@ -958,6 +1072,7 @@ static int lan966x_remove(struct platform_device *pdev) lan966x_mac_purge_entries(lan966x); lan966x_mdb_deinit(lan966x); lan966x_fdb_deinit(lan966x); + lan966x_ptp_deinit(lan966x); return 0; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 99c6d0a9f946..058e43531818 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -8,6 +8,7 @@ #include <linux/jiffies.h> #include <linux/phy.h> #include <linux/phylink.h> +#include <linux/ptp_clock_kernel.h> #include <net/switchdev.h> #include "lan966x_regs.h" @@ -50,6 +51,13 @@ #define LAN966X_SPEED_100 2 #define LAN966X_SPEED_10 3 +#define LAN966X_PHC_COUNT 3 +#define LAN966X_PHC_PORT 0 + +#define IFH_REW_OP_NOOP 0x0 +#define IFH_REW_OP_ONE_STEP_PTP 0x3 +#define IFH_REW_OP_TWO_STEP_PTP 0x4 + /* MAC table entry types. * ENTRYTYPE_NORMAL is subject to aging. * ENTRYTYPE_LOCKED is not subject to aging. @@ -70,6 +78,24 @@ struct lan966x_stat_layout { char name[ETH_GSTRING_LEN]; }; +struct lan966x_phc { + struct ptp_clock *clock; + struct ptp_clock_info info; + struct hwtstamp_config hwtstamp_config; + struct lan966x *lan966x; + u8 index; +}; + +struct lan966x_skb_cb { + u8 rew_op; + u16 ts_id; + unsigned long jiffies; +}; + +#define LAN966X_PTP_TIMEOUT msecs_to_jiffies(10) +#define LAN966X_SKB_CB(skb) \ + ((struct lan966x_skb_cb *)((skb)->cb)) + struct lan966x { struct device *dev; @@ -105,6 +131,7 @@ struct lan966x { /* interrupts */ int xtr_irq; int ana_irq; + int ptp_irq; /* worqueue for fdb */ struct workqueue_struct *fdb_work; @@ -113,6 +140,14 @@ struct lan966x { /* mdb */ struct list_head mdb_entries; struct list_head pgid_entries; + + /* ptp */ + bool ptp; + struct lan966x_phc phc[LAN966X_PHC_COUNT]; + spinlock_t ptp_clock_lock; /* lock for phc */ + spinlock_t ptp_ts_id_lock; /* lock for ts_id */ + struct mutex ptp_lock; /* lock for ptp interface state */ + u16 ptp_skbs; }; struct lan966x_port_config { @@ -135,6 +170,7 @@ struct lan966x_port { bool vlan_aware; bool learn_ena; + bool mcast_ena; struct phylink_config phylink_config; struct phylink_pcs phylink_pcs; @@ -142,6 +178,10 @@ struct lan966x_port { struct phylink *phylink; struct phy *serdes; struct fwnode_handle *fwnode; + + u8 ptp_cmd; + u16 ts_id; + struct sk_buff_head tx_skbs; }; extern const struct phylink_mac_ops lan966x_phylink_mac_ops; @@ -227,6 +267,20 @@ int lan966x_handle_port_mdb_del(struct lan966x_port *port, const struct switchdev_obj *obj); void lan966x_mdb_erase_entries(struct lan966x *lan966x, u16 vid); void lan966x_mdb_write_entries(struct lan966x *lan966x, u16 vid); +void lan966x_mdb_clear_entries(struct lan966x *lan966x); +void lan966x_mdb_restore_entries(struct lan966x *lan966x); + +int lan966x_ptp_init(struct lan966x *lan966x); +void lan966x_ptp_deinit(struct lan966x *lan966x); +int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr); +int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr); +void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb, + u64 timestamp); +int lan966x_ptp_txtstamp_request(struct lan966x_port *port, + struct sk_buff *skb); +void lan966x_ptp_txtstamp_release(struct lan966x_port *port, + struct sk_buff *skb); +irqreturn_t lan966x_ptp_irq_handler(int irq, void *args); static inline void __iomem *lan_addr(void __iomem *base[], int id, int tinst, int tcnt, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c b/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c index c68d0a99d292..2af55268bf4d 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_mdb.c @@ -504,3 +504,48 @@ void lan966x_mdb_erase_entries(struct lan966x *lan966x, u16 vid) lan966x_mdb_l2_cpu_remove(lan966x, mdb_entry, type); } } + +void lan966x_mdb_clear_entries(struct lan966x *lan966x) +{ + struct lan966x_mdb_entry *mdb_entry; + enum macaccess_entry_type type; + unsigned char mac[ETH_ALEN]; + + list_for_each_entry(mdb_entry, &lan966x->mdb_entries, list) { + type = lan966x_mdb_classify(mdb_entry->mac); + + lan966x_mdb_encode_mac(mac, mdb_entry, type); + /* Remove just the MAC entry, still keep the PGID in case of L2 + * entries because this can be restored at later point + */ + lan966x_mac_forget(lan966x, mac, mdb_entry->vid, type); + } +} + +void lan966x_mdb_restore_entries(struct lan966x *lan966x) +{ + struct lan966x_mdb_entry *mdb_entry; + enum macaccess_entry_type type; + unsigned char mac[ETH_ALEN]; + bool cpu_copy = false; + + list_for_each_entry(mdb_entry, &lan966x->mdb_entries, list) { + type = lan966x_mdb_classify(mdb_entry->mac); + + lan966x_mdb_encode_mac(mac, mdb_entry, type); + if (type == ENTRYTYPE_MACV4 || type == ENTRYTYPE_MACV6) { + /* Copy the frame to CPU only if the CPU is in the VLAN */ + if (lan966x_vlan_cpu_member_cpu_vlan_mask(lan966x, + mdb_entry->vid) && + mdb_entry->cpu_copy) + cpu_copy = true; + + lan966x_mac_ip_learn(lan966x, cpu_copy, mac, + mdb_entry->vid, type); + } else { + lan966x_mac_learn(lan966x, mdb_entry->pgid->index, + mdb_entry->mac, + mdb_entry->vid, type); + } + } +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index b66a9aa00ea4..38a7e95d69b4 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -9,6 +9,14 @@ #include "lan966x_main.h" +static struct phylink_pcs *lan966x_phylink_mac_select(struct phylink_config *config, + phy_interface_t interface) +{ + struct lan966x_port *port = netdev_priv(to_net_dev(config->dev)); + + return &port->phylink_pcs; +} + static void lan966x_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -114,6 +122,7 @@ static void lan966x_pcs_aneg_restart(struct phylink_pcs *pcs) const struct phylink_mac_ops lan966x_phylink_mac_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = lan966x_phylink_mac_select, .mac_config = lan966x_phylink_mac_config, .mac_prepare = lan966x_phylink_mac_prepare, .mac_link_down = lan966x_phylink_mac_link_down, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c new file mode 100644 index 000000000000..ae782778d6dd --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -0,0 +1,618 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/ptp_classify.h> + +#include "lan966x_main.h" + +#define LAN966X_MAX_PTP_ID 512 + +/* Represents 1ppm adjustment in 2^59 format with 6.037735849ns as reference + * The value is calculated as following: (1/1000000)/((2^-59)/6.037735849) + */ +#define LAN966X_1PPM_FORMAT 3480517749723LL + +/* Represents 1ppb adjustment in 2^29 format with 6.037735849ns as reference + * The value is calculated as following: (1/1000000000)/((2^59)/6.037735849) + */ +#define LAN966X_1PPB_FORMAT 3480517749LL + +#define TOD_ACC_PIN 0x5 + +enum { + PTP_PIN_ACTION_IDLE = 0, + PTP_PIN_ACTION_LOAD, + PTP_PIN_ACTION_SAVE, + PTP_PIN_ACTION_CLOCK, + PTP_PIN_ACTION_DELTA, + PTP_PIN_ACTION_TOD +}; + +static u64 lan966x_ptp_get_nominal_value(void) +{ + u64 res = 0x304d2df1; + + res <<= 32; + return res; +} + +int lan966x_ptp_hwtstamp_set(struct lan966x_port *port, struct ifreq *ifr) +{ + struct lan966x *lan966x = port->lan966x; + struct hwtstamp_config cfg; + struct lan966x_phc *phc; + + /* For now don't allow to run ptp on ports that are part of a bridge, + * because in case of transparent clock the HW will still forward the + * frames, so there would be duplicate frames + */ + if (lan966x->bridge_mask & BIT(port->chip_port)) + return -EINVAL; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + switch (cfg.tx_type) { + case HWTSTAMP_TX_ON: + port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + port->ptp_cmd = IFH_REW_OP_ONE_STEP_PTP; + break; + case HWTSTAMP_TX_OFF: + port->ptp_cmd = IFH_REW_OP_NOOP; + break; + default: + return -ERANGE; + } + + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + cfg.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + /* Commit back the result & save it */ + mutex_lock(&lan966x->ptp_lock); + phc = &lan966x->phc[LAN966X_PHC_PORT]; + memcpy(&phc->hwtstamp_config, &cfg, sizeof(cfg)); + mutex_unlock(&lan966x->ptp_lock); + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +int lan966x_ptp_hwtstamp_get(struct lan966x_port *port, struct ifreq *ifr) +{ + struct lan966x *lan966x = port->lan966x; + struct lan966x_phc *phc; + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + return copy_to_user(ifr->ifr_data, &phc->hwtstamp_config, + sizeof(phc->hwtstamp_config)) ? -EFAULT : 0; +} + +static int lan966x_ptp_classify(struct lan966x_port *port, struct sk_buff *skb) +{ + struct ptp_header *header; + u8 msgtype; + int type; + + if (port->ptp_cmd == IFH_REW_OP_NOOP) + return IFH_REW_OP_NOOP; + + type = ptp_classify_raw(skb); + if (type == PTP_CLASS_NONE) + return IFH_REW_OP_NOOP; + + header = ptp_parse_header(skb, type); + if (!header) + return IFH_REW_OP_NOOP; + + if (port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + return IFH_REW_OP_TWO_STEP_PTP; + + /* If it is sync and run 1 step then set the correct operation, + * otherwise run as 2 step + */ + msgtype = ptp_get_msgtype(header, type); + if ((msgtype & 0xf) == 0) + return IFH_REW_OP_ONE_STEP_PTP; + + return IFH_REW_OP_TWO_STEP_PTP; +} + +static void lan966x_ptp_txtstamp_old_release(struct lan966x_port *port) +{ + struct sk_buff *skb, *skb_tmp; + unsigned long flags; + + spin_lock_irqsave(&port->tx_skbs.lock, flags); + skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { + if time_after(LAN966X_SKB_CB(skb)->jiffies + LAN966X_PTP_TIMEOUT, + jiffies) + break; + + __skb_unlink(skb, &port->tx_skbs); + dev_kfree_skb_any(skb); + } + spin_unlock_irqrestore(&port->tx_skbs.lock, flags); +} + +int lan966x_ptp_txtstamp_request(struct lan966x_port *port, + struct sk_buff *skb) +{ + struct lan966x *lan966x = port->lan966x; + unsigned long flags; + u8 rew_op; + + rew_op = lan966x_ptp_classify(port, skb); + LAN966X_SKB_CB(skb)->rew_op = rew_op; + + if (rew_op != IFH_REW_OP_TWO_STEP_PTP) + return 0; + + lan966x_ptp_txtstamp_old_release(port); + + spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags); + if (lan966x->ptp_skbs == LAN966X_MAX_PTP_ID) { + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); + return -EBUSY; + } + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + skb_queue_tail(&port->tx_skbs, skb); + LAN966X_SKB_CB(skb)->ts_id = port->ts_id; + LAN966X_SKB_CB(skb)->jiffies = jiffies; + + lan966x->ptp_skbs++; + port->ts_id++; + if (port->ts_id == LAN966X_MAX_PTP_ID) + port->ts_id = 0; + + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); + + return 0; +} + +void lan966x_ptp_txtstamp_release(struct lan966x_port *port, + struct sk_buff *skb) +{ + struct lan966x *lan966x = port->lan966x; + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_ts_id_lock, flags); + port->ts_id--; + lan966x->ptp_skbs--; + skb_unlink(skb, &port->tx_skbs); + spin_unlock_irqrestore(&lan966x->ptp_ts_id_lock, flags); +} + +static void lan966x_get_hwtimestamp(struct lan966x *lan966x, + struct timespec64 *ts, + u32 nsec) +{ + /* Read current PTP time to get seconds */ + unsigned long flags; + u32 curr_nsec; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) | + PTP_PIN_CFG_PIN_DOM_SET(LAN966X_PHC_PORT) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + ts->tv_sec = lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + curr_nsec = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + ts->tv_nsec = nsec; + + /* Sec has incremented since the ts was registered */ + if (curr_nsec < nsec) + ts->tv_sec--; + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); +} + +irqreturn_t lan966x_ptp_irq_handler(int irq, void *args) +{ + int budget = LAN966X_MAX_PTP_ID; + struct lan966x *lan966x = args; + + while (budget--) { + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shhwtstamps; + struct lan966x_port *port; + struct timespec64 ts; + unsigned long flags; + u32 val, id, txport; + u32 delay; + + val = lan_rd(lan966x, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retrieved */ + if (!(val & PTP_TWOSTEP_CTRL_VLD)) + break; + + WARN_ON(val & PTP_TWOSTEP_CTRL_OVFL); + + if (!(val & PTP_TWOSTEP_CTRL_STAMP_TX)) + continue; + + /* Retrieve the ts Tx port */ + txport = PTP_TWOSTEP_CTRL_STAMP_PORT_GET(val); + + /* Retrieve its associated skb */ + port = lan966x->ports[txport]; + + /* Retrieve the delay */ + delay = lan_rd(lan966x, PTP_TWOSTEP_STAMP); + delay = PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(delay); + + /* Get next timestamp from fifo, which needs to be the + * rx timestamp which represents the id of the frame + */ + lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1), + PTP_TWOSTEP_CTRL_NXT, + lan966x, PTP_TWOSTEP_CTRL); + + val = lan_rd(lan966x, PTP_TWOSTEP_CTRL); + + /* Check if a timestamp can be retried */ + if (!(val & PTP_TWOSTEP_CTRL_VLD)) + break; + + /* Read RX timestamping to get the ID */ + id = lan_rd(lan966x, PTP_TWOSTEP_STAMP); + + spin_lock_irqsave(&port->tx_skbs.lock, flags); + skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { + if (LAN966X_SKB_CB(skb)->ts_id != id) + continue; + + __skb_unlink(skb, &port->tx_skbs); + skb_match = skb; + break; + } + spin_unlock_irqrestore(&port->tx_skbs.lock, flags); + + /* Next ts */ + lan_rmw(PTP_TWOSTEP_CTRL_NXT_SET(1), + PTP_TWOSTEP_CTRL_NXT, + lan966x, PTP_TWOSTEP_CTRL); + + if (WARN_ON(!skb_match)) + continue; + + spin_lock(&lan966x->ptp_ts_id_lock); + lan966x->ptp_skbs--; + spin_unlock(&lan966x->ptp_ts_id_lock); + + /* Get the h/w timestamp */ + lan966x_get_hwtimestamp(lan966x, &ts, delay); + + /* Set the timestamp into the skb */ + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb_match, &shhwtstamps); + + dev_kfree_skb_any(skb_match); + } + + return IRQ_HANDLED; +} + +static int lan966x_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + bool neg_adj = 0; + u64 tod_inc; + u64 ref; + + if (!scaled_ppm) + return 0; + + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + + tod_inc = lan966x_ptp_get_nominal_value(); + + /* The multiplication is split in 2 separate additions because of + * overflow issues. If scaled_ppm with 16bit fractional part was bigger + * than 20ppm then we got overflow. + */ + ref = LAN966X_1PPM_FORMAT * (scaled_ppm >> 16); + ref += (LAN966X_1PPM_FORMAT * (0xffff & scaled_ppm)) >> 16; + tod_inc = neg_adj ? tod_inc - ref : tod_inc + ref; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(1 << BIT(phc->index)), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + lan_wr((u32)tod_inc & 0xFFFFFFFF, lan966x, + PTP_CLK_PER_CFG(phc->index, 0)); + lan_wr((u32)(tod_inc >> 32), lan966x, + PTP_CLK_PER_CFG(phc->index, 1)); + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + return 0; +} + +static int lan966x_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + /* Must be in IDLE mode before the time can be loaded */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + /* Set new value */ + lan_wr(PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(upper_32_bits(ts->tv_sec)), + lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN)); + lan_wr(lower_32_bits(ts->tv_sec), + lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + lan_wr(ts->tv_nsec, lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + /* Apply new values */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_LOAD) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + return 0; +} + +static int lan966x_ptp_gettime64(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + unsigned long flags; + time64_t s; + s64 ns; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_SAVE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + s = lan_rd(lan966x, PTP_TOD_SEC_MSB(TOD_ACC_PIN)); + s <<= 32; + s |= lan_rd(lan966x, PTP_TOD_SEC_LSB(TOD_ACC_PIN)); + ns = lan_rd(lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + ns &= PTP_TOD_NSEC_TOD_NSEC; + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + + /* Deal with negative values */ + if ((ns & 0xFFFFFFF0) == 0x3FFFFFF0) { + s--; + ns &= 0xf; + ns += 999999984; + } + + set_normalized_timespec64(ts, s, ns); + return 0; +} + +static int lan966x_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct lan966x_phc *phc = container_of(ptp, struct lan966x_phc, info); + struct lan966x *lan966x = phc->lan966x; + + if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { + unsigned long flags; + + spin_lock_irqsave(&lan966x->ptp_clock_lock, flags); + + /* Must be in IDLE mode before the time can be loaded */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_IDLE) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + lan_wr(PTP_TOD_NSEC_TOD_NSEC_SET(delta), + lan966x, PTP_TOD_NSEC(TOD_ACC_PIN)); + + /* Adjust time with the value of PTP_TOD_NSEC */ + lan_rmw(PTP_PIN_CFG_PIN_ACTION_SET(PTP_PIN_ACTION_DELTA) | + PTP_PIN_CFG_PIN_DOM_SET(phc->index) | + PTP_PIN_CFG_PIN_SYNC_SET(0), + PTP_PIN_CFG_PIN_ACTION | + PTP_PIN_CFG_PIN_DOM | + PTP_PIN_CFG_PIN_SYNC, + lan966x, PTP_PIN_CFG(TOD_ACC_PIN)); + + spin_unlock_irqrestore(&lan966x->ptp_clock_lock, flags); + } else { + /* Fall back using lan966x_ptp_settime64 which is not exact */ + struct timespec64 ts; + u64 now; + + lan966x_ptp_gettime64(ptp, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + lan966x_ptp_settime64(ptp, &ts); + } + + return 0; +} + +static struct ptp_clock_info lan966x_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "lan966x ptp", + .max_adj = 200000, + .gettime64 = lan966x_ptp_gettime64, + .settime64 = lan966x_ptp_settime64, + .adjtime = lan966x_ptp_adjtime, + .adjfine = lan966x_ptp_adjfine, +}; + +static int lan966x_ptp_phc_init(struct lan966x *lan966x, + int index, + struct ptp_clock_info *clock_info) +{ + struct lan966x_phc *phc = &lan966x->phc[index]; + + phc->info = *clock_info; + phc->clock = ptp_clock_register(&phc->info, lan966x->dev); + if (IS_ERR(phc->clock)) + return PTR_ERR(phc->clock); + + phc->index = index; + phc->lan966x = lan966x; + + /* PTP Rx stamping is always enabled. */ + phc->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + + return 0; +} + +int lan966x_ptp_init(struct lan966x *lan966x) +{ + u64 tod_adj = lan966x_ptp_get_nominal_value(); + struct lan966x_port *port; + int err, i; + + if (!lan966x->ptp) + return 0; + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) { + err = lan966x_ptp_phc_init(lan966x, i, &lan966x_ptp_clock_info); + if (err) + return err; + } + + spin_lock_init(&lan966x->ptp_clock_lock); + spin_lock_init(&lan966x->ptp_ts_id_lock); + mutex_init(&lan966x->ptp_lock); + + /* Disable master counters */ + lan_wr(PTP_DOM_CFG_ENA_SET(0), lan966x, PTP_DOM_CFG); + + /* Configure the nominal TOD increment per clock cycle */ + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0x7), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) { + lan_wr((u32)tod_adj & 0xFFFFFFFF, lan966x, + PTP_CLK_PER_CFG(i, 0)); + lan_wr((u32)(tod_adj >> 32), lan966x, + PTP_CLK_PER_CFG(i, 1)); + } + + lan_rmw(PTP_DOM_CFG_CLKCFG_DIS_SET(0), + PTP_DOM_CFG_CLKCFG_DIS, + lan966x, PTP_DOM_CFG); + + /* Enable master counters */ + lan_wr(PTP_DOM_CFG_ENA_SET(0x7), lan966x, PTP_DOM_CFG); + + for (i = 0; i < lan966x->num_phys_ports; i++) { + port = lan966x->ports[i]; + if (!port) + continue; + + skb_queue_head_init(&port->tx_skbs); + } + + return 0; +} + +void lan966x_ptp_deinit(struct lan966x *lan966x) +{ + struct lan966x_port *port; + int i; + + for (i = 0; i < lan966x->num_phys_ports; i++) { + port = lan966x->ports[i]; + if (!port) + continue; + + skb_queue_purge(&port->tx_skbs); + } + + for (i = 0; i < LAN966X_PHC_COUNT; ++i) + ptp_clock_unregister(lan966x->phc[i].clock); +} + +void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb, + u64 timestamp) +{ + struct skb_shared_hwtstamps *shhwtstamps; + struct lan966x_phc *phc; + struct timespec64 ts; + u64 full_ts_in_ns; + + if (!lan966x->ptp) + return; + + phc = &lan966x->phc[LAN966X_PHC_PORT]; + lan966x_ptp_gettime64(&phc->info, &ts); + + /* Drop the sub-ns precision */ + timestamp = timestamp >> 2; + if (ts.tv_nsec < timestamp) + ts.tv_sec--; + ts.tv_nsec = timestamp; + full_ts_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = full_ts_in_ns; +} diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h index 797560172aca..0c0b3e173d53 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h @@ -19,6 +19,7 @@ enum lan966x_target { TARGET_DEV = 13, TARGET_GCB = 27, TARGET_ORG = 36, + TARGET_PTP = 41, TARGET_QS = 42, TARGET_QSYS = 46, TARGET_REW = 47, @@ -298,6 +299,24 @@ enum lan966x_target { /* ANA:PORT:CPU_FWD_CFG */ #define ANA_CPU_FWD_CFG(g) __REG(TARGET_ANA, 0, 1, 28672, g, 9, 128, 96, 0, 1, 4) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA BIT(6) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_MLD_REDIR_ENA, x) +#define ANA_CPU_FWD_CFG_MLD_REDIR_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_MLD_REDIR_ENA, x) + +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA BIT(5) +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA, x) +#define ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA, x) + +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA BIT(4) +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, x) +#define ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_GET(x)\ + FIELD_GET(ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, x) + #define ANA_CPU_FWD_CFG_SRC_COPY_ENA BIT(3) #define ANA_CPU_FWD_CFG_SRC_COPY_ENA_SET(x)\ FIELD_PREP(ANA_CPU_FWD_CFG_SRC_COPY_ENA, x) @@ -559,6 +578,108 @@ enum lan966x_target { #define DEV_PCS1G_STICKY_LINK_DOWN_STICKY_GET(x)\ FIELD_GET(DEV_PCS1G_STICKY_LINK_DOWN_STICKY, x) +/* PTP:PTP_CFG:PTP_DOM_CFG */ +#define PTP_DOM_CFG __REG(TARGET_PTP, 0, 1, 512, 0, 1, 16, 12, 0, 1, 4) + +#define PTP_DOM_CFG_ENA GENMASK(11, 9) +#define PTP_DOM_CFG_ENA_SET(x)\ + FIELD_PREP(PTP_DOM_CFG_ENA, x) +#define PTP_DOM_CFG_ENA_GET(x)\ + FIELD_GET(PTP_DOM_CFG_ENA, x) + +#define PTP_DOM_CFG_CLKCFG_DIS GENMASK(2, 0) +#define PTP_DOM_CFG_CLKCFG_DIS_SET(x)\ + FIELD_PREP(PTP_DOM_CFG_CLKCFG_DIS, x) +#define PTP_DOM_CFG_CLKCFG_DIS_GET(x)\ + FIELD_GET(PTP_DOM_CFG_CLKCFG_DIS, x) + +/* PTP:PTP_TOD_DOMAINS:CLK_PER_CFG */ +#define PTP_CLK_PER_CFG(g, r) __REG(TARGET_PTP, 0, 1, 528, g, 3, 28, 0, r, 2, 4) + +/* PTP:PTP_PINS:PTP_PIN_CFG */ +#define PTP_PIN_CFG(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 0, 0, 1, 4) + +#define PTP_PIN_CFG_PIN_ACTION GENMASK(29, 27) +#define PTP_PIN_CFG_PIN_ACTION_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_ACTION, x) +#define PTP_PIN_CFG_PIN_ACTION_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_ACTION, x) + +#define PTP_PIN_CFG_PIN_SYNC GENMASK(26, 25) +#define PTP_PIN_CFG_PIN_SYNC_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_SYNC, x) +#define PTP_PIN_CFG_PIN_SYNC_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_SYNC, x) + +#define PTP_PIN_CFG_PIN_DOM GENMASK(17, 16) +#define PTP_PIN_CFG_PIN_DOM_SET(x)\ + FIELD_PREP(PTP_PIN_CFG_PIN_DOM, x) +#define PTP_PIN_CFG_PIN_DOM_GET(x)\ + FIELD_GET(PTP_PIN_CFG_PIN_DOM, x) + +/* PTP:PTP_PINS:PTP_TOD_SEC_MSB */ +#define PTP_TOD_SEC_MSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 4, 0, 1, 4) + +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB GENMASK(15, 0) +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_SET(x)\ + FIELD_PREP(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x) +#define PTP_TOD_SEC_MSB_TOD_SEC_MSB_GET(x)\ + FIELD_GET(PTP_TOD_SEC_MSB_TOD_SEC_MSB, x) + +/* PTP:PTP_PINS:PTP_TOD_SEC_LSB */ +#define PTP_TOD_SEC_LSB(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 8, 0, 1, 4) + +/* PTP:PTP_PINS:PTP_TOD_NSEC */ +#define PTP_TOD_NSEC(g) __REG(TARGET_PTP, 0, 1, 0, g, 8, 64, 12, 0, 1, 4) + +#define PTP_TOD_NSEC_TOD_NSEC GENMASK(29, 0) +#define PTP_TOD_NSEC_TOD_NSEC_SET(x)\ + FIELD_PREP(PTP_TOD_NSEC_TOD_NSEC, x) +#define PTP_TOD_NSEC_TOD_NSEC_GET(x)\ + FIELD_GET(PTP_TOD_NSEC_TOD_NSEC, x) + +/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_CTRL */ +#define PTP_TWOSTEP_CTRL __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 0, 0, 1, 4) + +#define PTP_TWOSTEP_CTRL_NXT BIT(11) +#define PTP_TWOSTEP_CTRL_NXT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_NXT, x) +#define PTP_TWOSTEP_CTRL_NXT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_NXT, x) + +#define PTP_TWOSTEP_CTRL_VLD BIT(10) +#define PTP_TWOSTEP_CTRL_VLD_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_VLD, x) +#define PTP_TWOSTEP_CTRL_VLD_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_VLD, x) + +#define PTP_TWOSTEP_CTRL_STAMP_TX BIT(9) +#define PTP_TWOSTEP_CTRL_STAMP_TX_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_TX, x) +#define PTP_TWOSTEP_CTRL_STAMP_TX_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_TX, x) + +#define PTP_TWOSTEP_CTRL_STAMP_PORT GENMASK(8, 1) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_STAMP_PORT, x) +#define PTP_TWOSTEP_CTRL_STAMP_PORT_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_STAMP_PORT, x) + +#define PTP_TWOSTEP_CTRL_OVFL BIT(0) +#define PTP_TWOSTEP_CTRL_OVFL_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_CTRL_OVFL, x) +#define PTP_TWOSTEP_CTRL_OVFL_GET(x)\ + FIELD_GET(PTP_TWOSTEP_CTRL_OVFL, x) + +/* PTP:PTP_TS_FIFO:PTP_TWOSTEP_STAMP */ +#define PTP_TWOSTEP_STAMP __REG(TARGET_PTP, 0, 1, 612, 0, 1, 12, 4, 0, 1, 4) + +#define PTP_TWOSTEP_STAMP_STAMP_NSEC GENMASK(31, 2) +#define PTP_TWOSTEP_STAMP_STAMP_NSEC_SET(x)\ + FIELD_PREP(PTP_TWOSTEP_STAMP_STAMP_NSEC, x) +#define PTP_TWOSTEP_STAMP_STAMP_NSEC_GET(x)\ + FIELD_GET(PTP_TWOSTEP_STAMP_STAMP_NSEC, x) + /* DEVCPU_QS:XTR:XTR_GRP_CFG */ #define QS_XTR_GRP_CFG(r) __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 0, r, 2, 4) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c index 7de55f6a4da8..9fce865287e7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_switchdev.c @@ -9,6 +9,37 @@ static struct notifier_block lan966x_netdevice_nb __read_mostly; static struct notifier_block lan966x_switchdev_nb __read_mostly; static struct notifier_block lan966x_switchdev_blocking_nb __read_mostly; +static void lan966x_port_set_mcast_ip_flood(struct lan966x_port *port, + u32 pgid_ip) +{ + struct lan966x *lan966x = port->lan966x; + u32 flood_mask_ip; + + flood_mask_ip = lan_rd(lan966x, ANA_PGID(pgid_ip)); + flood_mask_ip = ANA_PGID_PGID_GET(flood_mask_ip); + + /* If mcast snooping is not enabled then use mcast flood mask + * to decide to enable multicast flooding or not. + */ + if (!port->mcast_ena) { + u32 flood_mask; + + flood_mask = lan_rd(lan966x, ANA_PGID(PGID_MC)); + flood_mask = ANA_PGID_PGID_GET(flood_mask); + + if (flood_mask & BIT(port->chip_port)) + flood_mask_ip |= BIT(port->chip_port); + else + flood_mask_ip &= ~BIT(port->chip_port); + } else { + flood_mask_ip &= ~BIT(port->chip_port); + } + + lan_rmw(ANA_PGID_PGID_SET(flood_mask_ip), + ANA_PGID_PGID, + lan966x, ANA_PGID(pgid_ip)); +} + static void lan966x_port_set_mcast_flood(struct lan966x_port *port, bool enabled) { @@ -23,6 +54,11 @@ static void lan966x_port_set_mcast_flood(struct lan966x_port *port, lan_rmw(ANA_PGID_PGID_SET(val), ANA_PGID_PGID, port->lan966x, ANA_PGID(PGID_MC)); + + if (!port->mcast_ena) { + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV4); + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV6); + } } static void lan966x_port_set_ucast_flood(struct lan966x_port *port, @@ -144,6 +180,28 @@ static void lan966x_port_ageing_set(struct lan966x_port *port, lan966x_mac_set_ageing(port->lan966x, ageing_time); } +static void lan966x_port_mc_set(struct lan966x_port *port, bool mcast_ena) +{ + struct lan966x *lan966x = port->lan966x; + + port->mcast_ena = mcast_ena; + if (mcast_ena) + lan966x_mdb_restore_entries(lan966x); + else + lan966x_mdb_clear_entries(lan966x); + + lan_rmw(ANA_CPU_FWD_CFG_IGMP_REDIR_ENA_SET(mcast_ena) | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA_SET(mcast_ena) | + ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA_SET(mcast_ena), + ANA_CPU_FWD_CFG_IGMP_REDIR_ENA | + ANA_CPU_FWD_CFG_MLD_REDIR_ENA | + ANA_CPU_FWD_CFG_IPMC_CTRL_COPY_ENA, + lan966x, ANA_CPU_FWD_CFG(port->chip_port)); + + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV4); + lan966x_port_set_mcast_ip_flood(port, PGID_MCIPV6); +} + static int lan966x_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) @@ -171,6 +229,9 @@ static int lan966x_port_attr_set(struct net_device *dev, const void *ctx, lan966x_vlan_port_set_vlan_aware(port, attr->u.vlan_filtering); lan966x_vlan_port_apply(port); break; + case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED: + lan966x_port_mc_set(port, !attr->u.mc_disabled); + break; default: err = -EOPNOTSUPP; break; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 16266275dd36..394de85d360d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -291,7 +291,6 @@ static int sparx5_create_port(struct sparx5 *sparx5, /* Create a phylink for PHY management. Also handles SFPs */ spx5_port->phylink_config.dev = &spx5_port->ndev->dev; spx5_port->phylink_config.type = PHYLINK_NETDEV; - spx5_port->phylink_config.pcs_poll = true; spx5_port->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD | MAC_5000FD | MAC_10000FD | MAC_25000FD; @@ -328,7 +327,6 @@ static int sparx5_create_port(struct sparx5 *sparx5, return PTR_ERR(phylink); spx5_port->phylink = phylink; - phylink_set_pcs(phylink, &spx5_port->phylink_pcs); return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index dc7e5ea6ec15..148d431fcde4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -145,9 +145,9 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) skb_put(skb, byte_cnt - ETH_FCS_LEN); eth_skb_pad(skb); skb->protocol = eth_type_trans(skb, netdev); - netif_rx(skb); netdev->stats.rx_bytes += skb->len; netdev->stats.rx_packets++; + netif_rx(skb); } static int sparx5_inject(struct sparx5 *sparx5, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 8ba33bc1a001..830da0e5ff27 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -26,6 +26,15 @@ static bool port_conf_has_changed(struct sparx5_port_config *a, struct sparx5_po return false; } +static struct phylink_pcs * +sparx5_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct sparx5_port *port = netdev_priv(to_net_dev(config->dev)); + + return &port->phylink_pcs; +} + static void sparx5_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -130,6 +139,7 @@ const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { const struct phylink_mac_ops sparx5_phylink_mac_ops = { .validate = phylink_generic_validate, + .mac_select_pcs = sparx5_phylink_mac_select_pcs, .mac_config = sparx5_phylink_mac_config, .mac_link_down = sparx5_phylink_mac_link_down, .mac_link_up = sparx5_phylink_mac_link_up, diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 636dfef24a6c..49b85ca578b0 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -663,7 +663,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_context *gc = gd->gdma_context; struct hw_channel_context *hwc; u32 length = gmi->length; - u32 req_msg_size; + size_t req_msg_size; int err; int i; @@ -674,7 +674,7 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, return -EINVAL; hwc = gc->hwc.driver_data; - req_msg_size = sizeof(*req) + num_page * sizeof(u64); + req_msg_size = struct_size(req, page_addr_list, num_page); if (req_msg_size > hwc->max_req_msg_size) return -EINVAL; diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h index 9a12607fb511..d36405af9432 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/drivers/net/ethernet/microsoft/mana/mana.h @@ -48,7 +48,15 @@ enum TRI_STATE { #define MAX_PORTS_IN_MANA_DEV 256 -struct mana_stats { +struct mana_stats_rx { + u64 packets; + u64 bytes; + u64 xdp_drop; + u64 xdp_tx; + struct u64_stats_sync syncp; +}; + +struct mana_stats_tx { u64 packets; u64 bytes; struct u64_stats_sync syncp; @@ -76,7 +84,7 @@ struct mana_txq { atomic_t pending_sends; - struct mana_stats stats; + struct mana_stats_tx stats; }; /* skb data and frags dma mappings */ @@ -298,10 +306,11 @@ struct mana_rxq { u32 buf_index; - struct mana_stats stats; + struct mana_stats_rx stats; struct bpf_prog __rcu *bpf_prog; struct xdp_rxq_info xdp_rxq; + struct page *xdp_save_page; /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 498d0f999275..b7d3ba1b4d17 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -136,7 +136,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) bool ipv4 = false, ipv6 = false; struct mana_tx_package pkg = {}; struct netdev_queue *net_txq; - struct mana_stats *tx_stats; + struct mana_stats_tx *tx_stats; struct gdma_queue *gdma_sq; unsigned int csum_type; struct mana_txq *txq; @@ -299,7 +299,8 @@ static void mana_get_stats64(struct net_device *ndev, { struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; - struct mana_stats *stats; + struct mana_stats_rx *rx_stats; + struct mana_stats_tx *tx_stats; unsigned int start; u64 packets, bytes; int q; @@ -310,26 +311,26 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); for (q = 0; q < num_queues; q++) { - stats = &apc->rxqs[q]->stats; + rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); st->rx_packets += packets; st->rx_bytes += bytes; } for (q = 0; q < num_queues; q++) { - stats = &apc->tx_qp[q].txq.stats; + tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); st->tx_packets += packets; st->tx_bytes += bytes; @@ -986,7 +987,7 @@ static struct sk_buff *mana_build_skb(void *buf_va, uint pkt_len, static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq) { - struct mana_stats *rx_stats = &rxq->stats; + struct mana_stats_rx *rx_stats = &rxq->stats; struct net_device *ndev = rxq->ndev; uint pkt_len = cqe->ppi[0].pkt_len; u16 rxq_idx = rxq->rxq_idx; @@ -1007,7 +1008,7 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, act = mana_run_xdp(ndev, rxq, &xdp, buf_va, pkt_len); if (act != XDP_PASS && act != XDP_TX) - goto drop; + goto drop_xdp; skb = mana_build_skb(buf_va, pkt_len, &xdp); @@ -1034,6 +1035,14 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, skb_set_hash(skb, hash_value, PKT_HASH_TYPE_L3); } + u64_stats_update_begin(&rx_stats->syncp); + rx_stats->packets++; + rx_stats->bytes += pkt_len; + + if (act == XDP_TX) + rx_stats->xdp_tx++; + u64_stats_update_end(&rx_stats->syncp); + if (act == XDP_TX) { skb_set_queue_mapping(skb, rxq_idx); mana_xdp_tx(skb, ndev); @@ -1042,15 +1051,19 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, napi_gro_receive(napi, skb); + return; + +drop_xdp: u64_stats_update_begin(&rx_stats->syncp); - rx_stats->packets++; - rx_stats->bytes += pkt_len; + rx_stats->xdp_drop++; u64_stats_update_end(&rx_stats->syncp); - return; drop: - free_page((unsigned long)buf_va); + WARN_ON_ONCE(rxq->xdp_save_page); + rxq->xdp_save_page = virt_to_page(buf_va); + ++ndev->stats.rx_dropped; + return; } @@ -1072,8 +1085,10 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, break; case CQE_RX_TRUNCATED: - netdev_err(ndev, "Dropped a truncated packet\n"); - return; + ++ndev->stats.rx_dropped; + rxbuf_oob = &rxq->rx_oobs[rxq->buf_index]; + netdev_warn_once(ndev, "Dropped a truncated packet\n"); + goto drop; case CQE_RX_COALESCED_4: netdev_err(ndev, "RX coalescing is unsupported\n"); @@ -1089,9 +1104,6 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, return; } - if (oob->cqe_hdr.cqe_type != CQE_RX_OKAY) - return; - pktlen = oob->ppi[0].pkt_len; if (pktlen == 0) { @@ -1105,7 +1117,13 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr]; WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1); - new_page = alloc_page(GFP_ATOMIC); + /* Reuse XDP dropped page if available */ + if (rxq->xdp_save_page) { + new_page = rxq->xdp_save_page; + rxq->xdp_save_page = NULL; + } else { + new_page = alloc_page(GFP_ATOMIC); + } if (new_page) { da = dma_map_page(dev, new_page, XDP_PACKET_HEADROOM, rxq->datasize, @@ -1135,6 +1153,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, mana_rx_skb(old_buf, oob, rxq); +drop: mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu); mana_post_pkt_rxq(rxq); @@ -1392,6 +1411,9 @@ static void mana_destroy_rxq(struct mana_port_context *apc, mana_deinit_cq(apc, &rxq->rx_cq); + if (rxq->xdp_save_page) + __free_page(rxq->xdp_save_page); + for (i = 0; i < rxq->num_rx_buf; i++) { rx_oob = &rxq->rx_oobs[i]; diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index c3c81ae3fafd..e13f2453eabb 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -23,7 +23,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset) if (stringset != ETH_SS_STATS) return -EINVAL; - return ARRAY_SIZE(mana_eth_stats) + num_queues * 4; + return ARRAY_SIZE(mana_eth_stats) + num_queues * 6; } static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) @@ -46,6 +46,10 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; sprintf(p, "rx_%d_bytes", i); p += ETH_GSTRING_LEN; + sprintf(p, "rx_%d_xdp_drop", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_%d_xdp_tx", i); + p += ETH_GSTRING_LEN; } for (i = 0; i < num_queues; i++) { @@ -62,9 +66,12 @@ static void mana_get_ethtool_stats(struct net_device *ndev, struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; void *eth_stats = &apc->eth_stats; - struct mana_stats *stats; + struct mana_stats_rx *rx_stats; + struct mana_stats_tx *tx_stats; unsigned int start; u64 packets, bytes; + u64 xdp_drop; + u64 xdp_tx; int q, i = 0; if (!apc->port_is_up) @@ -74,26 +81,30 @@ static void mana_get_ethtool_stats(struct net_device *ndev, data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); for (q = 0; q < num_queues; q++) { - stats = &apc->rxqs[q]->stats; + rx_stats = &apc->rxqs[q]->stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&rx_stats->syncp); + packets = rx_stats->packets; + bytes = rx_stats->bytes; + xdp_drop = rx_stats->xdp_drop; + xdp_tx = rx_stats->xdp_tx; + } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; + data[i++] = xdp_drop; + data[i++] = xdp_tx; } for (q = 0; q < num_queues; q++) { - stats = &apc->tx_qp[q].txq.stats; + tx_stats = &apc->tx_qp[q].txq.stats; do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - packets = stats->packets; - bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + start = u64_stats_fetch_begin_irq(&tx_stats->syncp); + packets = tx_stats->packets; + bytes = tx_stats->bytes; + } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index dfb4468fe287..ce865e619568 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -356,7 +356,7 @@ __nfp_tun_add_route_to_cache(struct list_head *route_list, return 0; } - entry = kmalloc(sizeof(*entry) + add_len, GFP_ATOMIC); + entry = kmalloc(struct_size(entry, ip_add, add_len), GFP_ATOMIC); if (!entry) { spin_unlock_bh(list_lock); return -ENOMEM; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index 3d61a8cb60b0..50007cc5b580 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -1,8 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ /* Copyright (C) 2015-2018 Netronome Systems, Inc. */ -/* - * nfp_net_ctrl.h +/* nfp_net_ctrl.h * Netronome network device driver: Control BAR layout * Authors: Jakub Kicinski <jakub.kicinski@netronome.com> * Jason McMullan <jason.mcmullan@netronome.com> @@ -15,30 +14,24 @@ #include <linux/types.h> -/** - * Configuration BAR size. +/* Configuration BAR size. * * The configuration BAR is 8K in size, but due to * THB-350, 32k needs to be reserved. */ #define NFP_NET_CFG_BAR_SZ (32 * 1024) -/** - * Offset in Freelist buffer where packet starts on RX - */ +/* Offset in Freelist buffer where packet starts on RX */ #define NFP_NET_RX_OFFSET 32 -/** - * LSO parameters +/* LSO parameters * %NFP_NET_LSO_MAX_HDR_SZ: Maximum header size supported for LSO frames * %NFP_NET_LSO_MAX_SEGS: Maximum number of segments LSO frame can produce */ #define NFP_NET_LSO_MAX_HDR_SZ 255 #define NFP_NET_LSO_MAX_SEGS 64 -/** - * Prepend field types - */ +/* Prepend field types */ #define NFP_NET_META_FIELD_SIZE 4 #define NFP_NET_META_HASH 1 /* next field carries hash type */ #define NFP_NET_META_MARK 2 @@ -49,9 +42,7 @@ #define NFP_META_PORT_ID_CTRL ~0U -/** - * Hash type pre-pended when a RSS hash was computed - */ +/* Hash type pre-pended when a RSS hash was computed */ #define NFP_NET_RSS_NONE 0 #define NFP_NET_RSS_IPV4 1 #define NFP_NET_RSS_IPV6 2 @@ -63,16 +54,14 @@ #define NFP_NET_RSS_IPV6_UDP 8 #define NFP_NET_RSS_IPV6_EX_UDP 9 -/** - * Ring counts +/* Ring counts * %NFP_NET_TXR_MAX: Maximum number of TX rings * %NFP_NET_RXR_MAX: Maximum number of RX rings */ #define NFP_NET_TXR_MAX 64 #define NFP_NET_RXR_MAX 64 -/** - * Read/Write config words (0x0000 - 0x002c) +/* Read/Write config words (0x0000 - 0x002c) * %NFP_NET_CFG_CTRL: Global control * %NFP_NET_CFG_UPDATE: Indicate which fields are updated * %NFP_NET_CFG_TXRS_ENABLE: Bitmask of enabled TX rings @@ -147,8 +136,7 @@ #define NFP_NET_CFG_LSC 0x0020 #define NFP_NET_CFG_MACADDR 0x0024 -/** - * Read-only words (0x0030 - 0x0050): +/* Read-only words (0x0030 - 0x0050): * %NFP_NET_CFG_VERSION: Firmware version number * %NFP_NET_CFG_STS: Status * %NFP_NET_CFG_CAP: Capabilities (same bits as %NFP_NET_CFG_CTRL) @@ -193,36 +181,31 @@ #define NFP_NET_CFG_START_TXQ 0x0048 #define NFP_NET_CFG_START_RXQ 0x004c -/** - * Prepend configuration +/* Prepend configuration */ #define NFP_NET_CFG_RX_OFFSET 0x0050 #define NFP_NET_CFG_RX_OFFSET_DYNAMIC 0 /* Prepend mode */ -/** - * RSS capabilities +/* RSS capabilities * %NFP_NET_CFG_RSS_CAP_HFUNC: supported hash functions (same bits as * %NFP_NET_CFG_RSS_HFUNC) */ #define NFP_NET_CFG_RSS_CAP 0x0054 #define NFP_NET_CFG_RSS_CAP_HFUNC 0xff000000 -/** - * TLV area start +/* TLV area start * %NFP_NET_CFG_TLV_BASE: start anchor of the TLV area */ #define NFP_NET_CFG_TLV_BASE 0x0058 -/** - * VXLAN/UDP encap configuration +/* VXLAN/UDP encap configuration * %NFP_NET_CFG_VXLAN_PORT: Base address of table of tunnels' UDP dst ports * %NFP_NET_CFG_VXLAN_SZ: Size of the UDP port table in bytes */ #define NFP_NET_CFG_VXLAN_PORT 0x0060 #define NFP_NET_CFG_VXLAN_SZ 0x0008 -/** - * BPF section +/* BPF section * %NFP_NET_CFG_BPF_ABI: BPF ABI version * %NFP_NET_CFG_BPF_CAP: BPF capabilities * %NFP_NET_CFG_BPF_MAX_LEN: Maximum size of JITed BPF code in bytes @@ -247,14 +230,12 @@ #define NFP_NET_CFG_BPF_CFG_MASK 7ULL #define NFP_NET_CFG_BPF_ADDR_MASK (~NFP_NET_CFG_BPF_CFG_MASK) -/** - * 40B reserved for future use (0x0098 - 0x00c0) +/* 40B reserved for future use (0x0098 - 0x00c0) */ #define NFP_NET_CFG_RESERVED 0x0098 #define NFP_NET_CFG_RESERVED_SZ 0x0028 -/** - * RSS configuration (0x0100 - 0x01ac): +/* RSS configuration (0x0100 - 0x01ac): * Used only when NFP_NET_CFG_CTRL_RSS is enabled * %NFP_NET_CFG_RSS_CFG: RSS configuration word * %NFP_NET_CFG_RSS_KEY: RSS "secret" key @@ -281,8 +262,7 @@ NFP_NET_CFG_RSS_KEY_SZ) #define NFP_NET_CFG_RSS_ITBL_SZ 0x80 -/** - * TX ring configuration (0x200 - 0x800) +/* TX ring configuration (0x200 - 0x800) * %NFP_NET_CFG_TXR_BASE: Base offset for TX ring configuration * %NFP_NET_CFG_TXR_ADDR: Per TX ring DMA address (8B entries) * %NFP_NET_CFG_TXR_WB_ADDR: Per TX ring write back DMA address (8B entries) @@ -301,8 +281,7 @@ #define NFP_NET_CFG_TXR_IRQ_MOD(_x) (NFP_NET_CFG_TXR_BASE + 0x500 + \ ((_x) * 0x4)) -/** - * RX ring configuration (0x0800 - 0x0c00) +/* RX ring configuration (0x0800 - 0x0c00) * %NFP_NET_CFG_RXR_BASE: Base offset for RX ring configuration * %NFP_NET_CFG_RXR_ADDR: Per RX ring DMA address (8B entries) * %NFP_NET_CFG_RXR_SZ: Per RX ring ring size (1B entries) @@ -318,8 +297,7 @@ #define NFP_NET_CFG_RXR_IRQ_MOD(_x) (NFP_NET_CFG_RXR_BASE + 0x300 + \ ((_x) * 0x4)) -/** - * Interrupt Control/Cause registers (0x0c00 - 0x0d00) +/* Interrupt Control/Cause registers (0x0c00 - 0x0d00) * These registers are only used when MSI-X auto-masking is not * enabled (%NFP_NET_CFG_CTRL_MSIXAUTO not set). The array is index * by MSI-X entry and are 1B in size. If an entry is zero, the @@ -334,8 +312,7 @@ #define NFP_NET_CFG_ICR_RXTX 0x1 #define NFP_NET_CFG_ICR_LSC 0x2 -/** - * General device stats (0x0d00 - 0x0d90) +/* General device stats (0x0d00 - 0x0d90) * all counters are 64bit. */ #define NFP_NET_CFG_STATS_BASE 0x0d00 @@ -368,8 +345,7 @@ #define NFP_NET_CFG_STATS_APP3_FRAMES (NFP_NET_CFG_STATS_BASE + 0xc0) #define NFP_NET_CFG_STATS_APP3_BYTES (NFP_NET_CFG_STATS_BASE + 0xc8) -/** - * Per ring stats (0x1000 - 0x1800) +/* Per ring stats (0x1000 - 0x1800) * options, 64bit per entry * %NFP_NET_CFG_TXR_STATS: TX ring statistics (Packet and Byte count) * %NFP_NET_CFG_RXR_STATS: RX ring statistics (Packet and Byte count) @@ -381,8 +357,7 @@ #define NFP_NET_CFG_RXR_STATS(_x) (NFP_NET_CFG_RXR_STATS_BASE + \ ((_x) * 0x10)) -/** - * General use mailbox area (0x1800 - 0x19ff) +/* General use mailbox area (0x1800 - 0x19ff) * 4B used for update command and 4B return code * followed by a max of 504B of variable length value */ @@ -399,8 +374,7 @@ #define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET 5 #define NFP_NET_CFG_MBOX_CMD_TLV_CMSG 6 -/** - * VLAN filtering using general use mailbox +/* VLAN filtering using general use mailbox * %NFP_NET_CFG_VLAN_FILTER: Base address of VLAN filter mailbox * %NFP_NET_CFG_VLAN_FILTER_VID: VLAN ID to filter * %NFP_NET_CFG_VLAN_FILTER_PROTO: VLAN proto to filter @@ -411,8 +385,7 @@ #define NFP_NET_CFG_VLAN_FILTER_PROTO (NFP_NET_CFG_VLAN_FILTER + 2) #define NFP_NET_CFG_VLAN_FILTER_SZ 0x0004 -/** - * TLV capabilities +/* TLV capabilities * %NFP_NET_CFG_TLV_TYPE: Offset of type within the TLV * %NFP_NET_CFG_TLV_TYPE_REQUIRED: Driver must be able to parse the TLV * %NFP_NET_CFG_TLV_LENGTH: Offset of length within the TLV @@ -438,8 +411,7 @@ #define NFP_NET_CFG_TLV_HEADER_TYPE 0x7fff0000 #define NFP_NET_CFG_TLV_HEADER_LENGTH 0x0000ffff -/** - * Capability TLV types +/* Capability TLV types * * %NFP_NET_CFG_TLV_TYPE_UNKNOWN: * Special TLV type to catch bugs, should never be encountered. Drivers should @@ -512,8 +484,7 @@ struct device; -/** - * struct nfp_net_tlv_caps - parsed control BAR TLV capabilities +/* struct nfp_net_tlv_caps - parsed control BAR TLV capabilities * @me_freq_mhz: ME clock_freq (MHz) * @mbox_off: vNIC mailbox area offset * @mbox_len: vNIC mailbox area length diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h index a3db0cbf6425..786be58a907e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h @@ -4,8 +4,7 @@ #ifndef _NFP_NET_SRIOV_H_ #define _NFP_NET_SRIOV_H_ -/** - * SRIOV VF configuration. +/* SRIOV VF configuration. * The configuration memory begins with a mailbox region for communication with * the firmware followed by individual VF entries. */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index ae4da189d955..df316b9e891d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -132,8 +132,7 @@ void nfp_devlink_port_unregister(struct nfp_port *port); void nfp_devlink_port_type_eth_set(struct nfp_port *port); void nfp_devlink_port_type_clear(struct nfp_port *port); -/** - * Mac stats (0x0000 - 0x0200) +/* Mac stats (0x0000 - 0x0200) * all counters are 64bit. */ #define NFP_MAC_STATS_BASE 0x0000 diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 10e7d8b21c46..730fea214b8a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -513,7 +513,7 @@ nfp_nsp_command_buf_dma_sg(struct nfp_nsp *nsp, dma_size = BIT_ULL(dma_order); nseg = DIV_ROUND_UP(max_size, chunk_size); - chunks = kzalloc(array_size(sizeof(*chunks), nseg), GFP_KERNEL); + chunks = kcalloc(nseg, sizeof(*chunks), GFP_KERNEL); if (!chunks) return -ENOMEM; diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index 5e25411ff02f..602f4d45d529 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -18,7 +18,7 @@ struct ionic_lif; #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 #define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 -#define DEVCMD_TIMEOUT 10 +#define DEVCMD_TIMEOUT 5 #define IONIC_ADMINQ_TIME_SLICE msecs_to_jiffies(100) #define IONIC_PHC_UPDATE_NS 10000000000 /* 10s in nanoseconds */ @@ -78,6 +78,9 @@ void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, u8 status, int err); int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); +int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_wait); +void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status, + int err); int ionic_set_dma_mask(struct ionic *ionic); int ionic_setup(struct ionic *ionic); @@ -89,4 +92,6 @@ int ionic_port_identify(struct ionic *ionic); int ionic_port_init(struct ionic *ionic); int ionic_port_reset(struct ionic *ionic); +const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr); + #endif /* _IONIC_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index 7e296fa71b36..6ffc62c41165 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -109,8 +109,8 @@ void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page) static void ionic_vf_dealloc_locked(struct ionic *ionic) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR }; struct ionic_vf *v; - dma_addr_t dma = 0; int i; if (!ionic->vfs) @@ -120,9 +120,8 @@ static void ionic_vf_dealloc_locked(struct ionic *ionic) v = &ionic->vfs[i]; if (v->stats_pa) { - (void)ionic_set_vf_config(ionic, i, - IONIC_VF_ATTR_STATSADDR, - (u8 *)&dma); + vfc.stats_pa = 0; + (void)ionic_set_vf_config(ionic, i, &vfc); dma_unmap_single(ionic->dev, v->stats_pa, sizeof(v->stats), DMA_FROM_DEVICE); v->stats_pa = 0; @@ -143,6 +142,7 @@ static void ionic_vf_dealloc(struct ionic *ionic) static int ionic_vf_alloc(struct ionic *ionic, int num_vfs) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_STATSADDR }; struct ionic_vf *v; int err = 0; int i; @@ -166,9 +166,10 @@ static int ionic_vf_alloc(struct ionic *ionic, int num_vfs) } ionic->num_vfs++; + /* ignore failures from older FW, we just won't get stats */ - (void)ionic_set_vf_config(ionic, i, IONIC_VF_ATTR_STATSADDR, - (u8 *)&v->stats_pa); + vfc.stats_pa = cpu_to_le64(v->stats_pa); + (void)ionic_set_vf_config(ionic, i, &vfc); } out: @@ -331,6 +332,9 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_deregister_lifs; } + mod_timer(&ionic->watchdog_timer, + round_jiffies(jiffies + ionic->watchdog_period)); + return 0; err_out_deregister_lifs: @@ -348,7 +352,6 @@ err_out_port_reset: err_out_reset: ionic_reset(ionic); err_out_teardown: - del_timer_sync(&ionic->watchdog_timer); pci_clear_master(pdev); /* Don't fail the probe for these errors, keep * the hw interface around for inspection diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index d57e80d44c9d..52a1b5cfd8e7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -33,7 +33,8 @@ static void ionic_watchdog_cb(struct timer_list *t) !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) ionic_link_status_check_request(lif, CAN_NOT_SLEEP); - if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state)) { + if (test_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state) && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) { netdev_err(lif->netdev, "rxmode change dropped\n"); @@ -46,6 +47,24 @@ static void ionic_watchdog_cb(struct timer_list *t) } } +static void ionic_watchdog_init(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + + timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0); + ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ; + + /* set times to ensure the first check will proceed */ + atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ); + idev->last_hb_time = jiffies - 2 * ionic->watchdog_period; + /* init as ready, so no transition if the first check succeeds */ + idev->last_fw_hb = 0; + idev->fw_hb_ready = true; + idev->fw_status_ready = true; + idev->fw_generation = IONIC_FW_STS_F_GENERATION & + ioread8(&idev->dev_info_regs->fw_status); +} + void ionic_init_devinfo(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; @@ -109,21 +128,7 @@ int ionic_dev_setup(struct ionic *ionic) return -EFAULT; } - timer_setup(&ionic->watchdog_timer, ionic_watchdog_cb, 0); - ionic->watchdog_period = IONIC_WATCHDOG_SECS * HZ; - - /* set times to ensure the first check will proceed */ - atomic_long_set(&idev->last_check_time, jiffies - 2 * HZ); - idev->last_hb_time = jiffies - 2 * ionic->watchdog_period; - /* init as ready, so no transition if the first check succeeds */ - idev->last_fw_hb = 0; - idev->fw_hb_ready = true; - idev->fw_status_ready = true; - idev->fw_generation = IONIC_FW_STS_F_GENERATION & - ioread8(&idev->dev_info_regs->fw_status); - - mod_timer(&ionic->watchdog_timer, - round_jiffies(jiffies + ionic->watchdog_period)); + ionic_watchdog_init(ionic); idev->db_pages = bar->vaddr; idev->phy_db_pages = bar->bus_addr; @@ -132,10 +137,21 @@ int ionic_dev_setup(struct ionic *ionic) } /* Devcmd Interface */ +bool ionic_is_fw_running(struct ionic_dev *idev) +{ + u8 fw_status = ioread8(&idev->dev_info_regs->fw_status); + + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + return (fw_status != 0xff) && (fw_status & IONIC_FW_STS_F_RUNNING); +} + int ionic_heartbeat_check(struct ionic *ionic) { - struct ionic_dev *idev = &ionic->idev; unsigned long check_time, last_check_time; + struct ionic_dev *idev = &ionic->idev; + struct ionic_lif *lif = ionic->lif; bool fw_status_ready = true; bool fw_hb_ready; u8 fw_generation; @@ -155,13 +171,10 @@ do_check_time: goto do_check_time; } - /* firmware is useful only if the running bit is set and - * fw_status != 0xff (bad PCI read) - * If fw_status is not ready don't bother with the generation. - */ fw_status = ioread8(&idev->dev_info_regs->fw_status); - if (fw_status == 0xff || !(fw_status & IONIC_FW_STS_F_RUNNING)) { + /* If fw_status is not ready don't bother with the generation */ + if (!ionic_is_fw_running(idev)) { fw_status_ready = false; } else { fw_generation = fw_status & IONIC_FW_STS_F_GENERATION; @@ -176,31 +189,41 @@ do_check_time: * the down, the next watchdog will see the fw is up * and the generation value stable, so will trigger * the fw-up activity. + * + * If we had already moved to FW_RESET from a RESET event, + * it is possible that we never saw the fw_status go to 0, + * so we fake the current idev->fw_status_ready here to + * force the transition and get FW up again. */ - fw_status_ready = false; + if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) + idev->fw_status_ready = false; /* go to running */ + else + fw_status_ready = false; /* go to down */ } } /* is this a transition? */ if (fw_status_ready != idev->fw_status_ready) { - struct ionic_lif *lif = ionic->lif; bool trigger = false; - idev->fw_status_ready = fw_status_ready; - - if (!fw_status_ready) { - dev_info(ionic->dev, "FW stopped %u\n", fw_status); - if (lif && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) - trigger = true; - } else { - dev_info(ionic->dev, "FW running %u\n", fw_status); - if (lif && test_bit(IONIC_LIF_F_FW_RESET, lif->state)) - trigger = true; + if (!fw_status_ready && lif && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + dev_info(ionic->dev, "FW stopped 0x%02x\n", fw_status); + trigger = true; + + } else if (fw_status_ready && lif && + test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + dev_info(ionic->dev, "FW running 0x%02x\n", fw_status); + trigger = true; } if (trigger) { struct ionic_deferred_work *work; + idev->fw_status_ready = fw_status_ready; + work = kzalloc(sizeof(*work), GFP_ATOMIC); if (work) { work->type = IONIC_DW_TYPE_LIF_RESET; @@ -210,12 +233,14 @@ do_check_time: } } - if (!fw_status_ready) + if (!idev->fw_status_ready) return -ENXIO; - /* wait at least one watchdog period since the last heartbeat */ + /* Because of some variability in the actual FW heartbeat, we + * wait longer than the DEVCMD_TIMEOUT before checking again. + */ last_check_time = idev->last_hb_time; - if (time_before(check_time, last_check_time + ionic->watchdog_period)) + if (time_before(check_time, last_check_time + DEVCMD_TIMEOUT * 2 * HZ)) return 0; fw_hb = ioread32(&idev->dev_info_regs->fw_heartbeat); @@ -392,60 +417,63 @@ void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type) } /* VF commands */ -int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data) +int ionic_set_vf_config(struct ionic *ionic, int vf, + struct ionic_vf_setattr_cmd *vfc) { union ionic_dev_cmd cmd = { .vf_setattr.opcode = IONIC_CMD_VF_SETATTR, - .vf_setattr.attr = attr, + .vf_setattr.attr = vfc->attr, .vf_setattr.vf_index = cpu_to_le16(vf), }; int err; + memcpy(cmd.vf_setattr.pad, vfc->pad, sizeof(vfc->pad)); + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_go(&ionic->idev, &cmd); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, + struct ionic_vf_getattr_comp *comp) +{ + union ionic_dev_cmd cmd = { + .vf_getattr.opcode = IONIC_CMD_VF_GETATTR, + .vf_getattr.attr = attr, + .vf_getattr.vf_index = cpu_to_le16(vf), + }; + int err; + + if (vf >= ionic->num_vfs) + return -EINVAL; + switch (attr) { case IONIC_VF_ATTR_SPOOFCHK: - cmd.vf_setattr.spoofchk = *data; - dev_dbg(ionic->dev, "%s: vf %d spoof %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_TRUST: - cmd.vf_setattr.trust = *data; - dev_dbg(ionic->dev, "%s: vf %d trust %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_LINKSTATE: - cmd.vf_setattr.linkstate = *data; - dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n", - __func__, vf, *data); - break; case IONIC_VF_ATTR_MAC: - ether_addr_copy(cmd.vf_setattr.macaddr, data); - dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n", - __func__, vf, data); - break; case IONIC_VF_ATTR_VLAN: - cmd.vf_setattr.vlanid = cpu_to_le16(*(u16 *)data); - dev_dbg(ionic->dev, "%s: vf %d vlan %d\n", - __func__, vf, *(u16 *)data); - break; case IONIC_VF_ATTR_RATE: - cmd.vf_setattr.maxrate = cpu_to_le32(*(u32 *)data); - dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n", - __func__, vf, *(u32 *)data); break; case IONIC_VF_ATTR_STATSADDR: - cmd.vf_setattr.stats_pa = cpu_to_le64(*(u64 *)data); - dev_dbg(ionic->dev, "%s: vf %d stats_pa 0x%08llx\n", - __func__, vf, *(u64 *)data); - break; default: return -EINVAL; } mutex_lock(&ionic->dev_cmd_lock); ionic_dev_cmd_go(&ionic->idev, &cmd); - err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + err = ionic_dev_cmd_wait_nomsg(ionic, DEVCMD_TIMEOUT); + memcpy_fromio(comp, &ionic->idev.dev_cmd_regs->comp.vf_getattr, + sizeof(*comp)); mutex_unlock(&ionic->dev_cmd_lock); + if (err && comp->status != IONIC_RC_ENOSUPP) + ionic_dev_cmd_dev_err_print(ionic, cmd.vf_getattr.opcode, + comp->status, err); + return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index e5acf3bd62b2..563c302eb033 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -318,7 +318,10 @@ void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable); void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type); void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type); -int ionic_set_vf_config(struct ionic *ionic, int vf, u8 attr, u8 *data); +int ionic_set_vf_config(struct ionic *ionic, int vf, + struct ionic_vf_setattr_cmd *vfc); +int ionic_dev_cmd_vf_getattr(struct ionic *ionic, int vf, u8 attr, + struct ionic_vf_getattr_comp *comp); void ionic_dev_cmd_queue_identify(struct ionic_dev *idev, u16 lif_type, u8 qtype, u8 qver); void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver); @@ -353,5 +356,6 @@ void ionic_q_rewind(struct ionic_queue *q, struct ionic_desc_info *start); void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, unsigned int stop_index); int ionic_heartbeat_check(struct ionic *ionic); +bool ionic_is_fw_running(struct ionic_dev *idev); #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 2ff7be17e5af..542e395fb037 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1112,12 +1112,17 @@ static bool ionic_notifyq_service(struct ionic_cq *cq, ionic_link_status_check_request(lif, CAN_NOT_SLEEP); break; case IONIC_EVENT_RESET: - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - netdev_err(lif->netdev, "Reset event dropped\n"); - } else { - work->type = IONIC_DW_TYPE_LIF_RESET; - ionic_lif_deferred_enqueue(&lif->deferred, work); + if (lif->ionic->idev.fw_status_ready && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "Reset event dropped\n"); + clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); + } else { + work->type = IONIC_DW_TYPE_LIF_RESET; + ionic_lif_deferred_enqueue(&lif->deferred, work); + } } break; default: @@ -1782,7 +1787,7 @@ static void ionic_lif_quiesce(struct ionic_lif *lif) err = ionic_adminq_post_wait(lif, &ctx); if (err) - netdev_err(lif->netdev, "lif quiesce failed %d\n", err); + netdev_dbg(lif->netdev, "lif quiesce failed %d\n", err); } static void ionic_txrx_disable(struct ionic_lif *lif) @@ -2152,6 +2157,76 @@ static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd } } +static int ionic_update_cached_vf_config(struct ionic *ionic, int vf) +{ + struct ionic_vf_getattr_comp comp = { 0 }; + int err; + u8 attr; + + attr = IONIC_VF_ATTR_VLAN; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].vlanid = comp.vlanid; + + attr = IONIC_VF_ATTR_SPOOFCHK; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].spoofchk = comp.spoofchk; + + attr = IONIC_VF_ATTR_LINKSTATE; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) { + switch (comp.linkstate) { + case IONIC_VF_LINK_STATUS_UP: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_ENABLE; + break; + case IONIC_VF_LINK_STATUS_DOWN: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_DISABLE; + break; + case IONIC_VF_LINK_STATUS_AUTO: + ionic->vfs[vf].linkstate = IFLA_VF_LINK_STATE_AUTO; + break; + default: + dev_warn(ionic->dev, "Unexpected link state %u\n", comp.linkstate); + break; + } + } + + attr = IONIC_VF_ATTR_RATE; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].maxrate = comp.maxrate; + + attr = IONIC_VF_ATTR_TRUST; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ionic->vfs[vf].trusted = comp.trust; + + attr = IONIC_VF_ATTR_MAC; + err = ionic_dev_cmd_vf_getattr(ionic, vf, attr, &comp); + if (err && comp.status != IONIC_RC_ENOSUPP) + goto err_out; + if (!err) + ether_addr_copy(ionic->vfs[vf].macaddr, comp.macaddr); + +err_out: + if (err) + dev_err(ionic->dev, "Failed to get %s for VF %d\n", + ionic_vf_attr_to_str(attr), vf); + + return err; +} + static int ionic_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivf) { @@ -2167,14 +2242,18 @@ static int ionic_get_vf_config(struct net_device *netdev, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ivf->vf = vf; - ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid); - ivf->qos = 0; - ivf->spoofchk = ionic->vfs[vf].spoofchk; - ivf->linkstate = ionic->vfs[vf].linkstate; - ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate); - ivf->trusted = ionic->vfs[vf].trusted; - ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr); + ivf->vf = vf; + ivf->qos = 0; + + ret = ionic_update_cached_vf_config(ionic, vf); + if (!ret) { + ivf->vlan = le16_to_cpu(ionic->vfs[vf].vlanid); + ivf->spoofchk = ionic->vfs[vf].spoofchk; + ivf->linkstate = ionic->vfs[vf].linkstate; + ivf->max_tx_rate = le32_to_cpu(ionic->vfs[vf].maxrate); + ivf->trusted = ionic->vfs[vf].trusted; + ether_addr_copy(ivf->mac, ionic->vfs[vf].macaddr); + } } up_read(&ionic->vf_op_lock); @@ -2220,6 +2299,7 @@ static int ionic_get_vf_stats(struct net_device *netdev, int vf, static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_MAC }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2235,7 +2315,11 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, IONIC_VF_ATTR_MAC, mac); + ether_addr_copy(vfc.macaddr, mac); + dev_dbg(ionic->dev, "%s: vf %d macaddr %pM\n", + __func__, vf, vfc.macaddr); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ether_addr_copy(ionic->vfs[vf].macaddr, mac); } @@ -2247,6 +2331,7 @@ static int ionic_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, __be16 proto) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_VLAN }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2269,8 +2354,11 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_VLAN, (u8 *)&vlan); + vfc.vlanid = cpu_to_le16(vlan); + dev_dbg(ionic->dev, "%s: vf %d vlan %d\n", + __func__, vf, le16_to_cpu(vfc.vlanid)); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ionic->vfs[vf].vlanid = cpu_to_le16(vlan); } @@ -2282,6 +2370,7 @@ static int ionic_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, static int ionic_set_vf_rate(struct net_device *netdev, int vf, int tx_min, int tx_max) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_RATE }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; int ret; @@ -2298,8 +2387,11 @@ static int ionic_set_vf_rate(struct net_device *netdev, int vf, if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_RATE, (u8 *)&tx_max); + vfc.maxrate = cpu_to_le32(tx_max); + dev_dbg(ionic->dev, "%s: vf %d maxrate %d\n", + __func__, vf, le32_to_cpu(vfc.maxrate)); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) lif->ionic->vfs[vf].maxrate = cpu_to_le32(tx_max); } @@ -2310,9 +2402,9 @@ static int ionic_set_vf_rate(struct net_device *netdev, int vf, static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_SPOOFCHK }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data = set; /* convert to u8 for config */ int ret; if (!netif_device_present(netdev)) @@ -2323,10 +2415,13 @@ static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_SPOOFCHK, &data); + vfc.spoofchk = set; + dev_dbg(ionic->dev, "%s: vf %d spoof %d\n", + __func__, vf, vfc.spoofchk); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) - ionic->vfs[vf].spoofchk = data; + ionic->vfs[vf].spoofchk = set; } up_write(&ionic->vf_op_lock); @@ -2335,9 +2430,9 @@ static int ionic_set_vf_spoofchk(struct net_device *netdev, int vf, bool set) static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_TRUST }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data = set; /* convert to u8 for config */ int ret; if (!netif_device_present(netdev)) @@ -2348,10 +2443,13 @@ static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_TRUST, &data); + vfc.trust = set; + dev_dbg(ionic->dev, "%s: vf %d trust %d\n", + __func__, vf, vfc.trust); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) - ionic->vfs[vf].trusted = data; + ionic->vfs[vf].trusted = set; } up_write(&ionic->vf_op_lock); @@ -2360,20 +2458,21 @@ static int ionic_set_vf_trust(struct net_device *netdev, int vf, bool set) static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) { + struct ionic_vf_setattr_cmd vfc = { .attr = IONIC_VF_ATTR_LINKSTATE }; struct ionic_lif *lif = netdev_priv(netdev); struct ionic *ionic = lif->ionic; - u8 data; + u8 vfls; int ret; switch (set) { case IFLA_VF_LINK_STATE_ENABLE: - data = IONIC_VF_LINK_STATUS_UP; + vfls = IONIC_VF_LINK_STATUS_UP; break; case IFLA_VF_LINK_STATE_DISABLE: - data = IONIC_VF_LINK_STATUS_DOWN; + vfls = IONIC_VF_LINK_STATUS_DOWN; break; case IFLA_VF_LINK_STATE_AUTO: - data = IONIC_VF_LINK_STATUS_AUTO; + vfls = IONIC_VF_LINK_STATUS_AUTO; break; default: return -EINVAL; @@ -2387,8 +2486,11 @@ static int ionic_set_vf_link_state(struct net_device *netdev, int vf, int set) if (vf >= pci_num_vf(ionic->pdev) || !ionic->vfs) { ret = -EINVAL; } else { - ret = ionic_set_vf_config(ionic, vf, - IONIC_VF_ATTR_LINKSTATE, &data); + vfc.linkstate = vfls; + dev_dbg(ionic->dev, "%s: vf %d linkstate %d\n", + __func__, vf, vfc.linkstate); + + ret = ionic_set_vf_config(ionic, vf, &vfc); if (!ret) ionic->vfs[vf].linkstate = set; } @@ -2835,6 +2937,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) mutex_unlock(&lif->queue_lock); + clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); dev_info(ionic->dev, "FW Down: LIFs stopped\n"); } @@ -2934,8 +3037,6 @@ void ionic_lif_free(struct ionic_lif *lif) /* unmap doorbell page */ ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); lif->kern_dbpage = NULL; - kfree(lif->dbid_inuse); - lif->dbid_inuse = NULL; mutex_destroy(&lif->config_lock); mutex_destroy(&lif->queue_lock); @@ -3135,22 +3236,12 @@ int ionic_lif_init(struct ionic_lif *lif) return -EINVAL; } - lif->dbid_inuse = bitmap_zalloc(lif->dbid_count, GFP_KERNEL); - if (!lif->dbid_inuse) { - dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n"); - return -ENOMEM; - } - - /* first doorbell id reserved for kernel (dbid aka pid == zero) */ - set_bit(0, lif->dbid_inuse); lif->kern_pid = 0; - dbpage_num = ionic_db_page_num(lif, lif->kern_pid); lif->kern_dbpage = ionic_bus_map_dbpage(lif->ionic, dbpage_num); if (!lif->kern_dbpage) { dev_err(dev, "Cannot map dbpage, aborting\n"); - err = -ENOMEM; - goto err_out_free_dbid; + return -ENOMEM; } err = ionic_lif_adminq_init(lif); @@ -3186,15 +3277,13 @@ int ionic_lif_init(struct ionic_lif *lif) return 0; err_out_notifyq_deinit: + napi_disable(&lif->adminqcq->napi); ionic_lif_qcq_deinit(lif, lif->notifyqcq); err_out_adminq_deinit: ionic_lif_qcq_deinit(lif, lif->adminqcq); ionic_lif_reset(lif); ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); lif->kern_dbpage = NULL; -err_out_free_dbid: - kfree(lif->dbid_inuse); - lif->dbid_inuse = NULL; return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 9f7ab2f17f93..a53984bf3544 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -135,6 +135,7 @@ enum ionic_lif_state_flags { IONIC_LIF_F_LINK_CHECK_REQUESTED, IONIC_LIF_F_FILTER_SYNC_NEEDED, IONIC_LIF_F_FW_RESET, + IONIC_LIF_F_FW_STOPPING, IONIC_LIF_F_SPLIT_INTR, IONIC_LIF_F_BROKEN, IONIC_LIF_F_TX_DIM_INTR, @@ -213,7 +214,6 @@ struct ionic_lif { u32 rx_coalesce_hw; /* what the hw is using */ u32 tx_coalesce_usecs; /* what the user asked for */ u32 tx_coalesce_hw; /* what the hw is using */ - unsigned long *dbid_inuse; unsigned int dbid_count; struct ionic_phc *phc; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 875f4ec42efe..4029b4e021f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -188,6 +188,28 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) } } +const char *ionic_vf_attr_to_str(enum ionic_vf_attr attr) +{ + switch (attr) { + case IONIC_VF_ATTR_SPOOFCHK: + return "IONIC_VF_ATTR_SPOOFCHK"; + case IONIC_VF_ATTR_TRUST: + return "IONIC_VF_ATTR_TRUST"; + case IONIC_VF_ATTR_LINKSTATE: + return "IONIC_VF_ATTR_LINKSTATE"; + case IONIC_VF_ATTR_MAC: + return "IONIC_VF_ATTR_MAC"; + case IONIC_VF_ATTR_VLAN: + return "IONIC_VF_ATTR_VLAN"; + case IONIC_VF_ATTR_RATE: + return "IONIC_VF_ATTR_RATE"; + case IONIC_VF_ATTR_STATSADDR: + return "IONIC_VF_ATTR_STATSADDR"; + default: + return "IONIC_VF_ATTR_UNKNOWN"; + } +} + static void ionic_adminq_flush(struct ionic_lif *lif) { struct ionic_desc_info *desc_info; @@ -215,9 +237,13 @@ static void ionic_adminq_flush(struct ionic_lif *lif) void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, u8 status, int err) { + const char *stat_str; + + stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" : + ionic_error_to_str(status); + netdev_err(lif->netdev, "%s (%d) failed: %s (%d)\n", - ionic_opcode_to_str(opcode), opcode, - ionic_error_to_str(status), err); + ionic_opcode_to_str(opcode), opcode, stat_str, err); } static int ionic_adminq_check_err(struct ionic_lif *lif, @@ -318,6 +344,7 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, if (do_msg && !test_bit(IONIC_LIF_F_FW_RESET, lif->state)) netdev_err(netdev, "Posting of %s (%d) failed: %d\n", name, ctx->cmd.cmd.opcode, err); + ctx->comp.comp.status = IONIC_RC_ERROR; return err; } @@ -331,11 +358,15 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx, if (remaining) break; - /* interrupt the wait if FW stopped */ - if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) { + /* force a check of FW status and break out if FW reset */ + (void)ionic_heartbeat_check(lif->ionic); + if ((test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !lif->ionic->idev.fw_status_ready) || + test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { if (do_msg) - netdev_err(netdev, "%s (%d) interrupted, FW in reset\n", - name, ctx->cmd.cmd.opcode); + netdev_warn(netdev, "%s (%d) interrupted, FW in reset\n", + name, ctx->cmd.cmd.opcode); + ctx->comp.comp.status = IONIC_RC_ERROR; return -ENXIO; } @@ -370,21 +401,34 @@ int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx * static void ionic_dev_cmd_clean(struct ionic *ionic) { - union __iomem ionic_dev_cmd_regs *regs = ionic->idev.dev_cmd_regs; + struct ionic_dev *idev = &ionic->idev; - iowrite32(0, ®s->doorbell); - memset_io(®s->cmd, 0, sizeof(regs->cmd)); + iowrite32(0, &idev->dev_cmd_regs->doorbell); + memset_io(&idev->dev_cmd_regs->cmd, 0, sizeof(idev->dev_cmd_regs->cmd)); } -int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +void ionic_dev_cmd_dev_err_print(struct ionic *ionic, u8 opcode, u8 status, + int err) +{ + const char *stat_str; + + stat_str = (err == -ETIMEDOUT) ? "TIMEOUT" : + ionic_error_to_str(status); + + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", + ionic_opcode_to_str(opcode), opcode, stat_str, err); +} + +static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds, + const bool do_msg) { struct ionic_dev *idev = &ionic->idev; unsigned long start_time; unsigned long max_wait; unsigned long duration; + int done = 0; + bool fw_up; int opcode; - int hb = 0; - int done; int err; /* Wait for dev cmd to complete, retrying if we get EAGAIN, @@ -394,31 +438,24 @@ int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) try_again: opcode = readb(&idev->dev_cmd_regs->cmd.cmd.opcode); start_time = jiffies; - do { + for (fw_up = ionic_is_fw_running(idev); + !done && fw_up && time_before(jiffies, max_wait); + fw_up = ionic_is_fw_running(idev)) { done = ionic_dev_cmd_done(idev); if (done) break; usleep_range(100, 200); - - /* Don't check the heartbeat on FW_CONTROL commands as they are - * notorious for interrupting the firmware's heartbeat update. - */ - if (opcode != IONIC_CMD_FW_CONTROL) - hb = ionic_heartbeat_check(ionic); - } while (!done && !hb && time_before(jiffies, max_wait)); + } duration = jiffies - start_time; dev_dbg(ionic->dev, "DEVCMD %s (%d) done=%d took %ld secs (%ld jiffies)\n", ionic_opcode_to_str(opcode), opcode, done, duration / HZ, duration); - if (!done && hb) { - /* It is possible (but unlikely) that FW was busy and missed a - * heartbeat check but is still alive and will process this - * request, so don't clean the dev_cmd in this case. - */ - dev_dbg(ionic->dev, "DEVCMD %s (%d) failed - FW halted\n", - ionic_opcode_to_str(opcode), opcode); + if (!done && !fw_up) { + ionic_dev_cmd_clean(ionic); + dev_warn(ionic->dev, "DEVCMD %s (%d) interrupted - FW is down\n", + ionic_opcode_to_str(opcode), opcode); return -ENXIO; } @@ -444,9 +481,9 @@ try_again: } if (!(opcode == IONIC_CMD_FW_CONTROL && err == IONIC_RC_EAGAIN)) - dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", - ionic_opcode_to_str(opcode), opcode, - ionic_error_to_str(err), err); + if (do_msg) + ionic_dev_cmd_dev_err_print(ionic, opcode, err, + ionic_error_to_errno(err)); return ionic_error_to_errno(err); } @@ -454,6 +491,16 @@ try_again: return 0; } +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +{ + return __ionic_dev_cmd_wait(ionic, max_seconds, true); +} + +int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_seconds) +{ + return __ionic_dev_cmd_wait(ionic, max_seconds, false); +} + int ionic_setup(struct ionic *ionic) { int err; @@ -540,6 +587,9 @@ int ionic_reset(struct ionic *ionic) struct ionic_dev *idev = &ionic->idev; int err; + if (!ionic_is_fw_running(idev)) + return 0; + mutex_lock(&ionic->dev_cmd_lock); ionic_dev_cmd_reset(idev); err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); @@ -612,15 +662,17 @@ int ionic_port_init(struct ionic *ionic) int ionic_port_reset(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; - int err; + int err = 0; if (!idev->port_info) return 0; - mutex_lock(&ionic->dev_cmd_lock); - ionic_dev_cmd_port_reset(idev); - err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); - mutex_unlock(&ionic->dev_cmd_lock); + if (ionic_is_fw_running(idev)) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + } dma_free_coherent(ionic->dev, idev->port_info_sz, idev->port_info, idev->port_info_pa); @@ -628,9 +680,6 @@ int ionic_port_reset(struct ionic *ionic) idev->port_info = NULL; idev->port_info_pa = 0; - if (err) - dev_err(ionic->dev, "Failed to reset port\n"); - return err; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index f6e785f949f9..b7363376dfc8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -376,10 +376,24 @@ static int ionic_lif_filter_add(struct ionic_lif *lif, spin_unlock_bh(&lif->rx_filters.lock); - if (err == -ENOSPC) { - if (le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) - lif->max_vlans = lif->nvlans; + /* store the max_vlans limit that we found */ + if (err == -ENOSPC && + le16_to_cpu(ctx.cmd.rx_filter_add.match) == IONIC_RX_FILTER_MATCH_VLAN) + lif->max_vlans = lif->nvlans; + + /* Prevent unnecessary error messages on recoverable + * errors as the filter will get retried on the next + * sync attempt. + */ + switch (err) { + case -ENOSPC: + case -ENXIO: + case -ETIMEDOUT: + case -EAGAIN: + case -EBUSY: return 0; + default: + break; } ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, @@ -494,9 +508,22 @@ static int ionic_lif_filter_del(struct ionic_lif *lif, spin_unlock_bh(&lif->rx_filters.lock); if (state != IONIC_FILTER_STATE_NEW) { - err = ionic_adminq_post_wait(lif, &ctx); - if (err && err != -EEXIST) + err = ionic_adminq_post_wait_nomsg(lif, &ctx); + + switch (err) { + /* ignore these errors */ + case -EEXIST: + case -ENXIO: + case -ETIMEDOUT: + case -EAGAIN: + case -EBUSY: + case 0: + break; + default: + ionic_adminq_netdev_err_print(lif, ctx.cmd.cmd.opcode, + ctx.comp.comp.status, err); return err; + } } return 0; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 94384f5d2a22..d197a70a49c9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -669,27 +669,37 @@ dma_fail: return -EIO; } +static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, + struct ionic_desc_info *desc_info) +{ + struct ionic_buf_info *buf_info = desc_info->bufs; + struct device *dev = q->dev; + unsigned int i; + + if (!desc_info->nbufs) + return; + + dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr, + buf_info->len, DMA_TO_DEVICE); + buf_info++; + for (i = 1; i < desc_info->nbufs; i++, buf_info++) + dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr, + buf_info->len, DMA_TO_DEVICE); + + desc_info->nbufs = 0; +} + static void ionic_tx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, struct ionic_cq_info *cq_info, void *cb_arg) { - struct ionic_buf_info *buf_info = desc_info->bufs; struct ionic_tx_stats *stats = q_to_tx_stats(q); struct ionic_qcq *qcq = q_to_qcq(q); struct sk_buff *skb = cb_arg; - struct device *dev = q->dev; - unsigned int i; u16 qi; - if (desc_info->nbufs) { - dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr, - buf_info->len, DMA_TO_DEVICE); - buf_info++; - for (i = 1; i < desc_info->nbufs; i++, buf_info++) - dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr, - buf_info->len, DMA_TO_DEVICE); - } + ionic_tx_desc_unmap_bufs(q, desc_info); if (!skb) return; @@ -931,8 +941,11 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) err = ionic_tx_tcp_inner_pseudo_csum(skb); else err = ionic_tx_tcp_pseudo_csum(skb); - if (err) + if (err) { + /* clean up mapping from ionic_tx_map_skb */ + ionic_tx_desc_unmap_bufs(q, desc_info); return err; + } if (encap) hdrlen = skb_inner_transport_header(skb) - skb->data + @@ -1003,8 +1016,8 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) return 0; } -static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_desc *desc = desc_info->txq_desc; struct ionic_buf_info *buf_info = desc_info->bufs; @@ -1038,12 +1051,10 @@ static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, stats->crc32_csum++; else stats->csum++; - - return 0; } -static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_desc *desc = desc_info->txq_desc; struct ionic_buf_info *buf_info = desc_info->bufs; @@ -1074,12 +1085,10 @@ static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, desc->csum_offset = 0; stats->csum_none++; - - return 0; } -static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) +static void ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, + struct ionic_desc_info *desc_info) { struct ionic_txq_sg_desc *sg_desc = desc_info->txq_sg_desc; struct ionic_buf_info *buf_info = &desc_info->bufs[1]; @@ -1093,31 +1102,24 @@ static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, } stats->frags += skb_shinfo(skb)->nr_frags; - - return 0; } static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) { struct ionic_desc_info *desc_info = &q->info[q->head_idx]; struct ionic_tx_stats *stats = q_to_tx_stats(q); - int err; if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) return -EIO; /* set up the initial descriptor */ if (skb->ip_summed == CHECKSUM_PARTIAL) - err = ionic_tx_calc_csum(q, skb, desc_info); + ionic_tx_calc_csum(q, skb, desc_info); else - err = ionic_tx_calc_no_csum(q, skb, desc_info); - if (err) - return err; + ionic_tx_calc_no_csum(q, skb, desc_info); /* add frags */ - err = ionic_tx_skb_frags(q, skb, desc_info); - if (err) - return err; + ionic_tx_skb_frags(q, skb, desc_info); skb_tx_timestamp(skb); stats->pkts++; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index da1eadabcb41..b3811ad4bcf0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -614,12 +614,13 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, usecs); } -int qed_mcp_cmd(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - u32 cmd, - u32 param, - u32 *o_mcp_resp, - u32 *o_mcp_param) +static int _qed_mcp_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param, + bool can_sleep) { struct qed_mcp_mb_params mb_params; int rc; @@ -627,6 +628,7 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, memset(&mb_params, 0, sizeof(mb_params)); mb_params.cmd = cmd; mb_params.param = param; + mb_params.flags = can_sleep ? QED_MB_FLAG_CAN_SLEEP : 0; rc = qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); if (rc) @@ -638,6 +640,28 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, return 0; } +int qed_mcp_cmd(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param) +{ + return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param, + o_mcp_resp, o_mcp_param, true)); +} + +int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param) +{ + return (_qed_mcp_cmd(p_hwfn, p_ptt, cmd, param, + o_mcp_resp, o_mcp_param, false)); +} + static int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -1728,8 +1752,8 @@ static void qed_mcp_update_bw(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_configure_pf_max_bandwidth(p_hwfn->cdev, p_info->bandwidth_max); /* Acknowledge the MFW */ - qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp, - ¶m); + qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_BW_UPDATE_ACK, 0, &resp, + ¶m); } static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -1766,8 +1790,8 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode); /* Acknowledge the MFW */ - qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0, - &resp, ¶m); + qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_S_TAG_UPDATE_ACK, 0, + &resp, ¶m); } static void qed_mcp_handle_fan_failure(struct qed_hwfn *p_hwfn, @@ -3675,8 +3699,8 @@ static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn, { int rc; - rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, param, - p_mcp_resp, p_mcp_param); + rc = qed_mcp_cmd_nosleep(p_hwfn, p_ptt, DRV_MSG_CODE_RESOURCE_CMD, + param, p_mcp_resp, p_mcp_param); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 369e1892450a..2f26bee54e6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -393,11 +393,12 @@ int qed_mcp_get_board_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_board_config); /** - * qed_mcp_cmd(): General function for sending commands to the MCP + * qed_mcp_cmd(): Sleepable function for sending commands to the MCP * mailbox. It acquire mutex lock for the entire * operation, from sending the request until the MCP * response. Waiting for MCP response will be checked up - * to 5 seconds every 5ms. + * to 5 seconds every 10ms. Should not be called from atomic + * context. * * @p_hwfn: HW device data. * @p_ptt: PTT required for register access. @@ -417,6 +418,31 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, u32 *o_mcp_param); /** + * qed_mcp_cmd_nosleep(): Function for sending commands to the MCP + * mailbox. It acquire mutex lock for the entire + * operation, from sending the request until the MCP + * response. Waiting for MCP response will be checked up + * to 5 seconds every 10us. Should be called when sleep + * is not allowed. + * + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @cmd: command to be sent to the MCP. + * @param: Optional param + * @o_mcp_resp: The MCP response code (exclude sequence). + * @o_mcp_param: Optional parameter provided by the MCP + * response + * + * Return: Int - 0 - Operation was successul. + */ +int qed_mcp_cmd_nosleep(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u32 cmd, + u32 param, + u32 *o_mcp_resp, + u32 *o_mcp_param); + +/** * qed_mcp_drain(): drains the nig, allowing completion to pass in * case of pauses. * (Should be called only from sleepable context) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 19e2621e0645..67014eb76969 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2667,10 +2667,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38: rtl_eri_set_bits(tp, 0xd4, 0x0c00); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: - rtl_eri_set_bits(tp, 0xd4, 0x1f80); - break; - case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63: r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80); break; default: @@ -2678,13 +2675,48 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp) } } +static void rtl_disable_exit_l1(struct rtl8169_private *tp) +{ + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: + rtl_eri_clear_bits(tp, 0xd4, 0x1f00); + break; + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_63: + r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0); + break; + default: + break; + } +} + static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { /* Don't enable ASPM in the chip if OS can't control ASPM */ if (enable && tp->aspm_manageable) { RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); + + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48: + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + /* reset ephy tx/rx disable timer */ + r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0); + /* chip can trigger L1.2 */ + r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, BIT(2)); + break; + default: + break; + } } else { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_45 ... RTL_GIGA_MAC_VER_48: + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_63: + r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0); + break; + default: + break; + } + RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } @@ -4683,7 +4715,7 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl_pci_commit(tp); rtl8169_cleanup(tp, true); - + rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); } @@ -4843,8 +4875,6 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp) rtl8169_down(tp); } -#ifdef CONFIG_PM - static int rtl8169_runtime_resume(struct device *dev) { struct rtl8169_private *tp = dev_get_drvdata(dev); @@ -4860,7 +4890,7 @@ static int rtl8169_runtime_resume(struct device *dev) return 0; } -static int __maybe_unused rtl8169_suspend(struct device *device) +static int rtl8169_suspend(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); @@ -4873,7 +4903,7 @@ static int __maybe_unused rtl8169_suspend(struct device *device) return 0; } -static int __maybe_unused rtl8169_resume(struct device *device) +static int rtl8169_resume(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); @@ -4915,13 +4945,11 @@ static int rtl8169_runtime_idle(struct device *device) } static const struct dev_pm_ops rtl8169_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume) - SET_RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume, - rtl8169_runtime_idle) + SYSTEM_SLEEP_PM_OPS(rtl8169_suspend, rtl8169_resume) + RUNTIME_PM_OPS(rtl8169_runtime_suspend, rtl8169_runtime_resume, + rtl8169_runtime_idle) }; -#endif /* CONFIG_PM */ - static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) { /* WoL fails with 8168b when the receiver is disabled. */ @@ -5255,6 +5283,16 @@ done: rtl_rar_set(tp, mac_addr); } +/* register is set if system vendor successfully tested ASPM 1.2 */ +static bool rtl_aspm_is_safe(struct rtl8169_private *tp) +{ + if (tp->mac_version >= RTL_GIGA_MAC_VER_60 && + r8168_mac_ocp_read(tp, 0xc0b2) & 0xf) + return true; + + return false; +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5333,7 +5371,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) * Chips from RTL8168h partially have issues with L1.2, but seem * to work fine with L1 and L1.1. */ - if (tp->mac_version >= RTL_GIGA_MAC_VER_45) + if (rtl_aspm_is_safe(tp)) + rc = 0; + else if (tp->mac_version >= RTL_GIGA_MAC_VER_45) rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); else rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); @@ -5460,9 +5500,7 @@ static struct pci_driver rtl8169_pci_driver = { .probe = rtl_init_one, .remove = rtl_remove_one, .shutdown = rtl_shutdown, -#ifdef CONFIG_PM - .driver.pm = &rtl8169_pm_ops, -#endif + .driver.pm = pm_ptr(&rtl8169_pm_ops), }; module_pci_driver(rtl8169_pci_driver); diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index f7ad5487879b..15c295f90196 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -429,15 +429,6 @@ static const struct phy_reg rtl8168d_1_phy_reg_init_0[] = { { 0x0d, 0xf880 } }; -static const struct phy_reg rtl8168d_1_phy_reg_init_1[] = { - { 0x1f, 0x0002 }, - { 0x05, 0x669a }, - { 0x1f, 0x0005 }, - { 0x05, 0x8330 }, - { 0x06, 0x669a }, - { 0x1f, 0x0002 } -}; - static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp, struct phy_device *phydev, u16 val) @@ -455,6 +446,29 @@ static void rtl8168d_apply_firmware_cond(struct rtl8169_private *tp, r8169_apply_firmware(tp); } +static void rtl8168d_1_common(struct phy_device *phydev) +{ + u16 val; + + phy_write_paged(phydev, 0x0002, 0x05, 0x669a); + r8168d_phy_param(phydev, 0x8330, 0xffff, 0x669a); + phy_write(phydev, 0x1f, 0x0002); + + val = phy_read(phydev, 0x0d); + + if ((val & 0x00ff) != 0x006c) { + static const u16 set[] = { + 0x0065, 0x0066, 0x0067, 0x0068, + 0x0069, 0x006a, 0x006b, 0x006c + }; + int i; + + val &= 0xff00; + for (i = 0; i < ARRAY_SIZE(set); i++) + phy_write(phydev, 0x0d, val | set[i]); + } +} + static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { @@ -469,25 +483,7 @@ static void rtl8168d_1_hw_phy_config(struct rtl8169_private *tp, phy_modify(phydev, 0x0c, 0x5d00, 0xa200); if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) { - int val; - - rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1); - - val = phy_read(phydev, 0x0d); - - if ((val & 0x00ff) != 0x006c) { - static const u32 set[] = { - 0x0065, 0x0066, 0x0067, 0x0068, - 0x0069, 0x006a, 0x006b, 0x006c - }; - int i; - - phy_write(phydev, 0x1f, 0x0002); - - val &= 0xff00; - for (i = 0; i < ARRAY_SIZE(set); i++) - phy_write(phydev, 0x0d, val | set[i]); - } + rtl8168d_1_common(phydev); } else { phy_write_paged(phydev, 0x0002, 0x05, 0x6662); r8168d_phy_param(phydev, 0x8330, 0xffff, 0x6662); @@ -513,24 +509,7 @@ static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp, rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_0); if (rtl8168d_efuse_read(tp, 0x01) == 0xb1) { - int val; - - rtl_writephy_batch(phydev, rtl8168d_1_phy_reg_init_1); - - val = phy_read(phydev, 0x0d); - if ((val & 0x00ff) != 0x006c) { - static const u32 set[] = { - 0x0065, 0x0066, 0x0067, 0x0068, - 0x0069, 0x006a, 0x006b, 0x006c - }; - int i; - - phy_write(phydev, 0x1f, 0x0002); - - val &= 0xff00; - for (i = 0; i < ARRAY_SIZE(set); i++) - phy_write(phydev, 0x0d, val | set[i]); - } + rtl8168d_1_common(phydev); } else { phy_write_paged(phydev, 0x0002, 0x05, 0x2642); r8168d_phy_param(phydev, 0x8330, 0xffff, 0x2642); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index b215cde68e10..24e2635c4c80 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1432,11 +1432,7 @@ static int ravb_phy_init(struct net_device *ndev) * at this time. */ if (soc_device_match(r8a7795es10)) { - err = phy_set_max_speed(phydev, SPEED_100); - if (err) { - netdev_err(ndev, "failed to limit PHY to 100Mbit/s\n"); - goto err_phy_disconnect; - } + phy_set_max_speed(phydev, SPEED_100); netdev_info(ndev, "limited PHY to 100Mbit/s\n"); } @@ -1457,8 +1453,6 @@ static int ravb_phy_init(struct net_device *ndev) return 0; -err_phy_disconnect: - phy_disconnect(phydev); err_deregister_fixed_link: if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); @@ -2854,7 +2848,6 @@ static int ravb_wol_restore(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - int ret; if (info->nc_queues) napi_enable(&priv->napi[RAVB_NC]); @@ -2863,9 +2856,7 @@ static int ravb_wol_restore(struct net_device *ndev) /* Disable MagicPacket */ ravb_modify(ndev, ECMR, ECMR_MPDE, 0); - ret = ravb_close(ndev); - if (ret < 0) - return ret; + ravb_close(ndev); return disable_irq_wake(priv->emac_irq); } diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index d947a628e166..67ade78fb767 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2026,14 +2026,8 @@ static int sh_eth_phy_init(struct net_device *ndev) } /* mask with MAC supported features */ - if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) { - int err = phy_set_max_speed(phydev, SPEED_100); - if (err) { - netdev_err(ndev, "failed to limit PHY to 100 Mbit/s\n"); - phy_disconnect(phydev); - return err; - } - } + if (mdp->cd->register_type != SH_ETH_REG_GIGABIT) + phy_set_max_speed(phydev, SPEED_100); phy_attached_info(phydev); @@ -3450,9 +3444,7 @@ static int sh_eth_wol_restore(struct net_device *ndev) * both be reset and all registers restored. This is what * happens during suspend and resume without WoL enabled. */ - ret = sh_eth_close(ndev); - if (ret < 0) - return ret; + sh_eth_close(ndev); ret = sh_eth_open(ndev); if (ret < 0) return ret; @@ -3464,7 +3456,7 @@ static int sh_eth_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct sh_eth_private *mdp = netdev_priv(ndev); - int ret = 0; + int ret; if (!netif_running(ndev)) return 0; @@ -3483,7 +3475,7 @@ static int sh_eth_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct sh_eth_private *mdp = netdev_priv(ndev); - int ret = 0; + int ret; if (!netif_running(ndev)) return 0; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 32161a56726c..77a0d9d7e65a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -127,7 +127,7 @@ bool sxgbe_eee_init(struct sxgbe_priv_data * const priv) /* MAC core supports the EEE feature. */ if (priv->hw_cap.eee) { /* Check if the PHY supports EEE */ - if (phy_init_eee(ndev->phydev, 1)) + if (phy_init_eee(ndev->phydev, true)) return false; priv->eee_active = 1; diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index 16a4cbae9326..c672f92d65e9 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -749,6 +749,7 @@ ether3_probe(struct expansion_card *ec, const struct ecard_id *id) const struct ether3_data *data = id->data; struct net_device *dev; int bus_type, ret; + u8 addr[ETH_ALEN]; ether3_banner(); @@ -776,7 +777,8 @@ ether3_probe(struct expansion_card *ec, const struct ecard_id *id) priv(dev)->seeq = priv(dev)->base + data->base_offset; dev->irq = ec->irq; - ether3_addr(dev->dev_addr, ec); + ether3_addr(addr, ec); + eth_hw_addr_set(dev, addr); priv(dev)->dev = dev; timer_setup(&priv(dev)->timer, ether3_ledoff, 0); diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index cf366ed2557c..50d535981a35 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3990,6 +3990,30 @@ static unsigned int ef10_check_caps(const struct efx_nic *efx, } } +static unsigned int efx_ef10_recycle_ring_size(const struct efx_nic *efx) +{ + unsigned int ret = EFX_RECYCLE_RING_SIZE_10G; + + /* There is no difference between PFs and VFs. The side is based on + * the maximum link speed of a given NIC. + */ + switch (efx->pci_dev->device & 0xfff) { + case 0x0903: /* Farmingdale can do up to 10G */ + break; + case 0x0923: /* Greenport can do up to 40G */ + case 0x0a03: /* Medford can do up to 40G */ + ret *= 4; + break; + default: /* Medford2 can do up to 100G */ + ret *= 10; + } + + if (IS_ENABLED(CONFIG_PPC64)) + ret *= 4; + + return ret; +} + #define EF10_OFFLOAD_FEATURES \ (NETIF_F_IP_CSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | \ @@ -4106,6 +4130,7 @@ const struct efx_nic_type efx_hunt_a0_vf_nic_type = { .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_ef10_recycle_ring_size, }; const struct efx_nic_type efx_hunt_a0_nic_type = { @@ -4243,4 +4268,5 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .check_caps = ef10_check_caps, .print_additional_fwver = efx_ef10_print_additional_fwver, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_ef10_recycle_ring_size, }; diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index f79b14a119ae..a07cbf45a326 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -23,6 +23,7 @@ #include "ef100_rx.h" #include "ef100_tx.h" #include "ef100_netdev.h" +#include "rx_common.h" #define EF100_MAX_VIS 4096 #define EF100_NUM_MCDI_BUFFERS 1 @@ -696,6 +697,12 @@ static unsigned int ef100_check_caps(const struct efx_nic *efx, } } +static unsigned int efx_ef100_recycle_ring_size(const struct efx_nic *efx) +{ + /* Maximum link speed for Riverhead is 100G */ + return 10 * EFX_RECYCLE_RING_SIZE_10G; +} + /* NIC level access functions */ #define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \ @@ -770,6 +777,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config, .rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config, .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + .rx_recycle_ring_size = efx_ef100_recycle_ring_size, .reconfigure_mac = ef100_reconfigure_mac, .reconfigure_port = efx_mcdi_port_reconfigure, @@ -849,6 +857,7 @@ const struct efx_nic_type ef100_vf_nic_type = { .rx_pull_rss_config = efx_mcdi_rx_pull_rss_config, .rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config, .rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts, + .rx_recycle_ring_size = efx_ef100_recycle_ring_size, .reconfigure_mac = ef100_reconfigure_mac, .test_nvram = efx_new_mcdi_nvram_test_all, diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index cc15ee8812d9..c75dc75e2857 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1282,6 +1282,7 @@ struct efx_udp_tunnel { * @udp_tnl_has_port: Check if a port has been added as UDP tunnel * @print_additional_fwver: Dump NIC-specific additional FW version info * @sensor_event: Handle a sensor event from MCDI + * @rx_recycle_ring_size: Size of the RX recycle ring * @revision: Hardware architecture revision * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address @@ -1460,6 +1461,7 @@ struct efx_nic_type { size_t (*print_additional_fwver)(struct efx_nic *efx, char *buf, size_t len); void (*sensor_event)(struct efx_nic *efx, efx_qword_t *ev); + unsigned int (*rx_recycle_ring_size)(const struct efx_nic *efx); int revision; unsigned int txd_ptr_tbl_base; diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h index b9cafe9cd568..0cef35c0c559 100644 --- a/drivers/net/ethernet/sfc/nic_common.h +++ b/drivers/net/ethernet/sfc/nic_common.h @@ -195,6 +195,11 @@ static inline void efx_sensor_event(struct efx_nic *efx, efx_qword_t *ev) efx->type->sensor_event(efx, ev); } +static inline unsigned int efx_rx_recycle_ring_size(const struct efx_nic *efx) +{ + return efx->type->rx_recycle_ring_size(efx); +} + /* Some statistics are computed as A - B where A and B each increase * linearly with some hardware counter(s) and the counters are read * asynchronously. If the counters contributing to B are always read diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 633ca77a26fd..1b22c7be0088 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -23,13 +23,6 @@ module_param(rx_refill_threshold, uint, 0444); MODULE_PARM_DESC(rx_refill_threshold, "RX descriptor ring refill threshold (%)"); -/* Number of RX buffers to recycle pages for. When creating the RX page recycle - * ring, this number is divided by the number of buffers per page to calculate - * the number of pages to store in the RX page recycle ring. - */ -#define EFX_RECYCLE_RING_SIZE_IOMMU 4096 -#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH) - /* RX maximum head room required. * * This must be at least 1 to prevent overflow, plus one packet-worth @@ -141,16 +134,7 @@ static void efx_init_rx_recycle_ring(struct efx_rx_queue *rx_queue) unsigned int bufs_in_recycle_ring, page_ring_size; struct efx_nic *efx = rx_queue->efx; - /* Set the RX recycle ring size */ -#ifdef CONFIG_PPC64 - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU; -#else - if (iommu_present(&pci_bus_type)) - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU; - else - bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU; -#endif /* CONFIG_PPC64 */ - + bufs_in_recycle_ring = efx_rx_recycle_ring_size(efx); page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring / efx->rx_bufs_per_page); rx_queue->page_ring = kcalloc(page_ring_size, diff --git a/drivers/net/ethernet/sfc/rx_common.h b/drivers/net/ethernet/sfc/rx_common.h index 207ccd8ba062..fbd2769307f9 100644 --- a/drivers/net/ethernet/sfc/rx_common.h +++ b/drivers/net/ethernet/sfc/rx_common.h @@ -18,6 +18,12 @@ #define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \ EFX_RX_USR_BUF_SIZE) +/* Number of RX buffers to recycle pages for. When creating the RX page recycle + * ring, this number is divided by the number of buffers per page to calculate + * the number of pages to store in the RX page recycle ring. + */ +#define EFX_RECYCLE_RING_SIZE_10G 256 + static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf) { return page_address(buf->page) + buf->page_offset; diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index 16347a6d0c47..ce3060e15b54 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -25,6 +25,7 @@ #include "mcdi_port_common.h" #include "selftest.h" #include "siena_sriov.h" +#include "rx_common.h" /* Hardware control for SFC9000 family including SFL9021 (aka Siena). */ @@ -958,6 +959,12 @@ static unsigned int siena_check_caps(const struct efx_nic *efx, return 0; } +static unsigned int efx_siena_recycle_ring_size(const struct efx_nic *efx) +{ + /* Maximum link speed is 10G */ + return EFX_RECYCLE_RING_SIZE_10G; +} + /************************************************************************** * * Revision-dependent attributes used by efx.c and nic.c @@ -1098,4 +1105,5 @@ const struct efx_nic_type siena_a0_nic_type = { .rx_hash_key_size = 16, .check_caps = siena_check_caps, .sensor_event = efx_mcdi_sensor_event, + .rx_recycle_ring_size = efx_siena_recycle_ring_size, }; diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index dd6f69ced4ee..fc9cef9dcefc 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1648,7 +1648,7 @@ static int smc911x_ethtool_geteeprom(struct net_device *dev, return ret; if ((ret=smc911x_ethtool_read_eeprom_byte(dev, &eebuf[i]))!=0) return ret; - } + } memcpy(data, eebuf+eeprom->offset, eeprom->len); return 0; } @@ -1667,11 +1667,11 @@ static int smc911x_ethtool_seteeprom(struct net_device *dev, return ret; /* write byte */ if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0) - return ret; + return ret; if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0) return ret; - } - return 0; + } + return 0; } static int smc911x_ethtool_geteeprom_len(struct net_device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 8e8778cfbbad..5943ff9f21c2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -383,10 +383,10 @@ static int intel_crosststamp(ktime_t *device, /* Repeat until the timestamps are from the FIFO last segment */ for (i = 0; i < num_snapshot; i++) { - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_ptptime(priv, ptpaddr, &ptp_time); *device = ns_to_ktime(ptp_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); get_arttime(priv->mii, intel_priv->mdio_adhoc_addr, &art_time); *system = convert_art_to_tsc(art_time); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 617d0e4c6495..f86cc83003f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -16,6 +16,7 @@ #include <linux/of_net.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/regmap.h> #include <linux/stmmac.h> @@ -57,7 +58,6 @@ struct emac_variant { }; /* struct sunxi_priv_data - hold all sunxi private data - * @tx_clk: reference to MAC TX clock * @ephy_clk: reference to the optional EPHY clock for the internal PHY * @regulator: reference to the optional regulator * @rst_ephy: reference to the optional EPHY reset for the internal PHY @@ -68,7 +68,6 @@ struct emac_variant { * @mux_handle: Internal pointer used by mdio-mux lib */ struct sunxi_priv_data { - struct clk *tx_clk; struct clk *ephy_clk; struct regulator *regulator; struct reset_control *rst_ephy; @@ -579,22 +578,14 @@ static int sun8i_dwmac_init(struct platform_device *pdev, void *priv) } } - ret = clk_prepare_enable(gmac->tx_clk); - if (ret) { - dev_err(&pdev->dev, "Could not enable AHB clock\n"); - goto err_disable_regulator; - } - if (gmac->use_internal_phy) { ret = sun8i_dwmac_power_internal_phy(netdev_priv(ndev)); if (ret) - goto err_disable_clk; + goto err_disable_regulator; } return 0; -err_disable_clk: - clk_disable_unprepare(gmac->tx_clk); err_disable_regulator: if (gmac->regulator) regulator_disable(gmac->regulator); @@ -756,7 +747,7 @@ static int sun8i_dwmac_reset(struct stmmac_priv *priv) if (err) { dev_err(priv->device, "EMAC reset timeout\n"); - return -EFAULT; + return err; } return 0; } @@ -1043,8 +1034,6 @@ static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv) if (gmac->variant->soc_has_internal_phy) sun8i_dwmac_unpower_internal_phy(gmac); - clk_disable_unprepare(gmac->tx_clk); - if (gmac->regulator) regulator_disable(gmac->regulator); } @@ -1167,12 +1156,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) return -EINVAL; } - gmac->tx_clk = devm_clk_get(dev, "stmmaceth"); - if (IS_ERR(gmac->tx_clk)) { - dev_err(dev, "Could not get TX clock\n"); - return PTR_ERR(gmac->tx_clk); - } - /* Optional regulator for PHY */ gmac->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(gmac->regulator)) { @@ -1254,6 +1237,12 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) ndev = dev_get_drvdata(&pdev->dev); priv = netdev_priv(ndev); + /* the MAC is runtime suspended after stmmac_dvr_probe(), so we + * need to ensure the MAC resume back before other operations such + * as reset. + */ + pm_runtime_get_sync(&pdev->dev); + /* The mux must be registered after parent MDIO * so after stmmac_dvr_probe() */ @@ -1272,12 +1261,15 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) goto dwmac_remove; } + pm_runtime_put(&pdev->dev); + return 0; dwmac_mux: reset_control_put(gmac->rst_ephy); clk_put(gmac->ephy_clk); dwmac_remove: + pm_runtime_put_noidle(&pdev->dev); stmmac_dvr_remove(&pdev->dev); dwmac_exit: sun8i_dwmac_exit(pdev, gmac); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index e2e0f977875d..c3f10a92b62b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -22,21 +22,21 @@ #define ETHER_CLK_SEL_RMII_CLK_EN BIT(2) #define ETHER_CLK_SEL_RMII_CLK_RST BIT(3) #define ETHER_CLK_SEL_DIV_SEL_2 BIT(4) -#define ETHER_CLK_SEL_DIV_SEL_20 BIT(0) +#define ETHER_CLK_SEL_DIV_SEL_20 0 #define ETHER_CLK_SEL_FREQ_SEL_125M (BIT(9) | BIT(8)) #define ETHER_CLK_SEL_FREQ_SEL_50M BIT(9) #define ETHER_CLK_SEL_FREQ_SEL_25M BIT(8) #define ETHER_CLK_SEL_FREQ_SEL_2P5M 0 -#define ETHER_CLK_SEL_TX_CLK_EXT_SEL_IN BIT(0) +#define ETHER_CLK_SEL_TX_CLK_EXT_SEL_IN 0 #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC BIT(10) #define ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV BIT(11) -#define ETHER_CLK_SEL_RX_CLK_EXT_SEL_IN BIT(0) +#define ETHER_CLK_SEL_RX_CLK_EXT_SEL_IN 0 #define ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC BIT(12) #define ETHER_CLK_SEL_RX_CLK_EXT_SEL_DIV BIT(13) -#define ETHER_CLK_SEL_TX_CLK_O_TX_I BIT(0) +#define ETHER_CLK_SEL_TX_CLK_O_TX_I 0 #define ETHER_CLK_SEL_TX_CLK_O_RMII_I BIT(14) #define ETHER_CLK_SEL_TX_O_E_N_IN BIT(15) -#define ETHER_CLK_SEL_RMII_CLK_SEL_IN BIT(0) +#define ETHER_CLK_SEL_RMII_CLK_SEL_IN 0 #define ETHER_CLK_SEL_RMII_CLK_SEL_RX_C BIT(16) #define ETHER_CLK_SEL_RX_TX_CLK_EN (ETHER_CLK_SEL_RX_CLK_EN | ETHER_CLK_SEL_TX_CLK_EN) @@ -49,13 +49,15 @@ struct visconti_eth { void __iomem *reg; u32 phy_intf_sel; struct clk *phy_ref_clk; + struct device *dev; spinlock_t lock; /* lock to protect register update */ }; static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) { struct visconti_eth *dwmac = priv; - unsigned int val, clk_sel_val; + struct net_device *netdev = dev_get_drvdata(dwmac->dev); + unsigned int val, clk_sel_val = 0; unsigned long flags; spin_lock_irqsave(&dwmac->lock, flags); @@ -85,7 +87,9 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) break; default: /* No bit control */ - break; + netdev_err(netdev, "Unsupported speed request (%d)", speed); + spin_unlock_irqrestore(&dwmac->lock, flags); + return; } writel(val, dwmac->reg + MAC_CTRL_REG); @@ -96,31 +100,41 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) val |= ETHER_CLK_SEL_TX_O_E_N_IN; writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + /* Set Clock-Mux, Start clock, Set TX_O direction */ switch (dwmac->phy_intf_sel) { case ETHER_CONFIG_INTF_RGMII: val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + val |= ETHER_CLK_SEL_RX_TX_CLK_EN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + val &= ~ETHER_CLK_SEL_TX_O_E_N_IN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); break; case ETHER_CONFIG_INTF_RMII: val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_DIV | - ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC | ETHER_CLK_SEL_TX_O_E_N_IN | + ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV | ETHER_CLK_SEL_TX_O_E_N_IN | ETHER_CLK_SEL_RMII_CLK_SEL_RX_C; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + val |= ETHER_CLK_SEL_RMII_CLK_RST; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + val |= ETHER_CLK_SEL_RMII_CLK_EN | ETHER_CLK_SEL_RX_TX_CLK_EN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); break; case ETHER_CONFIG_INTF_MII: default: val = clk_sel_val | ETHER_CLK_SEL_RX_CLK_EXT_SEL_RXC | - ETHER_CLK_SEL_TX_CLK_EXT_SEL_DIV | ETHER_CLK_SEL_TX_O_E_N_IN | - ETHER_CLK_SEL_RMII_CLK_EN; + ETHER_CLK_SEL_TX_CLK_EXT_SEL_TXC | ETHER_CLK_SEL_TX_O_E_N_IN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); + + val |= ETHER_CLK_SEL_RX_TX_CLK_EN; + writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); break; } - /* Start clock */ - writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - val |= ETHER_CLK_SEL_RX_TX_CLK_EN; - writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - - val &= ~ETHER_CLK_SEL_TX_O_E_N_IN; - writel(val, dwmac->reg + REG_ETHER_CLOCK_SEL); - spin_unlock_irqrestore(&dwmac->lock, flags); } @@ -219,6 +233,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) spin_lock_init(&dwmac->lock); dwmac->reg = stmmac_res.addr; + dwmac->dev = &pdev->dev; plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 1914ad698cab..acd70b9a3173 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -150,6 +150,7 @@ #define NUM_DWMAC100_DMA_REGS 9 #define NUM_DWMAC1000_DMA_REGS 23 +#define NUM_DWMAC4_DMA_REGS 27 void dwmac_enable_dma_transmission(void __iomem *ioaddr); void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan, bool rx, bool tx); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 40b5ed94cb54..57970ae2178d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -194,7 +194,6 @@ struct stmmac_priv { u32 tx_coal_timer[MTL_MAX_TX_QUEUES]; u32 rx_coal_frames[MTL_MAX_TX_QUEUES]; - int tx_coalesce; int hwts_tx_en; bool tx_path_in_lpi_mode; bool tso; @@ -229,7 +228,6 @@ struct stmmac_priv { unsigned int flow_ctrl; unsigned int pause; struct mii_bus *mii; - int mii_irq[PHY_MAX_ADDR]; struct phylink_config phylink_config; struct phylink *phylink; @@ -265,7 +263,7 @@ struct stmmac_priv { u32 adv_ts; int use_riwt; int irq_wake; - spinlock_t ptp_lock; + rwlock_t ptp_lock; /* Protects auxiliary snapshot registers from concurrent access. */ struct mutex aux_ts_lock; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 164dff5ec32e..abfb3cd5958d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -21,10 +21,18 @@ #include "dwxgmac2.h" #define REG_SPACE_SIZE 0x1060 +#define GMAC4_REG_SPACE_SIZE 0x116C #define MAC100_ETHTOOL_NAME "st_mac100" #define GMAC_ETHTOOL_NAME "st_gmac" #define XGMAC_ETHTOOL_NAME "st_xgmac" +/* Same as DMA_CHAN_BASE_ADDR defined in dwmac4_dma.h + * + * It is here because dwmac_dma.h and dwmac4_dam.h can not be included at the + * same time due to the conflicting macro names. + */ +#define GMAC4_DMA_CHAN_BASE_ADDR 0x00001100 + #define ETHTOOL_DMA_OFFSET 55 struct stmmac_stats { @@ -434,6 +442,8 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev) if (priv->plat->has_xgmac) return XGMAC_REGSIZE * 4; + else if (priv->plat->has_gmac4) + return GMAC4_REG_SPACE_SIZE; return REG_SPACE_SIZE; } @@ -446,8 +456,13 @@ static void stmmac_ethtool_gregs(struct net_device *dev, stmmac_dump_mac_regs(priv, priv->hw, reg_space); stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); - if (!priv->plat->has_xgmac) { - /* Copy DMA registers to where ethtool expects them */ + /* Copy DMA registers to where ethtool expects them */ + if (priv->plat->has_gmac4) { + /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */ + memcpy(®_space[ETHTOOL_DMA_OFFSET], + ®_space[GMAC4_DMA_CHAN_BASE_ADDR / 4], + NUM_DWMAC4_DMA_REGS * 4); + } else if (!priv->plat->has_xgmac) { memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 074e2cdfb0fa..22fea0f67245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -145,15 +145,20 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, static void get_systime(void __iomem *ioaddr, u64 *systime) { - u64 ns; - - /* Get the TSSS value */ - ns = readl(ioaddr + PTP_STNSR); - /* Get the TSS and convert sec time value to nanosecond */ - ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; + u64 ns, sec0, sec1; + + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + do { + sec0 = sec1; + /* Get the TSSS value */ + ns = readl_relaxed(ioaddr + PTP_STNSR); + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + } while (sec0 != sec1); if (systime) - *systime = ns; + *systime = ns + (sec1 * 1000000000ULL); } static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) @@ -191,9 +196,9 @@ static void timestamp_interrupt(struct stmmac_priv *priv) GMAC_TIMESTAMP_ATSNS_SHIFT; for (i = 0; i < num_snapshot; i++) { - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); get_ptptime(priv->ptpaddr, &ptp_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); event.type = PTP_CLOCK_EXTTS; event.index = 0; event.timestamp = ptp_time; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 6708ca2aa4f7..b745d624b2cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -402,7 +402,7 @@ static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en) * Description: this function is to verify and enter in LPI mode in case of * EEE. */ -static void stmmac_enable_eee_mode(struct stmmac_priv *priv) +static int stmmac_enable_eee_mode(struct stmmac_priv *priv) { u32 tx_cnt = priv->plat->tx_queues_to_use; u32 queue; @@ -412,13 +412,14 @@ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue]; if (tx_q->dirty_tx != tx_q->cur_tx) - return; /* still unfinished work */ + return -EBUSY; /* still unfinished work */ } /* Check and enter in LPI mode */ if (!priv->tx_path_in_lpi_mode) stmmac_set_eee_mode(priv, priv->hw, priv->plat->en_tx_lpi_clockgating); + return 0; } /** @@ -450,8 +451,8 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) { struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer); - stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + if (stmmac_enable_eee_mode(priv)) + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /** @@ -889,6 +890,9 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; int ret; + if (priv->plat->ptp_clk_freq_config) + priv->plat->ptp_clk_freq_config(priv); + ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); if (ret) return ret; @@ -911,8 +915,6 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) priv->hwts_tx_en = 0; priv->hwts_rx_en = 0; - stmmac_ptp_register(priv); - return 0; } @@ -936,105 +938,15 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) priv->pause, tx_cnt); } -static void stmmac_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - __ETHTOOL_DECLARE_LINK_MODE_MASK(mac_supported) = { 0, }; - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - int tx_cnt = priv->plat->tx_queues_to_use; - int max_speed = priv->plat->max_speed; - - phylink_set(mac_supported, 10baseT_Half); - phylink_set(mac_supported, 10baseT_Full); - phylink_set(mac_supported, 100baseT_Half); - phylink_set(mac_supported, 100baseT_Full); - phylink_set(mac_supported, 1000baseT_Half); - phylink_set(mac_supported, 1000baseT_Full); - phylink_set(mac_supported, 1000baseKX_Full); - - phylink_set(mac_supported, Autoneg); - phylink_set(mac_supported, Pause); - phylink_set(mac_supported, Asym_Pause); - phylink_set_port_modes(mac_supported); - - /* Cut down 1G if asked to */ - if ((max_speed > 0) && (max_speed < 1000)) { - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); - } else if (priv->plat->has_gmac4) { - if (!max_speed || max_speed >= 2500) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - } else if (priv->plat->has_xgmac) { - if (!max_speed || (max_speed >= 2500)) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 2500baseX_Full); - } - if (!max_speed || (max_speed >= 5000)) { - phylink_set(mac_supported, 5000baseT_Full); - } - if (!max_speed || (max_speed >= 10000)) { - phylink_set(mac_supported, 10000baseSR_Full); - phylink_set(mac_supported, 10000baseLR_Full); - phylink_set(mac_supported, 10000baseER_Full); - phylink_set(mac_supported, 10000baseLRM_Full); - phylink_set(mac_supported, 10000baseT_Full); - phylink_set(mac_supported, 10000baseKX4_Full); - phylink_set(mac_supported, 10000baseKR_Full); - } - if (!max_speed || (max_speed >= 25000)) { - phylink_set(mac_supported, 25000baseCR_Full); - phylink_set(mac_supported, 25000baseKR_Full); - phylink_set(mac_supported, 25000baseSR_Full); - } - if (!max_speed || (max_speed >= 40000)) { - phylink_set(mac_supported, 40000baseKR4_Full); - phylink_set(mac_supported, 40000baseCR4_Full); - phylink_set(mac_supported, 40000baseSR4_Full); - phylink_set(mac_supported, 40000baseLR4_Full); - } - if (!max_speed || (max_speed >= 50000)) { - phylink_set(mac_supported, 50000baseCR2_Full); - phylink_set(mac_supported, 50000baseKR2_Full); - phylink_set(mac_supported, 50000baseSR2_Full); - phylink_set(mac_supported, 50000baseKR_Full); - phylink_set(mac_supported, 50000baseSR_Full); - phylink_set(mac_supported, 50000baseCR_Full); - phylink_set(mac_supported, 50000baseLR_ER_FR_Full); - phylink_set(mac_supported, 50000baseDR_Full); - } - if (!max_speed || (max_speed >= 100000)) { - phylink_set(mac_supported, 100000baseKR4_Full); - phylink_set(mac_supported, 100000baseSR4_Full); - phylink_set(mac_supported, 100000baseCR4_Full); - phylink_set(mac_supported, 100000baseLR4_ER4_Full); - phylink_set(mac_supported, 100000baseKR2_Full); - phylink_set(mac_supported, 100000baseSR2_Full); - phylink_set(mac_supported, 100000baseCR2_Full); - phylink_set(mac_supported, 100000baseLR2_ER2_FR2_Full); - phylink_set(mac_supported, 100000baseDR2_Full); - } - } - - /* Half-Duplex can only work with single queue */ - if (tx_cnt > 1) { - phylink_set(mask, 10baseT_Half); - phylink_set(mask, 100baseT_Half); - phylink_set(mask, 1000baseT_Half); - } - - linkmode_and(supported, supported, mac_supported); - linkmode_andnot(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mac_supported); - linkmode_andnot(state->advertising, state->advertising, mask); + if (!priv->hw->xpcs) + return NULL; - /* If PCS is supported, check which modes it supports. */ - if (priv->hw->xpcs) - xpcs_validate(priv->hw->xpcs, supported, state); + return &priv->hw->xpcs->pcs; } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, @@ -1173,7 +1085,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = stmmac_validate, + .validate = phylink_generic_validate, + .