diff options
938 files changed, 17130 insertions, 7707 deletions
@@ -206,6 +206,7 @@ Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com> David Brownell <david-b@pacbell.net> David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org> David Heidelberg <david@ixit.cz> <d.okias@gmail.com> +David Hildenbrand <david@kernel.org> <david@redhat.com> David Rheinsberg <david@readahead.eu> <dh.herrmann@gmail.com> David Rheinsberg <david@readahead.eu> <dh.herrmann@googlemail.com> David Rheinsberg <david@readahead.eu> <david.rheinsberg@gmail.com> @@ -426,7 +427,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com> Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org> Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org> Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com> -Kirill A. Shutemov <kas@kernel.org> <kirill.shutemov@linux.intel.com> +Kiryl Shutsemau <kas@kernel.org> <kirill.shutemov@linux.intel.com> Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org> @@ -437,6 +438,7 @@ Krishna Manikandan <quic_mkrishn@quicinc.com> <mkrishn@codeaurora.org> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Krzysztof Kozlowski <krzk@kernel.org> <krzysztof.kozlowski@canonical.com> +Krzysztof Kozlowski <krzk@kernel.org> <krzysztof.kozlowski@linaro.org> Krzysztof WilczyÅ„ski <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com> Krzysztof WilczyÅ„ski <kwilczynski@kernel.org> <kw@linux.com> Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org> @@ -689,6 +691,8 @@ Sachin Mokashi <sachin.mokashi@intel.com> <sachinx.mokashi@intel.com> Sachin P Sant <ssant@in.ibm.com> Sai Prakash Ranjan <quic_saipraka@quicinc.com> <saiprakash.ranjan@codeaurora.org> Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> +Sam Protsenko <semen.protsenko@linaro.org> +Sam Protsenko <semen.protsenko@linaro.org> <semen.protsenko@globallogic.com> Sam Ravnborg <sam@mars.ravnborg.org> Sankeerth Billakanti <quic_sbillaka@quicinc.com> <sbillaka@codeaurora.org> Santosh Shilimkar <santosh.shilimkar@oracle.org> diff --git a/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml index d6ef468495c5..a105dc07ed12 100644 --- a/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml +++ b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml @@ -19,7 +19,12 @@ allOf: properties: compatible: - const: aspeed,ast2600-mdio + oneOf: + - const: aspeed,ast2600-mdio + - items: + - enum: + - aspeed,ast2700-mdio + - const: aspeed,ast2600-mdio reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml index 1219c5cb601f..519a11fbe972 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml @@ -32,11 +32,15 @@ properties: - description: AHB peripheral clock - description: CAN bus clock + resets: + maxItems: 1 + required: - compatible - reg - interrupts - clocks + - resets additionalProperties: false @@ -46,6 +50,7 @@ examples: compatible = "microchip,mpfs-can"; reg = <0x2010c000 0x1000>; clocks = <&clkcfg 17>, <&clkcfg 37>; + resets = <&clkcfg 17>; interrupt-parent = <&plic>; interrupts = <56>; }; diff --git a/Documentation/devicetree/bindings/net/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index ea8337846ab2..cb14c35ba996 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -38,7 +38,10 @@ properties: - cdns,sam9x60-macb # Microchip sam9x60 SoC - microchip,mpfs-macb # Microchip PolarFire SoC - const: cdns,macb # Generic - + - items: + - const: microchip,pic64gx-macb # Microchip PIC64GX SoC + - const: microchip,mpfs-macb # Microchip PolarFire SoC + - const: cdns,macb # Generic - items: - enum: - atmel,sama5d3-macb # 10/100Mbit IP on Atmel sama5d3 SoCs diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index b45f67f92e80..cc346946291a 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -112,7 +112,7 @@ properties: mediatek,wed: $ref: /schemas/types.yaml#/definitions/phandle-array - minItems: 2 + minItems: 1 maxItems: 2 items: maxItems: 1 @@ -249,6 +249,9 @@ allOf: minItems: 1 maxItems: 1 + mediatek,wed: + minItems: 2 + mediatek,wed-pcie: false else: properties: @@ -338,12 +341,13 @@ allOf: - const: netsys0 - const: netsys1 - mediatek,infracfg: false - mediatek,sgmiisys: minItems: 2 maxItems: 2 + mediatek,wed: + maxItems: 1 + - if: properties: compatible: @@ -385,6 +389,9 @@ allOf: minItems: 2 maxItems: 2 + mediatek,wed: + minItems: 2 + - if: properties: compatible: @@ -429,6 +436,19 @@ allOf: - const: xgp2 - const: xgp3 + mediatek,wed: + minItems: 2 + + - if: + properties: + compatible: + contains: + const: ralink,rt5350-eth + then: + properties: + mediatek,wed: + minItems: 2 + patternProperties: "^mac@[0-2]$": type: object diff --git a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml index ce21979a2d9a..e8d3814db0e9 100644 --- a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml @@ -70,6 +70,25 @@ required: allOf: - $ref: snps,dwmac.yaml# + - if: + properties: + compatible: + contains: + const: sophgo,sg2042-dwmac + then: + properties: + phy-mode: + enum: + - rgmii-rxid + - rgmii-id + else: + properties: + phy-mode: + enum: + - rgmii + - rgmii-rxid + - rgmii-txid + - rgmii-id unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml index 19d47fd414bc..ce04d2eadec9 100644 --- a/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/toshiba,visconti-pinctrl.yaml @@ -50,18 +50,20 @@ patternProperties: groups: description: Name of the pin group to use for the functions. - $ref: /schemas/types.yaml#/definitions/string - enum: [i2c0_grp, i2c1_grp, i2c2_grp, i2c3_grp, i2c4_grp, - i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp, - spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp, - spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp, - uart0_grp, uart1_grp, uart2_grp, uart3_grp, - pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp, - pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp, - pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp, - pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp, - pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp, - pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp] + items: + enum: [i2c0_grp, i2c1_grp, i2c2_grp, i2c3_grp, i2c4_grp, + i2c5_grp, i2c6_grp, i2c7_grp, i2c8_grp, + spi0_grp, spi0_cs0_grp, spi0_cs1_grp, spi0_cs2_grp, + spi1_grp, spi2_grp, spi3_grp, spi4_grp, spi5_grp, spi6_grp, + uart0_grp, uart1_grp, uart2_grp, uart3_grp, + pwm0_gpio4_grp, pwm0_gpio8_grp, pwm0_gpio12_grp, + pwm0_gpio16_grp, pwm1_gpio5_grp, pwm1_gpio9_grp, + pwm1_gpio13_grp, pwm1_gpio17_grp, pwm2_gpio6_grp, + pwm2_gpio10_grp, pwm2_gpio14_grp, pwm2_gpio18_grp, + pwm3_gpio7_grp, pwm3_gpio11_grp, pwm3_gpio15_grp, + pwm3_gpio19_grp, pcmif_out_grp, pcmif_in_grp] + minItems: 1 + maxItems: 8 drive-strength: enum: [2, 4, 6, 8, 16, 24, 32] diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml index 55ece6a8be5e..81e2164ea98f 100644 --- a/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/xlnx,versal-pinctrl.yaml @@ -74,6 +74,7 @@ patternProperties: '^conf': type: object + unevaluatedProperties: false description: Pinctrl node's client devices use subnodes for pin configurations, which in turn use the standard properties below. diff --git a/Documentation/input/event-codes.rst b/Documentation/input/event-codes.rst index 1ead9bb8d9c6..4424cbff251f 100644 --- a/Documentation/input/event-codes.rst +++ b/Documentation/input/event-codes.rst @@ -400,19 +400,30 @@ can report through the rotational axes (absolute and/or relative rx, ry, rz). All other axes retain their meaning. A device must not mix regular directional axes and accelerometer axes on the same event node. -INPUT_PROP_HAPTIC_TOUCHPAD --------------------------- +INPUT_PROP_PRESSUREPAD +---------------------- + +The INPUT_PROP_PRESSUREPAD property indicates that the device provides +simulated haptic feedback (e.g. a vibrator motor situated below the surface) +instead of physical haptic feedback (e.g. a hinge). This property is only set +if the device: -The INPUT_PROP_HAPTIC_TOUCHPAD property indicates that device: -- supports simple haptic auto and manual triggering - can differentiate between at least 5 fingers - uses correct resolution for the X/Y (units and value) -- reports correct force per touch, and correct units for them (newtons or grams) - follows the MT protocol type B +If the simulated haptic feedback is controllable by userspace the device must: + +- support simple haptic auto and manual triggering, and +- report correct force per touch, and correct units for them (newtons or grams), and +- provide the EV_FF FF_HAPTIC force feedback effect. + Summing up, such devices follow the MS spec for input devices in -Win8 and Win8.1, and in addition support the Simple haptic controller HID table, -and report correct units for the pressure. +Win8 and Win8.1, and in addition may support the Simple haptic controller HID +table, and report correct units for the pressure. + +Where applicable, this property is set in addition to INPUT_PROP_BUTTONPAD, it +does not replace that property. Guidelines ========== diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 5a234e9b5fa2..57f59fe23e3f 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -227,7 +227,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] # Start genetlink-c name-prefix: type: string diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 7b1ec153e834..b020a537d8ac 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -185,7 +185,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] # Make sure name-prefix does not appear in subsets (subsets inherit naming) dependencies: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index 246fa07bccf6..0166a7e4afbb 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -157,7 +157,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] struct: description: Name of the nested struct type. type: string diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 426d5aa7d955..837112da6738 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -859,6 +859,14 @@ attribute-sets: name: health-reporter-burst-period type: u64 doc: Time (in msec) for recoveries before starting the grace period. + + # TODO: fill in the attributes in between + + - + name: param-reset-default + type: flag + doc: Request restoring parameter to its default value. + value: 183 - name: dl-dev-stats subset-of: devlink @@ -1793,6 +1801,7 @@ operations: - param-type # param-value-data is missing here as the type is variable - param-value-cmode + - param-reset-default - name: region-get diff --git a/Documentation/netlink/specs/rt-addr.yaml b/Documentation/netlink/specs/rt-addr.yaml index 3a582eac1629..163a106c41bb 100644 --- a/Documentation/netlink/specs/rt-addr.yaml +++ b/Documentation/netlink/specs/rt-addr.yaml @@ -86,17 +86,18 @@ attribute-sets: - name: address type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: label type: string - name: broadcast - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: anycast diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 2a23e9699c0b..6beeb6ee5adf 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1707,11 +1707,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: ttl type: u8 @@ -1833,11 +1833,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: fwmark type: u32 @@ -1868,7 +1868,8 @@ attribute-sets: type: u32 - name: remote - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: ttl @@ -1914,6 +1915,35 @@ attribute-sets: type: binary struct: ifla-geneve-port-range - + name: linkinfo-hsr-attrs + name-prefix: ifla-hsr- + attributes: + - + name: slave1 + type: u32 + - + name: slave2 + type: u32 + - + name: multicast-spec + type: u8 + - + name: supervision-addr + type: binary + display-hint: mac + - + name: seq-nr + type: u16 + - + name: version + type: u8 + - + name: protocol + type: u8 + - + name: interlink + type: u32 + - name: linkinfo-iptun-attrs name-prefix: ifla-iptun- attributes: @@ -1923,11 +1953,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: ttl type: u8 @@ -1957,7 +1987,8 @@ attribute-sets: display-hint: ipv6 - name: 6rd-relay-prefix - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: 6rd-prefixlen @@ -2300,6 +2331,9 @@ sub-messages: value: geneve attribute-set: linkinfo-geneve-attrs - + value: hsr + attribute-set: linkinfo-hsr-attrs + - value: ipip attribute-set: linkinfo-iptun-attrs - diff --git a/Documentation/netlink/specs/rt-neigh.yaml b/Documentation/netlink/specs/rt-neigh.yaml index 2f568a6231c9..0f46ef313590 100644 --- a/Documentation/netlink/specs/rt-neigh.yaml +++ b/Documentation/netlink/specs/rt-neigh.yaml @@ -194,7 +194,7 @@ attribute-sets: - name: dst type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: lladdr type: binary diff --git a/Documentation/netlink/specs/rt-route.yaml b/Documentation/netlink/specs/rt-route.yaml index 1ecb3fadc067..33195db96746 100644 --- a/Documentation/netlink/specs/rt-route.yaml +++ b/Documentation/netlink/specs/rt-route.yaml @@ -87,11 +87,11 @@ attribute-sets: - name: dst type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: src type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: iif type: u32 @@ -101,14 +101,14 @@ attribute-sets: - name: gateway type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: priority type: u32 - name: prefsrc type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: metrics type: nest diff --git a/Documentation/netlink/specs/rt-rule.yaml b/Documentation/netlink/specs/rt-rule.yaml index bebee452a950..7f03a44ab036 100644 --- a/Documentation/netlink/specs/rt-rule.yaml +++ b/Documentation/netlink/specs/rt-rule.yaml @@ -96,10 +96,12 @@ attribute-sets: attributes: - name: dst - type: u32 + type: binary + display-hint: ipv4-or-v6 - name: src - type: u32 + type: binary + display-hint: ipv4-or-v6 - name: iifname type: string diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst index c0597d456641..ea17756dcda6 100644 --- a/Documentation/networking/devlink/devlink-params.rst +++ b/Documentation/networking/devlink/devlink-params.rst @@ -41,6 +41,16 @@ In order for ``driverinit`` parameters to take effect, the driver must support reloading via the ``devlink-reload`` command. This command will request a reload of the device driver. +Default parameter values +========================= + +Drivers may optionally export default values for parameters of cmode +``runtime`` and ``permanent``. For ``driverinit`` parameters, the last +value set by the driver will be used as the default value. Drivers can +also support resetting params with cmode ``runtime`` and ``permanent`` +to their default values. Resetting ``driverinit`` params is supported +by devlink core without additional driver support needed. + .. _devlink_params_generic: Generic configuration parameters diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 0e5f9c76e514..4bba4d780a4a 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -218,6 +218,20 @@ parameters. * ``balanced`` : Merges fewer CQEs, resulting in a moderate compression ratio but maintaining a balance between bandwidth savings and performance * ``aggressive`` : Merges more CQEs into a single entry, achieving a higher compression rate and maximizing performance, particularly under high traffic loads + * - ``swp_l4_csum_mode`` + - string + - permanent + - Configure how the L4 checksum is calculated by the device when using + Software Parser (SWP) hints for header locations. + + * ``default`` : Use the device's default checksum calculation + mode. The driver will discover during init whether or + full_csum or l4_only is in use. Setting this value explicitly + from userspace is not allowed, but some firmware versions may + return this value on param read. + * ``full_csum`` : Calculate full checksum including the pseudo-header + * ``l4_only`` : Calculate L4-only checksum, excluding the pseudo-header + The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD`` Info versions diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index c775cababc8c..75db2251649b 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -131,10 +131,7 @@ Contents: vxlan x25 x25-iface - xfrm_device - xfrm_proc - xfrm_sync - xfrm_sysctl + xfrm/index xdp-rx-metadata xsk-tx-metadata diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 2bae61be1859..bc9a01606daf 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -673,6 +673,16 @@ tcp_moderate_rcvbuf - BOOLEAN Default: 1 (enabled) +tcp_rcvbuf_low_rtt - INTEGER + rcvbuf autotuning can over estimate final socket rcvbuf, which + can lead to cache trashing for high throughput flows. + + For small RTT flows (below tcp_rcvbuf_low_rtt usecs), we can relax + rcvbuf growth: Few additional ms to reach the final (and smaller) + rcvbuf is a good tradeoff. + + Default : 1000 (1 ms) + tcp_mtu_probing - INTEGER Controls TCP Packetization-Layer Path MTU Discovery. Takes three values: @@ -875,8 +885,9 @@ tcp_comp_sack_slack_ns - LONG INTEGER timer used by SACK compression. This gives extra time for small RTT flows, and reduces system overhead by allowing opportunistic reduction of timer interrupts. + Too big values might reduce goodput. - Default : 100,000 ns (100 us) + Default : 10,000 ns (10 us) tcp_comp_sack_nr - INTEGER Max number of SACK that can be compressed. diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst index 8fae85ebb773..cc2000f55c29 100644 --- a/Documentation/networking/net_cachelines/inet_connection_sock.rst +++ b/Documentation/networking/net_cachelines/inet_connection_sock.rst @@ -12,8 +12,8 @@ struct inet_sock icsk_inet read_mostly r struct request_sock_queue icsk_accept_queue struct inet_bind_bucket icsk_bind_hash read_mostly tcp_set_state struct inet_bind2_bucket icsk_bind2_hash read_mostly tcp_set_state,inet_put_port -struct timer_list icsk_retransmit_timer read_write inet_csk_reset_xmit_timer,tcp_connect struct timer_list icsk_delack_timer read_mostly inet_csk_reset_xmit_timer,tcp_connect +struct timer_list icsk_keepalive_timer u32 icsk_rto read_write tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one u32 icsk_rto_min u32 icsk_rto_max read_mostly tcp_reset_xmit_timer diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst index 6e7b20afd2d4..beaf1880a19b 100644 --- a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst +++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst @@ -102,7 +102,8 @@ u8 sysctl_tcp_app_win u8 sysctl_tcp_frto tcp_enter_loss u8 sysctl_tcp_nometrics_save TCP_LAST_ACK/tcp_update_metrics u8 sysctl_tcp_no_ssthresh_metrics_save TCP_LAST_ACK/tcp_(update/init)_metrics -u8 sysctl_tcp_moderate_rcvbuf read_mostly read_mostly tcp_tso_should_defer(tx);tcp_rcv_space_adjust(rx) +u8 sysctl_tcp_moderate_rcvbuf read_mostly tcp_rcvbuf_grow() +u32 sysctl_tcp_rcvbuf_low_rtt read_mostly tcp_rcvbuf_grow() u8 sysctl_tcp_tso_win_divisor read_mostly tcp_tso_should_defer(tcp_write_xmit) u8 sysctl_tcp_workaround_signed_windows tcp_select_window int sysctl_tcp_limit_output_bytes read_mostly tcp_small_queue_check(tcp_write_xmit) diff --git a/Documentation/networking/xfrm/index.rst b/Documentation/networking/xfrm/index.rst new file mode 100644 index 000000000000..7d866da836fe --- /dev/null +++ b/Documentation/networking/xfrm/index.rst @@ -0,0 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============== +XFRM Framework +============== + +.. toctree:: + :maxdepth: 2 + + xfrm_device + xfrm_proc + xfrm_sync + xfrm_sysctl diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm/xfrm_device.rst index 122204da0fff..b0d85a5f57d1 100644 --- a/Documentation/networking/xfrm_device.rst +++ b/Documentation/networking/xfrm/xfrm_device.rst @@ -20,11 +20,15 @@ can radically increase throughput and decrease CPU utilization. The XFRM Device interface allows NIC drivers to offer to the stack access to the hardware offload. -Right now, there are two types of hardware offload that kernel supports. +Right now, there are two types of hardware offload that kernel supports: + * IPsec crypto offload: + * NIC performs encrypt/decrypt * Kernel does everything else + * IPsec packet offload: + * NIC performs encrypt/decrypt * NIC does encapsulation * Kernel and NIC have SA and policy in-sync @@ -34,7 +38,7 @@ Right now, there are two types of hardware offload that kernel supports. Userland access to the offload is typically through a system such as libreswan or KAME/raccoon, but the iproute2 'ip xfrm' command set can be handy when experimenting. An example command might look something -like this for crypto offload: +like this for crypto offload:: ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \ reqid 0x07 replay-window 32 \ @@ -42,7 +46,7 @@ like this for crypto offload: sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \ offload dev eth4 dir in -and for packet offload +and for packet offload:: ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \ reqid 0x07 replay-window 32 \ @@ -153,26 +157,26 @@ the packet's skb. At this point the data should be decrypted but the IPsec headers are still in the packet data; they are removed later up the stack in xfrm_input(). - find and hold the SA that was used to the Rx skb:: +1. Find and hold the SA that was used to the Rx skb:: - get spi, protocol, and destination IP from packet headers + /* get spi, protocol, and destination IP from packet headers */ xs = find xs from (spi, protocol, dest_IP) xfrm_state_hold(xs); - store the state information into the skb:: +2. Store the state information into the skb:: sp = secpath_set(skb); if (!sp) return; sp->xvec[sp->len++] = xs; sp->olen++; - indicate the success and/or error status of the offload:: +3. Indicate the success and/or error status of the offload:: xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; xo->status = crypto_status; - hand the packet to napi_gro_receive() as usual +4. Hand the packet to napi_gro_receive() as usual. In ESN mode, xdo_dev_state_advance_esn() is called from xfrm_replay_advance_esn() for RX, and xfrm_replay_overflow_offload_esn for TX. diff --git a/Documentation/networking/xfrm_proc.rst b/Documentation/networking/xfrm/xfrm_proc.rst index 973d1571acac..973d1571acac 100644 --- a/Documentation/networking/xfrm_proc.rst +++ b/Documentation/networking/xfrm/xfrm_proc.rst diff --git a/Documentation/networking/xfrm_sync.rst b/Documentation/networking/xfrm/xfrm_sync.rst index 6246503ceab2..dfc2ec0df380 100644 --- a/Documentation/networking/xfrm_sync.rst +++ b/Documentation/networking/xfrm/xfrm_sync.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -==== -XFRM -==== +========= +XFRM sync +========= The sync patches work is based on initial patches from Krisztian <hidden@balabit.hu> and others and additional patches @@ -36,7 +36,7 @@ is not driven by packet arrival. - the replay sequence for both inbound and outbound 1) Message Structure ----------------------- +-------------------- nlmsghdr:aevent_id:optional-TLVs. @@ -83,31 +83,31 @@ when going from kernel to user space) A program needs to subscribe to multicast group XFRMNLGRP_AEVENTS to get notified of these events. -2) TLVS reflect the different parameters: ------------------------------------------ +2) TLVS reflect the different parameters +---------------------------------------- a) byte value (XFRMA_LTIME_VAL) -This TLV carries the running/current counter for byte lifetime since -last event. + This TLV carries the running/current counter for byte lifetime since + last event. -b)replay value (XFRMA_REPLAY_VAL) +b) replay value (XFRMA_REPLAY_VAL) -This TLV carries the running/current counter for replay sequence since -last event. + This TLV carries the running/current counter for replay sequence since + last event. -c)replay threshold (XFRMA_REPLAY_THRESH) +c) replay threshold (XFRMA_REPLAY_THRESH) -This TLV carries the threshold being used by the kernel to trigger events -when the replay sequence is exceeded. + This TLV carries the threshold being used by the kernel to trigger events + when the replay sequence is exceeded. d) expiry timer (XFRMA_ETIMER_THRESH) -This is a timer value in milliseconds which is used as the nagle -value to rate limit the events. + This is a timer value in milliseconds which is used as the nagle + value to rate limit the events. -3) Default configurations for the parameters: ---------------------------------------------- +3) Default configurations for the parameters +-------------------------------------------- By default these events should be turned off unless there is at least one listener registered to listen to the multicast @@ -121,12 +121,14 @@ in case they are not specified. the two sysctls/proc entries are: a) /proc/sys/net/core/sysctl_xfrm_aevent_etime -used to provide default values for the XFRMA_ETIMER_THRESH in incremental -units of time of 100ms. The default is 10 (1 second) + + Used to provide default values for the XFRMA_ETIMER_THRESH in incremental + units of time of 100ms. The default is 10 (1 second) b) /proc/sys/net/core/sysctl_xfrm_aevent_rseqth -used to provide default values for XFRMA_REPLAY_THRESH parameter -in incremental packet count. The default is two packets. + + Used to provide default values for XFRMA_REPLAY_THRESH parameter + in incremental packet count. The default is two packets. 4) Message types ---------------- @@ -134,50 +136,51 @@ in incremental packet count. The default is two packets. a) XFRM_MSG_GETAE issued by user-->kernel. XFRM_MSG_GETAE does not carry any TLVs. -The response is a XFRM_MSG_NEWAE which is formatted based on what -XFRM_MSG_GETAE queried for. + The response is a XFRM_MSG_NEWAE which is formatted based on what + XFRM_MSG_GETAE queried for. + + The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -* if XFRM_AE_RTHR flag is set, then XFRMA_REPLAY_THRESH is also retrieved -* if XFRM_AE_ETHR flag is set, then XFRMA_ETIMER_THRESH is also retrieved + * if XFRM_AE_RTHR flag is set, then XFRMA_REPLAY_THRESH is also retrieved + * if XFRM_AE_ETHR flag is set, then XFRMA_ETIMER_THRESH is also retrieved b) XFRM_MSG_NEWAE is issued by either user space to configure or kernel to announce events or respond to a XFRM_MSG_GETAE. -i) user --> kernel to configure a specific SA. + i) user --> kernel to configure a specific SA. -any of the values or threshold parameters can be updated by passing the -appropriate TLV. + any of the values or threshold parameters can be updated by passing the + appropriate TLV. -A response is issued back to the sender in user space to indicate success -or failure. + A response is issued back to the sender in user space to indicate success + or failure. -In the case of success, additionally an event with -XFRM_MSG_NEWAE is also issued to any listeners as described in iii). + In the case of success, additionally an event with + XFRM_MSG_NEWAE is also issued to any listeners as described in iii). -ii) kernel->user direction as a response to XFRM_MSG_GETAE + ii) kernel->user direction as a response to XFRM_MSG_GETAE -The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. + The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -The threshold TLVs will be included if explicitly requested in -the XFRM_MSG_GETAE message. + The threshold TLVs will be included if explicitly requested in + the XFRM_MSG_GETAE message. -iii) kernel->user to report as event if someone sets any values or - thresholds for an SA using XFRM_MSG_NEWAE (as described in #i above). - In such a case XFRM_AE_CU flag is set to inform the user that - the change happened as a result of an update. - The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. + iii) kernel->user to report as event if someone sets any values or + thresholds for an SA using XFRM_MSG_NEWAE (as described in #i above). + In such a case XFRM_AE_CU flag is set to inform the user that + the change happened as a result of an update. + The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -iv) kernel->user to report event when replay threshold or a timeout - is exceeded. + iv) kernel->user to report event when replay threshold or a timeout + is exceeded. In such a case either XFRM_AE_CR (replay exceeded) or XFRM_AE_CE (timeout happened) is set to inform the user what happened. Note the two flags are mutually exclusive. The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -Exceptions to threshold settings --------------------------------- +5) Exceptions to threshold settings +----------------------------------- If you have an SA that is getting hit by traffic in bursts such that there is a period where the timer threshold expires with no packets diff --git a/Documentation/networking/xfrm_sysctl.rst b/Documentation/networking/xfrm/xfrm_sysctl.rst index 47b9bbdd0179..7d0c4b17c0bd 100644 --- a/Documentation/networking/xfrm_sysctl.rst +++ b/Documentation/networking/xfrm/xfrm_sysctl.rst @@ -4,8 +4,8 @@ XFRM Syscall ============ -/proc/sys/net/core/xfrm_* Variables: -==================================== +/proc/sys/net/core/xfrm_* Variables +=================================== xfrm_acq_expires - INTEGER default 30 - hard timeout in seconds for acquire requests diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst index 57d1964453e1..d5363b08f515 100644 --- a/Documentation/sound/codecs/cs35l56.rst +++ b/Documentation/sound/codecs/cs35l56.rst @@ -105,10 +105,10 @@ In this example the SSID is 10280c63. The format of the firmware file names is: -SoundWire (except CS35L56 Rev B0): +SoundWire: cs35lxx-b0-dsp1-misc-SSID[-spkidX]-l?u? -SoundWire CS35L56 Rev B0: +SoundWire CS35L56 Rev B0 firmware released before kernel version 6.16: cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN Non-SoundWire (HDA and I2S): @@ -127,9 +127,8 @@ Where: * spkidX is an optional part, used for laptops that have firmware configurations for different makes and models of internal speakers. -The CS35L56 Rev B0 continues to use the old filename scheme because a -large number of firmware files have already been published with these -names. +Early firmware for CS35L56 Rev B0 used the ALSA prefix (ampN) as the +filename qualifier. Support for the l?u? qualifier was added in kernel 6.16. Sound Open Firmware and ALSA topology files ------------------------------------------- diff --git a/Documentation/wmi/driver-development-guide.rst b/Documentation/wmi/driver-development-guide.rst index 99ef21fc1c1e..5680303ae314 100644 --- a/Documentation/wmi/driver-development-guide.rst +++ b/Documentation/wmi/driver-development-guide.rst @@ -54,6 +54,7 @@ to matching WMI devices using a struct wmi_device_id table: :: static const struct wmi_device_id foo_id_table[] = { + /* Only use uppercase letters! */ { "936DA01F-9ABD-4D9D-80C7-02AF85C822A8", NULL }, { } }; diff --git a/MAINTAINERS b/MAINTAINERS index 37f4278db851..09932ab7e0e8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3927,7 +3927,7 @@ F: crypto/async_tx/ F: include/linux/async_tx.h AT24 EEPROM DRIVER -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-i2c@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -4400,7 +4400,7 @@ BLOCK LAYER M: Jens Axboe <axboe@kernel.dk> L: linux-block@vger.kernel.org S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git F: Documentation/ABI/stable/sysfs-block F: Documentation/block/ F: block/ @@ -9266,7 +9266,6 @@ M: Ido Schimmel <idosch@nvidia.com> L: bridge@lists.linux.dev L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net:Bridge F: include/linux/if_bridge.h F: include/uapi/linux/if_bridge.h F: include/linux/netfilter_bridge/ @@ -10679,7 +10678,7 @@ F: tools/gpio/gpio-sloppy-logic-analyzer.sh GPIO SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-gpio@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -10696,7 +10695,7 @@ K: GPIOD_FLAGS_BIT_NONEXCLUSIVE K: devm_gpiod_unhinge GPIO UAPI -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> R: Kent Gibson <warthog618@gmail.com> L: linux-gpio@vger.kernel.org S: Maintained @@ -11528,7 +11527,7 @@ F: include/linux/platform_data/huawei-gaokun-ec.h HUGETLB SUBSYSTEM M: Muchun Song <muchun.song@linux.dev> M: Oscar Salvador <osalvador@suse.de> -R: David Hildenbrand <david@redhat.com> +R: David Hildenbrand <david@kernel.org> L: linux-mm@kvack.org S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -13735,7 +13734,7 @@ KERNEL VIRTUAL MACHINE for s390 (KVM/s390) M: Christian Borntraeger <borntraeger@linux.ibm.com> M: Janosch Frank <frankja@linux.ibm.com> M: Claudio Imbrenda <imbrenda@linux.ibm.com> -R: David Hildenbrand <david@redhat.com> +R: David Hildenbrand <david@kernel.org> L: kvm@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git @@ -13800,6 +13799,7 @@ F: Documentation/admin-guide/mm/kho.rst F: Documentation/core-api/kho/* F: include/linux/kexec_handover.h F: kernel/kexec_handover.c +F: lib/test_kho.c F: tools/testing/selftests/kho/ KEYS-ENCRYPTED @@ -15311,7 +15311,7 @@ F: drivers/pwm/pwm-max7360.c F: include/linux/mfd/max7360.h MAXIM MAX77650 PMIC MFD DRIVER -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/*/*max77650.yaml @@ -15413,14 +15413,12 @@ S: Supported F: drivers/net/phy/mxl-86110.c F: drivers/net/phy/mxl-gpy.c -MCAN MMIO DEVICE DRIVER -M: Chandrasekar Ramakrishnan <rcsekar@samsung.com> +MCAN DEVICE DRIVER +M: Markus Schneider-Pargmann <msp@baylibre.com> L: linux-can@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/can/bosch,m_can.yaml -F: drivers/net/can/m_can/m_can.c -F: drivers/net/can/m_can/m_can.h -F: drivers/net/can/m_can/m_can_platform.c +F: drivers/net/can/m_can/ MCBA MICROCHIP CAN BUS ANALYZER TOOL DRIVER R: Yasushi SHOJI <yashi@spacecubics.com> @@ -16207,7 +16205,7 @@ MEMORY CONTROLLER DRIVERS M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained -B: mailto:krzysztof.kozlowski@linaro.org +B: mailto:krzk@kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git F: Documentation/devicetree/bindings/memory-controllers/ F: drivers/memory/ @@ -16223,7 +16221,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux.git F: drivers/devfreq/tegra30-devfreq.c MEMORY HOT(UN)PLUG -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> M: Oscar Salvador <osalvador@suse.de> L: linux-mm@kvack.org S: Maintained @@ -16248,7 +16246,7 @@ F: tools/mm/ MEMORY MANAGEMENT - CORE M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@suse.cz> @@ -16304,7 +16302,7 @@ F: mm/execmem.c MEMORY MANAGEMENT - GUP (GET USER PAGES) M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Jason Gunthorpe <jgg@nvidia.com> R: John Hubbard <jhubbard@nvidia.com> R: Peter Xu <peterx@redhat.com> @@ -16320,7 +16318,7 @@ F: tools/testing/selftests/mm/gup_test.c MEMORY MANAGEMENT - KSM (Kernel Samepage Merging) M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Xu Xin <xu.xin16@zte.com.cn> R: Chengming Zhou <chengming.zhou@linux.dev> L: linux-mm@kvack.org @@ -16336,7 +16334,7 @@ F: mm/mm_slot.h MEMORY MANAGEMENT - MEMORY POLICY AND MIGRATION M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Zi Yan <ziy@nvidia.com> R: Matthew Brost <matthew.brost@intel.com> R: Joshua Hahn <joshua.hahnjy@gmail.com> @@ -16376,7 +16374,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - MISC M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Vlastimil Babka <vbabka@suse.cz> @@ -16464,7 +16462,7 @@ F: mm/shuffle.h MEMORY MANAGEMENT - RECLAIM M: Andrew Morton <akpm@linux-foundation.org> M: Johannes Weiner <hannes@cmpxchg.org> -R: David Hildenbrand <david@redhat.com> +R: David Hildenbrand <david@kernel.org> R: Michal Hocko <mhocko@kernel.org> R: Qi Zheng <zhengqi.arch@bytedance.com> R: Shakeel Butt <shakeel.butt@linux.dev> @@ -16477,7 +16475,7 @@ F: mm/workingset.c MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> @@ -16522,7 +16520,7 @@ F: mm/swapfile.c MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) M: Andrew Morton <akpm@linux-foundation.org> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Zi Yan <ziy@nvidia.com> R: Baolin Wang <baolin.wang@linux.alibaba.com> @@ -16624,7 +16622,7 @@ MEMORY MAPPING - MADVISE (MEMORY ADVICE) M: Andrew Morton <akpm@linux-foundation.org> M: Liam R. Howlett <Liam.Howlett@oracle.com> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> R: Vlastimil Babka <vbabka@suse.cz> R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org @@ -18068,6 +18066,7 @@ L: netdev@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git +F: Documentation/networking/xfrm/ F: include/net/xfrm.h F: include/uapi/linux/xfrm.h F: net/ipv4/ah4.c @@ -18798,6 +18797,10 @@ S: Maintained F: arch/arm/*omap*/*clock* OMAP DEVICE TREE SUPPORT +M: Aaro Koskinen <aaro.koskinen@iki.fi> +M: Andreas Kemnade <andreas@kemnade.info> +M: Kevin Hilman <khilman@baylibre.com> +M: Roger Quadros <rogerq@kernel.org> M: Tony Lindgren <tony@atomide.com> L: linux-omap@vger.kernel.org L: devicetree@vger.kernel.org @@ -19917,7 +19920,7 @@ F: drivers/pci/p2pdma.c F: include/linux/pci-p2pdma.h PCI POWER CONTROL -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-pci@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci.git @@ -20514,7 +20517,7 @@ F: include/linux/powercap.h F: kernel/configs/nopm.config POWER SEQUENCING -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-pm@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -21196,7 +21199,7 @@ F: Documentation/devicetree/bindings/i2c/qcom,i2c-cci.yaml F: drivers/i2c/busses/i2c-qcom-cci.c QUALCOMM INTERCONNECT BWMON DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-arm-msm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/interconnect/qcom,msm8998-bwmon.yaml @@ -21317,7 +21320,7 @@ F: Documentation/tee/qtee.rst F: drivers/tee/qcomtee/ QUALCOMM TRUST ZONE MEMORY ALLOCATOR -M: Bartosz Golaszewski <bartosz.golaszewski@linaro.org> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/firmware/qcom/qcom_tzmem.c @@ -22668,7 +22671,7 @@ F: arch/s390/mm S390 NETWORK DRIVERS M: Alexandra Winter <wintera@linux.ibm.com> -R: Aswin Karuvally <aswin@linux.ibm.com> +M: Aswin Karuvally <aswin@linux.ibm.com> L: linux-s390@vger.kernel.org L: netdev@vger.kernel.org S: Supported @@ -25685,7 +25688,7 @@ F: Documentation/devicetree/bindings/crypto/ti,am62l-dthev2.yaml F: drivers/crypto/ti/ TI DAVINCI MACHINE SUPPORT -M: Bartosz Golaszewski <brgl@bgdev.pl> +M: Bartosz Golaszewski <brgl@kernel.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git @@ -27107,7 +27110,7 @@ F: net/vmw_vsock/virtio_transport_common.c VIRTIO BALLOON M: "Michael S. Tsirkin" <mst@redhat.com> -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> L: virtualization@lists.linux.dev S: Maintained F: drivers/virtio/virtio_balloon.c @@ -27135,7 +27138,7 @@ S: Maintained F: drivers/char/virtio_console.c F: include/uapi/linux/virtio_console.h -VIRTIO CORE AND NET DRIVERS +VIRTIO CORE M: "Michael S. Tsirkin" <mst@redhat.com> M: Jason Wang <jasowang@redhat.com> R: Xuan Zhuo <xuanzhuo@linux.alibaba.com> @@ -27148,7 +27151,6 @@ F: Documentation/devicetree/bindings/virtio/ F: Documentation/driver-api/virtio/ F: drivers/block/virtio_blk.c F: drivers/crypto/virtio/ -F: drivers/net/virtio_net.c F: drivers/vdpa/ F: drivers/virtio/ F: include/linux/vdpa.h @@ -27157,7 +27159,6 @@ F: include/linux/vringh.h F: include/uapi/linux/virtio_*.h F: net/vmw_vsock/virtio* F: tools/virtio/ -F: tools/testing/selftests/drivers/net/virtio_net/ VIRTIO CRYPTO DRIVER M: Gonglei <arei.gonglei@huawei.com> @@ -27262,13 +27263,26 @@ F: drivers/iommu/virtio-iommu.c F: include/uapi/linux/virtio_iommu.h VIRTIO MEM DRIVER -M: David Hildenbrand <david@redhat.com> +M: David Hildenbrand <david@kernel.org> L: virtualization@lists.linux.dev S: Maintained W: https://virtio-mem.gitlab.io/ F: drivers/virtio/virtio_mem.c F: include/uapi/linux/virtio_mem.h +VIRTIO NET DRIVER +M: "Michael S. Tsirkin" <mst@redhat.com> +M: Jason Wang <jasowang@redhat.com> +R: Xuan Zhuo <xuanzhuo@linux.alibaba.com> +R: Eugenio Pérez <eperezma@redhat.com> +L: netdev@vger.kernel.org +L: virtualization@lists.linux.dev +S: Maintained +F: drivers/net/virtio_net.c +F: include/linux/virtio_net.h +F: include/uapi/linux/virtio_net.h +F: tools/testing/selftests/drivers/net/virtio_net/ + VIRTIO PMEM DRIVER M: Pankaj Gupta <pankaj.gupta.linux@gmail.com> L: virtualization@lists.linux.dev @@ -27868,7 +27882,7 @@ F: arch/x86/kernel/stacktrace.c F: arch/x86/kernel/unwind_*.c X86 TRUST DOMAIN EXTENSIONS (TDX) -M: Kirill A. Shutemov <kas@kernel.org> +M: Kiryl Shutsemau <kas@kernel.org> R: Dave Hansen <dave.hansen@linux.intel.com> R: Rick Edgecombe <rick.p.edgecombe@intel.com> L: x86@kernel.org @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-fuji-data64.dts b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-fuji-data64.dts index aa9576d8ab56..48ca25f57ef6 100644 --- a/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-fuji-data64.dts +++ b/arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-fuji-data64.dts @@ -1254,3 +1254,17 @@ max-frequency = <25000000>; bus-width = <4>; }; + +/* + * FIXME: rgmii delay is introduced by MAC (configured in u-boot now) + * instead of PCB on fuji board, so the "phy-mode" should be updated to + * "rgmii-[tx|rx]id" when the aspeed-mac driver can handle the delay + * properly. + */ +&mac3 { + status = "okay"; + phy-mode = "rgmii"; + phy-handle = <ðphy3>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_rgmii4_default>; +}; diff --git a/arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dts b/arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dts index ac44c745bdf8..a39a021a3910 100644 --- a/arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dts +++ b/arch/arm/boot/dts/broadcom/bcm47189-luxul-xap-1440.dts @@ -55,8 +55,8 @@ mdio { /delete-node/ switch@1e; - bcm54210e: ethernet-phy@0 { - reg = <0>; + bcm54210e: ethernet-phy@25 { + reg = <25>; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts index 06545a6052f7..43ff5eafb2bb 100644 --- a/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts +++ b/arch/arm/boot/dts/nxp/imx/imx51-zii-rdu1.dts @@ -259,7 +259,7 @@ pinctrl-0 = <&pinctrl_audmux>; status = "okay"; - ssi2 { + mux-ssi2 { fsl,audmux-port = <1>; fsl,port-config = < (IMX_AUDMUX_V2_PTCR_SYN | @@ -271,7 +271,7 @@ >; }; - aud3 { + mux-aud3 { fsl,audmux-port = <2>; fsl,port-config = < IMX_AUDMUX_V2_PTCR_SYN diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-rmm.dts b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-rmm.dts index 107b00b9a939..540642e99a41 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-rmm.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6ull-engicam-microgea-rmm.dts @@ -136,7 +136,7 @@ interrupt-parent = <&gpio2>; interrupts = <8 IRQ_TYPE_EDGE_FALLING>; reset-gpios = <&gpio2 14 GPIO_ACTIVE_LOW>; - report-rate-hz = <6>; + report-rate-hz = <60>; /* settings valid only for Hycon touchscreen */ touchscreen-size-x = <1280>; touchscreen-size-y = <800>; diff --git a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts index b8f256545022..3e0319fdb93f 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts +++ b/arch/arm64/boot/dts/broadcom/bcm2712-rpi-5-b.dts @@ -18,11 +18,21 @@ #include "bcm2712-rpi-5-b-ovl-rp1.dts" +/ { + aliases { + ethernet0 = &rp1_eth; + }; +}; + &pcie2 { #include "rp1-nexus.dtsi" }; &rp1_eth { + assigned-clocks = <&rp1_clocks RP1_CLK_ETH_TSU>, + <&rp1_clocks RP1_CLK_ETH>; + assigned-clock-rates = <50000000>, + <125000000>; status = "okay"; phy-mode = "rgmii-id"; phy-handle = <&phy1>; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-img.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-img.dtsi index 2cf0f7208350..a72b2f1c4a1b 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-img.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-img.dtsi @@ -67,7 +67,6 @@ img_subsys: bus@58000000 { power-domains = <&pd IMX_SC_R_CSI_0>; fsl,channel = <0>; fsl,num-irqs = <32>; - status = "disabled"; }; gpio0_mipi_csi0: gpio@58222000 { @@ -144,7 +143,6 @@ img_subsys: bus@58000000 { power-domains = <&pd IMX_SC_R_CSI_1>; fsl,channel = <0>; fsl,num-irqs = <32>; - status = "disabled"; }; gpio0_mipi_csi1: gpio@58242000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-kontron-bl-osm-s.dts b/arch/arm64/boot/dts/freescale/imx8mp-kontron-bl-osm-s.dts index 614b4ce330b1..0924ac50fd2d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-kontron-bl-osm-s.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-kontron-bl-osm-s.dts @@ -16,11 +16,20 @@ ethernet1 = &eqos; }; - extcon_usbc: usbc { - compatible = "linux,extcon-usb-gpio"; + connector { + compatible = "gpio-usb-b-connector", "usb-b-connector"; + id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; + label = "Type-C"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usb1_id>; - id-gpios = <&gpio1 10 GPIO_ACTIVE_HIGH>; + type = "micro"; + vbus-supply = <®_usb1_vbus>; + + port { + usb_dr_connector: endpoint { + remote-endpoint = <&usb3_dwc>; + }; + }; }; leds { @@ -244,9 +253,15 @@ hnp-disable; srp-disable; dr_mode = "otg"; - extcon = <&extcon_usbc>; usb-role-switch; + role-switch-default-mode = "peripheral"; status = "okay"; + + port { + usb3_dwc: endpoint { + remote-endpoint = <&usb_dr_connector>; + }; + }; }; &usb_dwc3_1 { @@ -273,7 +288,6 @@ }; &usb3_phy0 { - vbus-supply = <®_usb1_vbus>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 1292677cbe4e..6da961eb3fe5 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1886,7 +1886,7 @@ assigned-clock-rates = <3600000000>, <100000000>, <10000000>; assigned-clock-parents = <0>, <0>, <&scmi_clk IMX95_CLK_SYSPLL1_PFD1_DIV2>; - msi-map = <0x0 &its 0x98 0x1>; + msi-map = <0x0 &its 0x10 0x1>; power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>; status = "disabled"; }; @@ -1963,6 +1963,7 @@ assigned-clock-rates = <3600000000>, <100000000>, <10000000>; assigned-clock-parents = <0>, <0>, <&scmi_clk IMX95_CLK_SYSPLL1_PFD1_DIV2>; + msi-map = <0x0 &its 0x98 0x1>; power-domains = <&scmi_devpd IMX95_PD_HSIO_TOP>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi index a410fc335fa3..c0f17f8189fa 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi @@ -42,6 +42,7 @@ interrupt-parent = <&gpio>; interrupts = <TEGRA194_MAIN_GPIO(G, 4) IRQ_TYPE_LEVEL_LOW>; #phy-cells = <0>; + wakeup-source; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 283d9cbc4368..03b7c4313750 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -598,7 +598,6 @@ pinctrl-2 = <&otp_pin>; resets = <&cru SRST_TSADC>; reset-names = "tsadc-apb"; - rockchip,grf = <&grf>; rockchip,hw-tshut-temp = <100000>; #thermal-sensor-cells = <1>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-op1.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-op1.dtsi index c4f4f1ff6117..9da6fd82e46b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-op1.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-op1.dtsi @@ -3,7 +3,7 @@ * Copyright (c) 2016-2017 Fuzhou Rockchip Electronics Co., Ltd */ -#include "rk3399.dtsi" +#include "rk3399-base.dtsi" / { cluster0_opp: opp-table-0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso index 5e8f729c2cf2..141a921a06e4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso @@ -45,11 +45,11 @@ cam_dovdd_1v8: regulator-cam-dovdd-1v8 { compatible = "regulator-fixed"; - gpio = <&pca9670 3 GPIO_ACTIVE_LOW>; - regulator-max-microvolt = <1800000>; - regulator-min-microvolt = <1800000>; - regulator-name = "cam-dovdd-1v8"; - vin-supply = <&vcc1v8_video>; + gpio = <&pca9670 3 GPIO_ACTIVE_LOW>; + regulator-max-microvolt = <1800000>; + regulator-min-microvolt = <1800000>; + regulator-name = "cam-dovdd-1v8"; + vin-supply = <&vcc1v8_video>; }; cam_dvdd_1v2: regulator-cam-dvdd-1v2 { diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi index 7f578c50b4ad..b6cf03a7ba66 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi @@ -120,7 +120,7 @@ compatible = "regulator-fixed"; regulator-name = "vcc3v3_pcie"; enable-active-high; - gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_HIGH>; + gpios = <&gpio4 RK_PB1 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&pcie_drv>; regulator-always-on; @@ -187,7 +187,7 @@ vcc5v0_usb2b: regulator-vcc5v0-usb2b { compatible = "regulator-fixed"; enable-active-high; - gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; + gpio = <&gpio4 RK_PC4 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_usb2b_en>; regulator-name = "vcc5v0_usb2b"; @@ -199,7 +199,7 @@ vcc5v0_usb2t: regulator-vcc5v0-usb2t { compatible = "regulator-fixed"; enable-active-high; - gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>; + gpios = <&gpio3 RK_PD5 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_usb2t_en>; regulator-name = "vcc5v0_usb2t"; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi index d0e38412d56a..08bf40de17ea 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi @@ -789,7 +789,7 @@ vccio1-supply = <&vccio_acodec>; vccio2-supply = <&vcc_1v8>; vccio3-supply = <&vccio_sd>; - vccio4-supply = <&vcc_1v8>; + vccio4-supply = <&vcca1v8_pmu>; vccio5-supply = <&vcc_1v8>; vccio6-supply = <&vcc1v8_dvp>; vccio7-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts index 0f844806ec54..442a2bc43ba8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts @@ -482,6 +482,8 @@ }; &i2s1_8ch { + pinctrl-names = "default"; + pinctrl-0 = <&i2s1m0_sclktx &i2s1m0_lrcktx &i2s1m0_sdi0 &i2s1m0_sdo0>; rockchip,trcm-sync-tx-only; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index fc4e9e07f1cf..a86fc6b4e8c4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -276,12 +276,6 @@ opp-microvolt = <900000 900000 950000>; clock-latency-ns = <40000>; }; - - opp-2208000000 { - opp-hz = /bits/ 64 <2208000000>; - opp-microvolt = <950000 950000 950000>; - clock-latency-ns = <40000>; - }; }; cluster1_opp_table: opp-table-cluster1 { @@ -348,12 +342,6 @@ opp-microvolt = <925000 925000 950000>; clock-latency-ns = <40000>; }; - - opp-2304000000 { - opp-hz = /bits/ 64 <2304000000>; - opp-microvolt = <950000 950000 950000>; - clock-latency-ns = <40000>; - }; }; gpu_opp_table: opp-table-gpu { @@ -2561,8 +2549,6 @@ interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&i2c9m0_xfer>; - resets = <&cru SRST_I2C9>, <&cru SRST_P_I2C9>; - reset-names = "i2c", "apb"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-opp.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-opp.dtsi index 0f1a77697351..b5d630d2c879 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-opp.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-opp.dtsi @@ -115,7 +115,7 @@ }; }; - gpu_opp_table: opp-table { + gpu_opp_table: opp-table-gpu { compatible = "operating-points-v2"; opp-300000000 { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi index b44e89e1bb15..365c1d958f2d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi @@ -382,14 +382,12 @@ cap-mmc-highspeed; mmc-ddr-1_8v; mmc-hs200-1_8v; - mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; mmc-pwrseq = <&emmc_pwrseq>; no-sdio; no-sd; non-removable; pinctrl-names = "default"; - pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>; + pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk>; vmmc-supply = <&vcc_3v3_s3>; vqmmc-supply = <&vcc_1v8_s3>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi index 9884a5df47df..e1e0e3fc0ca7 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi @@ -66,7 +66,7 @@ }; }; - gpu_opp_table: opp-table { + gpu_opp_table: opp-table-gpu { compatible = "operating-points-v2"; opp-300000000 { diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts index ad6d04793b0a..83b9b6645a1e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-orangepi-5.dts @@ -14,8 +14,8 @@ gpios = <&gpio0 RK_PC5 GPIO_ACTIVE_HIGH>; regulator-name = "vcc3v3_pcie20"; regulator-boot-on; - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <1800000>; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; startup-delay-us = <50000>; vin-supply = <&vcc5v0_sys>; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index e3a2d37bd104..1a48faad2473 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1341,7 +1341,7 @@ CONFIG_COMMON_CLK_RS9_PCIE=y CONFIG_COMMON_CLK_VC3=y CONFIG_COMMON_CLK_VC5=y CONFIG_COMMON_CLK_BD718XX=m -CONFIG_CLK_RASPBERRYPI=m +CONFIG_CLK_RASPBERRYPI=y CONFIG_CLK_IMX8MM=y CONFIG_CLK_IMX8MN=y CONFIG_CLK_IMX8MP=y diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 2312e6ee595f..258cca4b4873 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -33,8 +33,8 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr); #define vma_alloc_zeroed_movable_folio vma_alloc_zeroed_movable_folio -void tag_clear_highpage(struct page *to); -#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGE +bool tag_clear_highpages(struct page *to, int numpages); +#define __HAVE_ARCH_TAG_CLEAR_HIGHPAGES #define clear_user_page(page, vaddr, pg) clear_page(page) #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index c022c1acb8c7..f1cb2447afc9 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -351,16 +351,6 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) * as long as we take care not to create a writable * mapping for executable code. */ - fallthrough; - - case EFI_ACPI_MEMORY_NVS: - /* - * ACPI NVS marks an area reserved for use by the - * firmware, even after exiting the boot service. - * This may be used by the firmware for sharing dynamic - * tables/data (e.g., ACPI CCEL) with the OS. Map it - * as read-only. - */ prot = PAGE_KERNEL_RO; break; diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c7d70d04c164..80a580e019c5 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -1032,6 +1032,8 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { /* No point mitigating Spectre-BHB alone. */ + } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { + /* Do nothing */ } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; set_bit(BHB_HW, &system_bhb_mitigations); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 870953b4a8a7..052bf0d4d0b0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -624,6 +624,7 @@ nommu: kvm_timer_vcpu_load(vcpu); kvm_vgic_load(vcpu); kvm_vcpu_load_debug(vcpu); + kvm_vcpu_load_fgt(vcpu); if (has_vhe()) kvm_vcpu_load_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); @@ -642,7 +643,6 @@ nommu: vcpu->arch.hcr_el2 |= HCR_TWI; vcpu_set_pauth_traps(vcpu); - kvm_vcpu_load_fgt(vcpu); if (is_protected_kvm_enabled()) { kvm_call_hyp_nvhe(__pkvm_vcpu_load, diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 8ae2bca81614..ec3fbe0b8d52 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -5609,7 +5609,11 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) guard(mutex)(&kvm->arch.config_lock); - if (!irqchip_in_kernel(kvm)) { + /* + * This hacks into the ID registers, so only perform it when the + * first vcpu runs, or the kvm_set_vm_id_reg() helper will scream. + */ + if (!irqchip_in_kernel(kvm) && !kvm_vm_has_ran_once(kvm)) { u64 val; val = kvm_read_vm_id_reg(kvm, SYS_ID_AA64PFR0_EL1) & ~ID_AA64PFR0_EL1_GIC; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 125dfa6c613b..a193b6a5d1e6 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -967,20 +967,21 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, return vma_alloc_folio(flags, 0, vma, vaddr); } -void tag_clear_highpage(struct page *page) +bool tag_clear_highpages(struct page *page, int numpages) { /* * Check if MTE is supported and fall back to clear_highpage(). * get_huge_zero_folio() unconditionally passes __GFP_ZEROTAGS and - * post_alloc_hook() will invoke tag_clear_highpage(). + * post_alloc_hook() will invoke tag_clear_highpages(). */ - if (!system_supports_mte()) { - clear_highpage(page); - return; - } + if (!system_supports_mte()) + return false; - /* Newly allocated page, shouldn't have been tagged yet */ - WARN_ON_ONCE(!try_page_mte_tagging(page)); - mte_zero_clear_page_tags(page_address(page)); - set_page_mte_tagged(page); + /* Newly allocated pages, shouldn't have been tagged yet */ + for (int i = 0; i < numpages; i++, page++) { + WARN_ON_ONCE(!try_page_mte_tagging(page)); + mte_zero_clear_page_tags(page_address(page)); + set_page_mte_tagged(page); + } + return true; } diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index d4cd4041bee7..f3efb00b6141 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -55,6 +55,27 @@ enum cpu_type_enum { CPU_LAST }; +static inline char *id_to_core_name(unsigned int id) +{ + if ((id & PRID_COMP_MASK) != PRID_COMP_LOONGSON) + return "Unknown"; + + switch (id & PRID_SERIES_MASK) { + case PRID_SERIES_LA132: + return "LA132"; + case PRID_SERIES_LA264: + return "LA264"; + case PRID_SERIES_LA364: + return "LA364"; + case PRID_SERIES_LA464: + return "LA464"; + case PRID_SERIES_LA664: + return "LA664"; + default: + return "Unknown"; + } +} + #endif /* !__ASSEMBLER__ */ /* diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index aafb3cd9e943..215e0f9e8aa3 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -10,10 +10,6 @@ #include <linux/types.h> -#ifndef __KERNEL__ -#include <stdint.h> -#endif - /* * For PTRACE_{POKE,PEEK}USR. 0 - 31 are GPRs, * 32 is syscall's original ARG0, 33 is PC, 34 is BADVADDR. @@ -41,44 +37,44 @@ struct user_pt_regs { } __attribute__((aligned(8))); struct user_fp_state { - uint64_t fpr[32]; - uint64_t fcc; - uint32_t fcsr; + __u64 fpr[32]; + __u64 fcc; + __u32 fcsr; }; struct user_lsx_state { /* 32 registers, 128 bits width per register. */ - uint64_t vregs[32*2]; + __u64 vregs[32*2]; }; struct user_lasx_state { /* 32 registers, 256 bits width per register. */ - uint64_t vregs[32*4]; + __u64 vregs[32*4]; }; struct user_lbt_state { - uint64_t scr[4]; - uint32_t eflags; - uint32_t ftop; + __u64 scr[4]; + __u32 eflags; + __u32 ftop; }; struct user_watch_state { - uint64_t dbg_info; + __u64 dbg_info; struct { - uint64_t addr; - uint64_t mask; - uint32_t ctrl; - uint32_t pad; + __u64 addr; + __u64 mask; + __u32 ctrl; + __u32 pad; } dbg_regs[8]; }; struct user_watch_state_v2 { - uint64_t dbg_info; + __u64 dbg_info; struct { - uint64_t addr; - uint64_t mask; - uint32_t ctrl; - uint32_t pad; + __u64 addr; + __u64 mask; + __u32 ctrl; + __u32 pad; } dbg_regs[14]; }; diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 6f943d1391ff..a2060a24b39f 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -277,7 +277,7 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int uint32_t config; uint64_t *vendor = (void *)(&cpu_full_name[VENDOR_OFFSET]); uint64_t *cpuname = (void *)(&cpu_full_name[CPUNAME_OFFSET]); - const char *core_name = "Unknown"; + const char *core_name = id_to_core_name(c->processor_id); switch (BIT(fls(c->isa_level) - 1)) { case LOONGARCH_CPU_ISA_LA32R: @@ -291,35 +291,23 @@ static inline void cpu_probe_loongson(struct cpuinfo_loongarch *c, unsigned int break; } - switch (c->processor_id & PRID_SERIES_MASK) { - case PRID_SERIES_LA132: - core_name = "LA132"; - break; - case PRID_SERIES_LA264: - core_name = "LA264"; - break; - case PRID_SERIES_LA364: - core_name = "LA364"; - break; - case PRID_SERIES_LA464: - core_name = "LA464"; - break; - case PRID_SERIES_LA664: - core_name = "LA664"; - break; - } - pr_info("%s Processor probed (%s Core)\n", __cpu_family[cpu], core_name); - if (!cpu_has_iocsr) + if (!cpu_has_iocsr) { + __cpu_full_name[cpu] = "Unknown"; return; - - if (!__cpu_full_name[cpu]) - __cpu_full_name[cpu] = cpu_full_name; + } *vendor = iocsr_read64(LOONGARCH_IOCSR_VENDOR); *cpuname = iocsr_read64(LOONGARCH_IOCSR_CPUNAME); + if (!__cpu_full_name[cpu]) { + if (((char *)vendor)[0] == 0) + __cpu_full_name[cpu] = "Unknown"; + else + __cpu_full_name[cpu] = cpu_full_name; + } + config = iocsr_read32(LOONGARCH_IOCSR_FEATURES); if (config & IOCSRF_CSRIPI) c->options |= LOONGARCH_CPU_CSRIPI; diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c index 2d64b7c81e5e..d7fafda1d541 100644 --- a/arch/loongarch/kernel/machine_kexec.c +++ b/arch/loongarch/kernel/machine_kexec.c @@ -237,6 +237,7 @@ void machine_crash_shutdown(struct pt_regs *regs) #ifdef CONFIG_SMP crash_smp_send_stop(); #endif + machine_kexec_mask_interrupts(); cpumask_set_cpu(crashing_cpu, &cpus_in_crash); pr_info("Starting crashdump kernel...\n"); @@ -274,6 +275,7 @@ void machine_kexec(struct kimage *image) /* We do not want to be bothered. */ local_irq_disable(); + machine_kexec_mask_interrupts(); pr_notice("EFI boot flag: 0x%lx\n", efi_boot); pr_notice("Command line addr: 0x%lx\n", cmdline_ptr); diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index ab9c660526a3..8b89898e20df 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -158,35 +158,9 @@ static void __init node_mem_init(unsigned int node) #ifdef CONFIG_ACPI_NUMA -/* - * add_numamem_region - * - * Add a uasable memory region described by BIOS. The - * routine gets each intersection between BIOS's region - * and node's region, and adds them into node's memblock - * pool. - * - */ -static void __init add_numamem_region(u64 start, u64 end, u32 type) -{ - u32 node = pa_to_nid(start); - u64 size = end - start; - static unsigned long num_physpages; - - if (start >= end) { - pr_debug("Invalid region: %016llx-%016llx\n", start, end); - return; - } +static unsigned long num_physpages; - num_physpages += (size >> PAGE_SHIFT); - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", - node, type, start, size); - pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", - start >> PAGE_SHIFT, end >> PAGE_SHIFT, num_physpages); - memblock_set_node(start, size, &memblock.memory, node); -} - -static void __init init_node_memblock(void) +static void __init info_node_memblock(void) { u32 mem_type; u64 mem_end, mem_start, mem_size; @@ -206,12 +180,20 @@ static void __init init_node_memblock(void) case EFI_BOOT_SERVICES_DATA: case EFI_PERSISTENT_MEMORY: case EFI_CONVENTIONAL_MEMORY: - add_numamem_region(mem_start, mem_end, mem_type); + num_physpages += (mem_size >> PAGE_SHIFT); + pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", + (u32)pa_to_nid(mem_start), mem_type, mem_start, mem_size); + pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", + mem_start >> PAGE_SHIFT, mem_end >> PAGE_SHIFT, num_physpages); break; case EFI_PAL_CODE: case EFI_UNUSABLE_MEMORY: case EFI_ACPI_RECLAIM_MEMORY: - add_numamem_region(mem_start, mem_end, mem_type); + num_physpages += (mem_size >> PAGE_SHIFT); + pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx Bytes\n", + (u32)pa_to_nid(mem_start), mem_type, mem_start, mem_size); + pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", + mem_start >> PAGE_SHIFT, mem_end >> PAGE_SHIFT, num_physpages); fallthrough; case EFI_RESERVED_TYPE: case EFI_RUNTIME_SERVICES_CODE: @@ -249,22 +231,16 @@ int __init init_numa_memory(void) for (i = 0; i < NR_CPUS; i++) set_cpuid_to_node(i, NUMA_NO_NODE); - numa_reset_distance(); - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - WARN_ON(memblock_clear_hotplug(0, PHYS_ADDR_MAX)); - /* Parse SRAT and SLIT if provided by firmware. */ - ret = acpi_disabled ? fake_numa_init() : acpi_numa_init(); + if (!acpi_disabled) + ret = numa_memblks_init(acpi_numa_init, false); + else + ret = numa_memblks_init(fake_numa_init, false); + if (ret < 0) return ret; - node_possible_map = numa_nodes_parsed; - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - init_node_memblock(); + info_node_memblock(); if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index cea30768ae92..63d2b7e7e844 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -17,6 +17,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; unsigned int isa = cpu_data[n].isa_level; + unsigned int prid = cpu_data[n].processor_id; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; @@ -37,6 +38,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "global_id\t\t: %d\n", cpu_data[n].global_id); seq_printf(m, "CPU Family\t\t: %s\n", __cpu_family[n]); seq_printf(m, "Model Name\t\t: %s\n", __cpu_full_name[n]); + seq_printf(m, "PRID\t\t\t: %s (%08x)\n", id_to_core_name(prid), prid); seq_printf(m, "CPU Revision\t\t: 0x%02x\n", version); seq_printf(m, "FPU Revision\t\t: 0x%02x\n", fp_version); seq_printf(m, "CPU MHz\t\t\t: %llu.%02llu\n", diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index cbe53d0b7fb0..f97dc9936401 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1624,6 +1624,9 @@ static int __arch_prepare_bpf_trampoline(struct jit_ctx *ctx, struct bpf_tramp_i /* Direct jump skips 5 NOP instructions */ else if (is_bpf_text_address((unsigned long)orig_call)) orig_call += LOONGARCH_BPF_FENTRY_NBYTES; + /* Module tracing not supported - cause kernel lockups */ + else if (is_module_text_address((unsigned long)orig_call)) + return -ENOTSUPP; if (flags & BPF_TRAMP_F_CALL_ORIG) { move_addr(ctx, LOONGARCH_GPR_A0, (const u64)im); diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c index 5bc9627a6cf9..d9fc5d520b37 100644 --- a/arch/loongarch/pci/pci.c +++ b/arch/loongarch/pci/pci.c @@ -50,11 +50,11 @@ static int __init pcibios_init(void) */ lsize = cpu_last_level_cache_line_size(); - BUG_ON(!lsize); + if (lsize) { + pci_dfl_cache_line_size = lsize >> 2; - pci_dfl_cache_line_size = lsize >> 2; - - pr_debug("PCI: pci_cache_line_size set to %d bytes\n", lsize); + pr_debug("PCI: pci_cache_line_size set to %d bytes\n", lsize); + } return 0; } diff --git a/arch/mips/boot/dts/econet/en751221.dtsi b/arch/mips/boot/dts/econet/en751221.dtsi index 66197e73d4f0..2abeef5b744a 100644 --- a/arch/mips/boot/dts/econet/en751221.dtsi +++ b/arch/mips/boot/dts/econet/en751221.dtsi @@ -18,7 +18,7 @@ cpu@0 { device_type = "cpu"; - compatible = "mips,mips24KEc"; + compatible = "mips,mips34Kc"; reg = <0>; }; }; diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 29191fa1801e..a3101f2268c6 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -692,7 +692,7 @@ unsigned long mips_stack_top(void) /* Space for the VDSO, data page & GIC user page */ if (current->thread.abi) { top -= PAGE_ALIGN(current->thread.abi->vdso->size); - top -= PAGE_SIZE; + top -= VDSO_NR_PAGES * PAGE_SIZE; top -= mips_gic_present() ? PAGE_SIZE : 0; /* Space to randomize the VDSO base */ diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 347126dc010d..3facf7cc6c7d 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/export.h> +#include <linux/sort.h> #include <asm/cpu.h> #include <asm/cpu-type.h> @@ -508,54 +509,78 @@ static int __init set_ntlb(char *str) __setup("ntlb=", set_ntlb); -/* Initialise all TLB entries with unique values */ + +/* Comparison function for EntryHi VPN fields. */ +static int r4k_vpn_cmp(const void *a, const void *b) +{ + long v = *(unsigned long *)a - *(unsigned long *)b; + int s = sizeof(long) > sizeof(int) ? sizeof(long) * 8 - 1: 0; + return s ? (v != 0) | v >> s : v; +} + +/* + * Initialise all TLB entries with unique values that do not clash with + * what we have been handed over and what we'll be using ourselves. + */ static void r4k_tlb_uniquify(void) { - int entry = num_wired_entries(); + unsigned long tlb_vpns[1 << MIPS_CONF1_TLBS_SIZE]; + int tlbsize = current_cpu_data.tlbsize; + int start = num_wired_entries(); + unsigned long vpn_mask; + int cnt, ent, idx, i; + + vpn_mask = GENMASK(cpu_vmbits - 1, 13); + vpn_mask |= IS_ENABLED(CONFIG_64BIT) ? 3ULL << 62 : 1 << 31; htw_stop(); + + for (i = start, cnt = 0; i < tlbsize; i++, cnt++) { + unsigned long vpn; + + write_c0_index(i); + mtc0_tlbr_hazard(); + tlb_read(); + tlb_read_hazard(); + vpn = read_c0_entryhi(); + vpn &= vpn_mask & PAGE_MASK; + tlb_vpns[cnt] = vpn; + + /* Prevent any large pages from overlapping regular ones. */ + write_c0_pagemask(read_c0_pagemask() & PM_DEFAULT_MASK); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + tlbw_use_hazard(); + } + + sort(tlb_vpns, cnt, sizeof(tlb_vpns[0]), r4k_vpn_cmp, NULL); + + write_c0_pagemask(PM_DEFAULT_MASK); write_c0_entrylo0(0); write_c0_entrylo1(0); - while (entry < current_cpu_data.tlbsize) { - unsigned long asid_mask = cpu_asid_mask(¤t_cpu_data); - unsigned long asid = 0; - int idx; + idx = 0; + ent = tlbsize; + for (i = start; i < tlbsize; i++) + while (1) { + unsigned long entryhi, vpn; - /* Skip wired MMID to make ginvt_mmid work */ - if (cpu_has_mmid) - asid = MMID_KERNEL_WIRED + 1; + entryhi = UNIQUE_ENTRYHI(ent); + vpn = entryhi & vpn_mask & PAGE_MASK; - /* Check for match before using UNIQUE_ENTRYHI */ - do { - if (cpu_has_mmid) { - write_c0_memorymapid(asid); - write_c0_entryhi(UNIQUE_ENTRYHI(entry)); + if (idx >= cnt || vpn < tlb_vpns[idx]) { + write_c0_entryhi(entryhi); + write_c0_index(i); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + ent++; + break; + } else if (vpn == tlb_vpns[idx]) { + ent++; } else { - write_c0_entryhi(UNIQUE_ENTRYHI(entry) | asid); + idx++; } - mtc0_tlbw_hazard(); - tlb_probe(); - tlb_probe_hazard(); - idx = read_c0_index(); - /* No match or match is on current entry */ - if (idx < 0 || idx == entry) - break; - /* - * If we hit a match, we need to try again with - * a different ASID. - */ - asid++; - } while (asid < asid_mask); - - if (idx >= 0 && idx != entry) - panic("Unable to uniquify TLB entry %d", idx); - - write_c0_index(entry); - mtc0_tlbw_hazard(); - tlb_write_indexed(); - entry++; - } + } tlbw_use_hazard(); htw_start(); @@ -602,6 +627,7 @@ static void r4k_tlb_configure(void) /* From this point on the ARC firmware is dead. */ r4k_tlb_uniquify(); + local_flush_tlb_all(); /* Did I tell you that ARC SUCKS? */ } diff --git a/arch/mips/mti-malta/malta-init.c b/arch/mips/mti-malta/malta-init.c index 000d6d50520a..82b0fd8576a2 100644 --- a/arch/mips/mti-malta/malta-init.c +++ b/arch/mips/mti-malta/malta-init.c @@ -241,16 +241,22 @@ mips_pci_controller: #endif /* - * Setup the Malta max (2GB) memory for PCI DMA in host bridge - * in transparent addressing mode. + * Set up memory mapping in host bridge for PCI DMA masters, + * in transparent addressing mode. For EVA use the Malta + * maximum of 2 GiB memory in the alias space at 0x80000000 + * as per PHYS_OFFSET. Otherwise use 256 MiB of memory in + * the regular space, avoiding mapping the PCI MMIO window + * for DMA as it seems to confuse the system controller's + * logic, causing PCI MMIO to stop working. */ - mask = PHYS_OFFSET | PCI_BASE_ADDRESS_MEM_PREFETCH; - MSC_WRITE(MSC01_PCI_BAR0, mask); - MSC_WRITE(MSC01_PCI_HEAD4, mask); + mask = PHYS_OFFSET ? PHYS_OFFSET : 0xf0000000; + MSC_WRITE(MSC01_PCI_BAR0, + mask | PCI_BASE_ADDRESS_MEM_PREFETCH); + MSC_WRITE(MSC01_PCI_HEAD4, + PHYS_OFFSET | PCI_BASE_ADDRESS_MEM_PREFETCH); - mask &= MSC01_PCI_BAR0_SIZE_MSK; MSC_WRITE(MSC01_PCI_P2SCMSKL, mask); - MSC_WRITE(MSC01_PCI_P2SCMAPL, mask); + MSC_WRITE(MSC01_PCI_P2SCMAPL, PHYS_OFFSET); /* Don't handle target retries indefinitely. */ if ((data & MSC01_PCI_CFG_MAXRTRY_MSK) == diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e24f4d88885a..9537a61ebae0 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -137,6 +137,7 @@ config PPC select ARCH_HAS_DMA_OPS if PPC64 select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE if ARCH_SUPPORTS_HUGETLBFS select ARCH_HAS_KCOV select ARCH_HAS_KERNEL_FPU_SUPPORT if PPC64 && PPC_FPU select ARCH_HAS_MEMBARRIER_CALLBACKS diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 7b527d18aa5e..4c321a8ea896 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -423,7 +423,6 @@ config PPC_64S_HASH_MMU config PPC_RADIX_MMU bool "Radix MMU Support" depends on PPC_BOOK3S_64 - select ARCH_HAS_GIGANTIC_PAGE default y help Enable support for the Power ISA 3.0 Radix style MMU. Currently this diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h index 3b09874d7a6d..7f5030ee1fcf 100644 --- a/arch/riscv/include/asm/vendorid_list.h +++ b/arch/riscv/include/asm/vendorid_list.h @@ -7,8 +7,8 @@ #define ANDES_VENDOR_ID 0x31e #define MICROCHIP_VENDOR_ID 0x029 +#define MIPS_VENDOR_ID 0x127 #define SIFIVE_VENDOR_ID 0x489 #define THEAD_VENDOR_ID 0x5b7 -#define MIPS_VENDOR_ID 0x722 #endif diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index 5e8cde055264..c443337056ab 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -648,9 +648,9 @@ int sbi_debug_console_read(char *bytes, unsigned int num_bytes) void __init sbi_init(void) { + bool srst_power_off = false; int ret; - sbi_set_power_off(); ret = sbi_get_spec_version(); if (ret > 0) sbi_spec_version = ret; @@ -683,6 +683,7 @@ void __init sbi_init(void) sbi_probe_extension(SBI_EXT_SRST)) { pr_info("SBI SRST extension detected\n"); register_platform_power_off(sbi_srst_power_off); + srst_power_off = true; sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot; sbi_srst_reboot_nb.priority = 192; register_restart_handler(&sbi_srst_reboot_nb); @@ -702,4 +703,7 @@ void __init sbi_init(void) __sbi_send_ipi = __sbi_send_ipi_v01; __sbi_rfence = __sbi_rfence_v01; } + + if (!srst_power_off) + sbi_set_power_off(); } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b7100c6a4054..6663f1619abb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1154,17 +1154,15 @@ static inline pte_t pte_mkhuge(pte_t pte) #define IPTE_NODAT 0x400 #define IPTE_GUEST_ASCE 0x800 -static __always_inline void __ptep_rdp(unsigned long addr, pte_t *ptep, - unsigned long opt, unsigned long asce, - int local) +static __always_inline void __ptep_rdp(unsigned long addr, pte_t *ptep, int local) { unsigned long pto; pto = __pa(ptep) & ~(PTRS_PER_PTE * sizeof(pte_t) - 1); - asm volatile(".insn rrf,0xb98b0000,%[r1],%[r2],%[asce],%[m4]" + asm volatile(".insn rrf,0xb98b0000,%[r1],%[r2],%%r0,%[m4]" : "+m" (*ptep) - : [r1] "a" (pto), [r2] "a" ((addr & PAGE_MASK) | opt), - [asce] "a" (asce), [m4] "i" (local)); + : [r1] "a" (pto), [r2] "a" (addr & PAGE_MASK), + [m4] "i" (local)); } static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep, @@ -1348,7 +1346,7 @@ static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma, * A local RDP can be used to do the flush. */ if (cpu_has_rdp() && !(pte_val(*ptep) & _PAGE_PROTECT)) - __ptep_rdp(address, ptep, 0, 0, 1); + __ptep_rdp(address, ptep, 1); } #define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 0fde20bbc50b..05974304d622 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -274,9 +274,9 @@ void ptep_reset_dat_prot(struct mm_struct *mm, unsigned long addr, pte_t *ptep, preempt_disable(); atomic_inc(&mm->context.flush_count); if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) - __ptep_rdp(addr, ptep, 0, 0, 1); + __ptep_rdp(addr, ptep, 1); else - __ptep_rdp(addr, ptep, 0, 0, 0); + __ptep_rdp(addr, ptep, 0); /* * PTE is not invalidated by RDP, only _PAGE_PROTECT is cleared. That * means it is still valid and active, and must not be changed according diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 745caa6c15a3..fa6c47b50989 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2789,13 +2789,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; - - if (perf_hw_regs(regs)) + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; unwind_start(&state, current, regs, NULL); - else + } else { unwind_start(&state, current, NULL, (void *)regs->sp); + } for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d6c945cc5d07..e228e564b15e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1325,8 +1325,6 @@ static void uncore_pci_sub_driver_init(void) continue; pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)]; - if (!pmu) - continue; if (uncore_pci_get_dev_die_info(pci_sub_dev, &die)) continue; diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 93156ac4ffe0..b08c95872eed 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,6 +56,11 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &arch_ftrace_regs(fregs)->regs; } +#define arch_ftrace_partial_regs(regs) do { \ + regs->flags &= ~X86_EFLAGS_FIXED; \ + regs->cs = __KERNEL_CS; \ +} while (0) + #define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c index 7047124490f6..d7c8ef1e354d 100644 --- a/arch/x86/kernel/acpi/cppc.c +++ b/arch/x86/kernel/acpi/cppc.c @@ -196,7 +196,7 @@ int amd_detect_prefcore(bool *detected) break; } - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { u32 tmp; int ret; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2ba9f2d42d8c..5d46709c58d0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1037,7 +1037,14 @@ static void init_amd_zen4(struct cpuinfo_x86 *c) static const struct x86_cpu_id zen5_rdseed_microcode[] = { ZEN_MODEL_STEP_UCODE(0x1a, 0x02, 0x1, 0x0b00215a), + ZEN_MODEL_STEP_UCODE(0x1a, 0x08, 0x1, 0x0b008121), ZEN_MODEL_STEP_UCODE(0x1a, 0x11, 0x0, 0x0b101054), + ZEN_MODEL_STEP_UCODE(0x1a, 0x24, 0x0, 0x0b204037), + ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x0, 0x0b404035), + ZEN_MODEL_STEP_UCODE(0x1a, 0x44, 0x1, 0x0b404108), + ZEN_MODEL_STEP_UCODE(0x1a, 0x60, 0x0, 0x0b600037), + ZEN_MODEL_STEP_UCODE(0x1a, 0x68, 0x0, 0x0b608038), + ZEN_MODEL_STEP_UCODE(0x1a, 0x70, 0x0, 0x0b700037), {}, }; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index dc82153009da..a881bf4c2011 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -224,6 +224,7 @@ static bool need_sha_check(u32 cur_rev) case 0xb1010: return cur_rev <= 0xb101046; break; case 0xb2040: return cur_rev <= 0xb204031; break; case 0xb4040: return cur_rev <= 0xb404031; break; + case 0xb4041: return cur_rev <= 0xb404101; break; case 0xb6000: return cur_rev <= 0xb600031; break; case 0xb6080: return cur_rev <= 0xb608031; break; case 0xb7000: return cur_rev <= 0xb700031; break; diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 367da3638167..823dbdd0eb41 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -354,12 +354,17 @@ SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR + /* Restore return_to_handler value that got eaten by previous ret instruction. */ + subq $8, %rsp + UNWIND_HINT_FUNC + /* Save ftrace_regs for function exit context */ subq $(FRAME_SIZE), %rsp movq %rax, RAX(%rsp) movq %rdx, RDX(%rsp) movq %rbp, RBP(%rsp) + movq %rsp, RSP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler @@ -368,7 +373,8 @@ SYM_CODE_START(return_to_handler) movq RDX(%rsp), %rdx movq RAX(%rsp), %rax - addq $(FRAME_SIZE), %rsp + addq $(FRAME_SIZE) + 8, %rsp + /* * Jump back to the old return address. This cannot be JMP_NOSPEC rdi * since IBT would demand that contain ENDBR, which simply isn't so for diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 10c21e4c5406..9d29b2e7e855 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -705,7 +705,11 @@ void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask) static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu) { - bool intercept = !(to_svm(vcpu)->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK); + struct vcpu_svm *svm = to_svm(vcpu); + bool intercept = !(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK); + + if (intercept == svm->lbr_msrs_intercepted) + return; svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHFROMIP, MSR_TYPE_RW, intercept); svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHTOIP, MSR_TYPE_RW, intercept); @@ -714,6 +718,8 @@ static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu) if (sev_es_guest(vcpu->kvm)) svm_set_intercept_for_msr(vcpu, MSR_IA32_DEBUGCTLMSR, MSR_TYPE_RW, intercept); + + svm->lbr_msrs_intercepted = intercept; } void svm_vcpu_free_msrpm(void *msrpm) @@ -1221,6 +1227,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) } svm->x2avic_msrs_intercepted = true; + svm->lbr_msrs_intercepted = true; svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index c856d8e0f95e..dd78e6402345 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -336,6 +336,7 @@ struct vcpu_svm { bool guest_state_loaded; bool x2avic_msrs_intercepted; + bool lbr_msrs_intercepted; /* Guest GIF value, used when vGIF is not enabled */ bool guest_gif; diff --git a/block/bdev.c b/block/bdev.c index 810707cca970..638f0cd458ae 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -231,7 +231,7 @@ int sb_set_blocksize(struct super_block *sb, int size) EXPORT_SYMBOL(sb_set_blocksize); -int sb_min_blocksize(struct super_block *sb, int size) +int __must_check sb_min_blocksize(struct super_block *sb, int size) { int minsize = bdev_logical_block_size(sb->s_bdev); if (size < minsize) diff --git a/drivers/acpi/acpi_mrrm.c b/drivers/acpi/acpi_mrrm.c index a6dbf623e557..6d69554c940e 100644 --- a/drivers/acpi/acpi_mrrm.c +++ b/drivers/acpi/acpi_mrrm.c @@ -152,26 +152,49 @@ ATTRIBUTE_GROUPS(memory_range); static __init int add_boot_memory_ranges(void) { - struct kobject *pkobj, *kobj; + struct kobject *pkobj, *kobj, **kobjs; int ret = -EINVAL; - char *name; + char name[16]; + int i; pkobj = kobject_create_and_add("memory_ranges", acpi_kobj); + if (!pkobj) + return -ENOMEM; - for (int i = 0; i < mrrm_mem_entry_num; i++) { - name = kasprintf(GFP_KERNEL, "range%d", i); - if (!name) { - ret = -ENOMEM; - break; - } + kobjs = kcalloc(mrrm_mem_entry_num, sizeof(*kobjs), GFP_KERNEL); + if (!kobjs) { + kobject_put(pkobj); + return -ENOMEM; + } + for (i = 0; i < mrrm_mem_entry_num; i++) { + scnprintf(name, sizeof(name), "range%d", i); kobj = kobject_create_and_add(name, pkobj); + if (!kobj) { + ret = -ENOMEM; + goto cleanup; + } ret = sysfs_create_groups(kobj, memory_range_groups); - if (ret) - return ret; + if (ret) { + kobject_put(kobj); + goto cleanup; + } + kobjs[i] = kobj; } + kfree(kobjs); + return 0; + +cleanup: + for (int j = 0; j < i; j++) { + if (kobjs[j]) { + sysfs_remove_groups(kobjs[j], memory_range_groups); + kobject_put(kobjs[j]); + } + } + kfree(kobjs); + kobject_put(pkobj); return ret; } diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index 3c87953dbd19..305c240a303f 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -182,6 +182,7 @@ bool einj_initialized __ro_after_init; static void __iomem *einj_param; static u32 v5param_size; +static u32 v66param_size; static bool is_v2; static void einj_exec_ctx_init(struct apei_exec_context *ctx) @@ -283,6 +284,24 @@ static void check_vendor_extension(u64 paddr, acpi_os_unmap_iomem(p, sizeof(v)); } +static u32 einjv2_init(struct einjv2_extension_struct *e) +{ + if (e->revision != 1) { + pr_info("Unknown v2 extension revision %u\n", e->revision); + return 0; + } + if (e->length < sizeof(*e) || e->length > PAGE_SIZE) { + pr_info(FW_BUG "Bad1 v2 extension length %u\n", e->length); + return 0; + } + if ((e->length - sizeof(*e)) % sizeof(e->component_arr[0])) { + pr_info(FW_BUG "Bad2 v2 extension length %u\n", e->length); + return 0; + } + + return (e->length - sizeof(*e)) / sizeof(e->component_arr[0]); +} + static void __iomem *einj_get_parameter_address(void) { int i; @@ -310,28 +329,21 @@ static void __iomem *einj_get_parameter_address(void) v5param_size = sizeof(v5param); p = acpi_os_map_iomem(pa_v5, sizeof(*p)); if (p) { - int offset, len; - memcpy_fromio(&v5param, p, v5param_size); acpi5 = 1; check_vendor_extension(pa_v5, &v5param); - if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) { - len = v5param.einjv2_struct.length; - offset = offsetof(struct einjv2_extension_struct, component_arr); - max_nr_components = (len - offset) / - sizeof(v5param.einjv2_struct.component_arr[0]); - /* - * The first call to acpi_os_map_iomem above does not include the - * component array, instead it is used to read and calculate maximum - * number of components supported by the system. Below, the mapping - * is expanded to include the component array. - */ + if (available_error_type & ACPI65_EINJV2_SUPP) { + struct einjv2_extension_struct *e; + + e = &v5param.einjv2_struct; + max_nr_components = einjv2_init(e); + + /* remap including einjv2_extension_struct */ acpi_os_unmap_iomem(p, v5param_size); - offset = offsetof(struct set_error_type_with_address, einjv2_struct); - v5param_size = offset + struct_size(&v5param.einjv2_struct, - component_arr, max_nr_components); - p = acpi_os_map_iomem(pa_v5, v5param_size); + v66param_size = v5param_size - sizeof(*e) + e->length; + p = acpi_os_map_iomem(pa_v5, v66param_size); } + return p; } } @@ -527,6 +539,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, u64 param3, u64 param4) { struct apei_exec_context ctx; + u32 param_size = is_v2 ? v66param_size : v5param_size; u64 val, trigger_paddr, timeout = FIRMWARE_TIMEOUT; int i, rc; @@ -539,11 +552,11 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, if (acpi5) { struct set_error_type_with_address *v5param; - v5param = kmalloc(v5param_size, GFP_KERNEL); + v5param = kmalloc(param_size, GFP_KERNEL); if (!v5param) return -ENOMEM; - memcpy_fromio(v5param, einj_param, v5param_size); + memcpy_fromio(v5param, einj_param, param_size); v5param->type = type; if (type & ACPI5_VENDOR_BIT) { switch (vendor_flags) { @@ -601,7 +614,7 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, break; } } - memcpy_toio(einj_param, v5param, v5param_size); + memcpy_toio(einj_param, v5param, param_size); kfree(v5param); } else { rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE); @@ -1132,9 +1145,14 @@ static void einj_remove(struct faux_device *fdev) struct apei_exec_context ctx; if (einj_param) { - acpi_size size = (acpi5) ? - v5param_size : - sizeof(struct einj_parameter); + acpi_size size; + + if (v66param_size) + size = v66param_size; + else if (acpi5) + size = v5param_size; + else + size = sizeof(struct einj_parameter); acpi_os_unmap_iomem(einj_param, size); if (vendor_errors.size) diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c index fd995a1d3d24..8cc8af8fd408 100644 --- a/drivers/acpi/arm64/gtdt.c +++ b/drivers/acpi/arm64/gtdt.c @@ -430,10 +430,10 @@ static int __init gtdt_platform_timer_init(void) continue; pdev = platform_device_register_data(NULL, "gtdt-arm-mmio-timer", - gwdt_count, &atm, + mmio_timer_count, &atm, sizeof(atm)); if (IS_ERR(pdev)) { - pr_err("Can't register timer %d\n", gwdt_count); + pr_err("Can't register timer %d\n", mmio_timer_count); continue; } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 6c684e54fe01..3bdeeee3414e 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -460,7 +460,7 @@ bool acpi_cpc_valid(void) if (acpi_disabled) return false; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); if (!cpc_ptr) return false; @@ -476,7 +476,7 @@ bool cppc_allow_fast_switch(void) struct cpc_desc *cpc_ptr; int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF]; if (!CPC_IN_SYSTEM_MEMORY(desired_reg) && @@ -1435,7 +1435,7 @@ bool cppc_perf_ctrs_in_pcc(void) { int cpu; - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct cpc_register_resource *ref_perf_reg; struct cpc_desc *cpc_desc; diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 5a36d57289b4..11e4483685c9 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -874,11 +874,33 @@ static void hmat_register_target_devices(struct memory_target *target) } } -static void hmat_register_target(struct memory_target *target) +static void hmat_hotplug_target(struct memory_target *target) { int nid = pxm_to_node(target->memory_pxm); /* + * Skip offline nodes. This can happen when memory marked EFI_MEMORY_SP, + * "specific purpose", is applied to all the memory in a proximity + * domain leading to * the node being marked offline / unplugged, or if + * memory-only "hotplug" node is offline. + */ + if (nid == NUMA_NO_NODE || !node_online(nid)) + return; + + guard(mutex)(&target_lock); + if (target->registered) + return; + + hmat_register_target_initiators(target); + hmat_register_target_cache(target); + hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); + hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); + target->registered = true; +} + +static void hmat_register_target(struct memory_target *target) +{ + /* * Devices may belong to either an offline or online * node, so unconditionally add them. */ @@ -895,25 +917,7 @@ static void hmat_register_target(struct memory_target *target) } mutex_unlock(&target_lock); - /* - * Skip offline nodes. This can happen when memory - * marked EFI_MEMORY_SP, "specific purpose", is applied - * to all the memory in a proximity domain leading to - * the node being marked offline / unplugged, or if - * memory-only "hotplug" node is offline. - */ - if (nid == NUMA_NO_NODE || !node_online(nid)) - return; - - mutex_lock(&target_lock); - if (!target->registered) { - hmat_register_target_initiators(target); - hmat_register_target_cache(target); - hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); - hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); - target->registered = true; - } - mutex_unlock(&target_lock); + hmat_hotplug_target(target); } static void hmat_register_targets(void) @@ -939,7 +943,7 @@ static int hmat_callback(struct notifier_block *self, if (!target) return NOTIFY_OK; - hmat_register_target(target); + hmat_hotplug_target(target); return NOTIFY_OK; } diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 53816dfab645..aa87ee1583a4 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -237,7 +237,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) struct acpi_srat_generic_affinity *p = (struct acpi_srat_generic_affinity *)header; - if (p->device_handle_type == 0) { + if (p->device_handle_type == 1) { /* * For pci devices this may be the only place they * are assigned a proximity domain diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c index 5d824435b26b..7644de24d2fa 100644 --- a/drivers/acpi/processor_driver.c +++ b/drivers/acpi/processor_driver.c @@ -166,7 +166,8 @@ static int __acpi_processor_start(struct acpi_device *device) if (result && !IS_ENABLED(CONFIG_ACPI_CPU_FREQ_PSS)) dev_dbg(&device->dev, "CPPC data invalid or not present\n"); - acpi_processor_power_init(pr); + if (cpuidle_get_driver() == &acpi_idle_driver) + acpi_processor_power_init(pr); acpi_pss_perf_init(pr); @@ -262,8 +263,6 @@ static int __init acpi_processor_driver_init(void) if (result < 0) return result; - acpi_processor_register_idle_driver(); - result = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "acpi/cpu-drv:online", acpi_soft_cpu_online, NULL); @@ -302,7 +301,6 @@ static void __exit acpi_processor_driver_exit(void) cpuhp_remove_state_nocalls(hp_online); cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD); - acpi_processor_unregister_idle_driver(); driver_unregister(&acpi_processor_driver); } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 22b051b94a86..4166090db642 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -51,7 +51,7 @@ module_param(latency_factor, uint, 0644); static DEFINE_PER_CPU(struct cpuidle_device *, acpi_cpuidle_device); -static struct cpuidle_driver acpi_idle_driver = { +struct cpuidle_driver acpi_idle_driver = { .name = "acpi_idle", .owner = THIS_MODULE, }; @@ -1357,102 +1357,79 @@ int acpi_processor_power_state_has_changed(struct acpi_processor *pr) return 0; } -void acpi_processor_register_idle_driver(void) -{ - struct acpi_processor *pr; - int ret = -ENODEV; - int cpu; - - /* - * Acpi idle driver is used by all possible CPUs. - * Install the idle handler by the processor power info of one in them. - * Note that we use previously set idle handler will be used on - * platforms that only support C1. - */ - for_each_cpu(cpu, (struct cpumask *)cpu_possible_mask) { - pr = per_cpu(processors, cpu); - if (!pr) - continue; - - ret = acpi_processor_get_power_info(pr); - if (!ret) { - pr->flags.power_setup_done = 1; - acpi_processor_setup_cpuidle_states(pr); - break; - } - } - - if (ret) { - pr_debug("No ACPI power information from any CPUs.\n"); - return; - } +static int acpi_processor_registered; - ret = cpuidle_register_driver(&acpi_idle_driver); - if (ret) { - pr_debug("register %s failed.\n", acpi_idle_driver.name); - return; - } - pr_debug("%s registered with cpuidle.\n", acpi_idle_driver.name); -} - -void acpi_processor_unregister_idle_driver(void) -{ - cpuidle_unregister_driver(&acpi_idle_driver); -} - -void acpi_processor_power_init(struct acpi_processor *pr) +int acpi_processor_power_init(struct acpi_processor *pr) { + int retval; struct cpuidle_device *dev; - /* - * The code below only works if the current cpuidle driver is the ACPI - * idle driver. - */ - if (cpuidle_get_driver() != &acpi_idle_driver) - return; - if (disabled_by_idle_boot_param()) - return; + return 0; acpi_processor_cstate_first_run_checks(); if (!acpi_processor_get_power_info(pr)) pr->flags.power_setup_done = 1; - if (!pr->flags.power) - return; - - dev = kzalloc(sizeof(*dev), GFP_KERNEL); - if (!dev) - return; + /* + * Install the idle handler if processor power management is supported. + * Note that we use previously set idle handler will be used on + * platforms that only support C1. + */ + if (pr->flags.power) { + /* Register acpi_idle_driver if not already registered */ + if (!acpi_processor_registered) { + acpi_processor_setup_cpuidle_states(pr); + retval = cpuidle_register_driver(&acpi_idle_driver); + if (retval) + return retval; + pr_debug("%s registered with cpuidle\n", + acpi_idle_driver.name); + } - per_cpu(acpi_cpuidle_device, pr->id) = dev; + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + per_cpu(acpi_cpuidle_device, pr->id) = dev; - acpi_processor_setup_cpuidle_dev(pr, dev); + acpi_processor_setup_cpuidle_dev(pr, dev); - /* - * Register a cpuidle device for this CPU. The cpuidle driver using - * this device is expected to be registered. - */ - if (cpuidle_register_device(dev)) { - per_cpu(acpi_cpuidle_device, pr->id) = NULL; - kfree(dev); + /* Register per-cpu cpuidle_device. Cpuidle driver + * must already be registered before registering device + */ + retval = cpuidle_register_device(dev); + if (retval) { + if (acpi_processor_registered == 0) + cpuidle_unregister_driver(&acpi_idle_driver); + + per_cpu(acpi_cpuidle_device, pr->id) = NULL; + kfree(dev); + return retval; + } + acpi_processor_registered++; } + return 0; } -void acpi_processor_power_exit(struct acpi_processor *pr) +int acpi_processor_power_exit(struct acpi_processor *pr) { struct cpuidle_device *dev = per_cpu(acpi_cpuidle_device, pr->id); if (disabled_by_idle_boot_param()) - return; + return 0; if (pr->flags.power) { cpuidle_unregister_device(dev); + acpi_processor_registered--; + if (acpi_processor_registered == 0) + cpuidle_unregister_driver(&acpi_idle_driver); + kfree(dev); } pr->flags.power_setup_done = 0; + return 0; } MODULE_IMPORT_NS("ACPI_PROCESSOR_IDLE"); diff --git a/drivers/android/binder_netlink.c b/drivers/android/binder_netlink.c index d05397a50ca6..81e8432b5904 100644 --- a/drivers/android/binder_netlink.c +++ b/drivers/android/binder_netlink.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/binder.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/drivers/android/binder_netlink.h b/drivers/android/binder_netlink.h index 882c7a6b537e..57399942a5e3 100644 --- a/drivers/android/binder_netlink.h +++ b/drivers/android/binder_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/binder.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_BINDER_GEN_H #define _LINUX_BINDER_GEN_H diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 2a210719c4ce..f48fb63d7e85 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3006,6 +3006,16 @@ int ata_dev_configure(struct ata_device *dev) } dev->n_sectors = ata_id_n_sectors(id); + if (ata_id_is_locked(id)) { + /* + * If Security locked, set capacity to zero to prevent + * any I/O, e.g. partition scanning, as any I/O to a + * locked drive will result in user visible errors. + */ + ata_dev_info(dev, + "Security locked, setting capacity to zero\n"); + dev->n_sectors = 0; + } /* get current R/W Multiple count setting */ if ((dev->id[47] >> 8) == 0x80 && (dev->id[59] & 0x100)) { diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index b43a3196e2be..434774e71fe6 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -992,6 +992,13 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc) return; } + if (ata_id_is_locked(dev->id)) { + /* Security locked */ + /* LOGICAL UNIT ACCESS NOT AUTHORIZED */ + ata_scsi_set_sense(dev, cmd, DATA_PROTECT, 0x74, 0x71); + return; + } + if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) { ata_dev_dbg(dev, "Missing result TF: reporting aborted command\n"); @@ -4894,8 +4901,10 @@ void ata_scsi_dev_rescan(struct work_struct *work) spin_unlock_irqrestore(ap->lock, flags); if (do_resume) { ret = scsi_resume_device(sdev); - if (ret == -EWOULDBLOCK) + if (ret == -EWOULDBLOCK) { + scsi_device_put(sdev); goto unlock_scan; + } dev->flags &= ~ATA_DFLAG_RESUMING; } ret = scsi_rescan_device(sdev); diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 4fea1149e003..f62e38571440 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -1374,7 +1374,9 @@ fore200e_open(struct atm_vcc *vcc) vcc->dev_data = NULL; + mutex_lock(&fore200e->rate_mtx); fore200e->available_cell_rate += vcc->qos.txtp.max_pcr; + mutex_unlock(&fore200e->rate_mtx); kfree(fore200e_vcc); return -EINVAL; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index e83503bdc1fd..1de1cd72b616 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -888,12 +888,15 @@ static void device_resume_early(struct device *dev, pm_message_t state, bool asy TRACE_DEVICE(dev); TRACE_RESUME(0); - if (dev->power.syscore || dev->power.direct_complete) + if (dev->power.direct_complete) goto Out; if (!dev->power.is_late_suspended) goto Out; + if (dev->power.syscore) + goto Skip; + if (!dpm_wait_for_superior(dev, async)) goto Out; @@ -926,11 +929,11 @@ Run: Skip: dev->power.is_late_suspended = false; + pm_runtime_enable(dev); Out: TRACE_RESUME(error); - pm_runtime_enable(dev); complete_all(&dev->power.completion); if (error) { @@ -1615,12 +1618,6 @@ static void device_suspend_late(struct device *dev, pm_message_t state, bool asy TRACE_DEVICE(dev); TRACE_SUSPEND(0); - /* - * Disable runtime PM for the device without checking if there is a - * pending resume request for it. - */ - __pm_runtime_disable(dev, false); - dpm_wait_for_subordinate(dev, async); if (READ_ONCE(async_error)) @@ -1631,9 +1628,18 @@ static void device_suspend_late(struct device *dev, pm_message_t state, bool asy goto Complete; } - if (dev->power.syscore || dev->power.direct_complete) + if (dev->power.direct_complete) goto Complete; + /* + * Disable runtime PM for the device without checking if there is a + * pending resume request for it. + */ + __pm_runtime_disable(dev, false); + + if (dev->power.syscore) + goto Skip; + if (dev->pm_domain) { info = "late power domain "; callback = pm_late_early_op(&dev->pm_domain->ops, state); @@ -1664,6 +1670,7 @@ Run: WRITE_ONCE(async_error, error); dpm_save_failed_dev(dev_name(dev)); pm_dev_err(dev, state, async ? " async late" : " late", error); + pm_runtime_enable(dev); goto Complete; } dpm_propagate_wakeup_to_parent(dev); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index a722446ec73d..fa683bb7f0b4 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2711,9 +2711,21 @@ static int btusb_recv_event_realtek(struct hci_dev *hdev, struct sk_buff *skb) static void btusb_mtk_claim_iso_intf(struct btusb_data *data) { - struct btmtk_data *btmtk_data = hci_get_priv(data->hdev); + struct btmtk_data *btmtk_data; int err; + if (!data->hdev) + return; + + btmtk_data = hci_get_priv(data->hdev); + if (!btmtk_data) + return; + + if (!btmtk_data->isopkt_intf) { + bt_dev_err(data->hdev, "Can't claim NULL iso interface"); + return; + } + /* * The function usb_driver_claim_interface() is documented to need * locks held if it's not called from a probe routine. The code here @@ -2735,17 +2747,30 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data) static void btusb_mtk_release_iso_intf(struct hci_dev *hdev) { - struct btmtk_data *btmtk_data = hci_get_priv(hdev); + struct btmtk_data *btmtk_data; + + if (!hdev) + return; + + btmtk_data = hci_get_priv(hdev); + if (!btmtk_data) + return; if (test_bit(BTMTK_ISOPKT_OVER_INTR, &btmtk_data->flags)) { usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor); clear_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags); - dev_kfree_skb_irq(btmtk_data->isopkt_skb); - btmtk_data->isopkt_skb = NULL; - usb_set_intfdata(btmtk_data->isopkt_intf, NULL); - usb_driver_release_interface(&btusb_driver, - btmtk_data->isopkt_intf); + if (btmtk_data->isopkt_skb) { + dev_kfree_skb_irq(btmtk_data->isopkt_skb); + btmtk_data->isopkt_skb = NULL; + } + + if (btmtk_data->isopkt_intf) { + usb_set_intfdata(btmtk_data->isopkt_intf, NULL); + usb_driver_release_interface(&btusb_driver, + btmtk_data->isopkt_intf); + btmtk_data->isopkt_intf = NULL; + } } clear_bit(BTMTK_ISOPKT_OVER_INTR, &btmtk_data->flags); diff --git a/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c b/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c index 70ce0ca0cb7d..0339c4af0fe5 100644 --- a/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c +++ b/drivers/clk/sunxi-ng/ccu-sun55i-a523-r.c @@ -121,11 +121,11 @@ static SUNXI_CCU_GATE_HW(bus_r_ir_rx_clk, "bus-r-ir-rx", &r_apb0_clk.common.hw, 0x1cc, BIT(0), 0); static SUNXI_CCU_GATE_HW(bus_r_dma_clk, "bus-r-dma", - &r_apb0_clk.common.hw, 0x1dc, BIT(0), 0); + &r_apb0_clk.common.hw, 0x1dc, BIT(0), CLK_IS_CRITICAL); static SUNXI_CCU_GATE_HW(bus_r_rtc_clk, "bus-r-rtc", &r_apb0_clk.common.hw, 0x20c, BIT(0), 0); static SUNXI_CCU_GATE_HW(bus_r_cpucfg_clk, "bus-r-cpucfg", - &r_apb0_clk.common.hw, 0x22c, BIT(0), 0); + &r_apb0_clk.common.hw, 0x22c, BIT(0), CLK_IS_CRITICAL); static struct ccu_common *sun55i_a523_r_ccu_clks[] = { &r_ahb_clk.common, diff --git a/drivers/clk/sunxi-ng/ccu-sun55i-a523.c b/drivers/clk/sunxi-ng/ccu-sun55i-a523.c index acb532f8361b..20dad06b37ca 100644 --- a/drivers/clk/sunxi-ng/ccu-sun55i-a523.c +++ b/drivers/clk/sunxi-ng/ccu-sun55i-a523.c @@ -300,7 +300,7 @@ static struct ccu_nm pll_audio0_4x_clk = { .m = _SUNXI_CCU_DIV(16, 6), .sdm = _SUNXI_CCU_SDM(pll_audio0_sdm_table, BIT(24), 0x178, BIT(31)), - .min_rate = 180000000U, + .min_rate = 90000000U, .max_rate = 3000000000U, .common = { .reg = 0x078, diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 38897bb14a2c..492a10f1bdbf 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -603,9 +603,6 @@ static bool turbo_is_disabled(void) { u64 misc_en; - if (!cpu_feature_enabled(X86_FEATURE_IDA)) - return true; - rdmsrq(MSR_IA32_MISC_ENABLE, misc_en); return !!(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); @@ -2106,7 +2103,8 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -2271,7 +2269,8 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled) && + cpu_feature_enabled(X86_FEATURE_IDA)) val |= (u64)1 << 32; return val; diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index a5b96adf2d1e..3b391a146635 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3871,10 +3871,12 @@ static ssize_t qm_get_qos_value(struct hisi_qm *qm, const char *buf, pdev = container_of(dev, struct pci_dev, dev); if (pci_physfn(pdev) != qm->pdev) { pci_err(qm->pdev, "the pdev input does not match the pf!\n"); + put_device(dev); return -EINVAL; } *fun_index = pdev->devfn; + put_device(dev); return 0; } diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c index 215a1a8ba7e9..07a74f702c3a 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c @@ -24,7 +24,8 @@ static int otx2_cpt_dl_egrp_delete(struct devlink *dl, u32 id, } static int otx2_cpt_dl_uc_info(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { ctx->val.vstr[0] = '\0'; @@ -32,7 +33,8 @@ static int otx2_cpt_dl_uc_info(struct devlink *dl, u32 id, } static int otx2_cpt_dl_t106_mode_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct otx2_cpt_devlink *cpt_dl = devlink_priv(dl); struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index b06fee1978ba..41b64d871c5a 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -3702,6 +3702,7 @@ static int cxl_region_debugfs_poison_inject(void *data, u64 offset) if (validate_region_offset(cxlr, offset)) return -EINVAL; + offset -= cxlr->params.cache_size; rc = region_offset_to_dpa_result(cxlr, offset, &result); if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) { dev_dbg(&cxlr->dev, @@ -3734,6 +3735,7 @@ static int cxl_region_debugfs_poison_clear(void *data, u64 offset) if (validate_region_offset(cxlr, offset)) return -EINVAL; + offset -= cxlr->params.cache_size; rc = region_offset_to_dpa_result(cxlr, offset, &result); if (rc || !result.cxlmd || result.dpa == ULLONG_MAX) { dev_dbg(&cxlr->dev, diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index dac14d843af7..b8c16586706c 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -6,8 +6,7 @@ * * Copyright IBM Corp. 2025 */ -#define KMSG_COMPONENT "dibs" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "dibs: " fmt #include <linux/module.h> #include <linux/types.h> diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 3c6d570babf8..36d11ff195df 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/dpll.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/drivers/dpll/dpll_nl.h b/drivers/dpll/dpll_nl.h index 3da10cfe9a6e..7419679b6977 100644 --- a/drivers/dpll/dpll_nl.h +++ b/drivers/dpll/dpll_nl.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/dpll.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_DPLL_GEN_H #define _LINUX_DPLL_GEN_H diff --git a/drivers/dpll/zl3073x/Makefile b/drivers/dpll/zl3073x/Makefile index 84e22aae57e5..bd324c7fe710 100644 --- a/drivers/dpll/zl3073x/Makefile +++ b/drivers/dpll/zl3073x/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ZL3073X) += zl3073x.o -zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o prop.o +zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o \ + out.o prop.o ref.o synth.o obj-$(CONFIG_ZL3073X_I2C) += zl3073x_i2c.o zl3073x_i2c-objs := i2c.o diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c index e42e527813cf..383e2397dd03 100644 --- a/drivers/dpll/zl3073x/core.c +++ b/drivers/dpll/zl3073x/core.c @@ -129,47 +129,6 @@ const struct regmap_config zl3073x_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(zl3073x_regmap_config, "ZL3073X"); -/** - * zl3073x_ref_freq_factorize - factorize given frequency - * @freq: input frequency - * @base: base frequency - * @mult: multiplier - * - * Checks if the given frequency can be factorized using one of the - * supported base frequencies. If so the base frequency and multiplier - * are stored into appropriate parameters if they are not NULL. - * - * Return: 0 on success, -EINVAL if the frequency cannot be factorized - */ -int -zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) -{ - static const u16 base_freqs[] = { - 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, - 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, - 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, - 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, - 32000, 40000, 50000, 62500, - }; - u32 div; - int i; - - for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { - div = freq / base_freqs[i]; - - if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { - if (base) - *base = base_freqs[i]; - if (mult) - *mult = div; - - return 0; - } - } - - return -EINVAL; -} - static bool zl3073x_check_reg(struct zl3073x_dev *zldev, unsigned int reg, size_t size) { @@ -593,190 +552,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, return rc; } -/** - * zl3073x_ref_state_fetch - get input reference state - * @zldev: pointer to zl3073x_dev structure - * @index: input reference index to fetch state for - * - * Function fetches information for the given input reference that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_ref *input = &zldev->ref[index]; - u8 ref_config; - int rc; - - /* If the input is differential then the configuration for N-pin - * reference is ignored and P-pin config is used for both. - */ - if (zl3073x_is_n_pin(index) && - zl3073x_ref_is_diff(zldev, index - 1)) { - input->enabled = zl3073x_ref_is_enabled(zldev, index - 1); - input->diff = true; - - return 0; - } - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read ref_config register */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref_config); - if (rc) - return rc; - - input->enabled = FIELD_GET(ZL_REF_CONFIG_ENABLE, ref_config); - input->diff = FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref_config); - - dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, - str_enabled_disabled(input->enabled), - input->diff ? "differential" : "single-ended"); - - return rc; -} - -/** - * zl3073x_out_state_fetch - get output state - * @zldev: pointer to zl3073x_dev structure - * @index: output index to fetch state for - * - * Function fetches information for the given output (not output pin) - * that are invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_out *out = &zldev->out[index]; - u8 output_ctrl, output_mode; - int rc; - - /* Read output configuration */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &output_ctrl); - if (rc) - return rc; - - /* Store info about output enablement and synthesizer the output - * is connected to. - */ - out->enabled = FIELD_GET(ZL_OUTPUT_CTRL_EN, output_ctrl); - out->synth = FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, output_ctrl); - - dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, - str_enabled_disabled(out->enabled), out->synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read output_mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - - /* Extract and store output signal format */ - out->signal_format = FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, - output_mode); - - dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, - out->signal_format); - - return rc; -} - -/** - * zl3073x_synth_state_fetch - get synth state - * @zldev: pointer to zl3073x_dev structure - * @index: synth index to fetch state for - * - * Function fetches information for the given synthesizer that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_synth *synth = &zldev->synth[index]; - u16 base, m, n; - u8 synth_ctrl; - u32 mult; - int rc; - - /* Read synth control register */ - rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth_ctrl); - if (rc) - return rc; - - /* Store info about synth enablement and DPLL channel the synth is - * driven by. - */ - synth->enabled = FIELD_GET(ZL_SYNTH_CTRL_EN, synth_ctrl); - synth->dpll = FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth_ctrl); - - dev_dbg(zldev->dev, "SYNTH%u is %s and driven by DPLL%u\n", index, - str_enabled_disabled(synth->enabled), synth->dpll); - - guard(mutex)(&zldev->multiop_lock); - - /* Read synth configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, - ZL_REG_SYNTH_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* The output frequency is determined by the following formula: - * base * multiplier * numerator / denominator - * - * Read registers with these values - */ - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &base); - if (rc) - return rc; - - rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &mult); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &m); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &n); - if (rc) - return rc; - - /* Check denominator for zero to avoid div by 0 */ - if (!n) { - dev_err(zldev->dev, - "Zero divisor for SYNTH%u retrieved from device\n", - index); - return -EINVAL; - } - - /* Compute and store synth frequency */ - zldev->synth[index].freq = div_u64(mul_u32_u32(base * m, mult), n); - - dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, - zldev->synth[index].freq); - - return rc; -} - static int zl3073x_dev_state_fetch(struct zl3073x_dev *zldev) { @@ -816,6 +591,21 @@ zl3073x_dev_state_fetch(struct zl3073x_dev *zldev) return rc; } +static void +zl3073x_dev_ref_status_update(struct zl3073x_dev *zldev) +{ + int i, rc; + + for (i = 0; i < ZL3073X_NUM_REFS; i++) { + rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(i), + &zldev->ref[i].mon_status); + if (rc) + dev_warn(zldev->dev, + "Failed to get REF%u status: %pe\n", i, + ERR_PTR(rc)); + } +} + /** * zl3073x_ref_phase_offsets_update - update reference phase offsets * @zldev: pointer to zl3073x_dev structure @@ -935,6 +725,9 @@ zl3073x_dev_periodic_work(struct kthread_work *work) struct zl3073x_dpll *zldpll; int rc; + /* Update input references status */ + zl3073x_dev_ref_status_update(zldev); + /* Update DPLL-to-connected-ref phase offsets registers */ rc = zl3073x_ref_phase_offsets_update(zldev, -1); if (rc) diff --git a/drivers/dpll/zl3073x/core.h b/drivers/dpll/zl3073x/core.h index 1dca4ddcf235..09bca2d0926d 100644 --- a/drivers/dpll/zl3073x/core.h +++ b/drivers/dpll/zl3073x/core.h @@ -9,7 +9,10 @@ #include <linux/mutex.h> #include <linux/types.h> +#include "out.h" +#include "ref.h" #include "regs.h" +#include "synth.h" struct device; struct regmap; @@ -28,42 +31,6 @@ struct zl3073x_dpll; ZL3073X_NUM_OUTPUT_PINS) /** - * struct zl3073x_ref - input reference invariant info - * @enabled: input reference is enabled or disabled - * @diff: true if input reference is differential - * @ffo: current fractional frequency offset - */ -struct zl3073x_ref { - bool enabled; - bool diff; - s64 ffo; -}; - -/** - * struct zl3073x_out - output invariant info - * @enabled: out is enabled or disabled - * @synth: synthesizer the out is connected to - * @signal_format: out signal format - */ -struct zl3073x_out { - bool enabled; - u8 synth; - u8 signal_format; -}; - -/** - * struct zl3073x_synth - synthesizer invariant info - * @freq: synthesizer frequency - * @dpll: ID of DPLL the synthesizer is driven by - * @enabled: synth is enabled or disabled - */ -struct zl3073x_synth { - u32 freq; - u8 dpll; - bool enabled; -}; - -/** * struct zl3073x_dev - zl3073x device * @dev: pointer to device * @regmap: regmap to access device registers @@ -175,7 +142,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, * Misc operations *****************/ -int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); int zl3073x_ref_phase_offsets_update(struct zl3073x_dev *zldev, int channel); static inline bool @@ -217,172 +183,141 @@ zl3073x_output_pin_out_get(u8 id) } /** - * zl3073x_ref_ffo_get - get current fractional frequency offset + * zl3073x_dev_ref_freq_get - get input reference frequency * @zldev: pointer to zl3073x device * @index: input reference index * - * Return: the latest measured fractional frequency offset + * Return: frequency of given input reference */ -static inline s64 -zl3073x_ref_ffo_get(struct zl3073x_dev *zldev, u8 index) +static inline u32 +zl3073x_dev_ref_freq_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].ffo; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_freq_get(ref); } /** - * zl3073x_ref_is_diff - check if the given input reference is differential + * zl3073x_dev_ref_is_diff - check if the given input reference is differential * @zldev: pointer to zl3073x device * @index: input reference index * * Return: true if reference is differential, false if reference is single-ended */ static inline bool -zl3073x_ref_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_diff(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].diff; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_is_diff(ref); } -/** - * zl3073x_ref_is_enabled - check if the given input reference is enabled +/* + * zl3073x_dev_ref_is_status_ok - check the given input reference status * @zldev: pointer to zl3073x device * @index: input reference index * - * Return: true if input refernce is enabled, false otherwise + * Return: true if the status is ok, false otherwise */ static inline bool -zl3073x_ref_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_status_ok(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].enabled; -} + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); -/** - * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by - * @zldev: pointer to zl3073x device - * @index: synth index - * - * Return: ID of DPLL the given synthetizer is driven by - */ -static inline u8 -zl3073x_synth_dpll_get(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->synth[index].dpll; + return zl3073x_ref_is_status_ok(ref); } /** - * zl3073x_synth_freq_get - get synth current freq + * zl3073x_dev_synth_freq_get - get synth current freq * @zldev: pointer to zl3073x device * @index: synth index * * Return: frequency of given synthetizer */ static inline u32 -zl3073x_synth_freq_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_synth_freq_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->synth[index].freq; -} + const struct zl3073x_synth *synth; -/** - * zl3073x_synth_is_enabled - check if the given synth is enabled - * @zldev: pointer to zl3073x device - * @index: synth index - * - * Return: true if synth is enabled, false otherwise - */ -static inline bool -zl3073x_synth_is_enabled(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->synth[index].enabled; + synth = zl3073x_synth_state_get(zldev, index); + return zl3073x_synth_freq_get(synth); } /** - * zl3073x_out_synth_get - get synth connected to given output + * zl3073x_dev_out_synth_get - get synth connected to given output * @zldev: pointer to zl3073x device * @index: output index * * Return: index of synth connected to given output. */ static inline u8 -zl3073x_out_synth_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_synth_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->out[index].synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + + return zl3073x_out_synth_get(out); } /** - * zl3073x_out_is_enabled - check if the given output is enabled + * zl3073x_dev_out_is_enabled - check if the given output is enabled * @zldev: pointer to zl3073x device * @index: output index * * Return: true if the output is enabled, false otherwise */ static inline bool -zl3073x_out_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_enabled(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Output is enabled only if associated synth is enabled */ - synth = zl3073x_out_synth_get(zldev, index); - if (zl3073x_synth_is_enabled(zldev, synth)) - return zldev->out[index].enabled; + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); - return false; + return zl3073x_synth_is_enabled(synth) && zl3073x_out_is_enabled(out); } /** - * zl3073x_out_signal_format_get - get output signal format - * @zldev: pointer to zl3073x device - * @index: output index - * - * Return: signal format of given output - */ -static inline u8 -zl3073x_out_signal_format_get(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->out[index].signal_format; -} - -/** - * zl3073x_out_dpll_get - get DPLL ID the output is driven by + * zl3073x_dev_out_dpll_get - get DPLL ID the output is driven by * @zldev: pointer to zl3073x device * @index: output index * * Return: ID of DPLL the given output is driven by */ static inline -u8 zl3073x_out_dpll_get(struct zl3073x_dev *zldev, u8 index) +u8 zl3073x_dev_out_dpll_get(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Get synthesizer connected to given output */ - synth = zl3073x_out_synth_get(zldev, index); + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); /* Return DPLL that drives the synth */ - return zl3073x_synth_dpll_get(zldev, synth); + return zl3073x_synth_dpll_get(synth); } /** - * zl3073x_out_is_diff - check if the given output is differential + * zl3073x_dev_out_is_diff - check if the given output is differential * @zldev: pointer to zl3073x device * @index: output index * * Return: true if output is differential, false if output is single-ended */ static inline bool -zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_diff(struct zl3073x_dev *zldev, u8 index) { - switch (zl3073x_out_signal_format_get(zldev, index)) { - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: - return true; - default: - break; - } + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); - return false; + return zl3073x_out_is_diff(out); } /** - * zl3073x_output_pin_is_enabled - check if the given output pin is enabled + * zl3073x_dev_output_pin_is_enabled - check if the given output pin is enabled * @zldev: pointer to zl3073x device * @id: output pin id * @@ -392,16 +327,21 @@ zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) * Return: true if output pin is enabled, false if output pin is disabled */ static inline bool -zl3073x_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) +zl3073x_dev_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) { - u8 output = zl3073x_output_pin_out_get(id); + u8 out_id = zl3073x_output_pin_out_get(id); + const struct zl3073x_out *out; + + out = zl3073x_out_state_get(zldev, out_id); - /* Check if the whole output is enabled */ - if (!zl3073x_out_is_enabled(zldev, output)) + /* Check if the output is enabled - call _dev_ helper that + * additionally checks for attached synth enablement. + */ + if (!zl3073x_dev_out_is_enabled(zldev, out_id)) return false; /* Check signal format */ - switch (zl3073x_out_signal_format_get(zldev, output)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DISABLED: /* Both output pins are disabled by signal format */ return false; diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c index d90150671d37..9879d85d29af 100644 --- a/drivers/dpll/zl3073x/dpll.c +++ b/drivers/dpll/zl3073x/dpll.c @@ -100,60 +100,6 @@ zl3073x_dpll_pin_direction_get(const struct dpll_pin *dpll_pin, void *pin_priv, return 0; } -/** - * zl3073x_dpll_input_ref_frequency_get - get input reference frequency - * @zldpll: pointer to zl3073x_dpll - * @ref_id: reference id - * @frequency: pointer to variable to store frequency - * - * Reads frequency of given input reference. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_dpll_input_ref_frequency_get(struct zl3073x_dpll *zldpll, u8 ref_id, - u32 *frequency) -{ - struct zl3073x_dev *zldev = zldpll->dev; - u16 base, mult, num, denom; - int rc; - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref_id)); - if (rc) - return rc; - - /* Read registers to compute resulting frequency */ - rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_BASE, &base); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_MULT, &mult); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_M, &num); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_N, &denom); - if (rc) - return rc; - - /* Sanity check that HW has not returned zero denominator */ - if (!denom) { - dev_err(zldev->dev, - "Zero divisor for ref %u frequency got from device\n", - ref_id); - return -EINVAL; - } - - /* Compute the frequency */ - *frequency = mul_u64_u32_div(base * mult, num, denom); - - return rc; -} - static int zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, void *pin_priv, @@ -165,39 +111,15 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 ref, ref_sync_ctrl, sync_mode; - u32 esync_div, ref_freq; - int rc; - - /* Get reference frequency */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, pin->id, &ref_freq); - if (rc) - return rc; - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; + const struct zl3073x_ref *ref; + u8 ref_id; - /* Get ref sync mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref_sync_ctrl); - if (rc) - return rc; + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); - /* Get esync divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_REF_ESYNC_DIV, &esync_div); - if (rc) - return rc; - - sync_mode = FIELD_GET(ZL_REF_SYNC_CTRL_MODE, ref_sync_ctrl); - - switch (sync_mode) { + switch (FIELD_GET(ZL_REF_SYNC_CTRL_MODE, ref->sync_ctrl)) { case ZL_REF_SYNC_CTRL_MODE_50_50_ESYNC_25_75: - esync->freq = (esync_div == ZL_REF_ESYNC_DIV_1HZ) ? 1 : 0; + esync->freq = ref->esync_n_div == ZL_REF_ESYNC_DIV_1HZ ? 