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, @@ -1253,12 +1166,12 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); + int max_speed = priv->plat->max_speed; int mode = priv->plat->phy_interface; struct phylink *phylink; priv->phylink_config.dev = &priv->dev->dev; priv->phylink_config.type = PHYLINK_NETDEV; - priv->phylink_config.pcs_poll = true; if (priv->plat->mdio_bus_data) priv->phylink_config.ovr_an_inband = mdio_bus_data->xpcs_an_inband; @@ -1266,14 +1179,50 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (!fwnode) fwnode = dev_fwnode(priv->device); + /* Set the platform/firmware specified interface mode */ + __set_bit(mode, priv->phylink_config.supported_interfaces); + + /* If we have an xpcs, it defines which PHY interfaces are supported. */ + if (priv->hw->xpcs) + xpcs_get_interfaces(priv->hw->xpcs, + priv->phylink_config.supported_interfaces); + + priv->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100; + + if (!max_speed || max_speed >= 1000) + priv->phylink_config.mac_capabilities |= MAC_1000; + + if (priv->plat->has_gmac4) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + } else if (priv->plat->has_xgmac) { + if (!max_speed || max_speed >= 2500) + priv->phylink_config.mac_capabilities |= MAC_2500FD; + if (!max_speed || max_speed >= 5000) + priv->phylink_config.mac_capabilities |= MAC_5000FD; + if (!max_speed || max_speed >= 10000) + priv->phylink_config.mac_capabilities |= MAC_10000FD; + if (!max_speed || max_speed >= 25000) + priv->phylink_config.mac_capabilities |= MAC_25000FD; + if (!max_speed || max_speed >= 40000) + priv->phylink_config.mac_capabilities |= MAC_40000FD; + if (!max_speed || max_speed >= 50000) + priv->phylink_config.mac_capabilities |= MAC_50000FD; + if (!max_speed || max_speed >= 100000) + priv->phylink_config.mac_capabilities |= MAC_100000FD; + } + + /* Half-Duplex can only work with single queue */ + if (priv->plat->tx_queues_to_use > 1) + priv->phylink_config.mac_capabilities &= + ~(MAC_10HD | MAC_100HD | MAC_1000HD); + phylink = phylink_create(&priv->phylink_config, fwnode, mode, &stmmac_phylink_mac_ops); if (IS_ERR(phylink)) return PTR_ERR(phylink); - if (priv->hw->xpcs) - phylink_set_pcs(phylink, &priv->hw->xpcs->pcs); - priv->phylink = phylink; return 0; } @@ -2647,8 +2596,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) if (priv->eee_enabled && !priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en) { - stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + if (stmmac_enable_eee_mode(priv)) + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /* We still have pending packets, let's call for a new scheduling */ @@ -3238,7 +3187,7 @@ static int stmmac_fpe_start_wq(struct stmmac_priv *priv) /** * stmmac_hw_setup - setup mac in a usable state. * @dev : pointer to the device structure. - * @init_ptp: initialize PTP if set + * @ptp_register: register PTP if set * Description: * this is the main function to setup the HW in a usable state because the * dma engine is reset, the core registers are configured (e.g. AXI, @@ -3248,7 +3197,7 @@ static int stmmac_fpe_start_wq(struct stmmac_priv *priv) * 0 on success and an appropriate (-)ve integer as defined in errno.h * file on failure. */ -static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) +static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) { struct stmmac_priv *priv = netdev_priv(dev); u32 rx_cnt = priv->plat->rx_queues_to_use; @@ -3305,13 +3254,13 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_mmc_setup(priv); - if (init_ptp) { - ret = stmmac_init_ptp(priv); - if (ret == -EOPNOTSUPP) - netdev_warn(priv->dev, "PTP not supported by HW\n"); - else if (ret) - netdev_warn(priv->dev, "PTP init failed\n"); - } + ret = stmmac_init_ptp(priv); + if (ret == -EOPNOTSUPP) + netdev_warn(priv->dev, "PTP not supported by HW\n"); + else if (ret) + netdev_warn(priv->dev, "PTP init failed\n"); + else if (ptp_register) + stmmac_ptp_register(priv); priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS; @@ -7250,6 +7199,10 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); + pm_runtime_get_sync(dev); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); + stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); @@ -7268,8 +7221,6 @@ int stmmac_dvr_remove(struct device *dev) if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); reset_control_assert(priv->plat->stmmac_ahb_rst); - pm_runtime_put(dev); - pm_runtime_disable(dev); if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 0d24ebd37873..e45fb191d8e6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -39,9 +39,9 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) diff = div_u64(adj, 1000000000ULL); addend = neg_adj ? (addend - diff) : (addend + diff); - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_config_addend(priv, priv->ptpaddr, addend); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); return 0; } @@ -86,9 +86,9 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) mutex_unlock(&priv->plat->est->lock); } - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); /* Caculate new basetime and re-configured EST after PTP time adjust. */ if (est_rst) { @@ -137,9 +137,9 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) unsigned long flags; u64 ns = 0; - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &ns); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); *ts = ns_to_timespec64(ns); @@ -162,9 +162,9 @@ static int stmmac_set_time(struct ptp_clock_info *ptp, container_of(ptp, struct stmmac_priv, ptp_clock_ops); unsigned long flags; - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); stmmac_init_systime(priv, priv->ptpaddr, ts->tv_sec, ts->tv_nsec); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); return 0; } @@ -194,12 +194,12 @@ static int stmmac_enable(struct ptp_clock_info *ptp, cfg->period.tv_sec = rq->perout.period.sec; cfg->period.tv_nsec = rq->perout.period.nsec; - spin_lock_irqsave(&priv->ptp_lock, flags); + write_lock_irqsave(&priv->ptp_lock, flags); ret = stmmac_flex_pps_config(priv, priv->ioaddr, rq->perout.index, cfg, on, priv->sub_second_inc, priv->systime_flags); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + write_unlock_irqrestore(&priv->ptp_lock, flags); break; case PTP_CLK_REQ_EXTTS: priv->plat->ext_snapshot_en = on; @@ -297,9 +297,6 @@ void stmmac_ptp_register(struct stmmac_priv *priv) { int i; - if (priv->plat->ptp_clk_freq_config) - priv->plat->ptp_clk_freq_config(priv); - for (i = 0; i < priv->dma_cap.pps_out_num; i++) { if (i >= STMMAC_PPS_MAX) break; @@ -317,7 +314,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv) stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num; stmmac_ptp_clock_ops.n_ext_ts = priv->dma_cap.aux_snapshot_n; - spin_lock_init(&priv->ptp_lock); + rwlock_init(&priv->ptp_lock); mutex_init(&priv->aux_ts_lock); priv->ptp_clock_ops = stmmac_ptp_clock_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index be3cb63675a5..9f1759593b94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1777,9 +1777,9 @@ static int stmmac_test_tbs(struct stmmac_priv *priv) if (ret) return ret; - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &curr_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); if (!curr_time) { ret = -EOPNOTSUPP; @@ -1799,9 +1799,9 @@ static int stmmac_test_tbs(struct stmmac_priv *priv) goto fail_disable; /* Check if expected time has elapsed */ - spin_lock_irqsave(&priv->ptp_lock, flags); + read_lock_irqsave(&priv->ptp_lock, flags); stmmac_get_systime(priv, priv->ptpaddr, &curr_time); - spin_unlock_irqrestore(&priv->ptp_lock, flags); + read_unlock_irqrestore(&priv->ptp_lock, flags); if ((curr_time - start_time) < STMMAC_TBS_LT_OFFSET) ret = -EINVAL; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index ba220593e6db..8f6817f346ba 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1146,7 +1146,7 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv) static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw, int size) { - struct page_pool_params pp_params; + struct page_pool_params pp_params = {}; struct page_pool *pool; pp_params.order = 0; diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index cf0917b29e30..5251fc324221 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1091,20 +1091,22 @@ static int tsi108_get_mac(struct net_device *dev) struct tsi108_prv_data *data = netdev_priv(dev); u32 word1 = TSI_READ(TSI108_MAC_ADDR1); u32 word2 = TSI_READ(TSI108_MAC_ADDR2); + u8 addr[ETH_ALEN]; /* Note that the octets are reversed from what the manual says, * producing an even weirder ordering... */ if (word2 == 0 && word1 == 0) { - dev->dev_addr[0] = 0x00; - dev->dev_addr[1] = 0x06; - dev->dev_addr[2] = 0xd2; - dev->dev_addr[3] = 0x00; - dev->dev_addr[4] = 0x00; + addr[0] = 0x00; + addr[1] = 0x06; + addr[2] = 0xd2; + addr[3] = 0x00; + addr[4] = 0x00; if (0x8 == data->phy) - dev->dev_addr[5] = 0x01; + addr[5] = 0x01; else - dev->dev_addr[5] = 0x02; + addr[5] = 0x02; + eth_hw_addr_set(dev, addr); word2 = (dev->dev_addr[0] << 16) | (dev->dev_addr[1] << 24); @@ -1114,12 +1116,13 @@ static int tsi108_get_mac(struct net_device *dev) TSI_WRITE(TSI108_MAC_ADDR1, word1); TSI_WRITE(TSI108_MAC_ADDR2, word2); } else { - dev->dev_addr[0] = (word2 >> 16) & 0xff; - dev->dev_addr[1] = (word2 >> 24) & 0xff; - dev->dev_addr[2] = (word1 >> 0) & 0xff; - dev->dev_addr[3] = (word1 >> 8) & 0xff; - dev->dev_addr[4] = (word1 >> 16) & 0xff; - dev->dev_addr[5] = (word1 >> 24) & 0xff; + addr[0] = (word2 >> 16) & 0xff; + addr[1] = (word2 >> 24) & 0xff; + addr[2] = (word1 >> 0) & 0xff; + addr[3] = (word1 >> 8) & 0xff; + addr[4] = (word1 >> 16) & 0xff; + addr[5] = (word1 >> 24) & 0xff; + eth_hw_addr_set(dev, addr); } if (!is_valid_ether_addr(dev->dev_addr)) { @@ -1136,14 +1139,12 @@ static int tsi108_set_mac(struct net_device *dev, void *addr) { struct tsi108_prv_data *data = netdev_priv(dev); u32 word1, word2; - int i; if (!is_valid_ether_addr(addr)) return -EADDRNOTAVAIL; - for (i = 0; i < 6; i++) - /* +2 is for the offset of the HW addr type */ - dev->dev_addr[i] = ((unsigned char *)addr)[i + 2]; + /* +2 is for the offset of the HW addr type */ + eth_hw_addr_set(dev, ((unsigned char *)addr) + 2); word2 = (dev->dev_addr[0] << 16) | (dev->dev_addr[1] << 24); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 5b4d153b1492..40108968b350 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -386,6 +386,7 @@ struct axidma_bd { * @phylink: Pointer to phylink instance * @phylink_config: phylink configuration settings * @pcs_phy: Reference to PCS/PMA PHY if used + * @pcs: phylink pcs structure for PCS PHY * @switch_x_sgmii: Whether switchable 1000BaseX/SGMII mode is enabled in the core * @axi_clk: AXI4-Lite bus clock * @misc_clks: Misc ethernet clocks (AXI4-Stream, Ref, MGT clocks) @@ -434,6 +435,7 @@ struct axienet_local { struct phylink_config phylink_config; struct mdio_device *pcs_phy; + struct phylink_pcs pcs; bool switch_x_sgmii; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 377c94ec2486..de0a6372ae0e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1537,78 +1537,78 @@ static const struct ethtool_ops axienet_ethtool_ops = { .nway_reset = axienet_ethtools_nway_reset, }; -static void axienet_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) { - struct net_device *ndev = to_net_dev(config->dev); - struct axienet_local *lp = netdev_priv(ndev); + return container_of(pcs, struct axienet_local, pcs); +} - switch (state->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - phylink_mii_c22_pcs_get_state(lp->pcs_phy, state); - break; - default: - break; - } +static void axienet_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; + + phylink_mii_c22_pcs_get_state(pcs_phy, state); } -static void axienet_mac_an_restart(struct phylink_config *config) +static void axienet_pcs_an_restart(struct phylink_pcs *pcs) { - struct net_device *ndev = to_net_dev(config->dev); - struct axienet_local *lp = netdev_priv(ndev); + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; - phylink_mii_c22_pcs_an_restart(lp->pcs_phy); + phylink_mii_c22_pcs_an_restart(pcs_phy); } -static int axienet_mac_prepare(struct phylink_config *config, unsigned int mode, - phy_interface_t iface) +static int axienet_pcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - struct net_device *ndev = to_net_dev(config->dev); + struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; + struct net_device *ndev = pcs_to_axienet_local(pcs)->ndev; struct axienet_local *lp = netdev_priv(ndev); int ret; - switch (iface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - if (!lp->switch_x_sgmii) - return 0; - - ret = mdiobus_write(lp->pcs_phy->bus, - lp->pcs_phy->addr, - XLNX_MII_STD_SELECT_REG, - iface == PHY_INTERFACE_MODE_SGMII ? + if (lp->switch_x_sgmii) { + ret = mdiodev_write(pcs_phy, XLNX_MII_STD_SELECT_REG, + interface == PHY_INTERFACE_MODE_SGMII ? XLNX_MII_STD_SELECT_SGMII : 0); - if (ret < 0) - netdev_warn(ndev, "Failed to switch PHY interface: %d\n", + if (ret < 0) { + netdev_warn(ndev, + "Failed to switch PHY interface: %d\n", ret); - return ret; - default: - return 0; + return ret; + } } + + ret = phylink_mii_c22_pcs_config(pcs_phy, mode, interface, advertising); + if (ret < 0) + netdev_warn(ndev, "Failed to configure PCS: %d\n", ret); + + return ret; } -static void axienet_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state) +static const struct phylink_pcs_ops axienet_pcs_ops = { + .pcs_get_state = axienet_pcs_get_state, + .pcs_config = axienet_pcs_config, + .pcs_an_restart = axienet_pcs_an_restart, +}; + +static struct phylink_pcs *axienet_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); - int ret; - switch (state->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode, - state->interface, - state->advertising); - if (ret < 0) - netdev_warn(ndev, "Failed to configure PCS: %d\n", - ret); - break; + if (interface == PHY_INTERFACE_MODE_1000BASEX || + interface == PHY_INTERFACE_MODE_SGMII) + return &lp->pcs; - default: - break; - } + return NULL; +} + +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, @@ -1663,9 +1663,7 @@ static void axienet_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops axienet_phylink_ops = { .validate = phylink_generic_validate, - .mac_pcs_get_state = axienet_mac_pcs_get_state, - .mac_an_restart = axienet_mac_an_restart, - .mac_prepare = axienet_mac_prepare, + .mac_select_pcs = axienet_mac_select_pcs, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, .mac_link_up = axienet_mac_link_up, @@ -2079,12 +2077,12 @@ static int axienet_probe(struct platform_device *pdev) ret = -EPROBE_DEFER; goto cleanup_mdio; } - lp->phylink_config.pcs_poll = true; + lp->pcs.ops = &axienet_pcs_ops; + lp->pcs.poll = true; } lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; - lp->phylink_config.legacy_pre_march2020 = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index ebd287039a54..5805e4a56385 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -1514,10 +1514,9 @@ acpi_find_extended_socket_device(acpi_handle obj_handle, u32 level, { struct acpi_device *device; bool *found = context; - int result; - result = acpi_bus_get_device(obj_handle, &device); - if (result) + device = acpi_fetch_acpi_dev(obj_handle); + if (!device) return AE_OK; if (strcmp(acpi_device_hid(device), ACPI_MOTHERBOARD_RESOURCE_HID)) diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 6376b8485976..980f2be32f05 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -950,9 +950,7 @@ static int yam_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __ ym = memdup_user(data, sizeof(struct yamdrv_ioctl_mcs)); if (IS_ERR(ym)) return PTR_ERR(ym); - if (ym->cmd != SIOCYAMSMCS) - return -EINVAL; - if (ym->bitrate > YAM_MAXBITRATE) { + if (ym->cmd != SIOCYAMSMCS || ym->bitrate > YAM_MAXBITRATE) { kfree(ym); return -EINVAL; } diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 7d67f41387f5..4f5ef8a9a9a8 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -100,6 +100,7 @@ struct at86rf230_local { unsigned long cal_timeout; bool is_tx; bool is_tx_from_off; + bool was_tx; u8 tx_retry; struct sk_buff *tx_skb; struct at86rf230_state_change tx; @@ -343,7 +344,11 @@ at86rf230_async_error_recover_complete(void *context) if (ctx->free) kfree(ctx); - ieee802154_wake_queue(lp->hw); + if (lp->was_tx) { + lp->was_tx = 0; + dev_kfree_skb_any(lp->tx_skb); + ieee802154_wake_queue(lp->hw); + } } static void @@ -352,7 +357,11 @@ at86rf230_async_error_recover(void *context) struct at86rf230_state_change *ctx = context; struct at86rf230_local *lp = ctx->lp; - lp->is_tx = 0; + if (lp->is_tx) { + lp->was_tx = 1; + lp->is_tx = 0; + } + at86rf230_async_state_change(lp, ctx, STATE_RX_AACK_ON, at86rf230_async_error_recover_complete); } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index ece6ff6049f6..f3438d3e104a 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1771,6 +1771,7 @@ static int ca8210_async_xmit_complete( status ); if (status != MAC_TRANSACTION_OVERFLOW) { + dev_kfree_skb_any(priv->tx_skb); ieee802154_wake_queue(priv->hw); return 0; } diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 8caa61ec718f..36f1c5aa98fc 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -786,6 +786,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, goto err_pib; } + pib->channel = 13; rcu_assign_pointer(phy->pib, pib); phy->idx = idx; INIT_LIST_HEAD(&phy->edges); diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 8dc04e2590b1..383231b85464 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -976,8 +976,8 @@ static void mcr20a_hw_setup(struct mcr20a_local *lp) dev_dbg(printdev(lp), "%s\n", __func__); phy->symbol_duration = 16; - phy->lifs_period = 40; - phy->sifs_period = 12; + phy->lifs_period = 40 * phy->symbol_duration; + phy->sifs_period = 12 * phy->symbol_duration; hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT | diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 1544564bc283..87e1d43c118c 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -320,6 +320,17 @@ gsi_trans_tre_release(struct gsi_trans_info *trans_info, u32 tre_count) atomic_add(tre_count, &trans_info->tre_avail); } +/* Return true if no transactions are allocated, false otherwise */ +bool gsi_channel_trans_idle(struct gsi *gsi, u32 channel_id) +{ + u32 tre_max = gsi_channel_tre_max(gsi, channel_id); + struct gsi_trans_info *trans_info; + + trans_info = &gsi->channel[channel_id].trans_info; + + return atomic_read(&trans_info->tre_avail) == tre_max; +} + /* Allocate a GSI transaction on a channel */ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, u32 tre_count, diff --git a/drivers/net/ipa/gsi_trans.h b/drivers/net/ipa/gsi_trans.h index 17fd1822d8a9..af379b49299e 100644 --- a/drivers/net/ipa/gsi_trans.h +++ b/drivers/net/ipa/gsi_trans.h @@ -130,6 +130,16 @@ void *gsi_trans_pool_alloc_dma(struct gsi_trans_pool *pool, dma_addr_t *addr); void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool); /** + * gsi_channel_trans_idle() - Return whether no transactions are allocated + * @gsi: GSI pointer + * @channel_id: Channel the transaction is associated with + * + * Return: True if no transactions are allocated, false otherwise + * + */ +bool gsi_channel_trans_idle(struct gsi *gsi, u32 channel_id); + +/** * gsi_channel_trans_alloc() - Allocate a GSI transaction on a channel * @gsi: GSI pointer * @channel_id: Channel the transaction is associated with diff --git a/drivers/net/ipa/ipa_data-v3.1.c b/drivers/net/ipa/ipa_data-v3.1.c index 06ddb85f39b2..8ff351aefd23 100644 --- a/drivers/net/ipa/ipa_data-v3.1.c +++ b/drivers/net/ipa/ipa_data-v3.1.c @@ -101,6 +101,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -148,6 +149,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v3.5.1.c b/drivers/net/ipa/ipa_data-v3.5.1.c index 760c22bbdf70..d1c466abddb2 100644 --- a/drivers/net/ipa/ipa_data-v3.5.1.c +++ b/drivers/net/ipa/ipa_data-v3.5.1.c @@ -92,6 +92,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -140,6 +141,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.11.c b/drivers/net/ipa/ipa_data-v4.11.c index fea91451a0c3..b1991cc6f0ca 100644 --- a/drivers/net/ipa/ipa_data-v4.11.c +++ b/drivers/net/ipa/ipa_data-v4.11.c @@ -86,6 +86,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -133,6 +134,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 32768, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.2.c b/drivers/net/ipa/ipa_data-v4.2.c index 2a231e79d5e1..1190a43e8743 100644 --- a/drivers/net/ipa/ipa_data-v4.2.c +++ b/drivers/net/ipa/ipa_data-v4.2.c @@ -82,6 +82,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -130,6 +131,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c index 2da2c4194f2e..944f72b0f285 100644 --- a/drivers/net/ipa/ipa_data-v4.5.c +++ b/drivers/net/ipa/ipa_data-v4.5.c @@ -95,6 +95,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -142,6 +143,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data-v4.9.c b/drivers/net/ipa/ipa_data-v4.9.c index 2421b5abb5d4..16786bff7ef8 100644 --- a/drivers/net/ipa/ipa_data-v4.9.c +++ b/drivers/net/ipa/ipa_data-v4.9.c @@ -87,6 +87,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .aggregation = true, .status_enable = true, .rx = { + .buffer_size = 8192, .pad_align = ilog2(sizeof(u32)), }, }, @@ -134,6 +135,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .qmap = true, .aggregation = true, .rx = { + .buffer_size = 8192, .aggr_close_eof = true, }, }, diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h index 6d329e9ce5d2..dbbeecf6df29 100644 --- a/drivers/net/ipa/ipa_data.h +++ b/drivers/net/ipa/ipa_data.h @@ -112,6 +112,7 @@ struct ipa_endpoint_tx_data { /** * struct ipa_endpoint_rx_data - configuration data for RX endpoints + * @buffer_size: requested receive buffer size (bytes) * @pad_align: power-of-2 boundary to which packet payload is aligned * @aggr_close_eof: whether aggregation closes on end-of-frame * @@ -125,6 +126,7 @@ struct ipa_endpoint_tx_data { * a "frame" consisting of several transfers has ended. */ struct ipa_endpoint_rx_data { + u32 buffer_size; u32 pad_align; bool aggr_close_eof; }; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 68291a3efd04..888e94278a84 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -25,10 +25,8 @@ #define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) -#define IPA_REPLENISH_BATCH 16 - -/* RX buffer is 1 page (or a power-of-2 contiguous pages) */ -#define IPA_RX_BUFFER_SIZE 8192 /* PAGE_SIZE > 4096 wastes a LOT */ +/* Hardware is told about receive buffers once a "batch" has been queued */ +#define IPA_REPLENISH_BATCH 16 /* Must be non-zero */ /* The amount of RX buffer space consumed by standard skb overhead */ #define IPA_RX_BUFFER_OVERHEAD (PAGE_SIZE - SKB_MAX_ORDER(NET_SKB_PAD, 0)) @@ -75,6 +73,14 @@ struct ipa_status { #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK GENMASK(31, 22) #define IPA_STATUS_FLAGS2_TAG_FMASK GENMASK_ULL(63, 16) +static u32 aggr_byte_limit_max(enum ipa_version version) +{ + if (version < IPA_VERSION_4_5) + return field_max(aggr_byte_limit_fmask(true)); + + return field_max(aggr_byte_limit_fmask(false)); +} + static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *all_data, const struct ipa_gsi_endpoint_data *data) @@ -87,6 +93,9 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return true; if (!data->toward_ipa) { + u32 buffer_size; + u32 limit; + if (data->endpoint.filter_support) { dev_err(dev, "filtering not supported for " "RX endpoint %u\n", @@ -94,6 +103,41 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return false; } + /* Nothing more to check for non-AP RX */ + if (data->ee_id != GSI_EE_AP) + return true; + + buffer_size = data->endpoint.config.rx.buffer_size; + /* The buffer size must hold an MTU plus overhead */ + limit = IPA_MTU + IPA_RX_BUFFER_OVERHEAD; + if (buffer_size < limit) { + dev_err(dev, "RX buffer size too small for RX endpoint %u (%u < %u)\n", + data->endpoint_id, buffer_size, limit); + return false; + } + + /* For an endpoint supporting receive aggregation, the + * aggregation byte limit defines the point at which an + * aggregation window will close. It is programmed into the + * IPA hardware as a number of KB. We don't use "hard byte + * limit" aggregation, so we need to supply enough space in + * a receive buffer to hold a complete MTU plus normal skb + * overhead *after* that aggregation byte limit has been + * crossed. + * + * This check just ensures the receive buffer size doesn't + * exceed what's representable in the aggregation limit field. + */ + if (data->endpoint.config.aggregation) { + limit += SZ_1K * aggr_byte_limit_max(ipa->version); + if (buffer_size > limit) { + dev_err(dev, "RX buffer size too large for aggregated RX endpoint %u (%u > %u)\n", + data->endpoint_id, buffer_size, limit); + + return false; + } + } + return true; /* Nothing more to check for RX */ } @@ -156,21 +200,12 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, return true; } -static u32 aggr_byte_limit_max(enum ipa_version version) -{ - if (version < IPA_VERSION_4_5) - return field_max(aggr_byte_limit_fmask(true)); - - return field_max(aggr_byte_limit_fmask(false)); -} - static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data) { const struct ipa_gsi_endpoint_data *dp = data; struct device *dev = &ipa->pdev->dev; enum ipa_endpoint_name name; - u32 limit; if (count > IPA_ENDPOINT_COUNT) { dev_err(dev, "too many endpoints specified (%u > %u)\n", @@ -178,26 +213,6 @@ static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, return false; } - /* The aggregation byte limit defines the point at which an - * aggregation window will close. It is programmed into the - * IPA hardware as a number of KB. We don't use "hard byte - * limit" aggregation, which means that we need to supply - * enough space in a receive buffer to hold a complete MTU - * plus normal skb overhead *after* that aggregation byte - * limit has been crossed. - * - * This check ensures we don't define a receive buffer size - * that would exceed what we can represent in the field that - * is used to program its size. - */ - limit = aggr_byte_limit_max(ipa->version) * SZ_1K; - limit += IPA_MTU + IPA_RX_BUFFER_OVERHEAD; - if (limit < IPA_RX_BUFFER_SIZE) { - dev_err(dev, "buffer size too big for aggregation (%u > %u)\n", - IPA_RX_BUFFER_SIZE, limit); - return false; - } - /* Make sure needed endpoints have defined data */ if (ipa_gsi_endpoint_data_empty(&data[IPA_ENDPOINT_AP_COMMAND_TX])) { dev_err(dev, "command TX endpoint not defined\n"); @@ -723,13 +738,15 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) if (endpoint->data->aggregation) { if (!endpoint->toward_ipa) { + const struct ipa_endpoint_rx_data *rx_data; bool close_eof; u32 limit; + rx_data = &endpoint->data->rx; val |= u32_encode_bits(IPA_ENABLE_AGGR, AGGR_EN_FMASK); val |= u32_encode_bits(IPA_GENERIC, AGGR_TYPE_FMASK); - limit = ipa_aggr_size_kb(IPA_RX_BUFFER_SIZE); + limit = ipa_aggr_size_kb(rx_data->buffer_size); val |= aggr_byte_limit_encoded(version, limit); limit = IPA_AGGR_TIME_LIMIT; @@ -737,7 +754,7 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) /* AGGR_PKT_LIMIT is 0 (unlimited) */ - close_eof = endpoint->data->rx.aggr_close_eof; + close_eof = rx_data->aggr_close_eof; val |= aggr_sw_eof_active_encoded(version, close_eof); /* AGGR_HARD_BYTE_LIMIT_ENABLE is 0 */ @@ -1020,134 +1037,98 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) iowrite32(val, ipa->reg_virt + offset); } -static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint) +static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint, + struct gsi_trans *trans) { - struct gsi_trans *trans; - bool doorbell = false; struct page *page; + u32 buffer_size; u32 offset; u32 len; int ret; - page = dev_alloc_pages(get_order(IPA_RX_BUFFER_SIZE)); + buffer_size = endpoint->data->rx.buffer_size; + page = dev_alloc_pages(get_order(buffer_size)); if (!page) return -ENOMEM; - trans = ipa_endpoint_trans_alloc(endpoint, 1); - if (!trans) - goto err_free_pages; - /* Offset the buffer to make space for skb headroom */ offset = NET_SKB_PAD; - len = IPA_RX_BUFFER_SIZE - offset; + len = buffer_size - offset; ret = gsi_trans_page_add(trans, page, len, offset); if (ret) - goto err_trans_free; - trans->data = page; /* transaction owns page now */ - - if (++endpoint->replenish_ready == IPA_REPLENISH_BATCH) { - doorbell = true; - endpoint->replenish_ready = 0; - } - - gsi_trans_commit(trans, doorbell); - - return 0; - -err_trans_free: - gsi_trans_free(trans); -err_free_pages: - __free_pages(page, get_order(IPA_RX_BUFFER_SIZE)); + __free_pages(page, get_order(buffer_size)); + else + trans->data = page; /* transaction owns page now */ - return -ENOMEM; + return ret; } /** * ipa_endpoint_replenish() - Replenish endpoint receive buffers * @endpoint: Endpoint to be replenished - * @add_one: Whether this is replacing a just-consumed buffer * * The IPA hardware can hold a fixed number of receive buffers for an RX * endpoint, based on the number of entries in the underlying channel ring * buffer. If an endpoint's "backlog" is non-zero, it indicates how many * more receive buffers can be supplied to the hardware. Replenishing for - * an endpoint can be disabled, in which case requests to replenish a - * buffer are "saved", and transferred to the backlog once it is re-enabled - * again. + * an endpoint can be disabled, in which case buffers are not queued to + * the hardware. */ -static void ipa_endpoint_replenish(struct ipa_endpoint *endpoint, bool add_one) +static void ipa_endpoint_replenish(struct ipa_endpoint *endpoint) { - struct gsi *gsi; - u32 backlog; - int delta; + struct gsi_trans *trans; - if (!test_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags)) { - if (add_one) - atomic_inc(&endpoint->replenish_saved); + if (!test_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags)) return; - } - /* If already active, just update the backlog */ - if (test_and_set_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags)) { - if (add_one) - atomic_inc(&endpoint->replenish_backlog); + /* Skip it if it's already active */ + if (test_and_set_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags)) return; - } - while (atomic_dec_not_zero(&endpoint->replenish_backlog)) - if (ipa_endpoint_replenish_one(endpoint)) + while ((trans = ipa_endpoint_trans_alloc(endpoint, 1))) { + bool doorbell; + + if (ipa_endpoint_replenish_one(endpoint, trans)) goto try_again_later; - clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - if (add_one) - atomic_inc(&endpoint->replenish_backlog); + /* Ring the doorbell if we've got a full batch */ + doorbell = !(++endpoint->replenish_count % IPA_REPLENISH_BATCH); + gsi_trans_commit(trans, doorbell); + } + + clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); return; try_again_later: + gsi_trans_free(trans); clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - /* The last one didn't succeed, so fix the backlog */ - delta = add_one ? 2 : 1; - backlog = atomic_add_return(delta, &endpoint->replenish_backlog); - /* Whenever a receive buffer transaction completes we'll try to * replenish again. It's unlikely, but if we fail to supply even * one buffer, nothing will trigger another replenish attempt. - * Receive buffer transactions use one TRE, so schedule work to - * try replenishing again if our backlog is *all* available TREs. + * If the hardware has no receive buffers queued, schedule work to + * try replenishing again. */ - gsi = &endpoint->ipa->gsi; - if (backlog == gsi_channel_tre_max(gsi, endpoint->channel_id)) + if (gsi_channel_trans_idle(&endpoint->ipa->gsi, endpoint->channel_id)) schedule_delayed_work(&endpoint->replenish_work, msecs_to_jiffies(1)); } static void ipa_endpoint_replenish_enable(struct ipa_endpoint *endpoint) { - struct gsi *gsi = &endpoint->ipa->gsi; - u32 max_backlog; - u32 saved; - set_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); - while ((saved = atomic_xchg(&endpoint->replenish_saved, 0))) - atomic_add(saved, &endpoint->replenish_backlog); /* Start replenishing if hardware currently has no buffers */ - max_backlog = gsi_channel_tre_max(gsi, endpoint->channel_id); - if (atomic_read(&endpoint->replenish_backlog) == max_backlog) - ipa_endpoint_replenish(endpoint, false); + if (gsi_channel_trans_idle(&endpoint->ipa->gsi, endpoint->channel_id)) + ipa_endpoint_replenish(endpoint); } static void ipa_endpoint_replenish_disable(struct ipa_endpoint *endpoint) { - u32 backlog; - clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); - while ((backlog = atomic_xchg(&endpoint->replenish_backlog, 0))) - atomic_add(backlog, &endpoint->replenish_saved); } static void ipa_endpoint_replenish_work(struct work_struct *work) @@ -1157,7 +1138,7 @@ static void ipa_endpoint_replenish_work(struct work_struct *work) endpoint = container_of(dwork, struct ipa_endpoint, replenish_work); - ipa_endpoint_replenish(endpoint, false); + ipa_endpoint_replenish(endpoint); } static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, @@ -1183,15 +1164,16 @@ static void ipa_endpoint_skb_copy(struct ipa_endpoint *endpoint, static bool ipa_endpoint_skb_build(struct ipa_endpoint *endpoint, struct page *page, u32 len) { + u32 buffer_size = endpoint->data->rx.buffer_size; struct sk_buff *skb; /* Nothing to do if there's no netdev */ if (!endpoint->netdev) return false; - WARN_ON(len > SKB_WITH_OVERHEAD(IPA_RX_BUFFER_SIZE - NET_SKB_PAD)); + WARN_ON(len > SKB_WITH_OVERHEAD(buffer_size - NET_SKB_PAD)); - skb = build_skb(page_address(page), IPA_RX_BUFFER_SIZE); + skb = build_skb(page_address(page), buffer_size); if (skb) { /* Reserve the headroom and account for the data */ skb_reserve(skb, NET_SKB_PAD); @@ -1289,8 +1271,9 @@ static bool ipa_endpoint_status_drop(struct ipa_endpoint *endpoint, static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, struct page *page, u32 total_len) { + u32 buffer_size = endpoint->data->rx.buffer_size; void *data = page_address(page) + NET_SKB_PAD; - u32 unused = IPA_RX_BUFFER_SIZE - total_len; + u32 unused = buffer_size - total_len; u32 resid = total_len; while (resid) { @@ -1360,10 +1343,8 @@ static void ipa_endpoint_rx_complete(struct ipa_endpoint *endpoint, { struct page *page; - ipa_endpoint_replenish(endpoint, true); - if (trans->cancelled) - return; + goto done; /* Parse or build a socket buffer using the actual received length */ page = trans->data; @@ -1371,6 +1352,8 @@ static void ipa_endpoint_rx_complete(struct ipa_endpoint *endpoint, ipa_endpoint_status_parse(endpoint, page, trans->len); else if (ipa_endpoint_skb_build(endpoint, page, trans->len)) trans->data = NULL; /* Pages have been consumed */ +done: + ipa_endpoint_replenish(endpoint); } void ipa_endpoint_trans_complete(struct ipa_endpoint *endpoint, @@ -1398,8 +1381,11 @@ void ipa_endpoint_trans_release(struct ipa_endpoint *endpoint, } else { struct page *page = trans->data; - if (page) - __free_pages(page, get_order(IPA_RX_BUFFER_SIZE)); + if (page) { + u32 buffer_size = endpoint->data->rx.buffer_size; + + __free_pages(page, get_order(buffer_size)); + } } } @@ -1704,9 +1690,6 @@ static void ipa_endpoint_setup_one(struct ipa_endpoint *endpoint) */ clear_bit(IPA_REPLENISH_ENABLED, endpoint->replenish_flags); clear_bit(IPA_REPLENISH_ACTIVE, endpoint->replenish_flags); - atomic_set(&endpoint->replenish_saved, - gsi_channel_tre_max(gsi, endpoint->channel_id)); - atomic_set(&endpoint->replenish_backlog, 0); INIT_DELAYED_WORK(&endpoint->replenish_work, ipa_endpoint_replenish_work); } @@ -1882,6 +1865,8 @@ u32 ipa_endpoint_init(struct ipa *ipa, u32 count, enum ipa_endpoint_name name; u32 filter_map; + BUILD_BUG_ON(!IPA_REPLENISH_BATCH); + if (!ipa_endpoint_data_valid(ipa, count, data)) return 0; /* Error */ diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h index 0313cdc607de..12fd5b16c18e 100644 --- a/drivers/net/ipa/ipa_endpoint.h +++ b/drivers/net/ipa/ipa_endpoint.h @@ -65,9 +65,7 @@ enum ipa_replenish_flag { * @evt_ring_id: GSI event ring used by the endpoint * @netdev: Network device pointer, if endpoint uses one * @replenish_flags: Replenishing state flags - * @replenish_ready: Number of replenish transactions without doorbell - * @replenish_saved: Replenish requests held while disabled - * @replenish_backlog: Number of buffers needed to fill hardware queue + * @replenish_count: Total number of replenish transactions committed * @replenish_work: Work item used for repeated replenish failures */ struct ipa_endpoint { @@ -86,9 +84,7 @@ struct ipa_endpoint { /* Receive buffer replenishing for RX endpoints */ DECLARE_BITMAP(replenish_flags, IPA_REPLENISH_COUNT); - u32 replenish_ready; - atomic_t replenish_saved; - atomic_t replenish_backlog; + u64 replenish_count; struct delayed_work replenish_work; /* global wq */ }; diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index b1c6c0fcb654..f2989aac47a6 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -11,6 +11,8 @@ #include <linux/pm_runtime.h> #include <linux/bitops.h> +#include "linux/soc/qcom/qcom_aoss.h" + #include "ipa.h" #include "ipa_power.h" #include "ipa_endpoint.h" @@ -64,6 +66,7 @@ enum ipa_power_flag { * struct ipa_power - IPA power management information * @dev: IPA device pointer * @core: IPA core clock + * @qmp: QMP handle for AOSS communication * @spinlock: Protects modem TX queue enable/disable * @flags: Boolean state flags * @interconnect_count: Number of elements in interconnect[] @@ -72,6 +75,7 @@ enum ipa_power_flag { struct ipa_power { struct device *dev; struct clk *core; + struct qmp *qmp; spinlock_t spinlock; /* used with STOPPED/STARTED power flags */ DECLARE_BITMAP(flags, IPA_POWER_FLAG_COUNT); u32 interconnect_count; @@ -382,6 +386,47 @@ void ipa_power_modem_queue_active(struct ipa *ipa) clear_bit(IPA_POWER_FLAG_STARTED, ipa->power->flags); } +static int ipa_power_retention_init(struct ipa_power *power) +{ + struct qmp *qmp = qmp_get(power->dev); + + if (IS_ERR(qmp)) { + if (PTR_ERR(qmp) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + /* We assume any other error means it's not defined/needed */ + qmp = NULL; + } + power->qmp = qmp; + + return 0; +} + +static void ipa_power_retention_exit(struct ipa_power *power) +{ + qmp_put(power->qmp); + power->qmp = NULL; +} + +/* Control register retention on power collapse */ +void ipa_power_retention(struct ipa *ipa, bool enable) +{ + static const char fmt[] = "{ class: bcm, res: ipa_pc, val: %c }"; + struct ipa_power *power = ipa->power; + char buf[36]; /* Exactly enough for fmt[]; size a multiple of 4 */ + int ret; + + if (!power->qmp) + return; /* Not needed on this platform */ + + (void)snprintf(buf, sizeof(buf), fmt, enable ? '1' : '0'); + + ret = qmp_send(power->qmp, buf, sizeof(buf)); + if (ret) + dev_err(power->dev, "error %d sending QMP %sable request\n", + ret, enable ? "en" : "dis"); +} + int ipa_power_setup(struct ipa *ipa) { int ret; @@ -438,12 +483,18 @@ ipa_power_init(struct device *dev, const struct ipa_power_data *data) if (ret) goto err_kfree; + ret = ipa_power_retention_init(power); + if (ret) + goto err_interconnect_exit; + pm_runtime_set_autosuspend_delay(dev, IPA_AUTOSUSPEND_DELAY); pm_runtime_use_autosuspend(dev); pm_runtime_enable(dev); return power; +err_interconnect_exit: + ipa_interconnect_exit(power); err_kfree: kfree(power); err_clk_put: @@ -460,6 +511,7 @@ void ipa_power_exit(struct ipa_power *power) pm_runtime_disable(dev); pm_runtime_dont_use_autosuspend(dev); + ipa_power_retention_exit(power); ipa_interconnect_exit(power); kfree(power); clk_put(clk); diff --git a/drivers/net/ipa/ipa_power.h b/drivers/net/ipa/ipa_power.h index 2151805d7fbb..6f84f057a209 100644 --- a/drivers/net/ipa/ipa_power.h +++ b/drivers/net/ipa/ipa_power.h @@ -41,6 +41,13 @@ void ipa_power_modem_queue_wake(struct ipa *ipa); void ipa_power_modem_queue_active(struct ipa *ipa); /** + * ipa_power_retention() - Control register retention on power collapse + * @ipa: IPA pointer + * @enable: Whether retention should be enabled or disabled + */ +void ipa_power_retention(struct ipa *ipa, bool enable); + +/** * ipa_power_setup() - Set up IPA power management * @ipa: IPA pointer * diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 856e55a080a7..fe11910518d9 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -11,6 +11,7 @@ #include "ipa.h" #include "ipa_uc.h" +#include "ipa_power.h" /** * DOC: The IPA embedded microcontroller @@ -154,6 +155,7 @@ static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id) case IPA_UC_RESPONSE_INIT_COMPLETED: if (ipa->uc_powered) { ipa->uc_loaded = true; + ipa_power_retention(ipa, true); pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); ipa->uc_powered = false; @@ -184,6 +186,9 @@ void ipa_uc_deconfig(struct ipa *ipa) ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_1); ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_0); + if (ipa->uc_loaded) + ipa_power_retention(ipa, false); + if (!ipa->uc_powered) return; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 16aa3a478e9e..3d0874331763 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3870,6 +3870,18 @@ static void macsec_common_dellink(struct net_device *dev, struct list_head *head struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; + /* If h/w offloading is available, propagate to the device */ + if (macsec_is_offloaded(macsec)) { + const struct macsec_ops *ops; + struct macsec_context ctx; + + ops = macsec_get_ops(netdev_priv(dev), &ctx); + if (ops) { + ctx.secy = &macsec->secy; + macsec_offload(ops->mdo_del_secy, &ctx); + } + } + unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); macsec_del_dev(macsec); @@ -3884,18 +3896,6 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); - /* If h/w offloading is available, propagate to the device */ - if (macsec_is_offloaded(macsec)) { - const struct macsec_ops *ops; - struct macsec_context ctx; - - ops = macsec_get_ops(netdev_priv(dev), &ctx); - if (ops) { - ctx.secy = &macsec->secy; - macsec_offload(ops->mdo_del_secy, &ctx); - } - } - macsec_common_dellink(dev, head); if (list_empty(&rxd->secys)) { @@ -4018,6 +4018,15 @@ static int macsec_newlink(struct net *net, struct net_device *dev, !macsec_check_offload(macsec->offload, macsec)) return -EOPNOTSUPP; + /* send_sci must be set to true when transmit sci explicitly is set */ + if ((data && data[IFLA_MACSEC_SCI]) && + (data && data[IFLA_MACSEC_INC_SCI])) { + u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); + + if (!send_sci) + return -EINVAL; + } + if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); mtu = real_dev->mtu - icv_len - macsec_extra_len(true); diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c index 7ab4e26db08c..7aafc221b5cf 100644 --- a/drivers/net/mdio/mdio-xgene.c +++ b/drivers/net/mdio/mdio-xgene.c @@ -285,7 +285,8 @@ static acpi_status acpi_register_phy(acpi_handle handle, u32 lvl, const union acpi_object *obj; u32 phy_addr; - if (acpi_bus_get_device(handle, &adev)) + adev = acpi_fetch_acpi_dev(handle); + if (!adev) return AE_OK; if (acpi_dev_get_property(adev, "phy-channel", ACPI_TYPE_INTEGER, &obj)) diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index cd6742e6ba8b..61418d4dc0cd 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -632,35 +632,43 @@ static void xpcs_resolve_pma(struct dw_xpcs *xpcs, } } -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state) +static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported) = { 0, }; const struct xpcs_compat *compat; + struct dw_xpcs *xpcs; int i; - /* phylink expects us to report all supported modes with - * PHY_INTERFACE_MODE_NA, just don't limit the supported and - * advertising masks and exit. - */ - if (state->interface == PHY_INTERFACE_MODE_NA) - return; - - linkmode_zero(xpcs_supported); - + xpcs = phylink_pcs_to_xpcs(pcs); compat = xpcs_find_compat(xpcs->id, state->interface); - /* Populate the supported link modes for this - * PHY interface type + /* Populate the supported link modes for this PHY interface type. + * FIXME: what about the port modes and autoneg bit? This masks + * all those away. */ if (compat) for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) set_bit(compat->supported[i], xpcs_supported); linkmode_and(supported, supported, xpcs_supported); - linkmode_and(state->advertising, state->advertising, xpcs_supported); + + return 0; +} + +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces) +{ + int i, j; + + for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) { + const struct xpcs_compat *compat = &xpcs->id->compat[i]; + + for (j = 0; j < compat->num_interfaces; j++) + if (compat->interface[j] < PHY_INTERFACE_MODE_MAX) + __set_bit(compat->interface[j], interfaces); + } } -EXPORT_SYMBOL_GPL(xpcs_validate); +EXPORT_SYMBOL_GPL(xpcs_get_interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) { @@ -1106,6 +1114,7 @@ static const struct xpcs_id xpcs_id_list[] = { }; static const struct phylink_pcs_ops xpcs_phylink_ops = { + .pcs_validate = xpcs_validate, .pcs_config = xpcs_config, .pcs_get_state = xpcs_get_state, .pcs_link_up = xpcs_link_up, diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 968dd43a2b1e..a8db1a19011b 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -533,9 +533,7 @@ static int aqcs109_config_init(struct phy_device *phydev) * PMA speed ability bits are the same for all members of the family, * AQCS109 however supports speeds up to 2.5G only. */ - ret = phy_set_max_speed(phydev, SPEED_2500); - if (ret) - return ret; + phy_set_max_speed(phydev, SPEED_2500); return aqr107_set_downshift(phydev, MDIO_AN_VEND_PROV_DOWNSHIFT_DFLT); } diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 5b6c0d120e09..73926006d319 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -19,6 +19,8 @@ #include <linux/regulator/of_regulator.h> #include <linux/regulator/driver.h> #include <linux/regulator/consumer.h> +#include <linux/phylink.h> +#include <linux/sfp.h> #include <dt-bindings/net/qca-ar803x.h> #define AT803X_SPECIFIC_FUNCTION_CONTROL 0x10 @@ -51,6 +53,8 @@ #define AT803X_INTR_ENABLE_PAGE_RECEIVED BIT(12) #define AT803X_INTR_ENABLE_LINK_FAIL BIT(11) #define AT803X_INTR_ENABLE_LINK_SUCCESS BIT(10) +#define AT803X_INTR_ENABLE_LINK_FAIL_BX BIT(8) +#define AT803X_INTR_ENABLE_LINK_SUCCESS_BX BIT(7) #define AT803X_INTR_ENABLE_WIRESPEED_DOWNGRADE BIT(5) #define AT803X_INTR_ENABLE_POLARITY_CHANGED BIT(1) #define AT803X_INTR_ENABLE_WOL BIT(0) @@ -85,7 +89,17 @@ #define AT803X_DEBUG_DATA 0x1E #define AT803X_MODE_CFG_MASK 0x0F -#define AT803X_MODE_CFG_SGMII 0x01 +#define AT803X_MODE_CFG_BASET_RGMII 0x00 +#define AT803X_MODE_CFG_BASET_SGMII 0x01 +#define AT803X_MODE_CFG_BX1000_RGMII_50OHM 0x02 +#define AT803X_MODE_CFG_BX1000_RGMII_75OHM 0x03 +#define AT803X_MODE_CFG_BX1000_CONV_50OHM 0x04 +#define AT803X_MODE_CFG_BX1000_CONV_75OHM 0x05 +#define AT803X_MODE_CFG_FX100_RGMII_50OHM 0x06 +#define AT803X_MODE_CFG_FX100_CONV_50OHM 0x07 +#define AT803X_MODE_CFG_RGMII_AUTO_MDET 0x0B +#define AT803X_MODE_CFG_FX100_RGMII_75OHM 0x0E +#define AT803X_MODE_CFG_FX100_CONV_75OHM 0x0F #define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ #define AT803X_PSSR_MR_AN_COMPLETE 0x0200 @@ -283,6 +297,8 @@ struct at803x_priv { u16 clk_25m_mask; u8 smarteee_lpi_tw_1g; u8 smarteee_lpi_tw_100m; + bool is_fiber; + bool is_1000basex; struct regulator_dev *vddio_rdev; struct regulator_dev *vddh_rdev; struct regulator *vddio; @@ -650,6 +666,55 @@ static int at8031_register_regulators(struct phy_device *phydev) return 0; } +static int at803x_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +{ + struct phy_device *phydev = upstream; + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support); + __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); + phy_interface_t iface; + + linkmode_zero(phy_support); + phylink_set(phy_support, 1000baseX_Full); + phylink_set(phy_support, 1000baseT_Full); + phylink_set(phy_support, Autoneg); + phylink_set(phy_support, Pause); + phylink_set(phy_support, Asym_Pause); + + linkmode_zero(sfp_support); + sfp_parse_support(phydev->sfp_bus, id, sfp_support); + /* Some modules support 10G modes as well as others we support. + * Mask out non-supported modes so the correct interface is picked. + */ + linkmode_and(sfp_support, phy_support, sfp_support); + + if (linkmode_empty(sfp_support)) { + dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n"); + return -EINVAL; + } + + iface = sfp_select_interface(phydev->sfp_bus, sfp_support); + + /* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes + * interface for use with SFP modules. + * However, some copper modules detected as having a preferred SGMII + * interface do default to and function in 1000Base-X mode, so just + * print a warning and allow such modules, as they may have some chance + * of working. + */ + if (iface == PHY_INTERFACE_MODE_SGMII) + dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n"); + else if (iface != PHY_INTERFACE_MODE_1000BASEX) + return -EINVAL; + + return 0; +} + +static const struct sfp_upstream_ops at803x_sfp_ops = { + .attach = phy_sfp_attach, + .detach = phy_sfp_detach, + .module_insert = at803x_sfp_insert, +}; + static int at803x_parse_dt(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -757,6 +822,11 @@ static int at803x_parse_dt(struct phy_device *phydev) phydev_err(phydev, "failed to get VDDIO regulator\n"); return PTR_ERR(priv->vddio); } + + /* Only AR8031/8033 support 1000Base-X for SFP modules */ + ret = phy_sfp_probe(phydev, &at803x_sfp_ops); + if (ret < 0) + return ret; } return 0; @@ -784,16 +854,24 @@ static int at803x_probe(struct phy_device *phydev) return ret; } - /* Some bootloaders leave the fiber page selected. - * Switch to the copper page, as otherwise we read - * the PHY capabilities from the fiber side. - */ if (phydev->drv->phy_id == ATH8031_PHY_ID) { - phy_lock_mdio_bus(phydev); - ret = at803x_write_page(phydev, AT803X_PAGE_COPPER); - phy_unlock_mdio_bus(phydev); - if (ret) + int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); + int mode_cfg; + + if (ccr < 0) goto err; + mode_cfg = ccr & AT803X_MODE_CFG_MASK; + + switch (mode_cfg) { + case AT803X_MODE_CFG_BX1000_RGMII_50OHM: + case AT803X_MODE_CFG_BX1000_RGMII_75OHM: + priv->is_1000basex = true; + fallthrough; + case AT803X_MODE_CFG_FX100_RGMII_50OHM: + case AT803X_MODE_CFG_FX100_RGMII_75OHM: + priv->is_fiber = true; + break; + } } return 0; @@ -815,6 +893,7 @@ static void at803x_remove(struct phy_device *phydev) static int at803x_get_features(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err; err = genphy_read_abilities(phydev); @@ -841,12 +920,13 @@ static int at803x_get_features(struct phy_device *phydev) * As a result of that, ESTATUS_1000_XFULL is set * to 1 even when operating in copper TP mode. * - * Remove this mode from the supported link modes, - * as this driver currently only supports copper - * operation. + * Remove this mode from the supported link modes + * when not operating in 1000BaseX mode. */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, - phydev->supported); + if (!priv->is_1000basex) + linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + phydev->supported); + return 0; } @@ -910,8 +990,27 @@ static int at8031_pll_config(struct phy_device *phydev) static int at803x_config_init(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int ret; + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + /* Some bootloaders leave the fiber page selected. + * Switch to the appropriate page (fiber or copper), as otherwise we + * read the PHY capabilities from the wrong page. + */ + phy_lock_mdio_bus(phydev); + ret = at803x_write_page(phydev, + priv->is_fiber ? AT803X_PAGE_FIBER : + AT803X_PAGE_COPPER); + phy_unlock_mdio_bus(phydev); + if (ret) + return ret; + + ret = at8031_pll_config(phydev); + if (ret < 0) + return ret; + } + /* The RX and TX delay default is: * after HW reset: RX delay enabled and TX delay disabled * after SW reset: RX delay enabled, while TX delay retains the @@ -941,12 +1040,6 @@ static int at803x_config_init(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->drv->phy_id == ATH8031_PHY_ID) { - ret = at8031_pll_config(phydev); - if (ret < 0) - return ret; - } - /* Ar803x extended next page bit is enabled by default. Cisco * multigig switches read this bit and attempt to negotiate 10Gbps * rates even if the next page bit is disabled. This is incorrect @@ -967,6 +1060,7 @@ static int at803x_ack_interrupt(struct phy_device *phydev) static int at803x_config_intr(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err; int value; @@ -983,6 +1077,10 @@ static int at803x_config_intr(struct phy_device *phydev) value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED; value |= AT803X_INTR_ENABLE_LINK_FAIL; value |= AT803X_INTR_ENABLE_LINK_SUCCESS; + if (priv->is_fiber) { + value |= AT803X_INTR_ENABLE_LINK_FAIL_BX; + value |= AT803X_INTR_ENABLE_LINK_SUCCESS_BX; + } err = phy_write(phydev, AT803X_INTR_ENABLE, value); } else { @@ -1115,8 +1213,12 @@ static int at803x_read_specific_status(struct phy_device *phydev) static int at803x_read_status(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int err, old_link = phydev->link; + if (priv->is_1000basex) + return genphy_c37_read_status(phydev); + /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); if (err) @@ -1170,6 +1272,7 @@ static int at803x_config_mdix(struct phy_device *phydev, u8 ctrl) static int at803x_config_aneg(struct phy_device *phydev) { + struct at803x_priv *priv = phydev->priv; int ret; ret = at803x_config_mdix(phydev, phydev->mdix_ctrl); @@ -1186,6 +1289,9 @@ static int at803x_config_aneg(struct phy_device *phydev) return ret; } + if (priv->is_1000basex) + return genphy_c37_config_aneg(phydev); + /* Do not restart auto-negotiation by setting ret to 0 defautly, * when calling __genphy_config_aneg later. */ @@ -1688,19 +1794,19 @@ static int qca808x_read_status(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->link && phydev->speed == SPEED_2500) - phydev->interface = PHY_INTERFACE_MODE_2500BASEX; - else - phydev->interface = PHY_INTERFACE_MODE_SMII; - - /* generate seed as a lower random value to make PHY linked as SLAVE easily, - * except for master/slave configuration fault detected. - * the reason for not putting this code into the function link_change_notify is - * the corner case where the link partner is also the qca8081 PHY and the seed - * value is configured as the same value, the link can't be up and no link change - * occurs. - */ - if (!phydev->link) { + if (phydev->link) { + if (phydev->speed == SPEED_2500) + phydev->interface = PHY_INTERFACE_MODE_2500BASEX; + else + phydev->interface = PHY_INTERFACE_MODE_SGMII; + } else { + /* generate seed as a lower random value to make PHY linked as SLAVE easily, + * except for master/slave configuration fault detected. + * the reason for not putting this code into the function link_change_notify is + * the corner case where the link partner is also the qca8081 PHY and the seed + * value is configured as the same value, the link can't be up and no link change + * occurs. + */ if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR) { qca808x_phy_ms_seed_enable(phydev, false); } else { diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index bb5104ae4610..3c683e0e40e9 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -854,6 +854,7 @@ static struct phy_driver broadcom_drivers[] = { .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM54616S", /* PHY_GBIT_FEATURES */ + .soft_reset = genphy_soft_reset, .config_init = bcm54xx_config_init, .config_aneg = bcm54616s_config_aneg, .config_intr = bcm_phy_config_intr, diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 271fc01f7f7f..2001f3329133 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -243,7 +243,7 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } -static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) +static void __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) { const struct phy_setting *p; int i; @@ -254,13 +254,11 @@ static int __set_linkmode_max_speed(u32 max_speed, unsigned long *addr) else break; } - - return 0; } -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +static void __set_phy_supported(struct phy_device *phydev, u32 max_speed) { - return __set_linkmode_max_speed(max_speed, phydev->supported); + __set_linkmode_max_speed(max_speed, phydev->supported); } /** @@ -273,17 +271,11 @@ static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) * is connected to a 1G PHY. This function allows the MAC to indicate its * maximum speed, and so limit what the PHY will advertise. */ -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed) { - int err; - - err = __set_phy_supported(phydev, max_speed); - if (err) - return err; + __set_phy_supported(phydev, max_speed); phy_advertise_supported(phydev); - - return 0; } EXPORT_SYMBOL(phy_set_max_speed); @@ -440,7 +432,9 @@ int phy_speed_down_core(struct phy_device *phydev) if (min_common_speed == SPEED_UNKNOWN) return -EINVAL; - return __set_linkmode_max_speed(min_common_speed, phydev->advertising); + __set_linkmode_max_speed(min_common_speed, phydev->advertising); + + return 0; } static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 74d8e1dc125f..ce0bb5951b81 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1746,6 +1746,9 @@ void phy_detach(struct phy_device *phydev) phy_driver_is_genphy_10g(phydev)) device_release_driver(&phydev->mdio.dev); + /* Assert the reset signal */ + phy_device_reset(phydev, 1); + /* * The phydev might go away on the put_device() below, so avoid * a use-after-free bug by reading the underlying bus first. @@ -1757,9 +1760,6 @@ void phy_detach(struct phy_device *phydev) ndev_owner = dev->dev.parent->driver->owner; if (ndev_owner != bus->owner) module_put(bus->owner); - - /* Assert the reset signal */ - phy_device_reset(phydev, 1); } EXPORT_SYMBOL(phy_detach); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 420201858564..5b53a3e23c89 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -132,17 +132,6 @@ void phylink_set_port_modes(unsigned long *mask) } EXPORT_SYMBOL_GPL(phylink_set_port_modes); -void phylink_set_10g_modes(unsigned long *mask) -{ - phylink_set(mask, 10000baseT_Full); - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); -} -EXPORT_SYMBOL_GPL(phylink_set_10g_modes); - static int phylink_is_empty_linkmode(const unsigned long *linkmode) { __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp) = { 0, }; diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 0c6c0d1843bc..c1512c9925a6 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -651,6 +651,11 @@ struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) else if (ret < 0) return ERR_PTR(ret); + if (!fwnode_device_is_available(ref.fwnode)) { + fwnode_handle_put(ref.fwnode); + return NULL; + } + bus = sfp_bus_get(ref.fwnode); fwnode_handle_put(ref.fwnode); if (!bus) diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index 2a1e31defe71..4334aafab59a 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -192,8 +192,8 @@ extern const struct driver_info ax88172a_info; /* ASIX specific flags */ #define FLAG_EEPROM_MAC (1UL << 0) /* init device MAC from eeprom */ -int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm); +int __must_check asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data, int in_pm); int asix_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, u16 size, void *data, int in_pm); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 71682970be58..524805285019 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -11,8 +11,8 @@ #define AX_HOST_EN_RETRIES 30 -int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm) +int __must_check asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data, int in_pm) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); @@ -27,9 +27,12 @@ int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely(ret < size)) { + ret = ret < 0 ? ret : -ENODATA; + netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); + } return ret; } @@ -79,7 +82,7 @@ static int asix_check_host_enable(struct usbnet *dev, int in_pm) 0, 0, 1, &smsr, in_pm); if (ret == -ENODEV) break; - else if (ret < sizeof(smsr)) + else if (ret < 0) continue; else if (smsr & AX_HOST_EN) break; @@ -579,8 +582,12 @@ int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc) return ret; } - asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, - (__u16)loc, 2, &res, 1); + ret = asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, + (__u16)loc, 2, &res, 1); + if (ret < 0) { + mutex_unlock(&dev->phy_mutex); + return ret; + } asix_set_hw_mii(dev, 1); mutex_unlock(&dev->phy_mutex); diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 4514d35ef4c4..6ea44e53713a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -755,7 +755,12 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) priv->phy_addr = ret; priv->embd_phy = ((priv->phy_addr & 0x1f) == 0x10); - asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &chipcode, 0); + ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &chipcode, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read STATMNGSTS_REG: %d\n", ret); + return ret; + } + chipcode &= AX_CHIPCODE_MASK; ret = (chipcode == AX_AX88772_CHIPCODE) ? ax88772_hw_reset(dev, 0) : @@ -858,7 +863,6 @@ static int marvell_phy_init(struct usbnet *dev) reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_MARVELL_LED_CTRL); netdev_dbg(dev->net, "MII_MARVELL_LED_CTRL (2) = 0x%04x\n", reg); - reg &= 0xfc0f; } return 0; @@ -920,11 +924,21 @@ static int ax88178_reset(struct usbnet *dev) int gpio0 = 0; u32 phyid; - asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status, 0); + ret = asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read GPIOS: %d\n", ret); + return ret; + } + netdev_dbg(dev->net, "GPIO Status: 0x%04x\n", status); asix_write_cmd(dev, AX_CMD_WRITE_ENABLE, 0, 0, 0, NULL, 0); - asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x0017, 0, 2, &eeprom, 0); + ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x0017, 0, 2, &eeprom, 0); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read EEPROM: %d\n", ret); + return ret; + } + asix_write_cmd(dev, AX_CMD_WRITE_DISABLE, 0, 0, 0, NULL, 0); netdev_dbg(dev->net, "EEPROM index 0x17 is 0x%04x\n", eeprom); diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 82bb5ed94c48..a7c1434fe2da 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -21,6 +21,7 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ipv6_stubs.h> +#include <net/ndisc.h> /* alternative VLAN for IP session 0 if not untagged */ #define MBIM_IPS0_VID 4094 diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index cd33955df0b6..6a769df0b421 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -121,7 +121,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone) if (tx_buf == NULL) goto free_rx_urb; - rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE, + rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, GFP_KERNEL, &rx_urb->transfer_dma); if (rx_buf == NULL) goto free_tx_buf; @@ -146,7 +146,7 @@ error_nomem: static void ipheth_free_urbs(struct ipheth_device *iphone) { - usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->rx_buf, + usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf, iphone->rx_urb->transfer_dma); usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf, iphone->tx_urb->transfer_dma); @@ -317,7 +317,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags) usb_fill_bulk_urb(dev->rx_urb, udev, usb_rcvbulkpipe(udev, dev->bulk_in), - dev->rx_buf, IPHETH_BUF_SIZE, + dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, ipheth_rcvbulk_callback, dev); dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; diff --git a/drivers/nfc/st-nci/vendor_cmds.c b/drivers/nfc/st-nci/vendor_cmds.c index 30d2912d1a05..6335d7afca24 100644 --- a/drivers/nfc/st-nci/vendor_cmds.c +++ b/drivers/nfc/st-nci/vendor_cmds.c @@ -456,7 +456,7 @@ static const struct nfc_vendor_cmd st_nci_vendor_cmds[] = { int st_nci_vendor_cmds_init(struct nci_dev *ndev) { - return nfc_set_vendor_cmds(ndev->nfc_dev, st_nci_vendor_cmds, + return nci_set_vendor_cmds(ndev, st_nci_vendor_cmds, sizeof(st_nci_vendor_cmds)); } EXPORT_SYMBOL(st_nci_vendor_cmds_init); diff --git a/drivers/nfc/st21nfca/vendor_cmds.c b/drivers/nfc/st21nfca/vendor_cmds.c index 74882866dbaf..bfa418d4c6b0 100644 --- a/drivers/nfc/st21nfca/vendor_cmds.c +++ b/drivers/nfc/st21nfca/vendor_cmds.c @@ -358,7 +358,7 @@ int st21nfca_vendor_cmds_init(struct nfc_hci_dev *hdev) struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev); init_completion(&info->vendor_info.req_completion); - return nfc_set_vendor_cmds(hdev->ndev, st21nfca_vendor_cmds, - sizeof(st21nfca_vendor_cmds)); + return nfc_hci_set_vendor_cmds(hdev, st21nfca_vendor_cmds, + sizeof(st21nfca_vendor_cmds)); } EXPORT_SYMBOL(st21nfca_vendor_cmds_init); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 7ae041e2b3fb..f79a66d4e22c 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1092,7 +1092,6 @@ static void __nvmf_concat_opt_tokens(struct seq_file *seq_file) static int nvmf_dev_show(struct seq_file *seq_file, void *private) { struct nvme_ctrl *ctrl; - int ret = 0; mutex_lock(&nvmf_dev_mutex); ctrl = seq_file->private; @@ -1106,7 +1105,7 @@ static int nvmf_dev_show(struct seq_file *seq_file, void *private) out_unlock: mutex_unlock(&nvmf_dev_mutex); - return ret; + return 0; } static int nvmf_dev_open(struct inode *inode, struct file *file) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d8585df2c2fd..6a99ed680915 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3391,7 +3391,8 @@ static const struct pci_device_id nvme_id_table[] = { NVME_QUIRK_DEALLOCATE_ZEROES, }, { PCI_VDEVICE(INTEL, 0x0a54), /* Intel P4500/P4600 */ .driver_data = NVME_QUIRK_STRIPE_SIZE | - NVME_QUIRK_DEALLOCATE_ZEROES, }, + NVME_QUIRK_DEALLOCATE_ZEROES | + NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x0a55), /* Dell Express Flash P4600 */ .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES, }, diff --git a/drivers/pci/controller/pcie-mt7621.c b/drivers/pci/controller/pcie-mt7621.c index 3824862ea144..33eb37a2225c 100644 --- a/drivers/pci/controller/pcie-mt7621.c +++ b/drivers/pci/controller/pcie-mt7621.c @@ -109,15 +109,6 @@ static inline void pcie_write(struct mt7621_pcie *pcie, u32 val, u32 reg) writel_relaxed(val, pcie->base + reg); } -static inline void pcie_rmw(struct mt7621_pcie *pcie, u32 reg, u32 clr, u32 set) -{ - u32 val = readl_relaxed(pcie->base + reg); - - val &= ~clr; - val |= set; - writel_relaxed(val, pcie->base + reg); -} - static inline u32 pcie_port_read(struct mt7621_pcie_port *port, u32 reg) { return readl_relaxed(port->base + reg); @@ -557,7 +548,7 @@ static struct platform_driver mt7621_pcie_driver = { .remove = mt7621_pcie_remove, .driver = { .name = "mt7621-pci", - .of_match_table = of_match_ptr(mt7621_pcie_ids), + .of_match_table = mt7621_pcie_ids, }, }; builtin_platform_driver(mt7621_pcie_driver); diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 0d63541c4052..e9cf318e6670 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -28,6 +28,7 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev) msi_domain_free_irqs_descs_locked(domain, &dev->dev); else pci_msi_legacy_teardown_msi_irqs(dev); + msi_free_msi_descs(&dev->dev); } /** @@ -171,8 +172,7 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); - info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS | - MSI_FLAG_FREE_MSI_DESCS; + info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c index cdbb4689db78..db761adef652 100644 --- a/drivers/pci/msi/legacy.c +++ b/drivers/pci/msi/legacy.c @@ -77,5 +77,4 @@ void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) { msi_device_destroy_sysfs(&dev->dev); arch_teardown_msi_irqs(dev); - msi_free_msi_descs(&dev->dev); } diff --git a/drivers/pinctrl/Makefile b/drivers/pinctrl/Makefile index 08c364d611f5..f64d29f614ec 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -42,9 +42,9 @@ obj-$(CONFIG_PINCTRL_PISTACHIO) += pinctrl-pistachio.o obj-$(CONFIG_PINCTRL_RK805) += pinctrl-rk805.o obj-$(CONFIG_PINCTRL_ROCKCHIP) += pinctrl-rockchip.o obj-$(CONFIG_PINCTRL_SINGLE) += pinctrl-single.o +obj-$(CONFIG_PINCTRL_ST) += pinctrl-st.o obj-$(CONFIG_PINCTRL_STARFIVE) += pinctrl-starfive.o obj-$(CONFIG_PINCTRL_STMFX) += pinctrl-stmfx.o -obj-$(CONFIG_PINCTRL_ST) += pinctrl-st.o obj-$(CONFIG_PINCTRL_SX150X) += pinctrl-sx150x.o obj-$(CONFIG_PINCTRL_TB10X) += pinctrl-tb10x.o obj-$(CONFIG_PINCTRL_THUNDERBAY) += pinctrl-thunderbay.o diff --git a/drivers/pinctrl/bcm/Kconfig b/drivers/pinctrl/bcm/Kconfig index 5123f4c33854..ac1e400bbbac 100644 --- a/drivers/pinctrl/bcm/Kconfig +++ b/drivers/pinctrl/bcm/Kconfig @@ -35,6 +35,7 @@ config PINCTRL_BCM63XX select PINCONF select GENERIC_PINCONF select GPIOLIB + select REGMAP select GPIO_REGMAP config PINCTRL_BCM6318 diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index c4ebfa852b42..47e433e09c5c 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -1269,16 +1269,18 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) sizeof(*girq->parents), GFP_KERNEL); if (!girq->parents) { - pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); - return -ENOMEM; + err = -ENOMEM; + goto out_remove; } if (is_7211) { pc->wake_irq = devm_kcalloc(dev, BCM2835_NUM_IRQS, sizeof(*pc->wake_irq), GFP_KERNEL); - if (!pc->wake_irq) - return -ENOMEM; + if (!pc->wake_irq) { + err = -ENOMEM; + goto out_remove; + } } /* @@ -1306,8 +1308,10 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) len = strlen(dev_name(pc->dev)) + 16; name = devm_kzalloc(pc->dev, len, GFP_KERNEL); - if (!name) - return -ENOMEM; + if (!name) { + err = -ENOMEM; + goto out_remove; + } snprintf(name, len, "%s:bank%d", dev_name(pc->dev), i); @@ -1326,11 +1330,14 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) err = gpiochip_add_data(&pc->gpio_chip, pc); if (err) { dev_err(dev, "could not add GPIO chip\n"); - pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); - return err; + goto out_remove; } return 0; + +out_remove: + pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); + return err; } static struct platform_driver bcm2835_pinctrl_driver = { diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index abffda1fd51e..1d5818269076 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1471,8 +1471,9 @@ static void chv_gpio_irq_handler(struct irq_desc *desc) offset = cctx->intr_lines[intr_line]; if (offset == CHV_INVALID_HWIRQ) { - dev_err(dev, "interrupt on unused interrupt line %u\n", intr_line); - continue; + dev_warn_once(dev, "interrupt on unmapped interrupt line %u\n", intr_line); + /* Some boards expect hwirq 0 to trigger in this case */ + offset = 0; } generic_handle_domain_irq(gc->irq.domain, offset); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 85750974d182..826d494f3cc6 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -451,8 +451,8 @@ static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) value &= ~PADCFG0_PMODE_MASK; value |= PADCFG0_PMODE_GPIO; - /* Disable input and output buffers */ - value |= PADCFG0_GPIORXDIS; + /* Disable TX buffer and enable RX (this will be input) */ + value &= ~PADCFG0_GPIORXDIS; value |= PADCFG0_GPIOTXDIS; /* Disable SCI/SMI/NMI generation */ @@ -497,9 +497,6 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, intel_gpio_set_gpio_mode(padcfg0); - /* Disable TX buffer and enable RX (this will be input) */ - __intel_gpio_set_direction(padcfg0, true); - raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; @@ -1115,9 +1112,6 @@ static int intel_gpio_irq_type(struct irq_data *d, unsigned int type) intel_gpio_set_gpio_mode(reg); - /* Disable TX buffer and enable RX (this will be input) */ - __intel_gpio_set_direction(reg, true); - value = readl(reg); value &= ~(PADCFG0_RXEVCFG_MASK | PADCFG0_RXINV); @@ -1216,6 +1210,39 @@ static irqreturn_t intel_gpio_irq(int irq, void *data) return IRQ_RETVAL(ret); } +static void intel_gpio_irq_init(struct intel_pinctrl *pctrl) +{ + int i; + + for (i = 0; i < pctrl->ncommunities; i++) { + const struct intel_community *community; + void __iomem *base; + unsigned int gpp; + + community = &pctrl->communities[i]; + base = community->regs; + + for (gpp = 0; gpp < community->ngpps; gpp++) { + /* Mask and clear all interrupts */ + writel(0, base + community->ie_offset + gpp * 4); + writel(0xffff, base + community->is_offset + gpp * 4); + } + } +} + +static int intel_gpio_irq_init_hw(struct gpio_chip *gc) +{ + struct intel_pinctrl *pctrl = gpiochip_get_data(gc); + + /* + * Make sure the interrupt lines are in a proper state before + * further configuration. + */ + intel_gpio_irq_init(pctrl); + + return 0; +} + static int intel_gpio_add_community_ranges(struct intel_pinctrl *pctrl, const struct intel_community *community) { @@ -1320,6 +1347,7 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) girq->num_parents = 0; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; + girq->init_hw = intel_gpio_irq_init_hw; ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl); if (ret) { @@ -1695,26 +1723,6 @@ int intel_pinctrl_suspend_noirq(struct device *dev) } EXPORT_SYMBOL_GPL(intel_pinctrl_suspend_noirq); -static void intel_gpio_irq_init(struct intel_pinctrl *pctrl) -{ - size_t i; - - for (i = 0; i < pctrl->ncommunities; i++) { - const struct intel_community *community; - void __iomem *base; - unsigned int gpp; - - community = &pctrl->communities[i]; - base = community->regs; - - for (gpp = 0; gpp < community->ngpps; gpp++) { - /* Mask and clear all interrupts */ - writel(0, base + community->ie_offset + gpp * 4); - writel(0xffff, base + community->is_offset + gpp * 4); - } - } -} - static bool intel_gpio_update_reg(void __iomem *reg, u32 mask, u32 value) { u32 curr, updated; diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index 8e081c90bdb2..639f1130e989 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -137,7 +137,8 @@ static inline int sgpio_addr_to_pin(struct sgpio_priv *priv, int port, int bit) static inline u32 sgpio_get_addr(struct sgpio_priv *priv, u32 rno, u32 off) { - return priv->properties->regoff[rno] + off; + return (priv->properties->regoff[rno] + off) * + regmap_get_reg_stride(priv->regs); } static u32 sgpio_readl(struct sgpio_priv *priv, u32 rno, u32 off) diff --git a/drivers/pinctrl/pinctrl-thunderbay.c b/drivers/pinctrl/pinctrl-thunderbay.c index b5b47f4dd774..79d44bca039e 100644 --- a/drivers/pinctrl/pinctrl-thunderbay.c +++ b/drivers/pinctrl/pinctrl-thunderbay.c @@ -773,63 +773,42 @@ static int thunderbay_build_groups(struct thunderbay_pinctrl *tpc) static int thunderbay_add_functions(struct thunderbay_pinctrl *tpc, struct function_desc *funcs) { - struct function_desc *function = funcs; int i; /* Assign the groups for each function */ - for (i = 0; i < tpc->soc->npins; i++) { - const struct pinctrl_pin_desc *pin_info = thunderbay_pins + i; - struct thunderbay_mux_desc *pin_mux = pin_info->drv_data; - - while (pin_mux->name) { - const char **grp; - int j, grp_num, match = 0; - size_t grp_size; - struct function_desc *func; - - for (j = 0; j < tpc->nfuncs; j++) { - if (!strcmp(pin_mux->name, function[j].name)) { - match = 1; - break; - } - } - - if (!match) - return -EINVAL; - - func = function + j; - grp_num = func->num_group_names; - grp_size = sizeof(*func->group_names); - - if (!func->group_names) { - func->group_names = devm_kcalloc(tpc->dev, - grp_num, - grp_size, - GFP_KERNEL); - if (!func->group_names) { - kfree(func); - return -ENOMEM; - } + for (i = 0; i < tpc->nfuncs; i++) { + struct function_desc *func = &funcs[i]; + const char **group_names; + unsigned int grp_idx = 0; + int j; + + group_names = devm_kcalloc(tpc->dev, func->num_group_names, + sizeof(*group_names), GFP_KERNEL); + if (!group_names) + return -ENOMEM; + + for (j = 0; j < tpc->soc->npins; j++) { + const struct pinctrl_pin_desc *pin_info = &thunderbay_pins[j]; + struct thunderbay_mux_desc *pin_mux; + + for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { + if (!strcmp(pin_mux->name, func->name)) + group_names[grp_idx++] = pin_info->name; } - - grp = func->group_names; - while (*grp) - grp++; - - *grp = pin_info->name; - pin_mux++; } + + func->group_names = group_names; } /* Add all functions */ for (i = 0; i < tpc->nfuncs; i++) { pinmux_generic_add_function(tpc->pctrl, - function[i].name, - function[i].group_names, - function[i].num_group_names, - function[i].data); + funcs[i].name, + funcs[i].group_names, + funcs[i].num_group_names, + funcs[i].data); } - kfree(function); + kfree(funcs); return 0; } @@ -839,27 +818,30 @@ static int thunderbay_build_functions(struct thunderbay_pinctrl *tpc) void *ptr; int pin; - /* Total number of functions is unknown at this point. Allocate first. */ + /* + * Allocate maximum possible number of functions. Assume every pin + * being part of 8 (hw maximum) globally unique muxes. + */ tpc->nfuncs = 0; thunderbay_funcs = kcalloc(tpc->soc->npins * 8, sizeof(*thunderbay_funcs), GFP_KERNEL); if (!thunderbay_funcs) return -ENOMEM; - /* Find total number of functions and each's properties */ + /* Setup 1 function for each unique mux */ for (pin = 0; pin < tpc->soc->npins; pin++) { const struct pinctrl_pin_desc *pin_info = thunderbay_pins + pin; - struct thunderbay_mux_desc *pin_mux = pin_info->drv_data; + struct thunderbay_mux_desc *pin_mux; - while (pin_mux->name) { - struct function_desc *func = thunderbay_funcs; + for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { + struct function_desc *func; - while (func->name) { + /* Check if we already have function for this mux */ + for (func = thunderbay_funcs; func->name; func++) { if (!strcmp(pin_mux->name, func->name)) { func->num_group_names++; break; } - func++; } if (!func->name) { @@ -868,8 +850,6 @@ static int thunderbay_build_functions(struct thunderbay_pinctrl *tpc) func->data = (int *)&pin_mux->mode; tpc->nfuncs++; } - - pin_mux++; } } diff --git a/drivers/pinctrl/pinctrl-zynqmp.c b/drivers/pinctrl/pinctrl-zynqmp.c index 42da6bd399ee..e14012209992 100644 --- a/drivers/pinctrl/pinctrl-zynqmp.c +++ b/drivers/pinctrl/pinctrl-zynqmp.c @@ -809,7 +809,6 @@ static int zynqmp_pinctrl_prepare_pin_desc(struct device *dev, unsigned int *npins) { struct pinctrl_pin_desc *pins, *pin; - char **pin_names; int ret; int i; @@ -821,14 +820,13 @@ static int zynqmp_pinctrl_prepare_pin_desc(struct device *dev, if (!pins) return -ENOMEM; - pin_names = devm_kasprintf_strarray(dev, ZYNQMP_PIN_PREFIX, *npins); - if (IS_ERR(pin_names)) - return PTR_ERR(pin_names); - for (i = 0; i < *npins; i++) { pin = &pins[i]; pin->number = i; - pin->name = pin_names[i]; + pin->name = devm_kasprintf(dev, GFP_KERNEL, "%s%d", + ZYNQMP_PIN_PREFIX, i); + if (!pin->name) + return -ENOMEM; } *zynqmp_pins = pins; diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c index ce1917e230f4..152b71226a80 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c @@ -363,16 +363,16 @@ static const struct sunxi_desc_pin h616_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "uart2"), /* CTS */ - SUNXI_FUNCTION(0x3, "i2s3"), /* DO0 */ + SUNXI_FUNCTION(0x3, "i2s3_dout0"), /* DO0 */ SUNXI_FUNCTION(0x4, "spi1"), /* MISO */ - SUNXI_FUNCTION(0x5, "i2s3"), /* DI1 */ + SUNXI_FUNCTION(0x5, "i2s3_din1"), /* DI1 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 6, 8)), /* PH_EINT8 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 9), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), - SUNXI_FUNCTION(0x3, "i2s3"), /* DI0 */ + SUNXI_FUNCTION(0x3, "i2s3_din0"), /* DI0 */ SUNXI_FUNCTION(0x4, "spi1"), /* CS1 */ - SUNXI_FUNCTION(0x3, "i2s3"), /* DO1 */ + SUNXI_FUNCTION(0x5, "i2s3_dout1"), /* DO1 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 6, 9)), /* PH_EINT9 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 10), SUNXI_FUNCTION(0x0, "gpio_in"), diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 5f0578e25f71..463f1ec5c14e 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -5,6 +5,7 @@ menuconfig SURFACE_PLATFORMS bool "Microsoft Surface Platform-Specific Device Drivers" + depends on ARM64 || X86 || COMPILE_TEST default y help Say Y here to get to see options for platform-specific device drivers diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index f794343d6aaa..4c72ba68b315 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -124,9 +124,10 @@ struct amd_pmc_dev { u32 cpu_id; u32 active_ips; /* SMU version information */ - u16 major; - u16 minor; - u16 rev; + u8 smu_program; + u8 major; + u8 minor; + u8 rev; struct device *dev; struct pci_dev *rdev; struct mutex lock; /* generic mutex lock */ @@ -180,11 +181,13 @@ static int amd_pmc_get_smu_version(struct amd_pmc_dev *dev) if (rc) return rc; - dev->major = (val >> 16) & GENMASK(15, 0); + dev->smu_program = (val >> 24) & GENMASK(7, 0); + dev->major = (val >> 16) & GENMASK(7, 0); dev->minor = (val >> 8) & GENMASK(7, 0); dev->rev = (val >> 0) & GENMASK(7, 0); - dev_dbg(dev->dev, "SMU version is %u.%u.%u\n", dev->major, dev->minor, dev->rev); + dev_dbg(dev->dev, "SMU program %u version is %u.%u.%u\n", + dev->smu_program, dev->major, dev->minor, dev->rev); return 0; } @@ -226,7 +229,7 @@ static int amd_pmc_stb_debugfs_release(struct inode *inode, struct file *filp) return 0; } -const struct file_operations amd_pmc_stb_debugfs_fops = { +static const struct file_operations amd_pmc_stb_debugfs_fops = { .owner = THIS_MODULE, .open = amd_pmc_stb_debugfs_open, .read = amd_pmc_stb_debugfs_read, diff --git a/drivers/platform/x86/asus-tf103c-dock.c b/drivers/platform/x86/asus-tf103c-dock.c index d4ef8f362ee6..6fd0c9fea82d 100644 --- a/drivers/platform/x86/asus-tf103c-dock.c +++ b/drivers/platform/x86/asus-tf103c-dock.c @@ -250,7 +250,7 @@ static int tf103c_dock_hid_raw_request(struct hid_device *hid, u8 reportnum, return 0; } -struct hid_ll_driver tf103c_dock_hid_ll_driver = { +static struct hid_ll_driver tf103c_dock_hid_ll_driver = { .parse = tf103c_dock_hid_parse, .start = tf103c_dock_hid_start, .stop = tf103c_dock_hid_stop, @@ -921,7 +921,7 @@ static int __maybe_unused tf103c_dock_resume(struct device *dev) return 0; } -SIMPLE_DEV_PM_OPS(tf103c_dock_pm_ops, tf103c_dock_suspend, tf103c_dock_resume); +static SIMPLE_DEV_PM_OPS(tf103c_dock_pm_ops, tf103c_dock_suspend, tf103c_dock_resume); static const struct acpi_device_id tf103c_dock_acpi_match[] = { {"NPCE69A"}, diff --git a/drivers/platform/x86/intel/crystal_cove_charger.c b/drivers/platform/x86/intel/crystal_cove_charger.c index 0374bc742513..e4299cfa2205 100644 --- a/drivers/platform/x86/intel/crystal_cove_charger.c +++ b/drivers/platform/x86/intel/crystal_cove_charger.c @@ -17,6 +17,7 @@ #include <linux/regmap.h> #define CHGRIRQ_REG 0x0a +#define MCHGRIRQ_REG 0x17 struct crystal_cove_charger_data { struct mutex buslock; /* irq_bus_lock */ @@ -25,8 +26,8 @@ struct crystal_cove_charger_data { struct irq_domain *irq_domain; int irq; int charger_irq; - bool irq_enabled; - bool irq_is_enabled; + u8 mask; + u8 new_mask; }; static irqreturn_t crystal_cove_charger_irq(int irq, void *data) @@ -53,13 +54,9 @@ static void crystal_cove_charger_irq_bus_sync_unlock(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - if (charger->irq_is_enabled != charger->irq_enabled) { - if (charger->irq_enabled) - enable_irq(charger->irq); - else - disable_irq(charger->irq); - - charger->irq_is_enabled = charger->irq_enabled; + if (charger->mask != charger->new_mask) { + regmap_write(charger->regmap, MCHGRIRQ_REG, charger->new_mask); + charger->mask = charger->new_mask; } mutex_unlock(&charger->buslock); @@ -69,14 +66,14 @@ static void crystal_cove_charger_irq_unmask(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - charger->irq_enabled = true; + charger->new_mask &= ~BIT(data->hwirq); } static void crystal_cove_charger_irq_mask(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - charger->irq_enabled = false; + charger->new_mask |= BIT(data->hwirq); } static void crystal_cove_charger_rm_irq_domain(void *data) @@ -130,10 +127,13 @@ static int crystal_cove_charger_probe(struct platform_device *pdev) irq_set_nested_thread(charger->charger_irq, true); irq_set_noprobe(charger->charger_irq); + /* Mask the single 2nd level IRQ before enabling the 1st level IRQ */ + charger->mask = charger->new_mask = BIT(0); + regmap_write(charger->regmap, MCHGRIRQ_REG, charger->mask); + ret = devm_request_threaded_irq(&pdev->dev, charger->irq, NULL, crystal_cove_charger_irq, - IRQF_ONESHOT | IRQF_NO_AUTOEN, - KBUILD_MODNAME, charger); + IRQF_ONESHOT, KBUILD_MODNAME, charger); if (ret) return dev_err_probe(&pdev->dev, ret, "requesting irq\n"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index c9a85eb2e860..e8424e70d81d 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -596,7 +596,10 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd, return ret; } -static DEFINE_MUTEX(punit_misc_dev_lock); +/* Lock to prevent module registration when already opened by user space */ +static DEFINE_MUTEX(punit_misc_dev_open_lock); +/* Lock to allow one share misc device for all ISST interace */ +static DEFINE_MUTEX(punit_misc_dev_reg_lock); static int misc_usage_count; static int misc_device_ret; static int misc_device_open; @@ -606,7 +609,7 @@ static int isst_if_open(struct inode *inode, struct file *file) int i, ret = 0; /* Fail open, if a module is going away */ - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -628,7 +631,7 @@ static int isst_if_open(struct inode *inode, struct file *file) } else { misc_device_open++; } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return ret; } @@ -637,7 +640,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) { int i; - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); misc_device_open--; for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -645,7 +648,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) if (cb->registered) module_put(cb->owner); } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return 0; } @@ -662,6 +665,43 @@ static struct miscdevice isst_if_char_driver = { .fops = &isst_if_char_driver_ops, }; +static int isst_misc_reg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_device_ret) + goto unlock_exit; + + if (!misc_usage_count) { + misc_device_ret = isst_if_cpu_info_init(); + if (misc_device_ret) + goto unlock_exit; + + misc_device_ret = misc_register(&isst_if_char_driver); + if (misc_device_ret) { + isst_if_cpu_info_exit(); + goto unlock_exit; + } + } + misc_usage_count++; + +unlock_exit: + mutex_unlock(&punit_misc_dev_reg_lock); + + return misc_device_ret; +} + +static void isst_misc_unreg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_usage_count) + misc_usage_count--; + if (!misc_usage_count && !misc_device_ret) { + misc_deregister(&isst_if_char_driver); + isst_if_cpu_info_exit(); + } + mutex_unlock(&punit_misc_dev_reg_lock); +} + /** * isst_if_cdev_register() - Register callback for IOCTL * @device_type: The device type this callback handling. @@ -679,38 +719,31 @@ static struct miscdevice isst_if_char_driver = { */ int isst_if_cdev_register(int device_type, struct isst_if_cmd_cb *cb) { - if (misc_device_ret) - return misc_device_ret; + int ret; if (device_type >= ISST_IF_DEV_MAX) return -EINVAL; - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); + /* Device is already open, we don't want to add new callbacks */ if (misc_device_open) { - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return -EAGAIN; } - if (!misc_usage_count) { - int ret; - - misc_device_ret = misc_register(&isst_if_char_driver); - if (misc_device_ret) - goto unlock_exit; - - ret = isst_if_cpu_info_init(); - if (ret) { - misc_deregister(&isst_if_char_driver); - misc_device_ret = ret; - goto unlock_exit; - } - } memcpy(&punit_callbacks[device_type], cb, sizeof(*cb)); punit_callbacks[device_type].registered = 1; - misc_usage_count++; -unlock_exit: - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); - return misc_device_ret; + ret = isst_misc_reg(); + if (ret) { + /* + * No need of mutex as the misc device register failed + * as no one can open device yet. Hence no contention. + */ + punit_callbacks[device_type].registered = 0; + return ret; + } + return 0; } EXPORT_SYMBOL_GPL(isst_if_cdev_register); @@ -725,16 +758,12 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_register); */ void isst_if_cdev_unregister(int device_type) { - mutex_lock(&punit_misc_dev_lock); - misc_usage_count--; + isst_misc_unreg(); + mutex_lock(&punit_misc_dev_open_lock); punit_callbacks[device_type].registered = 0; if (device_type == ISST_IF_DEV_MBOX) isst_delete_hash(); - if (!misc_usage_count && !misc_device_ret) { - misc_deregister(&isst_if_char_driver); - isst_if_cpu_info_exit(); - } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); } EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 098180fb1cfc..bd045486b933 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8679,9 +8679,10 @@ static const struct attribute_group fan_driver_attr_group = { .attrs = fan_driver_attributes, }; -#define TPACPI_FAN_Q1 0x0001 /* Unitialized HFSP */ -#define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ -#define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ +#define TPACPI_FAN_Q1 0x0001 /* Uninitialized HFSP */ +#define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ +#define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ +#define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8702,6 +8703,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ + TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) @@ -8730,6 +8732,11 @@ static int __init fan_init(struct ibm_init_struct *iibm) quirks = tpacpi_check_quirks(fan_quirk_table, ARRAY_SIZE(fan_quirk_table)); + if (quirks & TPACPI_FAN_NOFAN) { + pr_info("No integrated ThinkPad fan available\n"); + return -ENODEV; + } + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; @@ -10112,6 +10119,9 @@ static struct ibm_struct proxsensor_driver_data = { #define DYTC_CMD_MMC_GET 8 /* To get current MMC function and mode */ #define DYTC_CMD_RESET 0x1ff /* To reset back to default */ +#define DYTC_CMD_FUNC_CAP 3 /* To get DYTC capabilities */ +#define DYTC_FC_MMC 27 /* MMC Mode supported */ + #define DYTC_GET_FUNCTION_BIT 8 /* Bits 8-11 - function setting */ #define DYTC_GET_MODE_BIT 12 /* Bits 12-15 - mode setting */ @@ -10324,6 +10334,15 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (dytc_version < 5) return -ENODEV; + /* Check what capabilities are supported. Currently MMC is needed */ + err = dytc_command(DYTC_CMD_FUNC_CAP, &output); + if (err) + return err; + if (!(output & BIT(DYTC_FC_MMC))) { + dbg_printk(TPACPI_DBG_INIT, " DYTC MMC mode not supported\n"); + return -ENODEV; + } + dbg_printk(TPACPI_DBG_INIT, "DYTC version %d: thermal mode available\n", dytc_version); /* diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 494f23052678..bc97bfa8e8a6 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -770,6 +770,21 @@ static const struct ts_dmi_data predia_basic_data = { .properties = predia_basic_props, }; +static const struct property_entry rwc_nanote_p8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-y", 46), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rwc-nanote-p8.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data rwc_nanote_p8_data = { + .acpi_name = "MSSL1680:00", + .properties = rwc_nanote_p8_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1395,6 +1410,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* RWC NANOTE P8 */ + .driver_data = (void *)&rwc_nanote_p8_data, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Default string"), + DMI_MATCH(DMI_PRODUCT_NAME, "AY07J"), + DMI_MATCH(DMI_PRODUCT_SKU, "0001") + }, + }, + { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, .matches = { diff --git a/drivers/platform/x86/x86-android-tablets.c b/drivers/platform/x86/x86-android-tablets.c index 3ba63ad91b28..9360a8a92486 100644 --- a/drivers/platform/x86/x86-android-tablets.c +++ b/drivers/platform/x86/x86-android-tablets.c @@ -26,6 +26,7 @@ #include <linux/string.h> /* For gpio_get_desc() which is EXPORT_SYMBOL_GPL() */ #include "../../gpio/gpiolib.h" +#include "../../gpio/gpiolib-acpi.h" /* * Helper code to get Linux IRQ numbers given a description of the IRQ source @@ -47,7 +48,7 @@ struct x86_acpi_irq_data { int polarity; /* ACPI_ACTIVE_HIGH / ACPI_ACTIVE_LOW / ACPI_ACTIVE_BOTH */ }; -static int x86_acpi_irq_helper_gpiochip_find(struct gpio_chip *gc, void *data) +static int gpiochip_find_match_label(struct gpio_chip *gc, void *data) { return gc->label && !strcmp(gc->label, data); } @@ -73,7 +74,7 @@ static int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data) return irq; case X86_ACPI_IRQ_TYPE_GPIOINT: /* Like acpi_dev_gpio_irq_get(), but without parsing ACPI resources */ - chip = gpiochip_find(data->chip, x86_acpi_irq_helper_gpiochip_find); + chip = gpiochip_find(data->chip, gpiochip_find_match_label); if (!chip) { pr_err("error cannot find GPIO chip %s\n", data->chip); return -ENODEV; @@ -143,14 +144,17 @@ struct x86_serdev_info { }; struct x86_dev_info { + char *invalid_aei_gpiochip; const char * const *modules; - struct gpiod_lookup_table **gpiod_lookup_tables; + struct gpiod_lookup_table * const *gpiod_lookup_tables; const struct x86_i2c_client_info *i2c_client_info; const struct platform_device_info *pdev_info; const struct x86_serdev_info *serdev_info; int i2c_client_count; int pdev_count; int serdev_count; + int (*init)(void); + void (*exit)(void); }; /* Generic / shared bq24190 settings */ @@ -187,8 +191,8 @@ static struct bq24190_platform_data bq24190_pdata = { }; static const char * const bq24190_modules[] __initconst = { - "crystal_cove_charger", /* For the bq24190 IRQ */ - "bq24190_charger", /* For the Vbus regulator for intel-int3496 */ + "intel_crystal_cove_charger", /* For the bq24190 IRQ */ + "bq24190_charger", /* For the Vbus regulator for intel-int3496 */ NULL }; @@ -302,7 +306,7 @@ static struct gpiod_lookup_table asus_me176c_goodix_gpios = { }, }; -static struct gpiod_lookup_table *asus_me176c_gpios[] = { +static struct gpiod_lookup_table * const asus_me176c_gpios[] = { &int3496_gpo2_pin22_gpios, &asus_me176c_goodix_gpios, NULL @@ -317,6 +321,7 @@ static const struct x86_dev_info asus_me176c_info __initconst = { .serdev_count = ARRAY_SIZE(asus_me176c_serdevs), .gpiod_lookup_tables = asus_me176c_gpios, .modules = bq24190_modules, + .invalid_aei_gpiochip = "INT33FC:02", }; /* Asus TF103C tablets have an Android factory img with everything hardcoded */ @@ -405,7 +410,7 @@ static const struct x86_i2c_client_info asus_tf103c_i2c_clients[] __initconst = }, }; -static struct gpiod_lookup_table *asus_tf103c_gpios[] = { +static struct gpiod_lookup_table * const asus_tf103c_gpios[] = { &int3496_gpo2_pin22_gpios, NULL }; @@ -417,6 +422,7 @@ static const struct x86_dev_info asus_tf103c_info __initconst = { .pdev_count = ARRAY_SIZE(int3496_pdevs), .gpiod_lookup_tables = asus_tf103c_gpios, .modules = bq24190_modules, + .invalid_aei_gpiochip = "INT33FC:02", }; /* @@ -490,6 +496,39 @@ static const struct x86_dev_info chuwi_hi8_info __initconst = { .i2c_client_count = ARRAY_SIZE(chuwi_hi8_i2c_clients), }; +#define CZC_EC_EXTRA_PORT 0x68 +#define CZC_EC_ANDROID_KEYS 0x63 + +static int __init czc_p10t_init(void) +{ + /* + * The device boots up in "Windows 7" mode, when the home button sends a + * Windows specific key sequence (Left Meta + D) and the second button + * sends an unknown one while also toggling the Radio Kill Switch. + * This is a surprising behavior when the second button is labeled "Back". + * + * The vendor-supplied Android-x86 build switches the device to a "Android" + * mode by writing value 0x63 to the I/O port 0x68. This just seems to just + * set bit 6 on address 0x96 in the EC region; switching the bit directly + * seems to achieve the same result. It uses a "p10t_switcher" to do the + * job. It doesn't seem to be able to do anything else, and no other use + * of the port 0x68 is known. + * + * In the Android mode, the home button sends just a single scancode, + * which can be handled in Linux userspace more reasonably and the back + * button only sends a scancode without toggling the kill switch. + * The scancode can then be mapped either to Back or RF Kill functionality + * in userspace, depending on how the button is labeled on that particular + * model. + */ + outb(CZC_EC_ANDROID_KEYS, CZC_EC_EXTRA_PORT); + return 0; +} + +static const struct x86_dev_info czc_p10t __initconst = { + .init = czc_p10t_init, +}; + /* * Whitelabel (sold as various brands) TM800A550L tablets. * These tablet's DSDT contains a whole bunch of bogus ACPI I2C devices @@ -559,7 +598,7 @@ static struct gpiod_lookup_table whitelabel_tm800a550l_goodix_gpios = { }, }; -static struct gpiod_lookup_table *whitelabel_tm800a550l_gpios[] = { +static struct gpiod_lookup_table * const whitelabel_tm800a550l_gpios[] = { &whitelabel_tm800a550l_goodix_gpios, NULL }; @@ -642,6 +681,24 @@ static const struct dmi_system_id x86_android_tablet_ids[] __initconst = { .driver_data = (void *)&chuwi_hi8_info, }, { + /* CZC P10T */ + .ident = "CZC ODEON TPC-10 (\"P10T\")", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "CZC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ODEON*TPC-10"), + }, + .driver_data = (void *)&czc_p10t, + }, + { + /* A variant of CZC P10T */ + .ident = "ViewSonic ViewPad 10", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ViewSonic"), + DMI_MATCH(DMI_PRODUCT_NAME, "VPAD10"), + }, + .driver_data = (void *)&czc_p10t, + }, + { /* Whitelabel (sold as various brands) TM800A550L */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), @@ -669,7 +726,8 @@ static int serdev_count; static struct i2c_client **i2c_clients; static struct platform_device **pdevs; static struct serdev_device **serdevs; -static struct gpiod_lookup_table **gpiod_lookup_tables; +static struct gpiod_lookup_table * const *gpiod_lookup_tables; +static void (*exit_handler)(void); static __init int x86_instantiate_i2c_client(const struct x86_dev_info *dev_info, int idx) @@ -787,6 +845,9 @@ static void x86_android_tablet_cleanup(void) kfree(i2c_clients); + if (exit_handler) + exit_handler(); + for (i = 0; gpiod_lookup_tables && gpiod_lookup_tables[i]; i++) gpiod_remove_lookup_table(gpiod_lookup_tables[i]); } @@ -795,6 +856,7 @@ static __init int x86_android_tablet_init(void) { const struct x86_dev_info *dev_info; const struct dmi_system_id *id; + struct gpio_chip *chip; int i, ret = 0; id = dmi_first_match(x86_android_tablet_ids); @@ -804,6 +866,20 @@ static __init int x86_android_tablet_init(void) dev_info = id->driver_data; /* + * The broken DSDTs on these devices often also include broken + * _AEI (ACPI Event Interrupt) handlers, disable these. + */ + if (dev_info->invalid_aei_gpiochip) { + chip = gpiochip_find(dev_info->invalid_aei_gpiochip, + gpiochip_find_match_label); + if (!chip) { + pr_err("error cannot find GPIO chip %s\n", dev_info->invalid_aei_gpiochip); + return -ENODEV; + } + acpi_gpiochip_free_interrupts(chip); + } + + /* * Since this runs from module_init() it cannot use -EPROBE_DEFER, * instead pre-load any modules which are listed as requirements. */ @@ -814,6 +890,15 @@ static __init int x86_android_tablet_init(void) for (i = 0; gpiod_lookup_tables && gpiod_lookup_tables[i]; i++) gpiod_add_lookup_table(gpiod_lookup_tables[i]); + if (dev_info->init) { + ret = dev_info->init(); + if (ret < 0) { + x86_android_tablet_cleanup(); + return ret; + } + exit_handler = dev_info->exit; + } + i2c_clients = kcalloc(dev_info->i2c_client_count, sizeof(*i2c_clients), GFP_KERNEL); if (!i2c_clients) { x86_android_tablet_cleanup(); @@ -865,6 +950,6 @@ static __init int x86_android_tablet_init(void) module_init(x86_android_tablet_init); module_exit(x86_android_tablet_cleanup); -MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com"); +MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); MODULE_DESCRIPTION("X86 Android tablets DSDT fixups driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 0e4bc8b9329d..b6f2cfd15dd2 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -317,11 +317,18 @@ no_memory: } EXPORT_SYMBOL(ptp_clock_register); +static int unregister_vclock(struct device *dev, void *data) +{ + struct ptp_clock *ptp = dev_get_drvdata(dev); + + ptp_vclock_unregister(info_to_vclock(ptp->info)); + return 0; +} + int ptp_clock_unregister(struct ptp_clock *ptp) { if (ptp_vclock_in_use(ptp)) { - pr_err("ptp: virtual clock in use\n"); - return -EBUSY; + device_for_each_child(&ptp->dev, NULL, unregister_vclock); } ptp->defunct = 1; diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 41b92dc2f011..9233bfedeb17 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -14,7 +14,7 @@ static ssize_t clock_name_show(struct device *dev, struct device_attribute *attr, char *page) { struct ptp_clock *ptp = dev_get_drvdata(dev); - return snprintf(page, PAGE_SIZE-1, "%s\n", ptp->info->name); + return sysfs_emit(page, "%s\n", ptp->info->name); } static DEVICE_ATTR_RO(clock_name); @@ -387,7 +387,7 @@ static ssize_t ptp_pin_show(struct device *dev, struct device_attribute *attr, mutex_unlock(&ptp->pincfg_mux); - return snprintf(page, PAGE_SIZE, "%u %u\n", func, chan); + return sysfs_emit(page, "%u %u\n", func, chan); } static ssize_t ptp_pin_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index ab1d233173e1..cb179a3ea508 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -57,6 +57,30 @@ static int ptp_vclock_gettime(struct ptp_clock_info *ptp, return 0; } +static int ptp_vclock_gettimex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct ptp_clock *pptp = vclock->pclock; + struct timespec64 pts; + unsigned long flags; + int err; + u64 ns; + + err = pptp->info->gettimex64(pptp->info, &pts, sts); + if (err) + return err; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, timespec64_to_ns(&pts)); + spin_unlock_irqrestore(&vclock->lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + static int ptp_vclock_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts) { @@ -71,6 +95,28 @@ static int ptp_vclock_settime(struct ptp_clock_info *ptp, return 0; } +static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *xtstamp) +{ + struct ptp_vclock *vclock = info_to_vclock(ptp); + struct ptp_clock *pptp = vclock->pclock; + unsigned long flags; + int err; + u64 ns; + + err = pptp->info->getcrosststamp(pptp->info, xtstamp); + if (err) + return err; + + spin_lock_irqsave(&vclock->lock, flags); + ns = timecounter_cyc2time(&vclock->tc, ktime_to_ns(xtstamp->device)); + spin_unlock_irqrestore(&vclock->lock, flags); + + xtstamp->device = ns_to_ktime(ns); + + return 0; +} + static long ptp_vclock_refresh(struct ptp_clock_info *ptp) { struct ptp_vclock *vclock = info_to_vclock(ptp); @@ -84,11 +130,9 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp) static const struct ptp_clock_info ptp_vclock_info = { .owner = THIS_MODULE, .name = "ptp virtual clock", - /* The maximum ppb value that long scaled_ppm can support */ - .max_adj = 32767999, + .max_adj = 500000000, .adjfine = ptp_vclock_adjfine, .adjtime = ptp_vclock_adjtime, - .gettime64 = ptp_vclock_gettime, .settime64 = ptp_vclock_settime, .do_aux_work = ptp_vclock_refresh, }; @@ -124,6 +168,12 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) vclock->pclock = pclock; vclock->info = ptp_vclock_info; + if (pclock->info->gettimex64) + vclock->info.gettimex64 = ptp_vclock_gettimex; + else + vclock->info.gettime64 = ptp_vclock_gettime; + if (pclock->info->getcrosststamp) + vclock->info.getcrosststamp = ptp_vclock_getcrosststamp; vclock->cc = ptp_vclock_cc; snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt", diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c index fbc56b043071..b8bf76c170fe 100644 --- a/drivers/regulator/max20086-regulator.c +++ b/drivers/regulator/max20086-regulator.c @@ -7,6 +7,7 @@ #include <linux/err.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/module.h> #include <linux/regmap.h> @@ -140,7 +141,7 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) node = of_get_child_by_name(chip->dev->of_node, "regulators"); if (!node) { dev_err(chip->dev, "regulators node not found\n"); - return PTR_ERR(node); + return -ENODEV; } for (i = 0; i < chip->info->num_outputs; ++i) diff --git a/drivers/remoteproc/Kconfig b/drivers/remoteproc/Kconfig index 3ddd426fc969..166019786653 100644 --- a/drivers/remoteproc/Kconfig +++ b/drivers/remoteproc/Kconfig @@ -180,6 +180,7 @@ config QCOM_Q6V5_ADSP depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n + depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n select MFD_SYSCON select QCOM_PIL_INFO select QCOM_MDT_LOADER @@ -199,6 +200,7 @@ config QCOM_Q6V5_MSS depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n + depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n select MFD_SYSCON select QCOM_MDT_LOADER select QCOM_PIL_INFO @@ -218,6 +220,7 @@ config QCOM_Q6V5_PAS depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n + depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n select MFD_SYSCON select QCOM_PIL_INFO select QCOM_MDT_LOADER @@ -239,6 +242,7 @@ config QCOM_Q6V5_WCSS depends on RPMSG_QCOM_GLINK_SMEM || RPMSG_QCOM_GLINK_SMEM=n depends on QCOM_SYSMON || QCOM_SYSMON=n depends on RPMSG_QCOM_GLINK || RPMSG_QCOM_GLINK=n + depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n select MFD_SYSCON select QCOM_MDT_LOADER select QCOM_PIL_INFO diff --git a/drivers/remoteproc/qcom_q6v5.c b/drivers/remoteproc/qcom_q6v5.c index eada7e34f3af..442a388f8102 100644 --- a/drivers/remoteproc/qcom_q6v5.c +++ b/drivers/remoteproc/qcom_q6v5.c @@ -10,6 +10,7 @@ #include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/module.h> +#include <linux/soc/qcom/qcom_aoss.h> #include <linux/soc/qcom/smem.h> #include <linux/soc/qcom/smem_state.h> #include <linux/remoteproc.h> diff --git a/drivers/rpmsg/rpmsg_char.c b/drivers/rpmsg/rpmsg_char.c index d6214cb66026..5663cf799c95 100644 --- a/drivers/rpmsg/rpmsg_char.c +++ b/drivers/rpmsg/rpmsg_char.c @@ -93,7 +93,7 @@ static int rpmsg_eptdev_destroy(struct device *dev, void *data) /* wake up any blocked readers */ wake_up_interruptible(&eptdev->readq); - device_del(&eptdev->dev); + cdev_device_del(&eptdev->cdev, &eptdev->dev); put_device(&eptdev->dev); return 0; @@ -336,7 +336,6 @@ static void rpmsg_eptdev_release_device(struct device *dev) ida_simple_remove(&rpmsg_ept_ida, dev->id); ida_simple_remove(&rpmsg_minor_ida, MINOR(eptdev->dev.devt)); - cdev_del(&eptdev->cdev); kfree(eptdev); } @@ -381,19 +380,13 @@ static int rpmsg_eptdev_create(struct rpmsg_ctrldev *ctrldev, dev->id = ret; dev_set_name(dev, "rpmsg%d", ret); - ret = cdev_add(&eptdev->cdev, dev->devt, 1); + ret = cdev_device_add(&eptdev->cdev, &eptdev->dev); if (ret) goto free_ept_ida; /* We can now rely on the release function for cleanup */ dev->release = rpmsg_eptdev_release_device; - ret = device_add(dev); - if (ret) { - dev_err(dev, "device_add failed: %d\n", ret); - put_device(dev); - } - return ret; free_ept_ida: @@ -462,7 +455,6 @@ static void rpmsg_ctrldev_release_device(struct device *dev) ida_simple_remove(&rpmsg_ctrl_ida, dev->id); ida_simple_remove(&rpmsg_minor_ida, MINOR(dev->devt)); - cdev_del(&ctrldev->cdev); kfree(ctrldev); } @@ -497,19 +489,13 @@ static int rpmsg_chrdev_probe(struct rpmsg_device *rpdev) dev->id = ret; dev_set_name(&ctrldev->dev, "rpmsg_ctrl%d", ret); - ret = cdev_add(&ctrldev->cdev, dev->devt, 1); + ret = cdev_device_add(&ctrldev->cdev, &ctrldev->dev); if (ret) goto free_ctrl_ida; /* We can now rely on the release function for cleanup */ dev->release = rpmsg_ctrldev_release_device; - ret = device_add(dev); - if (ret) { - dev_err(&rpdev->dev, "device_add failed: %d\n", ret); - put_device(dev); - } - dev_set_drvdata(&rpdev->dev, ctrldev); return ret; @@ -535,7 +521,7 @@ static void rpmsg_chrdev_remove(struct rpmsg_device *rpdev) if (ret) dev_warn(&rpdev->dev, "failed to nuke endpoints: %d\n", ret); - device_del(&ctrldev->dev); + cdev_device_del(&ctrldev->cdev, &ctrldev->dev); put_device(&ctrldev->dev); } diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c index d24cafe02708..511bf8e0a436 100644 --- a/drivers/s390/scsi/zfcp_fc.c +++ b/drivers/s390/scsi/zfcp_fc.c @@ -521,6 +521,8 @@ static void zfcp_fc_adisc_handler(void *data) goto out; } + /* re-init to undo drop from zfcp_fc_adisc() */ + port->d_id = ntoh24(adisc_resp->adisc_port_id); /* port is good, unblock rport without going through erp */ zfcp_scsi_schedule_rport_register(port); out: @@ -534,6 +536,7 @@ static int zfcp_fc_adisc(struct zfcp_port *port) struct zfcp_fc_req *fc_req; struct zfcp_adapter *adapter = port->adapter; struct Scsi_Host *shost = adapter->scsi_host; + u32 d_id; int ret; fc_req = kmem_cache_zalloc(zfcp_fc_req_cache, GFP_ATOMIC); @@ -558,7 +561,15 @@ static int zfcp_fc_adisc(struct zfcp_port *port) fc_req->u.adisc.req.adisc_cmd = ELS_ADISC; hton24(fc_req->u.adisc.req.adisc_port_id, fc_host_port_id(shost)); - ret = zfcp_fsf_send_els(adapter, port->d_id, &fc_req->ct_els, + d_id = port->d_id; /* remember as destination for send els below */ + /* + * Force fresh GID_PN lookup on next port recovery. + * Must happen after request setup and before sending request, + * to prevent race with port->d_id re-init in zfcp_fc_adisc_handler(). + */ + port->d_id = 0; + + ret = zfcp_fsf_send_els(adapter, d_id, &fc_req->ct_els, ZFCP_FC_CTELS_TMO); if (ret) kmem_cache_free(zfcp_fc_req_cache, fc_req); diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index b9482da79512..3ebe66151dcb 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -1567,8 +1567,6 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) pci_try_set_mwi(pdev); retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (retval) - retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (retval) { TW_PRINTK(host, TW_DRIVER, 0x18, "Failed to set dma mask"); retval = -ENODEV; @@ -1786,8 +1784,6 @@ static int __maybe_unused twl_resume(struct device *dev) pci_try_set_mwi(pdev); retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (retval) - retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (retval) { TW_PRINTK(host, TW_DRIVER, 0x25, "Failed to set dma mask during resume"); retval = -ENODEV; diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 3ad3ebaca8e9..ad4972c0fc53 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -1507,7 +1507,6 @@ NCR_700_intr(int irq, void *dev_id) struct scsi_cmnd *SCp = hostdata->cmd; handled = 1; - SCp = hostdata->cmd; if(istat & SCSI_INT_PENDING) { udelay(10); diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c index 440ef32be048..e5aa982ffedc 100644 --- a/drivers/scsi/bfa/bfad.c +++ b/drivers/scsi/bfa/bfad.c @@ -732,9 +732,6 @@ bfad_pci_init(struct pci_dev *pdev, struct bfad_s *bfad) pci_set_master(pdev); rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (rc) - rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (rc) { rc = -ENODEV; printk(KERN_ERR "dma_set_mask_and_coherent fail %p\n", pdev); @@ -1560,9 +1557,6 @@ bfad_pci_slot_reset(struct pci_dev *pdev) rc = dma_set_mask_and_coherent(&bfad->pcidev->dev, DMA_BIT_MASK(64)); if (rc) - rc = dma_set_mask_and_coherent(&bfad->pcidev->dev, - DMA_BIT_MASK(32)); - if (rc) goto out_disable_device; if (restart_bfa(bfad) == -1) diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 71fa62bd3083..9be273c320e2 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -82,7 +82,7 @@ static int bnx2fc_bind_pcidev(struct bnx2fc_hba *hba); static void bnx2fc_unbind_pcidev(struct bnx2fc_hba *hba); static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, struct device *parent, int npiv); -static void bnx2fc_destroy_work(struct work_struct *work); +static void bnx2fc_port_destroy(struct fcoe_port *port); static struct bnx2fc_hba *bnx2fc_hba_lookup(struct net_device *phys_dev); static struct bnx2fc_interface *bnx2fc_interface_lookup(struct net_device @@ -907,9 +907,6 @@ static void bnx2fc_indicate_netevent(void *context, unsigned long event, __bnx2fc_destroy(interface); } mutex_unlock(&bnx2fc_dev_lock); - - /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); return; default: @@ -1215,8 +1212,8 @@ static int bnx2fc_vport_destroy(struct fc_vport *vport) mutex_unlock(&n_port->lp_mutex); bnx2fc_free_vport(interface->hba, port->lport); bnx2fc_port_shutdown(port->lport); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); return 0; } @@ -1525,7 +1522,6 @@ static struct fc_lport *bnx2fc_if_create(struct bnx2fc_interface *interface, port->lport = lport; port->priv = interface; port->get_netdev = bnx2fc_netdev; - INIT_WORK(&port->destroy_work, bnx2fc_destroy_work); /* Configure fcoe_port */ rc = bnx2fc_lport_config(lport); @@ -1653,8 +1649,8 @@ static void __bnx2fc_destroy(struct bnx2fc_interface *interface) bnx2fc_interface_cleanup(interface); bnx2fc_stop(interface); list_del(&interface->list); + bnx2fc_port_destroy(port); bnx2fc_interface_put(interface); - queue_work(bnx2fc_wq, &port->destroy_work); } /** @@ -1694,15 +1690,12 @@ netdev_err: return rc; } -static void bnx2fc_destroy_work(struct work_struct *work) +static void bnx2fc_port_destroy(struct fcoe_port *port) { - struct fcoe_port *port; struct fc_lport *lport; - port = container_of(work, struct fcoe_port, destroy_work); lport = port->lport; - - BNX2FC_HBA_DBG(lport, "Entered bnx2fc_destroy_work\n"); + BNX2FC_HBA_DBG(lport, "Entered %s, destroying lport %p\n", __func__, lport); bnx2fc_if_destroy(lport); } @@ -2556,9 +2549,6 @@ static void bnx2fc_ulp_exit(struct cnic_dev *dev) __bnx2fc_destroy(interface); mutex_unlock(&bnx2fc_dev_lock); - /* Ensure ALL destroy work has been completed before return */ - flush_workqueue(bnx2fc_wq); - bnx2fc_ulp_stop(hba); /* unregister cnic device */ if (test_and_clear_bit(BNX2FC_CNIC_REGISTERED, &hba->reg_with_cnic)) diff --git a/drivers/scsi/elx/libefc/efc_els.c b/drivers/scsi/elx/libefc/efc_els.c index 7bb4f9aad2c8..84bc81d7ce76 100644 --- a/drivers/scsi/elx/libefc/efc_els.c +++ b/drivers/scsi/elx/libefc/efc_els.c @@ -46,18 +46,14 @@ efc_els_io_alloc_size(struct efc_node *node, u32 reqlen, u32 rsplen) efc = node->efc; - spin_lock_irqsave(&node->els_ios_lock, flags); - if (!node->els_io_enabled) { efc_log_err(efc, "els io alloc disabled\n"); - spin_unlock_irqrestore(&node->els_ios_lock, flags); return NULL; } els = mempool_alloc(efc->els_io_pool, GFP_ATOMIC); if (!els) { atomic_add_return(1, &efc->els_io_alloc_failed_count); - spin_unlock_irqrestore(&node->els_ios_lock, flags); return NULL; } @@ -74,7 +70,6 @@ efc_els_io_alloc_size(struct efc_node *node, u32 reqlen, u32 rsplen) &els->io.req.phys, GFP_KERNEL); if (!els->io.req.virt) { mempool_free(els, efc->els_io_pool); - spin_unlock_irqrestore(&node->els_ios_lock, flags); return NULL; } @@ -94,10 +89,11 @@ efc_els_io_alloc_size(struct efc_node *node, u32 reqlen, u32 rsplen) /* add els structure to ELS IO list */ INIT_LIST_HEAD(&els->list_entry); + spin_lock_irqsave(&node->els_ios_lock, flags); list_add_tail(&els->list_entry, &node->els_ios_list); + spin_unlock_irqrestore(&node->els_ios_lock, flags); } - spin_unlock_irqrestore(&node->els_ios_lock, flags); return els; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index a05ec7aece5a..2f53a2ee024a 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -2666,9 +2666,6 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev, goto err_out; error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (error) - error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); - if (error) { dev_err(dev, "No usable DMA addressing method\n"); goto err_out; diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index a45ef9a5e12e..a01a3a7b706b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4695,8 +4695,6 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_out; rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (rc) - rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (rc) { dev_err(dev, "No usable DMA addressing method\n"); rc = -ENODEV; diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c index 253ceca54a84..7eb8c39da366 100644 --- a/drivers/scsi/myrs.c +++ b/drivers/scsi/myrs.c @@ -2267,7 +2267,8 @@ static void myrs_cleanup(struct myrs_hba *cs) myrs_unmap(cs); if (cs->mmio_base) { - cs->disable_intr(cs); + if (cs->disable_intr) + cs->disable_intr(cs); iounmap(cs->mmio_base); cs->mmio_base = NULL; } diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index bbf538fe15b3..2530d1365556 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -4151,10 +4151,22 @@ static int process_oq(struct pm8001_hba_info *pm8001_ha, u8 vec) u32 ret = MPI_IO_STATUS_FAIL; u32 regval; + /* + * Fatal errors are programmed to be signalled in irq vector + * pm8001_ha->max_q_num - 1 through pm8001_ha->main_cfg_tbl.pm80xx_tbl. + * fatal_err_interrupt + */ if (vec == (pm8001_ha->max_q_num - 1)) { + u32 mipsall_ready; + + if (pm8001_ha->chip_id == chip_8008 || + pm8001_ha->chip_id == chip_8009) + mipsall_ready = SCRATCH_PAD_MIPSALL_READY_8PORT; + else + mipsall_ready = SCRATCH_PAD_MIPSALL_READY_16PORT; + regval = pm8001_cr32(pm8001_ha, 0, MSGU_SCRATCH_PAD_1); - if ((regval & SCRATCH_PAD_MIPSALL_READY) != - SCRATCH_PAD_MIPSALL_READY) { + if ((regval & mipsall_ready) != mipsall_ready) { pm8001_ha->controller_fatal_error = true; pm8001_dbg(pm8001_ha, FAIL, "Firmware Fatal error! Regval:0x%x\n", diff --git a/drivers/scsi/pm8001/pm80xx_hwi.h b/drivers/scsi/pm8001/pm80xx_hwi.h index c7e5d93bea92..c41ed039c92a 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.h +++ b/drivers/scsi/pm8001/pm80xx_hwi.h @@ -1405,8 +1405,12 @@ typedef struct SASProtocolTimerConfig SASProtocolTimerConfig_t; #define SCRATCH_PAD_BOOT_LOAD_SUCCESS 0x0 #define SCRATCH_PAD_IOP0_READY 0xC00 #define SCRATCH_PAD_IOP1_READY 0x3000 -#define SCRATCH_PAD_MIPSALL_READY (SCRATCH_PAD_IOP1_READY | \ +#define SCRATCH_PAD_MIPSALL_READY_16PORT (SCRATCH_PAD_IOP1_READY | \ SCRATCH_PAD_IOP0_READY | \ + SCRATCH_PAD_ILA_READY | \ + SCRATCH_PAD_RAAE_READY) +#define SCRATCH_PAD_MIPSALL_READY_8PORT (SCRATCH_PAD_IOP0_READY | \ + SCRATCH_PAD_ILA_READY | \ SCRATCH_PAD_RAAE_READY) /* boot loader state */ diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 99a56ca1fb16..fab43dabe5b3 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -2250,6 +2250,7 @@ process_els: io_req->tm_flags == FCP_TMF_TGT_RESET) { clear_bit(QEDF_CMD_OUTSTANDING, &io_req->flags); io_req->sc_cmd = NULL; + kref_put(&io_req->refcount, qedf_release_cmd); complete(&io_req->tm_done); } diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index cdc66e2a9488..6ad28bc8e948 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -911,7 +911,7 @@ void qedf_ctx_soft_reset(struct fc_lport *lport) struct qed_link_output if_link; if (lport->vport) { - QEDF_ERR(NULL, "Cannot issue host reset on NPIV port.