1 : 0; esync->pulse = 25; break; default: @@ -209,7 +131,7 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, /* If the pin supports esync control expose its range but only * if the current reference frequency is > 1 Hz. */ - if (pin->esync_control && ref_freq > 1) { + if (pin->esync_control && zl3073x_ref_freq_get(ref) > 1) { esync->range = esync_freq_ranges; esync->range_num = ARRAY_SIZE(esync_freq_ranges); } else { @@ -217,7 +139,7 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, esync->range_num = 0; } - return rc; + return 0; } static int @@ -230,22 +152,11 @@ zl3073x_dpll_input_pin_esync_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 ref, ref_sync_ctrl, sync_mode; - int rc; + struct zl3073x_ref ref; + u8 ref_id, sync_mode; - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration into mailbox */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Get ref sync mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref_sync_ctrl); - if (rc) - return rc; + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); /* Use freq == 0 to disable esync */ if (!freq) @@ -253,25 +164,16 @@ zl3073x_dpll_input_pin_esync_set(const struct dpll_pin *dpll_pin, else sync_mode = ZL_REF_SYNC_CTRL_MODE_50_50_ESYNC_25_75; - ref_sync_ctrl &= ~ZL_REF_SYNC_CTRL_MODE; - ref_sync_ctrl |= FIELD_PREP(ZL_REF_SYNC_CTRL_MODE, sync_mode); - - /* Update ref sync control register */ - rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL, ref_sync_ctrl); - if (rc) - return rc; + ref.sync_ctrl &= ~ZL_REF_SYNC_CTRL_MODE; + ref.sync_ctrl |= FIELD_PREP(ZL_REF_SYNC_CTRL_MODE, sync_mode); if (freq) { - /* 1 Hz is only supported frequnecy currently */ - rc = zl3073x_write_u32(zldev, ZL_REG_REF_ESYNC_DIV, - ZL_REF_ESYNC_DIV_1HZ); - if (rc) - return rc; + /* 1 Hz is only supported frequency now */ + ref.esync_n_div = ZL_REF_ESYNC_DIV_1HZ; } - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Update reference configuration */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } static int @@ -295,17 +197,12 @@ zl3073x_dpll_input_pin_frequency_get(const struct dpll_pin *dpll_pin, { struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dpll_pin *pin = pin_priv; - u32 ref_freq; - u8 ref; - int rc; + u8 ref_id; - /* Read and return ref frequency */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, ref, &ref_freq); - if (!rc) - *frequency = ref_freq; + ref_id = zl3073x_input_pin_ref_get(pin->id); + *frequency = zl3073x_dev_ref_freq_get(zldpll->dev, ref_id); - return rc; + return 0; } static int @@ -318,39 +215,18 @@ zl3073x_dpll_input_pin_frequency_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u16 base, mult; - u8 ref; - int rc; + struct zl3073x_ref ref; + u8 ref_id; - /* Get base frequency and multiplier for the requested frequency */ - rc = zl3073x_ref_freq_factorize(frequency, &base, &mult); - if (rc) - return rc; + /* Get reference state */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); - guard(mutex)(&zldev->multiop_lock); + /* Update frequency */ + zl3073x_ref_freq_set(&ref, frequency); - /* Load reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - - /* Update base frequency, multiplier, numerator & denominator */ - rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_BASE, base); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_MULT, mult); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_M, 1); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_N, 1); - if (rc) - return rc; - - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Commit reference state */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } /** @@ -497,19 +373,10 @@ zl3073x_dpll_connected_ref_get(struct zl3073x_dpll *zldpll, u8 *ref) if (rc) return rc; - if (ZL3073X_DPLL_REF_IS_VALID(*ref)) { - u8 ref_status; - - /* Read the reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(*ref), - &ref_status); - if (rc) - return rc; - - /* If the monitor indicates an error nothing is connected */ - if (ref_status != ZL_REF_MON_STATUS_OK) - *ref = ZL3073X_DPLL_REF_NONE; - } + /* If the monitor indicates an error nothing is connected */ + if (ZL3073X_DPLL_REF_IS_VALID(*ref) && + !zl3073x_dev_ref_is_status_ok(zldev, *ref)) + *ref = ZL3073X_DPLL_REF_NONE; return 0; } @@ -524,34 +391,25 @@ zl3073x_dpll_input_pin_phase_offset_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 conn_ref, ref, ref_status; + const struct zl3073x_ref *ref; + u8 conn_id, ref_id; s64 ref_phase; int rc; /* Get currently connected reference */ - rc = zl3073x_dpll_connected_ref_get(zldpll, &conn_ref); + rc = zl3073x_dpll_connected_ref_get(zldpll, &conn_id); if (rc) return rc; /* Report phase offset only for currently connected pin if the phase - * monitor feature is disabled. + * monitor feature is disabled and only if the input pin signal is + * present. */ - ref = zl3073x_input_pin_ref_get(pin->id); - if (!zldpll->phase_monitor && ref != conn_ref) { + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); + if ((!zldpll->phase_monitor && ref_id != conn_id) || + !zl3073x_ref_is_status_ok(ref)) { *phase_offset = 0; - - return 0; - } - - /* Get this pin monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), &ref_status); - if (rc) - return rc; - - /* Report phase offset only if the input pin signal is present */ - if (ref_status != ZL_REF_MON_STATUS_OK) { - *phase_offset = 0; - return 0; } @@ -561,20 +419,12 @@ zl3073x_dpll_input_pin_phase_offset_get(const struct dpll_pin *dpll_pin, * the phase offset is modded to the period of the signal * the dpll is locked to. */ - if (ZL3073X_DPLL_REF_IS_VALID(conn_ref) && conn_ref != ref) { + if (ZL3073X_DPLL_REF_IS_VALID(conn_id) && conn_id != ref_id) { u32 conn_freq, ref_freq; - /* Get frequency of connected ref */ - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, conn_ref, - &conn_freq); - if (rc) - return rc; - - /* Get frequency of given ref */ - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, ref, - &ref_freq); - if (rc) - return rc; + /* Get frequency of connected and given ref */ + conn_freq = zl3073x_dev_ref_freq_get(zldev, conn_id); + ref_freq = zl3073x_ref_freq_get(ref); if (conn_freq > ref_freq) { s64 conn_period, div_factor; @@ -601,33 +451,23 @@ zl3073x_dpll_input_pin_phase_adjust_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; + const struct zl3073x_ref *ref; s64 phase_comp; - u8 ref; - int rc; - - guard(mutex)(&zldev->multiop_lock); + u8 ref_id; /* Read reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Read current phase offset compensation */ - rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, &phase_comp); - if (rc) - return rc; + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); /* Perform sign extension for 48bit signed value */ - phase_comp = sign_extend64(phase_comp, 47); + phase_comp = sign_extend64(ref->phase_comp, 47); /* Reverse two's complement negation applied during set and convert * to 32bit signed int */ *phase_adjust = (s32)-phase_comp; - return rc; + return 0; } static int @@ -641,32 +481,20 @@ zl3073x_dpll_input_pin_phase_adjust_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - s64 phase_comp; - u8 ref; - int rc; + struct zl3073x_ref ref; + u8 ref_id; + + /* Read reference configuration */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); /* The value in the register is stored as two's complement negation * of requested value. */ - phase_comp = -phase_adjust; - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Write the requested value into the compensation register */ - rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, phase_comp); - if (rc) - return rc; + ref.phase_comp = -phase_adjust; - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Update reference configuration */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } /** @@ -777,7 +605,7 @@ zl3073x_dpll_ref_state_get(struct zl3073x_dpll_pin *pin, { struct zl3073x_dpll *zldpll = pin->dpll; struct zl3073x_dev *zldev = zldpll->dev; - u8 ref, ref_conn, status; + u8 ref, ref_conn; int rc; ref = zl3073x_input_pin_ref_get(pin->id); @@ -797,20 +625,9 @@ zl3073x_dpll_ref_state_get(struct zl3073x_dpll_pin *pin, * pin as selectable. */ if (zldpll->refsel_mode == ZL_DPLL_MODE_REFSEL_MODE_AUTO && - pin->selectable) { - /* Read reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), - &status); - if (rc) - return rc; - - /* If the monitor indicates errors report the reference - * as disconnected - */ - if (status == ZL_REF_MON_STATUS_OK) { - *state = DPLL_PIN_STATE_SELECTABLE; - return 0; - } + zl3073x_dev_ref_is_status_ok(zldev, ref) && pin->selectable) { + *state = DPLL_PIN_STATE_SELECTABLE; + return 0; } /* Otherwise report the pin as disconnected */ @@ -953,21 +770,19 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 esync_period, esync_width; - u8 clock_type, synth; - u8 out, output_mode; - u32 output_div; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -975,38 +790,11 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - /* Read output divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); - - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, output_mode); + clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, out->mode); if (clock_type != ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC) { /* No need to read esync data if it is not enabled */ esync->freq = 0; @@ -1015,38 +803,21 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, goto finish; } - /* Read esync period */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &esync_period); - if (rc) - return rc; - - /* Check esync divisor for zero */ - if (!esync_period) { - dev_err(dev, "Zero esync divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get esync pulse width in units of half synth cycles */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, &esync_width); - if (rc) - return rc; - /* Compute esync frequency */ - esync->freq = synth_freq / output_div / esync_period; + esync->freq = synth_freq / out->div / out->esync_n_period; /* By comparing the esync_pulse_width to the half of the pulse width * the esync pulse percentage can be determined. * Note that half pulse width is in units of half synth cycles, which * is why it reduces down to be output_div. */ - esync->pulse = (50 * esync_width) / output_div; + esync->pulse = (50 * out->esync_n_width) / out->div; finish: /* Set supported esync ranges if the pin supports esync control and * if the output frequency is > 1 Hz. */ - if (pin->esync_control && (synth_freq / output_div) > 1) { + if (pin->esync_control && (synth_freq / out->div) > 1) { esync->range = esync_freq_ranges; esync->range_num = ARRAY_SIZE(esync_freq_ranges); } else { @@ -1064,21 +835,22 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, void *dpll_priv, u64 freq, struct netlink_ext_ack *extack) { - u32 esync_period, esync_width, output_div; struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 clock_type, out, output_mode, synth; + const struct zl3073x_synth *synth; + struct zl3073x_out out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(&out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -1086,19 +858,6 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - /* Select clock type */ if (freq) clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC; @@ -1106,38 +865,19 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_NORMAL; /* Update clock type in output mode */ - output_mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; - output_mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); - rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, output_mode); - if (rc) - return rc; + out.mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; + out.mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); /* If esync is being disabled just write mailbox and finish */ if (!freq) goto write_mailbox; - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); - - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(zldev->dev, - "Zero divisor for OUTPUT%u got from device\n", out); - return -EINVAL; - } + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); /* Compute and update esync period */ - esync_period = synth_freq / (u32)freq / output_div; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, esync_period); - if (rc) - return rc; + out.esync_n_period = synth_freq / (u32)freq / out.div; /* Half of the period in units of 1/2 synth cycle can be represented by * the output_div. To get the supported esync pulse width of 25% of the @@ -1145,15 +885,11 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, * assumes that output_div is even, otherwise some resolution will be * lost. */ - esync_width = output_div / 2; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, esync_width); - if (rc) - return rc; + out.esync_n_width = out.div / 2; write_mailbox: /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1166,83 +902,46 @@ zl3073x_dpll_output_pin_frequency_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u8 out, signal_format, synth; - u32 output_div, synth_freq; - int rc; - - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u32 synth_freq; + u8 out_id; - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; - } - - /* Read used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - switch (signal_format) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: /* In case of divided format we have to distiguish between * given output pin type. + * + * For P-pin the resulting frequency is computed as simple + * division of synth frequency and output divisor. + * + * For N-pin we have to divide additionally by divisor stored + * in esync_n_period output mailbox register that is used as + * N-pin divisor for these modes. */ - if (zl3073x_dpll_is_p_pin(pin)) { - /* For P-pin the resulting frequency is computed as - * simple division of synth frequency and output - * divisor. - */ - *frequency = synth_freq / output_div; - } else { - /* For N-pin we have to divide additionally by - * divisor stored in esync_period output mailbox - * register that is used as N-pin divisor for these - * modes. - */ - u32 ndiv; - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, - &ndiv); - if (rc) - return rc; + *frequency = synth_freq / out->div; - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; - } + if (!zl3073x_dpll_is_p_pin(pin)) + *frequency = (u32)*frequency / out->esync_n_period; - /* Compute final divisor for N-pin */ - *frequency = synth_freq / output_div / ndiv; - } break; default: /* In other modes the resulting frequency is computed as * division of synth frequency and output divisor. */ - *frequency = synth_freq / output_div; + *frequency = synth_freq / out->div; break; } - return rc; + return 0; } static int @@ -1255,28 +954,21 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 output_n_freq, output_p_freq; - u8 out, signal_format, synth; - u32 cur_div, new_div, ndiv; - u32 synth_freq; - int rc; + const struct zl3073x_synth *synth; + u8 out_id, signal_format; + u32 new_div, synth_freq; + struct zl3073x_out out; - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); + + /* Get attached synth frequency and compute new divisor */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); new_div = synth_freq / (u32)frequency; /* Get used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); - - guard(mutex)(&zldev->multiop_lock); - - /* Load output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; + signal_format = zl3073x_out_signal_format_get(&out); /* Check signal format */ if (signal_format != ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV && @@ -1284,99 +976,50 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, /* For non N-divided signal formats the frequency is computed * as division of synth frequency and output divisor. */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; + out.width = new_div; /* Commit output configuration */ - return zl3073x_mb_op(zldev, - ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - } - - /* For N-divided signal format get current divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &cur_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!cur_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; + return zl3073x_out_state_set(zldev, out_id, &out); } - /* Get N-pin divisor (shares the same register with esync */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &ndiv); - if (rc) - return rc; - - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; - } - - /* Compute current output frequency for P-pin */ - output_p_freq = synth_freq / cur_div; - - /* Compute current N-pin frequency */ - output_n_freq = output_p_freq / ndiv; - if (zl3073x_dpll_is_p_pin(pin)) { /* We are going to change output frequency for P-pin but * if the requested frequency is less than current N-pin * frequency then indicate a failure as we are not able * to compute N-pin divisor to keep its frequency unchanged. + * + * Update divisor for N-pin to keep N-pin frequency. */ - if (frequency <= output_n_freq) + out.esync_n_period = (out.esync_n_period * out.div) / new_div; + if (!out.esync_n_period) return -EINVAL; /* Update the output divisor */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; - - /* Compute new divisor for N-pin */ - ndiv = (u32)frequency / output_n_freq; + out.width = out.div; } else { /* We are going to change frequency of N-pin but if * the requested freq is greater or equal than freq of P-pin * in the output pair we cannot compute divisor for the N-pin. * In this case indicate a failure. + * + * Update divisor for N-pin */ - if (output_p_freq <= frequency) + out.esync_n_period = div64_u64(synth_freq, frequency * out.div); + if (!out.esync_n_period) return -EINVAL; - - /* Compute new divisor for N-pin */ - ndiv = output_p_freq / (u32)frequency; } - /* Update divisor for the N-pin */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, ndiv); - if (rc) - return rc; - /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, ndiv); - if (rc) - return rc; + out.esync_n_width = out.esync_n_period; /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1390,30 +1033,18 @@ zl3073x_dpll_output_pin_phase_adjust_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - s32 phase_comp; - u8 out; - int rc; - - guard(mutex)(&zldev->multiop_lock); + const struct zl3073x_out *out; + u8 out_id; - /* Read output configuration */ - out = zl3073x_output_pin_out_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read current output phase compensation */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, &phase_comp); - if (rc) - return rc; + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); /* Convert value to ps and reverse two's complement negation applied * during 'set' */ - *phase_adjust = -phase_comp * pin->phase_gran; + *phase_adjust = -out->phase_comp * pin->phase_gran; - return rc; + return 0; } static int @@ -1427,31 +1058,19 @@ zl3073x_dpll_output_pin_phase_adjust_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 out; - int rc; + struct zl3073x_out out; + u8 out_id; + + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); /* The value in the register is stored as two's complement negation * of requested value and expressed in half synth clock cycles. */ - phase_adjust = -phase_adjust / pin->phase_gran; - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - out = zl3073x_output_pin_out_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Write the requested value into the compensation register */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, phase_adjust); - if (rc) - return rc; + out.phase_comp = -phase_adjust / pin->phase_gran; /* Update output configuration from mailbox */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1848,33 +1467,32 @@ zl3073x_dpll_pin_is_registrable(struct zl3073x_dpll *zldpll, const char *name; if (dir == DPLL_PIN_DIRECTION_INPUT) { - u8 ref = zl3073x_input_pin_ref_get(index); - - name = "REF"; + u8 ref_id = zl3073x_input_pin_ref_get(index); + const struct zl3073x_ref *ref; /* Skip the pin if the DPLL is running in NCO mode */ if (zldpll->refsel_mode == ZL_DPLL_MODE_REFSEL_MODE_NCO) return false; - is_diff = zl3073x_ref_is_diff(zldev, ref); - is_enabled = zl3073x_ref_is_enabled(zldev, ref); + name = "REF"; + ref = zl3073x_ref_state_get(zldev, ref_id); + is_diff = zl3073x_ref_is_diff(ref); + is_enabled = zl3073x_ref_is_enabled(ref); } else { /* Output P&N pair shares single HW output */ u8 out = zl3073x_output_pin_out_get(index); - name = "OUT"; - /* Skip the pin if it is connected to different DPLL channel */ - if (zl3073x_out_dpll_get(zldev, out) != zldpll->id) { + if (zl3073x_dev_out_dpll_get(zldev, out) != zldpll->id) { dev_dbg(zldev->dev, - "%s%u is driven by different DPLL\n", name, - out); + "OUT%u is driven by different DPLL\n", out); return false; } - is_diff = zl3073x_out_is_diff(zldev, out); - is_enabled = zl3073x_output_pin_is_enabled(zldev, index); + name = "OUT"; + is_diff = zl3073x_dev_out_is_diff(zldev, out); + is_enabled = zl3073x_dev_output_pin_is_enabled(zldev, index); } /* Skip N-pin if the corresponding input/output is differential */ @@ -2031,42 +1649,26 @@ zl3073x_dpll_pin_phase_offset_check(struct zl3073x_dpll_pin *pin) struct zl3073x_dev *zldev = zldpll->dev; unsigned int reg; s64 phase_offset; - u8 ref; + u8 ref_id; int rc; - ref = zl3073x_input_pin_ref_get(pin->id); + /* No phase offset if the ref monitor reports signal errors */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + if (!zl3073x_dev_ref_is_status_ok(zldev, ref_id)) + return false; /* Select register to read phase offset value depending on pin and * phase monitor state: * 1) For connected pin use dpll_phase_err_data register * 2) For other pins use appropriate ref_phase register if the phase - * monitor feature is enabled and reference monitor does not - * report signal errors for given input pin + * monitor feature is enabled. */ - if (pin->pin_state == DPLL_PIN_STATE_CONNECTED) { + if (pin->pin_state == DPLL_PIN_STATE_CONNECTED) reg = ZL_REG_DPLL_PHASE_ERR_DATA(zldpll->id); - } else if (zldpll->phase_monitor) { - u8 status; - - /* Get reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), - &status); - if (rc) { - dev_err(zldev->dev, - "Failed to read %s refmon status: %pe\n", - pin->label, ERR_PTR(rc)); - - return false; - } - - if (status != ZL_REF_MON_STATUS_OK) - return false; - - reg = ZL_REG_REF_PHASE(ref); - } else { - /* The pin is not connected or phase monitor disabled */ + else if (zldpll->phase_monitor) + reg = ZL_REG_REF_PHASE(ref_id); + else return false; - } /* Read measured phase offset value */ rc = zl3073x_read_u48(zldev, reg, &phase_offset); @@ -2105,32 +1707,22 @@ zl3073x_dpll_pin_ffo_check(struct zl3073x_dpll_pin *pin) { struct zl3073x_dpll *zldpll = pin->dpll; struct zl3073x_dev *zldev = zldpll->dev; - u8 ref, status; - s64 ffo; - int rc; + const struct zl3073x_ref *ref; + u8 ref_id; /* Get reference monitor status */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), &status); - if (rc) { - dev_err(zldev->dev, "Failed to read %s refmon status: %pe\n", - pin->label, ERR_PTR(rc)); - - return false; - } + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); /* Do not report ffo changes if the reference monitor report errors */ - if (status != ZL_REF_MON_STATUS_OK) + if (!zl3073x_ref_is_status_ok(ref)) return false; - /* Get the latest measured ref's ffo */ - ffo = zl3073x_ref_ffo_get(zldev, ref); - /* Compare with previous value */ - if (pin->freq_offset != ffo) { + if (pin->freq_offset != ref->ffo) { dev_dbg(zldev->dev, "%s freq offset changed: %lld -> %lld\n", - pin->label, pin->freq_offset, ffo); - pin->freq_offset = ffo; + pin->label, pin->freq_offset, ref->ffo); + pin->freq_offset = ref->ffo; return true; } diff --git a/drivers/dpll/zl3073x/fw.c b/drivers/dpll/zl3073x/fw.c index def37fe8d9b0..55b638247f4b 100644 --- a/drivers/dpll/zl3073x/fw.c +++ b/drivers/dpll/zl3073x/fw.c @@ -352,12 +352,12 @@ struct zl3073x_fw *zl3073x_fw_load(struct zl3073x_dev *zldev, const char *data, } /** - * zl3073x_flash_bundle_flash - Flash all components + * zl3073x_fw_component_flash - Flash all components * @zldev: zl3073x device structure - * @components: pointer to components array + * @comp: pointer to components array * @extack: netlink extack pointer to report errors * - * Returns 0 in case of success or negative number otherwise. + * Return: 0 in case of success or negative number otherwise. */ static int zl3073x_fw_component_flash(struct zl3073x_dev *zldev, diff --git a/drivers/dpll/zl3073x/out.c b/drivers/dpll/zl3073x/out.c new file mode 100644 index 000000000000..86829a0c1c02 --- /dev/null +++ b/drivers/dpll/zl3073x/out.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bitfield.h> +#include <linux/cleanup.h> +#include <linux/dev_printk.h> +#include <linux/string.h> +#include <linux/string_choices.h> +#include <linux/types.h> + +#include "core.h" +#include "out.h" + +/** + * zl3073x_out_state_fetch - fetch output state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: output index to fetch state for + * + * Function fetches state of the given output from hardware and stores it + * for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_out *out = &zldev->out[index]; + int rc; + + /* Read output configuration */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &out->ctrl); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, + str_enabled_disabled(zl3073x_out_is_enabled(out)), + zl3073x_out_synth_get(out)); + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read output mode */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &out->mode); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, + zl3073x_out_signal_format_get(out)); + + /* Read output divisor */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &out->div); + if (rc) + return rc; + + if (!out->div) { + dev_err(zldev->dev, "Zero divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "OUT%u divisor: %u\n", index, out->div); + + /* Read output width */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_WIDTH, &out->width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + &out->esync_n_period); + if (rc) + return rc; + + if (!out->esync_n_period) { + dev_err(zldev->dev, + "Zero esync divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + &out->esync_n_width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + &out->phase_comp); + if (rc) + return rc; + + return rc; +} + +/** + * zl3073x_out_state_get - get current output state + * @zldev: pointer to zl3073x_dev structure + * @index: output index to get state for + * + * Return: pointer to given output state + */ +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->out[index]; +} + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out) +{ + struct zl3073x_out *dout = &zldev->out[index]; + int rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration into mailbox */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Update mailbox with changed values */ + if (dout->div != out->div) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, out->div); + if (!rc && dout->width != out->width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, out->width); + if (!rc && dout->esync_n_period != out->esync_n_period) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + out->esync_n_period); + if (!rc && dout->esync_n_width != out->esync_n_width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + out->esync_n_width); + if (!rc && dout->mode != out->mode) + rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, out->mode); + if (!rc && dout->phase_comp != out->phase_comp) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + out->phase_comp); + if (rc) + return rc; + + /* Commit output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* After successful commit store new state */ + dout->div = out->div; + dout->width = out->width; + dout->esync_n_period = out->esync_n_period; + dout->esync_n_width = out->esync_n_width; + dout->mode = out->mode; + dout->phase_comp = out->phase_comp; + + return 0; +} diff --git a/drivers/dpll/zl3073x/out.h b/drivers/dpll/zl3073x/out.h new file mode 100644 index 000000000000..e8ea7a0e0f07 --- /dev/null +++ b/drivers/dpll/zl3073x/out.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_OUT_H +#define _ZL3073X_OUT_H + +#include <linux/bitfield.h> +#include <linux/types.h> + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_out - output state + * @div: output divisor + * @width: output pulse width + * @esync_n_period: embedded sync or n-pin period (for n-div formats) + * @esync_n_width: embedded sync or n-pin pulse width + * @phase_comp: phase compensation + * @ctrl: output control + * @mode: output mode + */ +struct zl3073x_out { + u32 div; + u32 width; + u32 esync_n_period; + u32 esync_n_width; + s32 phase_comp; + u8 ctrl; + u8 mode; +}; + +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index); +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out); + +/** + * zl3073x_out_signal_format_get - get output signal format + * @out: pointer to out state + * + * Return: signal format of given output + */ +static inline u8 zl3073x_out_signal_format_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, out->mode); +} + +/** + * zl3073x_out_is_diff - check if the given output is differential + * @out: pointer to out state + * + * Return: true if output is differential, false if output is single-ended + */ +static inline bool zl3073x_out_is_diff(const struct zl3073x_out *out) +{ + switch (zl3073x_out_signal_format_get(out)) { + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: + return true; + default: + break; + } + + return false; +} + +/** + * zl3073x_out_is_enabled - check if the given output is enabled + * @out: pointer to out state + * + * Return: true if output is enabled, false if output is disabled + */ +static inline bool zl3073x_out_is_enabled(const struct zl3073x_out *out) +{ + return !!FIELD_GET(ZL_OUTPUT_CTRL_EN, out->ctrl); +} + +/** + * zl3073x_out_synth_get - get synth connected to given output + * @out: pointer to out state + * + * Return: index of synth connected to given output. + */ +static inline u8 zl3073x_out_synth_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, out->ctrl); +} + +#endif /* _ZL3073X_OUT_H */ diff --git a/drivers/dpll/zl3073x/prop.c b/drivers/dpll/zl3073x/prop.c index 9e1fca5cdaf1..4ed153087570 100644 --- a/drivers/dpll/zl3073x/prop.c +++ b/drivers/dpll/zl3073x/prop.c @@ -46,10 +46,10 @@ zl3073x_pin_check_freq(struct zl3073x_dev *zldev, enum dpll_pin_direction dir, /* Get output pin synthesizer */ out = zl3073x_output_pin_out_get(id); - synth = zl3073x_out_synth_get(zldev, out); + synth = zl3073x_dev_out_synth_get(zldev, out); /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); + synth_freq = zl3073x_dev_synth_freq_get(zldev, synth); /* Check the frequency divides synth frequency */ if (synth_freq % (u32)freq) @@ -93,13 +93,13 @@ zl3073x_prop_pin_package_label_set(struct zl3073x_dev *zldev, prefix = "REF"; ref = zl3073x_input_pin_ref_get(id); - is_diff = zl3073x_ref_is_diff(zldev, ref); + is_diff = zl3073x_dev_ref_is_diff(zldev, ref); } else { u8 out; prefix = "OUT"; out = zl3073x_output_pin_out_get(id); - is_diff = zl3073x_out_is_diff(zldev, out); + is_diff = zl3073x_dev_out_is_diff(zldev, out); } if (!is_diff) @@ -217,8 +217,8 @@ struct zl3073x_pin_props *zl3073x_pin_props_get(struct zl3073x_dev *zldev, * the synth frequency count. */ out = zl3073x_output_pin_out_get(index); - synth = zl3073x_out_synth_get(zldev, out); - f = 2 * zl3073x_synth_freq_get(zldev, synth); + synth = zl3073x_dev_out_synth_get(zldev, out); + f = 2 * zl3073x_dev_synth_freq_get(zldev, synth); props->dpll_props.phase_gran = f ? div_u64(PSEC_PER_SEC, f) : 1; } diff --git a/drivers/dpll/zl3073x/ref.c b/drivers/dpll/zl3073x/ref.c new file mode 100644 index 000000000000..aa2de13effa8 --- /dev/null +++ b/drivers/dpll/zl3073x/ref.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bitfield.h> +#include <linux/cleanup.h> +#include <linux/dev_printk.h> +#include <linux/string.h> +#include <linux/string_choices.h> +#include <linux/types.h> + +#include "core.h" +#include "ref.h" + +/** + * zl3073x_ref_freq_factorize - factorize given frequency + * @freq: input frequency + * @base: base frequency + * @mult: multiplier + * + * Checks if the given frequency can be factorized using one of the + * supported base frequencies. If so the base frequency and multiplier + * are stored into appropriate parameters if they are not NULL. + * + * Return: 0 on success, -EINVAL if the frequency cannot be factorized + */ +int +zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) +{ + static const u16 base_freqs[] = { + 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, + 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, + 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, + 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, + 32000, 40000, 50000, 62500, + }; + u32 div; + int i; + + for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { + div = freq / base_freqs[i]; + + if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { + if (base) + *base = base_freqs[i]; + if (mult) + *mult = div; + + return 0; + } + } + + return -EINVAL; +} + +/** + * zl3073x_ref_state_fetch - fetch input reference state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to fetch state for + * + * Function fetches state for the given input reference from hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_ref *ref = &zldev->ref[index]; + int rc; + + /* For differential type inputs the N-pin reference shares + * part of the configuration with the P-pin counterpart. + */ + if (zl3073x_is_n_pin(index) && zl3073x_ref_is_diff(ref - 1)) { + struct zl3073x_ref *p_ref = ref - 1; /* P-pin counterpart*/ + + /* Copy the shared items from the P-pin */ + ref->config = p_ref->config; + ref->esync_n_div = p_ref->esync_n_div; + ref->freq_base = p_ref->freq_base; + ref->freq_mult = p_ref->freq_mult; + ref->freq_ratio_m = p_ref->freq_ratio_m; + ref->freq_ratio_n = p_ref->freq_ratio_n; + ref->phase_comp = p_ref->phase_comp; + ref->sync_ctrl = p_ref->sync_ctrl; + + return 0; /* Finish - no non-shared items for now */ + } + + guard(mutex)(&zldev->multiop_lock); + + /* Read reference configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read ref_config register */ + rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref->config); + if (rc) + return rc; + + /* Read frequency related registers */ + rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_BASE, &ref->freq_base); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_MULT, &ref->freq_mult); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_M, &ref->freq_ratio_m); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_N, &ref->freq_ratio_n); + if (rc) + return rc; + + /* Read eSync and N-div rated registers */ + rc = zl3073x_read_u32(zldev, ZL_REG_REF_ESYNC_DIV, &ref->esync_n_div); + if (rc) + return rc; + rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref->sync_ctrl); + if (rc) + return rc; + + /* Read phase compensation register */ + rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, + &ref->phase_comp); + if (rc) + return rc; + + dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, + str_enabled_disabled(zl3073x_ref_is_enabled(ref)), + zl3073x_ref_is_diff(ref) ? "differential" : "single-ended"); + + return rc; +} + +/** + * zl3073x_ref_state_get - get current input reference state + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to get state for + * + * Return: pointer to given input reference state + */ +const struct zl3073x_ref * +zl3073x_ref_state_get(struct zl3073x_dev *zldev, u8 index) +{ + return &zldev->ref[index]; +} + +int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_ref *ref) +{ + struct zl3073x_ref *dref = &zldev->ref[index]; + int rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read reference configuration into mailbox */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Update mailbox with changed values */ + if (dref->freq_base != ref->freq_base) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_BASE, + ref->freq_base); + if (!rc && dref->freq_mult != ref->freq_mult) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_MULT, + ref->freq_mult); + if (!rc && dref->freq_ratio_m != ref->freq_ratio_m) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_M, + ref->freq_ratio_m); + if (!rc && dref->freq_ratio_n != ref->freq_ratio_n) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_N, + ref->freq_ratio_n); + if (!rc && dref->esync_n_div != ref->esync_n_div) + rc = zl3073x_write_u32(zldev, ZL_REG_REF_ESYNC_DIV, + ref->esync_n_div); + if (!rc && dref->sync_ctrl != ref->sync_ctrl) + rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL, + ref->sync_ctrl); + if (!rc && dref->phase_comp != ref->phase_comp) + rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, + ref->phase_comp); + if (rc) + return rc; + + /* Commit reference configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* After successful commit store new state */ + dref->freq_base = ref->freq_base; + dref->freq_mult = ref->freq_mult; + dref->freq_ratio_m = ref->freq_ratio_m; + dref->freq_ratio_n = ref->freq_ratio_n; + dref->esync_n_div = ref->esync_n_div; + dref->sync_ctrl = ref->sync_ctrl; + dref->phase_comp = ref->phase_comp; + + return 0; +} diff --git a/drivers/dpll/zl3073x/ref.h b/drivers/dpll/zl3073x/ref.h new file mode 100644 index 000000000000..efc7f59cd9f9 --- /dev/null +++ b/drivers/dpll/zl3073x/ref.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_REF_H +#define _ZL3073X_REF_H + +#include <linux/bitfield.h> +#include <linux/math64.h> +#include <linux/types.h> + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_ref - input reference state + * @ffo: current fractional frequency offset + * @phase_comp: phase compensation + * @esync_n_div: divisor for embedded sync or n-divided signal formats + * @freq_base: frequency base + * @freq_mult: frequnecy multiplier + * @freq_ratio_m: FEC mode multiplier + * @freq_ratio_n: FEC mode divisor + * @config: reference config + * @sync_ctrl: reference sync control + * @mon_status: reference monitor status + */ +struct zl3073x_ref { + s64 ffo; + u64 phase_comp; + u32 esync_n_div; + u16 freq_base; + u16 freq_mult; + u16 freq_ratio_m; + u16 freq_ratio_n; + u8 config; + u8 sync_ctrl; + u8 mon_status; +}; + +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index); + +const struct zl3073x_ref *zl3073x_ref_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_ref *ref); + +int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); + +/** + * zl3073x_ref_ffo_get - get current fractional frequency offset + * @ref: pointer to ref state + * + * Return: the latest measured fractional frequency offset + */ +static inline s64 +zl3073x_ref_ffo_get(const struct zl3073x_ref *ref) +{ + return ref->ffo; +} + +/** + * zl3073x_ref_freq_get - get given input reference frequency + * @ref: pointer to ref state + * + * Return: frequency of the given input reference + */ +static inline u32 +zl3073x_ref_freq_get(const struct zl3073x_ref *ref) +{ + return mul_u64_u32_div(ref->freq_base * ref->freq_mult, + ref->freq_ratio_m, ref->freq_ratio_n); +} + +/** + * zl3073x_ref_freq_set - set given input reference frequency + * @ref: pointer to ref state + * @freq: frequency to be set + * + * Return: 0 on success, <0 when frequency cannot be factorized + */ +static inline int +zl3073x_ref_freq_set(struct zl3073x_ref *ref, u32 freq) +{ + u16 base, mult; + int rc; + + rc = zl3073x_ref_freq_factorize(freq, &base, &mult); + if (rc) + return rc; + + ref->freq_base = base; + ref->freq_mult = mult; + + return 0; +} + +/** + * zl3073x_ref_is_diff - check if the given input reference is differential + * @ref: pointer to ref state + * + * Return: true if reference is differential, false if reference is single-ended + */ +static inline bool +zl3073x_ref_is_diff(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref->config); +} + +/** + * zl3073x_ref_is_enabled - check if the given input reference is enabled + * @ref: pointer to ref state + * + * Return: true if input refernce is enabled, false otherwise + */ +static inline bool +zl3073x_ref_is_enabled(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_ENABLE, ref->config); +} + +/** + * zl3073x_ref_is_status_ok - check the given input reference status + * @ref: pointer to ref state + * + * Return: true if the status is ok, false otherwise + */ +static inline bool +zl3073x_ref_is_status_ok(const struct zl3073x_ref *ref) +{ + return ref->mon_status == ZL_REF_MON_STATUS_OK; +} + +#endif /* _ZL3073X_REF_H */ diff --git a/drivers/dpll/zl3073x/synth.c b/drivers/dpll/zl3073x/synth.c new file mode 100644 index 000000000000..da839572dab2 --- /dev/null +++ b/drivers/dpll/zl3073x/synth.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/bitfield.h> +#include <linux/cleanup.h> +#include <linux/dev_printk.h> +#include <linux/string.h> +#include <linux/string_choices.h> +#include <linux/types.h> + +#include "core.h" +#include "synth.h" + +/** + * zl3073x_synth_state_fetch - fetch synth state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to fetch state for + * + * Function fetches state of the given synthesizer from the hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_synth *synth = &zldev->synth[index]; + int rc; + + /* Read synth control register */ + rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth->ctrl); + if (rc) + return rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read synth configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, + ZL_REG_SYNTH_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* The output frequency is determined by the following formula: + * base * multiplier * numerator / denominator + * + * Read registers with these values + */ + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &synth->freq_base); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &synth->freq_mult); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &synth->freq_m); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &synth->freq_n); + if (rc) + return rc; + + /* Check denominator for zero to avoid div by 0 */ + if (!synth->freq_n) { + dev_err(zldev->dev, + "Zero divisor for SYNTH%u retrieved from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, + zl3073x_synth_freq_get(synth)); + + return rc; +} + +/** + * zl3073x_synth_state_get - get current synth state + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to get state for + * + * Return: pointer to given synth state + */ +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->synth[index]; +} diff --git a/drivers/dpll/zl3073x/synth.h b/drivers/dpll/zl3073x/synth.h new file mode 100644 index 000000000000..6c55eb8a888c --- /dev/null +++ b/drivers/dpll/zl3073x/synth.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_SYNTH_H +#define _ZL3073X_SYNTH_H + +#include <linux/bitfield.h> +#include <linux/math64.h> +#include <linux/types.h> + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_synth - synthesizer state + * @freq_mult: frequency multiplier + * @freq_base: frequency base + * @freq_m: frequency numerator + * @freq_n: frequency denominator + * @ctrl: synth control + */ +struct zl3073x_synth { + u32 freq_mult; + u16 freq_base; + u16 freq_m; + u16 freq_n; + u8 ctrl; +}; + +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 synth_id); + +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 synth_id); + +int zl3073x_synth_state_set(struct zl3073x_dev *zldev, u8 synth_id, + const struct zl3073x_synth *synth); + +/** + * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by + * @synth: pointer to synth state + * + * Return: ID of DPLL the given synthetizer is driven by + */ +static inline u8 zl3073x_synth_dpll_get(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth->ctrl); +} + +/** + * zl3073x_synth_freq_get - get synth current freq + * @synth: pointer to synth state + * + * Return: frequency of given synthetizer + */ +static inline u32 zl3073x_synth_freq_get(const struct zl3073x_synth *synth) +{ + return mul_u64_u32_div(synth->freq_base * synth->freq_m, + synth->freq_mult, synth->freq_n); +} + +/** + * zl3073x_synth_is_enabled - check if the given synth is enabled + * @synth: pointer to synth state + * + * Return: true if synth is enabled, false otherwise + */ +static inline bool zl3073x_synth_is_enabled(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_EN, synth->ctrl); +} + +#endif /* _ZL3073X_SYNTH_H */ diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 103b2c2eba2a..0c5b94e64ea1 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1184,10 +1184,22 @@ altr_check_ocram_deps_init(struct altr_edac_device_dev *device) if (ret) return ret; - /* Verify OCRAM has been initialized */ + /* + * Verify that OCRAM has been initialized. + * During a warm reset, OCRAM contents are retained, but the control + * and status registers are reset to their default values. Therefore, + * ECC must be explicitly re-enabled in the control register. + * Error condition: if INITCOMPLETEA is clear and ECC_EN is already set. + */ if (!ecc_test_bits(ALTR_A10_ECC_INITCOMPLETEA, - (base + ALTR_A10_ECC_INITSTAT_OFST))) - return -ENODEV; + (base + ALTR_A10_ECC_INITSTAT_OFST))) { + if (!ecc_test_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST))) + ecc_set_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST)); + else + return -ENODEV; + } /* Enable IRQ on Single Bit Error */ writel(ALTR_A10_ECC_SERRINTEN, (base + ALTR_A10_ECC_ERRINTENS_OFST)); @@ -1357,7 +1369,7 @@ static const struct edac_device_prv_data a10_enetecc_data = { .ue_set_mask = ALTR_A10_ECC_TDERRA, .set_err_ofst = ALTR_A10_ECC_INTTEST_OFST, .ecc_irq_handler = altr_edac_a10_ecc_irq, - .inject_fops = &altr_edac_a10_device_inject2_fops, + .inject_fops = &altr_edac_a10_device_inject_fops, }; #endif /* CONFIG_EDAC_ALTERA_ETHERNET */ @@ -1447,7 +1459,7 @@ static const struct edac_device_prv_data a10_usbecc_data = { .ue_set_mask = ALTR_A10_ECC_TDERRA, .set_err_ofst = ALTR_A10_ECC_INTTEST_OFST, .ecc_irq_handler = altr_edac_a10_ecc_irq, - .inject_fops = &altr_edac_a10_device_inject2_fops, + .inject_fops = &altr_edac_a10_device_inject_fops, }; #endif /* CONFIG_EDAC_ALTERA_USB */ diff --git a/drivers/edac/versalnet_edac.c b/drivers/edac/versalnet_edac.c index 1ded4c3f0213..1a1092793092 100644 --- a/drivers/edac/versalnet_edac.c +++ b/drivers/edac/versalnet_edac.c @@ -605,21 +605,23 @@ static int rpmsg_cb(struct rpmsg_device *rpdev, void *data, length = result[MSG_ERR_LENGTH]; offset = result[MSG_ERR_OFFSET]; + /* + * The data can come in two stretches. Construct the regs from two + * messages. The offset indicates the offset from which the data is to + * be taken. + */ + for (i = 0 ; i < length; i++) { + k = offset + i; + j = ERROR_DATA + i; + mc_priv->regs[k] = result[j]; + } + if (result[TOTAL_ERR_LENGTH] > length) { if (!mc_priv->part_len) mc_priv->part_len = length; else mc_priv->part_len += length; - /* - * The data can come in 2 stretches. Construct the regs from 2 - * messages the offset indicates the offset from which the data is to - * be taken - */ - for (i = 0 ; i < length; i++) { - k = offset + i; - j = ERROR_DATA + i; - mc_priv->regs[k] = result[j]; - } + if (mc_priv->part_len < result[TOTAL_ERR_LENGTH]) return 0; mc_priv->part_len = 0; @@ -705,7 +707,7 @@ static int rpmsg_cb(struct rpmsg_device *rpdev, void *data, /* Convert to bytes */ length = result[TOTAL_ERR_LENGTH] * 4; log_non_standard_event(sec_type, &amd_versalnet_guid, mc_priv->message, - sec_sev, (void *)&result[ERROR_DATA], length); + sec_sev, (void *)&mc_priv->regs, length); return 0; } diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index e5e0174a0335..66e1106db5e7 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -577,6 +577,8 @@ void fw_card_initialize(struct fw_card *card, INIT_LIST_HEAD(&card->transactions.list); spin_lock_init(&card->transactions.lock); + spin_lock_init(&card->topology_map.lock); + card->split_timeout.hi = DEFAULT_SPLIT_TIMEOUT / 8000; card->split_timeout.lo = (DEFAULT_SPLIT_TIMEOUT % 8000) << 19; card->split_timeout.cycles = DEFAULT_SPLIT_TIMEOUT; diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 2f73bcd5696f..ed3ae8cdb0cd 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -441,12 +441,13 @@ static void update_topology_map(__be32 *buffer, size_t buffer_size, int root_nod const u32 *self_ids, int self_id_count) { __be32 *map = buffer; + u32 next_generation = be32_to_cpu(buffer[1]) + 1; int node_count = (root_node_id & 0x3f) + 1; memset(map, 0, buffer_size); *map++ = cpu_to_be32((self_id_count + 2) << 16); - *map++ = cpu_to_be32(be32_to_cpu(buffer[1]) + 1); + *map++ = cpu_to_be32(next_generation); *map++ = cpu_to_be32((node_count << 16) | self_id_count); while (self_id_count--) diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index 175836467f21..d8d93059ac04 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2548,10 +2548,17 @@ static int lineinfo_changed_notify(struct notifier_block *nb, container_of(nb, struct gpio_chardev_data, lineinfo_changed_nb); struct lineinfo_changed_ctx *ctx; struct gpio_desc *desc = data; + struct file *fp; if (!test_bit(gpio_chip_hwgpio(desc), cdev->watched_lines)) return NOTIFY_DONE; + /* Keep the file descriptor alive for the duration of the notification. */ + fp = get_file_active(&cdev->fp); + if (!fp) + /* Chardev file descriptor was or is being released. */ + return NOTIFY_DONE; + /* * If this is called from atomic context (for instance: with a spinlock * taken by the atomic notifier chain), any sleeping calls must be done @@ -2575,8 +2582,6 @@ static int lineinfo_changed_notify(struct notifier_block *nb, /* Keep the GPIO device alive until we emit the event. */ ctx->gdev = gpio_device_get(desc->gdev); ctx->cdev = cdev; - /* Keep the file descriptor alive too. */ - get_file(ctx->cdev->fp); INIT_WORK(&ctx->work, lineinfo_changed_func); queue_work(ctx->gdev->line_state_wq, &ctx->work); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index f5d5c45ddc0d..afedea02188d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -236,7 +236,7 @@ static int amdgpu_ctx_init_entity(struct amdgpu_ctx *ctx, u32 hw_ip, r = amdgpu_xcp_select_scheds(adev, hw_ip, hw_prio, fpriv, &num_scheds, &scheds); if (r) - goto cleanup_entity; + goto error_free_entity; } /* disable load balance if the hw engine retains context among dependent jobs */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 2819aceaab74..076bbc09f30c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3414,10 +3414,11 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev, (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX || adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SDMA)) continue; - /* skip CG for VCE/UVD, it's handled specially */ + /* skip CG for VCE/UVD/VPE, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN && + adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VPE && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_JPEG && adev->ip_blocks[i].version->funcs->set_powergating_state) { /* enable powergating to save power */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 8561ad7f6180..ed3bef1edfe4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -82,6 +82,18 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + /* + * Disable peer-to-peer access for DCC-enabled VRAM surfaces on GFX12+. + * Such buffers cannot be safely accessed over P2P due to device-local + * compression metadata. Fallback to system-memory path instead. + * Device supports GFX12 (GC 12.x or newer) + * BO was created with the AMDGPU_GEM_CREATE_GFX12_DCC flag + * + */ + if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(12, 0, 0) && + bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC) + attach->peer2peer = false; + if (!amdgpu_dmabuf_is_xgmi_accessible(attach_adev, bo) && pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c index 9cddbf50442a..37270c4dab8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_isp.c @@ -280,6 +280,8 @@ int isp_kernel_buffer_alloc(struct device *dev, u64 size, if (ret) return ret; + /* Ensure *bo is NULL so a new BO will be created */ + *bo = NULL; ret = amdgpu_bo_create_kernel(adev, size, ISP_MC_ADDR_ALIGN, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index aa9ee5dffa45..9d568c16beb1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1372,7 +1372,7 @@ uint64_t amdgpu_ttm_tt_pde_flags(struct ttm_tt *ttm, struct ttm_resource *mem) mem->mem_type == AMDGPU_PL_MMIO_REMAP)) { flags |= AMDGPU_PTE_SYSTEM; - if (ttm->caching == ttm_cached) + if (ttm && ttm->caching == ttm_cached) flags |= AMDGPU_PTE_SNOOPED; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 761bad98da3e..4d0096d0baa9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -151,15 +151,16 @@ void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_d { struct amdgpu_userq_fence *userq_fence, *tmp; struct dma_fence *fence; + unsigned long flags; u64 rptr; int i; if (!fence_drv) return; + spin_lock_irqsave(&fence_drv->fence_list_lock, flags); rptr = amdgpu_userq_fence_read(fence_drv); - spin_lock(&fence_drv->fence_list_lock); list_for_each_entry_safe(userq_fence, tmp, &fence_drv->fences, link) { fence = &userq_fence->base; @@ -174,7 +175,7 @@ void amdgpu_userq_fence_driver_process(struct amdgpu_userq_fence_driver *fence_d list_del(&userq_fence->link); dma_fence_put(fence); } - spin_unlock(&fence_drv->fence_list_lock); + spin_unlock_irqrestore(&fence_drv->fence_list_lock, flags); } void amdgpu_userq_fence_driver_destroy(struct kref *ref) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index c1a801203949..b1aaef962ad9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2078,7 +2078,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo *bo = before->bo_va->base.bo; amdgpu_vm_it_insert(before, &vm->va); - if (before->flags & AMDGPU_PTE_PRT_FLAG(adev)) + if (before->flags & AMDGPU_VM_PAGE_PRT) amdgpu_vm_prt_get(adev); if (amdgpu_vm_is_bo_always_valid(vm, bo) && @@ -2093,7 +2093,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, struct amdgpu_bo *bo = after->bo_va->base.bo; amdgpu_vm_it_insert(after, &vm->va); - if (after->flags & AMDGPU_PTE_PRT_FLAG(adev)) + if (after->flags & AMDGPU_VM_PAGE_PRT) amdgpu_vm_prt_get(adev); if (amdgpu_vm_is_bo_always_valid(vm, bo) && diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index d61eb9f187c6..f2be16e700c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -5872,9 +5872,9 @@ static void gfx_v11_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, if (flags & AMDGPU_IB_PREEMPTED) control |= INDIRECT_BUFFER_PRE_RESUME(1); - if (vmid) + if (vmid && !ring->adev->gfx.rs64_enable) gfx_v11_0_ring_emit_de_meta(ring, - (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false); + !amdgpu_sriov_vf(ring->adev) && (flags & AMDGPU_IB_PREEMPTED)); } amdgpu_ring_write(ring, header); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c index baf097d2e1ac..ab0bf880d3d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_1.c @@ -878,6 +878,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_1_dec_ring_vm_funcs = { .get_rptr = jpeg_v5_0_1_dec_ring_get_rptr, .get_wptr = jpeg_v5_0_1_dec_ring_get_wptr, .set_wptr = jpeg_v5_0_1_dec_ring_set_wptr, + .parse_cs = amdgpu_jpeg_dec_parse_cs, .emit_frame_size = SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c index eacf4e93ba2f..cb7123ec1a5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c @@ -141,7 +141,7 @@ static int vcn_v4_0_3_late_init(struct amdgpu_ip_block *ip_block) adev->vcn.supported_reset = amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]); - if (amdgpu_dpm_reset_vcn_is_supported(adev)) + if (amdgpu_dpm_reset_vcn_is_supported(adev) && !amdgpu_sriov_vf(adev)) adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c index 714350cabf2f..8bd457dea4cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c @@ -122,7 +122,9 @@ static int vcn_v5_0_1_late_init(struct amdgpu_ip_block *ip_block) switch (amdgpu_ip_version(adev, MP0_HWIP, 0)) { case IP_VERSION(13, 0, 12): - if ((adev->psp.sos.fw_version >= 0x00450025) && amdgpu_dpm_reset_vcn_is_supported(adev)) + if ((adev->psp.sos.fw_version >= 0x00450025) && + amdgpu_dpm_reset_vcn_is_supported(adev) && + !amdgpu_sriov_vf(adev)) adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE; break; default: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c index a65c67cf56ff..f1e7583650c4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c @@ -297,16 +297,16 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope goto out_err_unreserve; } - if (properties->ctx_save_restore_area_size != topo_dev->node_props.cwsr_size) { - pr_debug("queue cwsr size 0x%x not equal to node cwsr size 0x%x\n", + if (properties->ctx_save_restore_area_size < topo_dev->node_props.cwsr_size) { + pr_debug("queue cwsr size 0x%x not sufficient for node cwsr size 0x%x\n", properties->ctx_save_restore_area_size, topo_dev->node_props.cwsr_size); err = -EINVAL; goto out_err_unreserve; } - total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size) - * NUM_XCC(pdd->dev->xcc_mask); + total_cwsr_size = (properties->ctx_save_restore_area_size + + topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask); total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE); err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address, @@ -352,8 +352,8 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope topo_dev = kfd_topology_device_by_id(pdd->dev->id); if (!topo_dev) return -EINVAL; - total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size) - * NUM_XCC(pdd->dev->xcc_mask); + total_cwsr_size = (properties->ctx_save_restore_area_size + + topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask); total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE); kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 9d72411c3379..74a1d3e1d52b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -3687,6 +3687,8 @@ svm_range_set_attr(struct kfd_process *p, struct mm_struct *mm, svm_range_apply_attrs(p, prange, nattr, attrs, &update_mapping); /* TODO: unmap ranges from GPU that lost access */ } + update_mapping |= !p->xnack_enabled && !list_empty(&remap_list); + list_for_each_entry_safe(prange, next, &remove_list, update_list) { pr_debug("unlink old 0x%p prange 0x%p [0x%lx 0x%lx]\n", prange->svms, prange, prange->start, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 91c0188a29b2..2a7a491a62e0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -3859,6 +3859,97 @@ void amdgpu_dm_update_connector_after_detect( update_subconnector_property(aconnector); } +static bool are_sinks_equal(const struct dc_sink *sink1, const struct dc_sink *sink2) +{ + if (!sink1 || !sink2) + return false; + if (sink1->sink_signal != sink2->sink_signal) + return false; + + if (sink1->dc_edid.length != sink2->dc_edid.length) + return false; + + if (memcmp(sink1->dc_edid.raw_edid, sink2->dc_edid.raw_edid, + sink1->dc_edid.length) != 0) + return false; + return true; +} + + +/** + * DOC: hdmi_hpd_debounce_work + * + * HDMI HPD debounce delay in milliseconds. When an HDMI display toggles HPD + * (such as during power save transitions), this delay determines how long to + * wait before processing the HPD event. This allows distinguishing between a + * physical unplug (>hdmi_hpd_debounce_delay) + * and a spontaneous RX HPD toggle (<hdmi_hpd_debounce_delay). + * + * If the toggle is less than this delay, the driver compares sink capabilities + * and permits a hotplug event if they changed. + * + * The default value of 1500ms was chosen based on experimental testing with + * various monitors that exhibit spontaneous HPD toggling behavior. + */ +static void hdmi_hpd_debounce_work(struct work_struct *work) +{ + struct amdgpu_dm_connector *aconnector = + container_of(to_delayed_work(work), struct amdgpu_dm_connector, + hdmi_hpd_debounce_work); + struct drm_connector *connector = &aconnector->base; + struct drm_device *dev = connector->dev; + struct amdgpu_device *adev = drm_to_adev(dev); + struct dc *dc = aconnector->dc_link->ctx->dc; + bool fake_reconnect = false; + bool reallow_idle = false; + bool ret = false; + guard(mutex)(&aconnector->hpd_lock); + + /* Re-detect the display */ + scoped_guard(mutex, &adev->dm.dc_lock) { + if (dc->caps.ips_support && dc->ctx->dmub_srv->idle_allowed) { + dc_allow_idle_optimizations(dc, false); + reallow_idle = true; + } + ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); + } + + if (ret) { + /* Apply workaround delay for certain panels */ + apply_delay_after_dpcd_poweroff(adev, aconnector->dc_sink); + /* Compare sinks to determine if this was a spontaneous HPD toggle */ + if (are_sinks_equal(aconnector->dc_link->local_sink, aconnector->hdmi_prev_sink)) { + /* + * Sinks match - this was a spontaneous HDMI HPD toggle. + */ + drm_dbg_kms(dev, "HDMI HPD: Sink unchanged after debounce, internal re-enable\n"); + fake_reconnect = true; + } + + /* Update connector state */ + amdgpu_dm_update_connector_after_detect(aconnector); + + drm_modeset_lock_all(dev); + dm_restore_drm_connector_state(dev, connector); + drm_modeset_unlock_all(dev); + + /* Only notify OS if sink actually changed */ + if (!fake_reconnect && aconnector->base.force == DRM_FORCE_UNSPECIFIED) + drm_kms_helper_hotplug_event(dev); + } + + /* Release the cached sink reference */ + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } + + scoped_guard(mutex, &adev->dm.dc_lock) { + if (reallow_idle && dc->caps.ips_support) + dc_allow_idle_optimizations(dc, true); + } +} + static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) { struct drm_connector *connector = &aconnector->base; @@ -3868,6 +3959,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state); struct dc *dc = aconnector->dc_link->ctx->dc; bool ret = false; + bool debounce_required = false; if (adev->dm.disable_hpd_irq) return; @@ -3890,6 +3982,14 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) if (!dc_link_detect_connection_type(aconnector->dc_link, &new_connection_type)) drm_err(adev_to_drm(adev), "KMS: Failed to detect connector\n"); + /* + * Check for HDMI disconnect with debounce enabled. + */ + debounce_required = (aconnector->hdmi_hpd_debounce_delay_ms > 0 && + dc_is_hdmi_signal(aconnector->dc_link->connector_signal) && + new_connection_type == dc_connection_none && + aconnector->dc_link->local_sink != NULL); + if (aconnector->base.force && new_connection_type == dc_connection_none) { emulated_link_detect(aconnector->dc_link); @@ -3899,7 +3999,34 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector) if (aconnector->base.force == DRM_FORCE_UNSPECIFIED) drm_kms_helper_connector_hotplug_event(connector); + } else if (debounce_required) { + /* + * HDMI disconnect detected - schedule delayed work instead of + * processing immediately. This allows us to coalesce spurious + * HDMI signals from physical unplugs. + */ + drm_dbg_kms(dev, "HDMI HPD: Disconnect detected, scheduling debounce work (%u ms)\n", + aconnector->hdmi_hpd_debounce_delay_ms); + + /* Cache the current sink for later comparison */ + if (aconnector->hdmi_prev_sink) + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = aconnector->dc_link->local_sink; + if (aconnector->hdmi_prev_sink) + dc_sink_retain(aconnector->hdmi_prev_sink); + + /* Schedule delayed detection. */ + if (mod_delayed_work(system_wq, + &aconnector->hdmi_hpd_debounce_work, + msecs_to_jiffies(aconnector->hdmi_hpd_debounce_delay_ms))) + drm_dbg_kms(dev, "HDMI HPD: Re-scheduled debounce work\n"); + } else { + + /* If the aconnector->hdmi_hpd_debounce_work is scheduled, exit early */ + if (delayed_work_pending(&aconnector->hdmi_hpd_debounce_work)) + return; + scoped_guard(mutex, &adev->dm.dc_lock) { dc_exit_ips_for_hw_access(dc); ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD); @@ -7388,6 +7515,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) if (aconnector->mst_mgr.dev) drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); + /* Cancel and flush any pending HDMI HPD debounce work */ + cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work); + if (aconnector->hdmi_prev_sink) { + dc_sink_release(aconnector->hdmi_prev_sink); + aconnector->hdmi_prev_sink = NULL; + } + if (aconnector->bl_idx != -1) { backlight_device_unregister(dm->backlight_dev[aconnector->bl_idx]); dm->backlight_dev[aconnector->bl_idx] = NULL; @@ -8549,6 +8683,10 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, mutex_init(&aconnector->hpd_lock); mutex_init(&aconnector->handle_mst_msg_ready); + aconnector->hdmi_hpd_debounce_delay_ms = AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS; + INIT_DELAYED_WORK(&aconnector->hdmi_hpd_debounce_work, hdmi_hpd_debounce_work); + aconnector->hdmi_prev_sink = NULL; + /* * configure support HPD hot plug connector_>polled default value is 0 * which means HPD hot plug not supported diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index db75e991ac7b..8ca738957598 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -59,6 +59,7 @@ #define AMDGPU_HDR_MULT_DEFAULT (0x100000000LL) +#define AMDGPU_DM_HDMI_HPD_DEBOUNCE_MS 1500 /* #include "include/amdgpu_dal_power_if.h" #include "amdgpu_dm_irq.h" @@ -819,6 +820,11 @@ struct amdgpu_dm_connector { bool pack_sdp_v1_3; enum adaptive_sync_type as_type; struct amdgpu_hdmi_vsdb_info vsdb_info; + + /* HDMI HPD debounce support */ + unsigned int hdmi_hpd_debounce_delay_ms; + struct delayed_work hdmi_hpd_debounce_work; + struct dc_sink *hdmi_prev_sink; }; static inline void amdgpu_dm_set_mst_status(uint8_t *status, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 5e92eaa67aa3..dbd1da4d85d3 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -884,26 +884,28 @@ struct dsc_mst_fairness_params { }; #if defined(CONFIG_DRM_AMD_DC_FP) -static uint16_t get_fec_overhead_multiplier(struct dc_link *dc_link) +static uint64_t kbps_to_pbn(int kbps, bool is_peak_pbn) { - u8 link_coding_cap; - uint16_t fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_8B_10B; + uint64_t effective_kbps = (uint64_t)kbps; - link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(dc_link); - if (link_coding_cap == DP_128b_132b_ENCODING) - fec_overhead_multiplier_x1000 = PBN_FEC_OVERHEAD_MULTIPLIER_128B_132B; + if (is_peak_pbn) { // add 0.6% (1006/1000) overhead into effective kbps + effective_kbps *= 1006; + effective_kbps = div_u64(effective_kbps, 1000); + } - return fec_overhead_multiplier_x1000; + return (uint64_t) DIV64_U64_ROUND_UP(effective_kbps * 64, (54 * 8 * 1000)); } -static int kbps_to_peak_pbn(int kbps, uint16_t fec_overhead_multiplier_x1000) +static uint32_t pbn_to_kbps(unsigned int pbn, bool with_margin) { - u64 peak_kbps = kbps; + uint64_t pbn_effective = (uint64_t)pbn; + + if (with_margin) // deduct 0.6% (994/1000) overhead from effective pbn + pbn_effective *= (1000000 / PEAK_FACTOR_X1000); + else + pbn_effective *= 1000; - peak_kbps *= 1006; - peak_kbps *= fec_overhead_multiplier_x1000; - peak_kbps = div_u64(peak_kbps, 1000 * 1000); - return (int) DIV64_U64_ROUND_UP(peak_kbps * 64, (54 * 8 * 1000)); + return DIV_U64_ROUND_UP(pbn_effective * 8 * 54, 64); } static void set_dsc_configs_from_fairness_vars(struct dsc_mst_fairness_params *params, @@ -974,7 +976,7 @@ static int bpp_x16_from_pbn(struct dsc_mst_fairness_params param, int pbn) dc_dsc_get_default_config_option(param.sink->ctx->dc, &dsc_options); dsc_options.max_target_bpp_limit_override_x16 = drm_connector->display_info.max_dsc_bpp * 16; - kbps = div_u64((u64)pbn * 994 * 8 * 54, 64); + kbps = pbn_to_kbps(pbn, false); dc_dsc_compute_config( param.sink->ctx->dc->res_pool->dscs[0], ¶m.sink->dsc_caps.dsc_dec_caps, @@ -1003,12 +1005,11 @@ static int increase_dsc_bpp(struct drm_atomic_state *state, int link_timeslots_used; int fair_pbn_alloc; int ret = 0; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); for (i = 0; i < count; i++) { if (vars[i + k].dsc_enabled) { initial_slack[i] = - kbps_to_peak_pbn(params[i].bw_range.max_kbps, fec_overhead_multiplier_x1000) - vars[i + k].pbn; + kbps_to_pbn(params[i].bw_range.max_kbps, false) - vars[i + k].pbn; bpp_increased[i] = false; remaining_to_increase += 1; } else { @@ -1104,7 +1105,6 @@ static int try_disable_dsc(struct drm_atomic_state *state, int next_index; int remaining_to_try = 0; int ret; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); int var_pbn; for (i = 0; i < count; i++) { @@ -1137,7 +1137,7 @@ static int try_disable_dsc(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC index #%d, try no compression\n", next_index); var_pbn = vars[next_index].pbn; - vars[next_index].pbn = kbps_to_peak_pbn(params[next_index].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[next_index].pbn = kbps_to_pbn(params[next_index].bw_range.stream_kbps, true); ret = drm_dp_atomic_find_time_slots(state, params[next_index].port->mgr, params[next_index].port, @@ -1197,7 +1197,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, int count = 0; int i, k, ret; bool debugfs_overwrite = false; - uint16_t fec_overhead_multiplier_x1000 = get_fec_overhead_multiplier(dc_link); struct drm_connector_state *new_conn_state; memset(params, 0, sizeof(params)); @@ -1278,7 +1277,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try no compression\n"); for (i = 0; i < count; i++) { vars[i + k].aconnector = params[i].aconnector; - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, params[i].port, @@ -1300,7 +1299,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, DRM_DEBUG_DRIVER("MST_DSC Try max compression\n"); for (i = 0; i < count; i++) { if (params[i].compression_possible && params[i].clock_force_enable != DSC_CLK_FORCE_DISABLE) { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.min_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.min_kbps, false); vars[i + k].dsc_enabled = true; vars[i + k].bpp_x16 = params[i].bw_range.min_target_bpp_x16; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1308,7 +1307,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (ret < 0) return ret; } else { - vars[i + k].pbn = kbps_to_peak_pbn(params[i].bw_range.stream_kbps, fec_overhead_multiplier_x1000); + vars[i + k].pbn = kbps_to_pbn(params[i].bw_range.stream_kbps, false); vars[i + k].dsc_enabled = false; vars[i + k].bpp_x16 = 0; ret = drm_dp_atomic_find_time_slots(state, params[i].port->mgr, @@ -1763,18 +1762,6 @@ clean_exit: return ret; } -static uint32_t kbps_from_pbn(unsigned int pbn) -{ - uint64_t kbps = (uint64_t)pbn; - - kbps *= (1000000 / PEAK_FACTOR_X1000); - kbps *= 8; - kbps *= 54; - kbps /= 64; - - return (uint32_t)kbps; -} - static bool is_dsc_common_config_possible(struct dc_stream_state *stream, struct dc_dsc_bw_range *bw_range) { @@ -1873,7 +1860,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( dc_link_get_highest_encoding_format(stream->link)); cur_link_settings = stream->link->verified_link_cap; root_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings); - virtual_channel_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); + virtual_channel_bw_in_kbps = pbn_to_kbps(aconnector->mst_output_port->full_pbn, true); /* pick the end to end bw bottleneck */ end_to_end_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); @@ -1926,7 +1913,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( immediate_upstream_port = aconnector->mst_output_port->parent->port_parent; if (immediate_upstream_port) { - virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn); + virtual_channel_bw_in_kbps = pbn_to_kbps(immediate_upstream_port->full_pbn, true); virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps); } else { /* For topology LCT 1 case - only one mstb*/ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index b11383fba35f..1eb04772f5da 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -394,6 +394,8 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, display_count = dcn35_get_active_display_cnt_wa(dc, context, &all_active_disps); if (new_clocks->dtbclk_en && !new_clocks->ref_dtbclk_khz) new_clocks->ref_dtbclk_khz = 600000; + else if (!new_clocks->dtbclk_en && new_clocks->ref_dtbclk_khz > 590000) + new_clocks->ref_dtbclk_khz = 0; /* * if it is safe to lower, but we are already in the lower state, we don't have to do anything @@ -435,7 +437,7 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, actual_dtbclk = REG_READ(CLK1_CLK4_CURRENT_CNT); - if (actual_dtbclk) { + if (actual_dtbclk > 590000) { clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz; clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en; } diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c index de6d62401362..c899c09ea31b 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c @@ -1411,7 +1411,7 @@ static void dccg35_set_dtbclk_dto( __func__, params->otg_inst, params->pixclk_khz, params->ref_dtbclk_khz, req_dtbclk_khz, phase, modulo); - } else { + } else if (!params->ref_dtbclk_khz && !req_dtbclk_khz) { switch (params->otg_inst) { case 0: REG_UPDATE(DCCG_GATE_DISABLE_CNTL5, DTBCLK_P0_GATE_DISABLE, 0); diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 9477c9f9e196..59c42db5382e 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -614,6 +614,14 @@ void dcn20_dpp_pg_control( * DOMAIN11_PGFSM_PWR_STATUS, pwr_status, * 1, 1000); */ + + /* Force disable cursor on plane powerdown on DPP 5 using dpp_force_disable_cursor */ + if (!power_on) { + struct dpp *dpp5 = hws->ctx->dc->res_pool->dpps[dpp_inst]; + if (dpp5 && dpp5->funcs->dpp_force_disable_cursor) + dpp5->funcs->dpp_force_disable_cursor(dpp5); + } + break; default: BREAK_TO_DEBUGGER(); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index b12c11bd6a14..eb262ce42e2d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1691,7 +1691,7 @@ static bool retrieve_link_cap(struct dc_link *link) union edp_configuration_cap edp_config_cap; union dp_downstream_port_present ds_port = { 0 }; enum dc_status status = DC_ERROR_UNEXPECTED; - uint32_t read_dpcd_retry_cnt = 3; + uint32_t read_dpcd_retry_cnt = 20; int i; struct dp_sink_hw_fw_revision dp_hw_fw_revision; const uint32_t post_oui_delay = 30; // 30ms @@ -1734,12 +1734,13 @@ static bool retrieve_link_cap(struct dc_link *link) } dpcd_set_source_specific_data(link); - /* Sink may need to configure internals based on vendor, so allow some - * time before proceeding with possibly vendor specific transactions - */ - msleep(post_oui_delay); for (i = 0; i < read_dpcd_retry_cnt; i++) { + /* + * Sink may need to configure internals based on vendor, so allow some + * time before proceeding with possibly vendor specific transactions + */ + msleep(post_oui_delay); status = core_link_read_dpcd( link, DP_DPCD_REV, diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index ce421bcddcb0..1aae46d703ba 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -1260,6 +1260,17 @@ void mod_freesync_handle_v_update(struct mod_freesync *mod_freesync, update_v_total_for_static_ramp( core_freesync, stream, in_out_vrr); } + + /* + * If VRR is inactive, set vtotal min and max to nominal vtotal + */ + if (in_out_vrr->state == VRR_STATE_INACTIVE) { + in_out_vrr->adjust.v_total_min = + mod_freesync_calc_v_total_from_refresh(stream, + in_out_vrr->max_refresh_in_uhz); + in_out_vrr->adjust.v_total_max = in_out_vrr->adjust.v_total_min; + return; + } } unsigned long long mod_freesync_calc_nominal_field_rate( diff --git a/drivers/gpu/drm/clients/drm_client_setup.c b/drivers/gpu/drm/clients/drm_client_setup.c index 72480db1f00d..515aceac22b1 100644 --- a/drivers/gpu/drm/clients/drm_client_setup.c +++ b/drivers/gpu/drm/clients/drm_client_setup.c @@ -13,8 +13,8 @@ static char drm_client_default[16] = CONFIG_DRM_CLIENT_DEFAULT; module_param_string(active, drm_client_default, sizeof(drm_client_default), 0444); MODULE_PARM_DESC(active, - "Choose which drm client to start, default is" - CONFIG_DRM_CLIENT_DEFAULT "]"); + "Choose which drm client to start, default is " + CONFIG_DRM_CLIENT_DEFAULT); /** * drm_client_setup() - Setup in-kernel DRM clients diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 38f82391bfda..a30493ed9715 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -210,7 +210,7 @@ static struct drm_property_blob *create_in_format_blob(struct drm_device *dev, formats_size = sizeof(__u32) * plane->format_count; if (WARN_ON(!formats_size)) { /* 0 formats are never expected */ - return 0; + return ERR_PTR(-EINVAL); } modifiers_size = @@ -226,7 +226,7 @@ static struct drm_property_blob *create_in_format_blob(struct drm_device *dev, blob = drm_property_create_blob(dev, blob_size, NULL); if (IS_ERR(blob)) - return NULL; + return blob; blob_data = blob->data; blob_data->version = FORMAT_BLOB_CURRENT; diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 801235a5bc0a..a2d2cecf7121 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -39,14 +39,12 @@ bool intel_encoder_is_c10phy(struct intel_encoder *encoder) struct intel_display *display = to_intel_display(encoder); enum phy phy = intel_encoder_to_phy(encoder); - /* PTL doesn't have a PHY connected to PORT B; as such, - * there will never be a case where PTL uses PHY B. - * WCL uses PORT A and B with the C10 PHY. - * Reusing the condition for WCL and extending it for PORT B - * should not cause any issues for PTL. - */ - if (display->platform.pantherlake && phy < PHY_C) - return true; + if (display->platform.pantherlake) { + if (display->platform.pantherlake_wildcatlake) + return phy <= PHY_B; + else + return phy == PHY_A; + } if ((display->platform.lunarlake || display->platform.meteorlake) && phy < PHY_C) return true; diff --git a/drivers/gpu/drm/i915/display/intel_display_device.c b/drivers/gpu/drm/i915/display/intel_display_device.c index a002bc6ce7b0..f3f1f25b0f38 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.c +++ b/drivers/gpu/drm/i915/display/intel_display_device.c @@ -1404,8 +1404,20 @@ static const struct platform_desc bmg_desc = { PLATFORM_GROUP(dgfx), }; +static const u16 wcl_ids[] = { + INTEL_WCL_IDS(ID), + 0 +}; + static const struct platform_desc ptl_desc = { PLATFORM(pantherlake), + .subplatforms = (const struct subplatform_desc[]) { + { + SUBPLATFORM(pantherlake, wildcatlake), + .pciidlist = wcl_ids, + }, + {}, + } }; __diag_pop(); @@ -1482,6 +1494,7 @@ static const struct { INTEL_LNL_IDS(INTEL_DISPLAY_DEVICE, &lnl_desc), INTEL_BMG_IDS(INTEL_DISPLAY_DEVICE, &bmg_desc), INTEL_PTL_IDS(INTEL_DISPLAY_DEVICE, &ptl_desc), + INTEL_WCL_IDS(INTEL_DISPLAY_DEVICE, &ptl_desc), }; static const struct { diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h index f329f1beafef..a910642d589c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_device.h +++ b/drivers/gpu/drm/i915/display/intel_display_device.h @@ -101,7 +101,9 @@ struct pci_dev; /* Display ver 14.1 (based on GMD ID) */ \ func(battlemage) \ /* Display ver 30 (based on GMD ID) */ \ - func(pantherlake) + func(pantherlake) \ + func(pantherlake_wildcatlake) + #define __MEMBER(name) unsigned long name:1; #define __COUNT(x) 1 + diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 4a4cace1f879..e1455fd7277f 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -127,6 +127,9 @@ static bool dmc_firmware_param_disabled(struct intel_display *display) #define DISPLAY_VER13_DMC_MAX_FW_SIZE 0x20000 #define DISPLAY_VER12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE +#define XE3LPD_3002_DMC_PATH DMC_PATH(xe3lpd_3002) +MODULE_FIRMWARE(XE3LPD_3002_DMC_PATH); + #define XE3LPD_DMC_PATH DMC_PATH(xe3lpd) MODULE_FIRMWARE(XE3LPD_DMC_PATH); @@ -183,9 +186,10 @@ static const char *dmc_firmware_default(struct intel_display *display, u32 *size { const char *fw_path = NULL; u32 max_fw_size = 0; - - if (DISPLAY_VERx100(display) == 3002 || - DISPLAY_VERx100(display) == 3000) { + if (DISPLAY_VERx100(display) == 3002) { + fw_path = XE3LPD_3002_DMC_PATH; + max_fw_size = XE2LPD_DMC_MAX_FW_SIZE; + } else if (DISPLAY_VERx100(display) == 3000) { fw_path = XE3LPD_DMC_PATH; max_fw_size = XE2LPD_DMC_MAX_FW_SIZE; } else if (DISPLAY_VERx100(display) == 2000) { diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 10eb93a34cf2..4619237f1346 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -585,6 +585,10 @@ static void _panel_replay_init_dpcd(struct intel_dp *intel_dp) struct intel_display *display = to_intel_display(intel_dp); int ret; + /* TODO: Enable Panel Replay on MST once it's properly implemented. */ + if (intel_dp->mst_detect == DRM_DP_MST) + return; + ret = drm_dp_dpcd_read_data(&intel_dp->aux, DP_PANEL_REPLAY_CAP_SUPPORT, &intel_dp->pr_dpcd, sizeof(intel_dp->pr_dpcd)); if (ret < 0) @@ -888,7 +892,8 @@ static bool is_dc5_dc6_blocked(struct intel_dp *intel_dp) { struct intel_display *display = to_intel_display(intel_dp); u32 current_dc_state = intel_display_power_get_current_dc_state(display); - struct drm_vblank_crtc *vblank = &display->drm->vblank[intel_dp->psr.pipe]; + struct intel_crtc *crtc = intel_crtc_for_pipe(display, intel_dp->psr.pipe); + struct drm_vblank_crtc *vblank = drm_crtc_vblank_crtc(&crtc->base); return (current_dc_state != DC_STATE_EN_UPTO_DC5 && current_dc_state != DC_STATE_EN_UPTO_DC6) || diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index cac6d64ab67d..4e8b3f1c7e25 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -159,6 +159,8 @@ nvkm_falcon_fw_dtor(struct nvkm_falcon_fw *fw) nvkm_memory_unref(&fw->inst); nvkm_falcon_fw_dtor_sigs(fw); nvkm_firmware_dtor(&fw->fw); + kfree(fw->boot); + fw->boot = NULL; } static const struct nvkm_firmware_func diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c index 156c7a0b62a2..3f43686f0195 100644 --- a/drivers/gpu/drm/panthor/panthor_gem.c +++ b/drivers/gpu/drm/panthor/panthor_gem.c @@ -288,6 +288,23 @@ panthor_gem_create_with_handle(struct drm_file *file, panthor_gem_debugfs_set_usage_flags(bo, 0); + /* If this is a write-combine mapping, we query the sgt to force a CPU + * cache flush (dma_map_sgtable() is called when the sgt is created). + * This ensures the zero-ing is visible to any uncached mapping created + * by vmap/mmap. + * FIXME: Ideally this should be done when pages are allocated, not at + * BO creation time. + */ + if (shmem->map_wc) { + struct sg_table *sgt; + + sgt = drm_gem_shmem_get_pages_sgt(shmem); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + goto out_put_gem; + } + } + /* * Allocate an id of idr table where the obj is registered * and handle has the id what user can see. @@ -296,6 +313,7 @@ panthor_gem_create_with_handle(struct drm_file *file, if (!ret) *size = bo->base.base.size; +out_put_gem: /* drop reference from allocate - handle holds it now. */ drm_gem_object_put(&shmem->base); diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 5b5b54e876d4..167d6f122b8e 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -360,13 +360,6 @@ static bool radeon_fence_is_signaled(struct dma_fence *f) if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) return true; - if (down_read_trylock(&rdev->exclusive_lock)) { - radeon_fence_process(rdev, ring); - up_read(&rdev->exclusive_lock); - - if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) - return true; - } return false; } diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 59d5c1ba145a..6c84bd69b11f 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -3148,6 +3148,7 @@ static int tegra_dc_couple(struct tegra_dc *dc) dc->client.parent = &parent->client; dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); + put_device(companion); } return 0; diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index b5089b772267..ddfb2858acbf 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -913,15 +913,6 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) u32 value; int err; - /* If the bootloader enabled DSI it needs to be disabled - * in order for the panel initialization commands to be - * properly sent. - */ - value = tegra_dsi_readl(dsi, DSI_POWER_CONTROL); - - if (value & DSI_POWER_CONTROL_ENABLE) - tegra_dsi_disable(dsi); - err = tegra_dsi_prepare(dsi); if (err < 0) { dev_err(dsi->dev, "failed to prepare: %d\n", err); diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index 5adab6b22916..d0b6a1fa6efa 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -114,9 +114,12 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_ if (err) goto put_channel; - if (supported) + if (supported) { + struct pid *pid = get_task_pid(current, PIDTYPE_TGID); context->memory_context = host1x_memory_context_alloc( - host, client->base.dev, get_task_pid(current, PIDTYPE_TGID)); + host, client->base.dev, pid); + put_pid(pid); + } if (IS_ERR(context->memory_context)) { if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c index 718832b08d96..c46f17ba7236 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.c @@ -100,8 +100,10 @@ vmw_cursor_update_type(struct vmw_private *vmw, struct vmw_plane_state *vps) if (vmw->has_mob) { if ((vmw->capabilities2 & SVGA_CAP2_CURSOR_MOB) != 0) return VMW_CURSOR_UPDATE_MOB; + else + return VMW_CURSOR_UPDATE_GB_ONLY; } - + drm_warn_once(&vmw->drm, "Unknown Cursor Type!\n"); return VMW_CURSOR_UPDATE_NONE; } @@ -139,6 +141,7 @@ static u32 vmw_cursor_mob_size(enum vmw_cursor_update_type update_type, { switch (update_type) { case VMW_CURSOR_UPDATE_LEGACY: + case VMW_CURSOR_UPDATE_GB_ONLY: case VMW_CURSOR_UPDATE_NONE: return 0; case VMW_CURSOR_UPDATE_MOB: @@ -623,6 +626,7 @@ int vmw_cursor_plane_prepare_fb(struct drm_plane *plane, if (!surface || vps->cursor.legacy.id == surface->snooper.id) vps->cursor.update_type = VMW_CURSOR_UPDATE_NONE; break; + case VMW_CURSOR_UPDATE_GB_ONLY: case VMW_CURSOR_UPDATE_MOB: { bo = vmw_user_object_buffer(&vps->uo); if (bo) { @@ -737,6 +741,7 @@ void vmw_cursor_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_state *state) { + struct vmw_bo *bo; struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct drm_plane_state *old_state = @@ -762,6 +767,15 @@ vmw_cursor_plane_atomic_update(struct drm_plane *plane, case VMW_CURSOR_UPDATE_MOB: vmw_cursor_update_mob(dev_priv, vps); break; + case VMW_CURSOR_UPDATE_GB_ONLY: + bo = vmw_user_object_buffer(&vps->uo); + if (bo) + vmw_send_define_cursor_cmd(dev_priv, bo->map.virtual, + vps->base.crtc_w, + vps->base.crtc_h, + vps->base.hotspot_x, + vps->base.hotspot_y); + break; case VMW_CURSOR_UPDATE_NONE: /* do nothing */ break; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h index 40694925a70e..0c2cc0699b0d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cursor_plane.h @@ -33,6 +33,7 @@ static const u32 __maybe_unused vmw_cursor_plane_formats[] = { enum vmw_cursor_update_type { VMW_CURSOR_UPDATE_NONE = 0, VMW_CURSOR_UPDATE_LEGACY, + VMW_CURSOR_UPDATE_GB_ONLY, VMW_CURSOR_UPDATE_MOB, }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index d539f25b5fbe..3057f8baa7d2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3668,6 +3668,11 @@ static int vmw_cmd_check(struct vmw_private *dev_priv, cmd_id = header->id; + if (header->size > SVGA_CMD_MAX_DATASIZE) { + VMW_DEBUG_USER("SVGA3D command: %d is too big.\n", + cmd_id + SVGA_3D_CMD_BASE); + return -E2BIG; + } *size = header->size + sizeof(SVGA3dCmdHeader); cmd_id -= SVGA_3D_CMD_BASE; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index 7de20e56082c..fd4e76486f2d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -32,22 +32,22 @@ enum vmw_bo_dirty_method { /** * struct vmw_bo_dirty - Dirty information for buffer objects + * @ref_count: Reference count for this structure. Must be first member! * @start: First currently dirty bit * @end: Last currently dirty bit + 1 * @method: The currently used dirty method * @change_count: Number of consecutive method change triggers - * @ref_count: Reference count for this structure * @bitmap_size: The size of the bitmap in bits. Typically equal to the * nuber of pages in the bo. * @bitmap: A bitmap where each bit represents a page. A set bit means a * dirty page. */ struct vmw_bo_dirty { + struct kref ref_count; unsigned long start; unsigned long end; enum vmw_bo_dirty_method method; unsigned int change_count; - unsigned int ref_count; unsigned long bitmap_size; unsigned long bitmap[]; }; @@ -221,7 +221,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo) int ret; if (dirty) { - dirty->ref_count++; + kref_get(&dirty->ref_count); return 0; } @@ -235,7 +235,7 @@ int vmw_bo_dirty_add(struct vmw_bo *vbo) dirty->bitmap_size = num_pages; dirty->start = dirty->bitmap_size; dirty->end = 0; - dirty->ref_count = 1; + kref_init(&dirty->ref_count); if (num_pages < PAGE_SIZE / sizeof(pte_t)) { dirty->method = VMW_BO_DIRTY_PAGETABLE; } else { @@ -274,10 +274,8 @@ void vmw_bo_dirty_release(struct vmw_bo *vbo) { struct vmw_bo_dirty *dirty = vbo->dirty; - if (dirty && --dirty->ref_count == 0) { - kvfree(dirty); + if (dirty && kref_put(&dirty->ref_count, (void *)kvfree)) vbo->dirty = NULL; - } } /** diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 7219f6b884b6..4b288eb3f5b0 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -13,7 +13,6 @@ config DRM_XE select TMPFS select DRM_BUDDY select DRM_CLIENT_SELECTION - select DRM_EXEC select DRM_KMS_HELPER select DRM_KUNIT_TEST_HELPERS if DRM_XE_KUNIT_TEST != n select DRM_PANEL diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 51f2a03847f9..f680c8b8f258 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -168,6 +168,7 @@ #define XEHP_SLICE_COMMON_ECO_CHICKEN1 XE_REG_MCR(0x731c, XE_REG_OPTION_MASKED) #define MSC_MSAA_REODER_BUF_BYPASS_DISABLE REG_BIT(14) +#define FAST_CLEAR_VALIGN_FIX REG_BIT(13) #define XE2LPM_CCCHKNREG1 XE_REG(0x82a8) diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c index 0e502feaca81..6bb278167aaf 100644 --- a/drivers/gpu/drm/xe/tests/xe_mocs.c +++ b/drivers/gpu/drm/xe/tests/xe_mocs.c @@ -49,7 +49,7 @@ static void read_l3cc_table(struct xe_gt *gt, fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL); if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) { xe_force_wake_put(gt_to_fw(gt), fw_ref); - KUNIT_ASSERT_TRUE_MSG(test, true, "Forcewake Failed.\n"); + KUNIT_FAIL_AND_ABORT(test, "Forcewake Failed.\n"); } for (i = 0; i < info->num_mocs_regs; i++) { diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c index 870edaf69388..06976cc77918 100644 --- a/drivers/gpu/drm/xe/xe_irq.c +++ b/drivers/gpu/drm/xe/xe_irq.c @@ -847,22 +847,6 @@ static int xe_irq_msix_init(struct xe_device *xe) return 0; } -static irqreturn_t guc2host_irq_handler(int irq, void *arg) -{ - struct xe_device *xe = arg; - struct xe_tile *tile; - u8 id; - - if (!atomic_read(&xe->irq.enabled)) - return IRQ_NONE; - - for_each_tile(tile, xe, id) - xe_guc_irq_handler(&tile->primary_gt->uc.guc, - GUC_INTR_GUC2HOST); - - return IRQ_HANDLED; -} - static irqreturn_t xe_irq_msix_default_hwe_handler(int irq, void *arg) { unsigned int tile_id, gt_id; @@ -979,7 +963,7 @@ int xe_irq_msix_request_irqs(struct xe_device *xe) u16 msix; msix = GUC2HOST_MSIX; - err = xe_irq_msix_request_irq(xe, guc2host_irq_handler, xe, + err = xe_irq_msix_request_irq(xe, xe_irq_handler(xe), xe, DRIVER_NAME "-guc2host", false, &msix); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index 9a6df79fc5b6..89cc6d32f041 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -375,6 +375,7 @@ static const struct pci_device_id pciidlist[] = { INTEL_LNL_IDS(INTEL_VGA_DEVICE, &lnl_desc), INTEL_BMG_IDS(INTEL_VGA_DEVICE, &bmg_desc), INTEL_PTL_IDS(INTEL_VGA_DEVICE, &ptl_desc), + INTEL_WCL_IDS(INTEL_VGA_DEVICE, &ptl_desc), { } }; MODULE_DEVICE_TABLE(pci, pciidlist); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index ccb09ef4ec9e..cdd1dc540a59 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -3369,8 +3369,10 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, struct xe_vm *vm, op == DRM_XE_VM_BIND_OP_PREFETCH) || XE_IOCTL_DBG(xe, prefetch_region && op != DRM_XE_VM_BIND_OP_PREFETCH) || - XE_IOCTL_DBG(xe, (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC && - !(BIT(prefetch_region) & xe->info.mem_region_mask))) || + XE_IOCTL_DBG(xe, (prefetch_region != DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC && + /* Guard against undefined shift in BIT(prefetch_region) */ + (prefetch_region >= (sizeof(xe->info.mem_region_mask) * 8) || + !(BIT(prefetch_region) & xe->info.mem_region_mask)))) || XE_IOCTL_DBG(xe, obj && op == DRM_XE_VM_BIND_OP_UNMAP) || XE_IOCTL_DBG(xe, (flags & DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET) && diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c index cd03891654a1..3cf30718b200 100644 --- a/drivers/gpu/drm/xe/xe_wa.c +++ b/drivers/gpu/drm/xe/xe_wa.c @@ -679,6 +679,8 @@ static const struct xe_rtp_entry_sr engine_was[] = { }, { XE_RTP_NAME("14023061436"), XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3001), + FUNC(xe_rtp_match_first_render_or_compute), OR, + GRAPHICS_VERSION_RANGE(3003, 3005), FUNC(xe_rtp_match_first_render_or_compute)), XE_RTP_ACTIONS(SET(TDL_CHICKEN, QID_WAIT_FOR_THREAD_NOT_RUN_DISABLE)) }, @@ -916,6 +918,15 @@ static const struct xe_rtp_entry_sr lrc_was[] = { XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3003), ENGINE_CLASS(RENDER)), XE_RTP_ACTIONS(SET(COMMON_SLICE_CHICKEN4, SBE_PUSH_CONSTANT_BEHIND_FIX_ENABLE)) }, + { XE_RTP_NAME("14024681466"), + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3000, 3005), ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(XEHP_SLICE_COMMON_ECO_CHICKEN1, FAST_CLEAR_VALIGN_FIX)) + }, + { XE_RTP_NAME("15016589081"), + XE_RTP_RULES(GRAPHICS_VERSION(3000), GRAPHICS_STEP(A0, B0), + ENGINE_CLASS(RENDER)), + XE_RTP_ACTIONS(SET(CHICKEN_RASTER_1, DIS_CLIP_NEGATIVE_BOUNDING_BOX)) + }, }; static __maybe_unused const struct xe_rtp_entry oob_was[] = { diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c index 0a9b44ce4904..b0bab2a1ddcc 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c @@ -194,6 +194,8 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) if (rc) goto cleanup; + mp2_ops->stop(privdata, cl_data->sensor_idx[i]); + amd_sfh_wait_for_response(privdata, cl_data->sensor_idx[i], DISABLE_SENSOR); writel(0, privdata->mmio + amd_get_p2c_val(privdata, 0)); mp2_ops->start(privdata, info); status = amd_sfh_wait_for_response diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 61404d7a43ee..57da4f86a9fa 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -355,6 +355,7 @@ static const struct apple_key_translation swapped_fn_leftctrl_keys[] = { static const struct apple_non_apple_keyboard non_apple_keyboards[] = { { "SONiX USB DEVICE" }, + { "SONiX AK870 PRO" }, { "Keychron" }, { "AONE" }, { "GANSS" }, diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c index fee134a7eba3..5e9a5b8f7f16 100644 --- a/drivers/hid/hid-corsair-void.c +++ b/drivers/hid/hid-corsair-void.c @@ -553,9 +553,8 @@ static void corsair_void_add_battery(struct corsair_void_drvdata *drvdata) if (IS_ERR(new_supply)) { hid_err(drvdata->hid_dev, - "failed to register battery '%s' (reason: %ld)\n", - drvdata->battery_desc.name, - PTR_ERR(new_supply)); + "failed to register battery '%s' (reason: %pe)\n", + drvdata->battery_desc.name, new_supply); return; } diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index 69771fd35006..981d1b6e9658 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -75,7 +75,8 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ mouse_button_fixup(hdev, rdesc, *rsize, 20, 28, 22, 14, 8); break; - case USB_DEVICE_ID_ELECOM_M_XT3URBK: + case USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB: + case USB_DEVICE_ID_ELECOM_M_XT3URBK_018F: case USB_DEVICE_ID_ELECOM_M_XT3DRBK: case USB_DEVICE_ID_ELECOM_M_XT4DRBK: /* @@ -119,7 +120,8 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, static const struct hid_device_id elecom_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, diff --git a/drivers/hid/hid-haptic.c b/drivers/hid/hid-haptic.c index aa090684c1f2..fc8a9997f815 100644 --- a/drivers/hid/hid-haptic.c +++ b/drivers/hid/hid-haptic.c @@ -86,7 +86,7 @@ int hid_haptic_input_configured(struct hid_device *hdev, if (hi->application == HID_DG_TOUCHPAD) { if (haptic->auto_trigger_report && haptic->manual_trigger_report) { - __set_bit(INPUT_PROP_HAPTIC_TOUCHPAD, hi->input->propbit); + __set_bit(INPUT_PROP_PRESSUREPAD, hi->input->propbit); return 1; } return 0; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0723b4b1c9ec..c4589075a5ed 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -449,7 +449,8 @@ #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 #define USB_DEVICE_ID_ELECOM_M_XGL20DLBK 0x00e6 -#define USB_DEVICE_ID_ELECOM_M_XT3URBK 0x00fb +#define USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB 0x00fb +#define USB_DEVICE_ID_ELECOM_M_XT3URBK_018F 0x018f #define USB_DEVICE_ID_ELECOM_M_XT3DRBK 0x00fc #define USB_DEVICE_ID_ELECOM_M_XT4DRBK 0x00fd #define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe @@ -718,6 +719,7 @@ #define USB_DEVICE_ID_ITE_LENOVO_YOGA2 0x8350 #define I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720 0x837a #define USB_DEVICE_ID_ITE_LENOVO_YOGA900 0x8396 +#define I2C_DEVICE_ID_ITE_LENOVO_YOGA_SLIM_7X_KEYBOARD 0x8987 #define USB_DEVICE_ID_ITE8595 0x8595 #define USB_DEVICE_ID_ITE_MEDION_E1239T 0xce50 @@ -1543,7 +1545,7 @@ #define USB_VENDOR_ID_SIGNOTEC 0x2133 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011 0x0018 -#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY 0x4c4a -#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155 0x4155 +#define USB_VENDOR_ID_JIELI_SDK_DEFAULT 0x4c4a +#define USB_DEVICE_ID_JIELI_SDK_4155 0x4155 #endif diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index e56e7de53279..2bbb645c2ff4 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -399,10 +399,11 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_CHROMEBOOK_TROGDOR_POMPOM), HID_BATTERY_QUIRK_AVOID_QUERY }, /* - * Elan I2C-HID touchscreens seem to all report a non present battery, - * set HID_BATTERY_QUIRK_IGNORE for all Elan I2C-HID devices. + * Elan HID touchscreens seem to all report a non present battery, + * set HID_BATTERY_QUIRK_IGNORE for all Elan I2C and USB HID devices. */ { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, HID_ANY_ID), HID_BATTERY_QUIRK_IGNORE }, {} }; diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 654879814f97..9cc3e029e9f6 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -148,6 +148,14 @@ static const __u8 lenovo_tpIIbtkbd_need_fixup_collection[] = { 0x81, 0x01, /* Input (Const,Array,Abs,No Wrap,Linear,Preferred State,No Null Position) */ }; +static const __u8 lenovo_yoga7x_kbd_need_fixup_collection[] = { + 0x15, 0x00, // Logical Minimum (0) + 0x25, 0x65, // Logical Maximum (101) + 0x05, 0x07, // Usage Page (Keyboard) + 0x19, 0x00, // Usage Minimum (0) + 0x29, 0xDD, // Usage Maximum (221) +}; + static const __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { @@ -177,6 +185,13 @@ static const __u8 *lenovo_report_fixup(struct hid_device *hdev, __u8 *rdesc, rdesc[260] = 0x01; /* report count (2) = 0x01 */ } break; + case I2C_DEVICE_ID_ITE_LENOVO_YOGA_SLIM_7X_KEYBOARD: + if (*rsize == 176 && + memcmp(&rdesc[52], lenovo_yoga7x_kbd_need_fixup_collection, + sizeof(lenovo_yoga7x_kbd_need_fixup_collection)) == 0) { + rdesc[55] = rdesc[61]; // logical maximum = usage maximum + } + break; } return rdesc; } @@ -1538,6 +1553,8 @@ static const struct hid_device_id lenovo_devices[] = { USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X12_TAB2) }, + { HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC, + USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_YOGA_SLIM_7X_KEYBOARD) }, { } }; diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c index 0f76e241e0af..a7f10c45f62b 100644 --- a/drivers/hid/hid-ntrig.c +++ b/drivers/hid/hid-ntrig.c @@ -142,13 +142,13 @@ static void ntrig_report_version(struct hid_device *hdev) int ret; char buf[20]; struct usb_device *usb_dev = hid_to_usb_dev(hdev); - unsigned char *data = kmalloc(8, GFP_KERNEL); + unsigned char *data __free(kfree) = kmalloc(8, GFP_KERNEL); if (!hid_is_usb(hdev)) return; if (!data) - goto err_free; + return; ret = usb_control_msg(usb_dev, usb_rcvctrlpipe(usb_dev, 0), USB_REQ_CLEAR_FEATURE, @@ -163,9 +163,6 @@ static void ntrig_report_version(struct hid_device *hdev) hid_info(hdev, "Firmware version: %s (%02x%02x %02x%02x)\n", buf, data[2], data[3], data[4], data[5]); } - -err_free: - kfree(data); } static ssize_t show_phys_width(struct device *dev, diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 63f6eb9030d1..128aa6abd10b 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -1942,6 +1942,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4) "Failed to retrieve DualShock4 calibration info: %d\n", ret); ret = -EILSEQ; + kfree(buf); goto transfer_failed; } else { break; @@ -1959,6 +1960,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4) if (ret) { hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret); + kfree(buf); goto transfer_failed; } } diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index bcd4bccf1a7c..c89a015686c0 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -410,7 +410,8 @@ static const struct hid_device_id hid_have_special_driver[] = { #if IS_ENABLED(CONFIG_HID_ELECOM) { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_BM084) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XGL20DLBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_00FB) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3URBK_018F) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT3DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, @@ -915,7 +916,6 @@ static const struct hid_device_id hid_ignore_list[] = { #endif { HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) }, { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) }, - { HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) }, { } }; @@ -1064,6 +1064,18 @@ bool hid_ignore(struct hid_device *hdev) strlen(elan_acpi_id[i].id))) return true; break; + case USB_VENDOR_ID_JIELI_SDK_DEFAULT: + /* + * Multiple USB devices with identical IDs (mic & touchscreen). + * The touch screen requires hid core processing, but the + * microphone does not. They can be distinguished by manufacturer + * and serial number. + */ + if (hdev->product == USB_DEVICE_ID_JIELI_SDK_4155 && + strncmp(hdev->name, "SmartlinkTechnology", 19) == 0 && + strncmp(hdev->uniq, "20201111000001", 14) == 0) + return true; + break; } if (hdev->type == HID_TYPE_USBMOUSE && diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index ffa14a4621ef..4c4bac6f792b 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -1369,8 +1369,10 @@ static int uclogic_params_ugee_v2_init_event_hooks(struct hid_device *hdev, event_hook->hdev = hdev; event_hook->size = ARRAY_SIZE(reconnect_event); event_hook->event = kmemdup(reconnect_event, event_hook->size, GFP_KERNEL); - if (!event_hook->event) + if (!event_hook->event) { + kfree(event_hook); return -ENOMEM; + } list_add_tail(&event_hook->list, &p->event_hooks->list); diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index edd61ef50e16..95377c5f6335 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -806,8 +806,8 @@ static int pidff_request_effect_upload(struct pidff_device *pidff, int efnum) static int pidff_needs_playback(struct pidff_device *pidff, int effect_id, int n) { - return pidff->effect[effect_id].is_infinite || - pidff->effect[effect_id].loop_count != n; + return !pidff->effect[effect_id].is_infinite || + pidff->effect[effect_id].loop_count != n; } /* diff --git a/drivers/hwmon/gpd-fan.c b/drivers/hwmon/gpd-fan.c index 321794807e8d..f81c3bc422f4 100644 --- a/drivers/hwmon/gpd-fan.c +++ b/drivers/hwmon/gpd-fan.c @@ -12,9 +12,9 @@ * Copyright (c) 2024 Cryolitia PukNgae */ -#include <linux/acpi.h> #include <linux/dmi.h> #include <linux/hwmon.h> +#include <linux/io.h> #include <linux/ioport.h> #include <linux/kernel.h> #include <linux/module.h> @@ -276,31 +276,6 @@ static int gpd_generic_read_rpm(void) return (u16)high << 8 | low; } -static void gpd_win4_init_ec(void) -{ - u8 chip_id, chip_ver; - - gpd_ecram_read(0x2000, &chip_id); - - if (chip_id == 0x55) { - gpd_ecram_read(0x1060, &chip_ver); - gpd_ecram_write(0x1060, chip_ver | 0x80); - } -} - -static int gpd_win4_read_rpm(void) -{ - int ret; - - ret = gpd_generic_read_rpm(); - - if (ret == 0) - // Re-init EC when speed is 0 - gpd_win4_init_ec(); - - return ret; -} - static int gpd_wm2_read_rpm(void) { for (u16 pwm_ctr_offset = GPD_PWM_CTR_OFFSET; @@ -320,11 +295,10 @@ static int gpd_wm2_read_rpm(void) static int gpd_read_rpm(void) { switch (gpd_driver_priv.drvdata->board) { + case win4_6800u: case win_mini: case duo: return gpd_generic_read_rpm(); - case win4_6800u: - return gpd_win4_read_rpm(); case win_max_2: return gpd_wm2_read_rpm(); } @@ -607,6 +581,28 @@ static struct hwmon_chip_info gpd_fan_chip_info = { .info = gpd_fan_hwmon_channel_info }; +static void gpd_win4_init_ec(void) +{ + u8 chip_id, chip_ver; + + gpd_ecram_read(0x2000, &chip_id); + + if (chip_id == 0x55) { + gpd_ecram_read(0x1060, &chip_ver); + gpd_ecram_write(0x1060, chip_ver | 0x80); + } +} + +static void gpd_init_ec(void) +{ + // The buggy firmware won't initialize EC properly on boot. + // Before its initialization, reading RPM will always return 0, + // and writing PWM will have no effect. + // Initialize it manually on driver load. + if (gpd_driver_priv.drvdata->board == win4_6800u) + gpd_win4_init_ec(); +} + static int gpd_fan_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -634,6 +630,8 @@ static int gpd_fan_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hwdev), "Failed to register hwmon device\n"); + gpd_init_ec(); + return 0; } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index fc1e86f6c409..90daa58126f4 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -842,7 +842,7 @@ static int mlx5_query_node_guid(struct mlx5_ib_dev *dev, break; case MLX5_VPORT_ACCESS_METHOD_NIC: - err = mlx5_query_nic_vport_node_guid(dev->mdev, &tmp); + err = mlx5_query_nic_vport_node_guid(dev->mdev, 0, false, &tmp); break; default: diff --git a/drivers/input/keyboard/cros_ec_keyb.c b/drivers/input/keyboard/cros_ec_keyb.c index f7209c8ebbcc..1c6b0461dc35 100644 --- a/drivers/input/keyboard/cros_ec_keyb.c +++ b/drivers/input/keyboard/cros_ec_keyb.c @@ -261,6 +261,12 @@ static int cros_ec_keyb_work(struct notifier_block *nb, case EC_MKBP_EVENT_KEY_MATRIX: pm_wakeup_event(ckdev->dev, 0); + if (!ckdev->idev) { + dev_warn_once(ckdev->dev, + "Unexpected key matrix event\n"); + return NOTIFY_OK; + } + if (ckdev->ec->event_size != ckdev->cols) { dev_err(ckdev->dev, "Discarded incomplete key matrix event.\n"); diff --git a/drivers/input/keyboard/imx_sc_key.c b/drivers/input/keyboard/imx_sc_key.c index d18839f1f4f6..b620cd310cdb 100644 --- a/drivers/input/keyboard/imx_sc_key.c +++ b/drivers/input/keyboard/imx_sc_key.c @@ -158,7 +158,7 @@ static int imx_sc_key_probe(struct platform_device *pdev) return error; } - error = devm_add_action_or_reset(&pdev->dev, imx_sc_key_action, &priv); + error = devm_add_action_or_reset(&pdev->dev, imx_sc_key_action, priv); if (error) return error; diff --git a/drivers/input/tablet/pegasus_notetaker.c b/drivers/input/tablet/pegasus_notetaker.c index 8d6b71d59793..eabb4a0b8a0d 100644 --- a/drivers/input/tablet/pegasus_notetaker.c +++ b/drivers/input/tablet/pegasus_notetaker.c @@ -63,6 +63,9 @@ #define BUTTON_PRESSED 0xb5 #define COMMAND_VERSION 0xa9 +/* 1 Status + 1 Color + 2 X + 2 Y = 6 bytes */ +#define NOTETAKER_PACKET_SIZE 6 + /* in xy data packet */ #define BATTERY_NO_REPORT 0x40 #define BATTERY_LOW 0x41 @@ -311,6 +314,12 @@ static int pegasus_probe(struct usb_interface *intf, } pegasus->data_len = usb_maxpacket(dev, pipe); + if (pegasus->data_len < NOTETAKER_PACKET_SIZE) { + dev_err(&intf->dev, "packet size is too small (%d)\n", + pegasus->data_len); + error = -EINVAL; + goto err_free_mem; + } pegasus->data = usb_alloc_coherent(dev, pegasus->data_len, GFP_KERNEL, &pegasus->data_dma); diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index 252dcae039f8..f8798d11ec03 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -796,17 +796,6 @@ int goodix_reset_no_int_sync(struct goodix_ts_data *ts) usleep_range(6000, 10000); /* T4: > 5ms */ - /* - * Put the reset pin back in to input / high-impedance mode to save - * power. Only do this in the non ACPI case since some ACPI boards - * don't have a pull-up, so there the reset pin must stay active-high. - */ - if (ts->irq_pin_access_method == IRQ_PIN_ACCESS_GPIO) { - error = gpiod_direction_input(ts->gpiod_rst); - if (error) - goto error; - } - return 0; error: @@ -957,14 +946,6 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) return -EINVAL; } - /* - * Normally we put the reset pin in input / high-impedance mode to save - * power. But some x86/ACPI boards don't have a pull-up, so for the ACPI - * case, leave the pin as is. This results in the pin not being touched - * at all on x86/ACPI boards, except when needed for error-recover. - */ - ts->gpiod_rst_flags = GPIOD_ASIS; - return devm_acpi_dev_add_driver_gpios(dev, gpio_mapping); } #else @@ -989,12 +970,6 @@ static int goodix_get_gpio_config(struct goodix_ts_data *ts) return -EINVAL; dev = &ts->client->dev; - /* - * By default we request the reset pin as input, leaving it in - * high-impedance when not resetting the controller to save power. - */ - ts->gpiod_rst_flags = GPIOD_IN; - ts->avdd28 = devm_regulator_get(dev, "AVDD28"); if (IS_ERR(ts->avdd28)) return dev_err_probe(dev, PTR_ERR(ts->avdd28), "Failed to get AVDD28 regulator\n"); @@ -1019,7 +994,7 @@ retry_get_irq_gpio: ts->gpiod_int = gpiod; /* Get the reset line GPIO pin number */ - gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, ts->gpiod_rst_flags); + gpiod = devm_gpiod_get_optional(dev, GOODIX_GPIO_RST_NAME, GPIOD_ASIS); if (IS_ERR(gpiod)) return dev_err_probe(dev, PTR_ERR(gpiod), "Failed to get %s GPIO\n", GOODIX_GPIO_RST_NAME); @@ -1557,6 +1532,7 @@ MODULE_DEVICE_TABLE(i2c, goodix_ts_id); static const struct acpi_device_id goodix_acpi_match[] = { { "GDIX1001", 0 }, { "GDIX1002", 0 }, + { "GDIX1003", 0 }, { "GDX9110", 0 }, { } }; diff --git a/drivers/input/touchscreen/goodix.h b/drivers/input/touchscreen/goodix.h index 87797cc88b32..0d1e8a8d2cba 100644 --- a/drivers/input/touchscreen/goodix.h +++ b/drivers/input/touchscreen/goodix.h @@ -88,7 +88,6 @@ struct goodix_ts_data { struct gpio_desc *gpiod_rst; int gpio_count; int gpio_int_idx; - enum gpiod_flags gpiod_rst_flags; char id[GOODIX_ID_MAX_LEN + 1]; char cfg_name[64]; u16 version; diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c index 6f1010da221c..21d4a35538f6 100644 --- a/drivers/iommu/iommufd/driver.c +++ b/drivers/iommu/iommufd/driver.c @@ -161,8 +161,8 @@ int iommufd_viommu_report_event(struct iommufd_viommu *viommu, vevent = &veventq->lost_events_header; goto out_set_header; } - memcpy(vevent->event_data, event_data, data_len); vevent->data_len = data_len; + memcpy(vevent->event_data, event_data, data_len); veventq->num_events++; out_set_header: diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 627f9b78483a..85d0843ed07b 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -614,7 +614,6 @@ struct iommufd_veventq { struct iommufd_eventq common; struct iommufd_viommu *viommu; struct list_head node; /* for iommufd_viommu::veventqs */ - struct iommufd_vevent lost_events_header; enum iommu_veventq_type type; unsigned int depth; @@ -622,6 +621,9 @@ struct iommufd_veventq { /* Use common.lock for protection */ u32 num_events; u32 sequence; + + /* Must be last as it ends in a flexible-array member. */ + struct iommufd_vevent lost_events_header; }; static inline struct iommufd_veventq * diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index e5805885394e..70290b35b317 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -166,7 +166,8 @@ static int riscv_intc_domain_alloc(struct irq_domain *domain, static const struct irq_domain_ops riscv_intc_domain_ops = { .map = riscv_intc_domain_map, .xlate = irq_domain_xlate_onecell, - .alloc = riscv_intc_domain_alloc + .alloc = riscv_intc_domain_alloc, + .free = irq_domain_free_irqs_top, }; static struct fwnode_handle *riscv_intc_hwnode(void) diff --git a/drivers/md/dm-pcache/Makefile b/drivers/md/dm-pcache/Makefile index 86776e4acad2..cedfd38854f6 100644 --- a/drivers/md/dm-pcache/Makefile +++ b/drivers/md/dm-pcache/Makefile @@ -1,3 +1,3 @@ dm-pcache-y := dm_pcache.o cache_dev.o segment.o backing_dev.o cache.o cache_gc.o cache_writeback.o cache_segment.o cache_key.o cache_req.o -obj-m += dm-pcache.o +obj-$(CONFIG_DM_PCACHE) += dm-pcache.o diff --git a/drivers/md/dm-pcache/cache.c b/drivers/md/dm-pcache/cache.c index d8e92367d947..698697a7a73c 100644 --- a/drivers/md/dm-pcache/cache.c +++ b/drivers/md/dm-pcache/cache.c @@ -181,7 +181,7 @@ static void cache_info_init_default(struct pcache_cache *cache) { struct pcache_cache_info *cache_info = &cache->cache_info; - cache_info->header.seq = 0; + memset(cache_info, 0, sizeof(*cache_info)); cache_info->n_segs = cache->cache_dev->seg_num; cache_info_set_gc_percent(cache_info, PCACHE_CACHE_GC_PERCENT_DEFAULT); } @@ -411,7 +411,7 @@ void pcache_cache_stop(struct dm_pcache *pcache) { struct pcache_cache *cache = &pcache->cache; - cache_flush(cache); + pcache_cache_flush(cache); cancel_delayed_work_sync(&cache->gc_work); flush_work(&cache->clean_work); diff --git a/drivers/md/dm-pcache/cache.h b/drivers/md/dm-pcache/cache.h index 1136d86958c8..27613b56be54 100644 --- a/drivers/md/dm-pcache/cache.h +++ b/drivers/md/dm-pcache/cache.h @@ -339,7 +339,7 @@ void cache_seg_put(struct pcache_cache_segment *cache_seg); void cache_seg_set_next_seg(struct pcache_cache_segment *cache_seg, u32 seg_id); /* cache request*/ -int cache_flush(struct pcache_cache *cache); +int pcache_cache_flush(struct pcache_cache *cache); void miss_read_end_work_fn(struct work_struct *work); int pcache_cache_handle_req(struct pcache_cache *cache, struct pcache_request *pcache_req); diff --git a/drivers/md/dm-pcache/cache_req.c b/drivers/md/dm-pcache/cache_req.c index 27f94c1fa968..7854a30e07b7 100644 --- a/drivers/md/dm-pcache/cache_req.c +++ b/drivers/md/dm-pcache/cache_req.c @@ -790,7 +790,7 @@ err: } /** - * cache_flush - Flush all ksets to persist any pending cache data + * pcache_cache_flush - Flush all ksets to persist any pending cache data * @cache: Pointer to the cache structure * * This function iterates through all ksets associated with the provided `cache` @@ -802,7 +802,7 @@ err: * the respective error code, preventing the flush operation from proceeding to * subsequent ksets. */ -int cache_flush(struct pcache_cache *cache) +int pcache_cache_flush(struct pcache_cache *cache) { struct pcache_cache_kset *kset; int ret; @@ -827,7 +827,7 @@ int pcache_cache_handle_req(struct pcache_cache *cache, struct pcache_request *p struct bio *bio = pcache_req->bio; if (unlikely(bio->bi_opf & REQ_PREFLUSH)) - return cache_flush(cache); + return pcache_cache_flush(cache); if (bio_data_dir(bio) == READ) return cache_read(cache, pcache_req); diff --git a/drivers/md/dm-pcache/pcache_internal.h b/drivers/md/dm-pcache/pcache_internal.h index d427e534727c..b7a3319d2bd3 100644 --- a/drivers/md/dm-pcache/pcache_internal.h +++ b/drivers/md/dm-pcache/pcache_internal.h @@ -99,7 +99,7 @@ static inline void __must_check *pcache_meta_find_latest(struct pcache_meta_head /* Update latest if a more recent sequence is found */ if (!latest || pcache_meta_seq_after(meta->seq, seq_latest)) { seq_latest = meta->seq; - latest = (void *)header + (i * meta_max_size); + latest = meta_addr; } } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index d382a390d39a..72047b47a7a0 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -320,11 +320,7 @@ static int fec_alloc_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio) if (fio->bufs[n]) continue; - fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOWAIT); - if (unlikely(!fio->bufs[n])) { - DMERR("failed to allocate FEC buffer"); - return -ENOMEM; - } + fio->bufs[n] = mempool_alloc(&v->fec->prealloc_pool, GFP_NOIO); } /* try to allocate the maximum number of buffers */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f5e5e59b232b..6c83ab940af7 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2005,7 +2005,7 @@ static void dm_split_and_process_bio(struct mapped_device *md, * linear target or multiple linear targets pointing to the same * device), we can send the flush with data directly to it. */ - if (map->flush_bypasses_map) { + if (bio->bi_iter.bi_size && map->flush_bypasses_map) { struct list_head *devices = dm_table_get_devices(map); if (devices->next == devices->prev) goto send_preflush_with_data; diff --git a/drivers/memory/tegra/tegra210.c b/drivers/memory/tegra/tegra210.c index cfa61dd88557..3c2949c16fde 100644 --- a/drivers/memory/tegra/tegra210.c +++ b/drivers/memory/tegra/tegra210.c @@ -1015,7 +1015,7 @@ static const struct tegra_mc_client tegra210_mc_clients[] = { }, }, }, { - .id = TEGRA210_MC_SESRD, + .id = TEGRA210_MC_SESWR, .name = "seswr", .swgroup = TEGRA_SWGROUP_SE, .regs = { @@ -1079,7 +1079,7 @@ static const struct tegra_mc_client tegra210_mc_clients[] = { }, }, }, { - .id = TEGRA210_MC_ETRR, + .id = TEGRA210_MC_ETRW, .name = "etrw", .swgroup = TEGRA_SWGROUP_ETR, .regs = { diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 2c963cb6724b..10d0ef58ef49 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -950,7 +950,7 @@ config MMC_USHC config MMC_WMT tristate "Wondermedia SD/MMC Host Controller support" depends on ARCH_VT8500 || COMPILE_TEST - default y + default ARCH_VT8500 help This selects support for the SD/MMC Host Controller on Wondermedia WM8505/WM8650 based SoCs. diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c index 82dd906bb002..681354942e97 100644 --- a/drivers/mmc/host/dw_mmc-rockchip.c +++ b/drivers/mmc/host/dw_mmc-rockchip.c @@ -42,7 +42,7 @@ struct dw_mci_rockchip_priv_data { */ static int rockchip_mmc_get_internal_phase(struct dw_mci *host, bool sample) { - unsigned long rate = clk_get_rate(host->ciu_clk); + unsigned long rate = clk_get_rate(host->ciu_clk) / RK3288_CLKGEN_DIV; u32 raw_value; u16 degrees; u32 delay_num = 0; @@ -85,7 +85,7 @@ static int rockchip_mmc_get_phase(struct dw_mci *host, bool sample) static int rockchip_mmc_set_internal_phase(struct dw_mci *host, bool sample, int degrees) { - unsigned long rate = clk_get_rate(host->ciu_clk); + unsigned long rate = clk_get_rate(host->ciu_clk) / RK3288_CLKGEN_DIV; u8 nineties, remainder; u8 delay_num; u32 raw_value; diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c index 26d03352af63..b5ea058ed467 100644 --- a/drivers/mmc/host/pxamci.c +++ b/drivers/mmc/host/pxamci.c @@ -652,10 +652,9 @@ static int pxamci_probe(struct platform_device *pdev) host->clkrt = CLKRT_OFF; host->clk = devm_clk_get(dev, NULL); - if (IS_ERR(host->clk)) { - host->clk = NULL; - return PTR_ERR(host->clk); - } + if (IS_ERR(host->clk)) + return dev_err_probe(dev, PTR_ERR(host->clk), + "Failed to acquire clock\n"); host->clkrate = clk_get_rate(host->clk); @@ -703,46 +702,37 @@ static int pxamci_probe(struct platform_device *pdev) platform_set_drvdata(pdev, mmc); - host->dma_chan_rx = dma_request_chan(dev, "rx"); - if (IS_ERR(host->dma_chan_rx)) { - host->dma_chan_rx = NULL; + host->dma_chan_rx = devm_dma_request_chan(dev, "rx"); + if (IS_ERR(host->dma_chan_rx)) return dev_err_probe(dev, PTR_ERR(host->dma_chan_rx), "unable to request rx dma channel\n"); - } - host->dma_chan_tx = dma_request_chan(dev, "tx"); - if (IS_ERR(host->dma_chan_tx)) { - dev_err(dev, "unable to request tx dma channel\n"); - ret = PTR_ERR(host->dma_chan_tx); - host->dma_chan_tx = NULL; - goto out; - } + + host->dma_chan_tx = devm_dma_request_chan(dev, "tx"); + if (IS_ERR(host->dma_chan_tx)) + return dev_err_probe(dev, PTR_ERR(host->dma_chan_tx), + "unable to request tx dma channel\n"); if (host->pdata) { host->detect_delay_ms = host->pdata->detect_delay_ms; host->power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); - if (IS_ERR(host->power)) { - ret = PTR_ERR(host->power); - dev_err(dev, "Failed requesting gpio_power\n"); - goto out; - } + if (IS_ERR(host->power)) + return dev_err_probe(dev, PTR_ERR(host->power), + "Failed requesting gpio_power\n"); /* FIXME: should we pass detection delay to debounce? */ ret = mmc_gpiod_request_cd(mmc, "cd", 0, false, 0); - if (ret && ret != -ENOENT) { - dev_err(dev, "Failed requesting gpio_cd\n"); - goto out; - } + if (ret && ret != -ENOENT) + return dev_err_probe(dev, ret, "Failed requesting gpio_cd\n"); if (!host->pdata->gpio_card_ro_invert) mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH; ret = mmc_gpiod_request_ro(mmc, "wp", 0, 0); - if (ret && ret != -ENOENT) { - dev_err(dev, "Failed requesting gpio_ro\n"); - goto out; - } + if (ret && ret != -ENOENT) + return dev_err_probe(dev, ret, "Failed requesting gpio_ro\n"); + if (!ret) host->use_ro_gpio = true; @@ -759,16 +749,8 @@ static int pxamci_probe(struct platform_device *pdev) if (ret) { if (host->pdata && host->pdata->exit) host->pdata->exit(dev, mmc); - goto out; } - return 0; - -out: - if (host->dma_chan_rx) - dma_release_channel(host->dma_chan_rx); - if (host->dma_chan_tx) - dma_release_channel(host->dma_chan_tx); return ret; } @@ -791,8 +773,6 @@ static void pxamci_remove(struct platform_device *pdev) dmaengine_terminate_all(host->dma_chan_rx); dmaengine_terminate_all(host->dma_chan_tx); - dma_release_channel(host->dma_chan_rx); - dma_release_channel(host->dma_chan_tx); } } diff --git a/drivers/mmc/host/sdhci-of-dwcmshc.c b/drivers/mmc/host/sdhci-of-dwcmshc.c index eebd45389956..5b61401a7f3d 100644 --- a/drivers/mmc/host/sdhci-of-dwcmshc.c +++ b/drivers/mmc/host/sdhci-of-dwcmshc.c @@ -94,7 +94,7 @@ #define DLL_TXCLK_TAPNUM_DEFAULT 0x10 #define DLL_TXCLK_TAPNUM_90_DEGREES 0xA #define DLL_TXCLK_TAPNUM_FROM_SW BIT(24) -#define DLL_STRBIN_TAPNUM_DEFAULT 0x8 +#define DLL_STRBIN_TAPNUM_DEFAULT 0x4 #define DLL_STRBIN_TAPNUM_FROM_SW BIT(24) #define DLL_STRBIN_DELAY_NUM_SEL BIT(26) #define DLL_STRBIN_DELAY_NUM_OFFSET 16 diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 8dc4f5c493fc..335c702633ff 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -599,6 +599,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp) uint8_t *datbuf = NULL, *oobbuf = NULL; size_t datbuf_len, oobbuf_len; int ret = 0; + u64 end; if (copy_from_user(&req, argp, sizeof(req))) return -EFAULT; @@ -618,7 +619,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd, struct mtd_write_req __user *argp) req.len &= 0xffffffff; req.ooblen &= 0xffffffff; - if (req.start + req.len > mtd->size) + if (check_add_overflow(req.start, req.len, &end) || end > mtd->size) return -EINVAL; datbuf_len = min_t(size_t, req.len, mtd->erasesize); @@ -698,6 +699,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp) size_t datbuf_len, oobbuf_len; size_t orig_len, orig_ooblen; int ret = 0; + u64 end; if (copy_from_user(&req, argp, sizeof(req))) return -EFAULT; @@ -724,7 +726,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd, struct mtd_read_req __user *argp) req.len &= 0xffffffff; req.ooblen &= 0xffffffff; - if (req.start + req.len > mtd->size) { + if (check_add_overflow(req.start, req.len, &end) || end > mtd->size) { ret = -EINVAL; goto out; } diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig index 4a17271076bc..1e57c8de8578 100644 --- a/drivers/mtd/nand/Kconfig +++ b/drivers/mtd/nand/Kconfig @@ -63,7 +63,7 @@ config MTD_NAND_ECC_MEDIATEK config MTD_NAND_ECC_REALTEK tristate "Realtek RTL93xx hardware ECC engine" - depends on HAS_IOMEM + depends on HAS_IOMEM && HAS_DMA depends on MACH_REALTEK_RTL || COMPILE_TEST select MTD_NAND_ECC help diff --git a/drivers/mtd/nand/ecc-realtek.c b/drivers/mtd/nand/ecc-realtek.c index 7d718934c909..0046da37ea3e 100644 --- a/drivers/mtd/nand/ecc-realtek.c +++ b/drivers/mtd/nand/ecc-realtek.c @@ -380,7 +380,7 @@ static void rtl_ecc_cleanup_ctx(struct nand_device *nand) nand_ecc_cleanup_req_tweaking(&ctx->req_ctx); } -static struct nand_ecc_engine_ops rtl_ecc_engine_ops = { +static const struct nand_ecc_engine_ops rtl_ecc_engine_ops = { .init_ctx = rtl_ecc_init_ctx, .cleanup_ctx = rtl_ecc_cleanup_ctx, .prepare_io_req = rtl_ecc_prepare_io_req, @@ -418,8 +418,8 @@ static int rtl_ecc_probe(struct platform_device *pdev) rtlc->buf = dma_alloc_noncoherent(dev, RTL_ECC_DMA_SIZE, &rtlc->buf_dma, DMA_BIDIRECTIONAL, GFP_KERNEL); - if (IS_ERR(rtlc->buf)) - return PTR_ERR(rtlc->buf); + if (!rtlc->buf) + return -ENOMEM; rtlc->dev = dev; rtlc->engine.dev = dev; diff --git a/drivers/mtd/nand/onenand/onenand_samsung.c b/drivers/mtd/nand/onenand/onenand_samsung.c index f37a6138e461..6d6aa709a21f 100644 --- a/drivers/mtd/nand/onenand/onenand_samsung.c +++ b/drivers/mtd/nand/onenand/onenand_samsung.c @@ -906,7 +906,7 @@ static int s3c_onenand_probe(struct platform_device *pdev) err = devm_request_irq(&pdev->dev, r->start, s5pc110_onenand_irq, IRQF_SHARED, "onenand", - &onenand); + onenand); if (err) { dev_err(&pdev->dev, "failed to get irq\n"); return err; diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c index 6667eea95597..32ed38b89394 100644 --- a/drivers/mtd/nand/raw/cadence-nand-controller.c +++ b/drivers/mtd/nand/raw/cadence-nand-controller.c @@ -2871,7 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl) static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) { dma_cap_mask_t mask; - struct dma_device *dma_dev = cdns_ctrl->dmac->device; + struct dma_device *dma_dev; int ret; cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev, @@ -2915,6 +2915,7 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) } } + dma_dev = cdns_ctrl->dmac->device; cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma, cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0); diff --git a/drivers/mtd/nand/spi/fmsh.c b/drivers/mtd/nand/spi/fmsh.c index 8b2097bfc771..c2b9a8c113cb 100644 --- a/drivers/mtd/nand/spi/fmsh.c +++ b/drivers/mtd/nand/spi/fmsh.c @@ -58,7 +58,7 @@ static const struct spinand_info fmsh_spinand_table[] = { SPINAND_INFO_OP_VARIANTS(&read_cache_variants, &write_cache_variants, &update_cache_variants), - SPINAND_HAS_QE_BIT, + 0, SPINAND_ECCINFO(&fm25s01a_ooblayout, NULL)), }; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 49717b7b82a2..1a8de2bf8655 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -76,6 +76,7 @@ enum ad_link_speed_type { AD_LINK_SPEED_200000MBPS, AD_LINK_SPEED_400000MBPS, AD_LINK_SPEED_800000MBPS, + AD_LINK_SPEED_1600000MBPS, }; /* compare MAC addresses */ @@ -300,6 +301,7 @@ static inline int __check_agg_selection_timer(struct port *port) * %AD_LINK_SPEED_200000MBPS * %AD_LINK_SPEED_400000MBPS * %AD_LINK_SPEED_800000MBPS + * %AD_LINK_SPEED_1600000MBPS */ static u16 __get_link_speed(struct port *port) { @@ -379,6 +381,10 @@ static u16 __get_link_speed(struct port *port) speed = AD_LINK_SPEED_800000MBPS; break; + case SPEED_1600000: + speed = AD_LINK_SPEED_1600000MBPS; + break; + default: /* unknown speed value from ethtool. shouldn't happen */ if (slave->speed != SPEED_UNKNOWN) @@ -822,6 +828,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator) case AD_LINK_SPEED_800000MBPS: bandwidth = nports * 800000; break; + case AD_LINK_SPEED_1600000MBPS: + bandwidth = nports * 1600000; + break; default: bandwidth = 0; /* to silence the compiler */ } diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index d43d56694667..e15e320db476 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -124,6 +124,23 @@ config CAN_CAN327 If this driver is built as a module, it will be called can327. +config CAN_DUMMY + tristate "Dummy CAN" + help + A dummy CAN module supporting Classical CAN, CAN FD and CAN XL. It + exposes bittiming values which can be configured through the netlink + interface. + + The module will simply echo any frame sent to it. If debug messages + are activated, it prints all the CAN bittiming information in the + kernel log. Aside from that it does nothing. + + This is convenient for testing the CAN netlink interface. Most of the + users will never need this. If unsure, say NO. + + To compile this driver as a module, choose M here: the module will be + called dummy-can. + config CAN_FLEXCAN tristate "Support for Freescale FLEXCAN based chips" depends on OF || COLDFIRE || COMPILE_TEST diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index 56138d8ddfd2..d7bc10a6b8ea 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_CAN_CAN327) += can327.o obj-$(CONFIG_CAN_CC770) += cc770/ obj-$(CONFIG_CAN_C_CAN) += c_can/ obj-$(CONFIG_CAN_CTUCANFD) += ctucanfd/ +obj-$(CONFIG_CAN_DUMMY) += dummy_can.o obj-$(CONFIG_CAN_FLEXCAN) += flexcan/ obj-$(CONFIG_CAN_GRCAN) += grcan.o obj-$(CONFIG_CAN_IFI_CANFD) += ifi_canfd/ diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 0b93900b1dfa..8f82418230ce 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -2,6 +2,7 @@ /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> + * Copyright (c) 2025 Vincent Mailhol <mailhol@kernel.org> */ #include <linux/can/dev.h> @@ -151,3 +152,65 @@ int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, return -EINVAL; } + +int can_validate_pwm_bittiming(const struct net_device *dev, + const struct can_pwm *pwm, + struct netlink_ext_ack *extack) +{ + const struct can_priv *priv = netdev_priv(dev); + u32 xl_bit_time_tqmin = can_bit_time_tqmin(&priv->xl.data_bittiming); + u32 nom_bit_time_tqmin = can_bit_time_tqmin(&priv->bittiming); + u32 pwms_ns = can_tqmin_to_ns(pwm->pwms, priv->clock.freq); + u32 pwml_ns = can_tqmin_to_ns(pwm->pwml, priv->clock.freq); + + if (pwms_ns + pwml_ns > CAN_PWM_NS_MAX) { + NL_SET_ERR_MSG_FMT(extack, + "The PWM symbol duration: %u ns may not exceed %u ns", + pwms_ns + pwml_ns, CAN_PWM_NS_MAX); + return -EINVAL; + } + + if (pwms_ns < CAN_PWM_DECODE_NS) { + NL_SET_ERR_MSG_FMT(extack, + "PWMS: %u ns shall be at least %u ns", + pwms_ns, CAN_PWM_DECODE_NS); + return -EINVAL; + } + + if (pwm->pwms >= pwm->pwml) { + NL_SET_ERR_MSG_FMT(extack, + "PWMS: %u tqmin shall be smaller than PWML: %u tqmin", + pwm->pwms, pwm->pwml); + return -EINVAL; + } + + if (pwml_ns - pwms_ns < 2 * CAN_PWM_DECODE_NS) { + NL_SET_ERR_MSG_FMT(extack, + "At least %u ns shall separate PWMS: %u ns from PMWL: %u ns", + 2 * CAN_PWM_DECODE_NS, pwms_ns, pwml_ns); + return -EINVAL; + } + + if (xl_bit_time_tqmin % (pwm->pwms + pwm->pwml) != 0) { + NL_SET_ERR_MSG_FMT(extack, + "PWM duration: %u tqmin does not divide XL's bit time: %u tqmin", + pwm->pwms + pwm->pwml, xl_bit_time_tqmin); + return -EINVAL; + } + + if (pwm->pwmo >= pwm->pwms + pwm->pwml) { + NL_SET_ERR_MSG_FMT(extack, + "PWMO: %u tqmin can not be greater than PWMS + PWML: %u tqmin", + pwm->pwmo, pwm->pwms + pwm->pwml); + return -EINVAL; + } + + if (nom_bit_time_tqmin % (pwm->pwms + pwm->pwml) != pwm->pwmo) { + NL_SET_ERR_MSG_FMT(extack, + "Can not assemble nominal bit time: %u tqmin out of PWMS + PMWL and PWMO", + nom_bit_time_tqmin); + return -EINVAL; + } + + return 0; +} diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c index 394d6974f481..cc4022241553 100644 --- a/drivers/net/can/dev/calc_bittiming.c +++ b/drivers/net/can/dev/calc_bittiming.c @@ -2,6 +2,7 @@ /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> + * Copyright (C) 2021-2025 Vincent Mailhol <mailhol@kernel.org> */ #include <linux/units.h> @@ -9,6 +10,33 @@ #define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */ +/* CiA recommended sample points for Non Return to Zero encoding. */ +static int can_calc_sample_point_nrz(const struct can_bittiming *bt) +{ + if (bt->bitrate > 800 * KILO /* BPS */) + return 750; + + if (bt->bitrate > 500 * KILO /* BPS */) + return 800; + + return 875; +} + +/* Sample points for Pulse-Width Modulation encoding. */ +static int can_calc_sample_point_pwm(const struct can_bittiming *bt) +{ + if (bt->bitrate > 15 * MEGA /* BPS */) + return 625; + + if (bt->bitrate > 9 * MEGA /* BPS */) + return 600; + + if (bt->bitrate > 4 * MEGA /* BPS */) + return 560; + + return 520; +} + /* Bit-timing calculation derived from: * * Code based on LinCAN sources and H8S2638 project @@ -23,7 +51,7 @@ */ static int can_update_sample_point(const struct can_bittiming_const *btc, - const unsigned int sample_point_nominal, const unsigned int tseg, + const unsigned int sample_point_reference, const unsigned int tseg, unsigned int *tseg1_ptr, unsigned int *tseg2_ptr, unsigned int *sample_point_error_ptr) { @@ -34,7 +62,7 @@ can_update_sample_point(const struct can_bittiming_const *btc, for (i = 0; i <= 1; i++) { tseg2 = tseg + CAN_SYNC_SEG - - (sample_point_nominal * (tseg + CAN_SYNC_SEG)) / + (sample_point_reference * (tseg + CAN_SYNC_SEG)) / 1000 - i; tseg2 = clamp(tseg2, btc->tseg2_min, btc->tseg2_max); tseg1 = tseg - tseg2; @@ -45,9 +73,9 @@ can_update_sample_point(const struct can_bittiming_const *btc, sample_point = 1000 * (tseg + CAN_SYNC_SEG - tseg2) / (tseg + CAN_SYNC_SEG); - sample_point_error = abs(sample_point_nominal - sample_point); + sample_point_error = abs(sample_point_reference - sample_point); - if (sample_point <= sample_point_nominal && + if (sample_point <= sample_point_reference && sample_point_error < best_sample_point_error) { best_sample_point = sample_point; best_sample_point_error = sample_point_error; @@ -67,28 +95,24 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, { struct can_priv *priv = netdev_priv(dev); unsigned int bitrate; /* current bitrate */ - unsigned int bitrate_error; /* difference between current and nominal value */ + unsigned int bitrate_error; /* diff between calculated and reference value */ unsigned int best_bitrate_error = UINT_MAX; - unsigned int sample_point_error; /* difference between current and nominal value */ + unsigned int sample_point_error; /* diff between calculated and reference value */ unsigned int best_sample_point_error = UINT_MAX; - unsigned int sample_point_nominal; /* nominal sample point */ + unsigned int sample_point_reference; /* reference sample point */ unsigned int best_tseg = 0; /* current best value for tseg */ unsigned int best_brp = 0; /* current best value for brp */ unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0; u64 v64; int err; - /* Use CiA recommended sample points */ - if (bt->sample_point) { - sample_point_nominal = bt->sample_point; - } else { - if (bt->bitrate > 800 * KILO /* BPS */) - sample_point_nominal = 750; - else if (bt->bitrate > 500 * KILO /* BPS */) - sample_point_nominal = 800; - else - sample_point_nominal = 875; - } + if (bt->sample_point) + sample_point_reference = bt->sample_point; + else if (btc == priv->xl.data_bittiming_const && + (priv->ctrlmode & CAN_CTRLMODE_XL_TMS)) + sample_point_reference = can_calc_sample_point_pwm(bt); + else + sample_point_reference = can_calc_sample_point_nrz(bt); /* tseg even = round down, odd = round up */ for (tseg = (btc->tseg1_max + btc->tseg2_max) * 2 + 1; @@ -114,7 +138,7 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, if (bitrate_error < best_bitrate_error) best_sample_point_error = UINT_MAX; - can_update_sample_point(btc, sample_point_nominal, tseg / 2, + can_update_sample_point(btc, sample_point_reference, tseg / 2, &tseg1, &tseg2, &sample_point_error); if (sample_point_error >= best_sample_point_error) continue; @@ -129,23 +153,26 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, } if (best_bitrate_error) { - /* Error in one-tenth of a percent */ - v64 = (u64)best_bitrate_error * 1000; + /* Error in one-hundredth of a percent */ + v64 = (u64)best_bitrate_error * 10000; do_div(v64, bt->bitrate); bitrate_error = (u32)v64; + /* print at least 0.01% if the error is smaller */ + bitrate_error = max(bitrate_error, 1U); if (bitrate_error > CAN_CALC_MAX_ERROR) { NL_SET_ERR_MSG_FMT(extack, - "bitrate error: %u.%u%% too high", - bitrate_error / 10, bitrate_error % 10); + "bitrate error: %u.%02u%% too high", + bitrate_error / 100, + bitrate_error % 100); return -EINVAL; } NL_SET_ERR_MSG_FMT(extack, - "bitrate error: %u.%u%%", - bitrate_error / 10, bitrate_error % 10); + "bitrate error: %u.