\n"); + printk_ratelimited("Cannot issue host reset on NPIV port.\n"); return; } @@ -1864,6 +1864,7 @@ static int qedf_vport_create(struct fc_vport *vport, bool disabled) vport_qedf->cmd_mgr = base_qedf->cmd_mgr; init_completion(&vport_qedf->flogi_compl); INIT_LIST_HEAD(&vport_qedf->fcports); + INIT_DELAYED_WORK(&vport_qedf->stag_work, qedf_stag_change_work); rc = qedf_vport_libfc_config(vport, vn_port); if (rc) { @@ -3980,7 +3981,9 @@ void qedf_stag_change_work(struct work_struct *work) struct qedf_ctx *qedf = container_of(work, struct qedf_ctx, stag_work.work); - QEDF_ERR(&qedf->dbg_ctx, "Performing software context reset.\n"); + printk_ratelimited("[%s]:[%s:%d]:%d: Performing software context reset.", + dev_name(&qedf->pdev->dev), __func__, __LINE__, + qedf->dbg_ctx.host_no); qedf_ctx_soft_reset(qedf->lport); } diff --git a/drivers/scsi/ufs/ufshcd-pltfrm.c b/drivers/scsi/ufs/ufshcd-pltfrm.c index 8b16bbbcb806..87975d1a21c8 100644 --- a/drivers/scsi/ufs/ufshcd-pltfrm.c +++ b/drivers/scsi/ufs/ufshcd-pltfrm.c @@ -92,6 +92,11 @@ static int ufshcd_parse_clock_info(struct ufs_hba *hba) clki->min_freq = clkfreq[i]; clki->max_freq = clkfreq[i+1]; clki->name = devm_kstrdup(dev, name, GFP_KERNEL); + if (!clki->name) { + ret = -ENOMEM; + goto out; + } + if (!strcmp(name, "ref_clk")) clki->keep_link_active = true; dev_dbg(dev, "%s: min %u max %u name %s\n", "freq-table-hz", @@ -127,6 +132,8 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name, return -ENOMEM; vreg->name = devm_kstrdup(dev, name, GFP_KERNEL); + if (!vreg->name) + return -ENOMEM; snprintf(prop_name, MAX_PROP_SIZE, "%s-max-microamp", name); if (of_property_read_u32(np, prop_name, &vreg->max_uA)) { diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 460d2b440d2e..50b12d60dc1b 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -8613,7 +8613,7 @@ static void ufshcd_hba_exit(struct ufs_hba *hba) * @pwr_mode: device power mode to set * * Returns 0 if requested power mode is set successfully - * Returns non-zero if failed to set the requested power mode + * Returns < 0 if failed to set the requested power mode */ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, enum ufs_dev_pwr_mode pwr_mode) @@ -8667,8 +8667,11 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba, sdev_printk(KERN_WARNING, sdp, "START_STOP failed for power mode: %d, result %x\n", pwr_mode, ret); - if (ret > 0 && scsi_sense_valid(&sshdr)) - scsi_print_sense_hdr(sdp, NULL, &sshdr); + if (ret > 0) { + if (scsi_sense_valid(&sshdr)) + scsi_print_sense_hdr(sdp, NULL, &sshdr); + ret = -EIO; + } } if (!ret) diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h index 6a295c88d850..a7ff0e5b5494 100644 --- a/drivers/scsi/ufs/ufshci.h +++ b/drivers/scsi/ufs/ufshci.h @@ -142,7 +142,8 @@ static inline u32 ufshci_version(u32 major, u32 minor) #define INT_FATAL_ERRORS (DEVICE_FATAL_ERROR |\ CONTROLLER_FATAL_ERROR |\ SYSTEM_BUS_FATAL_ERROR |\ - CRYPTO_ENGINE_FATAL_ERROR) + CRYPTO_ENGINE_FATAL_ERROR |\ + UIC_LINK_LOST) /* HCS - Host Controller Status 30h */ #define DEVICE_PRESENT 0x1 diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index c9a769b8594b..86c76211b3d3 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -585,7 +585,7 @@ static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs) u32 rd = 0; u32 wr = 0; - if (qspi->base[CHIP_SELECT]) { + if (cs >= 0 && qspi->base[CHIP_SELECT]) { rd = bcm_qspi_read(qspi, CHIP_SELECT, 0); wr = (rd & ~0xff) | (1 << cs); if (rd == wr) diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index c208efeadd18..0bc7daa7afc8 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -693,6 +693,11 @@ static int meson_spicc_probe(struct platform_device *pdev) writel_relaxed(0, spicc->base + SPICC_INTREG); irq = platform_get_irq(pdev, 0); + if (irq < 0) { + ret = irq; + goto out_master; + } + ret = devm_request_irq(&pdev->dev, irq, meson_spicc_irq, 0, NULL, spicc); if (ret) { diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index a15de10ee286..753bd313e6fd 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -624,7 +624,7 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) else mdata->state = MTK_SPI_IDLE; - if (!master->can_dma(master, master->cur_msg->spi, trans)) { + if (!master->can_dma(master, NULL, trans)) { if (trans->rx_buf) { cnt = mdata->xfer_len / 4; ioread32_rep(mdata->base + SPI_RX_DATA_REG, diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 514337c86d2c..ffdc55f87e82 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -688,7 +688,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) struct resource *res; int ret, irq; - ctrl = spi_alloc_master(dev, sizeof(*qspi)); + ctrl = devm_spi_alloc_master(dev, sizeof(*qspi)); if (!ctrl) return -ENOMEM; @@ -697,58 +697,46 @@ static int stm32_qspi_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi"); qspi->io_base = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->io_base)) { - ret = PTR_ERR(qspi->io_base); - goto err_master_put; - } + if (IS_ERR(qspi->io_base)) + return PTR_ERR(qspi->io_base); qspi->phys_base = res->start; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_mm"); qspi->mm_base = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->mm_base)) { - ret = PTR_ERR(qspi->mm_base); - goto err_master_put; - } + if (IS_ERR(qspi->mm_base)) + return PTR_ERR(qspi->mm_base); qspi->mm_size = resource_size(res); - if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) { - ret = -EINVAL; - goto err_master_put; - } + if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) + return -EINVAL; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = irq; - goto err_master_put; - } + if (irq < 0) + return irq; ret = devm_request_irq(dev, irq, stm32_qspi_irq, 0, dev_name(dev), qspi); if (ret) { dev_err(dev, "failed to request irq\n"); - goto err_master_put; + return ret; } init_completion(&qspi->data_completion); init_completion(&qspi->match_completion); qspi->clk = devm_clk_get(dev, NULL); - if (IS_ERR(qspi->clk)) { - ret = PTR_ERR(qspi->clk); - goto err_master_put; - } + if (IS_ERR(qspi->clk)) + return PTR_ERR(qspi->clk); qspi->clk_rate = clk_get_rate(qspi->clk); - if (!qspi->clk_rate) { - ret = -EINVAL; - goto err_master_put; - } + if (!qspi->clk_rate) + return -EINVAL; ret = clk_prepare_enable(qspi->clk); if (ret) { dev_err(dev, "can not enable the clock\n"); - goto err_master_put; + return ret; } rstc = devm_reset_control_get_exclusive(dev, NULL); @@ -784,7 +772,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) pm_runtime_enable(dev); pm_runtime_get_noresume(dev); - ret = devm_spi_register_master(dev, ctrl); + ret = spi_register_master(ctrl); if (ret) goto err_pm_runtime_free; @@ -806,8 +794,6 @@ err_dma_free: stm32_qspi_dma_free(qspi); err_clk_disable: clk_disable_unprepare(qspi->clk); -err_master_put: - spi_master_put(qspi->ctrl); return ret; } @@ -817,6 +803,7 @@ static int stm32_qspi_remove(struct platform_device *pdev) struct stm32_qspi *qspi = platform_get_drvdata(pdev); pm_runtime_get_sync(qspi->dev); + spi_unregister_master(qspi->ctrl); /* disable qspi */ writel_relaxed(0, qspi->io_base + QSPI_CR); stm32_qspi_dma_free(qspi); diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 9bd3fd1652f7..7fc24505a72c 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -221,7 +221,6 @@ struct stm32_spi; * time between frames (if driver has this functionality) * @set_number_of_data: optional routine to configure registers to desired * number of data (if driver has this functionality) - * @can_dma: routine to determine if the transfer is eligible for DMA use * @transfer_one_dma_start: routine to start transfer a single spi_transfer * using DMA * @dma_rx_cb: routine to call after DMA RX channel operation is complete @@ -232,7 +231,7 @@ struct stm32_spi; * @baud_rate_div_min: minimum baud rate divisor * @baud_rate_div_max: maximum baud rate divisor * @has_fifo: boolean to know if fifo is used for driver - * @has_startbit: boolean to know if start bit is used to start transfer + * @flags: compatible specific SPI controller flags used at registration time */ struct stm32_spi_cfg { const struct stm32_spi_regspec *regs; @@ -253,6 +252,7 @@ struct stm32_spi_cfg { unsigned int baud_rate_div_min; unsigned int baud_rate_div_max; bool has_fifo; + u16 flags; }; /** @@ -1722,6 +1722,7 @@ static const struct stm32_spi_cfg stm32f4_spi_cfg = { .baud_rate_div_min = STM32F4_SPI_BR_DIV_MIN, .baud_rate_div_max = STM32F4_SPI_BR_DIV_MAX, .has_fifo = false, + .flags = SPI_MASTER_MUST_TX, }; static const struct stm32_spi_cfg stm32h7_spi_cfg = { @@ -1854,7 +1855,7 @@ static int stm32_spi_probe(struct platform_device *pdev) master->prepare_message = stm32_spi_prepare_msg; master->transfer_one = stm32_spi_transfer_one; master->unprepare_message = stm32_spi_unprepare_msg; - master->flags = SPI_MASTER_MUST_TX; + master->flags = spi->cfg->flags; spi->dma_tx = dma_request_chan(spi->dev, "tx"); if (IS_ERR(spi->dma_tx)) { diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index 342ee8d2c476..cc0da4822231 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -726,7 +726,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to get TX DMA capacities: %d\n", ret); - goto out_disable_clk; + goto out_release_dma; } dma_tx_burst = caps.max_burst; } @@ -735,7 +735,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (IS_ERR_OR_NULL(master->dma_rx)) { if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; - goto out_disable_clk; + goto out_release_dma; } master->dma_rx = NULL; dma_rx_burst = INT_MAX; @@ -744,7 +744,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to get RX DMA capacities: %d\n", ret); - goto out_disable_clk; + goto out_release_dma; } dma_rx_burst = caps.max_burst; } @@ -753,10 +753,20 @@ static int uniphier_spi_probe(struct platform_device *pdev) ret = devm_spi_register_master(&pdev->dev, master); if (ret) - goto out_disable_clk; + goto out_release_dma; return 0; +out_release_dma: + if (!IS_ERR_OR_NULL(master->dma_rx)) { + dma_release_channel(master->dma_rx); + master->dma_rx = NULL; + } + if (!IS_ERR_OR_NULL(master->dma_tx)) { + dma_release_channel(master->dma_tx); + master->dma_tx = NULL; + } + out_disable_clk: clk_disable_unprepare(priv->clk); diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c index 8075f60fd02c..2d5cf1714ae0 100644 --- a/drivers/target/iscsi/iscsi_target_tpg.c +++ b/drivers/target/iscsi/iscsi_target_tpg.c @@ -443,6 +443,9 @@ static bool iscsit_tpg_check_network_portal( break; } spin_unlock(&tpg->tpg_np_lock); + + if (match) + break; } spin_unlock(&tiqn->tiqn_tpg_lock); diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index ba27b274c967..0b1808e3a912 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -322,6 +322,7 @@ static int addr_cnt; #define GSM1_ESCAPE_BITS 0x20 #define XON 0x11 #define XOFF 0x13 +#define ISO_IEC_646_MASK 0x7F static const struct tty_port_operations gsm_port_ops; @@ -531,7 +532,8 @@ static int gsm_stuff_frame(const u8 *input, u8 *output, int len) int olen = 0; while (len--) { if (*input == GSM1_SOF || *input == GSM1_ESCAPE - || *input == XON || *input == XOFF) { + || (*input & ISO_IEC_646_MASK) == XON + || (*input & ISO_IEC_646_MASK) == XOFF) { *output++ = GSM1_ESCAPE; *output++ = *input++ ^ GSM1_ESCAPE_BITS; olen++; diff --git a/drivers/tty/rpmsg_tty.c b/drivers/tty/rpmsg_tty.c index dae2a4e44f38..29db413bbc03 100644 --- a/drivers/tty/rpmsg_tty.c +++ b/drivers/tty/rpmsg_tty.c @@ -50,10 +50,17 @@ static int rpmsg_tty_cb(struct rpmsg_device *rpdev, void *data, int len, void *p static int rpmsg_tty_install(struct tty_driver *driver, struct tty_struct *tty) { struct rpmsg_tty_port *cport = idr_find(&tty_idr, tty->index); + struct tty_port *port; tty->driver_data = cport; - return tty_port_install(&cport->port, driver, tty); + port = tty_port_get(&cport->port); + return tty_port_install(port, driver, tty); +} + +static void rpmsg_tty_cleanup(struct tty_struct *tty) +{ + tty_port_put(tty->port); } static int rpmsg_tty_open(struct tty_struct *tty, struct file *filp) @@ -106,12 +113,19 @@ static unsigned int rpmsg_tty_write_room(struct tty_struct *tty) return size; } +static void rpmsg_tty_hangup(struct tty_struct *tty) +{ + tty_port_hangup(tty->port); +} + static const struct tty_operations rpmsg_tty_ops = { .install = rpmsg_tty_install, .open = rpmsg_tty_open, .close = rpmsg_tty_close, .write = rpmsg_tty_write, .write_room = rpmsg_tty_write_room, + .hangup = rpmsg_tty_hangup, + .cleanup = rpmsg_tty_cleanup, }; static struct rpmsg_tty_port *rpmsg_tty_alloc_cport(void) @@ -137,8 +151,10 @@ static struct rpmsg_tty_port *rpmsg_tty_alloc_cport(void) return cport; } -static void rpmsg_tty_release_cport(struct rpmsg_tty_port *cport) +static void rpmsg_tty_destruct_port(struct tty_port *port) { + struct rpmsg_tty_port *cport = container_of(port, struct rpmsg_tty_port, port); + mutex_lock(&idr_lock); idr_remove(&tty_idr, cport->id); mutex_unlock(&idr_lock); @@ -146,7 +162,10 @@ static void rpmsg_tty_release_cport(struct rpmsg_tty_port *cport) kfree(cport); } -static const struct tty_port_operations rpmsg_tty_port_ops = { }; +static const struct tty_port_operations rpmsg_tty_port_ops = { + .destruct = rpmsg_tty_destruct_port, +}; + static int rpmsg_tty_probe(struct rpmsg_device *rpdev) { @@ -166,7 +185,8 @@ static int rpmsg_tty_probe(struct rpmsg_device *rpdev) cport->id, dev); if (IS_ERR(tty_dev)) { ret = dev_err_probe(dev, PTR_ERR(tty_dev), "Failed to register tty port\n"); - goto err_destroy; + tty_port_put(&cport->port); + return ret; } cport->rpdev = rpdev; @@ -177,12 +197,6 @@ static int rpmsg_tty_probe(struct rpmsg_device *rpdev) rpdev->src, rpdev->dst, cport->id); return 0; - -err_destroy: - tty_port_destroy(&cport->port); - rpmsg_tty_release_cport(cport); - - return ret; } static void rpmsg_tty_remove(struct rpmsg_device *rpdev) @@ -192,13 +206,11 @@ static void rpmsg_tty_remove(struct rpmsg_device *rpdev) dev_dbg(&rpdev->dev, "Removing rpmsg tty device %d\n", cport->id); /* User hang up to release the tty */ - if (tty_port_initialized(&cport->port)) - tty_port_tty_hangup(&cport->port, false); + tty_port_tty_hangup(&cport->port, false); tty_unregister_device(rpmsg_tty_driver, cport->id); - tty_port_destroy(&cport->port); - rpmsg_tty_release_cport(cport); + tty_port_put(&cport->port); } static struct rpmsg_device_id rpmsg_driver_tty_id_table[] = { diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index bce28729dd7b..be8626234627 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -83,8 +83,17 @@ static int of_platform_serial_setup(struct platform_device *ofdev, port->mapsize = resource_size(&resource); /* Check for shifted address mapping */ - if (of_property_read_u32(np, "reg-offset", &prop) == 0) + if (of_property_read_u32(np, "reg-offset", &prop) == 0) { + if (prop >= port->mapsize) { + dev_warn(&ofdev->dev, "reg-offset %u exceeds region size %pa\n", + prop, &port->mapsize); + ret = -EINVAL; + goto err_unprepare; + } + port->mapbase += prop; + port->mapsize -= prop; + } port->iotype = UPIO_MEM; if (of_property_read_u32(np, "reg-io-width", &prop) == 0) { diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index e8b5469e9dfa..e17e97ea86fa 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -4779,8 +4779,30 @@ static const struct pci_device_id serial_pci_tbl[] = { { PCI_VENDOR_ID_INTASHIELD, PCI_DEVICE_ID_INTASHIELD_IS400, PCI_ANY_ID, PCI_ANY_ID, 0, 0, /* 135a.0dc0 */ pbn_b2_4_115200 }, + /* Brainboxes Devices */ /* - * BrainBoxes UC-260 + * Brainboxes UC-101 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0BA1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-235/246 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0AA1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_1_115200 }, + /* + * Brainboxes UC-257 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0861, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-260/271/701/756 */ { PCI_VENDOR_ID_INTASHIELD, 0x0D21, PCI_ANY_ID, PCI_ANY_ID, @@ -4788,7 +4810,81 @@ static const struct pci_device_id serial_pci_tbl[] = { pbn_b2_4_115200 }, { PCI_VENDOR_ID_INTASHIELD, 0x0E34, PCI_ANY_ID, PCI_ANY_ID, - PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-268 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0841, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-275/279 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0881, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_8_115200 }, + /* + * Brainboxes UC-302 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08E1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-310 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08C1, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-313 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x08A3, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-320/324 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0A61, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_1_115200 }, + /* + * Brainboxes UC-346 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0B02, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-357 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0A81, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0A83, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_2_115200 }, + /* + * Brainboxes UC-368 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0C41, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, + pbn_b2_4_115200 }, + /* + * Brainboxes UC-420/431 + */ + { PCI_VENDOR_ID_INTASHIELD, 0x0921, + PCI_ANY_ID, PCI_ANY_ID, + 0, 0, pbn_b2_4_115200 }, /* * Perle PCI-RAS cards diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 2abb3de11a48..3b12bfc1ed67 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2056,7 +2056,10 @@ static void serial8250_break_ctl(struct uart_port *port, int break_state) serial8250_rpm_put(up); } -static void wait_for_lsr(struct uart_8250_port *up, int bits) +/* + * Wait for transmitter & holding register to empty + */ +static void wait_for_xmitr(struct uart_8250_port *up, int bits) { unsigned int status, tmout = 10000; @@ -2073,16 +2076,6 @@ static void wait_for_lsr(struct uart_8250_port *up, int bits) udelay(1); touch_nmi_watchdog(); } -} - -/* - * Wait for transmitter & holding register to empty - */ -static void wait_for_xmitr(struct uart_8250_port *up, int bits) -{ - unsigned int tmout; - - wait_for_lsr(up, bits); /* Wait up to 1s for flow control if necessary */ if (up->port.flags & UPF_CONS_FLOW) { @@ -3333,35 +3326,6 @@ static void serial8250_console_restore(struct uart_8250_port *up) } /* - * Print a string to the serial port using the device FIFO - * - * It sends fifosize bytes and then waits for the fifo - * to get empty. - */ -static void serial8250_console_fifo_write(struct uart_8250_port *up, - const char *s, unsigned int count) -{ - int i; - const char *end = s + count; - unsigned int fifosize = up->port.fifosize; - bool cr_sent = false; - - while (s != end) { - wait_for_lsr(up, UART_LSR_THRE); - - for (i = 0; i < fifosize && s != end; ++i) { - if (*s == '\n' && !cr_sent) { - serial_out(up, UART_TX, '\r'); - cr_sent = true; - } else { - serial_out(up, UART_TX, *s++); - cr_sent = false; - } - } - } -} - -/* * Print a string to the serial port trying not to disturb * any possible real use of the port... * @@ -3376,7 +3340,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, struct uart_8250_em485 *em485 = up->em485; struct uart_port *port = &up->port; unsigned long flags; - unsigned int ier, use_fifo; + unsigned int ier; int locked = 1; touch_nmi_watchdog(); @@ -3408,20 +3372,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, mdelay(port->rs485.delay_rts_before_send); } - use_fifo = (up->capabilities & UART_CAP_FIFO) && - port->fifosize > 1 && - (serial_port_in(port, UART_FCR) & UART_FCR_ENABLE_FIFO) && - /* - * After we put a data in the fifo, the controller will send - * it regardless of the CTS state. Therefore, only use fifo - * if we don't use control flow. - */ - !(up->port.flags & UPF_CONS_FLOW); - - if (likely(use_fifo)) - serial8250_console_fifo_write(up, s, count); - else - uart_console_write(port, s, count, serial8250_console_putchar); + uart_console_write(port, s, count, serial8250_console_putchar); /* * Finally, wait for transmitter to become empty diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 1f1df46242f9..ba053a68529f 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1582,9 +1582,6 @@ static void pl011_set_mctrl(struct uart_port *port, unsigned int mctrl) container_of(port, struct uart_amba_port, port); unsigned int cr; - if (port->rs485.flags & SER_RS485_ENABLED) - mctrl &= ~TIOCM_RTS; - cr = pl011_read(uap, REG_CR); #define TIOCMBIT(tiocmbit, uartbit) \ @@ -1808,14 +1805,8 @@ static int pl011_startup(struct uart_port *port) cr &= UART011_CR_RTS | UART011_CR_DTR; cr |= UART01x_CR_UARTEN | UART011_CR_RXE; - if (port->rs485.flags & SER_RS485_ENABLED) { - if (port->rs485.flags & SER_RS485_RTS_AFTER_SEND) - cr &= ~UART011_CR_RTS; - else - cr |= UART011_CR_RTS; - } else { + if (!(port->rs485.flags & SER_RS485_ENABLED)) cr |= UART011_CR_TXE; - } pl011_write(cr, uap, REG_CR); diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index dc40c4155356..0db90be4c3bc 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -144,6 +144,11 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) unsigned long flags; unsigned int old; + if (port->rs485.flags & SER_RS485_ENABLED) { + set &= ~TIOCM_RTS; + clear &= ~TIOCM_RTS; + } + spin_lock_irqsave(&port->lock, flags); old = port->mctrl; port->mctrl = (old & ~clear) | set; @@ -157,23 +162,10 @@ uart_update_mctrl(struct uart_port *port, unsigned int set, unsigned int clear) static void uart_port_dtr_rts(struct uart_port *uport, int raise) { - int rs485_on = uport->rs485_config && - (uport->rs485.flags & SER_RS485_ENABLED); - int RTS_after_send = !!(uport->rs485.flags & SER_RS485_RTS_AFTER_SEND); - - if (raise) { - if (rs485_on && RTS_after_send) { - uart_set_mctrl(uport, TIOCM_DTR); - uart_clear_mctrl(uport, TIOCM_RTS); - } else { - uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); - } - } else { - unsigned int clear = TIOCM_DTR; - - clear |= (!rs485_on || RTS_after_send) ? TIOCM_RTS : 0; - uart_clear_mctrl(uport, clear); - } + if (raise) + uart_set_mctrl(uport, TIOCM_DTR | TIOCM_RTS); + else + uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); } /* @@ -1075,11 +1067,6 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) goto out; if (!tty_io_error(tty)) { - if (uport->rs485.flags & SER_RS485_ENABLED) { - set &= ~TIOCM_RTS; - clear &= ~TIOCM_RTS; - } - uart_update_mctrl(uport, set, clear); ret = 0; } @@ -2390,6 +2377,9 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, */ spin_lock_irqsave(&port->lock, flags); port->mctrl &= TIOCM_DTR; + if (port->rs485.flags & SER_RS485_ENABLED && + !(port->rs485.flags & SER_RS485_RTS_AFTER_SEND)) + port->mctrl |= TIOCM_RTS; port->ops->set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 1f89ab0e49ac..9570002d07e7 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -550,11 +550,23 @@ static void stm32_usart_transmit_chars(struct uart_port *port) struct stm32_port *stm32_port = to_stm32_port(port); const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; struct circ_buf *xmit = &port->state->xmit; + u32 isr; + int ret; if (port->x_char) { if (stm32_usart_tx_dma_started(stm32_port) && stm32_usart_tx_dma_enabled(stm32_port)) stm32_usart_clr_bits(port, ofs->cr3, USART_CR3_DMAT); + + /* Check that TDR is empty before filling FIFO */ + ret = + readl_relaxed_poll_timeout_atomic(port->membase + ofs->isr, + isr, + (isr & USART_SR_TXE), + 10, 1000); + if (ret) + dev_warn(port->dev, "1 character may be erased\n"); + writel_relaxed(port->x_char, port->membase + ofs->tdr); port->x_char = 0; port->icount.tx++; @@ -730,7 +742,7 @@ static void stm32_usart_start_tx(struct uart_port *port) struct serial_rs485 *rs485conf = &port->rs485; struct circ_buf *xmit = &port->state->xmit; - if (uart_circ_empty(xmit)) + if (uart_circ_empty(xmit) && !port->x_char) return; if (rs485conf->flags & SER_RS485_ENABLED) { diff --git a/drivers/usb/cdns3/drd.c b/drivers/usb/cdns3/drd.c index 55c73b1d8704..d00ff98dffab 100644 --- a/drivers/usb/cdns3/drd.c +++ b/drivers/usb/cdns3/drd.c @@ -483,11 +483,11 @@ int cdns_drd_exit(struct cdns *cdns) /* Indicate the cdns3 core was power lost before */ bool cdns_power_is_lost(struct cdns *cdns) { - if (cdns->version == CDNS3_CONTROLLER_V1) { - if (!(readl(&cdns->otg_v1_regs->simulate) & BIT(0))) + if (cdns->version == CDNS3_CONTROLLER_V0) { + if (!(readl(&cdns->otg_v0_regs->simulate) & BIT(0))) return true; } else { - if (!(readl(&cdns->otg_v0_regs->simulate) & BIT(0))) + if (!(readl(&cdns->otg_v1_regs->simulate) & BIT(0))) return true; } return false; diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index 4169cf40a03b..8f8405b0d608 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -39,8 +39,11 @@ static int ulpi_match(struct device *dev, struct device_driver *driver) struct ulpi *ulpi = to_ulpi_dev(dev); const struct ulpi_device_id *id; - /* Some ULPI devices don't have a vendor id so rely on OF match */ - if (ulpi->id.vendor == 0) + /* + * Some ULPI devices don't have a vendor id + * or provide an id_table so rely on OF match. + */ + if (ulpi->id.vendor == 0 || !drv->id_table) return of_driver_match_device(dev, driver); for (id = drv->id_table; id->vendor; id++) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 3e01dd6e509b..d9712c2602af 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1563,6 +1563,13 @@ int usb_hcd_submit_urb (struct urb *urb, gfp_t mem_flags) urb->hcpriv = NULL; INIT_LIST_HEAD(&urb->urb_list); atomic_dec(&urb->use_count); + /* + * Order the write of urb->use_count above before the read + * of urb->reject below. Pairs with the memory barriers in + * usb_kill_urb() and usb_poison_urb(). + */ + smp_mb__after_atomic(); + atomic_dec(&urb->dev->urbnum); if (atomic_read(&urb->reject)) wake_up(&usb_kill_urb_queue); @@ -1665,6 +1672,13 @@ static void __usb_hcd_giveback_urb(struct urb *urb) usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); + /* + * Order the write of urb->use_count above before the read + * of urb->reject below. Pairs with the memory barriers in + * usb_kill_urb() and usb_poison_urb(). + */ + smp_mb__after_atomic(); + if (unlikely(atomic_read(&urb->reject))) wake_up(&usb_kill_urb_queue); usb_put_urb(urb); diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c index 30727729a44c..33d62d7e3929 100644 --- a/drivers/usb/core/urb.c +++ b/drivers/usb/core/urb.c @@ -715,6 +715,12 @@ void usb_kill_urb(struct urb *urb) if (!(urb && urb->dev && urb->ep)) return; atomic_inc(&urb->reject); + /* + * Order the write of urb->reject above before the read + * of urb->use_count below. Pairs with the barriers in + * __usb_hcd_giveback_urb() and usb_hcd_submit_urb(). + */ + smp_mb__after_atomic(); usb_hcd_unlink_urb(urb, -ENOENT); wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0); @@ -756,6 +762,12 @@ void usb_poison_urb(struct urb *urb) if (!urb) return; atomic_inc(&urb->reject); + /* + * Order the write of urb->reject above before the read + * of urb->use_count below. Pairs with the barriers in + * __usb_hcd_giveback_urb() and usb_hcd_submit_urb(). + */ + smp_mb__after_atomic(); if (!urb->dev || !urb->ep) return; diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index 2bc03f41c70a..eee3504397e6 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -5097,7 +5097,7 @@ int dwc2_hsotg_suspend(struct dwc2_hsotg *hsotg) hsotg->gadget.speed = USB_SPEED_UNKNOWN; spin_unlock_irqrestore(&hsotg->lock, flags); - for (ep = 0; ep < hsotg->num_of_eps; ep++) { + for (ep = 1; ep < hsotg->num_of_eps; ep++) { if (hsotg->eps_in[ep]) dwc2_hsotg_ep_disable_lock(&hsotg->eps_in[ep]->ep); if (hsotg->eps_out[ep]) diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c index 9cc3ad701a29..e14ac15e24c3 100644 --- a/drivers/usb/dwc3/dwc3-xilinx.c +++ b/drivers/usb/dwc3/dwc3-xilinx.c @@ -102,14 +102,26 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data) int ret; u32 reg; - usb3_phy = devm_phy_get(dev, "usb3-phy"); - if (PTR_ERR(usb3_phy) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; + usb3_phy = devm_phy_optional_get(dev, "usb3-phy"); + if (IS_ERR(usb3_phy)) { + ret = PTR_ERR(usb3_phy); + dev_err_probe(dev, ret, + "failed to get USB3 PHY\n"); goto err; - } else if (IS_ERR(usb3_phy)) { - usb3_phy = NULL; } + /* + * The following core resets are not required unless a USB3 PHY + * is used, and the subsequent register settings are not required + * unless a core reset is performed (they should be set properly + * by the first-stage boot loader, but may be reverted by a core + * reset). They may also break the configuration if USB3 is actually + * in use but the usb3-phy entry is missing from the device tree. + * Therefore, skip these operations in this case. + */ + if (!usb3_phy) + goto skip_usb3_phy; + crst = devm_reset_control_get_exclusive(dev, "usb_crst"); if (IS_ERR(crst)) { ret = PTR_ERR(crst); @@ -188,6 +200,7 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data) goto err; } +skip_usb3_phy: /* * This routes the USB DMA traffic to go through FPD path instead * of reaching DDR directly. This traffic routing is needed to diff --git a/drivers/usb/gadget/function/f_sourcesink.c b/drivers/usb/gadget/function/f_sourcesink.c index 1abf08e5164a..6803cd60cc6d 100644 --- a/drivers/usb/gadget/function/f_sourcesink.c +++ b/drivers/usb/gadget/function/f_sourcesink.c @@ -584,6 +584,7 @@ static int source_sink_start_ep(struct f_sourcesink *ss, bool is_in, if (is_iso) { switch (speed) { + case USB_SPEED_SUPER_PLUS: case USB_SPEED_SUPER: size = ss->isoc_maxpacket * (ss->isoc_mult + 1) * diff --git a/drivers/usb/gadget/udc/at91_udc.c b/drivers/usb/gadget/udc/at91_udc.c index dd0819df096e..9040a0561466 100644 --- a/drivers/usb/gadget/udc/at91_udc.c +++ b/drivers/usb/gadget/udc/at91_udc.c @@ -1895,7 +1895,7 @@ static int at91udc_probe(struct platform_device *pdev) at91_vbus_irq, 0, driver_name, udc); if (retval) { DBG("request vbus irq %d failed\n", - udc->board.vbus_pin); + desc_to_gpio(udc->board.vbus_pin)); goto err_unprepare_iclk; } } diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index c1edcc9b13ce..dc570ce4e831 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -437,6 +437,9 @@ static int __maybe_unused xhci_plat_suspend(struct device *dev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); int ret; + if (pm_runtime_suspended(dev)) + pm_runtime_resume(dev); + ret = xhci_priv_suspend_quirk(hcd); if (ret) return ret; diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 29191d33c0e3..1a05e3dcfec8 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2301,6 +2301,16 @@ UNUSUAL_DEV( 0x2027, 0xa001, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, usb_stor_euscsi_init, US_FL_SCM_MULT_TARG ), +/* + * Reported by DocMAX <mail@vacharakis.de> + * and Thomas Weißschuh <linux@weissschuh.net> + */ +UNUSUAL_DEV( 0x2109, 0x0715, 0x9999, 0x9999, + "VIA Labs, Inc.", + "VL817 SATA Bridge", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + UNUSUAL_DEV( 0x2116, 0x0320, 0x0001, 0x0001, "ST", "2A", diff --git a/drivers/usb/typec/port-mapper.c b/drivers/usb/typec/port-mapper.c index 07d307418b47..a7d507802509 100644 --- a/drivers/usb/typec/port-mapper.c +++ b/drivers/usb/typec/port-mapper.c @@ -56,7 +56,12 @@ int typec_link_ports(struct typec_port *con) { struct each_port_arg arg = { .port = con, .match = NULL }; + if (!has_acpi_companion(&con->dev)) + return 0; + bus_for_each_dev(&acpi_bus_type, NULL, &arg, typec_port_match); + if (!arg.match) + return 0; /* * REVISIT: Now each connector can have only a single component master. @@ -74,5 +79,6 @@ int typec_link_ports(struct typec_port *con) void typec_unlink_ports(struct typec_port *con) { - component_master_del(&con->dev, &typec_aggregate_ops); + if (has_acpi_companion(&con->dev)) + component_master_del(&con->dev, &typec_aggregate_ops); } diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index 35a1307349a2..e07d26a3cd8e 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -75,9 +75,25 @@ static int tcpci_write16(struct tcpci *tcpci, unsigned int reg, u16 val) static int tcpci_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc) { struct tcpci *tcpci = tcpc_to_tcpci(tcpc); + bool vconn_pres; + enum typec_cc_polarity polarity = TYPEC_POLARITY_CC1; unsigned int reg; int ret; + ret = regmap_read(tcpci->regmap, TCPC_POWER_STATUS, ®); + if (ret < 0) + return ret; + + vconn_pres = !!(reg & TCPC_POWER_STATUS_VCONN_PRES); + if (vconn_pres) { + ret = regmap_read(tcpci->regmap, TCPC_TCPC_CTRL, ®); + if (ret < 0) + return ret; + + if (reg & TCPC_TCPC_CTRL_ORIENTATION) + polarity = TYPEC_POLARITY_CC2; + } + switch (cc) { case TYPEC_CC_RA: reg = (TCPC_ROLE_CTRL_CC_RA << TCPC_ROLE_CTRL_CC1_SHIFT) | @@ -112,6 +128,16 @@ static int tcpci_set_cc(struct tcpc_dev *tcpc, enum typec_cc_status cc) break; } + if (vconn_pres) { + if (polarity == TYPEC_POLARITY_CC2) { + reg &= ~(TCPC_ROLE_CTRL_CC1_MASK << TCPC_ROLE_CTRL_CC1_SHIFT); + reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC1_SHIFT); + } else { + reg &= ~(TCPC_ROLE_CTRL_CC2_MASK << TCPC_ROLE_CTRL_CC2_SHIFT); + reg |= (TCPC_ROLE_CTRL_CC_OPEN << TCPC_ROLE_CTRL_CC2_SHIFT); + } + } + ret = regmap_write(tcpci->regmap, TCPC_ROLE_CTRL, reg); if (ret < 0) return ret; diff --git a/drivers/usb/typec/tcpm/tcpci.h b/drivers/usb/typec/tcpm/tcpci.h index 2be7a77d400e..b2edd45f13c6 100644 --- a/drivers/usb/typec/tcpm/tcpci.h +++ b/drivers/usb/typec/tcpm/tcpci.h @@ -98,6 +98,7 @@ #define TCPC_POWER_STATUS_SOURCING_VBUS BIT(4) #define TCPC_POWER_STATUS_VBUS_DET BIT(3) #define TCPC_POWER_STATUS_VBUS_PRES BIT(2) +#define TCPC_POWER_STATUS_VCONN_PRES BIT(1) #define TCPC_POWER_STATUS_SINKING_VBUS BIT(0) #define TCPC_FAULT_STATUS 0x1f diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 59d4fa2443f2..5fce795b69c7 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5156,7 +5156,8 @@ static void _tcpm_pd_vbus_off(struct tcpm_port *port) case SNK_TRYWAIT_DEBOUNCE: break; case SNK_ATTACH_WAIT: - tcpm_set_state(port, SNK_UNATTACHED, 0); + case SNK_DEBOUNCED: + /* Do nothing, as TCPM is still waiting for vbus to reaach VSAFE5V to connect */ break; case SNK_NEGOTIATE_CAPABILITIES: @@ -5263,6 +5264,10 @@ static void _tcpm_pd_vbus_vsafe0v(struct tcpm_port *port) case PR_SWAP_SNK_SRC_SOURCE_ON: /* Do nothing, vsafe0v is expected during transition */ break; + case SNK_ATTACH_WAIT: + case SNK_DEBOUNCED: + /*Do nothing, still waiting for VSAFE5V for connect */ + break; default: if (port->pwr_role == TYPEC_SINK && port->auto_vbus_discharge_enabled) tcpm_set_state(port, SNK_UNATTACHED, 0); diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index bff96d64dddf..6db7c8ddd51c 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -325,7 +325,7 @@ static int ucsi_ccg_init(struct ucsi_ccg *uc) if (status < 0) return status; - if (!data) + if (!(data & DEV_INT)) return 0; status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index 23999df52739..c8e0ea27caf1 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -287,8 +287,6 @@ struct hvfb_par { static uint screen_width = HVFB_WIDTH; static uint screen_height = HVFB_HEIGHT; -static uint screen_width_max = HVFB_WIDTH; -static uint screen_height_max = HVFB_HEIGHT; static uint screen_depth; static uint screen_fb_size; static uint dio_fb_size; /* FB size for deferred IO */ @@ -582,7 +580,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) int ret = 0; unsigned long t; u8 index; - int i; memset(msg, 0, sizeof(struct synthvid_msg)); msg->vid_hdr.type = SYNTHVID_RESOLUTION_REQUEST; @@ -613,13 +610,6 @@ static int synthvid_get_supported_resolution(struct hv_device *hdev) goto out; } - for (i = 0; i < msg->resolution_resp.resolution_count; i++) { - screen_width_max = max_t(unsigned int, screen_width_max, - msg->resolution_resp.supported_resolution[i].width); - screen_height_max = max_t(unsigned int, screen_height_max, - msg->resolution_resp.supported_resolution[i].height); - } - screen_width = msg->resolution_resp.supported_resolution[index].width; screen_height = @@ -941,7 +931,7 @@ static void hvfb_get_option(struct fb_info *info) if (x < HVFB_WIDTH_MIN || y < HVFB_HEIGHT_MIN || (synthvid_ver_ge(par->synthvid_version, SYNTHVID_VERSION_WIN10) && - (x > screen_width_max || y > screen_height_max)) || + (x * y * screen_depth / 8 > screen_fb_size)) || (par->synthvid_version == SYNTHVID_VERSION_WIN8 && x * y * screen_depth / 8 > SYNTHVID_FB_SIZE_WIN8) || (par->synthvid_version == SYNTHVID_VERSION_WIN7 && @@ -1194,8 +1184,8 @@ static int hvfb_probe(struct hv_device *hdev, } hvfb_get_option(info); - pr_info("Screen resolution: %dx%d, Color depth: %d\n", - screen_width, screen_height, screen_depth); + pr_info("Screen resolution: %dx%d, Color depth: %d, Frame buffer size: %d\n", + screen_width, screen_height, screen_depth, screen_fb_size); ret = hvfb_getmem(hdev, info); if (ret) { diff --git a/fs/Makefile b/fs/Makefile index dab324aea08f..208a74e0b00e 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -96,7 +96,7 @@ obj-$(CONFIG_EXPORTFS) += exportfs/ obj-$(CONFIG_NFSD) += nfsd/ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ -obj-$(CONFIG_UNICODE) += unicode/ +obj-y += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ obj-$(CONFIG_CIFS) += cifs/ diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ddea6acbddde..c07f35719ee3 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -817,20 +817,20 @@ static struct file_system_type bm_fs_type = { }; MODULE_ALIAS_FS("binfmt_misc"); +static struct ctl_table_header *binfmt_misc_header; + static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); - if (!register_sysctl_mount_point("fs/binfmt_misc")) { - pr_warn("Failed to create fs/binfmt_misc sysctl mount point"); - return -ENOMEM; - } + binfmt_misc_header = register_sysctl_mount_point("fs/binfmt_misc"); return 0; } static void __exit exit_misc_binfmt(void) { + unregister_sysctl_table(binfmt_misc_header); unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a5bd6926f7ff..d8af6620a941 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1214,6 +1214,35 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; /* + * Our start offset might be in the middle of an existing extent + * map, so take that into account. + */ + range_len = em->len - (cur - em->start); + /* + * If this range of the extent map is already flagged for delalloc, + * skip it, because: + * + * 1) We could deadlock later, when trying to reserve space for + * delalloc, because in case we can't immediately reserve space + * the flusher can start delalloc and wait for the respective + * ordered extents to complete. The deadlock would happen + * because we do the space reservation while holding the range + * locked, and starting writeback, or finishing an ordered + * extent, requires locking the range; + * + * 2) If there's delalloc there, it means there's dirty pages for + * which writeback has not started yet (we clean the delalloc + * flag when starting writeback and after creating an ordered + * extent). If we mark pages in an adjacent range for defrag, + * then we will have a larger contiguous range for delalloc, + * very likely resulting in a larger extent after writeback is + * triggered (except in a case of free space fragmentation). + */ + if (test_range_bit(&inode->io_tree, cur, cur + range_len - 1, + EXTENT_DELALLOC, 0, NULL)) + goto next; + + /* * For do_compress case, we want to compress all valid file * extents, thus no @extent_thresh or mergeable check. */ @@ -1221,7 +1250,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto add; /* Skip too large extent */ - if (em->len >= extent_thresh) + if (range_len >= extent_thresh) goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, @@ -1442,9 +1471,11 @@ static int defrag_one_cluster(struct btrfs_inode *inode, list_for_each_entry(entry, &target_list, list) { u32 range_len = entry->len; - /* Reached the limit */ - if (max_sectors && max_sectors == *sectors_defragged) + /* Reached or beyond the limit */ + if (max_sectors && *sectors_defragged >= max_sectors) { + ret = 1; break; + } if (max_sectors) range_len = min_t(u32, range_len, @@ -1465,7 +1496,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode, extent_thresh, newer_than, do_compress); if (ret < 0) break; - *sectors_defragged += range_len; + *sectors_defragged += range_len >> + inode->root->fs_info->sectorsize_bits; } out: list_for_each_entry_safe(entry, tmp, &target_list, list) { @@ -1484,6 +1516,12 @@ out: * @newer_than: minimum transid to defrag * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode * will be defragged. + * + * Return <0 for error. + * Return >=0 for the number of sectors defragged, and range->start will be updated + * to indicate the file offset where next defrag should be started at. + * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without + * defragging all the range). */ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, struct btrfs_ioctl_defrag_range_args *range, @@ -1499,6 +1537,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, int compress_type = BTRFS_COMPRESS_ZLIB; int ret = 0; u32 extent_thresh = range->extent_thresh; + pgoff_t start_index; if (isize == 0) return 0; @@ -1518,12 +1557,16 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, if (range->start + range->len > range->start) { /* Got a specific range */ - last_byte = min(isize, range->start + range->len) - 1; + last_byte = min(isize, range->start + range->len); } else { /* Defrag until file end */ - last_byte = isize - 1; + last_byte = isize; } + /* Align the range */ + cur = round_down(range->start, fs_info->sectorsize); + last_byte = round_up(last_byte, fs_info->sectorsize) - 1; + /* * If we were not given a ra, allocate a readahead context. As * readahead is just an optimization, defrag will work without it so @@ -1536,16 +1579,26 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, file_ra_state_init(ra, inode->i_mapping); } - /* Align the range */ - cur = round_down(range->start, fs_info->sectorsize); - last_byte = round_up(last_byte, fs_info->sectorsize) - 1; + /* + * Make writeback start from the beginning of the range, so that the + * defrag range can be written sequentially. + */ + start_index = cur >> PAGE_SHIFT; + if (start_index < inode->i_mapping->writeback_index) + inode->i_mapping->writeback_index = start_index; while (cur < last_byte) { + const unsigned long prev_sectors_defragged = sectors_defragged; u64 cluster_end; /* The cluster size 256K should always be page aligned */ BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); + if (btrfs_defrag_cancelled(fs_info)) { + ret = -EAGAIN; + break; + } + /* We want the cluster end at page boundary when possible */ cluster_end = (((cur >> PAGE_SHIFT) + (SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1; @@ -1567,14 +1620,27 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, cluster_end + 1 - cur, extent_thresh, newer_than, do_compress, §ors_defragged, max_to_defrag); + + if (sectors_defragged > prev_sectors_defragged) + balance_dirty_pages_ratelimited(inode->i_mapping); + btrfs_inode_unlock(inode, 0); if (ret < 0) break; cur = cluster_end + 1; + if (ret > 0) { + ret = 0; + break; + } } if (ra_allocated) kfree(ra); + /* + * Update range.start for autodefrag, this will indicate where to start + * in next run. + */ + range->start = cur; if (sectors_defragged) { /* * We have defragged some sectors, for compression case they @@ -3086,10 +3152,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, btrfs_inode_lock(inode, 0); err = btrfs_delete_subvolume(dir, dentry); btrfs_inode_unlock(inode, 0); - if (!err) { - fsnotify_rmdir(dir, dentry); - d_delete(dentry); - } + if (!err) + d_delete_notify(dir, dentry); out_dput: dput(dentry); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 7d305b974824..b472cd066d1c 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2218,6 +2218,7 @@ static int unsafe_request_wait(struct inode *inode) struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_mds_request *req1 = NULL, *req2 = NULL; + unsigned int max_sessions; int ret, err = 0; spin_lock(&ci->i_unsafe_lock); @@ -2236,36 +2237,44 @@ static int unsafe_request_wait(struct inode *inode) spin_unlock(&ci->i_unsafe_lock); /* + * The mdsc->max_sessions is unlikely to be changed + * mostly, here we will retry it by reallocating the + * sessions array memory to get rid of the mdsc->mutex + * lock. + */ +retry: + max_sessions = mdsc->max_sessions; + + /* * Trigger to flush the journal logs in all the relevant MDSes * manually, or in the worst case we must wait at most 5 seconds * to wait the journal logs to be flushed by the MDSes periodically. */ - if (req1 || req2) { + if ((req1 || req2) && likely(max_sessions)) { struct ceph_mds_session **sessions = NULL; struct ceph_mds_session *s; struct ceph_mds_request *req; - unsigned int max; int i; - /* - * The mdsc->max_sessions is unlikely to be changed - * mostly, here we will retry it by reallocating the - * sessions arrary memory to get rid of the mdsc->mutex - * lock. - */ -retry: - max = mdsc->max_sessions; - sessions = krealloc(sessions, max * sizeof(s), __GFP_ZERO); - if (!sessions) - return -ENOMEM; + sessions = kzalloc(max_sessions * sizeof(s), GFP_KERNEL); + if (!sessions) { + err = -ENOMEM; + goto out; + } spin_lock(&ci->i_unsafe_lock); if (req1) { list_for_each_entry(req, &ci->i_unsafe_dirops, r_unsafe_dir_item) { s = req->r_session; - if (unlikely(s->s_mds >= max)) { + if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); + for (i = 0; i < max_sessions; i++) { + s = sessions[i]; + if (s) + ceph_put_mds_session(s); + } + kfree(sessions); goto retry; } if (!sessions[s->s_mds]) { @@ -2278,8 +2287,14 @@ retry: list_for_each_entry(req, &ci->i_unsafe_iops, r_unsafe_target_item) { s = req->r_session; - if (unlikely(s->s_mds >= max)) { + if (unlikely(s->s_mds >= max_sessions)) { spin_unlock(&ci->i_unsafe_lock); + for (i = 0; i < max_sessions; i++) { + s = sessions[i]; + if (s) + ceph_put_mds_session(s); + } + kfree(sessions); goto retry; } if (!sessions[s->s_mds]) { @@ -2300,7 +2315,7 @@ retry: spin_unlock(&ci->i_ceph_lock); /* send flush mdlog request to MDSes */ - for (i = 0; i < max; i++) { + for (i = 0; i < max_sessions; i++) { s = sessions[i]; if (s) { send_flush_mdlog(s); @@ -2317,15 +2332,19 @@ retry: ceph_timeout_jiffies(req1->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req1); } if (req2) { ret = !wait_for_completion_timeout(&req2->r_safe_completion, ceph_timeout_jiffies(req2->r_timeout)); if (ret) err = -EIO; - ceph_mdsc_put_request(req2); } + +out: + if (req1) + ceph_mdsc_put_request(req1); + if (req2) + ceph_mdsc_put_request(req2); return err; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 5b9104b8e453..bbed3224ad68 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -583,6 +583,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, struct ceph_inode_info *ci = ceph_inode(dir); struct inode *inode; struct timespec64 now; + struct ceph_string *pool_ns; struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb); struct ceph_vino vino = { .ino = req->r_deleg_ino, .snap = CEPH_NOSNAP }; @@ -632,6 +633,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, in.max_size = cpu_to_le64(lo->stripe_unit); ceph_file_layout_to_legacy(lo, &in.layout); + /* lo is private, so pool_ns can't change */ + pool_ns = rcu_dereference_raw(lo->pool_ns); + if (pool_ns) { + iinfo.pool_ns_len = pool_ns->len; + iinfo.pool_ns_data = pool_ns->str; + } down_read(&mdsc->snap_rwsem); ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session, @@ -750,8 +757,10 @@ retry: restore_deleg_ino(dir, req->r_deleg_ino); ceph_mdsc_put_request(req); try_async = false; + ceph_put_string(rcu_dereference_raw(lo.pool_ns)); goto retry; } + ceph_put_string(rcu_dereference_raw(lo.pool_ns)); goto out_req; } } diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 1466b5d01cbb..d3cd2a94d1e8 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1780,8 +1780,8 @@ void configfs_unregister_group(struct config_group *group) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); + d_drop(dentry); fsnotify_rmdir(d_inode(parent), dentry); - d_delete(dentry); inode_unlock(d_inode(parent)); dput(dentry); @@ -1922,10 +1922,10 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); - fsnotify_rmdir(d_inode(root), dentry); inode_unlock(d_inode(dentry)); - d_delete(dentry); + d_drop(dentry); + fsnotify_rmdir(d_inode(root), dentry); inode_unlock(d_inode(root)); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 42e5a766d33c..4f25015aa534 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -621,8 +621,8 @@ void devpts_pty_kill(struct dentry *dentry) dentry->d_fsdata = NULL; drop_nlink(dentry->d_inode); - fsnotify_unlink(d_inode(dentry->d_parent), dentry); d_drop(dentry); + fsnotify_unlink(d_inode(dentry->d_parent), dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 71a3cdceaa03..242e74cfb060 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2485,7 +2485,7 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct fscrypt_str cf_name; #endif }; @@ -2721,7 +2721,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); @@ -2754,7 +2754,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif return err; @@ -2773,7 +2773,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); #endif return err; @@ -2790,7 +2790,7 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif @@ -2806,7 +2806,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif @@ -2822,7 +2822,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, static inline void ext4_fname_free_filename(struct ext4_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index f34f4176c1e7..147b5241dd94 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) const struct unicode_map *um = dir->i_sb->s_encoding; int r, dlen; unsigned char *buff; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 52c9bd154122..269d2d051ede 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1317,7 +1317,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. If quick is set, assume the name being looked up @@ -1428,7 +1428,7 @@ static bool ext4_match(struct inode *parent, f.crypto_buf = fname->crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { @@ -1800,7 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi } } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -2308,7 +2308,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) return -EINVAL; @@ -3126,7 +3126,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -3231,7 +3231,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) ext4_fc_track_unlink(handle, dentry); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eee0d9ebfa6c..ce60b5026bde 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1301,7 +1301,7 @@ static void ext4_put_super(struct super_block *sb) kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -1961,7 +1961,7 @@ static const struct mount_opts { {Opt_err, 0, 0} }; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; @@ -3606,7 +3606,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " @@ -4610,7 +4610,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err < 0) goto failed_mount; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb) && !sb->s_encoding) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -5514,7 +5514,7 @@ failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index f61e65ae27d8..d233c24ea342 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -309,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize); EXT4_ATTR_FEATURE(encryption); EXT4_ATTR_FEATURE(test_dummy_encryption_v2); #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) EXT4_ATTR_FEATURE(casefold); #endif #ifdef CONFIG_FS_VERITY @@ -317,7 +317,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); #endif @@ -329,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif #ifdef CONFIG_FS_VERITY @@ -337,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), #endif NULL, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 1820e9c106f7..166f08623362 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -16,7 +16,7 @@ #include "xattr.h" #include <trace/events/f2fs.h> -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -79,7 +79,7 @@ unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de) int f2fs_init_casefolded_name(const struct inode *dir, struct f2fs_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = dir->i_sb; if (IS_CASEFOLDED(dir)) { @@ -174,7 +174,7 @@ void f2fs_free_filename(struct f2fs_filename *fname) kfree(fname->crypto_buf.name); fname->crypto_buf.name = NULL; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; @@ -208,7 +208,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, return f2fs_find_target_dentry(&d, fname, max_slots); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. @@ -266,7 +266,7 @@ static inline int f2fs_match_name(const struct inode *dir, { struct fscrypt_name f; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { struct qstr cf = FSTR_TO_QSTR(&fname->cf_name); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index eb22fa91c2b2..68b44015514f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -488,7 +488,7 @@ struct f2fs_filename { */ struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * For casefolded directories: the casefolded name, but it's left NULL * if the original name is not valid Unicode, if the directory is both diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index e3beac546c63..3cb1e7a24740 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -105,7 +105,7 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname) return; } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (IS_CASEFOLDED(dir)) { /* * If the casefolded name is provided, hash it instead of the diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a728a0af9ce0..5f213f05556d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -561,7 +561,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, goto out_iput; } out_splice: -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -622,7 +622,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } f2fs_delete_entry(de, page, dir, inode); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 9683c80ff8c2..79773d322c47 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -46,7 +46,7 @@ static struct kmem_cache *fsync_entry_slab; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -149,7 +149,7 @@ static int init_recovered_filename(const struct inode *dir, if (err) return err; f2fs_hash_filename(dir, fname); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* Case-sensitive match is fine for recovery */ kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 76e6a3df9aba..baefd398ec1a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -257,7 +257,7 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) va_end(args); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct f2fs_sb_encodings { __u16 magic; char *name; @@ -1259,7 +1259,7 @@ default_check: return -EINVAL; } #endif -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi)) { f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); @@ -1619,7 +1619,7 @@ static void f2fs_put_super(struct super_block *sb) f2fs_destroy_iostat(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -3903,7 +3903,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) { const struct f2fs_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -4458,7 +4458,7 @@ free_bio_info: for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); sb->s_encoding = NULL; #endif diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index df406c16b2eb..8ac506671245 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -201,7 +201,7 @@ static ssize_t unusable_show(struct f2fs_attr *a, static ssize_t encoding_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) @@ -778,7 +778,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption); F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -797,7 +797,7 @@ F2FS_FEATURE_RO_ATTR(lost_found); F2FS_FEATURE_RO_ATTR(verity); #endif F2FS_FEATURE_RO_ATTR(sb_checksum); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(casefold); #endif F2FS_FEATURE_RO_ATTR(readonly); @@ -910,7 +910,7 @@ static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(encrypted_casefold), #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -929,7 +929,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(verity), #endif ATTR_LIST(sb_checksum), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif ATTR_LIST(readonly), diff --git a/fs/io_uring.c b/fs/io_uring.c index e54c4127422e..2e04f718319d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7822,10 +7822,15 @@ static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref) struct io_ring_ctx *ctx = node->rsrc_data->ctx; unsigned long flags; bool first_add = false; + unsigned long delay = HZ; spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); node->done = true; + /* if we are mid-quiesce then do not delay */ + if (node->rsrc_data->quiesce) + delay = 0; + while (!list_empty(&ctx->rsrc_ref_list)) { node = list_first_entry(&ctx->rsrc_ref_list, struct io_rsrc_node, node); @@ -7838,10 +7843,10 @@ static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref) spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); if (first_add) - mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ); + mod_delayed_work(system_wq, &ctx->rsrc_put_work, delay); } -static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) +static struct io_rsrc_node *io_rsrc_node_alloc(void) { struct io_rsrc_node *ref_node; @@ -7892,7 +7897,7 @@ static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) { if (ctx->rsrc_backup_node) return 0; - ctx->rsrc_backup_node = io_rsrc_node_alloc(ctx); + ctx->rsrc_backup_node = io_rsrc_node_alloc(); return ctx->rsrc_backup_node ? 0 : -ENOMEM; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index f13d548e4a7f..bf108d4493d2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2972,6 +2972,7 @@ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) jbd_unlock_bh_journal_head(bh); return jh; } +EXPORT_SYMBOL(jbd2_journal_grab_journal_head); static void __journal_remove_journal_head(struct buffer_head *bh) { @@ -3024,6 +3025,7 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) jbd_unlock_bh_journal_head(bh); } } +EXPORT_SYMBOL(jbd2_journal_put_journal_head); /* * Initialize jbd inode head diff --git a/fs/libfs.c b/fs/libfs.c index ba7438ab9371..974125270a42 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1379,7 +1379,7 @@ bool is_empty_dir_inode(struct inode *inode) (inode->i_op == &empty_dir_inode_operations); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Determine if the name of a dentry should be casefolded. * @@ -1473,7 +1473,7 @@ static const struct dentry_operations generic_encrypted_dentry_ops = { }; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) static const struct dentry_operations generic_encrypted_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, @@ -1508,10 +1508,10 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) #ifdef CONFIG_FS_ENCRYPTION bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) bool needs_ci_ops = dentry->d_sb->s_encoding; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) if (needs_encrypt_ops && needs_ci_ops) { d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops); return; @@ -1523,7 +1523,7 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) return; } #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (needs_ci_ops) { d_set_d_op(dentry, &generic_ci_dentry_ops); return; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index cb3a7512c33e..0a22a2faf552 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -179,19 +179,21 @@ nlm_delete_file(struct nlm_file *file) static int nlm_unlock_files(struct nlm_file *file) { struct file_lock lock; - struct file *f; + locks_init_lock(&lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; - for (f = file->f_file[0]; f <= file->f_file[1]; f++) { - if (f && vfs_lock_file(f, F_SETLK, &lock, NULL) < 0) { - pr_warn("lockd: unlock failure in %s:%d\n", - __FILE__, __LINE__); - return 1; - } - } + if (file->f_file[O_RDONLY] && + vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL)) + goto out_err; + if (file->f_file[O_WRONLY] && + vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, &lock, NULL)) + goto out_err; return 0; +out_err: + pr_warn("lockd: unlock failure in %s:%d\n", __FILE__, __LINE__); + return 1; } /* diff --git a/fs/namei.c b/fs/namei.c index b867a92c078e..3f1829b3ab5b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4024,13 +4024,12 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); - fsnotify_rmdir(dir, dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) - d_delete(dentry); + d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); @@ -4152,7 +4151,6 @@ int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir, if (!error) { dont_mount(dentry); detach_mounts(dentry); - fsnotify_unlink(dir, dentry); } } } @@ -4160,9 +4158,11 @@ out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ - if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { + fsnotify_unlink(dir, dentry); + } else if (!error) { fsnotify_link_count(target); - d_delete(dentry); + d_delete_notify(dir, dentry); } return error; diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index 6a2033131c06..ccd4f245cae2 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -170,7 +170,7 @@ struct cb_devicenotifyitem { }; struct cb_devicenotifyargs { - int ndevs; + uint32_t ndevs; struct cb_devicenotifyitem *devs; }; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 09c5b1cb3e07..c343666d9a42 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -358,7 +358,7 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp, struct cb_process_state *cps) { struct cb_devicenotifyargs *args = argp; - int i; + uint32_t i; __be32 res = 0; struct nfs_client *clp = cps->clp; struct nfs_server *server = NULL; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index a67c41ec545f..f90de8043b0f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -258,11 +258,9 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, void *argp) { struct cb_devicenotifyargs *args = argp; + uint32_t tmp, n, i; __be32 *p; __be32 status = 0; - u32 tmp; - int n, i; - args->ndevs = 0; /* Num of device notifications */ p = xdr_inline_decode(xdr, sizeof(uint32_t)); @@ -271,7 +269,7 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, goto out; } n = ntohl(*p++); - if (n <= 0) + if (n == 0) goto out; if (n > ULONG_MAX / sizeof(*args->devs)) { status = htonl(NFS4ERR_BADXDR); @@ -330,19 +328,21 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp, dev->cbd_immediate = 0; } - args->ndevs++; - dprintk("%s: type %d layout 0x%x immediate %d\n", __func__, dev->cbd_notify_type, dev->cbd_layout_type, dev->cbd_immediate); } + args->ndevs = n; + dprintk("%s: ndevs %d\n", __func__, args->ndevs); + return 0; +err: + kfree(args->devs); out: + args->devs = NULL; + args->ndevs = 0; dprintk("%s: status %d ndevs %d\n", __func__, ntohl(status), args->ndevs); return status; -err: - kfree(args->devs); - goto out; } static __be32 decode_sessionid(struct xdr_stream *xdr, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8d8b85b5a641..f18e80fda9bf 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -856,6 +856,13 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str server->namelen = pathinfo.max_namelen; } + if (clp->rpc_ops->discover_trunking != NULL && + (server->caps & NFS_CAP_FS_LOCATIONS)) { + error = clp->rpc_ops->discover_trunking(server, mntfh); + if (error < 0) + return error; + } + return 0; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 347793626f19..848f3b8fb821 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1325,6 +1325,14 @@ void nfs_clear_verifier_delegated(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ +static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry) +{ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) && + d_really_is_negative(dentry)) + return dentry->d_time == inode_peek_iversion_raw(dir); + return nfs_verify_change_attribute(dir, dentry->d_time); +} + /* * A check for whether or not the parent directory has changed. * In the case it has, we assume that the dentries are untrustworthy @@ -1338,7 +1346,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, return 1; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) return 0; - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { @@ -1347,7 +1355,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0) return 0; } - if (!nfs_verify_change_attribute(dir, dentry->d_time)) + if (!nfs_dentry_verify_change(dir, dentry)) return 0; return 1; } @@ -1437,6 +1445,9 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, return 0; if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) return 1; + /* Case insensitive server? Revalidate negative dentries */ + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + return 1; return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU); } @@ -1537,7 +1548,7 @@ out: * If the lookup failed despite the dentry change attribute being * a match, then we should revalidate the directory cache. */ - if (!ret && nfs_verify_change_attribute(dir, dentry->d_time)) + if (!ret && nfs_dentry_verify_change(dir, dentry)) nfs_mark_dir_for_revalidate(dir); return nfs_lookup_revalidate_done(dir, dentry, inode, ret); } @@ -1776,8 +1787,11 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); - if (error == -ENOENT) + if (error == -ENOENT) { + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); goto no_entry; + } if (error < 0) { res = ERR_PTR(error); goto out; @@ -1806,6 +1820,14 @@ out: } EXPORT_SYMBOL_GPL(nfs_lookup); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode) +{ + /* Case insensitive server? Revalidate dentries */ + if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE)) + d_prune_aliases(inode); +} +EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); + #if IS_ENABLED(CONFIG_NFS_V4) static int nfs4_lookup_revalidate(struct dentry *, unsigned int); @@ -1867,6 +1889,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, struct iattr attr = { .ia_valid = ATTR_OPEN }; struct inode *inode; unsigned int lookup_flags = 0; + unsigned long dir_verifier; bool switched = false; int created = 0; int err; @@ -1940,7 +1963,11 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, switch (err) { case -ENOENT: d_splice_alias(NULL, dentry); - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) + dir_verifier = inode_peek_iversion_raw(dir); + else + dir_verifier = nfs_save_change_attribute(dir); + nfs_set_verifier(dentry, dir_verifier); break; case -EISDIR: case -ENOTDIR: @@ -1968,6 +1995,24 @@ out: no_open: res = nfs_lookup(dir, dentry, lookup_flags); + if (!res) { + inode = d_inode(dentry); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) + res = ERR_PTR(-ENOTDIR); + else if (inode && S_ISREG(inode->i_mode)) + res = ERR_PTR(-EOPENSTALE); + } else if (!IS_ERR(res)) { + inode = d_inode(res); + if ((lookup_flags & LOOKUP_DIRECTORY) && inode && + !S_ISDIR(inode->i_mode)) { + dput(res); + res = ERR_PTR(-ENOTDIR); + } else if (inode && S_ISREG(inode->i_mode)) { + dput(res); + res = ERR_PTR(-EOPENSTALE); + } + } if (switched) { d_lookup_done(dentry); if (!res) @@ -2186,8 +2231,10 @@ static void nfs_dentry_remove_handle_error(struct inode *dir, switch (error) { case -ENOENT: d_delete(dentry); - fallthrough; + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + break; case 0: + nfs_d_prune_case_insensitive_aliases(d_inode(dentry)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); } } @@ -2380,6 +2427,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) trace_nfs_link_enter(inode, dir, dentry); d_drop(dentry); + if (S_ISREG(inode->i_mode)) + nfs_sync_inode(inode); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); @@ -2469,6 +2518,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir, } } + if (S_ISREG(old_inode->i_mode)) + nfs_sync_inode(old_inode); task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL); if (IS_ERR(task)) { error = PTR_ERR(task); @@ -2529,7 +2580,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt static void nfs_access_free_entry(struct nfs_access_entry *entry) { - put_cred(entry->cred); + put_group_info(entry->group_info); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); @@ -2655,6 +2706,43 @@ void nfs_access_zap_cache(struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); +static int access_cmp(const struct cred *a, const struct nfs_access_entry *b) +{ + struct group_info *ga, *gb; + int g; + + if (uid_lt(a->fsuid, b->fsuid)) + return -1; + if (uid_gt(a->fsuid, b->fsuid)) + return 1; + + if (gid_lt(a->fsgid, b->fsgid)) + return -1; + if (gid_gt(a->fsgid, b->fsgid)) + return 1; + + ga = a->group_info; + gb = b->group_info; + if (ga == gb) + return 0; + if (ga == NULL) + return -1; + if (gb == NULL) + return 1; + if (ga->ngroups < gb->ngroups) + return -1; + if (ga->ngroups > gb->ngroups) + return 1; + + for (g = 0; g < ga->ngroups; g++) { + if (gid_lt(ga->gid[g], gb->gid[g])) + return -1; + if (gid_gt(ga->gid[g], gb->gid[g])) + return 1; + } + return 0; +} + static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; @@ -2662,7 +2750,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co while (n != NULL) { struct nfs_access_entry *entry = rb_entry(n, struct nfs_access_entry, rb_node); - int cmp = cred_fscmp(cred, entry->cred); + int cmp = access_cmp(cred, entry); if (cmp < 0) n = n->rb_left; @@ -2674,7 +2762,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co return NULL; } -static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2704,8 +2792,7 @@ static int nfs_access_get_cached_locked(struct inode *inode, const struct cred * spin_lock(&inode->i_lock); retry = false; } - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); err = 0; out: @@ -2717,7 +2804,7 @@ out_zap: return -ENOENT; } -static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res) +static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask) { /* Only check the most recently returned cache entry, * but do it without locking. @@ -2733,35 +2820,36 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru)); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || - cred_fscmp(cred, cache->cred) != 0) + access_cmp(cred, cache) != 0) cache = NULL; if (cache == NULL) goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; err = 0; out: rcu_read_unlock(); return err; } -int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct -nfs_access_entry *res, bool may_block) +int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block) { int status; - status = nfs_access_get_cached_rcu(inode, cred, res); + status = nfs_access_get_cached_rcu(inode, cred, mask); if (status != 0) - status = nfs_access_get_cached_locked(inode, cred, res, + status = nfs_access_get_cached_locked(inode, cred, mask, may_block); return status; } EXPORT_SYMBOL_GPL(nfs_access_get_cached); -static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) +static void nfs_access_add_rbtree(struct inode *inode, + struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(inode); struct rb_root *root_node = &nfsi->access_cache; @@ -2774,7 +2862,7 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry * while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); - cmp = cred_fscmp(set->cred, entry->cred); + cmp = access_cmp(cred, entry); if (cmp < 0) p = &parent->rb_left; @@ -2796,13 +2884,16 @@ found: nfs_access_free_entry(entry); } -void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) +void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_cred(set->cred); + cache->fsuid = cred->fsuid; + cache->fsgid = cred->fsgid; + cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; /* The above field assignments must be visible @@ -2810,7 +2901,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) * use rcu_assign_pointer, so just force the memory barrier. */ smp_wmb(); - nfs_access_add_rbtree(inode, cache); + nfs_access_add_rbtree(inode, cache, cred); /* Update accounting */ smp_mb__before_atomic(); @@ -2875,7 +2966,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) trace_nfs_access_enter(inode); - status = nfs_access_get_cached(inode, cred, &cache, may_block); + status = nfs_access_get_cached(inode, cred, &cache.mask, may_block); if (status == 0) goto out_cached; @@ -2895,8 +2986,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else cache.mask |= NFS_ACCESS_EXECUTE; - cache.cred = cred; - status = NFS_PROTO(inode)->access(inode, &cache); + status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { if (!S_ISDIR(inode->i_mode)) @@ -2906,7 +2996,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) } goto out; } - nfs_access_add_cache(inode, &cache); + nfs_access_add_cache(inode, &cache, cred); out_cached: cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h index 79323b5dab0c..aed0748fd6ec 100644 --- a/fs/nfs/filelayout/filelayout.h +++ b/fs/nfs/filelayout/filelayout.h @@ -51,7 +51,7 @@ struct nfs4_file_layout_dsaddr { u32 stripe_count; u8 *stripe_indices; u32 ds_num; - struct nfs4_pnfs_ds *ds_list[1]; + struct nfs4_pnfs_ds *ds_list[]; }; struct nfs4_filelayout_segment { diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c index 86c3f7e69ec4..acf4b88889dc 100644 --- a/fs/nfs/filelayout/filelayoutdev.c +++ b/fs/nfs/filelayout/filelayoutdev.c @@ -136,9 +136,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, goto out_err_free_stripe_indices; } - dsaddr = kzalloc(sizeof(*dsaddr) + - (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), - gfp_flags); + dsaddr = kzalloc(struct_size(dsaddr, ds_list, num), gfp_flags); if (!dsaddr) goto out_err_free_stripe_indices; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 12f6acb483bb..2de7c56a1fbe 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -373,6 +373,7 @@ extern unsigned long nfs_access_cache_count(struct shrinker *shrink, extern unsigned long nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc); struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +void nfs_d_prune_case_insensitive_aliases(struct inode *inode); int nfs_create(struct user_namespace *, struct inode *, struct dentry *, umode_t, bool); int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *, diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7100514d306b..1597eef40d54 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -220,7 +220,8 @@ static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, task_flags); } -static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs3_accessargs arg = { .fh = NFS_FH(inode), @@ -231,7 +232,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) .rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS], .rpc_argp = &arg, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = -ENOMEM; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 8b21ff1be717..32129446beca 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -46,7 +46,7 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); - u32 bitmask[3]; + u32 bitmask[NFS_BITMASK_SZ]; struct nfs42_falloc_args args = { .falloc_fh = NFS_FH(inode), .falloc_offset = offset, @@ -69,9 +69,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, return status; } - memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask)); - if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED) - bitmask[1] |= FATTR4_WORD1_SPACE_USED; + nfs4_bitmask_set(bitmask, server->cache_consistency_bitmask, inode, + NFS_INO_INVALID_BLOCKS); res.falloc_fattr = nfs_alloc_fattr(); if (!res.falloc_fattr) @@ -1044,13 +1043,14 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); struct nfs_server *server = NFS_SERVER(dst_inode); + __u32 dst_bitmask[NFS_BITMASK_SZ]; struct nfs42_clone_args args = { .src_fh = NFS_FH(src_inode), .dst_fh = NFS_FH(dst_inode), .src_offset = src_offset, .dst_offset = dst_offset, .count = count, - .dst_bitmask = server->cache_consistency_bitmask, + .dst_bitmask = dst_bitmask, }; struct nfs42_clone_res res = { .server = server, @@ -1079,6 +1079,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, if (!res.dst_fattr) return -ENOMEM; + nfs4_bitmask_set(dst_bitmask, server->cache_consistency_bitmask, + dst_inode, NFS_INO_INVALID_BLOCKS); + status = nfs4_call_sync(server->client, server, msg, &args.seq_args, &res.seq_res, 0); trace_nfs4_clone(src_inode, dst_inode, &args, status); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ed5eaca6801e..84f39b6f1b1e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -260,8 +260,8 @@ struct nfs4_state_maintenance_ops { }; struct nfs4_mig_recovery_ops { - int (*get_locations)(struct inode *, struct nfs4_fs_locations *, - struct page *, const struct cred *); + int (*get_locations)(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, struct page *, const struct cred *); int (*fsid_present)(struct inode *, const struct cred *); }; @@ -280,7 +280,8 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, int nfs4_submount(struct fs_context *, struct nfs_server *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); - +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net, int port); /* nfs4proc.c */ extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); extern int nfs4_async_handle_error(struct rpc_task *task, @@ -302,8 +303,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); -extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, - struct page *page, const struct cred *); +extern int nfs4_proc_get_locations(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, + struct page *page, const struct cred *); extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct dentry *, @@ -315,6 +317,8 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_open_context *ctx, const struct nfs_lock_context *l_ctx, fmode_t fmode); +extern void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity); extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode); extern int update_open_stateid(struct nfs4_state *state, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index d8b5a250ca05..47a6cf892c95 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1343,8 +1343,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, } nfs_put_client(clp); - if (server->nfs_client->cl_hostname == NULL) + if (server->nfs_client->cl_hostname == NULL) { server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL); + if (server->nfs_client->cl_hostname == NULL) + return -ENOMEM; + } nfs_server_insert_lists(server); return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root))); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 873342308dc0..3680c8da510c 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -164,16 +164,21 @@ static int nfs4_validate_fspath(struct dentry *dentry, return 0; } -static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct net *net) +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, + size_t salen, struct net *net, int port) { ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); if (ret == 0) { - ret = nfs_dns_resolve_name(net, string, len, sa, salen); - if (ret < 0) - ret = 0; + ret = rpc_uaddr2sockaddr(net, string, len, sa, salen); + if (ret == 0) { + ret = nfs_dns_resolve_name(net, string, len, sa, salen); + if (ret < 0) + ret = 0; + } + } else if (port) { + rpc_set_port(sa, port); } return ret; } @@ -328,7 +333,7 @@ static int try_location(struct fs_context *fc, nfs_parse_server_name(buf->data, buf->len, &ctx->nfs_server.address, sizeof(ctx->nfs_server._address), - fc->net_ns); + fc->net_ns, 0); if (ctx->nfs_server.addrlen == 0) continue; @@ -496,7 +501,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, net); + sap, addr_bufsize, net, 0); if (salen == 0) continue; rpc_set_port(sap, NFS_PORT); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ee3bc79f6ca3..b18f31b2c9e7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -108,10 +108,6 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *, static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *, const struct cred *, bool); #endif -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], - const __u32 *src, struct inode *inode, - struct nfs_server *server, - struct nfs4_label *label); #ifdef CONFIG_NFS_V4_SECURITY_LABEL static inline struct nfs4_label * @@ -2653,9 +2649,8 @@ static int nfs4_opendata_access(const struct cred *cred, } else if ((fmode & FMODE_READ) && !opendata->file_created) mask = NFS4_ACCESS_READ; - cache.cred = cred; nfs_access_set_mask(&cache, opendata->o_res.access_result); - nfs_access_add_cache(state->inode, &cache); + nfs_access_add_cache(state->inode, &cache, cred); flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP; if ((mask & ~cache.mask & flags) == 0) @@ -3670,7 +3665,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) if (!nfs4_have_delegation(inode, FMODE_READ)) { nfs4_bitmask_set(calldata->arg.bitmask_store, server->cache_consistency_bitmask, - inode, server, NULL); + inode, 0); calldata->arg.bitmask = calldata->arg.bitmask_store; } else calldata->arg.bitmask = NULL; @@ -3841,7 +3836,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f FATTR4_WORD0_FH_EXPIRE_TYPE | FATTR4_WORD0_LINK_SUPPORT | FATTR4_WORD0_SYMLINK_SUPPORT | - FATTR4_WORD0_ACLSUPPORT; + FATTR4_WORD0_ACLSUPPORT | + FATTR4_WORD0_CASE_INSENSITIVE | + FATTR4_WORD0_CASE_PRESERVING; if (minorversion) bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT; @@ -3870,10 +3867,16 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.case_insensitive) + server->caps |= NFS_CAP_CASE_INSENSITIVE; + if (res.case_preserving) + server->caps |= NFS_CAP_CASE_PRESERVING; #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) server->caps |= NFS_CAP_SECURITY_LABEL; #endif + if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS) + server->caps |= NFS_CAP_FS_LOCATIONS; if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) @@ -3932,6 +3935,114 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) return err; } +static void test_fs_location_for_trunking(struct nfs4_fs_location *location, + struct nfs_client *clp, + struct nfs_server *server) +{ + int i; + + for (i = 0; i < location->nservers; i++) { + struct nfs4_string *srv_loc = &location->servers[i]; + struct sockaddr addr; + size_t addrlen; + struct xprt_create xprt_args = { + .ident = 0, + .net = clp->cl_net, + }; + struct nfs4_add_xprt_data xprtdata = { + .clp = clp, + }; + struct rpc_add_xprt_test rpcdata = { + .add_xprt_test = clp->cl_mvops->session_trunk, + .data = &xprtdata, + }; + char *servername = NULL; + + if (!srv_loc->len) + continue; + + addrlen = nfs_parse_server_name(srv_loc->data, srv_loc->len, + &addr, sizeof(addr), + clp->cl_net, server->port); + if (!addrlen) + return; + xprt_args.dstaddr = &addr; + xprt_args.addrlen = addrlen; + servername = kmalloc(srv_loc->len + 1, GFP_KERNEL); + if (!servername) + return; + memcpy(servername, srv_loc->data, srv_loc->len); + servername[srv_loc->len] = '\0'; + xprt_args.servername = servername; + + xprtdata.cred = nfs4_get_clid_cred(clp); + rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, + rpc_clnt_setup_test_and_add_xprt, + &rpcdata); + if (xprtdata.cred) + put_cred(xprtdata.cred); + kfree(servername); + } +} + +static int _nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_fs_locations *locations = NULL; + struct page *page; + const struct cred *cred; + struct nfs_client *clp = server->nfs_client; + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + int status = -ENOMEM, i; + + cred = ops->get_state_renewal_cred(clp); + if (cred == NULL) { + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + return -ENOKEY; + } + + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) + goto out; + + status = nfs4_proc_get_locations(server, fhandle, locations, page, + cred); + if (status) + goto out; + + for (i = 0; i < locations->nlocations; i++) + test_fs_location_for_trunking(&locations->locations[i], clp, + server); +out: + if (page) + __free_page(page); + kfree(locations); + return status; +} + +static int nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_exception exception = { + .interruptible = true, + }; + struct nfs_client *clp = server->nfs_client; + int err = 0; + + if (!nfs4_has_session(clp)) + goto out; + do { + err = nfs4_handle_exception(server, + _nfs4_discover_trunking(server, fhandle), + &exception); + } while (exception.retry); +out: + return err; +} + static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { @@ -4441,7 +4552,8 @@ static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, return err; } -static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs4_accessargs args = { @@ -4455,7 +4567,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS], .rpc_argp = &args, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = 0; @@ -4475,14 +4587,15 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry return status; } -static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_access(inode, entry); + err = _nfs4_proc_access(inode, entry, cred); trace_nfs4_access(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -4663,8 +4776,10 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, nfs_fattr_init(res->dir_attr); - if (inode) + if (inode) { nfs4_inode_return_delegation(inode); + nfs_d_prune_case_insensitive_aliases(inode); + } } static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data) @@ -4730,6 +4845,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; if (task->tk_status == 0) { + nfs_d_prune_case_insensitive_aliases(d_inode(data->old_dentry)); if (new_dir != old_dir) { /* Note: If we moved a directory, nlink will change */ nfs4_update_changeattr(old_dir, &res->old_cinfo, @@ -5422,14 +5538,14 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr) return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; } -static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, - struct inode *inode, struct nfs_server *server, - struct nfs4_label *label) +void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[], + struct inode *inode, unsigned long cache_validity) { - unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity); + struct nfs_server *server = NFS_SERVER(inode); unsigned int i; memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ); + cache_validity |= READ_ONCE(NFS_I(inode)->cache_validity); if (cache_validity & NFS_INO_INVALID_CHANGE) bitmask[0] |= FATTR4_WORD0_CHANGE; @@ -5441,8 +5557,6 @@ static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src, bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP; if (cache_validity & NFS_INO_INVALID_NLINK) bitmask[1] |= FATTR4_WORD1_NUMLINKS; - if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL) - bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL; if (cache_validity & NFS_INO_INVALID_CTIME) bitmask[1] |= FATTR4_WORD1_TIME_METADATA; if (cache_validity & NFS_INO_INVALID_MTIME) @@ -5469,7 +5583,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, } else { nfs4_bitmask_set(hdr->args.bitmask_store, server->cache_consistency_bitmask, - hdr->inode, server, NULL); + hdr->inode, NFS_INO_INVALID_BLOCKS); hdr->args.bitmask = hdr->args.bitmask_store; } @@ -6507,8 +6621,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; nfs4_bitmask_set(data->args.bitmask_store, - server->cache_consistency_bitmask, inode, server, - NULL); + server->cache_consistency_bitmask, inode, 0); data->args.bitmask = data->args.bitmask_store; nfs_copy_fh(&data->fh, NFS_FH(inode)); nfs4_stateid_copy(&data->stateid, stateid); @@ -7611,7 +7724,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, const char *key, const void *buf, size_t buflen, int flags) { - struct nfs_access_entry cache; + u32 mask; int ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) @@ -7626,8 +7739,8 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, * do a cached access check for the XA* flags to possibly avoid * doing an RPC and getting EACCES back. */ - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAWRITE)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAWRITE)) return -EACCES; } @@ -7648,14 +7761,14 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *key, void *buf, size_t buflen) { - struct nfs_access_entry cache; + u32 mask; ssize_t ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return -EOPNOTSUPP; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAREAD)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAREAD)) return -EACCES; } @@ -7680,13 +7793,13 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) ssize_t ret, size; char *buf; size_t buflen; - struct nfs_access_entry cache; + u32 mask; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return 0; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XALIST)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XALIST)) return 0; } @@ -7818,18 +7931,18 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, * appended to this compound to identify the client ID which is * performing recovery. */ -static int _nfs40_proc_get_locations(struct inode *inode, +static int _nfs40_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { .clientid = server->nfs_client->cl_clientid, - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7875,17 +7988,17 @@ static int _nfs40_proc_get_locations(struct inode *inode, * When the client supports GETATTR(fs_locations_info), it can * be plumbed in here. */ -static int _nfs41_proc_get_locations(struct inode *inode, +static int _nfs41_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7934,11 +8047,11 @@ static int _nfs41_proc_get_locations(struct inode *inode, * -NFS4ERR_LEASE_MOVED is returned if the server still has leases * from this client that require migration recovery. */ -int nfs4_proc_get_locations(struct inode *inode, +int nfs4_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; @@ -7951,10 +8064,11 @@ int nfs4_proc_get_locations(struct inode *inode, (unsigned long long)server->fsid.major, (unsigned long long)server->fsid.minor, clp->cl_hostname); - nfs_display_fhandle(NFS_FH(inode), __func__); + nfs_display_fhandle(fhandle, __func__); do { - status = ops->get_locations(inode, locations, page, cred); + status = ops->get_locations(server, fhandle, locations, page, + cred); if (status != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, status, &exception); @@ -10423,6 +10537,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .free_client = nfs4_free_client, .create_server = nfs4_create_server, .clone_server = nfs_clone_server, + .discover_trunking = nfs4_discover_trunking, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index d88b779f9dd0..f5a62c0d999b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2098,7 +2098,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } inode = d_inode(server->super->s_root); - result = nfs4_proc_get_locations(inode, locations, page, cred); + result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, + page, cred); if (result) { dprintk("<-- %s: failed to retrieve fs_locations: %d\n", __func__, result); @@ -2106,6 +2107,9 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } result = -NFS4ERR_NXIO; + if (!locations->nlocations) + goto out; + if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) { dprintk("<-- %s: No fs_locations data, migration skipped\n", __func__); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 69862bf6db00..8e70b92df4cc 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3533,6 +3533,42 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint return 0; } +static int decode_attr_case_insensitive(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_INSENSITIVE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_INSENSITIVE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_INSENSITIVE; + } + dprintk("%s: case_insensitive=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + +static int decode_attr_case_preserving(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_PRESERVING - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_PRESERVING)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_PRESERVING; + } + dprintk("%s: case_preserving=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; @@ -3696,8 +3732,6 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st if (unlikely(!p)) goto out_eio; n = be32_to_cpup(p); - if (n <= 0) - goto out_eio; for (res->nlocations = 0; res->nlocations < n; res->nlocations++) { u32 m; struct nfs4_fs_location *loc; @@ -4200,10 +4234,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap, } else printk(KERN_WARNING "%s: label too long (%u)!\n", __func__, len); + if (label && label->label) + dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n", + __func__, label->len, (char *)label->label, + label->len, label->pi, label->lfs); } - if (label && label->label) - dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__, - (char *)label->label, label->len, label->pi, label->lfs); return status; } @@ -4412,6 +4447,10 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re goto xdr_error; if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0) goto xdr_error; + if ((status = decode_attr_case_insensitive(xdr, bitmap, &res->case_insensitive)) != 0) + goto xdr_error; + if ((status = decode_attr_case_preserving(xdr, bitmap, &res->case_preserving)) != 0) + goto xdr_error; if ((status = decode_attr_exclcreat_supported(xdr, bitmap, res->exclcreat_bitmask)) != 0) goto xdr_error; diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 8cb70755e3c9..a6f740366963 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -142,10 +142,11 @@ static struct attribute *nfs_netns_client_attrs[] = { &nfs_netns_client_id.attr, NULL, }; +ATTRIBUTE_GROUPS(nfs_netns_client); static struct kobj_type nfs_netns_client_type = { .release = nfs_netns_client_release, - .default_attrs = nfs_netns_client_attrs, + .default_groups = nfs_netns_client_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = nfs_netns_client_namespace, }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 72900b89cf84..32063733443d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4130,8 +4130,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, - &old->cl_cred)) + &old->cl_cred)) { + old = NULL; goto out; + } status = mark_client_expired_locked(old); if (status) { old = NULL; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b9f27fbcd768..68b020f2002b 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1247,7 +1247,8 @@ static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) clear_ncl(d_inode(dentry)); dget(dentry); ret = simple_unlink(dir, dentry); - d_delete(dentry); + d_drop(dentry); + fsnotify_unlink(dir, dentry); dput(dentry); WARN_ON_ONCE(ret); } @@ -1338,8 +1339,8 @@ void nfsd_client_rmdir(struct dentry *dentry) dget(dentry); ret = simple_rmdir(dir, dentry); WARN_ON_ONCE(ret); + d_drop(dentry); fsnotify_rmdir(dir, dentry); - d_delete(dentry); dput(dentry); inode_unlock(dir); } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 73b1615f9d96..2ff6bd85ba8f 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -158,7 +158,6 @@ static size_t fanotify_event_len(unsigned int info_mode, struct fanotify_event *event) { size_t event_len = FAN_EVENT_METADATA_LEN; - struct fanotify_info *info; int fh_len; int dot_len = 0; @@ -168,8 +167,6 @@ static size_t fanotify_event_len(unsigned int info_mode, if (fanotify_is_error_event(event->mask)) event_len += FANOTIFY_ERROR_INFO_LEN; - info = fanotify_event_info(event); - if (fanotify_event_has_any_dir_fh(event)) { event_len += fanotify_dir_name_info_len(event); } else if ((info_mode & FAN_REPORT_NAME) && @@ -704,9 +701,6 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (fanotify_is_perm_event(event->mask)) FANOTIFY_PERM(event)->fd = fd; - if (f) - fd_install(fd, f); - if (info_mode) { ret = copy_info_records_to_user(event, info, info_mode, pidfd, buf, count); @@ -714,6 +708,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, goto out_close_fd; } + if (f) + fd_install(fd, f); + return metadata.event_len; out_close_fd: diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 731558a6f27d..dd77b7aaabf5 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -661,17 +661,6 @@ static struct ctl_table ocfs2_nm_table[] = { { } }; -static struct ctl_table ocfs2_mod_table[] = { - { - .procname = "nm", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_nm_table - }, - { } -}; - static struct ctl_table_header *ocfs2_table_header; /* @@ -682,7 +671,7 @@ static int __init ocfs2_stack_glue_init(void) { strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); - ocfs2_table_header = register_sysctl("fs/ocfs2", ocfs2_mod_table); + ocfs2_table_header = register_sysctl("fs/ocfs2/nm", ocfs2_nm_table); if (!ocfs2_table_header) { printk(KERN_ERR "ocfs2 stack glue: unable to register sysctl\n"); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 481017e1dac5..166c8918c825 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1251,26 +1251,23 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh, { struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data; struct journal_head *jh; - int ret = 1; + int ret; if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap)) return 0; - if (!buffer_jbd(bg_bh)) + jh = jbd2_journal_grab_journal_head(bg_bh); + if (!jh) return 1; - jbd_lock_bh_journal_head(bg_bh); - if (buffer_jbd(bg_bh)) { - jh = bh2jh(bg_bh); - spin_lock(&jh->b_state_lock); - bg = (struct ocfs2_group_desc *) jh->b_committed_data; - if (bg) - ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); - else - ret = 1; - spin_unlock(&jh->b_state_lock); - } - jbd_unlock_bh_journal_head(bg_bh); + spin_lock(&jh->b_state_lock); + bg = (struct ocfs2_group_desc *) jh->b_committed_data; + if (bg) + ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap); + else + ret = 1; + spin_unlock(&jh->b_state_lock); + jbd2_journal_put_journal_head(jh); return ret; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index b193d08a3dc3..e040970408d4 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -145,7 +145,7 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, if (err == -ENOTTY || err == -EINVAL) return 0; pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n", - old, err); + old->dentry, err); return err; } @@ -157,7 +157,9 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, */ if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) { err = ovl_set_protattr(inode, new->dentry, &oldfa); - if (err) + if (err == -EPERM) + pr_warn_once("copying fileattr: no xattr on upper\n"); + else if (err) return err; } @@ -167,8 +169,16 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, err = ovl_real_fileattr_get(new, &newfa); if (err) { + /* + * Returning an error if upper doesn't support fileattr will + * result in a regression, so revert to the old behavior. + */ + if (err == -ENOTTY || err == -EINVAL) { + pr_warn_once("copying fileattr: no support on upper\n"); + return 0; + } pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n", - new, err); + new->dentry, err); return err; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 1d6b7a50736b..ea8f6cd01f50 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -258,10 +258,6 @@ int udf_expand_file_adinicb(struct inode *inode) char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); int err; - struct writeback_control udf_wbc = { - .sync_mode = WB_SYNC_NONE, - .nr_to_write = 1, - }; WARN_ON_ONCE(!inode_is_locked(inode)); if (!iinfo->i_lenAlloc) { @@ -305,8 +301,10 @@ int udf_expand_file_adinicb(struct inode *inode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; /* from now on we have normal address_space methods */ inode->i_data.a_ops = &udf_aops; + set_page_dirty(page); + unlock_page(page); up_write(&iinfo->i_data_sem); - err = inode->i_data.a_ops->writepage(page, &udf_wbc); + err = filemap_fdatawrite(inode->i_mapping); if (err) { /* Restore everything back so that we don't lose data... */ lock_page(page); @@ -317,6 +315,7 @@ int udf_expand_file_adinicb(struct inode *inode) unlock_page(page); iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB; inode->i_data.a_ops = &udf_adinicb_aops; + iinfo->i_lenAlloc = inode->i_size; up_write(&iinfo->i_data_sem); } put_page(page); diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig index 610d7bc05d6e..da786a687fdc 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -3,21 +3,13 @@ # UTF-8 normalization # config UNICODE - bool "UTF-8 normalization and casefolding support" + tristate "UTF-8 normalization and casefolding support" help Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding - support. - -config UNICODE_UTF8_DATA - tristate "UTF-8 normalization and casefolding tables" - depends on UNICODE - default UNICODE - help - This contains a large table of case foldings, which can be loaded as - a separate module if you say M here. To be on the safe side stick - to the default of Y. Saying N here makes no sense, if you do not want - utf8 casefolding support, disable CONFIG_UNICODE instead. + support. If you say M here the large table of case foldings will + be a separate loadable module that gets requested only when a file + system actually use it. config UNICODE_NORMALIZATION_SELFTEST tristate "Test UTF-8 normalization support" - depends on UNICODE_UTF8_DATA + depends on UNICODE diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 2f9d9188852b..0cc87423de82 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_UNICODE) += unicode.o +ifneq ($(CONFIG_UNICODE),) +obj-y += unicode.o +endif +obj-$(CONFIG_UNICODE) += utf8data.o obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o -obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o unicode-y := utf8-norm.o utf8-core.o diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9c95df26fc26..f35aea98bc35 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1258,6 +1258,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index fa517ae604ad..8c92c974bd12 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -578,7 +589,6 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -939,6 +949,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -999,16 +1010,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1183,7 +1184,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1251,6 +1259,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1283,19 +1292,19 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1304,27 +1313,29 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1332,13 +1343,14 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1391,19 +1403,21 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) @@ -1724,7 +1738,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1976,12 +1989,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } @@ -2076,6 +2083,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2129,6 +2139,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e9993172f892..7a7be8c057f2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); @@ -564,4 +566,9 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..b12cfe3b12bb 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -307,6 +329,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,50 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } -#endif - -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) { + return false; } -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) { - return false; + return 0; } - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include <linux/compiler.h> /* for __PASTE */ +#include <linux/compiler_attributes.h> /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h new file mode 100644 index 000000000000..4359fb0221cf --- /dev/null +++ b/include/linux/dsa/tag_qca.