%02u%%", + bitrate_error / 100, bitrate_error % 100); } /* real sample point */ - bt->sample_point = can_update_sample_point(btc, sample_point_nominal, + bt->sample_point = can_update_sample_point(btc, sample_point_reference, best_tseg, &tseg1, &tseg2, NULL); @@ -198,3 +225,38 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, *ctrlmode |= tdc_auto; } } + +int can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack) +{ + struct can_priv *priv = netdev_priv(dev); + const struct can_pwm_const *pwm_const = priv->xl.pwm_const; + struct can_pwm *pwm = &priv->xl.pwm; + u32 xl_tqmin = can_bit_time_tqmin(&priv->xl.data_bittiming); + u32 xl_ns = can_tqmin_to_ns(xl_tqmin, priv->clock.freq); + u32 nom_tqmin = can_bit_time_tqmin(&priv->bittiming); + int pwm_per_bit_max = xl_tqmin / (pwm_const->pwms_min + pwm_const->pwml_min); + int pwm_per_bit; + u32 pwm_tqmin; + + /* For 5 MB/s databitrate or greater, xl_ns < CAN_PWM_NS_MAX + * giving us a pwm_per_bit of 1 and the loop immediately breaks + */ + for (pwm_per_bit = DIV_ROUND_UP(xl_ns, CAN_PWM_NS_MAX); + pwm_per_bit <= pwm_per_bit_max; pwm_per_bit++) + if (xl_tqmin % pwm_per_bit == 0) + break; + + if (pwm_per_bit > pwm_per_bit_max) { + NL_SET_ERR_MSG_FMT(extack, + "Can not divide the XL data phase's bit time: %u tqmin into multiple PWM symbols", + xl_tqmin); + return -EINVAL; + } + + pwm_tqmin = xl_tqmin / pwm_per_bit; + pwm->pwms = DIV_ROUND_UP_POW2(pwm_tqmin, 4); + pwm->pwml = pwm_tqmin - pwm->pwms; + pwm->pwmo = nom_tqmin % pwm_tqmin; + + return 0; +} diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 80e1ab18de87..091f30e94c61 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -92,29 +92,39 @@ const char *can_get_ctrlmode_str(u32 ctrlmode) { switch (ctrlmode & ~(ctrlmode - 1)) { case 0: - return "none"; + return "(none)"; case CAN_CTRLMODE_LOOPBACK: - return "loopback"; + return "LOOPBACK"; case CAN_CTRLMODE_LISTENONLY: - return "listen-only"; + return "LISTEN-ONLY"; case CAN_CTRLMODE_3_SAMPLES: - return "triple-sampling"; + return "TRIPLE-SAMPLING"; case CAN_CTRLMODE_ONE_SHOT: - return "one-shot"; + return "ONE-SHOT"; case CAN_CTRLMODE_BERR_REPORTING: - return "berr-reporting"; + return "BERR-REPORTING"; case CAN_CTRLMODE_FD: - return "fd"; + return "FD"; case CAN_CTRLMODE_PRESUME_ACK: - return "presume-ack"; + return "PRESUME-ACK"; case CAN_CTRLMODE_FD_NON_ISO: - return "fd-non-iso"; + return "FD-NON-ISO"; case CAN_CTRLMODE_CC_LEN8_DLC: - return "cc-len8-dlc"; + return "CC-LEN8-DLC"; case CAN_CTRLMODE_TDC_AUTO: - return "fd-tdc-auto"; + return "TDC-AUTO"; case CAN_CTRLMODE_TDC_MANUAL: - return "fd-tdc-manual"; + return "TDC-MANUAL"; + case CAN_CTRLMODE_RESTRICTED: + return "RESTRICTED"; + case CAN_CTRLMODE_XL: + return "XL"; + case CAN_CTRLMODE_XL_TDC_AUTO: + return "XL-TDC-AUTO"; + case CAN_CTRLMODE_XL_TDC_MANUAL: + return "XL-TDC-MANUAL"; + case CAN_CTRLMODE_XL_TMS: + return "TMS"; default: return "<unknown>"; } @@ -348,7 +358,13 @@ void can_set_default_mtu(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); - if (priv->ctrlmode & CAN_CTRLMODE_FD) { + if (priv->ctrlmode & CAN_CTRLMODE_XL) { + if (can_is_canxl_dev_mtu(dev->mtu)) + return; + dev->mtu = CANXL_MTU; + dev->min_mtu = CANXL_MIN_MTU; + dev->max_mtu = CANXL_MAX_MTU; + } else if (priv->ctrlmode & CAN_CTRLMODE_FD) { dev->mtu = CANFD_MTU; dev->min_mtu = CANFD_MTU; dev->max_mtu = CANFD_MTU; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 6f83b87d54fc..d6b0e686fb11 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -2,7 +2,7 @@ /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> - * Copyright (C) 2021 Vincent Mailhol <mailhol.vincent@wanadoo.fr> + * Copyright (C) 2021-2025 Vincent Mailhol <mailhol@kernel.org> */ #include <linux/can/dev.h> @@ -22,6 +22,10 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, [IFLA_CAN_TDC] = { .type = NLA_NESTED }, [IFLA_CAN_CTRLMODE_EXT] = { .type = NLA_NESTED }, + [IFLA_CAN_XL_DATA_BITTIMING] = { .len = sizeof(struct can_bittiming) }, + [IFLA_CAN_XL_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, + [IFLA_CAN_XL_TDC] = { .type = NLA_NESTED }, + [IFLA_CAN_XL_PWM] = { .type = NLA_NESTED }, }; static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { @@ -36,6 +40,18 @@ static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { [IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 }, }; +static const struct nla_policy can_pwm_policy[IFLA_CAN_PWM_MAX + 1] = { + [IFLA_CAN_PWM_PWMS_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWMS_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWML_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWML_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWMO_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWMO_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWMS] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWML] = { .type = NLA_U32 }, + [IFLA_CAN_PWM_PWMO] = { .type = NLA_U32 }, +}; + static int can_validate_bittiming(struct nlattr *data[], struct netlink_ext_ack *extack, int ifla_can_bittiming) @@ -70,7 +86,7 @@ static int can_validate_tdc(struct nlattr *data_tdc, return -EOPNOTSUPP; } - /* If one of the CAN_CTRLMODE_TDC_* flag is set then TDC + /* If one of the CAN_CTRLMODE_{,XL}_TDC_* flags is set then TDC * must be set and vice-versa */ if ((tdc_auto || tdc_manual) && !data_tdc) { @@ -82,8 +98,8 @@ static int can_validate_tdc(struct nlattr *data_tdc, return -EOPNOTSUPP; } - /* If providing TDC parameters, at least TDCO is needed. TDCV - * is needed if and only if CAN_CTRLMODE_TDC_MANUAL is set + /* If providing TDC parameters, at least TDCO is needed. TDCV is + * needed if and only if CAN_CTRLMODE_{,XL}_TDC_MANUAL is set */ if (data_tdc) { struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; @@ -116,6 +132,40 @@ static int can_validate_tdc(struct nlattr *data_tdc, return 0; } +static int can_validate_pwm(struct nlattr *data[], + struct netlink_ext_ack *extack, u32 flags) +{ + struct nlattr *tb_pwm[IFLA_CAN_PWM_MAX + 1]; + int err; + + if (!data[IFLA_CAN_XL_PWM]) + return 0; + + if (!(flags & CAN_CTRLMODE_XL_TMS)) { + NL_SET_ERR_MSG(extack, "PWM requires TMS"); + return -EOPNOTSUPP; + } + + err = nla_parse_nested(tb_pwm, IFLA_CAN_PWM_MAX, data[IFLA_CAN_XL_PWM], + can_pwm_policy, extack); + if (err) + return err; + + if (!tb_pwm[IFLA_CAN_PWM_PWMS] != !tb_pwm[IFLA_CAN_PWM_PWML]) { + NL_SET_ERR_MSG(extack, + "Provide either both PWMS and PWML, or none for automatic calculation"); + return -EOPNOTSUPP; + } + + if (tb_pwm[IFLA_CAN_PWM_PWMO] && + (!tb_pwm[IFLA_CAN_PWM_PWMS] || !tb_pwm[IFLA_CAN_PWM_PWML])) { + NL_SET_ERR_MSG(extack, "PWMO requires both PWMS and PWML"); + return -EOPNOTSUPP; + } + + return 0; +} + static int can_validate_databittiming(struct nlattr *data[], struct netlink_ext_ack *extack, int ifla_can_data_bittiming, u32 flags) @@ -126,10 +176,10 @@ static int can_validate_databittiming(struct nlattr *data[], bool is_on; int err; - /* Make sure that valid CAN FD configurations always consist of + /* Make sure that valid CAN FD/XL configurations always consist of * - nominal/arbitration bittiming * - data bittiming - * - control mode with CAN_CTRLMODE_FD set + * - control mode with CAN_CTRLMODE_{FD,XL} set * - TDC parameters are coherent (details in can_validate_tdc()) */ @@ -139,7 +189,10 @@ static int can_validate_databittiming(struct nlattr *data[], is_on = flags & CAN_CTRLMODE_FD; type = "FD"; } else { - return -EOPNOTSUPP; /* Place holder for CAN XL */ + data_tdc = data[IFLA_CAN_XL_TDC]; + tdc_flags = flags & CAN_CTRLMODE_XL_TDC_MASK; + is_on = flags & CAN_CTRLMODE_XL; + type = "XL"; } if (is_on) { @@ -175,6 +228,32 @@ static int can_validate_databittiming(struct nlattr *data[], return 0; } +static int can_validate_xl_flags(struct netlink_ext_ack *extack, + u32 masked_flags, u32 mask) +{ + if (masked_flags & CAN_CTRLMODE_XL) { + if (masked_flags & CAN_CTRLMODE_XL_TMS) { + const u32 tms_conflicts_mask = CAN_CTRLMODE_FD | + CAN_CTRLMODE_XL_TDC_MASK; + u32 tms_conflicts = masked_flags & tms_conflicts_mask; + + if (tms_conflicts) { + NL_SET_ERR_MSG_FMT(extack, + "TMS and %s are mutually exclusive", + can_get_ctrlmode_str(tms_conflicts)); + return -EOPNOTSUPP; + } + } + } else { + if (mask & CAN_CTRLMODE_XL_TMS) { + NL_SET_ERR_MSG(extack, "TMS requires CAN XL"); + return -EOPNOTSUPP; + } + } + + return 0; +} + static int can_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -188,6 +267,17 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); flags = cm->flags & cm->mask; + + if ((flags & CAN_CTRLMODE_LISTENONLY) && + (flags & CAN_CTRLMODE_RESTRICTED)) { + NL_SET_ERR_MSG(extack, + "LISTEN-ONLY and RESTRICTED modes are mutually exclusive"); + return -EOPNOTSUPP; + } + + err = can_validate_xl_flags(extack, flags, cm->mask); + if (err) + return err; } err = can_validate_bittiming(data, extack, IFLA_CAN_BITTIMING); @@ -199,6 +289,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], if (err) return err; + err = can_validate_databittiming(data, extack, + IFLA_CAN_XL_DATA_BITTIMING, flags); + if (err) + return err; + + err = can_validate_pwm(data, extack, flags); + if (err) + return err; + return 0; } @@ -208,7 +307,7 @@ static int can_ctrlmode_changelink(struct net_device *dev, { struct can_priv *priv = netdev_priv(dev); struct can_ctrlmode *cm; - u32 ctrlstatic, maskedflags, notsupp, ctrlstatic_missing; + u32 ctrlstatic, maskedflags, deactivated, notsupp, ctrlstatic_missing; if (!data[IFLA_CAN_CTRLMODE]) return 0; @@ -220,6 +319,7 @@ static int can_ctrlmode_changelink(struct net_device *dev, cm = nla_data(data[IFLA_CAN_CTRLMODE]); ctrlstatic = can_get_static_ctrlmode(priv); maskedflags = cm->flags & cm->mask; + deactivated = ~cm->flags & cm->mask; notsupp = maskedflags & ~(priv->ctrlmode_supported | ctrlstatic); ctrlstatic_missing = (maskedflags & ctrlstatic) ^ ctrlstatic; @@ -241,21 +341,40 @@ static int can_ctrlmode_changelink(struct net_device *dev, return -EOPNOTSUPP; } + /* If FD was active and is not turned off, check for XL conflicts */ + if (priv->ctrlmode & CAN_CTRLMODE_FD & ~deactivated) { + if (maskedflags & CAN_CTRLMODE_XL_TMS) { + NL_SET_ERR_MSG(extack, + "TMS can not be activated while CAN FD is on"); + return -EOPNOTSUPP; + } + } + /* If a top dependency flag is provided, reset all its dependencies */ if (cm->mask & CAN_CTRLMODE_FD) priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK; + if (cm->mask & CAN_CTRLMODE_XL) + priv->ctrlmode &= ~(CAN_CTRLMODE_XL_TDC_MASK | + CAN_CTRLMODE_XL_TMS); /* clear bits to be modified and copy the flag values */ priv->ctrlmode &= ~cm->mask; priv->ctrlmode |= maskedflags; - /* Wipe potential leftovers from previous CAN FD config */ + /* Wipe potential leftovers from previous CAN FD/XL config */ if (!(priv->ctrlmode & CAN_CTRLMODE_FD)) { memset(&priv->fd.data_bittiming, 0, sizeof(priv->fd.data_bittiming)); priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK; memset(&priv->fd.tdc, 0, sizeof(priv->fd.tdc)); } + if (!(priv->ctrlmode & CAN_CTRLMODE_XL)) { + memset(&priv->xl.data_bittiming, 0, + sizeof(priv->fd.data_bittiming)); + priv->ctrlmode &= ~CAN_CTRLMODE_XL_TDC_MASK; + memset(&priv->xl.tdc, 0, sizeof(priv->xl.tdc)); + memset(&priv->xl.pwm, 0, sizeof(priv->xl.pwm)); + } can_set_default_mtu(dev); @@ -330,7 +449,10 @@ static int can_dbt_changelink(struct net_device *dev, struct nlattr *data[], dbt_params = &priv->fd; tdc_mask = CAN_CTRLMODE_FD_TDC_MASK; } else { - return -EOPNOTSUPP; /* Place holder for CAN XL */ + data_bittiming = data[IFLA_CAN_XL_DATA_BITTIMING]; + data_tdc = data[IFLA_CAN_XL_TDC]; + dbt_params = &priv->xl; + tdc_mask = CAN_CTRLMODE_XL_TDC_MASK; } if (!data_bittiming) @@ -366,7 +488,8 @@ static int can_dbt_changelink(struct net_device *dev, struct nlattr *data[], if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); - need_tdc_calc = !(cm->mask & tdc_mask); + if (fd || !(priv->ctrlmode & CAN_CTRLMODE_XL_TMS)) + need_tdc_calc = !(cm->mask & tdc_mask); } if (data_tdc) { /* TDC parameters are provided: use them */ @@ -381,7 +504,7 @@ static int can_dbt_changelink(struct net_device *dev, struct nlattr *data[], */ can_calc_tdco(&dbt_params->tdc, dbt_params->tdc_const, &dbt, tdc_mask, &priv->ctrlmode, priv->ctrlmode_supported); - } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly + } /* else: both CAN_CTRLMODE_{,XL}_TDC_{AUTO,MANUAL} are explicitly * turned off. TDC is disabled: do nothing */ @@ -397,6 +520,76 @@ static int can_dbt_changelink(struct net_device *dev, struct nlattr *data[], return 0; } +static int can_pwm_changelink(struct net_device *dev, + const struct nlattr *pwm_nla, + struct netlink_ext_ack *extack) +{ + struct can_priv *priv = netdev_priv(dev); + const struct can_pwm_const *pwm_const = priv->xl.pwm_const; + struct nlattr *tb_pwm[IFLA_CAN_PWM_MAX + 1]; + struct can_pwm pwm = { 0 }; + int err; + + if (!(priv->ctrlmode & CAN_CTRLMODE_XL_TMS)) + return 0; + + if (!pwm_const) { + NL_SET_ERR_MSG(extack, "The device does not support PWM"); + return -EOPNOTSUPP; + } + + if (!pwm_nla) + return can_calc_pwm(dev, extack); + + err = nla_parse_nested(tb_pwm, IFLA_CAN_PWM_MAX, pwm_nla, + can_pwm_policy, extack); + if (err) + return err; + + if (tb_pwm[IFLA_CAN_PWM_PWMS]) { + pwm.pwms = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWMS]); + if (pwm.pwms < pwm_const->pwms_min || + pwm.pwms > pwm_const->pwms_max) { + NL_SET_ERR_MSG_FMT(extack, + "PWMS: %u tqmin is out of range: %u...%u", + pwm.pwms, pwm_const->pwms_min, + pwm_const->pwms_max); + return -EINVAL; + } + } + + if (tb_pwm[IFLA_CAN_PWM_PWML]) { + pwm.pwml = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWML]); + if (pwm.pwml < pwm_const->pwml_min || + pwm.pwml > pwm_const->pwml_max) { + NL_SET_ERR_MSG_FMT(extack, + "PWML: %u tqmin is out of range: %u...%u", + pwm.pwml, pwm_const->pwml_min, + pwm_const->pwml_max); + return -EINVAL; + } + } + + if (tb_pwm[IFLA_CAN_PWM_PWMO]) { + pwm.pwmo = nla_get_u32(tb_pwm[IFLA_CAN_PWM_PWMO]); + if (pwm.pwmo < pwm_const->pwmo_min || + pwm.pwmo > pwm_const->pwmo_max) { + NL_SET_ERR_MSG_FMT(extack, + "PWMO: %u tqmin is out of range: %u...%u", + pwm.pwmo, pwm_const->pwmo_min, + pwm_const->pwmo_max); + return -EINVAL; + } + } + + err = can_validate_pwm_bittiming(dev, &pwm, extack); + if (err) + return err; + + priv->xl.pwm = pwm; + return 0; +} + static int can_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -486,6 +679,14 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], if (err) return err; + /* CAN XL */ + err = can_dbt_changelink(dev, data, false, extack); + if (err) + return err; + err = can_pwm_changelink(dev, data[IFLA_CAN_XL_PWM], extack); + if (err) + return err; + if (data[IFLA_CAN_TERMINATION]) { const u16 termval = nla_get_u16(data[IFLA_CAN_TERMINATION]); const unsigned int num_term = priv->termination_const_cnt; @@ -553,14 +754,14 @@ static size_t can_data_bittiming_get_size(struct data_bittiming_params *dbt_para { size_t size = 0; - if (dbt_params->data_bittiming.bitrate) /* IFLA_CAN_DATA_BITTIMING */ + if (dbt_params->data_bittiming.bitrate) /* IFLA_CAN_{,XL}_DATA_BITTIMING */ size += nla_total_size(sizeof(dbt_params->data_bittiming)); - if (dbt_params->data_bittiming_const) /* IFLA_CAN_DATA_BITTIMING_CONST */ + if (dbt_params->data_bittiming_const) /* IFLA_CAN_{,XL}_DATA_BITTIMING_CONST */ size += nla_total_size(sizeof(*dbt_params->data_bittiming_const)); - if (dbt_params->data_bitrate_const) /* IFLA_CAN_DATA_BITRATE_CONST */ + if (dbt_params->data_bitrate_const) /* IFLA_CAN_{,XL}_DATA_BITRATE_CONST */ size += nla_total_size(sizeof(*dbt_params->data_bitrate_const) * dbt_params->data_bitrate_const_cnt); - size += can_tdc_get_size(dbt_params, tdc_flags);/* IFLA_CAN_TDC */ + size += can_tdc_get_size(dbt_params, tdc_flags);/* IFLA_CAN_{,XL}_TDC */ return size; } @@ -571,6 +772,30 @@ static size_t can_ctrlmode_ext_get_size(void) nla_total_size(sizeof(u32)); /* IFLA_CAN_CTRLMODE_SUPPORTED */ } +static size_t can_pwm_get_size(const struct can_pwm_const *pwm_const, + bool pwm_on) +{ + size_t size; + + if (!pwm_const || !pwm_on) + return 0; + + size = nla_total_size(0); /* nest IFLA_CAN_PWM */ + + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMS_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMS_MAX */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWML_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWML_MAX */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMO_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMO_MAX */ + + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMS */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWML */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_PWM_PWMO */ + + return size; +} + static size_t can_get_size(const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -600,6 +825,11 @@ static size_t can_get_size(const struct net_device *dev) size += can_data_bittiming_get_size(&priv->fd, priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK); + size += can_data_bittiming_get_size(&priv->xl, + priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MASK); + size += can_pwm_get_size(priv->xl.pwm_const, /* IFLA_CAN_XL_PWM */ + priv->ctrlmode & CAN_CTRLMODE_XL_TMS); + return size; } @@ -644,7 +874,9 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev, tdc_is_enabled = can_fd_tdc_is_enabled(priv); tdc_manual = priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL; } else { - return -EOPNOTSUPP; /* Place holder for CAN XL */ + dbt_params = &priv->xl; + tdc_is_enabled = can_xl_tdc_is_enabled(priv); + tdc_manual = priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MANUAL; } tdc_const = dbt_params->tdc_const; tdc = &dbt_params->tdc; @@ -695,6 +927,42 @@ err_cancel: return -EMSGSIZE; } +static int can_pwm_fill_info(struct sk_buff *skb, const struct can_priv *priv) +{ + const struct can_pwm_const *pwm_const = priv->xl.pwm_const; + const struct can_pwm *pwm = &priv->xl.pwm; + struct nlattr *nest; + + if (!pwm_const) + return 0; + + nest = nla_nest_start(skb, IFLA_CAN_XL_PWM); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, IFLA_CAN_PWM_PWMS_MIN, pwm_const->pwms_min) || + nla_put_u32(skb, IFLA_CAN_PWM_PWMS_MAX, pwm_const->pwms_max) || + nla_put_u32(skb, IFLA_CAN_PWM_PWML_MIN, pwm_const->pwml_min) || + nla_put_u32(skb, IFLA_CAN_PWM_PWML_MAX, pwm_const->pwml_max) || + nla_put_u32(skb, IFLA_CAN_PWM_PWMO_MIN, pwm_const->pwmo_min) || + nla_put_u32(skb, IFLA_CAN_PWM_PWMO_MAX, pwm_const->pwmo_max)) + goto err_cancel; + + if (priv->ctrlmode & CAN_CTRLMODE_XL_TMS) { + if (nla_put_u32(skb, IFLA_CAN_PWM_PWMS, pwm->pwms) || + nla_put_u32(skb, IFLA_CAN_PWM_PWML, pwm->pwml) || + nla_put_u32(skb, IFLA_CAN_PWM_PWMO, pwm->pwmo)) + goto err_cancel; + } + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int can_ctrlmode_ext_fill_info(struct sk_buff *skb, const struct can_priv *priv) { @@ -766,9 +1034,22 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) can_tdc_fill_info(skb, dev, IFLA_CAN_TDC) || - can_ctrlmode_ext_fill_info(skb, priv) - ) + can_ctrlmode_ext_fill_info(skb, priv) || + + can_bittiming_fill_info(skb, IFLA_CAN_XL_DATA_BITTIMING, + &priv->xl.data_bittiming) || + can_bittiming_const_fill_info(skb, IFLA_CAN_XL_DATA_BITTIMING_CONST, + priv->xl.data_bittiming_const) || + + can_bitrate_const_fill_info(skb, IFLA_CAN_XL_DATA_BITRATE_CONST, + priv->xl.data_bitrate_const, + priv->xl.data_bitrate_const_cnt) || + + can_tdc_fill_info(skb, dev, IFLA_CAN_XL_TDC) || + + can_pwm_fill_info(skb, priv) + ) return -EMSGSIZE; return 0; diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c new file mode 100644 index 000000000000..41953655e3d3 --- /dev/null +++ b/drivers/net/can/dummy_can.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (c) 2025 Vincent Mailhol <mailhol@kernel.org> */ + +#include <linux/array_size.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/units.h> +#include <linux/string_choices.h> + +#include <linux/can.h> +#include <linux/can/bittiming.h> +#include <linux/can/dev.h> +#include <linux/can/skb.h> + +struct dummy_can { + struct can_priv can; + struct net_device *dev; +}; + +static struct dummy_can *dummy_can; + +static const struct can_bittiming_const dummy_can_bittiming_const = { + .name = "dummy_can CC", + .tseg1_min = 2, + .tseg1_max = 256, + .tseg2_min = 2, + .tseg2_max = 128, + .sjw_max = 128, + .brp_min = 1, + .brp_max = 512, + .brp_inc = 1 +}; + +static const struct can_bittiming_const dummy_can_fd_databittiming_const = { + .name = "dummy_can FD", + .tseg1_min = 2, + .tseg1_max = 256, + .tseg2_min = 2, + .tseg2_max = 128, + .sjw_max = 128, + .brp_min = 1, + .brp_max = 512, + .brp_inc = 1 +}; + +static const struct can_tdc_const dummy_can_fd_tdc_const = { + .tdcv_min = 0, + .tdcv_max = 0, /* Manual mode not supported. */ + .tdco_min = 0, + .tdco_max = 127, + .tdcf_min = 0, + .tdcf_max = 127 +}; + +static const struct can_bittiming_const dummy_can_xl_databittiming_const = { + .name = "dummy_can XL", + .tseg1_min = 2, + .tseg1_max = 256, + .tseg2_min = 2, + .tseg2_max = 128, + .sjw_max = 128, + .brp_min = 1, + .brp_max = 512, + .brp_inc = 1 +}; + +static const struct can_tdc_const dummy_can_xl_tdc_const = { + .tdcv_min = 0, + .tdcv_max = 0, /* Manual mode not supported. */ + .tdco_min = 0, + .tdco_max = 127, + .tdcf_min = 0, + .tdcf_max = 127 +}; + +static const struct can_pwm_const dummy_can_pwm_const = { + .pwms_min = 1, + .pwms_max = 8, + .pwml_min = 2, + .pwml_max = 24, + .pwmo_min = 0, + .pwmo_max = 16, +}; + +static void dummy_can_print_bittiming(struct net_device *dev, + struct can_bittiming *bt) +{ + netdev_dbg(dev, "\tbitrate: %u\n", bt->bitrate); + netdev_dbg(dev, "\tsample_point: %u\n", bt->sample_point); + netdev_dbg(dev, "\ttq: %u\n", bt->tq); + netdev_dbg(dev, "\tprop_seg: %u\n", bt->prop_seg); + netdev_dbg(dev, "\tphase_seg1: %u\n", bt->phase_seg1); + netdev_dbg(dev, "\tphase_seg2: %u\n", bt->phase_seg2); + netdev_dbg(dev, "\tsjw: %u\n", bt->sjw); + netdev_dbg(dev, "\tbrp: %u\n", bt->brp); +} + +static void dummy_can_print_tdc(struct net_device *dev, struct can_tdc *tdc) +{ + netdev_dbg(dev, "\t\ttdcv: %u\n", tdc->tdcv); + netdev_dbg(dev, "\t\ttdco: %u\n", tdc->tdco); + netdev_dbg(dev, "\t\ttdcf: %u\n", tdc->tdcf); +} + +static void dummy_can_print_pwm(struct net_device *dev, struct can_pwm *pwm, + struct can_bittiming *dbt) +{ + netdev_dbg(dev, "\t\tpwms: %u\n", pwm->pwms); + netdev_dbg(dev, "\t\tpwml: %u\n", pwm->pwml); + netdev_dbg(dev, "\t\tpwmo: %u\n", pwm->pwmo); +} + +static void dummy_can_print_ctrlmode(struct net_device *dev) +{ + struct dummy_can *priv = netdev_priv(dev); + struct can_priv *can_priv = &priv->can; + unsigned long supported = can_priv->ctrlmode_supported; + u32 enabled = can_priv->ctrlmode; + + netdev_dbg(dev, "Control modes:\n"); + netdev_dbg(dev, "\tsupported: 0x%08x\n", (u32)supported); + netdev_dbg(dev, "\tenabled: 0x%08x\n", enabled); + + if (supported) { + int idx; + + netdev_dbg(dev, "\tlist:"); + for_each_set_bit(idx, &supported, BITS_PER_TYPE(u32)) + netdev_dbg(dev, "\t\t%s: %s\n", + can_get_ctrlmode_str(BIT(idx)), + enabled & BIT(idx) ? "on" : "off"); + } +} + +static void dummy_can_print_bittiming_info(struct net_device *dev) +{ + struct dummy_can *priv = netdev_priv(dev); + struct can_priv *can_priv = &priv->can; + + netdev_dbg(dev, "Clock frequency: %u\n", can_priv->clock.freq); + netdev_dbg(dev, "Maximum bitrate: %u\n", can_priv->bitrate_max); + netdev_dbg(dev, "MTU: %u\n", dev->mtu); + netdev_dbg(dev, "\n"); + + dummy_can_print_ctrlmode(dev); + netdev_dbg(dev, "\n"); + + netdev_dbg(dev, "Classical CAN nominal bittiming:\n"); + dummy_can_print_bittiming(dev, &can_priv->bittiming); + netdev_dbg(dev, "\n"); + + if (can_priv->ctrlmode & CAN_CTRLMODE_FD) { + netdev_dbg(dev, "CAN FD databittiming:\n"); + dummy_can_print_bittiming(dev, &can_priv->fd.data_bittiming); + if (can_fd_tdc_is_enabled(can_priv)) { + netdev_dbg(dev, "\tCAN FD TDC:\n"); + dummy_can_print_tdc(dev, &can_priv->fd.tdc); + } + } + netdev_dbg(dev, "\n"); + + if (can_priv->ctrlmode & CAN_CTRLMODE_XL) { + netdev_dbg(dev, "CAN XL databittiming:\n"); + dummy_can_print_bittiming(dev, &can_priv->xl.data_bittiming); + if (can_xl_tdc_is_enabled(can_priv)) { + netdev_dbg(dev, "\tCAN XL TDC:\n"); + dummy_can_print_tdc(dev, &can_priv->xl.tdc); + } + if (can_priv->ctrlmode & CAN_CTRLMODE_XL_TMS) { + netdev_dbg(dev, "\tCAN XL PWM:\n"); + dummy_can_print_pwm(dev, &can_priv->xl.pwm, + &can_priv->xl.data_bittiming); + } + } + netdev_dbg(dev, "\n"); +} + +static int dummy_can_netdev_open(struct net_device *dev) +{ + int ret; + struct can_priv *priv = netdev_priv(dev); + + dummy_can_print_bittiming_info(dev); + netdev_dbg(dev, "error-signalling is %s\n", + str_enabled_disabled(!can_dev_in_xl_only_mode(priv))); + + ret = open_candev(dev); + if (ret) + return ret; + netif_start_queue(dev); + netdev_dbg(dev, "dummy-can is up\n"); + + return 0; +} + +static int dummy_can_netdev_close(struct net_device *dev) +{ + netif_stop_queue(dev); + close_candev(dev); + netdev_dbg(dev, "dummy-can is down\n"); + + return 0; +} + +static netdev_tx_t dummy_can_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + if (can_dev_dropped_skb(dev, skb)) + return NETDEV_TX_OK; + + can_put_echo_skb(skb, dev, 0, 0); + dev->stats.tx_packets++; + dev->stats.tx_bytes += can_get_echo_skb(dev, 0, NULL); + + return NETDEV_TX_OK; +} + +static const struct net_device_ops dummy_can_netdev_ops = { + .ndo_open = dummy_can_netdev_open, + .ndo_stop = dummy_can_netdev_close, + .ndo_start_xmit = dummy_can_start_xmit, +}; + +static const struct ethtool_ops dummy_can_ethtool_ops = { + .get_ts_info = ethtool_op_get_ts_info, +}; + +static int __init dummy_can_init(void) +{ + struct net_device *dev; + struct dummy_can *priv; + int ret; + + dev = alloc_candev(sizeof(*priv), 1); + if (!dev) + return -ENOMEM; + + dev->netdev_ops = &dummy_can_netdev_ops; + dev->ethtool_ops = &dummy_can_ethtool_ops; + priv = netdev_priv(dev); + priv->can.bittiming_const = &dummy_can_bittiming_const; + priv->can.bitrate_max = 20 * MEGA /* BPS */; + priv->can.clock.freq = 160 * MEGA /* Hz */; + priv->can.fd.data_bittiming_const = &dummy_can_fd_databittiming_const; + priv->can.fd.tdc_const = &dummy_can_fd_tdc_const; + priv->can.xl.data_bittiming_const = &dummy_can_xl_databittiming_const; + priv->can.xl.tdc_const = &dummy_can_xl_tdc_const; + priv->can.xl.pwm_const = &dummy_can_pwm_const; + priv->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_FD | CAN_CTRLMODE_TDC_AUTO | + CAN_CTRLMODE_RESTRICTED | CAN_CTRLMODE_XL | + CAN_CTRLMODE_XL_TDC_AUTO | CAN_CTRLMODE_XL_TMS; + priv->dev = dev; + + ret = register_candev(priv->dev); + if (ret) { + free_candev(priv->dev); + return ret; + } + + dummy_can = priv; + netdev_dbg(dev, "dummy-can ready\n"); + + return 0; +} + +static void __exit dummy_can_exit(void) +{ + struct net_device *dev = dummy_can->dev; + + netdev_dbg(dev, "dummy-can bye bye\n"); + unregister_candev(dev); + free_candev(dev); +} + +module_init(dummy_can_init); +module_exit(dummy_can_exit); + +MODULE_DESCRIPTION("A dummy CAN driver, mainly to test the netlink interface"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Vincent Mailhol <mailhol@kernel.org>"); diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 49ab65274b51..7895e1fdea1c 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -468,6 +468,7 @@ struct rcar_canfd_global { struct platform_device *pdev; /* Respective platform device */ struct clk *clkp; /* Peripheral clock */ struct clk *can_clk; /* fCAN clock */ + struct clk *clk_ram; /* Clock RAM */ unsigned long channels_mask; /* Enabled channels mask */ bool extclk; /* CANFD or Ext clock */ bool fdmode; /* CAN FD or Classical CAN only mode */ @@ -709,6 +710,11 @@ static void rcar_canfd_set_bit_reg(void __iomem *addr, u32 val) rcar_canfd_update(val, val, addr); } +static void rcar_canfd_clear_bit_reg(void __iomem *addr, u32 val) +{ + rcar_canfd_update(val, 0, addr); +} + static void rcar_canfd_update_bit_reg(void __iomem *addr, u32 mask, u32 val) { rcar_canfd_update(mask, val, addr); @@ -755,25 +761,6 @@ static void rcar_canfd_set_rnc(struct rcar_canfd_global *gpriv, unsigned int ch, rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(w), rnc); } -static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv) -{ - if (gpriv->info->ch_interface_mode) { - u32 ch, val = gpriv->fdmode ? RCANFD_GEN4_FDCFG_FDOE - : RCANFD_GEN4_FDCFG_CLOE; - - for_each_set_bit(ch, &gpriv->channels_mask, - gpriv->info->max_channels) - rcar_canfd_set_bit_reg(&gpriv->fcbase[ch].cfdcfg, val); - } else { - if (gpriv->fdmode) - rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, - RCANFD_GRMCFG_RCMC); - else - rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG, - RCANFD_GRMCFG_RCMC); - } -} - static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv) { struct device *dev = &gpriv->pdev->dev; @@ -806,6 +793,16 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv) /* Reset Global error flags */ rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0x0); + /* Set the controller into appropriate mode */ + if (!gpriv->info->ch_interface_mode) { + if (gpriv->fdmode) + rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, + RCANFD_GRMCFG_RCMC); + else + rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG, + RCANFD_GRMCFG_RCMC); + } + /* Transition all Channels to reset mode */ for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) { rcar_canfd_clear_bit(gpriv->base, @@ -823,10 +820,23 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv) dev_dbg(dev, "channel %u reset failed\n", ch); return err; } - } - /* Set the controller into appropriate mode */ - rcar_canfd_set_mode(gpriv); + /* Set the controller into appropriate mode */ + if (gpriv->info->ch_interface_mode) { + /* Do not set CLOE and FDOE simultaneously */ + if (!gpriv->fdmode) { + rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg, + RCANFD_GEN4_FDCFG_FDOE); + rcar_canfd_set_bit_reg(&gpriv->fcbase[ch].cfdcfg, + RCANFD_GEN4_FDCFG_CLOE); + } else { + rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg, + RCANFD_GEN4_FDCFG_FDOE); + rcar_canfd_clear_bit_reg(&gpriv->fcbase[ch].cfdcfg, + RCANFD_GEN4_FDCFG_CLOE); + } + } + } return 0; } @@ -1569,8 +1579,8 @@ static int rcar_canfd_close(struct net_device *ndev) netif_stop_queue(ndev); rcar_canfd_stop(ndev); napi_disable(&priv->napi); - clk_disable_unprepare(gpriv->can_clk); close_candev(ndev); + clk_disable_unprepare(gpriv->can_clk); phy_power_off(priv->transceiver); return 0; } @@ -1960,22 +1970,120 @@ static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch) } } +static int rcar_canfd_global_init(struct rcar_canfd_global *gpriv) +{ + struct device *dev = &gpriv->pdev->dev; + u32 rule_entry = 0; + u32 ch, sts; + int err; + + err = reset_control_reset(gpriv->rstc1); + if (err) + return err; + + err = reset_control_reset(gpriv->rstc2); + if (err) + goto fail_reset1; + + /* Enable peripheral clock for register access */ + err = clk_prepare_enable(gpriv->clkp); + if (err) { + dev_err(dev, "failed to enable peripheral clock: %pe\n", + ERR_PTR(err)); + goto fail_reset2; + } + + /* Enable RAM clock */ + err = clk_prepare_enable(gpriv->clk_ram); + if (err) { + dev_err(dev, + "failed to enable RAM clock, error %d\n", err); + goto fail_clk; + } + + err = rcar_canfd_reset_controller(gpriv); + if (err) { + dev_err(dev, "reset controller failed: %pe\n", ERR_PTR(err)); + goto fail_ram_clk; + } + + /* Controller in Global reset & Channel reset mode */ + rcar_canfd_configure_controller(gpriv); + + /* Configure per channel attributes */ + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) { + /* Configure Channel's Rx fifo */ + rcar_canfd_configure_rx(gpriv, ch); + + /* Configure Channel's Tx (Common) fifo */ + rcar_canfd_configure_tx(gpriv, ch); + + /* Configure receive rules */ + rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry); + rule_entry += RCANFD_CHANNEL_NUMRULES; + } + + /* Configure common interrupts */ + rcar_canfd_enable_global_interrupts(gpriv); + + /* Start Global operation mode */ + rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK, + RCANFD_GCTR_GMDC_GOPM); + + /* Verify mode change */ + err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts, + !(sts & RCANFD_GSTS_GNOPM), 2, 500000); + if (err) { + dev_err(dev, "global operational mode failed\n"); + goto fail_mode; + } + + return 0; + +fail_mode: + rcar_canfd_disable_global_interrupts(gpriv); +fail_ram_clk: + clk_disable_unprepare(gpriv->clk_ram); +fail_clk: + clk_disable_unprepare(gpriv->clkp); +fail_reset2: + reset_control_assert(gpriv->rstc2); +fail_reset1: + reset_control_assert(gpriv->rstc1); + return err; +} + +static void rcar_canfd_global_deinit(struct rcar_canfd_global *gpriv, bool full) +{ + rcar_canfd_disable_global_interrupts(gpriv); + + if (full) { + rcar_canfd_reset_controller(gpriv); + + /* Enter global sleep mode */ + rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR); + } + + clk_disable_unprepare(gpriv->clk_ram); + clk_disable_unprepare(gpriv->clkp); + reset_control_assert(gpriv->rstc2); + reset_control_assert(gpriv->rstc1); +} + static int rcar_canfd_probe(struct platform_device *pdev) { struct phy *transceivers[RCANFD_NUM_CHANNELS] = { NULL, }; const struct rcar_canfd_hw_info *info; struct device *dev = &pdev->dev; void __iomem *addr; - u32 sts, ch, fcan_freq; struct rcar_canfd_global *gpriv; struct device_node *of_child; unsigned long channels_mask = 0; int err, ch_irq, g_irq; int g_err_irq, g_recc_irq; - u32 rule_entry = 0; bool fdmode = true; /* CAN FD only mode - default */ char name[9] = "channelX"; - struct clk *clk_ram; + u32 ch, fcan_freq; int i; info = of_device_get_match_data(dev); @@ -2065,10 +2173,10 @@ static int rcar_canfd_probe(struct platform_device *pdev) gpriv->extclk = gpriv->info->external_clk; } - clk_ram = devm_clk_get_optional_enabled(dev, "ram_clk"); - if (IS_ERR(clk_ram)) - return dev_err_probe(dev, PTR_ERR(clk_ram), - "cannot get enabled ram clock\n"); + gpriv->clk_ram = devm_clk_get_optional(dev, "ram_clk"); + if (IS_ERR(gpriv->clk_ram)) + return dev_err_probe(dev, PTR_ERR(gpriv->clk_ram), + "cannot get ram clock\n"); addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(addr)) { @@ -2117,59 +2225,9 @@ static int rcar_canfd_probe(struct platform_device *pdev) } } - err = reset_control_reset(gpriv->rstc1); + err = rcar_canfd_global_init(gpriv); if (err) - goto fail_dev; - err = reset_control_reset(gpriv->rstc2); - if (err) { - reset_control_assert(gpriv->rstc1); - goto fail_dev; - } - - /* Enable peripheral clock for register access */ - err = clk_prepare_enable(gpriv->clkp); - if (err) { - dev_err(dev, "failed to enable peripheral clock: %pe\n", - ERR_PTR(err)); - goto fail_reset; - } - - err = rcar_canfd_reset_controller(gpriv); - if (err) { - dev_err(dev, "reset controller failed: %pe\n", ERR_PTR(err)); - goto fail_clk; - } - - /* Controller in Global reset & Channel reset mode */ - rcar_canfd_configure_controller(gpriv); - - /* Configure per channel attributes */ - for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels) { - /* Configure Channel's Rx fifo */ - rcar_canfd_configure_rx(gpriv, ch); - - /* Configure Channel's Tx (Common) fifo */ - rcar_canfd_configure_tx(gpriv, ch); - - /* Configure receive rules */ - rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry); - rule_entry += RCANFD_CHANNEL_NUMRULES; - } - - /* Configure common interrupts */ - rcar_canfd_enable_global_interrupts(gpriv); - - /* Start Global operation mode */ - rcar_canfd_update_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GMDC_MASK, - RCANFD_GCTR_GMDC_GOPM); - - /* Verify mode change */ - err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts, - !(sts & RCANFD_GSTS_GNOPM), 2, 500000); - if (err) { - dev_err(dev, "global operational mode failed\n"); goto fail_mode; - } for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels) { err = rcar_canfd_channel_probe(gpriv, ch, fcan_freq, @@ -2188,12 +2246,7 @@ fail_channel: for_each_set_bit(ch, &gpriv->channels_mask, info->max_channels) rcar_canfd_channel_remove(gpriv, ch); fail_mode: - rcar_canfd_disable_global_interrupts(gpriv); -fail_clk: - clk_disable_unprepare(gpriv->clkp); -fail_reset: - reset_control_assert(gpriv->rstc1); - reset_control_assert(gpriv->rstc2); + rcar_canfd_global_deinit(gpriv, false); fail_dev: return err; } @@ -2203,33 +2256,79 @@ static void rcar_canfd_remove(struct platform_device *pdev) struct rcar_canfd_global *gpriv = platform_get_drvdata(pdev); u32 ch; - rcar_canfd_reset_controller(gpriv); - rcar_canfd_disable_global_interrupts(gpriv); - for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) { rcar_canfd_disable_channel_interrupts(gpriv->ch[ch]); rcar_canfd_channel_remove(gpriv, ch); } - /* Enter global sleep mode */ - rcar_canfd_set_bit(gpriv->base, RCANFD_GCTR, RCANFD_GCTR_GSLPR); - clk_disable_unprepare(gpriv->clkp); - reset_control_assert(gpriv->rstc1); - reset_control_assert(gpriv->rstc2); + rcar_canfd_global_deinit(gpriv, true); } -static int __maybe_unused rcar_canfd_suspend(struct device *dev) +static int rcar_canfd_suspend(struct device *dev) { + struct rcar_canfd_global *gpriv = dev_get_drvdata(dev); + int err; + u32 ch; + + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) { + struct rcar_canfd_channel *priv = gpriv->ch[ch]; + struct net_device *ndev = priv->ndev; + + if (!netif_running(ndev)) + continue; + + netif_device_detach(ndev); + + err = rcar_canfd_close(ndev); + if (err) { + netdev_err(ndev, "rcar_canfd_close() failed %pe\n", + ERR_PTR(err)); + return err; + } + + priv->can.state = CAN_STATE_SLEEPING; + } + + /* TODO Skip if wake-up (which is not yet supported) is enabled */ + rcar_canfd_global_deinit(gpriv, false); + return 0; } -static int __maybe_unused rcar_canfd_resume(struct device *dev) +static int rcar_canfd_resume(struct device *dev) { + struct rcar_canfd_global *gpriv = dev_get_drvdata(dev); + int err; + u32 ch; + + err = rcar_canfd_global_init(gpriv); + if (err) { + dev_err(dev, "rcar_canfd_global_init() failed %pe\n", ERR_PTR(err)); + return err; + } + + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->info->max_channels) { + struct rcar_canfd_channel *priv = gpriv->ch[ch]; + struct net_device *ndev = priv->ndev; + + if (!netif_running(ndev)) + continue; + + err = rcar_canfd_open(ndev); + if (err) { + netdev_err(ndev, "rcar_canfd_open() failed %pe\n", + ERR_PTR(err)); + return err; + } + + netif_device_attach(ndev); + } + return 0; } -static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend, - rcar_canfd_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend, + rcar_canfd_resume); static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = { { .compatible = "renesas,r8a779a0-canfd", .data = &rcar_gen4_hw_info }, @@ -2246,7 +2345,7 @@ static struct platform_driver rcar_canfd_driver = { .driver = { .name = RCANFD_DRV_NAME, .of_match_table = of_match_ptr(rcar_canfd_of_table), - .pm = &rcar_canfd_pm_ops, + .pm = pm_sleep_ptr(&rcar_canfd_pm_ops), }, .probe = rcar_canfd_probe, .remove = rcar_canfd_remove, diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index acfa49db3907..a8fa0d6516b9 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -548,8 +548,8 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id) if (priv->read_reg(priv, SJA1000_IER) == IRQ_OFF) goto out; - while ((isrc = priv->read_reg(priv, SJA1000_IR)) && - (n < SJA1000_MAX_IRQ)) { + while ((n < SJA1000_MAX_IRQ) && + (isrc = priv->read_reg(priv, SJA1000_IR))) { status = priv->read_reg(priv, SJA1000_SR); /* check for absent controller due to hw unplug */ diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 6fcb301ef611..af52285d5a4e 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -657,8 +657,8 @@ static irqreturn_t sun4i_can_interrupt(int irq, void *dev_id) u8 isrc, status; int n = 0; - while ((isrc = readl(priv->base + SUN4I_REG_INT_ADDR)) && - (n < SUN4I_CAN_MAX_IRQ)) { + while ((n < SUN4I_CAN_MAX_IRQ) && + (isrc = readl(priv->base + SUN4I_REG_INT_ADDR))) { n++; status = readl(priv->base + SUN4I_REG_STA_ADDR); diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 1321eb5e89ae..e29e85b67fd4 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -261,14 +261,21 @@ struct canfd_quirk { u8 quirk; } __packed; +/* struct gs_host_frame::echo_id == GS_HOST_FRAME_ECHO_ID_RX indicates + * a regular RX'ed CAN frame + */ +#define GS_HOST_FRAME_ECHO_ID_RX 0xffffffff + struct gs_host_frame { - u32 echo_id; - __le32 can_id; + struct_group(header, + u32 echo_id; + __le32 can_id; - u8 can_dlc; - u8 channel; - u8 flags; - u8 reserved; + u8 can_dlc; + u8 channel; + u8 flags; + u8 reserved; + ); union { DECLARE_FLEX_ARRAY(struct classic_can, classic_can); @@ -568,6 +575,37 @@ gs_usb_get_echo_skb(struct gs_can *dev, struct sk_buff *skb, return len; } +static unsigned int +gs_usb_get_minimum_rx_length(const struct gs_can *dev, const struct gs_host_frame *hf, + unsigned int *data_length_p) +{ + unsigned int minimum_length, data_length = 0; + + if (hf->flags & GS_CAN_FLAG_FD) { + if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX) + data_length = can_fd_dlc2len(hf->can_dlc); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + /* timestamp follows data field of max size */ + minimum_length = struct_size(hf, canfd_ts, 1); + else + minimum_length = sizeof(hf->header) + data_length; + } else { + if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX && + !(hf->can_id & cpu_to_le32(CAN_RTR_FLAG))) + data_length = can_cc_dlc2len(hf->can_dlc); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + /* timestamp follows data field of max size */ + minimum_length = struct_size(hf, classic_can_ts, 1); + else + minimum_length = sizeof(hf->header) + data_length; + } + + *data_length_p = data_length; + return minimum_length; +} + static void gs_usb_receive_bulk_callback(struct urb *urb) { struct gs_usb *parent = urb->context; @@ -576,6 +614,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) int rc; struct net_device_stats *stats; struct gs_host_frame *hf = urb->transfer_buffer; + unsigned int minimum_length, data_length; struct gs_tx_context *txc; struct can_frame *cf; struct canfd_frame *cfd; @@ -594,6 +633,15 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) return; } + minimum_length = sizeof(hf->header); + if (urb->actual_length < minimum_length) { + dev_err_ratelimited(&parent->udev->dev, + "short read (actual_length=%u, minimum_length=%u)\n", + urb->actual_length, minimum_length); + + goto resubmit_urb; + } + /* device reports out of range channel id */ if (hf->channel >= parent->channel_cnt) goto device_detach; @@ -609,20 +657,33 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (!netif_running(netdev)) goto resubmit_urb; - if (hf->echo_id == -1) { /* normal rx */ + minimum_length = gs_usb_get_minimum_rx_length(dev, hf, &data_length); + if (urb->actual_length < minimum_length) { + stats->rx_errors++; + stats->rx_length_errors++; + + if (net_ratelimit()) + netdev_err(netdev, + "short read (actual_length=%u, minimum_length=%u)\n", + urb->actual_length, minimum_length); + + goto resubmit_urb; + } + + if (hf->echo_id == GS_HOST_FRAME_ECHO_ID_RX) { /* normal rx */ if (hf->flags & GS_CAN_FLAG_FD) { skb = alloc_canfd_skb(netdev, &cfd); if (!skb) return; cfd->can_id = le32_to_cpu(hf->can_id); - cfd->len = can_fd_dlc2len(hf->can_dlc); + cfd->len = data_length; if (hf->flags & GS_CAN_FLAG_BRS) cfd->flags |= CANFD_BRS; if (hf->flags & GS_CAN_FLAG_ESI) cfd->flags |= CANFD_ESI; - memcpy(cfd->data, hf->canfd->data, cfd->len); + memcpy(cfd->data, hf->canfd->data, data_length); } else { skb = alloc_can_skb(netdev, &cf); if (!skb) @@ -631,7 +692,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) cf->can_id = le32_to_cpu(hf->can_id); can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode); - memcpy(cf->data, hf->classic_can->data, 8); + memcpy(cf->data, hf->classic_can->data, data_length); /* ERROR frames tell us information about the controller */ if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG) @@ -687,7 +748,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) resubmit_urb: usb_fill_bulk_urb(urb, parent->udev, parent->pipe_in, - hf, dev->parent->hf_size_rx, + hf, parent->hf_size_rx, gs_usb_receive_bulk_callback, parent); rc = usb_submit_urb(urb, GFP_ATOMIC); @@ -750,8 +811,21 @@ static void gs_usb_xmit_callback(struct urb *urb) struct gs_can *dev = txc->dev; struct net_device *netdev = dev->netdev; - if (urb->status) - netdev_info(netdev, "usb xmit fail %u\n", txc->echo_id); + if (!urb->status) + return; + + if (urb->status != -ESHUTDOWN && net_ratelimit()) + netdev_info(netdev, "failed to xmit URB %u: %pe\n", + txc->echo_id, ERR_PTR(urb->status)); + + netdev->stats.tx_dropped++; + netdev->stats.tx_errors++; + + can_free_echo_skb(netdev, txc->echo_id, NULL); + gs_free_tx_context(txc); + atomic_dec(&dev->active_tx_urbs); + + netif_wake_queue(netdev); } static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index c29828a94ad0..1167d38344f1 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -685,7 +685,7 @@ static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id, * for further details. */ if (tmp->len == 0) { - pos = round_up(pos, + pos = round_up(pos + 1, le16_to_cpu (dev->bulk_in->wMaxPacketSize)); continue; @@ -1732,7 +1732,7 @@ static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev, * number of events in case of a heavy rx load on the bus. */ if (cmd->len == 0) { - pos = round_up(pos, le16_to_cpu + pos = round_up(pos + 1, le16_to_cpu (dev->bulk_in->wMaxPacketSize)); continue; } diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c index bfe21f9f7dcd..cb23bea9c21b 100644 --- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c +++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c @@ -376,8 +376,18 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek) hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1); /* Register both leds */ - led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); - led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); + if (ret) { + dev_err(hellcreek->dev, "Failed to register sync_good LED\n"); + goto out; + } + + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + if (ret) { + dev_err(hellcreek->dev, "Failed to register is_gm LED\n"); + led_classdev_unregister(&hellcreek->led_sync_good); + goto out; + } ret = 0; diff --git a/drivers/net/dsa/ks8995.c b/drivers/net/dsa/ks8995.c index 5c4c83e00477..77d8b842693c 100644 --- a/drivers/net/dsa/ks8995.c +++ b/drivers/net/dsa/ks8995.c @@ -203,13 +203,13 @@ static const struct spi_device_id ks8995_id[] = { }; MODULE_DEVICE_TABLE(spi, ks8995_id); -static const struct of_device_id ks8895_spi_of_match[] = { +static const struct of_device_id ks8995_spi_of_match[] = { { .compatible = "micrel,ks8995" }, { .compatible = "micrel,ksz8864" }, { .compatible = "micrel,ksz8795" }, { }, }; -MODULE_DEVICE_TABLE(of, ks8895_spi_of_match); +MODULE_DEVICE_TABLE(of, ks8995_spi_of_match); static inline u8 get_chip_id(u8 val) { @@ -842,7 +842,7 @@ static void ks8995_remove(struct spi_device *spi) static struct spi_driver ks8995_driver = { .driver = { .name = "spi-ks8995", - .of_match_table = ks8895_spi_of_match, + .of_match_table = ks8995_spi_of_match, }, .probe = ks8995_probe, .remove = ks8995_remove, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 933ae8dc6337..0c10351fe5eb 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2587,8 +2587,8 @@ static int ksz_irq_phy_setup(struct ksz_device *dev) irq = irq_find_mapping(dev->ports[port].pirq.domain, PORT_SRC_PHY_INT); - if (irq < 0) { - ret = irq; + if (!irq) { + ret = -EINVAL; goto out; } ds->user_mii_bus->irq[phy] = irq; @@ -2952,8 +2952,8 @@ static int ksz_pirq_setup(struct ksz_device *dev, u8 p) snprintf(pirq->name, sizeof(pirq->name), "port_irq-%d", p); pirq->irq_num = irq_find_mapping(dev->girq.domain, p); - if (pirq->irq_num < 0) - return pirq->irq_num; + if (!pirq->irq_num) + return -EINVAL; return ksz_irq_common_setup(dev, pirq); } @@ -3038,12 +3038,12 @@ static int ksz_setup(struct dsa_switch *ds) dsa_switch_for_each_user_port(dp, dev->ds) { ret = ksz_pirq_setup(dev, dp->index); if (ret) - goto out_girq; + goto port_release; if (dev->info->ptp_capable) { ret = ksz_ptp_irq_setup(ds, dp->index); if (ret) - goto out_pirq; + goto pirq_release; } } } @@ -3053,7 +3053,7 @@ static int ksz_setup(struct dsa_switch *ds) if (ret) { dev_err(dev->dev, "Failed to register PTP clock: %d\n", ret); - goto out_ptpirq; + goto port_release; } } @@ -3076,17 +3076,16 @@ static int ksz_setup(struct dsa_switch *ds) out_ptp_clock_unregister: if (dev->info->ptp_capable) ksz_ptp_clock_unregister(ds); -out_ptpirq: - if (dev->irq > 0 && dev->info->ptp_capable) - dsa_switch_for_each_user_port(dp, dev->ds) - ksz_ptp_irq_free(ds, dp->index); -out_pirq: - if (dev->irq > 0) - dsa_switch_for_each_user_port(dp, dev->ds) +port_release: + if (dev->irq > 0) { + dsa_switch_for_each_user_port_continue_reverse(dp, dev->ds) { + if (dev->info->ptp_capable) + ksz_ptp_irq_free(ds, dp->index); +pirq_release: ksz_irq_free(&dev->ports[dp->index].pirq); -out_girq: - if (dev->irq > 0) + } ksz_irq_free(&dev->girq); + } return ret; } diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 35fc21b1ee48..997e4a76d0a6 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -1093,19 +1093,19 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) static const char * const name[] = {"pdresp-msg", "xdreq-msg", "sync-msg"}; const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops; + struct ksz_irq *ptpirq = &port->ptpirq; struct ksz_ptp_irq *ptpmsg_irq; ptpmsg_irq = &port->ptpmsg_irq[n]; + ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n); + if (!ptpmsg_irq->num) + return -EINVAL; ptpmsg_irq->port = port; ptpmsg_irq->ts_reg = ops->get_port_addr(port->num, ts_reg[n]); strscpy(ptpmsg_irq->name, name[n]); - ptpmsg_irq->num = irq_find_mapping(port->ptpirq.domain, n); - if (ptpmsg_irq->num < 0) - return ptpmsg_irq->num; - return request_threaded_irq(ptpmsg_irq->num, NULL, ksz_ptp_msg_thread_fn, IRQF_ONESHOT, ptpmsg_irq->name, ptpmsg_irq); @@ -1135,12 +1135,9 @@ int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) if (!ptpirq->domain) return -ENOMEM; - for (irq = 0; irq < ptpirq->nirqs; irq++) - irq_create_mapping(ptpirq->domain, irq); - ptpirq->irq_num = irq_find_mapping(port->pirq.domain, PORT_SRC_PTP_INT); - if (ptpirq->irq_num < 0) { - ret = ptpirq->irq_num; + if (!ptpirq->irq_num) { + ret = -EINVAL; goto out; } @@ -1159,12 +1156,11 @@ int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) out_ptp_msg: free_irq(ptpirq->irq_num, ptpirq); - while (irq--) + while (irq--) { free_irq(port->ptpmsg_irq[irq].num, &port->ptpmsg_irq[irq]); -out: - for (irq = 0; irq < ptpirq->nirqs; irq++) irq_dispose_mapping(port->ptpmsg_irq[irq].num); - + } +out: irq_domain_remove(ptpirq->domain); return ret; diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index b1ae3b9de3d1..5a1496fff445 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -540,6 +540,7 @@ static void lan937x_set_tune_adj(struct ksz_device *dev, int port, ksz_pread16(dev, port, reg, &data16); /* Update tune Adjust */ + data16 &= ~PORT_TUNE_ADJ; data16 |= FIELD_PREP(PORT_TUNE_ADJ, val); ksz_pwrite16(dev, port, reg, data16); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index f674c400f05b..aa2145cf29a6 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1302,14 +1302,7 @@ static int sja1105_set_port_speed(struct sja1105_private *priv, int port, * table, since this will be used for the clocking setup, and we no * longer need to store it in the static config (already told hardware * we want auto during upload phase). - * Actually for the SGMII port, the MAC is fixed at 1 Gbps and - * we need to configure the PCS only (if even that). */ - if (priv->phy_mode[port] == PHY_INTERFACE_MODE_SGMII) - speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS]; - else if (priv->phy_mode[port] == PHY_INTERFACE_MODE_2500BASEX) - speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS]; - mac[port].speed = speed; return 0; diff --git a/drivers/net/dsa/yt921x.c b/drivers/net/dsa/yt921x.c index 944988e29127..ebfd34f72314 100644 --- a/drivers/net/dsa/yt921x.c +++ b/drivers/net/dsa/yt921x.c @@ -39,60 +39,55 @@ struct yt921x_mib_desc { * to perform 32bit MIB overflow wraparound. */ static const struct yt921x_mib_desc yt921x_mib_descs[] = { - MIB_DESC(1, 0x00, NULL), /* RxBroadcast */ - MIB_DESC(1, 0x04, NULL), /* RxPause */ - MIB_DESC(1, 0x08, NULL), /* RxMulticast */ - MIB_DESC(1, 0x0c, NULL), /* RxCrcErr */ - - MIB_DESC(1, 0x10, NULL), /* RxAlignErr */ - MIB_DESC(1, 0x14, NULL), /* RxUnderSizeErr */ - MIB_DESC(1, 0x18, NULL), /* RxFragErr */ - MIB_DESC(1, 0x1c, NULL), /* RxPktSz64 */ - - MIB_DESC(1, 0x20, NULL), /* RxPktSz65To127 */ - MIB_DESC(1, 0x24, NULL), /* RxPktSz128To255 */ - MIB_DESC(1, 0x28, NULL), /* RxPktSz256To511 */ - MIB_DESC(1, 0x2c, NULL), /* RxPktSz512To1023 */ - - MIB_DESC(1, 0x30, NULL), /* RxPktSz1024To1518 */ - MIB_DESC(1, 0x34, NULL), /* RxPktSz1519ToMax */ - MIB_DESC(2, 0x38, NULL), /* RxGoodBytes */ - /* 0x3c */ - - MIB_DESC(2, 0x40, "RxBadBytes"), - /* 0x44 */ - MIB_DESC(2, 0x48, NULL), /* RxOverSzErr */ - /* 0x4c */ - - MIB_DESC(1, 0x50, NULL), /* RxDropped */ - MIB_DESC(1, 0x54, NULL), /* TxBroadcast */ - MIB_DESC(1, 0x58, NULL), /* TxPause */ - MIB_DESC(1, 0x5c, NULL), /* TxMulticast */ - - MIB_DESC(1, 0x60, NULL), /* TxUnderSizeErr */ - MIB_DESC(1, 0x64, NULL), /* TxPktSz64 */ - MIB_DESC(1, 0x68, NULL), /* TxPktSz65To127 */ - MIB_DESC(1, 0x6c, NULL), /* TxPktSz128To255 */ - - MIB_DESC(1, 0x70, NULL), /* TxPktSz256To511 */ - MIB_DESC(1, 0x74, NULL), /* TxPktSz512To1023 */ - MIB_DESC(1, 0x78, NULL), /* TxPktSz1024To1518 */ - MIB_DESC(1, 0x7c, NULL), /* TxPktSz1519ToMax */ - - MIB_DESC(2, 0x80, NULL), /* TxGoodBytes */ - /* 0x84 */ - MIB_DESC(2, 0x88, NULL), /* TxCollision */ - /* 0x8c */ - - MIB_DESC(1, 0x90, NULL), /* TxExcessiveCollistion */ - MIB_DESC(1, 0x94, NULL), /* TxMultipleCollision */ - MIB_DESC(1, 0x98, NULL), /* TxSingleCollision */ - MIB_DESC(1, 0x9c, NULL), /* TxPkt */ - - MIB_DESC(1, 0xa0, NULL), /* TxDeferred */ - MIB_DESC(1, 0xa4, NULL), /* TxLateCollision */ - MIB_DESC(1, 0xa8, "RxOAM"), - MIB_DESC(1, 0xac, "TxOAM"), + MIB_DESC(1, YT921X_MIB_DATA_RX_BROADCAST, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PAUSE, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_MULTICAST, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_CRC_ERR, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_RX_ALIGN_ERR, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_UNDERSIZE_ERR, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_FRAG_ERR, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_64, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_65_TO_127, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_128_TO_255, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_256_TO_511, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_512_TO_1023, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_1024_TO_1518, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_PKT_SZ_1519_TO_MAX, NULL), + MIB_DESC(2, YT921X_MIB_DATA_RX_GOOD_BYTES, NULL), + + MIB_DESC(2, YT921X_MIB_DATA_RX_BAD_BYTES, "RxBadBytes"), + MIB_DESC(1, YT921X_MIB_DATA_RX_OVERSIZE_ERR, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_RX_DROPPED, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_BROADCAST, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PAUSE, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_MULTICAST, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_TX_UNDERSIZE_ERR, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_64, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_65_TO_127, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_128_TO_255, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_256_TO_511, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_512_TO_1023, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_1024_TO_1518, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT_SZ_1519_TO_MAX, NULL), + + MIB_DESC(2, YT921X_MIB_DATA_TX_GOOD_BYTES, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_COLLISION, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_TX_EXCESSIVE_COLLISION, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_MULTIPLE_COLLISION, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_SINGLE_COLLISION, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_PKT, NULL), + + MIB_DESC(1, YT921X_MIB_DATA_TX_DEFERRED, NULL), + MIB_DESC(1, YT921X_MIB_DATA_TX_LATE_COLLISION, NULL), + MIB_DESC(1, YT921X_MIB_DATA_RX_OAM, "RxOAM"), + MIB_DESC(1, YT921X_MIB_DATA_TX_OAM, "TxOAM"), }; struct yt921x_info { @@ -705,7 +700,7 @@ static int yt921x_read_mib(struct yt921x_priv *priv, int port) res = yt921x_reg_read(priv, reg + 4, &val1); if (res) break; - val = ((u64)val0 << 32) | val1; + val = ((u64)val1 << 32) | val0; } WRITE_ONCE(*valp, val); diff --git a/drivers/net/dsa/yt921x.h b/drivers/net/dsa/yt921x.h index 3e85d90826fb..44719d841d40 100644 --- a/drivers/net/dsa/yt921x.h +++ b/drivers/net/dsa/yt921x.h @@ -173,6 +173,60 @@ #define YT921X_MIB_CTRL_ALL_PORT BIT(0) #define YT921X_MIBn_DATA0(port) (0xc0100 + 0x100 * (port)) #define YT921X_MIBn_DATAm(port, x) (YT921X_MIBn_DATA0(port) + 4 * (x)) +#define YT921X_MIB_DATA_RX_BROADCAST 0x00 +#define YT921X_MIB_DATA_RX_PAUSE 0x04 +#define YT921X_MIB_DATA_RX_MULTICAST 0x08 +#define YT921X_MIB_DATA_RX_CRC_ERR 0x0c + +#define YT921X_MIB_DATA_RX_ALIGN_ERR 0x10 +#define YT921X_MIB_DATA_RX_UNDERSIZE_ERR 0x14 +#define YT921X_MIB_DATA_RX_FRAG_ERR 0x18 +#define YT921X_MIB_DATA_RX_PKT_SZ_64 0x1c + +#define YT921X_MIB_DATA_RX_PKT_SZ_65_TO_127 0x20 +#define YT921X_MIB_DATA_RX_PKT_SZ_128_TO_255 0x24 +#define YT921X_MIB_DATA_RX_PKT_SZ_256_TO_511 0x28 +#define YT921X_MIB_DATA_RX_PKT_SZ_512_TO_1023 0x2c + +#define YT921X_MIB_DATA_RX_PKT_SZ_1024_TO_1518 0x30 +#define YT921X_MIB_DATA_RX_PKT_SZ_1519_TO_MAX 0x34 +/* 0x38: unused */ +#define YT921X_MIB_DATA_RX_GOOD_BYTES 0x3c + +/* 0x40: 64 bytes */ +#define YT921X_MIB_DATA_RX_BAD_BYTES 0x44 +/* 0x48: 64 bytes */ +#define YT921X_MIB_DATA_RX_OVERSIZE_ERR 0x4c + +#define YT921X_MIB_DATA_RX_DROPPED 0x50 +#define YT921X_MIB_DATA_TX_BROADCAST 0x54 +#define YT921X_MIB_DATA_TX_PAUSE 0x58 +#define YT921X_MIB_DATA_TX_MULTICAST 0x5c + +#define YT921X_MIB_DATA_TX_UNDERSIZE_ERR 0x60 +#define YT921X_MIB_DATA_TX_PKT_SZ_64 0x64 +#define YT921X_MIB_DATA_TX_PKT_SZ_65_TO_127 0x68 +#define YT921X_MIB_DATA_TX_PKT_SZ_128_TO_255 0x6c + +#define YT921X_MIB_DATA_TX_PKT_SZ_256_TO_511 0x70 +#define YT921X_MIB_DATA_TX_PKT_SZ_512_TO_1023 0x74 +#define YT921X_MIB_DATA_TX_PKT_SZ_1024_TO_1518 0x78 +#define YT921X_MIB_DATA_TX_PKT_SZ_1519_TO_MAX 0x7c + +/* 0x80: unused */ +#define YT921X_MIB_DATA_TX_GOOD_BYTES 0x84 +/* 0x88: 64 bytes */ +#define YT921X_MIB_DATA_TX_COLLISION 0x8c + +#define YT921X_MIB_DATA_TX_EXCESSIVE_COLLISION 0x90 +#define YT921X_MIB_DATA_TX_MULTIPLE_COLLISION 0x94 +#define YT921X_MIB_DATA_TX_SINGLE_COLLISION 0x98 +#define YT921X_MIB_DATA_TX_PKT 0x9c + +#define YT921X_MIB_DATA_TX_DEFERRED 0xa0 +#define YT921X_MIB_DATA_TX_LATE_COLLISION 0xa4 +#define YT921X_MIB_DATA_RX_OAM 0xa8 +#define YT921X_MIB_DATA_TX_OAM 0xac #define YT921X_EDATA_CTRL 0xe0000 #define YT921X_EDATA_CTRL_ADDR_M GENMASK(15, 8) diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index c373f21d95f5..0caabb0c3aa0 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -308,7 +308,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth, if (!airoha_is_valid_gdm_port(eth, port)) return -EINVAL; - if (dsa_port >= 0) + if (dsa_port >= 0 || eth->ports[1]) pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; else diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 0b53a1fab46d..4a6b35c84dab 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -255,7 +255,8 @@ int pdsc_dl_flash_update(struct devlink *dl, struct devlink_flash_update_params *params, struct netlink_ext_ack *extack); int pdsc_dl_enable_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int pdsc_dl_enable_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index d8dc39da4161..b576be626a29 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -22,7 +22,8 @@ pdsc_viftype *pdsc_dl_find_viftype_by_id(struct pdsc *pdsc, } int pdsc_dl_enable_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct pdsc *pdsc = devlink_priv(dl); struct pdsc_viftype *vt_entry; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index f3adf29b222b..0653e69f0ef7 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1259,6 +1259,11 @@ static int xgbe_start(struct xgbe_prv_data *pdata) udp_tunnel_nic_reset_ntf(netdev); + /* Reset the phy settings */ + ret = xgbe_phy_reset(pdata); + if (ret) + goto err_txrx; + netif_tx_start_all_queues(netdev); xgbe_start_timers(pdata); @@ -1268,6 +1273,10 @@ static int xgbe_start(struct xgbe_prv_data *pdata) return 0; +err_txrx: + hw_if->disable_rx(pdata); + hw_if->disable_tx(pdata); + err_irqs: xgbe_free_irqs(pdata); @@ -1574,11 +1583,6 @@ static int xgbe_open(struct net_device *netdev) goto err_dev_wq; } - /* Reset the phy settings */ - ret = xgbe_phy_reset(pdata); - if (ret) - goto err_an_wq; - /* Enable the clocks */ ret = clk_prepare_enable(pdata->sysclk); if (ret) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 35a381a83647..a68757e8fd22 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -989,6 +989,7 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata) return ret; } phy_data->phydev = phydev; + phy_data->phydev->mac_managed_pm = true; xgbe_phy_external_phy_quirks(pdata); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c index 1921741f7311..18b08277d2e1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.c @@ -15,6 +15,7 @@ #include "aq_hw.h" #include "aq_nic.h" +#include "hw_atl/hw_atl_llh.h" void aq_hw_write_reg_bit(struct aq_hw_s *aq_hw, u32 addr, u32 msk, u32 shift, u32 val) @@ -81,6 +82,27 @@ void aq_hw_write_reg64(struct aq_hw_s *hw, u32 reg, u64 value) lo_hi_writeq(value, hw->mmio + reg); } +int aq_hw_invalidate_descriptor_cache(struct aq_hw_s *hw) +{ + int err; + u32 val; + + /* Invalidate Descriptor Cache to prevent writing to the cached + * descriptors and to the data pointer of those descriptors + */ + hw_atl_rdm_rx_dma_desc_cache_init_tgl(hw); + + err = aq_hw_err_from_flags(hw); + if (err) + goto err_exit; + + readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get, + hw, val, val == 1, 1000U, 10000U); + +err_exit: + return err; +} + int aq_hw_err_from_flags(struct aq_hw_s *hw) { int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h index ffa6e4067c21..d89c63d88e4a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h @@ -35,6 +35,7 @@ u32 aq_hw_read_reg(struct aq_hw_s *hw, u32 reg); void aq_hw_write_reg(struct aq_hw_s *hw, u32 reg, u32 value); u64 aq_hw_read_reg64(struct aq_hw_s *hw, u32 reg); void aq_hw_write_reg64(struct aq_hw_s *hw, u32 reg, u64 value); +int aq_hw_invalidate_descriptor_cache(struct aq_hw_s *hw); int aq_hw_err_from_flags(struct aq_hw_s *hw); int aq_hw_num_tcs(struct aq_hw_s *hw); int aq_hw_q_per_tc(struct aq_hw_s *hw); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index f21de0c21e52..d23d23bed39f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -547,6 +547,11 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, if (!buff->is_eop) { unsigned int frag_cnt = 0U; + + /* There will be an extra fragment */ + if (buff->len > AQ_CFG_RX_HDR_SIZE) + frag_cnt++; + buff_ = buff; do { bool is_rsc_completed = true; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 493432d036b9..c7895bfb2ecf 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -1198,26 +1198,9 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { - int err; - u32 val; - hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); - /* Invalidate Descriptor Cache to prevent writing to the cached - * descriptors and to the data pointer of those descriptors - */ - hw_atl_rdm_rx_dma_desc_cache_init_tgl(self); - - err = aq_hw_err_from_flags(self); - - if (err) - goto err_exit; - - readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get, - self, val, val == 1, 1000U, 10000U); - -err_exit: - return err; + return aq_hw_invalidate_descriptor_cache(self); } int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self, struct aq_ring_s *ring) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c index b0ed572e88c6..0ce9caae8799 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c @@ -759,7 +759,7 @@ static int hw_atl2_hw_stop(struct aq_hw_s *self) { hw_atl_b0_hw_irq_disable(self, HW_ATL2_INT_MASK); - return 0; + return aq_hw_invalidate_descriptor_cache(self); } static struct aq_stats_s *hw_atl2_utils_get_hw_stats(struct aq_hw_s *self) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index fc8dec37a9e4..3d853eeb976f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3355,19 +3355,11 @@ static int bnx2x_get_rxfh_fields(struct net_device *dev, return 0; } -static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules __always_unused) +static u32 bnx2x_get_rx_ring_count(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = BNX2X_NUM_ETH_QUEUES(bp); - return 0; - default: - DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n"); - return -EOPNOTSUPP; - } + return BNX2X_NUM_ETH_QUEUES(bp); } static int bnx2x_set_rxfh_fields(struct net_device *dev, @@ -3674,7 +3666,7 @@ static const struct ethtool_ops bnx2x_ethtool_ops = { .get_strings = bnx2x_get_strings, .set_phys_id = bnx2x_set_phys_id, .get_ethtool_stats = bnx2x_get_ethtool_stats, - .get_rxnfc = bnx2x_get_rxnfc, + .get_rx_ring_count = bnx2x_get_rx_ring_count, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, @@ -3702,7 +3694,7 @@ static const struct ethtool_ops bnx2x_vf_ethtool_ops = { .get_sset_count = bnx2x_get_sset_count, .get_strings = bnx2x_get_strings, .get_ethtool_stats = bnx2x_get_ethtool_stats, - .get_rxnfc = bnx2x_get_rxnfc, + .get_rx_ring_count = bnx2x_get_rx_ring_count, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index f0f05d7315ac..aca4267babc8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -308,8 +308,11 @@ static int bnx2x_set_storm_rx_mode(struct bnx2x *bp); /**************************************************************************** * General service functions ****************************************************************************/ - -static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr); +static int bnx2x_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +static int bnx2x_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config); static void __storm_memset_dma_mapping(struct bnx2x *bp, u32 addr, dma_addr_t mapping) @@ -12813,14 +12816,9 @@ static int bnx2x_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (!netif_running(dev)) return -EAGAIN; - switch (cmd) { - case SIOCSHWTSTAMP: - return bnx2x_hwtstamp_ioctl(bp, ifr); - default: - DP(NETIF_MSG_LINK, "ioctl: phy id 0x%x, reg 0x%x, val_in 0x%x\n", - mdio->phy_id, mdio->reg_num, mdio->val_in); - return mdio_mii_ioctl(&bp->mdio, mdio, cmd); - } + DP(NETIF_MSG_LINK, "ioctl: phy id 0x%x, reg 0x%x, val_in 0x%x\n", + mdio->phy_id, mdio->reg_num, mdio->val_in); + return mdio_mii_ioctl(&bp->mdio, mdio, cmd); } static int bnx2x_validate_addr(struct net_device *dev) @@ -13036,6 +13034,8 @@ static const struct net_device_ops bnx2x_netdev_ops = { .ndo_get_phys_port_id = bnx2x_get_phys_port_id, .ndo_set_vf_link_state = bnx2x_set_vf_link_state, .ndo_features_check = bnx2x_features_check, + .ndo_hwtstamp_get = bnx2x_hwtstamp_get, + .ndo_hwtstamp_set = bnx2x_hwtstamp_set, }; static int bnx2x_init_dev(struct bnx2x *bp, struct pci_dev *pdev, @@ -15350,31 +15350,57 @@ int bnx2x_configure_ptp_filters(struct bnx2x *bp) return 0; } -static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr) +static int bnx2x_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; + struct bnx2x *bp = netdev_priv(dev); int rc; - DP(BNX2X_MSG_PTP, "HWTSTAMP IOCTL called\n"); + DP(BNX2X_MSG_PTP, "HWTSTAMP SET called\n"); - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; + if (!netif_running(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Device is down"); + return -EAGAIN; + } DP(BNX2X_MSG_PTP, "Requested tx_type: %d, requested rx_filters = %d\n", - config.tx_type, config.rx_filter); + config->tx_type, config->rx_filter); + + switch (config->tx_type) { + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_OFF: + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "One-step timestamping is not supported"); + return -ERANGE; + } bp->hwtstamp_ioctl_called = true; - bp->tx_type = config.tx_type; - bp->rx_filter = config.rx_filter; + bp->tx_type = config->tx_type; + bp->rx_filter = config->rx_filter; rc = bnx2x_configure_ptp_filters(bp); - if (rc) + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "HW configuration failure"); return rc; + } + + config->rx_filter = bp->rx_filter; + + return 0; +} + +static int bnx2x_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) +{ + struct bnx2x *bp = netdev_priv(dev); - config.rx_filter = bp->rx_filter; + config->rx_filter = bp->rx_filter; + config->tx_type = bp->tx_type; - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; + return 0; } /* Configures HW for PTP */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a625e7c311dd..d17d0ea89c36 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -877,7 +877,7 @@ static bool __bnxt_tx_int(struct bnxt *bp, struct bnxt_tx_ring_info *txr, next_tx_int: cons = NEXT_TX(cons); - dev_consume_skb_any(skb); + napi_consume_skb(skb, budget); } WRITE_ONCE(txr->tx_cons, cons); @@ -4479,7 +4479,14 @@ static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp, ring->fw_ring_id = INVALID_HW_RING_ID; if ((bp->flags & BNXT_FLAG_AGG_RINGS)) { type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | - RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; + RX_BD_TYPE_RX_AGG_BD; + + /* On P7, setting EOP will cause the chip to disable + * Relaxed Ordering (RO) for TPA data. Disable EOP for + * potentially higher performance with RO. + */ + if (BNXT_CHIP_P5_AND_MINUS(bp) || !(bp->flags & BNXT_FLAG_TPA)) + type |= RX_BD_FLAGS_AGG_EOP; bnxt_init_rxbd_pages(ring, type); } @@ -5688,6 +5695,10 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, u16 cmd = bnxt_vf_req_snif[i]; unsigned int bit, idx; + if ((bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN) && + cmd == HWRM_PORT_PHY_QCFG) + continue; + idx = cmd / 32; bit = cmd % 32; data[idx] |= 1 << bit; @@ -8506,6 +8517,11 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) if (flags & FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV) bp->fw_cap |= BNXT_FW_CAP_ENABLE_RDMA_SRIOV; + if (resp->roce_bidi_opt_mode & + FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED) + bp->cos0_cos1_shared = 1; + else + bp->cos0_cos1_shared = 0; switch (resp->port_partition_type) { case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0: @@ -9653,6 +9669,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->flags |= BNXT_FLAG_ROCEV1_CAP; if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED) bp->flags |= BNXT_FLAG_ROCEV2_CAP; + if (flags & FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_LINK_ADMIN; if (flags & FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED) bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED; if (flags & FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE) @@ -14020,11 +14038,19 @@ static void bnxt_dump_rx_sw_state(struct bnxt_napi *bnapi) static void bnxt_dump_cp_sw_state(struct bnxt_napi *bnapi) { - struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; - int i = bnapi->index; + struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring, *cpr2; + int i = bnapi->index, j; netdev_info(bnapi->bp->dev, "[%d]: cp{fw_ring: %d raw_cons: %x}\n", i, cpr->cp_ring_struct.fw_ring_id, cpr->cp_raw_cons); + for (j = 0; j < cpr->cp_ring_count; j++) { + cpr2 = &cpr->cp_ring_arr[j]; + if (!cpr2->bnapi) + continue; + netdev_info(bnapi->bp->dev, "[%d.%d]: cp{fw_ring: %d raw_cons: %x}\n", + i, j, cpr2->cp_ring_struct.fw_ring_id, + cpr2->cp_raw_cons); + } } static void bnxt_dbg_dump_states(struct bnxt *bp) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3613a172483a..f5f07a7e6b29 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -131,6 +131,7 @@ struct rx_bd { #define RX_BD_TYPE_48B_BD_SIZE (2 << 4) #define RX_BD_TYPE_64B_BD_SIZE (3 << 4) #define RX_BD_FLAGS_SOP (1 << 6) + #define RX_BD_FLAGS_AGG_EOP (1 << 6) #define RX_BD_FLAGS_EOP (1 << 7) #define RX_BD_FLAGS_BUFFERS (3 << 8) #define RX_BD_FLAGS_1_BUFFER_PACKET (0 << 8) @@ -2424,6 +2425,7 @@ struct bnxt { u8 tc_to_qidx[BNXT_MAX_QUEUE]; u8 q_ids[BNXT_MAX_QUEUE]; u8 max_q; + u8 cos0_cos1_shared; u8 num_tc; u16 max_pfcwd_tmo_ms; @@ -2482,6 +2484,7 @@ struct bnxt { #define BNXT_FW_CAP_ROCE_VF_RESC_MGMT_SUPPORTED BIT_ULL(6) #define BNXT_FW_CAP_KONG_MB_CHNL BIT_ULL(7) #define BNXT_FW_CAP_ROCE_VF_DYN_ALLOC_SUPPORT BIT_ULL(8) + #define BNXT_FW_CAP_LINK_ADMIN BIT_ULL(9) #define BNXT_FW_CAP_OVS_64BIT_HANDLE BIT_ULL(10) #define BNXT_FW_CAP_TRUSTED_VF BIT_ULL(11) #define BNXT_FW_CAP_ERROR_RECOVERY BIT_ULL(13) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 67ca02d84c97..15de802bbac4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -1086,7 +1086,8 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, } static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = bnxt_get_bp_from_dl(dl); struct hwrm_nvm_get_variable_input *req; @@ -1168,7 +1169,8 @@ static int bnxt_dl_msix_validate(struct devlink *dl, u32 id, } static int bnxt_remote_dev_reset_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = bnxt_get_bp_from_dl(dl); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 41686a6f84b5..efb9bf20e66b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -688,16 +688,22 @@ skip_ring_stats: buf[j] = *(rx_port_stats_ext + n); } for (i = 0; i < 8; i++, j++) { - long n = bnxt_tx_bytes_pri_arr[i].base_off + - bp->pri2cos_idx[i]; + u8 cos_idx = bp->pri2cos_idx[i]; + long n; + n = bnxt_tx_bytes_pri_arr[i].base_off + cos_idx; buf[j] = *(tx_port_stats_ext + n); + if (bp->cos0_cos1_shared && !cos_idx) + buf[j] += *(tx_port_stats_ext + n + 1); } for (i = 0; i < 8; i++, j++) { - long n = bnxt_tx_pkts_pri_arr[i].base_off + - bp->pri2cos_idx[i]; + u8 cos_idx = bp->pri2cos_idx[i]; + long n; + n = bnxt_tx_pkts_pri_arr[i].base_off + cos_idx; buf[j] = *(tx_port_stats_ext + n); + if (bp->cos0_cos1_shared && !cos_idx) + buf[j] += *(tx_port_stats_ext + n + 1); } } } @@ -4617,6 +4623,11 @@ static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extac PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG) return 0; + if (bp->link_info.phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASET || + bp->link_info.phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE){ + NL_SET_ERR_MSG_MOD(extack, "Operation not supported as PHY type is Base-T"); + return -EOPNOTSUPP; + } switch (bp->link_info.module_status) { case PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN: NL_SET_ERR_MSG_MOD(extack, "Transceiver module is powering down"); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 80fed2c07b9e..be7deb9cc410 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -332,6 +332,38 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return rc; } +static int bnxt_set_vf_link_admin_state(struct bnxt *bp, int vf_id) +{ + struct hwrm_func_cfg_input *req; + struct bnxt_vf_info *vf; + int rc; + + if (!(bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN)) + return 0; + + vf = &bp->pf.vf[vf_id]; + + rc = bnxt_hwrm_func_cfg_short_req_init(bp, &req); + if (rc) + return rc; + + req->fid = cpu_to_le16(vf->fw_fid); + switch (vf->flags & (BNXT_VF_LINK_FORCED | BNXT_VF_LINK_UP)) { + case BNXT_VF_LINK_FORCED: + req->options = + FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN; + break; + case (BNXT_VF_LINK_FORCED | BNXT_VF_LINK_UP): + req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP; + break; + default: + req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO; + break; + } + req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE); + return hwrm_req_send(bp, req); +} + int bnxt_set_vf_link_state(struct net_device *dev, int vf_id, int link) { struct bnxt *bp = netdev_priv(dev); @@ -357,10 +389,11 @@ int bnxt_set_vf_link_state(struct net_device *dev, int vf_id, int link) break; default: netdev_err(bp->dev, "Invalid link option\n"); - rc = -EINVAL; - break; + return -EINVAL; } - if (vf->flags & (BNXT_VF_LINK_UP | BNXT_VF_LINK_FORCED)) + if (bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN) + rc = bnxt_set_vf_link_admin_state(bp, vf_id); + else if (vf->flags & (BNXT_VF_LINK_UP | BNXT_VF_LINK_FORCED)) rc = bnxt_hwrm_fwd_async_event_cmpl(bp, vf, ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE); return rc; @@ -666,15 +699,21 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset) hwrm_req_hold(bp, req); for (i = 0; i < num_vfs; i++) { + struct bnxt_vf_info *vf = &pf->vf[i]; + + vf->fw_fid = pf->first_vf_id + i; + rc = bnxt_set_vf_link_admin_state(bp, i); + if (rc) + break; + if (reset) __bnxt_set_vf_params(bp, i); - req->vf_id = cpu_to_le16(pf->first_vf_id + i); + req->vf_id = cpu_to_le16(vf->fw_fid); rc = hwrm_req_send(bp, req); if (rc) break; pf->active_vfs = i + 1; - pf->vf[i].fw_fid = pf->first_vf_id + i; } if (pf->active_vfs) { @@ -741,6 +780,12 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) FUNC_CFG_REQ_ENABLES_NUM_VNICS | FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS); + if (bp->fw_cap & BNXT_FW_CAP_LINK_ADMIN) { + req->options = FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO; + req->enables |= + cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE); + } + mtu = bp->dev->mtu + VLAN_ETH_HLEN; req->mru = cpu_to_le16(mtu); req->admin_mtu = cpu_to_le16(mtu); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index f8c2c72b382d..927971c362f1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -142,7 +142,6 @@ int bnxt_register_dev(struct bnxt_en_dev *edev, edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp); bnxt_fill_msix_vecs(bp, bp->edev->msix_entries); - edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; exit: mutex_unlock(&edev->en_dev_lock); netdev_unlock(dev); @@ -159,8 +158,6 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev) ulp = edev->ulp_tbl; netdev_lock(dev); mutex_lock(&edev->en_dev_lock); - if (ulp->msix_requested) - edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; edev->ulp_tbl->msix_requested = 0; if (ulp->max_async_event_id) @@ -298,7 +295,7 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) struct bnxt_ulp_ops *ops; bool reset = false; - if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) + if (!edev) return; if (bnxt_ulp_registered(bp->edev)) { @@ -321,7 +318,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) struct bnxt_en_dev *edev = bp->edev; struct bnxt_ulp_ops *ops; - if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) + if (!edev) return; if (bnxt_ulp_registered(bp->edev)) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index 7b9dd8ebe4bc..3c5b8a53f715 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -58,7 +58,6 @@ struct bnxt_en_dev { #define BNXT_EN_FLAG_ROCEV2_CAP 0x2 #define BNXT_EN_FLAG_ROCE_CAP (BNXT_EN_FLAG_ROCEV1_CAP | \ BNXT_EN_FLAG_ROCEV2_CAP) - #define BNXT_EN_FLAG_MSIX_REQUESTED 0x4 #define BNXT_EN_FLAG_ULP_STOPPED 0x8 #define BNXT_EN_FLAG_VF 0x10 #define BNXT_EN_VF(edev) ((edev)->flags & BNXT_EN_FLAG_VF) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index fc6053414b7d..413028bdcacb 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -541,21 +541,11 @@ static int nicvf_get_rxfh_fields(struct net_device *dev, return 0; } -static int nicvf_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, u32 *rules) +static u32 nicvf_get_rx_ring_count(struct net_device *dev) { struct nicvf *nic = netdev_priv(dev); - int ret = -EOPNOTSUPP; - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = nic->rx_queues; - ret = 0; - break; - default: - break; - } - return ret; + return nic->rx_queues; } static int nicvf_set_rxfh_fields(struct net_device *dev, @@ -861,7 +851,7 @@ static const struct ethtool_ops nicvf_ethtool_ops = { .get_coalesce = nicvf_get_coalesce, .get_ringparam = nicvf_get_ringparam, .set_ringparam = nicvf_set_ringparam, - .get_rxnfc = nicvf_get_rxnfc, + .get_rx_ring_count = nicvf_get_rx_ring_count, .get_rxfh_key_size = nicvf_get_rxfh_key_size, .get_rxfh_indir_size = nicvf_get_rxfh_indir_size, .get_rxfh = nicvf_get_rxfh, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 7e2283c95b97..66b8854e059f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3485,7 +3485,7 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate) struct adapter *adap = pi->adapter; struct ch_sched_queue qe = { 0 }; struct ch_sched_params p = { 0 }; - struct sched_class *e; + struct ch_sched_class *e; u32 req_rate; int err = 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c index 1672d3afe5be..f8dcf0b4abcd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_matchall.c @@ -56,7 +56,7 @@ static int cxgb4_matchall_egress_validate(struct net_device *dev, struct port_info *pi = netdev2pinfo(dev); struct flow_action_entry *entry; struct ch_sched_queue qe; - struct sched_class *e; + struct ch_sched_class *e; u64 max_link_rate; u32 i, speed; int ret; @@ -180,7 +180,7 @@ static int cxgb4_matchall_alloc_tc(struct net_device *dev, struct port_info *pi = netdev2pinfo(dev); struct adapter *adap = netdev2adap(dev); struct flow_action_entry *entry; - struct sched_class *e; + struct ch_sched_class *e; int ret; u32 i; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c index 338b04f339b3..a2dcd2e24263 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.c @@ -330,7 +330,7 @@ static int cxgb4_mqprio_alloc_tc(struct net_device *dev, struct cxgb4_tc_port_mqprio *tc_port_mqprio; struct port_info *pi = netdev2pinfo(dev); struct adapter *adap = netdev2adap(dev); - struct sched_class *e; + struct ch_sched_class *e; int ret; u8 i; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index a1b14468d1ff..38a30aeee122 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -44,7 +44,7 @@ static int t4_sched_class_fw_cmd(struct port_info *pi, { struct adapter *adap = pi->adapter; struct sched_table *s = pi->sched_tbl; - struct sched_class *e; + struct ch_sched_class *e; int err = 0; e = &s->tab[p->u.params.class]; @@ -122,7 +122,7 @@ static void *t4_sched_entry_lookup(struct port_info *pi, const u32 val) { struct sched_table *s = pi->sched_tbl; - struct sched_class *e, *end; + struct ch_sched_class *e, *end; void *found = NULL; /* Look for an entry with matching @val */ @@ -166,8 +166,8 @@ static void *t4_sched_entry_lookup(struct port_info *pi, return found; } -struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev, - struct ch_sched_queue *p) +struct ch_sched_class *cxgb4_sched_queue_lookup(struct net_device *dev, + struct ch_sched_queue *p) { struct port_info *pi = netdev2pinfo(dev); struct sched_queue_entry *qe = NULL; @@ -187,7 +187,7 @@ static int t4_sched_queue_unbind(struct port_info *pi, struct ch_sched_queue *p) struct sched_queue_entry *qe = NULL; struct adapter *adap = pi->adapter; struct sge_eth_txq *txq; - struct sched_class *e; + struct ch_sched_class *e; int err = 0; if (p->queue < 0 || p->queue >= pi->nqsets) @@ -218,7 +218,7 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) struct sched_queue_entry *qe = NULL; struct adapter *adap = pi->adapter; struct sge_eth_txq *txq; - struct sched_class *e; + struct ch_sched_class *e; unsigned int qid; int err = 0; @@ -260,7 +260,7 @@ static int t4_sched_flowc_unbind(struct port_info *pi, struct ch_sched_flowc *p) { struct sched_flowc_entry *fe = NULL; struct adapter *adap = pi->adapter; - struct sched_class *e; + struct ch_sched_class *e; int err = 0; if (p->tid < 0 || p->tid >= adap->tids.neotids) @@ -288,7 +288,7 @@ static int t4_sched_flowc_bind(struct port_info *pi, struct ch_sched_flowc *p) struct sched_table *s = pi->sched_tbl; struct sched_flowc_entry *fe = NULL; struct adapter *adap = pi->adapter; - struct sched_class *e; + struct ch_sched_class *e; int err = 0; if (p->tid < 0 || p->tid >= adap->tids.neotids) @@ -322,7 +322,7 @@ out_err: } static void t4_sched_class_unbind_all(struct port_info *pi, - struct sched_class *e, + struct ch_sched_class *e, enum sched_bind_type type) { if (!e) @@ -476,12 +476,12 @@ int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, } /* If @p is NULL, fetch any available unused class */ -static struct sched_class *t4_sched_class_lookup(struct port_info *pi, - const struct ch_sched_params *p) +static struct ch_sched_class *t4_sched_class_lookup(struct port_info *pi, + const struct ch_sched_params *p) { struct sched_table *s = pi->sched_tbl; - struct sched_class *found = NULL; - struct sched_class *e, *end; + struct ch_sched_class *found = NULL; + struct ch_sched_class *e, *end; if (!p) { /* Get any available unused class */ @@ -522,10 +522,10 @@ static struct sched_class *t4_sched_class_lookup(struct port_info *pi, return found; } -static struct sched_class *t4_sched_class_alloc(struct port_info *pi, - struct ch_sched_params *p) +static struct ch_sched_class *t4_sched_class_alloc(struct port_info *pi, + struct ch_sched_params *p) { - struct sched_class *e = NULL; + struct ch_sched_class *e = NULL; u8 class_id; int err; @@ -579,8 +579,8 @@ static struct sched_class *t4_sched_class_alloc(struct port_info *pi, * scheduling class with matching @p is found, then the matching class is * returned. */ -struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev, - struct ch_sched_params *p) +struct ch_sched_class *cxgb4_sched_class_alloc(struct net_device *dev, + struct ch_sched_params *p) { struct port_info *pi = netdev2pinfo(dev); u8 class_id; @@ -607,7 +607,7 @@ void cxgb4_sched_class_free(struct net_device *dev, u8 classid) struct port_info *pi = netdev2pinfo(dev); struct sched_table *s = pi->sched_tbl; struct ch_sched_params p; - struct sched_class *e; + struct ch_sched_class *e; u32 speed; int ret; @@ -640,7 +640,7 @@ void cxgb4_sched_class_free(struct net_device *dev, u8 classid) } } -static void t4_sched_class_free(struct net_device *dev, struct sched_class *e) +static void t4_sched_class_free(struct net_device *dev, struct ch_sched_class *e) { struct port_info *pi = netdev2pinfo(dev); @@ -660,7 +660,7 @@ struct sched_table *t4_init_sched(unsigned int sched_size) s->sched_size = sched_size; for (i = 0; i < s->sched_size; i++) { - memset(&s->tab[i], 0, sizeof(struct sched_class)); + memset(&s->tab[i], 0, sizeof(struct ch_sched_class)); s->tab[i].idx = i; s->tab[i].state = SCHED_STATE_UNUSED; INIT_LIST_HEAD(&s->tab[i].entry_list); @@ -682,7 +682,7 @@ void t4_cleanup_sched(struct adapter *adap) continue; for (i = 0; i < s->sched_size; i++) { - struct sched_class *e; + struct ch_sched_class *e; e = &s->tab[i]; if (e->state == SCHED_STATE_ACTIVE) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h index 6b3c778815f0..4d3b5a757536 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.h +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h @@ -71,7 +71,7 @@ struct sched_flowc_entry { struct ch_sched_flowc param; }; -struct sched_class { +struct ch_sched_class { u8 state; u8 idx; struct ch_sched_params info; @@ -82,7 +82,7 @@ struct sched_class { struct sched_table { /* per port scheduling table */ u8 sched_size; - struct sched_class tab[] __counted_by(sched_size); + struct ch_sched_class tab[] __counted_by(sched_size); }; static inline bool can_sched(struct net_device *dev) @@ -103,15 +103,15 @@ static inline bool valid_class_id(struct net_device *dev, u8 class_id) return true; } -struct sched_class *cxgb4_sched_queue_lookup(struct net_device *dev, - struct ch_sched_queue *p); +struct ch_sched_class *cxgb4_sched_queue_lookup(struct net_device *dev, + struct ch_sched_queue *p); int cxgb4_sched_class_bind(struct net_device *dev, void *arg, enum sched_bind_type type); int cxgb4_sched_class_unbind(struct net_device *dev, void *arg, enum sched_bind_type type); -struct sched_class *cxgb4_sched_class_alloc(struct net_device *dev, - struct ch_sched_params *p); +struct ch_sched_class *cxgb4_sched_class_alloc(struct net_device *dev, + struct ch_sched_params *p); void cxgb4_sched_class_free(struct net_device *dev, u8 classid); struct sched_table *t4_init_sched(unsigned int size); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 4036db466e18..ee19933e2cca 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -159,19 +159,13 @@ static u8 tcp_state_to_flowc_state(u8 state) int send_tx_flowc_wr(struct sock *sk, int compl, u32 snd_nxt, u32 rcv_nxt) { - struct flowc_packed { - struct fw_flowc_wr fc; - struct fw_flowc_mnemval mnemval[FW_FLOWC_MNEM_MAX]; - } __packed sflowc; + DEFINE_RAW_FLEX(struct fw_flowc_wr, flowc, mnemval, FW_FLOWC_MNEM_MAX); int nparams, paramidx, flowclen16, flowclen; - struct fw_flowc_wr *flowc; struct chtls_sock *csk; struct tcp_sock *tp; csk = rcu_dereference_sk_user_data(sk); tp = tcp_sk(sk); - memset(&sflowc, 0, sizeof(sflowc)); - flowc = &sflowc.fc; #define FLOWC_PARAM(__m, __v) \ do { \ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index cb004fd16252..5bb31c8fab39 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1296,7 +1296,8 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo) (adapter->bmc_filt_mask & BMC_FILT_MULTICAST) static bool be_send_pkt_to_bmc(struct be_adapter *adapter, - struct sk_buff **skb) + struct sk_buff **skb, + struct be_wrb_params *wrb_params) { struct ethhdr *eh = (struct ethhdr *)(*skb)->data; bool os2bmc = false; @@ -1360,7 +1361,7 @@ done: * to BMC, asic expects the vlan to be inline in the packet. */ if (os2bmc) - *skb = be_insert_vlan_in_pkt(adapter, *skb, NULL); + *skb = be_insert_vlan_in_pkt(adapter, *skb, wrb_params); return os2bmc; } @@ -1387,7 +1388,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) /* if os2bmc is enabled and if the pkt is destined to bmc, * enqueue the pkt a 2nd time with mgmt bit set. */ - if (be_send_pkt_to_bmc(adapter, &skb)) { + if (be_send_pkt_to_bmc(adapter, &skb, &wrb_params)) { BE_WRB_F_SET(wrb_params.features, OS2BMC, 1); wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params); if (unlikely(!wrb_cnt)) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index d09e456f14c0..ed3fa80af8c3 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -467,6 +467,47 @@ revert_values: return res; } +static void dpaa_get_pause_stats(struct net_device *net_dev, + struct ethtool_pause_stats *s) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; + + if (mac_dev->get_pause_stats) + mac_dev->get_pause_stats(mac_dev->fman_mac, s); +} + +static void dpaa_get_rmon_stats(struct net_device *net_dev, + struct ethtool_rmon_stats *s, + const struct ethtool_rmon_hist_range **ranges) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; + + if (mac_dev->get_rmon_stats) + mac_dev->get_rmon_stats(mac_dev->fman_mac, s, ranges); +} + +static void dpaa_get_eth_ctrl_stats(struct net_device *net_dev, + struct ethtool_eth_ctrl_stats *s) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; + + if (mac_dev->get_eth_ctrl_stats) + mac_dev->get_eth_ctrl_stats(mac_dev->fman_mac, s); +} + +static void dpaa_get_eth_mac_stats(struct net_device *net_dev, + struct ethtool_eth_mac_stats *s) +{ + struct dpaa_priv *priv = netdev_priv(net_dev); + struct mac_device *mac_dev = priv->mac_dev; + + if (mac_dev->get_eth_mac_stats) + mac_dev->get_eth_mac_stats(mac_dev->fman_mac, s); +} + const struct ethtool_ops dpaa_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_RX_MAX_FRAMES, @@ -487,4 +528,8 @@ const struct ethtool_ops dpaa_ethtool_ops = { .get_ts_info = dpaa_get_ts_info, .get_coalesce = dpaa_get_coalesce, .set_coalesce = dpaa_set_coalesce, + .get_pause_stats = dpaa_get_pause_stats, + .get_rmon_stats = dpaa_get_rmon_stats, + .get_eth_ctrl_stats = dpaa_get_eth_ctrl_stats, + .get_eth_mac_stats = dpaa_get_eth_mac_stats, }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h index ebea4298791c..3ed0f7a02767 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h @@ -170,6 +170,9 @@ /* Port MAC 0/1 Maximum Frame Length Register */ #define ENETC4_PM_MAXFRM(mac) (0x5014 + (mac) * 0x400) +/* Port internal MDIO base address, use to access PCS */ +#define ENETC4_PM_IMDIO_BASE 0x5030 + /* Port MAC 0/1 Pause Quanta Register */ #define ENETC4_PM_PAUSE_QUANTA(mac) (0x5054 + (mac) * 0x400) @@ -198,6 +201,9 @@ #define SSP_1G 2 #define PM_IF_MODE_ENA BIT(15) +/* Port external MDIO Base address, use to access off-chip PHY */ +#define ENETC4_EMDIO_BASE 0x5c00 + /**********************ENETC Pseudo MAC port registers************************/ /* Port pseudo MAC receive octets counter (64-bit) */ #define ENETC4_PPMROCR 0x5080 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c index 9c634205e2a7..76263b8566bb 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c @@ -176,7 +176,12 @@ static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) bus->parent = dev; mdio_priv = bus->priv; mdio_priv->hw = &pf->si->hw; - mdio_priv->mdio_base = ENETC_EMDIO_BASE; + + if (is_enetc_rev1(pf->si)) + mdio_priv->mdio_base = ENETC_EMDIO_BASE; + else + mdio_priv->mdio_base = ENETC4_EMDIO_BASE; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); err = of_mdiobus_register(bus, np); @@ -221,7 +226,12 @@ static int enetc_imdio_create(struct enetc_pf *pf) bus->phy_mask = ~0; mdio_priv = bus->priv; mdio_priv->hw = &pf->si->hw; - mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE; + + if (is_enetc_rev1(pf->si)) + mdio_priv->mdio_base = ENETC_PM_IMDIO_BASE; + else + mdio_priv->mdio_base = ENETC4_PM_IMDIO_BASE; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev)); err = mdiobus_register(bus); diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index d7aee3c934d3..443983fdecd9 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -67,6 +67,9 @@ #define IERB_EMDIOFAUXR 0x344 #define IERB_T0FAUXR 0x444 #define IERB_ETBCR(a) (0x300c + 0x100 * (a)) +#define IERB_LBCR(a) (0x1010 + 0x40 * (a)) +#define LBCR_MDIO_PHYAD_PRTAD(addr) (((addr) & 0x1f) << 8) + #define IERB_EFAUXR(a) (0x3044 + 0x100 * (a)) #define IERB_VFAUXR(a) (0x4004 + 0x40 * (a)) #define FAUXR_LDID GENMASK(3, 0) @@ -322,6 +325,142 @@ static int netc_unlock_ierb_with_warm_reset(struct netc_blk_ctrl *priv) 1000, 100000, true, priv->prb, PRB_NETCRR); } +static int netc_get_phy_addr(struct device_node *np) +{ + struct device_node *mdio_node, *phy_node; + u32 addr = 0; + int err = 0; + + mdio_node = of_get_child_by_name(np, "mdio"); + if (!mdio_node) + return 0; + + phy_node = of_get_next_child(mdio_node, NULL); + if (!phy_node) + goto of_put_mdio_node; + + err = of_property_read_u32(phy_node, "reg", &addr); + if (err) + goto of_put_phy_node; + + if (addr >= PHY_MAX_ADDR) + err = -EINVAL; + +of_put_phy_node: + of_node_put(phy_node); + +of_put_mdio_node: + of_node_put(mdio_node); + + return err ? err : addr; +} + +static int netc_parse_emdio_phy_mask(struct device_node *np, u32 *phy_mask) +{ + u32 mask = 0; + + for_each_child_of_node_scoped(np, child) { + u32 addr; + int err; + + err = of_property_read_u32(child, "reg", &addr); + if (err) + return err; + + if (addr >= PHY_MAX_ADDR) + return -EINVAL; + + mask |= BIT(addr); + } + + *phy_mask = mask; + + return 0; +} + +static int netc_get_emdio_phy_mask(struct device_node *np, u32 *phy_mask) +{ + for_each_child_of_node_scoped(np, child) { + for_each_child_of_node_scoped(child, gchild) { + if (!of_device_is_compatible(gchild, "pci1131,ee00")) + continue; + + return netc_parse_emdio_phy_mask(gchild, phy_mask); + } + } + + return 0; +} + +static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; + struct device *dev = &pdev->dev; + int bus_devfn, addr, err; + u32 phy_mask = 0; + + err = netc_get_emdio_phy_mask(np, &phy_mask); + if (err) { + dev_err(dev, "Failed to get PHY address mask\n"); + return err; + } + + /* Update the port EMDIO PHY address through parsing phy properties. + * This is needed when using the port EMDIO but it's harmless when + * using the central EMDIO. So apply it on all cases. + */ + for_each_child_of_node_scoped(np, child) { + for_each_child_of_node_scoped(child, gchild) { + if (!of_device_is_compatible(gchild, "pci1131,e101")) + continue; + + bus_devfn = netc_of_pci_get_bus_devfn(gchild); + if (bus_devfn < 0) { + dev_err(dev, "Failed to get BDF number\n"); + return bus_devfn; + } + + addr = netc_get_phy_addr(gchild); + if (addr < 0) { + dev_err(dev, "Failed to get PHY address\n"); + return addr; + } + + if (phy_mask & BIT(addr)) { + dev_err(dev, + "Find same PHY address in EMDIO and ENETC node\n"); + return -EINVAL; + } + + /* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is + * 0, so no need to set the register. + */ + if (!addr) + continue; + + switch (bus_devfn) { + case IMX95_ENETC0_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(0), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + case IMX95_ENETC1_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(1), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + case IMX95_ENETC2_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(2), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + default: + break; + } + } + } + + return 0; +} + static int imx95_ierb_init(struct platform_device *pdev) { struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); @@ -349,7 +488,7 @@ static int imx95_ierb_init(struct platform_device *pdev) /* NETC TIMER */ netc_reg_write(priv->ierb, IERB_T0FAUXR, 7); - return 0; + return imx95_enetc_mdio_phyaddr_config(pdev); } static int imx94_get_enetc_id(struct device_node *np) @@ -424,12 +563,64 @@ end: return 0; } +static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv, + struct device_node *np, + u32 phy_mask) +{ + struct device *dev = &priv->pdev->dev; + int bus_devfn, addr; + + bus_devfn = netc_of_pci_get_bus_devfn(np); + if (bus_devfn < 0) { + dev_err(dev, "Failed to get BDF number\n"); + return bus_devfn; + } + + addr = netc_get_phy_addr(np); + if (addr <= 0) { + dev_err(dev, "Failed to get PHY address\n"); + return addr; + } + + if (phy_mask & BIT(addr)) { + dev_err(dev, + "Find same PHY address in EMDIO and ENETC node\n"); + return -EINVAL; + } + + switch (bus_devfn) { + case IMX94_ENETC0_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC0_LINK), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + case IMX94_ENETC1_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC1_LINK), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + case IMX94_ENETC2_BUS_DEVFN: + netc_reg_write(priv->ierb, IERB_LBCR(IMX94_ENETC2_LINK), + LBCR_MDIO_PHYAD_PRTAD(addr)); + break; + default: + break; + } + + return 0; +} + static int imx94_ierb_init(struct platform_device *pdev) { struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); struct device_node *np = pdev->dev.of_node; + u32 phy_mask = 0; int err; + err = netc_get_emdio_phy_mask(np, &phy_mask); + if (err) { + dev_err(&pdev->dev, "Failed to get PHY address mask\n"); + return err; + } + for_each_child_of_node_scoped(np, child) { for_each_child_of_node_scoped(child, gchild) { if (!of_device_is_compatible(gchild, "pci1131,e101")) @@ -438,6 +629,11 @@ static int imx94_ierb_init(struct platform_device *pdev) err = imx94_enetc_update_tid(priv, gchild); if (err) return err; + + err = imx94_enetc_mdio_phyaddr_config(priv, gchild, + phy_mask); + if (err) + return err; } } diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 41e0d85d15da..fd9a93d02f8e 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -24,9 +24,7 @@ #include <linux/timecounter.h> #include <net/xdp.h> -#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ - defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST) /* * Just figures, Motorola would have to change the offsets for * registers in the same peripheral device on different models @@ -242,23 +240,6 @@ struct bufdesc_ex { __fec16 res0[4]; }; -/* - * The following definitions courtesy of commproc.h, which where - * Copyright (c) 1997 Dan Malek (dmalek@jlc.net). - */ -#define BD_SC_EMPTY ((ushort)0x8000) /* Receive is empty */ -#define BD_SC_READY ((ushort)0x8000) /* Transmit is ready */ -#define BD_SC_WRAP ((ushort)0x2000) /* Last buffer descriptor */ -#define BD_SC_INTRPT ((ushort)0x1000) /* Interrupt on change */ -#define BD_SC_CM ((ushort)0x0200) /* Continuous mode */ -#define BD_SC_ID ((ushort)0x0100) /* Rec'd too many idles */ -#define BD_SC_P ((ushort)0x0100) /* xmt preamble */ -#define BD_SC_BR ((ushort)0x0020) /* Break received */ -#define BD_SC_FR ((ushort)0x0010) /* Framing error */ -#define BD_SC_PR ((ushort)0x0008) /* Parity error */ -#define BD_SC_OV ((ushort)0x0002) /* Overrun */ -#define BD_SC_CD ((ushort)0x0001) /* ?? */ - /* Buffer descriptor control/status used by Ethernet receive. */ #define BD_ENET_RX_EMPTY ((ushort)0x8000) @@ -530,12 +511,6 @@ struct bufdesc_prop { unsigned char dsize_log2; }; -struct fec_enet_priv_txrx_info { - int offset; - struct page *page; - struct sk_buff *skb; -}; - enum { RX_XDP_REDIRECT = 0, RX_XDP_PASS, @@ -575,7 +550,7 @@ struct fec_enet_priv_tx_q { struct fec_enet_priv_rx_q { struct bufdesc_prop bd; - struct fec_enet_priv_txrx_info rx_skb_info[RX_RING_SIZE]; + struct page *rx_buf[RX_RING_SIZE]; /* page_pool */ struct page_pool *page_pool; @@ -668,7 +643,6 @@ struct fec_enet_private { struct pm_qos_request pm_qos_req; unsigned int tx_align; - unsigned int rx_align; /* hw interrupt coalesce */ unsigned int rx_pkts_itr; @@ -687,6 +661,7 @@ struct fec_enet_private { unsigned int reload_period; int pps_enable; unsigned int next_counter; + bool perout_enable; struct hrtimer perout_timer; u64 perout_stime; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index b6fbb84cfb06..c685a5c0cc51 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -253,9 +253,7 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); * size bits. Other FEC hardware does not, so we need to take that into * account when setting it. */ -#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ - defined(CONFIG_ARM64) +#ifndef CONFIG_M5272 #define OPT_ARCH_HAS_MAX_FL 1 #else #define OPT_ARCH_HAS_MAX_FL 0 @@ -1012,7 +1010,7 @@ static void fec_enet_bd_init(struct net_device *dev) /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, &rxq->bd); - bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); + bdp->cbd_sc |= cpu_to_fec16(BD_ENET_RX_WRAP); rxq->bd.cur = rxq->bd.base; } @@ -1062,7 +1060,7 @@ static void fec_enet_bd_init(struct net_device *dev) /* Set the last buffer to wrap */ bdp = fec_enet_get_prevdesc(bdp, &txq->bd); - bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); + bdp->cbd_sc |= cpu_to_fec16(BD_ENET_TX_WRAP); txq->dirty_tx = bdp; } } @@ -1657,8 +1655,7 @@ static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, if (unlikely(!new_page)) return -ENOMEM; - rxq->rx_skb_info[index].page = new_page; - rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM; + rxq->rx_buf[index] = new_page; phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM; bdp->cbd_bufaddr = cpu_to_fec32(phys_addr); @@ -1773,7 +1770,6 @@ fec_enet_rx_queue(struct net_device *ndev, u16 queue_id, int budget) __fec32 cbd_bufaddr; u32 sub_len = 4; -#if !defined(CONFIG_M5272) /*If it has the FEC_QUIRK_HAS_RACC quirk property, the bit of * FEC_RACC_SHIFT16 is set by default in the probe function. */ @@ -1781,7 +1777,6 @@ fec_enet_rx_queue(struct net_device *ndev, u16 queue_id, int budget) data_start += 2; sub_len += 2; } -#endif #if defined(CONFIG_COLDFIRE) && !defined(CONFIG_COLDFIRE_COHERENT_DMA) /* @@ -1840,7 +1835,7 @@ fec_enet_rx_queue(struct net_device *ndev, u16 queue_id, int budget) ndev->stats.rx_bytes -= 2; index = fec_enet_get_bd_index(bdp, &rxq->bd); - page = rxq->rx_skb_info[index].page; + page = rxq->rx_buf[index]; cbd_bufaddr = bdp->cbd_bufaddr; if (fec_enet_update_cbd(rxq, bdp, index)) { ndev->stats.rx_dropped++; @@ -2517,9 +2512,7 @@ static int fec_enet_mii_probe(struct net_device *ndev) phy_set_max_speed(phy_dev, 1000); phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); -#if !defined(CONFIG_M5272) phy_support_sym_pause(phy_dev); -#endif } else phy_set_max_speed(phy_dev, 100); @@ -2710,9 +2703,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) } /* List of registers that can be safety be read to dump them with ethtool */ -#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ - defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST) static __u32 fec_enet_register_version = 2; static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, @@ -2786,30 +2777,22 @@ static u32 fec_enet_register_offset[] = { static void fec_enet_get_regs(struct net_device *ndev, struct ethtool_regs *regs, void *regbuf) { + u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset); struct fec_enet_private *fep = netdev_priv(ndev); u32 __iomem *theregs = (u32 __iomem *)fep->hwp; + u32 *reg_list = fec_enet_register_offset; struct device *dev = &fep->pdev->dev; u32 *buf = (u32 *)regbuf; u32 i, off; int ret; -#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ - defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ - defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) - u32 *reg_list; - u32 reg_cnt; - - if (!of_machine_is_compatible("fsl,imx6ul")) { - reg_list = fec_enet_register_offset; - reg_cnt = ARRAY_SIZE(fec_enet_register_offset); - } else { + +#if !defined(CONFIG_M5272) || defined(CONFIG_COMPILE_TEST) + if (of_machine_is_compatible("fsl,imx6ul")) { reg_list = fec_enet_register_offset_6ul; reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul); } -#else - /* coldfire */ - static u32 *reg_list = fec_enet_register_offset; - static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset); #endif + ret = pm_runtime_resume_and_get(dev); if (ret < 0) return; @@ -3328,7 +3311,8 @@ static void fec_enet_free_buffers(struct net_device *ndev) for (q = 0; q < fep->num_rx_queues; q++) { rxq = fep->rx_queue[q]; for (i = 0; i < rxq->bd.ring_size; i++) - page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false); + page_pool_put_full_page(rxq->page_pool, rxq->rx_buf[i], + false); for (i = 0; i < XDP_STATS_TOTAL; i++) rxq->stats[i] = 0; @@ -3454,6 +3438,19 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) return err; } + /* Some platforms require the RX buffer must be 64 bytes alignment. + * Some platforms require 16 bytes alignment. And some platforms + * require 4 bytes alignment. But since the page pool have been + * introduced into the driver, the address of RX buffer is always + * the page address plus FEC_ENET_XDP_HEADROOM, and + * FEC_ENET_XDP_HEADROOM is 256 bytes. Therefore, this address can + * satisfy all platforms. To prevent future modifications to + * FEC_ENET_XDP_HEADROOM from ignoring this hardware limitation, a + * BUILD_BUG_ON() test has been added, which ensures that + * FEC_ENET_XDP_HEADROOM provides the required alignment. + */ + BUILD_BUG_ON(FEC_ENET_XDP_HEADROOM & 0x3f); + for (i = 0; i < rxq->bd.ring_size; i++) { page = page_pool_dev_alloc_pages(rxq->page_pool); if (!page) @@ -3462,8 +3459,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) phys_addr = page_pool_get_dma_addr(page) + FEC_ENET_XDP_HEADROOM; bdp->cbd_bufaddr = cpu_to_fec32(phys_addr); - rxq->rx_skb_info[i].page = page; - rxq->rx_skb_info[i].offset = FEC_ENET_XDP_HEADROOM; + rxq->rx_buf[i] = page; bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY); if (fep->bufdesc_ex) { @@ -3476,7 +3472,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, &rxq->bd); - bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); + bdp->cbd_sc |= cpu_to_fec16(BD_ENET_RX_WRAP); return 0; err_alloc: @@ -3512,7 +3508,7 @@ fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue) /* Set the last buffer to wrap. */ bdp = fec_enet_get_prevdesc(bdp, &txq->bd); - bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP); + bdp->cbd_sc |= cpu_to_fec16(BD_ENET_TX_WRAP); return 0; @@ -4089,10 +4085,8 @@ static int fec_enet_init(struct net_device *ndev) WARN_ON(dsize != (1 << dsize_log2)); #if defined(CONFIG_ARM) || defined(CONFIG_ARM64) - fep->rx_align = 0xf; fep->tx_align = 0xf; #else - fep->rx_align = 0x3; fep->tx_align = 0x3; #endif fep->rx_pkts_itr = FEC_ITR_ICFT_DEFAULT; @@ -4181,10 +4175,8 @@ static int fec_enet_init(struct net_device *ndev) fep->csum_flags |= FLAG_RX_CSUM_ENABLED; } - if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) { + if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) fep->tx_align = 0; - fep->rx_align = 0x3f; - } ndev->hw_features = ndev->features; @@ -4402,11 +4394,9 @@ fec_probe(struct platform_device *pdev) fep->num_rx_queues = num_rx_qs; fep->num_tx_queues = num_tx_qs; -#if !defined(CONFIG_M5272) /* default enable pause frame auto negotiation */ if (fep->quirks & FEC_QUIRK_HAS_GBIT) fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG; -#endif /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index fa88b47d526c..4b7bad9a485d 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -128,6 +128,12 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) spin_lock_irqsave(&fep->tmreg_lock, flags); + if (fep->perout_enable) { + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + dev_err(&fep->pdev->dev, "PEROUT is running"); + return -EBUSY; + } + if (fep->pps_enable == enable) { spin_unlock_irqrestore(&fep->tmreg_lock, flags); return 0; @@ -243,6 +249,7 @@ static int fec_ptp_pps_perout(struct fec_enet_private *fep) * the FEC_TCCR register in time and missed the start time. */ if (fep->perout_stime < curr_time + 100 * NSEC_PER_MSEC) { + fep->perout_enable = false; dev_err(&fep->pdev->dev, "Current time is too close to the start time!\n"); spin_unlock_irqrestore(&fep->tmreg_lock, flags); return -1; @@ -497,7 +504,10 @@ static int fec_ptp_pps_disable(struct fec_enet_private *fep, uint channel) { unsigned long flags; + hrtimer_cancel(&fep->perout_timer); + spin_lock_irqsave(&fep->tmreg_lock, flags); + fep->perout_enable = false; writel(0, fep->hwp + FEC_TCSR(channel)); spin_unlock_irqrestore(&fep->tmreg_lock, flags); @@ -529,6 +539,8 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, return ret; } else if (rq->type == PTP_CLK_REQ_PEROUT) { + u32 reload_period; + /* Reject requests with unsupported flags */ if (rq->perout.flags) return -EOPNOTSUPP; @@ -548,12 +560,14 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } - fep->reload_period = div_u64(period_ns, 2); - if (on && fep->reload_period) { + reload_period = div_u64(period_ns, 2); + if (on && reload_period) { + u64 perout_stime; + /* Convert 1588 timestamp to ns*/ start_time.tv_sec = rq->perout.start.sec; start_time.tv_nsec = rq->perout.start.nsec; - fep->perout_stime = timespec64_to_ns(&start_time); + perout_stime = timespec64_to_ns(&start_time); mutex_lock(&fep->ptp_clk_mutex); if (!fep->ptp_clk_on) { @@ -562,18 +576,41 @@ static int fec_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } spin_lock_irqsave(&fep->tmreg_lock, flags); + + if (fep->pps_enable) { + dev_err(&fep->pdev->dev, "PPS is running"); + ret = -EBUSY; + goto unlock; + } + + if (fep->perout_enable) { + dev_err(&fep->pdev->dev, + "PEROUT has been enabled\n"); + ret = -EBUSY; + goto unlock; + } + /* Read current timestamp */ curr_time = timecounter_read(&fep->tc); - spin_unlock_irqrestore(&fep->tmreg_lock, flags); - mutex_unlock(&fep->ptp_clk_mutex); + if (perout_stime <= curr_time) { + dev_err(&fep->pdev->dev, + "Start time must be greater than current time\n"); + ret = -EINVAL; + goto unlock; + } /* Calculate time difference */ - delta = fep->perout_stime - curr_time; + delta = perout_stime - curr_time; + fep->reload_period = reload_period; + fep->perout_stime = perout_stime; + fep->perout_enable = true; - if (fep->perout_stime <= curr_time) { - dev_err(&fep->pdev->dev, "Start time must larger than current time!\n"); - return -EINVAL; - } +unlock: + spin_unlock_irqrestore(&fep->tmreg_lock, flags); + mutex_unlock(&fep->ptp_clk_mutex); + + if (ret) + return ret; /* Because the timer counter of FEC only has 31-bits, correspondingly, * the time comparison register FEC_TCCR also only low 31 bits can be @@ -681,8 +718,11 @@ static irqreturn_t fec_pps_interrupt(int irq, void *dev_id) fep->next_counter = (fep->next_counter + fep->reload_period) & fep->cc.mask; - event.type = PTP_CLOCK_PPS; - ptp_clock_event(fep->ptp_clock, &event); + if (fep->pps_enable) { + event.type = PTP_CLOCK_PPS; + ptp_clock_event(fep->ptp_clock, &event); + } + return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 0291093f2e4e..c84f0336c94c 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -649,6 +649,7 @@ static u32 memac_if_mode(phy_interface_t interface) return IF_MODE_GMII | IF_MODE_RGMII; case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: case PHY_INTERFACE_MODE_QSGMII: return IF_MODE_GMII; case PHY_INTERFACE_MODE_10GBASER: @@ -667,6 +668,7 @@ static struct phylink_pcs *memac_select_pcs(struct phylink_config *config, switch (iface) { case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: return memac->sgmii_pcs; case PHY_INTERFACE_MODE_QSGMII: return memac->qsgmii_pcs; @@ -685,6 +687,7 @@ static int memac_prepare(struct phylink_config *config, unsigned int mode, switch (iface) { case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_10GBASER: return phy_set_mode_ext(memac->serdes, PHY_MODE_ETHERNET, @@ -897,6 +900,89 @@ static int memac_set_exception(struct fman_mac *memac, return 0; } +static u64 memac_read64(void __iomem *reg) +{ + u32 low, high, tmp; + + do { + high = ioread32be(reg + 4); + low = ioread32be(reg); + tmp = ioread32be(reg + 4); + } while (high != tmp); + + return ((u64)high << 32) | low; +} + +static void memac_get_pause_stats(struct fman_mac *memac, + struct ethtool_pause_stats *s) +{ + s->tx_pause_frames = memac_read64(&memac->regs->txpf_l); + s->rx_pause_frames = memac_read64(&memac->regs->rxpf_l); +} + +static const struct ethtool_rmon_hist_range memac_rmon_ranges[] = { + { 64, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, 9600 }, + {}, +}; + +static void memac_get_rmon_stats(struct fman_mac *memac, + struct ethtool_rmon_stats *s, + const struct ethtool_rmon_hist_range **ranges) +{ + s->undersize_pkts = memac_read64(&memac->regs->rund_l); + s->oversize_pkts = memac_read64(&memac->regs->rovr_l); + s->fragments = memac_read64(&memac->regs->rfrg_l); + s->jabbers = memac_read64(&memac->regs->rjbr_l); + + s->hist[0] = memac_read64(&memac->regs->r64_l); + s->hist[1] = memac_read64(&memac->regs->r127_l); + s->hist[2] = memac_read64(&memac->regs->r255_l); + s->hist[3] = memac_read64(&memac->regs->r511_l); + s->hist[4] = memac_read64(&memac->regs->r1023_l); + s->hist[5] = memac_read64(&memac->regs->r1518_l); + s->hist[6] = memac_read64(&memac->regs->r1519x_l); + + s->hist_tx[0] = memac_read64(&memac->regs->t64_l); + s->hist_tx[1] = memac_read64(&memac->regs->t127_l); + s->hist_tx[2] = memac_read64(&memac->regs->t255_l); + s->hist_tx[3] = memac_read64(&memac->regs->t511_l); + s->hist_tx[4] = memac_read64(&memac->regs->t1023_l); + s->hist_tx[5] = memac_read64(&memac->regs->t1518_l); + s->hist_tx[6] = memac_read64(&memac->regs->t1519x_l); + + *ranges = memac_rmon_ranges; +} + +static void memac_get_eth_ctrl_stats(struct fman_mac *memac, + struct ethtool_eth_ctrl_stats *s) +{ + s->MACControlFramesTransmitted = memac_read64(&memac->regs->tcnp_l); + s->MACControlFramesReceived = memac_read64(&memac->regs->rcnp_l); +} + +static void memac_get_eth_mac_stats(struct fman_mac *memac, + struct ethtool_eth_mac_stats *s) +{ + s->FramesTransmittedOK = memac_read64(&memac->regs->tfrm_l); + s->FramesReceivedOK = memac_read64(&memac->regs->rfrm_l); + s->FrameCheckSequenceErrors = memac_read64(&memac->regs->rfcs_l); + s->AlignmentErrors = memac_read64(&memac->regs->raln_l); + s->OctetsTransmittedOK = memac_read64(&memac->regs->teoct_l); + s->FramesLostDueToIntMACXmitError = memac_read64(&memac->regs->terr_l); + s->OctetsReceivedOK = memac_read64(&memac->regs->reoct_l); + s->FramesLostDueToIntMACRcvError = memac_read64(&memac->regs->rdrntp_l); + s->MulticastFramesXmittedOK = memac_read64(&memac->regs->tmca_l); + s->BroadcastFramesXmittedOK = memac_read64(&memac->regs->tbca_l); + s->MulticastFramesReceivedOK = memac_read64(&memac->regs->rmca_l); + s->BroadcastFramesReceivedOK = memac_read64(&memac->regs->rbca_l); +} + static int memac_init(struct fman_mac *memac) { struct memac_cfg *memac_drv_param; @@ -1089,6 +1175,10 @@ int memac_initialization(struct mac_device *mac_dev, mac_dev->set_tstamp = memac_set_tstamp; mac_dev->enable = memac_enable; mac_dev->disable = memac_disable; + mac_dev->get_pause_stats = memac_get_pause_stats; + mac_dev->get_rmon_stats = memac_get_rmon_stats; + mac_dev->get_eth_ctrl_stats = memac_get_eth_ctrl_stats; + mac_dev->get_eth_mac_stats = memac_get_eth_mac_stats; mac_dev->fman_mac = memac_config(mac_dev, params); if (!mac_dev->fman_mac) @@ -1226,6 +1316,7 @@ int memac_initialization(struct mac_device *mac_dev, * those configurations modes don't use in-band autonegotiation. */ if (!of_property_present(mac_node, "managed") && + mac_dev->phy_if != PHY_INTERFACE_MODE_2500BASEX && mac_dev->phy_if != PHY_INTERFACE_MODE_MII && !phy_interface_mode_is_rgmii(mac_dev->phy_if)) mac_dev->phylink_config.default_an_inband = true; diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 955ace338965..63c2c5b4f99e 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -16,6 +16,11 @@ #include "fman.h" #include "fman_mac.h" +struct ethtool_eth_ctrl_stats; +struct ethtool_eth_mac_stats; +struct ethtool_pause_stats; +struct ethtool_rmon_stats; +struct ethtool_rmon_hist_range; struct fman_mac; struct mac_priv_s; @@ -46,6 +51,15 @@ struct mac_device { enet_addr_t *eth_addr); int (*remove_hash_mac_addr)(struct fman_mac *mac_dev, enet_addr_t *eth_addr); + void (*get_pause_stats)(struct fman_mac *memac, + struct ethtool_pause_stats *s); + void (*get_rmon_stats)(struct fman_mac *memac, + struct ethtool_rmon_stats *s, + const struct ethtool_rmon_hist_range **ranges); + void (*get_eth_ctrl_stats)(struct fman_mac *memac, + struct ethtool_eth_ctrl_stats *s); + void (*get_eth_mac_stats)(struct fman_mac *memac, + struct ethtool_eth_mac_stats *s); void (*update_speed)(struct mac_device *mac_dev, int speed); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index a33b44c1eb86..970d5ca8cdde 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -205,6 +205,13 @@ struct gve_rx_buf_state_dqo { s16 next; }; +/* Wrapper for XDP Rx metadata */ +struct gve_xdp_buff { + struct xdp_buff xdp; + struct gve_priv *gve; + const struct gve_rx_compl_desc_dqo *compl_desc; +}; + /* `head` and `tail` are indices into an array, or -1 if empty. */ struct gve_index_list { s16 head; diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h index 6eb442096e02..5871f773f0c7 100644 --- a/drivers/net/ethernet/google/gve/gve_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -36,6 +36,7 @@ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev); netdev_features_t gve_features_check_dqo(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); +int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp); bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean); bool gve_xdp_poll_dqo(struct gve_notify_block *block); bool gve_xsk_tx_poll_dqo(struct gve_notify_block *block, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 6fb8fbb38a7d..a5a2b18d309b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -2188,10 +2188,6 @@ static int gve_set_ts_config(struct net_device *dev, } kernel_config->rx_filter = HWTSTAMP_FILTER_ALL; - gve_clock_nic_ts_read(priv); - ptp_schedule_worker(priv->ptp->clock, 0); - } else { - ptp_cancel_worker_sync(priv->ptp->clock); } priv->ts_config.rx_filter = kernel_config->rx_filter; @@ -2352,6 +2348,10 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) xdp_set_features_flag_locked(priv->dev, xdp_features); } +static const struct xdp_metadata_ops gve_xdp_metadata_ops = { + .xmo_rx_timestamp = gve_xdp_rx_timestamp, +}; + static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) { int num_ntfy; @@ -2447,6 +2447,9 @@ setup_device: } gve_set_netdev_xdp_features(priv); + if (!gve_is_gqi(priv)) + priv->dev->xdp_metadata_ops = &gve_xdp_metadata_ops; + err = gve_setup_device_resources(priv); if (err) goto err_free_xsk_bitmap; diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c index a384a9ed4914..073677d82ee8 100644 --- a/drivers/net/ethernet/google/gve/gve_ptp.c +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -133,9 +133,21 @@ int gve_init_clock(struct gve_priv *priv) err = -ENOMEM; goto release_ptp; } + err = gve_clock_nic_ts_read(priv); + if (err) { + dev_err(&priv->pdev->dev, "failed to read NIC clock %d\n", err); + goto release_nic_ts_report; + } + ptp_schedule_worker(priv->ptp->clock, + msecs_to_jiffies(GVE_NIC_TS_SYNC_INTERVAL_MS)); return 0; +release_nic_ts_report: + dma_free_coherent(&priv->pdev->dev, + sizeof(struct gve_nic_ts_report), + priv->nic_ts_report, priv->nic_ts_report_bus); + priv->nic_ts_report = NULL; release_ptp: gve_ptp_release(priv); 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 1aff3bbb8cfc..f1bd8f5d5732 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -240,6 +240,11 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv, rx->rx_headroom = 0; } + /* struct gve_xdp_buff is overlaid on struct xdp_buff_xsk and utilizes + * the 24 byte field cb to store gve specific data. + */ + XSK_CHECK_PRIV_TYPE(struct gve_xdp_buff); + rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots : gve_get_rx_pages_per_qpl_dqo(cfg->ring_size); rx->dqo.buf_states = kvcalloc_node(rx->dqo.num_buf_states, @@ -456,20 +461,38 @@ static void gve_rx_skb_hash(struct sk_buff *skb, * Note that this means if the time delta between packet reception and the last * clock read is greater than ~2 seconds, this will provide invalid results. */ +static ktime_t gve_rx_get_hwtstamp(struct gve_priv *gve, u32 hwts) +{ + u64 last_read = READ_ONCE(gve->last_sync_nic_counter); + u32 low = (u32)last_read; + s32 diff = hwts - low; + + return ns_to_ktime(last_read + diff); +} + static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx, const struct gve_rx_compl_desc_dqo *desc) { - u64 last_read = READ_ONCE(rx->gve->last_sync_nic_counter); struct sk_buff *skb = rx->ctx.skb_head; - u32 ts, low; - s32 diff; - - if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID) { - ts = le32_to_cpu(desc->ts); - low = (u32)last_read; - diff = ts - low; - skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(last_read + diff); - } + + if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID) + skb_hwtstamps(skb)->hwtstamp = + gve_rx_get_hwtstamp(rx->gve, le32_to_cpu(desc->ts)); +} + +int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) +{ + const struct gve_xdp_buff *ctx = (void *)_ctx; + + if (!ctx->gve->nic_ts_report) + return -ENODATA; + + if (!(ctx->compl_desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID)) + return -ENODATA; + + *timestamp = gve_rx_get_hwtstamp(ctx->gve, + le32_to_cpu(ctx->compl_desc->ts)); + return 0; } static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx) @@ -683,16 +706,23 @@ err: } static int gve_rx_xsk_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, - struct gve_rx_buf_state_dqo *buf_state, int buf_len, + const struct gve_rx_compl_desc_dqo *compl_desc, + struct gve_rx_buf_state_dqo *buf_state, struct bpf_prog *xprog) { struct xdp_buff *xdp = buf_state->xsk_buff; + int buf_len = compl_desc->packet_len; struct gve_priv *priv = rx->gve; + struct gve_xdp_buff *gve_xdp; int xdp_act; xdp->data_end = xdp->data + buf_len; xsk_buff_dma_sync_for_cpu(xdp); + gve_xdp = (void *)xdp; + gve_xdp->gve = priv; + gve_xdp->compl_desc = compl_desc; + if (xprog) { xdp_act = bpf_prog_run_xdp(xprog, xdp); buf_len = xdp->data_end - xdp->data; @@ -782,7 +812,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, xprog = READ_ONCE(priv->xdp_prog); if (buf_state->xsk_buff) - return gve_rx_xsk_dqo(napi, rx, buf_state, buf_len, xprog); + return gve_rx_xsk_dqo(napi, rx, compl_desc, buf_state, xprog); /* Page might have not been used for awhile and was likely last written * by a different thread. @@ -840,23 +870,26 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, } if (xprog) { - struct xdp_buff xdp; + struct gve_xdp_buff gve_xdp; void *old_data; int xdp_act; - xdp_init_buff(&xdp, buf_state->page_info.buf_size, + xdp_init_buff(&gve_xdp.xdp, buf_state->page_info.buf_size, &rx->xdp_rxq); - xdp_prepare_buff(&xdp, + xdp_prepare_buff(&gve_xdp.xdp, buf_state->page_info.page_address + buf_state->page_info.page_offset, buf_state->page_info.pad, buf_len, false); - old_data = xdp.data; - xdp_act = bpf_prog_run_xdp(xprog, &xdp); - buf_state->page_info.pad += xdp.data - old_data; - buf_len = xdp.data_end - xdp.data; + gve_xdp.gve = priv; + gve_xdp.compl_desc = compl_desc; + + old_data = gve_xdp.xdp.data; + xdp_act = bpf_prog_run_xdp(xprog, &gve_xdp.xdp); + buf_state->page_info.pad += gve_xdp.xdp.data - old_data; + buf_len = gve_xdp.xdp.data_end - gve_xdp.xdp.data; if (xdp_act != XDP_PASS) { - gve_xdp_done_dqo(priv, rx, &xdp, xprog, xdp_act, + gve_xdp_done_dqo(priv, rx, &gve_xdp.xdp, xprog, xdp_act, buf_state); return 0; } diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index c6ff0968929d..97efc8d27e6f 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -730,7 +730,9 @@ unmap_drop: gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]); } drop: + u64_stats_update_begin(&tx->statss); tx->dropped_pkt++; + u64_stats_update_end(&tx->statss); return 0; } diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index 6f1d515673d2..40b89b3e5a31 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -1002,7 +1002,9 @@ static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx, return 0; drop: + u64_stats_update_begin(&tx->statss); tx->dropped_pkt++; + u64_stats_update_end(&tx->statss); dev_kfree_skb_any(skb); return 0; } @@ -1324,7 +1326,11 @@ static void remove_miss_completions(struct gve_priv *priv, /* This indicates the packet was dropped. */ dev_kfree_skb_any(pending_packet->skb); pending_packet->skb = NULL; + + u64_stats_update_begin(&tx->statss); tx->dropped_pkt++; + u64_stats_update_end(&tx->statss); + net_err_ratelimited("%s: No reinjection completion was received for: %d.