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __TAG_QCA_H +#define __TAG_QCA_H + +#define QCA_HDR_LEN 2 +#define QCA_HDR_VERSION 0x2 + +#define QCA_HDR_RECV_VERSION GENMASK(15, 14) +#define QCA_HDR_RECV_PRIORITY GENMASK(13, 11) +#define QCA_HDR_RECV_TYPE GENMASK(10, 6) +#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) +#define QCA_HDR_RECV_SOURCE_PORT GENMASK(2, 0) + +/* Packet type for recv */ +#define QCA_HDR_RECV_TYPE_NORMAL 0x0 +#define QCA_HDR_RECV_TYPE_MIB 0x1 +#define QCA_HDR_RECV_TYPE_RW_REG_ACK 0x2 + +#define QCA_HDR_XMIT_VERSION GENMASK(15, 14) +#define QCA_HDR_XMIT_PRIORITY GENMASK(13, 11) +#define QCA_HDR_XMIT_CONTROL GENMASK(10, 8) +#define QCA_HDR_XMIT_FROM_CPU BIT(7) +#define QCA_HDR_XMIT_DP_BIT GENMASK(6, 0) + +/* Packet type for xmit */ +#define QCA_HDR_XMIT_TYPE_NORMAL 0x0 +#define QCA_HDR_XMIT_TYPE_RW_REG 0x1 + +/* Check code for a valid mgmt packet. Switch will ignore the packet + * with this wrong. + */ +#define QCA_HDR_MGMT_CHECK_CODE_VAL 0x5 + +/* Specific define for in-band MDIO read/write with Ethernet packet */ +#define QCA_HDR_MGMT_SEQ_LEN 4 /* 4 byte for the seq */ +#define QCA_HDR_MGMT_COMMAND_LEN 4 /* 4 byte for the command */ +#define QCA_HDR_MGMT_DATA1_LEN 4 /* First 4 byte for the mdio data */ +#define QCA_HDR_MGMT_HEADER_LEN (QCA_HDR_MGMT_SEQ_LEN + \ + QCA_HDR_MGMT_COMMAND_LEN + \ + QCA_HDR_MGMT_DATA1_LEN) + +#define QCA_HDR_MGMT_DATA2_LEN 12 /* Other 12 byte for the mdio data */ +#define QCA_HDR_MGMT_PADDING_LEN 34 /* Padding to reach the min Ethernet packet */ + +#define QCA_HDR_MGMT_PKT_LEN (QCA_HDR_MGMT_HEADER_LEN + \ + QCA_HDR_LEN + \ + QCA_HDR_MGMT_DATA2_LEN + \ + QCA_HDR_MGMT_PADDING_LEN) + +#define QCA_HDR_MGMT_SEQ_NUM GENMASK(31, 0) /* 63, 32 */ +#define QCA_HDR_MGMT_CHECK_CODE GENMASK(31, 29) /* 31, 29 */ +#define QCA_HDR_MGMT_CMD BIT(28) /* 28 */ +#define QCA_HDR_MGMT_LENGTH GENMASK(23, 20) /* 23, 20 */ +#define QCA_HDR_MGMT_ADDR GENMASK(18, 0) /* 18, 0 */ + +/* Special struct emulating a Ethernet header */ +struct qca_mgmt_ethhdr { + u32 command; /* command bit 31:0 */ + u32 seq; /* seq 63:32 */ + u32 mdio_data; /* first 4byte mdio */ + __be16 hdr; /* qca hdr */ +} __packed; + +enum mdio_cmd { + MDIO_WRITE = 0x0, + MDIO_READ +}; + +struct mib_ethhdr { + u32 data[3]; /* first 3 mib counter */ + __be16 hdr; /* qca hdr */ +} __packed; + +struct qca_tagger_data { + void (*rw_reg_ack_handler)(struct dsa_switch *ds, + struct sk_buff *skb); + void (*mib_autocast_handler)(struct dsa_switch *ds, + struct sk_buff *skb); +}; + +#endif /* __TAG_QCA_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a26f37a27167..e0853f48b75e 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -70,9 +70,11 @@ enum { /** * struct kernel_ethtool_ringparam - RX/TX ring configuration * @rx_buf_len: Current length of buffers on the rx ring. + * @tcp_data_split: Scatter packet headers and data to separate buffers */ struct kernel_ethtool_ringparam { u32 rx_buf_len; + u8 tcp_data_split; }; /** @@ -111,7 +113,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; enum ethtool_link_ext_substate_module module; - u8 __link_ext_substate; + u32 __link_ext_substate; }; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..d23e999dc032 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1356,7 +1356,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); diff --git a/include/linux/fs.h b/include/linux/fs.h index f3daaea16554..e2d892b201b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1483,7 +1483,7 @@ struct super_block { #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 3a2d7dc3c607..bb8467cd11ae 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -225,16 +225,53 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, } /* + * fsnotify_delete - @dentry was unlinked and unhashed + * + * Caller must make sure that dentry->d_name is stable. + * + * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode + * as this may be called after d_delete() and old_dentry may be negative. + */ +static inline void fsnotify_delete(struct inode *dir, struct inode *inode, + struct dentry *dentry) +{ + __u32 mask = FS_DELETE; + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, + 0); +} + +/** + * d_delete_notify - delete a dentry and call fsnotify_delete() + * @dentry: The dentry to delete + * + * This helper is used to guaranty that the unlinked inode cannot be found + * by lookup of this name after fsnotify_delete() event has been delivered. + */ +static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + ihold(inode); + d_delete(dentry); + fsnotify_delete(dir, inode, dentry); + iput(inode); +} + +/* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* @@ -258,10 +295,10 @@ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8420fe504927..2be4dd7e90a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a59d25f19385..16870f86c74d 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -51,7 +51,7 @@ struct ipv6_devconf { __s32 use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - __s32 mc_forwarding; + atomic_t mc_forwarding; #endif __s32 disable_ipv6; __s32 drop_unicast_in_l2_multicast; @@ -371,19 +371,12 @@ static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk) return NULL; } -static inline struct inet6_request_sock * - inet6_rsk(const struct request_sock *rsk) -{ - return NULL; -} - static inline struct raw6_sock *raw6_sk(const struct sock *sk) { return NULL; } #define inet6_rcv_saddr(__sk) NULL -#define tcp_twsk_ipv6only(__sk) 0 #define inet_v6_ipv6only(__sk) 0 #endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _IPV6_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index f8397f300fcd..15e0e0209da4 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -66,11 +66,6 @@ static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, linkmode_clear_bit(nr, addr); } -static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) -{ - __change_bit(nr, addr); -} - static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a5a724c308d8..819ec92dc2a8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -80,7 +80,7 @@ LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, unsigned long *set_kern_flags) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) -LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, +LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, diff --git a/include/linux/mii.h b/include/linux/mii.h index 12ea29e04293..5ee13083cec7 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -355,56 +355,6 @@ static inline u32 mii_adv_to_ethtool_adv_x(u32 adv) } /** - * mii_lpa_mod_linkmode_adv_sgmii - * @lp_advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_LPA bits to - * linkmode advertisement settings for SGMII. - * Leaves other bits unchanged. - */ -static inline void -mii_lpa_mod_linkmode_lpa_sgmii(unsigned long *lp_advertising, u32 lpa) -{ - u32 speed_duplex = lpa & LPA_SGMII_DPX_SPD_MASK; - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_1000FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_100FULL); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10HALF); - - linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, lp_advertising, - speed_duplex == LPA_SGMII_10FULL); -} - -/** - * mii_lpa_to_linkmode_adv_sgmii - * @advertising: pointer to destination link mode. - * @lpa: value of the MII_LPA register - * - * A small helper function that translates MII_ADVERTISE bits - * to linkmode advertisement settings when in SGMII mode. - * Clears the old value of advertising. - */ -static inline void mii_lpa_to_linkmode_lpa_sgmii(unsigned long *lp_advertising, - u32 lpa) -{ - linkmode_zero(lp_advertising); - - mii_lpa_mod_linkmode_lpa_sgmii(lp_advertising, lpa); -} - -/** * mii_adv_mod_linkmode_adv_t * @advertising:pointer to destination link mode. * @adv: value of the MII_ADVERTISE register diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..27145c4d6820 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -64,13 +64,6 @@ enum { }; enum { - MLX5_MODIFY_TIR_BITMASK_LRO = 0x0, - MLX5_MODIFY_TIR_BITMASK_INDIRECT_TABLE = 0x1, - MLX5_MODIFY_TIR_BITMASK_HASH = 0x2, - MLX5_MODIFY_TIR_BITMASK_TUNNELED_OFFLOAD_EN = 0x3 -}; - -enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, diff --git a/include/linux/mm.h b/include/linux/mm.h index e1a84b1e6787..213cc569b192 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1506,11 +1506,18 @@ static inline u8 page_kasan_tag(const struct page *page) static inline void page_kasan_tag_set(struct page *page, u8 tag) { - if (kasan_enabled()) { - tag ^= 0xff; - page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); - page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } + unsigned long old_flags, flags; + + if (!kasan_enabled()) + return; + + tag ^= 0xff; + old_flags = READ_ONCE(page->flags); + do { + flags = old_flags; + flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); + flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9db36dc5d4cf..5140e5feb486 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -261,6 +261,7 @@ static_assert(sizeof(struct page) == sizeof(struct folio)); static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); +FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index 6b3267b49755..ed42bd5f639f 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -26,11 +26,6 @@ struct i40e_client_version { u8 rsvd; }; -enum i40e_client_state { - __I40E_CLIENT_NULL, - __I40E_CLIENT_REGISTERED -}; - enum i40e_client_instance_state { __I40E_CLIENT_INSTANCE_NONE, __I40E_CLIENT_INSTANCE_OPENED, @@ -190,11 +185,6 @@ struct i40e_client { const struct i40e_client_ops *ops; /* client ops provided by the client */ }; -static inline bool i40e_client_is_registered(struct i40e_client *client) -{ - return test_bit(__I40E_CLIENT_REGISTERED, &client->state); -} - void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); void i40e_client_device_unregister(struct i40e_info *ldev); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3213c7227b59..3fb6fb67ed77 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2548,6 +2548,7 @@ struct packet_type { struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); + struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; @@ -3816,14 +3817,7 @@ extern unsigned int netdev_budget_usecs; /* Called by rtnetlink.c:rtnl_unlock() */ void netdev_run_todo(void); -/** - * dev_put - release reference to device - * @dev: network device - * - * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. - */ -static inline void dev_put(struct net_device *dev) +static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3834,14 +3828,7 @@ static inline void dev_put(struct net_device *dev) } } -/** - * dev_hold - get reference to device - * @dev: network device - * - * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. - */ -static inline void dev_hold(struct net_device *dev) +static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT @@ -3852,11 +3839,24 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void __netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +/* netdev_tracker_alloc() can upgrade a prior untracked reference + * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. + */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER - ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); + refcount_dec(&dev->refcnt_tracker.no_tracker); + __netdev_tracker_alloc(dev, tracker, gfp); #endif } @@ -3872,8 +3872,8 @@ static inline void dev_hold_track(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { if (dev) { - dev_hold(dev); - netdev_tracker_alloc(dev, tracker, gfp); + __dev_hold(dev); + __netdev_tracker_alloc(dev, tracker, gfp); } } @@ -3882,10 +3882,34 @@ static inline void dev_put_track(struct net_device *dev, { if (dev) { netdev_tracker_free(dev, tracker); - dev_put(dev); + __dev_put(dev); } } +/** + * dev_hold - get reference to device + * @dev: network device + * + * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. + */ +static inline void dev_hold(struct net_device *dev) +{ + dev_hold_track(dev, NULL, GFP_ATOMIC); +} + +/** + * dev_put - release reference to device + * @dev: network device + * + * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. + */ +static inline void dev_put(struct net_device *dev) +{ + dev_put_track(dev, NULL); +} + static inline void dev_replace_track(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -3894,11 +3918,11 @@ static inline void dev_replace_track(struct net_device *odev, if (odev) netdev_tracker_free(odev, tracker); - dev_hold(ndev); - dev_put(odev); + __dev_hold(ndev); + __dev_put(odev); if (ndev) - netdev_tracker_alloc(ndev, tracker, gfp); + __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 1ec631838af9..bda1c385cffb 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -135,15 +135,6 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack, extack->cookie_len = sizeof(cookie); } -static inline void nl_set_extack_cookie_u32(struct netlink_ext_ack *extack, - u32 cookie) -{ - if (!extack) - return; - memcpy(extack->cookie, &cookie, sizeof(cookie)); - extack->cookie_len = sizeof(cookie); -} - void netlink_kernel_release(struct sock *sk); int __netlink_change_ngroups(struct sock *sk, unsigned int groups); int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 00835bacd236..02aa49323d1d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -61,7 +61,9 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; __u32 mask; struct rcu_head rcu_head; }; @@ -395,7 +397,7 @@ extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fa extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); @@ -532,8 +534,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); /* * linux/fs/nfs/symlink.c diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 77b2dba27bbb..ca0959e51e81 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -266,6 +266,8 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) #define NFS_CAP_LGOPEN (1U << 5) +#define NFS_CAP_CASE_INSENSITIVE (1U << 6) +#define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) @@ -282,5 +284,5 @@ struct nfs_server { #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) - +#define NFS_CAP_FS_LOCATIONS (1U << 30) #endif diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 967a0098f0a9..728cb0c1f0b6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1194,6 +1194,8 @@ struct nfs4_server_caps_res { u32 has_links; u32 has_symlinks; u32 fh_expire_type; + u32 case_insensitive; + u32 case_preserving; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1737,7 +1739,7 @@ struct nfs_rpc_ops { struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); - int (*access) (struct inode *, struct nfs_access_entry *); + int (*access) (struct inode *, struct nfs_access_entry *, const struct cred *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, @@ -1795,6 +1797,7 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); }; /* diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index add077a81b21..266eb26fb029 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -31,8 +31,7 @@ void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, unsigned int mode); -void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, - struct phylink_link_state *state); +void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces); int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 117f230bcdfd..733649184b27 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -693,18 +693,6 @@ struct perf_event { u64 total_time_running; u64 tstamp; - /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -852,6 +840,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset; /* * These fields let us detect when two contexts have both @@ -934,6 +923,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; }; struct perf_cgroup { diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..cd08cf1a8b0d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1661,7 +1661,7 @@ int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 713a0c928b7c..cca149f78d35 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -582,7 +582,6 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); -void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c7e627503d2..07481bb87d4e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -86,4 +86,9 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) +{ + return task_active_pid_ns(tsk) == &init_pid_ns; +} + #endif /* _LINUX_PID_NS_H */ diff --git a/include/linux/psi.h b/include/linux/psi.h index a70ca833c6d7..7f7d1d88c3bb 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -25,18 +25,17 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); - -#ifdef CONFIG_CGROUPS -int psi_cgroup_alloc(struct cgroup *cgrp); -void psi_cgroup_free(struct cgroup *cgrp); -void cgroup_move_task(struct task_struct *p, struct css_set *to); - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); +void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); #endif #else /* CONFIG_PSI */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 516c0fe836fd..1a3cef26d129 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -141,9 +141,6 @@ struct psi_trigger { * events to one per window */ u64 last_event_time; - - /* Refcounting to prevent premature destruction */ - struct kref refcount; }; struct psi_group { diff --git a/include/linux/quota.h b/include/linux/quota.h index 18ebd39c9487..fd692b4a41d5 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -91,7 +91,7 @@ extern bool qid_valid(struct kqid qid); * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to - * test for and handle handle invalid kqids being returned. + * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index 60f3453be23e..9ca353ab712b 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -13,6 +13,8 @@ struct ref_tracker_dir { spinlock_t lock; unsigned int quarantine_avail; refcount_t untracked; + refcount_t no_tracker; + bool dead; struct list_head list; /* List of active trackers */ struct list_head quarantine; /* List of dead trackers */ #endif @@ -26,7 +28,9 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, INIT_LIST_HEAD(&dir->quarantine); spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; + dir->dead = false; refcount_set(&dir->untracked, 1); + refcount_set(&dir->no_tracker, 1); stack_depot_init(); } diff --git a/include/linux/sched.h b/include/linux/sched.h index 508b91d57470..75ba8aa60248 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -619,10 +619,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * @@ -1684,7 +1680,6 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf11e1fbd69b..a5adbf6b51e8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,12 +314,38 @@ struct sk_buff; * used to translate the reason to string. */ enum skb_drop_reason { - SKB_DROP_REASON_NOT_SPECIFIED, - SKB_DROP_REASON_NO_SOCKET, - SKB_DROP_REASON_PKT_TOO_SMALL, - SKB_DROP_REASON_TCP_CSUM, - SKB_DROP_REASON_TCP_FILTER, - SKB_DROP_REASON_UDP_CSUM, + SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ + SKB_DROP_REASON_NO_SOCKET, /* socket not found */ + SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ + SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ + SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ + SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ + SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ + SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current + * host (interface is in promisc + * mode) + */ + SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ + SKB_DROP_REASON_IP_INHDR, /* there is something wrong with + * IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. + * see the document for rp_filter + * in ip-sysctl.rst for more + * information + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 + * is multicast, but L3 is + * unicast. + */ + SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ + SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ + SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ + SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as + * udp packet drop out of + * udp_memory_allocated. + */ SKB_DROP_REASON_MAX, }; @@ -557,6 +583,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ @@ -3898,11 +3925,6 @@ static inline ktime_t net_timedelta(ktime_t t) return ktime_sub(ktime_get_real(), t); } -static inline ktime_t net_invalid_timestamp(void) -{ - return 0; -} - static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 18a717fe62eb..1ff68a88c58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -29,7 +29,7 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - unsigned long copy; + DECLARE_BITMAP(copy, MAX_MSG_FRAGS + 2); /* The extra two elements: * 1) used for chaining the front and sections when the list becomes * partitioned (e.g. end < start). The crypto APIs require the @@ -38,7 +38,6 @@ struct sk_msg_sg { */ struct scatterlist data[MAX_MSG_FRAGS + 2]; }; -static_assert(BITS_PER_LONG >= NR_MSG_FRAG_IDS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -234,7 +233,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (test_bit(msg->sg.start, &msg->sg.copy)) { + if (test_bit(msg->sg.start, msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -253,7 +252,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - __set_bit(msg->sg.end, &msg->sg.copy); + __set_bit(msg->sg.end, msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -262,9 +261,9 @@ static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { if (copy_state) - __set_bit(i, &msg->sg.copy); + __set_bit(i, msg->sg.copy); else - __clear_bit(i, &msg->sg.copy); + __clear_bit(i, msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 571f605bc91e..382af90320ac 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -88,6 +88,7 @@ struct svc_xprt { struct list_head xpt_users; /* callbacks on free */ struct net *xpt_net; + netns_tracker ns_tracker; const struct cred *xpt_cred; struct rpc_xprt *xpt_bc_xprt; /* NFSv4.1 backchannel */ struct rpc_xprt_switch *xpt_bc_xps; /* NFSv4.1 backchannel */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 955ea4d7af0b..3cdc8d878d81 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -284,6 +284,7 @@ struct rpc_xprt { } stat; struct net *xprt_net; + netns_tracker ns_tracker; const char *servername; const char *address_strings[RPC_DISPLAY_MAX]; #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5785d909c321..3e8ecdebe601 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -430,15 +430,7 @@ struct platform_hibernation_ops { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ -extern void __register_nosave_region(unsigned long b, unsigned long e, int km); -static inline void __init register_nosave_region(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 0); -} -static inline void __init register_nosave_region_late(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 1); -} +extern void register_nosave_region(unsigned long b, unsigned long e); extern int swsusp_page_is_forbidden(struct page *); extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); @@ -458,7 +450,6 @@ int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 180adf7da785..6353d6db69b2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -265,7 +265,7 @@ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * return NULL; } -static inline struct sysctl_header *register_sysctl_mount_point(const char *path) +static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) { return NULL; } diff --git a/include/linux/udp.h b/include/linux/udp.h index ae66dadd8543..254a2654400f 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,11 +23,6 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } -static inline struct udphdr *inner_udp_hdr(const struct sk_buff *skb) -{ - return (struct udphdr *)skb_inner_transport_header(skb); -} - #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) diff --git a/include/linux/uio.h b/include/linux/uio.h index 1198a2bfc9bf..739285fe5a2f 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -273,6 +273,23 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) i->count = count; } +static inline int +iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes) +{ + size_t shorted = 0; + int npages; + + if (iov_iter_count(i) > max_bytes) { + shorted = iov_iter_count(i) - max_bytes; + iov_iter_truncate(i, max_bytes); + } + npages = iov_iter_npages(i, INT_MAX); + if (shorted) + iov_iter_reexpand(i, iov_iter_count(i) + shorted); + + return npages; +} + struct csum_state { __wsum csum; size_t off; diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 031f148ab373..b5deafd91f67 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -92,6 +92,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node) static inline void usb_role_switch_put(struct usb_role_switch *sw) { } static inline struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc) { diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 78ea3e332688..e7ce719838b5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -6,6 +6,8 @@ #define RTR_SOLICITATION_INTERVAL (4*HZ) #define RTR_SOLICITATION_MAX_INTERVAL (3600*HZ) /* 1 hour */ +#define MIN_VALID_LIFETIME (2*3600) /* 2 hours */ + #define TEMP_VALID_LIFETIME (7*86400) #define TEMP_PREFERRED_LIFETIME (86400) #define REGEN_MAX_RETRY (3) diff --git a/include/net/ax25.h b/include/net/ax25.h index 526e49589197..0f9790c455bb 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -187,18 +187,12 @@ typedef struct { typedef struct ax25_route { struct ax25_route *next; - refcount_t refcount; ax25_address callsign; struct net_device *dev; ax25_digi *digipeat; char ip_mode; } ax25_route; -static inline void ax25_hold_route(ax25_route *ax25_rt) -{ - refcount_inc(&ax25_rt->refcount); -} - void __ax25_put_route(ax25_route *ax25_rt); extern rwlock_t ax25_route_lock; @@ -213,12 +207,6 @@ static inline void ax25_route_lock_unuse(void) read_unlock(&ax25_route_lock); } -static inline void ax25_put_route(ax25_route *ax25_rt) -{ - if (refcount_dec_and_test(&ax25_rt->refcount)) - __ax25_put_route(ax25_rt); -} - typedef struct { char slave; /* slave_mode? */ struct timer_list slave_timer; /* timeout timer */ @@ -239,6 +227,7 @@ typedef struct ax25_dev { #if defined(CONFIG_AX25_DAMA_SLAVE) || defined(CONFIG_AX25_DAMA_MASTER) ax25_dama_info dama; #endif + refcount_t refcount; } ax25_dev; typedef struct ax25_cb { @@ -293,6 +282,17 @@ static __inline__ void ax25_cb_put(ax25_cb *ax25) } } +static inline void ax25_dev_hold(ax25_dev *ax25_dev) +{ + refcount_inc(&ax25_dev->refcount); +} + +static inline void ax25_dev_put(ax25_dev *ax25_dev) +{ + if (refcount_dec_and_test(&ax25_dev->refcount)) { + kfree(ax25_dev); + } +} static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev) { skb->dev = dev; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 586f69d084a2..f5caff1ddb29 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -258,6 +258,15 @@ struct adv_info { #define HCI_ADV_TX_POWER_NO_PREFERENCE 0x7F +struct monitored_device { + struct list_head list; + + bdaddr_t bdaddr; + __u8 addr_type; + __u16 handle; + bool notified; +}; + struct adv_pattern { struct list_head list; __u8 ad_type; @@ -294,6 +303,9 @@ struct adv_monitor { #define HCI_MAX_SHORT_NAME_LENGTH 10 +#define HCI_CONN_HANDLE_UNSET 0xffff +#define HCI_CONN_HANDLE_MAX 0x0eff + /* Min encryption key size to match with SMP */ #define HCI_MIN_ENC_KEY_SIZE 7 @@ -591,6 +603,9 @@ struct hci_dev { struct delayed_work interleave_scan; + struct list_head monitored_devices; + bool advmon_pend_notify; + #if IS_ENABLED(CONFIG_BT_LEDS) struct led_trigger *power_led; #endif @@ -1847,6 +1862,8 @@ void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle); int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip); int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status); int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status); +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type); u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 107b25deae68..99266f7aebdc 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -1104,3 +1104,19 @@ struct mgmt_ev_controller_resume { #define MGMT_WAKE_REASON_NON_BT_WAKE 0x0 #define MGMT_WAKE_REASON_UNEXPECTED 0x1 #define MGMT_WAKE_REASON_REMOTE_WAKE 0x2 + +#define MGMT_EV_ADV_MONITOR_DEVICE_FOUND 0x002f +struct mgmt_ev_adv_monitor_device_found { + __le16 monitor_handle; + struct mgmt_addr_info addr; + __s8 rssi; + __le32 flags; + __le16 eir_len; + __u8 eir[0]; +} __packed; + +#define MGMT_EV_ADV_MONITOR_DEVICE_LOST 0x0030 +struct mgmt_ev_adv_monitor_device_lost { + __le16 monitor_handle; + struct mgmt_addr_info addr; +} __packed; diff --git a/include/net/bonding.h b/include/net/bonding.h index f6ae3a4baea4..7dead855a72d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -346,7 +346,7 @@ static inline bool bond_uses_primary(struct bonding *bond) static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { - struct slave *slave = rcu_dereference(bond->curr_active_slave); + struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } @@ -699,20 +699,6 @@ static inline struct slave *bond_slave_has_mac(struct bonding *bond, } /* Caller must hold rcu_read_lock() for read */ -static inline struct slave *bond_slave_has_mac_rcu(struct bonding *bond, - const u8 *mac) -{ - struct list_head *iter; - struct slave *tmp; - - bond_for_each_slave_rcu(bond, tmp, iter) - if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) - return tmp; - - return NULL; -} - -/* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rx(struct bonding *bond, const u8 *mac) { struct list_head *iter; diff --git a/include/net/dsa.h b/include/net/dsa.h index 57b3e4e7413b..ca8c14b547b4 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -278,6 +278,10 @@ struct dsa_port { u8 devlink_port_setup:1; + /* Master state bits, valid only on CPU ports */ + u8 master_admin_up:1; + u8 master_oper_up:1; + u8 setup:1; struct device_node *dn; @@ -478,6 +482,12 @@ static inline bool dsa_port_is_unused(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_UNUSED; } +static inline bool dsa_port_master_is_operational(struct dsa_port *dp) +{ + return dsa_port_is_cpu(dp) && dp->master_admin_up && + dp->master_oper_up; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -581,6 +591,24 @@ static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) return port == dsa_upstream_port(ds, port); } +/* Return true if this is a DSA port leading away from the CPU */ +static inline bool dsa_is_downstream_port(struct dsa_switch *ds, int port) +{ + return dsa_is_dsa_port(ds, port) && !dsa_is_upstream_port(ds, port); +} + +/* Return the local port used to reach the CPU port */ +static inline unsigned int dsa_switch_upstream_port(struct dsa_switch *ds) +{ + struct dsa_port *dp; + + dsa_switch_for_each_available_port(dp, ds) { + return dsa_upstream_port(ds, dp->index); + } + + return ds->num_ports; +} + /* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning * that the routing port from @downstream_ds to @upstream_ds is also the port * which @downstream_ds uses to reach its dedicated CPU. @@ -1036,6 +1064,13 @@ struct dsa_switch_ops { int (*tag_8021q_vlan_add)(struct dsa_switch *ds, int port, u16 vid, u16 flags); int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); + + /* + * DSA master tracking operations + */ + void (*master_state_change)(struct dsa_switch *ds, + const struct net_device *master, + bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ diff --git a/include/net/gro.h b/include/net/gro.h index 8f75802d50fd..a765fedda5c4 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -29,46 +29,50 @@ struct napi_gro_cb { /* Number of segments aggregated. */ u16 count; - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; /* jiffies when first packet was created/queued */ unsigned long age; - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; + /* portion of the cb set to zero at every gro iteration */ + struct_group(zeroed, + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; - /* Used in tunnel GRO receive */ - u8 encap_mark:1; + /* Used in tunnel GRO receive */ + u8 encap_mark:1; - /* GRO checksum is valid */ - u8 csum_valid:1; + /* GRO checksum is valid */ + u8 csum_valid:1; - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; - /* Free the skb? */ - u8 free:2; + /* Free the skb? */ + u8 free:2; #define NAPI_GRO_FREE 1 #define NAPI_GRO_FREE_STOLEN_HEAD 2 - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + ); /* used to support CHECKSUM_COMPLETE for tunneling protocols */ __wsum csum; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 4ad47d9f9d27..3908296d103f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -285,6 +285,14 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); +static inline unsigned long +reqsk_timeout(struct request_sock *req, unsigned long max_timeout) +{ + u64 timeout = (u64)req->timeout << req->num_timeout; + + return (unsigned long)min_t(u64, timeout, max_timeout); +} + static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) { /* The below has to be done to allow calling inet_csk_destroy_sock */ diff --git a/include/net/inet_dscp.h b/include/net/inet_dscp.h new file mode 100644 index 000000000000..72f250dffada --- /dev/null +++ b/include/net/inet_dscp.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * inet_dscp.h: helpers for handling differentiated services codepoints (DSCP) + * + * DSCP is defined in RFC 2474: + * + * 0 1 2 3 4 5 6 7 + * +---+---+---+---+---+---+---+---+ + * | DSCP | CU | + * +---+---+---+---+---+---+---+---+ + * + * DSCP: differentiated services codepoint + * CU: currently unused + * + * The whole DSCP + CU bits form the DS field. + * The DS field is also commonly called TOS or Traffic Class (for IPv6). + * + * Note: the CU bits are now used for Explicit Congestion Notification + * (RFC 3168). + */ + +#ifndef _INET_DSCP_H +#define _INET_DSCP_H + +#include <linux/types.h> + +/* Special type for storing DSCP values. + * + * A dscp_t variable stores a DS field with the CU (ECN) bits cleared. + * Using dscp_t allows to strictly separate DSCP and ECN bits, thus avoiding + * bugs where ECN bits are erroneously taken into account during FIB lookups + * or policy routing. + * + * Note: to get the real DSCP value contained in a dscp_t variable one would + * have to do a bit shift after calling inet_dscp_to_dsfield(). We could have + * a helper for that, but there's currently no users. + */ +typedef u8 __bitwise dscp_t; + +#define INET_DSCP_MASK 0xfc + +static inline dscp_t inet_dsfield_to_dscp(__u8 dsfield) +{ + return (__force dscp_t)(dsfield & INET_DSCP_MASK); +} + +static inline __u8 inet_dscp_to_dsfield(dscp_t dscp) +{ + return (__force __u8)dscp; +} + +static inline bool inet_validate_dscp(__u8 val) +{ + return !(val & ~INET_DSCP_MASK); +} + +#endif /* _INET_DSCP_H */ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index dfd919b3119e..463ae5d33eb0 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -65,13 +65,13 @@ struct inet_timewait_sock { /* these three are in inet_sock */ __be16 tw_sport; /* And these are ours. */ - unsigned int tw_kill : 1, - tw_transparent : 1, + unsigned int tw_transparent : 1, tw_flowlabel : 20, - tw_pad : 2, /* 2 bits hole */ + tw_pad : 3, /* 3 bits hole */ tw_tos : 8; u32 tw_txhash; u32 tw_priority; + u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,8 +110,6 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); - static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index 81e23a102a0d..3984f2c39c4b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -517,7 +517,6 @@ void ip_dst_metrics_put(struct dst_entry *dst) kfree(p); } -u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, @@ -525,19 +524,18 @@ static inline void ip_select_ident_segs(struct net *net, struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb); + /* We had many attacks based on IPID, use the private + * generator as much as we can. + */ + if (sk && inet_sk(sk)->inet_daddr) { + iph->id = htons(inet_sk(sk)->inet_id); + inet_sk(sk)->inet_id += segs; + return; + } if ((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) { - /* This is only to work around buggy Windows95/2000 - * VJ compression implementations. If the ID field - * does not change, they drop every other packet in - * a TCP stream using header compression. - */ - if (sk && inet_sk(sk)->inet_daddr) { - iph->id = htons(inet_sk(sk)->inet_id); - inet_sk(sk)->inet_id += segs; - } else { - iph->id = 0; - } + iph->id = 0; } else { + /* Unfortunately we need the big hammer to get a suitable IPID */ __ip_select_ident(net, iph, segs); } } @@ -713,7 +711,7 @@ int ip_forward(struct sk_buff *skb); */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag); + __be32 daddr, struct rtable *rt); int __ip_options_echo(struct net *net, struct ip_options *dopt, struct sk_buff *skb, const struct ip_options *sopt); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index a9a4ccc0cdb5..40ae8f1b18e5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -282,7 +282,7 @@ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, fn = rcu_dereference(f6i->fib6_node); if (fn) { - *cookie = fn->fn_sernum; + *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c4297704bbcb..6a82bcb8813b 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -17,6 +17,7 @@ #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> +#include <net/inet_dscp.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> @@ -24,7 +25,7 @@ struct fib_config { u8 fc_dst_len; - u8 fc_tos; + dscp_t fc_dscp; u8 fc_protocol; u8 fc_scope; u8 fc_type; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 3afcb128e064..f693784e1419 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -15,9 +15,9 @@ #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> -#include <net/ndisc.h> #include <net/flow.h> #include <net/flow_dissector.h> +#include <net/inet_dscp.h> #include <net/snmp.h> #include <net/netns/hash.h> @@ -437,8 +437,16 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt); +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt); + +static inline struct ipv6_txoptions * +ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt) +{ + if (!opt) + return NULL; + return __ipv6_fixup_options(opt_space, opt); +} bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); @@ -967,6 +975,11 @@ static inline u8 ip6_tclass(__be32 flowinfo) return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } +static inline dscp_t ip6_dscp(__be32 flowinfo) +{ + return inet_dsfield_to_dscp(ip6_tclass(flowinfo)); +} + static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; @@ -1020,7 +1033,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, + struct ipcm6_cookie *ipc6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 0a4779175a52..5052c66e22d2 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H +#include <linux/icmpv6.h> #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 937389e04c8e..87419f7f5421 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -350,7 +350,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl, return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); -int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); +int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, + const bool immediate_ok); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); @@ -460,17 +461,24 @@ static inline struct neighbour * neigh_clone(struct neighbour *neigh) #define neigh_hold(n) refcount_inc(&(n)->refcnt) -static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +static __always_inline int neigh_event_send_probe(struct neighbour *neigh, + struct sk_buff *skb, + const bool immediate_ok) { unsigned long now = jiffies; - + if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); - if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) - return __neigh_event_send(neigh, skb); + if (!(neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) + return __neigh_event_send(neigh, skb, immediate_ok); return 0; } +static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +{ + return neigh_event_send_probe(neigh, skb, true); +} + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 5b61c462e534..374cc7b260fc 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -513,4 +513,10 @@ static inline void fnhe_genid_bump(struct net *net) atomic_inc(&net->fnhe_genid); } +#ifdef CONFIG_NET +void net_ns_init(void); +#else +static inline void net_ns_init(void) {} +#endif + #endif /* __NET_NET_NAMESPACE_H */ diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h new file mode 100644 index 000000000000..a473b56842c5 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_BPF_H +#define _NF_CONNTRACK_BPF_H + +#include <linux/btf.h> +#include <linux/kconfig.h> + +#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_conntrack_bpf(void); + +#else + +static inline int register_nf_conntrack_bpf(void) +{ + return 0; +} + +#endif + +#endif /* _NF_CONNTRACK_BPF_H */ diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 552bc25b1933..388244e315e7 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -10,6 +10,7 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + u8 sysctl_txrehash; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 78557643526e..f0687867b5cd 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -31,18 +31,16 @@ struct ping_group_range { struct inet_hashinfo; struct inet_timewait_death_row { - atomic_t tw_count; - char tw_pad[L1_CACHE_BYTES - sizeof(atomic_t)]; + refcount_t tw_refcount; - struct inet_hashinfo *hashinfo; + struct inet_hashinfo *hashinfo ____cacheline_aligned_in_smp; int sysctl_max_tw_buckets; }; struct tcp_fastopen_context; struct netns_ipv4 { - /* Please keep tcp_death_row at first field in netns_ipv4 */ - struct inet_timewait_death_row tcp_death_row ____cacheline_aligned_in_smp; + struct inet_timewait_death_row *tcp_death_row; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; @@ -70,11 +68,9 @@ struct netns_ipv4 { struct hlist_head *fib_table_hash; struct sock *fibnl; - struct sock * __percpu *icmp_sk; struct sock *mc_autojoin_sk; struct inet_peer_base *peers; - struct sock * __percpu *tcp_sk; struct fqdir *fqdir; u8 sysctl_icmp_echo_ignore_all; @@ -87,6 +83,7 @@ struct netns_ipv4 { u32 ip_rt_min_pmtu; int ip_rt_mtu_expires; + int ip_rt_min_advmss; struct local_ports ip_local_ports; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index a4b550380316..30cdfc4e1615 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -88,7 +88,6 @@ struct netns_ipv6 { struct fib6_table *fib6_local_tbl; struct fib_rules_ops *fib6_rules_ops; #endif - struct sock * __percpu *icmp_sk; struct sock *ndisc_sk; struct sock *tcp_sk; struct sock *igmp_sk; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 79a805542d0f..97c3c19872ff 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -201,21 +201,67 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, } #endif -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, + bool allow_direct); -/* Same as above but will try to sync the entire area pool->max_len */ -static inline void page_pool_put_full_page(struct page_pool *pool, - struct page *page, bool allow_direct) +static inline void page_pool_fragment_page(struct page *page, long nr) +{ + atomic_long_set(&page->pp_frag_count, nr); +} + +static inline long page_pool_defrag_page(struct page *page, long nr) +{ + long ret; + + /* If nr == pp_frag_count then we have cleared all remaining + * references to the page. No need to actually overwrite it, instead + * we can leave this to be overwritten by the calling function. + * + * The main advantage to doing this is that an atomic_read is + * generally a much cheaper operation than an atomic update, + * especially when dealing with a page that may be partitioned + * into only 2 or 3 pieces. + */ + if (atomic_long_read(&page->pp_frag_count) == nr) + return 0; + + ret = atomic_long_sub_return(nr, &page->pp_frag_count); + WARN_ON(ret < 0); + return ret; +} + +static inline bool page_pool_is_last_frag(struct page_pool *pool, + struct page *page) +{ + /* If fragments aren't enabled or count is 0 we were the last user */ + return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || + (page_pool_defrag_page(page, 1) == 0); +} + +static inline void page_pool_put_page(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size, + bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - page_pool_put_page(pool, page, -1, allow_direct); + if (!page_pool_is_last_frag(pool, page)) + return; + + page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); #endif } +/* Same as above but will try to sync the entire area pool->max_len */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + page_pool_put_page(pool, page, -1, allow_direct); +} + /* Same as above but the caller must guarantee safe context. e.g NAPI */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) @@ -243,30 +289,6 @@ static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) page->dma_addr_upper = upper_32_bits(addr); } -static inline void page_pool_set_frag_count(struct page *page, long nr) -{ - atomic_long_set(&page->pp_frag_count, nr); -} - -static inline long page_pool_atomic_sub_frag_count_return(struct page *page, - long nr) -{ - long ret; - - /* As suggested by Alexander, atomic_long_read() may cover up the - * reference count errors, so avoid calling atomic_long_read() in - * the cases of freeing or draining the page_frags, where we would - * not expect it to match or that are slowpath anyway. - */ - if (__builtin_constant_p(nr) && - atomic_long_read(&page->pp_frag_count) == nr) - return 0; - - ret = atomic_long_sub_return(nr, &page->pp_frag_count); - WARN_ON(ret < 0); - return ret; -} - static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 676cb8ea9e15..a3b57a93228a 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -1028,4 +1028,15 @@ struct tc_fifo_qopt_offload { }; }; +#ifdef CONFIG_NET_CLS_ACT +DECLARE_STATIC_KEY_FALSE(tc_skb_ext_tc); +void tc_skb_ext_tc_enable(void); +void tc_skb_ext_tc_disable(void); +#define tc_skb_ext_tc_enabled() static_branch_unlikely(&tc_skb_ext_tc) +#else /* CONFIG_NET_CLS_ACT */ +static inline void tc_skb_ext_tc_enable(void) { } +static inline void tc_skb_ext_tc_disable(void) { } +#define tc_skb_ext_tc_enabled() false +#endif + #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e7b21c0b3a6..44a35531952e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -63,12 +63,6 @@ static inline psched_time_t psched_get_time(void) return PSCHED_NS2TICKS(ktime_get_ns()); } -static inline psched_tdiff_t -psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound) -{ - return min(tv1 - tv2, bound); -} - struct qdisc_watchdog { u64 last_expires; struct hrtimer timer; diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 29e41ff3ec93..144c39db9898 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -70,6 +70,7 @@ struct request_sock { struct saved_syn *saved_syn; u32 secid; u32 peer_secid; + u32 timeout; }; static inline struct request_sock *inet_reqsk(const struct sock *sk) @@ -104,6 +105,7 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; + req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; diff --git a/include/net/route.h b/include/net/route.h index 4c858dcf1aa8..25404fc2b483 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -370,7 +370,7 @@ static inline struct neighbour *ip_neigh_gw4(struct net_device *dev, { struct neighbour *neigh; - neigh = __ipv4_neigh_lookup_noref(dev, daddr); + neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)daddr); if (unlikely(!neigh)) neigh = __neigh_create(&arp_tbl, &daddr, dev, false); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 472843eedbae..9bab396c1f3b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -518,11 +518,6 @@ static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) BUILD_BUG_ON(sizeof(qcb->data) < sz); } -static inline int qdisc_qlen_cpu(const struct Qdisc *q) -{ - return this_cpu_ptr(q->cpu_qstats)->qlen; -} - static inline int qdisc_qlen(const struct Qdisc *q) { return q->q.qlen; diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..d6c13f0fba40 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -316,6 +316,7 @@ struct sk_filter; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_txhash: computed flow hash for use on transmit + * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received @@ -491,6 +492,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + u8 sk_txrehash; #ifdef CONFIG_NET_RX_BUSY_POLL u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; @@ -587,6 +589,18 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) __tmp | SK_USER_DATA_NOCOPY); \ }) +static inline +struct net *sock_net(const struct sock *sk) +{ + return read_pnet(&sk->sk_net); +} + +static inline +void sock_net_set(struct sock *sk, struct net *net) +{ + write_pnet(&sk->sk_net, net); +} + /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK * or not whether his port will be reused by someone else. SK_FORCE_REUSE @@ -2054,7 +2068,7 @@ static inline void sk_set_txhash(struct sock *sk) static inline bool sk_rethink_txhash(struct sock *sk) { - if (sk->sk_txhash) { + if (sk->sk_txhash && sk->sk_txrehash == SOCK_TXREHASH_ENABLED) { sk_set_txhash(sk); return true; } @@ -2704,18 +2718,6 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static inline -struct net *sock_net(const struct sock *sk) -{ - return read_pnet(&sk->sk_net); -} - -static inline -void sock_net_set(struct sock *sk, struct net *net) -{ - write_pnet(&sk->sk_net, net); -} - static inline bool skb_sk_is_prefetched(struct sk_buff *skb) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 44e442bf23f9..eff2487d972d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1369,6 +1369,7 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +#ifdef CONFIG_INET void __sk_defer_free_flush(struct sock *sk); static inline void sk_defer_free_flush(struct sock *sk) @@ -1377,6 +1378,9 @@ static inline void sk_defer_free_flush(struct sock *sk) return; __sk_defer_free_flush(sk); } +#else +static inline void sk_defer_free_flush(struct sock *sk) {} +#endif int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); @@ -2354,7 +2358,7 @@ static inline u32 tcp_timeout_init(struct sock *sk) if (timeout <= 0) timeout = TCP_TIMEOUT_INIT; - return timeout; + return min_t(int, timeout, TCP_RTO_MAX); } static inline u32 tcp_rwnd_init_bpf(struct sock *sk) diff --git a/include/net/udplite.h b/include/net/udplite.h index 9185e45b997f..a3c53110d30b 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -70,49 +70,6 @@ static inline int udplite_checksum_init(struct sk_buff *skb, struct udphdr *uh) return 0; } -/* Slow-path computation of checksum. Socket is locked. */ -static inline __wsum udplite_csum_outgoing(struct sock *sk, struct sk_buff *skb) -{ - const struct udp_sock *up = udp_sk(skb->sk); - int cscov = up->len; - __wsum csum = 0; - - if (up->pcflag & UDPLITE_SEND_CC) { - /* - * Sender has set `partial coverage' option on UDP-Lite socket. - * The special case "up->pcslen == 0" signifies full coverage. - */ - if (up->pcslen < up->len) { - if (0 < up->pcslen) - cscov = up->pcslen; - udp_hdr(skb)->len = htons(up->pcslen); - } - /* - * NOTE: Causes for the error case `up->pcslen > up->len': - * (i) Application error (will not be penalized). - * (ii) Payload too big for send buffer: data is split - * into several packets, each with its own header. - * In this case (e.g. last segment), coverage may - * exceed packet length. - * Since packets with coverage length > packet length are - * illegal, we fall back to the defaults here. - */ - } - - skb->ip_summed = CHECKSUM_NONE; /* no HW support for checksumming */ - - skb_queue_walk(&sk->sk_write_queue, skb) { - const int off = skb_transport_offset(skb); - const int len = skb->len - off; - - csum = skb_checksum(skb, off, (cscov > len)? len : cscov, csum); - - if ((cscov -= len) <= 0) - break; - } - return csum; -} - /* Fast-path computation of checksum. Socket may not be locked. */ static inline __wsum udplite_csum(struct sk_buff *skb) { diff --git a/include/net/xdp.h b/include/net/xdp.h index 8f0812e4996d..b7721c3e4d1f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -60,12 +60,20 @@ struct xdp_rxq_info { u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; + u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { struct net_device *dev; }; +enum xdp_buff_flags { + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under + * pressure + */ +}; + struct xdp_buff { void *data; void *data_end; @@ -74,13 +82,40 @@ struct xdp_buff { struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + +static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; + xdp->flags = 0; } static __always_inline void @@ -111,6 +146,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; @@ -122,8 +171,19 @@ struct xdp_frame { */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -159,6 +219,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +static inline void +xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, + unsigned int size, unsigned int truesize, + bool pfmemalloc) +{ + skb_shinfo(skb)->nr_frags = nr_frags; + + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; + skb->pfmemalloc |= pfmemalloc; +} + /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) @@ -180,6 +253,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->flags = frame->flags; } static inline @@ -206,6 +280,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->flags = xdp->flags; return 0; } @@ -230,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) return xdp_frame; } +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); @@ -246,14 +323,37 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct skb_shared_info *sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); +} + +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size); +static inline int +xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id) +{ + return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); } -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 3e042ca2cedb..cfcfd26399f7 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -14,8 +14,19 @@ EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ - EM(SKB_DROP_REASON_TCP_FILTER, TCP_FILTER) \ + EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ + EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ + EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ + EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ + EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ + EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ + EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ + UNICAST_IN_L2_MULTICAST) \ + EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ + EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ + EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ + EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 1e566ac4b812..29982d60b68a 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -794,6 +794,9 @@ RPC_SHOW_SOCKET RPC_SHOW_SOCK + +#include <trace/events/net_probe_common.h> + /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. @@ -816,27 +819,32 @@ DECLARE_EVENT_CLASS(xs_socket_event, __field(unsigned int, socket_state) __field(unsigned int, sock_state) __field(unsigned long long, ino) - __string(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]) - __string(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( struct inode *inode = SOCK_INODE(socket); + const struct sock *sk = socket->sk; + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS(__entry, inet, sk); + __entry->socket_state = socket->state; __entry->sock_state = socket->sk->sk_state; __entry->ino = (unsigned long long)inode->i_ino; - __assign_str(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]); - __assign_str(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]); + ), TP_printk( - "socket:[%llu] dstaddr=%s/%s " + "socket:[%llu] srcaddr=%pISpc dstaddr=%pISpc " "state=%u (%s) sk_state=%u (%s)", - __entry->ino, __get_str(dstaddr), __get_str(dstport), + __entry->ino, + __entry->saddr, + __entry->daddr, __entry->socket_state, rpc_show_socket_state(__entry->socket_state), __entry->sock_state, @@ -866,29 +874,33 @@ DECLARE_EVENT_CLASS(xs_socket_event_done, __field(unsigned int, socket_state) __field(unsigned int, sock_state) __field(unsigned long long, ino) - __string(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]) - __string(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) ), TP_fast_assign( struct inode *inode = SOCK_INODE(socket); + const struct sock *sk = socket->sk; + const struct inet_sock *inet = inet_sk(sk); + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS(__entry, inet, sk); + __entry->socket_state = socket->state; __entry->sock_state = socket->sk->sk_state; __entry->ino = (unsigned long long)inode->i_ino; __entry->error = error; - __assign_str(dstaddr, - xprt->address_strings[RPC_DISPLAY_ADDR]); - __assign_str(dstport, - xprt->address_strings[RPC_DISPLAY_PORT]); ), TP_printk( - "error=%d socket:[%llu] dstaddr=%s/%s " + "error=%d socket:[%llu] srcaddr=%pISpc dstaddr=%pISpc " "state=%u (%s) sk_state=%u (%s)", __entry->error, - __entry->ino, __get_str(dstaddr), __get_str(dstport), + __entry->ino, + __entry->saddr, + __entry->daddr, __entry->socket_state, rpc_show_socket_state(__entry->socket_state), __entry->sock_state, @@ -953,7 +965,8 @@ TRACE_EVENT(rpc_socket_nospace, { BIT(XPRT_REMOVE), "REMOVE" }, \ { BIT(XPRT_CONGESTED), "CONGESTED" }, \ { BIT(XPRT_CWND_WAIT), "CWND_WAIT" }, \ - { BIT(XPRT_WRITE_SPACE), "WRITE_SPACE" }) + { BIT(XPRT_WRITE_SPACE), "WRITE_SPACE" }, \ + { BIT(XPRT_SND_IS_COOKIE), "SND_IS_COOKIE" }) DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class, TP_PROTO( @@ -1150,8 +1163,11 @@ DECLARE_EVENT_CLASS(xprt_writelock_event, __entry->task_id = -1; __entry->client_id = -1; } - __entry->snd_task_id = xprt->snd_task ? - xprt->snd_task->tk_pid : -1; + if (xprt->snd_task && + !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) + __entry->snd_task_id = xprt->snd_task->tk_pid; + else + __entry->snd_task_id = -1; ), TP_printk(SUNRPC_TRACE_TASK_SPECIFIER @@ -1196,8 +1212,12 @@ DECLARE_EVENT_CLASS(xprt_cong_event, __entry->task_id = -1; __entry->client_id = -1; } - __entry->snd_task_id = xprt->snd_task ? - xprt->snd_task->tk_pid : -1; + if (xprt->snd_task && + !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) + __entry->snd_task_id = xprt->snd_task->tk_pid; + else + __entry->snd_task_id = -1; + __entry->cong = xprt->cong; __entry->cwnd = xprt->cwnd; __entry->wait = test_bit(XPRT_CWND_WAIT, &xprt->state); diff --git a/include/trace/perf.h b/include/trace/perf.h index ea4405de175a..5d48c46a3008 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -23,8 +23,9 @@ #undef __get_rel_dynamic_array #define __get_rel_dynamic_array(field) \ - ((void *)(&__entry->__rel_loc_##field) + \ - sizeof(__entry->__rel_loc_##field) + \ + ((void *)__entry + \ + offsetof(typeof(*__entry), __rel_loc_##field) + \ + sizeof(__entry->__rel_loc_##field) + \ (__entry->__rel_loc_##field & 0xffff)) #undef __get_rel_dynamic_array_len diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 8c6f7c433518..3d29919045af 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -128,7 +128,7 @@ TRACE_MAKE_SYSTEM_STR(); struct trace_event_raw_##name { \ struct trace_entry ent; \ tstruct \ - char __data[0]; \ + char __data[]; \ }; \ \ static struct trace_event_class event_class_##name; @@ -318,9 +318,10 @@ TRACE_MAKE_SYSTEM_STR(); #define __get_str(field) ((char *)__get_dynamic_array(field)) #undef __get_rel_dynamic_array -#define __get_rel_dynamic_array(field) \ - ((void *)(&__entry->__rel_loc_##field) + \ - sizeof(__entry->__rel_loc_##field) + \ +#define __get_rel_dynamic_array(field) \ + ((void *)__entry + \ + offsetof(typeof(*__entry), __rel_loc_##field) + \ + sizeof(__entry->__rel_loc_##field) + \ (__entry->__rel_loc_##field & 0xffff)) #undef __get_rel_dynamic_array_len diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c77a1313b3b0..467ca2f28760 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -128,6 +128,8 @@ #define SO_RESERVE_MEM 73 +#define SO_TXREHASH 74 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..16a7574292a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1111,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1775,6 +1782,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1791,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2267,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2382,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2481,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3257,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5038,44 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5264,11 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/include/uapi/linux/cyclades.h b/include/uapi/linux/cyclades.h new file mode 100644 index 000000000000..6225c5aebe06 --- /dev/null +++ b/include/uapi/linux/cyclades.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_CYCLADES_H +#define _UAPI_LINUX_CYCLADES_H + +#warning "Support for features provided by this header has been removed" +#warning "Please consider updating your code" + +struct cyclades_monitor { + unsigned long int_count; + unsigned long char_count; + unsigned long char_max; + unsigned long char_last; +}; + +#define CYGETMON 0x435901 +#define CYGETTHRESH 0x435902 +#define CYSETTHRESH 0x435903 +#define CYGETDEFTHRESH 0x435904 +#define CYSETDEFTHRESH 0x435905 +#define CYGETTIMEOUT 0x435906 +#define CYSETTIMEOUT 0x435907 +#define CYGETDEFTIMEOUT 0x435908 +#define CYSETDEFTIMEOUT 0x435909 +#define CYSETRFLOW 0x43590a +#define CYGETRFLOW 0x43590b +#define CYSETRTSDTR_INV 0x43590c +#define CYGETRTSDTR_INV 0x43590d +#define CYZSETPOLLCYCLE 0x43590e +#define CYZGETPOLLCYCLE 0x43590f +#define CYGETCD1400VER 0x435910 +#define CYSETWAIT 0x435912 +#define CYGETWAIT 0x435913 + +#endif /* _UAPI_LINUX_CYCLADES_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index cca6e474a085..417d4280d7b5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -319,6 +319,12 @@ enum { /* RINGS */ enum { + ETHTOOL_TCP_DATA_SPLIT_UNKNOWN = 0, + ETHTOOL_TCP_DATA_SPLIT_DISABLED, + ETHTOOL_TCP_DATA_SPLIT_ENABLED, +}; + +enum { ETHTOOL_A_RINGS_UNSPEC, ETHTOOL_A_RINGS_HEADER, /* nest - _A_HEADER_* */ ETHTOOL_A_RINGS_RX_MAX, /* u32 */ @@ -330,6 +336,7 @@ enum { ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ + ETHTOOL_A_RINGS_TCP_DATA_SPLIT, /* u8 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 829ffdfcacca..38f6a8fdfd34 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -41,6 +41,15 @@ enum { /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + /* Insertion frequency: + * "k over n" packets (0 < k <= n) + * [0.0001% ... 100%] + */ +#define IOAM6_IPTUNNEL_FREQ_MIN 1 +#define IOAM6_IPTUNNEL_FREQ_MAX 1000000 + IOAM6_IPTUNNEL_FREQ_K, /* u32 */ + IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 9563d294f181..b46bcdb0cab1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 +#define KVM_CAP_SYS_ATTRIBUTES 209 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index c7008d87f1a4..8cb3a6fef553 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -84,12 +84,11 @@ struct smc_diag_conninfo { /* SMC_DIAG_LINKINFO */ struct smc_diag_linkinfo { - __u8 link_id; /* link identifier */ - __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ - __u8 ibport; /* RDMA device port number */ - __u8 gid[40]; /* local GID */ - __u8 peer_gid[40]; /* peer GID */ - __aligned_u64 net_cookie; /* RDMA device net namespace */ + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ }; struct smc_diag_lgrinfo { diff --git a/include/uapi/linux/socket.h b/include/uapi/linux/socket.h index eb0a9a5b6e71..51d6bb2f6765 100644 --- a/include/uapi/linux/socket.h +++ b/include/uapi/linux/socket.h @@ -31,4 +31,8 @@ struct __kernel_sockaddr_storage { #define SOCK_BUF_LOCK_MASK (SOCK_SNDBUF_LOCK | SOCK_RCVBUF_LOCK) +#define SOCK_TXREHASH_DEFAULT ((u8)-1) +#define SOCK_TXREHASH_DISABLED 0 +#define SOCK_TXREHASH_ENABLED 1 + #endif /* _UAPI_LINUX_SOCKET_H */ diff --git a/init/main.c b/init/main.c index 65fa2e41a9c0..ada50f5a15e4 100644 --- a/init/main.c +++ b/init/main.c @@ -99,6 +99,7 @@ #include <linux/kcsan.h> #include <linux/init_syscalls.h> #include <linux/stackdepot.h> +#include <net/net_namespace.h> #include <asm/io.h> #include <asm/bugs.h> @@ -1116,6 +1117,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) key_init(); security_init(); dbg_late_init(); + net_ns_init(); vfs_caches_init(); pagecache_init(); signals_init(); diff --git a/kernel/async.c b/kernel/async.c index b8d7a663497f..b2c4ba5686ee 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -205,9 +205,6 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* mark that this task has queued an async job, used by module init */ - current->flags |= PF_USED_ASYNC; - /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); diff --git a/kernel/audit.c b/kernel/audit.c index e4bbe2c70c26..7690c29d4ee4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -541,20 +541,22 @@ static void kauditd_printk_skb(struct sk_buff *skb) /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record + * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ -static void kauditd_rehold_skb(struct sk_buff *skb) +static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { - /* put the record back in the queue at the same place */ - skb_queue_head(&audit_hold_queue, skb); + /* put the record back in the queue */ + skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record + * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this @@ -564,19 +566,31 @@ static void kauditd_rehold_skb(struct sk_buff *skb) * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ -static void kauditd_hold_skb(struct sk_buff *skb) +static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ - if (!audit_default) { - kfree_skb(skb); - return; + if (!audit_default) + goto drop; + + /* the hold queue is only for when the daemon goes away completely, + * not -EAGAIN failures; if we are in a -EAGAIN state requeue the + * record on the retry queue unless it's full, in which case drop it + */ + if (error == -EAGAIN) { + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + audit_log_lost("kauditd retry queue overflow"); + goto drop; } - /* if we have room, queue the message */ + /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); @@ -585,24 +599,32 @@ static void kauditd_hold_skb(struct sk_buff *skb) /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); +drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record + * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ -static void kauditd_retry_skb(struct sk_buff *skb) +static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { - /* NOTE: because records should only live in the retry queue for a - * short period of time, before either being sent or moved to the hold - * queue, we don't currently enforce a limit on this queue */ - skb_queue_tail(&audit_retry_queue, skb); + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + + /* we have to drop the record, send it via printk as a last effort */ + kauditd_printk_skb(skb); + audit_log_lost("kauditd retry queue overflow"); + kfree_skb(skb); } /** @@ -640,7 +662,7 @@ static void auditd_reset(const struct auditd_connection *ac) /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) - kauditd_hold_skb(skb); + kauditd_hold_skb(skb, -ECONNREFUSED); } /** @@ -714,16 +736,18 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), - void (*err_hook)(struct sk_buff *skb)) + void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ - while ((skb = skb_dequeue(queue))) { + skb_tail = skb_peek_tail(queue); + while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); @@ -731,7 +755,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, -ECONNREFUSED); continue; } @@ -745,7 +769,7 @@ retry: rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c7a5be3bf8be..7f145aefbff8 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -837,13 +837,12 @@ static int fd_array_map_delete_elem(struct bpf_map *map, void *key) static void *prog_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { - struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog = bpf_prog_get(fd); if (IS_ERR(prog)) return prog; - if (!bpf_prog_array_compatible(array, prog)) { + if (!bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return ERR_PTR(-EINVAL); } @@ -1071,7 +1070,6 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) INIT_WORK(&aux->work, prog_array_map_clear_deferred); INIT_LIST_HEAD(&aux->poke_progs); mutex_init(&aux->poke_mutex); - spin_lock_init(&aux->owner.lock); map = array_map_alloc(attr); if (IS_ERR(map)) { diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 06062370c3b8..9e4ecc990647 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -207,7 +207,7 @@ BTF_ID(func, bpf_lsm_socket_socketpair) BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) -BTF_ID(func, bpf_lsm_task_getsecid_subj) +BTF_ID(func, bpf_lsm_current_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e16dafeb2450..a1c44c17ea9c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -198,6 +198,21 @@ DEFINE_IDR(btf_idr); DEFINE_SPINLOCK(btf_idr_lock); +enum btf_kfunc_hook { + BTF_KFUNC_HOOK_XDP, + BTF_KFUNC_HOOK_TC, + BTF_KFUNC_HOOK_STRUCT_OPS, + BTF_KFUNC_HOOK_MAX, +}; + +enum { + BTF_KFUNC_SET_MAX_CNT = 32, +}; + +struct btf_kfunc_set_tab { + struct btf_id_set *sets[BTF_KFUNC_HOOK_MAX][BTF_KFUNC_TYPE_MAX]; +}; + struct btf { void *data; struct btf_type **types; @@ -212,6 +227,7 @@ struct btf { refcount_t refcnt; u32 id; struct rcu_head rcu; + struct btf_kfunc_set_tab *kfunc_set_tab; /* split BTF support */ struct btf *base_btf; @@ -1531,8 +1547,30 @@ static void btf_free_id(struct btf *btf) spin_unlock_irqrestore(&btf_idr_lock, flags); } +static void btf_free_kfunc_set_tab(struct btf *btf) +{ + struct btf_kfunc_set_tab *tab = btf->kfunc_set_tab; + int hook, type; + + if (!tab) + return; + /* For module BTF, we directly assign the sets being registered, so + * there is nothing to free except kfunc_set_tab. + */ + if (btf_is_module(btf)) + goto free_tab; + for (hook = 0; hook < ARRAY_SIZE(tab->sets); hook++) { + for (type = 0; type < ARRAY_SIZE(tab->sets[0]); type++) + kfree(tab->sets[hook][type]); + } +free_tab: + kfree(tab); + btf->kfunc_set_tab = NULL; +} + static void btf_free(struct btf *btf) { + btf_free_kfunc_set_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -5616,17 +5654,45 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, return true; } +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + int len, sfx_len = sizeof("__sz") - 1; + const struct btf_type *t; + const char *param_name; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len < sfx_len) + return false; + param_name += len - sfx_len; + if (strncmp(param_name, "__sz", sfx_len)) + return false; + + return true; +} + static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok) { struct bpf_verifier_log *log = &env->log; + u32 i, nargs, ref_id, ref_obj_id = 0; bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; - u32 i, nargs, ref_id; + int ref_regno = 0; + bool rel = false; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -5704,6 +5770,16 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (reg->type == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; + /* Ensure only one argument is referenced PTR_TO_BTF_ID */ + if (reg->ref_obj_id) { + if (ref_obj_id) { + bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, ref_obj_id); + return -EFAULT; + } + ref_regno = regno; + ref_obj_id = reg->ref_obj_id; + } } else { reg_btf = btf_vmlinux; reg_ref_id = *reg2btf_ids[reg->type]; @@ -5727,17 +5803,33 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, u32 type_size; if (is_kfunc) { + bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); + /* Permit pointer to mem, but only when argument * type is pointer to scalar, or struct composed * (recursively) of scalars. + * When arg_mem_size is true, the pointer can be + * void *. */ if (!btf_type_is_scalar(ref_t) && - !__btf_type_is_scalar_struct(log, btf, ref_t, 0)) { + !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { bpf_log(log, - "arg#%d pointer type %s %s must point to scalar or struct with scalar\n", - i, btf_type_str(ref_t), ref_tname); + "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); return -EINVAL; } + + /* Check for mem, len pair */ + if (arg_mem_size) { + if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { + bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", + i, i + 1); + return -EINVAL; + } + i++; + continue; + } } resolve_ret = btf_resolve_size(btf, ref_t, &type_size); @@ -5758,7 +5850,23 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, } } - return 0; + /* Either both are set, or neither */ + WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); + if (is_kfunc) { + rel = btf_kfunc_id_set_contains(btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_RELEASE, func_id); + /* We already made sure ref_obj_id is set only for one argument */ + if (rel && !ref_obj_id) { + bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + /* Allow (!rel && ref_obj_id), so that passing such referenced PTR_TO_BTF_ID to + * other kfuncs works + */ + } + /* returns argument register number > 0 in case of reference release kfunc */ + return rel ? ref_regno : 0; } /* Compare BTF of a function with given bpf_reg_state. @@ -6200,12 +6308,17 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id) return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; } +enum { + BTF_MODULE_F_LIVE = (1 << 0), +}; + #ifdef CONFIG_DEBUG_INFO_BTF_MODULES struct btf_module { struct list_head list; struct module *module; struct btf *btf; struct bin_attribute *sysfs_attr; + int flags; }; static LIST_HEAD(btf_modules); @@ -6233,7 +6346,8 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, int err = 0; if (mod->btf_data_size == 0 || - (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) + (op != MODULE_STATE_COMING && op != MODULE_STATE_LIVE && + op != MODULE_STATE_GOING)) goto out; switch (op) { @@ -6292,6 +6406,17 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, } break; + case MODULE_STATE_LIVE: + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_mod->flags |= BTF_MODULE_F_LIVE; + break; + } + mutex_unlock(&btf_module_mutex); + break; case MODULE_STATE_GOING: mutex_lock(&btf_module_mutex); list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { @@ -6338,7 +6463,12 @@ struct module *btf_try_get_module(const struct btf *btf) if (btf_mod->btf != btf) continue; - if (try_module_get(btf_mod->module)) + /* We must only consider module whose __init routine has + * finished, hence we must check for BTF_MODULE_F_LIVE flag, + * which is set from the notifier callback for + * MODULE_STATE_LIVE. + */ + if ((btf_mod->flags & BTF_MODULE_F_LIVE) && try_module_get(btf_mod->module)) res = btf_mod->module; break; @@ -6349,6 +6479,36 @@ struct module *btf_try_get_module(const struct btf *btf) return res; } +/* Returns struct btf corresponding to the struct module + * + * This function can return NULL or ERR_PTR. Note that caller must + * release reference for struct btf iff btf_is_module is true. + */ +static struct btf *btf_get_module_btf(const struct module *module) +{ + struct btf *btf = NULL; +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + struct btf_module *btf_mod, *tmp; +#endif + + if (!module) + return bpf_get_btf_vmlinux(); +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + mutex_lock(&btf_module_mutex); + list_for_each_entry_safe(btf_mod, tmp, &btf_modules, list) { + if (btf_mod->module != module) + continue; + + btf_get(btf_mod->btf); + btf = btf_mod->btf; + break; + } + mutex_unlock(&btf_module_mutex); +#endif + + return btf; +} + BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf; @@ -6416,53 +6576,181 @@ BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) BTF_TRACING_TYPE_xxx #undef BTF_TRACING_TYPE -/* BTF ID set registration API for modules */ - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +/* Kernel Function (kfunc) BTF ID set registration API */ -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static int __btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, + enum btf_kfunc_type type, + struct btf_id_set *add_set, bool vmlinux_set) { - mutex_lock(&l->mutex); - list_add(&s->list, &l->list); - mutex_unlock(&l->mutex); + struct btf_kfunc_set_tab *tab; + struct btf_id_set *set; + u32 set_cnt; + int ret; + + if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) { + ret = -EINVAL; + goto end; + } + + if (!add_set->cnt) + return 0; + + tab = btf->kfunc_set_tab; + if (!tab) { + tab = kzalloc(sizeof(*tab), GFP_KERNEL | __GFP_NOWARN); + if (!tab) + return -ENOMEM; + btf->kfunc_set_tab = tab; + } + + set = tab->sets[hook][type]; + /* Warn when register_btf_kfunc_id_set is called twice for the same hook + * for module sets. + */ + if (WARN_ON_ONCE(set && !vmlinux_set)) { + ret = -EINVAL; + goto end; + } + + /* We don't need to allocate, concatenate, and sort module sets, because + * only one is allowed per hook. Hence, we can directly assign the + * pointer and return. + */ + if (!vmlinux_set) { + tab->sets[hook][type] = add_set; + return 0; + } + + /* In case of vmlinux sets, there may be more than one set being + * registered per hook. To create a unified set, we allocate a new set + * and concatenate all individual sets being registered. While each set + * is individually sorted, they may become unsorted when concatenated, + * hence re-sorting the final set again is required to make binary + * searching the set using btf_id_set_contains function work. + */ + set_cnt = set ? set->cnt : 0; + + if (set_cnt > U32_MAX - add_set->cnt) { + ret = -EOVERFLOW; + goto end; + } + + if (set_cnt + add_set->cnt > BTF_KFUNC_SET_MAX_CNT) { + ret = -E2BIG; + goto end; + } + + /* Grow set */ + set = krealloc(tab->sets[hook][type], + offsetof(struct btf_id_set, ids[set_cnt + add_set->cnt]), + GFP_KERNEL | __GFP_NOWARN); + if (!set) { + ret = -ENOMEM; + goto end; + } + + /* For newly allocated set, initialize set->cnt to 0 */ + if (!tab->sets[hook][type]) + set->cnt = 0; + tab->sets[hook][type] = set; + + /* Concatenate the two sets */ + memcpy(set->ids + set->cnt, add_set->ids, add_set->cnt * sizeof(set->ids[0])); + set->cnt += add_set->cnt; + + sort(set->ids, set->cnt, sizeof(set->ids[0]), btf_id_cmp_func, NULL); + + return 0; +end: + btf_free_kfunc_set_tab(btf); + return ret; } -EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) +static int btf_populate_kfunc_set(struct btf *btf, enum btf_kfunc_hook hook, + const struct btf_kfunc_id_set *kset) { - mutex_lock(&l->mutex); - list_del_init(&s->list); - mutex_unlock(&l->mutex); + bool vmlinux_set = !btf_is_module(btf); + int type, ret; + + for (type = 0; type < ARRAY_SIZE(kset->sets); type++) { + if (!kset->sets[type]) + continue; + + ret = __btf_populate_kfunc_set(btf, hook, type, kset->sets[type], vmlinux_set); + if (ret) + break; + } + return ret; } -EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner) +static bool __btf_kfunc_id_set_contains(const struct btf *btf, + enum btf_kfunc_hook hook, + enum btf_kfunc_type type, + u32 kfunc_btf_id) { - struct kfunc_btf_id_set *s; + struct btf_id_set *set; - mutex_lock(&klist->mutex); - list_for_each_entry(s, &klist->list, list) { - if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { - mutex_unlock(&klist->mutex); - return true; - } + if (hook >= BTF_KFUNC_HOOK_MAX || type >= BTF_KFUNC_TYPE_MAX) + return false; + if (!btf->kfunc_set_tab) + return false; + set = btf->kfunc_set_tab->sets[hook][type]; + if (!set) + return false; + return btf_id_set_contains(set, kfunc_btf_id); +} + +static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) +{ + switch (prog_type) { + case BPF_PROG_TYPE_XDP: + return BTF_KFUNC_HOOK_XDP; + case BPF_PROG_TYPE_SCHED_CLS: + return BTF_KFUNC_HOOK_TC; + case BPF_PROG_TYPE_STRUCT_OPS: + return BTF_KFUNC_HOOK_STRUCT_OPS; + default: + return BTF_KFUNC_HOOK_MAX; } - mutex_unlock(&klist->mutex); - return false; } -#define DEFINE_KFUNC_BTF_ID_LIST(name) \ - struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ - __MUTEX_INITIALIZER(name.mutex) }; \ - EXPORT_SYMBOL_GPL(name) +/* Caution: + * Reference to the module (obtained using btf_try_get_module) corresponding to + * the struct btf *MUST* be held when calling this function from verifier + * context. This is usually true as we stash references in prog's kfunc_btf_tab; + * keeping the reference for the duration of the call provides the necessary + * protection for looking up a well-formed btf->kfunc_set_tab. + */ +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id) +{ + enum btf_kfunc_hook hook; -DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); -DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + hook = bpf_prog_type_to_kfunc_hook(prog_type); + return __btf_kfunc_id_set_contains(btf, hook, type, kfunc_btf_id); +} -#endif +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *kset) +{ + enum btf_kfunc_hook hook; + struct btf *btf; + int ret; + + btf = btf_get_module_btf(kset->owner); + if (IS_ERR_OR_NULL(btf)) + return btf ? PTR_ERR(btf) : -ENOENT; + + hook = bpf_prog_type_to_kfunc_hook(prog_type); + ret = btf_populate_kfunc_set(btf, hook, kset); + /* reference is only taken for module BTF */ + if (btf_is_module(btf)) + btf_put(btf); + return ret; +} +EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 514b4681a90a..279ebbed75a5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1044,7 +1044,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr - * -EPERM - drop packet + * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. @@ -1079,8 +1079,9 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, cgrp->bpf.effective[atype], skb, __bpf_prog_run_save_cb); } else { ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb, - __bpf_prog_run_save_cb); - ret = (ret == 1 ? 0 : -EPERM); + __bpf_prog_run_save_cb, 0); + if (ret && !IS_ERR_VALUE((long)ret)) + ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); @@ -1107,10 +1108,9 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, bpf_prog_run); - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sk, + bpf_prog_run, 0); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -1142,7 +1142,6 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, }; struct sockaddr_storage unspec; struct cgroup *cgrp; - int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). @@ -1156,10 +1155,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run, flags); - - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG_FLAGS(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0, flags); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); @@ -1184,11 +1181,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - int ret; - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, - bpf_prog_run); - return ret == 1 ? 0 : -EPERM; + return BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], sock_ops, + bpf_prog_run, 0); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); @@ -1201,17 +1196,47 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, .major = major, .minor = minor, }; - int allow; + int ret; rcu_read_lock(); cgrp = task_dfl_cgroup(current); - allow = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, - bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0); rcu_read_unlock(); - return !allow; + return ret; } +BPF_CALL_0(bpf_get_retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + return ctx->retval; +} + +static const struct bpf_func_proto bpf_get_retval_proto = { + .func = bpf_get_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + +BPF_CALL_1(bpf_set_retval, int, retval) +{ + struct bpf_cg_run_ctx *ctx = + container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); + + ctx->retval = retval; + return 0; +} + +static const struct bpf_func_proto bpf_set_retval_proto = { + .func = bpf_set_retval, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1224,6 +1249,10 @@ cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; + case BPF_FUNC_get_retval: + return &bpf_get_retval_proto; + case BPF_FUNC_set_retval: + return &bpf_set_retval_proto; default: return bpf_base_func_proto(func_id); } @@ -1337,7 +1366,8 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, rcu_read_lock(); cgrp = task_dfl_cgroup(current); - ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, bpf_prog_run); + ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], &ctx, + bpf_prog_run, 0); rcu_read_unlock(); kfree(ctx.cur_val); @@ -1350,7 +1380,7 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, kfree(ctx.new_val); } - return ret == 1 ? 0 : -EPERM; + return ret; } #ifdef CONFIG_NET @@ -1452,13 +1482,11 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_SETSOCKOPT], - &ctx, bpf_prog_run); + &ctx, bpf_prog_run, 0); release_sock(sk); - if (!ret) { - ret = -EPERM; + if (ret) goto out; - } if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ @@ -1518,7 +1546,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, .sk = sk, .level = level, .optname = optname, - .retval = retval, + .current_task = current, }; int ret; @@ -1562,27 +1590,17 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, lock_sock(sk); ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); + &ctx, bpf_prog_run, retval); release_sock(sk); - if (!ret) { - ret = -EPERM; + if (ret < 0) goto out; - } if (ctx.optlen > max_optlen || ctx.optlen < 0) { ret = -EFAULT; goto out; } - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) { - ret = -EFAULT; - goto out; - } - if (ctx.optlen != 0) { if (copy_to_user(optval, ctx.optval, ctx.optlen) || put_user(ctx.optlen, optlen)) { @@ -1591,8 +1609,6 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, } } - ret = ctx.retval; - out: sockopt_free_buf(&ctx, &buf); return ret; @@ -1607,10 +1623,10 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, .sk = sk, .level = level, .optname = optname, - .retval = retval, .optlen = *optlen, .optval = optval, .optval_end = optval + *optlen, + .current_task = current, }; int ret; @@ -1623,25 +1639,19 @@ int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, */ ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[CGROUP_GETSOCKOPT], - &ctx, bpf_prog_run); - if (!ret) - return -EPERM; + &ctx, bpf_prog_run, retval); + if (ret < 0) + return ret; if (ctx.optlen > *optlen) return -EFAULT; - /* BPF programs only allowed to set retval to 0, not some - * arbitrary value. - */ - if (ctx.retval != 0 && ctx.retval != retval) - return -EFAULT; - /* BPF programs can shrink the buffer, export the modifications. */ if (ctx.optlen != 0) *optlen = ctx.optlen; - return ctx.retval; + return ret; } #endif @@ -2057,10 +2067,39 @@ static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen); break; case offsetof(struct bpf_sockopt, retval): - if (type == BPF_WRITE) - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval); - else - *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval); + BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); + + if (type == BPF_WRITE) { + int treg = BPF_REG_9; + + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + if (si->src_reg == treg || si->dst_reg == treg) + --treg; + *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg, + offsetof(struct bpf_sockopt_kern, tmp_reg)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + treg, si->dst_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + treg, treg, + offsetof(struct task_struct, bpf_ctx)); + *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + treg, si->src_reg, + offsetof(struct bpf_cg_run_ctx, retval)); + *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, + offsetof(struct bpf_sockopt_kern, tmp_reg)); + } else { + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sockopt_kern, current_task)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), + si->dst_reg, si->dst_reg, + offsetof(struct task_struct, bpf_ctx)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), + si->dst_reg, si->dst_reg, + offsetof(struct bpf_cg_run_ctx, retval)); + } break; case offsetof(struct bpf_sockopt, optval): *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index de3e5bc6781f..0a1cfd8544b9 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1829,28 +1829,30 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, } #endif -bool bpf_prog_array_compatible(struct bpf_array *array, - const struct bpf_prog *fp) +bool bpf_prog_map_compatible(struct bpf_map *map, + const struct bpf_prog *fp) { bool ret; if (fp->kprobe_override) return false; - spin_lock(&array->aux->owner.lock); - - if (!array->aux->owner.type) { + spin_lock(&map->owner.lock); + if (!map->owner.type) { /* There's no owner yet where we could check for * compatibility. */ - array->aux->owner.type = fp->type; - array->aux->owner.jited = fp->jited; + map->owner.type = fp->type; + map->owner.jited = fp->jited; + map->owner.xdp_has_frags = fp->aux->xdp_has_frags; ret = true; } else { - ret = array->aux->owner.type == fp->type && - array->aux->owner.jited == fp->jited; + ret = map->owner.type == fp->type && + map->owner.jited == fp->jited && + map->owner.xdp_has_frags == fp->aux->xdp_has_frags; } - spin_unlock(&array->aux->owner.lock); + spin_unlock(&map->owner.lock); + return ret; } @@ -1862,13 +1864,11 @@ static int bpf_check_tail_call(const struct bpf_prog *fp) mutex_lock(&aux->used_maps_mutex); for (i = 0; i < aux->used_map_cnt; i++) { struct bpf_map *map = aux->used_maps[i]; - struct bpf_array *array; - if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) + if (!map_type_contains_progs(map)) continue; - array = container_of(map, struct bpf_array, map); - if (!bpf_prog_array_compatible(array, fp)) { + if (!bpf_prog_map_compatible(map, fp)) { ret = -EINVAL; goto out; } diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index b3e6b9422238..650e5d21f90d 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -397,7 +397,8 @@ static int cpu_map_kthread_run(void *data) return 0; } -static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) +static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, + struct bpf_map *map, int fd) { struct bpf_prog *prog; @@ -405,7 +406,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->expected_attach_type != BPF_XDP_CPUMAP) { + if (prog->expected_attach_type != BPF_XDP_CPUMAP || + !bpf_prog_map_compatible(map, prog)) { bpf_prog_put(prog); return -EINVAL; } @@ -457,7 +459,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, rcpu->map_id = map->id; rcpu->value.qsize = value->qsize; - if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd)) + if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd)) goto free_ptr_ring; /* Setup kthread */ diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index fe019dbdb3f0..038f6d7a83e4 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -858,7 +858,8 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, BPF_PROG_TYPE_XDP, false); if (IS_ERR(prog)) goto err_put_dev; - if (prog->expected_attach_type != BPF_XDP_DEVMAP) + if (prog->expected_attach_type != BPF_XDP_DEVMAP || + !bpf_prog_map_compatible(&dtab->map, prog)) goto err_put_prog; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 638d7fd7b375..710ba9de12ce 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -104,7 +104,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, - VM_ALLOC | VM_USERMAP, PAGE_KERNEL); + VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 49e567209c6b..22c8ae94e4c1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -472,13 +472,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; - long res; + long res = -EINVAL; if (!try_get_task_stack(task)) return -EFAULT; regs = task_pt_regs(task); - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (regs) + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task); return res; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fa4505f9b611..72ce1edde950 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -556,16 +556,14 @@ static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { - const struct bpf_map *map = filp->private_data; - const struct bpf_array *array; + struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; - if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) { - array = container_of(map, struct bpf_array, map); - spin_lock(&array->aux->owner.lock); - type = array->aux->owner.type; - jited = array->aux->owner.jited; - spin_unlock(&array->aux->owner.lock); + if (map_type_contains_progs(map)) { + spin_lock(&map->owner.lock); + type = map->owner.type; + jited = map->owner.jited; + spin_unlock(&map->owner.lock); } seq_printf(m, @@ -874,6 +872,7 @@ static int map_create(union bpf_attr *attr) atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); + spin_lock_init(&map->owner.lock); map->spin_lock_off = -EINVAL; map->timer_off = -EINVAL; @@ -2217,7 +2216,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | - BPF_F_TEST_RND_HI32)) + BPF_F_TEST_RND_HI32 | + BPF_F_XDP_HAS_FRAGS)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2303,6 +2303,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; + prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; err = security_bpf_prog_alloc(prog->aux); if (err) @@ -3318,6 +3319,11 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); + case BPF_SK_SKB_STREAM_PARSER: + case BPF_SK_SKB_STREAM_VERDICT: + case BPF_SK_MSG_VERDICT: + case BPF_SK_SKB_VERDICT: + return sock_map_bpf_prog_query(attr, uattr); default: return -EINVAL; } diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 4b6974a195c1..5e7edf913060 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -550,11 +550,12 @@ static __always_inline u64 notrace bpf_prog_start_time(void) static void notrace inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; + unsigned int flags; stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); - u64_stats_update_end(&stats->syncp); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } /* The logic is similar to bpf_prog_run(), but with an explicit diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a39eedecc93a..dcf065ec2774 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -452,7 +452,8 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { return base_type(type) == PTR_TO_SOCKET || base_type(type) == PTR_TO_TCP_SOCK || - base_type(type) == PTR_TO_MEM; + base_type(type) == PTR_TO_MEM || + base_type(type) == PTR_TO_BTF_ID; } static bool type_is_rdonly_mem(u32 type) @@ -1743,7 +1744,7 @@ find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) } static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, - s16 offset, struct module **btf_modp) + s16 offset) { struct bpf_kfunc_btf kf_btf = { .offset = offset }; struct bpf_kfunc_btf_tab *tab; @@ -1797,8 +1798,6 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); } - if (btf_modp) - *btf_modp = b->module; return b->btf; } @@ -1815,8 +1814,7 @@ void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) } static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, - u32 func_id, s16 offset, - struct module **btf_modp) + u32 func_id, s16 offset) { if (offset) { if (offset < 0) { @@ -1827,7 +1825,7 @@ static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, return ERR_PTR(-EINVAL); } - return __find_kfunc_desc_btf(env, offset, btf_modp); + return __find_kfunc_desc_btf(env, offset); } return btf_vmlinux ?: ERR_PTR(-ENOENT); } @@ -1890,7 +1888,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) prog_aux->kfunc_btf_tab = btf_tab; } - desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL); + desc_btf = find_kfunc_desc_btf(env, func_id, offset); if (IS_ERR(desc_btf)) { verbose(env, "failed to find BTF for kernel function\n"); return PTR_ERR(desc_btf); @@ -2351,7 +2349,7 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; - desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL); + desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off); if (IS_ERR(desc_btf)) return "<error>"; @@ -3498,11 +3496,6 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, #define MAX_PACKET_OFF 0xffff -static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) -{ - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; -} - static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, const struct bpf_call_arg_meta *meta, enum bpf_access_type t) @@ -4877,6 +4870,62 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +static int check_mem_size_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + bool zero_size_allowed, + struct bpf_call_arg_meta *meta) +{ + int err; + + /* This is used to refine r0 return value bounds for helpers + * that enforce this value as an upper bound on return values. + * See do_refine_retval_range() for helpers that can refine + * the return value. C type of helper is u32 so we pull register + * bound from umax_value however, if negative verifier errors + * out. Only upper bounds can be learned because retval is an + * int type and negative retvals are allowed. + */ + if (meta) + meta->msize_max_value = reg->umax_value; + + /* The register is SCALAR_VALUE; the access check + * happens using its boundaries. + */ + if (!tnum_is_const(reg->var_off)) + /* For unprivileged variable accesses, disable raw + * mode so that the program is required to + * initialize all the memory that the helper could + * just partially fill up. + */ + meta = NULL; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", + regno); + return -EACCES; + } + + if (reg->umin_value == 0) { + err = check_helper_mem_access(env, regno - 1, 0, + zero_size_allowed, + meta); + if (err) + return err; + } + + if (reg->umax_value >= BPF_MAX_VAR_SIZ) { + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + regno); + return -EACCES; + } + err = check_helper_mem_access(env, regno - 1, + reg->umax_value, + zero_size_allowed, meta); + if (!err) + err = mark_chain_precision(env, regno); + return err; +} + int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { @@ -4900,6 +4949,28 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return check_helper_mem_access(env, regno, mem_size, true, NULL); } +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) +{ + struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; + bool may_be_null = type_may_be_null(mem_reg->type); + struct bpf_reg_state saved_reg; + int err; + + WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); + + if (may_be_null) { + saved_reg = *mem_reg; + mark_ptr_not_null_reg(mem_reg); + } + + err = check_mem_size_reg(env, reg, regno, true, NULL); + + if (may_be_null) + *mem_reg = saved_reg; + return err; +} + /* Implementation details: * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL * Two bpf_map_lookups (even with the same key) will have different reg->id. @@ -5439,51 +5510,7 @@ skip_type_check: } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - /* This is used to refine r0 return value bounds for helpers - * that enforce this value as an upper bound on return values. - * See do_refine_retval_range() for helpers that can refine - * the return value. C type of helper is u32 so we pull register - * bound from umax_value however, if negative verifier errors - * out. Only upper bounds can be learned because retval is an - * int type and negative retvals are allowed. - */ - meta->msize_max_value = reg->umax_value; - - /* The register is SCALAR_VALUE; the access check - * happens using its boundaries. - */ - if (!tnum_is_const(reg->var_off)) - /* For unprivileged variable accesses, disable raw - * mode so that the program is required to - * initialize all the memory that the helper could - * just partially fill up. - */ - meta = NULL; - - if (reg->smin_value < 0) { - verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", - regno); - return -EACCES; - } - - if (reg->umin_value == 0) { - err = check_helper_mem_access(env, regno - 1, 0, - zero_size_allowed, - meta); - if (err) - return err; - } - - if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", - regno); - return -EACCES; - } - err = check_helper_mem_access(env, regno - 1, - reg->umax_value, - zero_size_allowed, meta); - if (!err) - err = mark_chain_precision(env, regno); + err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta); } else if (arg_type_is_alloc_size(arg_type)) { if (!tnum_is_const(reg->var_off)) { verbose(env, "R%d is not a known constant'\n", @@ -6842,22 +6869,23 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } -static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) +static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; u32 i, nargs, func_id, ptr_type_id; - struct module *btf_mod = NULL; + int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; - int err; + bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) return 0; - desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod); + desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off); if (IS_ERR(desc_btf)) return PTR_ERR(desc_btf); @@ -6866,23 +6894,43 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) func_name = btf_name_by_offset(desc_btf, func->name_off); func_proto = btf_type_by_id(desc_btf, func->type); - if (!env->ops->check_kfunc_call || - !env->ops->check_kfunc_call(func_id, btf_mod)) { + if (!btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_CHECK, func_id)) { verbose(env, "calling kernel function %s is not allowed\n", func_name); return -EACCES; } + acq = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_ACQUIRE, func_id); + /* Check the arguments */ err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs); - if (err) + if (err < 0) return err; + /* In case of release function, we get register number of refcounted + * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now + */ + if (err) { + err = release_reference(env, regs[err].ref_obj_id); + if (err) { + verbose(env, "kfunc %s#%d reference has not been acquired before\n", + func_name, func_id); + return err; + } + } for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); + + if (acq && !btf_type_is_ptr(t)) { + verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); + return -EINVAL; + } + if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); @@ -6901,7 +6949,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; + if (btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), + BTF_KFUNC_TYPE_RET_NULL, func_id)) { + regs[BPF_REG_0].type |= PTR_MAYBE_NULL; + /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ + regs[BPF_REG_0].id = ++env->id_gen; + } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); + if (acq) { + int id = acquire_reference_state(env, insn_idx); + + if (id < 0) + return id; + regs[BPF_REG_0].id = id; + regs[BPF_REG_0].ref_obj_id = id; + } } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); @@ -11549,7 +11611,7 @@ static int do_check(struct bpf_verifier_env *env) if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) - err = check_kfunc_call(env, insn); + err = check_kfunc_call(env, insn, &env->insn_idx); else err = check_helper_call(env, insn, &env->insn_idx); if (err) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 41e0837a5a0b..0e877dbcfeea 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -549,6 +549,14 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((of->file->f_cred->user_ns != &init_user_ns) || + !capable(CAP_SYS_ADMIN)) + return -EPERM; + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; @@ -954,6 +962,12 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) + return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b31e1465868a..9d05c3ca2d5e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { @@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&ctx->psi.trigger, new); - + smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; @@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; - psi_trigger_replace(&ctx->psi.trigger, NULL); + psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dc653ab26e50..4c7254e8f49a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -591,6 +591,35 @@ static inline void free_cpuset(struct cpuset *cs) } /* + * validate_change_legacy() - Validate conditions specific to legacy (v1) + * behavior. + */ +static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + /* Each of our child cpusets must be a subset of us */ + ret = -EBUSY; + cpuset_for_each_child(c, css, cur) + if (!is_cpuset_subset(c, trial)) + goto out; + + /* On legacy hierarchy, we must be a subset of our parent cpuset. */ + ret = -EACCES; + par = parent_cs(cur); + if (par && !is_cpuset_subset(trial, par)) + goto out; + + ret = 0; +out: + return ret; +} + +/* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * @@ -614,20 +643,21 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; - int ret; - - /* The checks don't apply to root cpuset */ - if (cur == &top_cpuset) - return 0; + int ret = 0; rcu_read_lock(); - par = parent_cs(cur); - /* On legacy hierarchy, we must be a subset of our parent cpuset. */ - ret = -EACCES; - if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) + if (!is_in_v2_mode()) + ret = validate_change_legacy(cur, trial); + if (ret) + goto out; + + /* Remaining checks don't apply to root cpuset */ + if (cur == &top_cpuset) goto out; + par = parent_cs(cur); + /* * If either I or some sibling (!= me) is exclusive, we can't * overlap @@ -1175,9 +1205,7 @@ enum subparts_cmd { * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be - * permitted when checked by validate_change(). The validate_change() - * function will also prevent any changes to the cpu list if it is not - * a superset of children's cpu lists. + * permitted when checked by validate_change(). */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, @@ -1522,10 +1550,15 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; + percpu_rwsem_assert_held(&cpuset_rwsem); + /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. + * + * The update_cpumasks_hier() function may sleep. So we have to + * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { @@ -1533,8 +1566,13 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, continue; if (!sibling->use_parent_ecpus) continue; + if (!css_tryget_online(&sibling->css)) + continue; + rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); + rcu_read_lock(); + css_put(&sibling->css); } rcu_read_unlock(); } @@ -1607,8 +1645,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { - cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus, - cs->cpus_allowed); + cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); diff --git a/kernel/events/core.c b/kernel/events/core.c index fc18664f49b0..76c754e45d01 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -674,6 +674,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) WRITE_ONCE(event->state, state); } +/* + * UP store-release, load-acquire + */ + +#define __store_release(ptr, val) \ +do { \ + barrier(); \ + WRITE_ONCE(*(ptr), (val)); \ +} while (0) + +#define __load_acquire(ptr) \ +({ \ + __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ + barrier(); \ + ___p; \ +}) + #ifdef CONFIG_CGROUP_PERF static inline bool @@ -719,34 +736,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return t->time; } -static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { - struct perf_cgroup_info *info; - u64 now; - - now = perf_clock(); + struct perf_cgroup_info *t; - info = this_cpu_ptr(cgrp->info); + t = per_cpu_ptr(event->cgrp->info, event->cpu); + if (!__load_acquire(&t->active)) + return t->time; + now += READ_ONCE(t->timeoffset); + return now; +} - info->time += now - info->timestamp; +static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) +{ + if (adv) + info->time += now - info->timestamp; info->timestamp = now; + /* + * see update_context_time() + */ + WRITE_ONCE(info->timeoffset, info->time - info->timestamp); } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; + struct perf_cgroup_info *info; if (cgrp) { + u64 now = perf_clock(); + for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); - __update_cgrp_time(cgrp); + info = this_cpu_ptr(cgrp->info); + + __update_cgrp_time(info, now, true); + if (final) + __store_release(&info->active, 0); } } } static inline void update_cgrp_time_from_event(struct perf_event *event) { + struct perf_cgroup_info *info; struct perf_cgroup *cgrp; /* @@ -760,8 +794,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - __update_cgrp_time(event->cgrp); + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { + info = this_cpu_ptr(event->cgrp->info); + __update_cgrp_time(info, perf_clock(), true); + } } static inline void @@ -785,7 +821,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + __update_cgrp_time(info, ctx->timestamp, false); + __store_release(&info->active, 1); } } @@ -982,14 +1019,6 @@ out: } static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) -{ - struct perf_cgroup_info *t; - t = per_cpu_ptr(event->cgrp->info, event->cpu); - event->shadow_ctx_time = now - t->timestamp; -} - -static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; @@ -1066,7 +1095,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) { } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, + bool final) { } @@ -1098,12 +1128,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } -static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +static inline u64 perf_cgroup_event_time(struct perf_event *event) { + return 0; } -static inline u64 perf_cgroup_event_time(struct perf_event *event) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } @@ -1525,22 +1555,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) /* * Update the record of the current time in a context. */ -static void update_context_time(struct perf_event_context *ctx) +static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock(); - ctx->time += now - ctx->timestamp; + if (adv) + ctx->time += now - ctx->timestamp; ctx->timestamp = now; + + /* + * The above: time' = time + (now - timestamp), can be re-arranged + * into: time` = now + (time - timestamp), which gives a single value + * offset to compute future time without locks on. + * + * See perf_event_time_now(), which can be used from NMI context where + * it's (obviously) not possible to acquire ctx->lock in order to read + * both the above values in a consistent manner. + */ + WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); +} + +static void update_context_time(struct perf_event_context *ctx) +{ + __update_context_time(ctx, true); } static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; + if (unlikely(!ctx)) + return 0; + if (is_cgroup_event(event)) return perf_cgroup_event_time(event); - return ctx ? ctx->time : 0; + return ctx->time; +} + +static u64 perf_event_time_now(struct perf_event *event, u64 now) +{ + struct perf_event_context *ctx = event->ctx; + + if (unlikely(!ctx)) + return 0; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time_now(event, now); + + if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) + return ctx->time; + + now += READ_ONCE(ctx->timeoffset); + return now; } static enum event_type_t get_event_type(struct perf_event *event) @@ -2350,7 +2417,7 @@ __perf_remove_from_context(struct perf_event *event, if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, false); } event_sched_out(event, cpuctx, ctx); @@ -2361,6 +2428,9 @@ __perf_remove_from_context(struct perf_event *event, list_del_event(event, ctx); if (!ctx->nr_events && ctx->is_active) { + if (ctx == &cpuctx->ctx) + update_cgrp_time_from_cpuctx(cpuctx, true); + ctx->is_active = 0; ctx->rotate_necessary = 0; if (ctx->task) { @@ -2392,7 +2462,11 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla * event_function_call() user. */ raw_spin_lock_irq(&ctx->lock); - if (!ctx->is_active) { + /* + * Cgroup events are per-cpu events, and must IPI because of + * cgrp_cpuctx_list. + */ + if (!ctx->is_active && !is_cgroup_event(event)) { __perf_remove_from_context(event, __get_cpu_context(ctx), ctx, (void *)flags); raw_spin_unlock_irq(&ctx->lock); @@ -2482,40 +2556,6 @@ void perf_event_disable_inatomic(struct perf_event *event) irq_work_queue(&event->pending); } -static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx) -{ - /* - * use the correct time source for the time snapshot - * - * We could get by without this by leveraging the - * fact that to get to this function, the caller - * has most likely already called update_context_time() - * and update_cgrp_time_xx() and thus both timestamp - * are identical (or very close). Given that tstamp is, - * already adjusted for cgroup, we could say that: - * tstamp - ctx->timestamp - * is equivalent to - * tstamp - cgrp->timestamp. - * - * Then, in perf_output_read(), the calculation would - * work with no changes because: - * - event is guaranteed scheduled in - * - no scheduled out in between - * - thus the timestamp would be the same - * - * But this is a bit hairy. - * - * So instead, we have an explicit cgroup call to remain - * within the time source all along. We believe it - * is cleaner and simpler to understand. - */ - if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, event->tstamp); - else - event->shadow_ctx_time = event->tstamp - ctx->timestamp; -} - #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); @@ -2556,8 +2596,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - perf_set_shadow_time(event, ctx); - perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { @@ -2861,11 +2899,14 @@ perf_install_in_context(struct perf_event_context *ctx, * perf_event_attr::disabled events will not run and can be initialized * without IPI. Except when this is the first event for the context, in * that case we need the magic of the IPI to set ctx->is_active. + * Similarly, cgroup events for the context also needs the IPI to + * manipulate the cgrp_cpuctx_list. * * The IOC_ENABLE that is sure to follow the creation of a disabled * event will issue the IPI and reprogram the hardware. */ - if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && ctx->nr_events) { + if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && + ctx->nr_events && !is_cgroup_event(event)) { raw_spin_lock_irq(&ctx->lock); if (ctx->task == TASK_TOMBSTONE) { raw_spin_unlock_irq(&ctx->lock); @@ -3251,16 +3292,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, return; } - ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - - if (ctx->task) { - WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) - cpuctx->task_ctx = NULL; - } - /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last @@ -3274,7 +3305,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ @@ -3711,13 +3757,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +/* + * Because the userpage is strictly per-event (there is no concept of context, + * so there cannot be a context indirection), every userpage must be updated + * when context time starts :-( + * + * IOW, we must not miss EVENT_TIME edges. + */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false; perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_update_userpage(event); return true; @@ -3801,13 +3853,23 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { int is_active = ctx->is_active; - u64 now; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) return; + if (is_active ^ EVENT_TIME) { + /* start ctx time */ + __update_context_time(ctx, false); + perf_cgroup_set_timestamp(task, ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) @@ -3818,13 +3880,6 @@ ctx_sched_in(struct perf_event_context *ctx, is_active ^= ctx->is_active; /* changed bits */ - if (is_active & EVENT_TIME) { - /* start ctx time */ - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); - } - /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -4418,6 +4473,18 @@ static inline u64 perf_event_count(struct perf_event *event) return local64_read(&event->count) + atomic64_read(&event->child_count); } +static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = perf_event_time_now(event, *now); + __perf_update_times(event, ctx_time, enabled, running); +} + /* * NMI-safe method to read a local event, that is an event that * is: @@ -4477,10 +4544,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value, *value = local64_read(&event->count); if (enabled || running) { - u64 now = event->shadow_ctx_time + perf_clock(); - u64 __enabled, __running; + u64 __enabled, __running, __now;; - __perf_update_times(event, now, &__enabled, &__running); + calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) @@ -5802,18 +5868,6 @@ static int perf_event_index(struct perf_event *event) return event->pmu->event_idx(event); } -static void calc_timer_values(struct perf_event *event, - u64 *now, - u64 *enabled, - u64 *running) -{ - u64 ctx_time; - - *now = perf_clock(); - ctx_time = event->shadow_ctx_time + *now; - __perf_update_times(event, ctx_time, enabled, running); -} - static void perf_event_init_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; @@ -5938,6 +5992,8 @@ static void ring_buffer_attach(struct perf_event *event, struct perf_buffer *old_rb = NULL; unsigned long flags; + WARN_ON_ONCE(event->parent); + if (event->rb) { /* * Should be impossible, we set this when removing @@ -5995,6 +6051,9 @@ static void ring_buffer_wakeup(struct perf_event *event) { struct perf_buffer *rb; + if (event->parent) + event = event->parent; + rcu_read_lock(); rb = rcu_dereference(event->rb); if (rb) { @@ -6008,6 +6067,9 @@ struct perf_buffer *ring_buffer_get(struct perf_event *event) { struct perf_buffer *rb; + if (event->parent) + event = event->parent; + rcu_read_lock(); rb = rcu_dereference(event->rb); if (rb) { @@ -6353,7 +6415,6 @@ accounting: ring_buffer_attach(event, rb); perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { @@ -6717,7 +6778,7 @@ static unsigned long perf_prepare_sample_aux(struct perf_event *event, if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id())) goto out; - rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + rb = ring_buffer_get(sampler); if (!rb) goto out; @@ -6783,7 +6844,7 @@ static void perf_aux_sample_output(struct perf_event *event, if (WARN_ON_ONCE(!sampler || !data->aux_size)) return; - rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + rb = ring_buffer_get(sampler); if (!rb) return; diff --git a/kernel/module.c b/kernel/module.c index 24dab046e16c..46a5c2ed1928 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3725,12 +3725,6 @@ static noinline int do_init_module(struct module *mod) } freeinit->module_init = mod->init_layout.base; - /* - * We want to find out whether @mod uses async during init. Clear - * PF_USED_ASYNC. async_schedule*() will set it. - */ - current->flags &= ~PF_USED_ASYNC; - do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) @@ -3756,22 +3750,13 @@ static noinline int do_init_module(struct module *mod) /* * We need to finish all async code before the module init sequence - * is done. This has potential to deadlock. For example, a newly - * detected block device can trigger request_module() of the - * default iosched from async probing task. Once userland helper - * reaches here, async_synchronize_full() will wait on the async - * task waiting on request_module() and deadlock. - * - * This deadlock is avoided by perfomring async_synchronize_full() - * iff module init queued any async jobs. This isn't a full - * solution as it will deadlock the same if module loading from - * async jobs nests more than once; however, due to the various - * constraints, this hack seems to be the best option for now. - * Please refer to the following thread for details. + * is done. This has potential to deadlock if synchronous module + * loading is requested from async (which is not allowed!). * - * http://thread.gmane.org/gmane.linux.kernel/1420814 + * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous + * request_module() from async workers") for more details. */ - if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC)) + if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f7a986078213..330d49937692 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -978,8 +978,7 @@ static void memory_bm_recycle(struct memory_bitmap *bm) * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ -void __init __register_nosave_region(unsigned long start_pfn, - unsigned long end_pfn, int use_kmalloc) +void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; @@ -995,18 +994,12 @@ void __init __register_nosave_region(unsigned long start_pfn, goto Report; } } - if (use_kmalloc) { - /* During init, this shouldn't fail */ - region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); - BUG_ON(!region); - } else { - /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), - SMP_CACHE_BYTES); - if (!region) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct nosave_region)); - } + /* This allocation cannot fail */ + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); + if (!region) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 105df4dfc783..52571dcad768 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -39,23 +39,20 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) { struct rb_node *node; struct wakelock *wl; - char *str = buf; - char *end = buf + PAGE_SIZE; + int len = 0; mutex_lock(&wakelocks_lock); for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); if (wl->ws->active == show_active) - str += scnprintf(str, end - str, "%s ", wl->name); + len += sysfs_emit_at(buf, len, "%s ", wl->name); } - if (str > buf) - str--; - str += scnprintf(str, end - str, "\n"); + len += sysfs_emit_at(buf, len, "\n"); mutex_unlock(&wakelocks_lock); - return (str - buf); + return len; } #if CONFIG_PM_WAKELOCKS_LIMIT > 0 diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index 653ae04aab7f..c228343eeb97 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -12,7 +12,7 @@ static const int ten_thousand = 10000; static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 84f1d91604cc..d64f0b1d8cd3 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -123,7 +123,7 @@ static struct rcu_tasks rt_name = \ .call_func = call, \ .rtpcpu = &rt_name ## __percpu, \ .name = n, \ - .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS), \ + .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS) + 1, \ .percpu_enqueue_lim = 1, \ .percpu_dequeue_lim = 1, \ .barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex), \ @@ -216,6 +216,7 @@ static void cblist_init_generic(struct rcu_tasks *rtp) int cpu; unsigned long flags; int lim; + int shift; raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rcu_task_enqueue_lim < 0) { @@ -229,7 +230,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (lim > nr_cpu_ids) lim = nr_cpu_ids; - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids / lim)); + shift = ilog2(nr_cpu_ids / lim); + if (((nr_cpu_ids - 1) >> shift) >= lim) + shift++; + WRITE_ONCE(rtp->percpu_enqueue_shift, shift); WRITE_ONCE(rtp->percpu_dequeue_lim, lim); smp_store_release(&rtp->percpu_enqueue_lim, lim); for_each_possible_cpu(cpu) { @@ -298,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, if (unlikely(needadjust)) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim != nr_cpu_ids) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1); WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids); smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids); pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name); @@ -413,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim > 1) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2e4ae00e52d1..848eaa0efe0e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5822,8 +5822,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } if (schedstat_enabled() && rq->core->core_forceidle_count) { - if (cookie) - rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_start = rq_clock(rq->core); rq->core->core_forceidle_occupation = occ; } @@ -8219,9 +8218,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; spin_lock(lock); @@ -8239,9 +8236,7 @@ int __cond_resched_rwlock_read(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { read_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; read_lock(lock); @@ -8259,9 +8254,7 @@ int __cond_resched_rwlock_write(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { write_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; write_lock(lock); diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 1fb45672ec85..c8746a9a7ada 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -277,7 +277,7 @@ void __sched_core_account_forceidle(struct rq *rq) rq_i = cpu_rq(i); p = rq_i->core_pick ?: rq_i->curr; - if (!p->core_cookie) + if (p == rq_i->idle) continue; __schedstat_add(p->stats.core_forceidle_sum, delta); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 095b0aa378df..5146163bfabb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3028,9 +3028,11 @@ enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u32 divider = get_pelt_divider(&se->avg); sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } #else static inline void @@ -3381,7 +3383,6 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; } - /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3449,15 +3450,14 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3466,23 +3466,30 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq */ divider = get_pelt_divider(&cfs_rq->avg); + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; - se->avg.util_sum = se->avg.util_avg * divider; + new_sum = se->avg.util_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.util_sum; + se->avg.util_sum = new_sum; /* Update parent cfs_rq utilization */ - add_positive(&cfs_rq->avg.util_avg, delta); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + add_positive(&cfs_rq->avg.util_avg, delta_avg); + add_positive(&cfs_rq->avg.util_sum, delta_sum); + + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3493,19 +3500,25 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* Set new sched_entity's runnable */ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg; - se->avg.runnable_sum = se->avg.runnable_avg * divider; + new_sum = se->avg.runnable_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.runnable_sum; + se->avg.runnable_sum = new_sum; /* Update parent cfs_rq runnable */ - add_positive(&cfs_rq->avg.runnable_avg, delta); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + add_positive(&cfs_rq->avg.runnable_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; + s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3532,7 +3545,7 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq * assuming all tasks are equally runnable. */ if (scale_load_down(gcfs_rq->load.weight)) { - load_sum = div_s64(gcfs_rq->avg.load_sum, + load_sum = div_u64(gcfs_rq->avg.load_sum, scale_load_down(gcfs_rq->load.weight)); } @@ -3549,19 +3562,22 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); - load_sum = (s64)se_weight(se) * runnable_sum; - load_avg = div_s64(load_sum, divider); - - se->avg.load_sum = runnable_sum; + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); - delta = load_avg - se->avg.load_avg; - if (!delta) + delta_avg = load_avg - se->avg.load_avg; + if (!delta_avg) return; - se->avg.load_avg = load_avg; + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - add_positive(&cfs_rq->avg.load_avg, delta); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3652,7 +3668,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum * * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. * - * Returns true if the load decayed or we removed load. + * Return: true if the load decayed or we removed load. * * Since both these conditions indicate a changed cfs_rq->avg.load we should * call update_tg_load_avg() when this function returns true. @@ -3677,15 +3693,32 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sa->load_sum = sa->load_avg * divider; + sub_positive(&sa->load_sum, r * divider); + /* See sa->util_sum below */ + sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER); r = removed_util; sub_positive(&sa->util_avg, r); - sa->util_sum = sa->util_avg * divider; + sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sa->runnable_sum = sa->runnable_avg * divider; + sub_positive(&sa->runnable_sum, r * divider); + /* See sa->util_sum above */ + sa->runnable_sum = max_t(u32, sa->runnable_sum, + sa->runnable_avg * PELT_MIN_DIVIDER); /* * removed_runnable is the unweighted version of removed_load so we @@ -3772,17 +3805,18 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - /* - * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. - * See ___update_load_avg() for details. - */ - u32 divider = get_pelt_divider(&cfs_rq->avg); - dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); + sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -8539,6 +8573,8 @@ group_type group_classify(unsigned int imbalance_pct, * * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings * of @dst_cpu are idle and @sg has lower priority. + * + * Return: true if @dst_cpu can pull tasks, false otherwise. */ static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, @@ -8614,6 +8650,7 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. + * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. * @sg_status: Holds flag indicating the status of the sched_group @@ -9421,12 +9458,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. + * @env: The load balancing environment. * * Also calculates the amount of runnable load which should be moved * to restore balance. * - * @env: The load balancing environment. - * * Return: - The busiest group if imbalance exists. */ static struct sched_group *find_busiest_group(struct lb_env *env) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index b5add64d9698..3d2825408e3a 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -147,11 +147,11 @@ #endif #ifdef CONFIG_RSEQ -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \ +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ) #else -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 #endif #define MEMBARRIER_CMD_BITMASK \ @@ -159,7 +159,8 @@ | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ - | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) static void ipi_mb(void *info) { diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index e06071bf3472..c336f5f481bc 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif +#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) + static inline u32 get_pelt_divider(struct sched_avg *avg) { - return LOAD_AVG_MAX - 1024 + avg->period_contrib; + return PELT_MIN_DIVIDER + avg->period_contrib; } static inline void cfs_se_util_change(struct sched_avg *avg) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..e14358178849 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1082,44 +1082,6 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -static int psi_io_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_IO); -} - -static int psi_memory_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_MEM); -} - -static int psi_cpu_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_CPU); -} - -static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) -{ - if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return single_open(file, psi_show, NULL); -} - -static int psi_io_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_io_show); -} - -static int psi_memory_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_memory_show); -} - -static int psi_cpu_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_cpu_show); -} - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res) { @@ -1162,7 +1124,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1152,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1200,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1219,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,27 +1228,57 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } +#ifdef CONFIG_PROC_FS +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) +{ + if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + return single_open(file, psi_show, NULL); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_io_show); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_memory_show); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_cpu_show); +} + static ssize_t psi_write(struct file *file, const char __user *user_buf, size_t nbytes, enum psi_res res) { @@ -1316,14 +1299,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1351,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } @@ -1400,3 +1393,5 @@ static int __init psi_proc_init(void) return 0; } module_init(psi_proc_init); + +#endif /* CONFIG_PROC_FS */ diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 66b8af394e58..ddb5a7f48d69 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -70,7 +70,7 @@ late_initcall(stackleak_sysctls_init); #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void notrace stackleak_erase(void) +asmlinkage void noinstr stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -124,9 +124,8 @@ asmlinkage void notrace stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } -NOKPROBE_SYMBOL(stackleak_erase); -void __used __no_caller_saved_registers notrace stackleak_track_stack(void) +void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) { unsigned long sp = current_stack_pointer; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 752ed89a293b..a5eb5e7fd624 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -70,10 +70,16 @@ config HAVE_C_RECORDMCOUNT help C version of recordmcount available? +config HAVE_BUILDTIME_MCOUNT_SORT + bool + help + An architecture selects this if it sorts the mcount_loc section + at build time. + config BUILDTIME_MCOUNT_SORT bool default y - depends on BUILDTIME_TABLE_SORT && !S390 + depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE help Sort the mcount_loc section at build time. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 21aa30644219..06a9e220069e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1562,6 +1562,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { extern const struct bpf_func_proto bpf_skb_output_proto; extern const struct bpf_func_proto bpf_xdp_output_proto; +extern const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1661,6 +1662,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sock_from_file_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_trace_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a569a0cb81ee..c860f582b078 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7740,7 +7740,8 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) err = ERR_PTR(-ENOMEM); - tr->n_err_log_entries++; + else + tr->n_err_log_entries++; return err; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5e6a988a8a51..ada87bfb5bb8 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2503,6 +2503,8 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data, (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS); expr->fn = hist_field_unary_minus; expr->operands[0] = operand1; + expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = FIELD_OP_UNARY_MINUS; expr->name = expr_str(expr, 0); expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -2719,6 +2721,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, /* The operand sizes should be the same, so just pick one */ expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = field_op; expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -3935,6 +3938,7 @@ static int trace_action_create(struct hist_trigger_data *hist_data, var_ref_idx = find_var_ref_idx(hist_data, var_ref); if (WARN_ON(var_ref_idx < 0)) { + kfree(p); ret = var_ref_idx; goto err; } @@ -6163,7 +6167,9 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, lockdep_assert_held(&event_mutex); - if (glob && strlen(glob)) { + WARN_ON(!glob); + + if (strlen(glob)) { hist_err_clear(); last_cmd_set(file, param); } @@ -6196,7 +6202,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, continue; } break; - } while (p); + } while (1); if (!p) param = NULL; diff --git a/kernel/ucount.c b/kernel/ucount.c index 7b32c356ebc5..65b597431c86 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -190,6 +190,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) kfree(new); } else { hlist_add_head(&new->node, hashent); + get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } @@ -210,6 +211,7 @@ void put_ucounts(struct ucounts *ucounts) if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); + put_user_ns(ucounts->ns); kfree(ucounts); } } diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index a6789c0c626b..dc7b14aa3431 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -20,6 +20,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) unsigned long flags; bool leak = false; + dir->dead = true; spin_lock_irqsave(&dir->lock, flags); list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { list_del(&tracker->head); @@ -37,6 +38,7 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir) spin_unlock_irqrestore(&dir->lock, flags); WARN_ON_ONCE(leak); WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); + WARN_ON_ONCE(refcount_read(&dir->no_tracker) != 1); } EXPORT_SYMBOL(ref_tracker_dir_exit); @@ -72,6 +74,12 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir, gfp_t gfp_mask = gfp; unsigned long flags; + WARN_ON_ONCE(dir->dead); + + if (!trackerp) { + refcount_inc(&dir->no_tracker); + return 0; + } if (gfp & __GFP_DIRECT_RECLAIM) gfp_mask |= __GFP_NOFAIL; *trackerp = tracker = kzalloc(sizeof(*tracker), gfp_mask); @@ -81,7 +89,6 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir, return -ENOMEM; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); - nr_entries = filter_irq_stacks(entries, nr_entries); tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); spin_lock_irqsave(&dir->lock, flags); @@ -95,17 +102,23 @@ int ref_tracker_free(struct ref_tracker_dir *dir, struct ref_tracker **trackerp) { unsigned long entries[REF_TRACKER_STACK_ENTRIES]; - struct ref_tracker *tracker = *trackerp; depot_stack_handle_t stack_handle; + struct ref_tracker *tracker; unsigned int nr_entries; unsigned long flags; + WARN_ON_ONCE(dir->dead); + + if (!trackerp) { + refcount_dec(&dir->no_tracker); + return 0; + } + tracker = *trackerp; if (!tracker) { refcount_dec(&dir->untracked); return -EEXIST; } nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); - nr_entries = filter_irq_stacks(entries, nr_entries); stack_handle = stack_depot_save(entries, nr_entries, GFP_ATOMIC); spin_lock_irqsave(&dir->lock, flags); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 6220fa67fb7e..09d293c30fd2 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -488,9 +488,13 @@ void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, unsigned int users) { unsigned int wake_batch; + unsigned int min_batch; + unsigned int depth = (sbq->sb.depth + users - 1) / users; - wake_batch = clamp_val((sbq->sb.depth + users - 1) / - users, 4, SBQ_WAKE_BATCH); + min_batch = sbq->sb.depth >= (4 * SBQ_WAIT_QUEUES) ? 4 : 1; + + wake_batch = clamp_val(depth / SBQ_WAIT_QUEUES, + min_batch, SBQ_WAKE_BATCH); __sbitmap_queue_update_wake_batch(sbq, wake_batch); } EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 847cdbefab46..26a5c9007653 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -492,6 +492,7 @@ static void kmalloc_oob_in_memset(struct kunit *test) ptr = kmalloc(size, GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, memset(ptr, 0, size + KASAN_GRANULE_SIZE)); @@ -515,6 +516,7 @@ static void kmalloc_memmove_negative_size(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(invalid_size); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); @@ -531,6 +533,7 @@ static void kmalloc_memmove_invalid_size(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset((char *)ptr, 0, 64); + OPTIMIZER_HIDE_VAR(ptr); KUNIT_EXPECT_KASAN_FAIL(test, memmove((char *)ptr, (char *)ptr + 4, invalid_size)); kfree(ptr); @@ -893,6 +896,7 @@ static void kasan_memchr(struct kunit *test) ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, kasan_ptr_result = memchr(ptr, '1', size + 1)); @@ -919,6 +923,7 @@ static void kasan_memcmp(struct kunit *test) KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); memset(arr, 0, sizeof(arr)); + OPTIMIZER_HIDE_VAR(ptr); OPTIMIZER_HIDE_VAR(size); KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = memcmp(ptr, arr, size+1)); @@ -124,8 +124,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * considered failure, and furthermore, a likely bug in the caller, so a warning * is also emitted. */ -struct page *try_grab_compound_head(struct page *page, - int refs, unsigned int flags) +__maybe_unused struct page *try_grab_compound_head(struct page *page, + int refs, unsigned int flags) { if (flags & FOLL_GET) return try_get_compound_head(page, refs); @@ -208,10 +208,35 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) */ bool __must_check try_grab_page(struct page *page, unsigned int flags) { - if (!(flags & (FOLL_GET | FOLL_PIN))) - return true; + WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); - return try_grab_compound_head(page, 1, flags); + if (flags & FOLL_GET) + return try_get_page(page); + else if (flags & FOLL_PIN) { + int refs = 1; + + page = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + + if (hpage_pincount_available(page)) + hpage_pincount_add(page, 1); + else + refs = GUP_PIN_COUNTING_BIAS; + + /* + * Similar to try_grab_compound_head(): even if using the + * hpage_pincount_add/_sub() routines, be sure to + * *also* increment the normal page refcount field at least + * once, so that the page really is pinned. + */ + page_ref_add(page, refs); + + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); + } + + return true; } /** diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 14ae5c18e776..97a9ed8f87a9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1596,6 +1596,12 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, } /* + * Pages instantiated by device-dax (not filesystem-dax) + * may be compound pages. + */ + page = compound_head(page); + + /* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by * lock_page(), but dax pages do not use the page lock. This diff --git a/net/6lowpan/core.c b/net/6lowpan/core.c index a068757eabaf..7b3341cef926 100644 --- a/net/6lowpan/core.c +++ b/net/6lowpan/core.c @@ -5,6 +5,7 @@ * (C) 2015 Pengutronix, Alexander Aring <aar@pengutronix.de> */ +#include <linux/if_arp.h> #include <linux/module.h> #include <net/6lowpan.h> diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 02f43f3e2c56..3e49d28824ed 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; + struct sock *sk; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; @@ -85,13 +86,16 @@ static void ax25_kill_by_device(struct net_device *dev) again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { + sk = s->sk; + sock_hold(sk); spin_unlock_bh(&ax25_list_lock); - lock_sock(s->sk); + lock_sock(sk); s->ax25_dev = NULL; - release_sock(s->sk); + ax25_dev_put(ax25_dev); + release_sock(sk); ax25_disconnect(s, ENETUNREACH); spin_lock_bh(&ax25_list_lock); - + sock_put(sk); /* The entry could have been deleted from the * list meanwhile and thus the next pointer is * no longer valid. Play it safe and restart @@ -355,21 +359,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl))) return -EFAULT; - if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL) - return -ENODEV; - if (ax25_ctl.digi_count > AX25_MAX_DIGIS) return -EINVAL; if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr); + if (!ax25_dev) + return -ENODEV; + digi.ndigi = ax25_ctl.digi_count; for (k = 0; k < digi.ndigi; k++) digi.calls[k] = ax25_ctl.digi_addr[k]; - if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL) + ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev); + if (!ax25) { + ax25_dev_put(ax25_dev); return -ENOTCONN; + } switch (ax25_ctl.cmd) { case AX25_KILL: @@ -436,6 +444,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) } out_put: + ax25_dev_put(ax25_dev); ax25_cb_put(ax25); return ret; diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 256fadb94df3..d2a244e1c260 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; + ax25_dev_hold(ax25_dev); } spin_unlock_bh(&ax25_dev_lock); @@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev) return; } + refcount_set(&ax25_dev->refcount, 1); dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC); @@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev->next = ax25_dev_list; ax25_dev_list = ax25_dev; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_hold(ax25_dev); ax25_register_dev_sysctl(ax25_dev); } @@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev) if ((s = ax25_dev_list) == ax25_dev) { ax25_dev_list = s->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put_track(dev, &ax25_dev->dev_tracker); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev) if (s->next == ax25_dev) { s->next = ax25_dev->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put_track(dev, &ax25_dev->dev_tracker); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev) } spin_unlock_bh(&ax25_dev_lock); dev->ax25_ptr = NULL; + ax25_dev_put(ax25_dev); } int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) @@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) switch (cmd) { case SIOCAX25ADDFWD: - if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL) + fwd_dev = ax25_addr_ax25dev(&fwd->port_to); + if (!fwd_dev) { + ax25_dev_put(ax25_dev); return -EINVAL; - if (ax25_dev->forward != NULL) + } + if (ax25_dev->forward) { + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = fwd_dev->dev; + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); break; case SIOCAX25DELFWD: - if (ax25_dev->forward == NULL) + if (!ax25_dev->forward) { + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = NULL; + ax25_dev_put(ax25_dev); break; default: + ax25_dev_put(ax25_dev); return -EINVAL; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index d0b2e094bd55..b7c4d656a94b 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_dev *ax25_dev; int i; - if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL) - return -EINVAL; if (route->digi_count > AX25_MAX_DIGIS) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&route->port_addr); + if (!ax25_dev) + return -EINVAL; + write_lock_bh(&ax25_route_lock); ax25_rt = ax25_route_list; @@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if (route->digi_count != 0) { if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } ax25_rt = ax25_rt->next; @@ -108,10 +112,10 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } - refcount_set(&ax25_rt->refcount, 1); ax25_rt->callsign = route->dest_addr; ax25_rt->dev = ax25_dev->dev; ax25_rt->digipeat = NULL; @@ -120,6 +124,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); kfree(ax25_rt); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -132,6 +137,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_rt->next = ax25_route_list; ax25_route_list = ax25_rt; write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -160,12 +166,12 @@ static int ax25_rt_del(struct ax25_routes_struct *route) ax25cmp(&route->dest_addr, &s->callsign) == 0) { if (ax25_route_list == s) { ax25_route_list = s->next; - ax25_put_route(s); + __ax25_put_route(s); } else { for (t = ax25_route_list; t != NULL; t = t->next) { if (t->next == s) { t->next = s->next; - ax25_put_route(s); + __ax25_put_route(s); break; } } @@ -173,6 +179,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -215,6 +222,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option) out: write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return err; } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index f4004cf0ff6f..9f311fddfaf9 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -134,7 +134,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev) { struct inet6_dev *in6_dev = __in6_dev_get(dev); - if (in6_dev && in6_dev->cnf.mc_forwarding) + if (in6_dev && atomic_read(&in6_dev->cnf.mc_forwarding)) return BATADV_NO_FLAGS; else return BATADV_MCAST_WANT_NO_RTR6; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 04ebe901e86f..d10651108033 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -689,6 +689,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); + conn->handle = HCI_CONN_HANDLE_UNSET; conn->hdev = hdev; conn->type = type; conn->role = role; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2b7bd3655b07..5bde0ec41177 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2503,6 +2503,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) INIT_LIST_HEAD(&hdev->conn_hash.list); INIT_LIST_HEAD(&hdev->adv_instances); INIT_LIST_HEAD(&hdev->blocked_keys); + INIT_LIST_HEAD(&hdev->monitored_devices); INIT_LIST_HEAD(&hdev->local_codecs); INIT_WORK(&hdev->rx_work, hci_rx_work); @@ -3666,8 +3667,8 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) sco_recv_scodata(conn, skb); return; } else { - bt_dev_err(hdev, "SCO packet for unknown connection handle %d", - handle); + bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", + handle); } kfree_skb(skb); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index fc30f4c03d29..63b925921c87 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3068,6 +3068,11 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, struct hci_ev_conn_complete *ev = data; struct hci_conn *conn; + if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for invalid handle"); + return; + } + bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); @@ -3106,6 +3111,17 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, } } + /* The HCI_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); + goto unlock; + } + if (!ev->status) { conn->handle = __le16_to_cpu(ev->handle); @@ -4534,7 +4550,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); - return; + goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); @@ -4565,7 +4581,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, if (!info) { bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); - return; + goto unlock; } bacpy(&data.bdaddr, &info->bdaddr); @@ -4587,7 +4603,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, void *edata, bt_dev_err(hdev, "Malformed HCI Event: 0x%2.2x", HCI_EV_INQUIRY_RESULT_WITH_RSSI); } - +unlock: hci_dev_unlock(hdev); } @@ -4661,6 +4677,24 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, struct hci_ev_sync_conn_complete *ev = data; struct hci_conn *conn; + switch (ev->link_type) { + case SCO_LINK: + case ESCO_LINK: + break; + default: + /* As per Core 5.3 Vol 4 Part E 7.7.35 (p.2219), Link_Type + * for HCI_Synchronous_Connection_Complete is limited to + * either SCO or eSCO + */ + bt_dev_err(hdev, "Ignoring connect complete event for invalid link type"); + return; + } + + if (__le16_to_cpu(ev->handle) > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete for invalid handle"); + return; + } + bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); hci_dev_lock(hdev); @@ -4684,23 +4718,19 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, void *data, goto unlock; } + /* The HCI_Synchronous_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Sync_Conn_Complete event for existing connection"); + goto unlock; + } + switch (ev->status) { case 0x00: - /* The synchronous connection complete event should only be - * sent once per new connection. Receiving a successful - * complete event when the connection status is already - * BT_CONNECTED means that the device is misbehaving and sent - * multiple complete event packets for the same new connection. - * - * Registering the device more than once can corrupt kernel - * memory, hence upon detecting this invalid event, we report - * an error and ignore the packet. - */ - if (conn->state == BT_CONNECTED) { - bt_dev_err(hdev, "Ignoring connect complete event for existing connection"); - goto unlock; - } - conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; conn->type = ev->link_type; @@ -5496,6 +5526,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, struct smp_irk *irk; u8 addr_type; + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_err(hdev, "Ignoring HCI_LE_Connection_Complete for invalid handle"); + return; + } + hci_dev_lock(hdev); /* All controllers implicitly stop advertising in the event of a @@ -5537,6 +5572,17 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, cancel_delayed_work(&conn->le_conn_timeout); } + /* The HCI_LE_Connection_Complete event is only sent once per connection. + * Processing it more than once per connection can corrupt kernel memory. + * + * As the connection handle is set here for the first time, it indicates + * whether the connection is already set up. + */ + if (conn->handle != HCI_CONN_HANDLE_UNSET) { + bt_dev_err(hdev, "Ignoring HCI_Connection_Complete for existing connection"); + goto unlock; + } + le_conn_update_addr(conn, bdaddr, bdaddr_type, local_rpa); /* Lookup the identity address from the stored connection @@ -6798,7 +6844,7 @@ static const struct hci_ev { HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, sizeof(struct hci_ev_num_comp_blocks)), /* [0xff = HCI_EV_VENDOR] */ - HCI_EV(HCI_EV_VENDOR, msft_vendor_evt, 0), + HCI_EV_VL(HCI_EV_VENDOR, msft_vendor_evt, 0, HCI_MAX_EVENT_SIZE), }; static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb, @@ -6823,8 +6869,9 @@ static void hci_event_func(struct hci_dev *hdev, u8 event, struct sk_buff *skb, * decide if that is acceptable. */ if (skb->len > ev->max_len) - bt_dev_warn(hdev, "unexpected event 0x%2.2x length: %u > %u", - event, skb->len, ev->max_len); + bt_dev_warn_ratelimited(hdev, + "unexpected event 0x%2.2x length: %u > %u", + event, skb->len, ev->max_len); data = hci_ev_skb_pull(hdev, skb, event, ev->min_len); if (!data) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 0feb68f12545..6e71aa6b6fea 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -382,6 +382,9 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, { struct hci_cmd_sync_work_entry *entry; + if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) + return -ENODEV; + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; @@ -5140,8 +5143,8 @@ static void set_ext_conn_params(struct hci_conn *conn, p->max_ce_len = cpu_to_le16(0x0000); } -int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, - u8 own_addr_type) +static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, + struct hci_conn *conn, u8 own_addr_type) { struct hci_cp_le_ext_create_conn *cp; struct hci_cp_le_ext_conn_param *p; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 37087cf7dc5a..5dd684e0b259 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -42,7 +42,7 @@ #include "aosp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 21 +#define MGMT_REVISION 22 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -174,6 +174,8 @@ static const u16 mgmt_events[] = { MGMT_EV_ADV_MONITOR_REMOVED, MGMT_EV_CONTROLLER_SUSPEND, MGMT_EV_CONTROLLER_RESUME, + MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + MGMT_EV_ADV_MONITOR_DEVICE_LOST, }; static const u16 mgmt_untrusted_commands[] = { @@ -9589,12 +9591,116 @@ static bool is_filter_match(struct hci_dev *hdev, s8 rssi, u8 *eir, return true; } +void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle, + bdaddr_t *bdaddr, u8 addr_type) +{ + struct mgmt_ev_adv_monitor_device_lost ev; + + ev.monitor_handle = cpu_to_le16(handle); + bacpy(&ev.addr.bdaddr, bdaddr); + ev.addr.type = addr_type; + + mgmt_event(MGMT_EV_ADV_MONITOR_DEVICE_LOST, hdev, &ev, sizeof(ev), + NULL); +} + +static void mgmt_adv_monitor_device_found(struct hci_dev *hdev, + bdaddr_t *bdaddr, bool report_device, + struct sk_buff *skb, + struct sock *skip_sk) +{ + struct sk_buff *advmon_skb; + size_t advmon_skb_len; + __le16 *monitor_handle; + struct monitored_device *dev, *tmp; + bool matched = false; + bool notify = false; + + /* We have received the Advertisement Report because: + * 1. the kernel has initiated active discovery + * 2. if not, we have pend_le_reports > 0 in which case we are doing + * passive scanning + * 3. if none of the above is true, we have one or more active + * Advertisement Monitor + * + * For case 1 and 2, report all advertisements via MGMT_EV_DEVICE_FOUND + * and report ONLY one advertisement per device for the matched Monitor + * via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + * + * For case 3, since we are not active scanning and all advertisements + * received are due to a matched Advertisement Monitor, report all + * advertisements ONLY via MGMT_EV_ADV_MONITOR_DEVICE_FOUND event. + */ + if (report_device && !hdev->advmon_pend_notify) { + mgmt_event_skb(skb, skip_sk); + return; + } + + advmon_skb_len = (sizeof(struct mgmt_ev_adv_monitor_device_found) - + sizeof(struct mgmt_ev_device_found)) + skb->len; + advmon_skb = mgmt_alloc_skb(hdev, MGMT_EV_ADV_MONITOR_DEVICE_FOUND, + advmon_skb_len); + if (!advmon_skb) { + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + return; + } + + /* ADV_MONITOR_DEVICE_FOUND is similar to DEVICE_FOUND event except + * that it also has 'monitor_handle'. Make a copy of DEVICE_FOUND and + * store monitor_handle of the matched monitor. + */ + monitor_handle = skb_put(advmon_skb, sizeof(*monitor_handle)); + skb_put_data(advmon_skb, skb->data, skb->len); + + hdev->advmon_pend_notify = false; + + list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) { + if (!bacmp(&dev->bdaddr, bdaddr)) { + matched = true; + + if (!dev->notified) { + *monitor_handle = cpu_to_le16(dev->handle); + notify = true; + dev->notified = true; + } + } + + if (!dev->notified) + hdev->advmon_pend_notify = true; + } + + if (!report_device && + ((matched && !notify) || !msft_monitor_supported(hdev))) { + /* Handle 0 indicates that we are not active scanning and this + * is a subsequent advertisement report for an already matched + * Advertisement Monitor or the controller offloading support + * is not available. + */ + *monitor_handle = 0; + notify = true; + } + + if (report_device) + mgmt_event_skb(skb, skip_sk); + else + kfree_skb(skb); + + if (notify) + mgmt_event_skb(advmon_skb, skip_sk); + else + kfree_skb(advmon_skb); +} + void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 *dev_class, s8 rssi, u32 flags, u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len) { struct sk_buff *skb; struct mgmt_ev_device_found *ev; + bool report_device = hci_discovery_active(hdev); /* Don't send events for a non-kernel initiated discovery. With * LE one exception is if we have pend_le_reports > 0 in which @@ -9603,11 +9709,10 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, if (!hci_discovery_active(hdev)) { if (link_type == ACL_LINK) return; - if (link_type == LE_LINK && - list_empty(&hdev->pend_le_reports) && - !hci_is_adv_monitoring(hdev)) { + if (link_type == LE_LINK && !list_empty(&hdev->pend_le_reports)) + report_device = true; + else if (!hci_is_adv_monitoring(hdev)) return; - } } if (hdev->discovery.result_filtering) { @@ -9672,7 +9777,7 @@ void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, ev->eir_len = cpu_to_le16(eir_len + scan_rsp_len); - mgmt_event_skb(skb, NULL); + mgmt_adv_monitor_device_found(hdev, bdaddr, report_device, skb, NULL); } void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 6a943634b31a..9a3d77d3ca86 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -80,6 +80,14 @@ struct msft_rp_le_set_advertisement_filter_enable { __u8 sub_opcode; } __packed; +#define MSFT_EV_LE_MONITOR_DEVICE 0x02 +struct msft_ev_le_monitor_device { + __u8 addr_type; + bdaddr_t bdaddr; + __u8 monitor_handle; + __u8 monitor_state; +} __packed; + struct msft_monitor_advertisement_handle_data { __u8 msft_handle; __u16 mgmt_handle; @@ -204,6 +212,37 @@ static struct msft_monitor_advertisement_handle_data *msft_find_handle_data return NULL; } +/* This function requires the caller holds hdev->lock */ +static int msft_monitor_device_del(struct hci_dev *hdev, __u16 mgmt_handle, + bdaddr_t *bdaddr, __u8 addr_type, + bool notify) +{ + struct monitored_device *dev, *tmp; + int count = 0; + + list_for_each_entry_safe(dev, tmp, &hdev->monitored_devices, list) { + /* mgmt_handle == 0 indicates remove all devices, whereas, + * bdaddr == NULL indicates remove all devices matching the + * mgmt_handle. + */ + if ((!mgmt_handle || dev->handle == mgmt_handle) && + (!bdaddr || (!bacmp(bdaddr, &dev->bdaddr) && + addr_type == dev->addr_type))) { + if (notify && dev->notified) { + mgmt_adv_monitor_device_lost(hdev, dev->handle, + &dev->bdaddr, + dev->addr_type); + } + + list_del(&dev->list); + kfree(dev); + count++; + } + } + + return count; +} + static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev, u8 status, u16 opcode, struct sk_buff *skb) @@ -294,6 +333,10 @@ static void msft_le_cancel_monitor_advertisement_cb(struct hci_dev *hdev, if (monitor && !msft->suspending) hci_free_adv_monitor(hdev, monitor); + /* Clear any monitored devices by this Adv Monitor */ + msft_monitor_device_del(hdev, handle_data->mgmt_handle, NULL, + 0, false); + list_del(&handle_data->list); kfree(handle_data); } @@ -557,6 +600,14 @@ void msft_do_close(struct hci_dev *hdev) list_del(&handle_data->list); kfree(handle_data); } + + hci_dev_lock(hdev); + + /* Clear any devices that are being monitored and notify device lost */ + hdev->advmon_pend_notify = false; + msft_monitor_device_del(hdev, 0, NULL, 0, true); + + hci_dev_unlock(hdev); } void msft_register(struct hci_dev *hdev) @@ -590,10 +641,101 @@ void msft_unregister(struct hci_dev *hdev) kfree(msft); } +/* This function requires the caller holds hdev->lock */ +static void msft_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, + __u8 addr_type, __u16 mgmt_handle) +{ + struct monitored_device *dev; + + dev = kmalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + bt_dev_err(hdev, "MSFT vendor event %u: no memory", + MSFT_EV_LE_MONITOR_DEVICE); + return; + } + + bacpy(&dev->bdaddr, bdaddr); + dev->addr_type = addr_type; + dev->handle = mgmt_handle; + dev->notified = false; + + INIT_LIST_HEAD(&dev->list); + list_add(&dev->list, &hdev->monitored_devices); + hdev->advmon_pend_notify = true; +} + +/* This function requires the caller holds hdev->lock */ +static void msft_device_lost(struct hci_dev *hdev, bdaddr_t *bdaddr, + __u8 addr_type, __u16 mgmt_handle) +{ + if (!msft_monitor_device_del(hdev, mgmt_handle, bdaddr, addr_type, + true)) { + bt_dev_err(hdev, "MSFT vendor event %u: dev %pMR not in list", + MSFT_EV_LE_MONITOR_DEVICE, bdaddr); + } +} + +static void *msft_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, + u8 ev, size_t len) +{ + void *data; + + data = skb_pull_data(skb, len); + if (!data) + bt_dev_err(hdev, "Malformed MSFT vendor event: 0x%02x", ev); + + return data; +} + +/* This function requires the caller holds hdev->lock */ +static void msft_monitor_device_evt(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct msft_ev_le_monitor_device *ev; + struct msft_monitor_advertisement_handle_data *handle_data; + u8 addr_type; + + ev = msft_skb_pull(hdev, skb, MSFT_EV_LE_MONITOR_DEVICE, sizeof(*ev)); + if (!ev) + return; + + bt_dev_dbg(hdev, + "MSFT vendor event 0x%02x: handle 0x%04x state %d addr %pMR", + MSFT_EV_LE_MONITOR_DEVICE, ev->monitor_handle, + ev->monitor_state, &ev->bdaddr); + + handle_data = msft_find_handle_data(hdev, ev->monitor_handle, false); + if (!handle_data) + return; + + switch (ev->addr_type) { + case ADDR_LE_DEV_PUBLIC: + addr_type = BDADDR_LE_PUBLIC; + break; + + case ADDR_LE_DEV_RANDOM: + addr_type = BDADDR_LE_RANDOM; + break; + + default: + bt_dev_err(hdev, + "MSFT vendor event 0x%02x: unknown addr type 0x%02x", + MSFT_EV_LE_MONITOR_DEVICE, ev->addr_type); + return; + } + + if (ev->monitor_state) + msft_device_found(hdev, &ev->bdaddr, addr_type, + handle_data->mgmt_handle); + else + msft_device_lost(hdev, &ev->bdaddr, addr_type, + handle_data->mgmt_handle); +} + void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { struct msft_data *msft = hdev->msft_data; - u8 event; + u8 *evt_prefix; + u8 *evt; if (!msft) return; @@ -602,13 +744,12 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) * matches, and otherwise just return. */ if (msft->evt_prefix_len > 0) { - if (skb->len < msft->evt_prefix_len) + evt_prefix = msft_skb_pull(hdev, skb, 0, msft->evt_prefix_len); + if (!evt_prefix) return; - if (memcmp(skb->data, msft->evt_prefix, msft->evt_prefix_len)) + if (memcmp(evt_prefix, msft->evt_prefix, msft->evt_prefix_len)) return; - - skb_pull(skb, msft->evt_prefix_len); } /* Every event starts at least with an event code and the rest of @@ -617,10 +758,23 @@ void msft_vendor_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) if (skb->len < 1) return; - event = *skb->data; - skb_pull(skb, 1); + evt = msft_skb_pull(hdev, skb, 0, sizeof(*evt)); + if (!evt) + return; + + hci_dev_lock(hdev); + + switch (*evt) { + case MSFT_EV_LE_MONITOR_DEVICE: + msft_monitor_device_evt(hdev, skb); + break; - bt_dev_dbg(hdev, "MSFT vendor event %u", event); + default: + bt_dev_dbg(hdev, "MSFT vendor event 0x%02x", *evt); + break; + } + + hci_dev_unlock(hdev); } __u64 msft_get_features(struct hci_dev *hdev) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 46dd95755967..65b52b4bd6e1 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -5,6 +5,7 @@ #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/slab.h> +#include <linux/init.h> #include <linux/vmalloc.h> #include <linux/etherdevice.h> #include <linux/filter.h> @@ -130,7 +131,8 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, static int bpf_test_finish(const union bpf_attr *kattr, union bpf_attr __user *uattr, const void *data, - u32 size, u32 retval, u32 duration) + struct skb_shared_info *sinfo, u32 size, + u32 retval, u32 duration) { void __user *data_out = u64_to_user_ptr(kattr->test.data_out); int err = -EFAULT; @@ -145,8 +147,36 @@ static int bpf_test_finish(const union bpf_attr *kattr, err = -ENOSPC; } - if (data_out && copy_to_user(data_out, data, copy_size)) - goto out; + if (data_out) { + int len = sinfo ? copy_size - sinfo->xdp_frags_size : copy_size; + + if (copy_to_user(data_out, data, len)) + goto out; + + if (sinfo) { + int i, offset = len, data_len; + + for (i = 0; i < sinfo->nr_frags; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + + if (offset >= copy_size) { + err = -ENOSPC; + break; + } + + data_len = min_t(int, copy_size - offset, + skb_frag_size(frag)); + + if (copy_to_user(data_out + offset, + skb_frag_address(frag), + data_len)) + goto out; + + offset += data_len; + } + } + } + if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size))) goto out; if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval))) @@ -171,6 +201,8 @@ int noinline bpf_fentry_test1(int a) { return a + 1; } +EXPORT_SYMBOL_GPL(bpf_fentry_test1); +ALLOW_ERROR_INJECTION(bpf_fentry_test1, ERRNO); int noinline bpf_fentry_test2(int a, u64 b) { @@ -232,28 +264,142 @@ struct sock * noinline bpf_kfunc_call_test3(struct sock *sk) return sk; } +struct prog_test_ref_kfunc { + int a; + int b; + struct prog_test_ref_kfunc *next; +}; + +static struct prog_test_ref_kfunc prog_test_struct = { + .a = 42, + .b = 108, + .next = &prog_test_struct, +}; + +noinline struct prog_test_ref_kfunc * +bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) +{ + /* randomly return NULL */ + if (get_jiffies_64() % 2) + return NULL; + return &prog_test_struct; +} + +noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) +{ +} + +struct prog_test_pass1 { + int x0; + struct { + int x1; + struct { + int x2; + struct { + int x3; + }; + }; + }; +}; + +struct prog_test_pass2 { + int len; + short arr1[4]; + struct { + char arr2[4]; + unsigned long arr3[8]; + } x; +}; + +struct prog_test_fail1 { + void *p; + int x; +}; + +struct prog_test_fail2 { + int x8; + struct prog_test_pass1 x; +}; + +struct prog_test_fail3 { + int len; + char arr1[2]; + char arr2[]; +}; + +noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +{ +} + +noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +{ +} + +noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +{ +} + +noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +{ +} + __diag_pop(); ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); -BTF_SET_START(test_sk_kfunc_ids) +BTF_SET_START(test_sk_check_kfunc_ids) BTF_ID(func, bpf_kfunc_call_test1) BTF_ID(func, bpf_kfunc_call_test2) BTF_ID(func, bpf_kfunc_call_test3) -BTF_SET_END(test_sk_kfunc_ids) - -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) -{ - if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id)) - return true; - return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner); -} - -static void *bpf_test_init(const union bpf_attr *kattr, u32 size, - u32 headroom, u32 tailroom) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_ID(func, bpf_kfunc_call_test_release) +BTF_ID(func, bpf_kfunc_call_test_pass_ctx) +BTF_ID(func, bpf_kfunc_call_test_pass1) +BTF_ID(func, bpf_kfunc_call_test_pass2) +BTF_ID(func, bpf_kfunc_call_test_fail1) +BTF_ID(func, bpf_kfunc_call_test_fail2) +BTF_ID(func, bpf_kfunc_call_test_fail3) +BTF_ID(func, bpf_kfunc_call_test_mem_len_pass1) +BTF_ID(func, bpf_kfunc_call_test_mem_len_fail1) +BTF_ID(func, bpf_kfunc_call_test_mem_len_fail2) +BTF_SET_END(test_sk_check_kfunc_ids) + +BTF_SET_START(test_sk_acquire_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_SET_END(test_sk_acquire_kfunc_ids) + +BTF_SET_START(test_sk_release_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_release) +BTF_SET_END(test_sk_release_kfunc_ids) + +BTF_SET_START(test_sk_ret_null_kfunc_ids) +BTF_ID(func, bpf_kfunc_call_test_acquire) +BTF_SET_END(test_sk_ret_null_kfunc_ids) + +static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, + u32 size, u32 headroom, u32 tailroom) { void __user *data_in = u64_to_user_ptr(kattr->test.data_in); - u32 user_size = kattr->test.data_size_in; void *data; if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) @@ -581,7 +727,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, if (kattr->test.flags || kattr->test.cpu) return -EINVAL; - data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, + data = bpf_test_init(kattr, kattr->test.data_size_in, + size, NET_SKB_PAD + NET_IP_ALIGN, SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); if (IS_ERR(data)) return PTR_ERR(data); @@ -683,7 +830,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) size = skb_headlen(skb); - ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration); + ret = bpf_test_finish(kattr, uattr, skb->data, NULL, size, retval, + duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct __sk_buff)); @@ -758,16 +906,16 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { u32 tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - u32 headroom = XDP_PACKET_HEADROOM; u32 size = kattr->test.data_size_in; + u32 headroom = XDP_PACKET_HEADROOM; + u32 retval, duration, max_data_sz; u32 repeat = kattr->test.repeat; struct netdev_rx_queue *rxqueue; + struct skb_shared_info *sinfo; struct xdp_buff xdp = {}; - u32 retval, duration; + int i, ret = -EINVAL; struct xdp_md *ctx; - u32 max_data_sz; void *data; - int ret = -EINVAL; if (prog->expected_attach_type == BPF_XDP_DEVMAP || prog->expected_attach_type == BPF_XDP_CPUMAP) @@ -787,26 +935,60 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, headroom -= ctx->data; } - /* XDP have extra tailroom as (most) drivers use full page */ max_data_sz = 4096 - headroom - tailroom; + size = min_t(u32, size, max_data_sz); - data = bpf_test_init(kattr, max_data_sz, headroom, tailroom); + data = bpf_test_init(kattr, size, max_data_sz, headroom, tailroom); if (IS_ERR(data)) { ret = PTR_ERR(data); goto free_ctx; } rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0); - xdp_init_buff(&xdp, headroom + max_data_sz + tailroom, - &rxqueue->xdp_rxq); + rxqueue->xdp_rxq.frag_size = headroom + max_data_sz + tailroom; + xdp_init_buff(&xdp, rxqueue->xdp_rxq.frag_size, &rxqueue->xdp_rxq); xdp_prepare_buff(&xdp, data, headroom, size, true); + sinfo = xdp_get_shared_info_from_buff(&xdp); ret = xdp_convert_md_to_buff(ctx, &xdp); if (ret) goto free_data; + if (unlikely(kattr->test.data_size_in > size)) { + void __user *data_in = u64_to_user_ptr(kattr->test.data_in); + + while (size < kattr->test.data_size_in) { + struct page *page; + skb_frag_t *frag; + int data_len; + + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto out; + } + + frag = &sinfo->frags[sinfo->nr_frags++]; + __skb_frag_set_page(frag, page); + + data_len = min_t(int, kattr->test.data_size_in - size, + PAGE_SIZE); + skb_frag_size_set(frag, data_len); + + if (copy_from_user(page_address(page), data_in + size, + data_len)) { + ret = -EFAULT; + goto out; + } + sinfo->xdp_frags_size += data_len; + size += data_len; + } + xdp_buff_set_frags_flag(&xdp); + } + if (repeat > 1) bpf_prog_change_xdp(NULL, prog); + ret = bpf_test_run(prog, &xdp, repeat, &retval, &duration, true); /* We convert the xdp_buff back to an xdp_md before checking the return * code so the reference count of any held netdevice will be decremented @@ -816,12 +998,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, if (ret) goto out; - if (xdp.data_meta != data + headroom || - xdp.data_end != xdp.data_meta + size) - size = xdp.data_end - xdp.data_meta; - - ret = bpf_test_finish(kattr, uattr, xdp.data_meta, size, retval, - duration); + size = xdp.data_end - xdp.data_meta + sinfo->xdp_frags_size; + ret = bpf_test_finish(kattr, uattr, xdp.data_meta, sinfo, size, + retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, ctx, sizeof(struct xdp_md)); @@ -830,6 +1009,8 @@ out: if (repeat > 1) bpf_prog_change_xdp(prog, NULL); free_data: + for (i = 0; i < sinfo->nr_frags; i++) + __free_page(skb_frag_page(&sinfo->frags[i])); kfree(data); free_ctx: kfree(ctx); @@ -876,7 +1057,7 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (size < ETH_HLEN) return -EINVAL; - data = bpf_test_init(kattr, size, 0, 0); + data = bpf_test_init(kattr, kattr->test.data_size_in, size, 0, 0); if (IS_ERR(data)) return PTR_ERR(data); @@ -911,8 +1092,8 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, if (ret < 0) goto out; - ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), - retval, duration); + ret = bpf_test_finish(kattr, uattr, &flow_keys, NULL, + sizeof(flow_keys), retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(struct bpf_flow_keys)); @@ -1016,7 +1197,7 @@ int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kat user_ctx->cookie = sock_gen_cookie(ctx.selected_sk); } - ret = bpf_test_finish(kattr, uattr, NULL, 0, retval, duration); + ret = bpf_test_finish(kattr, uattr, NULL, NULL, 0, retval, duration); if (!ret) ret = bpf_ctx_finish(kattr, uattr, user_ctx, sizeof(*user_ctx)); @@ -1067,3 +1248,17 @@ out: kfree(ctx); return err; } + +static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &test_sk_check_kfunc_ids, + .acquire_set = &test_sk_acquire_kfunc_ids, + .release_set = &test_sk_release_kfunc_ids, + .ret_null_set = &test_sk_ret_null_kfunc_ids, +}; + +static int __init bpf_prog_test_run_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); +} +late_initcall(bpf_prog_test_run_init); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 84ba456a78cc..1402d5ca242d 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -560,10 +560,10 @@ static bool __allowed_ingress(const struct net_bridge *br, !br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { if (*state == BR_STATE_FORWARDING) { *state = br_vlan_get_pvid_state(vg); - return br_vlan_state_allowed(*state, true); - } else { - return true; + if (!br_vlan_state_allowed(*state, true)) + goto drop; } + return true; } } v = br_vlan_find(vg, *vid); @@ -2020,7 +2020,8 @@ static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) goto out_err; } err = br_vlan_dump_dev(dev, skb, cb, dump_flags); - if (err && err != -EMSGSIZE) + /* if the dump completed without an error we return 0 here */ + if (err != -EMSGSIZE) goto out_err; } else { for_each_netdev_rcu(net, dev) { diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index eba0efe64d05..fbf858ddec35 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook); + nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook); if (!nskb) return; @@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code); + nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code); if (!nskb) return; @@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook); + nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook); if (!nskb) return; @@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code); + nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code); if (!nskb) return; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 440139706130..52dd0b6835bc 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -268,7 +268,7 @@ static int receive(struct sk_buff *skb, struct net_device *dev, err = caifd->layer.up->receive(caifd->layer.up, pkt); - /* For -EILSEQ the packet is not freed so so it now */ + /* For -EILSEQ the packet is not freed so free it now */ if (err == -EILSEQ) cfpkt_destroy(pkt); diff --git a/net/core/dev.c b/net/core/dev.c index 1baab07820f6..f662c6a7d7b4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1037,7 +1037,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; @@ -1047,7 +1047,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) - set_bit(i, inuse); + __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); @@ -10172,7 +10172,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; - dev_hold(dev); + __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif @@ -10732,8 +10732,7 @@ static int __net_init netdev_init(struct net *net) BUILD_BUG_ON(GRO_HASH_BUCKETS > 8 * sizeof_field(struct napi_struct, gro_bitmask)); - if (net != &init_net) - INIT_LIST_HEAD(&net->dev_base_head); + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) diff --git a/net/core/filter.c b/net/core/filter.c index 4603b7cd3cd1..f497ca7a16d2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2603,7 +2603,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) + if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2809,7 +2809,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - __clear_bit(new, &msg->sg.copy); + __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@ -3783,6 +3783,28 @@ static const struct bpf_func_proto sk_skb_change_head_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; + +BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) +{ + return xdp_get_buff_len(xdp); +} + +static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) + +const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { + .func = bpf_xdp_get_buff_len, + .gpl_only = false, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], +}; + static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3817,11 +3839,208 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, + void *buf, unsigned long len, bool flush) +{ + unsigned long ptr_len, ptr_off = 0; + skb_frag_t *next_frag, *end_frag; + struct skb_shared_info *sinfo; + void *src, *dst; + u8 *ptr_buf; + + if (likely(xdp->data_end - xdp->data >= off + len)) { + src = flush ? buf : xdp->data + off; + dst = flush ? xdp->data + off : buf; + memcpy(dst, src, len); + return; + } + + sinfo = xdp_get_shared_info_from_buff(xdp); + end_frag = &sinfo->frags[sinfo->nr_frags]; + next_frag = &sinfo->frags[0]; + + ptr_len = xdp->data_end - xdp->data; + ptr_buf = xdp->data; + + while (true) { + if (off < ptr_off + ptr_len) { + unsigned long copy_off = off - ptr_off; + unsigned long copy_len = min(len, ptr_len - copy_off); + + src = flush ? buf : ptr_buf + copy_off; + dst = flush ? ptr_buf + copy_off : buf; + memcpy(dst, src, copy_len); + + off += copy_len; + len -= copy_len; + buf += copy_len; + } + + if (!len || next_frag == end_frag) + break; + + ptr_off += ptr_len; + ptr_buf = skb_frag_address(next_frag); + ptr_len = skb_frag_size(next_frag); + next_frag++; + } +} + +static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + u32 size = xdp->data_end - xdp->data; + void *addr = xdp->data; + int i; + + if (unlikely(offset > 0xffff || len > 0xffff)) + return ERR_PTR(-EFAULT); + + if (offset + len > xdp_get_buff_len(xdp)) + return ERR_PTR(-EINVAL); + + if (offset < size) /* linear area */ + goto out; + + offset -= size; + for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ + u32 frag_size = skb_frag_size(&sinfo->frags[i]); + + if (offset < frag_size) { + addr = skb_frag_address(&sinfo->frags[i]); + size = frag_size; + break; + } + offset -= frag_size; + } +out: + return offset + len < size ? addr + offset : NULL; +} + +BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, false); + else + memcpy(buf, ptr, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { + .func = bpf_xdp_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, + void *, buf, u32, len) +{ + void *ptr; + + ptr = bpf_xdp_pointer(xdp, offset, len); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + if (!ptr) + bpf_xdp_copy_buf(xdp, offset, buf, len, true); + else + memcpy(ptr, buf, len); + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { + .func = bpf_xdp_store_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + +static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; + struct xdp_rxq_info *rxq = xdp->rxq; + unsigned int tailroom; + + if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) + return -EOPNOTSUPP; + + tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + if (unlikely(offset > tailroom)) + return -EINVAL; + + memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); + skb_frag_size_add(frag, offset); + sinfo->xdp_frags_size += offset; + + return 0; +} + +static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) +{ + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + int i, n_frags_free = 0, len_free = 0; + + if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) + return -EINVAL; + + for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { + skb_frag_t *frag = &sinfo->frags[i]; + int shrink = min_t(int, offset, skb_frag_size(frag)); + + len_free += shrink; + offset -= shrink; + + if (skb_frag_size(frag) == shrink) { + struct page *page = skb_frag_page(frag); + + __xdp_return(page_address(page), &xdp->rxq->mem, + false, NULL); + n_frags_free++; + } else { + skb_frag_size_sub(frag, shrink); + break; + } + } + sinfo->nr_frags -= n_frags_free; + sinfo->xdp_frags_size -= len_free; + + if (unlikely(!sinfo->nr_frags)) { + xdp_buff_clear_frags_flag(xdp); + xdp->data_end -= offset; + } + + return 0; +} + BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; + if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ + if (offset < 0) + return bpf_xdp_frags_shrink_tail(xdp, -offset); + + return bpf_xdp_frags_increase_tail(xdp, offset); + } + /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; @@ -4047,6 +4266,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; + /* XDP_REDIRECT is not fully supported yet for xdp frags since + * not all XDP capable drivers can map non-linear xdp_frame in + * ndo_xdp_xmit. + */ + if (unlikely(xdp_buff_has_frags(xdp) && + map_type != BPF_MAP_TYPE_CPUMAP)) + return -EOPNOTSUPP; + if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); @@ -4590,10 +4817,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { }; #endif -static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff, +static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { - memcpy(dst_buff, src_buff + off, len); + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + + bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } @@ -4604,11 +4833,11 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(!xdp || - xdp_size > (unsigned long)(xdp->data_end - xdp->data))) + + if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; - return bpf_event_output(map, flags, meta, meta_size, xdp->data, + return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } @@ -4862,6 +5091,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, case SO_REUSEPORT: sk->sk_reuseport = valbool; break; + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + sk->sk_txrehash = (u8)val; + break; default: ret = -EINVAL; } @@ -5040,6 +5276,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, case SO_REUSEPORT: *((int *)optval) = sk->sk_reuseport; break; + case SO_TXREHASH: + *((int *)optval) = sk->sk_txrehash; + break; default: goto err_clear; } @@ -7533,6 +7772,12 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; + case BPF_FUNC_xdp_get_buff_len: + return &bpf_xdp_get_buff_len_proto; + case BPF_FUNC_xdp_load_bytes: + return &bpf_xdp_load_bytes_proto; + case BPF_FUNC_xdp_store_bytes: + return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: @@ -10062,7 +10307,6 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, - .check_kfunc_call = bpf_prog_test_check_kfunc_call, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { diff --git a/net/core/gro.c b/net/core/gro.c index a11b286d1495..ee5e7e889d8b 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -459,29 +459,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff skb_set_network_header(skb, skb_gro_offset(skb)); skb_reset_mac_len(skb); - NAPI_GRO_CB(skb)->same_flow = 0; + BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), + sizeof(u32))); /* Avoid slow unaligned acc */ + *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->encap_mark = 0; - NAPI_GRO_CB(skb)->recursion_counter = 0; - NAPI_GRO_CB(skb)->is_fou = 0; NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; /* Setup for GRO checksum validation */ switch (skb->ip_summed) { case CHECKSUM_COMPLETE: NAPI_GRO_CB(skb)->csum = skb->csum; NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; break; case CHECKSUM_UNNECESSARY: NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; } pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, @@ -634,7 +627,6 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (unlikely(skb->slow_gro)) { skb_orphan(skb); skb_ext_reset(skb); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index b0f5344d1185..95098d1a49bd 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -166,10 +166,10 @@ static void linkwatch_do_dev(struct net_device *dev) netdev_state_change(dev); } - /* Note: our callers are responsible for - * calling netdev_tracker_free(). + /* Note: our callers are responsible for calling netdev_tracker_free(). + * This is the reason we use __dev_put() instead of dev_put(). */ - dev_put(dev); + __dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6c2016f7f3d1..ec0bf737b076 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1133,7 +1133,8 @@ out: neigh_release(neigh); } -int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, + const bool immediate_ok) { int rc; bool immediate_probe = false; @@ -1154,12 +1155,17 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh_del_timer(neigh); - neigh->nud_state = NUD_INCOMPLETE; + neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; - next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), - HZ/100); + if (!immediate_ok) { + next = now + 1; + } else { + immediate_probe = true; + next = now + max(NEIGH_VAR(neigh->parms, + RETRANS_TIME), + HZ / 100); + } neigh_add_timer(neigh, next); - immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; @@ -1571,7 +1577,7 @@ static void neigh_managed_work(struct work_struct *work) write_lock_bh(&tbl->lock); list_for_each_entry(neigh, &tbl->managed_list, managed_list) - neigh_event_send(neigh, NULL); + neigh_event_send_probe(neigh, NULL, false); queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); write_unlock_bh(&tbl->lock); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index d8b9dbabd4a4..88cc0ad7d386 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -190,12 +190,23 @@ static const struct seq_operations softnet_seq_ops = { .show = softnet_seq_show, }; -static void *ptype_get_idx(loff_t pos) +static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { + struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; + struct net_device *dev; loff_t i = 0; int t; + for_each_netdev_rcu(seq_file_net(seq), dev) { + ptype_list = &dev->ptype_all; + list_for_each_entry_rcu(pt, ptype_list, list) { + if (i == pos) + return pt; + ++i; + } + } + list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; @@ -216,22 +227,40 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; + return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { + struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); + return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; + if (pt->dev) { + if (nxt != &pt->dev->ptype_all) + goto found; + + dev = pt->dev; + for_each_netdev_continue_rcu(seq_file_net(seq), dev) { + if (!list_empty(&dev->ptype_all)) { + nxt = dev->ptype_all.next; + goto found; + } + } + + nxt = ptype_all.next; + goto ptype_all; + } + if (pt->type == htons(ETH_P_ALL)) { +ptype_all: if (nxt != &ptype_all) goto found; hash = 0; @@ -260,7 +289,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a5b5bb99c644..0ec2f5906a27 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -44,13 +44,7 @@ EXPORT_SYMBOL_GPL(net_rwsem); static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif -struct net init_net = { - .ns.count = REFCOUNT_INIT(1), - .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), -#ifdef CONFIG_KEYS - .key_domain = &init_net_key_domain, -#endif -}; +struct net init_net; EXPORT_SYMBOL(init_net); static bool init_net_initialized; @@ -301,6 +295,7 @@ struct net *get_net_ns_by_id(const struct net *net, int id) return peer; } +EXPORT_SYMBOL_GPL(get_net_ns_by_id); /* * setup_net runs the initializers for the network namespace object. @@ -363,6 +358,8 @@ out_undo: static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; + return 0; } @@ -1084,7 +1081,7 @@ out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } -static int __init net_ns_init(void) +void __init net_ns_init(void) { struct net_generic *ng; @@ -1105,6 +1102,9 @@ static int __init net_ns_init(void) rcu_assign_pointer(init_net.gen, ng); +#ifdef CONFIG_KEYS + init_net.key_domain = &init_net_key_domain; +#endif down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); @@ -1119,12 +1119,8 @@ static int __init net_ns_init(void) RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, RTNL_FLAG_DOIT_UNLOCKED); - - return 0; } -pure_initcall(net_ns_init); - static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index bd62c01a2ec3..e25d359d84d9 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -423,11 +423,6 @@ static __always_inline struct page * __page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { - /* It is not the last user for the page frag case */ - if (pool->p.flags & PP_FLAG_PAGE_FRAG && - page_pool_atomic_sub_frag_count_return(page, 1)) - return NULL; - /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the * regular page allocator APIs. @@ -471,8 +466,8 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, return NULL; } -void page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +void page_pool_put_defragged_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); if (page && !page_pool_recycle_in_ring(pool, page)) { @@ -480,7 +475,7 @@ void page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_return_page(pool, page); } } -EXPORT_SYMBOL(page_pool_put_page); +EXPORT_SYMBOL(page_pool_put_defragged_page); /* Caller must not use data area after call, as this function overwrites it */ void page_pool_put_page_bulk(struct page_pool *pool, void **data, @@ -491,6 +486,10 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); + /* It is not the last user for the page frag case */ + if (!page_pool_is_last_frag(pool, page)) + continue; + page = __page_pool_put_page(pool, page, -1, false); /* Approved for bulk recycling in ptr_ring cache */ if (page) @@ -526,8 +525,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, long drain_count = BIAS_MAX - pool->frag_users; /* Some user is still using the page frag */ - if (likely(page_pool_atomic_sub_frag_count_return(page, - drain_count))) + if (likely(page_pool_defrag_page(page, drain_count))) return NULL; if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { @@ -548,8 +546,7 @@ static void page_pool_free_frag(struct page_pool *pool) pool->frag_page = NULL; - if (!page || - page_pool_atomic_sub_frag_count_return(page, drain_count)) + if (!page || page_pool_defrag_page(page, drain_count)) return; page_pool_return_page(pool, page); @@ -588,7 +585,7 @@ frag_reset: pool->frag_users = 1; *offset = 0; pool->frag_offset = size; - page_pool_set_frag_count(page, BIAS_MAX); + page_pool_fragment_page(page, BIAS_MAX); return page; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e476403231f0..710da8a36729 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3275,8 +3275,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1]; unsigned char name_assign_type = NET_NAME_USER; struct nlattr *linkinfo[IFLA_INFO_MAX + 1]; - const struct rtnl_link_ops *m_ops = NULL; - struct net_device *master_dev = NULL; + const struct rtnl_link_ops *m_ops; + struct net_device *master_dev; struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; struct nlattr *tb[IFLA_MAX + 1]; @@ -3314,6 +3314,8 @@ replay: else dev = NULL; + master_dev = NULL; + m_ops = NULL; if (dev) { master_dev = netdev_master_upper_dev_get(dev); if (master_dev) diff --git a/net/core/sock.c b/net/core/sock.c index 4ff806d71921..09d31a7dc68f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1447,6 +1447,15 @@ set_sndbuf: break; } + case SO_TXREHASH: + if (val < -1 || val > 1) { + ret = -EINVAL; + break; + } + /* Paired with READ_ONCE() in tcp_rtx_synack() */ + WRITE_ONCE(sk->sk_txrehash, (u8)val); + break; + default: ret = -ENOPROTOOPT; break; @@ -1834,6 +1843,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reserved_mem; break; + case SO_TXREHASH: + v.val = sk->sk_txrehash; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2266,6 +2279,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); + sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1); /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } @@ -2611,7 +2625,8 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, switch (cmsg->cmsg_type) { case SO_MARK: - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) && + !ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; @@ -3278,6 +3293,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; + sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 1827669eedd6..2d213c4011db 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1416,38 +1416,50 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) return NULL; } -static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - struct bpf_prog *old, u32 which) +static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog, + u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); - struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - pprog = &progs->msg_parser; + *pprog = &progs->msg_parser; break; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) case BPF_SK_SKB_STREAM_PARSER: - pprog = &progs->stream_parser; + *pprog = &progs->stream_parser; break; #endif case BPF_SK_SKB_STREAM_VERDICT: if (progs->skb_verdict) return -EBUSY; - pprog = &progs->stream_verdict; + *pprog = &progs->stream_verdict; break; case BPF_SK_SKB_VERDICT: if (progs->stream_verdict) return -EBUSY; - pprog = &progs->skb_verdict; + *pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + return 0; +} + +static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which) +{ + struct bpf_prog **pprog; + int ret; + + ret = sock_map_prog_lookup(map, &pprog, which); + if (ret) + return ret; + if (old) return psock_replace_prog(pprog, prog, old); @@ -1455,6 +1467,57 @@ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, return 0; } +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd; + struct bpf_prog **pprog; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + u32 id = 0; + int ret; + + if (attr->query.query_flags) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + rcu_read_lock(); + + ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type); + if (ret) + goto end; + + prog = *pprog; + prog_cnt = !prog ? 0 : 1; + + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + goto end; + + /* we do not hold the refcnt, the bpf prog may be released + * asynchronously and the id would be set to 0. + */ + id = data_race(prog->aux->id); + if (id == 0) + prog_cnt = 0; + +end: + rcu_read_unlock(); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) || + (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) || + copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + ret = -EFAULT; + + fdput(f); + return ret; +} + static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link) { switch (link->map->map_type) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7b4d485aac7a..dbeb8ecbcd98 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -593,6 +593,15 @@ static struct ctl_table netns_core_table[] = { .extra1 = SYSCTL_ZERO, .proc_handler = proc_dointvec_minmax }, + { + .procname = "txrehash", + .data = &init_net.core.sysctl_txrehash, + .maxlen = sizeof(u8), + .mode = 0644, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + .proc_handler = proc_dou8vec_minmax, + }, { } }; @@ -611,7 +620,7 @@ __setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); static __net_init int sysctl_core_net_init(struct net *net) { - struct ctl_table *tbl; + struct ctl_table *tbl, *tmp; tbl = netns_core_table; if (!net_eq(net, &init_net)) { @@ -619,7 +628,8 @@ static __net_init int sysctl_core_net_init(struct net *net) if (tbl == NULL) goto err_dup; - tbl[0].data = &net->core.sysctl_somaxconn; + for (tmp = tbl; tmp->procname; tmp++) + tmp->data += (char *)net - (char *)&init_net; /* Don't export any sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 7aba35504986..361df312ee7f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -162,8 +162,9 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) } /* Returns 0 on success, negative on failure */ -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id) +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size) { if (!dev) { WARN(1, "Missing net_device from driver"); @@ -185,11 +186,12 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->napi_id = napi_id; + xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } -EXPORT_SYMBOL_GPL(xdp_rxq_info_reg); +EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { @@ -369,8 +371,8 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, - struct xdp_buff *xdp) +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -406,12 +408,38 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, void xdp_return_frame(struct xdp_frame *xdpf) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, false, NULL); + } +out: __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdpf->mem, true, NULL); + } +out: __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); @@ -447,7 +475,7 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_mem_allocator *xa; if (mem->type != MEM_TYPE_PAGE_POOL) { - __xdp_return(xdpf->data, &xdpf->mem, false, NULL); + xdp_return_frame(xdpf); return; } @@ -466,12 +494,38 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); } + if (unlikely(xdp_frame_has_frags(xdpf))) { + struct skb_shared_info *sinfo; + int i; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + skb_frag_t *frag = &sinfo->frags[i]; + + bq->q[bq->count++] = skb_frag_address(frag); + if (bq->count == XDP_BULK_QUEUE_SIZE) + xdp_flush_frame_bulk(bq); + } + } bq->q[bq->count++] = xdpf->data; } EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); void xdp_return_buff(struct xdp_buff *xdp) { + struct skb_shared_info *sinfo; + int i; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_return(page_address(page), &xdp->rxq->mem, true, xdp); + } +out: __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } @@ -561,8 +615,14 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *skb, struct net_device *dev) { + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); unsigned int headroom, frame_size; void *hard_start; + u8 nr_frags; + + /* xdp frags frame */ + if (unlikely(xdp_frame_has_frags(xdpf))) + nr_frags = sinfo->nr_frags; /* Part of headroom was reserved to xdpf */ headroom = sizeof(*xdpf) + xdpf->headroom; @@ -582,6 +642,12 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, if (xdpf->metasize) skb_metadata_set(skb, xdpf->metasize); + if (unlikely(xdp_frame_has_frags(xdpf))) + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdpf->frame_sz, + xdp_frame_is_frag_pfmemalloc(xdpf)); + /* Essential SKB info: protocol and skb->dev */ skb->protocol = eth_type_trans(skb, dev); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 5183e627468d..671c377f0889 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -136,11 +136,6 @@ static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3) return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16); } -static inline u64 max48(const u64 seq1, const u64 seq2) -{ - return after48(seq1, seq2) ? seq1 : seq2; -} - /** * dccp_loss_count - Approximate the number of lost data packets in a burst loss * @s1: last known sequence number before the loss ('hole') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 0ea29270d7e5..ae662567a6cb 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1030,15 +1030,9 @@ static void __net_exit dccp_v4_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v4_ctl_sk); } -static void __net_exit dccp_v4_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET); -} - static struct pernet_operations dccp_v4_ops = { .init = dccp_v4_init_net, .exit = dccp_v4_exit_net, - .exit_batch = dccp_v4_exit_batch, .id = &dccp_v4_pernet_id, .size = sizeof(struct dccp_v4_pernet), }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index fa663518fa0e..eab3bd1ee9a0 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1115,15 +1115,9 @@ static void __net_exit dccp_v6_exit_net(struct net *net) inet_ctl_sock_destroy(pn->v6_ctl_sk); } -static void __net_exit dccp_v6_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&dccp_hashinfo, AF_INET6); -} - static struct pernet_operations dccp_v6_ops = { .init = dccp_v6_init_net, .exit = dccp_v6_exit_net, - .exit_batch = dccp_v6_exit_batch, .id = &dccp_v6_pernet_id, .size = sizeof(struct dccp_v6_pernet), }; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 91e7a2202697..64d805b27add 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -22,6 +22,7 @@ #include "feat.h" struct inet_timewait_death_row dccp_death_row = { + .tw_refcount = REFCOUNT_INIT(1), .sysctl_max_tw_buckets = NR_FILE * 2, .hashinfo = &dccp_hashinfo, }; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 3d21521453fe..909b045c9b11 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -15,6 +15,7 @@ #include <linux/of.h> #include <linux/of_net.h> #include <net/devlink.h> +#include <net/sch_generic.h> #include "dsa_priv.h" @@ -1064,9 +1065,18 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { if (dsa_port_is_cpu(dp)) { - err = dsa_master_setup(dp->master, dp); + struct net_device *master = dp->master; + bool admin_up = (master->flags & IFF_UP) && + !qdisc_tx_is_noop(master); + + err = dsa_master_setup(master, dp); if (err) return err; + + /* Replay master state event */ + dsa_tree_master_admin_state_change(dst, master, admin_up); + dsa_tree_master_oper_state_change(dst, master, + netif_oper_up(master)); } } @@ -1081,9 +1091,19 @@ static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) rtnl_lock(); - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - dsa_master_teardown(dp->master); + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_cpu(dp)) { + struct net_device *master = dp->master; + + /* Synthesizing an "admin down" state is sufficient for + * the switches to get a notification if the master is + * currently up and running. + */ + dsa_tree_master_admin_state_change(dst, master, false); + + dsa_master_teardown(master); + } + } rtnl_unlock(); } @@ -1279,6 +1299,52 @@ out_unlock: return err; } +static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, + struct net_device *master) +{ + struct dsa_notifier_master_state_info info; + struct dsa_port *cpu_dp = master->dsa_ptr; + + info.master = master; + info.operational = dsa_port_master_is_operational(cpu_dp); + + dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); +} + +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (up && cpu_dp->master_oper_up)) + notify = true; + + cpu_dp->master_admin_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up) +{ + struct dsa_port *cpu_dp = master->dsa_ptr; + bool notify = false; + + if ((dsa_port_master_is_operational(cpu_dp)) != + (cpu_dp->master_admin_up && up)) + notify = true; + + cpu_dp->master_oper_up = up; + + if (notify) + dsa_tree_master_state_change(dst, master); +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 760306f0012f..2bbfa9efe9f8 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -40,6 +40,7 @@ enum { DSA_NOTIFIER_TAG_PROTO_DISCONNECT, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, + DSA_NOTIFIER_MASTER_STATE_CHANGE, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -109,6 +110,12 @@ struct dsa_notifier_tag_8021q_vlan_info { u16 vid; }; +/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ +struct dsa_notifier_master_state_info { + const struct net_device *master; + bool operational; +}; + struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; @@ -482,6 +489,12 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, struct net_device *master, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); +void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); +void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *master, + bool up); unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 22241afcac81..2b5b0f294233 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2346,6 +2346,36 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, err = dsa_port_lag_change(dp, info->lower_state_info); return notifier_from_errno(err); } + case NETDEV_CHANGE: + case NETDEV_UP: { + /* Track state of master port. + * DSA driver may require the master port (and indirectly + * the tagger) to be available for some special operation. + */ + if (netdev_uses_dsa(dev)) { + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->ds->dst; + + /* Track when the master port is UP */ + dsa_tree_master_oper_state_change(dst, dev, + netif_oper_up(dev)); + + /* Track when the master port is ready and can accept + * packet. + * NETDEV_UP event is not enough to flag a port as ready. + * We also have to wait for linkwatch_do_dev to dev_activate + * and emit a NETDEV_CHANGE event. + * We check if a master port is ready by checking if the dev + * have a qdisc assigned and is not noop. + */ + dsa_tree_master_admin_state_change(dst, dev, + !qdisc_tx_is_noop(dev)); + + return NOTIFY_OK; + } + + return NOTIFY_DONE; + } case NETDEV_GOING_DOWN: { struct dsa_port *dp, *cpu_dp; struct dsa_switch_tree *dst; @@ -2357,6 +2387,8 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; + dsa_tree_master_admin_state_change(dst, dev, false); + list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) continue; diff --git a/net/dsa/switch.c b/net/dsa/switch.c index e3c7d2627a61..4866b58649e4 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -113,26 +113,15 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, return dsa_tag_8021q_bridge_join(ds, info); } -static int dsa_switch_bridge_leave(struct dsa_switch *ds, - struct dsa_notifier_bridge_info *info) +static int dsa_switch_sync_vlan_filtering(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) { - struct dsa_switch_tree *dst = ds->dst; struct netlink_ext_ack extack = {0}; bool change_vlan_filtering = false; bool vlan_filtering; struct dsa_port *dp; int err; - if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_leave) - ds->ops->port_bridge_leave(ds, info->port, info->bridge); - - if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_leave) - ds->ops->crosschip_bridge_leave(ds, info->tree_index, - info->sw_index, info->port, - info->bridge); - if (ds->needs_standalone_vlan_filtering && !br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; @@ -172,6 +161,31 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, return err; } + return 0; +} + +static int dsa_switch_bridge_leave(struct dsa_switch *ds, + struct dsa_notifier_bridge_info *info) +{ + struct dsa_switch_tree *dst = ds->dst; + int err; + + if (dst->index == info->tree_index && ds->index == info->sw_index && + ds->ops->port_bridge_leave) + ds->ops->port_bridge_leave(ds, info->port, info->bridge); + + if ((dst->index != info->tree_index || ds->index != info->sw_index) && + ds->ops->crosschip_bridge_leave) + ds->ops->crosschip_bridge_leave(ds, info->tree_index, + info->sw_index, info->port, + info->bridge); + + if (ds->dst->index == info->tree_index && ds->index == info->sw_index) { + err = dsa_switch_sync_vlan_filtering(ds, info); + if (err) + return err; + } + return dsa_tag_8021q_bridge_leave(ds, info); } @@ -683,6 +697,18 @@ dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, return 0; } +static int +dsa_switch_master_state_change(struct dsa_switch *ds, + struct dsa_notifier_master_state_info *info) +{ + if (!ds->ops->master_state_change) + return 0; + + ds->ops->master_state_change(ds, info->master, info->operational); + + return 0; +} + static int dsa_switch_event(struct notifier_block *nb, unsigned long event, void *info) { @@ -756,6 +782,9 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: err = dsa_switch_tag_8021q_vlan_del(ds, info); break; + case DSA_NOTIFIER_MASTER_STATE_CHANGE: + err = dsa_switch_master_state_change(ds, info); + break; default: err = -EOPNOTSUPP; break; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1ea9401b8ace..57d2e00f1e5d 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -4,30 +4,12 @@ */ #include <linux/etherdevice.h> +#include <linux/bitfield.h> +#include <net/dsa.h> +#include <linux/dsa/tag_qca.h> #include "dsa_priv.h" -#define QCA_HDR_LEN 2 -#define QCA_HDR_VERSION 0x2 - -#define QCA_HDR_RECV_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_RECV_VERSION_S 14 -#define QCA_HDR_RECV_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_RECV_PRIORITY_S 11 -#define QCA_HDR_RECV_TYPE_MASK GENMASK(10, 6) -#define QCA_HDR_RECV_TYPE_S 6 -#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) -#define QCA_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) - -#define QCA_HDR_XMIT_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_XMIT_VERSION_S 14 -#define QCA_HDR_XMIT_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_XMIT_PRIORITY_S 11 -#define QCA_HDR_XMIT_CONTROL_MASK GENMASK(10, 8) -#define QCA_HDR_XMIT_CONTROL_S 8 -#define QCA_HDR_XMIT_FROM_CPU BIT(7) -#define QCA_HDR_XMIT_DP_BIT_MASK GENMASK(6, 0) - static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -40,8 +22,9 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) phdr = dsa_etype_header_pos_tx(skb); /* Set the version field, and set destination port information */ - hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); + hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION); + hdr |= QCA_HDR_XMIT_FROM_CPU; + hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(dp->index)); *phdr = htons(hdr); @@ -50,10 +33,17 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 ver; - u16 hdr; - int port; + struct qca_tagger_data *tagger_data; + struct dsa_port *dp = dev->dsa_ptr; + struct dsa_switch *ds = dp->ds; + u8 ver, pk_type; __be16 *phdr; + int port; + u16 hdr; + + BUILD_BUG_ON(sizeof(struct qca_mgmt_ethhdr) != QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN); + + tagger_data = ds->tagger_data; if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) return NULL; @@ -62,16 +52,33 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) hdr = ntohs(*phdr); /* Make sure the version is correct */ - ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S; + ver = FIELD_GET(QCA_HDR_RECV_VERSION, hdr); if (unlikely(ver != QCA_HDR_VERSION)) return NULL; + /* Get pk type */ + pk_type = FIELD_GET(QCA_HDR_RECV_TYPE, hdr); + + /* Ethernet mgmt read/write packet */ + if (pk_type == QCA_HDR_RECV_TYPE_RW_REG_ACK) { + if (likely(tagger_data->rw_reg_ack_handler)) + tagger_data->rw_reg_ack_handler(ds, skb); + return NULL; + } + + /* Ethernet MIB counter packet */ + if (pk_type == QCA_HDR_RECV_TYPE_MIB) { + if (likely(tagger_data->mib_autocast_handler)) + tagger_data->mib_autocast_handler(ds, skb); + return NULL; + } + /* Remove QCA tag and recalculate checksum */ skb_pull_rcsum(skb, QCA_HDR_LEN); dsa_strip_etype_header(skb, QCA_HDR_LEN); /* Get source port information */ - port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); + port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr); skb->dev = dsa_master_find_slave(dev, 0, port); if (!skb->dev) @@ -80,12 +87,34 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) return skb; } +static int qca_tag_connect(struct dsa_switch *ds) +{ + struct qca_tagger_data *tagger_data; + + tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL); + if (!tagger_data) + return -ENOMEM; + + ds->tagger_data = tagger_data; + + return 0; +} + +static void qca_tag_disconnect(struct dsa_switch *ds) +{ + kfree(ds->tagger_data); + ds->tagger_data = NULL; +} + static const struct dsa_device_ops qca_netdev_ops = { .name = "qca", .proto = DSA_TAG_PROTO_QCA, + .connect = qca_tag_connect, + .disconnect = qca_tag_disconnect, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, .needed_headroom = QCA_HDR_LEN, + .promisc_on_master = true, }; MODULE_LICENSE("GPL"); diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index c1d5f5e0fdc9..18a5035d3bee 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -53,7 +53,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ nla_total_size(sizeof(u32)) + /* _RINGS_TX */ - nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u32)) + /* _RINGS_RX_BUF_LEN */ + nla_total_size(sizeof(u8)); /* _RINGS_TCP_DATA_SPLIT */ } static int rings_fill_reply(struct sk_buff *skb, @@ -61,9 +62,11 @@ static int rings_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct rings_reply_data *data = RINGS_REPDATA(reply_base); - const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam; + const struct kernel_ethtool_ringparam *kr = &data->kernel_ringparam; const struct ethtool_ringparam *ringparam = &data->ringparam; + WARN_ON(kr->tcp_data_split > ETHTOOL_TCP_DATA_SPLIT_ENABLED); + if ((ringparam->rx_max_pending && (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_MAX, ringparam->rx_max_pending) || @@ -84,9 +87,11 @@ static int rings_fill_reply(struct sk_buff *skb, ringparam->tx_max_pending) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX, ringparam->tx_pending))) || - (kernel_ringparam->rx_buf_len && - (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, - kernel_ringparam->rx_buf_len)))) + (kr->rx_buf_len && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, kr->rx_buf_len))) || + (kr->tcp_data_split && + (nla_put_u8(skb, ETHTOOL_A_RINGS_TCP_DATA_SPLIT, + kr->tcp_data_split)))) return -EMSGSIZE; return 0; diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 99f3af1a9d4d..fe6094e9a2db 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/debugfs.h> +#include <linux/jhash.h> #include "hsr_main.h" #include "hsr_framereg.h" @@ -28,6 +29,7 @@ hsr_node_table_show(struct seq_file *sfp, void *data) { struct hsr_priv *priv = (struct hsr_priv *)sfp->private; struct hsr_node *node; + int i; seq_printf(sfp, "Node Table entries for (%s) device\n", (priv->prot_version == PRP_V1 ? "PRP" : "HSR")); @@ -39,22 +41,28 @@ hsr_node_table_show(struct seq_file *sfp, void *data) seq_puts(sfp, "DAN-H\n"); rcu_read_lock(); - list_for_each_entry_rcu(node, &priv->node_db, mac_list) { - /* skip self node */ - if (hsr_addr_is_self(priv, node->macaddress_A)) - continue; - seq_printf(sfp, "%pM ", &node->macaddress_A[0]); - seq_printf(sfp, "%pM ", &node->macaddress_B[0]); - seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_A]); - seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_B]); - seq_printf(sfp, "%14x, ", node->addr_B_port); - - if (priv->prot_version == PRP_V1) - seq_printf(sfp, "%5x, %5x, %5x\n", - node->san_a, node->san_b, - (node->san_a == 0 && node->san_b == 0)); - else - seq_printf(sfp, "%5x\n", 1); + + for (i = 0 ; i < priv->hash_buckets; i++) { + hlist_for_each_entry_rcu(node, &priv->node_db[i], mac_list) { + /* skip self node */ + if (hsr_addr_is_self(priv, node->macaddress_A)) + continue; + seq_printf(sfp, "%pM ", &node->macaddress_A[0]); + seq_printf(sfp, "%pM ", &node->macaddress_B[0]); + seq_printf(sfp, "%10lx, ", + node->time_in[HSR_PT_SLAVE_A]); + seq_printf(sfp, "%10lx, ", + node->time_in[HSR_PT_SLAVE_B]); + seq_printf(sfp, "%14x, ", node->addr_B_port); + + if (priv->prot_version == PRP_V1) + seq_printf(sfp, "%5x, %5x, %5x\n", + node->san_a, node->san_b, + (node->san_a == 0 && + node->san_b == 0)); + else + seq_printf(sfp, "%5x\n", 1); + } } rcu_read_unlock(); return 0; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e57fdad9ef94..7f250216433d 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -485,12 +485,16 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], { bool unregister = false; struct hsr_priv *hsr; - int res; + int res, i; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); - INIT_LIST_HEAD(&hsr->node_db); - INIT_LIST_HEAD(&hsr->self_node_db); + INIT_HLIST_HEAD(&hsr->self_node_db); + hsr->hash_buckets = HSR_HSIZE; + get_random_bytes(&hsr->hash_seed, sizeof(hsr->hash_seed)); + for (i = 0; i < hsr->hash_buckets; i++) + INIT_HLIST_HEAD(&hsr->node_db[i]); + spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index e59cbb4f0cd1..5bf357734b11 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -570,20 +570,23 @@ static int fill_frame_info(struct hsr_frame_info *frame, struct ethhdr *ethhdr; __be16 proto; int ret; + u32 hash; /* Check if skb contains ethhdr */ if (skb->mac_len < sizeof(struct ethhdr)) return -EINVAL; memset(frame, 0, sizeof(*frame)); + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + hash = hsr_mac_hash(port->hsr, ethhdr->h_source); frame->is_supervision = is_supervision_frame(port->hsr, skb); - frame->node_src = hsr_get_node(port, &hsr->node_db, skb, + frame->node_src = hsr_get_node(port, &hsr->node_db[hash], skb, frame->is_supervision, port->type); if (!frame->node_src) return -1; /* Unknown node and !is_supervision, or no mem */ - ethhdr = (struct ethhdr *)skb_mac_header(skb); frame->is_vlan = false; proto = ethhdr->h_proto; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 0775f0f95dbf..b3c6ffa1894d 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -15,11 +15,28 @@ #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/rculist.h> +#include <linux/jhash.h> #include "hsr_main.h" #include "hsr_framereg.h" #include "hsr_netlink.h" -/* TODO: use hash lists for mac addresses (linux/jhash.h)? */ +u32 hsr_mac_hash(struct hsr_priv *hsr, const unsigned char *addr) +{ + u32 hash = jhash(addr, ETH_ALEN, hsr->hash_seed); + + return reciprocal_scale(hash, hsr->hash_buckets); +} + +struct hsr_node *hsr_node_get_first(struct hlist_head *head) +{ + struct hlist_node *first; + + first = rcu_dereference(hlist_first_rcu(head)); + if (first) + return hlist_entry(first, struct hsr_node, mac_list); + + return NULL; +} /* seq_nr_after(a, b) - return true if a is after (higher in sequence than) b, * false otherwise. @@ -42,8 +59,7 @@ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_node *node; - node = list_first_or_null_rcu(&hsr->self_node_db, struct hsr_node, - mac_list); + node = hsr_node_get_first(&hsr->self_node_db); if (!node) { WARN_ONCE(1, "HSR: No self node\n"); return false; @@ -59,12 +75,12 @@ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) /* Search for mac entry. Caller must hold rcu read lock. */ -static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, +static struct hsr_node *find_node_by_addr_A(struct hlist_head *node_db, const unsigned char addr[ETH_ALEN]) { struct hsr_node *node; - list_for_each_entry_rcu(node, node_db, mac_list) { + hlist_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, addr)) return node; } @@ -79,7 +95,7 @@ int hsr_create_self_node(struct hsr_priv *hsr, const unsigned char addr_a[ETH_ALEN], const unsigned char addr_b[ETH_ALEN]) { - struct list_head *self_node_db = &hsr->self_node_db; + struct hlist_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -90,14 +106,13 @@ int hsr_create_self_node(struct hsr_priv *hsr, ether_addr_copy(node->macaddress_B, addr_b); spin_lock_bh(&hsr->list_lock); - oldnode = list_first_or_null_rcu(self_node_db, - struct hsr_node, mac_list); + oldnode = hsr_node_get_first(self_node_db); if (oldnode) { - list_replace_rcu(&oldnode->mac_list, &node->mac_list); + hlist_replace_rcu(&oldnode->mac_list, &node->mac_list); spin_unlock_bh(&hsr->list_lock); kfree_rcu(oldnode, rcu_head); } else { - list_add_tail_rcu(&node->mac_list, self_node_db); + hlist_add_tail_rcu(&node->mac_list, self_node_db); spin_unlock_bh(&hsr->list_lock); } @@ -106,25 +121,25 @@ int hsr_create_self_node(struct hsr_priv *hsr, void hsr_del_self_node(struct hsr_priv *hsr) { - struct list_head *self_node_db = &hsr->self_node_db; + struct hlist_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; spin_lock_bh(&hsr->list_lock); - node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); + node = hsr_node_get_first(self_node_db); if (node) { - list_del_rcu(&node->mac_list); + hlist_del_rcu(&node->mac_list); kfree_rcu(node, rcu_head); } spin_unlock_bh(&hsr->list_lock); } -void hsr_del_nodes(struct list_head *node_db) +void hsr_del_nodes(struct hlist_head *node_db) { struct hsr_node *node; - struct hsr_node *tmp; + struct hlist_node *tmp; - list_for_each_entry_safe(node, tmp, node_db, mac_list) - kfree(node); + hlist_for_each_entry_safe(node, tmp, node_db, mac_list) + kfree_rcu(node, rcu_head); } void prp_handle_san_frame(bool san, enum hsr_port_type port, @@ -145,7 +160,7 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, * originating from the newly added node. */ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, - struct list_head *node_db, + struct hlist_head *node_db, unsigned char addr[], u16 seq_out, bool san, enum hsr_port_type rx_port) @@ -175,14 +190,14 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, hsr->proto_ops->handle_san_frame(san, rx_port, new_node); spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list, - lockdep_is_held(&hsr->list_lock)) { + hlist_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) goto out; } - list_add_tail_rcu(&new_node->mac_list, node_db); + hlist_add_tail_rcu(&new_node->mac_list, node_db); spin_unlock_bh(&hsr->list_lock); return new_node; out: @@ -202,7 +217,7 @@ void prp_update_san_info(struct hsr_node *node, bool is_sup) /* Get the hsr_node from which 'skb' was sent. */ -struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, +struct hsr_node *hsr_get_node(struct hsr_port *port, struct hlist_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port) { @@ -218,7 +233,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, ethhdr = (struct ethhdr *)skb_mac_header(skb); - list_for_each_entry_rcu(node, node_db, mac_list) { + hlist_for_each_entry_rcu(node, node_db, mac_list) { if (ether_addr_equal(node->macaddress_A, ethhdr->h_source)) { if (hsr->proto_ops->update_san_info) hsr->proto_ops->update_san_info(node, is_sup); @@ -268,11 +283,12 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) struct hsr_sup_tlv *hsr_sup_tlv; struct hsr_node *node_real; struct sk_buff *skb = NULL; - struct list_head *node_db; + struct hlist_head *node_db; struct ethhdr *ethhdr; int i; unsigned int pull_size = 0; unsigned int total_pull_size = 0; + u32 hash; /* Here either frame->skb_hsr or frame->skb_prp should be * valid as supervision frame always will have protocol @@ -310,11 +326,13 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) hsr_sp = (struct hsr_sup_payload *)skb->data; /* Merge node_curr (registered on macaddress_B) into node_real */ - node_db = &port_rcv->hsr->node_db; - node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); + node_db = port_rcv->hsr->node_db; + hash = hsr_mac_hash(hsr, hsr_sp->macaddress_A); + node_real = find_node_by_addr_A(&node_db[hash], hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, &node_db[hash], + hsr_sp->macaddress_A, HSR_SEQNR_START - 1, true, port_rcv->type); if (!node_real) @@ -348,7 +366,8 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) hsr_sp = (struct hsr_sup_payload *)skb->data; /* Check if redbox mac and node mac are equal. */ - if (!ether_addr_equal(node_real->macaddress_A, hsr_sp->macaddress_A)) { + if (!ether_addr_equal(node_real->macaddress_A, + hsr_sp->macaddress_A)) { /* This is a redbox supervision frame for a VDAN! */ goto done; } @@ -368,7 +387,7 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); - list_del_rcu(&node_curr->mac_list); + hlist_del_rcu(&node_curr->mac_list); spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); @@ -406,6 +425,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, struct hsr_port *port) { struct hsr_node *node_dst; + u32 hash; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: Mac header not set\n", __func__); @@ -415,7 +435,8 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, if (!is_unicast_ether_addr(eth_hdr(skb)->h_dest)) return; - node_dst = find_node_by_addr_A(&port->hsr->node_db, + hash = hsr_mac_hash(port->hsr, eth_hdr(skb)->h_dest); + node_dst = find_node_by_addr_A(&port->hsr->node_db[hash], eth_hdr(skb)->h_dest); if (!node_dst) { if (net_ratelimit()) @@ -491,59 +512,73 @@ static struct hsr_port *get_late_port(struct hsr_priv *hsr, void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); + struct hlist_node *tmp; struct hsr_node *node; - struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; + int i; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { - /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] - * nor time_in[HSR_PT_SLAVE_B], will ever be updated for - * the master port. Thus the master node will be repeatedly - * pruned leading to packet loss. - */ - if (hsr_addr_is_self(hsr, node->macaddress_A)) - continue; - - /* Shorthand */ - time_a = node->time_in[HSR_PT_SLAVE_A]; - time_b = node->time_in[HSR_PT_SLAVE_B]; - - /* Check for timestamps old enough to risk wrap-around */ - if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) - node->time_in_stale[HSR_PT_SLAVE_A] = true; - if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) - node->time_in_stale[HSR_PT_SLAVE_B] = true; - - /* Get age of newest frame from node. - * At least one time_in is OK here; nodes get pruned long - * before both time_ins can get stale - */ - timestamp = time_a; - if (node->time_in_stale[HSR_PT_SLAVE_A] || - (!node->time_in_stale[HSR_PT_SLAVE_B] && - time_after(time_b, time_a))) - timestamp = time_b; - - /* Warn of ring error only as long as we get frames at all */ - if (time_is_after_jiffies(timestamp + - msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { - rcu_read_lock(); - port = get_late_port(hsr, node); - if (port) - hsr_nl_ringerror(hsr, node->macaddress_A, port); - rcu_read_unlock(); - } - /* Prune old entries */ - if (time_is_before_jiffies(timestamp + - msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { - hsr_nl_nodedown(hsr, node->macaddress_A); - list_del_rcu(&node->mac_list); - /* Note that we need to free this entry later: */ - kfree_rcu(node, rcu_head); + for (i = 0; i < hsr->hash_buckets; i++) { + hlist_for_each_entry_safe(node, tmp, &hsr->node_db[i], + mac_list) { + /* Don't prune own node. + * Neither time_in[HSR_PT_SLAVE_A] + * nor time_in[HSR_PT_SLAVE_B], will ever be updated + * for the master port. Thus the master node will be + * repeatedly pruned leading to packet loss. + */ + if (hsr_addr_is_self(hsr, node->macaddress_A)) + continue; + + /* Shorthand */ + time_a = node->time_in[HSR_PT_SLAVE_A]; + time_b = node->time_in[HSR_PT_SLAVE_B]; + + /* Check for timestamps old enough to + * risk wrap-around + */ + if (time_after(jiffies, time_a + MAX_JIFFY_OFFSET / 2)) + node->time_in_stale[HSR_PT_SLAVE_A] = true; + if (time_after(jiffies, time_b + MAX_JIFFY_OFFSET / 2)) + node->time_in_stale[HSR_PT_SLAVE_B] = true; + + /* Get age of newest frame from node. + * At least one time_in is OK here; nodes get pruned + * long before both time_ins can get stale + */ + timestamp = time_a; + if (node->time_in_stale[HSR_PT_SLAVE_A] || + (!node->time_in_stale[HSR_PT_SLAVE_B] && + time_after(time_b, time_a))) + timestamp = time_b; + + /* Warn of ring error only as long as we get + * frames at all + */ + if (time_is_after_jiffies(timestamp + + msecs_to_jiffies(1.5 * MAX_SLAVE_DIFF))) { + rcu_read_lock(); + port = get_late_port(hsr, node); + if (port) + hsr_nl_ringerror(hsr, + node->macaddress_A, + port); + rcu_read_unlock(); + } + + /* Prune old entries */ + if (time_is_before_jiffies(timestamp + + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { + hsr_nl_nodedown(hsr, node->macaddress_A); + hlist_del_rcu(&node->mac_list); + /* Note that we need to free this + * entry later: + */ + kfree_rcu(node, rcu_head); + } } } spin_unlock_bh(&hsr->list_lock); @@ -557,17 +592,19 @@ void *hsr_get_next_node(struct hsr_priv *hsr, void *_pos, unsigned char addr[ETH_ALEN]) { struct hsr_node *node; + u32 hash; + + hash = hsr_mac_hash(hsr, addr); if (!_pos) { - node = list_first_or_null_rcu(&hsr->node_db, - struct hsr_node, mac_list); + node = hsr_node_get_first(&hsr->node_db[hash]); if (node) ether_addr_copy(addr, node->macaddress_A); return node; } node = _pos; - list_for_each_entry_continue_rcu(node, &hsr->node_db, mac_list) { + hlist_for_each_entry_continue_rcu(node, mac_list) { ether_addr_copy(addr, node->macaddress_A); return node; } @@ -587,8 +624,11 @@ int hsr_get_node_data(struct hsr_priv *hsr, struct hsr_node *node; struct hsr_port *port; unsigned long tdiff; + u32 hash; + + hash = hsr_mac_hash(hsr, addr); - node = find_node_by_addr_A(&hsr->node_db, addr); + node = find_node_by_addr_A(&hsr->node_db[hash], addr); if (!node) return -ENOENT; diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index bdbb8c822ba1..d7cce6b161e3 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -28,9 +28,11 @@ struct hsr_frame_info { bool is_from_san; }; +u32 hsr_mac_hash(struct hsr_priv *hsr, const unsigned char *addr); +struct hsr_node *hsr_node_get_first(struct hlist_head *head); void hsr_del_self_node(struct hsr_priv *hsr); -void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, +void hsr_del_nodes(struct hlist_head *node_db); +struct hsr_node *hsr_get_node(struct hsr_port *port, struct hlist_head *node_db, struct sk_buff *skb, bool is_sup, enum hsr_port_type rx_port); void hsr_handle_sup_frame(struct hsr_frame_info *frame); @@ -68,7 +70,7 @@ void prp_handle_san_frame(bool san, enum hsr_port_type port, void prp_update_san_info(struct hsr_node *node, bool is_sup); struct hsr_node { - struct list_head mac_list; + struct hlist_node mac_list; unsigned char macaddress_A[ETH_ALEN]; unsigned char macaddress_B[ETH_ALEN]; /* Local slave through which AddrB frames are received from this node */ diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 043e4e9a1694..ca556bda3467 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -63,6 +63,9 @@ struct hsr_tag { #define HSR_V1_SUP_LSDUSIZE 52 +#define HSR_HSIZE_SHIFT 8 +#define HSR_HSIZE BIT(HSR_HSIZE_SHIFT) + /* The helper functions below assumes that 'path' occupies the 4 most * significant bits of the 16-bit field shared by 'path' and 'LSDU_size' (or * equivalently, the 4 most significant bits of HSR tag byte 14). @@ -201,8 +204,8 @@ struct hsr_proto_ops { struct hsr_priv { struct rcu_head rcu_head; struct list_head ports; - struct list_head node_db; /* Known HSR nodes */ - struct list_head self_node_db; /* MACs of slaves */ + struct hlist_head node_db[HSR_HSIZE]; /* Known HSR nodes */ + struct hlist_head self_node_db; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ struct timer_list prune_timer; int announce_count; @@ -212,6 +215,8 @@ struct hsr_priv { spinlock_t seqnr_lock; /* locking for sequence_nr */ spinlock_t list_lock; /* locking for node list */ struct hsr_proto_ops *proto_ops; + u32 hash_buckets; + u32 hash_seed; #define PRP_LAN_ID 0x5 /* 0x1010 for A and 0x1011 for B. Bit 0 is set * based on SLAVE_A or SLAVE_B */ @@ -259,11 +264,6 @@ static inline u16 prp_get_skb_sequence_nr(struct prp_rct *rct) return ntohs(rct->sequence_nr); } -static inline u16 get_prp_lan_id(struct prp_rct *rct) -{ - return ntohs(rct->lan_id_and_LSDU_size) >> 12; -} - /* assume there is a valid rct */ static inline bool prp_check_lsdu_size(struct sk_buff *skb, struct prp_rct *rct, diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index f3c8f91dbe2c..1405c037cf7a 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -105,6 +105,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, static void hsr_dellink(struct net_device *dev, struct list_head *head) { struct hsr_priv *hsr = netdev_priv(dev); + int i; del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); @@ -113,7 +114,8 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) hsr_del_ports(hsr); hsr_del_self_node(hsr); - hsr_del_nodes(&hsr->node_db); + for (i = 0; i < hsr->hash_buckets; i++) + hsr_del_nodes(&hsr->node_db[i]); unregister_netdevice_queue(dev, head); } diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 2cf62718a282..2c087b7f17c5 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -47,6 +47,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> +#include <linux/if_arp.h> #include <net/ipv6.h> diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 277124f206e0..e0b072aecf0f 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1441,7 +1441,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1634,7 +1634,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1812,7 +1812,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1988,7 +1988,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index de610cb83694..b60c9fd7147e 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#include <linux/init.h> #include <linux/types.h> #include <linux/bpf_verifier.h> #include <linux/bpf.h> @@ -212,26 +213,23 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, } } -BTF_SET_START(bpf_tcp_ca_kfunc_ids) +BTF_SET_START(bpf_tcp_ca_check_kfunc_ids) BTF_ID(func, tcp_reno_ssthresh) BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) -BTF_SET_END(bpf_tcp_ca_kfunc_ids) +BTF_SET_END(bpf_tcp_ca_check_kfunc_ids) -static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner) -{ - if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id)) - return true; - return bpf_check_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, kfunc_btf_id, owner); -} +static const struct btf_kfunc_id_set bpf_tcp_ca_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_tcp_ca_check_kfunc_ids, +}; static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { .get_func_proto = bpf_tcp_ca_get_func_proto, .is_valid_access = bpf_tcp_ca_is_valid_access, .btf_struct_access = bpf_tcp_ca_btf_struct_access, - .check_kfunc_call = bpf_tcp_ca_check_kfunc_call, }; static int bpf_tcp_ca_init_member(const struct btf_type *t, @@ -300,3 +298,9 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .init = bpf_tcp_ca_init, .name = "tcp_congestion_ops", }; + +static int __init bpf_tcp_ca_kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_tcp_ca_kfunc_set); +} +late_initcall(bpf_tcp_ca_kfunc_init); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 4d61ddd8a0ec..c60e1d1ed2b0 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -32,6 +32,7 @@ #include <linux/list.h> #include <linux/slab.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -735,8 +736,16 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); + + if (!inet_validate_dscp(rtm->rtm_tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); + err = -EINVAL; + goto errout; + } + cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); + cfg->fc_dst_len = rtm->rtm_dst_len; - cfg->fc_tos = rtm->rtm_tos; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index e184bcb19943..a63014b54809 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -4,13 +4,14 @@ #include <linux/types.h> #include <linux/list.h> +#include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/nexthop.h> struct fib_alias { struct hlist_node fa_list; struct fib_info *fa_info; - u8 fa_tos; + dscp_t fa_dscp; u8 fa_type; u8 fa_state; u8 fa_slen; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index e0b6c8b6de57..117c48571cf0 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/export.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp.h> @@ -35,7 +36,7 @@ struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; - u8 tos; + dscp_t dscp; __be32 src; __be32 srcmask; __be32 dst; @@ -49,7 +50,7 @@ static bool fib4_rule_matchall(const struct fib_rule *rule) { struct fib4_rule *r = container_of(rule, struct fib4_rule, common); - if (r->dst_len || r->src_len || r->tos) + if (r->dst_len || r->src_len || r->dscp) return false; return fib_rule_matchall(rule); } @@ -185,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, ((daddr ^ r->dst) & r->dstmask)) return 0; - if (r->tos && (r->tos != fl4->flowi4_tos)) + if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) @@ -225,10 +226,12 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; - if (frh->tos & ~IPTOS_TOS_MASK) { - NL_SET_ERR_MSG(extack, "Invalid tos"); + if (!inet_validate_dscp(frh->tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); goto errout; } + rule4->dscp = inet_dsfield_to_dscp(frh->tos); /* split local/main if they are not already split */ err = fib_unmerge(net); @@ -270,7 +273,6 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; rule4->dstmask = inet_make_mask(rule4->dst_len); - rule4->tos = frh->tos; net->ipv4.fib_has_custom_rules = true; @@ -313,7 +315,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule4->dst_len != frh->dst_len)) return 0; - if (frh->tos && (rule4->tos != frh->tos)) + if (frh->tos && inet_dscp_to_dsfield(rule4->dscp) != frh->tos) return 0; #ifdef CONFIG_IP_ROUTE_CLASSID @@ -337,7 +339,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; - frh->tos = rule4->tos; + frh->tos = inet_dscp_to_dsfield(rule4->dscp); if ((rule4->dst_len && nla_put_in_addr(skb, FRA_DST, rule4->dst)) || diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b4589861b84c..c9c4f2f66b38 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -32,6 +32,7 @@ #include <linux/hash.h> #include <net/arp.