\n", priv->dev->name, (int)(pending_packet - tx->dqo.pending_packets)); diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 38875c196cb6..18eca7d12c20 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -151,6 +151,7 @@ config HIBMCGE select FIXED_PHY select MOTORCOMM_PHY select REALTEK_PHY + select PAGE_POOL help If you wish to compile a kernel for a BMC with HIBMC-xx_gmac then you should answer Y to this. This makes this driver suitable for use diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile index 1a9da564b306..d6610ba16855 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile +++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile @@ -3,6 +3,7 @@ # Makefile for the HISILICON BMC GE network device drivers. # +ccflags-y += -I$(src) obj-$(CONFIG_HIBMCGE) += hibmcge.o hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \ diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h index 2097e4c2b3d7..8e134da3e217 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h @@ -7,6 +7,7 @@ #include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/pci.h> +#include <net/page_pool/helpers.h> #include "hbg_reg.h" #define HBG_STATUS_DISABLE 0x0 @@ -55,6 +56,12 @@ struct hbg_buffer { dma_addr_t skb_dma; u32 skb_len; + struct page *page; + void *page_addr; + dma_addr_t page_dma; + u32 page_size; + u32 page_offset; + enum hbg_dir dir; struct hbg_ring *ring; struct hbg_priv *priv; @@ -78,6 +85,7 @@ struct hbg_ring { struct hbg_priv *priv; struct napi_struct napi; char *tout_log_buf; /* tx timeout log buffer */ + struct page_pool *page_pool; /* only for rx */ }; enum hbg_hw_event_type { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h index a39d1e796e4a..30b3903c8f2d 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h @@ -252,6 +252,8 @@ struct hbg_rx_desc { #define HBG_RX_DESC_W2_PKT_LEN_M GENMASK(31, 16) #define HBG_RX_DESC_W2_PORT_NUM_M GENMASK(15, 12) +#define HBG_RX_DESC_W3_IP_OFFSET_M GENMASK(23, 16) +#define HBG_RX_DESC_W3_VLAN_M GENMASK(15, 0) #define HBG_RX_DESC_W4_IP_TCP_UDP_M GENMASK(31, 30) #define HBG_RX_DESC_W4_IPSEC_B BIT(29) #define HBG_RX_DESC_W4_IP_VERSION_B BIT(28) @@ -269,6 +271,8 @@ struct hbg_rx_desc { #define HBG_RX_DESC_W4_L3_ERR_CODE_M GENMASK(12, 9) #define HBG_RX_DESC_W4_L2_ERR_B BIT(8) #define HBG_RX_DESC_W4_IDX_MATCH_B BIT(7) +#define HBG_RX_DESC_W4_PARSE_MODE_M GENMASK(6, 5) +#define HBG_RX_DESC_W5_VALID_SIZE_M GENMASK(15, 0) enum hbg_l3_err_code { HBG_L3_OK = 0, diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h new file mode 100644 index 000000000000..b70fd960da8d --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2025 Hisilicon Limited. */ + +/* This must be outside ifdef _HBG_TRACE_H */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hibmcge + +#if !defined(_HBG_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _HBG_TRACE_H_ + +#include <linux/bitfield.h> +#include <linux/pci.h> +#include <linux/tracepoint.h> +#include <linux/types.h> +#include "hbg_reg.h" + +TRACE_EVENT(hbg_rx_desc, + TP_PROTO(struct hbg_priv *priv, u32 index, + struct hbg_rx_desc *rx_desc), + TP_ARGS(priv, index, rx_desc), + + TP_STRUCT__entry(__field(u32, index) + __field(u8, port_num) + __field(u8, ip_offset) + __field(u8, parse_mode) + __field(u8, l4_error_code) + __field(u8, l3_error_code) + __field(u8, l2_error_code) + __field(u16, packet_len) + __field(u16, valid_size) + __field(u16, vlan) + __string(pciname, pci_name(priv->pdev)) + __string(devname, priv->netdev->name) + ), + + TP_fast_assign(__entry->index = index, + __entry->packet_len = + FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, + rx_desc->word2); + __entry->port_num = + FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M, + rx_desc->word2); + __entry->ip_offset = + FIELD_GET(HBG_RX_DESC_W3_IP_OFFSET_M, + rx_desc->word3); + __entry->vlan = + FIELD_GET(HBG_RX_DESC_W3_VLAN_M, + rx_desc->word3); + __entry->parse_mode = + FIELD_GET(HBG_RX_DESC_W4_PARSE_MODE_M, + rx_desc->word4); + __entry->l4_error_code = + FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, + rx_desc->word4); + __entry->l3_error_code = + FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, + rx_desc->word4); + __entry->l2_error_code = + FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B, + rx_desc->word4); + __entry->valid_size = + FIELD_GET(HBG_RX_DESC_W5_VALID_SIZE_M, + rx_desc->word5); + __assign_str(pciname); + __assign_str(devname); + ), + + TP_printk("%s %s index:%u, port num:%u, len:%u, valid size:%u, ip_offset:%u, vlan:0x%04x, parse mode:%u, l4_err:0x%x, l3_err:0x%x, l2_err:0x%x", + __get_str(pciname), __get_str(devname), __entry->index, + __entry->port_num, __entry->packet_len, + __entry->valid_size, __entry->ip_offset, __entry->vlan, + __entry->parse_mode, __entry->l4_error_code, + __entry->l3_error_code, __entry->l2_error_code + ) +); + +#endif /* _HBG_TRACE_H_ */ + +/* This must be outside ifdef _HBG_TRACE_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hbg_trace +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c index 8d814c8f19ea..a4ea92c31c2f 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c @@ -7,6 +7,9 @@ #include "hbg_reg.h" #include "hbg_txrx.h" +#define CREATE_TRACE_POINTS +#include "hbg_trace.h" + #define netdev_get_tx_ring(netdev) \ (&(((struct hbg_priv *)netdev_priv(netdev))->tx_ring)) @@ -28,6 +31,11 @@ typeof(ring) _ring = (ring); \ _ring->p = hbg_queue_next_prt(_ring->p, _ring); }) +#define hbg_get_page_order(ring) ({ \ + typeof(ring) _ring = (ring); \ + get_order(hbg_spec_max_frame_len(_ring->priv, _ring->dir)); }) +#define hbg_get_page_size(ring) (PAGE_SIZE << hbg_get_page_order((ring))) + #define HBG_TX_STOP_THRS 2 #define HBG_TX_START_THRS (2 * HBG_TX_STOP_THRS) @@ -62,6 +70,43 @@ static void hbg_dma_unmap(struct hbg_buffer *buffer) buffer->skb_dma = 0; } +static void hbg_buffer_free_page(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + + if (unlikely(!buffer->page)) + return; + + page_pool_put_full_page(ring->page_pool, buffer->page, false); + + buffer->page = NULL; + buffer->page_dma = 0; + buffer->page_addr = NULL; + buffer->page_size = 0; + buffer->page_offset = 0; +} + +static int hbg_buffer_alloc_page(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + u32 len = hbg_get_page_size(ring); + u32 offset; + + if (unlikely(!ring->page_pool)) + return 0; + + buffer->page = page_pool_dev_alloc_frag(ring->page_pool, &offset, len); + if (unlikely(!buffer->page)) + return -ENOMEM; + + buffer->page_dma = page_pool_get_dma_addr(buffer->page) + offset; + buffer->page_addr = page_address(buffer->page) + offset; + buffer->page_size = len; + buffer->page_offset = offset; + + return 0; +} + static void hbg_init_tx_desc(struct hbg_buffer *buffer, struct hbg_tx_desc *tx_desc) { @@ -135,24 +180,14 @@ static void hbg_buffer_free_skb(struct hbg_buffer *buffer) buffer->skb = NULL; } -static int hbg_buffer_alloc_skb(struct hbg_buffer *buffer) -{ - u32 len = hbg_spec_max_frame_len(buffer->priv, buffer->dir); - struct hbg_priv *priv = buffer->priv; - - buffer->skb = netdev_alloc_skb(priv->netdev, len); - if (unlikely(!buffer->skb)) - return -ENOMEM; - - buffer->skb_len = len; - memset(buffer->skb->data, 0, HBG_PACKET_HEAD_SIZE); - return 0; -} - static void hbg_buffer_free(struct hbg_buffer *buffer) { - hbg_dma_unmap(buffer); - hbg_buffer_free_skb(buffer); + if (buffer->skb) { + hbg_dma_unmap(buffer); + return hbg_buffer_free_skb(buffer); + } + + hbg_buffer_free_page(buffer); } static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget) @@ -374,25 +409,44 @@ static int hbg_rx_fill_one_buffer(struct hbg_priv *priv) struct hbg_buffer *buffer; int ret; - if (hbg_queue_is_full(ring->ntc, ring->ntu, ring)) + if (hbg_queue_is_full(ring->ntc, ring->ntu, ring) || + hbg_fifo_is_full(priv, ring->dir)) return 0; buffer = &ring->queue[ring->ntu]; - ret = hbg_buffer_alloc_skb(buffer); + ret = hbg_buffer_alloc_page(buffer); if (unlikely(ret)) return ret; - ret = hbg_dma_map(buffer); - if (unlikely(ret)) { - hbg_buffer_free_skb(buffer); - return ret; - } + memset(buffer->page_addr, 0, HBG_PACKET_HEAD_SIZE); + dma_sync_single_for_device(&priv->pdev->dev, buffer->page_dma, + HBG_PACKET_HEAD_SIZE, DMA_TO_DEVICE); - hbg_hw_fill_buffer(priv, buffer->skb_dma); + hbg_hw_fill_buffer(priv, buffer->page_dma); hbg_queue_move_next(ntu, ring); return 0; } +static int hbg_rx_fill_buffers(struct hbg_priv *priv) +{ + u32 remained = hbg_hw_get_fifo_used_num(priv, HBG_DIR_RX); + u32 max_count = priv->dev_specs.rx_fifo_num; + u32 refill_count; + int ret; + + if (unlikely(remained >= max_count)) + return 0; + + refill_count = max_count - remained; + while (refill_count--) { + ret = hbg_rx_fill_one_buffer(priv); + if (unlikely(ret)) + break; + } + + return ret; +} + static bool hbg_sync_data_from_hw(struct hbg_priv *priv, struct hbg_buffer *buffer) { @@ -401,13 +455,29 @@ static bool hbg_sync_data_from_hw(struct hbg_priv *priv, /* make sure HW write desc complete */ dma_rmb(); - dma_sync_single_for_cpu(&priv->pdev->dev, buffer->skb_dma, - buffer->skb_len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(&priv->pdev->dev, buffer->page_dma, + buffer->page_size, DMA_FROM_DEVICE); - rx_desc = (struct hbg_rx_desc *)buffer->skb->data; + rx_desc = (struct hbg_rx_desc *)buffer->page_addr; return FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2) != 0; } +static int hbg_build_skb(struct hbg_priv *priv, + struct hbg_buffer *buffer, u32 pkt_len) +{ + net_prefetch(buffer->page_addr); + + buffer->skb = napi_build_skb(buffer->page_addr, buffer->page_size); + if (unlikely(!buffer->skb)) + return -ENOMEM; + skb_mark_for_recycle(buffer->skb); + + /* page will be freed together with the skb */ + buffer->page = NULL; + + return 0; +} + static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) { struct hbg_ring *ring = container_of(napi, struct hbg_ring, napi); @@ -417,33 +487,39 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) u32 packet_done = 0; u32 pkt_len; + hbg_rx_fill_buffers(priv); while (packet_done < budget) { if (unlikely(hbg_queue_is_empty(ring->ntc, ring->ntu, ring))) break; buffer = &ring->queue[ring->ntc]; - if (unlikely(!buffer->skb)) + if (unlikely(!buffer->page)) goto next_buffer; if (unlikely(!hbg_sync_data_from_hw(priv, buffer))) break; - rx_desc = (struct hbg_rx_desc *)buffer->skb->data; + rx_desc = (struct hbg_rx_desc *)buffer->page_addr; pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2); + trace_hbg_rx_desc(priv, ring->ntc, rx_desc); + + if (unlikely(hbg_build_skb(priv, buffer, pkt_len))) { + hbg_buffer_free_page(buffer); + goto next_buffer; + } if (unlikely(!hbg_rx_pkt_check(priv, rx_desc, buffer->skb))) { - hbg_buffer_free(buffer); + hbg_buffer_free_skb(buffer); goto next_buffer; } - hbg_dma_unmap(buffer); skb_reserve(buffer->skb, HBG_PACKET_HEAD_SIZE + NET_IP_ALIGN); skb_put(buffer->skb, pkt_len); buffer->skb->protocol = eth_type_trans(buffer->skb, priv->netdev); - dev_sw_netstats_rx_add(priv->netdev, pkt_len); napi_gro_receive(napi, buffer->skb); buffer->skb = NULL; + buffer->page = NULL; next_buffer: hbg_rx_fill_one_buffer(priv); @@ -458,6 +534,42 @@ next_buffer: return packet_done; } +static void hbg_ring_page_pool_destory(struct hbg_ring *ring) +{ + if (!ring->page_pool) + return; + + page_pool_destroy(ring->page_pool); + ring->page_pool = NULL; +} + +static int hbg_ring_page_pool_init(struct hbg_priv *priv, struct hbg_ring *ring) +{ + u32 buf_size = hbg_spec_max_frame_len(priv, ring->dir); + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = hbg_get_page_order(ring), + .pool_size = ring->len * buf_size / hbg_get_page_size(ring), + .nid = dev_to_node(&priv->pdev->dev), + .dev = &priv->pdev->dev, + .napi = &ring->napi, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = hbg_get_page_size(ring), + }; + int ret = 0; + + ring->page_pool = page_pool_create(&pp_params); + if (IS_ERR(ring->page_pool)) { + ret = PTR_ERR(ring->page_pool); + dev_err(&priv->pdev->dev, + "failed to create page pool, ret = %d\n", ret); + ring->page_pool = NULL; + } + + return ret; +} + static void hbg_ring_uninit(struct hbg_ring *ring) { struct hbg_buffer *buffer; @@ -476,6 +588,7 @@ static void hbg_ring_uninit(struct hbg_ring *ring) buffer->priv = NULL; } + hbg_ring_page_pool_destory(ring); dma_free_coherent(&ring->priv->pdev->dev, ring->len * sizeof(*ring->queue), ring->queue, ring->queue_dma); @@ -491,8 +604,19 @@ static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring, { struct hbg_buffer *buffer; u32 i, len; + int ret; len = hbg_get_spec_fifo_max_num(priv, dir) + 1; + /* To improve receiving performance under high-stress scenarios, + * in the `hbg_napi_rx_poll()`, we first use the other half of + * the buffer to receive packets from the hardware via the + * `hbg_rx_fill_buffers()`, and then process the packets in the + * original half of the buffer to avoid packet loss caused by + * hardware overflow as much as possible. + */ + if (dir == HBG_DIR_RX) + len += hbg_get_spec_fifo_max_num(priv, dir); + ring->queue = dma_alloc_coherent(&priv->pdev->dev, len * sizeof(*ring->queue), &ring->queue_dma, GFP_KERNEL); @@ -514,11 +638,23 @@ static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring, ring->ntu = 0; ring->len = len; - if (dir == HBG_DIR_TX) + if (dir == HBG_DIR_TX) { netif_napi_add_tx(priv->netdev, &ring->napi, napi_poll); - else + } else { netif_napi_add(priv->netdev, &ring->napi, napi_poll); + ret = hbg_ring_page_pool_init(priv, ring); + if (ret) { + netif_napi_del(&ring->napi); + dma_free_coherent(&ring->priv->pdev->dev, + ring->len * sizeof(*ring->queue), + ring->queue, ring->queue_dma); + ring->queue = NULL; + ring->len = 0; + return ret; + } + } + napi_enable(&ring->napi); return 0; } @@ -541,21 +677,16 @@ static int hbg_tx_ring_init(struct hbg_priv *priv) static int hbg_rx_ring_init(struct hbg_priv *priv) { int ret; - u32 i; ret = hbg_ring_init(priv, &priv->rx_ring, hbg_napi_rx_poll, HBG_DIR_RX); if (ret) return ret; - for (i = 0; i < priv->rx_ring.len - 1; i++) { - ret = hbg_rx_fill_one_buffer(priv); - if (ret) { - hbg_ring_uninit(&priv->rx_ring); - return ret; - } - } + ret = hbg_rx_fill_buffers(priv); + if (ret) + hbg_ring_uninit(&priv->rx_ring); - return 0; + return ret; } int hbg_txrx_init(struct hbg_priv *priv) diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index cee57a2149ab..7b1ac90b3de4 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -551,9 +551,9 @@ static int e1000_set_eeprom(struct net_device *netdev, { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - size_t total_len, max_len; u16 *eeprom_buff; int ret_val = 0; + size_t max_len; int first_word; int last_word; void *ptr; @@ -571,10 +571,6 @@ static int e1000_set_eeprom(struct net_device *netdev, max_len = hw->nvm.word_size * 2; - if (check_add_overflow(eeprom->offset, eeprom->len, &total_len) || - total_len > max_len) - return -EFBIG; - first_word = eeprom->offset >> 1; last_word = (eeprom->offset + eeprom->len - 1) >> 1; eeprom_buff = kmalloc(max_len, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index bf2029144c1d..76e42abca965 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -734,22 +734,11 @@ static int fm10k_get_rssh_fields(struct net_device *dev, return 0; } -static int fm10k_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, - u32 __always_unused *rule_locs) +static u32 fm10k_get_rx_ring_count(struct net_device *dev) { struct fm10k_intfc *interface = netdev_priv(dev); - int ret = -EOPNOTSUPP; - switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = interface->num_rx_queues; - ret = 0; - break; - default: - break; - } - - return ret; + return interface->num_rx_queues; } static int fm10k_set_rssh_fields(struct net_device *dev, @@ -1160,7 +1149,7 @@ static const struct ethtool_ops fm10k_ethtool_ops = { .set_ringparam = fm10k_set_ringparam, .get_coalesce = fm10k_get_coalesce, .set_coalesce = fm10k_set_coalesce, - .get_rxnfc = fm10k_get_rxnfc, + .get_rx_ring_count = fm10k_get_rx_ring_count, .get_regs = fm10k_get_regs, .get_regs_len = fm10k_get_regs_len, .self_test = fm10k_self_test, diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c index bc205e3077c7..229179ccc131 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devlink.c +++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c @@ -24,7 +24,8 @@ static int i40e_max_mac_per_vf_set(struct devlink *devlink, static int i40e_max_mac_per_vf_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct i40e_pf *pf = devlink_priv(devlink); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 86c72596617a..f2c2646ea298 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -3522,6 +3522,20 @@ no_input_set: } /** + * i40e_get_rx_ring_count - get RX ring count + * @netdev: network interface device structure + * + * Return: number of RX rings. + **/ +static u32 i40e_get_rx_ring_count(struct net_device *netdev) +{ + struct i40e_netdev_priv *np = netdev_priv(netdev); + struct i40e_vsi *vsi = np->vsi; + + return vsi->rss_size; +} + +/** * i40e_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -3538,10 +3552,6 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = vsi->rss_size; - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = pf->fdir_pf_active_filters; /* report total rule count */ @@ -5819,6 +5829,7 @@ static const struct ethtool_ops i40e_ethtool_ops = { .set_msglevel = i40e_set_msglevel, .get_rxnfc = i40e_get_rxnfc, .set_rxnfc = i40e_set_rxnfc, + .get_rx_ring_count = i40e_get_rx_ring_count, .self_test = i40e_diag_test, .get_strings = i40e_get_strings, .get_eee = i40e_get_eee, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 9d91a382612d..8b30a3accd31 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2967,7 +2967,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, dev_err(&pf->pdev->dev, "Cannot add more MAC addresses: VF reached its maximum allowed limit (%d)\n", mac_add_max); - return -EPERM; + return -EPERM; } if (!vf_trusted) { dev_err(&pf->pdev->dev, diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index a3f8ced23266..2cc21289a707 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1639,6 +1639,19 @@ static int iavf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) } /** + * iavf_get_rx_ring_count - get RX ring count + * @netdev: network interface device structure + * + * Return: number of RX rings. + **/ +static u32 iavf_get_rx_ring_count(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->num_active_queues; +} + +/** * iavf_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -1653,10 +1666,6 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_active_queues; - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) break; @@ -1866,6 +1875,7 @@ static const struct ethtool_ops iavf_ethtool_ops = { .set_per_queue_coalesce = iavf_set_per_queue_coalesce, .set_rxnfc = iavf_set_rxnfc, .get_rxnfc = iavf_get_rxnfc, + .get_rx_ring_count = iavf_get_rx_ring_count, .get_rxfh_indir_size = iavf_get_rxfh_indir_size, .get_rxfh = iavf_get_rxfh, .set_rxfh = iavf_set_rxfh, diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 34a422a4a29c..88156082a41d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -793,7 +793,8 @@ void iavf_add_vlans(struct iavf_adapter *adapter) len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { - dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); + dev_info(&adapter->pdev->dev, + "virtchnl: Too many VLAN add (v1) requests; splitting into multiple messages to PF\n"); while (len > IAVF_MAX_AQ_BUF_SIZE) len = virtchnl_struct_size(vvfl, vlan_id, --count); @@ -838,7 +839,8 @@ void iavf_add_vlans(struct iavf_adapter *adapter) len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { - dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); + dev_info(&adapter->pdev->dev, + "virtchnl: Too many VLAN add (v2) requests; splitting into multiple messages to PF\n"); while (len > IAVF_MAX_AQ_BUF_SIZE) len = virtchnl_struct_size(vvfl_v2, filters, --count); @@ -941,7 +943,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) len = virtchnl_struct_size(vvfl, vlan_id, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { - dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); + dev_info(&adapter->pdev->dev, + "virtchnl: Too many VLAN delete (v1) requests; splitting into multiple messages to PF\n"); while (len > IAVF_MAX_AQ_BUF_SIZE) len = virtchnl_struct_size(vvfl, vlan_id, --count); @@ -987,7 +990,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) len = virtchnl_struct_size(vvfl_v2, filters, count); if (len > IAVF_MAX_AQ_BUF_SIZE) { - dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); + dev_info(&adapter->pdev->dev, + "virtchnl: Too many VLAN delete (v2) requests; splitting into multiple messages to PF\n"); while (len > IAVF_MAX_AQ_BUF_SIZE) len = virtchnl_struct_size(vvfl_v2, filters, --count); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 938914abbe06..d88b7f3fd1f9 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -610,11 +610,13 @@ exit_release_res: * @devlink: pointer to the devlink instance * @id: the parameter ID to set * @ctx: context to store the parameter value + * @extack: netlink extended ACK structure * * Return: zero on success and negative value on failure. */ static int ice_devlink_tx_sched_layers_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); int err; @@ -1349,7 +1351,8 @@ static const struct devlink_ops ice_sf_devlink_ops; static int ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); struct iidc_rdma_core_dev_info *cdev; @@ -1415,7 +1418,8 @@ ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id, static int ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); struct iidc_rdma_core_dev_info *cdev; @@ -1522,11 +1526,13 @@ static int ice_devlink_local_fwd_str_to_mode(const char *mode_str) * @devlink: Pointer to the devlink instance. * @id: The parameter ID to set. * @ctx: Context to store the parameter value. + * @extack: netlink extended ACK structure * * Return: Zero. */ static int ice_devlink_local_fwd_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); struct ice_port_info *pi; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index a1d9abee97e5..969d4f8f9c02 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3084,6 +3084,20 @@ static int ice_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) } /** + * ice_get_rx_ring_count - get RX ring count + * @netdev: network interface device structure + * + * Return: number of RX rings. + */ +static u32 ice_get_rx_ring_count(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_vsi *vsi = np->vsi; + + return vsi->rss_size; +} + +/** * ice_get_rxnfc - command to get Rx flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -3103,10 +3117,6 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, hw = &vsi->back->hw; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = vsi->rss_size; - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = hw->fdir_active_fltr; /* report total rule count */ @@ -4853,6 +4863,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .get_sset_count = ice_get_sset_count, .get_rxnfc = ice_get_rxnfc, .set_rxnfc = ice_set_rxnfc, + .get_rx_ring_count = ice_get_rx_ring_count, .get_ringparam = ice_get_ringparam, .set_ringparam = ice_set_ringparam, .nway_reset = ice_nway_reset, diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index 26b357c0ae15..b29fbdec9442 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -1121,7 +1121,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, * ice_fdir_has_frag - does flow type have 2 ptypes * @flow: flow ptype * - * returns true is there is a fragment packet for this ptype + * Return: true if there is a fragment packet for this ptype */ bool ice_fdir_has_frag(enum ice_fltr_ptype flow) { diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index d86db081579f..973a13d3d92a 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -534,7 +534,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, } if (completion_retval) { - dev_err(dev, "Firmware failed to erase %s (module 0x02%x), aq_err %s\n", + dev_err(dev, "Firmware failed to erase %s (module 0x%02x), aq_err %s\n", component, module, libie_aq_str((enum libie_aq_err)completion_retval)); NL_SET_ERR_MSG_MOD(extack, "Firmware failed to erase flash"); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 985b3e79b312..4c8d20f2d2c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -3253,7 +3253,7 @@ void ice_ptp_init(struct ice_pf *pf) err = ice_ptp_init_port(pf, &ptp->port); if (err) - goto err_exit; + goto err_clean_pf; /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); @@ -3270,13 +3270,19 @@ void ice_ptp_init(struct ice_pf *pf) dev_info(ice_pf_to_dev(pf), "PTP init successful\n"); return; +err_clean_pf: + mutex_destroy(&ptp->port.ps_lock); + ice_ptp_cleanup_pf(pf); err_exit: /* If we registered a PTP clock, release it */ if (pf->ptp.clock) { ptp_clock_unregister(ptp->clock); pf->ptp.clock = NULL; } - ptp->state = ICE_PTP_ERROR; + /* Keep ICE_PTP_UNINIT state to avoid ambiguity at driver unload + * and to avoid duplicated resources release. + */ + ptp->state = ICE_PTP_UNINIT; dev_err(ice_pf_to_dev(pf), "PTP failed %d\n", err); } @@ -3289,9 +3295,19 @@ err_exit: */ void ice_ptp_release(struct ice_pf *pf) { - if (pf->ptp.state != ICE_PTP_READY) + if (pf->ptp.state == ICE_PTP_UNINIT) return; + if (pf->ptp.state != ICE_PTP_READY) { + mutex_destroy(&pf->ptp.port.ps_lock); + ice_ptp_cleanup_pf(pf); + if (pf->ptp.clock) { + ptp_clock_unregister(pf->ptp.clock); + pf->ptp.clock = NULL; + } + return; + } + pf->ptp.state = ICE_PTP_UNINIT; /* Disable timestamping for both Tx and Rx */ diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index 7928f4e8e788..f73d5a3e83d4 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -842,6 +842,9 @@ int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || qpi->rxq.databuffer_size < 1024)) goto error_param; + + ring->rx_buf_len = qpi->rxq.databuffer_size; + if (qpi->rxq.max_pkt_size > max_frame_size || qpi->rxq.max_pkt_size < 64) goto error_param; diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index 50fa7be0c00d..8cfc68cbfa06 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -131,14 +131,12 @@ enum idpf_cap_field { /** * enum idpf_vport_state - Current vport state - * @__IDPF_VPORT_DOWN: Vport is down - * @__IDPF_VPORT_UP: Vport is up - * @__IDPF_VPORT_STATE_LAST: Must be last, number of states + * @IDPF_VPORT_UP: Vport is up + * @IDPF_VPORT_STATE_NBITS: Must be last, number of states */ enum idpf_vport_state { - __IDPF_VPORT_DOWN, - __IDPF_VPORT_UP, - __IDPF_VPORT_STATE_LAST, + IDPF_VPORT_UP, + IDPF_VPORT_STATE_NBITS }; /** @@ -162,7 +160,7 @@ struct idpf_netdev_priv { u16 vport_idx; u16 max_tx_hdr_size; u16 tx_max_bufs; - enum idpf_vport_state state; + DECLARE_BITMAP(state, IDPF_VPORT_STATE_NBITS); struct rtnl_link_stats64 netstats; spinlock_t stats_lock; }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index a5a1eec9ade8..2589e124e41c 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -6,6 +6,25 @@ #include "idpf_virtchnl.h" /** + * idpf_get_rx_ring_count - get RX ring count + * @netdev: network interface device structure + * + * Return: number of RX rings. + */ +static u32 idpf_get_rx_ring_count(struct net_device *netdev) +{ + struct idpf_vport *vport; + u32 num_rxq; + + idpf_vport_ctrl_lock(netdev); + vport = idpf_netdev_to_vport(netdev); + num_rxq = vport->num_rxq; + idpf_vport_ctrl_unlock(netdev); + + return num_rxq; +} + +/** * idpf_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -28,9 +47,6 @@ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, user_config = &np->adapter->vport_config[np->vport_idx]->user_config; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = vport->num_rxq; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = user_config->num_fsteer_fltrs; cmd->data = idpf_fsteer_max_rules(vport); @@ -386,7 +402,7 @@ static int idpf_get_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[np->vport_idx]->user_config.rss_data; - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; rxfh->hfunc = ETH_RSS_HASH_TOP; @@ -436,7 +452,7 @@ static int idpf_set_rxfh(struct net_device *netdev, } rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && @@ -1167,7 +1183,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) { + if (!test_bit(IDPF_VPORT_UP, np->state)) { idpf_vport_ctrl_unlock(netdev); return; @@ -1319,7 +1335,7 @@ static int idpf_get_q_coalesce(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; if (q_num >= vport->num_rxq && q_num >= vport->num_txq) { @@ -1507,7 +1523,7 @@ static int idpf_set_coalesce(struct net_device *netdev, idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto unlock_mutex; for (i = 0; i < vport->num_txq; i++) { @@ -1710,7 +1726,7 @@ static void idpf_get_ts_stats(struct net_device *netdev, ts_stats->err = u64_stats_read(&vport->tstamp_stats.discarded); } while (u64_stats_fetch_retry(&vport->tstamp_stats.stats_sync, start)); - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) goto exit; for (u16 i = 0; i < vport->num_txq_grp; i++) { @@ -1757,6 +1773,7 @@ static const struct ethtool_ops idpf_ethtool_ops = { .get_channels = idpf_get_channels, .get_rxnfc = idpf_get_rxnfc, .set_rxnfc = idpf_set_rxnfc, + .get_rx_ring_count = idpf_get_rx_ring_count, .get_rxfh_key_size = idpf_get_rxfh_key_size, .get_rxfh_indir_size = idpf_get_rxfh_indir_size, .get_rxfh = idpf_get_rxfh, diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 8a941f0fb048..7a7e101afeb6 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -519,7 +519,7 @@ static int idpf_del_mac_filter(struct idpf_vport *vport, } spin_unlock_bh(&vport_config->mac_filter_list_lock); - if (np->state == __IDPF_VPORT_UP) { + if (test_bit(IDPF_VPORT_UP, np->state)) { int err; err = idpf_add_del_mac_filters(vport, np, false, async); @@ -590,7 +590,7 @@ static int idpf_add_mac_filter(struct idpf_vport *vport, if (err) return err; - if (np->state == __IDPF_VPORT_UP) + if (test_bit(IDPF_VPORT_UP, np->state)) err = idpf_add_del_mac_filters(vport, np, true, async); return err; @@ -894,7 +894,7 @@ static void idpf_vport_stop(struct idpf_vport *vport, bool rtnl) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); - if (np->state <= __IDPF_VPORT_DOWN) + if (!test_bit(IDPF_VPORT_UP, np->state)) return; if (rtnl) @@ -921,7 +921,7 @@ static void idpf_vport_stop(struct idpf_vport *vport, bool rtnl) idpf_xdp_rxq_info_deinit_all(vport); idpf_vport_queues_rel(vport); idpf_vport_intr_rel(vport); - np->state = __IDPF_VPORT_DOWN; + clear_bit(IDPF_VPORT_UP, np->state); if (rtnl) rtnl_unlock(); @@ -1345,7 +1345,7 @@ static int idpf_up_complete(struct idpf_vport *vport) netif_tx_start_all_queues(vport->netdev); } - np->state = __IDPF_VPORT_UP; + set_bit(IDPF_VPORT_UP, np->state); return 0; } @@ -1391,7 +1391,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool rtnl) struct idpf_vport_config *vport_config; int err; - if (np->state != __IDPF_VPORT_DOWN) + if (test_bit(IDPF_VPORT_UP, np->state)) return -EBUSY; if (rtnl) @@ -1602,7 +1602,7 @@ void idpf_init_task(struct work_struct *work) /* Once state is put into DOWN, driver is ready for dev_open */ np = netdev_priv(vport->netdev); - np->state = __IDPF_VPORT_DOWN; + clear_bit(IDPF_VPORT_UP, np->state); if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags)) idpf_vport_open(vport, true); @@ -1801,7 +1801,7 @@ static void idpf_set_vport_state(struct idpf_adapter *adapter) continue; np = netdev_priv(adapter->netdevs[i]); - if (np->state == __IDPF_VPORT_UP) + if (test_bit(IDPF_VPORT_UP, np->state)) set_bit(IDPF_VPORT_UP_REQUESTED, adapter->vport_config[i]->flags); } @@ -1939,7 +1939,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, enum idpf_vport_reset_cause reset_cause) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); - enum idpf_vport_state current_state = np->state; + bool vport_is_up = test_bit(IDPF_VPORT_UP, np->state); struct idpf_adapter *adapter = vport->adapter; struct idpf_vport *new_vport; int err; @@ -1990,7 +1990,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, goto free_vport; } - if (current_state <= __IDPF_VPORT_DOWN) { + if (!vport_is_up) { idpf_send_delete_queues_msg(vport); } else { set_bit(IDPF_VPORT_DEL_QUEUES, vport->flags); @@ -2023,7 +2023,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, if (err) goto err_open; - if (current_state == __IDPF_VPORT_UP) + if (vport_is_up) err = idpf_vport_open(vport, false); goto free_vport; @@ -2033,7 +2033,7 @@ err_reset: vport->num_rxq, vport->num_bufq); err_open: - if (current_state == __IDPF_VPORT_UP) + if (vport_is_up) idpf_vport_open(vport, false); free_vport: diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index 7a06eaf46a08..de5d722cc21d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -141,6 +141,8 @@ destroy_wqs: destroy_workqueue(adapter->vc_event_wq); for (i = 0; i < adapter->max_vports; i++) { + if (!adapter->vport_config[i]) + continue; kfree(adapter->vport_config[i]->user_config.q_coalesce); kfree(adapter->vport_config[i]); adapter->vport_config[i] = NULL; diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index 61e613066140..e3ddf18dcbf5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -570,7 +570,7 @@ fetch_next_txq_desc: np = netdev_priv(tx_q->netdev); nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); - dont_wake = np->state != __IDPF_VPORT_UP || + dont_wake = !test_bit(IDPF_VPORT_UP, np->state) || !netif_carrier_ok(tx_q->netdev); __netif_txq_completed_wake(nq, ss.packets, ss.bytes, IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH, diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 828f7c444d30..1d91c56f7469 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -134,7 +134,7 @@ static void idpf_compl_desc_rel(struct idpf_compl_queue *complq) { idpf_xsk_clear_queue(complq, VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION); - if (!complq->comp) + if (!complq->desc_ring) return; dma_free_coherent(complq->netdev->dev.parent, complq->size, @@ -922,8 +922,8 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport) err = idpf_rx_desc_alloc(vport, q); if (err) { pci_err(vport->adapter->pdev, - "Memory allocation for Rx Queue %u failed\n", - i); + "Memory allocation for Rx queue %u from queue group %u failed\n", + j, i); goto err_out; } } @@ -939,8 +939,8 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport) err = idpf_bufq_desc_alloc(vport, q); if (err) { pci_err(vport->adapter->pdev, - "Memory allocation for Rx Buffer Queue %u failed\n", - i); + "Memory allocation for Rx Buffer Queue %u from queue group %u failed\n", + j, i); goto err_out; } } @@ -2275,7 +2275,7 @@ fetch_next_desc: /* Update BQL */ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx); - dont_wake = !complq_ok || np->state != __IDPF_VPORT_UP || + dont_wake = !complq_ok || !test_bit(IDPF_VPORT_UP, np->state) || !netif_carrier_ok(tx_q->netdev); /* Check if the TXQ needs to and can be restarted */ __netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes, diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index cbb5fa30f5a0..44cd4b466c48 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -68,7 +68,7 @@ static void idpf_handle_event_link(struct idpf_adapter *adapter, vport->link_up = v2e->link_status; - if (np->state != __IDPF_VPORT_UP) + if (!test_bit(IDPF_VPORT_UP, np->state)) return; if (vport->link_up) { @@ -2755,7 +2755,7 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) /* Don't send get_stats message if the link is down */ - if (np->state <= __IDPF_VPORT_DOWN) + if (!test_bit(IDPF_VPORT_UP, np->state)) return 0; stats_msg.vport_id = cpu_to_le32(vport->vport_id); diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c index 21ce25b0567f..958d16f87424 100644 --- a/drivers/net/ethernet/intel/idpf/xdp.c +++ b/drivers/net/ethernet/intel/idpf/xdp.c @@ -418,7 +418,7 @@ static int idpf_xdp_setup_prog(struct idpf_vport *vport, if (test_bit(IDPF_REMOVE_IN_PROG, vport->adapter->flags) || !test_bit(IDPF_VPORT_REG_NETDEV, cfg->flags) || !!vport->xdp_prog == !!prog) { - if (np->state == __IDPF_VPORT_UP) + if (test_bit(IDPF_VPORT_UP, np->state)) idpf_xdp_copy_prog_to_rqs(vport, prog); old = xchg(&vport->xdp_prog, prog); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 10e2445e0ded..b507576b28b2 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2541,6 +2541,13 @@ static int igb_get_rxfh_fields(struct net_device *dev, return 0; } +static u32 igb_get_rx_ring_count(struct net_device *dev) +{ + struct igb_adapter *adapter = netdev_priv(dev); + + return adapter->num_rx_queues; +} + static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2548,10 +2555,6 @@ static int igb_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_rx_queues; - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = adapter->nfc_filter_count; ret = 0; @@ -3473,6 +3476,7 @@ static const struct ethtool_ops igb_ethtool_ops = { .get_ts_info = igb_get_ts_info, .get_rxnfc = igb_get_rxnfc, .set_rxnfc = igb_set_rxnfc, + .get_rx_ring_count = igb_get_rx_ring_count, .get_eee = igb_get_eee, .set_eee = igb_set_eee, .get_module_info = igb_get_module_info, diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index bb783042d1af..e94c1922b97a 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1091,15 +1091,19 @@ static int igc_ethtool_get_rxfh_fields(struct net_device *dev, return 0; } +static u32 igc_ethtool_get_rx_ring_count(struct net_device *dev) +{ + struct igc_adapter *adapter = netdev_priv(dev); + + return adapter->num_rx_queues; +} + static int igc_ethtool_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { struct igc_adapter *adapter = netdev_priv(dev); switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_rx_queues; - return 0; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = adapter->nfc_rule_count; return 0; @@ -2170,6 +2174,7 @@ static const struct ethtool_ops igc_ethtool_ops = { .set_coalesce = igc_ethtool_set_coalesce, .get_rxnfc = igc_ethtool_get_rxnfc, .set_rxnfc = igc_ethtool_set_rxnfc, + .get_rx_ring_count = igc_ethtool_get_rx_ring_count, .get_rxfh_indir_size = igc_ethtool_get_rxfh_indir_size, .get_rxfh = igc_ethtool_get_rxfh, .set_rxfh = igc_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 2d660e9edb80..2ad81f687a84 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2805,6 +2805,14 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) return 64; } +static u32 ixgbe_get_rx_ring_count(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); + + return min_t(u32, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); +} + static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2812,11 +2820,6 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = min_t(int, adapter->num_rx_queues, - ixgbe_rss_indir_tbl_max(adapter)); - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = adapter->fdir_filter_count; ret = 0; @@ -3743,6 +3746,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_ethtool_stats = ixgbe_get_ethtool_stats, .get_coalesce = ixgbe_get_coalesce, .set_coalesce = ixgbe_set_coalesce, + .get_rx_ring_count = ixgbe_get_rx_ring_count, .get_rxnfc = ixgbe_get_rxnfc, .set_rxnfc = ixgbe_set_rxnfc, .get_rxfh_indir_size = ixgbe_rss_indir_size, @@ -3791,6 +3795,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops_e610 = { .get_ethtool_stats = ixgbe_get_ethtool_stats, .get_coalesce = ixgbe_get_coalesce, .set_coalesce = ixgbe_set_coalesce, + .get_rx_ring_count = ixgbe_get_rx_ring_count, .get_rxnfc = ixgbe_get_rxnfc, .set_rxnfc = ixgbe_set_rxnfc, .get_rxfh_indir_size = ixgbe_rss_indir_size, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3190ce7e44c7..4af3b3e71ff1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7449,7 +7449,7 @@ int ixgbe_open(struct net_device *netdev) adapter->hw.link.link_info.link_cfg_err); err = ixgbe_non_sfp_link_config(&adapter->hw); - if (ixgbe_non_sfp_link_config(&adapter->hw)) + if (err) e_dev_err("Link setup failed, err %d.\n", err); } @@ -12046,7 +12046,7 @@ err_dma: * @pdev: PCI device information struct * * ixgbe_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a + * that it should release a PCI device. This could be caused by a * Hot-Plug event, or because the driver is going to be removed from * memory. **/ diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index bebad564188e..537a60d5276f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -867,19 +867,11 @@ static int ixgbevf_set_coalesce(struct net_device *netdev, return 0; } -static int ixgbevf_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules __always_unused) +static u32 ixgbevf_get_rx_ring_count(struct net_device *dev) { struct ixgbevf_adapter *adapter = netdev_priv(dev); - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = adapter->num_rx_queues; - return 0; - default: - hw_dbg(&adapter->hw, "Command parameters not supported\n"); - return -EOPNOTSUPP; - } + return adapter->num_rx_queues; } static u32 ixgbevf_get_rxfh_indir_size(struct net_device *netdev) @@ -987,7 +979,7 @@ static const struct ethtool_ops ixgbevf_ethtool_ops = { .get_ethtool_stats = ixgbevf_get_ethtool_stats, .get_coalesce = ixgbevf_get_coalesce, .set_coalesce = ixgbevf_set_coalesce, - .get_rxnfc = ixgbevf_get_rxnfc, + .get_rx_ring_count = ixgbevf_get_rx_ring_count, .get_rxfh_indir_size = ixgbevf_get_rxfh_indir_size, .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, .get_rxfh = ixgbevf_get_rxfh, diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 039187607e98..516a6fdd23d0 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -241,23 +241,7 @@ struct ixgbevf_q_vector { char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ - struct ixgbevf_ring ring[0] ____cacheline_internodealigned_in_smp; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned int state; -#define IXGBEVF_QV_STATE_IDLE 0 -#define IXGBEVF_QV_STATE_NAPI 1 /* NAPI owns this QV */ -#define IXGBEVF_QV_STATE_POLL 2 /* poll owns this QV */ -#define IXGBEVF_QV_STATE_DISABLED 4 /* QV is disabled */ -#define IXGBEVF_QV_OWNED (IXGBEVF_QV_STATE_NAPI | IXGBEVF_QV_STATE_POLL) -#define IXGBEVF_QV_LOCKED (IXGBEVF_QV_OWNED | IXGBEVF_QV_STATE_DISABLED) -#define IXGBEVF_QV_STATE_NAPI_YIELD 8 /* NAPI yielded this QV */ -#define IXGBEVF_QV_STATE_POLL_YIELD 16 /* poll yielded this QV */ -#define IXGBEVF_QV_YIELD (IXGBEVF_QV_STATE_NAPI_YIELD | \ - IXGBEVF_QV_STATE_POLL_YIELD) -#define IXGBEVF_QV_USER_PEND (IXGBEVF_QV_STATE_POLL | \ - IXGBEVF_QV_STATE_POLL_YIELD) - spinlock_t lock; -#endif /* CONFIG_NET_RX_BUSY_POLL */ + struct ixgbevf_ring ring[] ____cacheline_internodealigned_in_smp; }; /* microsecond values for various ITR rates shifted by 2 to fit itr register diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 89ccb8eb82c7..7af44f858fa3 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5012,17 +5012,9 @@ static u32 mvneta_ethtool_get_rxfh_indir_size(struct net_device *dev) return MVNETA_RSS_LU_TABLE_SIZE; } -static int mvneta_ethtool_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, - u32 *rules __always_unused) +static u32 mvneta_ethtool_get_rx_ring_count(struct net_device *dev) { - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = rxq_number; - return 0; - default: - return -EOPNOTSUPP; - } + return rxq_number; } static int mvneta_config_rss(struct mvneta_port *pp) @@ -5356,7 +5348,7 @@ static const struct ethtool_ops mvneta_eth_tool_ops = { .get_ethtool_stats = mvneta_ethtool_get_stats, .get_sset_count = mvneta_ethtool_get_sset_count, .get_rxfh_indir_size = mvneta_ethtool_get_rxfh_indir_size, - .get_rxnfc = mvneta_ethtool_get_rxnfc, + .get_rx_ring_count = mvneta_ethtool_get_rx_ring_count, .get_rxfh = mvneta_ethtool_get_rxfh, .set_rxfh = mvneta_ethtool_set_rxfh, .get_link_ksettings = mvneta_ethtool_get_link_ksettings, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ab0c99aa9f9a..33426fded919 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5580,6 +5580,13 @@ static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev, return phylink_ethtool_ksettings_set(port->phylink, cmd); } +static u32 mvpp2_ethtool_get_rx_ring_count(struct net_device *dev) +{ + struct mvpp2_port *port = netdev_priv(dev); + + return port->nrxqs; +} + static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rules) { @@ -5590,9 +5597,6 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev, return -EOPNOTSUPP; switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = port->nrxqs; - break; case ETHTOOL_GRXCLSRLCNT: info->rule_cnt = port->n_rfs_rules; break; @@ -5827,6 +5831,7 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .set_pauseparam = mvpp2_ethtool_set_pause_param, .get_link_ksettings = mvpp2_ethtool_get_link_ksettings, .set_link_ksettings = mvpp2_ethtool_set_link_ksettings, + .get_rx_ring_count = mvpp2_ethtool_get_rx_ring_count, .get_rxnfc = mvpp2_ethtool_get_rxnfc, .set_rxnfc = mvpp2_ethtool_set_rxnfc, .get_rxfh_indir_size = mvpp2_ethtool_get_rxfh_indir_size, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 7370812ece2a..15d3cb0b9da6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1663,6 +1663,9 @@ static void print_tm_tree(struct seq_file *m, int blkaddr; u64 cfg; + if (!sq_ctx->ena) + return; + blkaddr = nix_hw->blkaddr; schq = sq_ctx->smq; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 3735372539bd..0f9953eaf1b0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1233,7 +1233,8 @@ static int rvu_af_dl_dwrr_mtu_set(struct devlink *devlink, u32 id, } static int rvu_af_dl_dwrr_mtu_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct rvu_devlink *rvu_dl = devlink_priv(devlink); struct rvu *rvu = rvu_dl->rvu; @@ -1259,7 +1260,8 @@ enum rvu_af_dl_param_id { }; static int rvu_af_npc_exact_feature_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct rvu_devlink *rvu_dl = devlink_priv(devlink); struct rvu *rvu = rvu_dl->rvu; @@ -1314,7 +1316,8 @@ static int rvu_af_npc_exact_feature_validate(struct devlink *devlink, u32 id, } static int rvu_af_dl_npc_mcam_high_zone_percent_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct rvu_devlink *rvu_dl = devlink_priv(devlink); struct rvu *rvu = rvu_dl->rvu; @@ -1376,7 +1379,8 @@ static int rvu_af_dl_npc_mcam_high_zone_percent_validate(struct devlink *devlink } static int rvu_af_dl_npc_def_rule_cntr_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct rvu_devlink *rvu_dl = devlink_priv(devlink); struct rvu *rvu = rvu_dl->rvu; @@ -1402,7 +1406,8 @@ static int rvu_af_dl_npc_def_rule_cntr_set(struct devlink *devlink, u32 id, } static int rvu_af_dl_nix_maxlf_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct rvu_devlink *rvu_dl = devlink_priv(devlink); struct rvu *rvu = rvu_dl->rvu; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index e13ae5484c19..a72694219df4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -48,7 +48,8 @@ static int otx2_dl_mcam_count_set(struct devlink *devlink, u32 id, } static int otx2_dl_mcam_count_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct otx2_devlink *otx2_dl = devlink_priv(devlink); struct otx2_nic *pfvf = otx2_dl->pfvf; @@ -84,7 +85,8 @@ static int otx2_dl_ucast_flt_cnt_set(struct devlink *devlink, u32 id, } static int otx2_dl_ucast_flt_cnt_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct otx2_devlink *otx2_dl = devlink_priv(devlink); struct otx2_nic *pfvf = otx2_dl->pfvf; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a68cd3f0304c..ad6298456639 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1727,6 +1727,13 @@ static int mlx4_en_get_num_flows(struct mlx4_en_priv *priv) } +static u32 mlx4_en_get_rx_ring_count(struct net_device *dev) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + return priv->rx_ring_num; +} + static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -1743,9 +1750,6 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return -EINVAL; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = priv->rx_ring_num; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = mlx4_en_get_num_flows(priv); break; @@ -2154,6 +2158,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = { .set_ringparam = mlx4_en_set_ringparam, .get_rxnfc = mlx4_en_get_rxnfc, .set_rxnfc = mlx4_en_set_rxnfc, + .get_rx_ring_count = mlx4_en_get_rx_ring_count, .get_rxfh_indir_size = mlx4_en_get_rxfh_indir_size, .get_rxfh_key_size = mlx4_en_get_rxfh_key_size, .get_rxfh = mlx4_en_get_rxfh, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 03d2fc7d9b09..2de226951e19 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -174,7 +174,8 @@ MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is defaul static atomic_t pf_loading = ATOMIC_INIT(0); static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { ctx->val.vbool = !!mlx4_internal_err_reset; return 0; @@ -189,7 +190,8 @@ static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id, } static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx4_priv *priv = devlink_priv(devlink); struct mlx4_dev *dev = &priv->dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 722282cebce9..5b08e5ffe0e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -181,6 +181,7 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { lockdep_assert_held(&cmd->alloc_lock); + cmd->ent_arr[idx] = NULL; set_bit(idx, &cmd->vars.bitmask); } @@ -1200,6 +1201,44 @@ out_err: return err; } +/* Check if all command slots are stalled (timed out and not recovered). + * returns true if all slots timed out on a recent command and have not been + * completed by FW yet. (stalled state) + * false otherwise (at least one slot is not stalled). + * + * In such odd situation "all_stalled", this serves as a protection mechanism + * to avoid blocking the kernel for long periods of time in case FW is not + * responding to commands. + */ +static bool mlx5_cmd_all_stalled(struct mlx5_core_dev *dev) +{ + struct mlx5_cmd *cmd = &dev->cmd; + bool all_stalled = true; + unsigned long flags; + int i; + + spin_lock_irqsave(&cmd->alloc_lock, flags); + + /* at least one command slot is free */ + if (bitmap_weight(&cmd->vars.bitmask, cmd->vars.max_reg_cmds) > 0) { + all_stalled = false; + goto out; + } + + for_each_clear_bit(i, &cmd->vars.bitmask, cmd->vars.max_reg_cmds) { + struct mlx5_cmd_work_ent *ent = dev->cmd.ent_arr[i]; + + if (!test_bit(MLX5_CMD_ENT_STATE_TIMEDOUT, &ent->state)) { + all_stalled = false; + break; + } + } +out: + spin_unlock_irqrestore(&cmd->alloc_lock, flags); + + return all_stalled; +} + /* Notes: * 1. Callback functions may not sleep * 2. page queue commands do not support asynchrous completion @@ -1230,6 +1269,15 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (callback && page_queue) return -EINVAL; + if (!page_queue && mlx5_cmd_all_stalled(dev)) { + mlx5_core_err_rl(dev, + "All CMD slots are stalled, aborting command\n"); + /* there's no reason to wait and block the whole kernel if FW + * isn't currently responding to all slots, fail immediately + */ + return -EAGAIN; + } + ent = cmd_alloc_ent(cmd, in, out, uout, uout_size, callback, context, page_queue); if (IS_ERR(ent)) @@ -1700,6 +1748,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force if (test_bit(i, &vector)) { ent = cmd->ent_arr[i]; + if (forced && ent->ret == -ETIMEDOUT) + set_bit(MLX5_CMD_ENT_STATE_TIMEDOUT, + &ent->state); + else if (!forced) /* real FW completion */ + clear_bit(MLX5_CMD_ENT_STATE_TIMEDOUT, + &ent->state); + /* if we already completed the command, ignore it */ if (!test_and_clear_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index c9555119a661..43b9bf8829cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -26,7 +26,8 @@ enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_ID_PCIE_CONG_IN_HIGH, MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_LOW, MLX5_DEVLINK_PARAM_ID_PCIE_CONG_OUT_HIGH, - MLX5_DEVLINK_PARAM_ID_CQE_COMPRESSION_TYPE + MLX5_DEVLINK_PARAM_ID_CQE_COMPRESSION_TYPE, + MLX5_DEVLINK_PARAM_ID_SWP_L4_CSUM_MODE, }; struct mlx5_trap_ctx { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 080e7eab52c7..7bcf822a89f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -54,7 +54,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) { mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n"); - return -ENOTSUPP; + return -EOPNOTSUPP; } tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 12e10feb30f0..424f8a2728a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -82,7 +82,7 @@ static struct mlx5e_skb_cb_hwtstamp *mlx5e_skb_cb_get_hwts(struct sk_buff *skb) } static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb, - struct mlx5e_ptp_cq_stats *cq_stats) + struct mlx5e_ptpsq *ptpsq) { struct skb_shared_hwtstamps hwts = {}; ktime_t diff; @@ -92,8 +92,17 @@ static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb, /* Maximal allowed diff is 1 / 128 second */ if (diff > (NSEC_PER_SEC >> 7)) { - cq_stats->abort++; - cq_stats->abort_abs_diff_ns += diff; + struct mlx5e_txqsq *sq = &ptpsq->txqsq; + + ptpsq->cq_stats->abort++; + ptpsq->cq_stats->abort_abs_diff_ns += diff; + if (diff > (NSEC_PER_SEC >> 1) && + !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { + netdev_warn(sq->channel->netdev, + "PTP TX timestamp difference between CQE and port exceeds threshold: %lld ns, recovering SQ %u\n", + (s64)diff, sq->sqn); + queue_work(sq->priv->wq, &ptpsq->report_unhealthy_work); + } return; } @@ -103,7 +112,7 @@ static void mlx5e_skb_cb_hwtstamp_tx(struct sk_buff *skb, void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, ktime_t hwtstamp, - struct mlx5e_ptp_cq_stats *cq_stats) + struct mlx5e_ptpsq *ptpsq) { switch (hwtstamp_type) { case (MLX5E_SKB_CB_CQE_HWTSTAMP): @@ -121,7 +130,7 @@ void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, !mlx5e_skb_cb_get_hwts(skb)->port_hwtstamp) return; - mlx5e_skb_cb_hwtstamp_tx(skb, cq_stats); + mlx5e_skb_cb_hwtstamp_tx(skb, ptpsq); memset(skb->cb, 0, sizeof(struct mlx5e_skb_cb_hwtstamp)); } @@ -209,7 +218,7 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe)); mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_PORT_HWTSTAMP, - hwtstamp, ptpsq->cq_stats); + hwtstamp, ptpsq); ptpsq->cq_stats->cqe++; mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 1c0e0a86a9ac..2a457a2ed707 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -147,7 +147,7 @@ enum { void mlx5e_skb_cb_hwtstamp_handler(struct sk_buff *skb, int hwtstamp_type, ktime_t hwtstamp, - struct mlx5e_ptp_cq_stats *cq_stats); + struct mlx5e_ptpsq *ptpsq); void mlx5e_skb_cb_hwtstamp_init(struct sk_buff *skb); #endif /* __MLX5_EN_PTP_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 9b93da4d52f6..cf8f14ce4cd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -627,7 +627,7 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, MLX5E_100MB); max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; max_bw_unit[i] = MLX5_100_MBPS_UNIT; - } else if (max_bw_value[i] <= upper_limit_gbps) { + } else if (maxrate->tc_maxrate[i] <= upper_limit_gbps) { max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], MLX5E_1GB); max_bw_unit[i] = MLX5_GBPS_UNIT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 01b8f05a23db..fe67c73849f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -261,6 +261,11 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT, ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT, ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT); + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1600TAUI_8_1600TBASE_CR8_KR8, ext, + ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT, + ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT, + ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT, + ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT); } static void mlx5e_ethtool_get_speed_arr(bool ext, @@ -2027,7 +2032,7 @@ static int mlx5e_get_module_info(struct net_device *netdev, int size_read = 0; u8 data[4] = {0}; - size_read = mlx5_query_module_eeprom(dev, 0, 2, data); + size_read = mlx5_query_module_eeprom(dev, 0, 2, data, NULL); if (size_read < 2) return -EIO; @@ -2069,6 +2074,7 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev, struct mlx5_core_dev *mdev = priv->mdev; int offset = ee->offset; int size_read; + u8 status = 0; int i = 0; if (!ee->len) @@ -2078,15 +2084,15 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev, while (i < ee->len) { size_read = mlx5_query_module_eeprom(mdev, offset, ee->len - i, - data + i); - + data + i, &status); if (!size_read) /* Done reading */ return 0; if (size_read < 0) { - netdev_err(priv->netdev, "%s: mlx5_query_eeprom failed:0x%x\n", - __func__, size_read); + netdev_err(netdev, + "%s: mlx5_query_eeprom failed:0x%x, status %u\n", + __func__, size_read, status); return size_read; } @@ -2106,6 +2112,7 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, struct mlx5_core_dev *mdev = priv->mdev; u8 *data = page_data->data; int size_read; + u8 status = 0; int i = 0; if (!page_data->length) @@ -2119,7 +2126,8 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, query.page = page_data->page; while (i < page_data->length) { query.size = page_data->length - i; - size_read = mlx5_query_module_eeprom_by_page(mdev, &query, data + i); + size_read = mlx5_query_module_eeprom_by_page(mdev, &query, + data + i, &status); /* Done reading, return how many bytes was read */ if (!size_read) @@ -2128,8 +2136,8 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, if (size_read < 0) { NL_SET_ERR_MSG_FMT_MOD( extack, - "Query module eeprom by page failed, read %u bytes, err %d", - i, size_read); + "Query module eeprom by page failed, read %u bytes, err %d, status %u", + i, size_read, status); return size_read; } @@ -2492,21 +2500,18 @@ static int mlx5e_set_rxfh_fields(struct net_device *dev, return mlx5e_ethtool_set_rxfh_fields(priv, cmd, extack); } +static u32 mlx5e_get_rx_ring_count(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + return priv->channels.params.num_channels; +} + static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); - /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part - * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, - * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc - * is compiled out via CONFIG_MLX5_EN_RXNFC=n. - */ - if (info->cmd == ETHTOOL_GRXRINGS) { - info->data = priv->channels.params.num_channels; - return 0; - } - return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } @@ -2766,6 +2771,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .remove_rxfh_context = mlx5e_remove_rxfh_context, .get_rxnfc = mlx5e_get_rxnfc, .set_rxnfc = mlx5e_set_rxnfc, + .get_rx_ring_count = mlx5e_get_rx_ring_count, .get_tunable = mlx5e_get_tunable, .set_tunable = mlx5e_set_tunable, .get_pause_stats = mlx5e_get_pause_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 79916f1abd14..63bdef5b4ba5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -704,7 +704,7 @@ static int validate_flow(struct mlx5e_priv *priv, num_tuples += ret; break; default: - return -ENOTSUPP; + return -EOPNOTSUPP; } if ((fs->flow_type & FLOW_EXT)) { ret = validate_vlan(fs); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 2702b3885f06..14884b9ea7f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -755,7 +755,7 @@ static void mlx5e_consume_skb(struct mlx5e_txqsq *sq, struct sk_buff *skb, hwts.hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, ts); if (sq->ptpsq) { mlx5e_skb_cb_hwtstamp_handler(skb, MLX5E_SKB_CB_CQE_HWTSTAMP, - hwts.hwtstamp, sq->ptpsq->cq_stats); + hwts.hwtstamp, sq->ptpsq); } else { skb_tstamp_tx(skb, &hwts); sq->stats->timestamps++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 56e6f54b1e2e..4278bcb04c72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -341,13 +341,6 @@ static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw, if (max_guarantee) return max_t(u32, max_guarantee / fw_max_bw_share, 1); - /* If nodes max min_rate divider is 0 but their parent has bw_share - * configured, then set bw_share for nodes to minimal value. - */ - - if (parent && parent->bw_share) - return 1; - /* If the node nodes has min_rate configured, a divider of 0 sets all * nodes' bw_share to 0, effectively disabling min guarantees. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e2ffb87b94cb..4b7a1ce7f406 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -875,13 +875,10 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) vport_num, 1, vport->info.link_state); - /* Host PF has its own mac/guid. */ - if (vport_num) { - mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, - vport->info.mac); - mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, - vport->info.node_guid); - } + mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, + vport->info.mac); + mlx5_query_nic_vport_node_guid(esw->dev, vport_num, true, + &vport->info.node_guid); flags = (vport->info.vlan || vport->info.qos) ? SET_VLAN_STRIP | SET_VLAN_INSERT : 0; @@ -947,12 +944,6 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, goto err_vhca_mapping; } - /* External controller host PF has factory programmed MAC. - * Read it from the device. - */ - if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) - mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac); - esw_vport_change_handle_locked(vport); esw->enabled_vports++; @@ -1483,7 +1474,7 @@ static void mlx5_esw_mode_change_notify(struct mlx5_eswitch *esw, u16 mode) info.new_mode = mode; - blocking_notifier_call_chain(&esw->n_head, 0, &info); + blocking_notifier_call_chain(&esw->dev->priv.esw_n_head, 0, &info); } static int mlx5_esw_egress_acls_init(struct mlx5_core_dev *dev) @@ -1978,7 +1969,8 @@ static int mlx5_devlink_esw_multiport_set(struct devlink *devlink, u32 id, } static int mlx5_devlink_esw_multiport_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); @@ -2059,7 +2051,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; else esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); esw_info(dev, "Total vports %d, per vport: max uc(%d) max mc(%d)\n", @@ -2235,6 +2226,9 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, ivi->vf = vport - 1; mutex_lock(&esw->state_lock); + + mlx5_query_nic_vport_mac_address(esw->dev, vport, true, + evport->info.mac); ether_addr_copy(ivi->mac, evport->info.mac); ivi->linkstate = evport->info.link_state; ivi->vlan = evport->info.vlan; @@ -2385,14 +2379,16 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0, dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS); } -int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *nb) +int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev, + struct notifier_block *nb) { - return blocking_notifier_chain_register(&esw->n_head, nb); + return blocking_notifier_chain_register(&dev->priv.esw_n_head, nb); } -void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *nb) +void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev, + struct notifier_block *nb) { - blocking_notifier_chain_unregister(&esw->n_head, nb); + blocking_notifier_chain_unregister(&dev->priv.esw_n_head, nb); } /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index beaec450a734..ad1073f7b79f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -403,7 +403,6 @@ struct mlx5_eswitch { struct { u32 large_group_num; } params; - struct blocking_notifier_head n_head; struct xarray paired; struct mlx5_devcom_comp_dev *devcom; u16 enabled_ipsec_vf_count; @@ -864,8 +863,10 @@ struct mlx5_esw_event_info { u16 new_mode; }; -int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *n); -void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *n); +int mlx5_esw_event_notifier_register(struct mlx5_core_dev *dev, + struct notifier_block *n); +void mlx5_esw_event_notifier_unregister(struct mlx5_core_dev *dev, + struct notifier_block *n); bool mlx5_esw_hold(struct mlx5_core_dev *dev); void mlx5_esw_release(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0b1a180ef238..8de6c7f6c294 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2618,7 +2618,8 @@ done: } static int esw_port_metadata_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); @@ -4491,6 +4492,9 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port); mutex_lock(&esw->state_lock); + + mlx5_query_nic_vport_mac_address(esw->dev, vport->vport, true, + vport->info.mac); ether_addr_copy(hw_addr, vport->info.mac); *hw_addr_len = ETH_ALEN; mutex_unlock(&esw->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index e5c1012921d2..1ec61164e6b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -211,7 +211,7 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps); if (!max_num_qps) { mlx5_fpga_err(fdev, "FPGA reports 0 QPs in SHELL_CAPS\n"); - err = -ENOTSUPP; + err = -EOPNOTSUPP; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1af76da8b132..ced747bef641 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -239,6 +239,10 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); MLX5_SET(set_flow_table_root_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(set_flow_table_root_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(set_flow_table_root_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_in(dev, set_flow_table_root, in); if (!err && @@ -302,6 +306,10 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); MLX5_SET(create_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(create_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(create_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en, en_decap); @@ -360,6 +368,10 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport); MLX5_SET(destroy_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(destroy_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(destroy_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_in(dev, destroy_flow_table, in); if (!err) @@ -394,6 +406,10 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport); MLX5_SET(modify_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(modify_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(modify_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); MLX5_SET(modify_flow_table_in, in, modify_field_select, MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID); if (next_ft) { @@ -429,6 +445,10 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); MLX5_SET(create_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(create_flow_group_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(create_flow_group_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out); if (!err) fg->id = MLX5_GET(create_flow_group_out, out, @@ -451,6 +471,10 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport); MLX5_SET(destroy_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(destroy_flow_group_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(destroy_flow_group_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); return mlx5_cmd_exec_in(dev, destroy_flow_group, in); } @@ -559,6 +583,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(set_fte_in, in, vport_number, ft->vport); MLX5_SET(set_fte_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(set_fte_in, in, eswitch_owner_vhca_id, ft->esw_owner_vhca_id); + MLX5_SET(set_fte_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); MLX5_SET(flow_context, in_flow_context, group_id, group_id); @@ -788,6 +815,10 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, MLX5_SET(delete_fte_in, in, vport_number, ft->vport); MLX5_SET(delete_fte_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(delete_fte_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(delete_fte_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); return mlx5_cmd_exec_in(dev, delete_fte, in); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2ca3bddbdf05..0a6031a64c6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -939,10 +939,10 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f return fg; } -static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, - enum fs_flow_table_type table_type, - enum fs_flow_table_op_mod op_mod, - u32 flags) +static struct mlx5_flow_table * +alloc_flow_table(struct mlx5_flow_table_attr *ft_attr, u16 vport, + enum fs_flow_table_type table_type, + enum fs_flow_table_op_mod op_mod) { struct mlx5_flow_table *ft; int ret; @@ -957,12 +957,13 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, return ERR_PTR(ret); } - ft->level = level; + ft->level = ft_attr->level; ft->node.type = FS_TYPE_FLOW_TABLE; ft->op_mod = op_mod; ft->type = table_type; ft->vport = vport; - ft->flags = flags; + ft->esw_owner_vhca_id = ft_attr->esw_owner_vhca_id; + ft->flags = ft_attr->flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); @@ -1370,10 +1371,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa /* The level is related to the * priority level range. */ - ft = alloc_flow_table(ft_attr->level, - vport, - root->table_type, - op_mod, ft_attr->flags); + ft = alloc_flow_table(ft_attr, vport, root->table_type, op_mod); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto unlock_root; @@ -3310,6 +3308,62 @@ err: return ret; } +static bool mlx5_fs_ns_is_empty(struct mlx5_flow_namespace *ns) +{ + struct fs_prio *iter_prio; + + fs_for_each_prio(iter_prio, ns) { + if (iter_prio->num_ft) + return false; + } + + return true; +} + +int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev, + struct mlx5_core_dev *new_dev, + enum fs_flow_table_type table_type) +{ + struct mlx5_flow_root_namespace **root; + int total_vports; + int i; + + switch (table_type) { + case FS_FT_RDMA_TRANSPORT_TX: + root = dev->priv.steering->rdma_transport_tx_root_ns; + total_vports = dev->priv.steering->rdma_transport_tx_vports; + break; + case FS_FT_RDMA_TRANSPORT_RX: + root = dev->priv.steering->rdma_transport_rx_root_ns; + total_vports = dev->priv.steering->rdma_transport_rx_vports; + break; + default: + WARN_ON_ONCE(true); + return -EINVAL; + } + + for (i = 0; i < total_vports; i++) { + mutex_lock(&root[i]->chain_lock); + if (!mlx5_fs_ns_is_empty(&root[i]->ns)) { + mutex_unlock(&root[i]->chain_lock); + goto err; + } + root[i]->dev = new_dev; + mutex_unlock(&root[i]->chain_lock); + } + return 0; +err: + while (i--) { + mutex_lock(&root[i]->chain_lock); + root[i]->dev = dev; + mutex_unlock(&root[i]->chain_lock); + } + /* If you hit this error try destroying all flow tables and try again */ + mlx5_core_err(dev, "Failed to set root device for RDMA TRANSPORT\n"); + return -EINVAL; +} +EXPORT_SYMBOL(mlx5_fs_set_root_dev); + static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering) { struct mlx5_core_dev *dev = steering->dev; @@ -3779,7 +3833,8 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id, } static int mlx5_fs_mode_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 8458ce203dac..1c6591425260 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -103,24 +103,6 @@ enum fs_node_type { FS_TYPE_FLOW_DEST }; -enum fs_flow_table_type { - FS_FT_NIC_RX = 0x0, - FS_FT_NIC_TX = 0x1, - FS_FT_ESW_EGRESS_ACL = 0x2, - FS_FT_ESW_INGRESS_ACL = 0x3, - FS_FT_FDB = 0X4, - FS_FT_SNIFFER_RX = 0X5, - FS_FT_SNIFFER_TX = 0X6, - FS_FT_RDMA_RX = 0X7, - FS_FT_RDMA_TX = 0X8, - FS_FT_PORT_SEL = 0X9, - FS_FT_FDB_RX = 0xa, - FS_FT_FDB_TX = 0xb, - FS_FT_RDMA_TRANSPORT_RX = 0xd, - FS_FT_RDMA_TRANSPORT_TX = 0xe, - FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX, -}; - enum fs_flow_table_op_mod { FS_FT_OP_MOD_NORMAL, FS_FT_OP_MOD_LAG_DEMUX, @@ -205,6 +187,7 @@ struct mlx5_flow_table { }; u32 id; u16 vport; + u16 esw_owner_vhca_id; unsigned int max_fte; unsigned int level; enum fs_flow_table_type type; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 89e399606877..2bceb42c98cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -73,7 +73,8 @@ static int mlx5_fw_reset_enable_remote_dev_reset_set(struct devlink *devlink, u3 } static int mlx5_fw_reset_enable_remote_dev_reset_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); struct mlx5_fw_reset *fw_reset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 4b3430ac3905..3b2f54ca30a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -266,21 +266,18 @@ static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return mlx5e_ethtool_set_rxnfc(priv, cmd); } +static u32 mlx5i_get_rx_ring_count(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + + return priv->channels.params.num_channels; +} + static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = mlx5i_epriv(dev); - /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part - * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, - * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc - * is compiled out via CONFIG_MLX5_EN_RXNFC=n. - */ - if (info->cmd == ETHTOOL_GRXRINGS) { - info->data = priv->channels.params.num_channels; - return 0; - } - return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } @@ -304,6 +301,7 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .set_rxfh_fields = mlx5i_set_rxfh_fields, .get_rxnfc = mlx5i_get_rxnfc, .set_rxnfc = mlx5i_set_rxnfc, + .get_rx_ring_count = mlx5i_get_rx_ring_count, .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c index 459a0b4d08e6..19bb620b7436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/nv_param.c @@ -8,6 +8,8 @@ enum { MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CONF = 0x80, MLX5_CLASS_0_CTRL_ID_NV_GLOBAL_PCI_CAP = 0x81, MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CONFIG = 0x10a, + MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CAP = 0x10b, + MLX5_CLASS_0_CTRL_ID_NV_SW_ACCELERATE_CONF = 0x11d, MLX5_CLASS_3_CTRL_ID_NV_PF_PCI_CONF = 0x80, }; @@ -32,6 +34,12 @@ union mlx5_ifc_config_item_type_auto_bits { u8 reserved_at_0[0x20]; }; +enum { + MLX5_ACCESS_MODE_NEXT = 0, + MLX5_ACCESS_MODE_CURRENT, + MLX5_ACCESS_MODE_DEFAULT, +}; + struct mlx5_ifc_config_item_bits { u8 valid[0x2]; u8 priority[0x2]; @@ -123,6 +131,17 @@ struct mlx5_ifc_nv_sw_offload_conf_bits { u8 lro_log_timeout0[0x4]; }; +struct mlx5_ifc_nv_sw_offload_cap_bits { + u8 reserved_at_0[0x19]; + u8 swp_l4_csum_mode_l4_only[0x1]; + u8 reserved_at_1a[0x6]; +}; + +struct mlx5_ifc_nv_sw_accelerate_conf_bits { + u8 swp_l4_csum_mode[0x2]; + u8 reserved_at_2[0x3e]; +}; + #define MNVDA_HDR_SZ \ (MLX5_ST_SZ_BYTES(mnvda_reg) - \ MLX5_BYTE_OFF(mnvda_reg, configuration_item_data)) @@ -195,12 +214,39 @@ mlx5_nv_param_read_sw_offload_conf(struct mlx5_core_dev *dev, void *mnvda, return mlx5_nv_param_read(dev, mnvda, len); } +static int +mlx5_nv_param_read_sw_offload_cap(struct mlx5_core_dev *dev, void *mnvda, + size_t len) +{ + MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0); + MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index, + MLX5_CLASS_0_CTRL_ID_NV_SW_OFFLOAD_CAP); + MLX5_SET_CFG_HDR_LEN(mnvda, nv_sw_offload_cap); + + return mlx5_nv_param_read(dev, mnvda, len); +} + +static int +mlx5_nv_param_read_sw_accelerate_conf(struct mlx5_core_dev *dev, void *mnvda, + size_t len, int access_mode) +{ + MLX5_SET_CFG_ITEM_TYPE(global, mnvda, type_class, 0); + MLX5_SET_CFG_ITEM_TYPE(global, mnvda, parameter_index, + MLX5_CLASS_0_CTRL_ID_NV_SW_ACCELERATE_CONF); + MLX5_SET_CFG_HDR_LEN(mnvda, nv_sw_accelerate_conf); + MLX5_SET(mnvda_reg, mnvda, configuration_item_header.access_mode, + access_mode); + + return mlx5_nv_param_read(dev, mnvda, len); +} + static const char *const cqe_compress_str[] = { "balanced", "aggressive" }; static int mlx5_nv_param_devlink_cqe_compress_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {}; @@ -268,6 +314,182 @@ mlx5_nv_param_devlink_cqe_compress_set(struct devlink *devlink, u32 id, return mlx5_nv_param_write(dev, mnvda, sizeof(mnvda)); } +enum swp_l4_csum_mode { + SWP_L4_CSUM_MODE_DEFAULT = 0, + SWP_L4_CSUM_MODE_FULL_CSUM = 1, + SWP_L4_CSUM_MODE_L4_ONLY = 2, +}; + +static const char *const + swp_l4_csum_mode_str[] = { "default", "full_csum", "l4_only" }; + +static int +mlx5_swp_l4_csum_mode_get(struct devlink *devlink, u32 id, + int access_mode, u8 *value, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {}; + void *data; + int err; + + err = mlx5_nv_param_read_sw_accelerate_conf(dev, mnvda, sizeof(mnvda), + access_mode); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to read sw_accelerate_conf mnvda reg"); + return err; + } + + data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data); + *value = MLX5_GET(nv_sw_accelerate_conf, data, swp_l4_csum_mode); + + if (*value >= ARRAY_SIZE(swp_l4_csum_mode_str)) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Invalid swp_l4_csum_mode value %u read from device", + *value); + return -EINVAL; + } + + return 0; +} + +static int +mlx5_devlink_swp_l4_csum_mode_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + u8 value; + int err; + + err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_NEXT, + &value, extack); + if (err) + return err; + + strscpy(ctx->val.vstr, swp_l4_csum_mode_str[value], + sizeof(ctx->val.vstr)); + return 0; +} + +static int +mlx5_devlink_swp_l4_csum_mode_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + u32 cap[MLX5_ST_SZ_DW(mnvda_reg)] = {}; + void *data; + int err, i; + + for (i = 0; i < ARRAY_SIZE(swp_l4_csum_mode_str); i++) { + if (!strcmp(val.vstr, swp_l4_csum_mode_str[i])) + break; + } + + if (i >= ARRAY_SIZE(swp_l4_csum_mode_str) || + i == SWP_L4_CSUM_MODE_DEFAULT) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid value, supported values are full_csum/l4_only"); + return -EINVAL; + } + + if (i == SWP_L4_CSUM_MODE_L4_ONLY) { + err = mlx5_nv_param_read_sw_offload_cap(dev, cap, sizeof(cap)); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to read sw_offload_cap"); + return err; + } + + data = MLX5_ADDR_OF(mnvda_reg, cap, configuration_item_data); + if (!MLX5_GET(nv_sw_offload_cap, data, swp_l4_csum_mode_l4_only)) { + NL_SET_ERR_MSG_MOD(extack, + "l4_only mode is not supported on this device"); + return -EOPNOTSUPP; + } + } + + return 0; +} + +static int +mlx5_swp_l4_csum_mode_set(struct devlink *devlink, u32 id, u8 value, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {}; + void *data; + int err; + + err = mlx5_nv_param_read_sw_accelerate_conf(dev, mnvda, sizeof(mnvda), + MLX5_ACCESS_MODE_NEXT); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to read sw_accelerate_conf mnvda reg"); + return err; + } + + data = MLX5_ADDR_OF(mnvda_reg, mnvda, configuration_item_data); + MLX5_SET(nv_sw_accelerate_conf, data, swp_l4_csum_mode, value); + + err = mlx5_nv_param_write(dev, mnvda, sizeof(mnvda)); + if (err) + NL_SET_ERR_MSG_MOD(extack, + "Failed to write sw_accelerate_conf mnvda reg"); + + return err; +} + +static int +mlx5_devlink_swp_l4_csum_mode_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + u8 value; + + if (!strcmp(ctx->val.vstr, "full_csum")) + value = SWP_L4_CSUM_MODE_FULL_CSUM; + else + value = SWP_L4_CSUM_MODE_L4_ONLY; + + return mlx5_swp_l4_csum_mode_set(devlink, id, value, extack); +} + +static int +mlx5_devlink_swp_l4_csum_mode_get_default(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + u8 value; + int err; + + err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_DEFAULT, + &value, extack); + if (err) + return err; + + strscpy(ctx->val.vstr, swp_l4_csum_mode_str[value], + sizeof(ctx->val.vstr)); + return 0; +} + +static int +mlx5_devlink_swp_l4_csum_mode_set_default(struct devlink *devlink, u32 id, + enum devlink_param_cmode cmode, + struct netlink_ext_ack *extack) +{ + u8 value; + int err; + + err = mlx5_swp_l4_csum_mode_get(devlink, id, MLX5_ACCESS_MODE_DEFAULT, + &value, extack); + if (err) + return err; + + return mlx5_swp_l4_csum_mode_set(devlink, id, value, extack); +} + static int mlx5_nv_param_read_global_pci_conf(struct mlx5_core_dev *dev, void *mnvda, size_t len) { @@ -302,7 +524,8 @@ static int mlx5_nv_param_read_per_host_pf_conf(struct mlx5_core_dev *dev, } static int mlx5_devlink_enable_sriov_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {}; @@ -413,7 +636,8 @@ static int mlx5_devlink_enable_sriov_set(struct devlink *devlink, u32 id, } static int mlx5_devlink_total_vfs_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); u32 mnvda[MLX5_ST_SZ_DW(mnvda_reg)] = {}; @@ -545,6 +769,14 @@ static const struct devlink_param mlx5_nv_param_devlink_params[] = { mlx5_nv_param_devlink_cqe_compress_get, mlx5_nv_param_devlink_cqe_compress_set, mlx5_nv_param_devlink_cqe_compress_validate), + DEVLINK_PARAM_DRIVER_WITH_DEFAULTS(MLX5_DEVLINK_PARAM_ID_SWP_L4_CSUM_MODE, + "swp_l4_csum_mode", DEVLINK_PARAM_TYPE_STRING, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + mlx5_devlink_swp_l4_csum_mode_get, + mlx5_devlink_swp_l4_csum_mode_set, + mlx5_devlink_swp_l4_csum_mode_validate, + mlx5_devlink_swp_l4_csum_mode_get_default, + mlx5_devlink_swp_l4_csum_mode_set_default), }; int mlx5_nv_param_register_dl_params(struct devlink *devlink) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c index 47fe215f66bf..ef06fe6cbb51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c @@ -19,13 +19,16 @@ struct mlx5_st { struct mutex lock; struct xa_limit index_limit; struct xarray idx_xa; /* key == index, value == struct mlx5_st_idx_data */ + u8 direct_mode : 1; }; struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) { struct pci_dev *pdev = dev->pdev; struct mlx5_st *st; + u8 direct_mode = 0; u16 num_entries; + u32 tbl_loc; int ret; if (!MLX5_CAP_GEN(dev, mkey_pcie_tph)) @@ -40,10 +43,16 @@ struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) if (!pdev->tph_cap) return NULL; - num_entries = pcie_tph_get_st_table_size(pdev); - /* We need a reserved entry for non TPH cases */ - if (num_entries < 2) - return NULL; + tbl_loc = pcie_tph_get_st_table_loc(pdev); + if (tbl_loc == PCI_TPH_LOC_NONE) + direct_mode = 1; + + if (!direct_mode) { + num_entries = pcie_tph_get_st_table_size(pdev); + /* We need a reserved entry for non TPH cases */ + if (num_entries < 2) + return NULL; + } /* The OS doesn't support ST */ ret = pcie_enable_tph(pdev, PCI_TPH_ST_DS_MODE); @@ -56,6 +65,10 @@ struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) mutex_init(&st->lock); xa_init_flags(&st->idx_xa, XA_FLAGS_ALLOC); + st->direct_mode = direct_mode; + if (st->direct_mode) + return st; + /* entry 0 is reserved for non TPH cases */ st->index_limit.min = MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX + 1; st->index_limit.max = num_entries - 1; @@ -96,6 +109,11 @@ int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type, if (ret) return ret; + if (st->direct_mode) { + *st_index = tag; + return 0; + } + mutex_lock(&st->lock); xa_for_each(&st->idx_xa, index, idx_data) { @@ -145,6 +163,9 @@ int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index) if (!st) return -EOPNOTSUPP; + if (st->direct_mode) + return 0; + mutex_lock(&st->lock); idx_data = xa_load(&st->idx_xa, st_index); if (WARN_ON_ONCE(!idx_data)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index d55e15c1f380..304912637c35 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -149,7 +149,7 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) struct mlx5_vxlan *vxlan; if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev)) - return ERR_PTR(-ENOTSUPP); + return ERR_PTR(-EOPNOTSUPP); vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); if (!vxlan) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c904696cbc3a..024339ce41f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1010,16 +1010,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_irq_cleanup; } - err = mlx5_events_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize events\n"); - goto err_eq_cleanup; - } - err = mlx5_fw_reset_init(dev); if (err) { mlx5_core_err(dev, "failed to initialize fw reset events\n"); - goto err_events_cleanup; + goto err_eq_cleanup; } mlx5_cq_debugfs_init(dev); @@ -1121,8 +1115,6 @@ err_tables_cleanup: mlx5_cleanup_reserved_gids(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_fw_reset_cleanup(dev); -err_events_cleanup: - mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); err_irq_cleanup: @@ -1155,7 +1147,6 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) mlx5_cleanup_reserved_gids(dev); mlx5_cq_debugfs_cleanup(dev); mlx5_fw_reset_cleanup(dev); - mlx5_events_cleanup(dev); mlx5_eq_table_cleanup(dev); mlx5_irq_table_cleanup(dev); mlx5_devcom_unregister_device(dev->priv.devc); @@ -1386,12 +1377,6 @@ static int mlx5_load(struct mlx5_core_dev *dev) mlx5_vhca_event_start(dev); - err = mlx5_sf_hw_table_create(dev); - if (err) { - mlx5_core_err(dev, "sf table create failed %d\n", err); - goto err_vhca; - } - err = mlx5_ec_init(dev); if (err) { mlx5_core_err(dev, "Failed to init embedded CPU\n"); @@ -1420,8 +1405,6 @@ err_sriov: mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); err_ec: - mlx5_sf_hw_table_destroy(dev); -err_vhca: mlx5_vhca_event_stop(dev); err_set_hca: mlx5_fs_core_cleanup(dev); @@ -1447,12 +1430,12 @@ static void mlx5_unload(struct mlx5_core_dev *dev) { mlx5_eswitch_disable(dev->priv.eswitch); mlx5_devlink_traps_unregister(priv_to_devlink(dev)); + mlx5_vhca_event_stop(dev); mlx5_sf_dev_table_destroy(dev); mlx5_sriov_detach(dev); mlx5_lag_remove_mdev(dev); mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); - mlx5_vhca_event_stop(dev); mlx5_fs_core_cleanup(dev); mlx5_fpga_device_stop(dev); mlx5_rsc_dump_cleanup(dev); @@ -1833,6 +1816,50 @@ static int vhca_id_show(struct seq_file *file, void *priv) DEFINE_SHOW_ATTRIBUTE(vhca_id); +static int mlx5_notifiers_init(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_events_init(dev); + if (err) { + mlx5_core_err(dev, "failed to initialize events\n"); + return err; + } + + BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.esw_n_head); + mlx5_vhca_state_notifier_init(dev); + + err = mlx5_sf_hw_notifier_init(dev); + if (err) + goto err_sf_hw_notifier; + + err = mlx5_sf_notifiers_init(dev); + if (err) + goto err_sf_notifiers; + + err = mlx5_sf_dev_notifier_init(dev); + if (err) + goto err_sf_dev_notifier; + + return 0; + +err_sf_dev_notifier: + mlx5_sf_notifiers_cleanup(dev); +err_sf_notifiers: + mlx5_sf_hw_notifier_cleanup(dev); +err_sf_hw_notifier: + mlx5_events_cleanup(dev); + return err; +} + +static void mlx5_notifiers_cleanup(struct mlx5_core_dev *dev) +{ + mlx5_sf_dev_notifier_cleanup(dev); + mlx5_sf_notifiers_cleanup(dev); + mlx5_sf_hw_notifier_cleanup(dev); + mlx5_events_cleanup(dev); +} + int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) { struct mlx5_priv *priv = &dev->priv; @@ -1888,6 +1915,10 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) if (err) goto err_hca_caps; + err = mlx5_notifiers_init(dev); + if (err) + goto err_hca_caps; + /* The conjunction of sw_vhca_id with sw_owner_id will be a global * unique id per function which uses mlx5_core. * Those values are supplied to FW as part of the init HCA command to @@ -1930,6 +1961,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) if (priv->sw_vhca_id > 0) ida_free(&sw_vhca_ida, dev->priv.sw_vhca_id); + mlx5_notifiers_cleanup(dev); mlx5_hca_caps_free(dev); mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index acef7d0ffa09..cfebc110c02f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -357,11 +357,11 @@ int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable); void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported, bool *enabled); int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, - u16 offset, u16 size, u8 *data); + u16 offset, u16 size, u8 *data, u8 *status); int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev, struct mlx5_module_eeprom_query_params *params, - u8 *data); + u8 *data, u8 *status); int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index e18a850c615c..aa3b5878e3da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -324,10 +324,8 @@ err_xa: free_irq(irq->map.virq, &irq->nh); err_req_irq: #ifdef CONFIG_RFS_ACCEL - if (i && rmap && *rmap) { - free_irq_cpu_rmap(*rmap); - *rmap = NULL; - } + if (i && rmap && *rmap) + irq_cpu_rmap_remove(*rmap, irq->map.virq); err_irq_rmap: #endif if (i && pci_msix_can_alloc_dyn(dev->pdev)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index aa9f2b0a77d3..85a9e534f442 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -289,11 +289,11 @@ int mlx5_query_module_num(struct mlx5_core_dev *dev, int *module_num) } static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num, - u8 *module_id) + u8 *module_id, u8 *status) { u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {}; u32 out[MLX5_ST_SZ_DW(mcia_reg)]; - int err, status; + int err; u8 *ptr; MLX5_SET(mcia_reg, in, i2c_device_address, MLX5_I2C_ADDR_LOW); @@ -308,12 +308,12 @@ static int mlx5_query_module_id(struct mlx5_core_dev *dev, int module_num, if (err) return err; - status = MLX5_GET(mcia_reg, out, status); - if (status) { - mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n", - status); + if (MLX5_GET(mcia_reg, out, status)) { + if (status) + *status = MLX5_GET(mcia_reg, out, status); return -EIO; } + ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); *module_id = ptr[0]; @@ -370,13 +370,14 @@ static int mlx5_mcia_max_bytes(struct mlx5_core_dev *dev) } static int mlx5_query_mcia(struct mlx5_core_dev *dev, - struct mlx5_module_eeprom_query_params *params, u8 *data) + struct mlx5_module_eeprom_query_params *params, + u8 *data, u8 *status) { u32 in[MLX5_ST_SZ_DW(mcia_reg)] = {}; u32 out[MLX5_ST_SZ_DW(mcia_reg)]; - int status, err; void *ptr; u16 size; + int err; size = min_t(int, params->size, mlx5_mcia_max_bytes(dev)); @@ -392,12 +393,9 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev, if (err) return err; - status = MLX5_GET(mcia_reg, out, status); - if (status) { - mlx5_core_err(dev, "query_mcia_reg failed: status: 0x%x\n", - status); + *status = MLX5_GET(mcia_reg, out, status); + if (*status) return -EIO; - } ptr = MLX5_ADDR_OF(mcia_reg, out, dword_0); memcpy(data, ptr, size); @@ -406,7 +404,7 @@ static int mlx5_query_mcia(struct mlx5_core_dev *dev, } int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, - u16 offset, u16 size, u8 *data) + u16 offset, u16 size, u8 *data, u8 *status) { struct mlx5_module_eeprom_query_params query = {0}; u8 module_id; @@ -416,7 +414,8 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, if (err) return err; - err = mlx5_query_module_id(dev, query.module_number, &module_id); + err = mlx5_query_module_id(dev, query.module_number, &module_id, + status); if (err) return err; @@ -441,12 +440,12 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, query.size = size; query.offset = offset; - return mlx5_query_mcia(dev, &query, data); + return mlx5_query_mcia(dev, &query, data, status); } int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev, struct mlx5_module_eeprom_query_params *params, - u8 *data) + u8 *data, u8 *status) { int err; @@ -460,7 +459,7 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev, return -EINVAL; } - return mlx5_query_mcia(dev, params, data); + return mlx5_query_mcia(dev, params, data, status); } static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc, @@ -1109,6 +1108,7 @@ mlx5e_ext_link_info[MLX5E_EXT_LINK_MODES_NUMBER] = { [MLX5E_200GAUI_1_200GBASE_CR1_KR1] = {.speed = 200000, .lanes = 1}, [MLX5E_400GAUI_2_400GBASE_CR2_KR2] = {.speed = 400000, .lanes = 2}, [MLX5E_800GAUI_4_800GBASE_CR4_KR4] = {.speed = 800000, .lanes = 4}, + [MLX5E_1600TAUI_8_1600TBASE_CR8_KR8] = {.speed = 1600000, .lanes = 8}, }; int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 99219ea52c4b..f310bde3d11f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -16,7 +16,6 @@ struct mlx5_sf_dev_table { struct xarray devices; phys_addr_t base_address; u64 sf_bar_length; - struct notifier_block nb; struct workqueue_struct *active_wq; struct work_struct work; u8 stop_active_wq:1; @@ -156,18 +155,23 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de static int mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data) { - struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb); + struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev, + priv.sf_dev_nb); + struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; const struct mlx5_vhca_state_event *event = data; struct mlx5_sf_dev *sf_dev; u16 max_functions; u16 sf_index; u16 base_id; - max_functions = mlx5_sf_max_functions(table->dev); + if (!table) + return 0; + + max_functions = mlx5_sf_max_functions(dev); if (!max_functions) return 0; - base_id = mlx5_sf_start_function_id(table->dev); + base_id = mlx5_sf_start_function_id(dev); if (event->function_id < base_id || event->function_id >= (base_id + max_functions)) return 0; @@ -177,19 +181,19 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ case MLX5_VHCA_STATE_INVALID: case MLX5_VHCA_STATE_ALLOCATED: if (sf_dev) - mlx5_sf_dev_del(table->dev, sf_dev, sf_index); + mlx5_sf_dev_del(dev, sf_dev, sf_index); break; case MLX5_VHCA_STATE_TEARDOWN_REQUEST: if (sf_dev) - mlx5_sf_dev_del(table->dev, sf_dev, sf_index); + mlx5_sf_dev_del(dev, sf_dev, sf_index); else - mlx5_core_err(table->dev, + mlx5_core_err(dev, "SF DEV: teardown state for invalid dev index=%d sfnum=0x%x\n", sf_index, event->sw_function_id); break; case MLX5_VHCA_STATE_ACTIVE: if (!sf_dev) - mlx5_sf_dev_add(table->dev, sf_index, event->function_id, + mlx5_sf_dev_add(dev, sf_index, event->function_id, event->sw_function_id); break; default: @@ -315,6 +319,15 @@ static void mlx5_sf_dev_destroy_active_works(struct mlx5_sf_dev_table *table) } } +int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_sf(dev)) + return 0; + + dev->priv.sf_dev_nb.notifier_call = mlx5_sf_dev_state_change_handler; + return mlx5_vhca_event_notifier_register(dev, &dev->priv.sf_dev_nb); +} + void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) { struct mlx5_sf_dev_table *table; @@ -329,17 +342,12 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) goto table_err; } - table->nb.notifier_call = mlx5_sf_dev_state_change_handler; table->dev = dev; table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12); table->base_address = pci_resource_start(dev->pdev, 2); xa_init(&table->devices); dev->priv.sf_dev_table = table; - err = mlx5_vhca_event_notifier_register(dev, &table->nb); - if (err) - goto vhca_err; - err = mlx5_sf_dev_create_active_works(table); if (err) goto add_active_err; @@ -351,10 +359,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) arm_err: mlx5_sf_dev_destroy_active_works(table); -add_active_err: - mlx5_vhca_event_notifier_unregister(dev, &table->nb); mlx5_vhca_event_work_queues_flush(dev); -vhca_err: +add_active_err: kfree(table); dev->priv.sf_dev_table = NULL; table_err: @@ -372,6 +378,14 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table) } } +void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_sf(dev)) + return; + + mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_dev_nb); +} + void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) { struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table; @@ -380,8 +394,6 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) return; mlx5_sf_dev_destroy_active_works(table); - mlx5_vhca_event_notifier_unregister(dev, &table->nb); - mlx5_vhca_event_work_queues_flush(dev); /* Now that event handler is not running, it is safe to destroy * the sf device without race. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h index b99131e95e37..3ab0449c770c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h @@ -25,7 +25,9 @@ struct mlx5_sf_peer_devlink_event_ctx { int err; }; +int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev); void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev); +void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev); void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev); int mlx5_sf_driver_register(void); @@ -35,10 +37,19 @@ bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev); #else +static inline int mlx5_sf_dev_notifier_init(struct mlx5_core_dev *dev) +{ + return 0; +} + static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) { } +static inline void mlx5_sf_dev_notifier_cleanup(struct mlx5_core_dev *dev) +{ +} + static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) { } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 3304f25cc805..b82323b8449e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -31,9 +31,6 @@ struct mlx5_sf_table { struct mlx5_core_dev *dev; /* To refer from notifier context. */ struct xarray function_ids; /* function id based lookup. */ struct mutex sf_state_lock; /* Serializes sf state among user cmds & vhca event handler. */ - struct notifier_block esw_nb; - struct notifier_block vhca_nb; - struct notifier_block mdev_nb; }; static struct mlx5_sf * @@ -391,11 +388,16 @@ static bool mlx5_sf_state_update_check(const struct mlx5_sf *sf, u8 new_state) static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data) { - struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, vhca_nb); + struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev, + priv.sf_table_vhca_nb); + struct mlx5_sf_table *table = dev->priv.sf_table; const struct mlx5_vhca_state_event *event = data; bool update = false; struct mlx5_sf *sf; + if (!table) + return 0; + mutex_lock(&table->sf_state_lock); sf = mlx5_sf_lookup_by_function_id(table, event->function_id); if (!sf) @@ -407,7 +409,7 @@ static int mlx5_sf_vhca_event(struct notifier_block *nb, unsigned long opcode, v update = mlx5_sf_state_update_check(sf, event->new_vhca_state); if (update) sf->hw_state = event->new_vhca_state; - trace_mlx5_sf_update_state(table->dev, sf->port_index, sf->controller, + trace_mlx5_sf_update_state(dev, sf->port_index, sf->controller, sf->hw_fn_id, sf->hw_state); unlock: mutex_unlock(&table->sf_state_lock); @@ -425,12 +427,16 @@ static void mlx5_sf_del_all(struct mlx5_sf_table *table) static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data) { - struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb); + struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev, + priv.sf_table_esw_nb); const struct mlx5_esw_event_info *mode = data; + if (!dev->priv.sf_table) + return 0; + switch (mode->new_mode) { case MLX5_ESWITCH_LEGACY: - mlx5_sf_del_all(table); + mlx5_sf_del_all(dev->priv.sf_table); break; default: break; @@ -441,15 +447,16 @@ static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, voi static int mlx5_sf_mdev_event(struct notifier_block *nb, unsigned long event, void *data) { - struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, mdev_nb); + struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev, + priv.sf_table_mdev_nb); struct mlx5_sf_peer_devlink_event_ctx *event_ctx = data; + struct mlx5_sf_table *table = dev->priv.sf_table; int ret = NOTIFY_DONE; struct mlx5_sf *sf; - if (event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK) + if (!table || event != MLX5_DRIVER_EVENT_SF_PEER_DEVLINK) return NOTIFY_DONE; - mutex_lock(&table->sf_state_lock); sf = mlx5_sf_lookup_by_function_id(table, event_ctx->fn_id); if (!sf) @@ -464,10 +471,40 @@ out: return ret; } +int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev) +{ + int err; + + if (mlx5_core_is_sf(dev)) + return 0; + + dev->priv.sf_table_esw_nb.notifier_call = mlx5_sf_esw_event; + err = mlx5_esw_event_notifier_register(dev, &dev->priv.sf_table_esw_nb); + if (err) + return err; + + dev->priv.sf_table_vhca_nb.notifier_call = mlx5_sf_vhca_event; + err = mlx5_vhca_event_notifier_register(dev, + &dev->priv.sf_table_vhca_nb); + if (err) + goto vhca_err; + + dev->priv.sf_table_mdev_nb.notifier_call = mlx5_sf_mdev_event; + err = mlx5_blocking_notifier_register(dev, &dev->priv.sf_table_mdev_nb); + if (err) + goto mdev_err; + + return 0; +mdev_err: + mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb); +vhca_err: + mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb); + return err; +} + int mlx5_sf_table_init(struct mlx5_core_dev *dev) { struct mlx5_sf_table *table; - int err; if (!mlx5_sf_table_supported(dev) || !mlx5_vhca_event_supported(dev)) return 0; @@ -480,28 +517,18 @@ int mlx5_sf_table_init(struct mlx5_core_dev *dev) table->dev = dev; xa_init(&table->function_ids); dev->priv.sf_table = table; - table->esw_nb.notifier_call = mlx5_sf_esw_event; - err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb); - if (err) - goto reg_err; - - table->vhca_nb.notifier_call = mlx5_sf_vhca_event; - err = mlx5_vhca_event_notifier_register(table->dev, &table->vhca_nb); - if (err) - goto vhca_err; - - table->mdev_nb.notifier_call = mlx5_sf_mdev_event; - mlx5_blocking_notifier_register(dev, &table->mdev_nb); return 0; +} -vhca_err: - mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb); -reg_err: - mutex_destroy(&table->sf_state_lock); - kfree(table); - dev->priv.sf_table = NULL; - return err; +void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_sf(dev)) + return; + + mlx5_blocking_notifier_unregister(dev, &dev->priv.sf_table_mdev_nb); + mlx5_vhca_event_notifier_unregister(dev, &dev->priv.sf_table_vhca_nb); + mlx5_esw_event_notifier_unregister(dev, &dev->priv.sf_table_esw_nb); } void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev) @@ -511,9 +538,6 @@ void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev) if (!table) return; - mlx5_blocking_notifier_unregister(dev, &table->mdev_nb); - mlx5_vhca_event_notifier_unregister(table->dev, &table->vhca_nb); - mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb); mutex_destroy(&table->sf_state_lock); WARN_ON(!xa_empty(&table->function_ids)); kfree(table); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 1f613320fe07..bd968f3b3855 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -30,9 +30,7 @@ enum mlx5_sf_hwc_index { }; struct mlx5_sf_hw_table { - struct mlx5_core_dev *dev; struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */ - struct notifier_block vhca_nb; struct mlx5_sf_hwc_table hwc[MLX5_SF_HWC_MAX]; }; @@ -71,14 +69,16 @@ mlx5_sf_table_fn_to_hwc(struct mlx5_sf_hw_table *table, u16 fn_id) return NULL; } -static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 controller, +static int mlx5_sf_hw_table_id_alloc(struct mlx5_core_dev *dev, + struct mlx5_sf_hw_table *table, + u32 controller, u32 usr_sfnum) { struct mlx5_sf_hwc_table *hwc; int free_idx = -1; int i; - hwc = mlx5_sf_controller_to_hwc(table->dev, controller); + hwc = mlx5_sf_controller_to_hwc(dev, controller); if (!hwc->sfs) return -ENOSPC; @@ -100,11 +100,13 @@ static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 control return free_idx; } -static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id) +static void mlx5_sf_hw_table_id_free(struct mlx5_core_dev *dev, + struct mlx5_sf_hw_table *table, + u32 controller, int id) { struct mlx5_sf_hwc_table *hwc; - hwc = mlx5_sf_controller_to_hwc(table->dev, controller); + hwc = mlx5_sf_controller_to_hwc(dev, controller); hwc->sfs[id].allocated = false; hwc->sfs[id].pending_delete = false; } @@ -120,7 +122,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr return -EOPNOTSUPP; mutex_lock(&table->table_lock); - sw_id = mlx5_sf_hw_table_id_alloc(table, controller, usr_sfnum); + sw_id = mlx5_sf_hw_table_id_alloc(dev, table, controller, usr_sfnum); if (sw_id < 0) { err = sw_id; goto exist_err; @@ -151,7 +153,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr vhca_err: mlx5_cmd_dealloc_sf(dev, hw_fn_id); err: - mlx5_sf_hw_table_id_free(table, controller, sw_id); + mlx5_sf_hw_table_id_free(dev, table, controller, sw_id); exist_err: mutex_unlock(&table->table_lock); return err; @@ -165,7 +167,7 @@ void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id) mutex_lock(&table->table_lock); hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id); mlx5_cmd_dealloc_sf(dev, hw_fn_id); - mlx5_sf_hw_table_id_free(table, controller, id); + mlx5_sf_hw_table_id_free(dev, table, controller, id); mutex_unlock(&table->table_lock); } @@ -216,10 +218,12 @@ static void mlx5_sf_hw_table_hwc_dealloc_all(struct mlx5_core_dev *dev, } } -static void mlx5_sf_hw_table_dealloc_all(struct mlx5_sf_hw_table *table) +static void mlx5_sf_hw_table_dealloc_all(struct mlx5_core_dev *dev, + struct mlx5_sf_hw_table *table) { - mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_EXTERNAL]); - mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_LOCAL]); + mlx5_sf_hw_table_hwc_dealloc_all(dev, + &table->hwc[MLX5_SF_HWC_EXTERNAL]); + mlx5_sf_hw_table_hwc_dealloc_all(dev, &table->hwc[MLX5_SF_HWC_LOCAL]); } static int mlx5_sf_hw_table_hwc_init(struct mlx5_sf_hwc_table *hwc, u16 max_fn, u16 base_id) @@ -301,7 +305,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) } mutex_init(&table->table_lock); - table->dev = dev; dev->priv.sf_hw_table = table; base_id = mlx5_sf_start_function_id(dev); @@ -338,19 +341,22 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev) mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]); mutex_destroy(&table->table_lock); kfree(table); + dev->priv.sf_hw_table = NULL; res_unregister: mlx5_sf_hw_table_res_unregister(dev); } static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode, void *data) { - struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb); + struct mlx5_core_dev *dev = container_of(nb, struct mlx5_core_dev, + priv.sf_hw_table_vhca_nb); + struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; const struct mlx5_vhca_state_event *event = data; struct mlx5_sf_hwc_table *hwc; struct mlx5_sf_hw *sf_hw; u16 sw_id; - if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED) + if (!table || event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED) return 0; hwc = mlx5_sf_table_fn_to_hwc(table, event->function_id); @@ -365,20 +371,28 @@ static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode * Hence recycle the sf hardware id for reuse. */ if (sf_hw->allocated && sf_hw->pending_delete) - mlx5_sf_hw_table_hwc_sf_free(table->dev, hwc, sw_id); + mlx5_sf_hw_table_hwc_sf_free(dev, hwc, sw_id); mutex_unlock(&table->table_lock); return 0; } -int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev) +int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev) { - struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table; - - if (!table) + if (mlx5_core_is_sf(dev)) return 0; - table->vhca_nb.notifier_call = mlx5_sf_hw_vhca_event; - return mlx5_vhca_event_notifier_register(dev, &table->vhca_nb); + dev->priv.sf_hw_table_vhca_nb.notifier_call = mlx5_sf_hw_vhca_event; + return mlx5_vhca_event_notifier_register(dev, + &dev->priv.sf_hw_table_vhca_nb); +} + +void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_sf(dev)) + return; + + mlx5_vhca_event_notifier_unregister(dev, + &dev->priv.sf_hw_table_vhca_nb); } void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) @@ -388,9 +402,8 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) if (!table) return; - mlx5_vhca_event_notifier_unregister(dev, &table->vhca_nb); /* Dealloc SFs whose firmware event has been missed. */ - mlx5_sf_hw_table_dealloc_all(table); + mlx5_sf_hw_table_dealloc_all(dev, table); } bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index 89559a37997a..d8a934a0e968 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -12,10 +12,13 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev); void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev); -int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev); +int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev); +void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev); void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev); +int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev); int mlx5_sf_table_init(struct mlx5_core_dev *dev); +void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev); void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev); bool mlx5_sf_table_empty(const struct mlx5_core_dev *dev); @@ -44,20 +47,33 @@ static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev) { } -static inline int mlx5_sf_hw_table_create(struct mlx5_core_dev *dev) +static inline int mlx5_sf_hw_notifier_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_sf_hw_notifier_cleanup(struct mlx5_core_dev *dev) +{ +} + static inline void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev) { } +static inline int mlx5_sf_notifiers_init(struct mlx5_core_dev *dev) +{ + return 0; +} + static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_sf_notifiers_cleanup(struct mlx5_core_dev *dev) +{ +} + static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev) { } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c index cda01ba441ae..b04cf6cf8956 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c @@ -9,15 +9,9 @@ #define CREATE_TRACE_POINTS #include "diag/vhca_tracepoint.h" -struct mlx5_vhca_state_notifier { - struct mlx5_core_dev *dev; - struct mlx5_nb nb; - struct blocking_notifier_head n_head; -}; - struct mlx5_vhca_event_work { struct work_struct work; - struct mlx5_vhca_state_notifier *notifier; + struct mlx5_core_dev *dev; struct mlx5_vhca_state_event event; }; @@ -95,16 +89,14 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * mlx5_vhca_event_arm(dev, event->function_id); trace_mlx5_sf_vhca_event(dev, event); - blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event); + blocking_notifier_call_chain(&dev->priv.vhca_state_n_head, 0, event); } static void mlx5_vhca_state_work_handler(struct work_struct *_work) { struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work); - struct mlx5_vhca_state_notifier *notifier = work->notifier; - struct mlx5_core_dev *dev = notifier->dev; - mlx5_vhca_event_notify(dev, &work->event); + mlx5_vhca_event_notify(work->dev, &work->event); kfree(work); } @@ -116,8 +108,8 @@ void mlx5_vhca_events_work_enqueue(struct mlx5_core_dev *dev, int idx, struct wo static int mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data) { - struct mlx5_vhca_state_notifier *notifier = - mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb); + struct mlx5_core_dev *dev = mlx5_nb_cof(nb, struct mlx5_core_dev, + priv.vhca_state_nb); struct mlx5_vhca_event_work *work; struct mlx5_eqe *eqe = data; int wq_idx; @@ -126,10 +118,10 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, &mlx5_vhca_state_work_handler); - work->notifier = notifier; + work->dev = dev; work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id); wq_idx = work->event.function_id % MLX5_DEV_MAX_WQS; - mlx5_vhca_events_work_enqueue(notifier->dev, wq_idx, &work->work); + mlx5_vhca_events_work_enqueue(dev, wq_idx, &work->work); return NOTIFY_OK; } @@ -145,9 +137,15 @@ void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap) MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1); } +void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev) +{ + BLOCKING_INIT_NOTIFIER_HEAD(&dev->priv.vhca_state_n_head); + MLX5_NB_INIT(&dev->priv.vhca_state_nb, mlx5_vhca_state_change_notifier, + VHCA_STATE_CHANGE); +} + int mlx5_vhca_event_init(struct mlx5_core_dev *dev) { - struct mlx5_vhca_state_notifier *notifier; char wq_name[MLX5_CMD_WQ_MAX_NAME]; struct mlx5_vhca_events *events; int err, i; @@ -160,7 +158,6 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev) return -ENOMEM; events->dev = dev; - dev->priv.vhca_events = events; for (i = 0; i < MLX5_DEV_MAX_WQS; i++) { snprintf(wq_name, MLX5_CMD_WQ_MAX_NAME, "mlx5_vhca_event%d", i); events->handler[i].wq = create_singlethread_workqueue(wq_name); @@ -169,20 +166,10 @@ int mlx5_vhca_event_init(struct mlx5_core_dev *dev) goto err_create_wq; } } + dev->priv.vhca_events = events; - notifier = kzalloc(sizeof(*notifier), GFP_KERNEL); - if (!notifier) { - err = -ENOMEM; - goto err_notifier; - } - - dev->priv.vhca_state_notifier = notifier; - notifier->dev = dev; - BLOCKING_INIT_NOTIFIER_HEAD(¬ifier->n_head); - MLX5_NB_INIT(¬ifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE); return 0; -err_notifier: err_create_wq: for (--i; i >= 0; i--) destroy_workqueue(events->handler[i].wq); @@ -211,8 +198,6 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev) if (!mlx5_vhca_event_supported(dev)) return; - kfree(dev->priv.vhca_state_notifier); - dev->priv.vhca_state_notifier = NULL; vhca_events = dev->priv.vhca_events; for (i = 0; i < MLX5_DEV_MAX_WQS; i++) destroy_workqueue(vhca_events->handler[i].wq); @@ -221,34 +206,30 @@ void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev) void mlx5_vhca_event_start(struct mlx5_core_dev *dev) { - struct mlx5_vhca_state_notifier *notifier; - - if (!dev->priv.vhca_state_notifier) + if (!mlx5_vhca_event_supported(dev)) return; - notifier = dev->priv.vhca_state_notifier; - mlx5_eq_notifier_register(dev, ¬ifier->nb); + mlx5_eq_notifier_register(dev, &dev->priv.vhca_state_nb); } void mlx5_vhca_event_stop(struct mlx5_core_dev *dev) { - struct mlx5_vhca_state_notifier *notifier; - - if (!dev->priv.vhca_state_notifier) + if (!mlx5_vhca_event_supported(dev)) return; - notifier = dev->priv.vhca_state_notifier; - mlx5_eq_notifier_unregister(dev, ¬ifier->nb); + mlx5_eq_notifier_unregister(dev, &dev->priv.vhca_state_nb); + + /* Flush workqueues of all pending events. */ + mlx5_vhca_event_work_queues_flush(dev); } int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb) { - if (!dev->priv.vhca_state_notifier) - return -EOPNOTSUPP; - return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb); + return blocking_notifier_chain_register(&dev->priv.vhca_state_n_head, + nb); } void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb) { - blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb); + blocking_notifier_chain_unregister(&dev->priv.vhca_state_n_head, nb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h index 1725ba64f8af..52790423874c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h @@ -18,6 +18,7 @@ static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev) } void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap); +void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev); int mlx5_vhca_event_init(struct mlx5_core_dev *dev); void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev); void mlx5_vhca_event_start(struct mlx5_core_dev *dev); @@ -37,6 +38,10 @@ static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *s { } +static inline void mlx5_vhca_state_notifier_init(struct mlx5_core_dev *dev) +{ +} + static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev) { return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c index 65740bb68b09..e8c67ed9f748 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c @@ -410,7 +410,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, switch (dmn->type) { case MLX5DR_DOMAIN_TYPE_NIC_RX: if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, rx)) - return -ENOTSUPP; + return -EOPNOTSUPP; dmn->info.supp_sw_steering = true; dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX; @@ -419,7 +419,7 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, break; case MLX5DR_DOMAIN_TYPE_NIC_TX: if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, tx)) - return -ENOTSUPP; + return -EOPNOTSUPP; dmn->info.supp_sw_steering = true; dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX; @@ -428,10 +428,10 @@ static int dr_domain_caps_init(struct mlx5_core_dev *mdev, break; case MLX5DR_DOMAIN_TYPE_FDB: if (!dmn->info.caps.eswitch_manager) - return -ENOTSUPP; + return -EOPNOTSUPP; if (!DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, fdb)) - return -ENOTSUPP; + return -EOPNOTSUPP; dmn->info.rx.type = DR_DOMAIN_NIC_TYPE_RX; dmn->info.tx.type = DR_DOMAIN_NIC_TYPE_TX; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 992873536c1b..306affbcfd3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -78,15 +78,14 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, } static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport, - u32 *out) + bool other_vport, u32 *out) { u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {}; MLX5_SET(query_nic_vport_context_in, in, opcode, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); MLX5_SET(query_nic_vport_context_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); + MLX5_SET(query_nic_vport_context_in, in, other_vport, other_vport); return mlx5_cmd_exec_inout(mdev, query_nic_vport_context, in, out); } @@ -97,7 +96,7 @@ int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {}; int err; - err = mlx5_query_nic_vport_context(mdev, vport, out); + err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out); if (!err) *min_inline = MLX5_GET(query_nic_vport_context_out, out, nic_vport_context.min_wqe_inline_mode); @@ -219,7 +218,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (!err) *mtu = MLX5_GET(query_nic_vport_context_out, out, nic_vport_context.mtu); @@ -429,7 +428,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -451,7 +450,7 @@ int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -462,7 +461,8 @@ out: return err; } -int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) +int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, + u16 vport, bool other_vport, u64 *node_guid) { u32 *out; int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); @@ -472,7 +472,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, vport, other_vport, out); if (err) goto out; @@ -529,7 +529,7 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -804,7 +804,7 @@ int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, vport, out); + err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out); if (err) goto out; @@ -908,7 +908,7 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c index b032d5a4b3b8..10f5bc4892fc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c @@ -601,6 +601,8 @@ int mlxsw_linecard_devlink_info_get(struct mlxsw_linecard *linecard, err = devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_FW_PSID, info->psid); + if (err) + goto unlock; sprintf(buf, "%u.%u.%u", info->fw_major, info->fw_minor, info->fw_sub_minor); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index b1d08e958bf9..69f9da9fb305 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -1489,7 +1489,8 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); struct mlxsw_sp_acl_tcam *tcam; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 6a4a81c63451..353fd9ca89a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -830,8 +830,10 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp, return -EINVAL; rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); - if (!rule) - return -EINVAL; + if (!rule) { + err = -EINVAL; + goto err_rule_get_stats; + } err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes, &drops, &lastuse, &used_hw_stats); diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index dff51f23d295..ca5c7ac2a5bc 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -26,6 +26,7 @@ config FBNIC depends on PTP_1588_CLOCK_OPTIONAL select NET_DEVLINK select PAGE_POOL + select PCS_XPCS select PHYLINK select PLDMFW help diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile index 15e8ff649615..72c41af65364 100644 --- a/drivers/net/ethernet/meta/fbnic/Makefile +++ b/drivers/net/ethernet/meta/fbnic/Makefile @@ -21,6 +21,7 @@ fbnic-y := fbnic_csr.o \ fbnic_pci.o \ fbnic_phylink.o \ fbnic_rpc.o \ + fbnic_mdio.o \ fbnic_time.o \ fbnic_tlv.o \ fbnic_txrx.o \ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index b03e5a3d5144..779a083b9215 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -34,7 +34,7 @@ struct fbnic_dev { u32 __iomem *uc_addr4; const struct fbnic_mac *mac; unsigned int fw_msix_vector; - unsigned int pcs_msix_vector; + unsigned int mac_msix_vector; unsigned short num_irqs; struct { @@ -83,6 +83,10 @@ struct fbnic_dev { /* Last @time_high refresh time in jiffies (to catch stalls) */ unsigned long last_read; + /* PMD specific data */ + unsigned long end_of_pmd_training; + u8 pmd_state; + /* Local copy of hardware statistics */ struct fbnic_hw_stats hw_stats; @@ -91,6 +95,9 @@ struct fbnic_dev { u64 prev_firmware_time; struct fbnic_fw_log fw_log; + + /* MDIO bus for PHYs */ + struct mii_bus *mdio_bus; }; /* Reserve entry 0 in the MSI-X "others" array until we have filled all @@ -175,8 +182,8 @@ void fbnic_fw_free_mbx(struct fbnic_dev *fbd); void fbnic_hwmon_register(struct fbnic_dev *fbd); void fbnic_hwmon_unregister(struct fbnic_dev *fbd); -int fbnic_pcs_request_irq(struct fbnic_dev *fbd); -void fbnic_pcs_free_irq(struct fbnic_dev *fbd); +int fbnic_mac_request_irq(struct fbnic_dev *fbd); +void fbnic_mac_free_irq(struct fbnic_dev *fbd); void fbnic_napi_name_irqs(struct fbnic_dev *fbd); int fbnic_napi_request_irq(struct fbnic_dev *fbd, @@ -200,6 +207,8 @@ void fbnic_dbg_exit(void); void fbnic_rpc_reset_valid_entries(struct fbnic_dev *fbd); +int fbnic_mdiobus_create(struct fbnic_dev *fbd); + void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version); int fbnic_csr_regs_len(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index d3a7ad921f18..422265dc7abd 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -787,6 +787,8 @@ enum { /* MAC PCS registers */ #define FBNIC_CSR_START_PCS 0x10000 /* CSR section delimiter */ +#define FBNIC_PCS_PAGE(n) (0x10000 + 0x400 * (n)) /* 0x40000 + 1024*n */ +#define FBNIC_PCS(reg, n) ((reg) + FBNIC_PCS_PAGE(n)) #define FBNIC_CSR_END_PCS 0x10668 /* CSR section delimiter */ #define FBNIC_CSR_START_RSFEC 0x10800 /* CSR section delimiter */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 95fac020eb93..693ebdf38705 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -1863,6 +1863,14 @@ fbnic_get_rmon_stats(struct net_device *netdev, *ranges = fbnic_rmon_ranges; } +static void fbnic_get_link_ext_stats(struct net_device *netdev, + struct ethtool_link_ext_stats *stats) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + stats->link_down_events = fbn->link_down_events; +} + static const struct ethtool_ops fbnic_ethtool_ops = { .cap_link_lanes_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | @@ -1874,6 +1882,7 @@ static const struct ethtool_ops fbnic_ethtool_ops = { .get_regs_len = fbnic_get_regs_len, .get_regs = fbnic_get_regs, .get_link = ethtool_op_get_link, + .get_link_ext_stats = fbnic_get_link_ext_stats, .get_coalesce = fbnic_get_coalesce, .set_coalesce = fbnic_set_coalesce, .get_ringparam = fbnic_get_ringparam, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index 1166fa17438d..d8d9b6cfde82 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -201,7 +201,7 @@ static int fbnic_mbx_alloc_rx_msgs(struct fbnic_dev *fbd) return -ENODEV; /* Fill all but 1 unused descriptors in the Rx queue. */ - count = (head - tail - 1) % FBNIC_IPC_MBX_DESC_LEN; + count = (head - tail - 1) & (FBNIC_IPC_MBX_DESC_LEN - 1); while (!err && count--) { struct fbnic_tlv_msg *msg; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c index 1c88a2bf3a7a..02e8b0b257fe 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c @@ -118,12 +118,12 @@ void fbnic_fw_free_mbx(struct fbnic_dev *fbd) fbd->fw_msix_vector = 0; } -static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) +static irqreturn_t fbnic_mac_msix_intr(int __always_unused irq, void *data) { struct fbnic_dev *fbd = data; struct fbnic_net *fbn; - if (fbd->mac->pcs_get_link_event(fbd) == FBNIC_LINK_EVENT_NONE) { + if (fbd->mac->get_link_event(fbd) == FBNIC_LINK_EVENT_NONE) { fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_PCS_MSIX_ENTRY); return IRQ_HANDLED; @@ -131,26 +131,28 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) fbn = netdev_priv(fbd->netdev); - phylink_pcs_change(&fbn->phylink_pcs, false); + /* Record link down events */ + if (!fbd->mac->get_link(fbd, fbn->aui, fbn->fec)) + phylink_pcs_change(fbn->pcs, false); return IRQ_HANDLED; } /** - * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link + * fbnic_mac_request_irq - Configure the MAC to enable it to advertise link * @fbd: Pointer to device to initialize * - * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ + * This function provides basic bringup for the MAC/PHY IRQ. For now the IRQ * will remain disabled until we start the MAC/PCS/PHY logic via phylink. * * Return: non-zero on failure. **/ -int fbnic_pcs_request_irq(struct fbnic_dev *fbd) +int fbnic_mac_request_irq(struct fbnic_dev *fbd) { struct pci_dev *pdev = to_pci_dev(fbd->dev); int vector, err; - WARN_ON(fbd->pcs_msix_vector); + WARN_ON(fbd->mac_msix_vector); vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY); if (vector < 0) @@ -159,7 +161,7 @@ int fbnic_pcs_request_irq(struct fbnic_dev *fbd) /* Request the IRQ for PCS link vector. * Map PCS cause to it, and unmask it */ - err = request_irq(vector, &fbnic_pcs_msix_intr, 0, + err = request_irq(vector, &fbnic_mac_msix_intr, 0, fbd->netdev->name, fbd); if (err) return err; @@ -168,22 +170,22 @@ int fbnic_pcs_request_irq(struct fbnic_dev *fbd) fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX), FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE); - fbd->pcs_msix_vector = vector; + fbd->mac_msix_vector = vector; return 0; } /** - * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping + * fbnic_mac_free_irq - Teardown the MAC IRQ to prepare for stopping * @fbd: Pointer to device that is stopping * - * This function undoes the work done in fbnic_pcs_request_irq and prepares + * This function undoes the work done in fbnic_mac_request_irq and prepares * the device to no longer receive traffic on the host interface. **/ -void fbnic_pcs_free_irq(struct fbnic_dev *fbd) +void fbnic_mac_free_irq(struct fbnic_dev *fbd) { /* Vector has already been freed */ - if (!fbd->pcs_msix_vector) + if (!fbd->mac_msix_vector) return; /* Disable interrupt */ @@ -192,14 +194,14 @@ void fbnic_pcs_free_irq(struct fbnic_dev *fbd) fbnic_wrfl(fbd); /* Synchronize IRQ to prevent race that would unmask vector */ - synchronize_irq(fbd->pcs_msix_vector); + synchronize_irq(fbd->mac_msix_vector); /* Mask the vector */ fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY); /* Free the vector */ - free_irq(fbd->pcs_msix_vector, fbd); - fbd->pcs_msix_vector = 0; + free_irq(fbd->mac_msix_vector, fbd); + fbd->mac_msix_vector = 0; } void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 2a84bd1d7e26..fc7abea4ef5b 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -434,14 +434,14 @@ static void fbnic_mac_tx_pause_config(struct fbnic_dev *fbd, bool tx_pause) wr32(fbd, FBNIC_RXB_PAUSE_DROP_CTRL, rxb_pause_ctrl); } -static int fbnic_pcs_get_link_event_asic(struct fbnic_dev *fbd) +static int fbnic_mac_get_link_event(struct fbnic_dev *fbd) { - u32 pcs_intr_mask = rd32(fbd, FBNIC_SIG_PCS_INTR_STS); + u32 intr_mask = rd32(fbd, FBNIC_SIG_PCS_INTR_STS); - if (pcs_intr_mask & FBNIC_SIG_PCS_INTR_LINK_DOWN) + if (intr_mask & FBNIC_SIG_PCS_INTR_LINK_DOWN) return FBNIC_LINK_EVENT_DOWN; - return (pcs_intr_mask & FBNIC_SIG_PCS_INTR_LINK_UP) ? + return (intr_mask & FBNIC_SIG_PCS_INTR_LINK_UP) ? FBNIC_LINK_EVENT_UP : FBNIC_LINK_EVENT_NONE; } @@ -466,9 +466,8 @@ static u32 __fbnic_mac_cmd_config_asic(struct fbnic_dev *fbd, return command_config; } -static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) +static bool fbnic_mac_get_link_status(struct fbnic_dev *fbd, u8 aui, u8 fec) { - struct fbnic_net *fbn = netdev_priv(fbd->netdev); u32 pcs_status, lane_mask = ~0; pcs_status = rd32(fbd, FBNIC_SIG_PCS_OUT0); @@ -476,7 +475,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) return false; /* Define the expected lane mask for the status bits we need to check */ - switch (fbn->aui) { + switch (aui) { case FBNIC_AUI_100GAUI2: lane_mask = 0xf; break; @@ -484,7 +483,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) lane_mask = 3; break; case FBNIC_AUI_LAUI2: - switch (fbn->fec) { + switch (fec) { case FBNIC_FEC_OFF: lane_mask = 0x63; break; @@ -502,7 +501,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) } /* Use an XOR to remove the bits we expect to see set */ - switch (fbn->fec) { + switch (fec) { case FBNIC_FEC_OFF: lane_mask ^= FIELD_GET(FBNIC_SIG_PCS_OUT0_BLOCK_LOCK, pcs_status); @@ -521,7 +520,46 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) return !lane_mask; } -static bool fbnic_pcs_get_link_asic(struct fbnic_dev *fbd) +static bool fbnic_pmd_update_state(struct fbnic_dev *fbd, bool signal_detect) +{ + /* Delay link up for 4 seconds to allow for link training. + * The state transitions for this are as follows: + * + * All states have the following two transitions in common: + * Loss of signal -> FBNIC_PMD_INITIALIZE + * The condition handled below (!signal) + * Reconfiguration -> FBNIC_PMD_INITIALIZE + * Occurs when mac_prepare starts a PHY reconfig + * FBNIC_PMD_TRAINING: + * signal still detected && 4s have passed -> Report link up + * When link is brought up in link_up -> FBNIC_PMD_SEND_DATA + * FBNIC_PMD_INITIALIZE: + * signal detected -> FBNIC_PMD_TRAINING + */ + if (!signal_detect) { + fbd->pmd_state = FBNIC_PMD_INITIALIZE; + return false; + } + + switch (fbd->pmd_state) { + case FBNIC_PMD_TRAINING: + return time_before(fbd->end_of_pmd_training, jiffies); + case FBNIC_PMD_LINK_READY: + case FBNIC_PMD_SEND_DATA: + return true; + } + + fbd->end_of_pmd_training = jiffies + 4 * HZ; + + /* Ensure end_of_training is visible before the state change */ + smp_wmb(); + + fbd->pmd_state = FBNIC_PMD_TRAINING; + + return false; +} + +static bool fbnic_mac_get_link(struct fbnic_dev *fbd, u8 aui, u8 fec) { bool link; @@ -538,7 +576,8 @@ static bool fbnic_pcs_get_link_asic(struct fbnic_dev *fbd) wr32(fbd, FBNIC_SIG_PCS_INTR_STS, FBNIC_SIG_PCS_INTR_LINK_DOWN | FBNIC_SIG_PCS_INTR_LINK_UP); - link = fbnic_mac_get_pcs_link_status(fbd); + link = fbnic_mac_get_link_status(fbd, aui, fec); + link = fbnic_pmd_update_state(fbd, link); /* Enable interrupt to only capture changes in link state */ wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, @@ -586,20 +625,15 @@ void fbnic_mac_get_fw_settings(struct fbnic_dev *fbd, u8 *aui, u8 *fec) } } -static int fbnic_pcs_enable_asic(struct fbnic_dev *fbd) +static void fbnic_mac_prepare(struct fbnic_dev *fbd, u8 aui, u8 fec) { /* Mask and clear the PCS interrupt, will be enabled by link handler */ wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, ~0); wr32(fbd, FBNIC_SIG_PCS_INTR_STS, ~0); - return 0; -} - -static void fbnic_pcs_disable_asic(struct fbnic_dev *fbd) -{ - /* Mask and clear the PCS interrupt */ - wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, ~0); - wr32(fbd, FBNIC_SIG_PCS_INTR_STS, ~0); + /* If we don't have link tear it all down and start over */ + if (!fbnic_mac_get_link_status(fbd, aui, fec)) + fbd->pmd_state = FBNIC_PMD_INITIALIZE; } static void fbnic_mac_link_down_asic(struct fbnic_dev *fbd) @@ -867,10 +901,9 @@ exit_free: static const struct fbnic_mac fbnic_mac_asic = { .init_regs = fbnic_mac_init_regs, - .pcs_enable = fbnic_pcs_enable_asic, - .pcs_disable = fbnic_pcs_disable_asic, - .pcs_get_link = fbnic_pcs_get_link_asic, - .pcs_get_link_event = fbnic_pcs_get_link_event_asic, + .get_link = fbnic_mac_get_link, + .get_link_event = fbnic_mac_get_link_event, + .prepare = fbnic_mac_prepare, .get_fec_stats = fbnic_mac_get_fec_stats, .get_pcs_stats = fbnic_mac_get_pcs_stats, .get_eth_mac_stats = fbnic_mac_get_eth_mac_stats, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h index ede5ff0dae22..f08fe8b7c497 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h @@ -10,6 +10,24 @@ struct fbnic_dev; #define FBNIC_MAX_JUMBO_FRAME_SIZE 9742 +/* States loosely based on section 136.8.11.7.5 of IEEE 802.3-2022 Ethernet + * Standard. These are needed to track the state of the PHY as it has a delay + * of several seconds from the time link comes up until it has completed + * training that we need to wait to report the link. + * + * Currently we treat training as a single block as this is managed by the + * firmware. + * + * We have FBNIC_PMD_SEND_DATA set to 0 as the expected default at driver load + * and we initialize the structure containing it to zero at allocation. + */ +enum { + FBNIC_PMD_SEND_DATA = 0x0, + FBNIC_PMD_INITIALIZE = 0x1, + FBNIC_PMD_TRAINING = 0x2, + FBNIC_PMD_LINK_READY = 0x3, +}; + enum { FBNIC_LINK_EVENT_NONE = 0, FBNIC_LINK_EVENT_UP = 1, @@ -38,6 +56,7 @@ enum { FBNIC_AUI_50GAUI1 = 2, /* 53.125GBd 53.125 * 1 */ FBNIC_AUI_100GAUI2 = 3, /* 106.25GBd 53.125 * 2 */ FBNIC_AUI_UNKNOWN = 4, + __FBNIC_AUI_MAX__ }; #define FBNIC_AUI_MODE_R2 (FBNIC_AUI_LAUI2) @@ -55,15 +74,15 @@ enum fbnic_sensor_id { * void (*init_regs)(struct fbnic_dev *fbd); * Initialize MAC registers to enable Tx/Rx paths and FIFOs. * - * void (*pcs_enable)(struct fbnic_dev *fbd); - * Configure and enable PCS to enable link if not already enabled - * void (*pcs_disable)(struct fbnic_dev *fbd); - * Shutdown the link if we are the only consumer of it. - * bool (*pcs_get_link)(struct fbnic_dev *fbd); - * Check PCS link status - * int (*pcs_get_link_event)(struct fbnic_dev *fbd) + * int (*get_link_event)(struct fbnic_dev *fbd) * Get the current link event status, reports true if link has * changed to either FBNIC_LINK_EVENT_DOWN or FBNIC_LINK_EVENT_UP + * bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec); + * Check link status + * + * void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec); + * Prepare PHY for init by fetching settings, disabling interrupts, + * and sending an updated PHY config to FW if needed. * * void (*link_down)(struct fbnic_dev *fbd); * Configure MAC for link down event @@ -74,10 +93,10 @@ enum fbnic_sensor_id { struct fbnic_mac { void (*init_regs)(struct fbnic_dev *fbd); - int (*pcs_enable)(struct fbnic_dev *fbd); - void (*pcs_disable)(struct fbnic_dev *fbd); - bool (*pcs_get_link)(struct fbnic_dev *fbd); - int (*pcs_get_link_event)(struct fbnic_dev *fbd); + int (*get_link_event)(struct fbnic_dev *fbd); + bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec); + + void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec); void (*get_fec_stats)(struct fbnic_dev *fbd, bool reset, struct fbnic_fec_stats *fec_stats); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c b/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c new file mode 100644 index 000000000000..709041f7fc43 --- /dev/null +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/mdio.h> +#include <linux/pcs/pcs-xpcs.h> + +#include "fbnic.h" +#include "fbnic_netdev.h" + +#define DW_VENDOR BIT(15) +#define FBNIC_PCS_VENDOR BIT(9) +#define FBNIC_PCS_ZERO_MASK (DW_VENDOR - FBNIC_PCS_VENDOR) + +static int +fbnic_mdio_read_pmd(struct fbnic_dev *fbd, int addr, int regnum) +{ + u8 aui = FBNIC_AUI_UNKNOWN; + struct fbnic_net *fbn; + int ret = 0; + + /* We don't need a second PMD, just one can handle both lanes */ + if (addr) + return 0; + + if (fbd->netdev) { + fbn = netdev_priv(fbd->netdev); + if (fbn->aui < FBNIC_AUI_UNKNOWN) + aui = fbn->aui; + } + + switch (regnum) { + case MDIO_DEVID1: + ret = MP_FBNIC_XPCS_PMA_100G_ID >> 16; + break; + case MDIO_DEVID2: + ret = MP_FBNIC_XPCS_PMA_100G_ID & 0xffff; + break; + case MDIO_DEVS1: + ret = MDIO_DEVS_PMAPMD | MDIO_DEVS_PCS; + break; + case MDIO_STAT2: + ret = MDIO_STAT2_DEVPRST_VAL; + break; + case MDIO_PMA_RXDET: + /* If training isn't complete default to 0 */ + if (fbd->pmd_state != FBNIC_PMD_SEND_DATA) + break; + /* Report either 1 or 2 lanes detected depending on config */ + ret = (MDIO_PMD_RXDET_GLOBAL | MDIO_PMD_RXDET_0) | + ((aui & FBNIC_AUI_MODE_R2) * + (MDIO_PMD_RXDET_1 / FBNIC_AUI_MODE_R2)); + break; + default: + break; + } + + dev_dbg(fbd->dev, + "SWMII PMD Rd: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, ret); + + return ret; +} + +static int +fbnic_mdio_read_pcs(struct fbnic_dev *fbd, int addr, int regnum) +{ + int ret, offset = 0; + + /* We will need access to both PCS instances to get config info */ + if (addr >= 2) + return 0; + + /* Report 0 for reserved registers */ + if (regnum & FBNIC_PCS_ZERO_MASK) + return 0; + + /* Intercept and return correct ID for PCS */ + if (regnum == MDIO_DEVID1) + return DW_XPCS_ID >> 16; + if (regnum == MDIO_DEVID2) + return DW_XPCS_ID & 0xffff; + if (regnum == MDIO_DEVS1) + return MDIO_DEVS_PMAPMD | MDIO_DEVS_PCS; + + /* Swap vendor page bit for FBNIC PCS vendor page bit */ + if (regnum & DW_VENDOR) + offset ^= DW_VENDOR | FBNIC_PCS_VENDOR; + + ret = fbnic_rd32(fbd, FBNIC_PCS_PAGE(addr) + (regnum ^ offset)); + + dev_dbg(fbd->dev, + "SWMII PCS Rd: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, ret); + + return ret; +} + +static int +fbnic_mdio_read_c45(struct mii_bus *bus, int addr, int devnum, int regnum) +{ + struct fbnic_dev *fbd = bus->priv; + + if (devnum == MDIO_MMD_PMAPMD) + return fbnic_mdio_read_pmd(fbd, addr, regnum); + + if (devnum == MDIO_MMD_PCS) + return fbnic_mdio_read_pcs(fbd, addr, regnum); + + return 0; +} + +static void +fbnic_mdio_write_pmd(struct fbnic_dev *fbd, int addr, int regnum, u16 val) +{ + dev_dbg(fbd->dev, + "SWMII PMD Wr: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, val); +} + +static void +fbnic_mdio_write_pcs(struct fbnic_dev *fbd, int addr, int regnum, u16 val) +{ + dev_dbg(fbd->dev, + "SWMII PCS Wr: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, val); + + /* Allow access to both halves of PCS for 50R2 config */ + if (addr > 2) + return; + + /* Skip write for reserved registers */ + if (regnum & FBNIC_PCS_ZERO_MASK) + return; + + /* Swap vendor page bit for FBNIC PCS vendor page bit */ + if (regnum & DW_VENDOR) + regnum ^= DW_VENDOR | FBNIC_PCS_VENDOR; + + fbnic_wr32(fbd, FBNIC_PCS_PAGE(addr) + regnum, val); +} + +static int +fbnic_mdio_write_c45(struct mii_bus *bus, int addr, int devnum, + int regnum, u16 val) +{ + struct fbnic_dev *fbd = bus->priv; + + if (devnum == MDIO_MMD_PMAPMD) + fbnic_mdio_write_pmd(fbd, addr, regnum, val); + + if (devnum == MDIO_MMD_PCS) + fbnic_mdio_write_pcs(fbd, addr, regnum, val); + + return 0; +} + +/** + * fbnic_mdiobus_create - Create an MDIO bus to allow interfacing w/ PHYs + * @fbd: Pointer to FBNIC device structure to populate bus on + * + * Initialize an MDIO bus and place a pointer to it on the fbd struct. This bus + * will be used to interface with the PMA/PMD and PCS. + * + * Return: 0 on success, negative on failure + **/ +int fbnic_mdiobus_create(struct fbnic_dev *fbd) +{ + struct mii_bus *bus; + int err; + + bus = devm_mdiobus_alloc(fbd->dev); + if (!bus) + return -ENOMEM; + + bus->name = "fbnic_mii_bus"; + bus->read_c45 = &fbnic_mdio_read_c45; + bus->write_c45 = &fbnic_mdio_write_c45; + + /* Disable PHY auto probing. We will add PCS manually */ + bus->phy_mask = ~0; + + bus->parent = fbd->dev; + bus->priv = fbd; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(fbd->dev)); + + err = devm_mdiobus_register(fbd->dev, bus); + if (err) { + dev_err(fbd->dev, "Failed to create MDIO bus: %d\n", err); + return err; + } + + fbd->mdio_bus = bus; + + return 0; +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index e95be0e7bd9e..81c9d5c9a4b2 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -44,7 +44,7 @@ int __fbnic_open(struct fbnic_net *fbn) if (err) goto time_stop; - err = fbnic_pcs_request_irq(fbd); + err = fbnic_mac_request_irq(fbd); if (err) goto time_stop; @@ -86,10 +86,10 @@ static int fbnic_stop(struct net_device *netdev) { struct fbnic_net *fbn = netdev_priv(netdev); + fbnic_mac_free_irq(fbn->fbd); phylink_suspend(fbn->phylink, fbnic_bmc_present(fbn->fbd)); fbnic_down(fbn); - fbnic_pcs_free_irq(fbn->fbd); fbnic_time_stop(fbn); fbnic_fw_xmit_ownership_msg(fbn->fbd, false); @@ -697,10 +697,7 @@ void fbnic_reset_queues(struct fbnic_net *fbn, **/ void fbnic_netdev_free(struct fbnic_dev *fbd) { - struct fbnic_net *fbn = netdev_priv(fbd->netdev); - - if (fbn->phylink) - phylink_destroy(fbn->phylink); + fbnic_phylink_destroy(fbd->netdev); free_netdev(fbd->netdev); fbd->netdev = NULL; @@ -802,7 +799,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netif_tx_stop_all_queues(netdev); - if (fbnic_phylink_init(netdev)) { + if (fbnic_phylink_create(netdev)) { fbnic_netdev_free(fbd); return NULL; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index b0a87c57910f..9129a658f8fa 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -44,7 +44,7 @@ struct fbnic_net { struct phylink *phylink; struct phylink_config phylink_config; - struct phylink_pcs phylink_pcs; + struct phylink_pcs *pcs; u8 aui; u8 fec; @@ -73,6 +73,8 @@ struct fbnic_net { /* Time stamping filter config */ struct kernel_hwtstamp_config hwtstamp_config; + + bool tx_pause; }; int __fbnic_open(struct fbnic_net *fbn); @@ -106,8 +108,10 @@ int fbnic_phylink_ethtool_ksettings_get(struct net_device *netdev, struct ethtool_link_ksettings *cmd); int fbnic_phylink_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam); +int fbnic_phylink_create(struct net_device *netdev); +void fbnic_phylink_destroy(struct net_device *netdev); int fbnic_phylink_init(struct net_device *netdev); - +void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev); bool fbnic_check_split_frames(struct bpf_prog *prog, unsigned int mtu, u32 hds_threshold); #endif /* _FBNIC_NETDEV_H_ */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 4620f1847f2e..861d98099c44 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -207,6 +207,10 @@ static void fbnic_service_task(struct work_struct *work) { struct fbnic_dev *fbd = container_of(to_delayed_work(work), struct fbnic_dev, service_task); + struct net_device *netdev = fbd->netdev; + + if (netif_running(netdev)) + fbnic_phylink_pmd_training_complete_notify(netdev); rtnl_lock(); @@ -224,7 +228,7 @@ static void fbnic_service_task(struct work_struct *work) netdev_unlock(fbd->netdev); } - if (netif_running(fbd->netdev)) + if (netif_running(netdev)) schedule_delayed_work(&fbd->service_task, HZ); rtnl_unlock(); @@ -335,6 +339,9 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_failure_mode; } + if (fbnic_mdiobus_create(fbd)) + goto init_failure_mode; + netdev = fbnic_netdev_alloc(fbd); if (!netdev) { dev_err(&pdev->dev, "Netdev allocation failed\n"); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index 7ce3fdd25282..09c5225111be 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) Meta Platforms, Inc. and affiliates. */ +#include <linux/pcs/pcs-xpcs.h> #include <linux/phy.h> #include <linux/phylink.h> @@ -101,88 +102,47 @@ int fbnic_phylink_get_fecparam(struct net_device *netdev, return 0; } -static struct fbnic_net * -fbnic_pcs_to_net(struct phylink_pcs *pcs) -{ - return container_of(pcs, struct fbnic_net, phylink_pcs); -} - -static void -fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, - struct phylink_link_state *state) +static struct phylink_pcs * +fbnic_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); - struct fbnic_dev *fbd = fbn->fbd; - - switch (fbn->aui) { - case FBNIC_AUI_25GAUI: - state->speed = SPEED_25000; - break; - case FBNIC_AUI_LAUI2: - case FBNIC_AUI_50GAUI1: - state->speed = SPEED_50000; - break; - case FBNIC_AUI_100GAUI2: - state->speed = SPEED_100000; - break; - default: - state->link = 0; - return; - } - - state->duplex = DUPLEX_FULL; + struct net_device *netdev = to_net_dev(config->dev); + struct fbnic_net *fbn = netdev_priv(netdev); - state->link = fbd->mac->pcs_get_link(fbd); + return fbn->pcs; } static int -fbnic_phylink_pcs_enable(struct phylink_pcs *pcs) +fbnic_phylink_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t iface) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); + struct net_device *netdev = to_net_dev(config->dev); + struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; - return fbd->mac->pcs_enable(fbd); + fbd->mac->prepare(fbd, fbn->aui, fbn->fec); + + return 0; } static void -fbnic_phylink_pcs_disable(struct phylink_pcs *pcs) +fbnic_phylink_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); - struct fbnic_dev *fbd = fbn->fbd; - - return fbd->mac->pcs_disable(fbd); } static int -fbnic_phylink_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, - phy_interface_t interface, - const unsigned long *advertising, - bool permit_pause_to_mac) -{ - return 0; -} - -static const struct phylink_pcs_ops fbnic_phylink_pcs_ops = { - .pcs_config = fbnic_phylink_pcs_config, - .pcs_enable = fbnic_phylink_pcs_enable, - .pcs_disable = fbnic_phylink_pcs_disable, - .pcs_get_state = fbnic_phylink_pcs_get_state, -}; - -static struct phylink_pcs * -fbnic_phylink_mac_select_pcs(struct phylink_config *config, - phy_interface_t interface) +fbnic_phylink_mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t iface) { struct net_device *netdev = to_net_dev(config->dev); struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; - return &fbn->phylink_pcs; -} + /* Retest the link state and restart interrupts */ + fbd->mac->get_link(fbd, fbn->aui, fbn->fec); -static void -fbnic_phylink_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state) -{ + return 0; } static void @@ -208,23 +168,48 @@ fbnic_phylink_mac_link_up(struct phylink_config *config, struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; + fbn->tx_pause = tx_pause; + fbnic_config_drop_mode(fbn, tx_pause); + fbd->mac->link_up(fbd, tx_pause, rx_pause); } static const struct phylink_mac_ops fbnic_phylink_mac_ops = { .mac_select_pcs = fbnic_phylink_mac_select_pcs, + .mac_prepare = fbnic_phylink_mac_prepare, .mac_config = fbnic_phylink_mac_config, + .mac_finish = fbnic_phylink_mac_finish, .mac_link_down = fbnic_phylink_mac_link_down, .mac_link_up = fbnic_phylink_mac_link_up, }; -int fbnic_phylink_init(struct net_device *netdev) +/** + * fbnic_phylink_create - Phylink device creation + * @netdev: Network Device struct to attach phylink device + * + * Initialize and attach a phylink instance to the device. The phylink + * device will make use of the netdev struct to track carrier and will + * eventually be used to expose the current state of the MAC and PCS + * setup. + * + * Return: 0 on success, negative on failure + **/ +int fbnic_phylink_create(struct net_device *netdev) { struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; + struct phylink_pcs *pcs; struct phylink *phylink; + int err; + + pcs = xpcs_create_pcs_mdiodev(fbd->mdio_bus, 0); + if (IS_ERR(pcs)) { + err = PTR_ERR(pcs); + dev_err(fbd->dev, "Failed to create PCS device: %d\n", err); + return err; + } - fbn->phylink_pcs.ops = &fbnic_phylink_pcs_ops; + fbn->pcs = pcs; fbn->phylink_config.dev = &netdev->dev; fbn->phylink_config.type = PHYLINK_NETDEV; @@ -247,10 +232,80 @@ int fbnic_phylink_init(struct net_device *netdev) phylink = phylink_create(&fbn->phylink_config, NULL, fbnic_phylink_select_interface(fbn->aui), &fbnic_phylink_mac_ops); - if (IS_ERR(phylink)) - return PTR_ERR(phylink); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + dev_err(netdev->dev.parent, + "Failed to create Phylink interface, err: %d\n", err); + xpcs_destroy_pcs(pcs); + return err; + } fbn->phylink = phylink; return 0; } + +/** + * fbnic_phylink_destroy - Teardown phylink related interfaces + * @netdev: Network Device struct containing phylink device + * + * Detach and free resources related to phylink interface. + **/ +void fbnic_phylink_destroy(struct net_device *netdev) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + if (fbn->phylink) + phylink_destroy(fbn->phylink); + if (fbn->pcs) + xpcs_destroy_pcs(fbn->pcs); +} + +/** + * fbnic_phylink_pmd_training_complete_notify - PMD training complete notifier + * @netdev: Netdev struct phylink device attached to + * + * When the link first comes up the PMD will have a period of 2 to 3 seconds + * where the link will flutter due to link training. To avoid spamming the + * kernel log with messages about this we add a delay of 4 seconds from the + * time of the last PCS report of link so that we can guarantee we are unlikely + * to see any further link loss events due to link training. + **/ +void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; + + if (fbd->pmd_state != FBNIC_PMD_TRAINING) + return; + + /* Prevent reading end_of_pmd_training until we verified state */ + smp_rmb(); + + if (!time_before(READ_ONCE(fbd->end_of_pmd_training), jiffies)) + return; + + /* At this point we have verified that the link has been up for + * the full training duration. As a first step we will try + * transitioning to link ready. + */ + if (cmpxchg(&fbd->pmd_state, FBNIC_PMD_TRAINING, + FBNIC_PMD_LINK_READY) != FBNIC_PMD_TRAINING) + return; + + /* Perform a follow-up check to verify that the link didn't flap + * just before our transition by rechecking the training timer. + */ + if (!time_before(READ_ONCE(fbd->end_of_pmd_training), jiffies)) + return; + + /* The training timeout has been completed. We are good to swap out + * link_ready for send_data assuming no other events have occurred + * that would have pulled us back into initialization or training. + */ + if (cmpxchg(&fbd->pmd_state, FBNIC_PMD_LINK_READY, + FBNIC_PMD_SEND_DATA) != FBNIC_PMD_LINK_READY) + return; + + phylink_pcs_change(fbn->pcs, false); +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index 57e18a68f5d2..13d508ce637f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -653,7 +653,8 @@ static void fbnic_clean_twq1(struct fbnic_napi_vector *nv, bool pp_allow_direct, FBNIC_TWD_TYPE_AL; total_bytes += FIELD_GET(FBNIC_TWD_LEN_MASK, twd); - page_pool_put_page(page->pp, page, -1, pp_allow_direct); + page_pool_put_page(pp_page_to_nmdesc(page)->pp, page, -1, + pp_allow_direct); next_desc: head++; head &= ring->size_mask; @@ -1807,7 +1808,7 @@ int fbnic_alloc_napi_vectors(struct fbnic_net *fbn) free_vectors: fbnic_free_napi_vectors(fbn); - return -ENOMEM; + return err; } static void fbnic_free_ring_resources(struct device *dev, @@ -2574,11 +2575,15 @@ write_ctl: } static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, - struct fbnic_ring *rcq) + struct fbnic_ring *rcq, bool tx_pause) { + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 drop_mode, rcq_ctl; - drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + if (!tx_pause && fbn->num_rx_queues > 1) + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + else + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_NEVER; /* Specify packet layout */ rcq_ctl = FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_DROP_MODE_MASK, drop_mode) | @@ -2588,6 +2593,21 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl); } +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause) +{ + int i, t; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + + for (t = 0; t < nv->rxt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[nv->txt_count + t]; + + fbnic_config_drop_mode_rcq(nv, &qt->cmpl, tx_pause); + } + } +} + static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc) { u32 threshold; @@ -2637,7 +2657,7 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, u32 hds_thresh = fbn->hds_thresh; u32 rcq_ctl = 0; - fbnic_config_drop_mode_rcq(nv, rcq); + fbnic_config_drop_mode_rcq(nv, rcq, fbn->tx_pause); /* Force lower bound on MAX_HEADER_BYTES. Below this, all frames should * be split at L4. It would also result in the frames being split at @@ -2700,7 +2720,6 @@ static void __fbnic_nv_enable(struct fbnic_napi_vector *nv) &nv->napi); fbnic_enable_bdq(&qt->sub0, &qt->sub1); - fbnic_config_drop_mode_rcq(nv, &qt->cmpl); fbnic_enable_rcq(nv, &qt->cmpl); } } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index ca37da5a0b17..27776e844e29 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -184,6 +184,7 @@ void fbnic_reset_netif_queues(struct fbnic_net *fbn); irqreturn_t fbnic_msix_clean_rings(int irq, void *data); void fbnic_napi_enable(struct fbnic_net *fbn); void fbnic_napi_disable(struct fbnic_net *fbn); +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause); void fbnic_enable(struct fbnic_net *fbn); void fbnic_disable(struct fbnic_net *fbn); void fbnic_flush(struct fbnic_net *fbn); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index b4377b8613c3..8c40db90ee8f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -1,11 +1,14 @@ // SPDX-License-Identifier: GPL-2.0+ #include <linux/ptp_classify.h> +#include <linux/units.h> #include "lan966x_main.h" #include "vcap_api.h" #include "vcap_api_client.h" +#define LAN9X66_CLOCK_RATE 165617754 + #define LAN966X_MAX_PTP_ID 512 /* Represents 1ppm adjustment in 2^59 format with 6.037735849ns as reference @@ -1126,5 +1129,5 @@ void lan966x_ptp_rxtstamp(struct lan966x *lan966x, struct sk_buff *skb, u32 lan966x_ptp_get_period_ps(void) { /* This represents the system clock period in picoseconds */ - return 15125; + return PICO / LAN9X66_CLOCK_RATE; } diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index effe0a2f207a..8fd70b34807a 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1300,7 +1300,6 @@ int mana_gd_post_work_request(struct gdma_queue *wq, struct gdma_posted_wqe_info *wqe_info) { u32 client_oob_size = wqe_req->inline_oob_size; - struct gdma_context *gc; u32 sgl_data_size; u32 max_wqe_size; u32 wqe_size; @@ -1330,11 +1329,8 @@ int mana_gd_post_work_request(struct gdma_queue *wq, if (wqe_size > max_wqe_size) return -EINVAL; - if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq)) { - gc = wq->gdma_dev->gdma_context; - dev_err(gc->dev, "unsuccessful flow control!