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -523,7 +524,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, fri.tb_id = tb_id; fri.dst = key; fri.dst_len = dst_len; - fri.tos = fa->fa_tos; + fri.tos = inet_dscp_to_dsfield(fa->fa_dscp); fri.type = fa->fa_type; fri.offload = fa->offload; fri.trap = fa->trap; @@ -1257,34 +1258,13 @@ fib_info_laddrhash_bucket(const struct net *net, __be32 val) return &fib_info_laddrhash[slot]; } -static struct hlist_head *fib_info_hash_alloc(int bytes) -{ - if (bytes <= PAGE_SIZE) - return kzalloc(bytes, GFP_KERNEL); - else - return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, - get_order(bytes)); -} - -static void fib_info_hash_free(struct hlist_head *hash, int bytes) -{ - if (!hash) - return; - - if (bytes <= PAGE_SIZE) - kfree(hash); - else - free_pages((unsigned long) hash, get_order(bytes)); -} - static void fib_info_hash_move(struct hlist_head *new_info_hash, struct hlist_head *new_laddrhash, unsigned int new_size) { struct hlist_head *old_info_hash, *old_laddrhash; unsigned int old_size = fib_info_hash_size; - unsigned int i, bytes; + unsigned int i; spin_lock_bh(&fib_info_lock); old_info_hash = fib_info_hash; @@ -1325,9 +1305,8 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash, spin_unlock_bh(&fib_info_lock); - bytes = old_size * sizeof(struct hlist_head *); - fib_info_hash_free(old_info_hash, bytes); - fib_info_hash_free(old_laddrhash, bytes); + kvfree(old_info_hash); + kvfree(old_laddrhash); } __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, @@ -1444,19 +1423,19 @@ struct fib_info *fib_create_info(struct fib_config *cfg, unsigned int new_size = fib_info_hash_size << 1; struct hlist_head *new_info_hash; struct hlist_head *new_laddrhash; - unsigned int bytes; + size_t bytes; if (!new_size) new_size = 16; - bytes = new_size * sizeof(struct hlist_head *); - new_info_hash = fib_info_hash_alloc(bytes); - new_laddrhash = fib_info_hash_alloc(bytes); + bytes = (size_t)new_size * sizeof(struct hlist_head *); + new_info_hash = kvzalloc(bytes, GFP_KERNEL); + new_laddrhash = kvzalloc(bytes, GFP_KERNEL); if (!new_info_hash || !new_laddrhash) { - fib_info_hash_free(new_info_hash, bytes); - fib_info_hash_free(new_laddrhash, bytes); - } else + kvfree(new_info_hash); + kvfree(new_laddrhash); + } else { fib_info_hash_move(new_info_hash, new_laddrhash, new_size); - + } if (!fib_info_hash_size) goto failure; } @@ -2061,7 +2040,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) int order = -1, last_idx = -1; struct fib_alias *fa, *fa1 = NULL; u32 last_prio = res->fi->fib_priority; - u8 last_tos = 0; + dscp_t last_dscp = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; @@ -2069,19 +2048,20 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (fa->fa_slen != slen) continue; - if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + if (fa->fa_dscp && + fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos)) continue; if (fa->tb_id != tb->tb_id) continue; if (next_fi->fib_priority > last_prio && - fa->fa_tos == last_tos) { - if (last_tos) + fa->fa_dscp == last_dscp) { + if (last_dscp) continue; break; } if (next_fi->fib_flags & RTNH_F_DEAD) continue; - last_tos = fa->fa_tos; + last_dscp = fa->fa_dscp; last_prio = next_fi->fib_priority; if (next_fi->fib_scope != res->scope || diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 8060524f4256..c05cd105e95e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -61,6 +61,7 @@ #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> +#include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> @@ -81,7 +82,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, - .tos = fa->fa_tos, + .tos = inet_dscp_to_dsfield(fa->fa_dscp), .type = fa->fa_type, .tb_id = fa->tb_id, }; @@ -98,7 +99,7 @@ static int call_fib_entry_notifiers(struct net *net, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, - .tos = fa->fa_tos, + .tos = inet_dscp_to_dsfield(fa->fa_dscp), .type = fa->fa_type, .tb_id = fa->tb_id, }; @@ -973,13 +974,13 @@ static struct key_vector *fib_find_node(struct trie *t, return n; } -/* Return the first fib alias matching TOS with +/* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching - * fib alias, regardless of TOS and priority. + * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, - u8 tos, u32 prio, u32 tb_id, + dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; @@ -988,6 +989,10 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, return NULL; hlist_for_each_entry(fa, fah, fa_list) { + /* Avoid Sparse warning when using dscp_t in inequalities */ + u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); + u8 __dscp = inet_dscp_to_dsfield(dscp); + if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) @@ -998,9 +1003,9 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, break; if (find_first) return fa; - if (fa->fa_tos > tos) + if (__fa_dscp > __dscp) continue; - if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) + if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } @@ -1027,8 +1032,8 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && - fa->fa_tos == fri->tos && fa->fa_info == fri->fi && - fa->fa_type == fri->type) + fa->fa_dscp == inet_dsfield_to_dscp(fri->tos) && + fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } @@ -1210,7 +1215,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; - u8 tos = cfg->fc_tos; + dscp_t dscp; u32 key; int err; @@ -1227,12 +1232,13 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto err; } + dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); - fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, + fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias - * with the same keys [prefix,tos,priority], if such key already + * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and @@ -1240,7 +1246,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, * of the new alias. */ - if (fa && fa->fa_tos == tos && + if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; @@ -1260,7 +1266,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || - (fa->fa_tos != tos)) + (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; @@ -1288,7 +1294,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto out; fi_drop = fa->fa_info; - new_fa->fa_tos = fa->fa_tos; + new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; @@ -1351,7 +1357,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, goto out; new_fa->fa_info = fi; - new_fa->fa_tos = tos; + new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; @@ -1567,7 +1573,8 @@ found: if (index >= (1ul << fa->fa_slen)) continue; } - if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos) + if (fa->fa_dscp && + inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) continue; if (fi->fib_dead) continue; @@ -1703,7 +1710,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; - u8 tos = cfg->fc_tos; + dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); @@ -1715,11 +1722,13 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!l) return -ESRCH; - fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); + dscp = cfg->fc_dscp; + fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; - pr_debug("Deleting %08x/%d tos=%d t=%p\n", key, plen, tos, t); + pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, + inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { @@ -1727,7 +1736,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || - (fa->fa_tos != tos)) + (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && @@ -2295,7 +2304,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; - fri.tos = fa->fa_tos; + fri.tos = inet_dscp_to_dsfield(fa->fa_dscp); fri.type = fa->fa_type; fri.offload = fa->offload; fri.trap = fa->trap; @@ -2807,8 +2816,9 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); - if (fa->fa_tos) - seq_printf(seq, " tos=%d", fa->fa_tos); + if (fa->fa_dscp) + seq_printf(seq, " tos=%d", + inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index b7e277d8a84d..72a375c7f417 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -192,24 +192,14 @@ struct icmp_control { static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1]; -/* - * The ICMP socket(s). This is the most convenient way to flow control - * our ICMP output as well as maintain a clean interface throughout - * all layers. All Socketless IP sends will soon be gone. - * - * On SMP we have one ICMP socket per-cpu. - */ -static struct sock *icmp_sk(struct net *net) -{ - return this_cpu_read(*net->ipv4.icmp_sk); -} +static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk); /* Called with BH disabled */ static inline struct sock *icmp_xmit_lock(struct net *net) { struct sock *sk; - sk = icmp_sk(net); + sk = this_cpu_read(ipv4_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path signals a @@ -217,11 +207,13 @@ static inline struct sock *icmp_xmit_lock(struct net *net) */ return NULL; } + sock_net_set(sk, net); return sk; } static inline void icmp_xmit_unlock(struct sock *sk) { + sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } @@ -363,14 +355,13 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, return 0; } -static void icmp_push_reply(struct icmp_bxm *icmp_param, +static void icmp_push_reply(struct sock *sk, + struct icmp_bxm *icmp_param, struct flowi4 *fl4, struct ipcm_cookie *ipc, struct rtable **rt) { - struct sock *sk; struct sk_buff *skb; - sk = icmp_sk(dev_net((*rt)->dst.dev)); if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, @@ -452,7 +443,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) if (IS_ERR(rt)) goto out_unlock; if (icmpv4_xrlim_allow(net, rt, &fl4, type, code)) - icmp_push_reply(icmp_param, &fl4, &ipc, &rt); + icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); @@ -766,7 +757,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!fl4.saddr) fl4.saddr = htonl(INADDR_DUMMY); - icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); + icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: @@ -1434,46 +1425,8 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = { }, }; -static void __net_exit icmp_sk_exit(struct net *net) -{ - int i; - - for_each_possible_cpu(i) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.icmp_sk, i)); - free_percpu(net->ipv4.icmp_sk); - net->ipv4.icmp_sk = NULL; -} - static int __net_init icmp_sk_init(struct net *net) { - int i, err; - - net->ipv4.icmp_sk = alloc_percpu(struct sock *); - if (!net->ipv4.icmp_sk) - return -ENOMEM; - - for_each_possible_cpu(i) { - struct sock *sk; - - err = inet_ctl_sock_create(&sk, PF_INET, - SOCK_RAW, IPPROTO_ICMP, net); - if (err < 0) - goto fail; - - *per_cpu_ptr(net->ipv4.icmp_sk, i) = sk; - - /* Enough space for 2 64K ICMP packets, including - * sk_buff/skb_shared_info struct overhead. - */ - sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); - - /* - * Speedup sock_wfree() - */ - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; - } - /* Control parameters for ECHO replies. */ net->ipv4.sysctl_icmp_echo_ignore_all = 0; net->ipv4.sysctl_icmp_echo_enable_probe = 0; @@ -1499,18 +1452,36 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; return 0; - -fail: - icmp_sk_exit(net); - return err; } static struct pernet_operations __net_initdata icmp_sk_ops = { .init = icmp_sk_init, - .exit = icmp_sk_exit, }; int __init icmp_init(void) { + int err, i; + + for_each_possible_cpu(i) { + struct sock *sk; + + err = inet_ctl_sock_create(&sk, PF_INET, + SOCK_RAW, IPPROTO_ICMP, &init_net); + if (err < 0) + return err; + + per_cpu(ipv4_icmp_sk, i) = sk; + + /* Enough space for 2 64K ICMP packets, including + * sk_buff/skb_shared_info struct overhead. + */ + sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); + + /* + * Speedup sock_wfree() + */ + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; + } return register_pernet_subsys(&icmp_sk_ops); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fc2a985f6064..1e5b53c2bb26 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -866,12 +866,9 @@ static void reqsk_timer_handler(struct timer_list *t) (!resend || !inet_rtx_syn_ack(sk_listener, req) || inet_rsk(req)->acked)) { - unsigned long timeo; - if (req->num_timeout++ == 0) atomic_dec(&queue->young); - timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); - mod_timer(&req->rsk_timer, jiffies + timeo); + mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); if (!nreq) return; @@ -1046,6 +1043,9 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); + if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) + sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); + /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 437afe392e66..9e0bbd026560 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -52,14 +52,15 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) spin_unlock(lock); /* Disassociate with bind bucket. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, - hashinfo->bhash_size)]; + bhead = &hashinfo->bhash[tw->tw_bslot]; spin_lock(&bhead->lock); inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - atomic_dec(&tw->tw_dr->tw_count); + if (refcount_dec_and_test(&tw->tw_dr->tw_refcount)) + kfree(tw->tw_dr); + inet_twsk_put(tw); } @@ -110,8 +111,12 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, - hashinfo->bhash_size)]; + /* Cache inet_bhashfn(), because 'struct net' might be no longer + * available later in inet_twsk_kill(). + */ + tw->tw_bslot = inet_bhashfn(twsk_net(tw), inet->inet_num, + hashinfo->bhash_size); + bhead = &hashinfo->bhash[tw->tw_bslot]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; WARN_ON(!icsk->icsk_bind_hash); @@ -145,10 +150,6 @@ static void tw_timer_handler(struct timer_list *t) { struct inet_timewait_sock *tw = from_timer(tw, t, tw_timer); - if (tw->tw_kill) - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITKILLED); - else - __NET_INC_STATS(twsk_net(tw), LINUX_MIB_TIMEWAITED); inet_twsk_kill(tw); } @@ -158,7 +159,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, { struct inet_timewait_sock *tw; - if (atomic_read(&dr->tw_count) >= dr->sysctl_max_tw_buckets) + if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets) return NULL; tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, @@ -244,59 +245,15 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) * of PAWS. */ - tw->tw_kill = timeo <= 4*HZ; if (!rearm) { + bool kill = timeo <= 4*HZ; + + __NET_INC_STATS(twsk_net(tw), kill ? LINUX_MIB_TIMEWAITKILLED : + LINUX_MIB_TIMEWAITED); BUG_ON(mod_timer(&tw->tw_timer, jiffies + timeo)); - atomic_inc(&tw->tw_dr->tw_count); + refcount_inc(&tw->tw_dr->tw_refcount); } else { mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); - -void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) -{ - struct inet_timewait_sock *tw; - struct sock *sk; - struct hlist_nulls_node *node; - unsigned int slot; - - for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { - struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; -restart_rcu: - cond_resched(); - rcu_read_lock(); -restart: - sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) - continue; - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count)) - continue; - - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) - continue; - - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->ns.count))) { - inet_twsk_put(tw); - goto restart; - } - - rcu_read_unlock(); - local_bh_disable(); - inet_twsk_deschedule_put(tw); - local_bh_enable(); - goto restart_rcu; - } - /* If the nulls value we got at the end of this lookup is - * not the expected one, we must restart lookup. - * We probably met an item that was moved to another chain. - */ - if (get_nulls_value(node) != slot) - goto restart; - rcu_read_unlock(); - } -} -EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3a025c011971..d94f9f7e60c3 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -196,7 +196,8 @@ resubmit: if (ipprot) { if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); + kfree_skb_reason(skb, + SKB_DROP_REASON_XFRM_POLICY); return; } nf_reset_ct(skb); @@ -215,7 +216,7 @@ resubmit: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); } - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_IP_NOPROTO); } else { __IP_INC_STATS(net, IPSTATS_MIB_INDELIVERS); consume_skb(skb); @@ -318,8 +319,10 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); + int err, drop_reason; struct rtable *rt; - int err; + + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (ip_can_use_hint(skb, iph, hint)) { err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos, @@ -396,19 +399,23 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, * so-called "hole-196" attack) so do it for both. */ if (in_dev && - IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) + IN_DEV_ORCONF(in_dev, DROP_UNICAST_IN_L2_MULTICAST)) { + drop_reason = SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST; goto drop; + } } return NET_RX_SUCCESS; drop: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return NET_RX_DROP; drop_error: - if (err == -EXDEV) + if (err == -EXDEV) { + drop_reason = SKB_DROP_REASON_IP_RPFILTER; __NET_INC_STATS(net, LINUX_MIB_IPRPFILTER); + } goto drop; } @@ -436,13 +443,16 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) { const struct iphdr *iph; + int drop_reason; u32 len; /* When the interface is in promisc. mode, drop all the crap * that it receives, do not try to analyse it. */ - if (skb->pkt_type == PACKET_OTHERHOST) + if (skb->pkt_type == PACKET_OTHERHOST) { + drop_reason = SKB_DROP_REASON_OTHERHOST; goto drop; + } __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); @@ -452,6 +462,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto out; } + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto inhdr_error; @@ -488,6 +499,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) len = ntohs(iph->tot_len); if (skb->len < len) { + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; __IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) @@ -516,11 +528,14 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) return skb; csum_error: + drop_reason = SKB_DROP_REASON_IP_CSUM; __IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: + if (drop_reason == SKB_DROP_REASON_NOT_SPECIFIED) + drop_reason = SKB_DROP_REASON_IP_INHDR; __IP_INC_STATS(net, IPSTATS_MIB_INHDRERRORS); drop: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); out: return NULL; } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index da1b5038bdfd..a9e22a098872 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -42,7 +42,7 @@ */ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, - __be32 daddr, struct rtable *rt, int is_frag) + __be32 daddr, struct rtable *rt) { unsigned char *iph = skb_network_header(skb); @@ -53,28 +53,15 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, if (opt->srr) memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4); - if (!is_frag) { - if (opt->rr_needaddr) - ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); - if (opt->ts_needaddr) - ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); - if (opt->ts_needtime) { - __be32 midtime; + if (opt->rr_needaddr) + ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt); + if (opt->ts_needaddr) + ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt); + if (opt->ts_needtime) { + __be32 midtime; - midtime = inet_current_timestamp(); - memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); - } - return; - } - if (opt->rr) { - memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]); - opt->rr = 0; - opt->rr_needaddr = 0; - } - if (opt->ts) { - memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]); - opt->ts = 0; - opt->ts_needaddr = opt->ts_needtime = 0; + midtime = inet_current_timestamp(); + memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 57c1d8431386..0c0574eb5f5b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -162,17 +162,24 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - if (ip_dont_fragment(sk, &rt->dst)) { + /* Do not bother generating IPID for small packets (eg SYNACK) */ + if (skb->len <= IPV4_MIN_MTU || ip_dont_fragment(sk, &rt->dst)) { iph->frag_off = htons(IP_DF); iph->id = 0; } else { iph->frag_off = 0; - __ip_select_ident(net, iph, 1); + /* TCP packets here are SYNACK with fat IPv4/TCP options. + * Avoid using the hashed IP ident generator. + */ + if (sk->sk_protocol == IPPROTO_TCP) + iph->id = (__force __be16)prandom_u32(); + else + __ip_select_ident(net, iph, 1); } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; - ip_options_build(skb, &opt->opt, daddr, rt, 0); + ip_options_build(skb, &opt->opt, daddr, rt); } skb->priority = sk->sk_priority; @@ -512,7 +519,7 @@ packet_routed: if (inet_opt && inet_opt->opt.optlen) { iph->ihl += inet_opt->opt.optlen >> 2; - ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); + ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt); } ip_select_ident_segs(net, skb, sk, @@ -825,15 +832,24 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, /* Everything is OK. Generate! */ ip_fraglist_init(skb, iph, hlen, &iter); - if (iter.frag) - ip_options_fragment(iter.frag); - for (;;) { /* Prepare header of the next frame, * before previous one went down. */ if (iter.frag) { + bool first_frag = (iter.offset == 0); + IPCB(iter.frag)->flags = IPCB(skb)->flags; ip_fraglist_prepare(skb, &iter); + if (first_frag && IPCB(skb)->opt.optlen) { + /* ipcb->opt is not populated for frags + * coming from __ip_make_skb(), + * ip_options_fragment() needs optlen + */ + IPCB(iter.frag)->opt.optlen = + IPCB(skb)->opt.optlen; + ip_options_fragment(iter.frag); + ip_send_check(iter.iph); + } } skb->tstamp = tstamp; @@ -1525,7 +1541,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, if (opt) { iph->ihl += opt->optlen >> 2; - ip_options_build(skb, opt, cork->addr, rt, 0); + ip_options_build(skb, opt, cork->addr, rt); } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 67087f95579f..aab384126f61 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -58,10 +58,6 @@ config NF_TABLES_ARP endif # NF_TABLES -config NF_FLOW_TABLE_IPV4 - tristate - select NF_FLOW_TABLE_INET - config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 0e56df3a45e2..bcf7bc71cb56 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -220,7 +220,8 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) continue; } - if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) + if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && + sk->sk_bound_dev_if != inet_sdif(skb)) continue; sock_hold(sk); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index f30273afb539..28836071f0a6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,8 +59,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, - atomic_read(&net->ipv4.tcp_death_row.tw_count), sockets, - proto_memory_allocated(&tcp_prot)); + refcount_read(&net->ipv4.tcp_death_row->tw_refcount) - 1, + sockets, proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), proto_memory_allocated(&udp_prot)); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9eb5fc247868..9f97b9cbf7b3 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -722,6 +722,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) int ret = -EINVAL; int chk_addr_ret; + lock_sock(sk); if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) goto out; @@ -741,7 +742,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; -out: return ret; +out: + release_sock(sk); + return ret; } /* diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ff6f91cdb6c4..634766e6c7cc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -84,6 +84,7 @@ #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> +#include <net/inet_dscp.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/route.h> @@ -112,14 +113,13 @@ #define DEFAULT_MIN_PMTU (512 + 20 + 20) #define DEFAULT_MTU_EXPIRES (10 * 60 * HZ) - +#define DEFAULT_MIN_ADVMSS 256 static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; -static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; @@ -458,7 +458,7 @@ static u32 *ip_tstamps __read_mostly; * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ -u32 ip_idents_reserve(u32 hash, int segs) +static u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; @@ -479,7 +479,6 @@ u32 ip_idents_reserve(u32 hash, int segs) */ return atomic_add_return(segs + delta, p_id) - segs; } -EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { @@ -1298,9 +1297,10 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { + struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, - ip_rt_min_advmss); + net->ipv4.ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } @@ -3392,7 +3392,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (fa->fa_slen == slen && fa->tb_id == fri.tb_id && - fa->fa_tos == fri.tos && + fa->fa_dscp == inet_dsfield_to_dscp(fri.tos) && fa->fa_info == res.fi && fa->fa_type == fri.type) { fri.offload = fa->offload; @@ -3535,13 +3535,6 @@ static struct ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "min_adv_mss", - .data = &ip_rt_min_advmss, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { } }; @@ -3569,6 +3562,13 @@ static struct ctl_table ipv4_route_netns_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "min_adv_mss", + .data = &init_net.ipv4.ip_rt_min_advmss, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { }, }; @@ -3631,6 +3631,7 @@ static __net_init int netns_ip_rt_init(struct net *net) /* Set default value for namespaceified sysctls */ net->ipv4.ip_rt_min_pmtu = DEFAULT_MIN_PMTU; net->ipv4.ip_rt_mtu_expires = DEFAULT_MTU_EXPIRES; + net->ipv4.ip_rt_min_advmss = DEFAULT_MIN_ADVMSS; return 0; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 97eb54774924..1cae27b5dcd8 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -589,6 +589,14 @@ static struct ctl_table ipv4_table[] = { }; static struct ctl_table ipv4_net_table[] = { + /* tcp_max_tw_buckets must be first in this table. */ + { + .procname = "tcp_max_tw_buckets", +/* .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, */ + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "icmp_echo_ignore_all", .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, @@ -1001,13 +1009,6 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &two, }, { - .procname = "tcp_max_tw_buckets", - .data = &init_net.ipv4.tcp_death_row.sysctl_max_tw_buckets, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_max_syn_backlog", .data = &init_net.ipv4.sysctl_max_syn_backlog, .maxlen = sizeof(int), @@ -1400,7 +1401,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + /* skip first entry (sysctl_max_tw_buckets) */ + for (i = 1; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { if (table[i].data) { /* Update the variables to point into * the current struct net @@ -1415,6 +1417,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } } + table[0].data = &net->ipv4.tcp_death_row->sysctl_max_tw_buckets; + net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); if (!net->ipv4.ipv4_hdr) goto err_reg; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3b75836db19b..a03a6bfb4353 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -842,6 +842,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, } release_sock(sk); + sk_defer_free_flush(sk); if (spliced) return spliced; @@ -893,8 +894,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ - new_size_goal = sk->sk_gso_max_size - 1 - MAX_TCP_HEADER; - new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal); + new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; @@ -1321,10 +1321,13 @@ new_segment: /* skb changing from pure zc to mixed, must charge zc */ if (unlikely(skb_zcopy_pure(skb))) { - if (!sk_wmem_schedule(sk, skb->data_len)) + u32 extra = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + + if (!sk_wmem_schedule(sk, extra)) goto wait_for_space; - sk_mem_charge(sk, skb->data_len); + sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index ec5550089b4d..02e8626ccb27 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -1154,7 +1154,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; -BTF_SET_START(tcp_bbr_kfunc_ids) +BTF_SET_START(tcp_bbr_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, bbr_init) @@ -1167,25 +1167,27 @@ BTF_ID(func, bbr_min_tso_segs) BTF_ID(func, bbr_set_state) #endif #endif -BTF_SET_END(tcp_bbr_kfunc_ids) +BTF_SET_END(tcp_bbr_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_bbr_check_kfunc_ids, +}; static int __init bbr_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); - ret = tcp_register_congestion_control(&tcp_bbr_cong_ops); - if (ret) + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_bbr_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&tcp_bbr_cong_ops); } static void __exit bbr_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index e07837e23b3f..24d562dd6225 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -485,7 +485,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; -BTF_SET_START(tcp_cubic_kfunc_ids) +BTF_SET_START(tcp_cubic_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, cubictcp_init) @@ -496,9 +496,12 @@ BTF_ID(func, cubictcp_cwnd_event) BTF_ID(func, cubictcp_acked) #endif #endif -BTF_SET_END(tcp_cubic_kfunc_ids) +BTF_SET_END(tcp_cubic_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_cubic_check_kfunc_ids, +}; static int __init cubictcp_register(void) { @@ -534,16 +537,14 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - ret = tcp_register_congestion_control(&cubictcp); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&cubictcp); } static void __exit cubictcp_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); tcp_unregister_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 0d7ab3cc7b61..1943a6630341 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -238,7 +238,7 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; -BTF_SET_START(tcp_dctcp_kfunc_ids) +BTF_SET_START(tcp_dctcp_check_kfunc_ids) #ifdef CONFIG_X86 #ifdef CONFIG_DYNAMIC_FTRACE BTF_ID(func, dctcp_init) @@ -249,25 +249,27 @@ BTF_ID(func, dctcp_cwnd_undo) BTF_ID(func, dctcp_state) #endif #endif -BTF_SET_END(tcp_dctcp_kfunc_ids) +BTF_SET_END(tcp_dctcp_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set); +static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &tcp_dctcp_check_kfunc_ids, +}; static int __init dctcp_register(void) { int ret; BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); - ret = tcp_register_congestion_control(&dctcp); - if (ret) + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_dctcp_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); - return 0; + return tcp_register_congestion_control(&dctcp); } static void __exit dctcp_unregister(void) { - unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); tcp_unregister_congestion_control(&dctcp); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dc49a3d551eb..af94a6d22a9d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, (mss != tcp_skb_seglen(skb))) goto out; + if (!tcp_skb_can_collapse(prev, skb)) + goto out; len = skb->len; pcount = tcp_skb_pcount(skb); if (tcp_skb_shift(prev, skb, pcount, len)) @@ -6723,6 +6725,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; + req->timeout = TCP_TIMEOUT_INIT; } return req; @@ -6939,9 +6942,10 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; - if (!want_cookie) - inet_csk_reqsk_queue_hash_add(sk, req, - tcp_timeout_init((struct sock *)req)); + if (!want_cookie) { + req->timeout = tcp_timeout_init((struct sock *)req); + inet_csk_reqsk_queue_hash_add(sk, req, req->timeout); + } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : TCP_SYNACK_COOKIE, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b53476e78c84..6873f46fc8ba 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -91,6 +91,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); +static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); + static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, @@ -206,7 +208,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct rtable *rt; int err; struct ip_options_rcu *inet_opt; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; @@ -810,7 +812,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; @@ -825,6 +828,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -908,7 +912,8 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); + ctl_sk = this_cpu_read(ipv4_tcp_sk); + sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? @@ -921,6 +926,7 @@ static void tcp_v4_send_ack(const struct sock *sk, transmit_time); ctl_sk->sk_mark = 0; + sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } @@ -2095,7 +2101,7 @@ process: nf_reset_ct(skb); if (tcp_filter(sk, skb)) { - drop_reason = SKB_DROP_REASON_TCP_FILTER; + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; @@ -3111,41 +3117,18 @@ EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { - int cpu; + struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row; if (net->ipv4.tcp_congestion_control) bpf_module_put(net->ipv4.tcp_congestion_control, net->ipv4.tcp_congestion_control->owner); - - for_each_possible_cpu(cpu) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); - free_percpu(net->ipv4.tcp_sk); + if (refcount_dec_and_test(&tcp_death_row->tw_refcount)) + kfree(tcp_death_row); } static int __net_init tcp_sk_init(struct net *net) { - int res, cpu, cnt; - - net->ipv4.tcp_sk = alloc_percpu(struct sock *); - if (!net->ipv4.tcp_sk) - return -ENOMEM; - - for_each_possible_cpu(cpu) { - struct sock *sk; - - res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, - IPPROTO_TCP, net); - if (res) - goto fail; - sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); - - /* Please enforce IP_DF and IPID==0 for RST and - * ACK sent in SYN-RECV and TIME-WAIT state. - */ - inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; - - *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; - } + int cnt; net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; @@ -3172,9 +3155,13 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; + net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL); + if (!net->ipv4.tcp_death_row) + return -ENOMEM; + refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1); cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; - net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; + net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2; + net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; @@ -3229,18 +3216,12 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_congestion_control = &tcp_reno; return 0; -fail: - tcp_sk_exit(net); - - return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; - inet_twsk_purge(&tcp_hashinfo, AF_INET); - list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } @@ -3326,6 +3307,24 @@ static void __init bpf_iter_register(void) void __init tcp_v4_init(void) { + int cpu, res; + + for_each_possible_cpu(cpu) { + struct sock *sk; + + res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, + IPPROTO_TCP, &init_net); + if (res) + panic("Failed to create the TCP control socket.\n"); + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + + per_cpu(ipv4_tcp_sk, cpu) = sk; + } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7c2d3ac2363a..6366df7aaf2a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -248,7 +248,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) const struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_sock *tp = tcp_sk(sk); struct inet_timewait_sock *tw; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; + struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; tw = inet_twsk_alloc(sk, tcp_death_row, state); @@ -583,7 +583,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout); + tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -622,8 +622,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, !inet_rtx_syn_ack(sk, req)) { unsigned long expires = jiffies; - expires += min(TCP_TIMEOUT_INIT << req->num_timeout, - TCP_RTO_MAX); + expires += reqsk_timeout(req, TCP_RTO_MAX); if (!fastopen) mod_timer_pending(&req->rsk_timer, expires); else diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5079832af5c1..e76bf1e9251e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1960,7 +1960,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, bytes = min_t(unsigned long, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), - sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); + sk->sk_gso_max_size); /* Goal is to send at least one packet per ms, * not one big TSO packet every 100 ms. @@ -4092,7 +4092,9 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) struct flowi fl; int res; - tcp_rsk(req)->txhash = net_tx_rndhash(); + /* Paired with WRITE_ONCE() in sock_setsockopt() */ + if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) + tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 090360939401..6b4d8361560f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2093,16 +2093,20 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); + int drop_reason; /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) + if (rc == -ENOMEM) { UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - else + drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; + } else { UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_PROTO_MEM; + } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2120,14 +2124,17 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { + int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); /* * Charge it to the socket, dropping if the queue is full. */ - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; + } nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { @@ -2204,8 +2211,10 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; + } udp_csum_pull_header(skb); @@ -2213,11 +2222,12 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) return __udp_queue_rcv_skb(sk, skb); csum_error: + drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return -1; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3eee17790a82..ef23e7dc538a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -554,7 +554,7 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, #ifdef CONFIG_IPV6_MROUTE if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, - devconf->mc_forwarding) < 0) + atomic_read(&devconf->mc_forwarding)) < 0) goto nla_put_failure; #endif if ((all || type == NETCONFA_PROXY_NEIGH) && @@ -2589,7 +2589,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, __u32 valid_lft, u32 prefered_lft) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(net, addr, dev, 1); - int create = 0; + int create = 0, update_lft = 0; if (!ifp && valid_lft) { int max_addresses = in6_dev->cnf.max_addresses; @@ -2633,19 +2633,32 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, unsigned long now; u32 stored_lft; - /* Update lifetime (RFC4862 5.5.3 e) - * We deviate from RFC4862 by honoring all Valid Lifetimes to - * improve the reaction of SLAAC to renumbering events - * (draft-gont-6man-slaac-renum-06, Section 4.2) - */ + /* update lifetime (RFC2462 5.5.3 e) */ spin_lock_bh(&ifp->lock); now = jiffies; if (ifp->valid_lft > (now - ifp->tstamp) / HZ) stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!create && stored_lft) { + const u32 minimum_lft = min_t(u32, + stored_lft, MIN_VALID_LIFETIME); + valid_lft = max(valid_lft, minimum_lft); + + /* RFC4862 Section 5.5.3e: + * "Note that the preferred lifetime of the + * corresponding address is always reset to + * the Preferred Lifetime in the received + * Prefix Information option, regardless of + * whether the valid lifetime is also reset or + * ignored." + * + * So we should always update prefered_lft here. + */ + update_lft = 1; + } + + if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; ifp->tstamp = now; @@ -5520,7 +5533,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OPTIMISTIC] = cnf->use_optimistic; #endif #ifdef CONFIG_IPV6_MROUTE - array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; + array[DEVCONF_MC_FORWARDING] = atomic_read(&cnf->mc_forwarding); #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; @@ -7171,7 +7184,9 @@ static void __net_exit addrconf_exit_net(struct net *net) NETCONFA_IFINDEX_ALL); #endif kfree(net->ipv6.devconf_dflt); + net->ipv6.devconf_dflt = NULL; kfree(net->ipv6.devconf_all); + net->ipv6.devconf_all = NULL; } static struct pernet_operations addrconf_ops = { diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 77e34aec7e82..658d5eabaf7e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1344,14 +1344,14 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, return opt2; } -struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, - struct ipv6_txoptions *opt) +struct ipv6_txoptions *__ipv6_fixup_options(struct ipv6_txoptions *opt_space, + struct ipv6_txoptions *opt) { /* * ignore the dest before srcrt unless srcrt is being included. * --yoshfuji */ - if (opt && opt->dst0opt && !opt->srcrt) { + if (opt->dst0opt && !opt->srcrt) { if (opt_space != opt) { memcpy(opt_space, opt, sizeof(*opt_space)); opt = opt_space; @@ -1362,7 +1362,7 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, return opt; } -EXPORT_SYMBOL_GPL(ipv6_fixup_options); +EXPORT_SYMBOL_GPL(__ipv6_fixup_options); /** * fl6_update_dst - update flowi destination address with info given diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index ec029c86ae06..e2a7b0059669 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -16,6 +16,7 @@ #include <linux/indirect_call_wrapper.h> #include <net/fib_rules.h> +#include <net/inet_dscp.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/ip6_route.h> @@ -25,14 +26,14 @@ struct fib6_rule { struct fib_rule common; struct rt6key src; struct rt6key dst; - u8 tclass; + dscp_t dscp; }; static bool fib6_rule_matchall(const struct fib_rule *rule) { struct fib6_rule *r = container_of(rule, struct fib6_rule, common); - if (r->dst.plen || r->src.plen || r->tclass) + if (r->dst.plen || r->src.plen || r->dscp) return false; return fib_rule_matchall(rule); } @@ -323,7 +324,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, return 0; } - if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel)) + if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel)) return 0; if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) @@ -349,6 +350,13 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; + if (!inet_validate_dscp(frh->tos)) { + NL_SET_ERR_MSG(extack, + "Invalid dsfield (tos): ECN bits must be 0"); + goto errout; + } + rule6->dscp = inet_dsfield_to_dscp(frh->tos); + if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); @@ -369,7 +377,6 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, rule6->src.plen = frh->src_len; rule6->dst.plen = frh->dst_len; - rule6->tclass = frh->tos; if (fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect++; @@ -402,7 +409,7 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) return 0; - if (frh->tos && (rule6->tclass != frh->tos)) + if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos) return 0; if (frh->src_len && @@ -423,7 +430,7 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; - frh->tos = rule6->tclass; + frh->tos = inet_dscp_to_dsfield(rule6->dscp); if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 96c5cc0f30ce..e6b978ea0e87 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -69,17 +69,7 @@ #include <linux/uaccess.h> -/* - * The ICMP socket(s). This is the most convenient way to flow control - * our ICMP output as well as maintain a clean interface throughout - * all layers. All Socketless IP sends will soon be gone. - * - * On SMP we have one ICMP socket per-cpu. - */ -static struct sock *icmpv6_sk(struct net *net) -{ - return this_cpu_read(*net->ipv6.icmp_sk); -} +static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk); static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) @@ -110,11 +100,11 @@ static const struct inet6_protocol icmpv6_protocol = { }; /* Called with BH disabled */ -static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) +static struct sock *icmpv6_xmit_lock(struct net *net) { struct sock *sk; - sk = icmpv6_sk(net); + sk = this_cpu_read(ipv6_icmp_sk); if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { /* This can happen if the output path (f.e. SIT or * ip6ip6 tunnel) signals dst_link_failure() for an @@ -122,11 +112,13 @@ static __inline__ struct sock *icmpv6_xmit_lock(struct net *net) */ return NULL; } + sock_net_set(sk, net); return sk; } -static __inline__ void icmpv6_xmit_unlock(struct sock *sk) +static void icmpv6_xmit_unlock(struct sock *sk) { + sock_net_set(sk, &init_net); spin_unlock(&sk->sk_lock.slock); } @@ -1034,59 +1026,27 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } -static void __net_exit icmpv6_sk_exit(struct net *net) -{ - int i; - - for_each_possible_cpu(i) - inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv6.icmp_sk, i)); - free_percpu(net->ipv6.icmp_sk); -} - -static int __net_init icmpv6_sk_init(struct net *net) +int __init icmpv6_init(void) { struct sock *sk; int err, i; - net->ipv6.icmp_sk = alloc_percpu(struct sock *); - if (!net->ipv6.icmp_sk) - return -ENOMEM; - for_each_possible_cpu(i) { err = inet_ctl_sock_create(&sk, PF_INET6, - SOCK_RAW, IPPROTO_ICMPV6, net); + SOCK_RAW, IPPROTO_ICMPV6, &init_net); if (err < 0) { pr_err("Failed to initialize the ICMP6 control socket (err %d)\n", err); - goto fail; + return err; } - *per_cpu_ptr(net->ipv6.icmp_sk, i) = sk; + per_cpu(ipv6_icmp_sk, i) = sk; /* Enough space for 2 64K ICMP packets, including * sk_buff struct overhead. */ sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024); } - return 0; - - fail: - icmpv6_sk_exit(net); - return err; -} - -static struct pernet_operations icmpv6_sk_ops = { - .init = icmpv6_sk_init, - .exit = icmpv6_sk_exit, -}; - -int __init icmpv6_init(void) -{ - int err; - - err = register_pernet_subsys(&icmpv6_sk_ops); - if (err < 0) - return err; err = -EAGAIN; if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0) @@ -1101,14 +1061,12 @@ sender_reg_err: inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); fail: pr_err("Failed to register ICMP6 protocol\n"); - unregister_pernet_subsys(&icmpv6_sk_ops); return err; } void icmpv6_cleanup(void) { inet6_unregister_icmp_sender(icmp6_send); - unregister_pernet_subsys(&icmpv6_sk_ops); inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6); } diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index f90a87389fcc..f6f5b83dd954 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -32,13 +32,25 @@ struct ioam6_lwt_encap { struct ioam6_trace_hdr traceh; } __packed; +struct ioam6_lwt_freq { + u32 k; + u32 n; +}; + struct ioam6_lwt { struct dst_cache cache; + struct ioam6_lwt_freq freq; + atomic_t pkt_cnt; u8 mode; struct in6_addr tundst; struct ioam6_lwt_encap tuninfo; }; +static struct netlink_range_validation freq_range = { + .min = IOAM6_IPTUNNEL_FREQ_MIN, + .max = IOAM6_IPTUNNEL_FREQ_MAX, +}; + static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt) { return (struct ioam6_lwt *)lwt->data; @@ -55,6 +67,8 @@ static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt) } static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_FREQ_K] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range), + [IOAM6_IPTUNNEL_FREQ_N] = NLA_POLICY_FULL_RANGE(NLA_U32, &freq_range), [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), @@ -96,6 +110,7 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, struct lwtunnel_state *lwt; struct ioam6_lwt *ilwt; int len_aligned, err; + u32 freq_k, freq_n; u8 mode; if (family != AF_INET6) @@ -106,6 +121,23 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, if (err < 0) return err; + if ((!tb[IOAM6_IPTUNNEL_FREQ_K] && tb[IOAM6_IPTUNNEL_FREQ_N]) || + (tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N])) { + NL_SET_ERR_MSG(extack, "freq: missing parameter"); + return -EINVAL; + } else if (!tb[IOAM6_IPTUNNEL_FREQ_K] && !tb[IOAM6_IPTUNNEL_FREQ_N]) { + freq_k = IOAM6_IPTUNNEL_FREQ_MIN; + freq_n = IOAM6_IPTUNNEL_FREQ_MIN; + } else { + freq_k = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_K]); + freq_n = nla_get_u32(tb[IOAM6_IPTUNNEL_FREQ_N]); + + if (freq_k > freq_n) { + NL_SET_ERR_MSG(extack, "freq: k > n is forbidden"); + return -EINVAL; + } + } + if (!tb[IOAM6_IPTUNNEL_MODE]) mode = IOAM6_IPTUNNEL_MODE_INLINE; else @@ -140,6 +172,10 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, return err; } + atomic_set(&ilwt->pkt_cnt, 0); + ilwt->freq.k = freq_k; + ilwt->freq.n = freq_n; + ilwt->mode = mode; if (tb[IOAM6_IPTUNNEL_DST]) ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); @@ -263,11 +299,18 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) struct in6_addr orig_daddr; struct ioam6_lwt *ilwt; int err = -EINVAL; + u32 pkt_cnt; if (skb->protocol != htons(ETH_P_IPV6)) goto drop; ilwt = ioam6_lwt_state(dst->lwtstate); + + /* Check for insertion frequency (i.e., "k over n" insertions) */ + pkt_cnt = atomic_fetch_inc(&ilwt->pkt_cnt); + if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k) + goto out; + orig_daddr = ipv6_hdr(skb)->daddr; switch (ilwt->mode) { @@ -358,6 +401,14 @@ static int ioam6_fill_encap_info(struct sk_buff *skb, struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int err; + err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_K, ilwt->freq.k); + if (err) + goto ret; + + err = nla_put_u32(skb, IOAM6_IPTUNNEL_FREQ_N, ilwt->freq.n); + if (err) + goto ret; + err = nla_put_u8(skb, IOAM6_IPTUNNEL_MODE, ilwt->mode); if (err) goto ret; @@ -379,7 +430,9 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int nlsize; - nlsize = nla_total_size(sizeof(ilwt->mode)) + + nlsize = nla_total_size(sizeof(ilwt->freq.k)) + + nla_total_size(sizeof(ilwt->freq.n)) + + nla_total_size(sizeof(ilwt->mode)) + nla_total_size(sizeof(ilwt->tuninfo.traceh)); if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) @@ -395,7 +448,9 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) struct ioam6_lwt *ilwt_a = ioam6_lwt_state(a); struct ioam6_lwt *ilwt_b = ioam6_lwt_state(b); - return (ilwt_a->mode != ilwt_b->mode || + return (ilwt_a->freq.k != ilwt_b->freq.k || + ilwt_a->freq.n != ilwt_b->freq.n || + ilwt_a->mode != ilwt_b->mode || (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || trace_a->namespace_id != trace_b->namespace_id); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 463c37dea449..413f66781e50 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -112,7 +112,7 @@ void fib6_update_sernum(struct net *net, struct fib6_info *f6i) fn = rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) - fn->fn_sernum = fib6_new_sernum(net); + WRITE_ONCE(fn->fn_sernum, fib6_new_sernum(net)); } /* @@ -590,12 +590,13 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, spin_unlock_bh(&table->tb6_lock); if (res > 0) { cb->args[4] = 1; - cb->args[5] = w->root->fn_sernum; + cb->args[5] = READ_ONCE(w->root->fn_sernum); } } else { - if (cb->args[5] != w->root->fn_sernum) { + int sernum = READ_ONCE(w->root->fn_sernum); + if (cb->args[5] != sernum) { /* Begin at the root if the tree changed */ - cb->args[5] = w->root->fn_sernum; + cb->args[5] = sernum; w->state = FWS_INIT; w->node = w->root; w->skip = w->count; @@ -1345,7 +1346,7 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt, /* paired with smp_rmb() in fib6_get_cookie_safe() */ smp_wmb(); while (fn) { - fn->fn_sernum = sernum; + WRITE_ONCE(fn->fn_sernum, sernum); fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&rt->fib6_table->tb6_lock)); } @@ -2174,8 +2175,8 @@ static int fib6_clean_node(struct fib6_walker *w) }; if (c->sernum != FIB6_NO_SERNUM_CHANGE && - w->node->fn_sernum != c->sernum) - w->node->fn_sernum = c->sernum; + READ_ONCE(w->node->fn_sernum) != c->sernum) + WRITE_ONCE(w->node->fn_sernum, c->sernum); if (!c->func) { WARN_ON_ONCE(c->sernum == FIB6_NO_SERNUM_CHANGE); @@ -2543,7 +2544,7 @@ static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter, iter->w.state = FWS_INIT; iter->w.node = iter->w.root; iter->w.args = iter; - iter->sernum = iter->w.root->fn_sernum; + iter->sernum = READ_ONCE(iter->w.root->fn_sernum); INIT_LIST_HEAD(&iter->w.lh); fib6_walker_link(net, &iter->w); } @@ -2571,8 +2572,10 @@ static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl, static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) { - if (iter->sernum != iter->w.root->fn_sernum) { - iter->sernum = iter->w.root->fn_sernum; + int sernum = READ_ONCE(iter->w.root->fn_sernum); + + if (iter->sernum != sernum) { + iter->sernum = sernum; iter->w.state = FWS_INIT; iter->w.node = iter->w.root; WARN_ON(iter->w.skip); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 80256717868e..d4b1e2c5aa76 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -508,7 +508,7 @@ int ip6_mc_input(struct sk_buff *skb) /* * IPv6 multicast router mode is now supported ;) */ - if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding && + if (atomic_read(&dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding) && !(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL)) && likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index b29e9ba5e113..d37a79a8554e 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -249,7 +249,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if ((first_word & htonl(0xF00FFFFF)) || !ipv6_addr_equal(&iph->saddr, &iph2->saddr) || !ipv6_addr_equal(&iph->daddr, &iph2->daddr) || - *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) { + iph->nexthdr != iph2->nexthdr) { not_same_flow: NAPI_GRO_CB(p)->same_flow = 0; continue; @@ -260,7 +260,8 @@ not_same_flow: goto not_same_flow; } /* flush if Traffic Class fields are different */ - NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000)); + NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) | + (__force __be32)(iph->hop_limit ^ iph2->hop_limit)); NAPI_GRO_CB(p)->flush |= flush; /* If the previous IP ID value was based on an atomic diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2995f8d89e7e..0c6c971ce0a5 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1350,11 +1350,16 @@ static void ip6_append_data_mtu(unsigned int *mtu, static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6, - struct rt6_info *rt, struct flowi6 *fl6) + struct rt6_info *rt) { struct ipv6_pinfo *np = inet6_sk(sk); unsigned int mtu; - struct ipv6_txoptions *opt = ipc6->opt; + struct ipv6_txoptions *nopt, *opt = ipc6->opt; + + /* callers pass dst together with a reference, set it first so + * ip6_cork_release() can put it down even in case of an error. + */ + cork->base.dst = &rt->dst; /* * setup for corking @@ -1363,39 +1368,32 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (WARN_ON(v6_cork->opt)) return -EINVAL; - v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); - if (unlikely(!v6_cork->opt)) + nopt = v6_cork->opt = kzalloc(sizeof(*opt), sk->sk_allocation); + if (unlikely(!nopt)) return -ENOBUFS; - v6_cork->opt->tot_len = sizeof(*opt); - v6_cork->opt->opt_flen = opt->opt_flen; - v6_cork->opt->opt_nflen = opt->opt_nflen; + nopt->tot_len = sizeof(*opt); + nopt->opt_flen = opt->opt_flen; + nopt->opt_nflen = opt->opt_nflen; - v6_cork->opt->dst0opt = ip6_opt_dup(opt->dst0opt, - sk->sk_allocation); - if (opt->dst0opt && !v6_cork->opt->dst0opt) + nopt->dst0opt = ip6_opt_dup(opt->dst0opt, sk->sk_allocation); + if (opt->dst0opt && !nopt->dst0opt) return -ENOBUFS; - v6_cork->opt->dst1opt = ip6_opt_dup(opt->dst1opt, - sk->sk_allocation); - if (opt->dst1opt && !v6_cork->opt->dst1opt) + nopt->dst1opt = ip6_opt_dup(opt->dst1opt, sk->sk_allocation); + if (opt->dst1opt && !nopt->dst1opt) return -ENOBUFS; - v6_cork->opt->hopopt = ip6_opt_dup(opt->hopopt, - sk->sk_allocation); - if (opt->hopopt && !v6_cork->opt->hopopt) + nopt->hopopt = ip6_opt_dup(opt->hopopt, sk->sk_allocation); + if (opt->hopopt && !nopt->hopopt) return -ENOBUFS; - v6_cork->opt->srcrt = ip6_rthdr_dup(opt->srcrt, - sk->sk_allocation); - if (opt->srcrt && !v6_cork->opt->srcrt) + nopt->srcrt = ip6_rthdr_dup(opt->srcrt, sk->sk_allocation); + if (opt->srcrt && !nopt->srcrt) return -ENOBUFS; /* need source address above miyazawa*/ } - dst_hold(&rt->dst); - cork->base.dst = &rt->dst; - cork->fl.u.ip6 = *fl6; v6_cork->hop_limit = ipc6->hlimit; v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) @@ -1426,9 +1424,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, } static int __ip6_append_data(struct sock *sk, - struct flowi6 *fl6, struct sk_buff_head *queue, - struct inet_cork *cork, + struct inet_cork_full *cork_full, struct inet6_cork *v6_cork, struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, @@ -1437,6 +1434,8 @@ static int __ip6_append_data(struct sock *sk, unsigned int flags, struct ipcm6_cookie *ipc6) { struct sk_buff *skb, *skb_prev = NULL; + struct inet_cork *cork = &cork_full->base; + struct flowi6 *fl6 = &cork_full->fl.u.ip6; unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu; struct ubuf_info *uarg = NULL; int exthdrlen = 0; @@ -1788,34 +1787,46 @@ int ip6_append_data(struct sock *sk, /* * setup for corking */ + dst_hold(&rt->dst); err = ip6_setup_cork(sk, &inet->cork, &np->cork, - ipc6, rt, fl6); + ipc6, rt); if (err) return err; + inet->cork.fl.u.ip6 = *fl6; exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; } else { - fl6 = &inet->cork.fl.u.ip6; transhdrlen = 0; } - return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base, + return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork, &np->cork, sk_page_frag(sk), getfrag, from, length, transhdrlen, flags, ipc6); } EXPORT_SYMBOL_GPL(ip6_append_data); +static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) +{ + struct dst_entry *dst = cork->base.dst; + + cork->base.dst = NULL; + cork->base.flags &= ~IPCORK_ALLFRAG; + skb_dst_set(skb, dst); +} + static void ip6_cork_release(struct inet_cork_full *cork, struct inet6_cork *v6_cork) { if (v6_cork->opt) { - kfree(v6_cork->opt->dst0opt); - kfree(v6_cork->opt->dst1opt); - kfree(v6_cork->opt->hopopt); - kfree(v6_cork->opt->srcrt); - kfree(v6_cork->opt); + struct ipv6_txoptions *opt = v6_cork->opt; + + kfree(opt->dst0opt); + kfree(opt->dst1opt); + kfree(opt->hopopt); + kfree(opt->srcrt); + kfree(opt); v6_cork->opt = NULL; } @@ -1824,7 +1835,6 @@ static void ip6_cork_release(struct inet_cork_full *cork, cork->base.dst = NULL; cork->base.flags &= ~IPCORK_ALLFRAG; } - memset(&cork->fl, 0, sizeof(cork->fl)); } struct sk_buff *__ip6_make_skb(struct sock *sk, @@ -1834,7 +1844,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, { struct sk_buff *skb, *tmp_skb; struct sk_buff **tail_skb; - struct in6_addr final_dst_buf, *final_dst = &final_dst_buf; + struct in6_addr *final_dst; struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *hdr; @@ -1864,9 +1874,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, /* Allow local fragmentation. */ skb->ignore_df = ip6_sk_ignore_df(sk); - - *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); + + final_dst = &fl6->daddr; if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); if (opt && opt->opt_nflen) @@ -1886,10 +1896,9 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = sk->sk_priority; skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time; - skb_dst_set(skb, dst_clone(&rt->dst)); + ip6_cork_steal_dst(skb, cork); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); @@ -1961,26 +1970,26 @@ struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm6_cookie *ipc6, struct flowi6 *fl6, - struct rt6_info *rt, unsigned int flags, - struct inet_cork_full *cork) + struct ipcm6_cookie *ipc6, struct rt6_info *rt, + unsigned int flags, struct inet_cork_full *cork) { struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); int err; - if (flags & MSG_PROBE) + if (flags & MSG_PROBE) { + dst_release(&rt->dst); return NULL; + } __skb_queue_head_init(&queue); cork->base.flags = 0; cork->base.addr = 0; cork->base.opt = NULL; - cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt); if (err) { ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); @@ -1988,7 +1997,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag; - err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, + err = __ip6_append_data(sk, &queue, cork, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index fe786df4f849..b47ffc81f9e5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1036,14 +1036,14 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t, if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Local address not yet configured!\n", - p->name); + pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", + p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) - pr_warn("%s xmit: Routing loop! Remote address found on this node!\n", - p->name); + pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", + p->name); else ret = 1; rcu_read_unlock(); @@ -1121,6 +1121,11 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); + } else if (skb->protocol == htons(ETH_P_IP)) { + struct rtable *rt = skb_rtable(skb); + + if (rt->rt_gw_family == AF_INET6) + memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr)); } } else if (t->parms.proto != 0 && !(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 7cf73e60e619..fd660414d482 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -732,7 +732,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, in6_dev = __in6_dev_get(dev); if (in6_dev) { - in6_dev->cnf.mc_forwarding--; + atomic_dec(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); @@ -900,7 +900,7 @@ static int mif6_add(struct net *net, struct mr_table *mrt, in6_dev = __in6_dev_get(dev); if (in6_dev) { - in6_dev->cnf.mc_forwarding++; + atomic_inc(&in6_dev->cnf.mc_forwarding); inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, dev->ifindex, &in6_dev->cnf); @@ -1551,7 +1551,7 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) } else { rcu_assign_pointer(mrt->mroute_sk, sk); sock_set_flag(sk, SOCK_RCU_FREE); - net->ipv6.devconf_all->mc_forwarding++; + atomic_inc(&net->ipv6.devconf_all->mc_forwarding); } write_unlock_bh(&mrt_lock); @@ -1567,14 +1567,19 @@ static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk) int ip6mr_sk_done(struct sock *sk) { - int err = -EACCES; struct net *net = sock_net(sk); + struct ipv6_devconf *devconf; struct mr_table *mrt; + int err = -EACCES; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return err; + devconf = net->ipv6.devconf_all; + if (!devconf || !atomic_read(&devconf->mc_forwarding)) + return err; + rtnl_lock(); ip6mr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { @@ -1584,7 +1589,7 @@ int ip6mr_sk_done(struct sock *sk) * so the RCU grace period before sk freeing * is guaranteed by sk_destruct() */ - net->ipv6.devconf_all->mc_forwarding--; + atomic_dec(&devconf->mc_forwarding); write_unlock_bh(&mrt_lock); inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_MC_FORWARDING, diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 97d3d1b36dbc..0ba62f4868f9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -47,10 +47,6 @@ config NFT_FIB_IPV6 endif # NF_TABLES_IPV6 endif # NF_TABLES -config NF_FLOW_TABLE_IPV6 - tristate - select NF_FLOW_TABLE_INET - config NF_DUP_IPV6 tristate "Netfilter IPv6 packet duplication to alternate destination" depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index b85383606df7..b8d6dc9aeeb6 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o -# flow table support -obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o - # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ /dev/null diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e6de94203c13..f4884cda13b9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2802,7 +2802,7 @@ static void ip6_link_failure(struct sk_buff *skb) if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) - fn->fn_sernum = -1; + WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 075ee8a2df3b..0c648bf07f39 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -148,6 +148,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_timewait_death_row *tcp_death_row; struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct in6_addr *saddr = NULL, *final_p, final; @@ -156,7 +157,6 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct dst_entry *dst; int addr_type; int err; - struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; @@ -308,6 +308,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); + tcp_death_row = sock_net(sk)->ipv4.tcp_death_row; err = inet6_hash_connect(tcp_death_row, sk); if (err) goto late_failure; @@ -2237,15 +2238,9 @@ static void __net_exit tcpv6_net_exit(struct net *net) inet_ctl_sock_destroy(net->ipv6.tcp_sk); } -static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list) -{ - inet_twsk_purge(&tcp_hashinfo, AF_INET6); -} - static struct pernet_operations tcpv6_net_ops = { .init = tcpv6_net_init, .exit = tcpv6_net_exit, - .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 528b81ef19c9..c6872596b408 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1266,23 +1266,17 @@ static int udp_v6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; struct udp_sock *up = udp_sk(sk); - struct flowi6 fl6; int err = 0; if (up->pending == AF_INET) return udp_push_pending_frames(sk); - /* ip6_finish_skb will release the cork, so make a copy of - * fl6 here. - */ - fl6 = inet_sk(sk)->cork.fl.u.ip6; - skb = ip6_finish_skb(sk); if (!skb) goto out; - err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); - + err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6, + &inet_sk(sk)->cork.base); out: up->len = 0; up->pending = 0; @@ -1300,7 +1294,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipv6_txoptions *opt = NULL; struct ipv6_txoptions *opt_to_free = NULL; struct ip6_flowlabel *flowlabel = NULL; - struct flowi6 fl6; + struct inet_cork_full cork; + struct flowi6 *fl6 = &cork.fl.u.ip6; struct dst_entry *dst; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; @@ -1363,9 +1358,6 @@ do_udp_sendmsg: } } - if (up->pending == AF_INET) - return udp_sendmsg(sk, msg, len); - /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ @@ -1374,6 +1366,8 @@ do_udp_sendmsg: getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; if (up->pending) { + if (up->pending == AF_INET) + return udp_sendmsg(sk, msg, len); /* * There are pending frames. * The socket lock must be held while it's corked. @@ -1391,19 +1385,19 @@ do_udp_sendmsg: } ulen += sizeof(struct udphdr); - memset(&fl6, 0, sizeof(fl6)); + memset(fl6, 0, sizeof(*fl6)); if (sin6) { if (sin6->sin6_port == 0) return -EINVAL; - fl6.fl6_dport = sin6->sin6_port; + fl6->fl6_dport = sin6->sin6_port; daddr = &sin6->sin6_addr; if (np->sndflow) { - fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; + if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } @@ -1420,24 +1414,24 @@ do_udp_sendmsg: if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) - fl6.flowi6_oif = sin6->sin6_scope_id; + fl6->flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl6.fl6_dport = inet->inet_dport; + fl6->fl6_dport = inet->inet_dport; daddr = &sk->sk_v6_daddr; - fl6.flowlabel = np->flow_label; + fl6->flowlabel = np->flow_label; connected = true; } - if (!fl6.flowi6_oif) - fl6.flowi6_oif = sk->sk_bound_dev_if; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = sk->sk_bound_dev_if; - if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; - fl6.flowi6_uid = sk->sk_uid; + fl6->flowi6_uid = sk->sk_uid; if (msg->msg_controllen) { opt = &opt_space; @@ -1447,14 +1441,14 @@ do_udp_sendmsg: err = udp_cmsg_send(sk, msg, &ipc6.gso_size); if (err > 0) - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } - if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { + flowlabel = fl6_sock_lookup(sk, fl6->flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } @@ -1471,16 +1465,17 @@ do_udp_sendmsg: opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; - fl6.flowi6_proto = sk->sk_protocol; - fl6.flowi6_mark = ipc6.sockc.mark; - fl6.daddr = *daddr; - if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - fl6.saddr = np->saddr; - fl6.fl6_sport = inet->inet_sport; + fl6->flowi6_proto = sk->sk_protocol; + fl6->flowi6_mark = ipc6.sockc.mark; + fl6->daddr = *daddr; + if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr)) + fl6->saddr = np->saddr; + fl6->fl6_sport = inet->inet_sport; if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, - (struct sockaddr *)sin6, &fl6.saddr); + (struct sockaddr *)sin6, + &fl6->saddr); if (err) goto out_no_dst; if (sin6) { @@ -1496,32 +1491,32 @@ do_udp_sendmsg: err = -EINVAL; goto out_no_dst; } - fl6.fl6_dport = sin6->sin6_port; - fl6.daddr = sin6->sin6_addr; + fl6->fl6_dport = sin6->sin6_port; + fl6->daddr = sin6->sin6_addr; } } - if (ipv6_addr_any(&fl6.daddr)) - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + if (ipv6_addr_any(&fl6->daddr)) + fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ - final_p = fl6_update_dst(&fl6, opt, &final); + final_p = fl6_update_dst(fl6, opt, &final); if (final_p) connected = false; - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { - fl6.flowi6_oif = np->mcast_oif; + if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) { + fl6->flowi6_oif = np->mcast_oif; connected = false; - } else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; + } else if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->ucast_oif; - security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); + security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); if (ipc6.tclass < 0) ipc6.tclass = np->tclass; - fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); + fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); - dst = ip6_sk_dst_lookup_flow(sk, &fl6, final_p, connected); + dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -1529,7 +1524,7 @@ do_udp_sendmsg: } if (ipc6.hlimit < 0) - ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); + ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst); if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -1537,17 +1532,17 @@ back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { - struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, - &fl6, (struct rt6_info *)dst, + (struct rt6_info *)dst, msg->msg_flags, &cork); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_v6_send_skb(skb, &fl6, &cork.base); - goto out; + err = udp_v6_send_skb(skb, fl6, &cork.base); + /* ip6_make_skb steals dst reference */ + goto out_no_dst; } lock_sock(sk); @@ -1568,7 +1563,7 @@ do_append_data: ipc6.dontfrag = np->dontfrag; up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), - &ipc6, &fl6, (struct rt6_info *)dst, + &ipc6, fl6, (struct rt6_info *)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_v6_flush_pending_frames(sk); @@ -1603,7 +1598,7 @@ out_no_dst: do_confirm: if (msg->msg_flags & MSG_PROBE) - dst_confirm_neigh(dst, &fl6.daddr); + dst_confirm_neigh(dst, &fl6->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; diff --git a/net/mctp/device.c b/net/mctp/device.c index ef2755f82f87..02ddc0f1bd3e 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -6,6 +6,7 @@ * Copyright (c) 2021 Google */ +#include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/mctp.h> #include <linux/netdevice.h> diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 645dd984fef0..3e82ac24d548 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -336,6 +336,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; + pr_debug("MP_RST: transient=%u reason=%u", + mp_opt->reset_transient, mp_opt->reset_reason); break; case MPTCPOPT_MP_FAIL: @@ -1264,22 +1266,30 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { - if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->send_mp_fail = 0; - - *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, - TCPOLEN_MPTCP_FAIL, - 0, 0); - put_unaligned_be64(opts->fail_seq, ptr); - ptr += 2; - } - - /* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive, - * see mptcp_established_options*() + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + /* Which options can be used together? + * + * X: mutually exclusive + * O: often used together + * C: can be used together in some cases + * P: could be used together but we prefer not to (optimisations) + * + * Opt: | MPC | MPJ | DSS | ADD | RM | PRIO | FAIL | FC | + * ------|------|------|------|------|------|------|------|------| + * MPC |------|------|------|------|------|------|------|------| + * MPJ | X |------|------|------|------|------|------|------| + * DSS | X | X |------|------|------|------|------|------| + * ADD | X | X | P |------|------|------|------|------| + * RM | C | C | C | P |------|------|------|------| + * PRIO | X | C | C | C | C |------|------|------| + * FAIL | X | X | C | X | X | X |------|------| + * FC | X | X | X | X | X | X | X |------| + * RST | X | X | X | X | X | X | O | O | + * ------|------|------|------|------|------|------|------|------| + * + * The same applies in mptcp_established_options() function. */ if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { struct mptcp_ext *mpext = &opts->ext_copy; @@ -1336,6 +1346,10 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, } ptr += 1; } + + /* We might need to add MP_FAIL options in rare cases */ + if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) + goto mp_fail; } else if (OPTIONS_MPTCP_MPC & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; @@ -1479,6 +1493,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (OPTION_MPTCP_RST & opts->suboptions) goto mp_rst; return; + } else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { +mp_fail: + /* MP_FAIL is mutually exclusive with others except RST */ + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_fail = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, + TCPOLEN_MPTCP_FAIL, + 0, 0); + put_unaligned_be64(opts->fail_seq, ptr); + ptr += 2; + + if (OPTION_MPTCP_RST & opts->suboptions) + goto mp_rst; + return; } else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { mp_rst: *ptr++ = mptcp_option(MPTCPOPT_RST, @@ -1489,9 +1518,6 @@ mp_rst: } if (OPTION_MPTCP_PRIO & opts->suboptions) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - subflow = mptcp_subflow_ctx(ssk); subflow->send_mp_prio = 0; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 75af1f701e1d..5464c2d268bd 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -478,6 +478,20 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) return NULL; } +static struct mptcp_pm_addr_entry * +__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, + bool lookup_by_id) +{ + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, &pernet->local_addr_list, list) { + if ((!lookup_by_id && addresses_equal(&entry->addr, info, true)) || + (lookup_by_id && entry->addr.id == info->id)) + return entry; + } + return NULL; +} + static int lookup_id_by_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *addr) { @@ -777,7 +791,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, removed = true; __MPTCP_INC_STATS(sock_net(sk), rm_type); } - __set_bit(rm_list->ids[1], msk->pm.id_avail_bitmap); + __set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap); if (!removed) continue; @@ -1160,14 +1174,8 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); - if (tb[MPTCP_PM_ADDR_ATTR_PORT]) { - if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - NL_SET_ERR_MSG_ATTR(info->extack, attr, - "flags must have signal when using port"); - return -EINVAL; - } + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); - } return 0; } @@ -1213,6 +1221,11 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; + if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + return -EINVAL; + } + entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); @@ -1714,9 +1727,20 @@ fail: return -EMSGSIZE; } -static int mptcp_nl_addr_backup(struct net *net, - struct mptcp_addr_info *addr, - u8 bkup) +static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, + struct mptcp_addr_info *addr) +{ + struct mptcp_rm_list list = { .nr = 0 }; + + list.ids[list.nr++] = addr->id; + + mptcp_pm_nl_rm_subflow_received(msk, &list); + mptcp_pm_create_subflow_or_signal_addr(msk); +} + +static int mptcp_nl_set_flags(struct net *net, + struct mptcp_addr_info *addr, + u8 bkup, u8 changed) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; @@ -1730,7 +1754,10 @@ static int mptcp_nl_addr_backup(struct net *net, lock_sock(sk); spin_lock_bh(&msk->pm.lock); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) + mptcp_pm_nl_fullmesh(msk, addr); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1747,6 +1774,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); + u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | + MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = sock_net(skb->sk); u8 bkup = 0, lookup_by_id = 0; int ret; @@ -1763,18 +1792,24 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; } - list_for_each_entry(entry, &pernet->local_addr_list, list) { - if ((!lookup_by_id && addresses_equal(&entry->addr, &addr.addr, true)) || - (lookup_by_id && entry->addr.id == addr.addr.id)) { - mptcp_nl_addr_backup(net, &entry->addr, bkup); - - if (bkup) - entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else - entry->flags &= ~MPTCP_PM_ADDR_FLAG_BACKUP; - } + spin_lock_bh(&pernet->lock); + entry = __lookup_addr(pernet, &addr.addr, lookup_by_id); + if (!entry) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; + } + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; } + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); + addr = *entry; + spin_unlock_bh(&pernet->lock); + + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 0e6b42c76ea0..85317ce38e3f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -408,7 +408,7 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); struct mptcp_subflow_context { struct list_head node;/* conn_list of subflows */ - char reset_start[0]; + struct_group(reset, unsigned long avg_pacing_rate; /* protected by msk socket lock */ u64 local_key; @@ -458,7 +458,7 @@ struct mptcp_subflow_context { long delegated_status; - char reset_end[0]; + ); struct list_head delegated_node; /* link into delegated_action, protected by local BH */ @@ -494,7 +494,7 @@ mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow) static inline void mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { - memset(subflow->reset_start, 0, subflow->reset_end - subflow->reset_start); + memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; } diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index a135b1a46014..238b6a620e88 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -14,6 +14,11 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o +ifeq ($(CONFIG_NF_CONNTRACK),m) +nf_conntrack-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_conntrack_bpf.o +else ifeq ($(CONFIG_NF_CONNTRACK),y) +nf_conntrack-$(CONFIG_DEBUG_INFO_BTF) += nf_conntrack_bpf.o +endif obj-$(CONFIG_NETFILTER) = netfilter.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 354cb472f386..d1c9dfbb11fa 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -621,7 +621,8 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, case NF_ACCEPT: break; case NF_DROP: - kfree_skb(skb); + kfree_skb_reason(skb, + SKB_DROP_REASON_NETFILTER_DROP); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c new file mode 100644 index 000000000000..8ad3f52579f3 --- /dev/null +++ b/net/netfilter/nf_conntrack_bpf.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable Conntrack Helpers for XDP and TC-BPF hook + * + * These are called from the XDP and SCHED_CLS BPF programs. Note that it is + * allowed to break compatibility for these functions since the interface they + * are exposed through to BPF programs is explicitly unstable. + */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/types.h> +#include <linux/btf_ids.h> +#include <linux/net_namespace.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> + +/* bpf_ct_opts - Options for CT lookup helpers + * + * Members: + * @netns_id - Specify the network namespace for lookup + * Values: + * BPF_F_CURRENT_NETNS (-1) + * Use namespace associated with ctx (xdp_md, __sk_buff) + * [0, S32_MAX] + * Network Namespace ID + * @error - Out parameter, set for any errors encountered + * Values: + * -EINVAL - Passed NULL for bpf_tuple pointer + * -EINVAL - opts->reserved is not 0 + * -EINVAL - netns_id is less than -1 + * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (12) + * -EPROTO - l4proto isn't one of IPPROTO_TCP or IPPROTO_UDP + * -ENONET - No network namespace found for netns_id + * -ENOENT - Conntrack lookup could not find entry for tuple + * -EAFNOSUPPORT - tuple__sz isn't one of sizeof(tuple->ipv4) + * or sizeof(tuple->ipv6) + * @l4proto - Layer 4 protocol + * Values: + * IPPROTO_TCP, IPPROTO_UDP + * @reserved - Reserved member, will be reused for more options in future + * Values: + * 0 + */ +struct bpf_ct_opts { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +}; + +enum { + NF_BPF_CT_OPTS_SZ = 12, +}; + +static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, + struct bpf_sock_tuple *bpf_tuple, + u32 tuple_len, u8 protonum, + s32 netns_id) +{ + struct nf_conntrack_tuple_hash *hash; + struct nf_conntrack_tuple tuple; + + if (unlikely(protonum != IPPROTO_TCP && protonum != IPPROTO_UDP)) + return ERR_PTR(-EPROTO); + if (unlikely(netns_id < BPF_F_CURRENT_NETNS)) + return ERR_PTR(-EINVAL); + + memset(&tuple, 0, sizeof(tuple)); + switch (tuple_len) { + case sizeof(bpf_tuple->ipv4): + tuple.src.l3num = AF_INET; + tuple.src.u3.ip = bpf_tuple->ipv4.saddr; + tuple.src.u.tcp.port = bpf_tuple->ipv4.sport; + tuple.dst.u3.ip = bpf_tuple->ipv4.daddr; + tuple.dst.u.tcp.port = bpf_tuple->ipv4.dport; + break; + case sizeof(bpf_tuple->ipv6): + tuple.src.l3num = AF_INET6; + memcpy(tuple.src.u3.ip6, bpf_tuple->ipv6.saddr, sizeof(bpf_tuple->ipv6.saddr)); + tuple.src.u.tcp.port = bpf_tuple->ipv6.sport; + memcpy(tuple.dst.u3.ip6, bpf_tuple->ipv6.daddr, sizeof(bpf_tuple->ipv6.daddr)); + tuple.dst.u.tcp.port = bpf_tuple->ipv6.dport; + break; + default: + return ERR_PTR(-EAFNOSUPPORT); + } + + tuple.dst.protonum = protonum; + + if (netns_id >= 0) { + net = get_net_ns_by_id(net, netns_id); + if (unlikely(!net)) + return ERR_PTR(-ENONET); + } + + hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple); + if (netns_id >= 0) + put_net(net); + if (!hash) + return ERR_PTR(-ENOENT); + return nf_ct_tuplehash_to_ctrack(hash); +} + +__diag_push(); +__diag_ignore(GCC, 8, "-Wmissing-prototypes", + "Global functions as their definitions will be in nf_conntrack BTF"); + +/* bpf_xdp_ct_lookup - Lookup CT entry for the given tuple, and acquire a + * reference to it + * + * Parameters: + * @xdp_ctx - Pointer to ctx (xdp_md) in XDP program + * Cannot be NULL + * @bpf_tuple - Pointer to memory representing the tuple to look up + * Cannot be NULL + * @tuple__sz - Length of the tuple structure + * Must be one of sizeof(bpf_tuple->ipv4) or + * sizeof(bpf_tuple->ipv6) + * @opts - Additional options for lookup (documented above) + * Cannot be NULL + * @opts__sz - Length of the bpf_ct_opts structure + * Must be NF_BPF_CT_OPTS_SZ (12) + */ +struct nf_conn * +bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, + u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) +{ + struct xdp_buff *ctx = (struct xdp_buff *)xdp_ctx; + struct net *caller_net; + struct nf_conn *nfct; + + BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ); + + if (!opts) + return NULL; + if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] || + opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + caller_net = dev_net(ctx->rxq->dev); + nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto, + opts->netns_id); + if (IS_ERR(nfct)) { + opts->error = PTR_ERR(nfct); + return NULL; + } + return nfct; +} + +/* bpf_skb_ct_lookup - Lookup CT entry for the given tuple, and acquire a + * reference to it + * + * Parameters: + * @skb_ctx - Pointer to ctx (__sk_buff) in TC program + * Cannot be NULL + * @bpf_tuple - Pointer to memory representing the tuple to look up + * Cannot be NULL + * @tuple__sz - Length of the tuple structure + * Must be one of sizeof(bpf_tuple->ipv4) or + * sizeof(bpf_tuple->ipv6) + * @opts - Additional options for lookup (documented above) + * Cannot be NULL + * @opts__sz - Length of the bpf_ct_opts structure + * Must be NF_BPF_CT_OPTS_SZ (12) + */ +struct nf_conn * +bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, + u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct net *caller_net; + struct nf_conn *nfct; + + BUILD_BUG_ON(sizeof(struct bpf_ct_opts) != NF_BPF_CT_OPTS_SZ); + + if (!opts) + return NULL; + if (!bpf_tuple || opts->reserved[0] || opts->reserved[1] || + opts->reserved[2] || opts__sz != NF_BPF_CT_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + caller_net = skb->dev ? dev_net(skb->dev) : sock_net(skb->sk); + nfct = __bpf_nf_ct_lookup(caller_net, bpf_tuple, tuple__sz, opts->l4proto, + opts->netns_id); + if (IS_ERR(nfct)) { + opts->error = PTR_ERR(nfct); + return NULL; + } + return nfct; +} + +/* bpf_ct_release - Release acquired nf_conn object + * + * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects + * the program if any references remain in the program in all of the explored + * states. + * + * Parameters: + * @nf_conn - Pointer to referenced nf_conn object, obtained using + * bpf_xdp_ct_lookup or bpf_skb_ct_lookup. + */ +void bpf_ct_release(struct nf_conn *nfct) +{ + if (!nfct) + return; + nf_ct_put(nfct); +} + +__diag_pop() + +BTF_SET_START(nf_ct_xdp_check_kfunc_ids) +BTF_ID(func, bpf_xdp_ct_lookup) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_xdp_check_kfunc_ids) + +BTF_SET_START(nf_ct_tc_check_kfunc_ids) +BTF_ID(func, bpf_skb_ct_lookup) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_tc_check_kfunc_ids) + +BTF_SET_START(nf_ct_acquire_kfunc_ids) +BTF_ID(func, bpf_xdp_ct_lookup) +BTF_ID(func, bpf_skb_ct_lookup) +BTF_SET_END(nf_ct_acquire_kfunc_ids) + +BTF_SET_START(nf_ct_release_kfunc_ids) +BTF_ID(func, bpf_ct_release) +BTF_SET_END(nf_ct_release_kfunc_ids) + +/* Both sets are identical */ +#define nf_ct_ret_null_kfunc_ids nf_ct_acquire_kfunc_ids + +static const struct btf_kfunc_id_set nf_conntrack_xdp_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &nf_ct_xdp_check_kfunc_ids, + .acquire_set = &nf_ct_acquire_kfunc_ids, + .release_set = &nf_ct_release_kfunc_ids, + .ret_null_set = &nf_ct_ret_null_kfunc_ids, +}; + +static const struct btf_kfunc_id_set nf_conntrack_tc_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &nf_ct_tc_check_kfunc_ids, + .acquire_set = &nf_ct_acquire_kfunc_ids, + .release_set = &nf_ct_release_kfunc_ids, + .ret_null_set = &nf_ct_ret_null_kfunc_ids, +}; + +int register_nf_conntrack_bpf(void) +{ + int ret; + + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &nf_conntrack_xdp_kfunc_set); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &nf_conntrack_tc_kfunc_set); +} diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 894a325d39f2..d38d689de23c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -34,6 +34,7 @@ #include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_bpf.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> @@ -1924,15 +1925,17 @@ repeat: pr_debug("nf_conntrack_in: Can't track with proto module\n"); nf_ct_put(ct); skb->_nfct = 0; - NF_CT_STAT_INC_ATOMIC(state->net, invalid); - if (ret == -NF_DROP) - NF_CT_STAT_INC_ATOMIC(state->net, drop); /* Special case: TCP tracker reports an attempt to reopen a * closed/aborted connection. We have to go back and create a * fresh conntrack. */ if (ret == -NF_REPEAT) goto repeat; + + NF_CT_STAT_INC_ATOMIC(state->net, invalid); + if (ret == -NF_DROP) + NF_CT_STAT_INC_ATOMIC(state->net, drop); + ret = -ret; goto out; } @@ -2748,8 +2751,15 @@ int nf_conntrack_init_start(void) conntrack_gc_work_init(&conntrack_gc_work); queue_delayed_work(system_power_efficient_wq, &conntrack_gc_work.dwork, HZ); + ret = register_nf_conntrack_bpf(); + if (ret < 0) + goto err_kfunc; + return 0; +err_kfunc: + cancel_delayed_work_sync(&conntrack_gc_work.dwork); + nf_conntrack_proto_fini(); err_proto: nf_conntrack_seqadj_fini(); err_seqadj: diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index 7f19ee259609..55415f011943 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -20,13 +20,14 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#define HELPER_NAME "netbios-ns" #define NMBD_PORT 137 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("NetBIOS name service broadcast connection tracking helper"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ip_conntrack_netbios_ns"); -MODULE_ALIAS_NFCT_HELPER("netbios_ns"); +MODULE_ALIAS_NFCT_HELPER(HELPER_NAME); static unsigned int timeout __read_mostly = 3; module_param(timeout, uint, 0400); @@ -44,7 +45,7 @@ static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff, } static struct nf_conntrack_helper helper __read_mostly = { - .name = "netbios-ns", + .name = HELPER_NAME, .tuple.src.l3num = NFPROTO_IPV4, .tuple.src.u.udp.port = cpu_to_be16(NMBD_PORT), .tuple.dst.protonum = IPPROTO_UDP, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 77938b1042f3..5fa16990da95 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr) prule = (struct nft_rule_dp *)ptr; prule->is_last = 1; - ptr += offsetof(struct nft_rule_dp, data); /* blob size does not include the trailer rule */ } @@ -8264,14 +8263,12 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha void *data, *data_boundary; struct nft_rule_dp *prule; struct nft_rule *rule; - int i; /* already handled or inactive chain? */ if (chain->blob_next || !nft_is_active_next(net, chain)) return 0; rule = list_entry(&chain->rules, struct nft_rule, list); - i = 0; data_size = 0; list_for_each_entry_continue(rule, &chain->rules, list) { @@ -8301,7 +8298,7 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha return -ENOMEM; size = 0; - track.last = last; + track.last = nft_expr_last(rule); nft_rule_for_each_expr(expr, last, rule) { track.cur = expr; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9d5947ab8d4e..e646e9ee4a98 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -167,12 +167,24 @@ nla_put_failure: return -1; } +static bool nft_byteorder_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + struct nft_byteorder *priv = nft_expr_priv(expr); + + track->regs[priv->dreg].selector = NULL; + track->regs[priv->dreg].bitwise = NULL; + + return false; +} + static const struct nft_expr_ops nft_byteorder_ops = { .type = &nft_byteorder_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)), .eval = nft_byteorder_eval, .init = nft_byteorder_init, .dump = nft_byteorder_dump, + .reduce = nft_byteorder_reduce, }; struct nft_expr_type nft_byteorder_type __read_mostly = { diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 7d00a1452b1d..3362417ebfdb 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -62,6 +62,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, { bool invert = false; u32 flags, limit; + int err; if (!tb[NFTA_CONNLIMIT_COUNT]) return -EINVAL; @@ -84,7 +85,15 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, priv->limit = limit; priv->invert = invert; - return nf_ct_netns_get(ctx->net, ctx->family); + err = nf_ct_netns_get(ctx->net, ctx->family); + if (err < 0) + goto err_netns; + + return 0; +err_netns: + kfree(priv->list); + + return err; } static void nft_connlimit_do_destroy(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 518d96c8c247..5adf8bb628a8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, ct = this_cpu_read(nft_ct_pcpu_template); if (likely(refcount_read(&ct->ct_general.use) == 1)) { + refcount_inc(&ct->ct_general.use); nf_ct_zone_add(ct, &zone); } else { - /* previous skb got queued to userspace */ + /* previous skb got queued to userspace, allocate temporary + * one until percpu template can be reused. + */ ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC); if (!ct) { regs->verdict.code = NF_DROP; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 67ad08320886..7e8a39a35627 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -37,6 +37,7 @@ #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/pkt_cls.h> #include "datapath.h" #include "flow.h" @@ -1601,8 +1602,6 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, dp->user_features = 0; } -DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support); - static int ovs_dp_set_upcall_portids(struct datapath *dp, const struct nlattr *ids) { @@ -1657,7 +1656,7 @@ u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id) static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) { - u32 user_features = 0; + u32 user_features = 0, old_features = dp->user_features; int err; if (a[OVS_DP_ATTR_USER_FEATURES]) { @@ -1696,10 +1695,12 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[]) return err; } - if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) - static_branch_enable(&tc_recirc_sharing_support); - else - static_branch_disable(&tc_recirc_sharing_support); + if ((dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && + !(old_features & OVS_DP_F_TC_RECIRC_SHARING)) + tc_skb_ext_tc_enable(); + else if (!(dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) && + (old_features & OVS_DP_F_TC_RECIRC_SHARING)) + tc_skb_ext_tc_disable(); return 0; } @@ -1839,6 +1840,9 @@ static void __dp_destroy(struct datapath *dp) struct flow_table *table = &dp->table; int i; + if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) + tc_skb_ext_tc_disable(); + for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { struct vport *vport; struct hlist_node *n; diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index fcfe6cb46441..0cd29971a907 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -253,8 +253,6 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex) extern struct notifier_block ovs_dp_device_notifier; extern struct genl_family dp_vport_genl_family; -DECLARE_STATIC_KEY_FALSE(tc_recirc_sharing_support); - void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key); void ovs_dp_detach_port(struct vport *); int ovs_dp_upcall(struct datapath *, struct sk_buff *, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 02096f2ec678..f6cd24fd530c 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -34,6 +34,7 @@ #include <net/mpls.h> #include <net/ndisc.h> #include <net/nsh.h> +#include <net/pkt_cls.h> #include <net/netfilter/nf_conntrack_zones.h> #include "conntrack.h" @@ -895,7 +896,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->mac_proto = res; #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - if (static_branch_unlikely(&tc_recirc_sharing_support)) { + if (tc_skb_ext_tc_enabled()) { tc_ext = skb_ext_find(skb, TC_SKB_EXT); key->recirc_id = tc_ext ? tc_ext->chain : 0; OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5bd409ab4cc2..ab87f22cc7ec 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1774,6 +1774,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; list_add(&match->list, &fanout_list); @@ -1788,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); - po->fanout = match; + + /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ + WRITE_ONCE(po->fanout, match); + po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); @@ -3353,6 +3357,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; + po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; @@ -3932,7 +3937,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, } case PACKET_FANOUT_DATA: { - if (!po->fanout) + /* Paired with the WRITE_ONCE() in fanout_add() */ + if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 6be2672a65ea..df864e692267 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -157,7 +157,7 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { struct sk_buff *skb; - unsigned long resend_at, rto_j; + unsigned long resend_at; rxrpc_seq_t cursor, seq, top; ktime_t now, max_age, oldest, ack_ts; int ix; @@ -165,10 +165,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); - rto_j = call->peer->rto_j; - now = ktime_get_real(); - max_age = ktime_sub(now, jiffies_to_usecs(rto_j)); + max_age = ktime_sub(now, jiffies_to_usecs(call->peer->rto_j)); spin_lock_bh(&call->lock); @@ -213,7 +211,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) } resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rto_j; + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); WRITE_ONCE(call->resend_at, resend_at); if (unacked) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 10f2bf2e9068..a45c83f22236 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -468,7 +468,7 @@ done: if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; - ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans); + ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); ack_lost_at += nowj; WRITE_ONCE(call->ack_lost_at, ack_lost_at); rxrpc_reduce_call_timer(call, ack_lost_at, nowj, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d4e27c679123..ff1e6b474fef 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -49,6 +49,23 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +#ifdef CONFIG_NET_CLS_ACT +DEFINE_STATIC_KEY_FALSE(tc_skb_ext_tc); +EXPORT_SYMBOL(tc_skb_ext_tc); + +void tc_skb_ext_tc_enable(void) +{ + static_branch_inc(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_enable); + +void tc_skb_ext_tc_disable(void) +{ + static_branch_dec(&tc_skb_ext_tc); +} +EXPORT_SYMBOL(tc_skb_ext_tc_disable); +#endif + static u32 destroy_obj_hashfn(const struct tcf_proto *tp) { return jhash_3words(tp->chain->index, tp->prio, @@ -1615,19 +1632,21 @@ int tcf_classify(struct sk_buff *skb, ret = __tcf_classify(skb, tp, orig_tp, res, compat_mode, &last_executed_chain); - /* If we missed on some chain */ - if (ret == TC_ACT_UNSPEC && last_executed_chain) { - struct tc_skb_cb *cb = tc_skb_cb(skb); + if (tc_skb_ext_tc_enabled()) { + /* If we missed on some chain */ + if (ret == TC_ACT_UNSPEC && last_executed_chain) { + struct tc_skb_cb *cb = tc_skb_cb(skb); - ext = tc_skb_ext_alloc(skb); - if (WARN_ON_ONCE(!ext)) - return TC_ACT_SHOT; - ext->chain = last_executed_chain; - ext->mru = cb->mru; - ext->post_ct = cb->post_ct; - ext->post_ct_snat = cb->post_ct_snat; - ext->post_ct_dnat = cb->post_ct_dnat; - ext->zone = cb->zone; + ext = tc_skb_ext_alloc(skb); + if (WARN_ON_ONCE(!ext)) + return TC_ACT_SHOT; + ext->chain = last_executed_chain; + ext->mru = cb->mru; + ext->post_ct = cb->post_ct; + ext->post_ct_snat = cb->post_ct_snat; + ext->post_ct_dnat = cb->post_ct_dnat; + ext->zone = cb->zone; + } } return ret; @@ -1945,9 +1964,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, bool prio_allocate; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; unsigned long cl; @@ -1976,6 +1995,8 @@ replay: tp = NULL; cl = 0; block = NULL; + q = NULL; + chain = NULL; flags = 0; if (prio == 0) { @@ -2798,8 +2819,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; - struct tcf_chain *chain = NULL; + struct Qdisc *q; + struct tcf_chain *chain; struct tcf_block *block; unsigned long cl; int err; @@ -2809,6 +2830,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, return -EPERM; replay: + q = NULL; err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 2cb496c84878..179825a3b2fd 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1204,7 +1204,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, err = -ENOENT; if (!ops) { - NL_SET_ERR_MSG(extack, "Specified qdisc not found"); + NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 9267922ea9c3..23a9d6242429 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1810,6 +1810,26 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + if (q->offload) { + /* Options not supported by the offload. */ + if (hopt->rate.overhead || hopt->ceil.overhead) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the overhead parameter"); + goto failure; + } + if (hopt->rate.mpu || hopt->ceil.mpu) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the mpu parameter"); + goto failure; + } + if (hopt->quantum) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the quantum parameter"); + goto failure; + } + if (hopt->prio) { + NL_SET_ERR_MSG(extack, "HTB offload doesn't support the prio parameter"); + goto failure; + } + } + /* Keeping backward compatible with rate_table based iproute2 tc */ if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) qdisc_put_rtab(qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB], diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 961854e56736..00b2e9deabb0 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -566,11 +566,114 @@ static void smc_stat_fallback(struct smc_sock *smc) mutex_unlock(&net->smc.mutex_fback_rsn); } -static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) +/* must be called under rcu read lock */ +static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key) { - wait_queue_head_t *smc_wait = sk_sleep(&smc->sk); - wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk); - unsigned long flags; + struct socket_wq *wq; + __poll_t flags; + + wq = rcu_dereference(smc->sk.sk_wq); + if (!skwq_has_sleeper(wq)) + return; + + /* wake up smc sk->sk_wq */ + if (!key) { + /* sk_state_change */ + wake_up_interruptible_all(&wq->wait); + } else { + flags = key_to_poll(key); + if (flags & (EPOLLIN | EPOLLOUT)) + /* sk_data_ready or sk_write_space */ + wake_up_interruptible_sync_poll(&wq->wait, flags); + else if (flags & EPOLLERR) + /* sk_error_report */ + wake_up_interruptible_poll(&wq->wait, flags); + } +} + +static int smc_fback_mark_woken(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) +{ + struct smc_mark_woken *mark = + container_of(wait, struct smc_mark_woken, wait_entry); + + mark->woken = true; + mark->key = key; + return 0; +} + +static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk, + void (*clcsock_callback)(struct sock *sk)) +{ + struct smc_mark_woken mark = { .woken = false }; + struct socket_wq *wq; + + init_waitqueue_func_entry(&mark.wait_entry, + smc_fback_mark_woken); + rcu_read_lock(); + wq = rcu_dereference(clcsk->sk_wq); + if (!wq) + goto out; + add_wait_queue(sk_sleep(clcsk), &mark.wait_entry); + clcsock_callback(clcsk); + remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry); + + if (mark.woken) + smc_fback_wakeup_waitqueue(smc, mark.key); +out: + rcu_read_unlock(); +} + +static void smc_fback_state_change(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); +} + +static void smc_fback_data_ready(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); +} + +static void smc_fback_write_space(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); +} + +static void smc_fback_error_report(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); +} + +static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) +{ + struct sock *clcsk; + + mutex_lock(&smc->clcsock_release_lock); + if (!smc->clcsock) { + mutex_unlock(&smc->clcsock_release_lock); + return -EBADF; + } + clcsk = smc->clcsock->sk; smc->use_fallback = true; smc->fallback_rsn = reason_code; @@ -582,22 +685,40 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; - /* There may be some entries remaining in - * smc socket->wq, which should be removed - * to clcsocket->wq during the fallback. + /* There might be some wait entries remaining + * in smc sk->sk_wq and they should be woken up + * as clcsock's wait queue is woken up. */ - spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); - list_splice_init(&smc_wait->head, &clc_wait->head); - spin_unlock(&clc_wait->lock); - spin_unlock_irqrestore(&smc_wait->lock, flags); + smc->clcsk_state_change = clcsk->sk_state_change; + smc->clcsk_data_ready = clcsk->sk_data_ready; + smc->clcsk_write_space = clcsk->sk_write_space; + smc->clcsk_error_report = clcsk->sk_error_report; + + clcsk->sk_state_change = smc_fback_state_change; + clcsk->sk_data_ready = smc_fback_data_ready; + clcsk->sk_write_space = smc_fback_write_space; + clcsk->sk_error_report = smc_fback_error_report; + + smc->clcsock->sk->sk_user_data = + (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); } + mutex_unlock(&smc->clcsock_release_lock); + return 0; } /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc_switch_to_fallback(smc, reason_code); + struct net *net = sock_net(&smc->sk); + int rc = 0; + + rc = smc_switch_to_fallback(smc, reason_code); + if (rc) { /* fallback fails */ + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ + return rc; + } smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) @@ -1518,11 +1639,12 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, { /* RDMA setup failed, switch back to TCP */ smc_conn_abort(new_smc, local_first); - if (reason_code < 0) { /* error, no fallback possible */ + if (reason_code < 0 || + smc_switch_to_fallback(new_smc, reason_code)) { + /* error, no fallback possible */ smc_listen_out_err(new_smc); return; } - smc_switch_to_fallback(new_smc, reason_code); if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); @@ -1964,8 +2086,11 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); - smc_listen_out_connected(new_smc); + rc = smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); + if (rc) + smc_listen_out_err(new_smc); + else + smc_listen_out_connected(new_smc); return; } @@ -2094,10 +2219,9 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc; + struct smc_sock *lsmc = + smc_clcsock_user_data(listen_clcsock); - lsmc = (struct smc_sock *) - ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY); if (!lsmc) return; lsmc->clcsk_data_ready(listen_clcsock); @@ -2254,7 +2378,9 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); + rc = smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); + if (rc) + goto out; } else { rc = -EINVAL; goto out; @@ -2447,6 +2573,11 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, /* generic setsockopts reaching us here always apply to the * CLC socket */ + mutex_lock(&smc->clcsock_release_lock); + if (!smc->clcsock) { + mutex_unlock(&smc->clcsock_release_lock); + return -EBADF; + } if (unlikely(!smc->clcsock->ops->setsockopt)) rc = -EOPNOTSUPP; else @@ -2456,6 +2587,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk_error_report(sk); } + mutex_unlock(&smc->clcsock_release_lock); if (optlen < sizeof(int)) return -EINVAL; @@ -2472,7 +2604,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); + rc = smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; } @@ -2494,8 +2626,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_CLOSED) { if (!val) { SMC_STAT_INC(smc, cork_cnt); - mod_delayed_work(smc->conn.lgr->tx_wq, - &smc->conn.tx_work, 0); + smc_tx_pending(&smc->conn); + cancel_delayed_work(&smc->conn.tx_work); } } break; @@ -2515,13 +2647,23 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct smc_sock *smc; + int rc; smc = smc_sk(sock->sk); + mutex_lock(&smc->clcsock_release_lock); + if (!smc->clcsock) { + mutex_unlock(&smc->clcsock_release_lock); + return -EBADF; + } /* socket options apply to the CLC socket */ - if (unlikely(!smc->clcsock->ops->getsockopt)) + if (unlikely(!smc->clcsock->ops->getsockopt)) { + mutex_unlock(&smc->clcsock_release_lock); return -EOPNOTSUPP; - return smc->clcsock->ops->getsockopt(smc->clcsock, level, optname, - optval, optlen); + } + rc = smc->clcsock->ops->getsockopt(smc->clcsock, level, optname, + optval, optlen); + mutex_unlock(&smc->clcsock_release_lock); + return rc; } static int smc_ioctl(struct socket *sock, unsigned int cmd, @@ -2623,8 +2765,10 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); } else { + lock_sock(sk); + rc = smc_tx_sendpage(smc, page, offset, size, flags); + release_sock(sk); SMC_STAT_INC(smc, sendpage_cnt); - rc = sock_no_sendpage(sock, page, offset, size, flags); } out: diff --git a/net/smc/smc.h b/net/smc/smc.h index 3d0b8e300deb..37b2001a0255 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -139,6 +139,12 @@ enum smc_urg_state { SMC_URG_READ = 3, /* data was already read */ }; +struct smc_mark_woken { + bool woken; + void *key; + wait_queue_entry_t wait_entry; +}; + struct smc_connection { struct rb_node alert_node; struct smc_link_group *lgr; /* link group of connection */ @@ -228,8 +234,14 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ + void (*clcsk_state_change)(struct sock *sk); + /* original stat_change fct. */ void (*clcsk_data_ready)(struct sock *sk); - /* original data_ready fct. **/ + /* original data_ready fct. */ + void (*clcsk_write_space)(struct sock *sk); + /* original write_space fct. */ + void (*clcsk_error_report)(struct sock *sk); + /* original error_report fct. */ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ struct work_struct connect_work; /* handle non-blocking connect*/ @@ -264,6 +276,12 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk) +{ + return (struct smc_sock *) + ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index b8898c787d23..1fca2f90a9c7 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_link *link = smc->conn.lnk; - struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net); struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, .lnk[0].ibport = link->ibport, .lnk[0].link_id = link->link_id, - .lnk[0].net_cookie = net->net_cookie, }; memcpy(linfo.lnk[0].ibname, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index be241d53020f..a96ce162825e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -31,7 +31,6 @@ #include "smc_tracepoint.h" #define SMC_TX_WORK_DELAY 0 -#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ @@ -236,16 +235,15 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) */ if ((msg->msg_flags & MSG_OOB) && !send_remaining) conn->urg_tx_pend = true; - if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && - (atomic_read(&conn->sndbuf_space) > - (conn->sndbuf_desc->len >> 1))) - /* for a corked socket defer the RDMA writes if there - * is still sufficient sndbuf_space available + if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc) || + msg->msg_flags & MSG_SENDPAGE_NOTLAST) && + (atomic_read(&conn->sndbuf_space))) + /* for a corked socket defer the RDMA writes if + * sndbuf_space is still available. The applications + * should known how/when to uncork it. */ - queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, - SMC_TX_CORK_DELAY); - else - smc_tx_sndbuf_nonempty(conn); + continue; + smc_tx_sndbuf_nonempty(conn); trace_smc_tx_sendmsg(smc, copylen); } /* while (msg_data_left(msg)) */ @@ -260,6 +258,22 @@ out_err: return rc; } +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset, + size_t size, int flags) +{ + struct msghdr msg = {.msg_flags = flags}; + char *kaddr = kmap(page); + struct kvec iov; + int rc; + + iov.iov_base = kaddr + offset; + iov.iov_len = size; + iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size); + rc = smc_tx_sendmsg(smc, &msg, size); + kunmap(page); + return rc; +} + /***************************** sndbuf consumer *******************************/ /* sndbuf consumer: actual data transfer of one target chunk with ISM write */ @@ -597,27 +611,32 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) return rc; } -/* Wakeup sndbuf consumers from process context - * since there is more data to transmit - */ -void smc_tx_work(struct work_struct *work) +void smc_tx_pending(struct smc_connection *conn) { - struct smc_connection *conn = container_of(to_delayed_work(work), - struct smc_connection, - tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; - lock_sock(&smc->sk); if (smc->sk.sk_err) - goto out; + return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; +} + +/* Wakeup sndbuf consumers from process context + * since there is more data to transmit + */ +void smc_tx_work(struct work_struct *work) +{ + struct smc_connection *conn = container_of(to_delayed_work(work), + struct smc_connection, + tx_work); + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); -out: + lock_sock(&smc->sk); + smc_tx_pending(conn); release_sock(&smc->sk); } diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index 07e6ad76224a..34b578498b1f 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -27,9 +27,12 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn) return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); } +void smc_tx_pending(struct smc_connection *conn); void smc_tx_work(struct work_struct *work); void smc_tx_init(struct smc_sock *smc); int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len); +int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset, + size_t size, int flags); int smc_tx_sndbuf_nonempty(struct smc_connection *conn); void smc_tx_sndbuf_nonfull(struct smc_sock *smc); void smc_tx_consumer_update(struct smc_connection *conn, bool force); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 5f42aa5fc612..8eb7e8544815 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -72,7 +72,8 @@ struct gss_auth { struct gss_api_mech *mech; enum rpc_gss_svc service; struct rpc_clnt *client; - struct net *net; + struct net *net; + netns_tracker ns_tracker; /* * There are two upcall pipes; dentry[1], named "gssd", is used * for the new text-based upcall; dentry[0] is named after the @@ -1013,7 +1014,8 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) goto err_free; } gss_auth->client = clnt; - gss_auth->net = get_net(rpc_net_ns(clnt)); + gss_auth->net = get_net_track(rpc_net_ns(clnt), &gss_auth->ns_tracker, + GFP_KERNEL); err = -EINVAL; gss_auth->mech = gss_mech_get_by_pseudoflavor(flavor); if (!gss_auth->mech) @@ -1068,7 +1070,7 @@ err_destroy_credcache: err_put_mech: gss_mech_put(gss_auth->mech); err_put_net: - put_net(gss_auth->net); + put_net_track(gss_auth->net, &gss_auth->ns_tracker); err_free: kfree(gss_auth->target_name); kfree(gss_auth); @@ -1084,7 +1086,7 @@ gss_free(struct gss_auth *gss_auth) gss_pipe_free(gss_auth->gss_pipe[0]); gss_pipe_free(gss_auth->gss_pipe[1]); gss_mech_put(gss_auth->mech); - put_net(gss_auth->net); + put_net_track(gss_auth->net, &gss_auth->ns_tracker); kfree(gss_auth->target_name); kfree(gss_auth); diff --git a/net/sunrpc/auth_gss/gss_generic_token.c b/net/sunrpc/auth_gss/gss_generic_token.c index fe97f3106536..4a4082bb22ad 100644 --- a/net/sunrpc/auth_gss/gss_generic_token.c +++ b/net/sunrpc/auth_gss/gss_generic_token.c @@ -222,10 +222,8 @@ g_verify_token_header(struct xdr_netobj *mech, int *body_size, if (ret) return ret; - if (!ret) { - *buf_in = buf; - *body_size = toksize; - } + *buf_in = buf; + *body_size = toksize; return ret; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index a312ea2bc440..c83fe618767c 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2900,7 +2900,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, unsigned long connect_timeout; unsigned long reconnect_timeout; unsigned char resvport, reuseport; - int ret = 0; + int ret = 0, ident; rcu_read_lock(); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); @@ -2914,8 +2914,11 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, reuseport = xprt->reuseport; connect_timeout = xprt->connect_timeout; reconnect_timeout = xprt->max_reconnect_timeout; + ident = xprt->xprt_class->ident; rcu_read_unlock(); + if (!xprtargs->ident) + xprtargs->ident = ident; xprt = xprt_create_transport(xprtargs); if (IS_ERR(xprt)) { ret = PTR_ERR(xprt); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index ee5336d73fdd..35588f0afa86 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -600,9 +600,9 @@ static int __rpc_rmdir(struct inode *dir, struct dentry *dentry) dget(dentry); ret = simple_rmdir(dir, dentry); + d_drop(dentry); if (!ret) fsnotify_rmdir(dir, dentry); - d_delete(dentry); dput(dentry); return ret; } @@ -613,9 +613,9 @@ static int __rpc_unlink(struct inode *dir, struct dentry *dentry) dget(dentry); ret = simple_unlink(dir, dentry); + d_drop(dentry); if (!ret) fsnotify_unlink(dir, dentry); - d_delete(dentry); dput(dentry); return ret; } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index b21ad7994147..db878e833b67 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -162,7 +162,7 @@ static void svc_xprt_free(struct kref *kref) if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) svcauth_unix_info_release(xprt); put_cred(xprt->xpt_cred); - put_net(xprt->xpt_net); + put_net_track(xprt->xpt_net, &xprt->ns_tracker); /* See comment on corresponding get in xs_setup_bc_tcp(): */ if (xprt->xpt_bc_xprt) xprt_put(xprt->xpt_bc_xprt); @@ -198,7 +198,7 @@ void svc_xprt_init(struct net *net, struct svc_xprt_class *xcl, mutex_init(&xprt->xpt_mutex); spin_lock_init(&xprt->xpt_lock); set_bit(XPT_BUSY, &xprt->xpt_flags); - xprt->xpt_net = get_net(net); + xprt->xpt_net = get_net_track(net, &xprt->ns_tracker, GFP_ATOMIC); strcpy(xprt->xpt_remotebuf, "uninitialized"); } EXPORT_SYMBOL_GPL(svc_xprt_init); diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 2766dd21935b..b64a0286b182 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -295,8 +295,10 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, online = 1; else if (!strncmp(buf, "remove", 6)) remove = 1; - else - return -EINVAL; + else { + count = -EINVAL; + goto out_put; + } if (wait_on_bit_lock(&xprt->state, XPRT_LOCKED, TASK_KILLABLE)) { count = -EINTR; @@ -307,25 +309,28 @@ static ssize_t rpc_sysfs_xprt_state_change(struct kobject *kobj, goto release_tasks; } if (offline) { - set_bit(XPRT_OFFLINE, &xprt->state); - spin_lock(&xps->xps_lock); - xps->xps_nactive--; - spin_unlock(&xps->xps_lock); + if (!test_and_set_bit(XPRT_OFFLINE, &xprt->state)) { + spin_lock(&xps->xps_lock); + xps->xps_nactive--; + spin_unlock(&xps->xps_lock); + } } else if (online) { - clear_bit(XPRT_OFFLINE, &xprt->state); - spin_lock(&xps->xps_lock); - xps->xps_nactive++; - spin_unlock(&xps->xps_lock); + if (test_and_clear_bit(XPRT_OFFLINE, &xprt->state)) { + spin_lock(&xps->xps_lock); + xps->xps_nactive++; + spin_unlock(&xps->xps_lock); + } } else if (remove) { if (test_bit(XPRT_OFFLINE, &xprt->state)) { - set_bit(XPRT_REMOVE, &xprt->state); - xprt_force_disconnect(xprt); - if (test_bit(XPRT_CONNECTED, &xprt->state)) { - if (!xprt->sending.qlen && - !xprt->pending.qlen && - !xprt->backlog.qlen && - !atomic_long_read(&xprt->queuelen)) - rpc_xprt_switch_remove_xprt(xps, xprt); + if (!test_and_set_bit(XPRT_REMOVE, &xprt->state)) { + xprt_force_disconnect(xprt); + if (test_bit(XPRT_CONNECTED, &xprt->state)) { + if (!xprt->sending.qlen && + !xprt->pending.qlen && + !xprt->backlog.qlen && + !atomic_long_read(&xprt->queuelen)) + rpc_xprt_switch_remove_xprt(xps, xprt); + } } } else { count = -EINVAL; @@ -422,6 +427,7 @@ static struct attribute *rpc_sysfs_xprt_attrs[] = { &rpc_sysfs_xprt_change_state.attr, NULL, }; +ATTRIBUTE_GROUPS(rpc_sysfs_xprt); static struct kobj_attribute rpc_sysfs_xprt_switch_info = __ATTR(xprt_switch_info, 0444, rpc_sysfs_xprt_switch_info_show, NULL); @@ -430,6 +436,7 @@ static struct attribute *rpc_sysfs_xprt_switch_attrs[] = { &rpc_sysfs_xprt_switch_info.attr, NULL, }; +ATTRIBUTE_GROUPS(rpc_sysfs_xprt_switch); static struct kobj_type rpc_sysfs_client_type = { .release = rpc_sysfs_client_release, @@ -439,14 +446,14 @@ static struct kobj_type rpc_sysfs_client_type = { static struct kobj_type rpc_sysfs_xprt_switch_type = { .release = rpc_sysfs_xprt_switch_release, - .default_attrs = rpc_sysfs_xprt_switch_attrs, + .default_groups = rpc_sysfs_xprt_switch_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = rpc_sysfs_xprt_switch_namespace, }; static struct kobj_type rpc_sysfs_xprt_type = { .release = rpc_sysfs_xprt_release, - .default_attrs = rpc_sysfs_xprt_attrs, + .default_groups = rpc_sysfs_xprt_groups, .sysfs_ops = &kobj_sysfs_ops, .namespace = rpc_sysfs_xprt_namespace, }; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index a02de2bddb28..5af484d6ba5e 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1835,7 +1835,7 @@ EXPORT_SYMBOL_GPL(xprt_alloc); void xprt_free(struct rpc_xprt *xprt) { - put_net(xprt->xprt_net); + put_net_track(xprt->xprt_net, &xprt->ns_tracker); xprt_free_all_slots(xprt); xprt_free_id(xprt); rpc_sysfs_xprt_destroy(xprt); @@ -2027,7 +2027,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net) xprt_init_xid(xprt); - xprt->xprt_net = get_net(net); + xprt->xprt_net = get_net_track(net, &xprt->ns_tracker, GFP_KERNEL); } /** diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 17f174d6ea3b..faba7136dd9a 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -13,10 +13,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - #undef RPCRDMA_BACKCHANNEL_DEBUG /** diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ff699307e820..515dd7a66a04 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -45,10 +45,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - static void frwr_cid_init(struct rpcrdma_ep *ep, struct rpcrdma_mr *mr) { diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8035a983c8ce..281ddb87ac8d 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -54,10 +54,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - /* Returns size of largest RPC-over-RDMA header in a Call message * * The largest Call header contains a full-size Read list and a diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 16e5696314a4..42e375dbdadb 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -60,10 +60,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - /* * tunables */ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3d3673ba9e1e..f172d1298013 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -63,17 +63,6 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -/* - * Globals/Macros - */ - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - -/* - * internal functions - */ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_sendctxs_destroy(struct rpcrdma_xprt *r_xprt); static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, @@ -274,8 +263,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ep->re_connect_status = -ENETUNREACH; goto wake_connect_worker; case RDMA_CM_EVENT_REJECTED: - dprintk("rpcrdma: connection to %pISpc rejected: %s\n", - sap, rdma_reject_msg(id, event->status)); ep->re_connect_status = -ECONNREFUSED; if (event->status == IB_CM_REJ_STALE_CONN) ep->re_connect_status = -ENOTCONN; @@ -291,8 +278,6 @@ disconnected: break; } - dprintk("RPC: %s: %pISpc on %s/frwr: %s\n", __func__, sap, - ep->re_id->device->name, rdma_event_msg(event->event)); return 0; } @@ -419,14 +404,6 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) ep->re_attr.qp_type = IB_QPT_RC; ep->re_attr.port_num = ~0; - dprintk("RPC: %s: requested max: dtos: send %d recv %d; " - "iovs: send %d recv %d\n", - __func__, - ep->re_attr.cap.max_send_wr, - ep->re_attr.cap.max_recv_wr, - ep->re_attr.cap.max_send_sge, - ep->re_attr.cap.max_recv_sge); - ep->re_send_batch = ep->re_max_requests >> 3; ep->re_send_count = ep->re_send_batch; init_waitqueue_head(&ep->re_connect_wait); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index d8ee06a9650a..69b6ee5a5fd1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1910,7 +1910,7 @@ static void xs_local_connect(struct rpc_xprt *xprt, struct rpc_task *task) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); int ret; - if (RPC_IS_ASYNC(task)) { + if (RPC_IS_ASYNC(task)) { /* * We want the AF_LOCAL connect to be resolved in the * filesystem namespace of the process making the rpc diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 64ae4c4c44f8..c5eec16213d7 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -226,14 +226,6 @@ static inline void msg_set_bits(struct tipc_msg *m, u32 w, m->hdr[w] |= htonl(val); } -static inline void msg_swap_words(struct tipc_msg *msg, u32 a, u32 b) -{ - u32 temp = msg->hdr[a]; - - msg->hdr[a] = msg->hdr[b]; - msg->hdr[b] = temp; -} - /* * Word 0 */ @@ -480,11 +472,6 @@ static inline void msg_incr_reroute_cnt(struct tipc_msg *m) msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1); } -static inline void msg_reset_reroute_cnt(struct tipc_msg *m) -{ - msg_set_bits(m, 1, 21, 0xf, 0); -} - static inline u32 msg_lookup_scope(struct tipc_msg *m) { return msg_bits(m, 1, 19, 0x3); @@ -800,11 +787,6 @@ static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n) msg_set_word(m, 2, n); } -static inline u32 msg_bcgap_after(struct tipc_msg *m) -{ - return msg_bits(m, 2, 16, 0xffff); -} - static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n) { msg_set_bits(m, 2, 16, 0xffff, n); @@ -868,11 +850,6 @@ static inline void msg_set_next_sent(struct tipc_msg *m, u16 n) msg_set_bits(m, 4, 0, 0xffff, n); } -static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n) -{ - msg_set_bits(m, 4, 0, 0xffff, n); -} - static inline u32 msg_bc_netid(struct tipc_msg *m) { return msg_word(m, 4); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index efc84845bb6b..0024a692f0f8 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1433,7 +1433,8 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (*zc && (out_iov || out_sg)) { if (out_iov) - n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1; + n_sgout = 1 + + iov_iter_npages_cap(out_iov, INT_MAX, data_len); else n_sgout = sg_nents(out_sg); n_sgin = skb_nsg(skb, rxm->offset + prot->prepend_size, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c19569819866..3e0d6281fd1e 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -3240,49 +3240,58 @@ static struct sock *unix_from_bucket(struct seq_file *seq, loff_t *pos) return sk; } -static struct sock *unix_next_socket(struct seq_file *seq, - struct sock *sk, - loff_t *pos) +static struct sock *unix_get_first(struct seq_file *seq, loff_t *pos) { unsigned long bucket = get_bucket(*pos); + struct sock *sk; - while (sk > (struct sock *)SEQ_START_TOKEN) { - sk = sk_next(sk); - if (!sk) - goto next_bucket; - if (sock_net(sk) == seq_file_net(seq)) - return sk; - } - - do { + while (bucket < ARRAY_SIZE(unix_socket_table)) { spin_lock(&unix_table_locks[bucket]); + sk = unix_from_bucket(seq, pos); if (sk) return sk; -next_bucket: - spin_unlock(&unix_table_locks[bucket++]); - *pos = set_bucket_offset(bucket, 1); - } while (bucket < ARRAY_SIZE(unix_socket_table)); + spin_unlock(&unix_table_locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + } return NULL; } +static struct sock *unix_get_next(struct seq_file *seq, struct sock *sk, + loff_t *pos) +{ + unsigned long bucket = get_bucket(*pos); + + for (sk = sk_next(sk); sk; sk = sk_next(sk)) + if (sock_net(sk) == seq_file_net(seq)) + return sk; + + spin_unlock(&unix_table_locks[bucket]); + + *pos = set_bucket_offset(++bucket, 1); + + return unix_get_first(seq, pos); +} + static void *unix_seq_start(struct seq_file *seq, loff_t *pos) { if (!