\n"); + if (wq->monitor_avl_buf && wqe_size > mana_gd_wq_avail_space(wq)) return -ENOSPC; - } if (wqe_info) wqe_info->wqe_size_in_bu = wqe_size / GDMA_WQE_BU_SIZE; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index cccd5b63cee6..1ad154f9db1a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -11,6 +11,7 @@ #include <linux/mm.h> #include <linux/pci.h> #include <linux/export.h> +#include <linux/skbuff.h> #include <net/checksum.h> #include <net/ip6_checksum.h> @@ -329,6 +330,21 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) cq = &apc->tx_qp[txq_idx].tx_cq; tx_stats = &txq->stats; + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES != MANA_MAX_TX_WQE_SGL_ENTRIES); + if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES && + skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* GSO skb with Hardware SGE limit exceeded is not expected here + * as they are handled in mana_features_check() callback + */ + if (skb_linearize(skb)) { + netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n", + skb_shinfo(skb)->nr_frags, + skb_is_gso(skb)); + goto tx_drop_count; + } + apc->eth_stats.tx_linear_pkt_cnt++; + } + pkg.tx_oob.s_oob.vcq_num = cq->gdma_id; pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame; @@ -442,8 +458,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) } } - WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); - if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; } else { @@ -478,9 +492,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (err) { (void)skb_dequeue_tail(&txq->pending_skbs); + mana_unmap_skb(skb, apc); netdev_warn(ndev, "Failed to post TX OOB: %d\n", err); - err = NETDEV_TX_BUSY; - goto tx_busy; + goto free_sgl_ptr; } err = NETDEV_TX_OK; @@ -500,7 +514,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) tx_stats->bytes += len + ((num_gso_seg - 1) * gso_hs); u64_stats_update_end(&tx_stats->syncp); -tx_busy: if (netif_tx_queue_stopped(net_txq) && mana_can_tx(gdma_sq)) { netif_tx_wake_queue(net_txq); apc->eth_stats.wake_queue++; @@ -518,6 +531,25 @@ tx_drop: return NETDEV_TX_OK; } +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) +static netdev_features_t mana_features_check(struct sk_buff *skb, + struct net_device *ndev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) { + /* Exceeds HW SGE limit. + * GSO case: + * Disable GSO so the stack will software-segment the skb + * into smaller skbs that fit the SGE budget. + * Non-GSO case: + * The xmit path will attempt skb_linearize() as a fallback. + */ + features &= ~NETIF_F_GSO_MASK; + } + return features; +} +#endif + static void mana_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *st) { @@ -534,6 +566,11 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); + if (apc->ac->hwc_timeout_occurred) + netdev_warn_once(ndev, "HWC timeout occurred\n"); + + st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe; + for (q = 0; q < num_queues; q++) { rx_stats = &apc->rxqs[q]->stats; @@ -878,6 +915,9 @@ static const struct net_device_ops mana_devops = { .ndo_open = mana_open, .ndo_stop = mana_close, .ndo_select_queue = mana_select_queue, +#if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES) + .ndo_features_check = mana_features_check, +#endif .ndo_start_xmit = mana_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_get_stats64 = mana_get_stats64, @@ -1646,7 +1686,7 @@ static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units) return 0; } -static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) +void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) { struct mana_skb_head *ash = (struct mana_skb_head *)skb->head; struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; @@ -2809,11 +2849,12 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } -void mana_query_gf_stats(struct mana_port_context *apc) +int mana_query_gf_stats(struct mana_context *ac) { + struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_gf_stat_resp resp = {}; struct mana_query_gf_stat_req req = {}; - struct net_device *ndev = apc->ndev; + struct device *dev = gc->dev; int err; mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, @@ -2847,52 +2888,54 @@ void mana_query_gf_stats(struct mana_port_context *apc) STATISTICS_FLAGS_HC_TX_BCAST_BYTES | STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR; - err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to query GF stats: %d\n", err); - return; + dev_err(dev, "Failed to query GF stats: %d\n", err); + return err; } err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, sizeof(resp)); if (err || resp.hdr.status) { - netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, - resp.hdr.status); - return; + dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); + return err; } - apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; - apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; - apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes; - apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; - apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; - apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; - apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; - apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; - apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; - apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; - apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; - apc->eth_stats.hc_tx_err_inval_vportoffset_pkt = + ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; + ac->hc_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; + ac->hc_stats.hc_rx_bytes = resp.hc_rx_bytes; + ac->hc_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; + ac->hc_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; + ac->hc_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; + ac->hc_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; + ac->hc_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; + ac->hc_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; + ac->hc_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; + ac->hc_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; + ac->hc_stats.hc_tx_err_inval_vportoffset_pkt = resp.tx_err_inval_vport_offset_pkt; - apc->eth_stats.hc_tx_err_vlan_enforcement = + ac->hc_stats.hc_tx_err_vlan_enforcement = resp.tx_err_vlan_enforcement; - apc->eth_stats.hc_tx_err_eth_type_enforcement = + ac->hc_stats.hc_tx_err_eth_type_enforcement = resp.tx_err_ethtype_enforcement; - apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; - apc->eth_stats.hc_tx_err_sqpdid_enforcement = + ac->hc_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; + ac->hc_stats.hc_tx_err_sqpdid_enforcement = resp.tx_err_SQPDID_enforcement; - apc->eth_stats.hc_tx_err_cqpdid_enforcement = + ac->hc_stats.hc_tx_err_cqpdid_enforcement = resp.tx_err_CQPDID_enforcement; - apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; - apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; - apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; - apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; - apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; - apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; - apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; - apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; - apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; - apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma; + ac->hc_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; + ac->hc_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; + ac->hc_stats.hc_tx_bytes = resp.hc_tx_bytes; + ac->hc_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + ac->hc_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + ac->hc_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + ac->hc_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; + ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma; + + return 0; } void mana_query_phy_stats(struct mana_port_context *apc) @@ -3427,6 +3470,24 @@ int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type even return 0; } +#define MANA_GF_STATS_PERIOD (2 * HZ) + +static void mana_gf_stats_work_handler(struct work_struct *work) +{ + struct mana_context *ac = + container_of(to_delayed_work(work), struct mana_context, gf_stats_work); + int err; + + err = mana_query_gf_stats(ac); + if (err == -ETIMEDOUT) { + /* HWC timeout detected - reset stats and stop rescheduling */ + ac->hwc_timeout_occurred = true; + memset(&ac->hc_stats, 0, sizeof(ac->hc_stats)); + return; + } + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; @@ -3519,6 +3580,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = add_adev(gd, "eth"); + + INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); + out: if (err) { mana_remove(gd, false); @@ -3543,6 +3608,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending) int i; disable_work_sync(&ac->link_change_work); + cancel_delayed_work_sync(&ac->gf_stats_work); /* adev currently doesn't support suspending, always remove it */ if (gd->adev) diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a1afa75a9463..0e2f4343ac67 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -15,66 +15,71 @@ struct mana_stats_desc { static const struct mana_stats_desc mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats, + {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, + {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + tx_cqe_unknown_type)}, + {"tx_linear_pkt_cnt", offsetof(struct mana_ethtool_stats, + tx_linear_pkt_cnt)}, + {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, + rx_coalesced_err)}, + {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + rx_cqe_unknown_type)}, +}; + +static const struct mana_stats_desc mana_hc_stats[] = { + {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_hc_stats, hc_rx_discards_no_wqe)}, - {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_rx_err_vport_disabled)}, - {"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)}, - {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bytes)}, + {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_pkts)}, - {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_bytes)}, - {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_pkts)}, - {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_bytes)}, - {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats, - hc_rx_mcast_pkts)}, - {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, + hc_rx_mcast_pkts)}, + {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_mcast_bytes)}, - {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gf_disabled)}, - {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vport_disabled)}, {"hc_tx_err_inval_vportoffset_pkt", - offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_vportoffset_pkt)}, - {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vlan_enforcement)}, {"hc_tx_err_eth_type_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)}, - {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_eth_type_enforcement)}, + {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sa_enforcement)}, {"hc_tx_err_sqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)}, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sqpdid_enforcement)}, {"hc_tx_err_cqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)}, - {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_cqpdid_enforcement)}, + {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_mtu_violation)}, - {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_oob)}, - {"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gdma", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gdma)}, - {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, - {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bytes)}, + {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_pkts)}, - {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_bytes)}, - {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_pkts)}, - {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_bytes)}, - {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_pkts)}, - {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_bytes)}, - {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, - {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - tx_cqe_unknown_type)}, - {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, - rx_coalesced_err)}, - {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - rx_cqe_unknown_type)}, }; static const struct mana_stats_desc mana_phy_stats[] = { @@ -138,7 +143,7 @@ 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) + ARRAY_SIZE(mana_phy_stats) + + return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + ARRAY_SIZE(mana_hc_stats) + num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT); } @@ -150,10 +155,12 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) if (stringset != ETH_SS_STATS) return; - for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++) ethtool_puts(&data, mana_eth_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_hc_stats); i++) + ethtool_puts(&data, mana_hc_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_phy_stats); i++) ethtool_puts(&data, mana_phy_stats[i].name); @@ -186,6 +193,7 @@ 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; + void *hc_stats = &apc->ac->hc_stats; void *phy_stats = &apc->phy_stats; struct mana_stats_rx *rx_stats; struct mana_stats_tx *tx_stats; @@ -207,8 +215,6 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; - /* we call mana function to update stats from GDMA */ - mana_query_gf_stats(apc); /* We call this mana function to get the phy stats from GDMA and includes * aggregate tx/rx drop counters, Per-TC(Traffic Channel) tx/rx and pause @@ -219,6 +225,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev, for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_hc_stats); q++) + data[i++] = *(u64 *)(hc_stats + mana_hc_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_phy_stats); q++) data[i++] = *(u64 *)(phy_stats + mana_phy_stats[q].offset); diff --git a/drivers/net/ethernet/netronome/nfp/devlink_param.c b/drivers/net/ethernet/netronome/nfp/devlink_param.c index 0e1a3800f371..85e3b19e6165 100644 --- a/drivers/net/ethernet/netronome/nfp/devlink_param.c +++ b/drivers/net/ethernet/netronome/nfp/devlink_param.c @@ -81,7 +81,8 @@ static const struct nfp_devlink_param_u8_arg nfp_devlink_u8_args[] = { static int nfp_devlink_param_u8_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { const struct nfp_devlink_param_u8_arg *arg; struct nfp_pf *pf = devlink_priv(devlink); diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index 94c5689b5abd..0c5278c0598c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -121,7 +121,8 @@ void qed_fw_reporters_destroy(struct devlink *devlink) } static int qed_dl_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct qed_devlink *qed_dl = devlink_priv(dl); struct qed_dev *cdev; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 847fa62c80df..e338bfc8b7b2 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -4,6 +4,7 @@ * Copyright (c) 2019-2020 Marvell International Ltd. */ +#include <linux/array_size.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> @@ -960,7 +961,7 @@ static inline void qede_tpa_cont(struct qede_dev *edev, { int i; - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); @@ -985,7 +986,7 @@ static int qede_tpa_end(struct qede_dev *edev, dma_unmap_page(rxq->dev, tpa_info->buffer.mapping, PAGE_SIZE, rxq->data_direction); - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); if (unlikely(i > 1)) diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index b5d744d2586f..66ab1b9d65a1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -506,25 +506,6 @@ static int qede_set_vf_trust(struct net_device *dev, int vfidx, bool setting) } #endif -static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct qede_dev *edev = netdev_priv(dev); - - if (!netif_running(dev)) - return -EAGAIN; - - switch (cmd) { - case SIOCSHWTSTAMP: - return qede_ptp_hw_ts(edev, ifr); - default: - DP_VERBOSE(edev, QED_MSG_DEBUG, - "default IOCTL cmd 0x%x\n", cmd); - return -EOPNOTSUPP; - } - - return 0; -} - static void qede_fp_sb_dump(struct qede_dev *edev, struct qede_fastpath *fp) { char *p_sb = (char *)fp->sb_info->sb_virt; @@ -717,7 +698,6 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = qede_change_mtu, - .ndo_eth_ioctl = qede_ioctl, .ndo_tx_timeout = qede_tx_timeout, #ifdef CONFIG_QED_SRIOV .ndo_set_vf_mac = qede_set_vf_mac, @@ -742,6 +722,8 @@ static const struct net_device_ops qede_netdev_ops = { #endif .ndo_xdp_xmit = qede_xdp_transmit, .ndo_setup_tc = qede_setup_tc_offload, + .ndo_hwtstamp_get = qede_hwtstamp_get, + .ndo_hwtstamp_set = qede_hwtstamp_set, }; static const struct net_device_ops qede_netdev_vf_ops = { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index a38f1e72c62b..d351be5fbda1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -199,18 +199,15 @@ static u64 qede_ptp_read_cc(struct cyclecounter *cc) return phc_cycles; } -static int qede_ptp_cfg_filters(struct qede_dev *edev) +static void qede_ptp_cfg_filters(struct qede_dev *edev) { enum qed_ptp_hwtstamp_tx_type tx_type = QED_PTP_HWTSTAMP_TX_ON; enum qed_ptp_filter_type rx_filter = QED_PTP_FILTER_NONE; struct qede_ptp *ptp = edev->ptp; - if (!ptp) - return -EIO; - if (!ptp->hw_ts_ioctl_called) { DP_INFO(edev, "TS IOCTL not called\n"); - return 0; + return; } switch (ptp->tx_type) { @@ -223,11 +220,6 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev) clear_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags); tx_type = QED_PTP_HWTSTAMP_TX_OFF; break; - - case HWTSTAMP_TX_ONESTEP_SYNC: - case HWTSTAMP_TX_ONESTEP_P2P: - DP_ERR(edev, "One-step timestamping is not supported\n"); - return -ERANGE; } spin_lock_bh(&ptp->lock); @@ -286,39 +278,65 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev) ptp->ops->cfg_filters(edev->cdev, rx_filter, tx_type); spin_unlock_bh(&ptp->lock); - - return 0; } -int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *ifr) +int qede_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; + struct qede_dev *edev = netdev_priv(netdev); struct qede_ptp *ptp; - int rc; + + if (!netif_running(netdev)) { + NL_SET_ERR_MSG_MOD(extack, "Device is down"); + return -EAGAIN; + } ptp = edev->ptp; - if (!ptp) + if (!ptp) { + NL_SET_ERR_MSG_MOD(extack, "HW timestamping is not supported"); return -EIO; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; + } DP_VERBOSE(edev, QED_MSG_DEBUG, - "HWTSTAMP IOCTL: Requested tx_type = %d, requested rx_filters = %d\n", - config.tx_type, config.rx_filter); + "HWTSTAMP SET: Requested tx_type = %d, requested rx_filters = %d\n", + config->tx_type, config->rx_filter); + + switch (config->tx_type) { + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_OFF: + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "One-step timestamping is not supported"); + return -ERANGE; + } ptp->hw_ts_ioctl_called = 1; - ptp->tx_type = config.tx_type; - ptp->rx_filter = config.rx_filter; + ptp->tx_type = config->tx_type; + ptp->rx_filter = config->rx_filter; - rc = qede_ptp_cfg_filters(edev); - if (rc) - return rc; + qede_ptp_cfg_filters(edev); + + config->rx_filter = ptp->rx_filter; + + return 0; +} - config.rx_filter = ptp->rx_filter; +int qede_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct qede_dev *edev = netdev_priv(netdev); + struct qede_ptp *ptp; - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; + ptp = edev->ptp; + if (!ptp) + return -EIO; + + config->tx_type = ptp->tx_type; + config->rx_filter = ptp->rx_filter; + + return 0; } int qede_ptp_get_ts_info(struct qede_dev *edev, struct kernel_ethtool_ts_info *info) diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.h b/drivers/net/ethernet/qlogic/qede/qede_ptp.h index adafc894797e..88f168395812 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.h +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.h @@ -14,7 +14,11 @@ void qede_ptp_rx_ts(struct qede_dev *edev, struct sk_buff *skb); void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb); -int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *req); +int qede_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config); +int qede_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); void qede_ptp_disable(struct qede_dev *edev); int qede_ptp_enable(struct qede_dev *edev); int qede_ptp_get_ts_info(struct qede_dev *edev, struct kernel_ethtool_ts_info *ts); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0b96b6aa4214..630319604211 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -59,6 +59,7 @@ #define FIRMWARE_8125D_2 "rtl_nic/rtl8125d-2.fw" #define FIRMWARE_8125K_1 "rtl_nic/rtl8125k-1.fw" #define FIRMWARE_8125BP_2 "rtl_nic/rtl8125bp-2.fw" +#define FIRMWARE_9151A_1 "rtl_nic/rtl9151a-1.fw" #define FIRMWARE_8126A_2 "rtl_nic/rtl8126a-2.fw" #define FIRMWARE_8126A_3 "rtl_nic/rtl8126a-3.fw" #define FIRMWARE_8127A_1 "rtl_nic/rtl8127a-1.fw" @@ -111,6 +112,7 @@ static const struct rtl_chip_info { { 0x7cf, 0x681, RTL_GIGA_MAC_VER_66, "RTL8125BP", FIRMWARE_8125BP_2 }, /* 8125D family. */ + { 0x7cf, 0x68b, RTL_GIGA_MAC_VER_64, "RTL9151A", FIRMWARE_9151A_1 }, { 0x7cf, 0x68a, RTL_GIGA_MAC_VER_64, "RTL8125K", FIRMWARE_8125K_1 }, { 0x7cf, 0x689, RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_2 }, { 0x7cf, 0x688, RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_1 }, @@ -774,6 +776,7 @@ MODULE_FIRMWARE(FIRMWARE_8125D_1); MODULE_FIRMWARE(FIRMWARE_8125D_2); MODULE_FIRMWARE(FIRMWARE_8125K_1); MODULE_FIRMWARE(FIRMWARE_8125BP_2); +MODULE_FIRMWARE(FIRMWARE_9151A_1); MODULE_FIRMWARE(FIRMWARE_8126A_2); MODULE_FIRMWARE(FIRMWARE_8126A_3); MODULE_FIRMWARE(FIRMWARE_8127A_1); @@ -1509,6 +1512,7 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_52: return RTL_DASH_EP; case RTL_GIGA_MAC_VER_66: + case RTL_GIGA_MAC_VER_80: return RTL_DASH_25_BP; default: return RTL_DASH_NONE; @@ -1517,11 +1521,20 @@ static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) static void rtl_set_d3_pll_down(struct rtl8169_private *tp, bool enable) { - if (tp->mac_version >= RTL_GIGA_MAC_VER_25 && - tp->mac_version != RTL_GIGA_MAC_VER_28 && - tp->mac_version != RTL_GIGA_MAC_VER_31 && - tp->mac_version != RTL_GIGA_MAC_VER_38) - r8169_mod_reg8_cond(tp, PMCH, D3_NO_PLL_DOWN, !enable); + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_24: + case RTL_GIGA_MAC_VER_28: + case RTL_GIGA_MAC_VER_31: + case RTL_GIGA_MAC_VER_38: + break; + case RTL_GIGA_MAC_VER_80: + r8169_mod_reg8_cond(tp, PMCH, D3_NO_PLL_DOWN, true); + break; + default: + r8169_mod_reg8_cond(tp, PMCH, D3HOT_NO_PLL_DOWN, true); + r8169_mod_reg8_cond(tp, PMCH, D3COLD_NO_PLL_DOWN, !enable); + break; + } } static void rtl_reset_packet_filter(struct rtl8169_private *tp) @@ -2376,26 +2389,6 @@ void r8169_apply_firmware(struct rtl8169_private *tp) } } -static void rtl8168_config_eee_mac(struct rtl8169_private *tp) -{ - /* Adjust EEE LED frequency */ - if (tp->mac_version != RTL_GIGA_MAC_VER_38) - RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); - - rtl_eri_set_bits(tp, 0x1b0, 0x0003); -} - -static void rtl8125a_config_eee_mac(struct rtl8169_private *tp) -{ - r8168_mac_ocp_modify(tp, 0xe040, 0, BIT(1) | BIT(0)); - r8168_mac_ocp_modify(tp, 0xeb62, 0, BIT(2) | BIT(1)); -} - -static void rtl8125b_config_eee_mac(struct rtl8169_private *tp) -{ - r8168_mac_ocp_modify(tp, 0xe040, 0, BIT(1) | BIT(0)); -} - static void rtl_rar_exgmac_set(struct rtl8169_private *tp, const u8 *addr) { rtl_eri_write(tp, 0xe0, ERIAR_MASK_1111, get_unaligned_le32(addr)); @@ -3173,8 +3166,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); - rtl8168_config_eee_mac(tp); - RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); rtl_mod_config5(tp, Spi_en, 0); @@ -3199,8 +3190,6 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN); RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN); rtl_mod_config5(tp, Spi_en, 0); - - rtl8168_config_eee_mac(tp); } static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) @@ -3250,8 +3239,6 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); - rtl8168_config_eee_mac(tp); - rtl_w0w1_eri(tp, 0x2fc, 0x01, 0x06); rtl_eri_clear_bits(tp, 0x1b0, BIT(12)); @@ -3392,8 +3379,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); - rtl8168_config_eee_mac(tp); - RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); @@ -3441,8 +3426,6 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); - rtl8168_config_eee_mac(tp); - rtl_w0w1_eri(tp, 0x2fc, 0x01, 0x06); RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN); @@ -3498,8 +3481,6 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp) rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000); - rtl8168_config_eee_mac(tp); - RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); @@ -3740,11 +3721,6 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp) rtl_loop_wait_low(tp, &rtl_mac_ocp_e00e_cond, 1000, 10); - if (tp->mac_version == RTL_GIGA_MAC_VER_61) - rtl8125a_config_eee_mac(tp); - else - rtl8125b_config_eee_mac(tp); - rtl_disable_rxdvgate(tp); } @@ -4747,6 +4723,41 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) return work_done; } +static void rtl_enable_tx_lpi(struct rtl8169_private *tp, bool enable) +{ + if (!rtl_supports_eee(tp)) + return; + + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_52: + /* Adjust EEE LED frequency */ + if (tp->mac_version != RTL_GIGA_MAC_VER_38) + RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07); + if (enable) + rtl_eri_set_bits(tp, 0x1b0, 0x0003); + else + rtl_eri_clear_bits(tp, 0x1b0, 0x0003); + break; + case RTL_GIGA_MAC_VER_61: + if (enable) { + r8168_mac_ocp_modify(tp, 0xe040, 0, 0x0003); + r8168_mac_ocp_modify(tp, 0xeb62, 0, 0x0006); + } else { + r8168_mac_ocp_modify(tp, 0xe040, 0x0003, 0); + r8168_mac_ocp_modify(tp, 0xeb62, 0x0006, 0); + } + break; + case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_LAST: + if (enable) + r8168_mac_ocp_modify(tp, 0xe040, 0, 0x0003); + else + r8168_mac_ocp_modify(tp, 0xe040, 0x0003, 0); + break; + default: + break; + } +} + static void r8169_phylink_handler(struct net_device *ndev) { struct rtl8169_private *tp = netdev_priv(ndev); @@ -4754,6 +4765,7 @@ static void r8169_phylink_handler(struct net_device *ndev) if (netif_carrier_ok(ndev)) { rtl_link_chg_patch(tp); + rtl_enable_tx_lpi(tp, tp->phydev->enable_tx_lpi); pm_request_resume(d); } else { pm_runtime_idle(d); @@ -5451,6 +5463,15 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } tp->aspm_manageable = !rc; + /* Fiber mode on RTL8127AF isn't supported */ + if (rtl_is_8125(tp)) { + u16 data = r8168_mac_ocp_read(tp, 0xd006); + + if ((data & 0xff) == 0x07) + return dev_err_probe(&pdev->dev, -ENODEV, + "Fiber mode not supported\n"); + } + tp->dash_type = rtl_get_dash_type(tp); tp->dash_enabled = rtl_dash_is_enabled(tp); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 75bad561b352..849c5a6c2af1 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -1521,8 +1521,10 @@ static int sxgbe_rx(struct sxgbe_priv_data *priv, int limit) skb = priv->rxq[qnum]->rx_skbuff[entry]; - if (unlikely(!skb)) + if (unlikely(!skb)) { netdev_err(priv->dev, "rx descriptor is not consistent\n"); + break; + } prefetch(skb->data - NET_IP_ALIGN); priv->rxq[qnum]->rx_skbuff[entry] = NULL; diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 87c5bea6c2a2..907fe2e927f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -349,6 +349,11 @@ config DWMAC_VISCONTI endif +config STMMAC_LIBPCI + tristate + help + This option enables the PCI bus helpers for the stmmac driver. + config DWMAC_INTEL tristate "Intel GMAC support" default X86 @@ -362,16 +367,18 @@ config DWMAC_INTEL config DWMAC_LOONGSON tristate "Loongson PCI DWMAC support" default MACH_LOONGSON64 - depends on (MACH_LOONGSON64 || COMPILE_TEST) && STMMAC_ETH && PCI + depends on (MACH_LOONGSON64 || COMPILE_TEST) && PCI depends on COMMON_CLK + select STMMAC_LIBPCI help This selects the LOONGSON PCI bus support for the stmmac driver, Support for ethernet controller on Loongson-2K1000 SoC and LS7A1000 bridge. config STMMAC_PCI tristate "STMMAC PCI bus support" - depends on STMMAC_ETH && PCI + depends on PCI depends on COMMON_CLK + select STMMAC_LIBPCI help This selects the platform specific bus support for the stmmac driver. This driver was tested on XLINX XC2V3000 FF1152AMT0221 diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 1681a8a28313..7bf528731034 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_DWMAC_VISCONTI) += dwmac-visconti.o stmmac-platform-objs:= stmmac_platform.o dwmac-altr-socfpga-objs := dwmac-socfpga.o +obj-$(CONFIG_STMMAC_LIBPCI) += stmmac_libpci.o obj-$(CONFIG_STMMAC_PCI) += stmmac-pci.o obj-$(CONFIG_DWMAC_INTEL) += dwmac-intel.o obj-$(CONFIG_DWMAC_LOONGSON) += dwmac-loongson.o diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index fb55efd52240..120a009c9992 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -83,14 +83,13 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb, return entry; } -static unsigned int is_jumbo_frm(int len, int enh_desc) +static bool is_jumbo_frm(unsigned int len, bool enh_desc) { - unsigned int ret = 0; + bool ret = false; if ((enh_desc && (len > BUF_SIZE_8KiB)) || - (!enh_desc && (len > BUF_SIZE_2KiB))) { - ret = 1; - } + (!enh_desc && (len > BUF_SIZE_2KiB))) + ret = true; return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 7395bbb94aea..49df46be3669 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -548,6 +548,19 @@ struct dma_features { #define LPI_CTRL_STATUS_TLPIEX BIT(1) /* Transmit LPI Exit */ #define LPI_CTRL_STATUS_TLPIEN BIT(0) /* Transmit LPI Entry */ +/* Common definitions for AXI Master Bus Mode */ +#define DMA_AXI_AAL BIT(12) +#define DMA_AXI_BLEN256 BIT(7) +#define DMA_AXI_BLEN128 BIT(6) +#define DMA_AXI_BLEN64 BIT(5) +#define DMA_AXI_BLEN32 BIT(4) +#define DMA_AXI_BLEN16 BIT(3) +#define DMA_AXI_BLEN8 BIT(2) +#define DMA_AXI_BLEN4 BIT(1) +#define DMA_AXI_BLEN_MASK GENMASK(7, 1) + +void stmmac_axi_blen_to_mask(u32 *regval, const u32 *blen, size_t len); + #define STMMAC_CHAIN_MODE 0x1 #define STMMAC_RING_MODE 0x2 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c index 84072c8ed741..5e0fc31762d9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c @@ -34,7 +34,7 @@ static void gmac_write_reg(struct anarion_gmac *gmac, uint8_t reg, uint32_t val) writel(val, gmac->ctl_block + reg); } -static int anarion_gmac_init(struct platform_device *pdev, void *priv) +static int anarion_gmac_init(struct device *dev, void *priv) { uint32_t sw_config; struct anarion_gmac *gmac = priv; @@ -52,7 +52,7 @@ static int anarion_gmac_init(struct platform_device *pdev, void *priv) return 0; } -static void anarion_gmac_exit(struct platform_device *pdev, void *priv) +static void anarion_gmac_exit(struct device *dev, void *priv) { struct anarion_gmac *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index c7cd6497d42d..d043bad4a862 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -38,8 +38,6 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, { struct device *dev = &pdev->dev; u32 burst_map = 0; - u32 bit_index = 0; - u32 a_index = 0; if (!plat_dat->axi) { plat_dat->axi = devm_kzalloc(&pdev->dev, @@ -83,30 +81,8 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, } device_property_read_u32(dev, "snps,burst-map", &burst_map); - /* converts burst-map bitmask to burst array */ - for (bit_index = 0; bit_index < 7; bit_index++) { - if (burst_map & (1 << bit_index)) { - switch (bit_index) { - case 0: - plat_dat->axi->axi_blen[a_index] = 4; break; - case 1: - plat_dat->axi->axi_blen[a_index] = 8; break; - case 2: - plat_dat->axi->axi_blen[a_index] = 16; break; - case 3: - plat_dat->axi->axi_blen[a_index] = 32; break; - case 4: - plat_dat->axi->axi_blen[a_index] = 64; break; - case 5: - plat_dat->axi->axi_blen[a_index] = 128; break; - case 6: - plat_dat->axi->axi_blen[a_index] = 256; break; - default: - break; - } - a_index++; - } - } + plat_dat->axi->axi_blen_regval = FIELD_PREP(DMA_AXI_BLEN_MASK, + burst_map); /* dwc-qos needs GMAC4, AAL, TSO and PMT */ plat_dat->core_type = DWMAC_CORE_GMAC4; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c index 1dcf2037001e..bcb8e000e720 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c @@ -58,14 +58,14 @@ static int eic7700_clks_config(void *priv, bool enabled) return ret; } -static int eic7700_dwmac_init(struct platform_device *pdev, void *priv) +static int eic7700_dwmac_init(struct device *dev, void *priv) { struct eic7700_qos_priv *dwc = priv; return eic7700_clks_config(dwc, true); } -static void eic7700_dwmac_exit(struct platform_device *pdev, void *priv) +static void eic7700_dwmac_exit(struct device *dev, void *priv) { struct eic7700_qos_priv *dwc = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index b2194e414ec1..aad1be1ec4c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -569,26 +569,6 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Set default number of RX and TX queues to use */ - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; } static struct phylink_pcs *intel_mgbe_select_pcs(struct stmmac_priv *priv, @@ -629,22 +609,12 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; - for (i = 0; i < plat->rx_queues_to_use; i++) { + for (i = 0; i < plat->rx_queues_to_use; i++) plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - plat->rx_queues_cfg[i].chan = i; - - /* Disable Priority config by default */ - plat->rx_queues_cfg[i].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[i].pkt_route = 0x0; - } for (i = 0; i < plat->tx_queues_to_use; i++) { plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - /* Disable Priority config by default */ - plat->tx_queues_cfg[i].use_prio = false; /* Default TX Q0 to use TSO and rest TXQ for TBS */ if (i > 0) plat->tx_queues_cfg[i].tbs_en = 1; @@ -680,9 +650,8 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->axi->axi_xit_frm = 0; plat->axi->axi_wr_osr_lmt = 1; plat->axi->axi_rd_osr_lmt = 1; - plat->axi->axi_blen[0] = 4; - plat->axi->axi_blen[1] = 8; - plat->axi->axi_blen[2] = 16; + plat->axi->axi_blen_regval = DMA_AXI_BLEN4 | DMA_AXI_BLEN8 | + DMA_AXI_BLEN16; plat->ptp_max_adj = plat->clk_ptp_rate; @@ -706,15 +675,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->ptp_clk_freq_config = intel_mgbe_ptp_clk_freq_config; - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - plat->flags |= STMMAC_FLAG_VLAN_FAIL_Q_EN; /* Use the last Rx queue */ @@ -1286,7 +1246,7 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (!intel_priv) return -ENOMEM; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index dd2fc39ec3e2..107a7c84ace8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -8,6 +8,7 @@ #include <linux/device.h> #include <linux/of_irq.h> #include "stmmac.h" +#include "stmmac_libpci.h" #include "dwmac_dma.h" #include "dwmac1000.h" @@ -95,28 +96,12 @@ static void loongson_default_data(struct pci_dev *pdev, plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; - /* Set default value for multicast hash bins */ + /* Increase the default value for multicast hash bins */ plat->multicast_filter_bins = 256; - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; - plat->clk_ref_rate = 125000000; plat->clk_ptp_rate = 125000000; - /* Default to phy auto-detection */ - plat->phy_addr = -1; - plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; @@ -140,8 +125,6 @@ static void loongson_default_data(struct pci_dev *pdev, break; default: ld->multichan = 0; - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; break; } } @@ -520,37 +503,6 @@ static int loongson_dwmac_fix_reset(struct stmmac_priv *priv, void __iomem *ioad 10000, 2000000); } -static int loongson_dwmac_suspend(struct device *dev, void *bsp_priv) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = pci_save_state(pdev); - if (ret) - return ret; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, true); - return 0; -} - -static int loongson_dwmac_resume(struct device *dev, void *bsp_priv) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - - ret = pci_enable_device(pdev); - if (ret) - return ret; - - pci_set_master(pdev); - - return 0; -} - static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct plat_stmmacenet_data *plat; @@ -559,7 +511,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id struct loongson_data *ld; int ret; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; @@ -595,8 +547,8 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->bsp_priv = ld; plat->mac_setup = loongson_dwmac_setup; plat->fix_soc_reset = loongson_dwmac_fix_reset; - plat->suspend = loongson_dwmac_suspend; - plat->resume = loongson_dwmac_resume; + plat->suspend = stmmac_pci_plat_suspend; + plat->resume = stmmac_pci_plat_resume; ld->dev = &pdev->dev; ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c index 894ee66f5c9b..de9aba756aac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c @@ -48,7 +48,7 @@ struct ls1x_dwmac { struct ls1x_data { int (*setup)(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat); - int (*init)(struct platform_device *pdev, void *bsp_priv); + int (*init)(struct device *dev, void *bsp_priv); }; static int ls1b_dwmac_setup(struct platform_device *pdev, @@ -79,7 +79,7 @@ static int ls1b_dwmac_setup(struct platform_device *pdev, return 0; } -static int ls1b_dwmac_syscon_init(struct platform_device *pdev, void *priv) +static int ls1b_dwmac_syscon_init(struct device *dev, void *priv) { struct ls1x_dwmac *dwmac = priv; struct plat_stmmacenet_data *plat = dwmac->plat_dat; @@ -98,7 +98,7 @@ static int ls1b_dwmac_syscon_init(struct platform_device *pdev, void *priv) GMAC0_USE_TXCLK | GMAC0_USE_PWM01); break; default: - dev_err(&pdev->dev, "Unsupported PHY mode %u\n", + dev_err(dev, "Unsupported PHY mode %u\n", plat->phy_interface); return -EOPNOTSUPP; } @@ -122,7 +122,7 @@ static int ls1b_dwmac_syscon_init(struct platform_device *pdev, void *priv) GMAC1_USE_TXCLK | GMAC1_USE_PWM23); break; default: - dev_err(&pdev->dev, "Unsupported PHY mode %u\n", + dev_err(dev, "Unsupported PHY mode %u\n", plat->phy_interface); return -EOPNOTSUPP; } @@ -133,7 +133,7 @@ static int ls1b_dwmac_syscon_init(struct platform_device *pdev, void *priv) return 0; } -static int ls1c_dwmac_syscon_init(struct platform_device *pdev, void *priv) +static int ls1c_dwmac_syscon_init(struct device *dev, void *priv) { struct ls1x_dwmac *dwmac = priv; struct plat_stmmacenet_data *plat = dwmac->plat_dat; @@ -143,7 +143,7 @@ static int ls1c_dwmac_syscon_init(struct platform_device *pdev, void *priv) phy_intf_sel = stmmac_get_phy_intf_sel(plat->phy_interface); if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && phy_intf_sel != PHY_INTF_SEL_RMII) { - dev_err(&pdev->dev, "Unsupported PHY-mode %u\n", + dev_err(dev, "Unsupported PHY-mode %u\n", plat->phy_interface); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 1a616a71c36a..0826a7bd32ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -116,27 +116,39 @@ struct qcom_ethqos { bool needs_sgmii_loopback; }; -static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset) +static u32 rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset) { return readl(ethqos->rgmii_base + offset); } -static void rgmii_writel(struct qcom_ethqos *ethqos, - int value, unsigned int offset) +static void rgmii_writel(struct qcom_ethqos *ethqos, u32 value, + unsigned int offset) { writel(value, ethqos->rgmii_base + offset); } -static void rgmii_updatel(struct qcom_ethqos *ethqos, - int mask, int val, unsigned int offset) +static void rgmii_updatel(struct qcom_ethqos *ethqos, u32 mask, u32 val, + unsigned int offset) { - unsigned int temp; + u32 temp; temp = rgmii_readl(ethqos, offset); temp = (temp & ~(mask)) | val; rgmii_writel(ethqos, temp, offset); } +static void rgmii_setmask(struct qcom_ethqos *ethqos, u32 mask, + unsigned int offset) +{ + rgmii_updatel(ethqos, mask, mask, offset); +} + +static void rgmii_clrmask(struct qcom_ethqos *ethqos, u32 mask, + unsigned int offset) +{ + rgmii_updatel(ethqos, mask, 0, offset); +} + static void rgmii_dump(void *priv) { struct qcom_ethqos *ethqos = priv; @@ -194,8 +206,7 @@ qcom_ethqos_set_sgmii_loopback(struct qcom_ethqos *ethqos, bool enable) static void ethqos_set_func_clk_en(struct qcom_ethqos *ethqos) { qcom_ethqos_set_sgmii_loopback(ethqos, true); - rgmii_updatel(ethqos, RGMII_CONFIG_FUNC_CLK_EN, - RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG); + rgmii_setmask(ethqos, RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG); } static const struct ethqos_emac_por emac_v2_3_0_por[] = { @@ -300,69 +311,55 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = { static int ethqos_dll_configure(struct qcom_ethqos *ethqos) { struct device *dev = ðqos->pdev->dev; - unsigned int val; - int retry = 1000; + u32 val; /* Set CDR_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EN, - SDCC_DLL_CONFIG_CDR_EN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_CDR_EN, SDCC_HC_REG_DLL_CONFIG); /* Set CDR_EXT_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EXT_EN, - SDCC_DLL_CONFIG_CDR_EXT_EN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_CDR_EXT_EN, + SDCC_HC_REG_DLL_CONFIG); /* Clear CK_OUT_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, - 0, SDCC_HC_REG_DLL_CONFIG); + rgmii_clrmask(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, + SDCC_HC_REG_DLL_CONFIG); /* Set DLL_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN, - SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG); if (!ethqos->has_emac_ge_3) { - rgmii_updatel(ethqos, SDCC_DLL_MCLK_GATING_EN, - 0, SDCC_HC_REG_DLL_CONFIG); + rgmii_clrmask(ethqos, SDCC_DLL_MCLK_GATING_EN, + SDCC_HC_REG_DLL_CONFIG); - rgmii_updatel(ethqos, SDCC_DLL_CDR_FINE_PHASE, - 0, SDCC_HC_REG_DLL_CONFIG); + rgmii_clrmask(ethqos, SDCC_DLL_CDR_FINE_PHASE, + SDCC_HC_REG_DLL_CONFIG); } /* Wait for CK_OUT_EN clear */ - do { - val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG); - val &= SDCC_DLL_CONFIG_CK_OUT_EN; - if (!val) - break; - mdelay(1); - retry--; - } while (retry > 0); - if (!retry) + if (read_poll_timeout_atomic(rgmii_readl, val, + !(val & SDCC_DLL_CONFIG_CK_OUT_EN), + 1000, 1000000, false, + ethqos, SDCC_HC_REG_DLL_CONFIG)) dev_err(dev, "Clear CK_OUT_EN timedout\n"); /* Set CK_OUT_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, - SDCC_DLL_CONFIG_CK_OUT_EN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, + SDCC_HC_REG_DLL_CONFIG); /* Wait for CK_OUT_EN set */ - retry = 1000; - do { - val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG); - val &= SDCC_DLL_CONFIG_CK_OUT_EN; - if (val) - break; - mdelay(1); - retry--; - } while (retry > 0); - if (!retry) + if (read_poll_timeout_atomic(rgmii_readl, val, + val & SDCC_DLL_CONFIG_CK_OUT_EN, + 1000, 1000000, false, + ethqos, SDCC_HC_REG_DLL_CONFIG)) dev_err(dev, "Set CK_OUT_EN timedout\n"); /* Set DDR_CAL_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_CAL_EN, - SDCC_DLL_CONFIG2_DDR_CAL_EN, SDCC_HC_REG_DLL_CONFIG2); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG2_DDR_CAL_EN, + SDCC_HC_REG_DLL_CONFIG2); if (!ethqos->has_emac_ge_3) { - rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DLL_CLOCK_DIS, - 0, SDCC_HC_REG_DLL_CONFIG2); + rgmii_clrmask(ethqos, SDCC_DLL_CONFIG2_DLL_CLOCK_DIS, + SDCC_HC_REG_DLL_CONFIG2); rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_MCLK_FREQ_CALC, 0x1A << 10, SDCC_HC_REG_DLL_CONFIG2); @@ -370,8 +367,7 @@ static int ethqos_dll_configure(struct qcom_ethqos *ethqos) rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SEL, BIT(2), SDCC_HC_REG_DLL_CONFIG2); - rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW, - SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW, + rgmii_setmask(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW, SDCC_HC_REG_DLL_CONFIG2); } @@ -392,8 +388,8 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed) phase_shift = RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN; /* Disable loopback mode */ - rgmii_updatel(ethqos, RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN, + RGMII_IO_MACRO_CONFIG2); /* Determine if this platform wants loopback enabled after programming */ if (ethqos->rgmii_config_loopback_en) @@ -402,29 +398,26 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed) loopback = 0; /* Select RGMII, write 0 to interface select */ - rgmii_updatel(ethqos, RGMII_CONFIG_INTF_SEL, - 0, RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_INTF_SEL, RGMII_IO_MACRO_CONFIG); switch (speed) { case SPEED_1000: - rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE, - RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, - 0, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, - RGMII_CONFIG_POS_NEG_DATA_SEL, + rgmii_setmask(ethqos, RGMII_CONFIG_DDR_MODE, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP, - RGMII_CONFIG_PROG_SWAP, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_setmask(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, + RGMII_IO_MACRO_CONFIG); + rgmii_setmask(ethqos, RGMII_CONFIG_PROG_SWAP, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, + RGMII_IO_MACRO_CONFIG2); rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN, phase_shift, RGMII_IO_MACRO_CONFIG2); - rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, - 0, RGMII_IO_MACRO_CONFIG2); - rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, - RGMII_CONFIG2_RX_PROG_SWAP, + rgmii_clrmask(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, + RGMII_IO_MACRO_CONFIG2); + rgmii_setmask(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, RGMII_IO_MACRO_CONFIG2); /* PRG_RCLK_DLY = TCXO period * TCXO_CYCLES_CNT / 2 * RX delay ns, @@ -439,87 +432,78 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed) rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_RCLK_DLY, 57, SDCC_HC_REG_DDR_CONFIG); } - rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_DLY_EN, - SDCC_DDR_CONFIG_PRG_DLY_EN, + rgmii_setmask(ethqos, SDCC_DDR_CONFIG_PRG_DLY_EN, SDCC_HC_REG_DDR_CONFIG); rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, loopback, RGMII_IO_MACRO_CONFIG); break; case SPEED_100: - rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE, - RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, - RGMII_CONFIG_BYPASS_TX_ID_EN, + rgmii_setmask(ethqos, RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, - 0, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP, - 0, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_setmask(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_PROG_SWAP, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, + RGMII_IO_MACRO_CONFIG2); rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN, phase_shift, RGMII_IO_MACRO_CONFIG2); rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_2, BIT(6), RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, + RGMII_IO_MACRO_CONFIG2); if (ethqos->has_emac_ge_3) - rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, - RGMII_CONFIG2_RX_PROG_SWAP, + rgmii_setmask(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, RGMII_IO_MACRO_CONFIG2); else - rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, + RGMII_IO_MACRO_CONFIG2); /* Write 0x5 to PRG_RCLK_DLY_CODE */ rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE, (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, - SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, + rgmii_setmask(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, - SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, + rgmii_setmask(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, SDCC_HC_REG_DDR_CONFIG); rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, loopback, RGMII_IO_MACRO_CONFIG); break; case SPEED_10: - rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE, - RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, - RGMII_CONFIG_BYPASS_TX_ID_EN, + rgmii_setmask(ethqos, RGMII_CONFIG_DDR_MODE, + RGMII_IO_MACRO_CONFIG); + rgmii_setmask(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, + RGMII_IO_MACRO_CONFIG); + rgmii_clrmask(ethqos, RGMII_CONFIG_PROG_SWAP, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL, - 0, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP, - 0, RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL, + RGMII_IO_MACRO_CONFIG2); rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN, phase_shift, RGMII_IO_MACRO_CONFIG2); rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_9, BIT(12) | GENMASK(9, 8), RGMII_IO_MACRO_CONFIG); - rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_RSVD_CONFIG15, + RGMII_IO_MACRO_CONFIG2); if (ethqos->has_emac_ge_3) - rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, - RGMII_CONFIG2_RX_PROG_SWAP, + rgmii_setmask(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, RGMII_IO_MACRO_CONFIG2); else - rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, - 0, RGMII_IO_MACRO_CONFIG2); + rgmii_clrmask(ethqos, RGMII_CONFIG2_RX_PROG_SWAP, + RGMII_IO_MACRO_CONFIG2); /* Write 0x5 to PRG_RCLK_DLY_CODE */ rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE, (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, - SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, + rgmii_setmask(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY, SDCC_HC_REG_DDR_CONFIG); - rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, - SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, + rgmii_setmask(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN, SDCC_HC_REG_DDR_CONFIG); rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN, loopback, RGMII_IO_MACRO_CONFIG); @@ -535,8 +519,8 @@ static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos, int speed) static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed) { struct device *dev = ðqos->pdev->dev; - volatile unsigned int dll_lock; - unsigned int i, retry = 1000; + unsigned int i; + u32 val; /* Reset to POR values and enable clk */ for (i = 0; i < ethqos->num_por; i++) @@ -547,12 +531,12 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed) /* Initialize the DLL first */ /* Set DLL_RST */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST, - SDCC_DLL_CONFIG_DLL_RST, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_DLL_RST, + SDCC_HC_REG_DLL_CONFIG); /* Set PDN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, - SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_PDN, + SDCC_HC_REG_DLL_CONFIG); if (ethqos->has_emac_ge_3) { if (speed == SPEED_1000) { @@ -566,21 +550,18 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed) } /* Clear DLL_RST */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST, 0, - SDCC_HC_REG_DLL_CONFIG); + rgmii_clrmask(ethqos, SDCC_DLL_CONFIG_DLL_RST, SDCC_HC_REG_DLL_CONFIG); /* Clear PDN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, 0, - SDCC_HC_REG_DLL_CONFIG); + rgmii_clrmask(ethqos, SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG); if (speed != SPEED_100 && speed != SPEED_10) { /* Set DLL_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN, - SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG); + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_DLL_EN, + SDCC_HC_REG_DLL_CONFIG); /* Set CK_OUT_EN */ - rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, - SDCC_DLL_CONFIG_CK_OUT_EN, + rgmii_setmask(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN, SDCC_HC_REG_DLL_CONFIG); /* Set USR_CTL bit 26 with mask of 3 bits */ @@ -589,14 +570,10 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos, int speed) SDCC_USR_CTL); /* wait for DLL LOCK */ - do { - mdelay(1); - dll_lock = rgmii_readl(ethqos, SDC4_STATUS); - if (dll_lock & SDC4_STATUS_DLL_LOCK) - break; - retry--; - } while (retry > 0); - if (!retry) + if (read_poll_timeout_atomic(rgmii_readl, val, + val & SDC4_STATUS_DLL_LOCK, + 1000, 1000000, true, + ethqos, SDC4_STATUS)) dev_err(dev, "Timeout while waiting for DLL lock\n"); } @@ -631,15 +608,13 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) switch (speed) { case SPEED_2500: - rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, - RGMII_CONFIG2_RGMII_CLK_SEL_CFG, + rgmii_setmask(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); ethqos_set_serdes_speed(ethqos, SPEED_2500); ethqos_pcs_set_inband(priv, false); break; case SPEED_1000: - rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, - RGMII_CONFIG2_RGMII_CLK_SEL_CFG, + rgmii_setmask(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); ethqos_set_serdes_speed(ethqos, SPEED_1000); ethqos_pcs_set_inband(priv, true); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c index bc7bb975803c..be7f5eb2cdcf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c @@ -91,7 +91,7 @@ static struct phylink_pcs *renesas_gmac_select_pcs(struct stmmac_priv *priv, return priv->hw->phylink_pcs; } -static int renesas_gbeth_init(struct platform_device *pdev, void *priv) +static int renesas_gbeth_init(struct device *dev, void *priv) { struct plat_stmmacenet_data *plat_dat; struct renesas_gbeth *gbeth = priv; @@ -113,7 +113,7 @@ static int renesas_gbeth_init(struct platform_device *pdev, void *priv) return ret; } -static void renesas_gbeth_exit(struct platform_device *pdev, void *priv) +static void renesas_gbeth_exit(struct device *dev, void *priv) { struct plat_stmmacenet_data *plat_dat; struct renesas_gbeth *gbeth = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index a5c7e03ebc63..0a95f54e725e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -149,11 +149,13 @@ static int rk_set_clk_mac_speed(struct rk_priv_data *bsp_priv, return clk_set_rate(clk_mac_speed, rate); } -#define HIWORD_UPDATE(val, mask, shift) \ - (FIELD_PREP_WM16((mask) << (shift), (val))) +#define GRF_FIELD(hi, lo, val) \ + FIELD_PREP_WM16(GENMASK_U16(hi, lo), val) +#define GRF_FIELD_CONST(hi, lo, val) \ + FIELD_PREP_WM16_CONST(GENMASK_U16(hi, lo), val) -#define GRF_BIT(nr) (BIT(nr) | BIT(nr+16)) -#define GRF_CLR_BIT(nr) (BIT(nr+16)) +#define GRF_BIT(nr) (BIT(nr) | BIT(nr+16)) +#define GRF_CLR_BIT(nr) (BIT(nr+16)) #define DELAY_ENABLE(soc, tx, rx) \ (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \ @@ -167,9 +169,9 @@ static int rk_set_clk_mac_speed(struct rk_priv_data *bsp_priv, #define RK_MACPHY_ENABLE GRF_BIT(0) #define RK_MACPHY_DISABLE GRF_CLR_BIT(0) #define RK_MACPHY_CFG_CLK_50M GRF_BIT(14) -#define RK_GMAC2PHY_RMII_MODE (GRF_BIT(6) | GRF_CLR_BIT(7)) -#define RK_GRF_CON2_MACPHY_ID HIWORD_UPDATE(0x1234, 0xffff, 0) -#define RK_GRF_CON3_MACPHY_ID HIWORD_UPDATE(0x35, 0x3f, 0) +#define RK_GMAC2PHY_RMII_MODE GRF_FIELD(7, 6, 1) +#define RK_GRF_CON2_MACPHY_ID GRF_FIELD(15, 0, 0x1234) +#define RK_GRF_CON3_MACPHY_ID GRF_FIELD(5, 0, 0x35) static void rk_gmac_integrated_ephy_powerup(struct rk_priv_data *priv) { @@ -203,7 +205,7 @@ static void rk_gmac_integrated_ephy_powerdown(struct rk_priv_data *priv) #define RK_FEPHY_SHUTDOWN GRF_BIT(1) #define RK_FEPHY_POWERUP GRF_CLR_BIT(1) #define RK_FEPHY_INTERNAL_RMII_SEL GRF_BIT(6) -#define RK_FEPHY_24M_CLK_SEL (GRF_BIT(8) | GRF_BIT(9)) +#define RK_FEPHY_24M_CLK_SEL GRF_FIELD(9, 8, 3) #define RK_FEPHY_PHY_ID GRF_BIT(11) static void rk_gmac_integrated_fephy_powerup(struct rk_priv_data *priv, @@ -232,15 +234,14 @@ static void rk_gmac_integrated_fephy_powerdown(struct rk_priv_data *priv, #define PX30_GRF_GMAC_CON1 0x0904 /* PX30_GRF_GMAC_CON1 */ -#define PX30_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ - GRF_BIT(6)) +#define PX30_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define PX30_GMAC_SPEED_10M GRF_CLR_BIT(2) #define PX30_GMAC_SPEED_100M GRF_BIT(2) static void px30_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, - PX30_GMAC_PHY_INTF_SEL_RMII); + PX30_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static int px30_set_speed(struct rk_priv_data *bsp_priv, @@ -285,23 +286,20 @@ static const struct rk_gmac_ops px30_ops = { #define RK3128_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) #define RK3128_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3128_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3128_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3128_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3128_GRF_MAC_CON1 */ -#define RK3128_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8)) -#define RK3128_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8)) +#define RK3128_GMAC_PHY_INTF_SEL(val) GRF_FIELD(8, 6, val) #define RK3128_GMAC_FLOW_CTRL GRF_BIT(9) #define RK3128_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) #define RK3128_GMAC_SPEED_10M GRF_CLR_BIT(10) #define RK3128_GMAC_SPEED_100M GRF_BIT(10) #define RK3128_GMAC_RMII_CLK_25M GRF_BIT(11) #define RK3128_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) -#define RK3128_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) -#define RK3128_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) -#define RK3128_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_CLK_125M GRF_FIELD_CONST(13, 12, 0) +#define RK3128_GMAC_CLK_25M GRF_FIELD_CONST(13, 12, 3) +#define RK3128_GMAC_CLK_2_5M GRF_FIELD_CONST(13, 12, 2) #define RK3128_GMAC_RMII_MODE GRF_BIT(14) #define RK3128_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) @@ -309,7 +307,7 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_PHY_INTF_SEL_RGMII | + RK3128_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3128_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0, DELAY_ENABLE(RK3128, tx_delay, rx_delay) | @@ -320,7 +318,8 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE); + RK3128_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3128_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3128_reg_speed_data = { @@ -350,23 +349,20 @@ static const struct rk_gmac_ops rk3128_ops = { #define RK3228_GRF_CON_MUX 0x50 /* RK3228_GRF_MAC_CON0 */ -#define RK3228_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3228_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3228_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3228_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3228_GRF_MAC_CON1 */ -#define RK3228_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3228_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3228_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3228_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3228_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3228_GMAC_SPEED_10M GRF_CLR_BIT(2) #define RK3228_GMAC_SPEED_100M GRF_BIT(2) #define RK3228_GMAC_RMII_CLK_25M GRF_BIT(7) #define RK3228_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(7) -#define RK3228_GMAC_CLK_125M (GRF_CLR_BIT(8) | GRF_CLR_BIT(9)) -#define RK3228_GMAC_CLK_25M (GRF_BIT(8) | GRF_BIT(9)) -#define RK3228_GMAC_CLK_2_5M (GRF_CLR_BIT(8) | GRF_BIT(9)) +#define RK3228_GMAC_CLK_125M GRF_FIELD_CONST(9, 8, 0) +#define RK3228_GMAC_CLK_25M GRF_FIELD_CONST(9, 8, 3) +#define RK3228_GMAC_CLK_2_5M GRF_FIELD_CONST(9, 8, 2) #define RK3228_GMAC_RMII_MODE GRF_BIT(10) #define RK3228_GMAC_RMII_MODE_CLR GRF_CLR_BIT(10) #define RK3228_GMAC_TXCLK_DLY_ENABLE GRF_BIT(0) @@ -381,7 +377,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_PHY_INTF_SEL_RGMII | + RK3228_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3228_GMAC_RMII_MODE_CLR | DELAY_ENABLE(RK3228, tx_delay, rx_delay)); @@ -393,7 +389,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_PHY_INTF_SEL_RMII | + RK3228_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | RK3228_GMAC_RMII_MODE); /* set MAC to RMII mode */ @@ -435,19 +431,16 @@ static const struct rk_gmac_ops rk3228_ops = { #define RK3288_GRF_SOC_CON3 0x0250 /*RK3288_GRF_SOC_CON1*/ -#define RK3288_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(6) | GRF_CLR_BIT(7) | \ - GRF_CLR_BIT(8)) -#define RK3288_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | \ - GRF_BIT(8)) +#define RK3288_GMAC_PHY_INTF_SEL(val) GRF_FIELD(8, 6, val) #define RK3288_GMAC_FLOW_CTRL GRF_BIT(9) #define RK3288_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) #define RK3288_GMAC_SPEED_10M GRF_CLR_BIT(10) #define RK3288_GMAC_SPEED_100M GRF_BIT(10) #define RK3288_GMAC_RMII_CLK_25M GRF_BIT(11) #define RK3288_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) -#define RK3288_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) -#define RK3288_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) -#define RK3288_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3288_GMAC_CLK_125M GRF_FIELD_CONST(13, 12, 0) +#define RK3288_GMAC_CLK_25M GRF_FIELD_CONST(13, 12, 3) +#define RK3288_GMAC_CLK_2_5M GRF_FIELD_CONST(13, 12, 2) #define RK3288_GMAC_RMII_MODE GRF_BIT(14) #define RK3288_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) @@ -456,14 +449,14 @@ static const struct rk_gmac_ops rk3228_ops = { #define RK3288_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) #define RK3288_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3288_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3288_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3288_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3288_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3288_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_PHY_INTF_SEL_RGMII | + RK3288_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3288_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3, DELAY_ENABLE(RK3288, tx_delay, rx_delay) | @@ -474,7 +467,8 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE); + RK3288_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3288_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3288_reg_speed_data = { @@ -501,8 +495,7 @@ static const struct rk_gmac_ops rk3288_ops = { #define RK3308_GRF_MAC_CON0 0x04a0 /* RK3308_GRF_MAC_CON0 */ -#define RK3308_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(2) | GRF_CLR_BIT(3) | \ - GRF_BIT(4)) +#define RK3308_GMAC_PHY_INTF_SEL(val) GRF_FIELD(4, 2, val) #define RK3308_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3308_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3308_GMAC_SPEED_10M GRF_CLR_BIT(0) @@ -511,7 +504,7 @@ static const struct rk_gmac_ops rk3288_ops = { static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, - RK3308_GMAC_PHY_INTF_SEL_RMII); + RK3308_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_reg_speed_data rk3308_reg_speed_data = { @@ -537,23 +530,20 @@ static const struct rk_gmac_ops rk3308_ops = { #define RK3328_GRF_MACPHY_CON1 0xb04 /* RK3328_GRF_MAC_CON0 */ -#define RK3328_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3328_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3328_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3328_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3328_GRF_MAC_CON1 */ -#define RK3328_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3328_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3328_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3328_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3328_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3328_GMAC_SPEED_10M GRF_CLR_BIT(2) #define RK3328_GMAC_SPEED_100M GRF_BIT(2) #define RK3328_GMAC_RMII_CLK_25M GRF_BIT(7) #define RK3328_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(7) -#define RK3328_GMAC_CLK_125M (GRF_CLR_BIT(11) | GRF_CLR_BIT(12)) -#define RK3328_GMAC_CLK_25M (GRF_BIT(11) | GRF_BIT(12)) -#define RK3328_GMAC_CLK_2_5M (GRF_CLR_BIT(11) | GRF_BIT(12)) +#define RK3328_GMAC_CLK_125M GRF_FIELD_CONST(12, 11, 0) +#define RK3328_GMAC_CLK_25M GRF_FIELD_CONST(12, 11, 3) +#define RK3328_GMAC_CLK_2_5M GRF_FIELD_CONST(12, 11, 2) #define RK3328_GMAC_RMII_MODE GRF_BIT(9) #define RK3328_GMAC_RMII_MODE_CLR GRF_CLR_BIT(9) #define RK3328_GMAC_TXCLK_DLY_ENABLE GRF_BIT(0) @@ -566,7 +556,7 @@ static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, - RK3328_GMAC_PHY_INTF_SEL_RGMII | + RK3328_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3328_GMAC_RMII_MODE_CLR | RK3328_GMAC_RXCLK_DLY_ENABLE | RK3328_GMAC_TXCLK_DLY_ENABLE); @@ -584,7 +574,7 @@ static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv) RK3328_GRF_MAC_CON1; regmap_write(bsp_priv->grf, reg, - RK3328_GMAC_PHY_INTF_SEL_RMII | + RK3328_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | RK3328_GMAC_RMII_MODE); } @@ -630,19 +620,16 @@ static const struct rk_gmac_ops rk3328_ops = { #define RK3366_GRF_SOC_CON7 0x041c /* RK3366_GRF_SOC_CON6 */ -#define RK3366_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3366_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3366_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3366_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3366_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3366_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3366_GMAC_SPEED_100M GRF_BIT(7) #define RK3366_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3366_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3366_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3366_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3366_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3366_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3366_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3366_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3366_GMAC_RMII_MODE GRF_BIT(6) #define RK3366_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -651,14 +638,14 @@ static const struct rk_gmac_ops rk3328_ops = { #define RK3366_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3366_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3366_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3366_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3366_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3366_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3366_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_PHY_INTF_SEL_RGMII | + RK3366_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3366_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7, DELAY_ENABLE(RK3366, tx_delay, rx_delay) | @@ -669,7 +656,8 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3366_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_PHY_INTF_SEL_RMII | RK3366_GMAC_RMII_MODE); + RK3366_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3366_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3366_reg_speed_data = { @@ -697,19 +685,16 @@ static const struct rk_gmac_ops rk3366_ops = { #define RK3368_GRF_SOC_CON16 0x0440 /* RK3368_GRF_SOC_CON15 */ -#define RK3368_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3368_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3368_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3368_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3368_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3368_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3368_GMAC_SPEED_100M GRF_BIT(7) #define RK3368_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3368_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3368_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3368_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3368_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3368_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3368_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3368_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3368_GMAC_RMII_MODE GRF_BIT(6) #define RK3368_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -718,14 +703,14 @@ static const struct rk_gmac_ops rk3366_ops = { #define RK3368_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3368_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3368_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3368_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3368_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3368_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3368_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_PHY_INTF_SEL_RGMII | + RK3368_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3368_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16, DELAY_ENABLE(RK3368, tx_delay, rx_delay) | @@ -736,7 +721,8 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE); + RK3368_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3368_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3368_reg_speed_data = { @@ -764,19 +750,16 @@ static const struct rk_gmac_ops rk3368_ops = { #define RK3399_GRF_SOC_CON6 0xc218 /* RK3399_GRF_SOC_CON5 */ -#define RK3399_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3399_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3399_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3399_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3399_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3399_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3399_GMAC_SPEED_100M GRF_BIT(7) #define RK3399_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3399_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3399_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3399_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3399_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3399_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3399_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3399_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3399_GMAC_RMII_MODE GRF_BIT(6) #define RK3399_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -785,14 +768,14 @@ static const struct rk_gmac_ops rk3368_ops = { #define RK3399_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3399_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3399_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3399_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3399_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3399_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3399_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_PHY_INTF_SEL_RGMII | + RK3399_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3399_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6, DELAY_ENABLE(RK3399, tx_delay, rx_delay) | @@ -803,7 +786,8 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3399_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_PHY_INTF_SEL_RMII | RK3399_GMAC_RMII_MODE); + RK3399_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3399_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3399_reg_speed_data = { @@ -901,8 +885,8 @@ static const struct rk_gmac_ops rk3506_ops = { #define RK3528_GMAC_TXCLK_DLY_ENABLE GRF_BIT(14) #define RK3528_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) -#define RK3528_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 8) -#define RK3528_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 0) +#define RK3528_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(15, 8, val) +#define RK3528_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(7, 0, val) #define RK3528_GMAC0_PHY_INTF_SEL_RMII GRF_BIT(1) #define RK3528_GMAC1_PHY_INTF_SEL_RGMII GRF_CLR_BIT(8) @@ -916,9 +900,9 @@ static const struct rk_gmac_ops rk3506_ops = { #define RK3528_GMAC1_CLK_RMII_DIV2 GRF_BIT(10) #define RK3528_GMAC1_CLK_RMII_DIV20 GRF_CLR_BIT(10) -#define RK3528_GMAC1_CLK_RGMII_DIV1 (GRF_CLR_BIT(11) | GRF_CLR_BIT(10)) -#define RK3528_GMAC1_CLK_RGMII_DIV5 (GRF_BIT(11) | GRF_BIT(10)) -#define RK3528_GMAC1_CLK_RGMII_DIV50 (GRF_BIT(11) | GRF_CLR_BIT(10)) +#define RK3528_GMAC1_CLK_RGMII_DIV1 GRF_FIELD_CONST(11, 10, 0) +#define RK3528_GMAC1_CLK_RGMII_DIV5 GRF_FIELD_CONST(11, 10, 3) +#define RK3528_GMAC1_CLK_RGMII_DIV50 GRF_FIELD_CONST(11, 10, 2) #define RK3528_GMAC0_CLK_RMII_GATE GRF_BIT(2) #define RK3528_GMAC0_CLK_RMII_NOGATE GRF_CLR_BIT(2) @@ -1029,10 +1013,7 @@ static const struct rk_gmac_ops rk3528_ops = { #define RK3568_GRF_GMAC1_CON1 0x038c /* RK3568_GRF_GMAC0_CON1 && RK3568_GRF_GMAC1_CON1 */ -#define RK3568_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3568_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3568_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3568_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3568_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3568_GMAC_RXCLK_DLY_ENABLE GRF_BIT(1) @@ -1041,8 +1022,8 @@ static const struct rk_gmac_ops rk3528_ops = { #define RK3568_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(0) /* RK3568_GRF_GMAC0_CON0 && RK3568_GRF_GMAC1_CON0 */ -#define RK3568_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3568_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3568_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3568_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) @@ -1059,7 +1040,7 @@ static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv, RK3568_GMAC_CLK_TX_DL_CFG(tx_delay)); regmap_write(bsp_priv->grf, con1, - RK3568_GMAC_PHY_INTF_SEL_RGMII | + RK3568_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3568_GMAC_RXCLK_DLY_ENABLE | RK3568_GMAC_TXCLK_DLY_ENABLE); } @@ -1070,7 +1051,8 @@ static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv) con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 : RK3568_GRF_GMAC0_CON1; - regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII); + regmap_write(bsp_priv->grf, con1, + RK3568_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_gmac_ops rk3568_ops = { @@ -1096,8 +1078,8 @@ static const struct rk_gmac_ops rk3568_ops = { #define RK3576_GMAC_TXCLK_DLY_ENABLE GRF_BIT(7) #define RK3576_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) -#define RK3576_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3576_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3576_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3576_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* SDGMAC_GRF */ #define RK3576_GRF_GMAC_CON0 0X0020 @@ -1112,12 +1094,9 @@ static const struct rk_gmac_ops rk3568_ops = { #define RK3576_GMAC_CLK_RMII_DIV2 GRF_BIT(5) #define RK3576_GMAC_CLK_RMII_DIV20 GRF_CLR_BIT(5) -#define RK3576_GMAC_CLK_RGMII_DIV1 \ - (GRF_CLR_BIT(6) | GRF_CLR_BIT(5)) -#define RK3576_GMAC_CLK_RGMII_DIV5 \ - (GRF_BIT(6) | GRF_BIT(5)) -#define RK3576_GMAC_CLK_RGMII_DIV50 \ - (GRF_BIT(6) | GRF_CLR_BIT(5)) +#define RK3576_GMAC_CLK_RGMII_DIV1 GRF_FIELD_CONST(6, 5, 0) +#define RK3576_GMAC_CLK_RGMII_DIV5 GRF_FIELD_CONST(6, 5, 3) +#define RK3576_GMAC_CLK_RGMII_DIV50 GRF_FIELD_CONST(6, 5, 2) #define RK3576_GMAC_CLK_RMII_GATE GRF_BIT(4) #define RK3576_GMAC_CLK_RMII_NOGATE GRF_CLR_BIT(4) @@ -1220,17 +1199,15 @@ static const struct rk_gmac_ops rk3576_ops = { #define RK3588_GMAC_TXCLK_DLY_ENABLE(id) GRF_BIT(2 * (id) + 2) #define RK3588_GMAC_TXCLK_DLY_DISABLE(id) GRF_CLR_BIT(2 * (id) + 2) -#define RK3588_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 8) -#define RK3588_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 0) +#define RK3588_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(15, 8, val) +#define RK3588_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(7, 0, val) /* php_grf */ #define RK3588_GRF_GMAC_CON0 0X0008 #define RK3588_GRF_CLK_CON1 0X0070 -#define RK3588_GMAC_PHY_INTF_SEL_RGMII(id) \ - (GRF_BIT(3 + (id) * 6) | GRF_CLR_BIT(4 + (id) * 6) | GRF_CLR_BIT(5 + (id) * 6)) -#define RK3588_GMAC_PHY_INTF_SEL_RMII(id) \ - (GRF_CLR_BIT(3 + (id) * 6) | GRF_CLR_BIT(4 + (id) * 6) | GRF_BIT(5 + (id) * 6)) +#define RK3588_GMAC_PHY_INTF_SEL(id, val) \ + (GRF_FIELD(5, 3, val) << ((id) * 6)) #define RK3588_GMAC_CLK_RMII_MODE(id) GRF_BIT(5 * (id)) #define RK3588_GMAC_CLK_RGMII_MODE(id) GRF_CLR_BIT(5 * (id)) @@ -1242,11 +1219,11 @@ static const struct rk_gmac_ops rk3576_ops = { #define RK3588_GMA_CLK_RMII_DIV20(id) GRF_CLR_BIT(5 * (id) + 2) #define RK3588_GMAC_CLK_RGMII_DIV1(id) \ - (GRF_CLR_BIT(5 * (id) + 2) | GRF_CLR_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 0) << ((id) * 5)) #define RK3588_GMAC_CLK_RGMII_DIV5(id) \ - (GRF_BIT(5 * (id) + 2) | GRF_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 3) << ((id) * 5)) #define RK3588_GMAC_CLK_RGMII_DIV50(id) \ - (GRF_CLR_BIT(5 * (id) + 2) | GRF_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 2) << ((id) * 5)) #define RK3588_GMAC_CLK_RMII_GATE(id) GRF_BIT(5 * (id) + 1) #define RK3588_GMAC_CLK_RMII_NOGATE(id) GRF_CLR_BIT(5 * (id) + 1) @@ -1260,7 +1237,7 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv, RK3588_GRF_GMAC_CON8; regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0, - RK3588_GMAC_PHY_INTF_SEL_RGMII(id)); + RK3588_GMAC_PHY_INTF_SEL(id, PHY_INTF_SEL_RGMII)); regmap_write(bsp_priv->php_grf, RK3588_GRF_CLK_CON1, RK3588_GMAC_CLK_RGMII_MODE(id)); @@ -1277,7 +1254,7 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3588_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0, - RK3588_GMAC_PHY_INTF_SEL_RMII(bsp_priv->id)); + RK3588_GMAC_PHY_INTF_SEL(bsp_priv->id, PHY_INTF_SEL_RMII)); regmap_write(bsp_priv->php_grf, RK3588_GRF_CLK_CON1, RK3588_GMAC_CLK_RMII_MODE(bsp_priv->id)); @@ -1347,8 +1324,7 @@ static const struct rk_gmac_ops rk3588_ops = { #define RV1108_GRF_GMAC_CON0 0X0900 /* RV1108_GRF_GMAC_CON0 */ -#define RV1108_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ - GRF_BIT(6)) +#define RV1108_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RV1108_GMAC_FLOW_CTRL GRF_BIT(3) #define RV1108_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RV1108_GMAC_SPEED_10M GRF_CLR_BIT(2) @@ -1359,7 +1335,7 @@ static const struct rk_gmac_ops rk3588_ops = { static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, - RV1108_GMAC_PHY_INTF_SEL_RMII); + RV1108_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_reg_speed_data rv1108_reg_speed_data = { @@ -1384,10 +1360,7 @@ static const struct rk_gmac_ops rv1108_ops = { #define RV1126_GRF_GMAC_CON2 0X0078 /* RV1126_GRF_GMAC_CON0 */ -#define RV1126_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RV1126_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RV1126_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RV1126_GMAC_FLOW_CTRL GRF_BIT(7) #define RV1126_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(7) #define RV1126_GMAC_M0_RXCLK_DLY_ENABLE GRF_BIT(1) @@ -1400,17 +1373,17 @@ static const struct rk_gmac_ops rv1108_ops = { #define RV1126_GMAC_M1_TXCLK_DLY_DISABLE GRF_CLR_BIT(2) /* RV1126_GRF_GMAC_CON1 */ -#define RV1126_GMAC_M0_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RV1126_GMAC_M0_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RV1126_GMAC_M0_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RV1126_GMAC_M0_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RV1126_GRF_GMAC_CON2 */ -#define RV1126_GMAC_M1_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RV1126_GMAC_M1_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RV1126_GMAC_M1_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RV1126_GMAC_M1_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0, - RV1126_GMAC_PHY_INTF_SEL_RGMII | + RV1126_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RV1126_GMAC_M0_RXCLK_DLY_ENABLE | RV1126_GMAC_M0_TXCLK_DLY_ENABLE | RV1126_GMAC_M1_RXCLK_DLY_ENABLE | @@ -1428,7 +1401,7 @@ static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rv1126_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0, - RV1126_GMAC_PHY_INTF_SEL_RMII); + RV1126_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_gmac_ops rv1126_ops = { @@ -1762,8 +1735,7 @@ static int rk_set_clk_tx_rate(void *bsp_priv_, struct clk *clk_tx_i, struct rk_priv_data *bsp_priv = bsp_priv_; if (bsp_priv->ops->set_speed) - return bsp_priv->ops->set_speed(bsp_priv, bsp_priv->phy_iface, - speed); + return bsp_priv->ops->set_speed(bsp_priv, interface, speed); return -EINVAL; } @@ -1790,6 +1762,22 @@ static int rk_gmac_resume(struct device *dev, void *bsp_priv_) return 0; } +static int rk_gmac_init(struct device *dev, void *bsp_priv) +{ + return rk_gmac_powerup(bsp_priv); +} + +static void rk_gmac_exit(struct device *dev, void *bsp_priv_) +{ + struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); + struct rk_priv_data *bsp_priv = bsp_priv_; + + rk_gmac_powerdown(bsp_priv); + + if (priv->plat->phy_node && bsp_priv->integrated_phy) + clk_put(bsp_priv->clk_phy); +} + static int rk_gmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -1822,6 +1810,8 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->get_interfaces = rk_get_interfaces; plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate; + plat_dat->init = rk_gmac_init; + plat_dat->exit = rk_gmac_exit; plat_dat->suspend = rk_gmac_suspend; plat_dat->resume = rk_gmac_resume; @@ -1833,33 +1823,7 @@ static int rk_gmac_probe(struct platform_device *pdev) if (ret) return ret; - ret = rk_gmac_powerup(plat_dat->bsp_priv); - if (ret) - return ret; - - ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); - if (ret) - goto err_gmac_powerdown; - - return 0; - -err_gmac_powerdown: - rk_gmac_powerdown(plat_dat->bsp_priv); - - return ret; -} - -static void rk_gmac_remove(struct platform_device *pdev) -{ - struct stmmac_priv *priv = netdev_priv(platform_get_drvdata(pdev)); - struct rk_priv_data *bsp_priv = priv->plat->bsp_priv; - - stmmac_dvr_remove(&pdev->dev); - - rk_gmac_powerdown(bsp_priv); - - if (priv->plat->phy_node && bsp_priv->integrated_phy) - clk_put(bsp_priv->clk_phy); + return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res); } static const struct of_device_id rk_gmac_dwmac_match[] = { @@ -1885,7 +1849,6 @@ MODULE_DEVICE_TABLE(of, rk_gmac_dwmac_match); static struct platform_driver rk_gmac_dwmac_driver = { .probe = rk_gmac_probe, - .remove = rk_gmac_remove, .driver = { .name = "rk_gmac-dwmac", .pm = &stmmac_simple_pm_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c index 2b7ad64bfdf7..5a485ee98fa7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c @@ -47,7 +47,7 @@ static int s32_gmac_write_phy_intf_select(struct s32_priv_data *gmac) return 0; } -static int s32_gmac_init(struct platform_device *pdev, void *priv) +static int s32_gmac_init(struct device *dev, void *priv) { struct s32_priv_data *gmac = priv; int ret; @@ -55,31 +55,31 @@ static int s32_gmac_init(struct platform_device *pdev, void *priv) /* Set initial TX interface clock */ ret = clk_prepare_enable(gmac->tx_clk); if (ret) { - dev_err(&pdev->dev, "Can't enable tx clock\n"); + dev_err(dev, "Can't enable tx clock\n"); return ret; } ret = clk_set_rate(gmac->tx_clk, GMAC_INTF_RATE_125M); if (ret) { - dev_err(&pdev->dev, "Can't set tx clock\n"); + dev_err(dev, "Can't set tx clock\n"); goto err_tx_disable; } /* Set initial RX interface clock */ ret = clk_prepare_enable(gmac->rx_clk); if (ret) { - dev_err(&pdev->dev, "Can't enable rx clock\n"); + dev_err(dev, "Can't enable rx clock\n"); goto err_tx_disable; } ret = clk_set_rate(gmac->rx_clk, GMAC_INTF_RATE_125M); if (ret) { - dev_err(&pdev->dev, "Can't set rx clock\n"); + dev_err(dev, "Can't set rx clock\n"); goto err_txrx_disable; } /* Set interface mode */ ret = s32_gmac_write_phy_intf_select(gmac); if (ret) { - dev_err(&pdev->dev, "Can't set PHY interface mode\n"); + dev_err(dev, "Can't set PHY interface mode\n"); goto err_txrx_disable; } @@ -92,7 +92,7 @@ err_tx_disable: return ret; } -static void s32_gmac_exit(struct platform_device *pdev, void *priv) +static void s32_gmac_exit(struct device *dev, void *priv) { struct s32_priv_data *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 49d651948e2b..a2b52d2c4eb6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -551,7 +551,7 @@ static struct phylink_pcs *socfpga_dwmac_select_pcs(struct stmmac_priv *priv, return priv->hw->phylink_pcs; } -static int socfpga_dwmac_init(struct platform_device *pdev, void *bsp_priv) +static int socfpga_dwmac_init(struct device *dev, void *bsp_priv) { struct socfpga_dwmac *dwmac = bsp_priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c index 3b7947a7a7ba..44d4ceb8415f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c @@ -7,11 +7,16 @@ #include <linux/clk.h> #include <linux/module.h> +#include <linux/property.h> #include <linux/mod_devicetable.h> #include <linux/platform_device.h> #include "stmmac_platform.h" +struct sophgo_dwmac_data { + bool has_internal_rx_delay; +}; + static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *stmmac_res) @@ -24,7 +29,6 @@ static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE; plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate; plat_dat->multicast_filter_bins = 0; - plat_dat->unicast_filter_entries = 1; return 0; } @@ -32,6 +36,7 @@ static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, static int sophgo_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; + const struct sophgo_dwmac_data *data; struct stmmac_resources stmmac_res; struct device *dev = &pdev->dev; int ret; @@ -50,11 +55,23 @@ static int sophgo_dwmac_probe(struct platform_device *pdev) if (ret) return ret; + data = device_get_match_data(&pdev->dev); + if (data && data->has_internal_rx_delay) { + plat_dat->phy_interface = phy_fix_phy_mode_for_mac_delays(plat_dat->phy_interface, + false, true); + if (plat_dat->phy_interface == PHY_INTERFACE_MODE_NA) + return -EINVAL; + } + return stmmac_dvr_probe(dev, plat_dat, &stmmac_res); } +static const struct sophgo_dwmac_data sg2042_dwmac_data = { + .has_internal_rx_delay = true, +}; + static const struct of_device_id sophgo_dwmac_match[] = { - { .compatible = "sophgo,sg2042-dwmac" }, + { .compatible = "sophgo,sg2042-dwmac", .data = &sg2042_dwmac_data }, { .compatible = "sophgo,sg2044-dwmac" }, { /* sentinel */ } }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index b0509ab6b31c..f50547b67fbc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -229,14 +229,14 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, return 0; } -static int sti_dwmac_init(struct platform_device *pdev, void *bsp_priv) +static int sti_dwmac_init(struct device *dev, void *bsp_priv) { struct sti_dwmac *dwmac = bsp_priv; return clk_prepare_enable(dwmac->clk); } -static void sti_dwmac_exit(struct platform_device *pdev, void *bsp_priv) +static void sti_dwmac_exit(struct device *dev, void *bsp_priv) { struct sti_dwmac *dwmac = bsp_priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 7434d4bbb526..8aa496ac85cc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -571,16 +571,16 @@ static const struct stmmac_dma_ops sun8i_dwmac_dma_ops = { static int sun8i_dwmac_power_internal_phy(struct stmmac_priv *priv); -static int sun8i_dwmac_init(struct platform_device *pdev, void *priv) +static int sun8i_dwmac_init(struct device *dev, void *priv) { - struct net_device *ndev = platform_get_drvdata(pdev); + struct net_device *ndev = dev_get_drvdata(dev); struct sunxi_priv_data *gmac = priv; int ret; if (gmac->regulator) { ret = regulator_enable(gmac->regulator); if (ret) { - dev_err(&pdev->dev, "Fail to enable regulator\n"); + dev_err(dev, "Fail to enable regulator\n"); return ret; } } @@ -1005,7 +1005,7 @@ static void sun8i_dwmac_unset_syscon(struct sunxi_priv_data *gmac) (H3_EPHY_SHUTDOWN | H3_EPHY_SELECT)); } -static void sun8i_dwmac_exit(struct platform_device *pdev, void *priv) +static void sun8i_dwmac_exit(struct device *dev, void *priv) { struct sunxi_priv_data *gmac = priv; @@ -1265,7 +1265,7 @@ static void sun8i_dwmac_shutdown(struct platform_device *pdev) struct stmmac_priv *priv = netdev_priv(ndev); struct sunxi_priv_data *gmac = priv->plat->bsp_priv; - sun8i_dwmac_exit(pdev, gmac); + sun8i_dwmac_exit(&pdev->dev, gmac); } static const struct of_device_id sun8i_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 7f560d78209d..52593ba3a3a3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -27,7 +27,7 @@ struct sunxi_priv_data { #define SUN7I_GMAC_GMII_RGMII_RATE 125000000 #define SUN7I_GMAC_MII_RATE 25000000 -static int sun7i_gmac_init(struct platform_device *pdev, void *priv) +static int sun7i_gmac_init(struct device *dev, void *priv) { struct sunxi_priv_data *gmac = priv; int ret = 0; @@ -58,7 +58,7 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv) return ret; } -static void sun7i_gmac_exit(struct platform_device *pdev, void *priv) +static void sun7i_gmac_exit(struct device *dev, void *priv) { struct sunxi_priv_data *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index a3378046b061..e291028ba56e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -186,7 +186,7 @@ static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) return 0; } -static int thead_dwmac_init(struct platform_device *pdev, void *priv) +static int thead_dwmac_init(struct device *dev, void *priv) { struct thead_dwmac *dwmac = priv; unsigned int reg; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index 118a22406a2e..5877fec9f6c3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -19,7 +19,6 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) { u32 value = readl(ioaddr + DMA_AXI_BUS_MODE); - int i; pr_info("dwmac1000: Master AXI performs %s burst length\n", !(value & DMA_AXI_UNDEF) ? "fixed" : "any"); @@ -39,33 +38,10 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) /* Depending on the UNDEF bit the Master AXI will perform any burst * length according to the BLEN programmed (by default all BLEN are - * set). + * set). Note that the UNDEF bit is readonly, and is the inverse of + * Bus Mode bit 16. */ - for (i = 0; i < AXI_BLEN; i++) { - switch (axi->axi_blen[i]) { - case 256: - value |= DMA_AXI_BLEN256; - break; - case 128: - value |= DMA_AXI_BLEN128; - break; - case 64: - value |= DMA_AXI_BLEN64; - break; - case 32: - value |= DMA_AXI_BLEN32; - break; - case 16: - value |= DMA_AXI_BLEN16; - break; - case 8: - value |= DMA_AXI_BLEN8; - break; - case 4: - value |= DMA_AXI_BLEN4; - break; - } - } + value = (value & ~DMA_AXI_BLEN_MASK) | axi->axi_blen_regval; writel(value, ioaddr + DMA_AXI_BUS_MODE); } @@ -159,10 +135,10 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv, if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable RX store and forward mode\n"); - csr6 |= DMA_CONTROL_RSF; + csr6 |= DMA_CONTROL_RSF | DMA_CONTROL_DFF; } else { pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode); - csr6 &= ~DMA_CONTROL_RSF; + csr6 &= ~(DMA_CONTROL_RSF | DMA_CONTROL_DFF); csr6 &= DMA_CONTROL_TC_RX_MASK; if (mode <= 32) csr6 |= DMA_CONTROL_RTC_32; @@ -286,6 +262,7 @@ const struct stmmac_dma_ops dwmac1000_dma_ops = { .dma_rx_mode = dwmac1000_dma_operation_mode_rx, .dma_tx_mode = dwmac1000_dma_operation_mode_tx, .enable_dma_transmission = dwmac_enable_dma_transmission, + .enable_dma_reception = dwmac_enable_dma_reception, .enable_dma_irq = dwmac_enable_dma_irq, .disable_dma_irq = dwmac_disable_dma_irq, .start_tx = dwmac_dma_start_tx, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index d87a8b595e6a..7b513324cfb0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -18,7 +18,6 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); - int i; pr_info("dwmac4: Master AXI performs %s burst length\n", (value & DMA_SYS_BUS_FB) ? "fixed" : "any"); @@ -38,33 +37,10 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) /* Depending on the UNDEF bit the Master AXI will perform any burst * length according to the BLEN programmed (by default all BLEN are - * set). + * set). Note that the UNDEF bit is readonly, and is the inverse of + * Bus Mode bit 16. */ - for (i = 0; i < AXI_BLEN; i++) { - switch (axi->axi_blen[i]) { - case 256: - value |= DMA_AXI_BLEN256; - break; - case 128: - value |= DMA_AXI_BLEN128; - break; - case 64: - value |= DMA_AXI_BLEN64; - break; - case 32: - value |= DMA_AXI_BLEN32; - break; - case 16: - value |= DMA_AXI_BLEN16; - break; - case 8: - value |= DMA_AXI_BLEN8; - break; - case 4: - value |= DMA_AXI_BLEN4; - break; - } - } + value = (value & ~DMA_AXI_BLEN_MASK) | axi->axi_blen_regval; writel(value, ioaddr + DMA_SYS_BUS_MODE); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h index 4f980dcd3958..f27126f05551 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h @@ -69,15 +69,8 @@ #define DMA_SYS_BUS_MB BIT(14) #define DMA_AXI_1KBBE BIT(13) -#define DMA_SYS_BUS_AAL BIT(12) +#define DMA_SYS_BUS_AAL DMA_AXI_AAL #define DMA_SYS_BUS_EAME BIT(11) -#define DMA_AXI_BLEN256 BIT(7) -#define DMA_AXI_BLEN128 BIT(6) -#define DMA_AXI_BLEN64 BIT(5) -#define DMA_AXI_BLEN32 BIT(4) -#define DMA_AXI_BLEN16 BIT(3) -#define DMA_AXI_BLEN8 BIT(2) -#define DMA_AXI_BLEN4 BIT(1) #define DMA_SYS_BUS_FB BIT(0) #define DMA_BURST_LEN_DEFAULT (DMA_AXI_BLEN256 | DMA_AXI_BLEN128 | \ @@ -85,8 +78,6 @@ DMA_AXI_BLEN16 | DMA_AXI_BLEN8 | \ DMA_AXI_BLEN4) -#define DMA_AXI_BURST_LEN_MASK 0x000000FE - /* DMA TBS Control */ #define DMA_TBS_FTOS GENMASK(31, 8) #define DMA_TBS_FTOV BIT(0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 5d9c18f5bbf5..054ecb20ce3f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -68,23 +68,14 @@ static inline u32 dma_chan_base_addr(u32 base, u32 chan) #define DMA_AXI_OSR_MAX 0xf #define DMA_AXI_MAX_OSR_LIMIT ((DMA_AXI_OSR_MAX << DMA_AXI_WR_OSR_LMT_SHIFT) | \ (DMA_AXI_OSR_MAX << DMA_AXI_RD_OSR_LMT_SHIFT)) -#define DMA_AXI_1KBBE BIT(13) -#define DMA_AXI_AAL BIT(12) -#define DMA_AXI_BLEN256 BIT(7) -#define DMA_AXI_BLEN128 BIT(6) -#define DMA_AXI_BLEN64 BIT(5) -#define DMA_AXI_BLEN32 BIT(4) -#define DMA_AXI_BLEN16 BIT(3) -#define DMA_AXI_BLEN8 BIT(2) -#define DMA_AXI_BLEN4 BIT(1) #define DMA_BURST_LEN_DEFAULT (DMA_AXI_BLEN256 | DMA_AXI_BLEN128 | \ DMA_AXI_BLEN64 | DMA_AXI_BLEN32 | \ DMA_AXI_BLEN16 | DMA_AXI_BLEN8 | \ DMA_AXI_BLEN4) -#define DMA_AXI_UNDEF BIT(0) +#define DMA_AXI_1KBBE BIT(13) -#define DMA_AXI_BURST_LEN_MASK 0x000000FE +#define DMA_AXI_UNDEF BIT(0) #define DMA_CUR_TX_BUF_ADDR 0x00001050 /* Current Host Tx Buffer */ #define DMA_CUR_RX_BUF_ADDR 0x00001054 /* Current Host Rx Buffer */ @@ -178,6 +169,7 @@ static inline u32 dma_chan_base_addr(u32 base, u32 chan) #define NUM_DWMAC4_DMA_REGS 27 void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan); +void dwmac_enable_dma_reception(void __iomem *ioaddr, u32 chan); void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 467f1a05747e..97a803d68e3a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -33,6 +33,11 @@ void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan) writel(1, ioaddr + DMA_CHAN_XMT_POLL_DEMAND(chan)); } +void dwmac_enable_dma_reception(void __iomem *ioaddr, u32 chan) +{ + writel(1, ioaddr + DMA_CHAN_RCV_POLL_DEMAND(chan)); +} + void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index e48cfa05000c..fecda3034d36 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -338,16 +338,9 @@ #define XGMAC_RD_OSR_LMT_SHIFT 16 #define XGMAC_EN_LPI BIT(15) #define XGMAC_LPI_XIT_PKT BIT(14) -#define XGMAC_AAL BIT(12) +#define XGMAC_AAL DMA_AXI_AAL #define XGMAC_EAME BIT(11) -#define XGMAC_BLEN GENMASK(7, 1) -#define XGMAC_BLEN256 BIT(7) -#define XGMAC_BLEN128 BIT(6) -#define XGMAC_BLEN64 BIT(5) -#define XGMAC_BLEN32 BIT(4) -#define XGMAC_BLEN16 BIT(3) -#define XGMAC_BLEN8 BIT(2) -#define XGMAC_BLEN4 BIT(1) +/* XGMAC_BLEN* are now defined as DMA_AXI_BLEN* in common.h */ #define XGMAC_UNDEF BIT(0) #define XGMAC_TX_EDMA_CTRL 0x00003040 #define XGMAC_TDPS GENMASK(29, 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 4d6bb995d8d8..cc1bdc0975d5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -84,7 +84,6 @@ static void dwxgmac2_dma_init_tx_chan(struct stmmac_priv *priv, static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) { u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE); - int i; if (axi->axi_lpi_en) value |= XGMAC_EN_LPI; @@ -102,32 +101,12 @@ static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) if (!axi->axi_fb) value |= XGMAC_UNDEF; - value &= ~XGMAC_BLEN; - for (i = 0; i < AXI_BLEN; i++) { - switch (axi->axi_blen[i]) { - case 256: - value |= XGMAC_BLEN256; - break; - case 128: - value |= XGMAC_BLEN128; - break; - case 64: - value |= XGMAC_BLEN64; - break; - case 32: - value |= XGMAC_BLEN32; - break; - case 16: - value |= XGMAC_BLEN16; - break; - case 8: - value |= XGMAC_BLEN8; - break; - case 4: - value |= XGMAC_BLEN4; - break; - } - } + /* Depending on the UNDEF bit the Master AXI will perform any burst + * length according to the BLEN programmed (by default all BLEN are + * set). Note that the UNDEF bit is readonly, and is the inverse of + * Bus Mode bit 16. + */ + value = (value & ~DMA_AXI_BLEN_MASK) | axi->axi_blen_regval; writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE); writel(XGMAC_TDPS, ioaddr + XGMAC_TX_EDMA_CTRL); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index d359722100fa..df6e8a567b1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -201,6 +201,7 @@ struct stmmac_dma_ops { void (*dma_diagnostic_fr)(struct stmmac_extra_stats *x, void __iomem *ioaddr); void (*enable_dma_transmission)(void __iomem *ioaddr, u32 chan); + void (*enable_dma_reception)(void __iomem *ioaddr, u32 chan); void (*enable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void (*disable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, @@ -261,6 +262,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, dma_diagnostic_fr, __args) #define stmmac_enable_dma_transmission(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, enable_dma_transmission, __args) +#define stmmac_enable_dma_reception(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_dma_reception, __args) #define stmmac_enable_dma_irq(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, enable_dma_irq, __priv, __args) #define stmmac_disable_dma_irq(__priv, __args...) \ @@ -541,7 +544,7 @@ struct stmmac_rx_queue; struct stmmac_mode_ops { void (*init) (void *des, dma_addr_t phy_addr, unsigned int size, unsigned int extend_desc); - unsigned int (*is_jumbo_frm) (int len, int ehn_desc); + bool (*is_jumbo_frm)(unsigned int len, bool enh_desc); int (*jumbo_frm)(struct stmmac_tx_queue *tx_q, struct sk_buff *skb, int csum); int (*set_16kib_bfsize)(int mtu); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index d218412ca832..382d94a3b972 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -91,14 +91,9 @@ static int jumbo_frm(struct stmmac_tx_queue *tx_q, struct sk_buff *skb, return entry; } -static unsigned int is_jumbo_frm(int len, int enh_desc) +static bool is_jumbo_frm(unsigned int len, bool enh_desc) { - unsigned int ret = 0; - - if (len >= BUF_SIZE_4KiB) - ret = 1; - - return ret; + return len >= BUF_SIZE_4KiB; } static void refill_desc3(struct stmmac_rx_queue *rx_q, struct dma_desc *p) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 0ea74c88a779..012b0a477255 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -254,8 +254,8 @@ struct stmmac_priv { int hwts_tx_en; bool tx_path_in_lpi_mode; bool tso; - int sph; - int sph_cap; + bool sph_active; + bool sph_capable; u32 sarc_type; u32 rx_riwt[MTL_MAX_RX_QUEUES]; int hwts_rx_en; @@ -408,6 +408,8 @@ int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size); int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, phy_interface_t interface, int speed); +struct plat_stmmacenet_data *stmmac_plat_dat_alloc(struct device *dev); + static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv) { return !!priv->xdp_prog; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.c new file mode 100644 index 000000000000..5c5dd502f79a --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PCI bus helpers for STMMAC driver + * Copyright (C) 2025 Yao Zi <ziyao@disroot.org> + */ + +#include <linux/device.h> +#include <linux/pci.h> + +#include "stmmac_libpci.h" + +int stmmac_pci_plat_suspend(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_pci_plat_suspend); + +int stmmac_pci_plat_resume(struct device *dev, void *bsp_priv) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_pci_plat_resume); + +MODULE_DESCRIPTION("STMMAC PCI helper library"); +MODULE_AUTHOR("Yao Zi <ziyao@disroot.org>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.h new file mode 100644 index 000000000000..71553184f982 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_libpci.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 Yao Zi <ziyao@disroot.org> + */ + +#ifndef __STMMAC_LIBPCI_H__ +#define __STMMAC_LIBPCI_H__ + +int stmmac_pci_plat_suspend(struct device *dev, void *bsp_priv); +int stmmac_pci_plat_resume(struct device *dev, void *bsp_priv); + +#endif /* __STMMAC_LIBPCI_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d202f604161e..da206b24aaed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -190,6 +190,44 @@ int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, EXPORT_SYMBOL_GPL(stmmac_set_clk_tx_rate); /** + * stmmac_axi_blen_to_mask() - convert a burst length array to reg value + * @regval: pointer to a u32 for the resulting register value + * @blen: pointer to an array of u32 containing the burst length values in bytes + * @len: the number of entries in the @blen array + */ +void stmmac_axi_blen_to_mask(u32 *regval, const u32 *blen, size_t len) +{ + size_t i; + u32 val; + + for (val = i = 0; i < len; i++) { + u32 burst = blen[i]; + + /* Burst values of zero must be skipped. */ + if (!burst) + continue; + + /* The valid range for the burst length is 4 to 256 inclusive, + * and it must be a power of two. + */ + if (burst < 4 || burst > 256 || !is_power_of_2(burst)) { + pr_err("stmmac: invalid burst length %u at index %zu\n", + burst, i); + continue; + } + + /* Since burst is a power of two, and the register field starts + * with burst = 4, shift right by two bits so bit 0 of the field + * corresponds with the minimum value. + */ + val |= burst >> 2; + } + + *regval = FIELD_PREP(DMA_AXI_BLEN_MASK, val); +} +EXPORT_SYMBOL_GPL(stmmac_axi_blen_to_mask); + +/** * stmmac_verify_args - verify the driver parameters. * Description: it checks the driver parameters and set a default in case of * errors. @@ -1245,7 +1283,11 @@ static int stmmac_phylink_setup(struct stmmac_priv *priv) /* Stmmac always requires an RX clock for hardware initialization */ config->mac_requires_rxc = true; - if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) + /* Disable EEE RX clock stop to ensure VLAN register access works + * correctly. + */ + if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI) && + !(priv->dev->features & NETIF_F_VLAN_FEATURES)) config->eee_rx_clk_stop_enable = true; /* Set the default transmit clock stop bit based on the platform glue */ @@ -1523,7 +1565,7 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, buf->page_offset = stmmac_rx_offset(priv); } - if (priv->sph && !buf->sec_page) { + if (priv->sph_active && !buf->sec_page) { buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) return -ENOMEM; @@ -2109,7 +2151,7 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv, pp_params.offset = stmmac_rx_offset(priv); pp_params.max_len = dma_conf->dma_buf_sz; - if (priv->sph) { + if (priv->sph_active) { pp_params.offset = 0; pp_params.max_len += stmmac_rx_offset(priv); } @@ -3603,7 +3645,7 @@ static int stmmac_hw_setup(struct net_device *dev) } /* Enable Split Header */ - sph_en = (priv->hw->rx_csum > 0) && priv->sph; + sph_en = (priv->hw->rx_csum > 0) && priv->sph_active; for (chan = 0; chan < rx_cnt; chan++) stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan); @@ -4579,18 +4621,18 @@ static bool stmmac_has_ip_ethertype(struct sk_buff *skb) */ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) { - unsigned int first_entry, tx_packets, enh_desc; + bool enh_desc, has_vlan, set_ic, is_jumbo = false; struct stmmac_priv *priv = netdev_priv(dev); unsigned int nopaged_len = skb_headlen(skb); - int i, csum_insertion = 0, is_jumbo = 0; u32 queue = skb_get_queue_mapping(skb); int nfrags = skb_shinfo(skb)->nr_frags; + unsigned int first_entry, tx_packets; int gso = skb_shinfo(skb)->gso_type; struct stmmac_txq_stats *txq_stats; struct dma_edesc *tbs_desc = NULL; struct dma_desc *desc, *first; struct stmmac_tx_queue *tx_q; - bool has_vlan, set_ic; + int i, csum_insertion = 0; int entry, first_tx; dma_addr_t des; u32 sdu_len; @@ -4895,7 +4937,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) break; } - if (priv->sph && !buf->sec_page) { + if (priv->sph_active && !buf->sec_page) { buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) break; @@ -4906,7 +4948,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) buf->addr = page_pool_get_dma_addr(buf->page) + buf->page_offset; stmmac_set_desc_addr(priv, p, buf->addr); - if (priv->sph) + if (priv->sph_active) stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true); else stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false); @@ -4931,6 +4973,8 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) rx_q->rx_tail_addr = rx_q->dma_rx_phy + (rx_q->dirty_rx * sizeof(struct dma_desc)); stmmac_set_rx_tail_ptr(priv, priv->ioaddr, rx_q->rx_tail_addr, queue); + /* Wake up Rx DMA from the suspend state if required */ + stmmac_enable_dma_reception(priv, priv->ioaddr, queue); } static unsigned int stmmac_rx_buf1_len(struct stmmac_priv *priv, @@ -4941,12 +4985,12 @@ static unsigned int stmmac_rx_buf1_len(struct stmmac_priv *priv, int coe = priv->hw->rx_csum; /* Not first descriptor, buffer is always zero */ - if (priv->sph && len) + if (priv->sph_active && len) return 0; /* First descriptor, get split header length */ stmmac_get_rx_header_len(priv, p, &hlen); - if (priv->sph && hlen) { + if (priv->sph_active && hlen) { priv->xstats.rx_split_hdr_pkt_n++; return hlen; } @@ -4969,7 +5013,7 @@ static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv, unsigned int plen = 0; /* Not split header, buffer is not available */ - if (!priv->sph) + if (!priv->sph_active) return 0; /* Not last descriptor */ @@ -5352,10 +5396,10 @@ static int stmmac_rx_zc(struct stmmac_priv *priv, int limit, u32 queue) len = 0; } +read_again: if (count >= limit) break; -read_again: buf1_len = 0; entry = next_entry; buf = &rx_q->buf_pool[entry]; @@ -6037,8 +6081,8 @@ static int stmmac_set_features(struct net_device *netdev, */ stmmac_rx_ipc(priv, priv->hw); - if (priv->sph_cap) { - bool sph_en = (priv->hw->rx_csum > 0) && priv->sph; + if (priv->sph_capable) { + bool sph_en = (priv->hw->rx_csum > 0) && priv->sph_active; u32 chan; for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++) @@ -6987,7 +7031,7 @@ int stmmac_xdp_open(struct net_device *dev) } /* Adjust Split header */ - sph_en = (priv->hw->rx_csum > 0) && priv->sph; + sph_en = (priv->hw->rx_csum > 0) && priv->sph_active; /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_cnt; chan++) { @@ -7489,7 +7533,8 @@ static int stmmac_dl_ts_coarse_set(struct devlink *dl, u32 id, } static int stmmac_dl_ts_coarse_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct stmmac_devlink_priv *dl_priv = devlink_priv(dl); struct stmmac_priv *priv = dl_priv->stmmac_priv; @@ -7555,19 +7600,43 @@ static void stmmac_unregister_devlink(struct stmmac_priv *priv) devlink_free(priv->devlink); } -/** - * stmmac_dvr_probe - * @device: device pointer - * @plat_dat: platform data pointer - * @res: stmmac resource pointer - * Description: this is the main probe function used to - * call the alloc_etherdev, allocate the priv structure. - * Return: - * returns 0 on success, otherwise errno. - */ -int stmmac_dvr_probe(struct device *device, - struct plat_stmmacenet_data *plat_dat, - struct stmmac_resources *res) +struct plat_stmmacenet_data *stmmac_plat_dat_alloc(struct device *dev) +{ + struct plat_stmmacenet_data *plat_dat; + int i; + + plat_dat = devm_kzalloc(dev, sizeof(*plat_dat), GFP_KERNEL); + if (!plat_dat) + return NULL; + + /* Set the defaults: + * - phy autodetection + * - determine GMII_Address CR field from CSR clock + * - allow MTU up to JUMBO_LEN + * - hash table size + * - one unicast filter entry + */ + plat_dat->phy_addr = -1; + plat_dat->clk_csr = -1; + plat_dat->maxmtu = JUMBO_LEN; + plat_dat->multicast_filter_bins = HASH_TABLE_SIZE; + plat_dat->unicast_filter_entries = 1; + + /* Set the mtl defaults */ + plat_dat->tx_queues_to_use = 1; + plat_dat->rx_queues_to_use = 1; + + /* Setup the default RX queue channel map */ + for (i = 0; i < ARRAY_SIZE(plat_dat->rx_queues_cfg); i++) + plat_dat->rx_queues_cfg[i].chan = i; + + return plat_dat; +} +EXPORT_SYMBOL_GPL(stmmac_plat_dat_alloc); + +static int __stmmac_dvr_probe(struct device *device, + struct plat_stmmacenet_data *plat_dat, + struct stmmac_resources *res) { struct net_device *ndev = NULL; struct stmmac_priv *priv; @@ -7702,8 +7771,8 @@ int stmmac_dvr_probe(struct device *device, if (priv->dma_cap.sphen && !(priv->plat->flags & STMMAC_FLAG_SPH_DISABLE)) { ndev->hw_features |= NETIF_F_GRO; - priv->sph_cap = true; - priv->sph = priv->sph_cap; + priv->sph_capable = true; + priv->sph_active = priv->sph_capable; dev_info(priv->device, "SPH feature enabled\n"); } @@ -7868,6 +7937,34 @@ error_wq_init: return ret; } + +/** + * stmmac_dvr_probe + * @dev: device pointer + * @plat_dat: platform data pointer + * @res: stmmac resource pointer + * Description: this is the main probe function used to + * call the alloc_etherdev, allocate the priv structure. + * Return: + * returns 0 on success, otherwise errno. + */ +int stmmac_dvr_probe(struct device *dev, struct plat_stmmacenet_data *plat_dat, + struct stmmac_resources *res) +{ + int ret; + + if (plat_dat->init) { + ret = plat_dat->init(dev, plat_dat->bsp_priv); + if (ret) + return ret; + } + + ret = __stmmac_dvr_probe(dev, plat_dat, res); + if (ret && plat_dat->exit) + plat_dat->exit(dev, plat_dat->bsp_priv); + + return ret; +} EXPORT_SYMBOL_GPL(stmmac_dvr_probe); /** @@ -7906,6 +8003,9 @@ void stmmac_dvr_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_put_noidle(dev); + + if (priv->plat->exit) + priv->plat->exit(dev, priv->plat->bsp_priv); } EXPORT_SYMBOL_GPL(stmmac_dvr_remove); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 94b3a3b27270..270ad066ced3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -14,6 +14,7 @@ #include <linux/dmi.h> #include "stmmac.h" +#include "stmmac_libpci.h" struct stmmac_pci_info { int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat); @@ -27,26 +28,6 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Set default number of RX and TX queues to use */ - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; } static int stmmac_default_data(struct pci_dev *pdev, @@ -81,22 +62,12 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - /* Set default number of RX and TX queues to use */ plat->tx_queues_to_use = 4; plat->rx_queues_to_use = 4; plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; for (i = 0; i < plat->tx_queues_to_use; i++) { - plat->tx_queues_cfg[i].use_prio = false; plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; plat->tx_queues_cfg[i].weight = 25; if (i > 0) @@ -104,15 +75,10 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, } plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; - for (i = 0; i < plat->rx_queues_to_use; i++) { - plat->rx_queues_cfg[i].use_prio = false; + for (i = 0; i < plat->rx_queues_to_use; i++) plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - plat->rx_queues_cfg[i].pkt_route = 0x0; - plat->rx_queues_cfg[i].chan = i; - } plat->bus_id = 1; - plat->phy_addr = -1; plat->phy_interface = PHY_INTERFACE_MODE_GMII; plat->dma_cfg->pbl = 32; @@ -127,10 +93,8 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, plat->axi->axi_rd_osr_lmt = 31; plat->axi->axi_fb = false; - plat->axi->axi_blen[0] = 4; - plat->axi->axi_blen[1] = 8; - plat->axi->axi_blen[2] = 16; - plat->axi->axi_blen[3] = 32; + plat->axi->axi_blen_regval = DMA_AXI_BLEN4 | DMA_AXI_BLEN8 | + DMA_AXI_BLEN16 | DMA_AXI_BLEN32; return 0; } @@ -139,37 +103,6 @@ static const struct stmmac_pci_info snps_gmac5_pci_info = { .setup = snps_gmac5_default_data, }; -static int stmmac_pci_suspend(struct device *dev, void *bsp_priv) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - ret = pci_save_state(pdev); - if (ret) - return ret; - - pci_disable_device(pdev); - pci_wake_from_d3(pdev, true); - return 0; -} - -static int stmmac_pci_resume(struct device *dev, void *bsp_priv) -{ - struct pci_dev *pdev = to_pci_dev(dev); - int ret; - - pci_restore_state(pdev); - pci_set_power_state(pdev, PCI_D0); - - ret = pci_enable_device(pdev); - if (ret) - return ret; - - pci_set_master(pdev); - - return 0; -} - /** * stmmac_pci_probe * @@ -191,7 +124,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, int ret; int i; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; @@ -249,8 +182,8 @@ static int stmmac_pci_probe(struct pci_dev *pdev, plat->safety_feat_cfg->prtyen = 1; plat->safety_feat_cfg->tmouten = 1; - plat->suspend = stmmac_pci_suspend; - plat->resume = stmmac_pci_resume; + plat->suspend = stmmac_pci_plat_suspend; + plat->resume = stmmac_pci_plat_resume; return stmmac_dvr_probe(&pdev->dev, plat, &res); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 6483d52b4c0f..8979a50b5507 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -95,6 +95,7 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) { struct device_node *np; struct stmmac_axi *axi; + u32 axi_blen[AXI_BLEN]; np = of_parse_phandle(pdev->dev.of_node, "snps,axi-config", 0); if (!np) @@ -117,7 +118,8 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) axi->axi_wr_osr_lmt = 1; if (of_property_read_u32(np, "snps,rd_osr_lmt", &axi->axi_rd_osr_lmt)) axi->axi_rd_osr_lmt = 1; - of_property_read_u32_array(np, "snps,blen", axi->axi_blen, AXI_BLEN); + of_property_read_u32_array(np, "snps,blen", axi_blen, AXI_BLEN); + stmmac_axi_blen_to_mask(&axi->axi_blen_regval, axi_blen, AXI_BLEN); of_node_put(np); return axi; @@ -137,13 +139,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev, u8 queue = 0; int ret = 0; - /* For backwards-compatibility with device trees that don't have any - * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back - * to one RX and TX queues each. - */ - plat->rx_queues_to_use = 1; - plat->tx_queues_to_use = 1; - /* First Queue must always be in DCB mode. As MTL_QUEUE_DCB = 1 we need * to always set this, otherwise Queue will be classified as AVB * (because MTL_QUEUE_AVB = 0). @@ -162,9 +157,8 @@ static int stmmac_mtl_setup(struct platform_device *pdev, } /* Processing RX queues common config */ - if (of_property_read_u32(rx_node, "snps,rx-queues-to-use", - &plat->rx_queues_to_use)) - plat->rx_queues_to_use = 1; + of_property_read_u32(rx_node, "snps,rx-queues-to-use", + &plat->rx_queues_to_use); if (of_property_read_bool(rx_node, "snps,rx-sched-sp")) plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; @@ -185,18 +179,13 @@ static int stmmac_mtl_setup(struct platform_device *pdev, else plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; - if (of_property_read_u32(q_node, "snps,map-to-dma-channel", - &plat->rx_queues_cfg[queue].chan)) - plat->rx_queues_cfg[queue].chan = queue; + of_property_read_u32(q_node, "snps,map-to-dma-channel", + &plat->rx_queues_cfg[queue].chan); /* TODO: Dynamic mapping to be included in the future */ - if (of_property_read_u32(q_node, "snps,priority", - &plat->rx_queues_cfg[queue].prio)) { - plat->rx_queues_cfg[queue].prio = 0; - plat->rx_queues_cfg[queue].use_prio = false; - } else { + if (!of_property_read_u32(q_node, "snps,priority", + &plat->rx_queues_cfg[queue].prio)) plat->rx_queues_cfg[queue].use_prio = true; - } /* RX queue specific packet type routing */ if (of_property_read_bool(q_node, "snps,route-avcp")) @@ -209,8 +198,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev, plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ; else if (of_property_read_bool(q_node, "snps,route-multi-broad")) plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ; - else - plat->rx_queues_cfg[queue].pkt_route = 0x0; queue++; } @@ -221,9 +208,8 @@ static int stmmac_mtl_setup(struct platform_device *pdev, } /* Processing TX queues common config */ - if (of_property_read_u32(tx_node, "snps,tx-queues-to-use", - &plat->tx_queues_to_use)) - plat->tx_queues_to_use = 1; + of_property_read_u32(tx_node, "snps,tx-queues-to-use", + &plat->tx_queues_to_use); if (of_property_read_bool(tx_node, "snps,tx-sched-wrr")) plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; @@ -268,13 +254,9 @@ static int stmmac_mtl_setup(struct platform_device *pdev, plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; } - if (of_property_read_u32(q_node, "snps,priority", - &plat->tx_queues_cfg[queue].prio)) { - plat->tx_queues_cfg[queue].prio = 0; - plat->tx_queues_cfg[queue].use_prio = false; - } else { + if (!of_property_read_u32(q_node, "snps,priority", + &plat->tx_queues_cfg[queue].prio)) plat->tx_queues_cfg[queue].use_prio = true; - } plat->tx_queues_cfg[queue].coe_unsupported = of_property_read_bool(q_node, "snps,coe-unsupported"); @@ -436,7 +418,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) void *ret; int rc; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return ERR_PTR(-ENOMEM); @@ -480,13 +462,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->bus_id = ++bus_id; } - /* Default to phy auto-detection */ - plat->phy_addr = -1; - - /* Default to get clk_csr from stmmac_clk_csr_set(), - * or get clk_csr from device tree. - */ - plat->clk_csr = -1; if (of_property_read_u32(np, "snps,clk-csr", &plat->clk_csr)) of_property_read_u32(np, "clk_csr", &plat->clk_csr); @@ -515,17 +490,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING; } - /* Set the maxmtu to a default of JUMBO_LEN in case the - * parameter is not present in the device tree. - */ - plat->maxmtu = JUMBO_LEN; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - /* * Currently only the properties needed on SPEAr600 * are provided. All other properties should be added @@ -785,40 +749,40 @@ EXPORT_SYMBOL_GPL(stmmac_get_platform_resources); /** * stmmac_pltfr_init - * @pdev: pointer to the platform device + * @dev: pointer to the device structure * @plat: driver data platform structure * Description: Call the platform's init callback (if any) and propagate * the return value. */ -static int stmmac_pltfr_init(struct platform_device *pdev, +static int stmmac_pltfr_init(struct device *dev, struct plat_stmmacenet_data *plat) { int ret = 0; if (plat->init) - ret = plat->init(pdev, plat->bsp_priv); + ret = plat->init(dev, plat->bsp_priv); return ret; } /** * stmmac_pltfr_exit - * @pdev: pointer to the platform device + * @dev: pointer to the device structure * @plat: driver data platform structure * Description: Call the platform's exit callback (if any). */ -static void stmmac_pltfr_exit(struct platform_device *pdev, +static void stmmac_pltfr_exit(struct device *dev, struct plat_stmmacenet_data *plat) { if (plat->exit) - plat->exit(pdev, plat->bsp_priv); + plat->exit(dev, plat->bsp_priv); } static int stmmac_plat_suspend(struct device *dev, void *bsp_priv) { struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); - stmmac_pltfr_exit(to_platform_device(dev), priv->plat); + stmmac_pltfr_exit(dev, priv->plat); return 0; } @@ -827,7 +791,7 @@ static int stmmac_plat_resume(struct device *dev, void *bsp_priv) { struct stmmac_priv *priv = netdev_priv(dev_get_drvdata(dev)); - return stmmac_pltfr_init(to_platform_device(dev), priv->plat); + return stmmac_pltfr_init(dev, priv->plat); } /** @@ -842,24 +806,12 @@ int stmmac_pltfr_probe(struct platform_device *pdev, struct plat_stmmacenet_data *plat, struct stmmac_resources *res) { - int ret; - if (!plat->suspend && plat->exit) plat->suspend = stmmac_plat_suspend; if (!plat->resume && plat->init) plat->resume = stmmac_plat_resume; - ret = stmmac_pltfr_init(pdev, plat); - if (ret) - return ret; - - ret = stmmac_dvr_probe(&pdev->dev, plat, res); - if (ret) { - stmmac_pltfr_exit(pdev, plat); - return ret; - } - - return ret; + return stmmac_dvr_probe(&pdev->dev, plat, res); } EXPORT_SYMBOL_GPL(stmmac_pltfr_probe); @@ -901,12 +853,7 @@ EXPORT_SYMBOL_GPL(devm_stmmac_pltfr_probe); */ void stmmac_pltfr_remove(struct platform_device *pdev) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *priv = netdev_priv(ndev); - struct plat_stmmacenet_data *plat = priv->plat; - stmmac_dvr_remove(&pdev->dev); - stmmac_pltfr_exit(pdev, plat); } EXPORT_SYMBOL_GPL(stmmac_pltfr_remove); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index a01bc394d1ac..e90a2c469b9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -1721,7 +1721,7 @@ static int stmmac_test_sph(struct stmmac_priv *priv) struct stmmac_packet_attrs attr = { }; int ret; - if (!priv->sph) + if (!priv->sph_active) return -EOPNOTSUPP; /* Check for UDP first */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index ff02a79c00d4..b18404dd5a8b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -122,7 +122,8 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, /* Extended Rx VLAN Filter Enable */ for (i = 0; i < hw->num_vlan; i++) { - if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid) { + if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && + ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { ret = vlan_write_filter(dev, hw, i, 0); if (!ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c index aa6f16d3df64..d7e4db7224b0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.c @@ -129,7 +129,7 @@ int stmmac_xdp_set_prog(struct stmmac_priv *priv, struct bpf_prog *prog, bpf_prog_put(old_prog); /* Disable RX SPH for XDP operation */ - priv->sph = priv->sph_cap && !stmmac_xdp_is_enabled(priv); + priv->sph_active = priv->sph_capable && !stmmac_xdp_is_enabled(priv); if (if_running && need_update) stmmac_xdp_open(dev); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index d5f358ec9820..5924db6be3fe 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -3068,7 +3068,8 @@ static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common) } static int am65_cpsw_dl_switch_mode_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct am65_cpsw_devlink *dl_priv = devlink_priv(dl); struct am65_cpsw_common *common = dl_priv->common; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 8b9e2078c602..ab88d4c02cbd 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1618,7 +1618,8 @@ static const struct devlink_ops cpsw_devlink_ops = { }; static int cpsw_dl_switch_mode_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct cpsw_devlink *dl_priv = devlink_priv(dl); struct cpsw_common *cpsw = dl_priv->cpsw; @@ -1753,7 +1754,8 @@ exit: } static int cpsw_dl_ale_ctrl_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct cpsw_devlink *dl_priv = devlink_priv(dl); struct cpsw_common *cpsw = dl_priv->cpsw; diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 0eed29d6187a..090aa74d3ce7 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -93,15 +93,91 @@ void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num) } EXPORT_SYMBOL_GPL(prueth_ndev_del_tx_napi); +static int emac_xsk_xmit_zc(struct prueth_emac *emac, + unsigned int q_idx) +{ + struct prueth_tx_chn *tx_chn = &emac->tx_chns[q_idx]; + struct xsk_buff_pool *pool = tx_chn->xsk_pool; + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *host_desc; + dma_addr_t dma_desc, dma_buf; + struct prueth_swdata *swdata; + struct xdp_desc xdp_desc; + int num_tx = 0, pkt_len; + int descs_avail, ret; + u32 *epib; + int i; + + descs_avail = k3_cppi_desc_pool_avail(tx_chn->desc_pool); + /* ensure that TX ring is not filled up by XDP, always MAX_SKB_FRAGS + * will be available for normal TX path and queue is stopped there if + * necessary + */ + if (descs_avail <= MAX_SKB_FRAGS) + return 0; + + descs_avail -= MAX_SKB_FRAGS; + + for (i = 0; i < descs_avail; i++) { + if (!xsk_tx_peek_desc(pool, &xdp_desc)) + break; + + dma_buf = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + pkt_len = xdp_desc.len; + xsk_buff_raw_dma_sync_for_device(pool, dma_buf, pkt_len); + + host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); + if (unlikely(!host_desc)) + break; + + cppi5_hdesc_init(host_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, + PRUETH_NAV_PS_DATA_SIZE); + cppi5_hdesc_set_pkttype(host_desc, 0); + epib = host_desc->epib; + epib[0] = 0; + epib[1] = 0; + cppi5_hdesc_set_pktlen(host_desc, pkt_len); + cppi5_desc_set_tags_ids(&host_desc->hdr, 0, + (emac->port_id | (q_idx << 8))); + + k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &dma_buf); + cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, + pkt_len); + + swdata = cppi5_hdesc_get_swdata(host_desc); + swdata->type = PRUETH_SWDATA_XSK; + + dma_desc = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, + host_desc); + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, + host_desc, dma_desc); + + if (ret) { + ndev->stats.tx_errors++; + k3_cppi_desc_pool_free(tx_chn->desc_pool, host_desc); + break; + } + + num_tx++; + } + + xsk_tx_release(tx_chn->xsk_pool); + return num_tx; +} + void prueth_xmit_free(struct prueth_tx_chn *tx_chn, struct cppi5_host_desc_t *desc) { struct cppi5_host_desc_t *first_desc, *next_desc; dma_addr_t buf_dma, next_desc_dma; + struct prueth_swdata *swdata; u32 buf_dma_len; first_desc = desc; next_desc = first_desc; + swdata = cppi5_hdesc_get_swdata(first_desc); + if (swdata->type == PRUETH_SWDATA_XSK) + goto free_pool; cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len); k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); @@ -126,6 +202,7 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn, k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); } +free_pool: k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc); } EXPORT_SYMBOL_GPL(prueth_xmit_free); @@ -139,7 +216,9 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn, struct prueth_swdata *swdata; struct prueth_tx_chn *tx_chn; unsigned int total_bytes = 0; + int xsk_frames_done = 0; struct xdp_frame *xdpf; + unsigned int pkt_len; struct sk_buff *skb; dma_addr_t desc_dma; int res, num_tx = 0; @@ -176,6 +255,11 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn, total_bytes += xdpf->len; xdp_return_frame(xdpf); break; + case PRUETH_SWDATA_XSK: + pkt_len = cppi5_hdesc_get_pktlen(desc_tx); + dev_sw_netstats_tx_add(ndev, 1, pkt_len); + xsk_frames_done++; + break; default: prueth_xmit_free(tx_chn, desc_tx); ndev->stats.tx_dropped++; @@ -204,6 +288,18 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn, __netif_tx_unlock(netif_txq); } + if (tx_chn->xsk_pool) { + if (xsk_frames_done) + xsk_tx_completed(tx_chn->xsk_pool, xsk_frames_done); + + if (xsk_uses_need_wakeup(tx_chn->xsk_pool)) + xsk_set_tx_need_wakeup(tx_chn->xsk_pool); + + netif_txq = netdev_get_tx_queue(ndev, chn); + txq_trans_cond_update(netif_txq); + emac_xsk_xmit_zc(emac, chn); + } + return num_tx; } @@ -212,7 +308,10 @@ static enum hrtimer_restart emac_tx_timer_callback(struct hrtimer *timer) struct prueth_tx_chn *tx_chns = container_of(timer, struct prueth_tx_chn, tx_hrtimer); - enable_irq(tx_chns->irq); + if (tx_chns->irq_disabled) { + tx_chns->irq_disabled = false; + enable_irq(tx_chns->irq); + } return HRTIMER_NORESTART; } @@ -235,7 +334,10 @@ static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget) ns_to_ktime(tx_chn->tx_pace_timeout_ns), HRTIMER_MODE_REL_PINNED); } else { - enable_irq(tx_chn->irq); + if (tx_chn->irq_disabled) { + tx_chn->irq_disabled = false; + enable_irq(tx_chn->irq); + } } } @@ -246,6 +348,7 @@ static irqreturn_t prueth_tx_irq(int irq, void *dev_id) { struct prueth_tx_chn *tx_chn = dev_id; + tx_chn->irq_disabled = true; disable_irq_nosync(irq); napi_schedule(&tx_chn->napi_tx); @@ -362,6 +465,29 @@ fail: } EXPORT_SYMBOL_GPL(prueth_init_tx_chns); +static struct page_pool *prueth_create_page_pool(struct prueth_emac *emac, + struct device *dma_dev, + int size) +{ + struct page_pool_params pp_params = { 0 }; + struct page_pool *pool; + + pp_params.order = 0; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; + pp_params.pool_size = size; + pp_params.nid = dev_to_node(emac->prueth->dev); + pp_params.dma_dir = DMA_BIDIRECTIONAL; + pp_params.dev = dma_dev; + pp_params.napi = &emac->napi_rx; + pp_params.max_len = PAGE_SIZE; + + pool = page_pool_create(&pp_params); + if (IS_ERR(pool)) + netdev_err(emac->ndev, "cannot create rx page pool\n"); + + return pool; +} + int prueth_init_rx_chns(struct prueth_emac *emac, struct prueth_rx_chn *rx_chn, char *name, u32 max_rflows, @@ -371,6 +497,7 @@ int prueth_init_rx_chns(struct prueth_emac *emac, struct device *dev = emac->prueth->dev; struct net_device *ndev = emac->ndev; u32 fdqring_id, hdesc_size; + struct page_pool *pool; int i, ret = 0, slice; int flow_id_base; @@ -413,6 +540,14 @@ int prueth_init_rx_chns(struct prueth_emac *emac, goto fail; } + pool = prueth_create_page_pool(emac, rx_chn->dma_dev, rx_chn->descs_num); + if (IS_ERR(pool)) { + ret = PTR_ERR(pool); + goto fail; + } + + rx_chn->pg_pool = pool; + flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn); if (emac->is_sr1 && !strcmp(name, "rxmgm")) { emac->rx_mgm_flow_id_base = flow_id_base; @@ -544,15 +679,15 @@ void emac_rx_timestamp(struct prueth_emac *emac, * emac_xmit_xdp_frame - transmits an XDP frame * @emac: emac device * @xdpf: data to transmit - * @page: page from page pool if already DMA mapped * @q_idx: queue id + * @buff_type: Type of buffer to be transmitted * * Return: XDP state */ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, struct xdp_frame *xdpf, - struct page *page, - unsigned int q_idx) + unsigned int q_idx, + enum prueth_tx_buff_type buff_type) { struct cppi5_host_desc_t *first_desc; struct net_device *ndev = emac->ndev; @@ -560,6 +695,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, struct prueth_tx_chn *tx_chn; dma_addr_t desc_dma, buf_dma; struct prueth_swdata *swdata; + struct page *page; u32 *epib; int ret; @@ -576,7 +712,12 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac, return ICSSG_XDP_CONSUMED; /* drop */ } - if (page) { /* already DMA mapped by page_pool */ + if (buff_type == PRUETH_TX_BUFF_TYPE_XDP_TX) { /* already DMA mapped by page_pool */ + page = virt_to_head_page(xdpf->data); + if (unlikely(!page)) { + netdev_err(ndev, "xdp tx: failed to get page from xdpf\n"); + goto drop_free_descs; + } buf_dma = page_pool_get_dma_addr(page); buf_dma += xdpf->headroom + sizeof(struct xdp_frame); } else { /* Map the linear buffer */ @@ -631,13 +772,11 @@ EXPORT_SYMBOL_GPL(emac_xmit_xdp_frame); * emac_run_xdp - run an XDP program * @emac: emac device * @xdp: XDP buffer containing the frame - * @page: page with RX data if already DMA mapped * @len: Rx descriptor packet length * * Return: XDP state */ -static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, - struct page *page, u32 *len) +static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, u32 *len) { struct net_device *ndev = emac->ndev; struct netdev_queue *netif_txq; @@ -664,7 +803,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp, q_idx = cpu % emac->tx_ch_num; netif_txq = netdev_get_tx_queue(ndev, q_idx); __netif_tx_lock(netif_txq, cpu); - result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx); + result = emac_xmit_xdp_frame(emac, xdpf, q_idx, + PRUETH_TX_BUFF_TYPE_XDP_TX); __netif_tx_unlock(netif_txq); if (result == ICSSG_XDP_CONSUMED) { ndev->stats.tx_dropped++; @@ -689,11 +829,188 @@ drop: fallthrough; /* handle aborts by dropping packet */ case XDP_DROP: ndev->stats.rx_dropped++; - page_pool_recycle_direct(emac->rx_chns.pg_pool, page); return ICSSG_XDP_CONSUMED; } } +static int prueth_dma_rx_push_mapped_zc(struct prueth_emac *emac, + struct prueth_rx_chn *rx_chn, + struct xdp_buff *xdp) +{ + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_rx; + struct prueth_swdata *swdata; + dma_addr_t desc_dma; + dma_addr_t buf_dma; + int buf_len; + + buf_dma = xsk_buff_xdp_get_dma(xdp); + desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool); + if (!desc_rx) { + netdev_err(ndev, "rx push: failed to allocate descriptor\n"); + return -ENOMEM; + } + desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx); + + cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT, + PRUETH_NAV_PS_DATA_SIZE); + k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma); + buf_len = xsk_pool_get_rx_frame_size(rx_chn->xsk_pool); + cppi5_hdesc_attach_buf(desc_rx, buf_dma, buf_len, buf_dma, buf_len); + swdata = cppi5_hdesc_get_swdata(desc_rx); + swdata->type = PRUETH_SWDATA_XSK; + swdata->data.xdp = xdp; + + return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, PRUETH_RX_FLOW_DATA, + desc_rx, desc_dma); +} + +static int prueth_rx_alloc_zc(struct prueth_emac *emac, int budget) +{ + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + struct xdp_buff *xdp; + int i, ret; + + for (i = 0; i < budget; i++) { + xdp = xsk_buff_alloc(rx_chn->xsk_pool); + if (!xdp) + break; + + ret = prueth_dma_rx_push_mapped_zc(emac, rx_chn, xdp); + if (ret) { + netdev_err(emac->ndev, "rx alloc: failed to map descriptors to xdp buff\n"); + xsk_buff_free(xdp); + break; + } + } + + return i; +} + +static void emac_dispatch_skb_zc(struct prueth_emac *emac, struct xdp_buff *xdp, u32 *psdata) +{ + unsigned int headroom = xdp->data - xdp->data_hard_start; + unsigned int pkt_len = xdp->data_end - xdp->data; + struct net_device *ndev = emac->ndev; + struct sk_buff *skb; + + skb = napi_alloc_skb(&emac->napi_rx, xdp->data_end - xdp->data_hard_start); + if (unlikely(!skb)) { + ndev->stats.rx_dropped++; + return; + } + + skb_reserve(skb, headroom); + skb_put(skb, pkt_len); + skb->dev = ndev; + + /* RX HW timestamp */ + if (emac->rx_ts_enabled) + emac_rx_timestamp(emac, skb, psdata); + + if (emac->prueth->is_switch_mode) + skb->offload_fwd_mark = emac->offload_fwd_mark; + skb->protocol = eth_type_trans(skb, ndev); + + skb_mark_for_recycle(skb); + napi_gro_receive(&emac->napi_rx, skb); + ndev->stats.rx_bytes += pkt_len; + ndev->stats.rx_packets++; +} + +static int emac_rx_packet_zc(struct prueth_emac *emac, u32 flow_id, + int budget) +{ + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + u32 buf_dma_len, pkt_len, port_id = 0; + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_rx; + struct prueth_swdata *swdata; + dma_addr_t desc_dma, buf_dma; + struct xdp_buff *xdp; + int xdp_status = 0; + int count = 0; + u32 *psdata; + int ret; + + while (count < budget) { + ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma); + if (ret) { + if (ret != -ENODATA) + netdev_err(ndev, "rx pop: failed: %d\n", ret); + break; + } + + if (cppi5_desc_is_tdcm(desc_dma)) { + complete(&emac->tdown_complete); + break; + } + + desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_rx); + if (swdata->type != PRUETH_SWDATA_XSK) { + netdev_err(ndev, "rx_pkt: invalid swdata->type %d\n", swdata->type); + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + break; + } + + xdp = swdata->data.xdp; + cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); + k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); + pkt_len = cppi5_hdesc_get_pktlen(desc_rx); + /* firmware adds 4 CRC bytes, strip them */ + pkt_len -= 4; + cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); + psdata = cppi5_hdesc_get_psdata(desc_rx); + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + count++; + xsk_buff_set_size(xdp, pkt_len); + xsk_buff_dma_sync_for_cpu(xdp); + + if (prueth_xdp_is_enabled(emac)) { + ret = emac_run_xdp(emac, xdp, &pkt_len); + switch (ret) { + case ICSSG_XDP_PASS: + /* prepare skb and send to n/w stack */ + emac_dispatch_skb_zc(emac, xdp, psdata); + xsk_buff_free(xdp); + break; + case ICSSG_XDP_CONSUMED: + xsk_buff_free(xdp); + break; + case ICSSG_XDP_TX: + case ICSSG_XDP_REDIR: + xdp_status |= ret; + break; + } + } else { + /* prepare skb and send to n/w stack */ + emac_dispatch_skb_zc(emac, xdp, psdata); + xsk_buff_free(xdp); + } + } + + if (xdp_status & ICSSG_XDP_REDIR) + xdp_do_flush(); + + /* Allocate xsk buffers from the pool for the "count" number of + * packets processed in order to be able to receive more packets. + */ + ret = prueth_rx_alloc_zc(emac, count); + + if (xsk_uses_need_wakeup(rx_chn->xsk_pool)) { + /* If the user space doesn't provide enough buffers then it must + * explicitly wake up the kernel when new buffers are available + */ + if (ret < count) + xsk_set_rx_need_wakeup(rx_chn->xsk_pool); + else + xsk_clear_rx_need_wakeup(rx_chn->xsk_pool); + } + + return count; +} + static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) { struct prueth_rx_chn *rx_chn = &emac->rx_chns; @@ -719,8 +1036,10 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) return ret; } - if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */ + if (cppi5_desc_is_tdcm(desc_dma)) { + complete(&emac->tdown_complete); return 0; + } desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); @@ -738,7 +1057,6 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) /* firmware adds 4 CRC bytes, strip them */ pkt_len -= 4; cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); /* if allocation fails we drop the packet but push the @@ -752,11 +1070,11 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state) } pa = page_address(page); - if (emac->xdp_prog) { + if (prueth_xdp_is_enabled(emac)) { xdp_init_buff(&xdp, PAGE_SIZE, &rx_chn->xdp_rxq); xdp_prepare_buff(&xdp, pa, PRUETH_HEADROOM, pkt_len, false); - *xdp_state = emac_run_xdp(emac, &xdp, page, &pkt_len); + *xdp_state = emac_run_xdp(emac, &xdp, &pkt_len); if (*xdp_state != ICSSG_XDP_PASS) goto requeue; headroom = xdp.data - xdp.data_hard_start; @@ -804,24 +1122,29 @@ requeue: return ret; } -static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma) +void prueth_rx_cleanup(void *data, dma_addr_t desc_dma) { struct prueth_rx_chn *rx_chn = data; struct cppi5_host_desc_t *desc_rx; struct prueth_swdata *swdata; struct page_pool *pool; + struct xdp_buff *xdp; struct page *page; pool = rx_chn->pg_pool; desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); - if (swdata->type == PRUETH_SWDATA_PAGE) { + if (rx_chn->xsk_pool) { + xdp = swdata->data.xdp; + xsk_buff_free(xdp); + } else { page = swdata->data.page; page_pool_recycle_direct(pool, page); } k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); } +EXPORT_SYMBOL_GPL(prueth_rx_cleanup); static int prueth_tx_ts_cookie_get(struct prueth_emac *emac) { @@ -1025,10 +1348,11 @@ drop_stop_q_busy: } EXPORT_SYMBOL_GPL(icssg_ndo_start_xmit); -static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma) +void prueth_tx_cleanup(void *data, dma_addr_t desc_dma) { struct prueth_tx_chn *tx_chn = data; struct cppi5_host_desc_t *desc_tx; + struct xsk_buff_pool *xsk_pool; struct prueth_swdata *swdata; struct xdp_frame *xdpf; struct sk_buff *skb; @@ -1045,17 +1369,23 @@ static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma) xdpf = swdata->data.xdpf; xdp_return_frame(xdpf); break; + case PRUETH_SWDATA_XSK: + xsk_pool = tx_chn->xsk_pool; + xsk_tx_completed(xsk_pool, 1); + break; default: break; } prueth_xmit_free(tx_chn, desc_tx); } +EXPORT_SYMBOL_GPL(prueth_tx_cleanup); irqreturn_t prueth_rx_irq(int irq, void *dev_id) { struct prueth_emac *emac = dev_id; + emac->rx_chns.irq_disabled = true; disable_irq_nosync(irq); napi_schedule(&emac->napi_rx); @@ -1083,6 +1413,7 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget) PRUETH_RX_FLOW_DATA_SR1 : PRUETH_RX_FLOW_DATA; int flow = emac->is_sr1 ? PRUETH_MAX_RX_FLOWS_SR1 : PRUETH_MAX_RX_FLOWS; + struct prueth_rx_chn *rx_chn = &emac->rx_chns; int xdp_state_or = 0; int num_rx = 0; int cur_budget; @@ -1090,14 +1421,18 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget) int ret; while (flow--) { - cur_budget = budget - num_rx; - - while (cur_budget--) { - ret = emac_rx_packet(emac, flow, &xdp_state); - xdp_state_or |= xdp_state; - if (ret) - break; - num_rx++; + if (rx_chn->xsk_pool) { + num_rx = emac_rx_packet_zc(emac, flow, budget); + } else { + cur_budget = budget - num_rx; + + while (cur_budget--) { + ret = emac_rx_packet(emac, flow, &xdp_state); + xdp_state_or |= xdp_state; + if (ret) + break; + num_rx++; + } } if (num_rx >= budget) @@ -1113,7 +1448,11 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget) ns_to_ktime(emac->rx_pace_timeout_ns), HRTIMER_MODE_REL_PINNED); } else { - enable_irq(emac->rx_chns.irq[rx_flow]); + if (emac->rx_chns.irq_disabled) { + /* re-enable the RX IRQ */ + emac->rx_chns.irq_disabled = false; + enable_irq(emac->rx_chns.irq[rx_flow]); + } } } @@ -1121,62 +1460,48 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget) } EXPORT_SYMBOL_GPL(icssg_napi_rx_poll); -static struct page_pool *prueth_create_page_pool(struct prueth_emac *emac, - struct device *dma_dev, - int size) -{ - struct page_pool_params pp_params = { 0 }; - struct page_pool *pool; - - pp_params.order = 0; - pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; - pp_params.pool_size = size; - pp_params.nid = dev_to_node(emac->prueth->dev); - pp_params.dma_dir = DMA_BIDIRECTIONAL; - pp_params.dev = dma_dev; - pp_params.napi = &emac->napi_rx; - pp_params.max_len = PAGE_SIZE; - - pool = page_pool_create(&pp_params); - if (IS_ERR(pool)) - netdev_err(emac->ndev, "cannot create rx page pool\n"); - - return pool; -} - int prueth_prepare_rx_chan(struct prueth_emac *emac, struct prueth_rx_chn *chn, int buf_size) { - struct page_pool *pool; struct page *page; + int desc_avail; int i, ret; - pool = prueth_create_page_pool(emac, chn->dma_dev, chn->descs_num); - if (IS_ERR(pool)) - return PTR_ERR(pool); - - chn->pg_pool = pool; + desc_avail = k3_cppi_desc_pool_avail(chn->desc_pool); + if (desc_avail < chn->descs_num) + netdev_warn(emac->ndev, + "not enough RX descriptors available %d < %d\n", + desc_avail, chn->descs_num); - for (i = 0; i < chn->descs_num; i++) { - /* NOTE: we're not using memory efficiently here. - * 1 full page (4KB?) used here instead of - * PRUETH_MAX_PKT_SIZE (~1.5KB?) + if (chn->xsk_pool) { + /* get pages from xsk_pool and push to RX ring + * queue as much as possible */ - page = page_pool_dev_alloc_pages(pool); - if (!page) { - netdev_err(emac->ndev, "couldn't allocate rx page\n"); - ret = -ENOMEM; + ret = prueth_rx_alloc_zc(emac, desc_avail); + if (!ret) goto recycle_alloc_pg; - } + } else { + for (i = 0; i < desc_avail; i++) { + /* NOTE: we're not using memory efficiently here. + * 1 full page (4KB?) used here instead of + * PRUETH_MAX_PKT_SIZE (~1.5KB?) + */ + page = page_pool_dev_alloc_pages(chn->pg_pool); + if (!page) { + netdev_err(emac->ndev, "couldn't allocate rx page\n"); + ret = -ENOMEM; + goto recycle_alloc_pg; + } - ret = prueth_dma_rx_push_mapped(emac, chn, page, buf_size); - if (ret < 0) { - netdev_err(emac->ndev, - "cannot submit page for rx chan %s ret %d\n", - chn->name, ret); - page_pool_recycle_direct(pool, page); - goto recycle_alloc_pg; + ret = prueth_dma_rx_push_mapped(emac, chn, page, buf_size); + if (ret < 0) { + netdev_err(emac->ndev, + "cannot submit page for rx chan %s ret %d\n", + chn->name, ret); + page_pool_recycle_direct(chn->pg_pool, page); + goto recycle_alloc_pg; + } } } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 57a7d1ceab08..f65041662173 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -47,6 +47,9 @@ NETIF_F_HW_HSR_TAG_INS | \ NETIF_F_HW_HSR_TAG_RM) +#define PRUETH_RX_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC |\ + DMA_ATTR_WEAK_ORDERING) + /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) @@ -392,7 +395,11 @@ static enum hrtimer_restart emac_rx_timer_callback(struct hrtimer *timer) container_of(timer, struct prueth_emac, rx_hrtimer); int rx_flow = PRUETH_RX_FLOW_DATA; - enable_irq(emac->rx_chns.irq[rx_flow]); + if (emac->rx_chns.irq_disabled) { + /* re-enable the RX IRQ */ + emac->rx_chns.irq_disabled = false; + enable_irq(emac->rx_chns.irq[rx_flow]); + } return HRTIMER_NORESTART; } @@ -566,31 +573,41 @@ const struct icss_iep_clockops prueth_iep_clockops = { .perout_enable = prueth_perout_enable, }; +static void prueth_destroy_xdp_rxqs(struct prueth_emac *emac) +{ + struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq; + + if (xdp_rxq_info_is_reg(rxq)) + xdp_rxq_info_unreg(rxq); +} + static int prueth_create_xdp_rxqs(struct prueth_emac *emac) { struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq; struct page_pool *pool = emac->rx_chns.pg_pool; + struct prueth_rx_chn *rx_chn = &emac->rx_chns; int ret; ret = xdp_rxq_info_reg(rxq, emac->ndev, 0, emac->napi_rx.napi_id); if (ret) return ret; - ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool); - if (ret) - xdp_rxq_info_unreg(rxq); - - return ret; -} - -static void prueth_destroy_xdp_rxqs(struct prueth_emac *emac) -{ - struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq; + if (rx_chn->xsk_pool) { + ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); + if (ret) + goto xdp_unreg; + xsk_pool_set_rxq_info(rx_chn->xsk_pool, rxq); + } else { + ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool); + if (ret) + goto xdp_unreg; + } - if (!xdp_rxq_info_is_reg(rxq)) - return; + return 0; - xdp_rxq_info_unreg(rxq); +xdp_unreg: + prueth_destroy_xdp_rxqs(emac); + return ret; } static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr) @@ -735,6 +752,128 @@ static int icssg_update_vlan_mcast(struct net_device *vdev, int vid, return 0; } +static void prueth_set_xsk_pool(struct prueth_emac *emac, u16 queue_id) +{ + struct prueth_tx_chn *tx_chn = &emac->tx_chns[queue_id]; + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + + if (emac->xsk_qid != queue_id) { + rx_chn->xsk_pool = NULL; + tx_chn->xsk_pool = NULL; + } else { + rx_chn->xsk_pool = xsk_get_pool_from_qid(emac->ndev, queue_id); + tx_chn->xsk_pool = xsk_get_pool_from_qid(emac->ndev, queue_id); + } +} + +static void prueth_destroy_txq(struct prueth_emac *emac) +{ + int ret, i; + + atomic_set(&emac->tdown_cnt, emac->tx_ch_num); + /* ensure new tdown_cnt value is visible */ + smp_mb__after_atomic(); + /* tear down and disable UDMA channels */ + reinit_completion(&emac->tdown_complete); + for (i = 0; i < emac->tx_ch_num; i++) + k3_udma_glue_tdown_tx_chn(emac->tx_chns[i].tx_chn, false); + + ret = wait_for_completion_timeout(&emac->tdown_complete, + msecs_to_jiffies(1000)); + if (!ret) + netdev_err(emac->ndev, "tx teardown timeout\n"); + + for (i = 0; i < emac->tx_ch_num; i++) { + napi_disable(&emac->tx_chns[i].napi_tx); + hrtimer_cancel(&emac->tx_chns[i].tx_hrtimer); + k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn, + &emac->tx_chns[i], + prueth_tx_cleanup); + k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn); + } +} + +static void prueth_destroy_rxq(struct prueth_emac *emac) +{ + int i, ret; + + /* tear down and disable UDMA channels */ + reinit_completion(&emac->tdown_complete); + k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true); + + /* When RX DMA Channel Teardown is initiated, it will result in an + * interrupt and a Teardown Completion Marker (TDCM) is queued into + * the RX Completion queue. Acknowledging the interrupt involves + * popping the TDCM descriptor from the RX Completion queue via the + * RX NAPI Handler. To avoid timing out when waiting for the TDCM to + * be popped, schedule the RX NAPI handler to run immediately. + */ + if (!napi_if_scheduled_mark_missed(&emac->napi_rx)) { + if (napi_schedule_prep(&emac->napi_rx)) + __napi_schedule(&emac->napi_rx); + } + + ret = wait_for_completion_timeout(&emac->tdown_complete, + msecs_to_jiffies(1000)); + if (!ret) + netdev_err(emac->ndev, "rx teardown timeout\n"); + + for (i = 0; i < PRUETH_MAX_RX_FLOWS; i++) { + napi_disable(&emac->napi_rx); + hrtimer_cancel(&emac->rx_hrtimer); + k3_udma_glue_reset_rx_chn(emac->rx_chns.rx_chn, i, + &emac->rx_chns, + prueth_rx_cleanup); + } + + prueth_destroy_xdp_rxqs(emac); + k3_udma_glue_disable_rx_chn(emac->rx_chns.rx_chn); +} + +static int prueth_create_txq(struct prueth_emac *emac) +{ + int ret, i; + + for (i = 0; i < emac->tx_ch_num; i++) { + ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn); + if (ret) + goto reset_tx_chan; + napi_enable(&emac->tx_chns[i].napi_tx); + } + return 0; + +reset_tx_chan: + /* Since interface is not yet up, there is wouldn't be + * any SKB for completion. So set false to free_skb + */ + prueth_reset_tx_chan(emac, i, false); + return ret; +} + +static int prueth_create_rxq(struct prueth_emac *emac) +{ + int ret; + + ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE); + if (ret) + return ret; + + ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn); + if (ret) + goto reset_rx_chn; + + ret = prueth_create_xdp_rxqs(emac); + if (ret) + goto reset_rx_chn; + + napi_enable(&emac->napi_rx); + return 0; + +reset_rx_chn: + prueth_reset_rx_chan(&emac->rx_chns, PRUETH_MAX_RX_FLOWS, false); + return ret; +} + /** * emac_ndo_open - EMAC device open * @ndev: network adapter device @@ -746,7 +885,7 @@ static int icssg_update_vlan_mcast(struct net_device *vdev, int vid, static int emac_ndo_open(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); - int ret, i, num_data_chn = emac->tx_ch_num; + int ret, num_data_chn = emac->tx_ch_num; struct icssg_flow_cfg __iomem *flow_cfg; struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); @@ -767,6 +906,7 @@ static int emac_ndo_open(struct net_device *ndev) return ret; } + emac->xsk_qid = -EINVAL; init_completion(&emac->cmd_complete); ret = prueth_init_tx_chns(emac); if (ret) { @@ -819,28 +959,13 @@ static int emac_ndo_open(struct net_device *ndev) goto stop; /* Prepare RX */ - ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE); + ret = prueth_create_rxq(emac); if (ret) goto free_tx_ts_irq; - ret = prueth_create_xdp_rxqs(emac); - if (ret) - goto reset_rx_chn; - - ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn); + ret = prueth_create_txq(emac); if (ret) - goto destroy_xdp_rxqs; - - for (i = 0; i < emac->tx_ch_num; i++) { - ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn); - if (ret) - goto reset_tx_chan; - } - - /* Enable NAPI in Tx and Rx direction */ - for (i = 0; i < emac->tx_ch_num; i++) - napi_enable(&emac->tx_chns[i].napi_tx); - napi_enable(&emac->napi_rx); + goto destroy_rxq; /* start PHY */ phy_start(ndev->phydev); @@ -851,15 +976,8 @@ static int emac_ndo_open(struct net_device *ndev) return 0; -reset_tx_chan: - /* Since interface is not yet up, there is wouldn't be - * any SKB for completion. So set false to free_skb - */ - prueth_reset_tx_chan(emac, i, false); -destroy_xdp_rxqs: - prueth_destroy_xdp_rxqs(emac); -reset_rx_chn: - prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false); +destroy_rxq: + prueth_destroy_rxq(emac); free_tx_ts_irq: free_irq(emac->tx_ts_irq, emac); stop: @@ -889,9 +1007,6 @@ static int emac_ndo_stop(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; - int rx_flow = PRUETH_RX_FLOW_DATA; - int max_rx_flows; - int ret, i; /* inform the upper layers. */ netif_tx_stop_all_queues(ndev); @@ -905,32 +1020,8 @@ static int emac_ndo_stop(struct net_device *ndev) else __dev_mc_unsync(ndev, icssg_prueth_del_mcast); - atomic_set(&emac->tdown_cnt, emac->tx_ch_num); - /* ensure new tdown_cnt value is visible */ - smp_mb__after_atomic(); - /* tear down and disable UDMA channels */ - reinit_completion(&emac->tdown_complete); - for (i = 0; i < emac->tx_ch_num; i++) - k3_udma_glue_tdown_tx_chn(emac->tx_chns[i].tx_chn, false); - - ret = wait_for_completion_timeout(&emac->tdown_complete, - msecs_to_jiffies(1000)); - if (!ret) - netdev_err(ndev, "tx teardown timeout\n"); - - prueth_reset_tx_chan(emac, emac->tx_ch_num, true); - for (i = 0; i < emac->tx_ch_num; i++) { - napi_disable(&emac->tx_chns[i].napi_tx); - hrtimer_cancel(&emac->tx_chns[i].tx_hrtimer); - } - - max_rx_flows = PRUETH_MAX_RX_FLOWS; - k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true); - - prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true); - prueth_destroy_xdp_rxqs(emac); - napi_disable(&emac->napi_rx); - hrtimer_cancel(&emac->rx_hrtimer); + prueth_destroy_txq(emac); + prueth_destroy_rxq(emac); cancel_work_sync(&emac->rx_mode_work); @@ -943,10 +1034,10 @@ static int emac_ndo_stop(struct net_device *ndev) free_irq(emac->tx_ts_irq, emac); - free_irq(emac->rx_chns.irq[rx_flow], emac); + free_irq(emac->rx_chns.irq[PRUETH_RX_FLOW_DATA], emac); prueth_ndev_del_tx_napi(emac, emac->tx_ch_num); - prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows); + prueth_cleanup_rx_chns(emac, &emac->rx_chns, PRUETH_MAX_RX_FLOWS); prueth_cleanup_tx_chns(emac); prueth->emacs_initialized--; @@ -1108,7 +1199,8 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame __netif_tx_lock(netif_txq, cpu); for (i = 0; i < n; i++) { xdpf = frames[i]; - err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx); + err = emac_xmit_xdp_frame(emac, xdpf, q_idx, + PRUETH_TX_BUFF_TYPE_XDP_NDO); if (err != ICSSG_XDP_TX) { ndev->stats.tx_dropped++; break; @@ -1141,6 +1233,109 @@ static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf) return 0; } +static int prueth_xsk_pool_enable(struct prueth_emac *emac, + struct xsk_buff_pool *pool, u16 queue_id) +{ + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + u32 frame_size; + int ret; + + if (queue_id >= PRUETH_MAX_RX_FLOWS || + queue_id >= emac->tx_ch_num) { + netdev_err(emac->ndev, "Invalid XSK queue ID %d\n", queue_id); + return -EINVAL; + } + + frame_size = xsk_pool_get_rx_frame_size(pool); + if (frame_size < PRUETH_MAX_PKT_SIZE) + return -EOPNOTSUPP; + + ret = xsk_pool_dma_map(pool, rx_chn->dma_dev, PRUETH_RX_DMA_ATTR); + if (ret) { + netdev_err(emac->ndev, "Failed to map XSK pool: %d\n", ret); + return ret; + } + + if (netif_running(emac->ndev)) { + /* stop packets from wire for graceful teardown */ + ret = icssg_set_port_state(emac, ICSSG_EMAC_PORT_DISABLE); + if (ret) + return ret; + prueth_destroy_rxq(emac); + } + + emac->xsk_qid = queue_id; + prueth_set_xsk_pool(emac, queue_id); + + if (netif_running(emac->ndev)) { + ret = prueth_create_rxq(emac); + if (ret) { + netdev_err(emac->ndev, "Failed to create RX queue: %d\n", ret); + return ret; + } + ret = icssg_set_port_state(emac, ICSSG_EMAC_PORT_FORWARD); + if (ret) { + prueth_destroy_rxq(emac); + return ret; + } + ret = prueth_xsk_wakeup(emac->ndev, queue_id, XDP_WAKEUP_RX); + if (ret) + return ret; + } + + return 0; +} + +static int prueth_xsk_pool_disable(struct prueth_emac *emac, u16 queue_id) +{ + struct xsk_buff_pool *pool; + int ret; + + if (queue_id >= PRUETH_MAX_RX_FLOWS || + queue_id >= emac->tx_ch_num) { + netdev_err(emac->ndev, "Invalid XSK queue ID %d\n", queue_id); + return -EINVAL; + } + + if (emac->xsk_qid != queue_id) { + netdev_err(emac->ndev, "XSK queue ID %d not registered\n", queue_id); + return -EINVAL; + } + + pool = xsk_get_pool_from_qid(emac->ndev, queue_id); + if (!pool) { + netdev_err(emac->ndev, "No XSK pool registered for queue %d\n", queue_id); + return -EINVAL; + } + + if (netif_running(emac->ndev)) { + /* stop packets from wire for graceful teardown */ + ret = icssg_set_port_state(emac, ICSSG_EMAC_PORT_DISABLE); + if (ret) + return ret; + prueth_destroy_rxq(emac); + } + + xsk_pool_dma_unmap(pool, PRUETH_RX_DMA_ATTR); + emac->xsk_qid = -EINVAL; + prueth_set_xsk_pool(emac, queue_id); + + if (netif_running(emac->ndev)) { + ret = prueth_create_rxq(emac); + if (ret) { + netdev_err(emac->ndev, "Failed to create RX queue: %d\n", ret); + return ret; + } + ret = icssg_set_port_state(emac, ICSSG_EMAC_PORT_FORWARD); + if (ret) { + prueth_destroy_rxq(emac); + return ret; + } + } + + return 0; +} + /** * emac_ndo_bpf - implements ndo_bpf for icssg_prueth * @ndev: network adapter device @@ -1155,11 +1350,58 @@ static int emac_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf) switch (bpf->command) { case XDP_SETUP_PROG: return emac_xdp_setup(emac, bpf); + case XDP_SETUP_XSK_POOL: + return bpf->xsk.pool ? + prueth_xsk_pool_enable(emac, bpf->xsk.pool, bpf->xsk.queue_id) : + prueth_xsk_pool_disable(emac, bpf->xsk.queue_id); default: return -EINVAL; } } +int prueth_xsk_wakeup(struct net_device *ndev, u32 qid, u32 flags) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth_tx_chn *tx_chn = &emac->tx_chns[qid]; + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + + if (emac->xsk_qid != qid) { + netdev_err(ndev, "XSK queue %d not registered\n", qid); + return -EINVAL; + } + + if (qid >= PRUETH_MAX_RX_FLOWS || qid >= emac->tx_ch_num) { + netdev_err(ndev, "Invalid XSK queue ID %d\n", qid); + return -EINVAL; + } + + if (!tx_chn->xsk_pool) { + netdev_err(ndev, "XSK pool not registered for queue %d\n", qid); + return -EINVAL; + } + + if (!rx_chn->xsk_pool) { + netdev_err(ndev, "XSK pool not registered for RX queue %d\n", qid); + return -EINVAL; + } + + if (flags & XDP_WAKEUP_TX) { + if (!napi_if_scheduled_mark_missed(&tx_chn->napi_tx)) { + if (likely(napi_schedule_prep(&tx_chn->napi_tx))) + __napi_schedule(&tx_chn->napi_tx); + } + } + + if (flags & XDP_WAKEUP_RX) { + if (!napi_if_scheduled_mark_missed(&emac->napi_rx)) { + if (likely(napi_schedule_prep(&emac->napi_rx))) + __napi_schedule(&emac->napi_rx); + } + } + + return 0; +} + static const struct net_device_ops emac_netdev_ops = { .ndo_open = emac_ndo_open, .ndo_stop = emac_ndo_stop, @@ -1178,6 +1420,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_xdp_xmit = emac_xdp_xmit, .ndo_hwtstamp_get = icssg_ndo_get_ts_config, .ndo_hwtstamp_set = icssg_ndo_set_ts_config, + .ndo_xsk_wakeup = prueth_xsk_wakeup, }; static int prueth_netdev_init(struct prueth *prueth, @@ -1311,7 +1554,8 @@ static int prueth_netdev_init(struct prueth *prueth, xdp_set_features_flag(ndev, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT); + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_XSK_ZEROCOPY); netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll); hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f0fa9688d9a0..10eadd356650 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -38,6 +38,8 @@ #include <net/devlink.h> #include <net/xdp.h> #include <net/page_pool/helpers.h> +#include <net/xsk_buff_pool.h> +#include <net/xdp_sock_drv.h> #include "icssg_config.h" #include "icss_iep.h" @@ -126,6 +128,8 @@ struct prueth_tx_chn { char name[32]; struct hrtimer tx_hrtimer; unsigned long tx_pace_timeout_ns; + struct xsk_buff_pool *xsk_pool; + bool irq_disabled; }; struct prueth_rx_chn { @@ -138,6 +142,8 @@ struct prueth_rx_chn { char name[32]; struct page_pool *pg_pool; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; + bool irq_disabled; }; enum prueth_swdata_type { @@ -146,6 +152,12 @@ enum prueth_swdata_type { PRUETH_SWDATA_PAGE, PRUETH_SWDATA_CMD, PRUETH_SWDATA_XDPF, + PRUETH_SWDATA_XSK, +}; + +enum prueth_tx_buff_type { + PRUETH_TX_BUFF_TYPE_XDP_TX, + PRUETH_TX_BUFF_TYPE_XDP_NDO, }; struct prueth_swdata { @@ -155,6 +167,7 @@ struct prueth_swdata { struct page *page; u32 cmd; struct xdp_frame *xdpf; + struct xdp_buff *xdp; } data; }; @@ -241,6 +254,7 @@ struct prueth_emac { struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID]; struct bpf_prog *xdp_prog; struct xdp_attachment_info xdpi; + int xsk_qid; }; /* The buf includes headroom compatible with both skb and xdpf */ @@ -499,7 +513,14 @@ void prueth_put_cores(struct prueth *prueth, int slice); u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns); u32 emac_xmit_xdp_frame(struct prueth_emac *emac, struct xdp_frame *xdpf, - struct page *page, - unsigned int q_idx); + unsigned int q_idx, + enum prueth_tx_buff_type buff_type); +void prueth_rx_cleanup(void *data, dma_addr_t desc_dma); +void prueth_tx_cleanup(void *data, dma_addr_t desc_dma); +int prueth_xsk_wakeup(struct net_device *ndev, u32 qid, u32 flags); +static inline bool prueth_xdp_is_enabled(struct prueth_emac *emac) +{ + return !!READ_ONCE(emac->xdp_prog); +} #endif /* __NET_TI_ICSSG_PRUETH_H */ diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 4f6cc6cd1f03..8f46e9be76b1 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2657,7 +2657,7 @@ static int gbe_hwtstamp_set(void *intf_priv, struct kernel_hwtstamp_config *cfg, phy = gbe_intf->slave->phy; if (phy_has_hwtstamp(phy)) - return phy->mii_ts->hwtstamp(phy->mii_ts, cfg, extack); + return phy->mii_ts->hwtstamp_set(phy->mii_ts, cfg, extack); switch (cfg->tx_type) { case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 5ee8e8980393..591866fc9055 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -260,6 +260,7 @@ void gelic_card_down(struct gelic_card *card) if (atomic_dec_if_positive(&card->users) == 0) { pr_debug("%s: real do\n", __func__); napi_disable(&card->napi); + timer_delete_sync(&card->rx_oom_timer); /* * Disable irq. Wireless interrupts will * be disabled later if any @@ -970,7 +971,8 @@ static void gelic_net_pass_skb_up(struct gelic_descr *descr, * gelic_card_decode_one_descr - processes an rx descriptor * @card: card structure * - * returns 1 if a packet has been sent to the stack, otherwise 0 + * returns 1 if a packet has been sent to the stack, -ENOMEM on skb alloc + * failure, otherwise 0 * * processes an rx descriptor by iommu-unmapping the data buffer and passing * the packet up to the stack @@ -981,16 +983,18 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) struct gelic_descr_chain *chain = &card->rx_chain; struct gelic_descr *descr = chain->head; struct net_device *netdev = NULL; - int dmac_chain_ended; + int dmac_chain_ended = 0; + int prepare_rx_ret; status = gelic_descr_get_status(descr); if (status == GELIC_DESCR_DMA_CARDOWNED) return 0; - if (status == GELIC_DESCR_DMA_NOT_IN_USE) { + if (status == GELIC_DESCR_DMA_NOT_IN_USE || !descr->skb) { dev_dbg(ctodev(card), "dormant descr? %p\n", descr); - return 0; + dmac_chain_ended = 1; + goto refill; } /* netdevice select */ @@ -1048,9 +1052,10 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) refill: /* is the current descriptor terminated with next_descr == NULL? */ - dmac_chain_ended = - be32_to_cpu(descr->hw_regs.dmac_cmd_status) & - GELIC_DESCR_RX_DMA_CHAIN_END; + if (!dmac_chain_ended) + dmac_chain_ended = + be32_to_cpu(descr->hw_regs.dmac_cmd_status) & + GELIC_DESCR_RX_DMA_CHAIN_END; /* * So that always DMAC can see the end * of the descriptor chain to avoid @@ -1062,10 +1067,11 @@ refill: gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE); /* - * this call can fail, but for now, just leave this - * descriptor without skb + * this call can fail, propagate the error */ - gelic_descr_prepare_rx(card, descr); + prepare_rx_ret = gelic_descr_prepare_rx(card, descr); + if (prepare_rx_ret) + return prepare_rx_ret; chain->tail = descr; chain->head = descr->next; @@ -1087,6 +1093,13 @@ refill: return 1; } +static void gelic_rx_oom_timer(struct timer_list *t) +{ + struct gelic_card *card = timer_container_of(card, t, rx_oom_timer); + + napi_schedule(&card->napi); +} + /** * gelic_net_poll - NAPI poll function called by the stack to return packets * @napi: napi structure @@ -1099,14 +1112,22 @@ static int gelic_net_poll(struct napi_struct *napi, int budget) { struct gelic_card *card = container_of(napi, struct gelic_card, napi); int packets_done = 0; + int work_result = 0; while (packets_done < budget) { - if (!gelic_card_decode_one_descr(card)) + work_result = gelic_card_decode_one_descr(card); + if (work_result != 1) break; packets_done++; } + if (work_result == -ENOMEM) { + napi_complete_done(napi, packets_done); + mod_timer(&card->rx_oom_timer, jiffies + 1); + return packets_done; + } + if (packets_done < budget) { napi_complete_done(napi, packets_done); gelic_card_rx_irq_on(card); @@ -1576,6 +1597,8 @@ static struct gelic_card *gelic_alloc_card_net(struct net_device **netdev) mutex_init(&card->updown_lock); atomic_set(&card->users, 0); + timer_setup(&card->rx_oom_timer, gelic_rx_oom_timer, 0); + return card; } diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index f7d7931e51b7..c10f1984a5a1 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -268,6 +268,7 @@ struct gelic_vlan_id { struct gelic_card { struct napi_struct napi; struct net_device *netdev[GELIC_PORT_MAX]; + struct timer_list rx_oom_timer; /* * hypervisor requires irq_status should be * 8 bytes aligned, but u64 member is diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index 9aa3964187e1..f362e51c73ee 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -240,9 +240,6 @@ int wx_nway_reset(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); - if (wx->mac.type == wx_mac_aml40) - return -EOPNOTSUPP; - return phylink_ethtool_nway_reset(wx->phylink); } EXPORT_SYMBOL(wx_nway_reset); @@ -261,9 +258,6 @@ int wx_set_link_ksettings(struct net_device *netdev, { struct wx *wx = netdev_priv(netdev); - if (wx->mac.type == wx_mac_aml40) - return -EOPNOTSUPP; - return phylink_ethtool_ksettings_set(wx->phylink, cmd); } EXPORT_SYMBOL(wx_set_link_ksettings); @@ -273,9 +267,6 @@ void wx_get_pauseparam(struct net_device *netdev, { struct wx *wx = netdev_priv(netdev); - if (wx->mac.type == wx_mac_aml40) - return; - phylink_ethtool_get_pauseparam(wx->phylink, pause); } EXPORT_SYMBOL(wx_get_pauseparam); @@ -285,9 +276,6 @@ int wx_set_pauseparam(struct net_device *netdev, { struct wx *wx = netdev_priv(netdev); - if (wx->mac.type == wx_mac_aml40) - return -EOPNOTSUPP; - return phylink_ethtool_set_pauseparam(wx->phylink, pause); } EXPORT_SYMBOL(wx_set_pauseparam); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index b1a6ef5709a9..29e5c5470c94 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -1249,7 +1249,7 @@ enum wx_pf_flags { WX_FLAG_RX_HWTSTAMP_IN_REGISTER, WX_FLAG_PTP_PPS_ENABLED, WX_FLAG_NEED_LINK_CONFIG, - WX_FLAG_NEED_SFP_RESET, + WX_FLAG_NEED_MODULE_RESET, WX_FLAG_NEED_UPDATE_LINK, WX_FLAG_NEED_DO_RESET, WX_FLAG_RX_MERGE_ENABLED, diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index 35eebdb07761..62d7f47d4f8d 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -17,10 +17,15 @@ void txgbe_gpio_init_aml(struct wx *wx) { - u32 status; + u32 status, mod_rst; + + if (wx->mac.type == wx_mac_aml40) + mod_rst = TXGBE_GPIOBIT_4; + else + mod_rst = TXGBE_GPIOBIT_2; - wr32(wx, WX_GPIO_INTTYPE_LEVEL, TXGBE_GPIOBIT_2); - wr32(wx, WX_GPIO_INTEN, TXGBE_GPIOBIT_2); + wr32(wx, WX_GPIO_INTTYPE_LEVEL, mod_rst); + wr32(wx, WX_GPIO_INTEN, mod_rst); status = rd32(wx, WX_GPIO_INTSTATUS); for (int i = 0; i < 6; i++) { @@ -33,13 +38,18 @@ irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data) { struct txgbe *txgbe = data; struct wx *wx = txgbe->wx; - u32 status; + u32 status, mod_rst; + + if (wx->mac.type == wx_mac_aml40) + mod_rst = TXGBE_GPIOBIT_4; + else + mod_rst = TXGBE_GPIOBIT_2; wr32(wx, WX_GPIO_INTMASK, 0xFF); status = rd32(wx, WX_GPIO_INTSTATUS); - if (status & TXGBE_GPIOBIT_2) { - set_bit(WX_FLAG_NEED_SFP_RESET, wx->flags); - wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_2); + if (status & mod_rst) { + set_bit(WX_FLAG_NEED_MODULE_RESET, wx->flags); + wr32(wx, WX_GPIO_EOI, mod_rst); wx_service_event_schedule(wx); } @@ -51,7 +61,7 @@ int txgbe_test_hostif(struct wx *wx) { struct txgbe_hic_ephy_getlink buffer; - if (wx->mac.type != wx_mac_aml) + if (wx->mac.type == wx_mac_sp) return 0; buffer.hdr.cmd = FW_PHY_GET_LINK_CMD; @@ -63,15 +73,49 @@ int txgbe_test_hostif(struct wx *wx) WX_HI_COMMAND_TIMEOUT, true); } -static int txgbe_identify_sfp_hostif(struct wx *wx, struct txgbe_hic_i2c_read *buffer) +int txgbe_read_eeprom_hostif(struct wx *wx, + struct txgbe_hic_i2c_read *buffer, + u32 length, u8 *data) { - buffer->hdr.cmd = FW_READ_SFP_INFO_CMD; + u32 dword_len, offset, value, i; + int err; + + buffer->hdr.cmd = FW_READ_EEPROM_CMD; buffer->hdr.buf_len = sizeof(struct txgbe_hic_i2c_read) - sizeof(struct wx_hic_hdr); buffer->hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + err = wx_host_interface_command(wx, (u32 *)buffer, + sizeof(struct txgbe_hic_i2c_read), + WX_HI_COMMAND_TIMEOUT, false); + if (err != 0) + return err; + + /* buffer length offset to read return data */ + offset = sizeof(struct txgbe_hic_i2c_read) >> 2; + dword_len = round_up(length, 4) >> 2; + + for (i = 0; i < dword_len; i++) { + value = rd32a(wx, WX_FW2SW_MBOX, i + offset); + le32_to_cpus(&value); + + memcpy(data, &value, 4); + data += 4; + } + + return 0; +} + +static int txgbe_identify_module_hostif(struct wx *wx, + struct txgbe_hic_get_module_info *buffer) +{ + buffer->hdr.cmd = FW_GET_MODULE_INFO_CMD; + buffer->hdr.buf_len = sizeof(struct txgbe_hic_get_module_info) - + sizeof(struct wx_hic_hdr); + buffer->hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + return wx_host_interface_command(wx, (u32 *)buffer, - sizeof(struct txgbe_hic_i2c_read), + sizeof(struct txgbe_hic_get_module_info), WX_HI_COMMAND_TIMEOUT, true); } @@ -85,6 +129,9 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int buffer.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; switch (speed) { + case SPEED_40000: + buffer.speed = TXGBE_LINK_SPEED_40GB_FULL; + break; case SPEED_25000: buffer.speed = TXGBE_LINK_SPEED_25GB_FULL; break; @@ -104,17 +151,21 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int WX_HI_COMMAND_TIMEOUT, true); } -static void txgbe_get_link_capabilities(struct wx *wx, int *speed, int *duplex) +static void txgbe_get_link_capabilities(struct wx *wx, int *speed, + int *autoneg, int *duplex) { struct txgbe *txgbe = wx->priv; - if (test_bit(PHY_INTERFACE_MODE_25GBASER, txgbe->sfp_interfaces)) + if (test_bit(PHY_INTERFACE_MODE_XLGMII, txgbe->link_interfaces)) + *speed = SPEED_40000; + else if (test_bit(PHY_INTERFACE_MODE_25GBASER, txgbe->link_interfaces)) *speed = SPEED_25000; - else if (test_bit(PHY_INTERFACE_MODE_10GBASER, txgbe->sfp_interfaces)) + else if (test_bit(PHY_INTERFACE_MODE_10GBASER, txgbe->link_interfaces)) *speed = SPEED_10000; else *speed = SPEED_UNKNOWN; + *autoneg = phylink_test(txgbe->advertising, Autoneg); *duplex = *speed == SPEED_UNKNOWN ? DUPLEX_HALF : DUPLEX_FULL; } @@ -125,6 +176,8 @@ static void txgbe_get_mac_link(struct wx *wx, int *speed) status = rd32(wx, TXGBE_CFG_PORT_ST); if (!(status & TXGBE_CFG_PORT_ST_LINK_UP)) *speed = SPEED_UNKNOWN; + else if (status & TXGBE_CFG_PORT_ST_LINK_AML_40G) + *speed = SPEED_40000; else if (status & TXGBE_CFG_PORT_ST_LINK_AML_25G) *speed = SPEED_25000; else if (status & TXGBE_CFG_PORT_ST_LINK_AML_10G) @@ -135,11 +188,11 @@ static void txgbe_get_mac_link(struct wx *wx, int *speed) int txgbe_set_phy_link(struct wx *wx) { - int speed, duplex, err; + int speed, autoneg, duplex, err; - txgbe_get_link_capabilities(wx, &speed, &duplex); + txgbe_get_link_capabilities(wx, &speed, &autoneg, &duplex); - err = txgbe_set_phy_link_hostif(wx, speed, 0, duplex); + err = txgbe_set_phy_link_hostif(wx, speed, autoneg, duplex); if (err) { wx_err(wx, "Failed to setup link\n"); return err; @@ -148,40 +201,128 @@ int txgbe_set_phy_link(struct wx *wx) return 0; } -static int txgbe_sfp_to_linkmodes(struct wx *wx, struct txgbe_sfp_id *id) +static int txgbe_sfp_to_linkmodes(struct wx *wx, struct txgbe_sff_id *id) { __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, }; DECLARE_PHY_INTERFACE_MASK(interfaces); struct txgbe *txgbe = wx->priv; - if (id->com_25g_code & (TXGBE_SFF_25GBASESR_CAPABLE | - TXGBE_SFF_25GBASEER_CAPABLE | - TXGBE_SFF_25GBASELR_CAPABLE)) { - phylink_set(modes, 25000baseSR_Full); + if (id->cable_tech & TXGBE_SFF_DA_PASSIVE_CABLE) { + txgbe->link_port = PORT_DA; + phylink_set(modes, Autoneg); + if (id->com_25g_code == TXGBE_SFF_25GBASECR_91FEC || + id->com_25g_code == TXGBE_SFF_25GBASECR_74FEC || + id->com_25g_code == TXGBE_SFF_25GBASECR_NOFEC) { + phylink_set(modes, 25000baseCR_Full); + phylink_set(modes, 10000baseCR_Full); + __set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces); + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + } else { + phylink_set(modes, 10000baseCR_Full); + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + } + } else if (id->cable_tech & TXGBE_SFF_DA_ACTIVE_CABLE) { + txgbe->link_port = PORT_DA; + phylink_set(modes, Autoneg); + phylink_set(modes, 25000baseCR_Full); __set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces); + } else { + if (id->com_25g_code == TXGBE_SFF_25GBASESR_CAPABLE || + id->com_25g_code == TXGBE_SFF_25GBASEER_CAPABLE || + id->com_25g_code == TXGBE_SFF_25GBASELR_CAPABLE) { + txgbe->link_port = PORT_FIBRE; + phylink_set(modes, 25000baseSR_Full); + __set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces); + } + if (id->com_10g_code & TXGBE_SFF_10GBASESR_CAPABLE) { + txgbe->link_port = PORT_FIBRE; + phylink_set(modes, 10000baseSR_Full); + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + } + if (id->com_10g_code & TXGBE_SFF_10GBASELR_CAPABLE) { + txgbe->link_port = PORT_FIBRE; + phylink_set(modes, 10000baseLR_Full); + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + } } - if (id->com_10g_code & TXGBE_SFF_10GBASESR_CAPABLE) { - phylink_set(modes, 10000baseSR_Full); - __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + + if (phy_interface_empty(interfaces)) { + wx_err(wx, "unsupported SFP module\n"); + return -EINVAL; + } + + phylink_set(modes, Pause); + phylink_set(modes, Asym_Pause); + phylink_set(modes, FIBRE); + + if (!linkmode_equal(txgbe->link_support, modes)) { + linkmode_copy(txgbe->link_support, modes); + phy_interface_and(txgbe->link_interfaces, + wx->phylink_config.supported_interfaces, + interfaces); + linkmode_copy(txgbe->advertising, modes); + + set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags); } - if (id->com_10g_code & TXGBE_SFF_10GBASELR_CAPABLE) { - phylink_set(modes, 10000baseLR_Full); + + return 0; +} + +static int txgbe_qsfp_to_linkmodes(struct wx *wx, struct txgbe_sff_id *id) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = { 0, }; + DECLARE_PHY_INTERFACE_MASK(interfaces); + struct txgbe *txgbe = wx->priv; + + if (id->transceiver_type & TXGBE_SFF_ETHERNET_40G_CR4) { + txgbe->link_port = PORT_DA; + phylink_set(modes, Autoneg); + phylink_set(modes, 40000baseCR4_Full); + phylink_set(modes, 10000baseCR_Full); + __set_bit(PHY_INTERFACE_MODE_XLGMII, interfaces); __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); } + if (id->transceiver_type & TXGBE_SFF_ETHERNET_40G_SR4) { + txgbe->link_port = PORT_FIBRE; + phylink_set(modes, 40000baseSR4_Full); + __set_bit(PHY_INTERFACE_MODE_XLGMII, interfaces); + } + if (id->transceiver_type & TXGBE_SFF_ETHERNET_40G_LR4) { + txgbe->link_port = PORT_FIBRE; + phylink_set(modes, 40000baseLR4_Full); + __set_bit(PHY_INTERFACE_MODE_XLGMII, interfaces); + } + if (id->transceiver_type & TXGBE_SFF_ETHERNET_40G_ACTIVE) { + txgbe->link_port = PORT_DA; + phylink_set(modes, Autoneg); + phylink_set(modes, 40000baseCR4_Full); + __set_bit(PHY_INTERFACE_MODE_XLGMII, interfaces); + } + if (id->transceiver_type & TXGBE_SFF_ETHERNET_RSRVD) { + if (id->sff_opt1 & TXGBE_SFF_ETHERNET_100G_CR4) { + txgbe->link_port = PORT_DA; + phylink_set(modes, Autoneg); + phylink_set(modes, 40000baseCR4_Full); + phylink_set(modes, 25000baseCR_Full); + phylink_set(modes, 10000baseCR_Full); + __set_bit(PHY_INTERFACE_MODE_XLGMII, interfaces); + __set_bit(PHY_INTERFACE_MODE_25GBASER, interfaces); + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + } + } if (phy_interface_empty(interfaces)) { - wx_err(wx, "unsupported SFP module\n"); + wx_err(wx, "unsupported QSFP module\n"); return -EINVAL; } phylink_set(modes, Pause); phylink_set(modes, Asym_Pause); phylink_set(modes, FIBRE); - txgbe->link_port = PORT_FIBRE; - if (!linkmode_equal(txgbe->sfp_support, modes)) { - linkmode_copy(txgbe->sfp_support, modes); - phy_interface_and(txgbe->sfp_interfaces, + if (!linkmode_equal(txgbe->link_support, modes)) { + linkmode_copy(txgbe->link_support, modes); + phy_interface_and(txgbe->link_interfaces, wx->phylink_config.supported_interfaces, interfaces); linkmode_copy(txgbe->advertising, modes); @@ -192,40 +333,53 @@ static int txgbe_sfp_to_linkmodes(struct wx *wx, struct txgbe_sfp_id *id) return 0; } -int txgbe_identify_sfp(struct wx *wx) +int txgbe_identify_module(struct wx *wx) { - struct txgbe_hic_i2c_read buffer; - struct txgbe_sfp_id *id; + struct txgbe_hic_get_module_info buffer; + struct txgbe_sff_id *id; int err = 0; + u32 mod_abs; u32 gpio; + if (wx->mac.type == wx_mac_aml40) + mod_abs = TXGBE_GPIOBIT_4; + else + mod_abs = TXGBE_GPIOBIT_2; + gpio = rd32(wx, WX_GPIO_EXT); - if (gpio & TXGBE_GPIOBIT_2) + if (gpio & mod_abs) return -ENODEV; - err = txgbe_identify_sfp_hostif(wx, &buffer); + err = txgbe_identify_module_hostif(wx, &buffer); if (err) { - wx_err(wx, "Failed to identify SFP module\n"); + wx_err(wx, "Failed to identify module\n"); return err; } id = &buffer.id; - if (id->identifier != TXGBE_SFF_IDENTIFIER_SFP) { - wx_err(wx, "Invalid SFP module\n"); + if (id->identifier != TXGBE_SFF_IDENTIFIER_SFP && + id->identifier != TXGBE_SFF_IDENTIFIER_QSFP && + id->identifier != TXGBE_SFF_IDENTIFIER_QSFP_PLUS && + id->identifier != TXGBE_SFF_IDENTIFIER_QSFP28) { + wx_err(wx, "Invalid module\n"); return -ENODEV; } - return txgbe_sfp_to_linkmodes(wx, id); + if (id->transceiver_type == 0xFF) + return txgbe_sfp_to_linkmodes(wx, id); + + return txgbe_qsfp_to_linkmodes(wx, id); } void txgbe_setup_link(struct wx *wx) { struct txgbe *txgbe = wx->priv; - phy_interface_zero(txgbe->sfp_interfaces); - linkmode_zero(txgbe->sfp_support); + phy_interface_zero(txgbe->link_interfaces); + linkmode_zero(txgbe->link_support); - txgbe_identify_sfp(wx); + set_bit(WX_FLAG_NEED_MODULE_RESET, wx->flags); + wx_service_event_schedule(wx); } static void txgbe_get_link_state(struct phylink_config *config, @@ -278,6 +432,9 @@ static void txgbe_mac_link_up_aml(struct phylink_config *config, txcfg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK; switch (speed) { + case SPEED_40000: + txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_40G; + break; case SPEED_25000: txcfg |= TXGBE_AML_MAC_TX_CFG_SPEED_25G; break; @@ -342,7 +499,18 @@ int txgbe_phylink_init_aml(struct txgbe *txgbe) MAC_SYM_PAUSE | MAC_ASYM_PAUSE; config->get_fixed_state = txgbe_get_link_state; - phy_mode = PHY_INTERFACE_MODE_25GBASER; + if (wx->mac.type == wx_mac_aml40) { + config->mac_capabilities |= MAC_40000FD; + phy_mode = PHY_INTERFACE_MODE_XLGMII; + __set_bit(PHY_INTERFACE_MODE_XLGMII, config->supported_interfaces); + state.speed = SPEED_40000; + state.duplex = DUPLEX_FULL; + } else { + phy_mode = PHY_INTERFACE_MODE_25GBASER; + state.speed = SPEED_25000; + state.duplex = DUPLEX_FULL; + } + __set_bit(PHY_INTERFACE_MODE_25GBASER, config->supported_interfaces); __set_bit(PHY_INTERFACE_MODE_10GBASER, config->supported_interfaces); @@ -350,8 +518,6 @@ int txgbe_phylink_init_aml(struct txgbe *txgbe) if (IS_ERR(phylink)) return PTR_ERR(phylink); - state.speed = SPEED_25000; - state.duplex = DUPLEX_FULL; err = phylink_set_fixed_link(phylink, &state); if (err) { wx_err(wx, "Failed to set fixed link\n"); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h index 25d4971ca0d9..4f6df0ee860b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.h @@ -7,8 +7,11 @@ void txgbe_gpio_init_aml(struct wx *wx); irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data); int txgbe_test_hostif(struct wx *wx); +int txgbe_read_eeprom_hostif(struct wx *wx, + struct txgbe_hic_i2c_read *buffer, + u32 length, u8 *data); int txgbe_set_phy_link(struct wx *wx); -int txgbe_identify_sfp(struct wx *wx); +int txgbe_identify_module(struct wx *wx); void txgbe_setup_link(struct wx *wx); int txgbe_phylink_init_aml(struct txgbe *txgbe); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index e285b088c7b2..f3cb00109529 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -10,6 +10,7 @@ #include "../libwx/wx_lib.h" #include "txgbe_type.h" #include "txgbe_fdir.h" +#include "txgbe_aml.h" #include "txgbe_ethtool.h" int txgbe_get_link_ksettings(struct net_device *netdev, @@ -19,9 +20,6 @@ int txgbe_get_link_ksettings(struct net_device *netdev, struct txgbe *txgbe = wx->priv; int err; - if (wx->mac.type == wx_mac_aml40) - return -EOPNOTSUPP; - err = wx_get_link_ksettings(netdev, cmd); if (err) return err; @@ -30,8 +28,9 @@ int txgbe_get_link_ksettings(struct net_device *netdev, return 0; cmd->base.port = txgbe->link_port; - cmd->base.autoneg = AUTONEG_DISABLE; - linkmode_copy(cmd->link_modes.supported, txgbe->sfp_support); + cmd->base.autoneg = phylink_test(txgbe->advertising, Autoneg) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; + linkmode_copy(cmd->link_modes.supported, txgbe->link_support); linkmode_copy(cmd->link_modes.advertising, txgbe->advertising); return 0; @@ -536,6 +535,34 @@ static int txgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } +static int +txgbe_get_module_eeprom_by_page(struct net_device *netdev, + const struct ethtool_module_eeprom *page_data, + struct netlink_ext_ack *extack) +{ + struct wx *wx = netdev_priv(netdev); + struct txgbe_hic_i2c_read buffer; + int err; + + if (!test_bit(WX_FLAG_SWFW_RING, wx->flags)) + return -EOPNOTSUPP; + + buffer.length = cpu_to_be32(page_data->length); + buffer.offset = cpu_to_be32(page_data->offset); + buffer.page = page_data->page; + buffer.bank = page_data->bank; + buffer.i2c_address = page_data->i2c_address; + + err = txgbe_read_eeprom_hostif(wx, &buffer, page_data->length, + page_data->data); + if (err) { + wx_err(wx, "Failed to read module EEPROM\n"); + return err; + } + + return page_data->length; +} + static const struct ethtool_ops txgbe_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ | @@ -570,6 +597,7 @@ static const struct ethtool_ops txgbe_ethtool_ops = { .set_msglevel = wx_set_msglevel, .get_ts_info = wx_get_ts_info, .get_ts_stats = wx_get_ptp_stats, + .get_module_eeprom_by_page = txgbe_get_module_eeprom_by_page, }; void txgbe_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c index 3885283681ec..aa14958d439a 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c @@ -23,7 +23,7 @@ void txgbe_irq_enable(struct wx *wx, bool queues) { u32 misc_ien = TXGBE_PX_MISC_IEN_MASK; - if (wx->mac.type == wx_mac_aml) { + if (wx->mac.type != wx_mac_sp) { misc_ien |= TXGBE_PX_MISC_GPIO; txgbe_gpio_init_aml(wx); } @@ -201,10 +201,7 @@ static void txgbe_del_irq_domain(struct txgbe *txgbe) void txgbe_free_misc_irq(struct txgbe *txgbe) { - if (txgbe->wx->mac.type == wx_mac_aml40) - return; - - if (txgbe->wx->mac.type == wx_mac_aml) + if (txgbe->wx->mac.type != wx_mac_sp) free_irq(txgbe->gpio_irq, txgbe); free_irq(txgbe->link_irq, txgbe); @@ -219,9 +216,6 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe) struct wx *wx = txgbe->wx; int hwirq, err; - if (wx->mac.type == wx_mac_aml40) - goto skip_sp_irq; - txgbe->misc.nirqs = TXGBE_IRQ_MAX; txgbe->misc.domain = irq_domain_create_simple(NULL, txgbe->misc.nirqs, 0, &txgbe_misc_irq_domain_ops, txgbe); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index daa761e48f9d..0de051450a82 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -89,21 +89,21 @@ static int txgbe_enumerate_functions(struct wx *wx) return physfns; } -static void txgbe_sfp_detection_subtask(struct wx *wx) +static void txgbe_module_detection_subtask(struct wx *wx) { int err; - if (!test_bit(WX_FLAG_NEED_SFP_RESET, wx->flags)) + if (!test_bit(WX_FLAG_NEED_MODULE_RESET, wx->flags)) return; - /* wait for SFP module ready */ + /* wait for SFF module ready */ msleep(200); - err = txgbe_identify_sfp(wx); + err = txgbe_identify_module(wx); if (err) return; - clear_bit(WX_FLAG_NEED_SFP_RESET, wx->flags); + clear_bit(WX_FLAG_NEED_MODULE_RESET, wx->flags); } static void txgbe_link_config_subtask(struct wx *wx) @@ -128,7 +128,7 @@ static void txgbe_service_task(struct work_struct *work) { struct wx *wx = container_of(work, struct wx, service_task); - txgbe_sfp_detection_subtask(wx); + txgbe_module_detection_subtask(wx); txgbe_link_config_subtask(wx); wx_service_event_complete(wx); @@ -144,7 +144,6 @@ static void txgbe_init_service(struct wx *wx) static void txgbe_up_complete(struct wx *wx) { struct net_device *netdev = wx->netdev; - u32 reg; wx_control_hw(wx, true); wx_configure_vectors(wx); @@ -155,12 +154,8 @@ static void txgbe_up_complete(struct wx *wx) switch (wx->mac.type) { case wx_mac_aml40: - reg = rd32(wx, TXGBE_AML_MAC_TX_CFG); - reg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK; - reg |= TXGBE_AML_MAC_TX_CFG_SPEED_40G; - wr32(wx, WX_MAC_TX_CFG, reg); - txgbe_enable_sec_tx_path(wx); - netif_carrier_on(wx->netdev); + txgbe_setup_link(wx); + phylink_start(wx->phylink); break; case wx_mac_aml: /* Enable TX laser */ @@ -276,7 +271,7 @@ void txgbe_down(struct wx *wx) switch (wx->mac.type) { case wx_mac_aml40: - netif_carrier_off(wx->netdev); + phylink_stop(wx->phylink); break; case wx_mac_aml: phylink_stop(wx->phylink); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 03f1b9bc604d..8ea7aa07ae4e 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -579,7 +579,6 @@ int txgbe_init_phy(struct txgbe *txgbe) switch (wx->mac.type) { case wx_mac_aml40: - return 0; case wx_mac_aml: return txgbe_phylink_init_aml(txgbe); case wx_mac_sp: @@ -653,7 +652,6 @@ void txgbe_remove_phy(struct txgbe *txgbe) { switch (txgbe->wx->mac.type) { case wx_mac_aml40: - return; case wx_mac_aml: phylink_destroy(txgbe->wx->phylink); return; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index b9a4ba48f5b9..82433e9cb0e3 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -98,6 +98,7 @@ /* Port cfg registers */ #define TXGBE_CFG_PORT_ST 0x14404 #define TXGBE_CFG_PORT_ST_LINK_UP BIT(0) +#define TXGBE_CFG_PORT_ST_LINK_AML_40G BIT(2) #define TXGBE_CFG_PORT_ST_LINK_AML_25G BIT(3) #define TXGBE_CFG_PORT_ST_LINK_AML_10G BIT(4) #define TXGBE_CFG_VXLAN 0x14410 @@ -317,8 +318,12 @@ void txgbe_do_reset(struct net_device *netdev); #define TXGBE_LINK_SPEED_UNKNOWN 0 #define TXGBE_LINK_SPEED_10GB_FULL 4 #define TXGBE_LINK_SPEED_25GB_FULL 0x10 +#define TXGBE_LINK_SPEED_40GB_FULL 0x20 #define TXGBE_SFF_IDENTIFIER_SFP 0x3 +#define TXGBE_SFF_IDENTIFIER_QSFP 0xC +#define TXGBE_SFF_IDENTIFIER_QSFP_PLUS 0xD +#define TXGBE_SFF_IDENTIFIER_QSFP28 0x11 #define TXGBE_SFF_DA_PASSIVE_CABLE 0x4 #define TXGBE_SFF_DA_ACTIVE_CABLE 0x8 #define TXGBE_SFF_DA_SPEC_ACTIVE_LIMIT 0x4 @@ -331,6 +336,12 @@ void txgbe_do_reset(struct net_device *netdev); #define TXGBE_SFF_25GBASECR_91FEC 0xB #define TXGBE_SFF_25GBASECR_74FEC 0xC #define TXGBE_SFF_25GBASECR_NOFEC 0xD +#define TXGBE_SFF_ETHERNET_RSRVD BIT(7) +#define TXGBE_SFF_ETHERNET_40G_CR4 BIT(3) +#define TXGBE_SFF_ETHERNET_40G_SR4 BIT(2) +#define TXGBE_SFF_ETHERNET_40G_LR4 BIT(1) +#define TXGBE_SFF_ETHERNET_40G_ACTIVE BIT(0) +#define TXGBE_SFF_ETHERNET_100G_CR4 0xB #define TXGBE_PHY_FEC_RS BIT(0) #define TXGBE_PHY_FEC_BASER BIT(1) @@ -341,9 +352,10 @@ void txgbe_do_reset(struct net_device *netdev); #define FW_PHY_GET_LINK_CMD 0xC0 #define FW_PHY_SET_LINK_CMD 0xC1 -#define FW_READ_SFP_INFO_CMD 0xC5 +#define FW_GET_MODULE_INFO_CMD 0xC5 +#define FW_READ_EEPROM_CMD 0xC6 -struct txgbe_sfp_id { +struct txgbe_sff_id { u8 identifier; /* A0H 0x00 */ u8 com_1g_code; /* A0H 0x06 */ u8 com_10g_code; /* A0H 0x03 */ @@ -358,9 +370,9 @@ struct txgbe_sfp_id { u8 reserved[5]; }; -struct txgbe_hic_i2c_read { +struct txgbe_hic_get_module_info { struct wx_hic_hdr hdr; - struct txgbe_sfp_id id; + struct txgbe_sff_id id; }; struct txgbe_hic_ephy_setlink { @@ -383,6 +395,16 @@ struct txgbe_hic_ephy_getlink { u8 resv[6]; }; +struct txgbe_hic_i2c_read { + struct wx_hic_hdr hdr; + __be32 offset; + __be32 length; + u8 page; + u8 bank; + u8 i2c_address; + u8 resv; +}; + #define NODE_PROP(_NAME, _PROP) \ (const struct software_node) { \ .name = _NAME, \ @@ -451,8 +473,8 @@ struct txgbe { int fdir_filter_count; spinlock_t fdir_perfect_lock; /* spinlock for FDIR */ - DECLARE_PHY_INTERFACE_MASK(sfp_interfaces); - __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); + DECLARE_PHY_INTERFACE_MASK(link_interfaces); + __ETHTOOL_DECLARE_LINK_MODE_MASK(link_support); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); u8 link_port; }; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 39c892e46cb0..3d47d749ef9f 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1624,22 +1624,15 @@ netvsc_get_rxfh_fields(struct net_device *ndev, return 0; } -static int -netvsc_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules) +static u32 netvsc_get_rx_ring_count(struct net_device *dev) { struct net_device_context *ndc = netdev_priv(dev); struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev); if (!nvdev) - return -ENODEV; - - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = nvdev->num_chn; return 0; - } - return -EOPNOTSUPP; + + return nvdev->num_chn; } static int @@ -1969,7 +1962,7 @@ static const struct ethtool_ops ethtool_ops = { .get_channels = netvsc_get_channels, .set_channels = netvsc_set_channels, .get_ts_info = ethtool_op_get_ts_info, - .get_rxnfc = netvsc_get_rxnfc, + .get_rx_ring_count = netvsc_get_rx_ring_count, .get_rxfh_key_size = netvsc_get_rxfh_key_size, .get_rxfh_indir_size = netvsc_rss_indir_size, .get_rxfh = netvsc_get_rxfh, diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index d7e3ddbcab6f..dea411e132db 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -52,8 +52,8 @@ static u8 ipvlan_get_v4_hash(const void *iaddr) { const struct in_addr *ip4_addr = iaddr; - return jhash_1word(ip4_addr->s_addr, ipvlan_jhash_secret) & - IPVLAN_HASH_MASK; + return jhash_1word((__force u32)ip4_addr->s_addr, ipvlan_jhash_secret) & + IPVLAN_HASH_MASK; } static bool addr_equal(bool is_v6, struct ipvl_addr *addr, const void *iaddr) diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index 9b41d4697a40..ba7091518265 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -92,11 +92,6 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, if (fwnode_property_read_bool(child, "broken-turn-around")) mdio->phy_ignore_ta_mask |= 1 << addr; - fwnode_property_read_u32(child, "reset-assert-us", - &phy->mdio.reset_assert_delay); - fwnode_property_read_u32(child, "reset-deassert-us", - &phy->mdio.reset_deassert_delay); - /* Associate the fwnode with the device structure so it * can be looked up later */ diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 1357348e01d5..b8d298c04d3f 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -63,14 +63,11 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, /* Associate the OF node with the device structure so it * can be looked up later. */ - fwnode_handle_get(fwnode); - device_set_node(&mdiodev->dev, fwnode); + device_set_node(&mdiodev->dev, fwnode_handle_get(fwnode)); /* All data is now stored in the mdiodev struct; register it. */ rc = mdio_device_register(mdiodev); if (rc) { - device_set_node(&mdiodev->dev, NULL); - fwnode_handle_put(fwnode); mdio_device_free(mdiodev); return rc; } diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index bb6e03a92956..9cb4dfc242f5 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -50,7 +50,7 @@ MODULE_LICENSE("GPL"); /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ #define MAX_EXTRADATA_NAME_LEN (MAX_EXTRADATA_ENTRY_LEN - \ MAX_EXTRADATA_VALUE_LEN - 3) -#define MAX_EXTRADATA_ITEMS 16 +#define MAX_USERDATA_ITEMS 256 #define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; @@ -115,6 +115,8 @@ enum sysdata_feature { SYSDATA_RELEASE = BIT(2), /* Include a per-target message ID as part of sysdata */ SYSDATA_MSGID = BIT(3), + /* Sentinel: highest bit position */ + MAX_SYSDATA_ITEMS = 4, }; /** @@ -122,8 +124,9 @@ enum sysdata_feature { * @list: Links this target into the target_list. * @group: Links us into the configfs subsystem hierarchy. * @userdata_group: Links to the userdata configfs hierarchy - * @extradata_complete: Cached, formatted string of append - * @userdata_length: String length of usedata in extradata_complete. + * @userdata: Cached, formatted string of append + * @userdata_length: String length of userdata. + * @sysdata: Cached, formatted string of append * @sysdata_fields: Sysdata features enabled. * @msgcounter: Message sent counter. * @stats: Packet send stats for the target. Used for debugging. @@ -152,8 +155,10 @@ struct netconsole_target { #ifdef CONFIG_NETCONSOLE_DYNAMIC struct config_group group; struct config_group userdata_group; - char extradata_complete[MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS]; + char *userdata; size_t userdata_length; + char sysdata[MAX_EXTRADATA_ENTRY_LEN * MAX_SYSDATA_ITEMS]; + /* bit-wise with sysdata_feature bits */ u32 sysdata_fields; /* protected by target_list_lock */ @@ -802,28 +807,14 @@ out_unlock: return ret; } -/* Count number of entries we have in extradata. - * This is important because the extradata_complete only supports - * MAX_EXTRADATA_ITEMS entries. Before enabling any new {user,sys}data - * feature, number of entries needs to checked for available space. +/* Count number of entries we have in userdata. + * This is important because userdata only supports MAX_USERDATA_ITEMS + * entries. Before enabling any new userdata feature, number of entries needs + * to checked for available space. */ -static size_t count_extradata_entries(struct netconsole_target *nt) +static size_t count_userdata_entries(struct netconsole_target *nt) { - size_t entries; - - /* Userdata entries */ - entries = list_count_nodes(&nt->userdata_group.cg_children); - /* Plus sysdata entries */ - if (nt->sysdata_fields & SYSDATA_CPU_NR) - entries += 1; - if (nt->sysdata_fields & SYSDATA_TASKNAME) - entries += 1; - if (nt->sysdata_fields & SYSDATA_RELEASE) - entries += 1; - if (nt->sysdata_fields & SYSDATA_MSGID) - entries += 1; - - return entries; + return list_count_nodes(&nt->userdata_group.cg_children); } static ssize_t remote_mac_store(struct config_item *item, const char *buf, @@ -884,45 +875,77 @@ static ssize_t userdatum_value_show(struct config_item *item, char *buf) return sysfs_emit(buf, "%s\n", &(to_userdatum(item)->value[0])); } -static void update_userdata(struct netconsole_target *nt) +/* Navigate configfs and calculate the lentgh of the formatted string + * representing userdata. + * Must be called holding netconsole_subsys.su_mutex + */ +static int calc_userdata_len(struct netconsole_target *nt) { + struct userdatum *udm_item; + struct config_item *item; struct list_head *entry; - int child_count = 0; - unsigned long flags; + int len = 0; - spin_lock_irqsave(&target_list_lock, flags); + list_for_each(entry, &nt->userdata_group.cg_children) { + item = container_of(entry, struct config_item, ci_entry); + udm_item = to_userdatum(item); + /* Skip userdata with no value set */ + if (udm_item->value[0]) { + len += snprintf(NULL, 0, " %s=%s\n", item->ci_name, + udm_item->value); + } + } + return len; +} - /* Clear the current string in case the last userdatum was deleted */ - nt->userdata_length = 0; - nt->extradata_complete[0] = 0; +static int update_userdata(struct netconsole_target *nt) +{ + struct userdatum *udm_item; + struct config_item *item; + struct list_head *entry; + char *old_buf = NULL; + char *new_buf = NULL; + unsigned long flags; + int offset = 0; + int len; - list_for_each(entry, &nt->userdata_group.cg_children) { - struct userdatum *udm_item; - struct config_item *item; + /* Calculate required buffer size */ + len = calc_userdata_len(nt); - if (child_count >= MAX_EXTRADATA_ITEMS) { - spin_unlock_irqrestore(&target_list_lock, flags); - WARN_ON_ONCE(1); - return; - } - child_count++; + if (WARN_ON_ONCE(len > MAX_EXTRADATA_ENTRY_LEN * MAX_USERDATA_ITEMS)) + return -ENOSPC; + + /* Allocate new buffer */ + if (len) { + new_buf = kmalloc(len + 1, GFP_KERNEL); + if (!new_buf) + return -ENOMEM; + } + /* Write userdata to new buffer */ + list_for_each(entry, &nt->userdata_group.cg_children) { item = container_of(entry, struct config_item, ci_entry); udm_item = to_userdatum(item); - /* Skip userdata with no value set */ - if (strnlen(udm_item->value, MAX_EXTRADATA_VALUE_LEN) == 0) - continue; - - /* This doesn't overflow extradata_complete since it will write - * one entry length (1/MAX_EXTRADATA_ITEMS long), entry count is - * checked to not exceed MAX items with child_count above - */ - nt->userdata_length += scnprintf(&nt->extradata_complete[nt->userdata_length], - MAX_EXTRADATA_ENTRY_LEN, " %s=%s\n", - item->ci_name, udm_item->value); + if (udm_item->value[0]) { + offset += scnprintf(&new_buf[offset], len + 1 - offset, + " %s=%s\n", item->ci_name, + udm_item->value); + } } + + WARN_ON_ONCE(offset != len); + + /* Switch to new buffer and free old buffer */ + spin_lock_irqsave(&target_list_lock, flags); + old_buf = nt->userdata; + nt->userdata = new_buf; + nt->userdata_length = offset; spin_unlock_irqrestore(&target_list_lock, flags); + + kfree(old_buf); + + return 0; } static ssize_t userdatum_value_store(struct config_item *item, const char *buf, @@ -946,7 +969,9 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); - update_userdata(nt); + ret = update_userdata(nt); + if (ret < 0) + goto out_unlock; ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); @@ -962,7 +987,7 @@ static void disable_sysdata_feature(struct netconsole_target *nt, enum sysdata_feature feature) { nt->sysdata_fields &= ~feature; - nt->extradata_complete[nt->userdata_length] = 0; + nt->sysdata[0] = 0; } static ssize_t sysdata_msgid_enabled_store(struct config_item *item, @@ -982,12 +1007,6 @@ static ssize_t sysdata_msgid_enabled_store(struct config_item *item, if (msgid_enabled == curr) goto unlock_ok; - if (msgid_enabled && - count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { - ret = -ENOSPC; - goto unlock; - } - if (msgid_enabled) nt->sysdata_fields |= SYSDATA_MSGID; else @@ -995,7 +1014,6 @@ static ssize_t sysdata_msgid_enabled_store(struct config_item *item, unlock_ok: ret = strnlen(buf, count); -unlock: mutex_unlock(&dynamic_netconsole_mutex); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1018,12 +1036,6 @@ static ssize_t sysdata_release_enabled_store(struct config_item *item, if (release_enabled == curr) goto unlock_ok; - if (release_enabled && - count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { - ret = -ENOSPC; - goto unlock; - } - if (release_enabled) nt->sysdata_fields |= SYSDATA_RELEASE; else @@ -1031,7 +1043,6 @@ static ssize_t sysdata_release_enabled_store(struct config_item *item, unlock_ok: ret = strnlen(buf, count); -unlock: mutex_unlock(&dynamic_netconsole_mutex); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1054,12 +1065,6 @@ static ssize_t sysdata_taskname_enabled_store(struct config_item *item, if (taskname_enabled == curr) goto unlock_ok; - if (taskname_enabled && - count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { - ret = -ENOSPC; - goto unlock; - } - if (taskname_enabled) nt->sysdata_fields |= SYSDATA_TASKNAME; else @@ -1067,7 +1072,6 @@ static ssize_t sysdata_taskname_enabled_store(struct config_item *item, unlock_ok: ret = strnlen(buf, count); -unlock: mutex_unlock(&dynamic_netconsole_mutex); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1092,27 +1096,16 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item, /* no change requested */ goto unlock_ok; - if (cpu_nr_enabled && - count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { - /* user wants the new feature, but there is no space in the - * buffer. - */ - ret = -ENOSPC; - goto unlock; - } - if (cpu_nr_enabled) nt->sysdata_fields |= SYSDATA_CPU_NR; else - /* This is special because extradata_complete might have - * remaining data from previous sysdata, and it needs to be - * cleaned. + /* This is special because sysdata might have remaining data + * from previous sysdata, and it needs to be cleaned. */ disable_sysdata_feature(nt, SYSDATA_CPU_NR); unlock_ok: ret = strnlen(buf, count); -unlock: mutex_unlock(&dynamic_netconsole_mutex); mutex_unlock(&netconsole_subsys.su_mutex); return ret; @@ -1156,7 +1149,7 @@ static struct config_item *userdatum_make_item(struct config_group *group, ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); - if (count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) + if (count_userdata_entries(nt) >= MAX_USERDATA_ITEMS) return ERR_PTR(-ENOSPC); udm = kzalloc(sizeof(*udm), GFP_KERNEL); @@ -1234,7 +1227,10 @@ static struct configfs_attribute *netconsole_target_attrs[] = { static void netconsole_target_release(struct config_item *item) { - kfree(to_target(item)); + struct netconsole_target *nt = to_target(item); + + kfree(nt->userdata); + kfree(nt); } static struct configfs_item_operations netconsole_target_item_ops = { @@ -1363,22 +1359,21 @@ static void populate_configfs_item(struct netconsole_target *nt, static int sysdata_append_cpu_nr(struct netconsole_target *nt, int offset) { - /* Append cpu=%d at extradata_complete after userdata str */ - return scnprintf(&nt->extradata_complete[offset], + return scnprintf(&nt->sysdata[offset], MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n", raw_smp_processor_id()); } static int sysdata_append_taskname(struct netconsole_target *nt, int offset) { - return scnprintf(&nt->extradata_complete[offset], + return scnprintf(&nt->sysdata[offset], MAX_EXTRADATA_ENTRY_LEN, " taskname=%s\n", current->comm); } static int sysdata_append_release(struct netconsole_target *nt, int offset) { - return scnprintf(&nt->extradata_complete[offset], + return scnprintf(&nt->sysdata[offset], MAX_EXTRADATA_ENTRY_LEN, " release=%s\n", init_utsname()->release); } @@ -1386,46 +1381,36 @@ static int sysdata_append_release(struct netconsole_target *nt, int offset) static int sysdata_append_msgid(struct netconsole_target *nt, int offset) { wrapping_assign_add(nt->msgcounter, 1); - return scnprintf(&nt->extradata_complete[offset], + return scnprintf(&nt->sysdata[offset], MAX_EXTRADATA_ENTRY_LEN, " msgid=%u\n", nt->msgcounter); } /* - * prepare_extradata - append sysdata at extradata_complete in runtime + * prepare_sysdata - append sysdata in runtime * @nt: target to send message to */ -static int prepare_extradata(struct netconsole_target *nt) +static int prepare_sysdata(struct netconsole_target *nt) { - int extradata_len; - - /* userdata was appended when configfs write helper was called - * by update_userdata(). - */ - extradata_len = nt->userdata_length; + int sysdata_len = 0; if (!nt->sysdata_fields) goto out; if (nt->sysdata_fields & SYSDATA_CPU_NR) - extradata_len += sysdata_append_cpu_nr(nt, extradata_len); + sysdata_len += sysdata_append_cpu_nr(nt, sysdata_len); if (nt->sysdata_fields & SYSDATA_TASKNAME) - extradata_len += sysdata_append_taskname(nt, extradata_len); + sysdata_len += sysdata_append_taskname(nt, sysdata_len); if (nt->sysdata_fields & SYSDATA_RELEASE) - extradata_len += sysdata_append_release(nt, extradata_len); + sysdata_len += sysdata_append_release(nt, sysdata_len); if (nt->sysdata_fields & SYSDATA_MSGID) - extradata_len += sysdata_append_msgid(nt, extradata_len); + sysdata_len += sysdata_append_msgid(nt, sysdata_len); - WARN_ON_ONCE(extradata_len > - MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS); + WARN_ON_ONCE(sysdata_len > + MAX_EXTRADATA_ENTRY_LEN * MAX_SYSDATA_ITEMS); out: - return extradata_len; -} -#else /* CONFIG_NETCONSOLE_DYNAMIC not set */ -static int prepare_extradata(struct netconsole_target *nt) -{ - return 0; + return sysdata_len; } #endif /* CONFIG_NETCONSOLE_DYNAMIC */ @@ -1527,11 +1512,13 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt, int msg_len, int release_len) { - const char *extradata = NULL; + const char *userdata = NULL; + const char *sysdata = NULL; const char *release; #ifdef CONFIG_NETCONSOLE_DYNAMIC - extradata = nt->extradata_complete; + userdata = nt->userdata; + sysdata = nt->sysdata; #endif if (release_len) { @@ -1543,10 +1530,15 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt, memcpy(nt->buf, msg, msg_len); } - if (extradata) + if (userdata) msg_len += scnprintf(&nt->buf[msg_len], - MAX_PRINT_CHUNK - msg_len, - "%s", extradata); + MAX_PRINT_CHUNK - msg_len, "%s", + userdata); + + if (sysdata) + msg_len += scnprintf(&nt->buf[msg_len], + MAX_PRINT_CHUNK - msg_len, "%s", + sysdata); send_udp(nt, nt->buf, msg_len); } @@ -1560,89 +1552,93 @@ static void append_release(char *buf) } static void send_fragmented_body(struct netconsole_target *nt, - const char *msgbody, int header_len, - int msgbody_len, int extradata_len) + const char *msgbody_ptr, int header_len, + int msgbody_len, int sysdata_len) { - int sent_extradata, preceding_bytes; - const char *extradata = NULL; - int body_len, offset = 0; + const char *userdata_ptr = NULL; + const char *sysdata_ptr = NULL; + int data_len, data_sent = 0; + int userdata_offset = 0; + int sysdata_offset = 0; + int msgbody_offset = 0; + int userdata_len = 0; #ifdef CONFIG_NETCONSOLE_DYNAMIC - extradata = nt->extradata_complete; + userdata_ptr = nt->userdata; + sysdata_ptr = nt->sysdata; + userdata_len = nt->userdata_length; #endif + if (WARN_ON_ONCE(!userdata_ptr && userdata_len != 0)) + return; - /* body_len represents the number of bytes that will be sent. This is + if (WARN_ON_ONCE(!sysdata_ptr && sysdata_len != 0)) + return; + + /* data_len represents the number of bytes that will be sent. This is * bigger than MAX_PRINT_CHUNK, thus, it will be split in multiple * packets */ - body_len = msgbody_len + extradata_len; + data_len = msgbody_len + userdata_len + sysdata_len; /* In each iteration of the while loop below, we send a packet - * containing the header and a portion of the body. The body is - * composed of two parts: msgbody and extradata. We keep track of how - * many bytes have been sent so far using the offset variable, which - * ranges from 0 to the total length of the body. + * containing the header and a portion of the data. The data is + * composed of three parts: msgbody, userdata, and sysdata. + * We keep track of how many bytes have been sent from each part using + * the *_offset variables. + * We keep track of how many bytes have been sent overall using the + * data_sent variable, which ranges from 0 to the total bytes to be + * sent. */ - while (offset < body_len) { - int this_header = header_len; - bool msgbody_written = false; - int this_offset = 0; + while (data_sent < data_len) { + int userdata_left = userdata_len - userdata_offset; + int sysdata_left = sysdata_len - sysdata_offset; + int msgbody_left = msgbody_len - msgbody_offset; + int buf_offset = 0; int this_chunk = 0; - this_header += scnprintf(nt->buf + this_header, - MAX_PRINT_CHUNK - this_header, - ",ncfrag=%d/%d;", offset, - body_len); - - /* Not all msgbody data has been written yet */ - if (offset < msgbody_len) { - this_chunk = min(msgbody_len - offset, - MAX_PRINT_CHUNK - this_header); - if (WARN_ON_ONCE(this_chunk <= 0)) - return; - memcpy(nt->buf + this_header, msgbody + offset, - this_chunk); - this_offset += this_chunk; + /* header is already populated in nt->buf, just append to it */ + buf_offset = header_len; + + buf_offset += scnprintf(nt->buf + buf_offset, + MAX_PRINT_CHUNK - buf_offset, + ",ncfrag=%d/%d;", data_sent, + data_len); + + /* append msgbody first */ + this_chunk = min(msgbody_left, MAX_PRINT_CHUNK - buf_offset); + memcpy(nt->buf + buf_offset, msgbody_ptr + msgbody_offset, + this_chunk); + msgbody_offset += this_chunk; + buf_offset += this_chunk; + data_sent += this_chunk; + + /* after msgbody, append userdata */ + if (userdata_ptr && userdata_left) { + this_chunk = min(userdata_left, + MAX_PRINT_CHUNK - buf_offset); + memcpy(nt->buf + buf_offset, + userdata_ptr + userdata_offset, this_chunk); + userdata_offset += this_chunk; + buf_offset += this_chunk; + data_sent += this_chunk; } - /* msgbody was finally written, either in the previous - * messages and/or in the current buf. Time to write - * the extradata. - */ - msgbody_written |= offset + this_offset >= msgbody_len; - - /* Msg body is fully written and there is pending extradata to - * write, append extradata in this chunk - */ - if (msgbody_written && offset + this_offset < body_len) { - /* Track how much user data was already sent. First - * time here, sent_userdata is zero - */ - sent_extradata = (offset + this_offset) - msgbody_len; - /* offset of bytes used in current buf */ - preceding_bytes = this_chunk + this_header; - - if (WARN_ON_ONCE(sent_extradata < 0)) - return; - - this_chunk = min(extradata_len - sent_extradata, - MAX_PRINT_CHUNK - preceding_bytes); - if (WARN_ON_ONCE(this_chunk < 0)) - /* this_chunk could be zero if all the previous - * message used all the buffer. This is not a - * problem, extradata will be sent in the next - * iteration - */ - return; - - memcpy(nt->buf + this_header + this_offset, - extradata + sent_extradata, - this_chunk); - this_offset += this_chunk; + /* after userdata, append sysdata */ + if (sysdata_ptr && sysdata_left) { + this_chunk = min(sysdata_left, + MAX_PRINT_CHUNK - buf_offset); + memcpy(nt->buf + buf_offset, + sysdata_ptr + sysdata_offset, this_chunk); + sysdata_offset += this_chunk; + buf_offset += this_chunk; + data_sent += this_chunk; } - send_udp(nt, nt->buf, this_header + this_offset); - offset += this_offset; + /* if all is good, send the packet out */ + if (WARN_ON_ONCE(data_sent > data_len)) + return; + + send_udp(nt, nt->buf, buf_offset); } } @@ -1650,7 +1646,7 @@ static void send_msg_fragmented(struct netconsole_target *nt, const char *msg, int msg_len, int release_len, - int extradata_len) + int sysdata_len) { int header_len, msgbody_len; const char *msgbody; @@ -1679,7 +1675,7 @@ static void send_msg_fragmented(struct netconsole_target *nt, * will be replaced */ send_fragmented_body(nt, msgbody, header_len, msgbody_len, - extradata_len); + sysdata_len); } /** @@ -1695,19 +1691,22 @@ static void send_msg_fragmented(struct netconsole_target *nt, static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { + int userdata_len = 0; int release_len = 0; - int extradata_len; - - extradata_len = prepare_extradata(nt); + int sysdata_len = 0; +#ifdef CONFIG_NETCONSOLE_DYNAMIC + sysdata_len = prepare_sysdata(nt); + userdata_len = nt->userdata_length; +#endif if (nt->release) release_len = strlen(init_utsname()->release) + 1; - if (msg_len + release_len + extradata_len <= MAX_PRINT_CHUNK) + if (msg_len + release_len + sysdata_len + userdata_len <= MAX_PRINT_CHUNK) return send_msg_no_fragmentation(nt, msg, msg_len, release_len); return send_msg_fragmented(nt, msg, msg_len, release_len, - extradata_len); + sysdata_len); } static void write_ext_msg(struct console *con, const char *msg, @@ -1912,6 +1911,9 @@ fail: static void free_param_target(struct netconsole_target *nt) { netpoll_cleanup(&nt->np); +#ifdef CONFIG_NETCONSOLE_DYNAMIC + kfree(nt->userdata); +#endif kfree(nt); } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 95f66c1f59db..2683a989873e 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -320,6 +320,8 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) &nsim_dev->max_macs); debugfs_create_bool("test1", 0600, nsim_dev->ddir, &nsim_dev->test1); + debugfs_create_u32("test2", 0600, nsim_dev->ddir, + &nsim_dev->test2); nsim_dev->take_snapshot = debugfs_create_file("take_snapshot", 0200, nsim_dev->ddir, @@ -521,8 +523,53 @@ err_out: enum nsim_devlink_param_id { NSIM_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, NSIM_DEVLINK_PARAM_ID_TEST1, + NSIM_DEVLINK_PARAM_ID_TEST2, }; +static int +nsim_devlink_param_test2_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + ctx->val.vu32 = nsim_dev->test2; + return 0; +} + +static int +nsim_devlink_param_test2_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + nsim_dev->test2 = ctx->val.vu32; + return 0; +} + +#define NSIM_DEV_TEST2_DEFAULT 1234 + +static int +nsim_devlink_param_test2_get_default(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + ctx->val.vu32 = NSIM_DEV_TEST2_DEFAULT; + return 0; +} + +static int +nsim_devlink_param_test2_reset_default(struct devlink *devlink, u32 id, + enum devlink_param_cmode cmode, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + nsim_dev->test2 = NSIM_DEV_TEST2_DEFAULT; + return 0; +} + static const struct devlink_param nsim_devlink_params[] = { DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), @@ -531,6 +578,14 @@ static const struct devlink_param nsim_devlink_params[] = { "test1", DEVLINK_PARAM_TYPE_BOOL, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), NULL, NULL, NULL), + DEVLINK_PARAM_DRIVER_WITH_DEFAULTS(NSIM_DEVLINK_PARAM_ID_TEST2, + "test2", DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + nsim_devlink_param_test2_get, + nsim_devlink_param_test2_set, + NULL, + nsim_devlink_param_test2_get_default, + nsim_devlink_param_test2_reset_default), }; static void nsim_devlink_set_params_init_values(struct nsim_dev *nsim_dev, @@ -1590,6 +1645,7 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->fw_update_flash_chunk_time_ms = NSIM_DEV_FLASH_CHUNK_TIME_MS_DEFAULT; nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; + nsim_dev->test2 = NSIM_DEV_TEST2_DEFAULT; spin_lock_init(&nsim_dev->fa_cookie_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index fa1d97885caa..6927c1962277 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -133,15 +133,21 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) if (!nsim_ipsec_tx(ns, skb)) goto out_drop_any; - peer_ns = rcu_dereference(ns->peer); - if (!peer_ns) - goto out_drop_any; + /* Check if loopback mode is enabled */ + if (dev->features & NETIF_F_LOOPBACK) { + peer_ns = ns; + peer_dev = dev; + } else { + peer_ns = rcu_dereference(ns->peer); + if (!peer_ns) + goto out_drop_any; + peer_dev = peer_ns->netdev; + } dr = nsim_do_psp(skb, ns, peer_ns, &psp_ext); if (dr) goto out_drop_free; - peer_dev = peer_ns->netdev; rxq = skb_get_queue_mapping(skb); if (rxq >= peer_dev->num_rx_queues) rxq = rxq % peer_dev->num_rx_queues; @@ -433,13 +439,8 @@ static int nsim_rcv(struct nsim_rq *rq, int budget) } /* skb might be discard at netif_receive_skb, save the len */ - skblen = skb->len; - skb_mark_napi_id(skb, &rq->napi); - ret = netif_receive_skb(skb); - if (ret == NET_RX_SUCCESS) - dev_dstats_rx_add(dev, skblen); - else - dev_dstats_rx_dropped(dev); + dev_dstats_rx_add(dev, skb->len); + napi_gro_receive(&rq->napi, skb); } nsim_start_peer_tx_queue(dev, rq); @@ -981,7 +982,8 @@ static void nsim_setup(struct net_device *dev) NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_LRO | - NETIF_F_TSO; + NETIF_F_TSO | + NETIF_F_LOOPBACK; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; dev->max_mtu = ETH_MAX_MTU; dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_HW_OFFLOAD; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index af6fcfcda8ba..d1a941e2b18f 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -331,6 +331,7 @@ struct nsim_dev { u32 fw_update_flash_chunk_time_ms; u32 max_macs; bool test1; + u32 test2; bool dont_allow_reload; bool fail_reload; struct devlink_region *dummy_region; diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c index 14298188c5f1..ecbe9dcf4f7d 100644 --- a/drivers/net/ovpn/netlink-gen.c +++ b/drivers/net/ovpn/netlink-gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ovpn.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h index 220b5b2fdd4f..b2301580770f 100644 --- a/drivers/net/ovpn/netlink-gen.h +++ b/drivers/net/ovpn/netlink-gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ovpn.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_OVPN_GEN_H #define _LINUX_OVPN_GEN_H diff --git a/drivers/net/pcs/pcs-xpcs-plat.c b/drivers/net/pcs/pcs-xpcs-plat.c index 9e1ccc319a1d..b8c48f9effbf 100644 --- a/drivers/net/pcs/pcs-xpcs-plat.c +++ b/drivers/net/pcs/pcs-xpcs-plat.c @@ -365,9 +365,6 @@ static int xpcs_plat_init_dev(struct dw_xpcs_plat *pxpcs) err_clean_data: mdiodev->dev.platform_data = NULL; - fwnode_handle_put(dev_fwnode(&mdiodev->dev)); - device_set_node(&mdiodev->dev, NULL); - mdio_device_free(mdiodev); return ret; @@ -456,5 +453,5 @@ static struct platform_driver xpcs_plat_driver = { module_platform_driver(xpcs_plat_driver); MODULE_DESCRIPTION("Synopsys DesignWare XPCS platform device driver"); -MODULE_AUTHOR("Signed-off-by: Serge Semin <fancer.lancer@gmail.com>"); +MODULE_AUTHOR("Serge Semin <fancer.lancer@gmail.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 3d1bd5aac093..9679f2b35a44 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -37,6 +37,16 @@ static const int xpcs_10gkr_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_25gbaser_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const int xpcs_xlgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -67,6 +77,40 @@ static const int xpcs_xlgmii_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_50gbaser_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseDR_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + +static const int xpcs_50gbaser2_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + +static const int xpcs_100gbasep_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const int xpcs_10gbaser_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -523,9 +567,57 @@ static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs, return speed; } -static void xpcs_resolve_pma(struct dw_xpcs *xpcs, - struct phylink_link_state *state) +static int xpcs_c45_read_pcs_speed(struct dw_xpcs *xpcs, + struct phylink_link_state *state) { + int pcs_ctrl1; + + pcs_ctrl1 = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_CTRL1); + if (pcs_ctrl1 < 0) + return pcs_ctrl1; + + switch (pcs_ctrl1 & MDIO_CTRL1_SPEEDSEL) { + case MDIO_PCS_CTRL1_SPEED25G: + state->speed = SPEED_25000; + break; + case MDIO_PCS_CTRL1_SPEED50G: + state->speed = SPEED_50000; + break; + case MDIO_PCS_CTRL1_SPEED100G: + state->speed = SPEED_100000; + break; + default: + state->speed = SPEED_UNKNOWN; + break; + } + + return 0; +} + +static int xpcs_resolve_pma(struct dw_xpcs *xpcs, + struct phylink_link_state *state) +{ + int pmd_rxdet, err = 0; + + /* The Meta Platforms FBNIC PMD will go into a training state for + * about 4 seconds when the link first comes up. During this time the + * PCS link will bounce. To avoid reporting link up too soon we include + * the PMD state provided by the driver. + */ + if (xpcs->info.pma == MP_FBNIC_XPCS_PMA_100G_ID) { + pmd_rxdet = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_PMA_RXDET); + if (pmd_rxdet < 0) { + state->link = false; + return pmd_rxdet; + } + + /* Verify Rx lanes are trained before reporting link up */ + if (!(pmd_rxdet & MDIO_PMD_RXDET_GLOBAL)) { + state->link = false; + return 0; + } + } + state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX; state->duplex = DUPLEX_FULL; @@ -536,10 +628,18 @@ static void xpcs_resolve_pma(struct dw_xpcs *xpcs, case PHY_INTERFACE_MODE_XLGMII: state->speed = xpcs_get_max_xlgmii_speed(xpcs, state); break; + case PHY_INTERFACE_MODE_100GBASEP: + case PHY_INTERFACE_MODE_LAUI: + case PHY_INTERFACE_MODE_50GBASER: + case PHY_INTERFACE_MODE_25GBASER: + err = xpcs_c45_read_pcs_speed(xpcs, state); + break; default: state->speed = SPEED_UNKNOWN; break; } + + return err; } static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported, @@ -945,10 +1045,10 @@ static int xpcs_get_state_c73(struct dw_xpcs *xpcs, phylink_resolve_c73(state); } else { - xpcs_resolve_pma(xpcs, state); + ret = xpcs_resolve_pma(xpcs, state); } - return 0; + return ret; } static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, @@ -1284,17 +1384,16 @@ static int xpcs_read_ids(struct dw_xpcs *xpcs) if (ret < 0) return ret; - id = ret; + id = ret << 16; ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID2); if (ret < 0) return ret; - /* Note the inverted dword order and masked out Model/Revision numbers - * with respect to what is done with the PCS ID... + /* For now we only record the OUI for the PMAPMD, we may want to + * add the model number at some point in the future. */ - ret = (ret >> 10) & 0x3F; - id |= ret << 16; + id |= ret & MDIO_DEVID2_OUI; /* Set the PMA ID if it hasn't been pre-initialized */ if (xpcs->info.pma == DW_XPCS_PMA_ID_NATIVE) @@ -1313,10 +1412,26 @@ static const struct dw_xpcs_compat synopsys_xpcs_compat[] = { .supported = xpcs_10gkr_features, .an_mode = DW_AN_C73, }, { + .interface = PHY_INTERFACE_MODE_25GBASER, + .supported = xpcs_25gbaser_features, + .an_mode = DW_AN_C73, + }, { .interface = PHY_INTERFACE_MODE_XLGMII, .supported = xpcs_xlgmii_features, .an_mode = DW_AN_C73, }, { + .interface = PHY_INTERFACE_MODE_50GBASER, + .supported = xpcs_50gbaser_features, + .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_LAUI, + .supported = xpcs_50gbaser2_features, + .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_100GBASEP, + .supported = xpcs_100gbasep_features, + .an_mode = DW_AN_C73, + }, { .interface = PHY_INTERFACE_MODE_10GBASER, .supported = xpcs_10gbaser_features, .an_mode = DW_10GBASER, @@ -1495,7 +1610,8 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev) xpcs_get_interfaces(xpcs, xpcs->pcs.supported_interfaces); - if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID) + if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID || + xpcs->info.pma == MP_FBNIC_XPCS_PMA_100G_ID) xpcs->pcs.poll = false; else xpcs->need_reset = true; diff --git a/drivers/net/phy/adin1100.c b/drivers/net/phy/adin1100.c index bd7a47a903ac..8f9753d4318c 100644 --- a/drivers/net/phy/adin1100.c +++ b/drivers/net/phy/adin1100.c @@ -192,16 +192,15 @@ static irqreturn_t adin_phy_handle_interrupt(struct phy_device *phydev) static int adin_set_powerdown_mode(struct phy_device *phydev, bool en) { int ret; - int val; - val = en ? ADIN_CRSM_SFT_PD_CNTRL_EN : 0; ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, - ADIN_CRSM_SFT_PD_CNTRL, val); + ADIN_CRSM_SFT_PD_CNTRL, + en ? ADIN_CRSM_SFT_PD_CNTRL_EN : 0); if (ret < 0) return ret; return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, ADIN_CRSM_STAT, ret, - (ret & ADIN_CRSM_SFT_PD_RDY) == val, + !!(ret & ADIN_CRSM_SFT_PD_RDY) == en, 1000, 30000, true); } diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c index d3501f8487d9..65d609ed69fb 100644 --- a/drivers/net/phy/bcm-phy-ptp.c +++ b/drivers/net/phy/bcm-phy-ptp.c @@ -780,9 +780,21 @@ out: kfree_skb(skb); } -static int bcm_ptp_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +static int bcm_ptp_hwtstamp_get(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg) +{ + struct bcm_ptp_private *priv = mii2priv(mii_ts); + + cfg->rx_filter = priv->hwts_rx ? HWTSTAMP_FILTER_PTP_V2_EVENT + : HWTSTAMP_FILTER_NONE; + cfg->tx_type = priv->tx_type; + + return 0; +} + +static int bcm_ptp_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct bcm_ptp_private *priv = mii2priv(mii_ts); u16 mode, ctrl; @@ -898,7 +910,8 @@ static void bcm_ptp_init(struct bcm_ptp_private *priv) priv->mii_ts.rxtstamp = bcm_ptp_rxtstamp; priv->mii_ts.txtstamp = bcm_ptp_txtstamp; - priv->mii_ts.hwtstamp = bcm_ptp_hwtstamp; + priv->mii_ts.hwtstamp_set = bcm_ptp_hwtstamp_set; + priv->mii_ts.hwtstamp_get = bcm_ptp_hwtstamp_get; priv->mii_ts.ts_info = bcm_ptp_ts_info; priv->phydev->mii_ts = &priv->mii_ts; diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 74396453f5bb..b950acc9c49b 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1176,9 +1176,21 @@ static irqreturn_t dp83640_handle_interrupt(struct phy_device *phydev) return IRQ_HANDLED; } -static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +static int dp83640_hwtstamp_get(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg) +{ + struct dp83640_private *dp83640 = + container_of(mii_ts, struct dp83640_private, mii_ts); + + cfg->rx_filter = dp83640->hwts_rx_en; + cfg->tx_type = dp83640->hwts_tx_en; + + return 0; +} + +static int dp83640_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct dp83640_private *dp83640 = container_of(mii_ts, struct dp83640_private, mii_ts); @@ -1198,7 +1210,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - dp83640->hwts_rx_en = 1; + dp83640->hwts_rx_en = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V1; cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; @@ -1206,7 +1218,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - dp83640->hwts_rx_en = 1; + dp83640->hwts_rx_en = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; dp83640->layer = PTP_CLASS_L4; dp83640->version = PTP_CLASS_V2; cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; @@ -1214,7 +1226,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - dp83640->hwts_rx_en = 1; + dp83640->hwts_rx_en = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; dp83640->layer = PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; @@ -1222,7 +1234,7 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - dp83640->hwts_rx_en = 1; + dp83640->hwts_rx_en = HWTSTAMP_FILTER_PTP_V2_EVENT; dp83640->layer = PTP_CLASS_L4 | PTP_CLASS_L2; dp83640->version = PTP_CLASS_V2; cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; @@ -1407,7 +1419,8 @@ static int dp83640_probe(struct phy_device *phydev) dp83640->phydev = phydev; dp83640->mii_ts.rxtstamp = dp83640_rxtstamp; dp83640->mii_ts.txtstamp = dp83640_txtstamp; - dp83640->mii_ts.hwtstamp = dp83640_hwtstamp; + dp83640->mii_ts.hwtstamp_set = dp83640_hwtstamp_set; + dp83640->mii_ts.hwtstamp_get = dp83640_hwtstamp_get; dp83640->mii_ts.ts_info = dp83640_ts_info; INIT_DELAYED_WORK(&dp83640->ts_work, rx_timestamp_work); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 36a0c1b7f59c..5f5de01c41e1 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -937,15 +937,15 @@ static void dp83867_link_change_notify(struct phy_device *phydev) * whenever there is a link change. */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - int val = 0; + int val; - val = phy_clear_bits(phydev, DP83867_CFG2, - DP83867_SGMII_AUTONEG_EN); - if (val < 0) - return; + val = phy_modify_changed(phydev, DP83867_CFG2, + DP83867_SGMII_AUTONEG_EN, 0); - phy_set_bits(phydev, DP83867_CFG2, - DP83867_SGMII_AUTONEG_EN); + /* Keep the in-band setting made by dp83867_config_inband() */ + if (val != 0) + phy_set_bits(phydev, DP83867_CFG2, + DP83867_SGMII_AUTONEG_EN); } } @@ -1116,6 +1116,25 @@ static int dp83867_led_polarity_set(struct phy_device *phydev, int index, DP83867_LED_POLARITY(index), polarity); } +static unsigned int dp83867_inband_caps(struct phy_device *phydev, + phy_interface_t interface) +{ + if (interface == PHY_INTERFACE_MODE_SGMII) + return LINK_INBAND_ENABLE | LINK_INBAND_DISABLE; + + return 0; +} + +static int dp83867_config_inband(struct phy_device *phydev, unsigned int modes) +{ + int val = 0; + + if (modes == LINK_INBAND_ENABLE) + val = DP83867_SGMII_AUTONEG_EN; + + return phy_modify(phydev, DP83867_CFG2, DP83867_SGMII_AUTONEG_EN, val); +} + static struct phy_driver dp83867_driver[] = { { .phy_id = DP83867_PHY_ID, @@ -1149,6 +1168,9 @@ static struct phy_driver dp83867_driver[] = { .led_hw_control_set = dp83867_led_hw_control_set, .led_hw_control_get = dp83867_led_hw_control_get, .led_polarity_set = dp83867_led_polarity_set, + + .inband_caps = dp83867_inband_caps, + .config_inband = dp83867_config_inband, }, }; module_phy_driver(dp83867_driver); diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 715f0356f895..50684271f81a 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -19,7 +19,6 @@ #include <linux/of.h> #include <linux/idr.h> #include <linux/netdevice.h> -#include <linux/linkmode.h> #include "swphy.h" @@ -125,6 +124,7 @@ static int __fixed_phy_add(int phy_addr, fp->addr = phy_addr; fp->status = *status; + fp->status.link = true; list_add_tail(&fp->node, &fmb_phys); @@ -173,40 +173,10 @@ struct phy_device *fixed_phy_register(const struct fixed_phy_status *status, return ERR_PTR(-EINVAL); } - /* propagate the fixed link values to struct phy_device */ - phy->link = 1; - phy->speed = status->speed; - phy->duplex = status->duplex; - phy->pause = status->pause; - phy->asym_pause = status->asym_pause; - of_node_get(np); phy->mdio.dev.of_node = np; phy->is_pseudo_fixed_link = true; - switch (status->speed) { - case SPEED_1000: - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phy->supported); - fallthrough; - case SPEED_100: - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phy->supported); - fallthrough; - case SPEED_10: - default: - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - phy->supported); - } - - phy_advertise_supported(phy); - ret = phy_device_register(phy); if (ret) { phy_device_free(phy); diff --git a/drivers/net/phy/mdio-private.h b/drivers/net/phy/mdio-private.h new file mode 100644 index 000000000000..8bc6d9088af1 --- /dev/null +++ b/drivers/net/phy/mdio-private.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef __MDIO_PRIVATE_H +#define __MDIO_PRIVATE_H + +/* MDIO internal helpers + */ + +int mdio_device_register_reset(struct mdio_device *mdiodev); +void mdio_device_unregister_reset(struct mdio_device *mdiodev); + +#endif /* __MDIO_PRIVATE_H */ diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 4354241137d5..afdf1ad6c0e6 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -29,37 +29,11 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <linux/unistd.h> +#include "mdio-private.h" #define CREATE_TRACE_POINTS #include <trace/events/mdio.h> -static int mdiobus_register_gpiod(struct mdio_device *mdiodev) -{ - /* Deassert the optional reset signal */ - mdiodev->reset_gpio = gpiod_get_optional(&mdiodev->dev, - "reset", GPIOD_OUT_LOW); - if (IS_ERR(mdiodev->reset_gpio)) - return PTR_ERR(mdiodev->reset_gpio); - - if (mdiodev->reset_gpio) - gpiod_set_consumer_name(mdiodev->reset_gpio, "PHY reset"); - - return 0; -} - -static int mdiobus_register_reset(struct mdio_device *mdiodev) -{ - struct reset_control *reset; - - reset = reset_control_get_optional_exclusive(&mdiodev->dev, "phy"); - if (IS_ERR(reset)) - return PTR_ERR(reset); - - mdiodev->reset_ctrl = reset; - - return 0; -} - int mdiobus_register_device(struct mdio_device *mdiodev) { int err; @@ -68,17 +42,10 @@ int mdiobus_register_device(struct mdio_device *mdiodev) return -EBUSY; if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) { - err = mdiobus_register_gpiod(mdiodev); + err = mdio_device_register_reset(mdiodev); if (err) return err; - err = mdiobus_register_reset(mdiodev); - if (err) { - gpiod_put(mdiodev->reset_gpio); - mdiodev->reset_gpio = NULL; - return err; - } - /* Assert the reset signal */ mdio_device_reset(mdiodev, 1); } @@ -94,8 +61,7 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL; - gpiod_put(mdiodev->reset_gpio); - reset_control_put(mdiodev->reset_ctrl); + mdio_device_unregister_reset(mdiodev); mdiodev->bus->mdio_map[mdiodev->addr] = NULL; @@ -373,7 +339,7 @@ EXPORT_SYMBOL_GPL(mdio_bus_class); * mdio_find_bus - Given the name of a mdiobus, find the mii_bus. * @mdio_name: The name of a mdiobus. * - * Returns a reference to the mii_bus, or NULL if none found. The + * Return: a reference to the mii_bus, or NULL if none found. The * embedded struct device will have its reference count incremented, * and this must be put_deviced'ed once the bus is finished with. */ @@ -391,7 +357,7 @@ EXPORT_SYMBOL(mdio_find_bus); * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. * @mdio_bus_np: Pointer to the mii_bus. * - * Returns a reference to the mii_bus, or NULL if none found. The + * Return: a reference to the mii_bus, or NULL if none found. The * embedded struct device will have its reference count incremented, * and this must be put once the bus is finished with. * @@ -439,6 +405,8 @@ out: * @addr: the phy address * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * Read a MDIO bus register. Caller must hold the mdio bus lock. * * NOTE: MUST NOT be called from interrupt context. @@ -471,6 +439,8 @@ EXPORT_SYMBOL(__mdiobus_read); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * Write a MDIO bus register. Caller must hold the mdio bus lock. * * NOTE: MUST NOT be called from interrupt context. @@ -504,8 +474,11 @@ EXPORT_SYMBOL(__mdiobus_write); * @mask: bit mask of bits to clear * @set: bit mask of bits to set * + * Return: 1 if the register was modified, 0 if no change was needed, + * negative on any error condition + * * Read, modify, and if any change, write the register value back to the - * device. Any error returns a negative number. + * device. * * NOTE: MUST NOT be called from interrupt context. */ @@ -535,6 +508,8 @@ EXPORT_SYMBOL_GPL(__mdiobus_modify_changed); * @devad: device address to read * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * Read a MDIO bus register. Caller must hold the mdio bus lock. * * NOTE: MUST NOT be called from interrupt context. @@ -568,6 +543,8 @@ EXPORT_SYMBOL(__mdiobus_c45_read); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * Write a MDIO bus register. Caller must hold the mdio bus lock. * * NOTE: MUST NOT be called from interrupt context. @@ -603,6 +580,9 @@ EXPORT_SYMBOL(__mdiobus_c45_write); * @mask: bit mask of bits to clear * @set: bit mask of bits to set * + * Return: 1 if the register was modified, 0 if no change was needed, + * negative on any error condition + * * Read, modify, and if any change, write the register value back to the * device. Any error returns a negative number. * @@ -633,6 +613,8 @@ static int __mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, * @addr: the phy address * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * In case of nested MDIO bus access avoid lockdep false positives by * using mutex_lock_nested(). * @@ -658,6 +640,8 @@ EXPORT_SYMBOL(mdiobus_read_nested); * @addr: the phy address * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. @@ -681,6 +665,8 @@ EXPORT_SYMBOL(mdiobus_read); * @devad: device address to read * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. @@ -704,6 +690,8 @@ EXPORT_SYMBOL(mdiobus_c45_read); * @devad: device address to read * @regnum: register number to read * + * Return: The register value if successful, negative error code on failure + * * In case of nested MDIO bus access avoid lockdep false positives by * using mutex_lock_nested(). * @@ -731,6 +719,8 @@ EXPORT_SYMBOL(mdiobus_c45_read_nested); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * In case of nested MDIO bus access avoid lockdep false positives by * using mutex_lock_nested(). * @@ -757,6 +747,8 @@ EXPORT_SYMBOL(mdiobus_write_nested); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. @@ -781,6 +773,8 @@ EXPORT_SYMBOL(mdiobus_write); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. @@ -806,6 +800,8 @@ EXPORT_SYMBOL(mdiobus_c45_write); * @regnum: register number to write * @val: value to write to @regnum * + * Return: Zero if successful, negative error code on failure + * * In case of nested MDIO bus access avoid lockdep false positives by * using mutex_lock_nested(). * @@ -834,6 +830,8 @@ EXPORT_SYMBOL(mdiobus_c45_write_nested); * @regnum: register number to write * @mask: bit mask of bits to clear * @set: bit mask of bits to set + * + * Return: 0 on success, negative on any error condition */ int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) @@ -854,6 +852,8 @@ EXPORT_SYMBOL_GPL(__mdiobus_modify); * @regnum: register number to write * @mask: bit mask of bits to clear * @set: bit mask of bits to set + * + * Return: 0 on success, negative on any error condition */ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) { @@ -876,6 +876,8 @@ EXPORT_SYMBOL_GPL(mdiobus_modify); * @regnum: register number to write * @mask: bit mask of bits to clear * @set: bit mask of bits to set + * + * Return: 0 on success, negative on any error condition */ int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum, u16 mask, u16 set) @@ -899,6 +901,9 @@ EXPORT_SYMBOL_GPL(mdiobus_c45_modify); * @regnum: register number to write * @mask: bit mask of bits to clear * @set: bit mask of bits to set + * + * Return: 1 if the register was modified, 0 if no change was needed, + * negative on any error condition */ int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) @@ -922,6 +927,9 @@ EXPORT_SYMBOL_GPL(mdiobus_modify_changed); * @regnum: register number to write * @mask: bit mask of bits to clear * @set: bit mask of bits to set + * + * Return: 1 if the register was modified, 0 if no change was needed, + * negative on any error condition */ int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad, u32 regnum, u16 mask, u16 set) @@ -942,10 +950,10 @@ EXPORT_SYMBOL_GPL(mdiobus_c45_modify_changed); * @dev: target MDIO device * @drv: given MDIO driver * - * Description: Given a MDIO device, and a MDIO driver, return 1 if - * the driver supports the device. Otherwise, return 0. This may - * require calling the devices own match function, since different classes - * of MDIO devices have different match criteria. + * Return: 1 if the driver supports the device, 0 otherwise + * + * Description: This may require calling the devices own match function, + * since different classes of MDIO devices have different match criteria. */ static int mdio_bus_match(struct device *dev, const struct device_driver *drv) { diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index f64176e0e197..6e90ed42cd98 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -22,6 +22,7 @@ #include <linux/string.h> #include <linux/unistd.h> #include <linux/property.h> +#include "mdio-private.h" void mdio_device_free(struct mdio_device *mdiodev) { @@ -77,6 +78,8 @@ EXPORT_SYMBOL(mdio_device_create); /** * mdio_device_register - Register the mdio device on the MDIO bus * @mdiodev: mdio_device structure to be added to the MDIO bus + * + * Return: Zero if successful, negative error code on failure */ int mdio_device_register(struct mdio_device *mdiodev) { @@ -118,6 +121,59 @@ void mdio_device_remove(struct mdio_device *mdiodev) } EXPORT_SYMBOL(mdio_device_remove); +/** + * mdio_device_register_reset - Read and initialize the reset properties of + * an mdio device + * @mdiodev: mdio_device structure + * + * Return: Zero if successful, negative error code on failure + */ +int mdio_device_register_reset(struct mdio_device *mdiodev) +{ + struct reset_control *reset; + + /* Deassert the optional reset signal */ + mdiodev->reset_gpio = gpiod_get_optional(&mdiodev->dev, + "reset", GPIOD_OUT_LOW); + if (IS_ERR(mdiodev->reset_gpio)) + return PTR_ERR(mdiodev->reset_gpio); + + if (mdiodev->reset_gpio) + gpiod_set_consumer_name(mdiodev->reset_gpio, "PHY reset"); + + reset = reset_control_get_optional_exclusive(&mdiodev->dev, "phy"); + if (IS_ERR(reset)) { + gpiod_put(mdiodev->reset_gpio); + mdiodev->reset_gpio = NULL; + return PTR_ERR(reset); + } + + mdiodev->reset_ctrl = reset; + + /* Read optional firmware properties */ + device_property_read_u32(&mdiodev->dev, "reset-assert-us", + &mdiodev->reset_assert_delay); + device_property_read_u32(&mdiodev->dev, "reset-deassert-us", + &mdiodev->reset_deassert_delay); + + return 0; +} + +/** + * mdio_device_unregister_reset - uninitialize the reset properties of + * an mdio device + * @mdiodev: mdio_device structure + */ +void mdio_device_unregister_reset(struct mdio_device *mdiodev) +{ + gpiod_put(mdiodev->reset_gpio); + mdiodev->reset_gpio = NULL; + reset_control_put(mdiodev->reset_ctrl); + mdiodev->reset_ctrl = NULL; + mdiodev->reset_assert_delay = 0; + mdiodev->reset_deassert_delay = 0; +} + void mdio_device_reset(struct mdio_device *mdiodev, int value) { unsigned int d; @@ -152,6 +208,8 @@ EXPORT_SYMBOL(mdio_device_reset); * * Description: Take care of setting up the mdio_device structure * and calling the driver to probe the device. + * + * Return: Zero if successful, negative error code on failure */ static int mdio_probe(struct device *dev) { @@ -202,6 +260,8 @@ static void mdio_shutdown(struct device *dev) /** * mdio_driver_register - register an mdio_driver with the MDIO layer * @drv: new mdio_driver to register + * + * Return: Zero if successful, negative error code on failure */ int mdio_driver_register(struct mdio_driver *drv) { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 57ea947369fe..05de68b9f719 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2988,6 +2988,8 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, #define LAN_EXT_PAGE_ACCESS_ADDRESS_DATA 0x17 #define LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC 0x4000 +#define LAN8814_QSGMII_TX_CONFIG 0x35 +#define LAN8814_QSGMII_TX_CONFIG_QSGMII BIT(3) #define LAN8814_QSGMII_SOFT_RESET 0x43 #define LAN8814_QSGMII_SOFT_RESET_BIT BIT(0) #define LAN8814_QSGMII_PCS1G_ANEG_CONFIG 0x13 @@ -3145,9 +3147,9 @@ static void lan8814_flush_fifo(struct phy_device *phydev, bool egress) lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_TSU_INT_STS); } -static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +static int lan8814_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct kszphy_ptp_priv *ptp_priv = container_of(mii_ts, struct kszphy_ptp_priv, mii_ts); @@ -4387,7 +4389,7 @@ static void lan8814_ptp_init(struct phy_device *phydev) ptp_priv->mii_ts.rxtstamp = lan8814_rxtstamp; ptp_priv->mii_ts.txtstamp = lan8814_txtstamp; - ptp_priv->mii_ts.hwtstamp = lan8814_hwtstamp; + ptp_priv->mii_ts.hwtstamp_set = lan8814_hwtstamp_set; ptp_priv->mii_ts.ts_info = lan8814_ts_info; phydev->mii_ts = &ptp_priv->mii_ts; @@ -4501,12 +4503,24 @@ static void lan8814_setup_led(struct phy_device *phydev, int val) static int lan8814_config_init(struct phy_device *phydev) { struct kszphy_priv *lan8814 = phydev->priv; + int ret; - /* Disable ANEG with QSGMII PCS Host side */ - lanphy_modify_page_reg(phydev, LAN8814_PAGE_PORT_REGS, - LAN8814_QSGMII_PCS1G_ANEG_CONFIG, - LAN8814_QSGMII_PCS1G_ANEG_CONFIG_ANEG_ENA, - 0); + /* Based on the interface type select how the advertise ability is + * encoded, to set as SGMII or as USGMII. + */ + if (phydev->interface == PHY_INTERFACE_MODE_QSGMII) + ret = lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_TX_CONFIG, + LAN8814_QSGMII_TX_CONFIG_QSGMII, + LAN8814_QSGMII_TX_CONFIG_QSGMII); + else + ret = lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_TX_CONFIG, + LAN8814_QSGMII_TX_CONFIG_QSGMII, + 0); + + if (ret < 0) + return ret; /* MDI-X setting for swap A,B transmit */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8814_ALIGN_SWAP, @@ -5028,9 +5042,9 @@ static void lan8841_ptp_enable_processing(struct kszphy_ptp_priv *ptp_priv, #define LAN8841_PTP_TX_TIMESTAMP_EN 443 #define LAN8841_PTP_TX_MOD 445 -static int lan8841_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +static int lan8841_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct kszphy_ptp_priv *ptp_priv = container_of(mii_ts, struct kszphy_ptp_priv, mii_ts); struct phy_device *phydev = ptp_priv->phydev; @@ -5910,7 +5924,7 @@ static int lan8841_probe(struct phy_device *phydev) ptp_priv->mii_ts.rxtstamp = lan8841_rxtstamp; ptp_priv->mii_ts.txtstamp = lan8814_txtstamp; - ptp_priv->mii_ts.hwtstamp = lan8841_hwtstamp; + ptp_priv->mii_ts.hwtstamp_set = lan8841_hwtstamp_set; ptp_priv->mii_ts.ts_info = lan8841_ts_info; phydev->mii_ts = &ptp_priv->mii_ts; @@ -6640,6 +6654,8 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = kszphy_resume, .config_intr = lan8814_config_intr, + .inband_caps = lan8842_inband_caps, + .config_inband = lan8842_config_inband, .handle_interrupt = lan8814_handle_interrupt, .cable_test_start = lan8814_cable_test_start, .cable_test_get_status = ksz886x_cable_test_get_status, diff --git a/drivers/net/phy/microchip_rds_ptp.c b/drivers/net/phy/microchip_rds_ptp.c index e6514ce04c29..4c6326b0ceaf 100644 --- a/drivers/net/phy/microchip_rds_ptp.c +++ b/drivers/net/phy/microchip_rds_ptp.c @@ -476,9 +476,9 @@ static bool mchp_rds_ptp_rxtstamp(struct mii_timestamper *mii_ts, return true; } -static int mchp_rds_ptp_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +static int mchp_rds_ptp_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct mchp_rds_ptp_clock *clock = container_of(mii_ts, struct mchp_rds_ptp_clock, @@ -1281,7 +1281,7 @@ struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd, clock->mii_ts.rxtstamp = mchp_rds_ptp_rxtstamp; clock->mii_ts.txtstamp = mchp_rds_ptp_txtstamp; - clock->mii_ts.hwtstamp = mchp_rds_ptp_hwtstamp; + clock->mii_ts.hwtstamp_set = mchp_rds_ptp_hwtstamp_set; clock->mii_ts.ts_info = mchp_rds_ptp_ts_info; phydev->mii_ts = &clock->mii_ts; diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index 2eef5956b9cc..65c9d7bd9315 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -85,6 +85,10 @@ enum rgmii_clock_delay { #define LED_MODE_SEL_MASK(x) (GENMASK(3, 0) << LED_MODE_SEL_POS(x)) #define LED_MODE_SEL(x, mode) (((mode) << LED_MODE_SEL_POS(x)) & LED_MODE_SEL_MASK(x)) +#define MSCC_PHY_LED_BEHAVIOR 30 +#define LED_COMBINE_DIS_MASK(x) BIT(x) +#define LED_COMBINE_DIS(x, dis) (((dis) ? 