*pos) return SEQ_START_TOKEN; - if (get_bucket(*pos) >= ARRAY_SIZE(unix_socket_table)) - return NULL; - - return unix_next_socket(seq, NULL, pos); + return unix_get_first(seq, pos); } static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; - return unix_next_socket(seq, v, pos); + + if (v == SEQ_START_TOKEN) + return unix_get_first(seq, pos); + + return unix_get_next(seq, v, pos); } static void unix_seq_stop(struct seq_file *seq, void *v) @@ -3347,6 +3356,15 @@ static const struct seq_operations unix_seq_ops = { }; #if IS_BUILTIN(CONFIG_UNIX) && defined(CONFIG_BPF_SYSCALL) +struct bpf_unix_iter_state { + struct seq_net_private p; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + struct sock **batch; + bool st_bucket_done; +}; + struct bpf_iter__unix { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct unix_sock *, unix_sk); @@ -3365,24 +3383,156 @@ static int unix_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, return bpf_iter_run_prog(prog, &ctx); } +static int bpf_iter_unix_hold_batch(struct seq_file *seq, struct sock *start_sk) + +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected = 1; + struct sock *sk; + + sock_hold(start_sk); + iter->batch[iter->end_sk++] = start_sk; + + for (sk = sk_next(start_sk); sk; sk = sk_next(sk)) { + if (sock_net(sk) != seq_file_net(seq)) + continue; + + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++] = sk; + } + + expected++; + } + + spin_unlock(&unix_table_locks[start_sk->sk_hash]); + + return expected; +} + +static void bpf_iter_unix_put_batch(struct bpf_unix_iter_state *iter) +{ + while (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); +} + +static int bpf_iter_unix_realloc_batch(struct bpf_unix_iter_state *iter, + unsigned int new_batch_sz) +{ + struct sock **new_batch; + + new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, + GFP_USER | __GFP_NOWARN); + if (!new_batch) + return -ENOMEM; + + bpf_iter_unix_put_batch(iter); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +static struct sock *bpf_iter_unix_batch(struct seq_file *seq, + loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + unsigned int expected; + bool resized = false; + struct sock *sk; + + if (iter->st_bucket_done) + *pos = set_bucket_offset(get_bucket(*pos) + 1, 1); + +again: + /* Get a new batch */ + iter->cur_sk = 0; + iter->end_sk = 0; + + sk = unix_get_first(seq, pos); + if (!sk) + return NULL; /* Done */ + + expected = bpf_iter_unix_hold_batch(seq, sk); + + if (iter->end_sk == expected) { + iter->st_bucket_done = true; + return sk; + } + + if (!resized && !bpf_iter_unix_realloc_batch(iter, expected * 3 / 2)) { + resized = true; + goto again; + } + + return sk; +} + +static void *bpf_iter_unix_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (!*pos) + return SEQ_START_TOKEN; + + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + return bpf_iter_unix_batch(seq, pos); +} + +static void *bpf_iter_unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_unix_iter_state *iter = seq->private; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so advance to the next sk in + * the batch. + */ + if (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++]); + + ++*pos; + + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk]; + else + sk = bpf_iter_unix_batch(seq, pos); + + return sk; +} + static int bpf_iter_unix_seq_show(struct seq_file *seq, void *v) { struct bpf_iter_meta meta; struct bpf_prog *prog; struct sock *sk = v; uid_t uid; + bool slow; + int ret; if (v == SEQ_START_TOKEN) return 0; + slow = lock_sock_fast(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); meta.seq = seq; prog = bpf_iter_get_info(&meta, false); - return unix_prog_seq_show(prog, &meta, v, uid); + ret = unix_prog_seq_show(prog, &meta, v, uid); +unlock: + unlock_sock_fast(sk, slow); + return ret; } static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) { + struct bpf_unix_iter_state *iter = seq->private; struct bpf_iter_meta meta; struct bpf_prog *prog; @@ -3393,12 +3543,13 @@ static void bpf_iter_unix_seq_stop(struct seq_file *seq, void *v) (void)unix_prog_seq_show(prog, &meta, v, 0); } - unix_seq_stop(seq, v); + if (iter->cur_sk < iter->end_sk) + bpf_iter_unix_put_batch(iter); } static const struct seq_operations bpf_iter_unix_seq_ops = { - .start = unix_seq_start, - .next = unix_seq_next, + .start = bpf_iter_unix_seq_start, + .next = bpf_iter_unix_seq_next, .stop = bpf_iter_unix_seq_stop, .show = bpf_iter_unix_seq_show, }; @@ -3447,13 +3598,55 @@ static struct pernet_operations unix_net_ops = { DEFINE_BPF_ITER_FUNC(unix, struct bpf_iter_meta *meta, struct unix_sock *unix_sk, uid_t uid) +#define INIT_BATCH_SZ 16 + +static int bpf_iter_init_unix(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_unix_iter_state *iter = priv_data; + int err; + + err = bpf_iter_init_seq_net(priv_data, aux); + if (err) + return err; + + err = bpf_iter_unix_realloc_batch(iter, INIT_BATCH_SZ); + if (err) { + bpf_iter_fini_seq_net(priv_data); + return err; + } + + return 0; +} + +static void bpf_iter_fini_unix(void *priv_data) +{ + struct bpf_unix_iter_state *iter = priv_data; + + bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); +} + static const struct bpf_iter_seq_info unix_seq_info = { .seq_ops = &bpf_iter_unix_seq_ops, - .init_seq_private = bpf_iter_init_seq_net, - .fini_seq_private = bpf_iter_fini_seq_net, - .seq_priv_size = sizeof(struct seq_net_private), + .init_seq_private = bpf_iter_init_unix, + .fini_seq_private = bpf_iter_fini_unix, + .seq_priv_size = sizeof(struct bpf_unix_iter_state), }; +static const struct bpf_func_proto * +bpf_iter_unix_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_setsockopt: + return &bpf_sk_setsockopt_proto; + case BPF_FUNC_getsockopt: + return &bpf_sk_getsockopt_proto; + default: + return NULL; + } +} + static struct bpf_iter_reg unix_reg_info = { .target = "unix", .ctx_arg_info_size = 1, @@ -3461,6 +3654,7 @@ static struct bpf_iter_reg unix_reg_info = { { offsetof(struct bpf_iter__unix, unix_sk), PTR_TO_BTF_ID_OR_NULL }, }, + .get_func_proto = bpf_iter_unix_get_func_proto, .seq_info = &unix_seq_info, }; diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 8675fa5273df..3ec8ad9c1750 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -26,12 +26,12 @@ static void int_exit(int sig) { __u32 curr_prog_id = 0; - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given interface\n"); else @@ -143,7 +143,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index a70b094c8ec5..6c61d5f570fb 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -34,12 +34,12 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given iface\n"); else @@ -173,7 +173,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 4ad896782f77..79ccd9891924 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -33,7 +33,7 @@ static int do_attach(int idx, int prog_fd, int map_fd, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, prog_fd, xdp_flags); + err = bpf_xdp_attach(idx, prog_fd, xdp_flags, NULL); if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); return err; @@ -51,7 +51,7 @@ static int do_detach(int idx, const char *name) { int err; - err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + err = bpf_xdp_detach(idx, xdp_flags, NULL); if (err < 0) printf("ERROR: failed to detach program from %s\n", name); diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index cfaf7e50e431..2d565ba54b8c 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -43,13 +43,13 @@ static void int_exit(int sig) int i = 0; for (i = 0; i < total_ifindex; i++) { - if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) { - printf("bpf_get_link_xdp_id on iface %d failed\n", + if (bpf_xdp_query_id(ifindex_list[i], flags, &prog_id)) { + printf("bpf_xdp_query_id on iface %d failed\n", ifindex_list[i]); exit(1); } if (prog_id_list[i] == prog_id) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_xdp_detach(ifindex_list[i], flags, NULL); else if (!prog_id) printf("couldn't find a prog id on iface %d\n", ifindex_list[i]); @@ -716,12 +716,12 @@ int main(int ac, char **argv) } prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *)); for (i = 0; i < total_ifindex; i++) { - if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) { + if (bpf_xdp_attach(ifindex_list[i], prog_fd, flags, NULL) < 0) { printf("link set xdp fd failed\n"); int recovery_index = i; for (i = 0; i < recovery_index; i++) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + bpf_xdp_detach(ifindex_list[i], flags, NULL); return 1; } diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 74a2926eba08..fb2532d13aac 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -62,15 +62,15 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(EXIT_FAIL); } if (prog_id == curr_prog_id) { fprintf(stderr, "Interrupted: Removing XDP program on ifindex:%d device:%s\n", ifindex, ifname); - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); } else if (!curr_prog_id) { printf("couldn't find a prog id on a given iface\n"); } else { @@ -209,7 +209,7 @@ static struct datarec *alloc_record_per_cpu(void) static struct record *alloc_record_per_rxq(void) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); struct record *array; array = calloc(nr_rxqs, sizeof(struct record)); @@ -222,7 +222,7 @@ static struct record *alloc_record_per_rxq(void) static struct stats_record *alloc_stats_record(void) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); struct stats_record *rec; int i; @@ -241,7 +241,7 @@ static struct stats_record *alloc_stats_record(void) static void free_stats_record(struct stats_record *r) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); int i; for (i = 0; i < nr_rxqs; i++) @@ -289,7 +289,7 @@ static void stats_collect(struct stats_record *rec) map_collect_percpu(fd, 0, &rec->stats); fd = bpf_map__fd(rx_queue_index_map); - max_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + max_rxqs = bpf_map__max_entries(rx_queue_index_map); for (i = 0; i < max_rxqs; i++) map_collect_percpu(fd, i, &rec->rxq[i]); } @@ -335,7 +335,7 @@ static void stats_print(struct stats_record *stats_rec, struct stats_record *stats_prev, int action, __u32 cfg_opt) { - unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries; + unsigned int nr_rxqs = bpf_map__max_entries(rx_queue_index_map); unsigned int nr_cpus = bpf_num_possible_cpus(); double pps = 0, err = 0; struct record *rec, *prev; @@ -582,7 +582,7 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 587eacb49103..0a2b3e997aed 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -30,7 +30,7 @@ static int do_attach(int idx, int fd, const char *name) __u32 info_len = sizeof(info); int err; - err = bpf_set_link_xdp_fd(idx, fd, xdp_flags); + err = bpf_xdp_attach(idx, fd, xdp_flags, NULL); if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); return err; @@ -51,13 +51,13 @@ static int do_detach(int idx, const char *name) __u32 curr_prog_id = 0; int err = 0; - err = bpf_get_link_xdp_id(idx, &curr_prog_id, xdp_flags); + err = bpf_xdp_query_id(idx, xdp_flags, &curr_prog_id); if (err) { - printf("bpf_get_link_xdp_id failed\n"); + printf("bpf_xdp_query_id failed\n"); return err; } if (prog_id == curr_prog_id) { - err = bpf_set_link_xdp_fd(idx, -1, xdp_flags); + err = bpf_xdp_detach(idx, xdp_flags, NULL); if (err < 0) printf("ERROR: failed to detach prog from %s\n", name); } else if (!curr_prog_id) { diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c index 8740838e7767..ae70a7943d85 100644 --- a/samples/bpf/xdp_sample_user.c +++ b/samples/bpf/xdp_sample_user.c @@ -1265,7 +1265,7 @@ static int __sample_remove_xdp(int ifindex, __u32 prog_id, int xdp_flags) int ret; if (prog_id) { - ret = bpf_get_link_xdp_id(ifindex, &cur_prog_id, xdp_flags); + ret = bpf_xdp_query_id(ifindex, xdp_flags, &cur_prog_id); if (ret < 0) return -errno; @@ -1278,7 +1278,7 @@ static int __sample_remove_xdp(int ifindex, __u32 prog_id, int xdp_flags) } } - return bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + return bpf_xdp_detach(ifindex, xdp_flags, NULL); } int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, @@ -1295,8 +1295,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, xdp_flags |= !force ? XDP_FLAGS_UPDATE_IF_NOEXIST : 0; xdp_flags |= generic ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE; - ret = bpf_set_link_xdp_fd(ifindex, bpf_program__fd(xdp_prog), - xdp_flags); + ret = bpf_xdp_attach(ifindex, bpf_program__fd(xdp_prog), xdp_flags, NULL); if (ret < 0) { ret = -errno; fprintf(stderr, @@ -1308,7 +1307,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, return ret; } - ret = bpf_get_link_xdp_id(ifindex, &prog_id, xdp_flags); + ret = bpf_xdp_query_id(ifindex, xdp_flags, &prog_id); if (ret < 0) { ret = -errno; fprintf(stderr, diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 1d4f305d02aa..7370c03c96fc 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -32,12 +32,12 @@ static void int_exit(int sig) __u32 curr_prog_id = 0; if (ifindex > -1) { - if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(1); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given iface\n"); else @@ -288,7 +288,7 @@ int main(int argc, char **argv) } } - if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { + if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) { printf("link set xdp fd failed\n"); return 1; } @@ -302,7 +302,7 @@ int main(int argc, char **argv) poll_stats(kill_after_s); - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + bpf_xdp_detach(ifindex, xdp_flags, NULL); return 0; } diff --git a/samples/bpf/xdpsock_ctrl_proc.c b/samples/bpf/xdpsock_ctrl_proc.c index cc4408797ab7..28b5f2a9fa08 100644 --- a/samples/bpf/xdpsock_ctrl_proc.c +++ b/samples/bpf/xdpsock_ctrl_proc.c @@ -173,7 +173,7 @@ main(int argc, char **argv) unlink(SOCKET_NAME); /* Unset fd for given ifindex */ - err = bpf_set_link_xdp_fd(ifindex, -1, 0); + err = bpf_xdp_detach(ifindex, 0, NULL); if (err) { fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex); return err; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index aa50864e4415..19288a2bbc75 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -571,13 +571,13 @@ static void remove_xdp_program(void) { u32 curr_prog_id = 0; - if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { - printf("bpf_get_link_xdp_id failed\n"); + if (bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &curr_prog_id)) { + printf("bpf_xdp_query_id failed\n"); exit(EXIT_FAILURE); } if (prog_id == curr_prog_id) - bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + bpf_xdp_detach(opt_ifindex, opt_xdp_flags, NULL); else if (!curr_prog_id) printf("couldn't find a prog id on a given interface\n"); else @@ -1027,7 +1027,7 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, if (ret) exit_with_error(-ret); - ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags); + ret = bpf_xdp_query_id(opt_ifindex, opt_xdp_flags, &prog_id); if (ret) exit_with_error(-ret); @@ -1760,7 +1760,7 @@ static void load_xdp_program(char **argv, struct bpf_object **obj) exit(EXIT_FAILURE); } - if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) { + if (bpf_xdp_attach(opt_ifindex, prog_fd, opt_xdp_flags, NULL) < 0) { fprintf(stderr, "ERROR: link set xdp fd failed\n"); exit(EXIT_FAILURE); } diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c index 52e7c4ffd228..2220509588a0 100644 --- a/samples/bpf/xsk_fwd.c +++ b/samples/bpf/xsk_fwd.c @@ -974,8 +974,8 @@ static void remove_xdp_program(void) int i; for (i = 0 ; i < n_ports; i++) - bpf_set_link_xdp_fd(if_nametoindex(port_params[i].iface), -1, - port_params[i].xsk_cfg.xdp_flags); + bpf_xdp_detach(if_nametoindex(port_params[i].iface), + port_params[i].xsk_cfg.xdp_flags, NULL); } int main(int argc, char **argv) diff --git a/scripts/Makefile b/scripts/Makefile index ecd3acacd0ec..ce5aa9030b74 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -25,7 +25,7 @@ HOSTCFLAGS_sorttable.o += -I$(srctree)/tools/arch/x86/include HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED endif -ifdef CONFIG_DYNAMIC_FTRACE +ifdef CONFIG_BUILDTIME_MCOUNT_SORT HOSTCFLAGS_sorttable.o += -DMCOUNT_SORT_ENABLED endif diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index a6403ddf5de7..096625242475 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -87,21 +87,25 @@ class HeaderParser(object): self.line = '' self.helpers = [] self.commands = [] + self.desc_unique_helpers = set() + self.define_unique_helpers = [] + self.desc_syscalls = [] + self.enum_syscalls = [] def parse_element(self): proto = self.parse_symbol() - desc = self.parse_desc() - ret = self.parse_ret() + desc = self.parse_desc(proto) + ret = self.parse_ret(proto) return APIElement(proto=proto, desc=desc, ret=ret) def parse_helper(self): proto = self.parse_proto() - desc = self.parse_desc() - ret = self.parse_ret() + desc = self.parse_desc(proto) + ret = self.parse_ret(proto) return Helper(proto=proto, desc=desc, ret=ret) def parse_symbol(self): - p = re.compile(' \* ?(.+)$') + p = re.compile(' \* ?(BPF\w+)$') capture = p.match(self.line) if not capture: raise NoSyscallCommandFound @@ -127,16 +131,15 @@ class HeaderParser(object): self.line = self.reader.readline() return capture.group(1) - def parse_desc(self): + def parse_desc(self, proto): p = re.compile(' \* ?(?:\t| {5,8})Description$') capture = p.match(self.line) if not capture: - # Helper can have empty description and we might be parsing another - # attribute: return but do not consume. - return '' + raise Exception("No description section found for " + proto) # Description can be several lines, some of them possibly empty, and it # stops when another subsection title is met. desc = '' + desc_present = False while True: self.line = self.reader.readline() if self.line == ' *\n': @@ -145,21 +148,24 @@ class HeaderParser(object): p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)') capture = p.match(self.line) if capture: + desc_present = True desc += capture.group(1) + '\n' else: break + + if not desc_present: + raise Exception("No description found for " + proto) return desc - def parse_ret(self): + def parse_ret(self, proto): p = re.compile(' \* ?(?:\t| {5,8})Return$') capture = p.match(self.line) if not capture: - # Helper can have empty retval and we might be parsing another - # attribute: return but do not consume. - return '' + raise Exception("No return section found for " + proto) # Return value description can be several lines, some of them possibly # empty, and it stops when another subsection title is met. ret = '' + ret_present = False while True: self.line = self.reader.readline() if self.line == ' *\n': @@ -168,44 +174,101 @@ class HeaderParser(object): p = re.compile(' \* ?(?:\t| {5,8})(?:\t| {8})(.*)') capture = p.match(self.line) if capture: + ret_present = True ret += capture.group(1) + '\n' else: break + + if not ret_present: + raise Exception("No return found for " + proto) return ret - def seek_to(self, target, help_message): + def seek_to(self, target, help_message, discard_lines = 1): self.reader.seek(0) offset = self.reader.read().find(target) if offset == -1: raise Exception(help_message) self.reader.seek(offset) self.reader.readline() - self.reader.readline() + for _ in range(discard_lines): + self.reader.readline() self.line = self.reader.readline() - def parse_syscall(self): + def parse_desc_syscall(self): self.seek_to('* DOC: eBPF Syscall Commands', 'Could not find start of eBPF syscall descriptions list') while True: try: command = self.parse_element() self.commands.append(command) + self.desc_syscalls.append(command.proto) + except NoSyscallCommandFound: break - def parse_helpers(self): + def parse_enum_syscall(self): + self.seek_to('enum bpf_cmd {', + 'Could not find start of bpf_cmd enum', 0) + # Searches for either one or more BPF\w+ enums + bpf_p = re.compile('\s*(BPF\w+)+') + # Searches for an enum entry assigned to another entry, + # for e.g. BPF_PROG_RUN = BPF_PROG_TEST_RUN, which is + # not documented hence should be skipped in check to + # determine if the right number of syscalls are documented + assign_p = re.compile('\s*(BPF\w+)\s*=\s*(BPF\w+)') + bpf_cmd_str = '' + while True: + capture = assign_p.match(self.line) + if capture: + # Skip line if an enum entry is assigned to another entry + self.line = self.reader.readline() + continue + capture = bpf_p.match(self.line) + if capture: + bpf_cmd_str += self.line + else: + break + self.line = self.reader.readline() + # Find the number of occurences of BPF\w+ + self.enum_syscalls = re.findall('(BPF\w+)+', bpf_cmd_str) + + def parse_desc_helpers(self): self.seek_to('* Start of BPF helper function descriptions:', 'Could not find start of eBPF helper descriptions list') while True: try: helper = self.parse_helper() self.helpers.append(helper) + proto = helper.proto_break_down() + self.desc_unique_helpers.add(proto['name']) except NoHelperFound: break + def parse_define_helpers(self): + # Parse the number of FN(...) in #define __BPF_FUNC_MAPPER to compare + # later with the number of unique function names present in description. + # Note: seek_to(..) discards the first line below the target search text, + # resulting in FN(unspec) being skipped and not added to self.define_unique_helpers. + self.seek_to('#define __BPF_FUNC_MAPPER(FN)', + 'Could not find start of eBPF helper definition list') + # Searches for either one or more FN(\w+) defines or a backslash for newline + p = re.compile('\s*(FN\(\w+\))+|\\\\') + fn_defines_str = '' + while True: + capture = p.match(self.line) + if capture: + fn_defines_str += self.line + else: + break + self.line = self.reader.readline() + # Find the number of occurences of FN(\w+) + self.define_unique_helpers = re.findall('FN\(\w+\)', fn_defines_str) + def run(self): - self.parse_syscall() - self.parse_helpers() + self.parse_desc_syscall() + self.parse_enum_syscall() + self.parse_desc_helpers() + self.parse_define_helpers() self.reader.close() ############################################################################### @@ -235,6 +298,25 @@ class Printer(object): self.print_one(elem) self.print_footer() + def elem_number_check(self, desc_unique_elem, define_unique_elem, type, instance): + """ + Checks the number of helpers/syscalls documented within the header file + description with those defined as part of enum/macro and raise an + Exception if they don't match. + """ + nr_desc_unique_elem = len(desc_unique_elem) + nr_define_unique_elem = len(define_unique_elem) + if nr_desc_unique_elem != nr_define_unique_elem: + exception_msg = ''' +The number of unique %s in description (%d) doesn\'t match the number of unique %s defined in %s (%d) +''' % (type, nr_desc_unique_elem, type, instance, nr_define_unique_elem) + if nr_desc_unique_elem < nr_define_unique_elem: + # Function description is parsed until no helper is found (which can be due to + # misformatting). Hence, only print the first missing/misformatted helper/enum. + exception_msg += ''' +The description for %s is not present or formatted correctly. +''' % (define_unique_elem[nr_desc_unique_elem]) + raise Exception(exception_msg) class PrinterRST(Printer): """ @@ -295,7 +377,6 @@ class PrinterRST(Printer): print('') - class PrinterHelpersRST(PrinterRST): """ A printer for dumping collected information about helpers as a ReStructured @@ -305,6 +386,7 @@ class PrinterHelpersRST(PrinterRST): """ def __init__(self, parser): self.elements = parser.helpers + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') def print_header(self): header = '''\ @@ -478,6 +560,7 @@ class PrinterSyscallRST(PrinterRST): """ def __init__(self, parser): self.elements = parser.commands + self.elem_number_check(parser.desc_syscalls, parser.enum_syscalls, 'syscall', 'bpf_cmd') def print_header(self): header = '''\ @@ -509,6 +592,7 @@ class PrinterHelpers(Printer): """ def __init__(self, parser): self.elements = parser.helpers + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') type_fwds = [ 'struct bpf_fib_lookup', diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 842889f3dcb7..a9f8c63a96d1 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -838,7 +838,7 @@ int devcgroup_check_permission(short type, u32 major, u32 minor, short access) int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); if (rc) - return -EPERM; + return rc; #ifdef CONFIG_CGROUP_DEVICE return devcgroup_legacy_check_permission(type, major, minor, access); diff --git a/security/security.c b/security/security.c index 3d4eb474f35b..22261d79f333 100644 --- a/security/security.c +++ b/security/security.c @@ -1048,8 +1048,19 @@ int security_dentry_init_security(struct dentry *dentry, int mode, const char **xattr_name, void **ctx, u32 *ctxlen) { - return call_int_hook(dentry_init_security, -EOPNOTSUPP, dentry, mode, - name, xattr_name, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.dentry_init_security, list) { + rc = hp->hook.dentry_init_security(dentry, mode, name, + xattr_name, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(dentry_init_security)) + return rc; + } + return LSM_RET_DEFAULT(dentry_init_security); } EXPORT_SYMBOL(security_dentry_init_security); diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 2ec6e5cd25d9..feb206f3acb4 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -152,6 +152,8 @@ static void cond_list_destroy(struct policydb *p) for (i = 0; i < p->cond_list_len; i++) cond_node_destroy(&p->cond_list[i]); kfree(p->cond_list); + p->cond_list = NULL; + p->cond_list_len = 0; } void cond_policydb_destroy(struct policydb *p) @@ -441,7 +443,6 @@ int cond_read_list(struct policydb *p, void *fp) return 0; err: cond_list_destroy(p); - p->cond_list = NULL; return rc; } diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 2da3316bb559..bf6e96011dfe 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -452,6 +452,9 @@ struct kvm_sync_regs { #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001 +/* attributes for system fd (group 0) */ +#define KVM_X86_XCOMP_GUEST_SUPP 0 + struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 59833125ac0a..a2c665beda87 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -902,7 +902,7 @@ static int do_show(int argc, char **argv) equal_fn_for_key_as_id, NULL); btf_map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!btf_prog_table || !btf_map_table) { + if (IS_ERR(btf_prog_table) || IS_ERR(btf_map_table)) { hashmap__free(btf_prog_table); hashmap__free(btf_map_table); if (fd >= 0) diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 3571a281c43f..effe136119d7 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -50,6 +50,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, const char *attach_flags_str, int level) { + char prog_name[MAX_PROG_FULL_NAME]; struct bpf_prog_info info = {}; __u32 info_len = sizeof(info); int prog_fd; @@ -63,6 +64,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, return -1; } + get_prog_full_name(&info, prog_fd, prog_name, sizeof(prog_name)); if (json_output) { jsonw_start_object(json_wtr); jsonw_uint_field(json_wtr, "id", info.id); @@ -73,7 +75,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, jsonw_uint_field(json_wtr, "attach_type", attach_type); jsonw_string_field(json_wtr, "attach_flags", attach_flags_str); - jsonw_string_field(json_wtr, "name", info.name); + jsonw_string_field(json_wtr, "name", prog_name); jsonw_end_object(json_wtr); } else { printf("%s%-8u ", level ? " " : "", info.id); @@ -81,7 +83,7 @@ static int show_bpf_prog(int id, enum bpf_attach_type attach_type, printf("%-15s", attach_type_name[attach_type]); else printf("type %-10u", attach_type); - printf(" %-15s %-15s\n", attach_flags_str, info.name); + printf(" %-15s %-15s\n", attach_flags_str, prog_name); } close(prog_fd); diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index fa8eb8134344..111dff809c7b 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -24,6 +24,7 @@ #include <bpf/bpf.h> #include <bpf/hashmap.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <bpf/btf.h> #include "main.h" @@ -304,6 +305,49 @@ const char *get_fd_type_name(enum bpf_obj_type type) return names[type]; } +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len) +{ + const char *prog_name = prog_info->name; + const struct btf_type *func_type; + const struct bpf_func_info finfo; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + struct btf *prog_btf = NULL; + + if (buff_len <= BPF_OBJ_NAME_LEN || + strlen(prog_info->name) < BPF_OBJ_NAME_LEN - 1) + goto copy_name; + + if (!prog_info->btf_id || prog_info->nr_func_info == 0) + goto copy_name; + + info.nr_func_info = 1; + info.func_info_rec_size = prog_info->func_info_rec_size; + if (info.func_info_rec_size > sizeof(finfo)) + info.func_info_rec_size = sizeof(finfo); + info.func_info = ptr_to_u64(&finfo); + + if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) + goto copy_name; + + prog_btf = btf__load_from_kernel_by_id(info.btf_id); + if (!prog_btf) + goto copy_name; + + func_type = btf__type_by_id(prog_btf, finfo.type_id); + if (!func_type || !btf_is_func(func_type)) + goto copy_name; + + prog_name = btf__name_by_offset(prog_btf, func_type->name_off); + +copy_name: + snprintf(name_buff, buff_len, "%s", prog_name); + + if (prog_btf) + btf__free(prog_btf); +} + int get_fd_type(int fd) { char path[PATH_MAX]; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index b4695df2ea3d..43e3f8700ecc 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -227,7 +227,7 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name) /* only generate definitions for memory-mapped internal maps */ if (!bpf_map__is_internal(map)) continue; - if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + if (!(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; if (!get_map_ident(map, map_ident, sizeof(map_ident))) @@ -468,7 +468,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) if (!get_map_ident(map, ident, sizeof(ident))) continue; if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) printf("\tmunmap(skel->%1$s, %2$zd);\n", ident, bpf_map_mmap_sz(map)); codegen("\ @@ -536,7 +536,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h continue; if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; codegen("\ @@ -600,10 +600,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h continue; if (!bpf_map__is_internal(map) || - !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + !(bpf_map__map_flags(map) & BPF_F_MMAPABLE)) continue; - if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) + if (bpf_map__map_flags(map) & BPF_F_RDONLY_PROG) mmap_flags = "PROT_READ"; else mmap_flags = "PROT_READ | PROT_WRITE"; @@ -927,7 +927,6 @@ static int do_skeleton(int argc, char **argv) s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ goto err; \n\ - obj->skeleton = s; \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -962,7 +961,7 @@ static int do_skeleton(int argc, char **argv) i, bpf_map__name(map), i, ident); /* memory-mapped internal maps */ if (bpf_map__is_internal(map) && - (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) { + (bpf_map__map_flags(map) & BPF_F_MMAPABLE)) { printf("\ts->maps[%zu].mmaped = (void **)&obj->%s;\n", i, ident); } @@ -1000,6 +999,7 @@ static int do_skeleton(int argc, char **argv) \n\ s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ \n\ + obj->skeleton = s; \n\ return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 2c258db0d352..97dec81950e5 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -2,6 +2,7 @@ /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <net/if.h> #include <stdio.h> #include <unistd.h> @@ -306,7 +307,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { link_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!link_table) { + if (IS_ERR(link_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 020e91a542d5..9d01fa9de033 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -478,7 +478,14 @@ int main(int argc, char **argv) } if (!legacy_libbpf) { - ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + enum libbpf_strict_mode mode; + + /* Allow legacy map definitions for skeleton generation. + * It will still be rejected if users use LIBBPF_STRICT_ALL + * mode for loading generated skeleton. + */ + mode = (__LIBBPF_STRICT_LAST - 1) & ~LIBBPF_STRICT_MAP_DEFINITIONS; + ret = libbpf_set_strict_mode(mode); if (ret) p_err("failed to enable libbpf strict mode: %d", ret); } diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 8d76d937a62b..0c3840596b5a 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -140,6 +140,10 @@ struct cmd { int cmd_select(const struct cmd *cmds, int argc, char **argv, int (*help)(int argc, char **argv)); +#define MAX_PROG_FULL_NAME 128 +void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd, + char *name_buff, size_t buff_len); + int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index cc530a229812..c66a3c979b7a 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -699,7 +699,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { map_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!map_table) { + if (IS_ERR(map_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 649053704bd7..526a332c48e6 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -551,7 +551,7 @@ static int do_attach_detach_xdp(int progfd, enum net_attach_type attach_type, if (attach_type == NET_ATTACH_TYPE_XDP_OFFLOAD) flags |= XDP_FLAGS_HW_MODE; - return bpf_set_link_xdp_fd(ifindex, progfd, flags); + return bpf_xdp_attach(ifindex, progfd, flags, NULL); } static int do_attach(int argc, char **argv) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index 56b598eee043..7c384d10e95f 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2020 Facebook */ #include <errno.h> +#include <linux/err.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -101,7 +102,7 @@ int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type) libbpf_print_fn_t default_print; *map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!*map) { + if (IS_ERR(*map)) { p_err("failed to create hashmap for PID references"); return -1; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 2a21d50516bc..cf935c63e6f5 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -424,8 +424,10 @@ out_free: free(value); } -static void print_prog_header_json(struct bpf_prog_info *info) +static void print_prog_header_json(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + jsonw_uint_field(json_wtr, "id", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) jsonw_string_field(json_wtr, "type", @@ -433,8 +435,10 @@ static void print_prog_header_json(struct bpf_prog_info *info) else jsonw_uint_field(json_wtr, "type", info->type); - if (*info->name) - jsonw_string_field(json_wtr, "name", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + jsonw_string_field(json_wtr, "name", prog_name); + } jsonw_name(json_wtr, "tag"); jsonw_printf(json_wtr, "\"" BPF_TAG_FMT "\"", @@ -455,7 +459,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) char *memlock; jsonw_start_object(json_wtr); - print_prog_header_json(info); + print_prog_header_json(info, fd); print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -507,16 +511,20 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) jsonw_end_object(json_wtr); } -static void print_prog_header_plain(struct bpf_prog_info *info) +static void print_prog_header_plain(struct bpf_prog_info *info, int fd) { + char prog_name[MAX_PROG_FULL_NAME]; + printf("%u: ", info->id); if (info->type < ARRAY_SIZE(prog_type_name)) printf("%s ", prog_type_name[info->type]); else printf("type %u ", info->type); - if (*info->name) - printf("name %s ", info->name); + if (*info->name) { + get_prog_full_name(info, fd, prog_name, sizeof(prog_name)); + printf("name %s ", prog_name); + } printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); @@ -534,7 +542,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) { char *memlock; - print_prog_header_plain(info); + print_prog_header_plain(info, fd); if (info->load_time) { char buf[32]; @@ -641,7 +649,7 @@ static int do_show(int argc, char **argv) if (show_pinned) { prog_table = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL); - if (!prog_table) { + if (IS_ERR(prog_table)) { p_err("failed to create hashmap for pinned paths"); return -1; } @@ -972,10 +980,10 @@ static int do_dump(int argc, char **argv) if (json_output && nb_fds > 1) { jsonw_start_object(json_wtr); /* prog object */ - print_prog_header_json(&info); + print_prog_header_json(&info, fds[i]); jsonw_name(json_wtr, "insns"); } else if (nb_fds > 1) { - print_prog_header_plain(&info); + print_prog_header_plain(&info, fds[i]); } err = prog_dump(&info, mode, filepath, opcodes, visual, linum); diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 2f693b082bdb..e08a6ff2866c 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -480,7 +480,6 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { LIBBPF_OPTS(bpf_object_open_opts, open_opts); - const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); int nr_errs = 0, nr_maps = 0; @@ -510,8 +509,7 @@ static int do_register(int argc, char **argv) } bpf_object__for_each_map(map, obj) { - def = bpf_map__def(map); - if (def->type != BPF_MAP_TYPE_STRUCT_OPS) + if (bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS) continue; link = bpf_map__attach_struct_ops(map); diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 9ddeca947635..19a3112e271a 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -9,7 +9,11 @@ ifeq ($(V),1) msg = else Q = @ - msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + ifeq ($(silent),1) + msg = + else + msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + endif MAKEFLAGS=--no-print-directory endif @@ -20,6 +24,8 @@ LD = $(HOSTLD) ARCH = $(HOSTARCH) RM ?= rm CROSS_COMPILE = +CFLAGS := $(KBUILD_HOSTCFLAGS) +LDFLAGS := $(KBUILD_HOSTLDFLAGS) OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -47,10 +53,10 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT) $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) \ - DESTDIR=$(LIBBPF_DESTDIR) prefix= \ + DESTDIR=$(LIBBPF_DESTDIR) prefix= EXTRA_CFLAGS="$(CFLAGS)" \ $(abspath $@) install_headers -CFLAGS := -g \ +CFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ diff --git a/tools/bpf/runqslower/runqslower.bpf.c b/tools/bpf/runqslower/runqslower.bpf.c index ab9353f2fd46..9a5c1f008fe6 100644 --- a/tools/bpf/runqslower/runqslower.bpf.c +++ b/tools/bpf/runqslower/runqslower.bpf.c @@ -68,7 +68,7 @@ int handle__sched_switch(u64 *ctx) */ struct task_struct *prev = (struct task_struct *)ctx[1]; struct task_struct *next = (struct task_struct *)ctx[2]; - struct event event = {}; + struct runq_event event = {}; u64 *tsp, delta_us; long state; u32 pid; diff --git a/tools/bpf/runqslower/runqslower.c b/tools/bpf/runqslower/runqslower.c index 2414cc764461..d78f4148597f 100644 --- a/tools/bpf/runqslower/runqslower.c +++ b/tools/bpf/runqslower/runqslower.c @@ -100,7 +100,7 @@ static int bump_memlock_rlimit(void) void handle_event(void *ctx, int cpu, void *data, __u32 data_sz) { - const struct event *e = data; + const struct runq_event *e = data; struct tm *tm; char ts[32]; time_t t; diff --git a/tools/bpf/runqslower/runqslower.h b/tools/bpf/runqslower/runqslower.h index 9db225425e5f..4f70f07200c2 100644 --- a/tools/bpf/runqslower/runqslower.h +++ b/tools/bpf/runqslower/runqslower.h @@ -4,7 +4,7 @@ #define TASK_COMM_LEN 16 -struct event { +struct runq_event { char task[TASK_COMM_LEN]; __u64 delta_us; pid_t pid; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b0383d371b9a..16a7574292a5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1111,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1775,6 +1782,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1791,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2267,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2382,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2481,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3257,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. @@ -5018,6 +5038,44 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5206,6 +5264,11 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ + FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 9563d294f181..b46bcdb0cab1 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1133,6 +1133,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 +#define KVM_CAP_SYS_ATTRIBUTES 209 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h deleted file mode 100644 index 45fcbf99d72e..000000000000 --- a/tools/include/uapi/linux/lirc.h +++ /dev/null @@ -1,229 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * lirc.h - linux infrared remote control header file - * last modified 2010/07/13 by Jarod Wilson - */ - -#ifndef _LINUX_LIRC_H -#define _LINUX_LIRC_H - -#include <linux/types.h> -#include <linux/ioctl.h> - -#define PULSE_BIT 0x01000000 -#define PULSE_MASK 0x00FFFFFF - -#define LIRC_MODE2_SPACE 0x00000000 -#define LIRC_MODE2_PULSE 0x01000000 -#define LIRC_MODE2_FREQUENCY 0x02000000 -#define LIRC_MODE2_TIMEOUT 0x03000000 - -#define LIRC_VALUE_MASK 0x00FFFFFF -#define LIRC_MODE2_MASK 0xFF000000 - -#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) -#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) -#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) -#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) - -#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) -#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) - -#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE) -#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) -#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) -#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) - -/* used heavily by lirc userspace */ -#define lirc_t int - -/*** lirc compatible hardware features ***/ - -#define LIRC_MODE2SEND(x) (x) -#define LIRC_SEND2MODE(x) (x) -#define LIRC_MODE2REC(x) ((x) << 16) -#define LIRC_REC2MODE(x) ((x) >> 16) - -#define LIRC_MODE_RAW 0x00000001 -#define LIRC_MODE_PULSE 0x00000002 -#define LIRC_MODE_MODE2 0x00000004 -#define LIRC_MODE_SCANCODE 0x00000008 -#define LIRC_MODE_LIRCCODE 0x00000010 - - -#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) -#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) -#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) -#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_SEND_MASK 0x0000003f - -#define LIRC_CAN_SET_SEND_CARRIER 0x00000100 -#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200 -#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400 - -#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW) -#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE) -#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2) -#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE) -#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) - -#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) -#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) - -#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 -#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 -#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 -#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 -#define LIRC_CAN_SET_REC_FILTER 0x08000000 - -#define LIRC_CAN_MEASURE_CARRIER 0x02000000 -#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 - -#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) -#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) - -#define LIRC_CAN_NOTIFY_DECODE 0x01000000 - -/*** IOCTL commands for lirc driver ***/ - -#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) - -#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) -#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) -#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) - -#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) -#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) - -/* code length in bits, currently only for LIRC_MODE_LIRCCODE */ -#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) - -#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32) -#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32) -/* Note: these can reset the according pulse_width */ -#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) -#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) -#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) -#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) - -/* - * when a timeout != 0 is set the driver will send a - * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is - * never sent, timeout is disabled by default - */ -#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32) - -/* 1 enables, 0 disables timeout reports in MODE2 */ -#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) - -/* - * if enabled from the next key press on the driver will send - * LIRC_MODE2_FREQUENCY packets - */ -#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) - -/* - * to set a range use LIRC_SET_REC_CARRIER_RANGE with the - * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound - */ -#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) - -#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) - -/* - * Return the recording timeout, which is either set by - * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols. - */ -#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32) - -/* - * struct lirc_scancode - decoded scancode with protocol for use with - * LIRC_MODE_SCANCODE - * - * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR - * was decoded. - * @flags: should be 0 for transmit. When receiving scancodes, - * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set - * depending on the protocol - * @rc_proto: see enum rc_proto - * @keycode: the translated keycode. Set to 0 for transmit. - * @scancode: the scancode received or to be sent - */ -struct lirc_scancode { - __u64 timestamp; - __u16 flags; - __u16 rc_proto; - __u32 keycode; - __u64 scancode; -}; - -/* Set if the toggle bit of rc-5 or rc-6 is enabled */ -#define LIRC_SCANCODE_FLAG_TOGGLE 1 -/* Set if this is a nec or sanyo repeat */ -#define LIRC_SCANCODE_FLAG_REPEAT 2 - -/** - * enum rc_proto - the Remote Controller protocol - * - * @RC_PROTO_UNKNOWN: Protocol not known - * @RC_PROTO_OTHER: Protocol known but proprietary - * @RC_PROTO_RC5: Philips RC5 protocol - * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol - * @RC_PROTO_RC5_SZ: StreamZap variant of RC5 - * @RC_PROTO_JVC: JVC protocol - * @RC_PROTO_SONY12: Sony 12 bit protocol - * @RC_PROTO_SONY15: Sony 15 bit protocol - * @RC_PROTO_SONY20: Sony 20 bit protocol - * @RC_PROTO_NEC: NEC protocol - * @RC_PROTO_NECX: Extended NEC protocol - * @RC_PROTO_NEC32: NEC 32 bit protocol - * @RC_PROTO_SANYO: Sanyo protocol - * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard - * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse - * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol - * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol - * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol - * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol - * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol - * @RC_PROTO_SHARP: Sharp protocol - * @RC_PROTO_XMP: XMP protocol - * @RC_PROTO_CEC: CEC protocol - * @RC_PROTO_IMON: iMon Pad protocol - * @RC_PROTO_RCMM12: RC-MM protocol 12 bits - * @RC_PROTO_RCMM24: RC-MM protocol 24 bits - * @RC_PROTO_RCMM32: RC-MM protocol 32 bits - */ -enum rc_proto { - RC_PROTO_UNKNOWN = 0, - RC_PROTO_OTHER = 1, - RC_PROTO_RC5 = 2, - RC_PROTO_RC5X_20 = 3, - RC_PROTO_RC5_SZ = 4, - RC_PROTO_JVC = 5, - RC_PROTO_SONY12 = 6, - RC_PROTO_SONY15 = 7, - RC_PROTO_SONY20 = 8, - RC_PROTO_NEC = 9, - RC_PROTO_NECX = 10, - RC_PROTO_NEC32 = 11, - RC_PROTO_SANYO = 12, - RC_PROTO_MCIR2_KBD = 13, - RC_PROTO_MCIR2_MSE = 14, - RC_PROTO_RC6_0 = 15, - RC_PROTO_RC6_6A_20 = 16, - RC_PROTO_RC6_6A_24 = 17, - RC_PROTO_RC6_6A_32 = 18, - RC_PROTO_RC6_MCE = 19, - RC_PROTO_SHARP = 20, - RC_PROTO_XMP = 21, - RC_PROTO_CEC = 22, - RC_PROTO_IMON = 23, - RC_PROTO_RCMM12 = 24, - RC_PROTO_RCMM24 = 25, - RC_PROTO_RCMM32 = 26, -}; - -#endif diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 550b4cbb6c99..418b259166f8 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -754,10 +754,10 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, .flags = flags, ); - return bpf_prog_attach_xattr(prog_fd, target_fd, type, &opts); + return bpf_prog_attach_opts(prog_fd, target_fd, type, &opts); } -int bpf_prog_attach_xattr(int prog_fd, int target_fd, +int bpf_prog_attach_opts(int prog_fd, int target_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts) { @@ -778,6 +778,11 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, return libbpf_err_errno(ret); } +__attribute__((alias("bpf_prog_attach_opts"))) +int bpf_prog_attach_xattr(int prog_fd, int target_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); + int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 14e0d97ad2cf..c2e8327010f9 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -391,6 +391,10 @@ struct bpf_prog_attach_opts { LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_attach_opts(int prog_fd, int attachable_fd, + enum bpf_attach_type type, + const struct bpf_prog_attach_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_prog_attach_opts() instead") LIBBPF_API int bpf_prog_attach_xattr(int prog_fd, int attachable_fd, enum bpf_attach_type type, const struct bpf_prog_attach_opts *opts); diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 963b1060d944..44df982d2a5c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -133,7 +133,7 @@ struct bpf_map_def { unsigned int value_size; unsigned int max_entries; unsigned int map_flags; -}; +} __attribute__((deprecated("use BTF-defined maps in .maps section"))); enum libbpf_pin_type { LIBBPF_PIN_NONE, diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 9aa19c89f758..1383e26c5d1f 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1620,20 +1620,37 @@ static int btf_commit_type(struct btf *btf, int data_sz) struct btf_pipe { const struct btf *src; struct btf *dst; + struct hashmap *str_off_map; /* map string offsets from src to dst */ }; static int btf_rewrite_str(__u32 *str_off, void *ctx) { struct btf_pipe *p = ctx; - int off; + void *mapped_off; + int off, err; if (!*str_off) /* nothing to do for empty strings */ return 0; + if (p->str_off_map && + hashmap__find(p->str_off_map, (void *)(long)*str_off, &mapped_off)) { + *str_off = (__u32)(long)mapped_off; + return 0; + } + off = btf__add_str(p->dst, btf__str_by_offset(p->src, *str_off)); if (off < 0) return off; + /* Remember string mapping from src to dst. It avoids + * performing expensive string comparisons. + */ + if (p->str_off_map) { + err = hashmap__append(p->str_off_map, (void *)(long)*str_off, (void *)(long)off); + if (err) + return err; + } + *str_off = off; return 0; } @@ -1680,6 +1697,9 @@ static int btf_rewrite_type_ids(__u32 *type_id, void *ctx) return 0; } +static size_t btf_dedup_identity_hash_fn(const void *key, void *ctx); +static bool btf_dedup_equal_fn(const void *k1, const void *k2, void *ctx); + int btf__add_btf(struct btf *btf, const struct btf *src_btf) { struct btf_pipe p = { .src = src_btf, .dst = btf }; @@ -1713,6 +1733,11 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) if (!off) return libbpf_err(-ENOMEM); + /* Map the string offsets from src_btf to the offsets from btf to improve performance */ + p.str_off_map = hashmap__new(btf_dedup_identity_hash_fn, btf_dedup_equal_fn, NULL); + if (IS_ERR(p.str_off_map)) + return libbpf_err(-ENOMEM); + /* bulk copy types data for all types from src_btf */ memcpy(t, src_btf->types_data, data_sz); @@ -1754,6 +1779,8 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf) btf->hdr->str_off += data_sz; btf->nr_types += cnt; + hashmap__free(p.str_off_map); + /* return type ID of the first added BTF type */ return btf->start_id + btf->nr_types - cnt; err_out: @@ -1767,6 +1794,8 @@ err_out: * wasn't modified, so doesn't need restoring, see big comment above */ btf->hdr->str_len = old_strs_len; + hashmap__free(p.str_off_map); + return libbpf_err(err); } diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 061839f04525..51862fdee850 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -375,8 +375,28 @@ btf_dump__dump_type_data(struct btf_dump *d, __u32 id, const struct btf_dump_type_data_opts *opts); /* - * A set of helpers for easier BTF types handling + * A set of helpers for easier BTF types handling. + * + * The inline functions below rely on constants from the kernel headers which + * may not be available for applications including this header file. To avoid + * compilation errors, we define all the constants here that were added after + * the initial introduction of the BTF_KIND* constants. */ +#ifndef BTF_KIND_FUNC +#define BTF_KIND_FUNC 12 /* Function */ +#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ +#endif +#ifndef BTF_KIND_VAR +#define BTF_KIND_VAR 14 /* Variable */ +#define BTF_KIND_DATASEC 15 /* Section */ +#endif +#ifndef BTF_KIND_FLOAT +#define BTF_KIND_FLOAT 16 /* Floating point */ +#endif +/* The kernel header switched to enums, so these two were never #defined */ +#define BTF_KIND_DECL_TAG 17 /* Decl Tag */ +#define BTF_KIND_TYPE_TAG 18 /* Type Tag */ + static inline __u16 btf_kind(const struct btf_type *t) { return BTF_INFO_KIND(t->info); diff --git a/tools/lib/bpf/hashmap.c b/tools/lib/bpf/hashmap.c index 3c20b126d60d..aeb09c288716 100644 --- a/tools/lib/bpf/hashmap.c +++ b/tools/lib/bpf/hashmap.c @@ -75,7 +75,7 @@ void hashmap__clear(struct hashmap *map) void hashmap__free(struct hashmap *map) { - if (!map) + if (IS_ERR_OR_NULL(map)) return; hashmap__clear(map); @@ -238,4 +238,3 @@ bool hashmap__delete(struct hashmap *map, const void *key, return true; } - diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7f10dd501a52..a8c750373ad5 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -235,6 +235,8 @@ enum sec_def_flags { SEC_SLEEPABLE = 8, /* allow non-strict prefix matching */ SEC_SLOPPY_PFX = 16, + /* BPF program support non-linear XDP buffer */ + SEC_XDP_FRAGS = 32, }; struct bpf_sec_def { @@ -1937,6 +1939,11 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (obj->efile.maps_shndx < 0) return 0; + if (libbpf_mode & LIBBPF_STRICT_MAP_DEFINITIONS) { + pr_warn("legacy map definitions in SEC(\"maps\") are not supported\n"); + return -EOPNOTSUPP; + } + if (!symbols) return -EINVAL; @@ -1999,6 +2006,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + pr_warn("map '%s' (legacy): legacy map definitions are deprecated, use BTF-defined maps instead\n", map_name); + if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) { pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); return -ENOTSUP; @@ -4190,6 +4199,7 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map) return 0; if (!bpf_map__is_internal(map)) { + pr_warn("Use of BPF_ANNOTATE_KV_PAIR is deprecated, use BTF-defined maps in .maps section instead\n"); ret = btf__get_map_kv_tids(obj->btf, map->name, def->key_size, def->value_size, &key_type_id, &value_type_id); @@ -6562,6 +6572,9 @@ static int libbpf_preload_prog(struct bpf_program *prog, if (def & SEC_SLEEPABLE) opts->prog_flags |= BPF_F_SLEEPABLE; + if (prog->type == BPF_PROG_TYPE_XDP && (def & SEC_XDP_FRAGS)) + opts->prog_flags |= BPF_F_XDP_HAS_FRAGS; + if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { @@ -8600,8 +8613,11 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("lsm.s/", LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm), SEC_DEF("iter/", TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter), SEC_DEF("syscall", SYSCALL, 0, SEC_SLEEPABLE), + SEC_DEF("xdp.frags/devmap", XDP, BPF_XDP_DEVMAP, SEC_XDP_FRAGS), SEC_DEF("xdp_devmap/", XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags/cpumap", XDP, BPF_XDP_CPUMAP, SEC_XDP_FRAGS), SEC_DEF("xdp_cpumap/", XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE), + SEC_DEF("xdp.frags", XDP, BPF_XDP, SEC_XDP_FRAGS), SEC_DEF("xdp", XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), SEC_DEF("perf_event", PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX), SEC_DEF("lwt_in", LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX), @@ -11795,6 +11811,9 @@ void bpf_object__detach_skeleton(struct bpf_object_skeleton *s) void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s) { + if (!s) + return; + if (s->progs) bpf_object__detach_skeleton(s); if (s->obj) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8b9bc5e90c2b..94670066de62 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -706,7 +706,8 @@ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map); LIBBPF_API int bpf_map__fd(const struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); /* get map definition */ -LIBBPF_API const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); +LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 8, "use appropriate getters or setters instead") +const struct bpf_map_def *bpf_map__def(const struct bpf_map *map); /* get map name */ LIBBPF_API const char *bpf_map__name(const struct bpf_map *map); /* get/set map type */ @@ -832,13 +833,42 @@ struct bpf_xdp_set_link_opts { }; #define bpf_xdp_set_link_opts__last_field old_fd +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_attach() instead") LIBBPF_API int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query_id() instead") LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_xdp_query() instead") LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +struct bpf_xdp_attach_opts { + size_t sz; + int old_prog_fd; + size_t :0; +}; +#define bpf_xdp_attach_opts__last_field old_prog_fd + +struct bpf_xdp_query_opts { + size_t sz; + __u32 prog_id; /* output */ + __u32 drv_prog_id; /* output */ + __u32 hw_prog_id; /* output */ + __u32 skb_prog_id; /* output */ + __u8 attach_mode; /* output */ + size_t :0; +}; +#define bpf_xdp_query_opts__last_field attach_mode + +LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_detach(int ifindex, __u32 flags, + const struct bpf_xdp_attach_opts *opts); +LIBBPF_API int bpf_xdp_query(int ifindex, int flags, struct bpf_xdp_query_opts *opts); +LIBBPF_API int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id); + /* TC related API */ enum bpf_tc_attach_point { BPF_TC_INGRESS = 1 << 0, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 529783967793..e10f0822845a 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -247,6 +247,7 @@ LIBBPF_0.0.8 { bpf_link_create; bpf_link_update; bpf_map__set_initial_value; + bpf_prog_attach_opts; bpf_program__attach_cgroup; bpf_program__attach_lsm; bpf_program__is_lsm; @@ -427,6 +428,10 @@ LIBBPF_0.7.0 { bpf_program__log_level; bpf_program__set_log_buf; bpf_program__set_log_level; + bpf_xdp_attach; + bpf_xdp_detach; + bpf_xdp_query; + bpf_xdp_query_id; libbpf_probe_bpf_helper; libbpf_probe_bpf_map_type; libbpf_probe_bpf_prog_type; diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h index 79131f761a27..3c2b281c2bc3 100644 --- a/tools/lib/bpf/libbpf_legacy.h +++ b/tools/lib/bpf/libbpf_legacy.h @@ -73,6 +73,11 @@ enum libbpf_strict_mode { * operation. */ LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK = 0x10, + /* + * Error out on any SEC("maps") map definition, which are deprecated + * in favor of BTF-defined map definitions in SEC(".maps"). + */ + LIBBPF_STRICT_MAP_DEFINITIONS = 0x20, __LIBBPF_STRICT_LAST, }; diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 39f25e09b51e..c39c37f99d5c 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -217,6 +217,28 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); } +int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + int old_prog_fd, err; + + if (!OPTS_VALID(opts, bpf_xdp_attach_opts)) + return libbpf_err(-EINVAL); + + old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); + if (old_prog_fd) + flags |= XDP_FLAGS_REPLACE; + else + old_prog_fd = -1; + + err = __bpf_set_link_xdp_fd_replace(ifindex, prog_fd, old_prog_fd, flags); + return libbpf_err(err); +} + +int bpf_xdp_detach(int ifindex, __u32 flags, const struct bpf_xdp_attach_opts *opts) +{ + return bpf_xdp_attach(ifindex, -1, flags, opts); +} + int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts) { @@ -303,69 +325,98 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, - size_t info_size, __u32 flags) +int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { - struct xdp_id_md xdp_id = {}; - __u32 mask; - int ret; struct libbpf_nla_req req = { .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), .nh.nlmsg_type = RTM_GETLINK, .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, .ifinfo.ifi_family = AF_PACKET, }; + struct xdp_id_md xdp_id = {}; + int err; - if (flags & ~XDP_FLAGS_MASK || !info_size) + if (!OPTS_VALID(opts, bpf_xdp_query_opts)) + return libbpf_err(-EINVAL); + + if (xdp_flags & ~XDP_FLAGS_MASK) return libbpf_err(-EINVAL); /* Check whether the single {HW,DRV,SKB} mode is set */ - flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); - mask = flags - 1; - if (flags && flags & mask) + xdp_flags &= XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE; + if (xdp_flags & (xdp_flags - 1)) return libbpf_err(-EINVAL); xdp_id.ifindex = ifindex; - xdp_id.flags = flags; + xdp_id.flags = xdp_flags; - ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, get_xdp_info, &xdp_id); - if (!ret) { - size_t sz = min(info_size, sizeof(xdp_id.info)); + if (err) + return libbpf_err(err); - memcpy(info, &xdp_id.info, sz); - memset((void *) info + sz, 0, info_size - sz); - } + OPTS_SET(opts, prog_id, xdp_id.info.prog_id); + OPTS_SET(opts, drv_prog_id, xdp_id.info.drv_prog_id); + OPTS_SET(opts, hw_prog_id, xdp_id.info.hw_prog_id); + OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); + OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); - return libbpf_err(ret); + return 0; } -static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) +int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, + size_t info_size, __u32 flags) { - flags &= XDP_FLAGS_MODES; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + size_t sz; + int err; + + if (!info_size) + return libbpf_err(-EINVAL); - if (info->attach_mode != XDP_ATTACHED_MULTI && !flags) - return info->prog_id; - if (flags & XDP_FLAGS_DRV_MODE) - return info->drv_prog_id; - if (flags & XDP_FLAGS_HW_MODE) - return info->hw_prog_id; - if (flags & XDP_FLAGS_SKB_MODE) - return info->skb_prog_id; + err = bpf_xdp_query(ifindex, flags, &opts); + if (err) + return libbpf_err(err); + + /* struct xdp_link_info field layout matches struct bpf_xdp_query_opts + * layout after sz field + */ + sz = min(info_size, offsetofend(struct xdp_link_info, attach_mode)); + memcpy(info, &opts.prog_id, sz); + memset((void *)info + sz, 0, info_size - sz); return 0; } -int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +int bpf_xdp_query_id(int ifindex, int flags, __u32 *prog_id) { - struct xdp_link_info info; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); int ret; - ret = bpf_get_link_xdp_info(ifindex, &info, sizeof(info), flags); - if (!ret) - *prog_id = get_xdp_id(&info, flags); + ret = bpf_xdp_query(ifindex, flags, &opts); + if (ret) + return libbpf_err(ret); + + flags &= XDP_FLAGS_MODES; - return libbpf_err(ret); + if (opts.attach_mode != XDP_ATTACHED_MULTI && !flags) + *prog_id = opts.prog_id; + else if (flags & XDP_FLAGS_DRV_MODE) + *prog_id = opts.drv_prog_id; + else if (flags & XDP_FLAGS_HW_MODE) + *prog_id = opts.hw_prog_id; + else if (flags & XDP_FLAGS_SKB_MODE) + *prog_id = opts.skb_prog_id; + else + *prog_id = 0; + + return 0; +} + + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + return bpf_xdp_query_id(ifindex, flags, prog_id); } typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 7ecfaac7536a..ef2832b4d5cc 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -1005,24 +1005,22 @@ __bpf_map__config_value(struct bpf_map *map, { struct bpf_map_op *op; const char *map_name = bpf_map__name(map); - const struct bpf_map_def *def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } - if (def->type != BPF_MAP_TYPE_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; } - if (def->key_size < sizeof(unsigned int)) { + if (bpf_map__key_size(map) < sizeof(unsigned int)) { pr_debug("Map %s has incorrect key size\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE; } - switch (def->value_size) { + switch (bpf_map__value_size(map)) { case 1: case 2: case 4: @@ -1064,7 +1062,6 @@ __bpf_map__config_event(struct bpf_map *map, struct parse_events_term *term, struct evlist *evlist) { - const struct bpf_map_def *def; struct bpf_map_op *op; const char *map_name = bpf_map__name(map); struct evsel *evsel = evlist__find_evsel_by_str(evlist, term->val.str); @@ -1075,18 +1072,16 @@ __bpf_map__config_event(struct bpf_map *map, return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("Unable to get map definition from '%s'\n", - map_name); - return PTR_ERR(def); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); + return PTR_ERR(map); } /* * No need to check key_size and value_size: * kernel has already checked them. */ - if (def->type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + if (bpf_map__type(map) != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n", map_name); return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE; @@ -1135,7 +1130,6 @@ config_map_indices_range_check(struct parse_events_term *term, const char *map_name) { struct parse_events_array *array = &term->array; - const struct bpf_map_def *def; unsigned int i; if (!array->nr_ranges) @@ -1146,10 +1140,8 @@ config_map_indices_range_check(struct parse_events_term *term, return -BPF_LOADER_ERRNO__INTERNAL; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: Unable to get map definition from '%s'\n", - map_name); + if (!map) { + pr_debug("Map '%s' is invalid\n", map_name); return -BPF_LOADER_ERRNO__INTERNAL; } @@ -1158,7 +1150,7 @@ config_map_indices_range_check(struct parse_events_term *term, size_t length = array->ranges[i].length; unsigned int idx = start + length - 1; - if (idx >= def->max_entries) { + if (idx >= bpf_map__max_entries(map)) { pr_debug("ERROR: index %d too large\n", idx); return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG; } @@ -1251,21 +1243,21 @@ out: } typedef int (*map_config_func_t)(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg); static int foreach_key_array_all(map_config_func_t func, void *arg, const char *name, - int map_fd, const struct bpf_map_def *pdef, + int map_fd, const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i; int err; - for (i = 0; i < pdef->max_entries; i++) { - err = func(name, map_fd, pdef, op, &i, arg); + for (i = 0; i < bpf_map__max_entries(map); i++) { + err = func(name, map_fd, map, op, &i, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, i); @@ -1278,7 +1270,7 @@ foreach_key_array_all(map_config_func_t func, static int foreach_key_array_ranges(map_config_func_t func, void *arg, const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op) { unsigned int i, j; @@ -1291,7 +1283,7 @@ foreach_key_array_ranges(map_config_func_t func, void *arg, for (j = 0; j < length; j++) { unsigned int idx = start + j; - err = func(name, map_fd, pdef, op, &idx, arg); + err = func(name, map_fd, map, op, &idx, arg); if (err) { pr_debug("ERROR: failed to insert value to %s[%u]\n", name, idx); @@ -1307,9 +1299,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, map_config_func_t func, void *arg) { - int err, map_fd; + int err, map_fd, type; struct bpf_map_op *op; - const struct bpf_map_def *def; const char *name = bpf_map__name(map); struct bpf_map_priv *priv = bpf_map__priv(map); @@ -1322,9 +1313,8 @@ bpf_map_config_foreach_key(struct bpf_map *map, return 0; } - def = bpf_map__def(map); - if (IS_ERR(def)) { - pr_debug("ERROR: failed to get definition from map %s\n", name); + if (!map) { + pr_debug("Map '%s' is invalid\n", name); return -BPF_LOADER_ERRNO__INTERNAL; } map_fd = bpf_map__fd(map); @@ -1333,19 +1323,19 @@ bpf_map_config_foreach_key(struct bpf_map *map, return map_fd; } + type = bpf_map__type(map); list_for_each_entry(op, &priv->ops_list, list) { - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: switch (op->key_type) { case BPF_MAP_KEY_ALL: err = foreach_key_array_all(func, arg, name, - map_fd, def, op); + map_fd, map, op); break; case BPF_MAP_KEY_RANGES: err = foreach_key_array_ranges(func, arg, name, - map_fd, def, - op); + map_fd, map, op); break; default: pr_debug("ERROR: keytype for map '%s' invalid\n", @@ -1454,7 +1444,7 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey, static int apply_obj_config_map_for_key(const char *name, int map_fd, - const struct bpf_map_def *pdef, + const struct bpf_map *map, struct bpf_map_op *op, void *pkey, void *arg __maybe_unused) { @@ -1463,7 +1453,7 @@ apply_obj_config_map_for_key(const char *name, int map_fd, switch (op->op_type) { case BPF_MAP_OP_SET_VALUE: err = apply_config_value_for_key(map_fd, pkey, - pdef->value_size, + bpf_map__value_size(map), op->v.value); break; case BPF_MAP_OP_SET_EVSEL: diff --git a/tools/perf/util/bpf_map.c b/tools/perf/util/bpf_map.c index eb853ca67cf4..c863ae0c5cb5 100644 --- a/tools/perf/util/bpf_map.c +++ b/tools/perf/util/bpf_map.c @@ -9,25 +9,25 @@ #include <stdlib.h> #include <unistd.h> -static bool bpf_map_def__is_per_cpu(const struct bpf_map_def *def) +static bool bpf_map__is_per_cpu(enum bpf_map_type type) { - return def->type == BPF_MAP_TYPE_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_ARRAY || - def->type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - def->type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; + return type == BPF_MAP_TYPE_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_ARRAY || + type == BPF_MAP_TYPE_LRU_PERCPU_HASH || + type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE; } -static void *bpf_map_def__alloc_value(const struct bpf_map_def *def) +static void *bpf_map__alloc_value(const struct bpf_map *map) { - if (bpf_map_def__is_per_cpu(def)) - return malloc(round_up(def->value_size, 8) * sysconf(_SC_NPROCESSORS_CONF)); + if (bpf_map__is_per_cpu(bpf_map__type(map))) + return malloc(round_up(bpf_map__value_size(map), 8) * + sysconf(_SC_NPROCESSORS_CONF)); - return malloc(def->value_size); + return malloc(bpf_map__value_size(map)); } int bpf_map__fprintf(struct bpf_map *map, FILE *fp) { - const struct bpf_map_def *def = bpf_map__def(map); void *prev_key = NULL, *key, *value; int fd = bpf_map__fd(map), err; int printed = 0; @@ -35,15 +35,15 @@ int bpf_map__fprintf(struct bpf_map *map, FILE *fp) if (fd < 0) return fd; - if (IS_ERR(def)) - return PTR_ERR(def); + if (!map) + return PTR_ERR(map); err = -ENOMEM; - key = malloc(def->key_size); + key = malloc(bpf_map__key_size(map)); if (key == NULL) goto out; - value = bpf_map_def__alloc_value(def); + value = bpf_map__alloc_value(map); if (value == NULL) goto out_free_key; diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index b0be5f40a3f1..79d102304470 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -90,7 +90,7 @@ EXTRA_WARNINGS += -Wstrict-aliasing=3 else ifneq ($(CROSS_COMPILE),) CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc)) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null)) ifneq ($(GCC_TOOLCHAIN_DIR),) CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 44bbe54f25f1..3c4196cef3ed 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,6 +6,7 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> +import importlib.abc import importlib.util import logging import subprocess diff --git a/tools/testing/scatterlist/linux/mm.h b/tools/testing/scatterlist/linux/mm.h index 16ec895bbe5f..5bd9e6e80625 100644 --- a/tools/testing/scatterlist/linux/mm.h +++ b/tools/testing/scatterlist/linux/mm.h @@ -74,7 +74,7 @@ static inline unsigned long page_to_phys(struct page *page) __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) -#define preemptible() (1) +#define pagefault_disabled() (0) static inline void *kmap(struct page *page) { @@ -127,6 +127,7 @@ kmalloc_array(unsigned int n, unsigned int size, unsigned int flags) #define kmemleak_free(a) #define PageSlab(p) (0) +#define flush_dcache_page(p) #define MAX_ERRNO 4095 diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index af798b9d232c..a3c1e67441f9 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -261,7 +261,7 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type) } ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD, - "Set FPSIMD registers via %s\n", type->name); + "Got FPSIMD registers via %s\n", type->name); if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD) goto out; @@ -557,7 +557,14 @@ static int do_parent(pid_t child) } /* prctl() flags */ - ptrace_set_get_inherit(child, &vec_types[i]); + if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) { + ptrace_set_get_inherit(child, &vec_types[i]); + } else { + ksft_test_result_skip("%s SVE_PT_VL_INHERIT set\n", + vec_types[i].name); + ksft_test_result_skip("%s SVE_PT_VL_INHERIT cleared\n", + vec_types[i].name); + } /* Step through every possible VQ */ for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 42ffc24e9e71..945f92d71db3 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -21,7 +21,7 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= -CFLAGS += -g -O0 -rdynamic -Wall $(GENFLAGS) $(SAN_CFLAGS) \ +CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) LDFLAGS += $(SAN_CFLAGS) @@ -292,7 +292,7 @@ IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG)) -BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ +BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index df3b292a8ffe..bdbacf5adcd2 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -109,26 +109,31 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; -BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_SET_START(bpf_testmod_check_kfunc_ids) BTF_ID(func, bpf_testmod_test_mod_kfunc) -BTF_SET_END(bpf_testmod_kfunc_ids) +BTF_SET_END(bpf_testmod_check_kfunc_ids) -static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); +static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = { + .owner = THIS_MODULE, + .check_set = &bpf_testmod_check_kfunc_ids, +}; + +extern int bpf_fentry_test1(int a); static int bpf_testmod_init(void) { int ret; - ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); - if (ret) + ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set); + if (ret < 0) return ret; - register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); - return 0; + if (bpf_fentry_test1(0) < 0) + return -EINVAL; + return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } static void bpf_testmod_exit(void) { - unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f6287132fa89..763db63a3890 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -48,3 +48,8 @@ CONFIG_IMA_READ_POLICY=y CONFIG_BLK_DEV_LOOP=y CONFIG_FUNCTION_TRACER=y CONFIG_DYNAMIC_FTRACE=y +CONFIG_NETFILTER=y +CONFIG_NF_DEFRAG_IPV4=y +CONFIG_NF_DEFRAG_IPV6=y +CONFIG_NF_CONNTRACK=y +CONFIG_USERFAULTFD=y diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c index d0f06e40c16d..eac71fbb24ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c +++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c @@ -1,13 +1,24 @@ // SPDX-License-Identifier: GPL-2.0 -#include <test_progs.h> -#include "bind_perm.skel.h" - +#define _GNU_SOURCE +#include <sched.h> +#include <stdlib.h> #include <sys/types.h> #include <sys/socket.h> #include <sys/capability.h> +#include "test_progs.h" +#include "bind_perm.skel.h" + static int duration; +static int create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return -1; + + return 0; +} + void try_bind(int family, int port, int expected_errno) { struct sockaddr_storage addr = {}; @@ -75,6 +86,9 @@ void test_bind_perm(void) struct bind_perm *skel; int cgroup_fd; + if (create_netns()) + return; + cgroup_fd = test__join_cgroup("/bind_perm"); if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno)) return; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..ee725d4d98a5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt_unix.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include <sys/socket.h> +#include <sys/un.h> +#include <test_progs.h> +#include "bpf_iter_setsockopt_unix.skel.h" + +#define NR_CASES 5 + +static int create_unix_socket(struct bpf_iter_setsockopt_unix *skel) +{ + struct sockaddr_un addr = { + .sun_family = AF_UNIX, + .sun_path = "", + }; + socklen_t len; + int fd, err; + + fd = socket(AF_UNIX, SOCK_STREAM, 0); + if (!ASSERT_NEQ(fd, -1, "socket")) + return -1; + + len = offsetof(struct sockaddr_un, sun_path); + err = bind(fd, (struct sockaddr *)&addr, len); + if (!ASSERT_OK(err, "bind")) + return -1; + + len = sizeof(addr); + err = getsockname(fd, (struct sockaddr *)&addr, &len); + if (!ASSERT_OK(err, "getsockname")) + return -1; + + memcpy(&skel->bss->sun_path, &addr.sun_path, + len - offsetof(struct sockaddr_un, sun_path)); + + return fd; +} + +static void test_sndbuf(struct bpf_iter_setsockopt_unix *skel, int fd) +{ + socklen_t optlen; + int i, err; + + for (i = 0; i < NR_CASES; i++) { + if (!ASSERT_NEQ(skel->data->sndbuf_getsockopt[i], -1, + "bpf_(get|set)sockopt")) + return; + + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->data->sndbuf_setsockopt[i]), + sizeof(skel->data->sndbuf_setsockopt[i])); + if (!ASSERT_OK(err, "setsockopt")) + return; + + optlen = sizeof(skel->bss->sndbuf_getsockopt_expected[i]); + err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, + &(skel->bss->sndbuf_getsockopt_expected[i]), + &optlen); + if (!ASSERT_OK(err, "getsockopt")) + return; + + if (!ASSERT_EQ(skel->data->sndbuf_getsockopt[i], + skel->bss->sndbuf_getsockopt_expected[i], + "bpf_(get|set)sockopt")) + return; + } +} + +void test_bpf_iter_setsockopt_unix(void) +{ + struct bpf_iter_setsockopt_unix *skel; + int err, unix_fd, iter_fd; + char buf; + + skel = bpf_iter_setsockopt_unix__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + unix_fd = create_unix_socket(skel); + if (!ASSERT_NEQ(unix_fd, -1, "create_unix_server")) + goto destroy; + + skel->links.change_sndbuf = bpf_program__attach_iter(skel->progs.change_sndbuf, NULL); + if (!ASSERT_OK_PTR(skel->links.change_sndbuf, "bpf_program__attach_iter")) + goto destroy; + + iter_fd = bpf_iter_create(bpf_link__fd(skel->links.change_sndbuf)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto destroy; + + while ((err = read(iter_fd, &buf, sizeof(buf))) == -1 && + errno == EAGAIN) + ; + if (!ASSERT_OK(err, "read iter error")) + goto destroy; + + test_sndbuf(skel, unix_fd); +destroy: + bpf_iter_setsockopt_unix__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c new file mode 100644 index 000000000000..d43f548c572c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <unistd.h> +#include <pthread.h> +#include <sys/mman.h> +#include <stdatomic.h> +#include <test_progs.h> +#include <sys/syscall.h> +#include <linux/module.h> +#include <linux/userfaultfd.h> + +#include "ksym_race.skel.h" +#include "bpf_mod_race.skel.h" +#include "kfunc_call_race.skel.h" + +/* This test crafts a race between btf_try_get_module and do_init_module, and + * checks whether btf_try_get_module handles the invocation for a well-formed + * but uninitialized module correctly. Unless the module has completed its + * initcalls, the verifier should fail the program load and return ENXIO. + * + * userfaultfd is used to trigger a fault in an fmod_ret program, and make it + * sleep, then the BPF program is loaded and the return value from verifier is + * inspected. After this, the userfaultfd is closed so that the module loading + * thread makes forward progress, and fmod_ret injects an error so that the + * module load fails and it is freed. + * + * If the verifier succeeded in loading the supplied program, it will end up + * taking reference to freed module, and trigger a crash when the program fd + * is closed later. This is true for both kfuncs and ksyms. In both cases, + * the crash is triggered inside bpf_prog_free_deferred, when module reference + * is finally released. + */ + +struct test_config { + const char *str_open; + void *(*bpf_open_and_load)(); + void (*bpf_destroy)(void *); +}; + +enum test_state { + _TS_INVALID, + TS_MODULE_LOAD, + TS_MODULE_LOAD_FAIL, +}; + +static _Atomic enum test_state state = _TS_INVALID; + +static int sys_finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int sys_delete_module(const char *name, unsigned int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +static int load_module(const char *mod) +{ + int ret, fd; + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) + return fd; + + ret = sys_finit_module(fd, "", 0); + close(fd); + if (ret < 0) + return ret; + return 0; +} + +static void *load_module_thread(void *p) +{ + + if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail")) + atomic_store(&state, TS_MODULE_LOAD); + else + atomic_store(&state, TS_MODULE_LOAD_FAIL); + return p; +} + +static int sys_userfaultfd(int flags) +{ + return syscall(__NR_userfaultfd, flags); +} + +static int test_setup_uffd(void *fault_addr) +{ + struct uffdio_register uffd_register = {}; + struct uffdio_api uffd_api = {}; + int uffd; + + uffd = sys_userfaultfd(O_CLOEXEC); + if (uffd < 0) + return -errno; + + uffd_api.api = UFFD_API; + uffd_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffd_api)) { + close(uffd); + return -1; + } + + uffd_register.range.start = (unsigned long)fault_addr; + uffd_register.range.len = 4096; + uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) { + close(uffd); + return -1; + } + return uffd; +} + +static void test_bpf_mod_race_config(const struct test_config *config) +{ + void *fault_addr, *skel_fail; + struct bpf_mod_race *skel; + struct uffd_msg uffd_msg; + pthread_t load_mod_thrd; + _Atomic int *blockingp; + int uffd, ret; + + fault_addr = mmap(0, 4096, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration")) + return; + + if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod")) + goto end_mmap; + + skel = bpf_mod_race__open(); + if (!ASSERT_OK_PTR(skel, "bpf_mod_kfunc_race__open")) + goto end_module; + + skel->rodata->bpf_mod_race_config.tgid = getpid(); + skel->rodata->bpf_mod_race_config.inject_error = -4242; + skel->rodata->bpf_mod_race_config.fault_addr = fault_addr; + if (!ASSERT_OK(bpf_mod_race__load(skel), "bpf_mod___load")) + goto end_destroy; + blockingp = (_Atomic int *)&skel->bss->bpf_blocking; + + if (!ASSERT_OK(bpf_mod_race__attach(skel), "bpf_mod_kfunc_race__attach")) + goto end_destroy; + + uffd = test_setup_uffd(fault_addr); + if (!ASSERT_GE(uffd, 0, "userfaultfd open + register address")) + goto end_destroy; + + if (!ASSERT_OK(pthread_create(&load_mod_thrd, NULL, load_module_thread, NULL), + "load module thread")) + goto end_uffd; + + /* Now, we either fail loading module, or block in bpf prog, spin to find out */ + while (!atomic_load(&state) && !atomic_load(blockingp)) + ; + if (!ASSERT_EQ(state, _TS_INVALID, "module load should block")) + goto end_join; + if (!ASSERT_EQ(*blockingp, 1, "module load blocked")) { + pthread_kill(load_mod_thrd, SIGKILL); + goto end_uffd; + } + + /* We might have set bpf_blocking to 1, but may have not blocked in + * bpf_copy_from_user. Read userfaultfd descriptor to verify that. + */ + if (!ASSERT_EQ(read(uffd, &uffd_msg, sizeof(uffd_msg)), sizeof(uffd_msg), + "read uffd block event")) + goto end_join; + if (!ASSERT_EQ(uffd_msg.event, UFFD_EVENT_PAGEFAULT, "read uffd event is pagefault")) + goto end_join; + + /* We know that load_mod_thrd is blocked in the fmod_ret program, the + * module state is still MODULE_STATE_COMING because mod->init hasn't + * returned. This is the time we try to load a program calling kfunc and + * check if we get ENXIO from verifier. + */ + skel_fail = config->bpf_open_and_load(); + ret = errno; + if (!ASSERT_EQ(skel_fail, NULL, config->str_open)) { + /* Close uffd to unblock load_mod_thrd */ + close(uffd); + uffd = -1; + while (atomic_load(blockingp) != 2) + ; + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); + config->bpf_destroy(skel_fail); + goto end_join; + + } + ASSERT_EQ(ret, ENXIO, "verifier returns ENXIO"); + ASSERT_EQ(skel->data->res_try_get_module, false, "btf_try_get_module == false"); + + close(uffd); + uffd = -1; +end_join: + pthread_join(load_mod_thrd, NULL); + if (uffd < 0) + ASSERT_EQ(atomic_load(&state), TS_MODULE_LOAD_FAIL, "load_mod_thrd success"); +end_uffd: + if (uffd >= 0) + close(uffd); +end_destroy: + bpf_mod_race__destroy(skel); + ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu"); +end_module: + sys_delete_module("bpf_testmod", 0); + ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod"); +end_mmap: + munmap(fault_addr, 4096); + atomic_store(&state, _TS_INVALID); +} + +static const struct test_config ksym_config = { + .str_open = "ksym_race__open_and_load", + .bpf_open_and_load = (void *)ksym_race__open_and_load, + .bpf_destroy = (void *)ksym_race__destroy, +}; + +static const struct test_config kfunc_config = { + .str_open = "kfunc_call_race__open_and_load", + .bpf_open_and_load = (void *)kfunc_call_race__open_and_load, + .bpf_destroy = (void *)kfunc_call_race__destroy, +}; + +void serial_test_bpf_mod_race(void) +{ + if (test__start_subtest("ksym (used_btfs UAF)")) + test_bpf_mod_race_config(&ksym_config); + if (test__start_subtest("kfunc (kfunc_btf_tab UAF)")) + test_bpf_mod_race_config(&kfunc_config); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c new file mode 100644 index 000000000000..e3166a81e989 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> +#include "test_bpf_nf.skel.h" + +enum { + TEST_XDP, + TEST_TC_BPF, +}; + +void test_bpf_nf_ct(int mode) +{ + struct test_bpf_nf *skel; + int prog_fd, err, retval; + + skel = test_bpf_nf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load")) + return; + + if (mode == TEST_XDP) + prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test); + else + prog_fd = bpf_program__fd(skel->progs.nf_skb_ct_test); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, + (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto end; + + ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple"); + ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0"); + ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1"); + ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ"); + ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP"); + ASSERT_EQ(skel->bss->test_enonet_netns_id, -ENONET, "Test ENONET for bad but valid netns_id"); + ASSERT_EQ(skel->bss->test_enoent_lookup, -ENOENT, "Test ENOENT for failed lookup"); + ASSERT_EQ(skel->bss->test_eafnosupport, -EAFNOSUPPORT, "Test EAFNOSUPPORT for invalid len__tuple"); +end: + test_bpf_nf__destroy(skel); +} + +void test_bpf_nf(void) +{ + if (test__start_subtest("xdp-ct")) + test_bpf_nf_ct(TEST_XDP); + if (test__start_subtest("tc-bpf-ct")) + test_bpf_nf_ct(TEST_TC_BPF); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8ba53acf9eb4..14f9b6136794 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4560,6 +4560,8 @@ static void do_test_file(unsigned int test_num) has_btf_ext = btf_ext != NULL; btf_ext__free(btf_ext); + /* temporary disable LIBBPF_STRICT_MAP_DEFINITIONS to test legacy maps */ + libbpf_set_strict_mode((__LIBBPF_STRICT_LAST - 1) & ~LIBBPF_STRICT_MAP_DEFINITIONS); obj = bpf_object__open(test->file); err = libbpf_get_error(obj); if (CHECK(err, "obj: %d", err)) @@ -4684,6 +4686,8 @@ skip: fprintf(stderr, "OK"); done: + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + btf__free(btf); free(func_info); bpf_object__close(obj); diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index d3e8f729c623..38b3c47293da 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -194,14 +194,14 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE; attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_override", "unexpected success\n")) goto err; CHECK_FAIL(errno != EINVAL); attach_opts.flags = BPF_F_REPLACE; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_multi", "unexpected success\n")) goto err; @@ -209,7 +209,7 @@ void serial_test_cgroup_attach_multi(void) attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE; attach_opts.replace_prog_fd = -1; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_bad_fd", "unexpected success\n")) goto err; @@ -217,7 +217,7 @@ void serial_test_cgroup_attach_multi(void) /* replacing a program that is not attached to cgroup should fail */ attach_opts.replace_prog_fd = allow_prog[3]; - if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(!bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "fail_prog_replace_no_ent", "unexpected success\n")) goto err; @@ -225,14 +225,14 @@ void serial_test_cgroup_attach_multi(void) /* replace 1st from the top program */ attach_opts.replace_prog_fd = allow_prog[0]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; /* replace program with itself */ attach_opts.replace_prog_fd = allow_prog[6]; - if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1, + if (CHECK(bpf_prog_attach_opts(allow_prog[6], cg1, BPF_CGROUP_INET_EGRESS, &attach_opts), "prog_replace", "errno=%d\n", errno)) goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c new file mode 100644 index 000000000000..0b47c3c000c7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <test_progs.h> +#include <cgroup_helpers.h> +#include <network_helpers.h> + +#include "cgroup_getset_retval_setsockopt.skel.h" +#include "cgroup_getset_retval_getsockopt.skel.h" + +#define SOL_CUSTOM 0xdeadbeef + +static int zero; + +static void test_setsockopt_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, assert that + * we actually get that error when we run setsockopt() + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, and one that gets the + * previously set errno. Assert that we get the same errno back. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno. + * Assert that, without anything setting one, we get 0. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_get_retval = NULL, *link_set_eunatch = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that gets the previously set errno, and then + * one that sets the errno to EUNATCH. Assert that the get does not + * see EUNATCH set later, and does not prevent EUNATCH from being set. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + bpf_link__destroy(link_set_eunatch); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_set_eisconn = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that sets EISCONN, + * and then one that gets the exported errno. Assert both the syscall + * and the helper sees the last set errno. + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EISCONN, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_legacy_eperm = NULL, *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that return a reject without setting errno + * (legacy reject), and one that gets the errno. Assert that for + * backward compatibility the syscall result in EPERM, and this + * is also visible to the helper. + */ + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EPERM, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 2, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EPERM, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_setsockopt *obj; + struct bpf_link *link_set_eunatch = NULL, *link_legacy_eperm = NULL; + struct bpf_link *link_get_retval = NULL; + + obj = cgroup_getset_retval_setsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach setsockopt that sets EUNATCH, then one that return a reject + * without setting errno, and then one that gets the exported errno. + * Assert both the syscall and the helper's errno are unaffected by + * the second prog (i.e. legacy rejects does not override the errno + * to EPERM). + */ + link_set_eunatch = bpf_program__attach_cgroup(obj->progs.set_eunatch, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eunatch, "cg-attach-set_eunatch")) + goto close_bpf_object; + link_legacy_eperm = bpf_program__attach_cgroup(obj->progs.legacy_eperm, + cgroup_fd); + if (!ASSERT_OK_PTR(link_legacy_eperm, "cg-attach-legacy_eperm")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(setsockopt(sock_fd, SOL_SOCKET, SO_REUSEADDR, + &zero, sizeof(int)), "setsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EUNATCH, "setsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EUNATCH, "retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eunatch); + bpf_link__destroy(link_legacy_eperm); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_setsockopt__destroy(obj); +} + +static void test_getsockopt_get(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that gets previously set errno. Assert that the + * error from kernel is in both ctx_retval_value and retval_value. + */ + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EOPNOTSUPP, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, -EOPNOTSUPP, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, -EOPNOTSUPP, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_override(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN. Assert that this + * overrides the value from kernel. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + + if (!ASSERT_ERR(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + if (!ASSERT_EQ(errno, EISCONN, "getsockopt-errno")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 1, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd) +{ + struct cgroup_getset_retval_getsockopt *obj; + struct bpf_link *link_set_eisconn = NULL, *link_clear_retval = NULL; + struct bpf_link *link_get_retval = NULL; + int buf; + socklen_t optlen = sizeof(buf); + + obj = cgroup_getset_retval_getsockopt__open_and_load(); + if (!ASSERT_OK_PTR(obj, "skel-load")) + return; + + /* Attach getsockopt that sets retval to -EISCONN, and one that clears + * ctx retval. Assert that the clearing ctx retval is synced to helper + * and clears any errors both from kernel and BPF.. + */ + link_set_eisconn = bpf_program__attach_cgroup(obj->progs.set_eisconn, + cgroup_fd); + if (!ASSERT_OK_PTR(link_set_eisconn, "cg-attach-set_eisconn")) + goto close_bpf_object; + link_clear_retval = bpf_program__attach_cgroup(obj->progs.clear_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_clear_retval, "cg-attach-clear_retval")) + goto close_bpf_object; + link_get_retval = bpf_program__attach_cgroup(obj->progs.get_retval, + cgroup_fd); + if (!ASSERT_OK_PTR(link_get_retval, "cg-attach-get_retval")) + goto close_bpf_object; + + if (!ASSERT_OK(getsockopt(sock_fd, SOL_CUSTOM, 0, + &buf, &optlen), "getsockopt")) + goto close_bpf_object; + + if (!ASSERT_EQ(obj->bss->invocations, 3, "invocations")) + goto close_bpf_object; + if (!ASSERT_FALSE(obj->bss->assertion_error, "assertion_error")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->retval_value, 0, "retval_value")) + goto close_bpf_object; + if (!ASSERT_EQ(obj->bss->ctx_retval_value, 0, "ctx_retval_value")) + goto close_bpf_object; + +close_bpf_object: + bpf_link__destroy(link_set_eisconn); + bpf_link__destroy(link_clear_retval); + bpf_link__destroy(link_get_retval); + + cgroup_getset_retval_getsockopt__destroy(obj); +} + +void test_cgroup_getset_retval(void) +{ + int cgroup_fd = -1; + int sock_fd = -1; + + cgroup_fd = test__join_cgroup("/cgroup_getset_retval"); + if (!ASSERT_GE(cgroup_fd, 0, "cg-create")) + goto close_fd; + + sock_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0); + if (!ASSERT_GE(sock_fd, 0, "start-server")) + goto close_fd; + + if (test__start_subtest("setsockopt-set")) + test_setsockopt_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-set_and_get")) + test_setsockopt_set_and_get(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero")) + test_setsockopt_default_zero(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-default_zero_and_set")) + test_setsockopt_default_zero_and_set(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-override")) + test_setsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_eperm")) + test_setsockopt_legacy_eperm(cgroup_fd, sock_fd); + + if (test__start_subtest("setsockopt-legacy_no_override")) + test_setsockopt_legacy_no_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-get")) + test_getsockopt_get(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-override")) + test_getsockopt_override(cgroup_fd, sock_fd); + + if (test__start_subtest("getsockopt-retval_sync")) + test_getsockopt_retval_sync(cgroup_fd, sock_fd); + +close_fd: + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index ac54e3f91d42..dfafd62df50b 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -457,7 +457,7 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) if (map_fd < 0) return -1; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index 9da131b32e13..917165e04427 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -121,7 +121,7 @@ static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration) if (CHECK_FAIL(map_fd < 0)) return; - buff = malloc(bpf_map__def(map)->value_size); + buff = malloc(bpf_map__value_size(map)); if (buff) err = bpf_map_update_elem(map_fd, &zero, buff, 0); free(buff); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c index 1db86eab101b..57331c606964 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c @@ -20,7 +20,7 @@ void test_global_data_init(void) if (CHECK_FAIL(!map || !bpf_map__is_internal(map))) goto out; - sz = bpf_map__def(map)->value_size; + sz = bpf_map__value_size(map); newval = malloc(sz); if (CHECK_FAIL(!newval)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7d7445ccc141..b39a4f09aefd 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -27,6 +27,12 @@ static void test_main(void) ASSERT_OK(err, "bpf_prog_test_run(test2)"); ASSERT_EQ(retval, 3, "test2-retval"); + prog_fd = skel->progs.kfunc_call_test_ref_btf_id.prog_fd; + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + ASSERT_OK(err, "bpf_prog_test_run(test_ref_btf_id)"); + ASSERT_EQ(retval, 0, "test_ref_btf_id-retval"); + kfunc_call_test_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 85db0f4cdd95..b97a8f236b3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -8,6 +8,7 @@ #include "test_sockmap_update.skel.h" #include "test_sockmap_invalid_update.skel.h" #include "test_sockmap_skb_verdict_attach.skel.h" +#include "test_sockmap_progs_query.skel.h" #include "bpf_iter_sockmap.skel.h" #define TCP_REPAIR 19 /* TCP sock is under repair right now */ @@ -315,6 +316,63 @@ out: test_sockmap_skb_verdict_attach__destroy(skel); } +static __u32 query_prog_id(int prog_fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int err; + + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") || + !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd")) + return 0; + + return info.id; +} + +static void test_sockmap_progs_query(enum bpf_attach_type attach_type) +{ + struct test_sockmap_progs_query *skel; + int err, map_fd, verdict_fd; + __u32 attach_flags = 0; + __u32 prog_ids[3] = {}; + __u32 prog_cnt = 3; + + skel = test_sockmap_progs_query__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_sockmap_progs_query__open_and_load")) + return; + + map_fd = bpf_map__fd(skel->maps.sock_map); + + if (attach_type == BPF_SK_MSG_VERDICT) + verdict_fd = bpf_program__fd(skel->progs.prog_skmsg_verdict); + else + verdict_fd = bpf_program__fd(skel->progs.prog_skb_verdict); + + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 0, "wrong program count on query"); + + err = bpf_prog_attach(verdict_fd, map_fd, attach_type, 0); + if (!ASSERT_OK(err, "bpf_prog_attach failed")) + goto out; + + prog_cnt = 1; + err = bpf_prog_query(map_fd, attach_type, 0 /* query flags */, + &attach_flags, prog_ids, &prog_cnt); + ASSERT_OK(err, "bpf_prog_query failed"); + ASSERT_EQ(attach_flags, 0, "wrong attach_flags on query"); + ASSERT_EQ(prog_cnt, 1, "wrong program count on query"); + ASSERT_EQ(prog_ids[0], query_prog_id(verdict_fd), + "wrong prog_ids on query"); + + bpf_prog_detach2(verdict_fd, map_fd, attach_type); +out: + test_sockmap_progs_query__destroy(skel); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -341,4 +399,12 @@ void test_sockmap_basic(void) test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT, BPF_SK_SKB_VERDICT); } + if (test__start_subtest("sockmap msg_verdict progs query")) + test_sockmap_progs_query(BPF_SK_MSG_VERDICT); + if (test__start_subtest("sockmap stream_parser progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_PARSER); + if (test__start_subtest("sockmap stream_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT); + if (test__start_subtest("sockmap skb_verdict progs query")) + test_sockmap_progs_query(BPF_SK_SKB_VERDICT); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 7e21bfab6358..2cf0c7a3fe23 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -1413,14 +1413,12 @@ close_srv1: static void test_ops_cleanup(const struct bpf_map *map) { - const struct bpf_map_def *def; int err, mapfd; u32 key; - def = bpf_map__def(map); mapfd = bpf_map__fd(map); - for (key = 0; key < def->max_entries; key++) { + for (key = 0; key < bpf_map__max_entries(map); key++) { err = bpf_map_delete_elem(mapfd, &key); if (err && errno != EINVAL && errno != ENOENT) FAIL_ERRNO("map_delete: expected EINVAL/ENOENT"); @@ -1443,13 +1441,13 @@ static const char *family_str(sa_family_t family) static const char *map_type_str(const struct bpf_map *map) { - const struct bpf_map_def *def; + int type; - def = bpf_map__def(map); - if (IS_ERR(def)) + if (!map) return "invalid"; + type = bpf_map__type(map); - switch (def->type) { + switch (type) { case BPF_MAP_TYPE_SOCKMAP: return "sockmap"; case BPF_MAP_TYPE_SOCKHASH: diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 4b937e5dbaca..30a99d2ed5c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -173,11 +173,11 @@ static int getsetsockopt(void) } memset(&buf, 0, sizeof(buf)); - buf.zc.address = 12345; /* rejected by BPF */ + buf.zc.address = 12345; /* Not page aligned. Rejected by tcp_zerocopy_receive() */ optlen = sizeof(buf.zc); errno = 0; err = getsockopt(fd, SOL_TCP, TCP_ZEROCOPY_RECEIVE, &buf, &optlen); - if (errno != EPERM) { + if (errno != EINVAL) { log_err("Unexpected getsockopt(TCP_ZEROCOPY_RECEIVE) err=%d errno=%d", err, errno); goto err; diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index 5dc0f425bd11..796f231582f8 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -37,7 +37,7 @@ static void test_tailcall_1(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -53,7 +53,7 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, &duration, &retval, NULL); CHECK(err || retval != i, "tailcall", @@ -69,7 +69,7 @@ static void test_tailcall_1(void) CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", err, errno, retval); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -90,8 +90,8 @@ static void test_tailcall_1(void) CHECK(err || retval != 0, "tailcall", "err %d errno %d retval %d\n", err, errno, retval); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; snprintf(prog_name, sizeof(prog_name), "classifier_%d", j); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -107,8 +107,8 @@ static void test_tailcall_1(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { - j = bpf_map__def(prog_array)->max_entries - 1 - i; + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + j = bpf_map__max_entries(prog_array) - 1 - i; err = bpf_prog_test_run(main_fd, 1, buff, sizeof(buff), 0, &duration, &retval, NULL); @@ -125,7 +125,7 @@ static void test_tailcall_1(void) CHECK(err || retval != 3, "tailcall", "err %d errno %d retval %d\n", err, errno, retval); - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_delete_elem(map_fd, &i); if (CHECK_FAIL(err >= 0 || errno != ENOENT)) goto out; @@ -175,7 +175,7 @@ static void test_tailcall_2(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -353,7 +353,7 @@ static void test_tailcall_4(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -369,7 +369,7 @@ static void test_tailcall_4(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -380,7 +380,7 @@ static void test_tailcall_4(void) "err %d errno %d retval %d\n", err, errno, retval); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &i, BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -441,7 +441,7 @@ static void test_tailcall_5(void) if (CHECK_FAIL(map_fd < 0)) return; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -457,7 +457,7 @@ static void test_tailcall_5(void) goto out; } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -468,7 +468,7 @@ static void test_tailcall_5(void) "err %d errno %d retval %d\n", err, errno, retval); } - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { err = bpf_map_update_elem(data_fd, &zero, &key[i], BPF_ANY); if (CHECK_FAIL(err)) goto out; @@ -520,7 +520,7 @@ static void test_tailcall_bpf2bpf_1(void) goto out; /* nop -> jmp */ - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -681,7 +681,7 @@ static void test_tailcall_bpf2bpf_3(void) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); @@ -778,7 +778,7 @@ static void test_tailcall_bpf2bpf_4(bool noise) if (CHECK_FAIL(map_fd < 0)) goto out; - for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) { + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { snprintf(prog_name, sizeof(prog_name), "classifier_%d", i); prog = bpf_object__find_program_by_name(obj, prog_name); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c new file mode 100644 index 000000000000..31c188666e81 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_frags.