1 : 0) << (x)) + #define MSCC_EXT_PAGE_CSR_CNTL_17 17 #define MSCC_EXT_PAGE_CSR_CNTL_18 18 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 8678ebf89cca..2b9fb8a675a6 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -22,6 +22,24 @@ #include "mscc_serdes.h" #include "mscc.h" +struct vsc85xx_probe_config { + const struct vsc85xx_hw_stat *hw_stats; + size_t shared_size; + size_t nstats; + u16 supp_led_modes; + u8 nleds; + bool check_rate_magic; + bool use_package; + bool has_ptp; +}; + +static const u32 vsc85xx_default_led_modes_4[] = { + VSC8531_LINK_1000_ACTIVITY, + VSC8531_LINK_100_ACTIVITY, + VSC8531_LINK_ACTIVITY, + VSC8531_DUPLEX_COLLISION +}; + static const struct vsc85xx_hw_stat vsc85xx_hw_stats[] = { { .string = "phy_receive_errors", @@ -177,17 +195,19 @@ static int vsc85xx_led_cntl_set(struct phy_device *phydev, u8 led_num, u8 mode) { - int rc; - u16 reg_val; + u16 mask = LED_MODE_SEL_MASK(led_num); + u16 val = LED_MODE_SEL(led_num, mode); - mutex_lock(&phydev->lock); - reg_val = phy_read(phydev, MSCC_PHY_LED_MODE_SEL); - reg_val &= ~LED_MODE_SEL_MASK(led_num); - reg_val |= LED_MODE_SEL(led_num, (u16)mode); - rc = phy_write(phydev, MSCC_PHY_LED_MODE_SEL, reg_val); - mutex_unlock(&phydev->lock); + return phy_modify(phydev, MSCC_PHY_LED_MODE_SEL, mask, val); +} - return rc; +static int vsc85xx_led_combine_disable_set(struct phy_device *phydev, + u8 led_num, bool combine_disable) +{ + u16 val = LED_COMBINE_DIS(led_num, combine_disable); + u16 mask = LED_COMBINE_DIS_MASK(led_num); + + return phy_modify(phydev, MSCC_PHY_LED_BEHAVIOR, mask, val); } static int vsc85xx_mdix_get(struct phy_device *phydev, u8 *mdix) @@ -443,7 +463,7 @@ static int vsc85xx_dt_led_mode_get(struct phy_device *phydev, #endif /* CONFIG_OF_MDIO */ static int vsc85xx_dt_led_modes_get(struct phy_device *phydev, - u32 *default_mode) + const u32 *default_mode) { struct vsc8531_private *priv = phydev->priv; char led_dt_prop[28]; @@ -2218,12 +2238,13 @@ static int vsc85xx_config_inband(struct phy_device *phydev, unsigned int modes) reg_val); } -static int vsc8514_probe(struct phy_device *phydev) +static int vsc85xx_probe_common(struct phy_device *phydev, + const struct vsc85xx_probe_config *cfg, + const u32 *default_led_mode) { struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; + struct device_node *np; + int ret; vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); if (!vsc8531) @@ -2231,119 +2252,291 @@ static int vsc8514_probe(struct phy_device *phydev) phydev->priv = vsc8531; - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, - vsc8531->base_addr, 0); + /* Check rate magic if needed (only for non-package PHYs) */ + if (cfg->check_rate_magic) { + ret = vsc85xx_edge_rate_magic_get(phydev); + if (ret < 0) + return ret; + + vsc8531->rate_magic = ret; + } + + /* Set up package if needed */ + if (cfg->use_package) { + vsc8584_get_base_addr(phydev); + ret = devm_phy_package_join(&phydev->mdio.dev, phydev, + vsc8531->base_addr, + cfg->shared_size); + if (ret) + return ret; + } - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; - vsc8531->hw_stats = vsc85xx_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); + /* Configure LED settings */ + vsc8531->nleds = cfg->nleds; + vsc8531->supp_led_modes = cfg->supp_led_modes; + + /* Configure hardware stats */ + vsc8531->hw_stats = cfg->hw_stats; + vsc8531->nstats = cfg->nstats; vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + /* PTP setup for VSC8584 */ + if (cfg->has_ptp) { + if (phy_package_probe_once(phydev)) { + ret = vsc8584_ptp_probe_once(phydev); + if (ret) + return ret; + } + + ret = vsc8584_ptp_probe(phydev); + if (ret) + return ret; + } + + /* + * Check for LED configuration in device tree if available + * or fall back to default `vsc8531,led-x-mode` DT properties. + */ + np = of_get_child_by_name(phydev->mdio.dev.of_node, "leds"); + if (np) { + of_node_put(np); + + /* Force to defaults */ + for (unsigned int i = 0; i < vsc8531->nleds; i++) + vsc8531->leds_mode[i] = default_led_mode[i]; + + return 0; + } + + /* Parse LED modes from device tree */ + return vsc85xx_dt_led_modes_get(phydev, default_led_mode); } -static int vsc8574_probe(struct phy_device *phydev) +static int vsc85xx_led_brightness_set(struct phy_device *phydev, + u8 index, enum led_brightness value) { - struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; + struct vsc8531_private *vsc8531 = phydev->priv; - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; + if (index >= vsc8531->nleds) + return -EINVAL; - phydev->priv = vsc8531; + return vsc85xx_led_cntl_set(phydev, index, value == LED_OFF ? + VSC8531_FORCE_LED_OFF : VSC8531_FORCE_LED_ON); +} - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, - vsc8531->base_addr, 0); +static int vsc85xx_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + static const unsigned long supported = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK) | + BIT(TRIGGER_NETDEV_RX) | + BIT(TRIGGER_NETDEV_TX); + struct vsc8531_private *vsc8531 = phydev->priv; - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; - vsc8531->hw_stats = vsc8584_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; + if (index >= vsc8531->nleds) + return -EINVAL; + + if (rules & ~supported) + return -EOPNOTSUPP; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + return 0; } -static int vsc8584_probe(struct phy_device *phydev) +static int vsc85xx_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) { - struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; - int ret; + struct vsc8531_private *vsc8531 = phydev->priv; + u8 mode, behavior; + int rc; - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; + if (index >= vsc8531->nleds) + return -EINVAL; - phydev->priv = vsc8531; + rc = phy_read(phydev, MSCC_PHY_LED_MODE_SEL); + if (rc < 0) + return rc; + mode = (rc & LED_MODE_SEL_MASK(index)) >> LED_MODE_SEL_POS(index); + + rc = phy_read(phydev, MSCC_PHY_LED_BEHAVIOR); + if (rc < 0) + return rc; + behavior = (rc & LED_COMBINE_DIS_MASK(index)) >> index; - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, vsc8531->base_addr, - sizeof(struct vsc85xx_shared_private)); + switch (mode) { + case VSC8531_LINK_ACTIVITY: + case VSC8531_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK); + break; - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; - vsc8531->hw_stats = vsc8584_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; + case VSC8531_LINK_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK); + break; - if (phy_package_probe_once(phydev)) { - ret = vsc8584_ptp_probe_once(phydev); - if (ret) - return ret; + case VSC8531_LINK_100_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_100_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_100_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + default: + *rules = 0; + break; } - ret = vsc8584_ptp_probe(phydev); - if (ret) + if (!behavior && *rules) + *rules |= BIT(TRIGGER_NETDEV_RX) | BIT(TRIGGER_NETDEV_TX); + + return 0; +} + +static int vsc85xx_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + struct vsc8531_private *vsc8531 = phydev->priv; + u8 mode = VSC8531_FORCE_LED_ON; + bool combine_disable = false; + bool has_rx, has_tx; + int ret; + + if (index >= vsc8531->nleds) + return -EINVAL; + + if (rules & BIT(TRIGGER_NETDEV_LINK)) + mode = VSC8531_LINK_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10)) + mode = VSC8531_LINK_10_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_100)) + mode = VSC8531_LINK_100_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_100) && + rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_100_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10) && + rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_10_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10) && + rules & BIT(TRIGGER_NETDEV_LINK_100)) + mode = VSC8531_LINK_10_100_ACTIVITY; + + /* + * The VSC85xx PHYs provides an option to control LED behavior. By + * default, the LEDx combine function is enabled, meaning the LED + * will be on when there is link/activity or duplex/collision. If + * the combine function is disabled, the LED will be on only for + * link or duplex. + * + * To control this behavior, we check the selected rules. If both + * RX and TX activity are not selected, the LED combine function + * is disabled; otherwise, it remains enabled. + */ + has_rx = !!(rules & BIT(TRIGGER_NETDEV_RX)); + has_tx = !!(rules & BIT(TRIGGER_NETDEV_TX)); + if (!has_rx && !has_tx) + combine_disable = true; + + ret = vsc85xx_led_combine_disable_set(phydev, index, combine_disable); + if (ret < 0) return ret; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + return vsc85xx_led_cntl_set(phydev, index, mode); } -static int vsc85xx_probe(struct phy_device *phydev) +static int vsc8514_probe(struct phy_device *phydev) { - struct vsc8531_private *vsc8531; - int rate_magic; - u32 default_mode[2] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY}; + static const struct vsc85xx_probe_config vsc8514_cfg = { + .nleds = 4, + .supp_led_modes = VSC85XX_SUPP_LED_MODES, + .hw_stats = vsc85xx_hw_stats, + .nstats = ARRAY_SIZE(vsc85xx_hw_stats), + .use_package = true, + .shared_size = 0, + .has_ptp = false, + .check_rate_magic = false, + }; - rate_magic = vsc85xx_edge_rate_magic_get(phydev); - if (rate_magic < 0) - return rate_magic; + return vsc85xx_probe_common(phydev, &vsc8514_cfg, vsc85xx_default_led_modes_4); +} - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; +static int vsc8574_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc8574_cfg = { + .nleds = 4, + .supp_led_modes = VSC8584_SUPP_LED_MODES, + .hw_stats = vsc8584_hw_stats, + .nstats = ARRAY_SIZE(vsc8584_hw_stats), + .use_package = true, + .shared_size = 0, + .has_ptp = false, + .check_rate_magic = false, + }; - phydev->priv = vsc8531; + return vsc85xx_probe_common(phydev, &vsc8574_cfg, vsc85xx_default_led_modes_4); +} - vsc8531->rate_magic = rate_magic; - vsc8531->nleds = 2; - vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; - vsc8531->hw_stats = vsc85xx_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; +static int vsc8584_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc8584_cfg = { + .nleds = 4, + .supp_led_modes = VSC8584_SUPP_LED_MODES, + .hw_stats = vsc8584_hw_stats, + .nstats = ARRAY_SIZE(vsc8584_hw_stats), + .use_package = true, + .shared_size = sizeof(struct vsc85xx_shared_private), + .has_ptp = true, + .check_rate_magic = false, + }; + + return vsc85xx_probe_common(phydev, &vsc8584_cfg, vsc85xx_default_led_modes_4); +} + +static int vsc85xx_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc85xx_cfg = { + .nleds = 2, + .supp_led_modes = VSC85XX_SUPP_LED_MODES, + .hw_stats = vsc85xx_hw_stats, + .nstats = ARRAY_SIZE(vsc85xx_hw_stats), + .use_package = false, + .has_ptp = false, + .check_rate_magic = true, + }; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + return vsc85xx_probe_common(phydev, &vsc85xx_cfg, vsc85xx_default_led_modes_4); } static void vsc85xx_remove(struct phy_device *phydev) @@ -2376,6 +2569,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8502, @@ -2400,6 +2597,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8504, @@ -2427,6 +2628,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8514, @@ -2452,6 +2657,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8530, @@ -2476,6 +2685,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8531, @@ -2500,6 +2713,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8540, @@ -2524,6 +2741,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8541, @@ -2548,6 +2769,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8552, @@ -2574,6 +2799,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { PHY_ID_MATCH_EXACT(PHY_ID_VSC856X), @@ -2597,6 +2826,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8572, @@ -2625,6 +2858,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8574, @@ -2653,6 +2890,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { PHY_ID_MATCH_EXACT(PHY_ID_VSC8575), @@ -2678,6 +2919,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { PHY_ID_MATCH_EXACT(PHY_ID_VSC8582), @@ -2703,6 +2948,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { PHY_ID_MATCH_EXACT(PHY_ID_VSC8584), @@ -2729,6 +2978,10 @@ static struct phy_driver vsc85xx_driver[] = { .link_change_notify = &vsc85xx_link_change_notify, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, } }; diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index d692df7d975c..4865eac74b0e 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1051,9 +1051,21 @@ static void vsc85xx_ts_reset_fifo(struct phy_device *phydev) val); } -static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +static int vsc85xx_hwtstamp_get(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg) +{ + struct vsc8531_private *vsc8531 = + container_of(mii_ts, struct vsc8531_private, mii_ts); + + cfg->tx_type = vsc8531->ptp->tx_type; + cfg->rx_filter = vsc8531->ptp->rx_filter; + + return 0; +} + +static int vsc85xx_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct vsc8531_private *vsc8531 = container_of(mii_ts, struct vsc8531_private, mii_ts); @@ -1611,7 +1623,8 @@ int vsc8584_ptp_probe(struct phy_device *phydev) vsc8531->mii_ts.rxtstamp = vsc85xx_rxtstamp; vsc8531->mii_ts.txtstamp = vsc85xx_txtstamp; - vsc8531->mii_ts.hwtstamp = vsc85xx_hwtstamp; + vsc8531->mii_ts.hwtstamp_set = vsc85xx_hwtstamp_set; + vsc8531->mii_ts.hwtstamp_get = vsc85xx_hwtstamp_get; vsc8531->mii_ts.ts_info = vsc85xx_ts_info; phydev->mii_ts = &vsc8531->mii_ts; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 0c8dc16ee7bd..8e2fd6b942b6 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -30,6 +30,9 @@ #define PHY_ID_GPY241B 0x67C9DE40 #define PHY_ID_GPY241BM 0x67C9DE80 #define PHY_ID_GPY245B 0x67C9DEC0 +#define PHY_ID_MXL86211C 0xC1335400 +#define PHY_ID_MXL86252 0xC1335520 +#define PHY_ID_MXL86282 0xC1335500 #define PHY_CTL1 0x13 #define PHY_CTL1_MDICD BIT(3) @@ -199,6 +202,29 @@ static int gpy_hwmon_read(struct device *dev, return 0; } +static int mxl862x2_hwmon_read(struct device *dev, + enum hwmon_sensor_types type, + u32 attr, int channel, long *value) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + long tmp; + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_TEMP_STA); + if (ret < 0) + return ret; + if (!ret) + return -ENODATA; + + tmp = (s16)ret; + tmp *= 78125; + tmp /= 10000; + + *value = tmp; + + return 0; +} + static umode_t gpy_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) @@ -216,19 +242,35 @@ static const struct hwmon_ops gpy_hwmon_hwmon_ops = { .read = gpy_hwmon_read, }; +static const struct hwmon_ops mxl862x2_hwmon_hwmon_ops = { + .is_visible = gpy_hwmon_is_visible, + .read = mxl862x2_hwmon_read, +}; + static const struct hwmon_chip_info gpy_hwmon_chip_info = { .ops = &gpy_hwmon_hwmon_ops, .info = gpy_hwmon_info, }; +static const struct hwmon_chip_info mxl862x2_hwmon_chip_info = { + .ops = &mxl862x2_hwmon_hwmon_ops, + .info = gpy_hwmon_info, +}; + static int gpy_hwmon_register(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; + const struct hwmon_chip_info *info; struct device *hwmon_dev; + if (phy_id_compare_model(phydev->phy_id, PHY_ID_MXL86252) || + phy_id_compare_model(phydev->phy_id, PHY_ID_MXL86282)) + info = &mxl862x2_hwmon_chip_info; + else + info = &gpy_hwmon_chip_info; + hwmon_dev = devm_hwmon_device_register_with_info(dev, NULL, phydev, - &gpy_hwmon_chip_info, - NULL); + info, NULL); return PTR_ERR_OR_ZERO(hwmon_dev); } @@ -540,7 +582,7 @@ static int gpy_update_interface(struct phy_device *phydev) /* Interface mode is fixed for USXGMII and integrated PHY */ if (phydev->interface == PHY_INTERFACE_MODE_USXGMII || phydev->interface == PHY_INTERFACE_MODE_INTERNAL) - return -EINVAL; + return 0; /* Automatically switch SERDES interface between SGMII and 2500-BaseX * according to speed. Disable ANEG in 2500-BaseX mode. @@ -578,13 +620,7 @@ static int gpy_update_interface(struct phy_device *phydev) break; } - if (phydev->speed == SPEED_2500 || phydev->speed == SPEED_1000) { - ret = genphy_read_master_slave(phydev); - if (ret < 0) - return ret; - } - - return gpy_update_mdix(phydev); + return 0; } static int gpy_read_status(struct phy_device *phydev) @@ -639,6 +675,16 @@ static int gpy_read_status(struct phy_device *phydev) ret = gpy_update_interface(phydev); if (ret < 0) return ret; + + if (phydev->speed == SPEED_2500 || phydev->speed == SPEED_1000) { + ret = genphy_read_master_slave(phydev); + if (ret < 0) + return ret; + } + + ret = gpy_update_mdix(phydev); + if (ret < 0) + return ret; } return 0; @@ -1268,6 +1314,72 @@ static struct phy_driver gpy_drivers[] = { .get_wol = gpy_get_wol, .set_loopback = gpy_loopback, }, + { + PHY_ID_MATCH_MODEL(PHY_ID_MXL86211C), + .name = "Maxlinear Ethernet MxL86211C", + .get_features = genphy_c45_pma_read_abilities, + .config_init = gpy_config_init, + .probe = gpy_probe, + .suspend = genphy_suspend, + .resume = genphy_resume, + .config_aneg = gpy_config_aneg, + .aneg_done = genphy_c45_aneg_done, + .read_status = gpy_read_status, + .config_intr = gpy_config_intr, + .handle_interrupt = gpy_handle_interrupt, + .set_wol = gpy_set_wol, + .get_wol = gpy_get_wol, + .set_loopback = gpy_loopback, + .led_brightness_set = gpy_led_brightness_set, + .led_hw_is_supported = gpy_led_hw_is_supported, + .led_hw_control_get = gpy_led_hw_control_get, + .led_hw_control_set = gpy_led_hw_control_set, + .led_polarity_set = gpy_led_polarity_set, + }, + { + PHY_ID_MATCH_MODEL(PHY_ID_MXL86252), + .name = "MaxLinear Ethernet MxL86252", + .get_features = genphy_c45_pma_read_abilities, + .config_init = gpy_config_init, + .probe = gpy_probe, + .suspend = genphy_suspend, + .resume = genphy_resume, + .config_aneg = gpy_config_aneg, + .aneg_done = genphy_c45_aneg_done, + .read_status = gpy_read_status, + .config_intr = gpy_config_intr, + .handle_interrupt = gpy_handle_interrupt, + .set_wol = gpy_set_wol, + .get_wol = gpy_get_wol, + .set_loopback = gpy_loopback, + .led_brightness_set = gpy_led_brightness_set, + .led_hw_is_supported = gpy_led_hw_is_supported, + .led_hw_control_get = gpy_led_hw_control_get, + .led_hw_control_set = gpy_led_hw_control_set, + .led_polarity_set = gpy_led_polarity_set, + }, + { + PHY_ID_MATCH_MODEL(PHY_ID_MXL86282), + .name = "MaxLinear Ethernet MxL86282", + .get_features = genphy_c45_pma_read_abilities, + .config_init = gpy_config_init, + .probe = gpy_probe, + .suspend = genphy_suspend, + .resume = genphy_resume, + .config_aneg = gpy_config_aneg, + .aneg_done = genphy_c45_aneg_done, + .read_status = gpy_read_status, + .config_intr = gpy_config_intr, + .handle_interrupt = gpy_handle_interrupt, + .set_wol = gpy_set_wol, + .get_wol = gpy_get_wol, + .set_loopback = gpy_loopback, + .led_brightness_set = gpy_led_brightness_set, + .led_hw_is_supported = gpy_led_hw_is_supported, + .led_hw_control_get = gpy_led_hw_control_get, + .led_hw_control_set = gpy_led_hw_control_set, + .led_polarity_set = gpy_led_polarity_set, + }, }; module_phy_driver(gpy_drivers); @@ -1284,6 +1396,9 @@ static const struct mdio_device_id __maybe_unused gpy_tbl[] = { {PHY_ID_MATCH_MODEL(PHY_ID_GPY241B)}, {PHY_ID_MATCH_MODEL(PHY_ID_GPY241BM)}, {PHY_ID_MATCH_MODEL(PHY_ID_GPY245B)}, + {PHY_ID_MATCH_MODEL(PHY_ID_MXL86211C)}, + {PHY_ID_MATCH_MODEL(PHY_ID_MXL86252)}, + {PHY_ID_MATCH_MODEL(PHY_ID_MXL86282)}, { } }; MODULE_DEVICE_TABLE(mdio, gpy_tbl); diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 87adb6508017..f526528d2e32 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1012,9 +1012,22 @@ static bool nxp_c45_rxtstamp(struct mii_timestamper *mii_ts, return true; } -static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +static int nxp_c45_hwtstamp_get(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg) +{ + struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, + mii_ts); + + cfg->tx_type = priv->hwts_tx; + cfg->rx_filter = priv->hwts_rx ? HWTSTAMP_FILTER_PTP_V2_L2_EVENT + : HWTSTAMP_FILTER_NONE; + + return 0; +} + +static int nxp_c45_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, mii_ts); @@ -1749,7 +1762,8 @@ static int nxp_c45_probe(struct phy_device *phydev) IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) { priv->mii_ts.rxtstamp = nxp_c45_rxtstamp; priv->mii_ts.txtstamp = nxp_c45_txtstamp; - priv->mii_ts.hwtstamp = nxp_c45_hwtstamp; + priv->mii_ts.hwtstamp_set = nxp_c45_hwtstamp_set; + priv->mii_ts.hwtstamp_get = nxp_c45_hwtstamp_get; priv->mii_ts.ts_info = nxp_c45_ts_info; phydev->mii_ts = &priv->mii_ts; ret = nxp_c45_init_ptp_clock(priv); diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index e8e5be4684ab..f5e23b53994f 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -148,12 +148,12 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) ctrl2 |= MDIO_PMA_CTRL2_1000BT; break; case SPEED_2500: - ctrl1 |= MDIO_CTRL1_SPEED2_5G; + ctrl1 |= MDIO_PMA_CTRL1_SPEED2_5G; /* Assume 2.5Gbase-T */ ctrl2 |= MDIO_PMA_CTRL2_2_5GBT; break; case SPEED_5000: - ctrl1 |= MDIO_CTRL1_SPEED5G; + ctrl1 |= MDIO_PMA_CTRL1_SPEED5G; /* Assume 5Gbase-T */ ctrl2 |= MDIO_PMA_CTRL2_5GBT; break; @@ -618,10 +618,10 @@ int genphy_c45_read_pma(struct phy_device *phydev) case MDIO_PMA_CTRL1_SPEED1000: phydev->speed = SPEED_1000; break; - case MDIO_CTRL1_SPEED2_5G: + case MDIO_PMA_CTRL1_SPEED2_5G: phydev->speed = SPEED_2500; break; - case MDIO_CTRL1_SPEED5G: + case MDIO_PMA_CTRL1_SPEED5G: phydev->speed = SPEED_5000; break; case MDIO_CTRL1_SPEED10G: diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h index b7f0c6a3037a..4951a39f3828 100644 --- a/drivers/net/phy/phy-caps.h +++ b/drivers/net/phy/phy-caps.h @@ -29,6 +29,7 @@ enum { LINK_CAPA_200000FD, LINK_CAPA_400000FD, LINK_CAPA_800000FD, + LINK_CAPA_1600000FD, __LINK_CAPA_MAX, }; diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 605ca20ae192..277c034bc32f 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -17,7 +17,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 121, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 125, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -55,6 +55,8 @@ const char *phy_speed_to_str(int speed) return "400Gbps"; case SPEED_800000: return "800Gbps"; + case SPEED_1600000: + return "1600Gbps"; case SPEED_UNKNOWN: return "Unknown"; default: @@ -102,6 +104,49 @@ const char *phy_rate_matching_to_str(int rate_matching) EXPORT_SYMBOL_GPL(phy_rate_matching_to_str); /** + * phy_fix_phy_mode_for_mac_delays - Convenience function for fixing PHY + * mode based on whether mac adds internal delay + * + * @interface: The current interface mode of the port + * @mac_txid: True if the mac adds internal tx delay + * @mac_rxid: True if the mac adds internal rx delay + * + * Return: fixed PHY mode, or PHY_INTERFACE_MODE_NA if the interface can + * not apply the internal delay + */ +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid) +{ + if (!phy_interface_mode_is_rgmii(interface)) + return interface; + + if (mac_txid && mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_txid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_RXID; + if (interface == PHY_INTERFACE_MODE_RGMII_TXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_TXID; + if (interface == PHY_INTERFACE_MODE_RGMII_RXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + return interface; +} +EXPORT_SYMBOL_GPL(phy_fix_phy_mode_for_mac_delays); + +/** * phy_interface_num_ports - Return the number of links that can be carried by * a given MAC-PHY physical link. Returns 0 if this is * unknown, the number of links else. diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 02da4a203ddd..13dd1691886d 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -405,12 +405,14 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) return 0; case SIOCSHWTSTAMP: - if (phydev->mii_ts && phydev->mii_ts->hwtstamp) { + if (phydev->mii_ts && phydev->mii_ts->hwtstamp_set) { if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; hwtstamp_config_to_kernel(&kernel_cfg, &cfg); - ret = phydev->mii_ts->hwtstamp(phydev->mii_ts, &kernel_cfg, &extack); + ret = phydev->mii_ts->hwtstamp_set(phydev->mii_ts, + &kernel_cfg, + &extack); if (ret) return ret; @@ -476,6 +478,9 @@ int __phy_hwtstamp_get(struct phy_device *phydev, if (!phydev) return -ENODEV; + if (phydev->mii_ts && phydev->mii_ts->hwtstamp_get) + return phydev->mii_ts->hwtstamp_get(phydev->mii_ts, config); + return -EOPNOTSUPP; } @@ -493,8 +498,9 @@ int __phy_hwtstamp_set(struct phy_device *phydev, if (!phydev) return -ENODEV; - if (phydev->mii_ts && phydev->mii_ts->hwtstamp) - return phydev->mii_ts->hwtstamp(phydev->mii_ts, config, extack); + if (phydev->mii_ts && phydev->mii_ts->hwtstamp_set) + return phydev->mii_ts->hwtstamp_set(phydev->mii_ts, config, + extack); return -EOPNOTSUPP; } diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c index 23c808b59b6f..3a05982b39bf 100644 --- a/drivers/net/phy/phy_caps.c +++ b/drivers/net/phy/phy_caps.c @@ -25,6 +25,7 @@ static struct link_capabilities link_caps[__LINK_CAPA_MAX] __ro_after_init = { { SPEED_200000, DUPLEX_FULL, {0} }, /* LINK_CAPA_200000FD */ { SPEED_400000, DUPLEX_FULL, {0} }, /* LINK_CAPA_400000FD */ { SPEED_800000, DUPLEX_FULL, {0} }, /* LINK_CAPA_800000FD */ + { SPEED_1600000, DUPLEX_FULL, {0} }, /* LINK_CAPA_1600000FD */ }; static int speed_duplex_to_capa(int speed, unsigned int duplex) @@ -52,6 +53,7 @@ static int speed_duplex_to_capa(int speed, unsigned int duplex) case SPEED_200000: return LINK_CAPA_200000FD; case SPEED_400000: return LINK_CAPA_400000FD; case SPEED_800000: return LINK_CAPA_800000FD; + case SPEED_1600000: return LINK_CAPA_1600000FD; } return -EINVAL; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 6e1243bf68aa..43d8380aaefb 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -640,6 +640,9 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, static void phylink_fill_fixedlink_supported(unsigned long *supported) { + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, supported); diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index 417f9a88aab6..67ecf3d4af2b 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -90,6 +90,14 @@ #define RTL8211F_LEDCR_MASK GENMASK(4, 0) #define RTL8211F_LEDCR_SHIFT 5 +/* RTL8211F(D)(I)-VD-CG CLKOUT configuration is specified via magic values + * to undocumented register pages. The names here do not reflect the datasheet. + * Unlike other PHY models, CLKOUT configuration does not go through PHYCR2. + */ +#define RTL8211FVD_CLKOUT_PAGE 0xd05 +#define RTL8211FVD_CLKOUT_REG 0x11 +#define RTL8211FVD_CLKOUT_EN BIT(8) + /* RTL8211F RGMII configuration */ #define RTL8211F_RGMII_PAGE 0xd08 @@ -193,9 +201,8 @@ MODULE_AUTHOR("Johnson Leung"); MODULE_LICENSE("GPL"); struct rtl821x_priv { - u16 phycr1; - u16 phycr2; - bool has_phycr2; + bool enable_aldps; + bool disable_clk_out; struct clk *clk; /* rtl8211f */ u16 iner; @@ -245,8 +252,6 @@ static int rtl821x_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; struct rtl821x_priv *priv; - u32 phy_id = phydev->drv->phy_id; - int ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -257,24 +262,10 @@ static int rtl821x_probe(struct phy_device *phydev) return dev_err_probe(dev, PTR_ERR(priv->clk), "failed to get phy clock\n"); - ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1); - if (ret < 0) - return ret; - - priv->phycr1 = ret & (RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF); - if (of_property_read_bool(dev->of_node, "realtek,aldps-enable")) - priv->phycr1 |= RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF; - - priv->has_phycr2 = !(phy_id == RTL_8211FVD_PHYID); - if (priv->has_phycr2) { - ret = phy_read_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2); - if (ret < 0) - return ret; - - priv->phycr2 = ret & RTL8211F_CLKOUT_EN; - if (of_property_read_bool(dev->of_node, "realtek,clkout-disable")) - priv->phycr2 &= ~RTL8211F_CLKOUT_EN; - } + priv->enable_aldps = of_property_read_bool(dev->of_node, + "realtek,aldps-enable"); + priv->disable_clk_out = of_property_read_bool(dev->of_node, + "realtek,clkout-disable"); phydev->priv = priv; @@ -587,22 +578,11 @@ static int rtl8211c_config_init(struct phy_device *phydev) CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER); } -static int rtl8211f_config_init(struct phy_device *phydev) +static int rtl8211f_config_rgmii_delay(struct phy_device *phydev) { - struct rtl821x_priv *priv = phydev->priv; - struct device *dev = &phydev->mdio.dev; u16 val_txdly, val_rxdly; int ret; - ret = phy_modify_paged_changed(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1, - RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF, - priv->phycr1); - if (ret < 0) { - dev_err(dev, "aldps mode configuration failed: %pe\n", - ERR_PTR(ret)); - return ret; - } - switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: val_txdly = 0; @@ -632,53 +612,118 @@ static int rtl8211f_config_init(struct phy_device *phydev) RTL8211F_TXCR, RTL8211F_TX_DELAY, val_txdly); if (ret < 0) { - dev_err(dev, "Failed to update the TX delay register\n"); + phydev_err(phydev, "Failed to update the TX delay register: %pe\n", + ERR_PTR(ret)); return ret; } else if (ret) { - dev_dbg(dev, - "%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n", - str_enable_disable(val_txdly)); + phydev_dbg(phydev, + "%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n", + str_enable_disable(val_txdly)); } else { - dev_dbg(dev, - "2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n", - str_enabled_disabled(val_txdly)); + phydev_dbg(phydev, + "2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n", + str_enabled_disabled(val_txdly)); } ret = phy_modify_paged_changed(phydev, RTL8211F_RGMII_PAGE, RTL8211F_RXCR, RTL8211F_RX_DELAY, val_rxdly); if (ret < 0) { - dev_err(dev, "Failed to update the RX delay register\n"); + phydev_err(phydev, "Failed to update the RX delay register: %pe\n", + ERR_PTR(ret)); return ret; } else if (ret) { - dev_dbg(dev, - "%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n", - str_enable_disable(val_rxdly)); + phydev_dbg(phydev, + "%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n", + str_enable_disable(val_rxdly)); } else { - dev_dbg(dev, - "2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n", - str_enabled_disabled(val_rxdly)); + phydev_dbg(phydev, + "2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n", + str_enabled_disabled(val_rxdly)); } - if (!priv->has_phycr2) + return 0; +} + +static int rtl8211f_config_clk_out(struct phy_device *phydev) +{ + struct rtl821x_priv *priv = phydev->priv; + int ret; + + /* The value is preserved if the device tree property is absent */ + if (!priv->disable_clk_out) + return 0; + + if (phydev->drv->phy_id == RTL_8211FVD_PHYID) + ret = phy_modify_paged(phydev, RTL8211FVD_CLKOUT_PAGE, + RTL8211FVD_CLKOUT_REG, + RTL8211FVD_CLKOUT_EN, 0); + else + ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, + RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN, 0); + if (ret) + return ret; + + return genphy_soft_reset(phydev); +} + +/* Advance Link Down Power Saving (ALDPS) mode changes crystal/clock behaviour, + * which causes the RXC clock signal to stop for tens to hundreds of + * milliseconds. + * + * Some MACs need the RXC clock to support their internal RX logic, so ALDPS is + * only enabled based on an opt-in device tree property. + */ +static int rtl8211f_config_aldps(struct phy_device *phydev) +{ + struct rtl821x_priv *priv = phydev->priv; + u16 mask = RTL8211F_ALDPS_PLL_OFF | + RTL8211F_ALDPS_ENABLE | + RTL8211F_ALDPS_XTAL_OFF; + + /* The value is preserved if the device tree property is absent */ + if (!priv->enable_aldps) + return 0; + + return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR1, + mask, mask); +} + +static int rtl8211f_config_phy_eee(struct phy_device *phydev) +{ + /* RTL8211FVD has no PHYCR2 register */ + if (phydev->drv->phy_id == RTL_8211FVD_PHYID) return 0; /* Disable PHY-mode EEE so LPI is passed to the MAC */ - ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2, - RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0); + return phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, RTL8211F_PHYCR2, + RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0); +} + +static int rtl8211f_config_init(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + int ret; + + ret = rtl8211f_config_aldps(phydev); + if (ret) { + dev_err(dev, "aldps mode configuration failed: %pe\n", + ERR_PTR(ret)); + return ret; + } + + ret = rtl8211f_config_rgmii_delay(phydev); if (ret) return ret; - ret = phy_modify_paged(phydev, RTL8211F_PHYCR_PAGE, - RTL8211F_PHYCR2, RTL8211F_CLKOUT_EN, - priv->phycr2); - if (ret < 0) { + ret = rtl8211f_config_clk_out(phydev); + if (ret) { dev_err(dev, "clkout configuration failed: %pe\n", ERR_PTR(ret)); return ret; } - return genphy_soft_reset(phydev); + return rtl8211f_config_phy_eee(phydev); } static int rtl821x_suspend(struct phy_device *phydev) diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 29dc04c299a3..0a41d2b45d8c 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -1134,10 +1134,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EPERM; } - err = team_dev_type_check_change(dev, port_dev); - if (err) - return err; - if (port_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", @@ -1155,10 +1151,16 @@ static int team_port_add(struct team *team, struct net_device *port_dev, INIT_LIST_HEAD(&port->qom_list); port->orig.mtu = port_dev->mtu; - err = dev_set_mtu(port_dev, dev->mtu); - if (err) { - netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); - goto err_set_mtu; + /* + * MTU assignment will be handled in team_dev_type_check_change + * if dev and port_dev are of different types + */ + if (dev->type == port_dev->type) { + err = dev_set_mtu(port_dev, dev->mtu); + if (err) { + netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); + goto err_set_mtu; + } } memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len); @@ -1233,6 +1235,10 @@ static int team_port_add(struct team *team, struct net_device *port_dev, } } + err = team_dev_type_check_change(dev, port_dev); + if (err) + goto err_set_dev_type; + if (dev->flags & IFF_UP) { netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); @@ -1251,6 +1257,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return 0; +err_set_dev_type: err_set_slave_promisc: __team_option_inst_del_port(team, port); diff --git a/drivers/net/team/team_nl.c b/drivers/net/team/team_nl.c index 208424ab78f5..6db21725f9cc 100644 --- a/drivers/net/team/team_nl.c +++ b/drivers/net/team/team_nl.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/team.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/drivers/net/team/team_nl.h b/drivers/net/team/team_nl.h index c9ec1b22ac4d..74816b193475 100644 --- a/drivers/net/team/team_nl.h +++ b/drivers/net/team/team_nl.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/team.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_TEAM_GEN_H #define _LINUX_TEAM_GEN_H diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h index 81662328b2c7..a5f93b6c4482 100644 --- a/drivers/net/tun_vnet.h +++ b/drivers/net/tun_vnet.h @@ -244,7 +244,7 @@ tun_vnet_hdr_tnl_from_skb(unsigned int flags, if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), - vlan_hlen)) { + vlan_hlen, true)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 3d10cf791c51..1d9faa70ba3b 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -142,16 +142,16 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) if (alt->desc.bAlternateSetting != 0 || !(dev->driver_info->flags & FLAG_NO_SETINT)) { - tmp = usb_set_interface (dev->udev, alt->desc.bInterfaceNumber, - alt->desc.bAlternateSetting); + tmp = usb_set_interface(dev->udev, alt->desc.bInterfaceNumber, + alt->desc.bAlternateSetting); if (tmp < 0) return tmp; } - dev->in = usb_rcvbulkpipe (dev->udev, - in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); - dev->out = usb_sndbulkpipe (dev->udev, - out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->in = usb_rcvbulkpipe(dev->udev, + in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->out = usb_sndbulkpipe(dev->udev, + out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); dev->status = status; return 0; } @@ -163,7 +163,7 @@ int usbnet_get_ethernet_addr(struct usbnet *dev, int iMACAddress) int tmp = -1, ret; unsigned char buf [13]; - ret = usb_string(dev->udev, iMACAddress, buf, sizeof buf); + ret = usb_string(dev->udev, iMACAddress, buf, sizeof(buf)); if (ret == 12) tmp = hex2bin(addr, buf, 6); if (tmp < 0) { @@ -215,7 +215,7 @@ static void intr_complete(struct urb *urb) break; } - status = usb_submit_urb (urb, GFP_ATOMIC); + status = usb_submit_urb(urb, GFP_ATOMIC); if (status != 0) netif_err(dev, timer, dev->net, "intr resubmit --> %d\n", status); @@ -231,24 +231,24 @@ static int init_status(struct usbnet *dev, struct usb_interface *intf) if (!dev->driver_info->status) return 0; - pipe = usb_rcvintpipe (dev->udev, - dev->status->desc.bEndpointAddress - & USB_ENDPOINT_NUMBER_MASK); + pipe = usb_rcvintpipe(dev->udev, + dev->status->desc.bEndpointAddress + & USB_ENDPOINT_NUMBER_MASK); maxp = usb_maxpacket(dev->udev, pipe); /* avoid 1 msec chatter: min 8 msec poll rate */ period = max ((int) dev->status->desc.bInterval, (dev->udev->speed == USB_SPEED_HIGH) ? 7 : 3); - buf = kmalloc (maxp, GFP_KERNEL); + buf = kmalloc(maxp, GFP_KERNEL); if (buf) { - dev->interrupt = usb_alloc_urb (0, GFP_KERNEL); + dev->interrupt = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt) { - kfree (buf); + kfree(buf); return -ENOMEM; } else { usb_fill_int_urb(dev->interrupt, dev->udev, pipe, - buf, maxp, intr_complete, dev, period); + buf, maxp, intr_complete, dev, period); dev->interrupt->transfer_flags |= URB_FREE_BUFFER; dev_dbg(&intf->dev, "status ep%din, %d bytes period %d\n", @@ -339,7 +339,7 @@ void usbnet_skb_return(struct usbnet *dev, struct sk_buff *skb) /* only update if unset to allow minidriver rx_fixup override */ if (skb->protocol == 0) - skb->protocol = eth_type_trans (skb, dev->net); + skb->protocol = eth_type_trans(skb, dev->net); flags = u64_stats_update_begin_irqsave(&stats64->syncp); u64_stats_inc(&stats64->rx_packets); @@ -347,8 +347,8 @@ void usbnet_skb_return(struct usbnet *dev, struct sk_buff *skb) u64_stats_update_end_irqrestore(&stats64->syncp, flags); netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", - skb->len + sizeof (struct ethhdr), skb->protocol); - memset (skb->cb, 0, sizeof (struct skb_data)); + skb->len + sizeof(struct ethhdr), skb->protocol); + memset(skb->cb, 0, sizeof(struct skb_data)); if (skb_defer_rx_timestamp(skb)) return; @@ -511,8 +511,8 @@ static int rx_submit(struct usbnet *dev, struct urb *urb, gfp_t flags) skb = __netdev_alloc_skb_ip_align(dev->net, size, flags); if (!skb) { netif_dbg(dev, rx_err, dev->net, "no rx skb\n"); - usbnet_defer_kevent (dev, EVENT_RX_MEMORY); - usb_free_urb (urb); + usbnet_defer_kevent(dev, EVENT_RX_MEMORY); + usb_free_urb(urb); return -ENOMEM; } @@ -521,27 +521,27 @@ static int rx_submit(struct usbnet *dev, struct urb *urb, gfp_t flags) entry->dev = dev; entry->length = 0; - usb_fill_bulk_urb (urb, dev->udev, dev->in, - skb->data, size, rx_complete, skb); + usb_fill_bulk_urb(urb, dev->udev, dev->in, + skb->data, size, rx_complete, skb); - spin_lock_irqsave (&dev->rxq.lock, lockflags); + spin_lock_irqsave(&dev->rxq.lock, lockflags); - if (netif_running (dev->net) && - netif_device_present (dev->net) && + if (netif_running(dev->net) && + netif_device_present(dev->net) && test_bit(EVENT_DEV_OPEN, &dev->flags) && - !test_bit (EVENT_RX_HALT, &dev->flags) && - !test_bit (EVENT_DEV_ASLEEP, &dev->flags) && + !test_bit(EVENT_RX_HALT, &dev->flags) && + !test_bit(EVENT_DEV_ASLEEP, &dev->flags) && !usbnet_going_away(dev)) { - switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { + switch (retval = usb_submit_urb(urb, GFP_ATOMIC)) { case -EPIPE: - usbnet_defer_kevent (dev, EVENT_RX_HALT); + usbnet_defer_kevent(dev, EVENT_RX_HALT); break; case -ENOMEM: - usbnet_defer_kevent (dev, EVENT_RX_MEMORY); + usbnet_defer_kevent(dev, EVENT_RX_MEMORY); break; case -ENODEV: netif_dbg(dev, ifdown, dev->net, "device gone\n"); - netif_device_detach (dev->net); + netif_device_detach(dev->net); break; case -EHOSTUNREACH: retval = -ENOLINK; @@ -558,10 +558,10 @@ static int rx_submit(struct usbnet *dev, struct urb *urb, gfp_t flags) netif_dbg(dev, ifdown, dev->net, "rx: stopped\n"); retval = -ENOLINK; } - spin_unlock_irqrestore (&dev->rxq.lock, lockflags); + spin_unlock_irqrestore(&dev->rxq.lock, lockflags); if (retval) { - dev_kfree_skb_any (skb); - usb_free_urb (urb); + dev_kfree_skb_any(skb); + usb_free_urb(urb); } return retval; } @@ -572,7 +572,7 @@ static int rx_submit(struct usbnet *dev, struct urb *urb, gfp_t flags) static inline int rx_process(struct usbnet *dev, struct sk_buff *skb) { if (dev->driver_info->rx_fixup && - !dev->driver_info->rx_fixup (dev, skb)) { + !dev->driver_info->rx_fixup(dev, skb)) { /* With RX_ASSEMBLE, rx_fixup() must update counters */ if (!(dev->driver_info->flags & FLAG_RX_ASSEMBLE)) dev->net->stats.rx_errors++; @@ -605,7 +605,7 @@ static void rx_complete(struct urb *urb) int urb_status = urb->status; enum skb_state state; - skb_put (skb, urb->actual_length); + skb_put(skb, urb->actual_length); state = rx_done; entry->urb = NULL; @@ -621,7 +621,7 @@ static void rx_complete(struct urb *urb) */ case -EPIPE: dev->net->stats.rx_errors++; - usbnet_defer_kevent (dev, EVENT_RX_HALT); + usbnet_defer_kevent(dev, EVENT_RX_HALT); fallthrough; /* software-driven interface shutdown */ @@ -639,8 +639,8 @@ static void rx_complete(struct urb *urb) case -ETIME: case -EILSEQ: dev->net->stats.rx_errors++; - if (!timer_pending (&dev->delay)) { - mod_timer (&dev->delay, jiffies + THROTTLE_JIFFIES); + if (!timer_pending(&dev->delay)) { + mod_timer(&dev->delay, jiffies + THROTTLE_JIFFIES); netif_dbg(dev, link, dev->net, "rx throttle %d\n", urb_status); } @@ -676,14 +676,14 @@ block: state = defer_bh(dev, skb, &dev->rxq, state); if (urb) { - if (netif_running (dev->net) && - !test_bit (EVENT_RX_HALT, &dev->flags) && + if (netif_running(dev->net) && + !test_bit(EVENT_RX_HALT, &dev->flags) && state != unlink_start) { - rx_submit (dev, urb, GFP_ATOMIC); + rx_submit(dev, urb, GFP_ATOMIC); usb_mark_last_busy(dev->udev); return; } - usb_free_urb (urb); + usb_free_urb(urb); } netif_dbg(dev, rx_err, dev->net, "no read resubmitted\n"); } @@ -761,7 +761,7 @@ found: spin_unlock_irqrestore(&q->lock, flags); // during some PM-driven resume scenarios, // these (async) unlinks complete immediately - retval = usb_unlink_urb (urb); + retval = usb_unlink_urb(urb); if (retval != -EINPROGRESS && retval != 0) netdev_dbg(dev->net, "unlink urb err, %d\n", retval); else @@ -769,7 +769,7 @@ found: usb_put_urb(urb); spin_lock_irqsave(&q->lock, flags); } - spin_unlock_irqrestore (&q->lock, flags); + spin_unlock_irqrestore(&q->lock, flags); return count; } @@ -830,7 +830,7 @@ int usbnet_stop(struct net_device *net) int retval, pm, mpn; clear_bit(EVENT_DEV_OPEN, &dev->flags); - netif_stop_queue (net); + netif_stop_queue(net); netdev_reset_queue(net); netif_info(dev, ifdown, dev->net, @@ -910,23 +910,29 @@ int usbnet_open(struct net_device *net) } // put into "known safe" state - if (info->reset && (retval = info->reset (dev)) < 0) { - netif_info(dev, ifup, dev->net, - "open reset fail (%d) usbnet usb-%s-%s, %s\n", - retval, - dev->udev->bus->bus_name, - dev->udev->devpath, - info->description); - goto done; + if (info->reset) { + retval = info->reset(dev); + if (retval < 0) { + netif_info(dev, ifup, dev->net, + "open reset fail (%d) usbnet usb-%s-%s, %s\n", + retval, + dev->udev->bus->bus_name, + dev->udev->devpath, + info->description); + goto done; + } } /* hard_mtu or rx_urb_size may change in reset() */ usbnet_update_max_qlen(dev); // insist peer be connected - if (info->check_connect && (retval = info->check_connect (dev)) < 0) { - netif_err(dev, ifup, dev->net, "can't open; %d\n", retval); - goto done; + if (info->check_connect) { + retval = info->check_connect(dev); + if (retval < 0) { + netif_err(dev, ifup, dev->net, "can't open; %d\n", retval); + goto done; + } } /* start any status interrupt transfer */ @@ -1056,7 +1062,7 @@ u32 usbnet_get_link(struct net_device *net) /* If a check_connect is defined, return its result */ if (dev->driver_info->check_connect) - return dev->driver_info->check_connect (dev) == 0; + return dev->driver_info->check_connect(dev) == 0; /* if the device has mii operations, use those */ if (dev->mii.mdio_read) @@ -1085,7 +1091,7 @@ void usbnet_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) strscpy(info->driver, dev->driver_name, sizeof(info->driver)); strscpy(info->fw_version, dev->driver_info->description, sizeof(info->fw_version)); - usb_make_path (dev->udev, info->bus_info, sizeof info->bus_info); + usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } EXPORT_SYMBOL_GPL(usbnet_get_drvinfo); @@ -1175,64 +1181,64 @@ usbnet_deferred_kevent(struct work_struct *work) int status; /* usb_clear_halt() needs a thread context */ - if (test_bit (EVENT_TX_HALT, &dev->flags)) { - unlink_urbs (dev, &dev->txq); + if (test_bit(EVENT_TX_HALT, &dev->flags)) { + unlink_urbs(dev, &dev->txq); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto fail_pipe; - status = usb_clear_halt (dev->udev, dev->out); + status = usb_clear_halt(dev->udev, dev->out); usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { - if (netif_msg_tx_err (dev)) + if (netif_msg_tx_err(dev)) fail_pipe: netdev_err(dev->net, "can't clear tx halt, status %d\n", status); } else { - clear_bit (EVENT_TX_HALT, &dev->flags); + clear_bit(EVENT_TX_HALT, &dev->flags); if (status != -ESHUTDOWN) - netif_wake_queue (dev->net); + netif_wake_queue(dev->net); } } - if (test_bit (EVENT_RX_HALT, &dev->flags)) { - unlink_urbs (dev, &dev->rxq); + if (test_bit(EVENT_RX_HALT, &dev->flags)) { + unlink_urbs(dev, &dev->rxq); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto fail_halt; - status = usb_clear_halt (dev->udev, dev->in); + status = usb_clear_halt(dev->udev, dev->in); usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { - if (netif_msg_rx_err (dev)) + if (netif_msg_rx_err(dev)) fail_halt: netdev_err(dev->net, "can't clear rx halt, status %d\n", status); } else { - clear_bit (EVENT_RX_HALT, &dev->flags); + clear_bit(EVENT_RX_HALT, &dev->flags); if (!usbnet_going_away(dev)) queue_work(system_bh_wq, &dev->bh_work); } } /* work could resubmit itself forever if memory is tight */ - if (test_bit (EVENT_RX_MEMORY, &dev->flags)) { + if (test_bit(EVENT_RX_MEMORY, &dev->flags)) { struct urb *urb = NULL; int resched = 1; - if (netif_running (dev->net)) - urb = usb_alloc_urb (0, GFP_KERNEL); + if (netif_running(dev->net)) + urb = usb_alloc_urb(0, GFP_KERNEL); else - clear_bit (EVENT_RX_MEMORY, &dev->flags); + clear_bit(EVENT_RX_MEMORY, &dev->flags); if (urb != NULL) { - clear_bit (EVENT_RX_MEMORY, &dev->flags); + clear_bit(EVENT_RX_MEMORY, &dev->flags); status = usb_autopm_get_interface(dev->intf); if (status < 0) { usb_free_urb(urb); goto fail_lowmem; } - if (rx_submit (dev, urb, GFP_KERNEL) == -ENOLINK) + if (rx_submit(dev, urb, GFP_KERNEL) == -ENOLINK) resched = 0; usb_autopm_put_interface(dev->intf); fail_lowmem: @@ -1246,7 +1252,7 @@ fail_lowmem: const struct driver_info *info = dev->driver_info; int retval = 0; - clear_bit (EVENT_LINK_RESET, &dev->flags); + clear_bit(EVENT_LINK_RESET, &dev->flags); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto skip_reset; @@ -1266,10 +1272,10 @@ skip_reset: __handle_link_change(dev); } - if (test_bit (EVENT_LINK_CHANGE, &dev->flags)) + if (test_bit(EVENT_LINK_CHANGE, &dev->flags)) __handle_link_change(dev); - if (test_bit (EVENT_SET_RX_MODE, &dev->flags)) + if (test_bit(EVENT_SET_RX_MODE, &dev->flags)) __handle_set_rx_mode(dev); @@ -1298,7 +1304,7 @@ static void tx_complete(struct urb *urb) switch (urb->status) { case -EPIPE: - usbnet_defer_kevent (dev, EVENT_TX_HALT); + usbnet_defer_kevent(dev, EVENT_TX_HALT); break; /* software-driven interface shutdown */ @@ -1313,13 +1319,13 @@ static void tx_complete(struct urb *urb) case -ETIME: case -EILSEQ: usb_mark_last_busy(dev->udev); - if (!timer_pending (&dev->delay)) { - mod_timer (&dev->delay, - jiffies + THROTTLE_JIFFIES); + if (!timer_pending(&dev->delay)) { + mod_timer(&dev->delay, + jiffies + THROTTLE_JIFFIES); netif_dbg(dev, link, dev->net, "tx throttle %d\n", urb->status); } - netif_stop_queue (dev->net); + netif_stop_queue(dev->net); break; default: netif_dbg(dev, tx_err, dev->net, @@ -1338,7 +1344,7 @@ void usbnet_tx_timeout(struct net_device *net, unsigned int txqueue) { struct usbnet *dev = netdev_priv(net); - unlink_urbs (dev, &dev->txq); + unlink_urbs(dev, &dev->txq); queue_work(system_bh_wq, &dev->bh_work); /* this needs to be handled individually because the generic layer * doesn't know what is sufficient and could not restore private @@ -1400,7 +1406,7 @@ netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) // some devices want funky USB-level framing, for // win32 driver (usually) and/or hardware quirks if (info->tx_fixup) { - skb = info->tx_fixup (dev, skb, GFP_ATOMIC); + skb = info->tx_fixup(dev, skb, GFP_ATOMIC); if (!skb) { /* packet collected; minidriver waiting for more */ if (info->flags & FLAG_MULTI_PACKET) @@ -1410,7 +1416,8 @@ netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) } } - if (!(urb = usb_alloc_urb (0, GFP_ATOMIC))) { + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) { netif_dbg(dev, tx_err, dev->net, "no urb\n"); goto drop; } @@ -1419,8 +1426,8 @@ netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) entry->urb = urb; entry->dev = dev; - usb_fill_bulk_urb (urb, dev->udev, dev->out, - skb->data, skb->len, tx_complete, skb); + usb_fill_bulk_urb(urb, dev->udev, dev->out, + skb->data, skb->len, tx_complete, skb); if (dev->can_dma_sg) { if (build_dma_sg(skb, urb) < 0) goto drop; @@ -1490,8 +1497,8 @@ netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) switch ((retval = usb_submit_urb (urb, GFP_ATOMIC))) { case -EPIPE: - netif_stop_queue (net); - usbnet_defer_kevent (dev, EVENT_TX_HALT); + netif_stop_queue(net); + usbnet_defer_kevent(dev, EVENT_TX_HALT); usb_autopm_put_interface_async(dev->intf); break; default: @@ -1506,7 +1513,7 @@ netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) if (dev->txq.qlen >= TX_QLEN (dev)) netif_stop_queue (net); } - spin_unlock_irqrestore (&dev->txq.lock, flags); + spin_unlock_irqrestore(&dev->txq.lock, flags); if (retval) { netif_dbg(dev, tx_err, dev->net, "drop, code %d\n", retval); @@ -1514,7 +1521,7 @@ drop: dev->net->stats.tx_dropped++; not_drop: if (skb) - dev_kfree_skb_any (skb); + dev_kfree_skb_any(skb); if (urb) { kfree(urb->sg); usb_free_urb(urb); @@ -1625,7 +1632,7 @@ static void usbnet_bh(struct timer_list *t) queue_work(system_bh_wq, &dev->bh_work); } if (dev->txq.qlen < TX_QLEN (dev)) - netif_wake_queue (dev->net); + netif_wake_queue(dev->net); } } @@ -1658,7 +1665,7 @@ void usbnet_disconnect(struct usb_interface *intf) return; usbnet_mark_going_away(dev); - xdev = interface_to_usbdev (intf); + xdev = interface_to_usbdev(intf); netif_info(dev, probe, dev->net, "unregister '%s' usb-%s-%s, %s\n", intf->dev.driver->name, @@ -1666,7 +1673,7 @@ void usbnet_disconnect(struct usb_interface *intf) dev->driver_info->description); net = dev->net; - unregister_netdev (net); + unregister_netdev(net); cancel_work_sync(&dev->kevent); @@ -1737,7 +1744,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) dev_dbg (&udev->dev, "blacklisted by %s\n", name); return -ENODEV; } - xdev = interface_to_usbdev (udev); + xdev = interface_to_usbdev(udev); interface = udev->cur_altsetting; status = -ENOMEM; @@ -1767,10 +1774,10 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) skb_queue_head_init(&dev->rxq_pause); spin_lock_init(&dev->bql_spinlock); INIT_WORK(&dev->bh_work, usbnet_bh_work); - INIT_WORK (&dev->kevent, usbnet_deferred_kevent); + INIT_WORK(&dev->kevent, usbnet_deferred_kevent); init_usb_anchor(&dev->deferred); timer_setup(&dev->delay, usbnet_bh, 0); - mutex_init (&dev->phy_mutex); + mutex_init(&dev->phy_mutex); mutex_init(&dev->interrupt_mutex); dev->interrupt_count = 0; @@ -1792,7 +1799,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) // allow device-specific bind/init procedures // NOTE net->name still not usable ... if (info->bind) { - status = info->bind (dev, udev); + status = info->bind(dev, udev); if (status < 0) goto out1; @@ -1817,18 +1824,18 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) if (net->mtu > (dev->hard_mtu - net->hard_header_len)) net->mtu = dev->hard_mtu - net->hard_header_len; } else if (!info->in || !info->out) - status = usbnet_get_endpoints (dev, udev); + status = usbnet_get_endpoints(dev, udev); else { u8 ep_addrs[3] = { info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 }; - dev->in = usb_rcvbulkpipe (xdev, info->in); - dev->out = usb_sndbulkpipe (xdev, info->out); + dev->in = usb_rcvbulkpipe(xdev, info->in); + dev->out = usb_sndbulkpipe(xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) - status = usb_set_interface (xdev, - interface->desc.bInterfaceNumber, - interface->desc.bAlternateSetting); + status = usb_set_interface(xdev, + interface->desc.bInterfaceNumber, + interface->desc.bAlternateSetting); else status = 0; @@ -1836,7 +1843,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) status = -EINVAL; } if (status >= 0 && dev->status) - status = init_status (dev, udev); + status = init_status(dev, udev); if (status < 0) goto out3; @@ -1870,7 +1877,7 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) } } - status = register_netdev (net); + status = register_netdev(net); if (status) goto out5; netif_info(dev, probe, dev->net, @@ -1881,9 +1888,9 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) net->dev_addr); // ok, it's ready to go. - usb_set_intfdata (udev, dev); + usb_set_intfdata(udev, dev); - netif_device_attach (net); + netif_device_attach(net); if (dev->driver_info->flags & FLAG_LINK_INTR) usbnet_link_change(dev, 0, 0); @@ -1896,7 +1903,7 @@ out4: usb_free_urb(dev->interrupt); out3: if (info->unbind) - info->unbind (dev, udev); + info->unbind(dev, udev); out1: /* subdrivers must undo all they did in bind() if they * fail it, but we may fail later and a deferred kevent @@ -1938,7 +1945,7 @@ int usbnet_suspend(struct usb_interface *intf, pm_message_t message) * accelerate emptying of the rx and queues, to avoid * having everything error out. */ - netif_device_detach (dev->net); + netif_device_detach(dev->net); usbnet_terminate_urbs(dev); __usbnet_status_stop_force(dev); @@ -1946,7 +1953,7 @@ int usbnet_suspend(struct usb_interface *intf, pm_message_t message) * reattach so runtime management can use and * wake the device */ - netif_device_attach (dev->net); + netif_device_attach(dev->net); } return 0; } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 87a63c4bee77..14e6f2a2fb77 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -392,14 +392,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) } /* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */ __skb_push(skb, ETH_HLEN); - /* Depend on prior success packets started NAPI consumer via - * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped, - * paired with empty check in veth_poll(). - */ netif_tx_stop_queue(txq); - smp_mb__after_atomic(); - if (unlikely(__ptr_ring_empty(&rq->xdp_ring))) - netif_tx_wake_queue(txq); + /* Makes sure NAPI peer consumer runs. Consumer is responsible + * for starting txq again, until then ndo_start_xmit (this + * function) will not be invoked by the netstack again. + */ + __veth_xdp_flush(rq); break; case NET_RX_DROP: /* same as NET_XMIT_DROP */ drop: @@ -900,17 +898,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { - struct veth_priv *priv = netdev_priv(rq->dev); - int queue_idx = rq->xdp_rxq.queue_index; - struct netdev_queue *peer_txq; - struct net_device *peer_dev; int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; - /* NAPI functions as RCU section */ - peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; - for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); @@ -959,9 +949,6 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); - if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) - netif_tx_wake_queue(peer_txq); - return done; } @@ -969,17 +956,28 @@ static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); + struct veth_priv *priv = netdev_priv(rq->dev); + int queue_idx = rq->xdp_rxq.queue_index; + struct netdev_queue *peer_txq; struct veth_stats stats = {}; + struct net_device *peer_dev; struct veth_xdp_tx_bq bq; int done; bq.count = 0; + /* NAPI functions as RCU section */ + peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); + peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; + xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); if (stats.xdp_redirect > 0) xdp_do_flush(); + if (stats.xdp_tx > 0) + veth_xdp_flush(rq, &bq); + xdp_clear_return_frame_no_direct(); if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ @@ -992,9 +990,12 @@ static int veth_poll(struct napi_struct *napi, int budget) } } - if (stats.xdp_tx > 0) - veth_xdp_flush(rq, &bq); - xdp_clear_return_frame_no_direct(); + /* Release backpressure per NAPI poll */ + smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */ + if (peer_txq && netif_tx_queue_stopped(peer_txq)) { + txq_trans_cond_update(peer_txq); + netif_tx_wake_queue(peer_txq); + } return done; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index cfa006b88688..1bb3aeca66c6 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -775,10 +775,26 @@ static bool virtqueue_napi_complete(struct napi_struct *napi, return false; } +static void virtnet_tx_wake_queue(struct virtnet_info *vi, + struct send_queue *sq) +{ + unsigned int index = vq2txq(sq->vq); + struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); + + if (netif_tx_queue_stopped(txq)) { + u64_stats_update_begin(&sq->stats.syncp); + u64_stats_inc(&sq->stats.wake); + u64_stats_update_end(&sq->stats.syncp); + netif_tx_wake_queue(txq); + } +} + static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; - struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; + unsigned int index = vq2txq(vq); + struct send_queue *sq = &vi->sq[index]; + struct napi_struct *napi = &sq->napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); @@ -786,8 +802,7 @@ static void skb_xmit_done(struct virtqueue *vq) if (napi->weight) virtqueue_napi_schedule(napi, vq); else - /* We were probably waiting for more output buffers. */ - netif_wake_subqueue(vi->dev, vq2txq(vq)); + virtnet_tx_wake_queue(vi, sq); } #define MRG_CTX_HEADER_SHIFT 22 @@ -3080,13 +3095,8 @@ static void virtnet_poll_cleantx(struct receive_queue *rq, int budget) free_old_xmit(sq, txq, !!budget); } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq))); - if (sq->vq->num_free >= MAX_SKB_FRAGS + 2 && - netif_tx_queue_stopped(txq)) { - u64_stats_update_begin(&sq->stats.syncp); - u64_stats_inc(&sq->stats.wake); - u64_stats_update_end(&sq->stats.syncp); - netif_tx_wake_queue(txq); - } + if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) + virtnet_tx_wake_queue(vi, sq); __netif_tx_unlock(txq); } @@ -3276,13 +3286,8 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) else free_old_xmit(sq, txq, !!budget); - if (sq->vq->num_free >= MAX_SKB_FRAGS + 2 && - netif_tx_queue_stopped(txq)) { - u64_stats_update_begin(&sq->stats.syncp); - u64_stats_inc(&sq->stats.wake); - u64_stats_update_end(&sq->stats.syncp); - netif_tx_wake_queue(txq); - } + if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) + virtnet_tx_wake_queue(vi, sq); if (xsk_done >= budget) { __netif_tx_unlock(txq); @@ -3339,7 +3344,8 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb, bool orphan) hdr = &skb_vnet_common_hdr(skb)->tnl_hdr; if (virtio_net_hdr_tnl_from_skb(skb, hdr, vi->tx_tnl, - virtio_is_little_endian(vi->vdev), 0)) + virtio_is_little_endian(vi->vdev), 0, + false)) return -EPROTO; if (vi->mergeable_rx_bufs) @@ -3537,6 +3543,9 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq) /* Prevent the upper layer from trying to send packets. */ netif_stop_subqueue(vi->dev, qindex); + u64_stats_update_begin(&sq->stats.syncp); + u64_stats_inc(&sq->stats.stop); + u64_stats_update_end(&sq->stats.syncp); __netif_tx_unlock_bh(txq); } @@ -3553,7 +3562,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq) __netif_tx_lock_bh(txq); sq->reset = false; - netif_tx_wake_queue(txq); + virtnet_tx_wake_queue(vi, sq); __netif_tx_unlock_bh(txq); if (running) diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index cc4d7573839d..a14d0ad978e1 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -1081,23 +1081,11 @@ vmxnet3_set_rss_hash_opt(struct net_device *netdev, return 0; } -static int -vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info, - u32 *rules) +static u32 vmxnet3_get_rx_ring_count(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - int err = 0; - - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = adapter->num_rx_queues; - break; - default: - err = -EOPNOTSUPP; - break; - } - return err; + return adapter->num_rx_queues; } #ifdef VMXNET3_RSS @@ -1335,7 +1323,7 @@ static const struct ethtool_ops vmxnet3_ethtool_ops = { .get_ethtool_stats = vmxnet3_get_ethtool_stats, .get_ringparam = vmxnet3_get_ringparam, .set_ringparam = vmxnet3_set_ringparam, - .get_rxnfc = vmxnet3_get_rxnfc, + .get_rx_ring_count = vmxnet3_get_rx_ring_count, #ifdef VMXNET3_RSS .get_rxfh_indir_size = vmxnet3_get_rss_indir_size, .get_rxfh = vmxnet3_get_rss, diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h index 99fe772ad679..b1eec2216360 100644 --- a/drivers/net/vxlan/vxlan_private.h +++ b/drivers/net/vxlan/vxlan_private.h @@ -188,8 +188,6 @@ int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify); -u32 eth_vni_hash(const unsigned char *addr, __be32 vni); -u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni); int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index d50c35328363..7b9d9989e517 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -7759,6 +7759,13 @@ int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev, INIT_LIST_HEAD(&list); list_for_each_entry_safe(ch_info, tmp, &scan_info->chan_list, list) { + /* The operating channel (tx_null == true) should + * not be last in the list, to avoid breaking + * RTL8851BU and RTL8832BU. + */ + if (list_len + 1 == RTW89_SCAN_LIST_LIMIT_AX && ch_info->tx_null) + break; + list_move_tail(&ch_info->list, &list); list_len++; diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c index 33d6342124bc..301a9d294d30 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c @@ -21,7 +21,8 @@ static struct iosm_coredump_file_info list[IOSM_NOF_CD_REGION] = { /* Get the param values for the specific param ID's */ static int ipc_devlink_get_param(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct iosm_devlink *ipc_devlink = devlink_priv(dl); diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index c814fbd756a1..0dace12f5ad0 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -78,8 +78,9 @@ struct mhi_mbim_context { struct mbim_tx_hdr { struct usb_cdc_ncm_nth16 nth16; + + /* Must be last as it ends in a flexible-array member. */ struct usb_cdc_ncm_ndp16 ndp16; - struct usb_cdc_ncm_dpe16 dpe16[2]; } __packed; static struct mhi_mbim_link *mhi_mbim_get_link_rcu(struct mhi_mbim_context *mbim, @@ -98,7 +99,7 @@ static struct mhi_mbim_link *mhi_mbim_get_link_rcu(struct mhi_mbim_context *mbim static int mhi_mbim_get_link_mux_id(struct mhi_controller *cntrl) { if (strcmp(cntrl->name, "foxconn-dw5934e") == 0 || - strcmp(cntrl->name, "foxconn-t99w515") == 0) + strcmp(cntrl->name, "foxconn-t99w640") == 0) return WDS_BIND_MUX_DATA_PORT_MUX_ID; return 0; @@ -107,20 +108,20 @@ static int mhi_mbim_get_link_mux_id(struct mhi_controller *cntrl) static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, u16 tx_seq) { + DEFINE_RAW_FLEX(struct mbim_tx_hdr, mbim_hdr, ndp16.dpe16, 2); unsigned int dgram_size = skb->len; struct usb_cdc_ncm_nth16 *nth16; struct usb_cdc_ncm_ndp16 *ndp16; - struct mbim_tx_hdr *mbim_hdr; /* Only one NDP is sent, containing the IP packet (no aggregation) */ /* Ensure we have enough headroom for crafting MBIM header */ - if (skb_cow_head(skb, sizeof(struct mbim_tx_hdr))) { + if (skb_cow_head(skb, __struct_size(mbim_hdr))) { dev_kfree_skb_any(skb); return NULL; } - mbim_hdr = skb_push(skb, sizeof(struct mbim_tx_hdr)); + mbim_hdr = skb_push(skb, __struct_size(mbim_hdr)); /* Fill NTB header */ nth16 = &mbim_hdr->nth16; @@ -133,12 +134,11 @@ static struct sk_buff *mbim_tx_fixup(struct sk_buff *skb, unsigned int session, /* Fill the unique NDP */ ndp16 = &mbim_hdr->ndp16; ndp16->dwSignature = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN | (session << 24)); - ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) - + sizeof(struct usb_cdc_ncm_dpe16) * 2); + ndp16->wLength = cpu_to_le16(struct_size(ndp16, dpe16, 2)); ndp16->wNextNdpIndex = 0; /* Datagram follows the mbim header */ - ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(sizeof(struct mbim_tx_hdr)); + ndp16->dpe16[0].wDatagramIndex = cpu_to_le16(__struct_size(mbim_hdr)); ndp16->dpe16[0].wDatagramLength = cpu_to_le16(dgram_size); /* null termination */ @@ -584,7 +584,8 @@ static void mhi_mbim_setup(struct net_device *ndev) { ndev->header_ops = NULL; /* No header */ ndev->type = ARPHRD_RAWIP; - ndev->needed_headroom = sizeof(struct mbim_tx_hdr); + ndev->needed_headroom = + struct_size_t(struct mbim_tx_hdr, ndp16.dpe16, 2); ndev->hard_header_len = 0; ndev->addr_len = 0; ndev->flags = IFF_POINTOPOINT | IFF_NOARP; diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c index 689c920ca898..43ac1c3f1ad0 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c @@ -897,7 +897,7 @@ static void t7xx_cldma_hw_start_send(struct cldma_ctrl *md_ctrl, int qno, * @queue: CLDMA queue. * @recv_skb: Receiving skb callback. */ -void t7xx_cldma_set_recv_skb(struct cldma_queue *queue, +static void t7xx_cldma_set_recv_skb(struct cldma_queue *queue, int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb)) { queue->recv_skb = recv_skb; diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h index f2d9941be9c8..9d0107e18a7b 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.h +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.h @@ -126,8 +126,6 @@ void t7xx_cldma_switch_cfg(struct cldma_ctrl *md_ctrl, enum cldma_cfg cfg_id); void t7xx_cldma_start(struct cldma_ctrl *md_ctrl); int t7xx_cldma_stop(struct cldma_ctrl *md_ctrl); void t7xx_cldma_reset(struct cldma_ctrl *md_ctrl); -void t7xx_cldma_set_recv_skb(struct cldma_queue *queue, - int (*recv_skb)(struct cldma_queue *queue, struct sk_buff *skb)); int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb); void t7xx_cldma_stop_all_qs(struct cldma_ctrl *md_ctrl, enum mtk_txrx tx_rx); void t7xx_cldma_clear_all_qs(struct cldma_ctrl *md_ctrl, enum mtk_txrx tx_rx); diff --git a/drivers/nfc/mei_phy.h b/drivers/nfc/mei_phy.h index 2b1edb3eba15..9b9c5eb54e07 100644 --- a/drivers/nfc/mei_phy.h +++ b/drivers/nfc/mei_phy.h @@ -12,11 +12,11 @@ #define MEI_NFC_MAX_HCI_PAYLOAD 300 /** - * struct nfc_mei_phy + * struct nfc_mei_phy - NFC description of the MEI PHY and interface functions * * @cldev: mei client device * @hdev: nfc hci device - + * * @send_wq: send completion wait queue * @fw_ivn: NFC Interface Version Number * @vendor_id: NFC manufacturer ID diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index fa4181d7de73..f1f719351f3f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4901,7 +4901,6 @@ void nvme_remove_admin_tag_set(struct nvme_ctrl *ctrl) */ nvme_stop_keep_alive(ctrl); blk_mq_destroy_queue(ctrl->admin_q); - blk_put_queue(ctrl->admin_q); if (ctrl->ops->flags & NVME_F_FABRICS) { blk_mq_destroy_queue(ctrl->fabrics_q); blk_put_queue(ctrl->fabrics_q); @@ -5045,6 +5044,8 @@ static void nvme_free_ctrl(struct device *dev) container_of(dev, struct nvme_ctrl, ctrl_device); struct nvme_subsystem *subsys = ctrl->subsys; + if (ctrl->admin_q) + blk_put_queue(ctrl->admin_q); if (!subsys || ctrl->instance != subsys->instance) ida_free(&nvme_instance_ida, ctrl->instance); nvme_free_cels(ctrl); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 03987f497a5b..2c903729b0b9 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2355,17 +2355,11 @@ nvme_fc_ctrl_free(struct kref *ref) container_of(ref, struct nvme_fc_ctrl, ref); unsigned long flags; - if (ctrl->ctrl.tagset) - nvme_remove_io_tag_set(&ctrl->ctrl); - /* remove from rport list */ spin_lock_irqsave(&ctrl->rport->lock, flags); list_del(&ctrl->ctrl_list); spin_unlock_irqrestore(&ctrl->rport->lock, flags); - nvme_unquiesce_admin_queue(&ctrl->ctrl); - nvme_remove_admin_tag_set(&ctrl->ctrl); - kfree(ctrl->queues); put_device(ctrl->dev); @@ -3259,13 +3253,20 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nctrl) { struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); - cancel_work_sync(&ctrl->ioerr_work); cancel_delayed_work_sync(&ctrl->connect_work); + /* * kill the association on the link side. this will block * waiting for io to terminate */ nvme_fc_delete_association(ctrl); + cancel_work_sync(&ctrl->ioerr_work); + + if (ctrl->ctrl.tagset) + nvme_remove_io_tag_set(&ctrl->ctrl); + + nvme_unquiesce_admin_queue(&ctrl->ctrl); + nvme_remove_admin_tag_set(&ctrl->ctrl); } static void diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 543e17aead12..e35eccacee8c 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -793,7 +793,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) return; } nvme_add_ns_head_cdev(head); - kblockd_schedule_work(&head->partition_scan_work); + queue_work(nvme_wq, &head->partition_scan_work); } nvme_mpath_add_sysfs_link(ns->head); diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c index ceba21684e82..300d5e032f6d 100644 --- a/drivers/nvme/target/auth.c +++ b/drivers/nvme/target/auth.c @@ -298,7 +298,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, const char *hash_name; u8 *challenge = req->sq->dhchap_c1; struct nvme_dhchap_key *transformed_key; - u8 buf[4], sc_c = ctrl->concat ? 1 : 0; + u8 buf[4]; int ret; hash_name = nvme_auth_hmac_name(ctrl->shash_id); @@ -367,7 +367,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, ret = crypto_shash_update(shash, buf, 2); if (ret) goto out; - *buf = sc_c; + *buf = req->sq->sc_c; ret = crypto_shash_update(shash, buf, 1); if (ret) goto out; diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index bf01ec414c55..5946681cb0e3 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -43,6 +43,7 @@ static u8 nvmet_auth_negotiate(struct nvmet_req *req, void *d) data->auth_protocol[0].dhchap.halen, data->auth_protocol[0].dhchap.dhlen); req->sq->dhchap_tid = le16_to_cpu(data->t_id); + req->sq->sc_c = data->sc_c; if (data->sc_c != NVME_AUTH_SECP_NOSC) { if (!IS_ENABLED(CONFIG_NVME_TARGET_TCP_TLS)) return NVME_AUTH_DHCHAP_FAILURE_CONCAT_MISMATCH; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 51df72f5e89b..f3b09f4099f0 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -159,6 +159,7 @@ struct nvmet_sq { bool authenticated; struct delayed_work auth_expired_work; u16 dhchap_tid; + u8 sc_c; u8 dhchap_status; u8 dhchap_step; u8 *dhchap_c1; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 4492b809094b..36f8c0985430 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -958,6 +958,7 @@ void pci_save_aspm_l1ss_state(struct pci_dev *dev); void pci_restore_aspm_l1ss_state(struct pci_dev *dev); #ifdef CONFIG_PCIEASPM +void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap); void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); @@ -965,6 +966,7 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev); void pci_configure_ltr(struct pci_dev *pdev); void pci_bridge_reconfigure_ltr(struct pci_dev *pdev); #else +static inline void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap) { } static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 79b965158473..cedea47a3547 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -814,7 +814,6 @@ static void pcie_aspm_override_default_link_state(struct pcie_link_state *link) static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) { struct pci_dev *child = link->downstream, *parent = link->pdev; - u32 parent_lnkcap, child_lnkcap; u16 parent_lnkctl, child_lnkctl; struct pci_bus *linkbus = parent->subordinate; @@ -829,9 +828,8 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * If ASPM not supported, don't mess with the clocks and link, * bail out now. */ - pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap); - pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap); - if (!(parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPMS)) + if (!(parent->aspm_l0s_support && child->aspm_l0s_support) && + !(parent->aspm_l1_support && child->aspm_l1_support)) return; /* Configure common clock before checking latencies */ @@ -843,8 +841,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * read-only Link Capabilities may change depending on common clock * configuration (PCIe r5.0, sec 7.5.3.6). */ - pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap); - pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap); pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl); pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl); @@ -864,7 +860,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * given link unless components on both sides of the link each * support L0s. */ - if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L0S) + if (parent->aspm_l0s_support && child->aspm_l0s_support) link->aspm_support |= PCIE_LINK_STATE_L0S; if (child_lnkctl & PCI_EXP_LNKCTL_ASPM_L0S) @@ -873,7 +869,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) link->aspm_enabled |= PCIE_LINK_STATE_L0S_DW; /* Setup L1 state */ - if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L1) + if (parent->aspm_l1_support && child->aspm_l1_support) link->aspm_support |= PCIE_LINK_STATE_L1; if (parent_lnkctl & child_lnkctl & PCI_EXP_LNKCTL_ASPM_L1) @@ -1530,6 +1526,19 @@ int pci_enable_link_state_locked(struct pci_dev *pdev, int state) } EXPORT_SYMBOL(pci_enable_link_state_locked); +void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap) +{ + if (lnkcap & PCI_EXP_LNKCAP_ASPM_L0S) + pdev->aspm_l0s_support = 0; + if (lnkcap & PCI_EXP_LNKCAP_ASPM_L1) + pdev->aspm_l1_support = 0; + + pci_info(pdev, "ASPM: Link Capabilities%s%s treated as unsupported to avoid device defect\n", + lnkcap & PCI_EXP_LNKCAP_ASPM_L0S ? " L0s" : "", + lnkcap & PCI_EXP_LNKCAP_ASPM_L1 ? " L1" : ""); + +} + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 0ce98e18b5a8..9cd032dff31e 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1656,6 +1656,13 @@ void set_pcie_port_type(struct pci_dev *pdev) if (reg32 & PCI_EXP_LNKCAP_DLLLARC) pdev->link_active_reporting = 1; +#ifdef CONFIG_PCIEASPM + if (reg32 & PCI_EXP_LNKCAP_ASPM_L0S) + pdev->aspm_l0s_support = 1; + if (reg32 & PCI_EXP_LNKCAP_ASPM_L1) + pdev->aspm_l1_support = 1; +#endif + parent = pci_upstream_bridge(pdev); if (!parent) return; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 214ed060ca1b..b9c252aa6fe0 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -2494,28 +2494,27 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, */ static void quirk_disable_aspm_l0s(struct pci_dev *dev) { - pci_info(dev, "Disabling L0s\n"); - pci_disable_link_state(dev, PCIE_LINK_STATE_L0S); -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a7, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a9, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10b6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c7, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c8, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10d6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10db, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10dd, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10e1, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10ec, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); + pcie_aspm_remove_cap(dev, PCI_EXP_LNKCAP_ASPM_L0S); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10a7, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10a9, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10b6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c7, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c8, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10d6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10db, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10dd, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e1, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10ec, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) { - pci_info(dev, "Disabling ASPM L0s/L1\n"); - pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); + pcie_aspm_remove_cap(dev, + PCI_EXP_LNKCAP_ASPM_L0S | PCI_EXP_LNKCAP_ASPM_L1); } /* @@ -2523,7 +2522,10 @@ static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; * disable both L0s and L1 for now to be safe. */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, 0x0451, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PASEMI, 0xa002, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0x1105, quirk_disable_aspm_l0s_l1); /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c index cc64f93709a4..ca4f97be7538 100644 --- a/drivers/pci/tph.c +++ b/drivers/pci/tph.c @@ -155,7 +155,16 @@ static u8 get_st_modes(struct pci_dev *pdev) return reg; } -static u32 get_st_table_loc(struct pci_dev *pdev) +/** + * pcie_tph_get_st_table_loc - Return the device's ST table location + * @pdev: PCI device to query + * + * Return: + * PCI_TPH_LOC_NONE - Not present + * PCI_TPH_LOC_CAP - Located in the TPH Requester Extended Capability + * PCI_TPH_LOC_MSIX - Located in the MSI-X Table + */ +u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev) { u32 reg; @@ -163,6 +172,7 @@ static u32 get_st_table_loc(struct pci_dev *pdev) return FIELD_GET(PCI_TPH_CAP_LOC_MASK, reg); } +EXPORT_SYMBOL(pcie_tph_get_st_table_loc); /* * Return the size of ST table. If ST table is not in TPH Requester Extended @@ -174,7 +184,7 @@ u16 pcie_tph_get_st_table_size(struct pci_dev *pdev) u32 loc; /* Check ST table location first */ - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* defined in pci_regs.h */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); @@ -299,7 +309,7 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) */ set_ctrl_reg_req_en(pdev, PCI_TPH_REQ_DISABLE); - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index e255c1b069ec..7dd282da67ce 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1109,7 +1109,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) /* compute hardware counter index */ hidx = info->csr - CSR_CYCLE; - /* check if the corresponding bit is set in sscountovf or overflow mask in shmem */ + /* check if the corresponding bit is set in scountovf or overflow mask in shmem */ if (!(overflow & BIT(hidx))) continue; diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c index 68abb6d6cecd..a8f82104a384 100644 --- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c +++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c @@ -532,6 +532,11 @@ static int cs42l43_gpio_add_pin_ranges(struct gpio_chip *chip) return ret; } +static void cs42l43_fwnode_put(void *data) +{ + fwnode_handle_put(data); +} + static int cs42l43_pin_probe(struct platform_device *pdev) { struct cs42l43 *cs42l43 = dev_get_drvdata(pdev->dev.parent); @@ -563,10 +568,20 @@ static int cs42l43_pin_probe(struct platform_device *pdev) priv->gpio_chip.ngpio = CS42L43_NUM_GPIOS; if (is_of_node(fwnode)) { - fwnode = fwnode_get_named_child_node(fwnode, "pinctrl"); - - if (fwnode && !fwnode->dev) - fwnode->dev = priv->dev; + struct fwnode_handle *child; + + child = fwnode_get_named_child_node(fwnode, "pinctrl"); + if (child) { + ret = devm_add_action_or_reset(&pdev->dev, + cs42l43_fwnode_put, child); + if (ret) { + fwnode_handle_put(child); + return ret; + } + if (!child->dev) + child->dev = priv->dev; + fwnode = child; + } } priv->gpio_chip.fwnode = fwnode; diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8189.c b/drivers/pinctrl/mediatek/pinctrl-mt8189.c index 7028aff55ae5..f6a3e584588b 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8189.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8189.c @@ -1642,9 +1642,7 @@ static const struct mtk_pin_reg_calc mt8189_reg_cals[PINCTRL_PIN_REG_MAX] = { }; static const char * const mt8189_pinctrl_register_base_names[] = { - "gpio_base", "iocfg_bm0_base", "iocfg_bm1_base", "iocfg_bm2_base", "iocfg_lm_base", - "iocfg_lt0_base", "iocfg_lt1_base", "iocfg_rb0_base", "iocfg_rb1_base", - "iocfg_rt_base" + "base", "lm", "rb0", "rb1", "bm0", "bm1", "bm2", "lt0", "lt1", "rt", }; static const struct mtk_eint_hw mt8189_eint_hw = { diff --git a/drivers/pinctrl/mediatek/pinctrl-mt8196.c b/drivers/pinctrl/mediatek/pinctrl-mt8196.c index 82a73929c7a0..dec957c1724b 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mt8196.c +++ b/drivers/pinctrl/mediatek/pinctrl-mt8196.c @@ -1801,10 +1801,8 @@ static const struct mtk_pin_reg_calc mt8196_reg_cals[PINCTRL_PIN_REG_MAX] = { }; static const char * const mt8196_pinctrl_register_base_names[] = { - "iocfg0", "iocfg_rt", "iocfg_rm1", "iocfg_rm2", - "iocfg_rb", "iocfg_bm1", "iocfg_bm2", "iocfg_bm3", - "iocfg_lt", "iocfg_lm1", "iocfg_lm2", "iocfg_lb1", - "iocfg_lb2", "iocfg_tm1", "iocfg_tm2", "iocfg_tm3", + "base", "rt", "rm1", "rm2", "rb", "bm1", "bm2", "bm3", + "lt", "lm1", "lm2", "lb1", "lb2", "tm1", "tm2", "tm3", }; static const struct mtk_eint_hw mt8196_eint_hw = { diff --git a/drivers/pinctrl/nxp/pinctrl-s32cc.c b/drivers/pinctrl/nxp/pinctrl-s32cc.c index 501eb296c760..35511f83d056 100644 --- a/drivers/pinctrl/nxp/pinctrl-s32cc.c +++ b/drivers/pinctrl/nxp/pinctrl-s32cc.c @@ -392,6 +392,7 @@ static int s32_pmx_gpio_request_enable(struct pinctrl_dev *pctldev, gpio_pin->pin_id = offset; gpio_pin->config = config; + INIT_LIST_HEAD(&gpio_pin->list); spin_lock_irqsave(&ipctl->gpio_configs_lock, flags); list_add(&gpio_pin->list, &ipctl->gpio_configs); @@ -951,7 +952,7 @@ int s32_pinctrl_probe(struct platform_device *pdev, spin_lock_init(&ipctl->gpio_configs_lock); s32_pinctrl_desc = - devm_kmalloc(&pdev->dev, sizeof(*s32_pinctrl_desc), GFP_KERNEL); + devm_kzalloc(&pdev->dev, sizeof(*s32_pinctrl_desc), GFP_KERNEL); if (!s32_pinctrl_desc) return -ENOMEM; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 67525d542c5b..e99871b90ab9 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -189,7 +189,7 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev, */ if (d && i != gpio_func && !test_and_set_bit(d->hwirq, pctrl->disabled_for_mux)) - disable_irq(irq); + disable_irq_nosync(irq); raw_spin_lock_irqsave(&pctrl->lock, flags); diff --git a/drivers/pinctrl/realtek/Kconfig b/drivers/pinctrl/realtek/Kconfig index 0fc6bd4fcb7e..400c9e5b16ad 100644 --- a/drivers/pinctrl/realtek/Kconfig +++ b/drivers/pinctrl/realtek/Kconfig @@ -6,6 +6,7 @@ config PINCTRL_RTD default y select PINMUX select GENERIC_PINCONF + select REGMAP_MMIO config PINCTRL_RTD1619B tristate "Realtek DHC 1619B pin controller driver" diff --git a/drivers/platform/arm64/lenovo-thinkpad-t14s.c b/drivers/platform/arm64/lenovo-thinkpad-t14s.c index 1d5d11adaf32..cf6a1d3b2617 100644 --- a/drivers/platform/arm64/lenovo-thinkpad-t14s.c +++ b/drivers/platform/arm64/lenovo-thinkpad-t14s.c @@ -120,6 +120,7 @@ static int t14s_ec_write(void *context, unsigned int reg, if (ret < 0) return ret; + fsleep(10000); return 0; } @@ -157,6 +158,7 @@ static int t14s_ec_read(void *context, unsigned int reg, out: i2c_unlock_bus(client->adapter, I2C_LOCK_SEGMENT); + fsleep(10000); return ret; } @@ -191,6 +193,8 @@ static int t14s_ec_read_evt(struct t14s_ec *ec, u8 *val) if (ret < 0) goto out; + fsleep(10000); + ret = 0; out: @@ -557,12 +561,6 @@ static int t14s_ec_probe(struct i2c_client *client) return dev_err_probe(dev, PTR_ERR(ec->regmap), "Failed to init regmap\n"); - ret = devm_request_threaded_irq(dev, client->irq, NULL, - t14s_ec_irq_handler, - IRQF_ONESHOT, dev_name(dev), ec); - if (ret < 0) - return dev_err_probe(dev, ret, "Failed to get IRQ\n"); - ret = t14s_leds_probe(ec); if (ret < 0) return ret; @@ -579,6 +577,12 @@ static int t14s_ec_probe(struct i2c_client *client) if (ret < 0) return ret; + ret = devm_request_threaded_irq(dev, client->irq, NULL, + t14s_ec_irq_handler, + IRQF_ONESHOT, dev_name(dev), ec); + if (ret < 0) + return dev_err_probe(dev, ret, "Failed to get IRQ\n"); + /* * Disable wakeup support by default, because the driver currently does * not support masking any events and the laptop should not wake up when diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index c122016d82f1..c883a28e0916 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -545,6 +545,7 @@ config MSI_WMI config MSI_WMI_PLATFORM tristate "MSI WMI Platform features" depends on ACPI_WMI + depends on DMI depends on HWMON help Say Y here if you want to have support for WMI-based platform features diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 13eb22b35aa8..d848afc91f87 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -102,6 +102,7 @@ MODULE_ALIAS("wmi:676AA15E-6A47-4D9F-A2CC-1E6D18D14026"); enum acer_wmi_event_ids { WMID_HOTKEY_EVENT = 0x1, + WMID_BACKLIGHT_EVENT = 0x4, WMID_ACCEL_OR_KBD_DOCK_EVENT = 0x5, WMID_GAMING_TURBO_KEY_EVENT = 0x7, WMID_AC_EVENT = 0x8, @@ -2369,6 +2370,9 @@ static void acer_wmi_notify(union acpi_object *obj, void *context) sparse_keymap_report_event(acer_wmi_input_dev, scancode, 1, true); } break; + case WMID_BACKLIGHT_EVENT: + /* Already handled by acpi-video */ + break; case WMID_ACCEL_OR_KBD_DOCK_EVENT: acer_gsensor_event(); acer_kbd_dock_event(&return_value); diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index d63aaad7ef59..404e62ad293a 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -122,6 +122,14 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "21A1"), } }, + { + .ident = "ROG Xbox Ally RC73YA", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "RC73YA"), + } + }, /* https://bugzilla.kernel.org/show_bug.cgi?id=218024 */ { .ident = "V14 G4 AMN", @@ -204,6 +212,23 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "82ND"), } }, + /* https://gitlab.freedesktop.org/drm/amd/-/issues/4618 */ + { + .ident = "Lenovo Legion Go 2", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83N0"), + } + }, + { + .ident = "Lenovo Legion Go 2", + .driver_data = &quirk_s2idle_bug, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83N1"), + } + }, /* https://gitlab.freedesktop.org/drm/amd/-/issues/2684 */ { .ident = "HP Laptop 15s-eq2xxx", diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index bd318fd02ccf..cae3fcafd4d7 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -106,6 +106,7 @@ static void amd_pmc_get_ip_info(struct amd_pmc_dev *dev) switch (dev->cpu_id) { case AMD_CPU_ID_PCO: case AMD_CPU_ID_RN: + case AMD_CPU_ID_VG: case AMD_CPU_ID_YC: case AMD_CPU_ID_CB: dev->num_ips = 12; @@ -517,6 +518,7 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) case AMD_CPU_ID_PCO: return MSG_OS_HINT_PCO; case AMD_CPU_ID_RN: + case AMD_CPU_ID_VG: case AMD_CPU_ID_YC: case AMD_CPU_ID_CB: case AMD_CPU_ID_PS: @@ -717,6 +719,7 @@ static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RV) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_SP) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_SHP) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_VG) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, { } diff --git a/drivers/platform/x86/amd/pmc/pmc.h b/drivers/platform/x86/amd/pmc/pmc.h index 62f3e51020fd..fe3f53eb5955 100644 --- a/drivers/platform/x86/amd/pmc/pmc.h +++ b/drivers/platform/x86/amd/pmc/pmc.h @@ -156,6 +156,7 @@ void amd_mp2_stb_deinit(struct amd_pmc_dev *dev); #define AMD_CPU_ID_RN 0x1630 #define AMD_CPU_ID_PCO AMD_CPU_ID_RV #define AMD_CPU_ID_CZN AMD_CPU_ID_RN +#define AMD_CPU_ID_VG 0x1645 #define AMD_CPU_ID_YC 0x14B5 #define AMD_CPU_ID_CB 0x14D8 #define AMD_CPU_ID_PS 0x14E8 diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index f417dcc9af35..fadf7aac6779 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -90,34 +90,34 @@ static struct awcc_quirks empty_quirks; static const struct dmi_system_id awcc_dmi_table[] __initconst = { { - .ident = "Alienware Area-51m", + .ident = "Alienware 16 Aurora", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware 16 Aurora"), }, - .driver_data = &generic_quirks, + .driver_data = &g_series_quirks, }, { - .ident = "Alienware Area-51m R2", + .ident = "Alienware Area-51m", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m R2"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware m15 R5", + .ident = "Alienware m15", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R5"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware m15 R7", + .ident = "Alienware m16 R1 AMD", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R7"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), }, .driver_data = &generic_quirks, }, @@ -130,14 +130,6 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &g_series_quirks, }, { - .ident = "Alienware m16 R1 AMD", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"), - }, - .driver_data = &generic_quirks, - }, - { .ident = "Alienware m16 R2", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -146,114 +138,66 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &generic_quirks, }, { - .ident = "Alienware m17 R5", + .ident = "Alienware m17", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware m18 R2", + .ident = "Alienware m18", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18 R2"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware x15 R1", + .ident = "Alienware x15", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x15 R1"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x15"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware x15 R2", + .ident = "Alienware x17", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x15 R2"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x17"), }, .driver_data = &generic_quirks, }, { - .ident = "Alienware x17 R2", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), - DMI_MATCH(DMI_PRODUCT_NAME, "Alienware x17 R2"), - }, - .driver_data = &generic_quirks, - }, - { - .ident = "Dell Inc. G15 5510", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5510"), - }, - .driver_data = &g_series_quirks, - }, - { - .ident = "Dell Inc. G15 5511", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5511"), - }, - .driver_data = &g_series_quirks, - }, - { - .ident = "Dell Inc. G15 5515", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5515"), - }, - .driver_data = &g_series_quirks, - }, - { - .ident = "Dell Inc. G15 5530", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5530"), - }, - .driver_data = &g_series_quirks, - }, - { - .ident = "Dell Inc. G16 7630", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Dell G16 7630"), - }, - .driver_data = &g_series_quirks, - }, - { - .ident = "Dell Inc. G3 3500", + .ident = "Dell Inc. G15", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "G3 3500"), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15"), }, .driver_data = &g_series_quirks, }, { - .ident = "Dell Inc. G3 3590", + .ident = "Dell Inc. G16", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "G3 3590"), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell G16"), }, .driver_data = &g_series_quirks, }, { - .ident = "Dell Inc. G5 5500", + .ident = "Dell Inc. G3", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "G5 5500"), + DMI_MATCH(DMI_PRODUCT_NAME, "G3"), }, .driver_data = &g_series_quirks, }, { - .ident = "Dell Inc. G5 5505", + .ident = "Dell Inc. G5", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "G5 5505"), + DMI_MATCH(DMI_PRODUCT_NAME, "G5"), }, .driver_data = &g_series_quirks, }, diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 8b3533d6ba09..ad9d9f97960f 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -92,9 +92,11 @@ static const char * const victus_thermal_profile_boards[] = { "8A25" }; -/* DMI Board names of Victus 16-r1000 and Victus 16-s1000 laptops */ +/* DMI Board names of Victus 16-r and Victus 16-s laptops */ static const char * const victus_s_thermal_profile_boards[] = { - "8C99", "8C9C" + "8BBE", "8BD4", "8BD5", + "8C78", "8C99", "8C9C", + "8D41", }; enum hp_wmi_radio { diff --git a/drivers/platform/x86/huawei-wmi.c b/drivers/platform/x86/huawei-wmi.c index c3772df34679..8a4c54089ace 100644 --- a/drivers/platform/x86/huawei-wmi.c +++ b/drivers/platform/x86/huawei-wmi.c @@ -81,6 +81,10 @@ static const struct key_entry huawei_wmi_keymap[] = { { KE_KEY, 0x289, { KEY_WLAN } }, // Huawei |M| key { KE_KEY, 0x28a, { KEY_CONFIG } }, + // HONOR YOYO key + { KE_KEY, 0x28b, { KEY_NOTIFICATION_CENTER } }, + // HONOR print screen + { KE_KEY, 0x28e, { KEY_PRINT } }, // Keyboard backlit { KE_IGNORE, 0x293, { KEY_KBDILLUMTOGGLE } }, { KE_IGNORE, 0x294, { KEY_KBDILLUMUP } }, diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index f25a427cccda..9c07a7faf18f 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -55,6 +55,7 @@ static const struct acpi_device_id intel_hid_ids[] = { { "INTC10CB" }, { "INTC10CC" }, { "INTC10F1" }, + { "INTC10F2" }, { } }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids); diff --git a/drivers/platform/x86/intel/punit_ipc.c b/drivers/platform/x86/intel/punit_ipc.c index bafac8aa2baf..14513010daad 100644 --- a/drivers/platform/x86/intel/punit_ipc.c +++ b/drivers/platform/x86/intel/punit_ipc.c @@ -250,7 +250,7 @@ static int intel_punit_ipc_probe(struct platform_device *pdev) } else { ret = devm_request_irq(&pdev->dev, irq, intel_punit_ioc, IRQF_NO_SUSPEND, "intel_punit_ipc", - &punit_ipcdev); + punit_ipcdev); if (ret) { dev_err(&pdev->dev, "Failed to request irq: %d\n", irq); return ret; diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c b/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c index 3f4343147dad..950ede5eab76 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c @@ -108,11 +108,11 @@ static int isst_if_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = pci_read_config_dword(pdev, 0xD0, &mmio_base); if (ret) - return ret; + return pcibios_err_to_errno(ret); ret = pci_read_config_dword(pdev, 0xFC, &pcu_base); if (ret) - return ret; + return pcibios_err_to_errno(ret); pcu_base &= GENMASK(10, 0); base_addr = (u64)mmio_base << 23 | (u64) pcu_base << 12; diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h index 70ae11519837..0abe850ef54e 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.h @@ -40,7 +40,7 @@ * @agent_type_mask: Bit mask of all hardware agents for this domain * @uncore_attr_group: Attribute group storage * @max_freq_khz_kobj_attr: Storage for kobject attribute max_freq_khz - * @mix_freq_khz_kobj_attr: Storage for kobject attribute min_freq_khz + * @min_freq_khz_kobj_attr: Storage for kobject attribute min_freq_khz * @initial_max_freq_khz_kobj_attr: Storage for kobject attribute initial_max_freq_khz * @initial_min_freq_khz_kobj_attr: Storage for kobject attribute initial_min_freq_khz * @current_freq_khz_kobj_attr: Storage for kobject attribute current_freq_khz @@ -48,13 +48,14 @@ * @fabric_cluster_id_kobj_attr: Storage for kobject attribute fabric_cluster_id * @package_id_kobj_attr: Storage for kobject attribute package_id * @elc_low_threshold_percent_kobj_attr: - Storage for kobject attribute elc_low_threshold_percent + * Storage for kobject attribute elc_low_threshold_percent * @elc_high_threshold_percent_kobj_attr: - Storage for kobject attribute elc_high_threshold_percent + * Storage for kobject attribute elc_high_threshold_percent * @elc_high_threshold_enable_kobj_attr: - Storage for kobject attribute elc_high_threshold_enable + * Storage for kobject attribute elc_high_threshold_enable * @elc_floor_freq_khz_kobj_attr: Storage for kobject attribute elc_floor_freq_khz * @agent_types_kobj_attr: Storage for kobject attribute agent_type + * @die_id_kobj_attr: Attribute storage for die_id information * @uncore_attrs: Attribute storage for group creation * * This structure is used to encapsulate all data related to uncore sysfs diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c index 2a6897035150..0dfc552b2802 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency.c @@ -256,6 +256,10 @@ static const struct x86_cpu_id intel_uncore_cpu_ids[] = { X86_MATCH_VFM(INTEL_ARROWLAKE, NULL), X86_MATCH_VFM(INTEL_ARROWLAKE_H, NULL), X86_MATCH_VFM(INTEL_LUNARLAKE_M, NULL), + X86_MATCH_VFM(INTEL_PANTHERLAKE_L, NULL), + X86_MATCH_VFM(INTEL_WILDCATLAKE_L, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE, NULL), + X86_MATCH_VFM(INTEL_NOVALAKE_L, NULL), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_cpu_ids); diff --git a/drivers/platform/x86/msi-wmi-platform.c b/drivers/platform/x86/msi-wmi-platform.c index dc5e9878cb68..e912fcc12d12 100644 --- a/drivers/platform/x86/msi-wmi-platform.c +++ b/drivers/platform/x86/msi-wmi-platform.c @@ -14,6 +14,7 @@ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/device/driver.h> +#include <linux/dmi.h> #include <linux/errno.h> #include <linux/hwmon.h> #include <linux/kernel.h> @@ -28,7 +29,7 @@ #define DRIVER_NAME "msi-wmi-platform" -#define MSI_PLATFORM_GUID "ABBC0F6E-8EA1-11d1-00A0-C90629100000" +#define MSI_PLATFORM_GUID "ABBC0F6E-8EA1-11D1-00A0-C90629100000" #define MSI_WMI_PLATFORM_INTERFACE_VERSION 2 @@ -448,7 +449,45 @@ static struct wmi_driver msi_wmi_platform_driver = { .probe = msi_wmi_platform_probe, .no_singleton = true, }; -module_wmi_driver(msi_wmi_platform_driver); + +/* + * MSI reused the WMI GUID from the WMI-ACPI sample code provided by Microsoft, + * so other manufacturers might use it as well for their WMI-ACPI implementations. + */ +static const struct dmi_system_id msi_wmi_platform_whitelist[] __initconst = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MICRO-STAR INT"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star International"), + }, + }, + { } +}; + +static int __init msi_wmi_platform_module_init(void) +{ + if (!dmi_check_system(msi_wmi_platform_whitelist)) { + if (!force) + return -ENODEV; + + pr_warn("Ignoring DMI whitelist\n"); + } + + return wmi_driver_register(&msi_wmi_platform_driver); +} + +static void __exit msi_wmi_platform_module_exit(void) +{ + wmi_driver_unregister(&msi_wmi_platform_driver); +} + +module_init(msi_wmi_platform_module_init); +module_exit(msi_wmi_platform_module_exit); + MODULE_AUTHOR("Armin Wolf <W_Armin@gmx.de>"); MODULE_DESCRIPTION("MSI WMI platform features"); diff --git a/drivers/pmdomain/arm/scmi_pm_domain.c b/drivers/pmdomain/arm/scmi_pm_domain.c index 8fe1c0a501c9..b5e2ffd5ea64 100644 --- a/drivers/pmdomain/arm/scmi_pm_domain.c +++ b/drivers/pmdomain/arm/scmi_pm_domain.c @@ -41,7 +41,7 @@ static int scmi_pd_power_off(struct generic_pm_domain *domain) static int scmi_pm_domain_probe(struct scmi_device *sdev) { - int num_domains, i; + int num_domains, i, ret; struct device *dev = &sdev->dev; struct device_node *np = dev->of_node; struct scmi_pm_domain *scmi_pd; @@ -108,9 +108,18 @@ static int scmi_pm_domain_probe(struct scmi_device *sdev) scmi_pd_data->domains = domains; scmi_pd_data->num_domains = num_domains; + ret = of_genpd_add_provider_onecell(np, scmi_pd_data); + if (ret) + goto err_rm_genpds; + dev_set_drvdata(dev, scmi_pd_data); - return of_genpd_add_provider_onecell(np, scmi_pd_data); + return 0; +err_rm_genpds: + for (i = num_domains - 1; i >= 0; i--) + pm_genpd_remove(domains[i]); + + return ret; } static void scmi_pm_domain_remove(struct scmi_device *sdev) diff --git a/drivers/pmdomain/imx/gpc.c b/drivers/pmdomain/imx/gpc.c index 33991f3c6b55..a34b260274f7 100644 --- a/drivers/pmdomain/imx/gpc.c +++ b/drivers/pmdomain/imx/gpc.c @@ -536,6 +536,8 @@ static void imx_gpc_remove(struct platform_device *pdev) return; } } + + of_node_put(pgc_node); } static struct platform_driver imx_gpc_driver = { diff --git a/drivers/pmdomain/samsung/exynos-pm-domains.c b/drivers/pmdomain/samsung/exynos-pm-domains.c index 5d478bb37ad6..5c3aa8983087 100644 --- a/drivers/pmdomain/samsung/exynos-pm-domains.c +++ b/drivers/pmdomain/samsung/exynos-pm-domains.c @@ -92,13 +92,14 @@ static const struct of_device_id exynos_pm_domain_of_match[] = { { }, }; -static const char *exynos_get_domain_name(struct device_node *node) +static const char *exynos_get_domain_name(struct device *dev, + struct device_node *node) { const char *name; if (of_property_read_string(node, "label", &name) < 0) name = kbasename(node->full_name); - return kstrdup_const(name, GFP_KERNEL); + return devm_kstrdup_const(dev, name, GFP_KERNEL); } static int exynos_pd_probe(struct platform_device *pdev) @@ -115,20 +116,27 @@ static int exynos_pd_probe(struct platform_device *pdev) if (!pd) return -ENOMEM; - pd->pd.name = exynos_get_domain_name(np); + pd->pd.name = exynos_get_domain_name(dev, np); if (!pd->pd.name) return -ENOMEM; pd->base = of_iomap(np, 0); - if (!pd->base) { - kfree_const(pd->pd.name); + if (!pd->base) return -ENODEV; - } pd->pd.power_off = exynos_pd_power_off; pd->pd.power_on = exynos_pd_power_on; pd->local_pwr_cfg = pm_domain_cfg->local_pwr_cfg; + /* + * Some Samsung platforms with bootloaders turning on the splash-screen + * and handing it over to the kernel, requires the power-domains to be + * reset during boot. + */ + if (IS_ENABLED(CONFIG_ARM) && + of_device_is_compatible(np, "samsung,exynos4210-pd")) + exynos_pd_power_off(&pd->pd); + on = readl_relaxed(pd->base + 0x4) & pd->local_pwr_cfg; pm_genpd_init(&pd->pd, NULL, !on); @@ -147,15 +155,6 @@ static int exynos_pd_probe(struct platform_device *pdev) parent.np, child.np); } - /* - * Some Samsung platforms with bootloaders turning on the splash-screen - * and handing it over to the kernel, requires the power-domains to be - * reset during boot. As a temporary hack to manage this, let's enforce - * a sync_state. - */ - if (!ret) - of_genpd_sync_state(np); - pm_runtime_enable(dev); return ret; } diff --git a/drivers/power/supply/intel_dc_ti_battery.c b/drivers/power/supply/intel_dc_ti_battery.c index 56b0c92e9d28..67a75281b0ac 100644 --- a/drivers/power/supply/intel_dc_ti_battery.c +++ b/drivers/power/supply/intel_dc_ti_battery.c @@ -127,7 +127,8 @@ struct dc_ti_battery_chip { static int dc_ti_battery_get_voltage_and_current_now(struct power_supply *psy, int *volt, int *curr) { struct dc_ti_battery_chip *chip = power_supply_get_drvdata(psy); - s64 cnt_start_usec, now_usec, sleep_usec; + ktime_t ktime; + s64 sleep_usec; unsigned int reg_val; s32 acc, smpl_ctr; int ret; @@ -141,16 +142,17 @@ static int dc_ti_battery_get_voltage_and_current_now(struct power_supply *psy, i if (ret) goto out_err; - cnt_start_usec = ktime_get_ns() / NSEC_PER_USEC; + ktime = ktime_get(); /* Read Vbat, convert IIO mV to power-supply ųV */ ret = iio_read_channel_processed_scale(chip->vbat_channel, volt, 1000); if (ret < 0) goto out_err; + ktime = ktime_sub(ktime_get(), ktime); + /* Sleep at least 3 sample-times + slack to get 3+ CC samples */ - now_usec = ktime_get_ns() / NSEC_PER_USEC; - sleep_usec = 3 * SMPL_INTVL_US + SLEEP_SLACK_US - (now_usec - cnt_start_usec); + sleep_usec = 3 * SMPL_INTVL_US + SLEEP_SLACK_US - ktime_to_us(ktime); if (sleep_usec > 0 && sleep_usec < 1000000) usleep_range(sleep_usec, sleep_usec + SLEEP_SLACK_US); diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index 68f1f7fdaa9d..790eb42b78db 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -328,9 +328,31 @@ static u64 ines_find_txts(struct ines_port *port, struct sk_buff *skb) return ns; } -static int ines_hwtstamp(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack) +static int ines_hwtstamp_get(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg) +{ + struct ines_port *port = container_of(mii_ts, struct ines_port, mii_ts); + unsigned long flags; + u32 port_conf; + + cfg->rx_filter = port->rxts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT + : HWTSTAMP_FILTER_NONE; + if (port->txts_enabled) { + spin_lock_irqsave(&port->lock, flags); + port_conf = ines_read32(port, port_conf); + spin_unlock_irqrestore(&port->lock, flags); + cfg->tx_type = (port_conf & CM_ONE_STEP) ? HWTSTAMP_TX_ONESTEP_P2P + : HWTSTAMP_TX_OFF; + } else { + cfg->tx_type = HWTSTAMP_TX_OFF; + } + + return 0; +} + +static int ines_hwtstamp_set(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct ines_port *port = container_of(mii_ts, struct ines_port, mii_ts); u32 cm_one_step = 0, port_conf, ts_stat_rx, ts_stat_tx; @@ -709,7 +731,8 @@ static struct mii_timestamper *ines_ptp_probe_channel(struct device *device, } port->mii_ts.rxtstamp = ines_rxtstamp; port->mii_ts.txtstamp = ines_txtstamp; - port->mii_ts.hwtstamp = ines_hwtstamp; + port->mii_ts.hwtstamp_set = ines_hwtstamp_set; + port->mii_ts.hwtstamp_get = ines_hwtstamp_get; port->mii_ts.link_state = ines_link_state; port->mii_ts.ts_info = ines_ts_info; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index eeebe4d149f7..bf8187c963aa 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -25,8 +25,7 @@ #include <linux/crc16.h> #include <linux/dpll.h> -#define PCI_VENDOR_ID_FACEBOOK 0x1d9b -#define PCI_DEVICE_ID_FACEBOOK_TIMECARD 0x0400 +#define PCI_DEVICE_ID_META_TIMECARD 0x0400 #define PCI_VENDOR_ID_CELESTICA 0x18d4 #define PCI_DEVICE_ID_CELESTICA_TIMECARD 0x1008 @@ -1030,7 +1029,7 @@ static struct ocp_resource ocp_adva_resource[] = { }; static const struct pci_device_id ptp_ocp_pcidev_id[] = { - { PCI_DEVICE_DATA(FACEBOOK, TIMECARD, &ocp_fb_resource) }, + { PCI_DEVICE_DATA(META, TIMECARD, &ocp_fb_resource) }, { PCI_DEVICE_DATA(CELESTICA, TIMECARD, &ocp_fb_resource) }, { PCI_DEVICE_DATA(OROLIA, ARTCARD, &ocp_art_resource) }, { PCI_DEVICE_DATA(ADVA, TIMECARD, &ocp_adva_resource) }, @@ -2225,6 +2224,9 @@ ptp_ocp_ts_enable(void *priv, u32 req, bool enable) static void ptp_ocp_unregister_ext(struct ptp_ocp_ext_src *ext) { + if (!ext) + return; + ext->info->enable(ext, ~0, false); pci_free_irq(ext->bp->pdev, ext->irq_vec, ext); kfree(ext); @@ -3250,20 +3252,16 @@ signal_show(struct device *dev, struct device_attribute *attr, char *buf) struct dev_ext_attribute *ea = to_ext_attr(attr); struct ptp_ocp *bp = dev_get_drvdata(dev); struct ptp_ocp_signal *signal; + int gen = (uintptr_t)ea->var; struct timespec64 ts; - ssize_t count; - int i; - - i = (uintptr_t)ea->var; - signal = &bp->signal[i]; - count = sysfs_emit(buf, "%llu %d %llu %d", signal->period, - signal->duty, signal->phase, signal->polarity); + signal = &bp->signal[gen]; ts = ktime_to_timespec64(signal->start); - count += sysfs_emit_at(buf, count, " %ptT TAI\n", &ts); - return count; + return sysfs_emit(buf, "%llu %d %llu %d %ptT TAI\n", + signal->period, signal->duty, signal->phase, signal->polarity, + &ts.tv_sec); } static EXT_ATTR_RW(signal, signal, 0); static EXT_ATTR_RW(signal, signal, 1); @@ -4562,21 +4560,14 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_detach_sysfs(bp); ptp_ocp_attr_group_del(bp); timer_delete_sync(&bp->watchdog); - if (bp->ts0) - ptp_ocp_unregister_ext(bp->ts0); - if (bp->ts1) - ptp_ocp_unregister_ext(bp->ts1); - if (bp->ts2) - ptp_ocp_unregister_ext(bp->ts2); - if (bp->ts3) - ptp_ocp_unregister_ext(bp->ts3); - if (bp->ts4) - ptp_ocp_unregister_ext(bp->ts4); - if (bp->pps) - ptp_ocp_unregister_ext(bp->pps); + ptp_ocp_unregister_ext(bp->ts0); + ptp_ocp_unregister_ext(bp->ts1); + ptp_ocp_unregister_ext(bp->ts2); + ptp_ocp_unregister_ext(bp->ts3); + ptp_ocp_unregister_ext(bp->ts4); + ptp_ocp_unregister_ext(bp->pps); for (i = 0; i < 4; i++) - if (bp->signal_out[i]) - ptp_ocp_unregister_ext(bp->signal_out[i]); + ptp_ocp_unregister_ext(bp->signal_out[i]); for (i = 0; i < __PORT_COUNT; i++) if (bp->port[i].line != -1) serial8250_unregister_port(bp->port[i].line); @@ -4829,8 +4820,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; out_dpll: - while (i) { - --i; + while (i--) { dpll_pin_unregister(bp->dpll, bp->sma[i].dpll_pin, &dpll_pins_ops, &bp->sma[i]); dpll_pin_put(bp->sma[i].dpll_pin); } diff --git a/drivers/pwm/pwm-adp5585.c b/drivers/pwm/pwm-adp5585.c index dc2860979e24..806f8d79b0d7 100644 --- a/drivers/pwm/pwm-adp5585.c +++ b/drivers/pwm/pwm-adp5585.c @@ -190,13 +190,13 @@ static int adp5585_pwm_probe(struct platform_device *pdev) return 0; } -static const struct adp5585_pwm_chip adp5589_pwm_chip_info = { +static const struct adp5585_pwm_chip adp5585_pwm_chip_info = { .pwm_cfg = ADP5585_PWM_CFG, .pwm_offt_low = ADP5585_PWM_OFFT_LOW, .pwm_ont_low = ADP5585_PWM_ONT_LOW, }; -static const struct adp5585_pwm_chip adp5585_pwm_chip_info = { +static const struct adp5585_pwm_chip adp5589_pwm_chip_info = { .pwm_cfg = ADP5589_PWM_CFG, .pwm_offt_low = ADP5589_PWM_OFFT_LOW, .pwm_ont_low = ADP5589_PWM_ONT_LOW, diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c index 1cb647ed70c6..a2d16e9abfb5 100644 --- a/drivers/regulator/fixed.c +++ b/drivers/regulator/fixed.c @@ -334,6 +334,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev) ret = dev_err_probe(&pdev->dev, PTR_ERR(drvdata->dev), "Failed to register regulator: %ld\n", PTR_ERR(drvdata->dev)); + gpiod_put(cfg.ena_gpiod); return ret; } diff --git a/drivers/reset/reset-imx8mp-audiomix.c b/drivers/reset/reset-imx8mp-audiomix.c index 6b357adfe646..eceb37ff5dc5 100644 --- a/drivers/reset/reset-imx8mp-audiomix.c +++ b/drivers/reset/reset-imx8mp-audiomix.c @@ -14,8 +14,8 @@ #include <linux/reset-controller.h> #define IMX8MP_AUDIOMIX_EARC_RESET_OFFSET 0x200 -#define IMX8MP_AUDIOMIX_EARC_RESET_MASK BIT(1) -#define IMX8MP_AUDIOMIX_EARC_PHY_RESET_MASK BIT(2) +#define IMX8MP_AUDIOMIX_EARC_RESET_MASK BIT(0) +#define IMX8MP_AUDIOMIX_EARC_PHY_RESET_MASK BIT(1) #define IMX8MP_AUDIOMIX_DSP_RUNSTALL_OFFSET 0x108 #define IMX8MP_AUDIOMIX_DSP_RUNSTALL_MASK BIT(5) diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 0aeafa772fb1..407b7c516658 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -701,7 +701,6 @@ static void mpc_rcvd_sweep_req(struct mpcg_info *mpcginfo) grp->sweep_req_pend_num--; ctcmpc_send_sweep_resp(ch); - kfree(mpcginfo); return; } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index edc0bcd46923..10b53bba373c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -761,7 +761,7 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, if (rc) QETH_DBF_MESSAGE(2, "IPA: %s(%#x) for device %x returned %#x \"%s\"\n", ipa_name, com, CARD_DEVID(card), rc, - qeth_get_ipa_msg(rc)); + qeth_get_ipa_msg(com, rc)); else QETH_DBF_MESSAGE(5, "IPA: %s(%#x) for device %x succeeded\n", ipa_name, com, CARD_DEVID(card)); diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c index d9266f7d8187..1add124e033b 100644 --- a/drivers/s390/net/qeth_core_mpc.c +++ b/drivers/s390/net/qeth_core_mpc.c @@ -139,82 +139,237 @@ struct ipa_rc_msg { const char *msg; }; -static const struct ipa_rc_msg qeth_ipa_rc_msg[] = { +static const struct ipa_rc_msg qeth_ipa_rc_def_msg[] = { {IPA_RC_SUCCESS, "success"}, {IPA_RC_NOTSUPP, "Command not supported"}, - {IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"}, - {IPA_RC_UNKNOWN_ERROR, "IPA command failed - reason unknown"}, {IPA_RC_UNSUPPORTED_COMMAND, "Command not supported"}, - {IPA_RC_VNICC_OOSEQ, "Command issued out of sequence"}, - {IPA_RC_INVALID_FORMAT, "invalid format or length"}, {IPA_RC_DUP_IPV6_REMOTE, "ipv6 address already registered remote"}, - {IPA_RC_SBP_IQD_NOT_CONFIGURED, "Not configured for bridgeport"}, {IPA_RC_DUP_IPV6_HOME, "ipv6 address already registered"}, {IPA_RC_UNREGISTERED_ADDR, "Address not registered"}, - {IPA_RC_NO_ID_AVAILABLE, "No identifiers available"}, {IPA_RC_ID_NOT_FOUND, "Identifier not found"}, - {IPA_RC_SBP_IQD_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, - {IPA_RC_SBP_IQD_CURRENT_SECOND, "Bridgeport is currently secondary"}, - {IPA_RC_SBP_IQD_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, - {IPA_RC_INVALID_IP_VERSION, "IP version incorrect"}, - {IPA_RC_SBP_IQD_CURRENT_PRIMARY, "Bridgeport is currently primary"}, {IPA_RC_LAN_FRAME_MISMATCH, "LAN and frame mismatch"}, - {IPA_RC_SBP_IQD_NO_QDIO_QUEUES, "QDIO queues not established"}, {IPA_RC_L2_UNSUPPORTED_CMD, "Unsupported layer 2 command"}, - {IPA_RC_L2_DUP_MAC, "Duplicate MAC address"}, {IPA_RC_L2_ADDR_TABLE_FULL, "Layer2 address table full"}, - {IPA_RC_L2_DUP_LAYER3_MAC, "Duplicate with layer 3 MAC"}, - {IPA_RC_L2_GMAC_NOT_FOUND, "GMAC not found"}, - {IPA_RC_L2_MAC_NOT_AUTH_BY_HYP, "L2 mac not authorized by hypervisor"}, {IPA_RC_L2_MAC_NOT_AUTH_BY_ADP, "L2 mac not authorized by adapter"}, - {IPA_RC_L2_MAC_NOT_FOUND, "L2 mac address not found"}, - {IPA_RC_L2_INVALID_VLAN_ID, "L2 invalid vlan id"}, - {IPA_RC_L2_DUP_VLAN_ID, "L2 duplicate vlan id"}, - {IPA_RC_L2_VLAN_ID_NOT_FOUND, "L2 vlan id not found"}, - {IPA_RC_VNICC_VNICBP, "VNIC is BridgePort"}, - {IPA_RC_SBP_OSA_NOT_CONFIGURED, "Not configured for bridgeport"}, - {IPA_RC_SBP_OSA_OS_MISMATCH, "OS mismatch"}, - {IPA_RC_SBP_OSA_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, - {IPA_RC_SBP_OSA_CURRENT_SECOND, "Bridgeport is currently secondary"}, - {IPA_RC_SBP_OSA_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, - {IPA_RC_SBP_OSA_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, - {IPA_RC_SBP_OSA_CURRENT_PRIMARY, "Bridgeport is currently primary"}, - {IPA_RC_SBP_OSA_NO_QDIO_QUEUES, "QDIO queues not established"}, {IPA_RC_DATA_MISMATCH, "Data field mismatch (v4/v6 mixed)"}, {IPA_RC_INVALID_MTU_SIZE, "Invalid MTU size"}, {IPA_RC_INVALID_LANTYPE, "Invalid LAN type"}, {IPA_RC_INVALID_LANNUM, "Invalid LAN num"}, - {IPA_RC_DUPLICATE_IP_ADDRESS, "Address already registered"}, - {IPA_RC_IP_ADDR_TABLE_FULL, "IP address table full"}, {IPA_RC_LAN_PORT_STATE_ERROR, "LAN port state error"}, {IPA_RC_SETIP_NO_STARTLAN, "Setip no startlan received"}, {IPA_RC_SETIP_ALREADY_RECEIVED, "Setip already received"}, - {IPA_RC_IP_ADDR_ALREADY_USED, "IP address already in use on LAN"}, - {IPA_RC_MC_ADDR_NOT_FOUND, "Multicast address not found"}, {IPA_RC_SETIP_INVALID_VERSION, "SETIP invalid IP version"}, {IPA_RC_UNSUPPORTED_SUBCMD, "Unsupported assist subcommand"}, {IPA_RC_ARP_ASSIST_NO_ENABLE, "Only partial success, no enable"}, - {IPA_RC_PRIMARY_ALREADY_DEFINED, "Primary already defined"}, - {IPA_RC_SECOND_ALREADY_DEFINED, "Secondary already defined"}, - {IPA_RC_INVALID_SETRTG_INDICATOR, "Invalid SETRTG indicator"}, - {IPA_RC_MC_ADDR_ALREADY_DEFINED, "Multicast address already defined"}, - {IPA_RC_LAN_OFFLINE, "STRTLAN_LAN_DISABLED - LAN offline"}, - {IPA_RC_VEPA_TO_VEB_TRANSITION, "Adj. switch disabled port mode RR"}, {IPA_RC_INVALID_IP_VERSION2, "Invalid IP version"}, /* default for qeth_get_ipa_msg(): */ {IPA_RC_FFFF, "Unknown Error"} }; -const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc) +static const struct ipa_rc_msg qeth_ipa_rc_adp_parms_msg[] = { + {IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_diag_ass_msg[] = { + {IPA_RC_INVALID_FORMAT, "invalid format or length"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_addr_msg[] = { + {IPA_RC_UNKNOWN_ERROR, "IPA command failed - reason unknown"}, + {IPA_RC_NO_ID_AVAILABLE, "No identifiers available"}, + {IPA_RC_INVALID_IP_VERSION, "IP version incorrect"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_vnicc_msg[] = { + {IPA_RC_VNICC_OOSEQ, "Command issued out of sequence"}, + {IPA_RC_VNICC_VNICBP, "VNIC is BridgePort"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_sbp_iqd_msg[] = { + {IPA_RC_SBP_IQD_NOT_CONFIGURED, "Not configured for bridgeport"}, + {IPA_RC_SBP_IQD_OS_MISMATCH, "OS mismatch"}, + {IPA_RC_SBP_IQD_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, + {IPA_RC_SBP_IQD_CURRENT_SECOND, "Bridgeport is currently secondary"}, + {IPA_RC_SBP_IQD_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, + {IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, + {IPA_RC_SBP_IQD_CURRENT_PRIMARY, "Bridgeport is currently primary"}, + {IPA_RC_SBP_IQD_NO_QDIO_QUEUES, "QDIO queues not established"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_sbp_osa_msg[] = { + {IPA_RC_SBP_OSA_NOT_CONFIGURED, "Not configured for bridgeport"}, + {IPA_RC_SBP_OSA_OS_MISMATCH, "OS mismatch"}, + {IPA_RC_SBP_OSA_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, + {IPA_RC_SBP_OSA_CURRENT_SECOND, "Bridgeport is currently secondary"}, + {IPA_RC_SBP_OSA_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, + {IPA_RC_SBP_OSA_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, + {IPA_RC_SBP_OSA_CURRENT_PRIMARY, "Bridgeport is currently primary"}, + {IPA_RC_SBP_OSA_NO_QDIO_QUEUES, "QDIO queues not established"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_mac_msg[] = { + {IPA_RC_L2_DUP_MAC, "Duplicate MAC address"}, + {IPA_RC_L2_DUP_LAYER3_MAC, "Duplicate with layer 3 MAC"}, + {IPA_RC_L2_GMAC_NOT_FOUND, "GMAC not found"}, + {IPA_RC_L2_MAC_NOT_AUTH_BY_HYP, "L2 mac not authorized by hypervisor"}, + {IPA_RC_L2_MAC_NOT_FOUND, "L2 mac address not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_ip_msg[] = { + {IPA_RC_DUPLICATE_IP_ADDRESS, "Address already registered"}, + {IPA_RC_IP_ADDR_TABLE_FULL, "IP address table full"}, + {IPA_RC_IP_ADDR_ALREADY_USED, "IP address already in use on LAN"}, + {IPA_RC_MC_ADDR_NOT_FOUND, "Multicast address not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_lan_msg[] = { + {IPA_RC_LAN_OFFLINE, "STRTLAN_LAN_DISABLED - LAN offline"}, + {IPA_RC_VEPA_TO_VEB_TRANSITION, "Adj. switch disabled port mode RR"}, +}; + +static const struct ipa_rc_msg qeth_ipa_rc_vlan_msg[] = { + {IPA_RC_L2_INVALID_VLAN_ID, "L2 invalid vlan id"}, + {IPA_RC_L2_DUP_VLAN_ID, "L2 duplicate vlan id"}, + {IPA_RC_L2_VLAN_ID_NOT_FOUND, "L2 vlan id not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_rtg_msg[] = { + {IPA_RC_PRIMARY_ALREADY_DEFINED, "Primary already defined"}, + {IPA_RC_SECOND_ALREADY_DEFINED, "Secondary already defined"}, + {IPA_RC_INVALID_SETRTG_INDICATOR, "Invalid SETRTG indicator"}, + {IPA_RC_MC_ADDR_ALREADY_DEFINED, "Multicast address already defined"} +}; + +struct ipa_cmd_rc_map { + enum qeth_ipa_cmds cmd; + const struct ipa_rc_msg *msg_arr; + const size_t arr_len; +}; + +static const struct ipa_cmd_rc_map qeth_ipa_cmd_rc_map[] = { + { + .cmd = IPA_CMD_SETADAPTERPARMS, + .msg_arr = qeth_ipa_rc_adp_parms_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_adp_parms_msg) + }, + { + .cmd = IPA_CMD_SET_DIAG_ASS, + .msg_arr = qeth_ipa_rc_diag_ass_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_diag_ass_msg) + }, + { + .cmd = IPA_CMD_CREATE_ADDR, + .msg_arr = qeth_ipa_rc_addr_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_addr_msg) + }, + { + .cmd = IPA_CMD_DESTROY_ADDR, + .msg_arr = qeth_ipa_rc_addr_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_addr_msg) + }, + { + .cmd = IPA_CMD_VNICC, + .msg_arr = qeth_ipa_rc_vnicc_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vnicc_msg) + }, + { + .cmd = IPA_CMD_SETBRIDGEPORT_IQD, + .msg_arr = qeth_ipa_rc_sbp_iqd_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_sbp_iqd_msg) + }, + { + .cmd = IPA_CMD_SETBRIDGEPORT_OSA, + .msg_arr = qeth_ipa_rc_sbp_osa_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_sbp_osa_msg) + }, + { + .cmd = IPA_CMD_SETVMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_DELVMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_SETGMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_DELGMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_SETIP, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_SETIPM, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_DELIPM, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_STARTLAN, + .msg_arr = qeth_ipa_rc_lan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_lan_msg) + }, + { + .cmd = IPA_CMD_STOPLAN, + .msg_arr = qeth_ipa_rc_lan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_lan_msg) + }, + { + .cmd = IPA_CMD_SETVLAN, + .msg_arr = qeth_ipa_rc_vlan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vlan_msg) + }, + { + .cmd = IPA_CMD_DELVLAN, + .msg_arr = qeth_ipa_rc_vlan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vlan_msg) + }, + { + .cmd = IPA_CMD_SETRTG, + .msg_arr = qeth_ipa_rc_rtg_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_rtg_msg) + } +}; + +const char *qeth_get_ipa_msg(enum qeth_ipa_cmds cmd, + enum qeth_ipa_return_codes rc) { int x; + const struct ipa_rc_msg *msg_arr = NULL; + size_t arr_len = 0; - for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_msg) - 1; x++) - if (qeth_ipa_rc_msg[x].rc == rc) - return qeth_ipa_rc_msg[x].msg; - return qeth_ipa_rc_msg[x].msg; -} + for (x = 0; x < ARRAY_SIZE(qeth_ipa_cmd_rc_map); x++) { + if (qeth_ipa_cmd_rc_map[x].cmd == cmd) { + msg_arr = qeth_ipa_cmd_rc_map[x].msg_arr; + arr_len = qeth_ipa_cmd_rc_map[x].arr_len; + break; + } + } + for (x = 0; x < arr_len; x++) { + if (msg_arr[x].rc == rc) + return msg_arr[x].msg; + } + + for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_def_msg) - 1; x++) { + if (qeth_ipa_rc_def_msg[x].rc == rc) + return qeth_ipa_rc_def_msg[x].msg; + } + return qeth_ipa_rc_def_msg[x].msg; +} struct ipa_cmd_names { enum qeth_ipa_cmds cmd; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 6257f00786b3..252fc84e6eca 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -159,13 +159,17 @@ enum qeth_ipa_return_codes { IPA_RC_SUCCESS = 0x0000, IPA_RC_NOTSUPP = 0x0001, IPA_RC_IP_TABLE_FULL = 0x0002, + IPA_RC_INVALID_SUBCMD = 0x0002, IPA_RC_UNKNOWN_ERROR = 0x0003, + IPA_RC_HARDWARE_AUTH_ERROR = 0x0003, IPA_RC_UNSUPPORTED_COMMAND = 0x0004, IPA_RC_TRACE_ALREADY_ACTIVE = 0x0005, + IPA_RC_VNICC_OOSEQ = 0x0005, IPA_RC_INVALID_FORMAT = 0x0006, IPA_RC_DUP_IPV6_REMOTE = 0x0008, IPA_RC_SBP_IQD_NOT_CONFIGURED = 0x000C, IPA_RC_DUP_IPV6_HOME = 0x0010, + IPA_RC_SBP_IQD_OS_MISMATCH = 0x0010, IPA_RC_UNREGISTERED_ADDR = 0x0011, IPA_RC_NO_ID_AVAILABLE = 0x0012, IPA_RC_ID_NOT_FOUND = 0x0013, @@ -173,6 +177,7 @@ enum qeth_ipa_return_codes { IPA_RC_SBP_IQD_CURRENT_SECOND = 0x0018, IPA_RC_SBP_IQD_LIMIT_SECOND = 0x001C, IPA_RC_INVALID_IP_VERSION = 0x0020, + IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN = 0x0020, IPA_RC_SBP_IQD_CURRENT_PRIMARY = 0x0024, IPA_RC_LAN_FRAME_MISMATCH = 0x0040, IPA_RC_SBP_IQD_NO_QDIO_QUEUES = 0x00EB, @@ -220,16 +225,6 @@ enum qeth_ipa_return_codes { IPA_RC_INVALID_IP_VERSION2 = 0xf001, IPA_RC_FFFF = 0xffff }; -/* for VNIC Characteristics */ -#define IPA_RC_VNICC_OOSEQ 0x0005 - -/* for SET_DIAGNOSTIC_ASSIST */ -#define IPA_RC_INVALID_SUBCMD IPA_RC_IP_TABLE_FULL -#define IPA_RC_HARDWARE_AUTH_ERROR IPA_RC_UNKNOWN_ERROR - -/* for SETBRIDGEPORT (double occupancies) */ -#define IPA_RC_SBP_IQD_OS_MISMATCH IPA_RC_DUP_IPV6_HOME -#define IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN IPA_RC_INVALID_IP_VERSION /* IPA function flags; each flag marks availability of respective function */ enum qeth_ipa_funcs { @@ -862,8 +857,9 @@ enum qeth_ipa_arp_return_codes { QETH_IPA_ARP_RC_Q_NO_DATA = 0x0008, }; -extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); -extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); +const char *qeth_get_ipa_msg(enum qeth_ipa_cmds cmd, + enum qeth_ipa_return_codes rc); +const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); /* Helper functions */ #define IS_IPA_REPLY(cmd) ((cmd)->hdr.initiator == IPA_CMD_INITIATOR_HOST) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 4c62c597c7be..b3af9b78fa12 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -2208,9 +2208,17 @@ sg_remove_sfp_usercontext(struct work_struct *work) write_lock_irqsave(&sfp->rq_list_lock, iflags); while (!list_empty(&sfp->rq_list)) { srp = list_first_entry(&sfp->rq_list, Sg_request, entry); - sg_finish_rem_req(srp); list_del(&srp->entry); + write_unlock_irqrestore(&sfp->rq_list_lock, iflags); + + sg_finish_rem_req(srp); + /* + * sg_rq_end_io() uses srp->parentfp. Hence, only clear + * srp->parentfp after blk_mq_free_request() has been called. + */ srp->parentfp = NULL; + + write_lock_irqsave(&sfp->rq_list_lock, iflags); } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 155ddeb8fcd4..bbf1fd4fe1e9 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -519,9 +519,15 @@ static void mx51_ecspi_trigger(struct spi_imx_data *spi_imx) { u32 reg; - reg = readl(spi_imx->base + MX51_ECSPI_CTRL); - reg |= MX51_ECSPI_CTRL_XCH; - writel(reg, spi_imx->base + MX51_ECSPI_CTRL); + if (spi_imx->usedma) { + reg = readl(spi_imx->base + MX51_ECSPI_DMA); + reg |= MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN; + writel(reg, spi_imx->base + MX51_ECSPI_DMA); + } else { + reg = readl(spi_imx->base + MX51_ECSPI_CTRL); + reg |= MX51_ECSPI_CTRL_XCH; + writel(reg, spi_imx->base + MX51_ECSPI_CTRL); + } } static void mx51_ecspi_disable(struct spi_imx_data *spi_imx) @@ -759,7 +765,6 @@ static void mx51_setup_wml(struct spi_imx_data *spi_imx) writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml - 1) | MX51_ECSPI_DMA_TX_WML(tx_wml) | MX51_ECSPI_DMA_RXT_WML(spi_imx->wml) | - MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN | MX51_ECSPI_DMA_RXTDEN, spi_imx->base + MX51_ECSPI_DMA); } @@ -1520,6 +1525,8 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, reinit_completion(&spi_imx->dma_tx_completion); dma_async_issue_pending(controller->dma_tx); + spi_imx->devtype_data->trigger(spi_imx); + transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len); /* Wait SDMA to finish the data transfer.*/ diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c index d59cc8a18484..c86dc56f38b4 100644 --- a/drivers/spi/spi-xilinx.c +++ b/drivers/spi/spi-xilinx.c @@ -300,7 +300,7 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) /* Read out all the data from the Rx FIFO */ rx_words = n_words; - stalled = 10; + stalled = 32; while (rx_words) { if (rx_words == n_words && !(stalled--) && !