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include <network_helpers.h> + +void test_xdp_update_frags(void) +{ + const char *file = "./test_xdp_update_frags.o"; + __u32 duration, retval, size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u32 *offset; + __u8 *buf; + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(128); + if (!ASSERT_OK_PTR(buf, "alloc buf 128b")) + goto out; + + memset(buf, 0, 128); + offset = (__u32 *)buf; + *offset = 16; + buf[*offset] = 0xaa; /* marker at offset 16 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 31 (head) */ + + err = bpf_prog_test_run(prog_fd, 1, buf, 128, + buf, &size, &retval, &duration); + + /* test_xdp_update_frags: buf[16,31]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[16], 0xbb, "xdp_update_frag buf[16]"); + ASSERT_EQ(buf[31], 0xbb, "xdp_update_frag buf[31]"); + + free(buf); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 5000; + buf[*offset] = 0xaa; /* marker at offset 5000 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 5015 (frag0) */ + + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + /* test_xdp_update_frags: buf[5000,5015]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[5000], 0xbb, "xdp_update_frag buf[5000]"); + ASSERT_EQ(buf[5015], 0xbb, "xdp_update_frag buf[5015]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 3510; + buf[*offset] = 0xaa; /* marker at offset 3510 (head) */ + buf[*offset + 15] = 0xaa; /* marker at offset 3525 (frag0) */ + + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + /* test_xdp_update_frags: buf[3510,3525]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[3510], 0xbb, "xdp_update_frag buf[3510]"); + ASSERT_EQ(buf[3525], 0xbb, "xdp_update_frag buf[3525]"); + + memset(buf, 0, 9000); + offset = (__u32 *)buf; + *offset = 7606; + buf[*offset] = 0xaa; /* marker at offset 7606 (frag0) */ + buf[*offset + 15] = 0xaa; /* marker at offset 7621 (frag1) */ + + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + /* test_xdp_update_frags: buf[7606,7621]: 0xaa -> 0xbb */ + ASSERT_OK(err, "xdp_update_frag"); + ASSERT_EQ(retval, XDP_PASS, "xdp_update_frag retval"); + ASSERT_EQ(buf[7606], 0xbb, "xdp_update_frag buf[7606]"); + ASSERT_EQ(buf[7621], 0xbb, "xdp_update_frag buf[7621]"); + + free(buf); +out: + bpf_object__close(obj); +} + +void test_xdp_adjust_frags(void) +{ + if (test__start_subtest("xdp_adjust_frags")) + test_xdp_update_frags(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 3f5a17c38be5..ccc9e63254a8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -11,22 +11,21 @@ static void test_xdp_adjust_tail_shrink(void) char buf[128]; err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_shrink")) return; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) - 20; /* Test shrink with 20 bytes */ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(size, expect_sz, "ipv6 size"); + bpf_object__close(obj); } @@ -39,21 +38,20 @@ static void test_xdp_adjust_tail_grow(void) int err, prog_fd; err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (CHECK_FAIL(err)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - CHECK(err || retval != XDP_DROP, - "ipv4", "err %d errno %d retval %d size %d\n", - err, errno, retval, size); + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(retval, XDP_DROP, "ipv4 retval"); expect_sz = sizeof(pkt_v6) + 40; /* Test grow with 40 bytes */ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6) /* 74 */, buf, &size, &retval, &duration); - CHECK(err || retval != XDP_TX || size != expect_sz, - "ipv6", "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, retval, size, expect_sz); + ASSERT_OK(err, "ipv6"); + ASSERT_EQ(retval, XDP_TX, "ipv6 retval"); + ASSERT_EQ(size, expect_sz, "ipv6 size"); bpf_object__close(obj); } @@ -76,7 +74,7 @@ static void test_xdp_adjust_tail_grow2(void) }; err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &tattr.prog_fd); - if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno)) + if (ASSERT_OK(err, "test_xdp_adjust_tail_grow")) return; /* Test case-64 */ @@ -86,21 +84,17 @@ static void test_xdp_adjust_tail_grow2(void) /* Kernel side alloc packet memory area that is zero init */ err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(errno != ENOSPC /* Due limit copy_size in bpf_test_finish */ - || tattr.retval != XDP_TX - || tattr.data_size_out != 192, /* Expected grow size */ - "case-64", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(errno, ENOSPC, "case-64 errno"); /* Due limit copy_size in bpf_test_finish */ + ASSERT_EQ(tattr.retval, XDP_TX, "case-64 retval"); + ASSERT_EQ(tattr.data_size_out, 192, "case-64 data_size_out"); /* Expected grow size */ /* Extra checks for data contents */ - CHECK_ATTR(tattr.data_size_out != 192 - || buf[0] != 1 || buf[63] != 1 /* 0-63 memset to 1 */ - || buf[64] != 0 || buf[127] != 0 /* 64-127 memset to 0 */ - || buf[128] != 1 || buf[191] != 1, /*128-191 memset to 1 */ - "case-64-data", - "err %d errno %d retval %d size %d\n", - err, errno, tattr.retval, tattr.data_size_out); + ASSERT_EQ(buf[0], 1, "case-64-data buf[0]"); /* 0-63 memset to 1 */ + ASSERT_EQ(buf[63], 1, "case-64-data buf[63]"); + ASSERT_EQ(buf[64], 0, "case-64-data buf[64]"); /* 64-127 memset to 0 */ + ASSERT_EQ(buf[127], 0, "case-64-data buf[127]"); + ASSERT_EQ(buf[128], 1, "case-64-data buf[128]"); /* 128-191 memset to 1 */ + ASSERT_EQ(buf[191], 1, "case-64-data buf[191]"); /* Test case-128 */ memset(buf, 2, sizeof(buf)); @@ -109,24 +103,139 @@ static void test_xdp_adjust_tail_grow2(void) err = bpf_prog_test_run_xattr(&tattr); max_grow = 4096 - XDP_PACKET_HEADROOM - tailroom; /* 3520 */ - CHECK_ATTR(err - || tattr.retval != XDP_TX - || tattr.data_size_out != max_grow,/* Expect max grow size */ - "case-128", - "err %d errno %d retval %d size %d expect-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, max_grow); + ASSERT_OK(err, "case-128"); + ASSERT_EQ(tattr.retval, XDP_TX, "case-128 retval"); + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128 data_size_out"); /* Expect max grow */ /* Extra checks for data content: Count grow size, will contain zeros */ for (i = 0, cnt = 0; i < sizeof(buf); i++) { if (buf[i] == 0) cnt++; } - CHECK_ATTR((cnt != (max_grow - tattr.data_size_in)) /* Grow increase */ - || tattr.data_size_out != max_grow, /* Total grow size */ - "case-128-data", - "err %d errno %d retval %d size %d grow-size %d\n", - err, errno, tattr.retval, tattr.data_size_out, cnt); + ASSERT_EQ(cnt, max_grow - tattr.data_size_in, "case-128-data cnt"); /* Grow increase */ + ASSERT_EQ(tattr.data_size_out, max_grow, "case-128-data data_size_out"); /* Total grow */ + + bpf_object__close(obj); +} + +void test_xdp_adjust_frags_tail_shrink(void) +{ + const char *file = "./test_xdp_adjust_tail_shrink.o"; + __u32 duration, retval, size, exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, prog_fd; + __u8 *buf; + + /* For the individual test cases, the first byte in the packet + * indicates which test will be run. + */ + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(9000); + if (!ASSERT_OK_PTR(buf, "alloc buf 9Kb")) + goto out; + + memset(buf, 0, 9000); + + /* Test case removing 10 bytes from last frag, NOT freeing it */ + exp_size = 8990; /* 9000 - 10 */ + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "9Kb-10b"); + ASSERT_EQ(retval, XDP_TX, "9Kb-10b retval"); + ASSERT_EQ(size, exp_size, "9Kb-10b size"); + + /* Test case removing one of two pages, assuming 4K pages */ + buf[0] = 1; + exp_size = 4900; /* 9000 - 4100 */ + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "9Kb-4Kb"); + ASSERT_EQ(retval, XDP_TX, "9Kb-4Kb retval"); + ASSERT_EQ(size, exp_size, "9Kb-4Kb size"); + + /* Test case removing two pages resulting in a linear xdp_buff */ + buf[0] = 2; + exp_size = 800; /* 9000 - 8200 */ + err = bpf_prog_test_run(prog_fd, 1, buf, 9000, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "9Kb-9Kb"); + ASSERT_EQ(retval, XDP_TX, "9Kb-9Kb retval"); + ASSERT_EQ(size, exp_size, "9Kb-9Kb size"); + + free(buf); +out: + bpf_object__close(obj); +} + +void test_xdp_adjust_frags_tail_grow(void) +{ + const char *file = "./test_xdp_adjust_tail_grow.o"; + __u32 duration, retval, size, exp_size; + struct bpf_program *prog; + struct bpf_object *obj; + int err, i, prog_fd; + __u8 *buf; + + obj = bpf_object__open(file); + if (libbpf_get_error(obj)) + return; + + prog = bpf_object__next_program(obj, NULL); + if (bpf_object__load(obj)) + return; + + prog_fd = bpf_program__fd(prog); + + buf = malloc(16384); + if (!ASSERT_OK_PTR(buf, "alloc buf 16Kb")) + goto out; + + /* Test case add 10 bytes to last frag */ + memset(buf, 1, 16384); + size = 9000; + exp_size = size + 10; + err = bpf_prog_test_run(prog_fd, 1, buf, size, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(retval, XDP_TX, "9Kb+10b retval"); + ASSERT_EQ(size, exp_size, "9Kb+10b size"); + + for (i = 0; i < 9000; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-old"); + + for (i = 9000; i < 9010; i++) + ASSERT_EQ(buf[i], 0, "9Kb+10b-new"); + + for (i = 9010; i < 16384; i++) + ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched"); + + /* Test a too large grow */ + memset(buf, 1, 16384); + size = 9001; + exp_size = size; + err = bpf_prog_test_run(prog_fd, 1, buf, size, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "9Kb+10b"); + ASSERT_EQ(retval, XDP_DROP, "9Kb+10b retval"); + ASSERT_EQ(size, exp_size, "9Kb+10b size"); + free(buf); +out: bpf_object__close(obj); } @@ -138,4 +247,8 @@ void test_xdp_adjust_tail(void) test_xdp_adjust_tail_grow(); if (test__start_subtest("xdp_adjust_tail_grow2")) test_xdp_adjust_tail_grow2(); + if (test__start_subtest("xdp_adjust_frags_tail_shrink")) + test_xdp_adjust_frags_tail_shrink(); + if (test__start_subtest("xdp_adjust_frags_tail_grow")) + test_xdp_adjust_frags_tail_grow(); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index c98a897ad692..9c395ea680c6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -10,40 +10,97 @@ struct meta { int pkt_len; }; +struct test_ctx_s { + bool passed; + int pkt_size; +}; + +struct test_ctx_s test_ctx; + static void on_sample(void *ctx, int cpu, void *data, __u32 size) { - int duration = 0; struct meta *meta = (struct meta *)data; struct ipv4_packet *trace_pkt_v4 = data + sizeof(*meta); + unsigned char *raw_pkt = data + sizeof(*meta); + struct test_ctx_s *tst_ctx = ctx; + + ASSERT_GE(size, sizeof(pkt_v4) + sizeof(*meta), "check_size"); + ASSERT_EQ(meta->ifindex, if_nametoindex("lo"), "check_meta_ifindex"); + ASSERT_EQ(meta->pkt_len, tst_ctx->pkt_size, "check_meta_pkt_len"); + ASSERT_EQ(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), 0, + "check_packet_content"); + + if (meta->pkt_len > sizeof(pkt_v4)) { + for (int i = 0; i < meta->pkt_len - sizeof(pkt_v4); i++) + ASSERT_EQ(raw_pkt[i + sizeof(pkt_v4)], (unsigned char)i, + "check_packet_content"); + } + + tst_ctx->passed = true; +} - if (CHECK(size < sizeof(pkt_v4) + sizeof(*meta), - "check_size", "size %u < %zu\n", - size, sizeof(pkt_v4) + sizeof(*meta))) - return; +#define BUF_SZ 9000 - if (CHECK(meta->ifindex != if_nametoindex("lo"), "check_meta_ifindex", - "meta->ifindex = %d\n", meta->ifindex)) +static void run_xdp_bpf2bpf_pkt_size(int pkt_fd, struct perf_buffer *pb, + struct test_xdp_bpf2bpf *ftrace_skel, + int pkt_size) +{ + __u32 duration = 0, retval, size; + __u8 *buf, *buf_in; + int err; + + if (!ASSERT_LE(pkt_size, BUF_SZ, "pkt_size") || + !ASSERT_GE(pkt_size, sizeof(pkt_v4), "pkt_size")) return; - if (CHECK(meta->pkt_len != sizeof(pkt_v4), "check_meta_pkt_len", - "meta->pkt_len = %zd\n", sizeof(pkt_v4))) + buf_in = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf_in, "buf_in malloc()")) return; - if (CHECK(memcmp(trace_pkt_v4, &pkt_v4, sizeof(pkt_v4)), - "check_packet_content", "content not the same\n")) + buf = malloc(BUF_SZ); + if (!ASSERT_OK_PTR(buf, "buf malloc()")) { + free(buf_in); return; + } + + test_ctx.passed = false; + test_ctx.pkt_size = pkt_size; + + memcpy(buf_in, &pkt_v4, sizeof(pkt_v4)); + if (pkt_size > sizeof(pkt_v4)) { + for (int i = 0; i < (pkt_size - sizeof(pkt_v4)); i++) + buf_in[i + sizeof(pkt_v4)] = i; + } + + /* Run test program */ + err = bpf_prog_test_run(pkt_fd, 1, buf_in, pkt_size, + buf, &size, &retval, &duration); + + ASSERT_OK(err, "ipv4"); + ASSERT_EQ(retval, XDP_PASS, "ipv4 retval"); + ASSERT_EQ(size, pkt_size, "ipv4 size"); + + /* Make sure bpf_xdp_output() was triggered and it sent the expected + * data to the perf ring buffer. + */ + err = perf_buffer__poll(pb, 100); - *(bool *)ctx = true; + ASSERT_GE(err, 0, "perf_buffer__poll"); + ASSERT_TRUE(test_ctx.passed, "test passed"); + /* Verify test results */ + ASSERT_EQ(ftrace_skel->bss->test_result_fentry, if_nametoindex("lo"), + "fentry result"); + ASSERT_EQ(ftrace_skel->bss->test_result_fexit, XDP_PASS, "fexit result"); + + free(buf); + free(buf_in); } void test_xdp_bpf2bpf(void) { - __u32 duration = 0, retval, size; - char buf[128]; int err, pkt_fd, map_fd; - bool passed = false; - struct iphdr iph; - struct iptnl_info value4 = {.family = AF_INET}; + int pkt_sizes[] = {sizeof(pkt_v4), 1024, 4100, 8200}; + struct iptnl_info value4 = {.family = AF_INET6}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; @@ -52,7 +109,7 @@ void test_xdp_bpf2bpf(void) /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); - if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n")) + if (!ASSERT_OK_PTR(pkt_skel, "test_xdp__open_and_load")) return; pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel); @@ -62,7 +119,7 @@ void test_xdp_bpf2bpf(void) /* Load trace program */ ftrace_skel = test_xdp_bpf2bpf__open(); - if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) + if (!ASSERT_OK_PTR(ftrace_skel, "test_xdp_bpf2bpf__open")) goto out; /* Demonstrate the bpf_program__set_attach_target() API rather than @@ -77,50 +134,24 @@ void test_xdp_bpf2bpf(void) bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); err = test_xdp_bpf2bpf__load(ftrace_skel); - if (CHECK(err, "__load", "ftrace skeleton failed\n")) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__load")) goto out; err = test_xdp_bpf2bpf__attach(ftrace_skel); - if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err)) + if (!ASSERT_OK(err, "test_xdp_bpf2bpf__attach")) goto out; /* Set up perf buffer */ - pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, - on_sample, NULL, &passed, NULL); + pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 8, + on_sample, NULL, &test_ctx, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; - /* Run test program */ - err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), - buf, &size, &retval, &duration); - memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); - if (CHECK(err || retval != XDP_TX || size != 74 || - iph.protocol != IPPROTO_IPIP, "ipv4", - "err %d errno %d retval %d size %d\n", - err, errno, retval, size)) - goto out; - - /* Make sure bpf_xdp_output() was triggered and it sent the expected - * data to the perf ring buffer. - */ - err = perf_buffer__poll(pb, 100); - if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err)) - goto out; - - CHECK_FAIL(!passed); - - /* Verify test results */ - if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"), - "result", "fentry failed err %llu\n", - ftrace_skel->bss->test_result_fentry)) - goto out; - - CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result", - "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit); - + for (int i = 0; i < ARRAY_SIZE(pkt_sizes); i++) + run_xdp_bpf2bpf_pkt_size(pkt_fd, pb, ftrace_skel, + pkt_sizes[i]); out: - if (pb) - perf_buffer__free(pb); + perf_buffer__free(pb); test_xdp__destroy(pkt_skel); test_xdp_bpf2bpf__destroy(ftrace_skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index fd812bd43600..13aabb3b6cf2 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -3,11 +3,12 @@ #include <linux/if_link.h> #include <test_progs.h> +#include "test_xdp_with_cpumap_frags_helpers.skel.h" #include "test_xdp_with_cpumap_helpers.skel.h" #define IFINDEX_LO 1 -void serial_test_xdp_cpumap_attach(void) +void test_xdp_with_cpumap_helpers(void) { struct test_xdp_with_cpumap_helpers *skel; struct bpf_prog_info info = {}; @@ -54,6 +55,67 @@ void serial_test_xdp_cpumap_attach(void) err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_CPUMAP program to cpumap entry"); + /* Try to attach BPF_XDP program with frags to cpumap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry"); + out_close: test_xdp_with_cpumap_helpers__destroy(skel); } + +void test_xdp_with_cpumap_frags_helpers(void) +{ + struct test_xdp_with_cpumap_frags_helpers *skel; + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + struct bpf_cpumap_val val = { + .qsize = 192, + }; + int err, frags_prog_fd, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_cpumap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load")) + return; + + frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags); + map_fd = bpf_map__fd(skel->maps.cpu_map); + err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = frags_prog_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to cpumap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read cpumap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to cpumap entry prog_id"); + + /* Try to attach BPF_XDP program to cpumap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.qsize = 192; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_cm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to cpumap entry"); + +out_close: + test_xdp_with_cpumap_frags_helpers__destroy(skel); +} + +void serial_test_xdp_cpumap_attach(void) +{ + if (test__start_subtest("CPUMAP with programs in entries")) + test_xdp_with_cpumap_helpers(); + + if (test__start_subtest("CPUMAP with frags programs in entries")) + test_xdp_with_cpumap_frags_helpers(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 3079d5568f8f..2a784ccd3136 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -4,6 +4,7 @@ #include <test_progs.h> #include "test_xdp_devmap_helpers.skel.h" +#include "test_xdp_with_devmap_frags_helpers.skel.h" #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 @@ -56,6 +57,15 @@ static void test_xdp_with_devmap_helpers(void) err = bpf_map_update_elem(map_fd, &idx, &val, 0); ASSERT_NEQ(err, 0, "Add non-BPF_XDP_DEVMAP program to devmap entry"); + /* Try to attach BPF_XDP program with frags to devmap when we have + * already loaded a BPF_XDP program on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); + out_close: test_xdp_with_devmap_helpers__destroy(skel); } @@ -71,12 +81,57 @@ static void test_neg_xdp_devmap_helpers(void) } } +void test_xdp_with_devmap_frags_helpers(void) +{ + struct test_xdp_with_devmap_frags_helpers *skel; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = { + .ifindex = IFINDEX_LO, + }; + __u32 len = sizeof(info); + int err, dm_fd_frags, map_fd; + __u32 idx = 0; + + skel = test_xdp_with_devmap_frags_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + return; + + dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len); + if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd_frags; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add frags program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, + "Match program id to devmap entry prog_id"); + + /* Try to attach BPF_XDP program to devmap when we have + * already loaded a BPF_XDP program with frags on the map + */ + idx = 1; + val.ifindex = 1; + val.bpf_prog.fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_NEQ(err, 0, "Add BPF_XDP program to devmap entry"); + +out_close: + test_xdp_with_devmap_frags_helpers__destroy(skel); +} void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) test_xdp_with_devmap_helpers(); + if (test__start_subtest("DEVMAP with frags programs in entries")) + test_xdp_with_devmap_frags_helpers(); + if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); } diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c new file mode 100644 index 000000000000..eafc877ea460 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ +#include "bpf_iter.h" +#include "bpf_tracing_net.h" +#include <bpf/bpf_helpers.h> +#include <limits.h> + +#define AUTOBIND_LEN 6 +char sun_path[AUTOBIND_LEN]; + +#define NR_CASES 5 +int sndbuf_setsockopt[NR_CASES] = {-1, 0, 8192, INT_MAX / 2, INT_MAX}; +int sndbuf_getsockopt[NR_CASES] = {-1, -1, -1, -1, -1}; +int sndbuf_getsockopt_expected[NR_CASES]; + +static inline int cmpname(struct unix_sock *unix_sk) +{ + int i; + + for (i = 0; i < AUTOBIND_LEN; i++) { + if (unix_sk->addr->name->sun_path[i] != sun_path[i]) + return -1; + } + + return 0; +} + +SEC("iter/unix") +int change_sndbuf(struct bpf_iter__unix *ctx) +{ + struct unix_sock *unix_sk = ctx->unix_sk; + int i, err; + + if (!unix_sk || !unix_sk->addr) + return 0; + + if (unix_sk->addr->name->sun_path[0]) + return 0; + + if (cmpname(unix_sk)) + return 0; + + for (i = 0; i < NR_CASES; i++) { + err = bpf_setsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_setsockopt[i], + sizeof(sndbuf_setsockopt[i])); + if (err) + break; + + err = bpf_getsockopt(unix_sk, SOL_SOCKET, SO_SNDBUF, + &sndbuf_getsockopt[i], + sizeof(sndbuf_getsockopt[i])); + if (err) + break; + } + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c index c21e3f545371..e6aefae38894 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c @@ -63,7 +63,7 @@ int dump_unix(struct bpf_iter__unix *ctx) BPF_SEQ_PRINTF(seq, " @"); for (i = 1; i < len; i++) { - /* unix_mkname() tests this upper bound. */ + /* unix_validate_addr() tests this upper bound. */ if (i >= sizeof(struct sockaddr_un)) break; diff --git a/tools/testing/selftests/bpf/progs/bpf_mod_race.c b/tools/testing/selftests/bpf/progs/bpf_mod_race.c new file mode 100644 index 000000000000..82a5c6c6ba83 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_mod_race.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile struct { + /* thread to activate trace programs for */ + pid_t tgid; + /* return error from __init function */ + int inject_error; + /* uffd monitored range start address */ + void *fault_addr; +} bpf_mod_race_config = { -1 }; + +int bpf_blocking = 0; +int res_try_get_module = -1; + +static __always_inline bool check_thread_id(void) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + return task->tgid == bpf_mod_race_config.tgid; +} + +/* The trace of execution is something like this: + * + * finit_module() + * load_module() + * prepare_coming_module() + * notifier_call(MODULE_STATE_COMING) + * btf_parse_module() + * btf_alloc_id() // Visible to userspace at this point + * list_add(btf_mod->list, &btf_modules) + * do_init_module() + * freeinit = kmalloc() + * ret = mod->init() + * bpf_prog_widen_race() + * bpf_copy_from_user() + * ...<sleep>... + * if (ret < 0) + * ... + * free_module() + * return ret + * + * At this point, module loading thread is blocked, we now load the program: + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module_live == false + * return -ENXIO + * + * Without the fix (try_get_module_live in btf_try_get_module): + * + * bpf_check + * add_kfunc_call/check_pseudo_btf_id + * btf_try_get_module + * try_get_module == true + * <store module reference in btf_kfunc_tab or used_btf array> + * ... + * return fd + * + * Now, if we inject an error in the blocked program, our module will be freed + * (going straight from MODULE_STATE_COMING to MODULE_STATE_GOING). + * Later, when bpf program is freed, it will try to module_put already freed + * module. This is why try_get_module_live returns false if mod->state is not + * MODULE_STATE_LIVE. + */ + +SEC("fmod_ret.s/bpf_fentry_test1") +int BPF_PROG(widen_race, int a, int ret) +{ + char dst; + + if (!check_thread_id()) + return 0; + /* Indicate that we will attempt to block */ + bpf_blocking = 1; + bpf_copy_from_user(&dst, 1, bpf_mod_race_config.fault_addr); + return bpf_mod_race_config.inject_error; +} + +SEC("fexit/do_init_module") +int BPF_PROG(fexit_init_module, struct module *mod, int ret) +{ + if (!check_thread_id()) + return 0; + /* Indicate that we finished blocking */ + bpf_blocking = 2; + return 0; +} + +SEC("fexit/btf_try_get_module") +int BPF_PROG(fexit_module_get, const struct btf *btf, struct module *mod) +{ + res_try_get_module = !!mod; + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index e0f42601be9b..1c1289ba5fc5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -5,6 +5,8 @@ #define AF_INET 2 #define AF_INET6 10 +#define SOL_SOCKET 1 +#define SO_SNDBUF 7 #define __SO_ACCEPTCON (1 << 16) #define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c new file mode 100644 index 000000000000..b2a409e6382a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; +__u32 ctx_retval_value = 0; + +SEC("cgroup/getsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + ctx_retval_value = ctx->retval; + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/getsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 1; +} + +SEC("cgroup/getsockopt") +int clear_retval(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + ctx->retval = 0; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c new file mode 100644 index 000000000000..d6e5903e06ba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright 2021 Google LLC. + */ + +#include <errno.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +__u32 invocations = 0; +__u32 assertion_error = 0; +__u32 retval_value = 0; + +SEC("cgroup/setsockopt") +int get_retval(struct bpf_sockopt *ctx) +{ + retval_value = bpf_get_retval(); + __sync_fetch_and_add(&invocations, 1); + + return 1; +} + +SEC("cgroup/setsockopt") +int set_eunatch(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EUNATCH)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int set_eisconn(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + if (bpf_set_retval(-EISCONN)) + assertion_error = 1; + + return 0; +} + +SEC("cgroup/setsockopt") +int legacy_eperm(struct bpf_sockopt *ctx) +{ + __sync_fetch_and_add(&invocations, 1); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c index 68a5a9db928a..7e94412d47a5 100644 --- a/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/freplace_cls_redirect.c @@ -7,12 +7,12 @@ #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") sock_map = { - .type = BPF_MAP_TYPE_SOCKMAP, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, int); + __uint(max_entries, 2); +} sock_map SEC(".maps"); SEC("freplace/cls_redirect") int freplace_cls_redirect_test(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c new file mode 100644 index 000000000000..4e8fed75a4e0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; + +SEC("tc") +int kfunc_call_fail(struct __sk_buff *ctx) +{ + bpf_testmod_test_mod_kfunc(0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index 8a8cf59017aa..5aecbb9fdc68 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -1,13 +1,20 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include <linux/bpf.h> +#include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "bpf_tcp_helpers.h" extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; +extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym; +extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym; +extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym; +extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym; +extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym; +extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; +extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; + SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) { @@ -44,4 +51,45 @@ int kfunc_call_test1(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_ref_btf_id(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *pt; + unsigned long s = 0; + int ret = 0; + + pt = bpf_kfunc_call_test_acquire(&s); + if (pt) { + if (pt->a != 42 || pt->b != 108) + ret = -1; + bpf_kfunc_call_test_release(pt); + } + return ret; +} + +SEC("tc") +int kfunc_call_test_pass(struct __sk_buff *skb) +{ + struct prog_test_pass1 p1 = {}; + struct prog_test_pass2 p2 = {}; + short a = 0; + __u64 b = 0; + long c = 0; + char d = 0; + int e = 0; + + bpf_kfunc_call_test_pass_ctx(skb); + bpf_kfunc_call_test_pass1(&p1); + bpf_kfunc_call_test_pass2(&p2); + + bpf_kfunc_call_test_mem_len_pass1(&a, sizeof(a)); + bpf_kfunc_call_test_mem_len_pass1(&b, sizeof(b)); + bpf_kfunc_call_test_mem_len_pass1(&c, sizeof(c)); + bpf_kfunc_call_test_mem_len_pass1(&d, sizeof(d)); + bpf_kfunc_call_test_mem_len_pass1(&e, sizeof(e)); + bpf_kfunc_call_test_mem_len_fail2(&b, -1); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/ksym_race.c b/tools/testing/selftests/bpf/progs/ksym_race.c new file mode 100644 index 000000000000..def97f2fed90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ksym_race.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +extern int bpf_testmod_ksym_percpu __ksym; + +SEC("tc") +int ksym_fail(struct __sk_buff *ctx) +{ + return *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 1612a32007b6..495990d355ef 100644 --- a/tools/testing/selftests/bpf/progs/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c @@ -2,19 +2,19 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") htab = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} htab SEC(".maps"); -struct bpf_map_def SEC("maps") array = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(long), - .max_entries = 2, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, long); + __uint(max_entries, 2); +} array SEC(".maps"); /* Sample program which should always load for testing control paths. */ SEC(".text") int func() diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 95d5b941bc1f..c9abfe3a11af 100644 --- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c @@ -7,8 +7,6 @@ int bpf_prog1(struct __sk_buff *skb) { void *data_end = (void *)(long) skb->data_end; void *data = (void *)(long) skb->data; - __u32 lport = skb->local_port; - __u32 rport = skb->remote_port; __u8 *d = data; int err; diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c index 79c8139b63b8..d0298dccedcd 100644 --- a/tools/testing/selftests/bpf/progs/sockopt_sk.c +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -73,17 +73,17 @@ int _getsockopt(struct bpf_sockopt *ctx) */ if (optval + sizeof(struct tcp_zerocopy_receive) > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ if (((struct tcp_zerocopy_receive *)optval)->address != 0) - return 0; /* EPERM, unexpected data */ + return 0; /* unexpected data */ return 1; } if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -96,24 +96,24 @@ int _getsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ if (!ctx->retval) - return 0; /* EPERM, kernel should not have handled + return 0; /* kernel should not have handled * SOL_CUSTOM, something is wrong! */ ctx->retval = 0; /* Reset system call return value to zero */ @@ -152,7 +152,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Overwrite SO_SNDBUF value */ if (optval + sizeof(__u32) > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ *(__u32 *)optval = 0x55AA; ctx->optlen = 4; @@ -164,7 +164,7 @@ int _setsockopt(struct bpf_sockopt *ctx) /* Always use cubic */ if (optval + 5 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ memcpy(optval, "cubic", 5); ctx->optlen = 5; @@ -175,10 +175,10 @@ int _setsockopt(struct bpf_sockopt *ctx) if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) { /* Original optlen is larger than PAGE_SIZE. */ if (ctx->optlen != page_size * 2) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ /* Make sure we can trim the buffer. */ optval[0] = 0; @@ -189,21 +189,21 @@ int _setsockopt(struct bpf_sockopt *ctx) * bytes of data. */ if (optval_end - optval != page_size) - return 0; /* EPERM, unexpected data size */ + return 0; /* unexpected data size */ return 1; } if (ctx->level != SOL_CUSTOM) - return 0; /* EPERM, deny everything except custom level */ + return 0; /* deny everything except custom level */ if (optval + 1 > optval_end) - return 0; /* EPERM, bounds check */ + return 0; /* bounds check */ storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, BPF_SK_STORAGE_GET_F_CREATE); if (!storage) - return 0; /* EPERM, couldn't get sk storage */ + return 0; /* couldn't get sk storage */ storage->val = optval[0]; ctx->optlen = -1; /* BPF has consumed this option, don't call kernel diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c new file mode 100644 index 000000000000..f00a9731930e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> + +#define EAFNOSUPPORT 97 +#define EPROTO 71 +#define ENONET 64 +#define EINVAL 22 +#define ENOENT 2 + +int test_einval_bpf_tuple = 0; +int test_einval_reserved = 0; +int test_einval_netns_id = 0; +int test_einval_len_opts = 0; +int test_eproto_l4proto = 0; +int test_enonet_netns_id = 0; +int test_enoent_lookup = 0; +int test_eafnosupport = 0; + +struct nf_conn; + +struct bpf_ct_opts___local { + s32 netns_id; + s32 error; + u8 l4proto; + u8 reserved[3]; +} __attribute__((preserve_access_index)); + +struct nf_conn *bpf_xdp_ct_lookup(struct xdp_md *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +struct nf_conn *bpf_skb_ct_lookup(struct __sk_buff *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32) __ksym; +void bpf_ct_release(struct nf_conn *) __ksym; + +static __always_inline void +nf_ct_test(struct nf_conn *(*func)(void *, struct bpf_sock_tuple *, u32, + struct bpf_ct_opts___local *, u32), + void *ctx) +{ + struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 }; + struct bpf_sock_tuple bpf_tuple; + struct nf_conn *ct; + + __builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4)); + + ct = func(ctx, NULL, 0, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_einval_bpf_tuple = opts_def.error; + + opts_def.reserved[0] = 1; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.reserved[0] = 0; + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_einval_reserved = opts_def.error; + + opts_def.netns_id = -2; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_einval_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def) - 1); + if (ct) + bpf_ct_release(ct); + else + test_einval_len_opts = opts_def.error; + + opts_def.l4proto = IPPROTO_ICMP; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.l4proto = IPPROTO_TCP; + if (ct) + bpf_ct_release(ct); + else + test_eproto_l4proto = opts_def.error; + + opts_def.netns_id = 0xf00f; + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + opts_def.netns_id = -1; + if (ct) + bpf_ct_release(ct); + else + test_enonet_netns_id = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_enoent_lookup = opts_def.error; + + ct = func(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4) - 1, &opts_def, sizeof(opts_def)); + if (ct) + bpf_ct_release(ct); + else + test_eafnosupport = opts_def.error; +} + +SEC("xdp") +int nf_xdp_ct_test(struct xdp_md *ctx) +{ + nf_ct_test((void *)bpf_xdp_ct_lookup, ctx); + return 0; +} + +SEC("tc") +int nf_skb_ct_test(struct __sk_buff *ctx) +{ + nf_ct_test((void *)bpf_skb_ct_lookup, ctx); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index 160ead6c67b2..07c94df13660 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c @@ -9,12 +9,15 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(struct ipv_counts), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c index 1884a5bd10f5..762671a2e90c 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c @@ -9,6 +9,8 @@ struct ipv_counts { unsigned int v6; }; +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" /* just to validate we can handle maps in multiple sections */ struct bpf_map_def SEC("maps") btf_map_legacy = { .type = BPF_MAP_TYPE_ARRAY, @@ -16,6 +18,7 @@ struct bpf_map_def SEC("maps") btf_map_legacy = { .value_size = sizeof(long long), .max_entries = 4, }; +#pragma GCC diagnostic pop BPF_ANNOTATE_KV_PAIR(btf_map_legacy, int, struct ipv_counts); diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 15e0f9945fe4..1dabb88f8cb4 100644 --- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c @@ -8,12 +8,12 @@ struct ipv_counts { unsigned int v6; }; -struct bpf_map_def SEC("maps") btf_map = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(struct ipv_counts), - .max_entries = 4, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct ipv_counts)); + __uint(max_entries, 4); +} btf_map SEC(".maps"); __attribute__((noinline)) int test_long_fname_2(void) diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index c304cd5b8cad..37aacc66cd68 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c @@ -10,12 +10,12 @@ #define NUM_CGROUP_LEVELS 4 -struct bpf_map_def SEC("maps") cgroup_ids = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u64), - .max_entries = NUM_CGROUP_LEVELS, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u64); + __uint(max_entries, NUM_CGROUP_LEVELS); +} cgroup_ids SEC(".maps"); static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level) { diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c new file mode 100644 index 000000000000..9d58d61c0dee --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_progs_query.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +SEC("sk_skb") +int prog_skb_verdict(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_msg") +int prog_skmsg_verdict(struct sk_msg_md *msg) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c index bf28814bfde5..950a70b61e74 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_edt.c +++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c @@ -17,12 +17,12 @@ #define THROTTLE_RATE_BPS (5 * 1000 * 1000) /* flow_key => last_tstamp timestamp used */ -struct bpf_map_def SEC("maps") flow_map = { - .type = BPF_MAP_TYPE_HASH, - .key_size = sizeof(uint32_t), - .value_size = sizeof(uint64_t), - .max_entries = 1, -}; +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, uint32_t); + __type(value, uint64_t); + __uint(max_entries, 1); +} flow_map SEC(".maps"); static inline int throttle_flow(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c index cd747cd93dbe..6edebce563b5 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c @@ -16,12 +16,12 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -struct bpf_map_def SEC("maps") results = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(__u32), - .value_size = sizeof(__u32), - .max_entries = 3, -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 3); +} results SEC(".maps"); static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk, void *iph, __u32 ip_size, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 199c61b7d062..53b64c999450 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -7,11 +7,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) { void *data_end = (void *)(long)xdp->data_end; void *data = (void *)(long)xdp->data; - unsigned int data_len; + int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; /* Data length determine test case */ - data_len = data_end - data; if (data_len == 54) { /* sizeof(pkt_v4) */ offset = 4096; /* test too large offset */ @@ -20,7 +19,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) } else if (data_len == 64) { offset = 128; } else if (data_len == 128) { - offset = 4096 - 256 - 320 - data_len; /* Max tail grow 3520 */ + /* Max tail grow 3520 */ + offset = 4096 - 256 - 320 - data_len; + } else if (data_len == 9000) { + offset = 10; + } else if (data_len == 9001) { + offset = 4096; } else { return XDP_ABORTED; /* No matching test */ } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c index b7448253d135..ca68c038357c 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c @@ -12,14 +12,38 @@ SEC("xdp") int _xdp_adjust_tail_shrink(struct xdp_md *xdp) { - void *data_end = (void *)(long)xdp->data_end; - void *data = (void *)(long)xdp->data; + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; int offset = 0; - if (data_end - data == 54) /* sizeof(pkt_v4) */ + switch (bpf_xdp_get_buff_len(xdp)) { + case 54: + /* sizeof(pkt_v4) */ offset = 256; /* shrink too much */ - else + break; + case 9000: + /* non-linear buff test cases */ + if (data + 1 > data_end) + return XDP_DROP; + + switch (data[0]) { + case 0: + offset = 10; + break; + case 1: + offset = 4100; + break; + case 2: + offset = 8200; + break; + default: + return XDP_DROP; + } + break; + default: offset = 20; + break; + } if (bpf_xdp_adjust_tail(xdp, 0 - offset)) return XDP_DROP; return XDP_TX; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index 58cf4345f5cc..3379d303f41a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -49,7 +49,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) void *data = (void *)(long)xdp->data; meta.ifindex = xdp->rxq->dev->ifindex; - meta.pkt_len = data_end - data; + meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp); bpf_xdp_output(xdp, &perf_buf_map, ((__u64) meta.pkt_len << 32) | BPF_F_CURRENT_CPU, diff --git a/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c new file mode 100644 index 000000000000..2a3496d8e327 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_update_frags.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <bpf/bpf_helpers.h> + +int _version SEC("version") = 1; + +SEC("xdp.frags") +int xdp_adjust_frags(struct xdp_md *xdp) +{ + __u8 *data_end = (void *)(long)xdp->data_end; + __u8 *data = (void *)(long)xdp->data; + __u8 val[16] = {}; + __u32 offset; + int err; + + if (data + sizeof(__u32) > data_end) + return XDP_DROP; + + offset = *(__u32 *)data; + err = bpf_xdp_load_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + if (val[0] != 0xaa || val[15] != 0xaa) /* marker */ + return XDP_DROP; + + val[0] = 0xbb; /* update the marker */ + val[15] = 0xbb; + err = bpf_xdp_store_bytes(xdp, offset, val, sizeof(val)); + if (err < 0) + return XDP_DROP; + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c new file mode 100644 index 000000000000..62fb7cd4d87a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +#define IFINDEX_LO 1 + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 4); +} cpu_map SEC(".maps"); + +SEC("xdp_cpumap/dummy_cm") +int xdp_dummy_cm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c index 532025057711..48007f17dfa8 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c @@ -33,4 +33,10 @@ int xdp_dummy_cm(struct xdp_md *ctx) return XDP_PASS; } +SEC("xdp.frags/cpumap") +int xdp_dummy_cm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c new file mode 100644 index 000000000000..e1caf510b7d2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_frags_helpers.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 4); +} dm_ports SEC(".maps"); + +/* valid program on DEVMAP entry via SEC name; + * has access to egress and ingress ifindex + */ +SEC("xdp_devmap/map_prog") +int xdp_dummy_dm(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 1e6b9c38ea6d..8ae11fab8316 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -40,4 +40,11 @@ int xdp_dummy_dm(struct xdp_md *ctx) return XDP_PASS; } + +SEC("xdp.frags/devmap") +int xdp_dummy_dm_frags(struct xdp_md *ctx) +{ + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index ebf68dce5504..2893e9f2f1e0 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -28,7 +28,6 @@ // 5. We can read keycode from same /dev/lirc device #include <linux/bpf.h> -#include <linux/lirc.h> #include <linux/input.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 76cd903117af..29bbaa58233c 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -31,6 +31,7 @@ #include <linux/if_ether.h> #include <linux/btf.h> +#include <bpf/btf.h> #include <bpf/bpf.h> #include <bpf/libbpf.h> @@ -66,6 +67,11 @@ static bool unpriv_disabled = false; static int skips; static bool verbose = false; +struct kfunc_btf_id_pair { + const char *kfunc; + int insn_idx; +}; + struct bpf_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -92,6 +98,7 @@ struct bpf_test { int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; int fixup_map_timer[MAX_FIXUPS]; + struct kfunc_btf_id_pair fixup_kfunc_btf_id[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -744,6 +751,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; int *fixup_map_timer = test->fixup_map_timer; + struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -936,6 +944,26 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_timer++; } while (*fixup_map_timer); } + + /* Patch in kfunc BTF IDs */ + if (fixup_kfunc_btf_id->kfunc) { + struct btf *btf; + int btf_id; + + do { + btf_id = 0; + btf = btf__load_vmlinux_btf(); + if (btf) { + btf_id = btf__find_by_name_kind(btf, + fixup_kfunc_btf_id->kfunc, + BTF_KIND_FUNC); + btf_id = btf_id < 0 ? 0 : btf_id; + } + btf__free(btf); + prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id; + fixup_kfunc_btf_id++; + } while (fixup_kfunc_btf_id->kfunc); + } } struct libcap { diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index d7b74eb28333..829be2b9e08e 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -22,6 +22,81 @@ .result = ACCEPT, }, { + "calls: invalid kfunc call: ptr_to_mem to struct with non-scalar", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail1 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail1", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with nesting depth > 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "max struct nesting depth exceeded\narg#0 pointer type STRUCT prog_test_fail2", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail2", 2 }, + }, +}, +{ + "calls: invalid kfunc call: ptr_to_mem to struct with FAM", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type STRUCT prog_test_fail3 must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_fail3", 2 }, + }, +}, +{ + "calls: invalid kfunc call: reg->type != PTR_TO_CTX", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 expected pointer to ctx, but got PTR", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_pass_ctx", 2 }, + }, +}, +{ + "calls: invalid kfunc call: void * not allowed in func proto without mem size arg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "arg#0 pointer type UNKNOWN must point to scalar", + .fixup_kfunc_btf_id = { + { "bpf_kfunc_call_test_mem_len_fail1", 2 }, + }, +}, +{ "calls: basic sanity", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 0a5d23da486d..ffa5502ad95e 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -906,7 +906,10 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) return true; case STAT_TEST_RX_FULL: xsk_stat = stats.rx_ring_full; - expected_stat -= RX_FULL_RXQSIZE; + if (ifobject->umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS) + expected_stat = ifobject->umem->num_frames - RX_FULL_RXQSIZE; + else + expected_stat = XSK_RING_PROD__DEFAULT_NUM_DESCS - RX_FULL_RXQSIZE; break; case STAT_TEST_RX_FILL_EMPTY: xsk_stat = stats.rx_fill_ring_empty_descs; diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index 31f8c9a76c5f..60ce18ed0666 100755 --- a/tools/testing/selftests/cpufreq/main.sh +++ b/tools/testing/selftests/cpufreq/main.sh @@ -194,5 +194,5 @@ prerequisite # Run requested functions clear_dumps $OUTFILE -do_test >> $OUTFILE.txt +do_test | tee -a $OUTFILE.txt dmesg_dumps $OUTFILE diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index dd61118df66e..12c5e27d32c1 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -5,7 +5,7 @@ CFLAGS += -D_GNU_SOURCE TEST_PROGS := binfmt_script non-regular TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 -TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe +TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 12631f0076a1..11e157d7533b 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -11,7 +11,7 @@ all: @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ if [ -e $$DIR/$(TEST_PROGS) ]; then \ rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ fi \ @@ -32,6 +32,6 @@ override define CLEAN @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ done endef diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 471eaa7b3a3f..11779405dc80 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) } t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); } void __wait_for_test(struct __test_metadata *t) @@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255); diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 81ebf99d6ff0..0e4926bc9a58 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -85,6 +85,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test +TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index 66775de26952..4ed6aa049a91 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -345,7 +345,6 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, * guest_code - The vCPU's entry point */ void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code); -void vm_xsave_req_perm(void); bool vm_is_unrestricted_guest(struct kvm_vm *vm); diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 423d8a61bd2e..8a470da7b71a 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -458,6 +458,7 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void); void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid); +void vm_xsave_req_perm(int bit); enum x86_page_size { X86_PAGE_SIZE_4K = 0, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8c53f96ab7fe..d8cf851ab119 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -393,13 +393,6 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, struct kvm_vm *vm; int i; -#ifdef __x86_64__ - /* - * Permission needs to be requested before KVM_SET_CPUID2. - */ - vm_xsave_req_perm(); -#endif - /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 5f9d7e91dc69..9f000dfb5594 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -665,16 +665,31 @@ static bool is_xfd_supported(void) return !!(eax & CPUID_XFD_BIT); } -void vm_xsave_req_perm(void) +void vm_xsave_req_perm(int bit) { - unsigned long bitmask; + int kvm_fd; + u64 bitmask; long rc; + struct kvm_device_attr attr = { + .group = 0, + .attr = KVM_X86_XCOMP_GUEST_SUPP, + .addr = (unsigned long) &bitmask + }; + + kvm_fd = open_kvm_dev_path_or_exit(); + rc = ioctl(kvm_fd, KVM_GET_DEVICE_ATTR, &attr); + close(kvm_fd); + if (rc == -1 && (errno == ENXIO || errno == EINVAL)) + exit(KSFT_SKIP); + TEST_ASSERT(rc == 0, "KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) error: %ld", rc); + if (!(bitmask & (1ULL << bit))) + exit(KSFT_SKIP); if (!is_xfd_supported()) - return; + exit(KSFT_SKIP); + + rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit); - rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, - XSTATE_XTILE_DATA_BIT); /* * The older kernel version(<5.15) can't support * ARCH_REQ_XCOMP_GUEST_PERM and directly return. @@ -684,7 +699,7 @@ void vm_xsave_req_perm(void) rc = syscall(SYS_arch_prctl, ARCH_GET_XCOMP_GUEST_PERM, &bitmask); TEST_ASSERT(rc == 0, "prctl(ARCH_GET_XCOMP_GUEST_PERM) error: %ld", rc); - TEST_ASSERT(bitmask & XFEATURE_XTILE_MASK, + TEST_ASSERT(bitmask & (1ULL << bit), "prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure bitmask=0x%lx", bitmask); } diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c index 523c1e99ed64..52a3ef6629e8 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86_64/amx_test.c @@ -329,6 +329,8 @@ int main(int argc, char *argv[]) u32 amx_offset; int stage, ret; + vm_xsave_req_perm(XSTATE_XTILE_DATA_BIT); + /* Create VM */ vm = vm_create_default(VCPU_ID, 0, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c index 2da8eb8e2d96..a626d40fdb48 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86_64/smm_test.c @@ -105,7 +105,6 @@ static void guest_code(void *arg) if (cpu_has_svm()) { run_guest(svm->vmcb, svm->vmcb_gpa); - svm->vmcb->save.rip += 3; run_guest(svm->vmcb, svm->vmcb_gpa); } else { vmlaunch(); diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index e54106643337..4c88238fc8f0 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -207,15 +207,21 @@ TEST(check_file_mmap) errno = 0; fd = open(".", O_TMPFILE | O_RDWR, 0600); - ASSERT_NE(-1, fd) { - TH_LOG("Can't create temporary file: %s", - strerror(errno)); + if (fd < 0) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Can't create temporary file: %s", + strerror(errno)); + } + SKIP(goto out_free, "O_TMPFILE not supported by filesystem."); } errno = 0; retval = fallocate(fd, 0, 0, FILE_SIZE); - ASSERT_EQ(0, retval) { - TH_LOG("Error allocating space for the temporary file: %s", - strerror(errno)); + if (retval) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Error allocating space for the temporary file: %s", + strerror(errno)); + } + SKIP(goto out_close, "fallocate not supported by filesystem."); } /* @@ -271,7 +277,9 @@ TEST(check_file_mmap) } munmap(addr, FILE_SIZE); +out_close: close(fd); +out_free: free(vec); } diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 43ea8407a82e..4f70baad867d 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -96,7 +96,7 @@ fib_rule6_del() fib_rule6_del_by_pref() { - pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP -6 rule show $1 table $RTABLE | cut -d ":" -f 1) $IP -6 rule del pref $pref } @@ -104,17 +104,36 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule6 check: $1" + log_test $? 0 "rule6 check: $description" fib_rule6_del_by_pref "$match" - log_test $? 0 "rule6 del by pref: $match" + log_test $? 0 "rule6 del by pref: $description" +} + +fib_rule6_test_reject() +{ + local match="$1" + local rc + + $IP -6 rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule6 check: $match" + + if [ $rc -eq 0 ]; then + $IP -6 rule del $match table $RTABLE + fi } fib_rule6_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink @@ -124,8 +143,21 @@ fib_rule6_test() match="from $SRC_IP6 iif $DEV" fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule6_test_reject "$match" + done + + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" @@ -165,7 +197,7 @@ fib_rule4_del() fib_rule4_del_by_pref() { - pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1) + pref=$($IP rule show $1 table $RTABLE | cut -d ":" -f 1) $IP rule del pref $pref } @@ -173,17 +205,36 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" + local description="$3" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" - log_test $? 0 "rule4 check: $1" + log_test $? 0 "rule4 check: $description" fib_rule4_del_by_pref "$match" - log_test $? 0 "rule4 del by pref: $match" + log_test $? 0 "rule4 del by pref: $description" +} + +fib_rule4_test_reject() +{ + local match="$1" + local rc + + $IP rule add $match table $RTABLE 2>/dev/null + rc=$? + log_test $rc 2 "rule4 check: $match" + + if [ $rc -eq 0 ]; then + $IP rule del $match table $RTABLE + fi } fib_rule4_test() { + local getmatch + local match + local cnt + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink @@ -192,14 +243,27 @@ fib_rule4_test() # need enable forwarding and disable rp_filter temporarily as all the # addresses are in the same subnet and egress device == ingress device. - ip netns exec testns sysctl -w net.ipv4.ip_forward=1 - ip netns exec testns sysctl -w net.ipv4.conf.$DEV.rp_filter=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=1 + ip netns exec testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" - ip netns exec testns sysctl -w net.ipv4.ip_forward=0 + ip netns exec testns sysctl -qw net.ipv4.ip_forward=0 + + # Reject dsfield (tos) options which have ECN bits set + for cnt in $(seq 1 3); do + match="dsfield $cnt" + fib_rule4_test_reject "$match" + done + # Don't take ECN bits into account when matching on dsfield match="tos 0x10" - fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + # Using option 'tos' instead of 'dsfield' as old iproute2 + # versions don't support 'dsfield' in ip rule show. + getmatch="tos $cnt" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getmatch redirect to table" + done match="fwmark 0x64" getmatch="mark 0x64" diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 996af1ae3d3d..bb73235976b3 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1447,6 +1447,81 @@ ipv4_local_rt_cache() log_test $? 0 "Cached route removed from VRF port device" } +ipv4_rt_dsfield() +{ + echo + echo "IPv4 route with dsfield tests" + + run_cmd "$IP route flush 172.16.102.0/24" + + # New routes should reject dsfield options that interfere with ECN + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x01 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x01" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x02 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x02" + + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x03 via 172.16.101.2" + log_test $? 2 "Reject route with dsfield 0x03" + + # A generic route that doesn't take DSCP into account + run_cmd "$IP route add 172.16.102.0/24 via 172.16.101.2" + + # A more specific route for DSCP 0x10 + run_cmd "$IP route add 172.16.102.0/24 dsfield 0x10 via 172.16.103.2" + + # DSCP 0x10 should match the specific route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \ + grep -q "via 172.16.103.2" + log_test $? 0 "IPv4 route with DSCP and ECN:CE" + + # Unknown DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE" + + # Null DSCP should match the generic route, no matter the ECN bits + $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT" + + $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)" + + $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \ + grep -q "via 172.16.101.2" + log_test $? 0 "IPv4 route with no DSCP and ECN:CE" +} + ipv4_route_test() { route_setup @@ -1454,6 +1529,7 @@ ipv4_route_test() ipv4_rt_add ipv4_rt_replace ipv4_local_rt_cache + ipv4_rt_dsfield route_cleanup } diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index b90dff8d3a94..64bd00fe9a4f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -28,8 +28,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge vlan_filtering 1 ageing_time 1000 \ + ip link add dev br0 type bridge \ + vlan_filtering 1 \ + ageing_time $LOW_AGEING_TIME \ mcast_snooping 0 ip link set dev $swp1 master br0 diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index c15c6c85c984..1c8a26046589 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -27,8 +27,9 @@ h2_destroy() switch_create() { - # 10 Seconds ageing time. - ip link add dev br0 type bridge ageing_time 1000 mcast_snooping 0 + ip link add dev br0 type bridge \ + ageing_time $LOW_AGEING_TIME \ + mcast_snooping 0 ip link set dev $swp1 master br0 ip link set dev $swp2 master br0 diff --git a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh index e134a5f529c9..1b3b46292179 100644 --- a/tools/testing/selftests/net/forwarding/fib_offload_lib.sh +++ b/tools/testing/selftests/net/forwarding/fib_offload_lib.sh @@ -99,15 +99,15 @@ fib_ipv4_tos_test() fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" false check_err $? "Route not in hardware when should" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 2 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 2 metric 1024" false + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 8 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 8 metric 1024" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0 metric 1024" true check_err $? "Lowest TOS route still in hardware when should not" - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 metric 1024 - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1 metric 1024" true + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 metric 1024 + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4 metric 1024" true check_err $? "Middle TOS route in hardware when should not" log_test "IPv4 routes with TOS" @@ -277,11 +277,11 @@ fib_ipv4_replay_tos_test() ip -n $ns link set dev dummy1 up ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 0 - ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 1 + ip -n $ns route add 192.0.2.0/24 dev dummy1 tos 4 devlink -N $ns dev reload $devlink_dev - fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 1" false + fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 4" false check_err $? "Highest TOS route not in hardware when should" fib4_trap_check $ns "192.0.2.0/24 dev dummy1 tos 0" true diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index b0980a2efa31..4a546509de90 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -41,6 +41,8 @@ NETIF_CREATE=yes # Timeout (in seconds) before ping exits regardless of how many packets have # been sent or received PING_TIMEOUT=5 +# Minimum ageing_time (in centiseconds) supported by hardware +LOW_AGEING_TIME=1000 # Flag for tc match, supposed to be skip_sw/skip_hw which means do not process # filter by software/hardware TC_FLAG=skip_hw diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7da783d6f453..e7e434a4758b 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -24,6 +24,7 @@ PING_COUNT=${PING_COUNT:=10} PING_TIMEOUT=${PING_TIMEOUT:=5} WAIT_TIMEOUT=${WAIT_TIMEOUT:=20} INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600} +LOW_AGEING_TIME=${LOW_AGEING_TIME:=1000} REQUIRE_JQ=${REQUIRE_JQ:=yes} REQUIRE_MZ=${REQUIRE_MZ:=yes} diff --git a/tools/testing/selftests/net/forwarding/pedit_ip.sh b/tools/testing/selftests/net/forwarding/pedit_ip.sh new file mode 100755 index 000000000000..d14efb2d23b2 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/pedit_ip.sh @@ -0,0 +1,201 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test sends traffic from H1 to H2. Either on ingress of $swp1, or on +# egress of $swp2, the traffic is acted upon by a pedit action. An ingress +# filter installed on $h2 verifies that the packet looks like expected. +# +# +----------------------+ +----------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +----|-----------------+ +----------------|-----+ +# | | +# +----|----------------------------------------------------------------|-----+ +# | SW | | | +# | +-|----------------------------------------------------------------|-+ | +# | | + $swp1 BR $swp2 + | | +# | +--------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + test_ip4_src + test_ip4_dst + test_ip6_src + test_ip6_dst +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 2001:db8:1::2/64 + tc qdisc add dev $h2 clsact +} + +h2_destroy() +{ + tc qdisc del dev $h2 clsact + simple_if_fini $h2 192.0.2.2/28 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add name br1 up type bridge vlan_filtering 1 + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + 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 $swp2 nomaster + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h2mac=$(mac_get $h2) + + vrf_prepare + h1_create + h2_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h2_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +do_test_pedit_ip() +{ + local pedit_locus=$1; shift + local pedit_action=$1; shift + local match_prot=$1; shift + local match_flower=$1; shift + local mz_flags=$1; shift + + tc filter add $pedit_locus handle 101 pref 1 \ + flower action pedit ex munge $pedit_action + tc filter add dev $h2 ingress handle 101 pref 1 prot $match_prot \ + flower skip_hw $match_flower action pass + + RET=0 + + $MZ $mz_flags $h1 -c 10 -d 20msec -p 100 -a own -b $h2mac -q -t ip + + local pkts + pkts=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= 10" \ + tc_rule_handle_stats_get "dev $h2 ingress" 101) + check_err $? "Expected to get 10 packets, but got $pkts." + + pkts=$(tc_rule_handle_stats_get "$pedit_locus" 101) + ((pkts >= 10)) + check_err $? "Expected to get 10 packets on pedit rule, but got $pkts." + + log_test "$pedit_locus pedit $pedit_action" + + tc filter del dev $h2 ingress pref 1 + tc filter del $pedit_locus pref 1 +} + +do_test_pedit_ip6() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 2001:db8:2::1" ipv6 \ + "$flower_addr 2001:db8:2::1" \ + "-6 -A 2001:db8:1::1 -B 2001:db8:1::2" +} + +do_test_pedit_ip4() +{ + local locus=$1; shift + local pedit_addr=$1; shift + local flower_addr=$1; shift + + do_test_pedit_ip "$locus" "$pedit_addr set 198.51.100.1" ip \ + "$flower_addr 198.51.100.1" \ + "-A 192.0.2.1 -B 192.0.2.2" +} + +test_ip4_src() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip src" src_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip src" src_ip +} + +test_ip4_dst() +{ + do_test_pedit_ip4 "dev $swp1 ingress" "ip dst" dst_ip + do_test_pedit_ip4 "dev $swp2 egress" "ip dst" dst_ip +} + +test_ip6_src() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 src" src_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 src" src_ip +} + +test_ip6_dst() +{ + do_test_pedit_ip6 "dev $swp1 ingress" "ip6 dst" dst_ip + do_test_pedit_ip6 "dev $swp2 egress" "ip6 dst" dst_ip +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index 8f6997d35816..d9d1d4190126 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -240,11 +240,8 @@ static int check_ioam6_data(__u8 **p, struct ioam6_trace_hdr *ioam6h, *p += sizeof(__u32); } - if (ioam6h->type.bit6) { - if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) - return 1; + if (ioam6h->type.bit6) *p += sizeof(__u32); - } if (ioam6h->type.bit7) { if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 27d0eb9afdca..4a565fb84137 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -15,6 +15,7 @@ timeout_test=$((timeout_poll * 2 + 1)) mptcp_connect="" capture=0 checksum=0 +ip_mptcp=0 do_all_tests=1 TEST_COUNT=0 @@ -75,6 +76,7 @@ init() # let $ns2 reach any $ns1 address from any interface ip -net "$ns2" route add default via 10.0.$i.1 dev ns2eth$i metric 10$i + ip -net "$ns2" route add default via dead:beef:$i::1 dev ns2eth$i metric 10$i done } @@ -238,6 +240,16 @@ is_v6() [ -z "${1##*:*}" ] } +is_addr() +{ + [ -z "${1##*[.:]*}" ] +} + +is_number() +{ + [[ $1 == ?(-)+([0-9]) ]] +} + # $1: ns, $2: port wait_local_port_listen() { @@ -277,6 +289,109 @@ wait_rm_addr() done } +pm_nl_set_limits() +{ + local ns=$1 + local addrs=$2 + local subflows=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp limits set add_addr_accepted $addrs subflows $subflows + else + ip netns exec $ns ./pm_nl_ctl limits $addrs $subflows + fi +} + +pm_nl_add_endpoint() +{ + local ns=$1 + local addr=$2 + local flags + local port + local dev + local id + local nr=2 + + for p in $@ + do + if [ $p = "flags" ]; then + eval _flags=\$"$nr" + [ ! -z $_flags ]; flags="flags $_flags" + fi + if [ $p = "dev" ]; then + eval _dev=\$"$nr" + [ ! -z $_dev ]; dev="dev $_dev" + fi + if [ $p = "id" ]; then + eval _id=\$"$nr" + [ ! -z $_id ]; id="id $_id" + fi + if [ $p = "port" ]; then + eval _port=\$"$nr" + [ ! -z $_port ]; port="port $_port" + fi + + let nr+=1 + done + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint add $addr ${_flags//","/" "} $dev $id $port + else + ip netns exec $ns ./pm_nl_ctl add $addr $flags $dev $id $port + fi +} + +pm_nl_del_endpoint() +{ + local ns=$1 + local id=$2 + local addr=$3 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint delete id $id $addr + else + ip netns exec $ns ./pm_nl_ctl del $id $addr + fi +} + +pm_nl_flush_endpoint() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint flush + else + ip netns exec $ns ./pm_nl_ctl flush + fi +} + +pm_nl_show_endpoints() +{ + local ns=$1 + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint show + else + ip netns exec $ns ./pm_nl_ctl dump + fi +} + +pm_nl_change_endpoint() +{ + local ns=$1 + local flags=$2 + local id=$3 + local addr=$4 + local port="" + + if [ $ip_mptcp -eq 1 ]; then + ip -n $ns mptcp endpoint change id $id ${flags//","/" "} + else + if [ $5 -ne 0 ]; then port="port $5"; fi + ip netns exec $ns ./pm_nl_ctl set $addr flags $flags $port + fi +} + do_transfer() { listener_ns="$1" @@ -288,7 +403,7 @@ do_transfer() addr_nr_ns1="$7" addr_nr_ns2="$8" speed="$9" - bkup="${10}" + sflags="${10}" port=$((10000+$TEST_COUNT)) TEST_COUNT=$((TEST_COUNT+1)) @@ -377,31 +492,36 @@ do_transfer() else addr="10.0.$counter.1" fi - ip netns exec $ns1 ./pm_nl_ctl add $addr flags signal + pm_nl_add_endpoint $ns1 $addr flags signal let counter+=1 let add_nr_ns1-=1 done elif [ $addr_nr_ns1 -lt 0 ]; then let rm_nr_ns1=-addr_nr_ns1 if [ $rm_nr_ns1 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${listener_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns1 ] - do - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${connector_ns}) - ip netns exec ${listener_ns} ./pm_nl_ctl del $id - wait_rm_addr ${connector_ns} ${rm_addr} - let counter+=1 - let pos+=5 + counter=0 + pm_nl_show_endpoints ${listener_ns} | while read line; do + local arr=($line) + local nr=0 + + for i in ${arr[@]}; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns1 ]; then + break + fi + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${connector_ns}) + pm_nl_del_endpoint ${listener_ns} $id + wait_rm_addr ${connector_ns} ${rm_addr} + let counter+=1 + fi + let nr+=1 done - fi + done elif [ $rm_nr_ns1 -eq 8 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${listener_ns} elif [ $rm_nr_ns1 -eq 9 ]; then - ip netns exec ${listener_ns} ./pm_nl_ctl del 0 ${connect_addr} + pm_nl_del_endpoint ${listener_ns} 0 ${connect_addr} fi fi @@ -425,30 +545,36 @@ do_transfer() else addr="10.0.$counter.2" fi - ip netns exec $ns2 ./pm_nl_ctl add $addr flags $flags + pm_nl_add_endpoint $ns2 $addr flags $flags let counter+=1 let add_nr_ns2-=1 done elif [ $addr_nr_ns2 -lt 0 ]; then let rm_nr_ns2=-addr_nr_ns2 if [ $rm_nr_ns2 -lt 8 ]; then - counter=1 - pos=1 - dump=(`ip netns exec ${connector_ns} ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - while [ $counter -le $rm_nr_ns2 ] - do - # rm_addr are serialized, allow the previous one to complete - id=${dump[$pos]} - rm_addr=$(rm_addr_count ${listener_ns}) - ip netns exec ${connector_ns} ./pm_nl_ctl del $id - wait_rm_addr ${listener_ns} ${rm_addr} - let counter+=1 - let pos+=5 + counter=0 + pm_nl_show_endpoints ${connector_ns} | while read line; do + local arr=($line) + local nr=0 + + for i in ${arr[@]}; do + if [ $i = "id" ]; then + if [ $counter -eq $rm_nr_ns2 ]; then + break + fi + # rm_addr are serialized, allow the previous one to + # complete + id=${arr[$nr+1]} + rm_addr=$(rm_addr_count ${listener_ns}) + pm_nl_del_endpoint ${connector_ns} $id + wait_rm_addr ${listener_ns} ${rm_addr} + let counter+=1 + fi + let nr+=1 done - fi + done elif [ $rm_nr_ns2 -eq 8 ]; then - ip netns exec ${connector_ns} ./pm_nl_ctl flush + pm_nl_flush_endpoint ${connector_ns} elif [ $rm_nr_ns2 -eq 9 ]; then local addr if is_v6 "${connect_addr}"; then @@ -456,19 +582,34 @@ do_transfer() else addr="10.0.1.2" fi - ip netns exec ${connector_ns} ./pm_nl_ctl del 0 $addr + pm_nl_del_endpoint ${connector_ns} 0 $addr fi fi - if [ ! -z $bkup ]; then + if [ ! -z $sflags ]; then sleep 1 for netns in "$ns1" "$ns2"; do - dump=(`ip netns exec $netns ./pm_nl_ctl dump`) - if [ ${#dump[@]} -gt 0 ]; then - addr=${dump[${#dump[@]} - 1]} - backup="ip netns exec $netns ./pm_nl_ctl set $addr flags $bkup" - $backup - fi + pm_nl_show_endpoints $netns | while read line; do + local arr=($line) + local addr + local port=0 + local id + + for i in ${arr[@]}; do + if is_addr $i; then + addr=$i + elif is_number $i; then + # The minimum expected port number is 10000 + if [ $i -gt 10000 ]; then + port=$i + # The maximum id number is 255 + elif [ $i -lt 255 ]; then + id=$i + fi + fi + done + pm_nl_change_endpoint $netns $sflags $id $addr $port + done done fi @@ -544,7 +685,7 @@ run_tests() addr_nr_ns1="${5:-0}" addr_nr_ns2="${6:-0}" speed="${7:-fast}" - bkup="${8:-""}" + sflags="${8:-""}" lret=0 oldin="" @@ -573,7 +714,7 @@ run_tests() fi do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ - ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${bkup} + ${test_linkfail} ${addr_nr_ns1} ${addr_nr_ns2} ${speed} ${sflags} lret=$? } @@ -977,51 +1118,51 @@ subflows_tests() # subflow limited by client reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by client" 0 0 0 # subflow limited by server reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 0 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, limited by server" 1 1 0 # subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow" 1 1 1 # multiple subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows" 2 2 2 # multiple subflows limited by server reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows, limited by server" 2 2 1 # single subflow, dev reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow dev ns2eth3 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow, dev" 1 1 1 } @@ -1031,28 +1172,28 @@ subflows_error_tests() # If a single subflow is configured, and matches the MPC src # address, no additional subflow should be created reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "no MPC reuse with single endpoint" 0 0 0 # multiple subflows, with subflow creation error reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "multi subflows, with failing subflow" 1 1 1 # multiple subflows, with subflow timeout on MPJ reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "multi subflows, with subflow timeout" 1 1 1 @@ -1061,9 +1202,9 @@ subflows_error_tests() # closed subflow (due to reset) is not reused if additional # subflows are added later reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & @@ -1073,7 +1214,7 @@ subflows_error_tests() # mpj subflow will be in TW after the reset wait_for_tw $ns2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow wait # additional subflow could be created only if the PM select @@ -1085,16 +1226,16 @@ signal_address_tests() { # add_address, unused reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "unused signal address" 0 0 0 chk_add_nr 1 1 # accept and use add_addr reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address" 1 1 1 chk_add_nr 1 1 @@ -1104,59 +1245,59 @@ signal_address_tests() # belong to different subnets or one of the listed local address could be # used for 'add_addr' subflow reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal" 2 2 2 chk_add_nr 1 1 # accept and use add_addr with additional subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 chk_add_nr 1 1 # signal addresses reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal addresses" 3 3 3 chk_add_nr 3 3 # signal invalid addresses reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal invalid addresses" 1 1 1 chk_add_nr 3 3 # signal addresses race test reset - ip netns exec $ns1 ./pm_nl_ctl limits 4 4 - ip netns exec $ns2 ./pm_nl_ctl limits 4 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.1.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal run_tests $ns1 $ns2 10.0.1.1 # the server will not signal the address terminating @@ -1176,11 +1317,11 @@ link_failure_tests() # active backup and link switch-over. # Let's set some arbitrary (low) virtual link limits. init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "multiple flows, signal, link failure" 3 3 3 chk_add_nr 1 1 @@ -1190,11 +1331,11 @@ link_failure_tests() # for bidirectional transfer reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 dev ns2eth4 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 chk_add_nr 1 1 @@ -1204,11 +1345,11 @@ link_failure_tests() # will never be used reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 export FAILING_LINKS="1" - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "backup subflow unused, link failure" 2 2 2 chk_add_nr 1 1 @@ -1218,10 +1359,10 @@ link_failure_tests() # the traffic reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup export FAILING_LINKS="1 2" run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr "backup flow used, multi links fail" 2 2 2 @@ -1233,10 +1374,10 @@ link_failure_tests() # for bidirectional transfer reset init_shapers - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 dev ns2eth3 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr "backup flow used, bidi, link failure" 2 2 2 chk_add_nr 1 1 @@ -1248,38 +1389,38 @@ add_addr_timeout_tests() { # add_addr timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 chk_add_nr 4 0 # add_addr timeout IPv6 reset_with_add_addr_timeout 6 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1 chk_add_nr 4 0 # signal addresses timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 0 0 0 least chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2 chk_add_nr 8 0 # signal invalid addresses timeout reset_with_add_addr_timeout - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 0 0 0 least chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1 chk_add_nr 8 0 @@ -1289,28 +1430,28 @@ remove_tests() { # single subflow, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow chk_join_nr "remove single subflow" 1 1 1 chk_rm_nr 1 1 # multiple subflows, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow chk_join_nr "remove multiple subflows" 2 2 2 chk_rm_nr 2 2 # single address, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow chk_join_nr "remove single address" 1 1 1 chk_add_nr 1 1 @@ -1318,10 +1459,10 @@ remove_tests() # subflow and signal, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow chk_join_nr "remove subflow and signal" 2 2 2 chk_add_nr 1 1 @@ -1329,11 +1470,11 @@ remove_tests() # subflows and signal, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow chk_join_nr "remove subflows and signal" 3 3 3 chk_add_nr 1 1 @@ -1341,11 +1482,11 @@ remove_tests() # addresses remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow chk_join_nr "remove addresses" 3 3 3 chk_add_nr 3 3 @@ -1353,11 +1494,11 @@ remove_tests() # invalid addresses remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow chk_join_nr "remove invalid addresses" 1 1 1 chk_add_nr 3 3 @@ -1365,11 +1506,11 @@ remove_tests() # subflows and signal, flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush subflows and signal" 3 3 3 chk_add_nr 1 1 @@ -1377,22 +1518,22 @@ remove_tests() # subflows flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow id 150 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush subflows" 3 3 3 chk_rm_nr 3 3 # addresses flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal id 250 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.4.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow chk_join_nr "flush addresses" 3 3 3 chk_add_nr 3 3 @@ -1400,11 +1541,11 @@ remove_tests() # invalid addresses flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 3 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.12.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl add 10.0.14.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 3 3 + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow chk_join_nr "flush invalid addresses" 1 1 1 chk_add_nr 3 3 @@ -1412,18 +1553,18 @@ remove_tests() # remove id 0 subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow chk_join_nr "remove id 0 subflow" 1 1 1 chk_rm_nr 1 1 # remove id 0 address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow chk_join_nr "remove id 0 address" 1 1 1 chk_add_nr 1 1 @@ -1434,37 +1575,37 @@ add_tests() { # add single subflow reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow chk_join_nr "add single subflow" 1 1 1 # add signal address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow chk_join_nr "add signal address" 1 1 1 chk_add_nr 1 1 # add multiple subflows reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow chk_join_nr "add multiple subflows" 2 2 2 # add multiple subflows IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow chk_join_nr "add multiple subflows IPv6" 2 2 2 # add multiple addresses IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow chk_join_nr "add multiple addresses IPv6" 2 2 2 chk_add_nr 2 2 @@ -1474,33 +1615,33 @@ ipv6_tests() { # subflow IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "single subflow IPv6" 1 1 1 # add_address, unused IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "unused signal address IPv6" 0 0 0 chk_add_nr 1 1 # signal address IPv6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow chk_join_nr "single address IPv6" 1 1 1 chk_add_nr 1 1 # single address IPv6, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow chk_join_nr "remove single address IPv6" 1 1 1 chk_add_nr 1 1 @@ -1508,10 +1649,10 @@ ipv6_tests() # subflow and signal IPv6, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow chk_join_nr "remove subflow and signal IPv6" 2 2 2 chk_add_nr 1 1 @@ -1522,76 +1663,76 @@ v4mapped_tests() { # subflow IPv4-mapped to IPv4-mapped reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "single subflow IPv4-mapped" 1 1 1 # signal address IPv4-mapped with IPv4-mapped sk reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "signal address IPv4-mapped" 1 1 1 chk_add_nr 1 1 # subflow v4-map-v6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "single subflow v4-map-v6" 1 1 1 # signal address v4-map-v6 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 "::ffff:10.0.1.1" chk_join_nr "signal address v4-map-v6" 1 1 1 chk_add_nr 1 1 # subflow v6-map-v4 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add "::ffff:10.0.3.2" flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow v6-map-v4" 1 1 1 # signal address v6-map-v4 reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add "::ffff:10.0.2.1" flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address v6-map-v4" 1 1 1 chk_add_nr 1 1 # no subflow IPv6 to v4 address reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "no JOIN with diff families v4-v6" 0 0 0 # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add dead:beef:2::10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "no JOIN with diff families v4-v6-2" 0 0 0 # no subflow IPv4 to v6 address, no need to slow down too then reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 dead:beef:1::1 chk_join_nr "no JOIN with diff families v6-v4" 0 0 0 } @@ -1600,50 +1741,60 @@ backup_tests() { # single subflow, backup reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,backup + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup chk_join_nr "single subflow, backup" 1 1 1 chk_prio_nr 0 1 # single address, backup reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup chk_join_nr "single address, backup" 1 1 1 chk_add_nr 1 1 chk_prio_nr 1 0 + + # single address with port, backup + reset + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr "single address with port, backup" 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 0 } add_addr_ports_tests() { # signal address with port reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address with port" 1 1 1 chk_add_nr 1 1 1 # subflow and signal with port reset - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal with port" 2 2 2 chk_add_nr 1 1 1 # single address with port, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow chk_join_nr "remove single address with port" 1 1 1 chk_add_nr 1 1 1 @@ -1651,10 +1802,10 @@ add_addr_ports_tests() # subflow and signal with port, remove reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow chk_join_nr "remove subflow and signal with port" 2 2 2 chk_add_nr 1 1 1 @@ -1662,11 +1813,11 @@ add_addr_ports_tests() # subflows and signal with port, flush reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow chk_join_nr "flush subflows and signal with port" 3 3 3 chk_add_nr 1 1 @@ -1674,20 +1825,20 @@ add_addr_ports_tests() # multiple addresses with port reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10100 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple addresses with port" 2 2 2 chk_add_nr 2 2 2 # multiple addresses with ports reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal port 10100 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.3.1 flags signal port 10101 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple addresses with ports" 2 2 2 chk_add_nr 2 2 2 @@ -1697,56 +1848,56 @@ syncookies_tests() { # single subflow, syncookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow with syn cookies" 1 1 1 # multiple subflows with syn cookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows with syn cookies" 2 2 2 # multiple subflows limited by server reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflows limited by server w cookies" 2 1 1 # test signal address with cookies reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address with syn cookies" 1 1 1 chk_add_nr 1 1 # test cookie with subflow and signal reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns1 ./pm_nl_ctl limits 0 2 - ip netns exec $ns2 ./pm_nl_ctl limits 1 2 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and signal w cookies" 2 2 2 chk_add_nr 1 1 # accept and use add_addr with additional subflows reset_with_cookies - ip netns exec $ns1 ./pm_nl_ctl limits 0 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow - ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflows and signal w. cookies" 3 3 3 chk_add_nr 1 1 @@ -1756,29 +1907,29 @@ checksum_tests() { # checksum test 0 0 reset_with_checksum 0 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 0 0" # checksum test 1 1 reset_with_checksum 1 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 1 1" # checksum test 0 1 reset_with_checksum 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 0 1" # checksum test 1 0 reset_with_checksum 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 0 1 - ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 run_tests $ns1 $ns2 10.0.1.1 chk_csum_nr "checksum test 1 0" } @@ -1787,26 +1938,26 @@ deny_join_id0_tests() { # subflow allow join id0 ns1 reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow allow join id0 ns1" 1 1 1 # subflow allow join id0 ns2 reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "single subflow allow join id0 ns2" 0 0 0 # signal address allow join id0 ns1 # ADD_ADDRs are not affected by allow_join_id0 value. reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address allow join id0 ns1" 1 1 1 chk_add_nr 1 1 @@ -1814,28 +1965,28 @@ deny_join_id0_tests() # signal address allow join id0 ns2 # ADD_ADDRs are not affected by allow_join_id0 value. reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 1 1 - ip netns exec $ns2 ./pm_nl_ctl limits 1 1 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "signal address allow join id0 ns2" 1 1 1 chk_add_nr 1 1 # subflow and address allow join id0 ns1 reset_with_allow_join_id0 1 0 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and address allow join id0 1" 2 2 2 # subflow and address allow join id0 ns2 reset_with_allow_join_id0 0 1 - ip netns exec $ns1 ./pm_nl_ctl limits 2 2 - ip netns exec $ns2 ./pm_nl_ctl limits 2 2 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "subflow and address allow join id0 2" 1 1 1 } @@ -1846,10 +1997,10 @@ fullmesh_tests() # 2 fullmesh addrs in ns2, added before the connection, # 1 non-fullmesh addr in ns1, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 0 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow,fullmesh - ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow,fullmesh + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow chk_join_nr "fullmesh test 2x1" 4 4 4 chk_add_nr 1 1 @@ -1858,9 +2009,9 @@ fullmesh_tests() # 1 non-fullmesh addr in ns1, added before the connection, # 1 fullmesh addr in ns2, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 1 3 - ip netns exec $ns2 ./pm_nl_ctl limits 1 3 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow chk_join_nr "fullmesh test 1x1" 3 3 3 chk_add_nr 1 1 @@ -1869,9 +2020,9 @@ fullmesh_tests() # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection. reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 5 - ip netns exec $ns2 ./pm_nl_ctl limits 1 5 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow chk_join_nr "fullmesh test 1x2" 5 5 5 chk_add_nr 1 1 @@ -1881,12 +2032,50 @@ fullmesh_tests() # 2 fullmesh addrs in ns2, added during the connection, # limit max_subflows to 4. reset - ip netns exec $ns1 ./pm_nl_ctl limits 2 4 - ip netns exec $ns2 ./pm_nl_ctl limits 1 4 - ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow chk_join_nr "fullmesh test 1x2, limited" 4 4 4 chk_add_nr 1 1 + + # set fullmesh flag + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr "set fullmesh flag test" 2 2 2 + chk_rm_nr 0 1 + + # set nofullmesh flag + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr "set nofullmesh flag test" 2 2 2 + chk_rm_nr 0 1 + + # set backup,fullmesh flags + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr "set backup,fullmesh flags test" 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + + # set nobackup,nofullmesh flags + reset + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr "set nobackup,nofullmesh flags test" 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 } all_tests() @@ -1928,6 +2117,7 @@ usage() echo " -m fullmesh_tests" echo " -c capture pcap files" echo " -C enable data checksum" + echo " -i use ip mptcp" echo " -h help" } @@ -1949,9 +2139,12 @@ for arg in "$@"; do if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then checksum=1 fi + if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"i"[0-9a-zA-Z]*$ ]]; then + ip_mptcp=1 + fi - # exception for the capture/checksum options, the rest means: a part of the tests - if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then + # exception for the capture/checksum/ip_mptcp options, the rest means: a part of the tests + if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ] && [ "${arg}" != "-i" ]; then do_all_tests=0 fi done @@ -1961,7 +2154,7 @@ if [ $do_all_tests -eq 1 ]; then exit $ret fi -while getopts 'fesltra64bpkdmchCS' opt; do +while getopts 'fesltra64bpkdmchCSi' opt; do case $opt in f) subflows_tests @@ -2012,6 +2205,8 @@ while getopts 'fesltra64bpkdmchCS' opt; do ;; C) ;; + i) + ;; h | *) usage ;; diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index cbacf9f6538b..89839d1ff9d8 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -164,4 +164,22 @@ id 253 flags 10.0.0.5 id 254 flags 10.0.0.2 id 255 flags 10.0.0.3" "wrap-around ids" +ip netns exec $ns1 ./pm_nl_ctl flush +ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1 flags subflow +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags backup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup 10.0.1.1" "set flags (backup)" +ip netns exec $ns1 ./pm_nl_ctl set 10.0.1.1 flags nobackup +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nobackup)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,fullmesh 10.0.1.1" " (fullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags nofullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow 10.0.1.1" " (nofullmesh)" +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh +check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ +subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" + exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 354784512748..22a5ec1e128e 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -28,7 +28,7 @@ static void syntax(char *argv[]) fprintf(stderr, "\tadd [flags signal|subflow|backup|fullmesh] [id <nr>] [dev <name>] <ip>\n"); fprintf(stderr, "\tdel <id> [<ip>]\n"); fprintf(stderr, "\tget <id>\n"); - fprintf(stderr, "\tset <ip> [flags backup|nobackup]\n"); + fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n"); fprintf(stderr, "\tflush\n"); fprintf(stderr, "\tdump\n"); fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n"); @@ -657,8 +657,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) u_int32_t flags = 0; u_int16_t family; int nest_start; + int use_id = 0; + u_int8_t id; int off = 0; - int arg; + int arg = 2; memset(data, 0, sizeof(data)); nh = (void *)data; @@ -674,29 +676,45 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) nest->rta_len = RTA_LENGTH(0); off += NLMSG_ALIGN(nest->rta_len); - /* addr data */ - rta = (void *)(data + off); - if (inet_pton(AF_INET, argv[2], RTA_DATA(rta))) { - family = AF_INET; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; - rta->rta_len = RTA_LENGTH(4); - } else if (inet_pton(AF_INET6, argv[2], RTA_DATA(rta))) { - family = AF_INET6; - rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; - rta->rta_len = RTA_LENGTH(16); + if (!strcmp(argv[arg], "id")) { + if (++arg >= argc) + error(1, 0, " missing id value"); + + use_id = 1; + id = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_ID; + rta->rta_len = RTA_LENGTH(1); + memcpy(RTA_DATA(rta), &id, 1); + off += NLMSG_ALIGN(rta->rta_len); } else { - error(1, errno, "can't parse ip %s", argv[2]); + /* addr data */ + rta = (void *)(data + off); + if (inet_pton(AF_INET, argv[arg], RTA_DATA(rta))) { + family = AF_INET; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4; + rta->rta_len = RTA_LENGTH(4); + } else if (inet_pton(AF_INET6, argv[arg], RTA_DATA(rta))) { + family = AF_INET6; + rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6; + rta->rta_len = RTA_LENGTH(16); + } else { + error(1, errno, "can't parse ip %s", argv[arg]); + } + off += NLMSG_ALIGN(rta->rta_len); + + /* family */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &family, 2); + off += NLMSG_ALIGN(rta->rta_len); } - off += NLMSG_ALIGN(rta->rta_len); - /* family */ - rta = (void *)(data + off); - rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY; - rta->rta_len = RTA_LENGTH(2); - memcpy(RTA_DATA(rta), &family, 2); - off += NLMSG_ALIGN(rta->rta_len); + if (++arg >= argc) + error(1, 0, " missing flags keyword"); - for (arg = 3; arg < argc; arg++) { + for (; arg < argc; arg++) { if (!strcmp(argv[arg], "flags")) { char *tok, *str; @@ -704,12 +722,14 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) if (++arg >= argc) error(1, 0, " missing flags value"); - /* do not support flag list yet */ for (str = argv[arg]; (tok = strtok(str, ",")); str = NULL) { if (!strcmp(tok, "backup")) flags |= MPTCP_PM_ADDR_FLAG_BACKUP; - else if (strcmp(tok, "nobackup")) + else if (!strcmp(tok, "fullmesh")) + flags |= MPTCP_PM_ADDR_FLAG_FULLMESH; + else if (strcmp(tok, "nobackup") && + strcmp(tok, "nofullmesh")) error(1, errno, "unknown flag %s", argv[arg]); } @@ -719,6 +739,21 @@ int set_flags(int fd, int pm_family, int argc, char *argv[]) rta->rta_len = RTA_LENGTH(4); memcpy(RTA_DATA(rta), &flags, 4); off += NLMSG_ALIGN(rta->rta_len); + } else if (!strcmp(argv[arg], "port")) { + u_int16_t port; + + if (use_id) + error(1, 0, " port can't be used with id"); + + if (++arg >= argc) + error(1, 0, " missing port value"); + + port = atoi(argv[arg]); + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT; + rta->rta_len = RTA_LENGTH(2); + memcpy(RTA_DATA(rta), &port, 2); + off += NLMSG_ALIGN(rta->rta_len); } else { error(1, 0, "unknown keyword %s", argv[arg]); } diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index c9ce3dfa42ee..0900c5438fbb 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -216,9 +216,9 @@ kci_test_route_get() check_err $? ip route get fe80::1 dev "$devdummy" > /dev/null check_err $? - ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x10 mark 0x1 > /dev/null check_err $? - ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + ip route get ::1 from ::1 iif lo oif lo tos 0x10 mark 0x1 > /dev/null check_err $? ip addr add dev "$devdummy" 10.23.7.11/24 check_err $? diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index aee631c5284e..044bc0e9ed81 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -325,8 +325,8 @@ int main(int argc, char **argv) struct ifreq device; struct ifreq hwtstamp; struct hwtstamp_config hwconfig, hwconfig_requested; - struct so_timestamping so_timestamping_get = { 0, -1 }; - struct so_timestamping so_timestamping = { 0, -1 }; + struct so_timestamping so_timestamping_get = { 0, 0 }; + struct so_timestamping so_timestamping = { 0, 0 }; struct sockaddr_in addr; struct ip_mreq imr; struct in_addr iaddr; diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index ed61f6cab60f..df322e47a54f 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add" +BUGS="flush_remove_add reload" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -354,6 +354,23 @@ TYPE_flush_remove_add=" display Add two elements, flush, re-add " +TYPE_reload=" +display net,mac with reload +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 1 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() { nft flush ruleset } +# - add ranged element, check that packets match it +# - reload the set, check packets still match +test_bug_reload() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + rstart=${start} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + # check kernel does allocate pcpu sctrach map + # for reload with no elemet add/delete + ( echo flush set inet filter test ; + nft list set inet filter test ) | nft -f - + + start=${rstart} + range_size=1 + + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset +} + test_reported_issues() { eval test_bug_"${subtest}" } diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 349a319a9e51..79fe627b9e81 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -899,6 +899,144 @@ EOF ip netns exec "$ns0" nft delete table $family nat } +test_stateless_nat_ip() +{ + local lret=0 + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules" + return 1 + fi + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table ip stateless { + map xlate_in { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2, + } + } + map xlate_out { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99 + } + } + + chain prerouting { + type filter hook prerouting priority -400; policy accept; + ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in + ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add ip statless rules" + return $ksft_skip + fi + + reset_counters + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules" + lret=1 + fi + + # ns1 should have seen packets from .2.2, due to stateless rewrite. + expect="packets 1 bytes 84" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 1" + lret=1 + fi + + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3" + lret=1 + fi + + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4" + lret=1 + fi + done + + reset_counters + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run stateless nat frag test without socat tool" + if [ $lret -eq 0 ]; then + return $ksft_skip + fi + + ip netns exec "$ns0" nft delete table ip stateless + return $lret + fi + + local tmpfile=$(mktemp) + dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null + + local outfile=$(mktemp) + ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null & + sc_r=$! + + sleep 1 + # re-do with large ping -> ip fragmentation + ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null + if [ $? -ne 0 ] ; then + echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2 + lret=1 + fi + + wait + + cmp "$tmpfile" "$outfile" + if [ $? -ne 0 ]; then + ls -l "$tmpfile" "$outfile" + echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2 + lret=1 + fi + + rm -f "$tmpfile" "$outfile" + + # ns1 should have seen packets from 2.2, due to stateless rewrite. + expect="packets 3 bytes 4164" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 5" + lret=1 + fi + + ip netns exec "$ns0" nft delete table ip stateless + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete table ip stateless" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP statless for $ns2" + + return $lret +} + # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF @@ -965,6 +1103,19 @@ table inet filter { EOF done +# special case for stateless nat check, counter needs to +# be done before (input) ip defragmentation +ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF +table inet filter { + counter ns0insl {} + + chain pre { + type filter hook prerouting priority -400; policy accept; + ip saddr 10.0.2.2 counter name "ns0insl" + } +} +EOF + sleep 3 # test basic connectivity for i in 1 2; do @@ -1019,6 +1170,7 @@ $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet test_port_shadowing +test_stateless_nat_ip if [ $ret -ne 0 ];then echo -n "FAIL: " diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index 04633119b29a..5a8db0b48928 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -9,7 +9,7 @@ ns="ns-$sfx" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -zones=20000 +zones=2000 have_ct_tool=0 ret=0 @@ -75,10 +75,10 @@ EOF while [ $i -lt $max_zones ]; do local start=$(date +%s%3N) - i=$((i + 10000)) + i=$((i + 1000)) j=$((j + 1)) # nft rule in output places each packet in a different zone. - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 + dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break @@ -86,7 +86,7 @@ EOF stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)" done if [ $have_ct_tool -eq 1 ]; then @@ -128,11 +128,11 @@ test_conntrack_tool() { break fi - if [ $((i%10000)) -eq 0 ];then + if [ $((i%1000)) -eq 0 ];then stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total)" + echo "PASS: added 1000 entries in $duration ms (now $i total)" start=$stop fi done diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 4b93b1417b86..843ba56d8e49 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk -$(TEST_GEN_PROGS): helpers.c +$(TEST_GEN_PROGS): helpers.c helpers.h diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index a6ea27344db2..7056340b9339 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -9,6 +9,7 @@ #define _GNU_SOURCE #include <stdint.h> +#include <stdbool.h> #include <errno.h> #include <linux/types.h> #include "../kselftest.h" @@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how); (similar to chroot(2)). */ #endif /* RESOLVE_IN_ROOT */ -#define E_func(func, ...) \ - do { \ - if (func(__VA_ARGS__) < 0) \ - ksft_exit_fail_msg("%s:%d %s failed\n", \ - __FILE__, __LINE__, #func);\ +#define E_func(func, ...) \ + do { \ + errno = 0; \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \ + __FILE__, __LINE__, #func, errno); \ } while (0) #define E_asprintf(...) E_func(asprintf, __VA_ARGS__) diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 1bddbe934204..7fb902099de4 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -259,6 +259,16 @@ void test_openat2_flags(void) unlink(path); fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + ksft_test_result_skip("openat2 with %s fails with %d (%s)\n", + test->name, fd, strerror(-fd)); + goto next; + } + if (test->err >= 0) failed = (fd < 0); else @@ -303,7 +313,7 @@ skip: else resultfn("openat2 with %s fails with %d (%s)\n", test->name, test->err, strerror(-test->err)); - +next: free(fdpath); fflush(stdout); } diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings index ba4d85f74cd6..a953c96aa16e 100644 --- a/tools/testing/selftests/rtc/settings +++ b/tools/testing/selftests/rtc/settings @@ -1 +1 @@ -timeout=90 +timeout=180 diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 3d603f1394af..883ca85424bc 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts); typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts); typedef time_t (*vdso_time_t)(time_t *t); -static int vdso_test_gettimeofday(void) +#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__ +#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x +#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x + +static void vdso_test_gettimeofday(void) { /* Find gettimeofday. */ vdso_gettimeofday_t vdso_gettimeofday = (vdso_gettimeofday_t)vdso_sym(version, name[0]); if (!vdso_gettimeofday) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0])); + return; } struct timeval tv; long ret = vdso_gettimeofday(&tv, 0); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0])); } - - return KSFT_PASS; } -static int vdso_test_clock_gettime(clockid_t clk_id) +static void vdso_test_clock_gettime(clockid_t clk_id) { /* Find clock_gettime. */ vdso_clock_gettime_t vdso_clock_gettime = (vdso_clock_gettime_t)vdso_sym(version, name[1]); if (!vdso_clock_gettime) { - printf("Could not find %s\n", name[1]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1])); + return; } struct timespec ts; long ret = vdso_clock_gettime(clk_id, &ts); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[1]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1])); } - - return KSFT_PASS; } -static int vdso_test_time(void) +static void vdso_test_time(void) { /* Find time. */ vdso_time_t vdso_time = (vdso_time_t)vdso_sym(version, name[2]); if (!vdso_time) { - printf("Could not find %s\n", name[2]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2])); + return; } long ret = vdso_time(NULL); if (ret > 0) { - printf("The time in hours since January 1, 1970 is %lld\n", + ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", (long long)(ret / 3600)); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[2]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2])); } - - return KSFT_PASS; } -static int vdso_test_clock_getres(clockid_t clk_id) +static void vdso_test_clock_getres(clockid_t clk_id) { + int clock_getres_fail = 0; + /* Find clock_getres. */ vdso_clock_getres_t vdso_clock_getres = (vdso_clock_getres_t)vdso_sym(version, name[3]); if (!vdso_clock_getres) { - printf("Could not find %s\n", name[3]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3])); + return; } struct timespec ts, sys_ts; long ret = vdso_clock_getres(clk_id, &ts); if (ret == 0) { - printf("The resolution is %lld %lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The vdso resolution is %lld %lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); } else { - printf("%s failed\n", name[3]); - return KSFT_FAIL; + clock_getres_fail++; } ret = syscall(SYS_clock_getres, clk_id, &sys_ts); - if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) { - printf("%s failed\n", name[3]); - return KSFT_FAIL; - } + ksft_print_msg("The syscall resolution is %lld %lld\n", + (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec); - return KSFT_PASS; + if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) + clock_getres_fail++; + + if (clock_getres_fail > 0) { + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3])); + } else { + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); + } } const char *vdso_clock_name[12] = { @@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = { * This function calls vdso_test_clock_gettime and vdso_test_clock_getres * with different values for clock_id. */ -static inline int vdso_test_clock(clockid_t clock_id) +static inline void vdso_test_clock(clockid_t clock_id) { - int ret0, ret1; - - ret0 = vdso_test_clock_gettime(clock_id); - /* A skipped test is considered passed */ - if (ret0 == KSFT_SKIP) - ret0 = KSFT_PASS; - - ret1 = vdso_test_clock_getres(clock_id); - /* A skipped test is considered passed */ - if (ret1 == KSFT_SKIP) - ret1 = KSFT_PASS; + ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]); - ret0 += ret1; + vdso_test_clock_gettime(clock_id); - printf("clock_id: %s", vdso_clock_name[clock_id]); - - if (ret0 > 0) - printf(" [FAIL]\n"); - else - printf(" [PASS]\n"); - - return ret0; + vdso_test_clock_getres(clock_id); } +#define VDSO_TEST_PLAN 16 + int main(int argc, char **argv) { unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - int ret; + + ksft_print_header(); + ksft_set_plan(VDSO_TEST_PLAN); if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); @@ -201,44 +192,42 @@ int main(int argc, char **argv) vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - ret = vdso_test_gettimeofday(); + vdso_test_gettimeofday(); #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret += vdso_test_clock(CLOCK_REALTIME); + vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME - ret += vdso_test_clock(CLOCK_BOOTTIME); + vdso_test_clock(CLOCK_BOOTTIME); #endif #ifdef CLOCK_TAI - ret += vdso_test_clock(CLOCK_TAI); + vdso_test_clock(CLOCK_TAI); #endif #ifdef CLOCK_REALTIME_COARSE - ret += vdso_test_clock(CLOCK_REALTIME_COARSE); + vdso_test_clock(CLOCK_REALTIME_COARSE); #endif #ifdef CLOCK_MONOTONIC - ret += vdso_test_clock(CLOCK_MONOTONIC); + vdso_test_clock(CLOCK_MONOTONIC); #endif #ifdef CLOCK_MONOTONIC_RAW - ret += vdso_test_clock(CLOCK_MONOTONIC_RAW); + vdso_test_clock(CLOCK_MONOTONIC_RAW); #endif #ifdef CLOCK_MONOTONIC_COARSE - ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE); + vdso_test_clock(CLOCK_MONOTONIC_COARSE); #endif #endif - ret += vdso_test_time(); - - if (ret > 0) - return KSFT_FAIL; + vdso_test_time(); - return KSFT_PASS; + ksft_print_cnts(); + return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL; } diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 232e958ec454..b0b91d9b0dc2 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,9 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh" -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - . ./zram_lib.sh run_zram () { @@ -18,14 +15,4 @@ echo "" check_prereqs -# check zram module exists -MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko -if [ -f $MODULE_PATH ]; then - run_zram -elif [ -b /dev/zram0 ]; then - run_zram -else - echo "$TCID : No zram.ko module or /dev/zram0 device file not found" - echo "$TCID : CONFIG_ZRAM is not set" - exit $ksft_skip -fi +run_zram diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index 114863d9fb87..8f4affe34f3e 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,9 +33,7 @@ zram_algs="lzo" zram_fill_fs() { - local mem_free0=$(free -m | awk 'NR==2 {print $4}') - - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "fill zram$i..." local b=0 while [ true ]; do @@ -45,29 +43,17 @@ zram_fill_fs() b=$(($b + 1)) done echo "zram$i can be filled with '$b' KB" - done - local mem_free1=$(free -m | awk 'NR==2 {print $4}') - local used_mem=$(($mem_free0 - $mem_free1)) + local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"` + local v=$((100 * 1024 * $b / $mem_used_total)) + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + return + fi - local total_size=0 - for sm in $zram_sizes; do - local s=$(echo $sm | sed 's/M//') - total_size=$(($total_size + $s)) + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" done - - echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" - - local v=$((100 * $total_size / $used_mem)) - - if [ "$v" -lt 100 ]; then - echo "FAIL compression ratio: 0.$v:1" - ERR_CODE=-1 - zram_cleanup - return - fi - - echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" } check_prereqs @@ -81,7 +67,6 @@ zram_mount zram_fill_fs zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh index e83b404807c0..2418b0c4ed13 100755 --- a/tools/testing/selftests/zram/zram02.sh +++ b/tools/testing/selftests/zram/zram02.sh @@ -36,7 +36,6 @@ zram_set_memlimit zram_makeswap zram_swapoff zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 6f872f266fd1..21ec1966de76 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -5,12 +5,17 @@ # Author: Alexey Kodanev <alexey.kodanev@oracle.com> # Modified: Naresh Kamboju <naresh.kamboju@linaro.org> -MODULE=0 dev_makeswap=-1 dev_mounted=-1 - +dev_start=0 +dev_end=-1 +module_load=-1 +sys_control=-1 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +kernel_version=`uname -r | cut -d'.' -f1,2` +kernel_major=${kernel_version%.*} +kernel_minor=${kernel_version#*.} trap INT @@ -25,68 +30,104 @@ check_prereqs() fi } +kernel_gte() +{ + major=${1%.*} + minor=${1#*.} + + if [ $kernel_major -gt $major ]; then + return 0 + elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then + return 0 + fi + + return 1 +} + zram_cleanup() { echo "zram cleanup" local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_makeswap); do swapoff /dev/zram$i done - for i in $(seq 0 $dev_mounted); do + for i in $(seq $dev_start $dev_mounted); do umount /dev/zram$i done - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo 1 > /sys/block/zram${i}/reset rm -rf zram$i done -} + if [ $sys_control -eq 1 ]; then + for i in $(seq $dev_start $dev_end); do + echo $i > /sys/class/zram-control/hot_remove + done + fi -zram_unload() -{ - if [ $MODULE -ne 0 ] ; then - echo "zram rmmod zram" + if [ $module_load -eq 1 ]; then rmmod zram > /dev/null 2>&1 fi } zram_load() { - # check zram module exists - MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko - if [ -f $MODULE_PATH ]; then - MODULE=1 - echo "create '$dev_num' zram device(s)" - modprobe zram num_devices=$dev_num - if [ $? -ne 0 ]; then - echo "failed to insert zram module" - exit 1 - fi - - dev_num_created=$(ls /dev/zram* | wc -w) + echo "create '$dev_num' zram device(s)" + + # zram module loaded, new kernel + if [ -d "/sys/class/zram-control" ]; then + echo "zram modules already loaded, kernel supports" \ + "zram-control interface" + dev_start=$(ls /dev/zram* | wc -w) + dev_end=$(($dev_start + $dev_num - 1)) + sys_control=1 + + for i in $(seq $dev_start $dev_end); do + cat /sys/class/zram-control/hot_add > /dev/null + done + + echo "all zram devices (/dev/zram$dev_start~$dev_end" \ + "successfully created" + return 0 + fi - if [ "$dev_num_created" -ne "$dev_num" ]; then - echo "unexpected num of devices: $dev_num_created" - ERR_CODE=-1 + # detect old kernel or built-in + modprobe zram num_devices=$dev_num + if [ ! -d "/sys/class/zram-control" ]; then + if grep -q '^zram' /proc/modules; then + rmmod zram > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "zram module is being used on old kernel" \ + "without zram-control interface" + exit $ksft_skip + fi else - echo "zram load module successful" + echo "test needs CONFIG_ZRAM=m on old kernel without" \ + "zram-control interface" + exit $ksft_skip fi - elif [ -b /dev/zram0 ]; then - echo "/dev/zram0 device file found: OK" - else - echo "ERROR: No zram.ko module or no /dev/zram0 device found" - echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + modprobe zram num_devices=$dev_num fi + + module_load=1 + dev_end=$(($dev_num - 1)) + echo "all zram devices (/dev/zram0~$dev_end) successfully created" } zram_max_streams() { echo "set max_comp_streams to zram device(s)" - local i=0 + kernel_gte 4.7 + if [ $? -eq 0 ]; then + echo "The device attribute max_comp_streams was"\ + "deprecated in 4.7" + return 0 + fi + + local i=$dev_start for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams" echo $max_s > $sys_path || \ @@ -98,7 +139,7 @@ zram_max_streams() echo "FAIL can't set max_streams '$max_s', get $max_stream" i=$(($i + 1)) - echo "$sys_path = '$max_streams' ($i/$dev_num)" + echo "$sys_path = '$max_streams'" done echo "zram max streams: OK" @@ -108,15 +149,16 @@ zram_compress_alg() { echo "test that we can set compression algorithm" - local algs=$(cat /sys/block/zram0/comp_algorithm) + local i=$dev_start + local algs=$(cat /sys/block/zram${i}/comp_algorithm) echo "supported algs: $algs" - local i=0 + for alg in $zram_algs; do local sys_path="/sys/block/zram${i}/comp_algorithm" echo "$alg" > $sys_path || \ echo "FAIL can't set '$alg' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$alg' ($i/$dev_num)" + echo "$sys_path = '$alg'" done echo "zram set compression algorithm: OK" @@ -125,14 +167,14 @@ zram_compress_alg() zram_set_disksizes() { echo "set disk size to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_sizes; do local sys_path="/sys/block/zram${i}/disksize" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set disksizes: OK" @@ -142,14 +184,14 @@ zram_set_memlimit() { echo "set memory limit to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_mem_limits; do local sys_path="/sys/block/zram${i}/mem_limit" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set memory limit: OK" @@ -158,8 +200,8 @@ zram_set_memlimit() zram_makeswap() { echo "make swap with zram device(s)" - local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + local i=$dev_start + for i in $(seq $dev_start $dev_end); do mkswap /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -182,7 +224,7 @@ zram_makeswap() zram_swapoff() { local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_end); do swapoff /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -196,7 +238,7 @@ zram_swapoff() zram_makefs() { - local i=0 + local i=$dev_start for fs in $zram_filesystems; do # if requested fs not supported default it to ext2 which mkfs.$fs > /dev/null 2>&1 || fs=ext2 @@ -215,7 +257,7 @@ zram_makefs() zram_mount() { local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "mount /dev/zram$i" mkdir zram$i mount /dev/zram$i zram$i > /dev/null || \ diff --git a/tools/tracing/Makefile b/tools/tracing/Makefile index 87e0ec48e2e7..95e485f12d97 100644 --- a/tools/tracing/Makefile +++ b/tools/tracing/Makefile @@ -1,11 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 include ../scripts/Makefile.include -all: latency +all: latency rtla -clean: latency_clean +clean: latency_clean rtla_clean -install: latency_install +install: latency_install rtla_install latency: $(call descend,latency) @@ -16,4 +16,14 @@ latency_install: latency_clean: $(call descend,latency,clean) -.PHONY: all install clean latency latency_install latency_clean +rtla: + $(call descend,rtla) + +rtla_install: + $(call descend,rtla,install) + +rtla_clean: + $(call descend,rtla,clean) + +.PHONY: all install clean latency latency_install latency_clean \ + rtla rtla_install rtla_clean diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile index 2d52ff0bff7d..7c39728d08de 100644 --- a/tools/tracing/rtla/Makefile +++ b/tools/tracing/rtla/Makefile @@ -59,7 +59,7 @@ endif .PHONY: all all: rtla -rtla: $(OBJ) doc +rtla: $(OBJ) $(CC) -o rtla $(LDFLAGS) $(OBJ) $(LIBS) static: $(OBJ) diff --git a/usr/include/Makefile b/usr/include/Makefile index 7be7468c177b..83822c33e9e7 100644 --- a/usr/include/Makefile +++ b/usr/include/Makefile @@ -28,6 +28,7 @@ no-header-test += linux/am437x-vpfe.h no-header-test += linux/android/binder.h no-header-test += linux/android/binderfs.h no-header-test += linux/coda.h +no-header-test += linux/cyclades.h no-header-test += linux/errqueue.h no-header-test += linux/fsmap.h no-header-test += linux/hdlc/ioctl.h diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 2ad013b8bde9..59b1dd4a549e 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -463,8 +463,8 @@ bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin) idx = srcu_read_lock(&kvm->irq_srcu); gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin); if (gsi != -1) - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) + hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list, + link, srcu_read_lock_held(&kvm->irq_srcu)) if (kian->gsi == gsi) { srcu_read_unlock(&kvm->irq_srcu, idx); return true; @@ -480,8 +480,8 @@ void kvm_notify_acked_gsi(struct kvm *kvm, int gsi) { struct kvm_irq_ack_notifier *kian; - hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list, - link) + hlist_for_each_entry_srcu(kian, &kvm->irq_ack_notifier_list, + link, srcu_read_lock_held(&kvm->irq_srcu)) if (kian->gsi == gsi) kian->irq_acked(kian); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9a20f2299386..58d31da8a2f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2248,7 +2248,6 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn return NULL; } -EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { @@ -2463,9 +2462,8 @@ static int kvm_try_get_pfn(kvm_pfn_t pfn) } static int hva_to_pfn_remapped(struct vm_area_struct *vma, - unsigned long addr, bool *async, - bool write_fault, bool *writable, - kvm_pfn_t *p_pfn) + unsigned long addr, bool write_fault, + bool *writable, kvm_pfn_t *p_pfn) { kvm_pfn_t pfn; pte_t *ptep; @@ -2575,7 +2573,7 @@ retry: if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { - r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn); + r = hva_to_pfn_remapped(vma, addr, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) |