(sr & XSPI_SR_TX_EMPTY_MASK) && diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 2e0647a06890..e25df9990f82 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2851,6 +2851,18 @@ static acpi_status acpi_register_spi_device(struct spi_controller *ctlr, acpi_set_modalias(adev, acpi_device_hid(adev), spi->modalias, sizeof(spi->modalias)); + /* + * This gets re-tried in spi_probe() for -EPROBE_DEFER handling in case + * the GPIO controller does not have a driver yet. This needs to be done + * here too, because this call sets the GPIO direction and/or bias. + * Setting these needs to be done even if there is no driver, in which + * case spi_probe() will never get called. + * TODO: ideally the setup of the GPIO should be handled in a generic + * manner in the ACPI/gpiolib core code. + */ + if (spi->irq < 0) + spi->irq = acpi_dev_gpio_irq_get(adev, 0); + acpi_device_set_enumerated(adev); adev->power.flags.ignore_parent = true; diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c index c7b7da629741..01a8e349dc4d 100644 --- a/drivers/target/loopback/tcm_loop.c +++ b/drivers/target/loopback/tcm_loop.c @@ -894,6 +894,9 @@ static ssize_t tcm_loop_tpg_address_show(struct config_item *item, struct tcm_loop_tpg, tl_se_tpg); struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba; + if (!tl_hba->sh) + return -ENODEV; + return snprintf(page, PAGE_SIZE, "%d:0:%d\n", tl_hba->sh->host_no, tl_tpg->tl_tpgt); } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 35ded4330431..8f7f50acb6d6 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -592,14 +592,15 @@ static void vhost_net_busy_poll(struct vhost_net *net, static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *tnvq, unsigned int *out_num, unsigned int *in_num, - struct msghdr *msghdr, bool *busyloop_intr) + struct msghdr *msghdr, bool *busyloop_intr, + unsigned int *ndesc) { struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX]; struct vhost_virtqueue *rvq = &rnvq->vq; struct vhost_virtqueue *tvq = &tnvq->vq; - int r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), - out_num, in_num, NULL, NULL); + int r = vhost_get_vq_desc_n(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), + out_num, in_num, NULL, NULL, ndesc); if (r == tvq->num && tvq->busyloop_timeout) { /* Flush batched packets first */ @@ -610,8 +611,8 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net, vhost_net_busy_poll(net, rvq, tvq, busyloop_intr, false); - r = vhost_get_vq_desc(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), - out_num, in_num, NULL, NULL); + r = vhost_get_vq_desc_n(tvq, tvq->iov, ARRAY_SIZE(tvq->iov), + out_num, in_num, NULL, NULL, ndesc); } return r; @@ -642,12 +643,14 @@ static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, unsigned int *out, unsigned int *in, - size_t *len, bool *busyloop_intr) + size_t *len, bool *busyloop_intr, + unsigned int *ndesc) { struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, + busyloop_intr, ndesc); if (ret < 0 || ret == vq->num) return ret; @@ -766,6 +769,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) int sent_pkts = 0; bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); + unsigned int ndesc = 0; do { bool busyloop_intr = false; @@ -774,7 +778,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) vhost_tx_batch(net, nvq, sock, &msg); head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, - &busyloop_intr); + &busyloop_intr, &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; @@ -806,7 +810,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) goto done; } else if (unlikely(err != -ENOSPC)) { vhost_tx_batch(net, nvq, sock, &msg); - vhost_discard_vq_desc(vq, 1); + vhost_discard_vq_desc(vq, 1, ndesc); vhost_net_enable_vq(net, vq); break; } @@ -829,7 +833,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { if (err == -EAGAIN || err == -ENOMEM || err == -ENOBUFS) { - vhost_discard_vq_desc(vq, 1); + vhost_discard_vq_desc(vq, 1, ndesc); vhost_net_enable_vq(net, vq); break; } @@ -868,6 +872,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) int err; struct vhost_net_ubuf_ref *ubufs; struct ubuf_info_msgzc *ubuf; + unsigned int ndesc = 0; bool zcopy_used; int sent_pkts = 0; @@ -879,7 +884,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) busyloop_intr = false; head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, - &busyloop_intr); + &busyloop_intr, &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(head < 0)) break; @@ -941,7 +946,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN; } if (retry) { - vhost_discard_vq_desc(vq, 1); + vhost_discard_vq_desc(vq, 1, ndesc); vhost_net_enable_vq(net, vq); break; } @@ -1045,11 +1050,12 @@ static int get_rx_bufs(struct vhost_net_virtqueue *nvq, unsigned *iovcount, struct vhost_log *log, unsigned *log_num, - unsigned int quota) + unsigned int quota, + unsigned int *ndesc) { struct vhost_virtqueue *vq = &nvq->vq; bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); - unsigned int out, in; + unsigned int out, in, desc_num, n = 0; int seg = 0; int headcount = 0; unsigned d; @@ -1064,9 +1070,9 @@ static int get_rx_bufs(struct vhost_net_virtqueue *nvq, r = -ENOBUFS; goto err; } - r = vhost_get_vq_desc(vq, vq->iov + seg, - ARRAY_SIZE(vq->iov) - seg, &out, - &in, log, log_num); + r = vhost_get_vq_desc_n(vq, vq->iov + seg, + ARRAY_SIZE(vq->iov) - seg, &out, + &in, log, log_num, &desc_num); if (unlikely(r < 0)) goto err; @@ -1093,6 +1099,7 @@ static int get_rx_bufs(struct vhost_net_virtqueue *nvq, ++headcount; datalen -= len; seg += in; + n += desc_num; } *iovcount = seg; @@ -1113,9 +1120,11 @@ static int get_rx_bufs(struct vhost_net_virtqueue *nvq, nheads[0] = headcount; } + *ndesc = n; + return headcount; err: - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, n); return r; } @@ -1151,6 +1160,7 @@ static void handle_rx(struct vhost_net *net) struct iov_iter fixup; __virtio16 num_buffers; int recv_pkts = 0; + unsigned int ndesc; mutex_lock_nested(&vq->mutex, VHOST_NET_VQ_RX); sock = vhost_vq_get_backend(vq); @@ -1182,7 +1192,8 @@ static void handle_rx(struct vhost_net *net) headcount = get_rx_bufs(nvq, vq->heads + count, vq->nheads + count, vhost_len, &in, vq_log, &log, - likely(mergeable) ? UIO_MAXIOV : 1); + likely(mergeable) ? UIO_MAXIOV : 1, + &ndesc); /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) goto out; @@ -1228,7 +1239,7 @@ static void handle_rx(struct vhost_net *net) if (unlikely(err != sock_len)) { pr_debug("Discarded rx packet: " " len %d, expected %zd\n", err, sock_len); - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, ndesc); continue; } /* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */ @@ -1252,7 +1263,7 @@ static void handle_rx(struct vhost_net *net) copy_to_iter(&num_buffers, sizeof num_buffers, &fixup) != sizeof num_buffers) { vq_err(vq, "Failed num_buffers write"); - vhost_discard_vq_desc(vq, headcount); + vhost_discard_vq_desc(vq, headcount, ndesc); goto out; } nvq->done_idx += headcount; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 8570fdf2e14a..a78226b37739 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -2792,18 +2792,34 @@ static int get_indirect(struct vhost_virtqueue *vq, return 0; } -/* This looks in the virtqueue and for the first available buffer, and converts - * it to an iovec for convenient access. Since descriptors consist of some - * number of output then some number of input descriptors, it's actually two - * iovecs, but we pack them into one and note how many of each there were. +/** + * vhost_get_vq_desc_n - Fetch the next available descriptor chain and build iovecs + * @vq: target virtqueue + * @iov: array that receives the scatter/gather segments + * @iov_size: capacity of @iov in elements + * @out_num: the number of output segments + * @in_num: the number of input segments + * @log: optional array to record addr/len for each writable segment; NULL if unused + * @log_num: optional output; number of entries written to @log when provided + * @ndesc: optional output; number of descriptors consumed from the available ring + * (useful for rollback via vhost_discard_vq_desc) * - * This function returns the descriptor number found, or vq->num (which is - * never a valid descriptor number) if none was found. A negative code is - * returned on error. */ -int vhost_get_vq_desc(struct vhost_virtqueue *vq, - struct iovec iov[], unsigned int iov_size, - unsigned int *out_num, unsigned int *in_num, - struct vhost_log *log, unsigned int *log_num) + * Extracts one available descriptor chain from @vq and translates guest addresses + * into host iovecs. + * + * On success, advances @vq->last_avail_idx by 1 and @vq->next_avail_head by the + * number of descriptors consumed (also stored via @ndesc when non-NULL). + * + * Return: + * - head index in [0, @vq->num) on success; + * - @vq->num if no descriptor is currently available; + * - negative errno on failure + */ +int vhost_get_vq_desc_n(struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num, + unsigned int *ndesc) { bool in_order = vhost_has_feature(vq, VIRTIO_F_IN_ORDER); struct vring_desc desc; @@ -2921,17 +2937,49 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, vq->last_avail_idx++; vq->next_avail_head += c; + if (ndesc) + *ndesc = c; + /* Assume notifications from guest are disabled at this point, * if they aren't we would need to update avail_event index. */ BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY)); return head; } +EXPORT_SYMBOL_GPL(vhost_get_vq_desc_n); + +/* This looks in the virtqueue and for the first available buffer, and converts + * it to an iovec for convenient access. Since descriptors consist of some + * number of output then some number of input descriptors, it's actually two + * iovecs, but we pack them into one and note how many of each there were. + * + * This function returns the descriptor number found, or vq->num (which is + * never a valid descriptor number) if none was found. A negative code is + * returned on error. + */ +int vhost_get_vq_desc(struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num) +{ + return vhost_get_vq_desc_n(vq, iov, iov_size, out_num, in_num, + log, log_num, NULL); +} EXPORT_SYMBOL_GPL(vhost_get_vq_desc); -/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */ -void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n) +/** + * vhost_discard_vq_desc - Reverse the effect of vhost_get_vq_desc_n() + * @vq: target virtqueue + * @nbufs: number of buffers to roll back + * @ndesc: number of descriptors to roll back + * + * Rewinds the internal consumer cursors after a failed attempt to use buffers + * returned by vhost_get_vq_desc_n(). + */ +void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int nbufs, + unsigned int ndesc) { - vq->last_avail_idx -= n; + vq->next_avail_head -= ndesc; + vq->last_avail_idx -= nbufs; } EXPORT_SYMBOL_GPL(vhost_discard_vq_desc); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 621a6d9a8791..b49f08e4a1b4 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -230,7 +230,15 @@ int vhost_get_vq_desc(struct vhost_virtqueue *, struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num); -void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); + +int vhost_get_vq_desc_n(struct vhost_virtqueue *vq, + struct iovec iov[], unsigned int iov_size, + unsigned int *out_num, unsigned int *in_num, + struct vhost_log *log, unsigned int *log_num, + unsigned int *ndesc); + +void vhost_discard_vq_desc(struct vhost_virtqueue *, int nbuf, + unsigned int ndesc); bool vhost_vq_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work); bool vhost_vq_has_work(struct vhost_virtqueue *vq); diff --git a/fs/afs/cell.c b/fs/afs/cell.c index f31359922e98..d9b6fa1088b7 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -229,7 +229,7 @@ error: * @name: The name of the cell. * @namesz: The strlen of the cell name. * @vllist: A colon/comma separated list of numeric IP addresses or NULL. - * @excl: T if an error should be given if the cell name already exists. + * @reason: The reason we're doing the lookup * @trace: The reason to be logged if the lookup is successful. * * Look up a cell record by name and query the DNS for VL server addresses if @@ -239,7 +239,8 @@ error: */ struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace) { struct afs_cell *cell, *candidate, *cursor; @@ -247,12 +248,18 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, enum afs_cell_state state; int ret, n; - _enter("%s,%s", name, vllist); + _enter("%s,%s,%u", name, vllist, reason); - if (!excl) { + if (reason != AFS_LOOKUP_CELL_PRELOAD) { cell = afs_find_cell(net, name, namesz, trace); - if (!IS_ERR(cell)) + if (!IS_ERR(cell)) { + if (reason == AFS_LOOKUP_CELL_DYNROOT) + goto no_wait; + if (cell->state == AFS_CELL_SETTING_UP || + cell->state == AFS_CELL_UNLOOKED) + goto lookup_cell; goto wait_for_cell; + } } /* Assume we're probably going to create a cell and preallocate and @@ -298,26 +305,69 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, rb_insert_color(&cell->net_node, &net->cells); up_write(&net->cells_lock); - afs_queue_cell(cell, afs_cell_trace_queue_new); +lookup_cell: + if (reason != AFS_LOOKUP_CELL_PRELOAD && + reason != AFS_LOOKUP_CELL_ROOTCELL) { + set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); + afs_queue_cell(cell, afs_cell_trace_queue_new); + } wait_for_cell: - _debug("wait_for_cell"); state = smp_load_acquire(&cell->state); /* vs error */ - if (state != AFS_CELL_ACTIVE && - state != AFS_CELL_DEAD) { + switch (state) { + case AFS_CELL_ACTIVE: + case AFS_CELL_DEAD: + break; + case AFS_CELL_UNLOOKED: + default: + if (reason == AFS_LOOKUP_CELL_PRELOAD || + reason == AFS_LOOKUP_CELL_ROOTCELL) + break; + _debug("wait_for_cell"); afs_see_cell(cell, afs_cell_trace_wait); wait_var_event(&cell->state, ({ state = smp_load_acquire(&cell->state); /* vs error */ state == AFS_CELL_ACTIVE || state == AFS_CELL_DEAD; })); + _debug("waited_for_cell %d %d", cell->state, cell->error); } +no_wait: /* Check the state obtained from the wait check. */ + state = smp_load_acquire(&cell->state); /* vs error */ if (state == AFS_CELL_DEAD) { ret = cell->error; goto error; } + if (state == AFS_CELL_ACTIVE) { + switch (cell->dns_status) { + case DNS_LOOKUP_NOT_DONE: + if (cell->dns_source == DNS_RECORD_FROM_CONFIG) { + ret = 0; + break; + } + fallthrough; + default: + ret = -EIO; + goto error; + case DNS_LOOKUP_GOOD: + case DNS_LOOKUP_GOOD_WITH_BAD: + ret = 0; + break; + case DNS_LOOKUP_GOT_NOT_FOUND: + ret = -ENOENT; + goto error; + case DNS_LOOKUP_BAD: + ret = -EREMOTEIO; + goto error; + case DNS_LOOKUP_GOT_LOCAL_FAILURE: + case DNS_LOOKUP_GOT_TEMP_FAILURE: + case DNS_LOOKUP_GOT_NS_FAILURE: + ret = -EDESTADDRREQ; + goto error; + } + } _leave(" = %p [cell]", cell); return cell; @@ -325,7 +375,7 @@ wait_for_cell: cell_already_exists: _debug("cell exists"); cell = cursor; - if (excl) { + if (reason == AFS_LOOKUP_CELL_PRELOAD) { ret = -EEXIST; } else { afs_use_cell(cursor, trace); @@ -384,7 +434,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) return -EINVAL; /* allocate a cell record for the root/workstation cell */ - new_root = afs_lookup_cell(net, rootcell, len, vllist, false, + new_root = afs_lookup_cell(net, rootcell, len, vllist, + AFS_LOOKUP_CELL_ROOTCELL, afs_cell_trace_use_lookup_ws); if (IS_ERR(new_root)) { _leave(" = %ld", PTR_ERR(new_root)); @@ -777,6 +828,7 @@ static bool afs_manage_cell(struct afs_cell *cell) switch (cell->state) { case AFS_CELL_SETTING_UP: goto set_up_cell; + case AFS_CELL_UNLOOKED: case AFS_CELL_ACTIVE: goto cell_is_active; case AFS_CELL_REMOVING: @@ -797,7 +849,7 @@ set_up_cell: goto remove_cell; } - afs_set_cell_state(cell, AFS_CELL_ACTIVE); + afs_set_cell_state(cell, AFS_CELL_UNLOOKED); cell_is_active: if (afs_has_cell_expired(cell, &next_manage)) @@ -807,6 +859,8 @@ cell_is_active: ret = afs_update_cell(cell); if (ret < 0) cell->error = ret; + if (cell->state == AFS_CELL_UNLOOKED) + afs_set_cell_state(cell, AFS_CELL_ACTIVE); } if (next_manage < TIME64_MAX && cell->net->live) { diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 8c6130789fde..dc9d29e3739e 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -108,7 +108,8 @@ static struct dentry *afs_dynroot_lookup_cell(struct inode *dir, struct dentry * dotted = true; } - cell = afs_lookup_cell(net, name, len, NULL, false, + cell = afs_lookup_cell(net, name, len, NULL, + AFS_LOOKUP_CELL_DYNROOT, afs_cell_trace_use_lookup_dynroot); if (IS_ERR(cell)) { ret = PTR_ERR(cell); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index a45ae5c2ef8a..b92f96f56767 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -343,6 +343,7 @@ extern const char afs_init_sysname[]; enum afs_cell_state { AFS_CELL_SETTING_UP, + AFS_CELL_UNLOOKED, AFS_CELL_ACTIVE, AFS_CELL_REMOVING, AFS_CELL_DEAD, @@ -1049,9 +1050,18 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, extern int afs_cell_init(struct afs_net *, const char *); extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned, enum afs_cell_trace); +enum afs_lookup_cell_for { + AFS_LOOKUP_CELL_DYNROOT, + AFS_LOOKUP_CELL_MOUNTPOINT, + AFS_LOOKUP_CELL_DIRECT_MOUNT, + AFS_LOOKUP_CELL_PRELOAD, + AFS_LOOKUP_CELL_ROOTCELL, + AFS_LOOKUP_CELL_ALIAS_CHECK, +}; struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace); extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace); void afs_unuse_cell(struct afs_cell *cell, enum afs_cell_trace reason); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 1ad048e6e164..57c204a3c04e 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -107,7 +107,8 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (size > AFS_MAXCELLNAME) return -ENAMETOOLONG; - cell = afs_lookup_cell(ctx->net, p, size, NULL, false, + cell = afs_lookup_cell(ctx->net, p, size, NULL, + AFS_LOOKUP_CELL_MOUNTPOINT, afs_cell_trace_use_lookup_mntpt); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 40e879c8ca77..44520549b509 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -122,7 +122,8 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (strcmp(buf, "add") == 0) { struct afs_cell *cell; - cell = afs_lookup_cell(net, name, strlen(name), args, true, + cell = afs_lookup_cell(net, name, strlen(name), args, + AFS_LOOKUP_CELL_PRELOAD, afs_cell_trace_use_lookup_add); if (IS_ERR(cell)) { ret = PTR_ERR(cell); diff --git a/fs/afs/super.c b/fs/afs/super.c index da407f2d6f0d..d672b7ab57ae 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -290,7 +290,7 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) /* lookup the cell record */ if (cellname) { cell = afs_lookup_cell(ctx->net, cellname, cellnamesz, - NULL, false, + NULL, AFS_LOOKUP_CELL_DIRECT_MOUNT, afs_cell_trace_use_lookup_mount); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%*.*s'\n", diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 709b4cdb723e..fc9676abd252 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -269,7 +269,8 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) if (!name_len || name_len > AFS_MAXCELLNAME) master = ERR_PTR(-EOPNOTSUPP); else - master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false, + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, + AFS_LOOKUP_CELL_ALIAS_CHECK, afs_cell_trace_use_lookup_canonical); kfree(cell_name); if (IS_ERR(master)) diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 1d41ce477df5..984b365df046 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -61,7 +61,19 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) off = (ino - BFS_ROOT_INO) % BFS_INODES_PER_BLOCK; di = (struct bfs_inode *)bh->b_data + off; - inode->i_mode = 0x0000FFFF & le32_to_cpu(di->i_mode); + /* + * https://martin.hinner.info/fs/bfs/bfs-structure.html explains that + * BFS in SCO UnixWare environment used only lower 9 bits of di->i_mode + * value. This means that, although bfs_write_inode() saves whole + * inode->i_mode bits (which include S_IFMT bits and S_IS{UID,GID,VTX} + * bits), middle 7 bits of di->i_mode value can be garbage when these + * bits were not saved by bfs_write_inode(). + * Since we can't tell whether middle 7 bits are garbage, use only + * lower 12 bits (i.e. tolerate S_IS{UID,GID,VTX} bits possibly being + * garbage) and reconstruct S_IFMT bits for Linux environment from + * di->i_vtype value. + */ + inode->i_mode = 0x00000FFF & le32_to_cpu(di->i_mode); if (le32_to_cpu(di->i_vtype) == BFS_VDIR) { inode->i_mode |= S_IFDIR; inode->i_op = &bfs_dir_inops; @@ -71,6 +83,11 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) inode->i_op = &bfs_file_inops; inode->i_fop = &bfs_file_operations; inode->i_mapping->a_ops = &bfs_aops; + } else { + brelse(bh); + printf("Unknown vtype=%u %s:%08lx\n", + le32_to_cpu(di->i_vtype), inode->i_sb->s_id, ino); + goto error; } BFS_I(inode)->i_sblock = le32_to_cpu(di->i_sblock); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a839f960cd4a..a8b1d79e4af0 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -837,8 +837,10 @@ out: inode_unlock(d_inode(root)); if (err) { - if (f) + if (f) { + exe_file_allow_write_access(f); filp_close(f, NULL); + } kfree(e); return err; } diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 1f4d8ce56667..6de97565d5f7 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -533,6 +533,7 @@ static struct file_system_type efivarfs_type = { .init_fs_context = efivarfs_init_fs_context, .kill_sb = efivarfs_kill_sb, .parameters = efivarfs_parameters, + .fs_flags = FS_POWER_FREEZE, }; static __init int efivarfs_init(void) diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 7f9592856bf7..74d451f732c7 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -433,7 +433,10 @@ static int exfat_read_boot_sector(struct super_block *sb) struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ - sb_min_blocksize(sb, 512); + if (!sb_min_blocksize(sb, 512)) { + exfat_err(sb, "unable to set blocksize"); + return -EINVAL; + } /* read boot sector */ sbi->boot_bh = sb_bread(sb, 0); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 9648ed097816..9cfe20a3daaf 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1595,8 +1595,12 @@ int fat_fill_super(struct super_block *sb, struct fs_context *fc, setup(sb); /* flavour-specific stuff that needs options */ + error = -EINVAL; + if (!sb_min_blocksize(sb, 512)) { + fat_msg(sb, KERN_ERR, "unable to set blocksize"); + goto out_fail; + } error = -EIO; - sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector"); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 6bc7c97b017d..b2f6486fe1d5 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -373,7 +373,7 @@ static int virtio_fs_add_queues_sysfs(struct virtio_fs *fs) sprintf(buff, "%d", i); fsvq->kobj = kobject_create_and_add(buff, fs->mqs_kobj); - if (!fs->mqs_kobj) { + if (!fsvq->kobj) { ret = -ENOMEM; goto out_del; } diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 1e1acf5775ab..86455eebbf6c 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -979,7 +979,7 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hostfs_fs_info *fsi = fc->s_fs_info; struct fs_parse_result result; - char *host_root; + char *host_root, *tmp_root; int opt; opt = fs_parse(fc, hostfs_param_specs, param, &result); @@ -990,11 +990,13 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_hostfs: host_root = param->string; if (!*host_root) - host_root = ""; - fsi->host_root_path = - kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root); - if (fsi->host_root_path == NULL) + break; + tmp_root = kasprintf(GFP_KERNEL, "%s%s", + fsi->host_root_path, host_root); + if (!tmp_root) return -ENOMEM; + kfree(fsi->host_root_path); + fsi->host_root_path = tmp_root; break; } @@ -1004,17 +1006,17 @@ static int hostfs_parse_param(struct fs_context *fc, struct fs_parameter *param) static int hostfs_parse_monolithic(struct fs_context *fc, void *data) { struct hostfs_fs_info *fsi = fc->s_fs_info; - char *host_root = (char *)data; + char *tmp_root, *host_root = (char *)data; /* NULL is printed as '(null)' by printf(): avoid that. */ if (host_root == NULL) - host_root = ""; + return 0; - fsi->host_root_path = - kasprintf(GFP_KERNEL, "%s/%s", root_ino, host_root); - if (fsi->host_root_path == NULL) + tmp_root = kasprintf(GFP_KERNEL, "%s%s", fsi->host_root_path, host_root); + if (!tmp_root) return -ENOMEM; - + kfree(fsi->host_root_path); + fsi->host_root_path = tmp_root; return 0; } @@ -1049,6 +1051,11 @@ static int hostfs_init_fs_context(struct fs_context *fc) if (!fsi) return -ENOMEM; + fsi->host_root_path = kasprintf(GFP_KERNEL, "%s/", root_ino); + if (!fsi->host_root_path) { + kfree(fsi); + return -ENOMEM; + } fc->s_fs_info = fsi; fc->ops = &hostfs_context_ops; return 0; diff --git a/fs/inode.c b/fs/inode.c index ec9339024ac3..cff1d3af0d57 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1967,6 +1967,18 @@ retry: } EXPORT_SYMBOL(iput); +/** + * iput_not_last - put an inode assuming this is not the last reference + * @inode: inode to put + */ +void iput_not_last(struct inode *inode) +{ + VFS_BUG_ON_INODE(atomic_read(&inode->i_count) < 2, inode); + + WARN_ON(atomic_sub_return(1, &inode->i_count) == 0); +} +EXPORT_SYMBOL(iput_not_last); + #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 6f0e6b19383c..ad3143d4066b 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -610,6 +610,11 @@ static int isofs_fill_super(struct super_block *s, struct fs_context *fc) goto out_freesbi; } opt->blocksize = sb_min_blocksize(s, opt->blocksize); + if (!opt->blocksize) { + printk(KERN_ERR + "ISOFS: unable to set blocksize\n"); + goto out_freesbi; + } sbi->s_high_sierra = 0; /* default is iso9660 */ sbi->s_session = opt->session; diff --git a/fs/lockd/netlink.c b/fs/lockd/netlink.c index 6e00b02cad90..880c42b4f8c3 100644 --- a/fs/lockd/netlink.c +++ b/fs/lockd/netlink.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/lockd.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/fs/lockd/netlink.h b/fs/lockd/netlink.h index 1920543a7955..d8408f077dd8 100644 --- a/fs/lockd/netlink.h +++ b/fs/lockd/netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/lockd.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_LOCKD_GEN_H #define _LINUX_LOCKD_GEN_H diff --git a/fs/namespace.c b/fs/namespace.c index d82910f33dc4..2bad25709b2c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -132,16 +132,6 @@ EXPORT_SYMBOL_GPL(fs_kobj); */ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock); -static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node) -{ - struct ns_common *ns; - - if (!node) - return NULL; - ns = rb_entry(node, struct ns_common, ns_tree_node); - return container_of(ns, struct mnt_namespace, ns); -} - static void mnt_ns_release(struct mnt_namespace *ns) { /* keep alive for {list,stat}mount() */ @@ -151,7 +141,8 @@ static void mnt_ns_release(struct mnt_namespace *ns) kfree(ns); } } -DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) +DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, + if (!IS_ERR(_T)) mnt_ns_release(_T)) static void mnt_ns_release_rcu(struct rcu_head *rcu) { @@ -5454,11 +5445,11 @@ static int statmount_string(struct kstatmount *s, u64 flag) ret = statmount_sb_source(s, seq); break; case STATMOUNT_MNT_UIDMAP: - sm->mnt_uidmap = start; + offp = &sm->mnt_uidmap; ret = statmount_mnt_uidmap(s, seq); break; case STATMOUNT_MNT_GIDMAP: - sm->mnt_gidmap = start; + offp = &sm->mnt_gidmap; ret = statmount_mnt_gidmap(s, seq); break; default: @@ -5736,7 +5727,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; - if (kreq->spare != 0) + if (kreq->mnt_ns_fd != 0 && kreq->mnt_ns_id) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -5753,16 +5744,12 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq { struct mnt_namespace *mnt_ns; - if (kreq->mnt_ns_id && kreq->spare) - return ERR_PTR(-EINVAL); - - if (kreq->mnt_ns_id) - return lookup_mnt_ns(kreq->mnt_ns_id); - - if (kreq->spare) { + if (kreq->mnt_ns_id) { + mnt_ns = lookup_mnt_ns(kreq->mnt_ns_id); + } else if (kreq->mnt_ns_fd) { struct ns_common *ns; - CLASS(fd, f)(kreq->spare); + CLASS(fd, f)(kreq->mnt_ns_fd); if (fd_empty(f)) return ERR_PTR(-EBADF); @@ -5777,6 +5764,8 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq } else { mnt_ns = current->nsproxy->mnt_ns; } + if (!mnt_ns) + return ERR_PTR(-ENOENT); refcount_inc(&mnt_ns->passive); return mnt_ns; @@ -5801,8 +5790,8 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, return ret; ns = grab_requested_mnt_ns(&kreq); - if (!ns) - return -ENOENT; + if (IS_ERR(ns)) + return PTR_ERR(ns); if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) @@ -5912,8 +5901,8 @@ static void __free_klistmount_free(const struct klistmount *kls) static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq, size_t nr_mnt_ids) { - u64 last_mnt_id = kreq->param; + struct mnt_namespace *ns; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -5927,9 +5916,10 @@ static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req * if (!kls->kmnt_ids) return -ENOMEM; - kls->ns = grab_requested_mnt_ns(kreq); - if (!kls->ns) - return -ENOENT; + ns = grab_requested_mnt_ns(kreq); + if (IS_ERR(ns)) + return PTR_ERR(ns); + kls->ns = ns; kls->mnt_parent_id = kreq->mnt_id; return 0; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 4e3dcc157a83..54699299d5b1 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -338,6 +338,14 @@ again: /* Match the xprt security policy */ if (clp->cl_xprtsec.policy != data->xprtsec.policy) continue; + if (clp->cl_xprtsec.policy == RPC_XPRTSEC_TLS_X509) { + if (clp->cl_xprtsec.cert_serial != + data->xprtsec.cert_serial) + continue; + if (clp->cl_xprtsec.privkey_serial != + data->xprtsec.privkey_serial) + continue; + } refcount_inc(&clp->cl_count); return clp; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 46d9c65d50f8..ea9f6ca8f30f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2268,11 +2268,12 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, return -ENAMETOOLONG; if (open_flags & O_CREAT) { - file->f_mode |= FMODE_CREATED; error = nfs_do_create(dir, dentry, mode, open_flags); - if (error) + if (!error) { + file->f_mode |= FMODE_CREATED; + return finish_open(file, dentry, NULL); + } else if (error != -EEXIST || open_flags & O_EXCL) return error; - return finish_open(file, dentry, NULL); } if (d_in_lookup(dentry)) { /* The only flags nfs_lookup considers are diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 18b57c7c2f97..13ad70fc00d8 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -718,6 +718,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct nfs_fattr *fattr; loff_t oldsize = i_size_read(inode); int error = 0; + kuid_t task_uid = current_fsuid(); + kuid_t owner_uid = inode->i_uid; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); @@ -739,9 +741,11 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); if (attr->ia_valid & ATTR_MTIME_SET) { - nfs_set_timestamps_to_ts(inode, attr); - attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| + if (uid_eq(task_uid, owner_uid)) { + nfs_set_timestamps_to_ts(inode, attr); + attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_timestamps(inode, attr->ia_valid); attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME); @@ -751,10 +755,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { if (attr->ia_valid & ATTR_ATIME_SET) { - spin_lock(&inode->i_lock); - nfs_set_timestamps_to_ts(inode, attr); - spin_unlock(&inode->i_lock); - attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + if (uid_eq(task_uid, owner_uid)) { + spin_lock(&inode->i_lock); + nfs_set_timestamps_to_ts(inode, attr); + spin_unlock(&inode->i_lock); + attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME; diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index 2c0455e91571..656976b4f42c 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -42,10 +42,9 @@ struct nfs_local_kiocb { /* Begin mostly DIO-specific members */ size_t end_len; short int end_iter_index; - short int n_iters; + atomic_t n_iters; bool iter_is_dio_aligned[NFSLOCAL_MAX_IOS]; - loff_t offset[NFSLOCAL_MAX_IOS] ____cacheline_aligned; - struct iov_iter iters[NFSLOCAL_MAX_IOS]; + struct iov_iter iters[NFSLOCAL_MAX_IOS] ____cacheline_aligned; /* End mostly DIO-specific members */ }; @@ -314,7 +313,9 @@ nfs_local_iocb_alloc(struct nfs_pgio_header *hdr, init_sync_kiocb(&iocb->kiocb, file); iocb->hdr = hdr; + iocb->kiocb.ki_pos = hdr->args.offset; iocb->kiocb.ki_flags &= ~IOCB_APPEND; + iocb->kiocb.ki_complete = NULL; iocb->aio_complete_work = NULL; iocb->end_iter_index = -1; @@ -388,13 +389,24 @@ static bool nfs_iov_iter_aligned_bvec(const struct iov_iter *i, return true; } +static void +nfs_local_iter_setup(struct iov_iter *iter, int rw, struct bio_vec *bvec, + unsigned int nvecs, unsigned long total, + size_t start, size_t len) +{ + iov_iter_bvec(iter, rw, bvec, nvecs, total); + if (start) + iov_iter_advance(iter, start); + iov_iter_truncate(iter, len); +} + /* * Setup as many as 3 iov_iter based on extents described by @local_dio. * Returns the number of iov_iter that were setup. */ static int nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, - unsigned int nvecs, size_t len, + unsigned int nvecs, unsigned long total, struct nfs_local_dio *local_dio) { int n_iters = 0; @@ -402,39 +414,17 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, /* Setup misaligned start? */ if (local_dio->start_len) { - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - iters[n_iters].count = local_dio->start_len; - iocb->offset[n_iters] = iocb->hdr->args.offset; - iocb->iter_is_dio_aligned[n_iters] = false; + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, + nvecs, total, 0, local_dio->start_len); ++n_iters; } - /* Setup misaligned end? - * If so, the end is purposely setup to be issued using buffered IO - * before the middle (which will use DIO, if DIO-aligned, with AIO). - * This creates problems if/when the end results in a partial write. - * So must save index and length of end to handle this corner case. - */ - if (local_dio->end_len) { - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - iocb->offset[n_iters] = local_dio->end_offset; - iov_iter_advance(&iters[n_iters], - local_dio->start_len + local_dio->middle_len); - iocb->iter_is_dio_aligned[n_iters] = false; - /* Save index and length of end */ - iocb->end_iter_index = n_iters; - iocb->end_len = local_dio->end_len; - ++n_iters; - } - - /* Setup DIO-aligned middle to be issued last, to allow for - * DIO with AIO completion (see nfs_local_call_{read,write}). + /* + * Setup DIO-aligned middle, if there is no misaligned end (below) + * then AIO completion is used, see nfs_local_call_{read,write} */ - iov_iter_bvec(&iters[n_iters], rw, iocb->bvec, nvecs, len); - if (local_dio->start_len) - iov_iter_advance(&iters[n_iters], local_dio->start_len); - iters[n_iters].count -= local_dio->end_len; - iocb->offset[n_iters] = local_dio->middle_offset; + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, nvecs, + total, local_dio->start_len, local_dio->middle_len); iocb->iter_is_dio_aligned[n_iters] = nfs_iov_iter_aligned_bvec(&iters[n_iters], @@ -442,12 +432,22 @@ nfs_local_iters_setup_dio(struct nfs_local_kiocb *iocb, int rw, if (unlikely(!iocb->iter_is_dio_aligned[n_iters])) { trace_nfs_local_dio_misaligned(iocb->hdr->inode, - iocb->hdr->args.offset, len, local_dio); + local_dio->start_len, local_dio->middle_len, local_dio); return 0; /* no DIO-aligned IO possible */ } + iocb->end_iter_index = n_iters; ++n_iters; - iocb->n_iters = n_iters; + /* Setup misaligned end? */ + if (local_dio->end_len) { + nfs_local_iter_setup(&iters[n_iters], rw, iocb->bvec, + nvecs, total, local_dio->start_len + + local_dio->middle_len, local_dio->end_len); + iocb->end_iter_index = n_iters; + ++n_iters; + } + + atomic_set(&iocb->n_iters, n_iters); return n_iters; } @@ -473,18 +473,26 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) } len = hdr->args.count - total; + /* + * For each iocb, iocb->n_iters is always at least 1 and we always + * end io after first nfs_local_pgio_done call unless misaligned DIO. + */ + atomic_set(&iocb->n_iters, 1); + if (test_bit(NFS_IOHDR_ODIRECT, &hdr->flags)) { struct nfs_local_dio local_dio; if (nfs_is_local_dio_possible(iocb, rw, len, &local_dio) && - nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) + nfs_local_iters_setup_dio(iocb, rw, v, len, &local_dio) != 0) { + /* Ensure DIO WRITE's IO on stable storage upon completion */ + if (rw == ITER_SOURCE) + iocb->kiocb.ki_flags |= IOCB_DSYNC|IOCB_SYNC; return; /* is DIO-aligned */ + } } /* Use buffered IO */ - iocb->offset[0] = hdr->args.offset; iov_iter_bvec(&iocb->iters[0], rw, iocb->bvec, v, len); - iocb->n_iters = 1; } static void @@ -504,9 +512,11 @@ nfs_local_pgio_init(struct nfs_pgio_header *hdr, hdr->task.tk_start = ktime_get(); } -static void -nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) +static bool +nfs_local_pgio_done(struct nfs_local_kiocb *iocb, long status, bool force) { + struct nfs_pgio_header *hdr = iocb->hdr; + /* Must handle partial completions */ if (status >= 0) { hdr->res.count += status; @@ -517,6 +527,12 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status) hdr->res.op_status = nfs_localio_errno_to_nfs4_stat(status); hdr->task.tk_status = status; } + + if (force) + return true; + + BUG_ON(atomic_read(&iocb->n_iters) <= 0); + return atomic_dec_and_test(&iocb->n_iters); } static void @@ -547,11 +563,11 @@ static inline void nfs_local_pgio_aio_complete(struct nfs_local_kiocb *iocb) queue_work(nfsiod_workqueue, &iocb->work); } -static void -nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) +static void nfs_local_read_done(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; struct file *filp = iocb->kiocb.ki_filp; + long status = hdr->task.tk_status; if ((iocb->kiocb.ki_flags & IOCB_DIRECT) && status == -EINVAL) { /* Underlying FS will return -EINVAL if misaligned DIO is attempted. */ @@ -564,20 +580,27 @@ nfs_local_read_done(struct nfs_local_kiocb *iocb, long status) */ hdr->res.replen = 0; - if (hdr->res.count != hdr->args.count || - hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) + /* nfs_readpage_result() handles short read */ + + if (hdr->args.offset + hdr->res.count >= i_size_read(file_inode(filp))) hdr->res.eof = true; dprintk("%s: read %ld bytes eof %d.\n", __func__, status > 0 ? status : 0, hdr->res.eof); } +static inline void nfs_local_read_iocb_done(struct nfs_local_kiocb *iocb) +{ + nfs_local_read_done(iocb); + nfs_local_pgio_release(iocb); +} + static void nfs_local_read_aio_complete_work(struct work_struct *work) { struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); - nfs_local_pgio_release(iocb); + nfs_local_read_iocb_done(iocb); } static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) @@ -585,8 +608,10 @@ static void nfs_local_read_aio_complete(struct kiocb *kiocb, long ret) struct nfs_local_kiocb *iocb = container_of(kiocb, struct nfs_local_kiocb, kiocb); - nfs_local_pgio_done(iocb->hdr, ret); - nfs_local_read_done(iocb, ret); + /* AIO completion of DIO read should always be last to complete */ + if (unlikely(!nfs_local_pgio_done(iocb, ret, false))) + return; + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_read_aio_complete_work */ } @@ -596,32 +621,36 @@ static void nfs_local_call_read(struct work_struct *work) container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; const struct cred *save_cred; + bool force_done = false; ssize_t status; + int n_iters; save_cred = override_creds(filp->f_cred); - for (int i = 0; i < iocb->n_iters ; i++) { + n_iters = atomic_read(&iocb->n_iters); + for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { iocb->kiocb.ki_flags |= IOCB_DIRECT; - iocb->kiocb.ki_complete = nfs_local_read_aio_complete; - iocb->aio_complete_work = nfs_local_read_aio_complete_work; - } + /* Only use AIO completion if DIO-aligned segment is last */ + if (i == iocb->end_iter_index) { + iocb->kiocb.ki_complete = nfs_local_read_aio_complete; + iocb->aio_complete_work = nfs_local_read_aio_complete_work; + } + } else + iocb->kiocb.ki_flags &= ~IOCB_DIRECT; - iocb->kiocb.ki_pos = iocb->offset[i]; status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); if (status != -EIOCBQUEUED) { - nfs_local_pgio_done(iocb->hdr, status); - if (iocb->hdr->task.tk_status) + if (unlikely(status >= 0 && status < iocb->iters[i].count)) + force_done = true; /* Partial read */ + if (nfs_local_pgio_done(iocb, status, force_done)) { + nfs_local_read_iocb_done(iocb); break; + } } } revert_creds(save_cred); - - if (status != -EIOCBQUEUED) { - nfs_local_read_done(iocb, status); - nfs_local_pgio_release(iocb); - } } static int @@ -736,11 +765,10 @@ static void nfs_local_vfs_getattr(struct nfs_local_kiocb *iocb) fattr->du.nfs3.used = stat.blocks << 9; } -static void -nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) +static void nfs_local_write_done(struct nfs_local_kiocb *iocb) { struct nfs_pgio_header *hdr = iocb->hdr; - struct inode *inode = hdr->inode; + long status = hdr->task.tk_status; dprintk("%s: wrote %ld bytes.\n", __func__, status > 0 ? status : 0); @@ -759,10 +787,17 @@ nfs_local_write_done(struct nfs_local_kiocb *iocb, long status) nfs_set_pgio_error(hdr, -ENOSPC, hdr->args.offset); status = -ENOSPC; /* record -ENOSPC in terms of nfs_local_pgio_done */ - nfs_local_pgio_done(hdr, status); + (void) nfs_local_pgio_done(iocb, status, true); } if (hdr->task.tk_status < 0) - nfs_reset_boot_verifier(inode); + nfs_reset_boot_verifier(hdr->inode); +} + +static inline void nfs_local_write_iocb_done(struct nfs_local_kiocb *iocb) +{ + nfs_local_write_done(iocb); + nfs_local_vfs_getattr(iocb); + nfs_local_pgio_release(iocb); } static void nfs_local_write_aio_complete_work(struct work_struct *work) @@ -770,8 +805,7 @@ static void nfs_local_write_aio_complete_work(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); + nfs_local_write_iocb_done(iocb); } static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) @@ -779,8 +813,10 @@ static void nfs_local_write_aio_complete(struct kiocb *kiocb, long ret) struct nfs_local_kiocb *iocb = container_of(kiocb, struct nfs_local_kiocb, kiocb); - nfs_local_pgio_done(iocb->hdr, ret); - nfs_local_write_done(iocb, ret); + /* AIO completion of DIO write should always be last to complete */ + if (unlikely(!nfs_local_pgio_done(iocb, ret, false))) + return; + nfs_local_pgio_aio_complete(iocb); /* Calls nfs_local_write_aio_complete_work */ } @@ -791,63 +827,40 @@ static void nfs_local_call_write(struct work_struct *work) struct file *filp = iocb->kiocb.ki_filp; unsigned long old_flags = current->flags; const struct cred *save_cred; + bool force_done = false; ssize_t status; + int n_iters; current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; save_cred = override_creds(filp->f_cred); file_start_write(filp); - for (int i = 0; i < iocb->n_iters ; i++) { + n_iters = atomic_read(&iocb->n_iters); + for (int i = 0; i < n_iters ; i++) { if (iocb->iter_is_dio_aligned[i]) { iocb->kiocb.ki_flags |= IOCB_DIRECT; - iocb->kiocb.ki_complete = nfs_local_write_aio_complete; - iocb->aio_complete_work = nfs_local_write_aio_complete_work; - } -retry: - iocb->kiocb.ki_pos = iocb->offset[i]; + /* Only use AIO completion if DIO-aligned segment is last */ + if (i == iocb->end_iter_index) { + iocb->kiocb.ki_complete = nfs_local_write_aio_complete; + iocb->aio_complete_work = nfs_local_write_aio_complete_work; + } + } else + iocb->kiocb.ki_flags &= ~IOCB_DIRECT; + status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) { - /* partial write */ - if (i == iocb->end_iter_index) { - /* Must not account partial end, otherwise, due - * to end being issued before middle: the partial - * write accounting in nfs_local_write_done() - * would incorrectly advance hdr->args.offset - */ - status = 0; - } else { - /* Partial write at start or buffered middle, - * exit early. - */ - nfs_local_pgio_done(iocb->hdr, status); - break; - } - } else if (unlikely(status == -ENOTBLK && - (iocb->kiocb.ki_flags & IOCB_DIRECT))) { - /* VFS will return -ENOTBLK if DIO WRITE fails to - * invalidate the page cache. Retry using buffered IO. - */ - iocb->kiocb.ki_flags &= ~IOCB_DIRECT; - iocb->kiocb.ki_complete = NULL; - iocb->aio_complete_work = NULL; - goto retry; - } - nfs_local_pgio_done(iocb->hdr, status); - if (iocb->hdr->task.tk_status) + if (unlikely(status >= 0 && status < iocb->iters[i].count)) + force_done = true; /* Partial write */ + if (nfs_local_pgio_done(iocb, status, force_done)) { + nfs_local_write_iocb_done(iocb); break; + } } } file_end_write(filp); revert_creds(save_cred); current->flags = old_flags; - - if (status != -EIOCBQUEUED) { - nfs_local_write_done(iocb, status); - nfs_local_vfs_getattr(iocb); - nfs_local_pgio_release(iocb); - } } static int diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 0d7310c1ee0c..5d97c1d38bb6 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -2,6 +2,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/sunrpc/addr.h> +#include <net/handshake.h> #include "internal.h" #include "nfs3_fs.h" #include "netns.h" @@ -98,7 +99,11 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_clp->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, .connect_timeout = connect_timeout, .reconnect_timeout = connect_timeout, }; @@ -111,9 +116,14 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf; switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_clp->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_clp->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) cl_init.nconnect = mds_clp->cl_nconnect; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5998d6bd8a4f..3a4baed993c9 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -11,6 +11,7 @@ #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/bc_xprt.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <net/handshake.h> #include "internal.h" #include "callback.h" #include "delegation.h" @@ -983,7 +984,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_srv->nfs_client->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, }; char buf[INET6_ADDRSTRLEN + 1]; @@ -992,9 +997,14 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf; switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_srv->nfs_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_srv->nfs_client->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) { cl_init.nconnect = mds_clp->cl_nconnect; cl_init.max_connect = NFS_MAX_TRANSPORTS; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 411776718494..93c6ce04332b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4715,16 +4715,19 @@ static int _nfs4_proc_lookupp(struct inode *inode, }; unsigned short task_flags = 0; - if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) + if (server->flags & NFS_MOUNT_SOFTREVAL) task_flags |= RPC_TASK_TIMEOUT; + if (server->caps & NFS_CAP_MOVEABLE) + task_flags |= RPC_TASK_MOVEABLE; args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); + nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); dprintk("NFS call lookupp ino=0x%lx\n", inode->i_ino); - status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, - &res.seq_res, task_flags); + status = nfs4_do_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, task_flags); dprintk("NFS reply lookupp: %d\n", status); return status; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 7b32afb29782..9976cc16b689 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -809,8 +809,11 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, unsigned int retrans) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10; + int ds_proto; int status = 0; dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -834,27 +837,28 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, .xprtsec = clp->cl_xprtsec, }; - if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; - if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue; /* Add this address as an alias */ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, - rpc_clnt_test_and_add_xprt, NULL); + rpc_clnt_test_and_add_xprt, NULL); continue; } - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = get_v3_ds_connect(mds_srv, - &da->da_addr, - da->da_addrlen, da->da_transport, - timeo, retrans); + + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = get_v3_ds_connect(mds_srv, &da->da_addr, da->da_addrlen, + ds_proto, timeo, retrans); if (IS_ERR(clp)) continue; clp->cl_rpcclient->cl_softerr = 0; @@ -880,7 +884,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, u32 minor_version) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; + int ds_proto; int status = 0; dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -908,12 +915,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .data = &xprtdata, }; - if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) { + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) { struct sockaddr *addr = (struct sockaddr *)&da->da_addr; struct sockaddr_in *sin = @@ -944,7 +947,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; xprt_args.servername = servername; } - if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue; /** @@ -958,15 +964,14 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, if (xprtdata.cred) put_cred(xprtdata.cred); } else { - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = nfs4_set_ds_client(mds_srv, - &da->da_addr, - da->da_addrlen, - da->da_transport, timeo, - retrans, minor_version); + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = nfs4_set_ds_client(mds_srv, &da->da_addr, + da->da_addrlen, ds_proto, + timeo, retrans, minor_version); if (IS_ERR(clp)) continue; @@ -977,7 +982,6 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, clp = ERR_PTR(-EIO); continue; } - } } diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c index 545148d42dcc..ea6e6168092b 100644 --- a/fs/nfs/sysfs.c +++ b/fs/nfs/sysfs.c @@ -189,6 +189,7 @@ static struct nfs_netns_client *nfs_netns_client_alloc(struct kobject *parent, return p; kobject_put(&p->kobject); + kobject_put(&p->nfs_net_kobj); } return NULL; } diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c index ca54aa583530..ac51a44e1065 100644 --- a/fs/nfsd/netlink.c +++ b/fs/nfsd/netlink.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/nfsd.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h index 8eb903f24c41..478117ff6b8c 100644 --- a/fs/nfsd/netlink.h +++ b/fs/nfsd/netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/nfsd.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_NFSD_GEN_H #define _LINUX_NFSD_GEN_H diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 018055fd2cdb..e3ea6fe7edb4 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -16,6 +16,7 @@ static struct cached_fid *init_cached_dir(const char *path); static void free_cached_dir(struct cached_fid *cfid); static void smb2_close_cached_fid(struct kref *ref); static void cfids_laundromat_worker(struct work_struct *work); +static void close_cached_dir_locked(struct cached_fid *cfid); struct cached_dir_dentry { struct list_head entry; @@ -388,7 +389,7 @@ out: * lease. Release one here, and the second below. */ cfid->has_lease = false; - close_cached_dir(cfid); + close_cached_dir_locked(cfid); } spin_unlock(&cfids->cfid_list_lock); @@ -480,18 +481,52 @@ void drop_cached_dir_by_name(const unsigned int xid, struct cifs_tcon *tcon, spin_lock(&cfid->cfids->cfid_list_lock); if (cfid->has_lease) { cfid->has_lease = false; - close_cached_dir(cfid); + close_cached_dir_locked(cfid); } spin_unlock(&cfid->cfids->cfid_list_lock); close_cached_dir(cfid); } - +/** + * close_cached_dir - drop a reference of a cached dir + * + * The release function will be called with cfid_list_lock held to remove the + * cached dirs from the list before any other thread can take another @cfid + * ref. Must not be called with cfid_list_lock held; use + * close_cached_dir_locked() called instead. + * + * @cfid: cached dir + */ void close_cached_dir(struct cached_fid *cfid) { + lockdep_assert_not_held(&cfid->cfids->cfid_list_lock); kref_put_lock(&cfid->refcount, smb2_close_cached_fid, &cfid->cfids->cfid_list_lock); } +/** + * close_cached_dir_locked - put a reference of a cached dir with + * cfid_list_lock held + * + * Calling close_cached_dir() with cfid_list_lock held has the potential effect + * of causing a deadlock if the invariant of refcount >= 2 is false. + * + * This function is used in paths that hold cfid_list_lock and expect at least + * two references. If that invariant is violated, WARNs and returns without + * dropping a reference; the final put must still go through + * close_cached_dir(). + * + * @cfid: cached dir + */ +static void close_cached_dir_locked(struct cached_fid *cfid) +{ + lockdep_assert_held(&cfid->cfids->cfid_list_lock); + + if (WARN_ON(kref_read(&cfid->refcount) < 2)) + return; + + kref_put(&cfid->refcount, smb2_close_cached_fid); +} + /* * Called from cifs_kill_sb when we unmount a share */ diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 7da194f29fef..dcc50a2bfa4b 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1363,6 +1363,14 @@ do_retry: if (rdata->result == -ENODATA) { rdata->result = 0; __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + trace_smb3_read_err(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start + rdata->subreq.transferred, + rdata->subreq.len - rdata->subreq.transferred, + rdata->result); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && @@ -1374,6 +1382,13 @@ do_retry: } if (rdata->got_bytes) __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); + trace_smb3_read_done(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start + rdata->subreq.transferred, + rdata->got_bytes); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, @@ -1445,6 +1460,13 @@ cifs_async_readv(struct cifs_io_subrequest *rdata) rdata->iov[1].iov_base = (char *)smb + 4; rdata->iov[1].iov_len = get_rfc1002_length(smb); + trace_smb3_read_enter(rdata->rreq->debug_id, + rdata->subreq.debug_index, + rdata->xid, + rdata->req->cfile->fid.netfid, + tcon->tid, tcon->ses->Suid, + rdata->subreq.start, rdata->subreq.len); + rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive, cifs_readv_callback, NULL, rdata, 0, NULL); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 176301191f29..388efb35fb98 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4451,6 +4451,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid) out: kfree(ctx->username); + kfree(ctx->domainname); kfree_sensitive(ctx->password); kfree(origin_fullpath); kfree(ctx); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index e60927b2a7c8..2a0d8b87bd8e 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1435,12 +1435,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, cifs_errorf(fc, "Unknown error parsing devname\n"); goto cifs_parse_mount_err; } + kfree(ctx->source); ctx->source = smb3_fs_context_fullpath(ctx, '/'); if (IS_ERR(ctx->source)) { ctx->source = NULL; cifs_errorf(fc, "OOM when copying UNC string\n"); goto cifs_parse_mount_err; } + kfree(fc->source); fc->source = kstrdup(ctx->source, GFP_KERNEL); if (fc->source == NULL) { cifs_errorf(fc, "OOM when copying UNC string\n"); @@ -1468,7 +1470,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, break; } - if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) > + if (strnlen(param->string, CIFS_MAX_USERNAME_LEN) == CIFS_MAX_USERNAME_LEN) { pr_warn("username too long\n"); goto cifs_parse_mount_err; @@ -1832,6 +1834,10 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, ctx->password = NULL; kfree_sensitive(ctx->password2); ctx->password2 = NULL; + kfree(ctx->source); + ctx->source = NULL; + kfree(fc->source); + fc->source = NULL; return -EINVAL; } diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 85a4c55b61b8..c6c428c2e08d 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -290,6 +290,9 @@ static void smbd_disconnect_rdma_connection(struct smbdirect_socket *sc) break; case SMBDIRECT_SOCKET_CREATED: + sc->status = SMBDIRECT_SOCKET_DISCONNECTED; + break; + case SMBDIRECT_SOCKET_CONNECTED: sc->status = SMBDIRECT_SOCKET_ERROR; break; diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 051cd9dbba13..915cedde5d66 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -830,7 +830,7 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) if (!server || server->terminate) continue; - if (CIFS_CHAN_NEEDS_RECONNECT(ses, i)) + if (CIFS_CHAN_NEEDS_RECONNECT(ses, cur)) continue; /* diff --git a/fs/super.c b/fs/super.c index 5bab94fb7e03..277b84e5c279 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1183,11 +1183,14 @@ static inline bool get_active_super(struct super_block *sb) static const char *filesystems_freeze_ptr = "filesystems_freeze"; -static void filesystems_freeze_callback(struct super_block *sb, void *unused) +static void filesystems_freeze_callback(struct super_block *sb, void *freeze_all_ptr) { if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) return; + if (freeze_all_ptr && !(sb->s_type->fs_flags & FS_POWER_FREEZE)) + return; + if (!get_active_super(sb)) return; @@ -1201,9 +1204,13 @@ static void filesystems_freeze_callback(struct super_block *sb, void *unused) deactivate_super(sb); } -void filesystems_freeze(void) +void filesystems_freeze(bool freeze_all) { - __iterate_supers(filesystems_freeze_callback, NULL, + void *freeze_all_ptr = NULL; + + if (freeze_all) + freeze_all_ptr = &freeze_all; + __iterate_supers(filesystems_freeze_callback, freeze_all_ptr, SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE); } diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index 5902398185a8..df629892462f 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -184,7 +184,7 @@ xrep_symlink_salvage_inline( sc->ip->i_disk_size == 1 && old_target[0] == '?') return 0; - nr = min(XFS_SYMLINK_MAXLEN, xfs_inode_data_fork_size(ip)); + nr = min(XFS_SYMLINK_MAXLEN, ifp->if_bytes); memcpy(target_buf, ifp->if_data, nr); return nr; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 1067ebb3b001..bc71aa9dcee8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1693,7 +1693,10 @@ xfs_fs_fill_super( if (error) return error; - sb_min_blocksize(sb, BBSIZE); + if (!sb_min_blocksize(sb, BBSIZE)) { + xfs_err(mp, "unable to set blocksize"); + return -EINVAL; + } sb->s_xattr = xfs_xattr_handlers; sb->s_export_op = &xfs_export_operations; #ifdef CONFIG_XFS_QUOTA diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 7146a8e9e9c2..d0eccbd920e5 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -417,15 +417,32 @@ static inline void acpi_processor_throttling_init(void) {} #endif /* CONFIG_ACPI_CPU_FREQ_PSS */ /* in processor_idle.c */ +extern struct cpuidle_driver acpi_idle_driver; #ifdef CONFIG_ACPI_PROCESSOR_IDLE -void acpi_processor_power_init(struct acpi_processor *pr); -void acpi_processor_power_exit(struct acpi_processor *pr); +int acpi_processor_power_init(struct acpi_processor *pr); +int acpi_processor_power_exit(struct acpi_processor *pr); int acpi_processor_power_state_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); -void acpi_processor_register_idle_driver(void); -void acpi_processor_unregister_idle_driver(void); -int acpi_processor_ffh_lpi_probe(unsigned int cpu); -int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#else +static inline int acpi_processor_power_init(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_exit(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_state_has_changed(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_hotplug(struct acpi_processor *pr) +{ + return -ENODEV; +} #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ /* in processor_thermal.c */ @@ -448,6 +465,11 @@ static inline void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) } #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_ACPI_PROCESSOR_IDLE +extern int acpi_processor_ffh_lpi_probe(unsigned int cpu); +extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#endif + void acpi_processor_init_invariance_cppc(void); #endif diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h index da6301a6fcea..69d4ae92d822 100644 --- a/include/drm/intel/pciids.h +++ b/include/drm/intel/pciids.h @@ -877,7 +877,10 @@ MACRO__(0xB08F, ## __VA_ARGS__), \ MACRO__(0xB090, ## __VA_ARGS__), \ MACRO__(0xB0A0, ## __VA_ARGS__), \ - MACRO__(0xB0B0, ## __VA_ARGS__), \ + MACRO__(0xB0B0, ## __VA_ARGS__) + +/* WCL */ +#define INTEL_WCL_IDS(MACRO__, ...) \ MACRO__(0xFD80, ## __VA_ARGS__), \ MACRO__(0xFD81, ## __VA_ARGS__) diff --git a/include/linux/ata.h b/include/linux/ata.h index 792e10a09787..c9013e472aa3 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -566,6 +566,7 @@ struct ata_bmdma_prd { #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) #define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) +#define ata_id_is_locked(id) (((id)[ATA_ID_DLF] & 0x7) == 0x7) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index d30816dd93c7..726d909e87ce 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2020 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> - * Copyright (c) 2021 Vincent Mailhol <mailhol.vincent@wanadoo.fr> + * Copyright (c) 2021-2025 Vincent Mailhol <mailhol@kernel.org> */ #ifndef _CAN_BITTIMING_H @@ -16,10 +16,12 @@ #define CAN_CTRLMODE_FD_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) +#define CAN_CTRLMODE_XL_TDC_MASK \ + (CAN_CTRLMODE_XL_TDC_AUTO | CAN_CTRLMODE_XL_TDC_MANUAL) #define CAN_CTRLMODE_TDC_AUTO_MASK \ - (CAN_CTRLMODE_TDC_AUTO) + (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_XL_TDC_AUTO) #define CAN_CTRLMODE_TDC_MANUAL_MASK \ - (CAN_CTRLMODE_TDC_MANUAL) + (CAN_CTRLMODE_TDC_MANUAL | CAN_CTRLMODE_XL_TDC_MANUAL) /* * struct can_tdc - CAN FD Transmission Delay Compensation parameters @@ -85,6 +87,11 @@ struct can_tdc { u32 tdcf; }; +/* The transceiver decoding margin corresponds to t_Decode in ISO 11898-2 */ +#define CAN_PWM_DECODE_NS 5 +/* Maximum PWM symbol duration. Corresponds to t_SymbolNom_MAX - t_Decode */ +#define CAN_PWM_NS_MAX (205 - CAN_PWM_DECODE_NS) + /* * struct can_tdc_const - CAN hardware-dependent constant for * Transmission Delay Compensation @@ -118,11 +125,48 @@ struct can_tdc_const { u32 tdcf_max; }; +/* + * struct can_pwm - CAN Pulse-Width Modulation (PWM) parameters + * + * @pwms: pulse width modulation short phase + * @pwml: pulse width modulation long phase + * @pwmo: pulse width modulation offset + */ +struct can_pwm { + u32 pwms; + u32 pwml; + u32 pwmo; +}; + +/* + * struct can_pwm - CAN hardware-dependent constants for Pulse-Width + * Modulation (PWM) + * + * @pwms_min: PWM short phase minimum value. Must be at least 1. + * @pwms_max: PWM short phase maximum value + * @pwml_min: PWM long phase minimum value. Must be at least 1. + * @pwml_max: PWM long phase maximum value + * @pwmo_min: PWM offset phase minimum value + * @pwmo_max: PWM offset phase maximum value + */ +struct can_pwm_const { + u32 pwms_min; + u32 pwms_max; + u32 pwml_min; + u32 pwml_max; + u32 pwmo_min; + u32 pwmo_max; +}; + struct data_bittiming_params { const struct can_bittiming_const *data_bittiming_const; struct can_bittiming data_bittiming; const struct can_tdc_const *tdc_const; - struct can_tdc tdc; + const struct can_pwm_const *pwm_const; + union { + struct can_tdc tdc; + struct can_pwm pwm; + }; const u32 *data_bitrate_const; unsigned int data_bitrate_const_cnt; int (*do_set_data_bittiming)(struct net_device *dev); @@ -136,12 +180,14 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, const struct can_bittiming *dbt, u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported); + +int can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) { - netdev_err(dev, "bit-timing calculation not available\n"); + NL_SET_ERR_MSG(extack, "bit-timing calculation not available\n"); return -EINVAL; } @@ -151,6 +197,14 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported) { } + +static inline int +can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, + "bit-timing calculation not available: manually provide PWML and PWMS\n"); + return -EINVAL; +} #endif /* CONFIG_CAN_CALC_BITTIMING */ void can_sjw_set_default(struct can_bittiming *bt); @@ -164,6 +218,10 @@ int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const unsigned int bitrate_const_cnt, struct netlink_ext_ack *extack); +int can_validate_pwm_bittiming(const struct net_device *dev, + const struct can_pwm *pwm, + struct netlink_ext_ack *extack); + /* * can_get_relative_tdco() - TDCO relative to the sample point * @@ -206,4 +264,17 @@ static inline unsigned int can_bit_time(const struct can_bittiming *bt) return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2; } +/* Duration of one bit in minimum time quantum */ +static inline unsigned int can_bit_time_tqmin(const struct can_bittiming *bt) +{ + return can_bit_time(bt) * bt->brp; +} + +/* Convert a duration from minimum a minimum time quantum to nano seconds */ +static inline u32 can_tqmin_to_ns(u32 tqmin, u32 clock_freq) +{ + return DIV_U64_ROUND_CLOSEST(mul_u32_u32(tqmin, NSEC_PER_SEC), + clock_freq); +} + #endif /* !_CAN_BITTIMING_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index bd7410b5d8a6..52c8be5c160e 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -47,7 +47,7 @@ struct can_priv { const struct can_bittiming_const *bittiming_const; struct can_bittiming bittiming; - struct data_bittiming_params fd; + struct data_bittiming_params fd, xl; unsigned int bitrate_const_cnt; const u32 *bitrate_const; u32 bitrate_max; @@ -85,6 +85,11 @@ static inline bool can_fd_tdc_is_enabled(const struct can_priv *priv) return !!(priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK); } +static inline bool can_xl_tdc_is_enabled(const struct can_priv *priv) +{ + return !!(priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MASK); +} + static inline u32 can_get_static_ctrlmode(struct can_priv *priv) { return priv->ctrlmode & ~priv->ctrlmode_supported; @@ -95,22 +100,6 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu) return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); } -/* drop skb if it does not contain a valid CAN frame for sending */ -static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) -{ - struct can_priv *priv = netdev_priv(dev); - - if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { - netdev_info_once(dev, - "interface in listen only mode, dropping skb\n"); - kfree_skb(skb); - dev->stats.tx_dropped++; - return true; - } - - return can_dropped_invalid_skb(dev, skb); -} - void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, @@ -146,6 +135,51 @@ void can_bus_off(struct net_device *dev); const char *can_get_state_str(const enum can_state state); const char *can_get_ctrlmode_str(u32 ctrlmode); +static inline bool can_dev_in_xl_only_mode(struct can_priv *priv) +{ + const u32 mixed_mode = CAN_CTRLMODE_FD | CAN_CTRLMODE_XL; + + /* When CAN XL is enabled but FD is disabled we are running in + * the so-called 'CANXL-only mode' where the error signalling is + * disabled. This helper function determines the required value + * to disable error signalling in the CAN XL controller. + * The so-called CC/FD/XL 'mixed mode' requires error signalling. + */ + return ((priv->ctrlmode & mixed_mode) == CAN_CTRLMODE_XL); +} + +/* drop skb if it does not contain a valid CAN frame for sending */ +static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) +{ + struct can_priv *priv = netdev_priv(dev); + u32 silent_mode = priv->ctrlmode & (CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_RESTRICTED); + + if (silent_mode) { + netdev_info_once(dev, "interface in %s mode, dropping skb\n", + can_get_ctrlmode_str(silent_mode)); + goto invalid_skb; + } + + if (!(priv->ctrlmode & CAN_CTRLMODE_FD) && can_is_canfd_skb(skb)) { + netdev_info_once(dev, "CAN FD is disabled, dropping skb\n"); + goto invalid_skb; + } + + if (can_dev_in_xl_only_mode(priv) && !can_is_canxl_skb(skb)) { + netdev_info_once(dev, + "Error signaling is disabled, dropping skb\n"); + goto invalid_skb; + } + + return can_dropped_invalid_skb(dev, skb); + +invalid_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; +} + void can_state_get_by_berr_counter(const struct net_device *dev, const struct can_berr_counter *bec, enum can_state *tx_state, diff --git a/include/linux/entry-virt.h b/include/linux/entry-virt.h index 42c89e3e5ca7..bfa767702d9a 100644 --- a/include/linux/entry-virt.h +++ b/include/linux/entry-virt.h @@ -32,7 +32,7 @@ */ static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work); -#ifndef arch_xfer_to_guest_mode_work +#ifndef arch_xfer_to_guest_mode_handle_work static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work) { return 0; diff --git a/include/linux/filter.h b/include/linux/filter.h index a104b3994230..03e7516c6187 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -901,6 +901,26 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) cb->data_end = skb->data + skb_headlen(skb); } +static inline int bpf_prog_run_data_pointers( + const struct bpf_prog *prog, + struct sk_buff *skb) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + void *save_data_meta, *save_data_end; + int res; + + save_data_meta = cb->data_meta; + save_data_end = cb->data_end; + + bpf_compute_data_pointers(skb); + res = bpf_prog_run(prog, skb); + + cb->data_meta = save_data_meta; + cb->data_end = save_data_end; + + return res; +} + /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c895146c1444..dd3b57cfadee 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2689,6 +2689,7 @@ struct file_system_type { #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_LBS 128 /* FS supports LBS */ +#define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2823,6 +2824,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); +void iput_not_last(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); @@ -3423,8 +3425,8 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); -extern int sb_set_blocksize(struct super_block *, int); -extern int sb_min_blocksize(struct super_block *, int); +int sb_set_blocksize(struct super_block *sb, int size); +int __must_check sb_min_blocksize(struct super_block *sb, int size); int generic_file_mmap(struct file *, struct vm_area_struct *); int generic_file_mmap_prepare(struct vm_area_desc *desc); @@ -3606,7 +3608,7 @@ extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); -void filesystems_freeze(void); +void filesystems_freeze(bool freeze_all); void filesystems_thaw(void); extern int dcache_dir_open(struct inode *, struct file *); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 7ded7df6e9b5..07f8c309e432 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -193,6 +193,10 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs #if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \ defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS) +#ifndef arch_ftrace_partial_regs +#define arch_ftrace_partial_regs(regs) do {} while (0) +#endif + static __always_inline struct pt_regs * ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) { @@ -202,7 +206,11 @@ ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) * Since arch_ftrace_get_regs() will check some members and may return * NULL, we can not use it. */ - return &arch_ftrace_regs(fregs)->regs; + regs = &arch_ftrace_regs(fregs)->regs; + + /* Allow arch specific updates to regs. */ + arch_ftrace_partial_regs(regs); + return regs; } #endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 105cc4c00cc3..abc20f9810fd 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -249,10 +249,12 @@ static inline void clear_highpage_kasan_tagged(struct page *page) kunmap_local(kaddr); } -#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE +#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES -static inline void tag_clear_highpage(struct page *page) +/* Return false to let people know we did not initialize the pages */ +static inline bool tag_clear_highpages(struct page *page, int numpages) { + return false; } #endif diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index 995db62570f9..3102c425c8e0 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -27,7 +27,9 @@ struct phy_device; * as soon as a timestamp becomes available. One of the PTP_CLASS_ * values is passed in 'type'. * - * @hwtstamp: Handles SIOCSHWTSTAMP ioctl for hardware time stamping. + * @hwtstamp_set: Handles SIOCSHWTSTAMP ioctl for hardware time stamping. + * + * @hwtstamp_get: Handles SIOCGHWTSTAMP ioctl for hardware time stamping. * * @link_state: Allows the device to respond to changes in the link * state. The caller invokes this function while holding @@ -51,9 +53,12 @@ struct mii_timestamper { void (*txtstamp)(struct mii_timestamper *mii_ts, struct sk_buff *skb, int type); - int (*hwtstamp)(struct mii_timestamper *mii_ts, - struct kernel_hwtstamp_config *kernel_config, - struct netlink_ext_ack *extack); + int (*hwtstamp_set)(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *kernel_config, + struct netlink_ext_ack *extack); + + int (*hwtstamp_get)(struct mii_timestamper *mii_ts, + struct kernel_hwtstamp_config *kernel_config); void (*link_state)(struct mii_timestamper *mii_ts, struct phy_device *phydev); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 046396269ccf..1c54aa6f74fb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -488,7 +488,6 @@ struct mlx5_devcom_dev; struct mlx5_fw_reset; struct mlx5_eq_table; struct mlx5_irq_table; -struct mlx5_vhca_state_notifier; struct mlx5_sf_dev_table; struct mlx5_sf_hw_table; struct mlx5_sf_table; @@ -599,6 +598,7 @@ struct mlx5_priv { struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; + struct blocking_notifier_head esw_n_head; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; @@ -614,12 +614,18 @@ struct mlx5_priv { struct mlx5_bfreg_data bfregs; struct mlx5_sq_bfreg bfreg; #ifdef CONFIG_MLX5_SF - struct mlx5_vhca_state_notifier *vhca_state_notifier; + struct mlx5_nb vhca_state_nb; + struct blocking_notifier_head vhca_state_n_head; + struct notifier_block sf_dev_nb; struct mlx5_sf_dev_table *sf_dev_table; struct mlx5_core_dev *parent_mdev; #endif #ifdef CONFIG_MLX5_SF_MANAGER + struct notifier_block sf_hw_table_vhca_nb; struct mlx5_sf_hw_table *sf_hw_table; + struct notifier_block sf_table_esw_nb; + struct notifier_block sf_table_vhca_nb; + struct notifier_block sf_table_mdev_nb; struct mlx5_sf_table *sf_table; #endif struct blocking_notifier_head lag_nh; @@ -819,6 +825,7 @@ typedef void (*mlx5_cmd_cbk_t)(int status, void *context); enum { MLX5_CMD_ENT_STATE_PENDING_COMP, + MLX5_CMD_ENT_STATE_TIMEDOUT, }; struct mlx5_cmd_work_ent { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 7bf2449c53b2..9cadb1d5e6df 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -71,6 +71,7 @@ enum { MLX5_FLOW_TABLE_UNMANAGED = BIT(3), MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4), MLX5_FLOW_TABLE_UPLINK_VPORT = BIT(5), + MLX5_FLOW_TABLE_OTHER_ESWITCH = BIT(6), }; #define LEFTOVERS_RULE_NUM 2 @@ -128,6 +129,24 @@ enum { FDB_PER_VPORT, }; +enum fs_flow_table_type { + FS_FT_NIC_RX = 0x0, + FS_FT_NIC_TX = 0x1, + FS_FT_ESW_EGRESS_ACL = 0x2, + FS_FT_ESW_INGRESS_ACL = 0x3, + FS_FT_FDB = 0X4, + FS_FT_SNIFFER_RX = 0X5, + FS_FT_SNIFFER_TX = 0X6, + FS_FT_RDMA_RX = 0X7, + FS_FT_RDMA_TX = 0X8, + FS_FT_PORT_SEL = 0X9, + FS_FT_FDB_RX = 0xa, + FS_FT_FDB_TX = 0xb, + FS_FT_RDMA_TRANSPORT_RX = 0xd, + FS_FT_RDMA_TRANSPORT_TX = 0xe, + FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX, +}; + struct mlx5_pkt_reformat; struct mlx5_modify_hdr; struct mlx5_flow_definer; @@ -209,6 +228,7 @@ struct mlx5_flow_table_attr { u32 flags; u16 uid; u16 vport; + u16 esw_owner_vhca_id; struct mlx5_flow_table *next_ft; struct { @@ -354,4 +374,8 @@ u32 mlx5_flow_table_id(struct mlx5_flow_table *ft); struct mlx5_flow_root_namespace * mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type); + +int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev, + struct mlx5_core_dev *new_dev, + enum fs_flow_table_type table_type); #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1b0b36aa2a76..e9dcd4bf355d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5251,13 +5251,15 @@ struct mlx5_ifc_set_fte_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8809,13 +8811,15 @@ struct mlx5_ifc_destroy_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8840,13 +8844,15 @@ struct mlx5_ifc_destroy_flow_group_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8985,13 +8991,15 @@ struct mlx5_ifc_delete_fte_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -9535,13 +9543,15 @@ struct mlx5_ifc_create_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x20]; @@ -9580,7 +9590,8 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; @@ -9588,7 +9599,7 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 table_type[0x8]; u8 reserved_at_88[0x4]; u8 group_type[0x4]; - u8 reserved_at_90[0x10]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -11878,10 +11889,12 @@ struct mlx5_ifc_set_flow_table_root_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x10]; + u8 eswitch_owner_vhca_id[0x10]; u8 table_type[0x8]; u8 reserved_at_88[0x7]; @@ -11921,14 +11934,16 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x10]; u8 modify_field_select[0x10]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 58770b86f793..1df9d9a57bbc 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -112,6 +112,7 @@ enum mlx5e_ext_link_mode { MLX5E_400GAUI_2_400GBASE_CR2_KR2 = 17, MLX5E_800GAUI_8_800GBASE_CR8_KR8 = 19, MLX5E_800GAUI_4_800GBASE_CR4_KR4 = 20, + MLX5E_1600TAUI_8_1600TBASE_CR8_KR8 = 23, MLX5E_EXT_LINK_MODES_NUMBER, }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index c87b9507cfa1..f876bfc0669c 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -73,7 +73,8 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group); -int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); +int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, + u16 vport, bool other_vport, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, u16 vport, u64 node_guid); int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, diff --git a/include/linux/mm.h b/include/linux/mm.h index d16b33bacc32..7c79b3369b82 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2074,7 +2074,7 @@ static inline unsigned long folio_nr_pages(const struct folio *folio) return folio_large_nr_pages(folio); } -#if !defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) +#if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS) /* * We don't expect any folios that exceed buddy sizes (and consequently * memory sections). @@ -2087,10 +2087,17 @@ static inline unsigned long folio_nr_pages(const struct folio *folio) * pages are guaranteed to be contiguous. */ #define MAX_FOLIO_ORDER PFN_SECTION_SHIFT -#else +#elif defined(CONFIG_HUGETLB_PAGE) /* * There is no real limit on the folio size. We limit them to the maximum we - * currently expect (e.g., hugetlb, dax). + * currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect + * no folios larger than 16 GiB on 64bit and 1 GiB on 32bit. + */ +#define MAX_FOLIO_ORDER get_order(IS_ENABLED(CONFIG_64BIT) ? SZ_16G : SZ_1G) +#else +/* + * Without hugetlb, gigantic folios that are bigger than a single PUD are + * currently impossible. */ #define MAX_FOLIO_ORDER PUD_ORDER #endif diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h index 9e4e331b1603..ba28140ce670 100644 --- a/include/linux/pci-tph.h +++ b/include/linux/pci-tph.h @@ -29,6 +29,7 @@ int pcie_tph_get_cpu_st(struct pci_dev *dev, void pcie_disable_tph(struct pci_dev *pdev); int pcie_enable_tph(struct pci_dev *pdev, int mode); u16 pcie_tph_get_st_table_size(struct pci_dev *pdev); +u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev); #else static inline int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) diff --git a/include/linux/pci.h b/include/linux/pci.h index d1fdf81fbe1e..bf97d49c23cf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -412,6 +412,8 @@ struct pci_dev { u16 l1ss; /* L1SS Capability pointer */ #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state */ + unsigned int aspm_l0s_support:1; /* ASPM L0s support */ + unsigned int aspm_l1_support:1; /* ASPM L1 support */ unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index e40f554ff717..36073f7b6bb4 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -38,7 +38,9 @@ enum dw_xpcs_pma_id { DW_XPCS_PMA_GEN4_6G_ID, DW_XPCS_PMA_GEN5_10G_ID, DW_XPCS_PMA_GEN5_12G_ID, - WX_TXGBE_XPCS_PMA_10G_ID = 0x0018fc80, + WX_TXGBE_XPCS_PMA_10G_ID = 0xfc806000, + /* Meta Platforms OUI 88:25:08, model 0, revision 0 */ + MP_FBNIC_XPCS_PMA_100G_ID = 0x46904000, }; struct dw_xpcs_info { diff --git a/include/linux/phy.h b/include/linux/phy.h index bf5457341ca8..059a104223c4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1915,7 +1915,7 @@ static inline bool phy_polling_mode(struct phy_device *phydev) */ static inline bool phy_has_hwtstamp(struct phy_device *phydev) { - return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp; + return phydev && phydev->mii_ts && phydev->mii_ts->hwtstamp_set; } /** @@ -1950,7 +1950,7 @@ static inline int phy_hwtstamp(struct phy_device *phydev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { - return phydev->mii_ts->hwtstamp(phydev->mii_ts, cfg, extack); + return phydev->mii_ts->hwtstamp_set(phydev->mii_ts, cfg, extack); } static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, @@ -2040,6 +2040,9 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) return phydev->is_pseudo_fixed_link; } +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid); + int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ff90281ddf90..86737076101d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3778,8 +3778,8 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, enum dma_data_direction dir) { if (skb_frag_is_net_iov(frag)) { - return netmem_to_net_iov(frag->netmem)->dma_addr + offset + - frag->offset; + return netmem_to_net_iov(frag->netmem)->desc.dma_addr + + offset + frag->offset; } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 4f70a6551e68..f1054b9c2d8a 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -113,7 +113,7 @@ struct stmmac_axi { u32 axi_wr_osr_lmt; u32 axi_rd_osr_lmt; bool axi_kbbe; - u32 axi_blen[AXI_BLEN]; + u32 axi_blen_regval; bool axi_fb; bool axi_mb; bool axi_rb; @@ -264,8 +264,8 @@ struct plat_stmmacenet_data { unsigned int mode, phy_interface_t interface); void (*ptp_clk_freq_config)(struct stmmac_priv *priv); - int (*init)(struct platform_device *pdev, void *priv); - void (*exit)(struct platform_device *pdev, void *priv); + int (*init)(struct device *dev, void *priv); + void (*exit)(struct device *dev, void *priv); int (*suspend)(struct device *dev, void *priv); int (*resume)(struct device *dev, void *priv); int (*mac_setup)(void *priv, struct mac_device_info *mac); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b673c31569f3..75dabb763c65 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -384,7 +384,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool little_endian, - int vlan_hlen) + int vlan_hlen, + bool has_data_valid) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,8 +395,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, false, - vlan_hlen); + return virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index b8100dbfe5d7..0cb87687837f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -749,7 +749,6 @@ struct hci_conn { __u8 remote_cap; __u8 remote_auth; - __u8 remote_id; unsigned int sent; @@ -857,11 +856,12 @@ extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); -void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); +int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) @@ -869,23 +869,30 @@ static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, return 0; } -static inline void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) +static inline int sco_recv_scodata(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb) { + kfree_skb(skb); + return -ENOENT; } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } -static inline void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, - u16 flags) + +static inline int iso_recv(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb, u16 flags) { + kfree_skb(skb); + return -ENOENT; } #endif diff --git a/include/net/devlink.h b/include/net/devlink.h index d01046ef0577..cb839e0435a1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -479,6 +479,10 @@ struct devlink_flash_notify { * @set: set parameter value, used for runtime and permanent * configuration modes * @validate: validate input value is applicable (within value range, etc.) + * @get_default: get parameter default value, used for runtime and permanent + * configuration modes + * @reset_default: reset parameter to default value, used for runtime and permanent + * configuration modes * * This struct should be used by the driver to fill the data for * a parameter it registers. @@ -490,13 +494,20 @@ struct devlink_param { enum devlink_param_type type; unsigned long supported_cmodes; int (*get)(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int (*set)(struct devlink *devlink, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); int (*validate)(struct devlink *devlink, u32 id, union devlink_param_value val, struct netlink_ext_ack *extack); + int (*get_default)(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); + int (*reset_default)(struct devlink *devlink, u32 id, + enum devlink_param_cmode cmode, + struct netlink_ext_ack *extack); }; struct devlink_param_item { @@ -508,6 +519,7 @@ struct devlink_param_item { * until reload. */ bool driverinit_value_new_valid; + union devlink_param_value driverinit_default; }; enum devlink_param_generic_id { @@ -629,6 +641,37 @@ enum devlink_param_generic_id { .validate = _validate, \ } +#define DEVLINK_PARAM_GENERIC_WITH_DEFAULTS(_id, _cmodes, _get, _set, \ + _validate, _get_default, \ + _reset_default) \ +{ \ + .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ + .name = DEVLINK_PARAM_GENERIC_##_id##_NAME, \ + .type = DEVLINK_PARAM_GENERIC_##_id##_TYPE, \ + .generic = true, \ + .supported_cmodes = _cmodes, \ + .get = _get, \ + .set = _set, \ + .validate = _validate, \ + .get_default = _get_default, \ + .reset_default = _reset_default, \ +} + +#define DEVLINK_PARAM_DRIVER_WITH_DEFAULTS(_id, _name, _type, _cmodes, \ + _get, _set, _validate, \ + _get_default, _reset_default) \ +{ \ + .id = _id, \ + .name = _name, \ + .type = _type, \ + .supported_cmodes = _cmodes, \ + .get = _get, \ + .set = _set, \ + .validate = _validate, \ + .get_default = _get_default, \ + .reset_default = _reset_default, \ +} + /* Identifier of board design */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_ID "board.id" /* Revision of board design */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 2df2e2ead9a8..e40cdc12f7f3 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1251,7 +1251,8 @@ struct dsa_switch_ops { dsa_devlink_param_get, dsa_devlink_param_set, NULL) int dsa_devlink_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx); + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx, struct netlink_ext_ack *extack); @@ -1314,11 +1315,6 @@ static inline int dsa_devlink_port_to_port(struct devlink_port *port) return port->index; } -struct dsa_switch_driver { - struct list_head list; - const struct dsa_switch_ops *ops; -}; - bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); diff --git a/include/net/gro.h b/include/net/gro.h index e3affb2e2ca8..b65f631c521d 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -593,4 +593,31 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); +static inline struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) +{ + unsigned int thlen, hlen, off; + struct tcphdr *th; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*th); + th = skb_gro_header(skb, hlen, off); + if (unlikely(!th)) + return NULL; + + thlen = th->doff * 4; + if (unlikely(thlen < sizeof(*th))) + return NULL; + + hlen = off + thlen; + if (!skb_gro_may_pull(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + return NULL; + } + + skb_gro_pull(skb, thlen); + + return th; +} + #endif /* _NET_GRO_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fd40af2221b9..ecb362025c4e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -56,7 +56,9 @@ struct inet_connection_sock_af_ops { * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node * @icsk_bind2_hash: Bind node in the bhash2 table - * @icsk_retransmit_timer: Resend (no ack) + * @icsk_delack_timer: Delayed ACK timer + * @icsk_keepalive_timer: Keepalive timer + * @mptcp_tout_timer: mptcp timer * @icsk_rto: Retransmit timeout * @icsk_pmtu_cookie Last pmtu seen by socket * @icsk_ca_ops Pluggable congestion control hook @@ -81,8 +83,11 @@ struct inet_connection_sock { struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; struct inet_bind2_bucket *icsk_bind2_hash; - struct timer_list icsk_retransmit_timer; - struct timer_list icsk_delack_timer; + struct timer_list icsk_delack_timer; + union { + struct timer_list icsk_keepalive_timer; + struct timer_list mptcp_tout_timer; + }; __u32 icsk_rto; __u32 icsk_rto_min; u32 icsk_rto_max; @@ -184,10 +189,9 @@ static inline void inet_csk_delack_init(struct sock *sk) memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack)); } -static inline unsigned long -icsk_timeout(const struct inet_connection_sock *icsk) +static inline unsigned long tcp_timeout_expires(const struct sock *sk) { - return READ_ONCE(icsk->icsk_retransmit_timer.expires); + return READ_ONCE(sk->tcp_retransmit_timer.expires); } static inline unsigned long @@ -203,7 +207,7 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) { smp_store_release(&icsk->icsk_pending, 0); #ifdef INET_CSK_CLEAR_TIMERS - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer(sk, &sk->tcp_retransmit_timer); #endif } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, 0); @@ -235,7 +239,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 || what == ICSK_TIME_LOSS_PROBE || what == ICSK_TIME_REO_TIMEOUT) { smp_store_release(&icsk->icsk_pending, what); - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, when); + sk_reset_timer(sk, &sk->tcp_retransmit_timer, when); } else if (what == ICSK_TIME_DACK) { smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_TIMER); diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 637f42485dba..a4cf307859f8 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -486,6 +486,8 @@ struct gdma_wqe { #define INLINE_OOB_SMALL_SIZE 8 #define INLINE_OOB_LARGE_SIZE 24 +#define MANA_MAX_TX_WQE_SGL_ENTRIES 30 + #define MAX_TX_WQE_SIZE 512 #define MAX_RX_WQE_SIZE 256 @@ -592,6 +594,12 @@ enum { #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) +/* Driver supports linearizing the skb when num_sge exceeds hardware limit */ +#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20) + +/* Driver can send HWC periodically to query stats */ +#define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21) + #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \ @@ -601,7 +609,9 @@ enum { GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ - GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE) + GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ + GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \ + GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 8906901535f5..d7e089c6b694 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -375,6 +375,14 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 tx_cqe_err; + u64 tx_cqe_unknown_type; + u64 tx_linear_pkt_cnt; + u64 rx_coalesced_err; + u64 rx_cqe_unknown_type; +}; + +struct mana_ethtool_hc_stats { u64 hc_rx_discards_no_wqe; u64 hc_rx_err_vport_disabled; u64 hc_rx_bytes; @@ -402,10 +410,6 @@ struct mana_ethtool_stats { u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; u64 hc_tx_err_gdma; - u64 tx_cqe_err; - u64 tx_cqe_unknown_type; - u64 rx_coalesced_err; - u64 rx_cqe_unknown_type; }; struct mana_ethtool_phy_stats { @@ -473,9 +477,14 @@ struct mana_context { u16 num_ports; u8 bm_hostmode; + struct mana_ethtool_hc_stats hc_stats; struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; + /* Workqueue for querying hardware stats */ + struct delayed_work gf_stats_work; + bool hwc_timeout_occurred; + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; /* Link state change work */ @@ -577,13 +586,14 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); -void mana_query_gf_stats(struct mana_port_context *apc); +int mana_query_gf_stats(struct mana_context *ac); int mana_query_link_cfg(struct mana_port_context *apc); int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, int enable_clamping); void mana_query_phy_stats(struct mana_port_context *apc); int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues); void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); +void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; extern struct dentry *mana_debugfs_root; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index de9d36acc8e2..2dbd46fc4734 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,17 +74,18 @@ struct netns_ipv4 { /* TXRX readonly hotpath cache lines */ __cacheline_group_begin(netns_ipv4_read_txrx); - u8 sysctl_tcp_moderate_rcvbuf; __cacheline_group_end(netns_ipv4_read_txrx); /* RX readonly hotpath cache line */ __cacheline_group_begin(netns_ipv4_read_rx); + u8 sysctl_tcp_moderate_rcvbuf; u8 sysctl_ip_early_demux; u8 sysctl_tcp_early_demux; u8 sysctl_tcp_l3mdev_accept; /* 3 bytes hole, try to pack */ int sysctl_tcp_reordering; int sysctl_tcp_rmem[3]; + int sysctl_tcp_rcvbuf_low_rtt; __cacheline_group_end(netns_ipv4_read_rx); struct inet_timewait_death_row tcp_death_row; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c64fd896b1f9..99ac747b7906 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -536,6 +536,8 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: + if (!skb_transport_header_was_set(skb)) + break; return skb_transport_header(skb); } diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 4678db45832a..e703c507d0da 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -114,12 +114,13 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, void __qdisc_run(struct Qdisc *q); -static inline void qdisc_run(struct Qdisc *q) +static inline struct sk_buff *qdisc_run(struct Qdisc *q) { if (qdisc_run_begin(q)) { __qdisc_run(q); - qdisc_run_end(q); + return qdisc_run_end(q); } + return NULL; } extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 94966692ccdf..c3a7268b567e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -88,6 +88,8 @@ struct Qdisc { #define TCQ_F_INVISIBLE 0x80 /* invisible by default in dump */ #define TCQ_F_NOLOCK 0x100 /* qdisc does not require locking */ #define TCQ_F_OFFLOADED 0x200 /* qdisc is offloaded to HW */ +#define TCQ_F_DEQUEUE_DROPS 0x400 /* ->dequeue() can drop packets in q->to_free */ + u32 limit; const struct Qdisc_ops *ops; struct qdisc_size_table __rcu *stab; @@ -103,17 +105,26 @@ struct Qdisc { int pad; refcount_t refcnt; - /* - * For performance sake on SMP, we put highly modified fields at the end - */ - struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; - struct qdisc_skb_head q; - struct gnet_stats_basic_sync bstats; - struct gnet_stats_queue qstats; - bool running; /* must be written under qdisc spinlock */ - unsigned long state; - struct Qdisc *next_sched; - struct sk_buff_head skb_bad_txq; + /* Cache line potentially dirtied in dequeue() or __netif_reschedule(). */ + __cacheline_group_begin(Qdisc_read_mostly) ____cacheline_aligned; + struct sk_buff_head gso_skb; + struct Qdisc *next_sched; + struct sk_buff_head skb_bad_txq; + __cacheline_group_end(Qdisc_read_mostly); + + /* Fields dirtied in dequeue() fast path. */ + __cacheline_group_begin(Qdisc_write) ____cacheline_aligned; + struct qdisc_skb_head q; + unsigned long state; + struct gnet_stats_basic_sync bstats; + bool running; /* must be written under qdisc spinlock */ + + /* Note : we only change qstats.backlog in fast path. */ + struct gnet_stats_queue qstats; + + struct sk_buff *to_free; + __cacheline_group_end(Qdisc_write); + atomic_long_t defer_count ____cacheline_aligned_in_smp; struct llist_head defer_list; @@ -211,8 +222,10 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) return true; } -static inline void qdisc_run_end(struct Qdisc *qdisc) +static inline struct sk_buff *qdisc_run_end(struct Qdisc *qdisc) { + struct sk_buff *to_free = NULL; + if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); @@ -225,9 +238,16 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) if (unlikely(test_bit(__QDISC_STATE_MISSED, &qdisc->state))) __netif_schedule(qdisc); - } else { - WRITE_ONCE(qdisc->running, false); + return NULL; + } + + if (qdisc->flags & TCQ_F_DEQUEUE_DROPS) { + to_free = qdisc->to_free; + if (to_free) + qdisc->to_free = NULL; } + WRITE_ONCE(qdisc->running, false); + return to_free; } static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) @@ -429,13 +449,16 @@ struct tcf_proto { }; struct qdisc_skb_cb { - struct { - unsigned int pkt_len; - u16 slave_dev_queue_mapping; - u16 tc_classid; - }; + unsigned int pkt_len; + u16 pkt_segs; + u16 tc_classid; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; + + u16 slave_dev_queue_mapping; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; }; typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); @@ -826,6 +849,15 @@ static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb) return qdisc_skb_cb(skb)->pkt_len; } +static inline unsigned int qdisc_pkt_segs(const struct sk_buff *skb) +{ + u32 pkt_segs = qdisc_skb_cb(skb)->pkt_segs; + + DEBUG_NET_WARN_ON_ONCE(pkt_segs != + (skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1)); + return pkt_segs; +} + /* additional qdisc xmit flags (NET_XMIT_MASK in linux/netdevice.h) */ enum net_xmit_qdisc_t { __NET_XMIT_STOLEN = 0x00010000, @@ -867,9 +899,7 @@ static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, static inline void bstats_update(struct gnet_stats_basic_sync *bstats, const struct sk_buff *skb) { - _bstats_update(bstats, - qdisc_pkt_len(skb), - skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1); + _bstats_update(bstats, qdisc_pkt_len(skb), qdisc_pkt_segs(skb)); } static inline void qdisc_bstats_cpu_update(struct Qdisc *sch, @@ -1064,11 +1094,8 @@ struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u32 drop_reason; - u16 zone; /* Only valid if post_ct = true */ + u16 zone; /* Only valid if qdisc_skb_cb(skb)->post_ct = true */ u16 mru; - u8 post_ct:1; - u8 post_ct_snat:1; - u8 post_ct_dnat:1; }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) @@ -1091,6 +1118,28 @@ static inline void tcf_set_drop_reason(const struct sk_buff *skb, tc_skb_cb(skb)->drop_reason = reason; } +static inline void tcf_kfree_skb_list(struct sk_buff *skb) +{ + while (unlikely(skb)) { + struct sk_buff *next = skb->next; + + prefetch(next); + kfree_skb_reason(skb, tcf_get_drop_reason(skb)); + skb = next; + } +} + +static inline void qdisc_dequeue_drop(struct Qdisc *q, struct sk_buff *skb, + enum skb_drop_reason reason) +{ + DEBUG_NET_WARN_ON_ONCE(!(q->flags & TCQ_F_DEQUEUE_DROPS)); + DEBUG_NET_WARN_ON_ONCE(q->flags & TCQ_F_NOLOCK); + + tcf_set_drop_reason(skb, reason); + skb->next = q->to_free; + q->to_free = skb; +} + /* Instead of calling kfree_skb() while root qdisc lock is held, * queue the skb for future freeing at end of __dev_xmit_skb() */ diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 3d5879e08e78..6f2cd562b1de 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -72,7 +72,6 @@ struct sctp_shared_key *sctp_auth_get_shkey( int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep, struct sctp_association *asoc, gfp_t gfp); -int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp); const struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id); const struct sctp_hmac * sctp_auth_asoc_get_hmac(const struct sctp_association *asoc); diff --git a/include/net/sock.h b/include/net/sock.h index a5f36ea9d46f..02253c6a578b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -305,6 +305,8 @@ struct sk_filter; * @sk_txrehash: enable TX hash rethink * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer + * @tcp_retransmit_timer: tcp retransmit timer + * @mptcp_retransmit_timer: mptcp retransmit timer * @sk_stamp: time stamp of last packet received * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING flags @@ -481,11 +483,12 @@ struct sock { struct rb_root tcp_rtx_queue; }; struct sk_buff_head sk_write_queue; - u32 sk_dst_pending_confirm; - u32 sk_pacing_status; /* see enum sk_pacing */ struct page_frag sk_frag; - struct timer_list sk_timer; - + union { + struct timer_list sk_timer; + struct timer_list tcp_retransmit_timer; + struct timer_list mptcp_retransmit_timer; + }; unsigned long sk_pacing_rate; /* bytes per second */ atomic_t sk_zckey; atomic_t sk_tskey; @@ -493,6 +496,8 @@ struct sock { __cacheline_group_end(sock_write_tx); __cacheline_group_begin(sock_read_tx); + u32 sk_dst_pending_confirm; + u32 sk_pacing_status; /* see enum sk_pacing */ unsigned long sk_max_pacing_rate; long sk_sndtimeo; u32 sk_priority; @@ -1631,6 +1636,8 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) sk_mem_reclaim(sk); } +void __sk_charge(struct sock *sk, gfp_t gfp); + #if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) static inline void sk_owner_set(struct sock *sk, struct module *owner) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 4833ec7903ec..0deb5e9dd911 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2313,7 +2313,6 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index f3014e4f54fc..0a14daaa5dd4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -536,7 +536,8 @@ static inline int xfrm_af2proto(unsigned int family) static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { - if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || + if ((x->sel.family != AF_UNSPEC) || + (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else diff --git a/include/uapi/linux/android/binder_netlink.h b/include/uapi/linux/android/binder_netlink.h index b218f96d6668..bf69833c9a19 100644 --- a/include/uapi/linux/android/binder_netlink.h +++ b/include/uapi/linux/android/binder_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/binder.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ANDROID_BINDER_NETLINK_H #define _UAPI_LINUX_ANDROID_BINDER_NETLINK_H diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index ef62f56eaaef..c30d16746159 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -5,6 +5,7 @@ * Definitions for the CAN netlink interface * * Copyright (c) 2009 Wolfgang Grandegger <wg@grandegger.com> + * Copyright (c) 2021-2025 Vincent Mailhol <mailhol@kernel.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the version 2 of the GNU General Public License @@ -103,6 +104,11 @@ struct can_ctrlmode { #define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ #define CAN_CTRLMODE_TDC_AUTO 0x200 /* FD transceiver automatically calculates TDCV */ #define CAN_CTRLMODE_TDC_MANUAL 0x400 /* FD TDCV is manually set up by user */ +#define CAN_CTRLMODE_RESTRICTED 0x800 /* Restricted operation mode */ +#define CAN_CTRLMODE_XL 0x1000 /* CAN XL mode */ +#define CAN_CTRLMODE_XL_TDC_AUTO 0x2000 /* XL transceiver automatically calculates TDCV */ +#define CAN_CTRLMODE_XL_TDC_MANUAL 0x4000 /* XL TDCV is manually set up by user */ +#define CAN_CTRLMODE_XL_TMS 0x8000 /* Transceiver Mode Switching */ /* * CAN device statistics @@ -138,6 +144,11 @@ enum { IFLA_CAN_BITRATE_MAX, IFLA_CAN_TDC, /* FD */ IFLA_CAN_CTRLMODE_EXT, + IFLA_CAN_XL_DATA_BITTIMING, + IFLA_CAN_XL_DATA_BITTIMING_CONST, + IFLA_CAN_XL_DATA_BITRATE_CONST, + IFLA_CAN_XL_TDC, + IFLA_CAN_XL_PWM, /* add new constants above here */ __IFLA_CAN_MAX, @@ -179,6 +190,29 @@ enum { IFLA_CAN_CTRLMODE_MAX = __IFLA_CAN_CTRLMODE - 1 }; +/* + * CAN FD/XL Pulse-Width Modulation (PWM) + * + * Please refer to struct can_pwm_const and can_pwm in + * include/linux/can/bittiming.h for further details. + */ +enum { + IFLA_CAN_PWM_UNSPEC, + IFLA_CAN_PWM_PWMS_MIN, /* u32 */ + IFLA_CAN_PWM_PWMS_MAX, /* u32 */ + IFLA_CAN_PWM_PWML_MIN, /* u32 */ + IFLA_CAN_PWM_PWML_MAX, /* u32 */ + IFLA_CAN_PWM_PWMO_MIN, /* u32 */ + IFLA_CAN_PWM_PWMO_MAX, /* u32 */ + IFLA_CAN_PWM_PWMS, /* u32 */ + IFLA_CAN_PWM_PWML, /* u32 */ + IFLA_CAN_PWM_PWMO, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_PWM, + IFLA_CAN_PWM_MAX = __IFLA_CAN_PWM - 1 +}; + /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 157f11d3fb72..e7d6b6d13470 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -639,6 +639,9 @@ enum devlink_attr { DEVLINK_ATTR_HEALTH_REPORTER_BURST_PERIOD, /* u64 */ + DEVLINK_ATTR_PARAM_VALUE_DEFAULT, /* dynamic */ + DEVLINK_ATTR_PARAM_RESET_DEFAULT, /* flag */ + /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate * net/devlink/netlink_gen.c. diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 69d35570ac4f..b7ff9c44f9aa 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/dpll.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_DPLL_H #define _UAPI_LINUX_DPLL_H diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8bd5ea5469d9..eb7ff2602fbb 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2077,6 +2077,10 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118, ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119, ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120, + ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT = 121, + ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT = 122, + ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT = 123, + ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT = 124, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS @@ -2190,6 +2194,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_200000 200000 #define SPEED_400000 400000 #define SPEED_800000 800000 +#define SPEED_1600000 1600000 #define SPEED_UNKNOWN -1 diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index b71b175df46d..556a0c834df5 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ethtool.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index b5cd3e7b3775..bb6bef74d2d1 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_FOU_H #define _UAPI_LINUX_FOU_H diff --git a/include/uapi/linux/handshake.h b/include/uapi/linux/handshake.h index 662e7de46c54..d7e40f594888 100644 --- a/include/uapi/linux/handshake.h +++ b/include/uapi/linux/handshake.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/handshake.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_HANDSHAKE_H #define _UAPI_LINUX_HANDSHAKE_H diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 2c93b7b731c8..df9d44a11540 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -92,7 +92,9 @@ #define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ -#define ETH_P_MXLGSW 0x88C3 /* MaxLinear GSW DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_MXLGSW 0x88C3 /* Infineon Technologies Corporate Research ST + * Used by MaxLinear GSW DSA + */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ diff --git a/include/uapi/linux/if_team.h b/include/uapi/linux/if_team.h index a5c06243a435..f4cd839ae725 100644 --- a/include/uapi/linux/if_team.h +++ b/include/uapi/linux/if_team.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/team.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_IF_TEAM_H #define _UAPI_LINUX_IF_TEAM_H diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 9cd89bcc1d9c..30f3c9eaafaa 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -27,7 +27,7 @@ #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ #define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ -#define INPUT_PROP_HAPTIC_TOUCHPAD 0x07 /* is a haptic touchpad */ +#define INPUT_PROP_PRESSUREPAD 0x07 /* pressure triggers clicks */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 5d754322a27c..3539ccbfd064 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -36,6 +36,9 @@ struct io_uring_query_opcode { __u64 enter_flags; /* Bitmask of all supported IOSQE_* flags */ __u64 sqe_flags; + /* The number of available query opcodes */ + __u32 nr_query_opcodes; + __u32 __pad; }; #endif diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index 8197a4800604..40aa545101a3 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -52,7 +52,7 @@ struct isst_if_cpu_map { /** * struct isst_if_cpu_maps - structure for CPU map IOCTL * @cmd_count: Number of CPU mapping command in cpu_map[] - * @cpu_map[]: Holds one or more CPU map data structure + * @cpu_map: Holds one or more CPU map data structure * * This structure used with ioctl ISST_IF_GET_PHY_ID to send * one or more CPU mapping commands. Here IOCTL return value indicates @@ -82,8 +82,8 @@ struct isst_if_io_reg { /** * struct isst_if_io_regs - structure for IO register commands - * @cmd_count: Number of io reg commands in io_reg[] - * @io_reg[]: Holds one or more io_reg command structure + * @req_count: Number of io reg commands in io_reg[] + * @io_reg: Holds one or more io_reg command structure * * This structure used with ioctl ISST_IF_IO_CMD to send * one or more read/write commands to PUNIT. Here IOCTL return value @@ -120,7 +120,7 @@ struct isst_if_mbox_cmd { /** * struct isst_if_mbox_cmds - structure for mailbox commands * @cmd_count: Number of mailbox commands in mbox_cmd[] - * @mbox_cmd[]: Holds one or more mbox commands + * @mbox_cmd: Holds one or more mbox commands * * This structure used with ioctl ISST_IF_MBOX_COMMAND to send * one or more mailbox commands to PUNIT. Here IOCTL return value @@ -152,7 +152,7 @@ struct isst_if_msr_cmd { /** * struct isst_if_msr_cmds - structure for msr commands * @cmd_count: Number of mailbox commands in msr_cmd[] - * @msr_cmd[]: Holds one or more msr commands + * @msr_cmd: Holds one or more msr commands * * This structure used with ioctl ISST_IF_MSR_COMMAND to send * one or more MSR commands. IOCTL return value indicates number of @@ -167,8 +167,9 @@ struct isst_if_msr_cmds { * struct isst_core_power - Structure to get/set core_power feature * @get_set: 0: Get, 1: Set * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @enable: Feature enable status + * @supported: Power domain supports SST_CP interface * @priority_type: Priority type for the feature (ordered/proportional) * * Structure to get/set core_power feature state using IOCTL @@ -187,11 +188,11 @@ struct isst_core_power { * struct isst_clos_param - Structure to get/set clos praram * @get_set: 0: Get, 1: Set * @socket_id: Socket/package id - * @power_domain: Power Domain id - * clos: Clos ID for the parameters - * min_freq_mhz: Minimum frequency in MHz - * max_freq_mhz: Maximum frequency in MHz - * prop_prio: Proportional priority from 0-15 + * @power_domain_id: Power Domain id + * @clos: Clos ID for the parameters + * @min_freq_mhz: Minimum frequency in MHz + * @max_freq_mhz: Maximum frequency in MHz + * @prop_prio: Proportional priority from 0-15 * * Structure to get/set per clos property using IOCTL * ISST_IF_CLOS_PARAM. @@ -209,7 +210,7 @@ struct isst_clos_param { /** * struct isst_if_clos_assoc - Structure to assign clos to a CPU * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @logical_cpu: CPU number * @clos: Clos ID to assign to the logical CPU * @@ -228,6 +229,7 @@ struct isst_if_clos_assoc { * @get_set: Request is for get or set * @punit_cpu_map: Set to 1 if the CPU number is punit numbering not * Linux CPU number + * @assoc_info: CLOS data for this CPU * * Structure used to get/set associate CPUs to clos using IOCTL * ISST_IF_CLOS_ASSOC. @@ -257,7 +259,7 @@ struct isst_tpmi_instance_count { /** * struct isst_perf_level_info - Structure to get information on SST-PP levels * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @logical_cpu: CPU number * @clos: Clos ID to assign to the logical CPU * @max_level: Maximum performance level supported by the platform @@ -267,8 +269,8 @@ struct isst_tpmi_instance_count { * @feature_state: SST-BF and SST-TF (enabled/disabled) status at current level * @locked: SST-PP performance level change is locked/unlocked * @enabled: SST-PP feature is enabled or not - * @sst-tf_support: SST-TF support status at this level - * @sst-bf_support: SST-BF support status at this level + * @sst_tf_support: SST-TF support status at this level + * @sst_bf_support: SST-BF support status at this level * * Structure to get SST-PP details using IOCTL ISST_IF_PERF_LEVELS. */ @@ -289,7 +291,7 @@ struct isst_perf_level_info { /** * struct isst_perf_level_control - Structure to set SST-PP level * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: level to set * * Structure used change SST-PP level using IOCTL ISST_IF_PERF_SET_LEVEL. @@ -303,7 +305,7 @@ struct isst_perf_level_control { /** * struct isst_perf_feature_control - Structure to activate SST-BF/SST-TF * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @feature: bit 0 = SST-BF state, bit 1 = SST-TF state * * Structure used to enable SST-BF/SST-TF using IOCTL ISST_IF_PERF_SET_FEATURE. @@ -320,7 +322,7 @@ struct isst_perf_feature_control { /** * struct isst_perf_level_data_info - Structure to get SST-PP level details * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @tdp_ratio: TDP Ratio * @base_freq_mhz: Base frequency in MHz @@ -341,8 +343,8 @@ struct isst_perf_feature_control { * @pm_fabric_freq_mhz: Fabric (Uncore) minimum frequency * @max_buckets: Maximum trl buckets * @max_trl_levels: Maximum trl levels - * @bucket_core_counts[TRL_MAX_BUCKETS]: Number of cores per bucket - * @trl_freq_mhz[TRL_MAX_LEVELS][TRL_MAX_BUCKETS]: maximum frequency + * @bucket_core_counts: Number of cores per bucket + * @trl_freq_mhz: maximum frequency * for a bucket and trl level * * Structure used to get information on frequencies and TDP for a SST-PP @@ -402,7 +404,7 @@ struct isst_perf_level_fabric_info { /** * struct isst_perf_level_cpu_mask - Structure to get SST-PP level CPU mask * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @punit_cpu_map: Set to 1 if the CPU number is punit numbering not * Linux CPU number. If 0 CPU buffer is copied to user space @@ -430,7 +432,7 @@ struct isst_perf_level_cpu_mask { /** * struct isst_base_freq_info - Structure to get SST-BF frequencies * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @high_base_freq_mhz: High priority CPU base frequency * @low_base_freq_mhz: Low priority CPU base frequency @@ -453,9 +455,11 @@ struct isst_base_freq_info { /** * struct isst_turbo_freq_info - Structure to get SST-TF frequencies * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @max_clip_freqs: Maximum number of low priority core clipping frequencies + * @max_buckets: Maximum trl buckets + * @max_trl_levels: Maximum trl levels * @lp_clip_freq_mhz: Clip frequencies per trl level * @bucket_core_counts: Maximum number of cores for a bucket * @trl_freq_mhz: Frequencies per trl level for each bucket diff --git a/include/uapi/linux/lockd_netlink.h b/include/uapi/linux/lockd_netlink.h index 21c65aec3bc6..2d766a0fa6ea 100644 --- a/include/uapi/linux/lockd_netlink.h +++ b/include/uapi/linux/lockd_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/lockd.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_LOCKD_NETLINK_H #define _UAPI_LINUX_LOCKD_NETLINK_H diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 6975f182b22c..8d769f100de6 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -116,10 +116,24 @@ #define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00) /* 10PASS-TS/2BASE-TL */ #define MDIO_CTRL1_SPEED10P2B (MDIO_CTRL1_SPEEDSELEXT | 0x04) +/* Note: the MDIO_CTRL1_SPEED_XXX values for everything past 10PASS-TS/2BASE-TL + * do not match between the PCS and PMA values. Any additions past this point + * should be PMA or PCS specific. The following 2 defines are workarounds for + * values added before this was caught. They should be considered deprecated. + */ +#define MDIO_CTRL1_SPEED2_5G MDIO_PMA_CTRL1_SPEED2_5G +#define MDIO_CTRL1_SPEED5G MDIO_PMA_CTRL1_SPEED5G +/* 100 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED100G (MDIO_CTRL1_SPEEDSELEXT | 0x10) +/* 25 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED25G (MDIO_CTRL1_SPEEDSELEXT | 0x14) +/* 50 Gb/s */ +#define MDIO_PCS_CTRL1_SPEED50G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 2.5 Gb/s */ -#define MDIO_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) +#define MDIO_PMA_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 5 Gb/s */ -#define MDIO_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) +#define MDIO_PMA_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) + /* Status register 1. */ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ @@ -133,6 +147,11 @@ #define MDIO_AN_STAT1_PAGE 0x0040 /* Page received */ #define MDIO_AN_STAT1_XNP 0x0080 /* Extended next page status */ +/* Device Identifier 2 */ +#define MDIO_DEVID2_OUI 0xfc00 /* OUI Portion of PHY ID */ +#define MDIO_DEVID2_MODEL_NUM 0x03f0 /* Manufacturer's Model Number */ +#define MDIO_DEVID2_REV_NUM 0x000f /* Revision Number */ + /* Speed register. */ #define MDIO_SPEED_10G 0x0001 /* 10G capable */ #define MDIO_PMA_SPEED_2B 0x0002 /* 2BASE-TL capable */ diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 7fa67c2031a5..5d3f8c9e3a62 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -197,7 +197,7 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 spare; + __u32 mnt_ns_fd; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index bf44a5cf5b5a..c97d060ee90b 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_MPTCP_PM_H #define _UAPI_LINUX_MPTCP_PM_H diff --git a/include/uapi/linux/net_shaper.h b/include/uapi/linux/net_shaper.h index d8834b59f7d7..3dd22c2930d9 100644 --- a/include/uapi/linux/net_shaper.h +++ b/include/uapi/linux/net_shaper.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/net_shaper.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NET_SHAPER_H #define _UAPI_LINUX_NET_SHAPER_H diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 048c8de1a130..e0b579a1df4f 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NETDEV_H #define _UAPI_LINUX_NETDEV_H diff --git a/include/uapi/linux/nfsd_netlink.h b/include/uapi/linux/nfsd_netlink.h index 887cbd12b695..e157e2009ea8 100644 --- a/include/uapi/linux/nfsd_netlink.h +++ b/include/uapi/linux/nfsd_netlink.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/nfsd.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NFSD_NETLINK_H #define _UAPI_LINUX_NFSD_NETLINK_H diff --git a/include/uapi/linux/ovpn.h b/include/uapi/linux/ovpn.h index 680d1522dc87..959b41def61f 100644 --- a/include/uapi/linux/ovpn.h +++ b/include/uapi/linux/ovpn.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/ovpn.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_OVPN_H #define _UAPI_LINUX_OVPN_H diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index d8449c043ba1..a3a336488dc3 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/psp.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_PSP_H #define _UAPI_LINUX_PSP_H diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 386ad36f1a0a..cab5cadca8ef 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -249,8 +249,9 @@ struct tee_ioctl_param { * @cancel_id: [in] Cancellation id, a unique value to identify this request * @session: [out] Session id * @ret: [out] return value - * @ret_origin [out] origin of the return value - * @num_params [in] number of parameters following this struct + * @ret_origin: [out] origin of the return value + * @num_params: [in] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters */ struct tee_ioctl_open_session_arg { __u8 uuid[TEE_IOCTL_UUID_LEN]; @@ -276,14 +277,14 @@ struct tee_ioctl_open_session_arg { struct tee_ioctl_buf_data) /** - * struct tee_ioctl_invoke_func_arg - Invokes a function in a Trusted - * Application + * struct tee_ioctl_invoke_arg - Invokes a function in a Trusted Application * @func: [in] Trusted Application function, specific to the TA * @session: [in] Session id * @cancel_id: [in] Cancellation id, a unique value to identify this request * @ret: [out] return value - * @ret_origin [out] origin of the return value - * @num_params [in] number of parameters following this struct + * @ret_origin: [out] origin of the return value + * @num_params: [in] number of parameters following this struct + * @params: array of ioctl parameters */ struct tee_ioctl_invoke_arg { __u32 func; @@ -338,7 +339,8 @@ struct tee_ioctl_close_session_arg { /** * struct tee_iocl_supp_recv_arg - Receive a request for a supplicant function * @func: [in] supplicant function - * @num_params [in/out] number of parameters following this struct + * @num_params: [in/out] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters * * @num_params is the number of params that tee-supplicant has room to * receive when input, @num_params is the number of actual params @@ -363,7 +365,8 @@ struct tee_iocl_supp_recv_arg { /** * struct tee_iocl_supp_send_arg - Send a response to a received request * @ret: [out] return value - * @num_params [in] number of parameters following this struct + * @num_params: [in] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters */ struct tee_iocl_supp_send_arg { __u32 ret; @@ -454,11 +457,13 @@ struct tee_ioctl_shm_register_fd_data { */ /** - * struct tee_ioctl_invoke_func_arg - Invokes an object in a Trusted Application + * struct tee_ioctl_object_invoke_arg - Invokes an object in a + * Trusted Application * @id: [in] Object id * @op: [in] Object operation, specific to the object * @ret: [out] return value * @num_params: [in] number of parameters following this struct + * @params: array of ioctl parameters */ struct tee_ioctl_object_invoke_arg { __u64 id; diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c index 27a09aa4c9d0..3b75931bd569 100644 --- a/io_uring/cmd_net.c +++ b/io_uring/cmd_net.c @@ -127,7 +127,7 @@ static int io_uring_cmd_timestamp(struct socket *sock, if (!unlikely(skb_queue_empty(&list))) { scoped_guard(spinlock_irqsave, &q->lock) - skb_queue_splice(q, &list); + skb_queue_splice(&list, q); } return -EAGAIN; } diff --git a/io_uring/query.c b/io_uring/query.c index 645301bd2c82..cf02893ba911 100644 --- a/io_uring/query.c +++ b/io_uring/query.c @@ -20,6 +20,8 @@ static ssize_t io_query_ops(void *data) e->ring_setup_flags = IORING_SETUP_FLAGS; e->enter_flags = IORING_ENTER_FLAGS; e->sqe_flags = SQE_VALID_FLAGS; + e->nr_query_opcodes = __IO_URING_QUERY_MAX; + e->__pad = 0; return sizeof(*e); } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 2602d76d5ff0..0010c4992490 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -943,8 +943,8 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, struct req_iterator rq_iter; struct io_mapped_ubuf *imu; struct io_rsrc_node *node; - struct bio_vec bv, *bvec; - u16 nr_bvecs; + struct bio_vec bv; + unsigned int nr_bvecs = 0; int ret = 0; io_ring_submit_lock(ctx, issue_flags); @@ -965,8 +965,11 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, goto unlock; } - nr_bvecs = blk_rq_nr_phys_segments(rq); - imu = io_alloc_imu(ctx, nr_bvecs); + /* + * blk_rq_nr_phys_segments() may overestimate the number of bvecs + * but avoids needing to iterate over the bvecs + */ + imu = io_alloc_imu(ctx, blk_rq_nr_phys_segments(rq)); if (!imu) { kfree(node); ret = -ENOMEM; @@ -977,16 +980,15 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, imu->len = blk_rq_bytes(rq); imu->acct_pages = 0; imu->folio_shift = PAGE_SHIFT; - imu->nr_bvecs = nr_bvecs; refcount_set(&imu->refs, 1); imu->release = release; imu->priv = rq; imu->is_kbuf = true; imu->dir = 1 << rq_data_dir(rq); - bvec = imu->bvec; rq_for_each_bvec(bv, rq, rq_iter) - *bvec++ = bv; + imu->bvec[nr_bvecs++] = bv; + imu->nr_bvecs = nr_bvecs; node->buf = imu; data->nodes[index] = node; diff --git a/io_uring/rw.c b/io_uring/rw.c index 5b2241a5813c..abe68ba9c9dc 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -463,7 +463,10 @@ int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) void io_readv_writev_cleanup(struct io_kiocb *req) { + struct io_async_rw *rw = req->async_data; + lockdep_assert_held(&req->ctx->uring_lock); + io_vec_free(&rw->vec); io_rw_recycle(req, 0); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3e830fd31f5f..0785eb739eb8 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -4167,7 +4167,8 @@ release_prog: } /** - * bpf_task_work_schedule_signal - Schedule BPF callback using task_work_add with TWA_SIGNAL mode + * bpf_task_work_schedule_signal_impl - Schedule BPF callback using task_work_add with TWA_SIGNAL + * mode * @task: Task struct for which callback should be scheduled * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping * @map__map: bpf_map that embeds struct bpf_task_work in the values @@ -4176,15 +4177,17 @@ release_prog: * * Return: 0 if task work has been scheduled successfully, negative error code otherwise */ -__bpf_kfunc int bpf_task_work_schedule_signal(struct task_struct *task, struct bpf_task_work *tw, - void *map__map, bpf_task_work_callback_t callback, - void *aux__prog) +__bpf_kfunc int bpf_task_work_schedule_signal_impl(struct task_struct *task, + struct bpf_task_work *tw, void *map__map, + bpf_task_work_callback_t callback, + void *aux__prog) { return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_SIGNAL); } /** - * bpf_task_work_schedule_resume - Schedule BPF callback using task_work_add with TWA_RESUME mode + * bpf_task_work_schedule_resume_impl - Schedule BPF callback using task_work_add with TWA_RESUME + * mode * @task: Task struct for which callback should be scheduled * @tw: Pointer to struct bpf_task_work in BPF map value for internal bookkeeping * @map__map: bpf_map that embeds struct bpf_task_work in the values @@ -4193,9 +4196,10 @@ __bpf_kfunc int bpf_task_work_schedule_signal(struct task_struct *task, struct b * * Return: 0 if task work has been scheduled successfully, negative error code otherwise */ -__bpf_kfunc int bpf_task_work_schedule_resume(struct task_struct *task, struct bpf_task_work *tw, - void *map__map, bpf_task_work_callback_t callback, - void *aux__prog) +__bpf_kfunc int bpf_task_work_schedule_resume_impl(struct task_struct *task, + struct bpf_task_work *tw, void *map__map, + bpf_task_work_callback_t callback, + void *aux__prog) { return bpf_task_work_schedule(task, tw, map__map, callback, aux__prog, TWA_RESUME); } @@ -4374,9 +4378,9 @@ BTF_ID_FLAGS(func, bpf_strnstr); #if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS) BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU) #endif -BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_task_work_schedule_signal, KF_TRUSTED_ARGS) -BTF_ID_FLAGS(func, bpf_task_work_schedule_resume, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_stream_vprintk_impl, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_work_schedule_signal_impl, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_work_schedule_resume_impl, KF_TRUSTED_ARGS) BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c index eb6c5a21c2ef..ff16c631951b 100644 --- a/kernel/bpf/stream.c +++ b/kernel/bpf/stream.c @@ -355,7 +355,8 @@ __bpf_kfunc_start_defs(); * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the * enum in headers. */ -__bpf_kfunc int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, u32 len__sz, void *aux__prog) +__bpf_kfunc int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args, + u32 len__sz, void *aux__prog) { struct bpf_bprintf_data data = { .get_bin_args = true, diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 5949095e51c3..f2cb0b097093 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -479,11 +479,6 @@ again: * BPF_TRAMP_F_SHARE_IPMODIFY is set, we can generate the * trampoline again, and retry register. */ - /* reset fops->func and fops->trampoline for re-register */ - tr->fops->func = NULL; - tr->fops->trampoline = 0; - - /* free im memory and reallocate later */ bpf_tramp_image_free(im); goto again; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ff40e5e65c43..fbe4bb91c564 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8866,7 +8866,7 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; - int i, fr; + int i, fr, num_slots; reset_idmap_scratch(env); for (fr = old->curframe; fr >= 0; fr--) { @@ -8879,7 +8879,9 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env, &fcur->regs[i], &env->idmap_scratch); - for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) { + num_slots = min(fold->allocated_stack / BPF_REG_SIZE, + fcur->allocated_stack / BPF_REG_SIZE); + for (i = 0; i < num_slots; i++) { if (!is_spilled_reg(&fold->stack[i]) || !is_spilled_reg(&fcur->stack[i])) continue; @@ -12259,8 +12261,8 @@ enum special_kfunc_type { KF_bpf_res_spin_lock_irqsave, KF_bpf_res_spin_unlock_irqrestore, KF___bpf_trap, - KF_bpf_task_work_schedule_signal, - KF_bpf_task_work_schedule_resume, + KF_bpf_task_work_schedule_signal_impl, + KF_bpf_task_work_schedule_resume_impl, }; BTF_ID_LIST(special_kfunc_list) @@ -12331,13 +12333,13 @@ BTF_ID(func, bpf_res_spin_unlock) BTF_ID(func, bpf_res_spin_lock_irqsave) BTF_ID(func, bpf_res_spin_unlock_irqrestore) BTF_ID(func, __bpf_trap) -BTF_ID(func, bpf_task_work_schedule_signal) -BTF_ID(func, bpf_task_work_schedule_resume) +BTF_ID(func, bpf_task_work_schedule_signal_impl) +BTF_ID(func, bpf_task_work_schedule_resume_impl) static bool is_task_work_add_kfunc(u32 func_id) { - return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal] || - func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume]; + return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal_impl] || + func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume_impl]; } static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 3b1c43382eec..99dac1aa972a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -373,7 +373,7 @@ static int __crash_shrink_memory(struct resource *old_res, old_res->start = 0; old_res->end = 0; } else { - crashk_res.end = ram_res->start - 1; + old_res->end = ram_res->start - 1; } crash_free_reserved_phys_range(ram_res->start, ram_res->end); diff --git a/kernel/events/core.c b/kernel/events/core.c index 1fd347da9026..2c35acc2722b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -11901,7 +11901,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags) static void cpu_clock_event_del(struct perf_event *event, int flags) { - cpu_clock_event_stop(event, flags); + cpu_clock_event_stop(event, PERF_EF_UPDATE); } static void cpu_clock_event_read(struct perf_event *event) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 53166ef86ba4..26e45f86b955 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -821,8 +821,7 @@ int hibernate(void) goto Restore; ksys_sync_helper(); - if (filesystem_freeze_enabled) - filesystems_freeze(); + filesystems_freeze(filesystem_freeze_enabled); error = freeze_processes(); if (error) @@ -928,8 +927,7 @@ int hibernate_quiet_exec(int (*func)(void *data), void *data) if (error) goto restore; - if (filesystem_freeze_enabled) - filesystems_freeze(); + filesystems_freeze(filesystem_freeze_enabled); error = freeze_processes(); if (error) @@ -1079,8 +1077,7 @@ static int software_resume(void) if (error) goto Restore; - if (filesystem_freeze_enabled) - filesystems_freeze(); + filesystems_freeze(filesystem_freeze_enabled); pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index b4ca17c2fecf..3d4ebedad69f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -375,8 +375,7 @@ static int suspend_prepare(suspend_state_t state) if (error) goto Restore; - if (filesystem_freeze_enabled) - filesystems_freeze(); + filesystems_freeze(filesystem_freeze_enabled); trace_suspend_resume(TPS("freeze_processes"), 0, true); error = suspend_freeze_processes(); trace_suspend_resume(TPS("freeze_processes"), 0, false); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 0beff7eeaaba..70ae21f7370d 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -635,7 +635,7 @@ struct cmp_data { }; /* Indicates the image size after compression */ -static atomic_t compressed_size = ATOMIC_INIT(0); +static atomic64_t compressed_size = ATOMIC_INIT(0); /* * Compression function that runs in its own thread. @@ -664,7 +664,7 @@ static int compress_threadfn(void *data) d->ret = crypto_acomp_compress(d->cr); d->cmp_len = d->cr->dlen; - atomic_set(&compressed_size, atomic_read(&compressed_size) + d->cmp_len); + atomic64_add(d->cmp_len, &compressed_size); atomic_set_release(&d->stop, 1); wake_up(&d->done); } @@ -689,14 +689,14 @@ static int save_compressed_image(struct swap_map_handle *handle, ktime_t start; ktime_t stop; size_t off; - unsigned thr, run_threads, nr_threads; + unsigned int thr, run_threads, nr_threads; unsigned char *page = NULL; struct cmp_data *data = NULL; struct crc_data *crc = NULL; hib_init_batch(&hb); - atomic_set(&compressed_size, 0); + atomic64_set(&compressed_size, 0); /* * We'll limit the number of threads for compression to limit memory @@ -877,11 +877,14 @@ out_finish: stop = ktime_get(); if (!ret) ret = err2; - if (!ret) + if (!ret) { + swsusp_show_speed(start, stop, nr_to_write, "Wrote"); + pr_info("Image size after compression: %lld kbytes\n", + (atomic64_read(&compressed_size) / 1024)); pr_info("Image saving done\n"); - swsusp_show_speed(start, stop, nr_to_write, "Wrote"); - pr_info("Image size after compression: %d kbytes\n", - (atomic_read(&compressed_size) / 1024)); + } else { + pr_err("Image saving failed: %d\n", ret); + } out_clean: hib_finish_batch(&hb); @@ -899,7 +902,8 @@ out_clean: } vfree(data); } - if (page) free_page((unsigned long)page); + if (page) + free_page((unsigned long)page); return ret; } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index ecb251e883ea..979484dab2d3 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -25,7 +25,7 @@ static struct scx_sched __rcu *scx_root; * guarantee system safety. Maintain a dedicated task list which contains every * task between its fork and eventual free. */ -static DEFINE_SPINLOCK(scx_tasks_lock); +static DEFINE_RAW_SPINLOCK(scx_tasks_lock); static LIST_HEAD(scx_tasks); /* ops enable/disable */ @@ -476,7 +476,7 @@ static void scx_task_iter_start(struct scx_task_iter *iter) BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS & ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1)); - spin_lock_irq(&scx_tasks_lock); + raw_spin_lock_irq(&scx_tasks_lock); iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR }; list_add(&iter->cursor.tasks_node, &scx_tasks); @@ -507,14 +507,14 @@ static void scx_task_iter_unlock(struct scx_task_iter *iter) __scx_task_iter_rq_unlock(iter); if (iter->list_locked) { iter->list_locked = false; - spin_unlock_irq(&scx_tasks_lock); + raw_spin_unlock_irq(&scx_tasks_lock); } } static void __scx_task_iter_maybe_relock(struct scx_task_iter *iter) { if (!iter->list_locked) { - spin_lock_irq(&scx_tasks_lock); + raw_spin_lock_irq(&scx_tasks_lock); iter->list_locked = true; } } @@ -2940,9 +2940,9 @@ void scx_post_fork(struct task_struct *p) } } - spin_lock_irq(&scx_tasks_lock); + raw_spin_lock_irq(&scx_tasks_lock); list_add_tail(&p->scx.tasks_node, &scx_tasks); - spin_unlock_irq(&scx_tasks_lock); + raw_spin_unlock_irq(&scx_tasks_lock); percpu_up_read(&scx_fork_rwsem); } @@ -2966,9 +2966,9 @@ void sched_ext_free(struct task_struct *p) { unsigned long flags; - spin_lock_irqsave(&scx_tasks_lock, flags); + raw_spin_lock_irqsave(&scx_tasks_lock, flags); list_del_init(&p->scx.tasks_node); - spin_unlock_irqrestore(&scx_tasks_lock, flags); + raw_spin_unlock_irqrestore(&scx_tasks_lock, flags); /* * @p is off scx_tasks and wholly ours. scx_enable()'s READY -> ENABLED @@ -4276,7 +4276,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) size_t avail, used; bool idle; - rq_lock(rq, &rf); + rq_lock_irqsave(rq, &rf); idle = list_empty(&rq->scx.runnable_list) && rq->curr->sched_class == &idle_sched_class; @@ -4345,7 +4345,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) scx_dump_task(&s, &dctx, p, ' '); next: - rq_unlock(rq, &rf); + rq_unlock_irqrestore(rq, &rf); } dump_newline(&s); @@ -4479,8 +4479,11 @@ static struct scx_sched *scx_alloc_and_add_sched(struct sched_ext_ops *ops) goto err_free_gdsqs; sch->helper = kthread_run_worker(0, "sched_ext_helper"); - if (!sch->helper) + if (IS_ERR(sch->helper)) { + ret = PTR_ERR(sch->helper); goto err_free_pcpu; + } + sched_set_fifo(sch->helper->task); atomic_set(&sch->exit_kind, SCX_EXIT_NONE); @@ -5321,8 +5324,8 @@ void __init init_sched_ext_class(void) BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_kick_if_idle, GFP_KERNEL, n)); BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_preempt, GFP_KERNEL, n)); BUG_ON(!zalloc_cpumask_var_node(&rq->scx.cpus_to_wait, GFP_KERNEL, n)); - init_irq_work(&rq->scx.deferred_irq_work, deferred_irq_workfn); - init_irq_work(&rq->scx.kick_cpus_irq_work, kick_cpus_irq_workfn); + rq->scx.deferred_irq_work = IRQ_WORK_INIT_HARD(deferred_irq_workfn); + rq->scx.kick_cpus_irq_work = IRQ_WORK_INIT_HARD(kick_cpus_irq_workfn); if (cpu_online(cpu)) cpu_rq(cpu)->scx.flags |= SCX_RQ_ONLINE; @@ -6401,7 +6404,7 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf) guard(rcu)(); - sch = rcu_dereference(sch); + sch = rcu_dereference(scx_root); if (unlikely(!sch)) return; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index aa3120104a51..56e17b625c72 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -475,12 +475,6 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, if (!kc->timer_create) return -EOPNOTSUPP; - new_timer = alloc_posix_timer(); - if (unlikely(!new_timer)) - return -EAGAIN; - - spin_lock_init(&new_timer->it_lock); - /* Special case for CRIU to restore timers with a given timer ID. */ if (unlikely(current->signal->timer_create_restore_ids)) { if (copy_from_user(&req_id, created_timer_id, sizeof(req_id))) @@ -490,6 +484,12 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, return -EINVAL; } + new_timer = alloc_posix_timer(); + if (unlikely(!new_timer)) + return -EAGAIN; + + spin_lock_init(&new_timer->it_lock); + /* * Add the timer to the hash table. The timer is not yet valid * after insertion, but has a unique ID allocated. diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index c527b421c865..466e083c8272 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1152,16 +1152,15 @@ static bool report_idle_softirq(void) return false; } - if (ratelimit >= 10) - return false; - /* On RT, softirq handling may be waiting on some lock */ if (local_bh_blocked()) return false; - pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", - pending); - ratelimit++; + if (ratelimit < 10) { + pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", + pending); + ratelimit++; + } return true; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3a4d3b2e3f74..08e0943b54da 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -3060,29 +3060,32 @@ static const struct attribute_group aux_clock_enable_attr_group = { static int __init tk_aux_sysfs_init(void) { struct kobject *auxo, *tko = kobject_create_and_add("time", kernel_kobj); + int ret = -ENOMEM; if (!tko) - return -ENOMEM; + return ret; auxo = kobject_create_and_add("aux_clocks", tko); - if (!auxo) { - kobject_put(tko); - return -ENOMEM; - } + if (!auxo) + goto err_clean; for (int i = 0; i < MAX_AUX_CLOCKS; i++) { char id[2] = { [0] = '0' + i, }; struct kobject *clk = kobject_create_and_add(id, auxo); if (!clk) - return -ENOMEM; - - int ret = sysfs_create_group(clk, &aux_clock_enable_attr_group); + goto err_clean; + ret = sysfs_create_group(clk, &aux_clock_enable_attr_group); if (ret) - return ret; + goto err_clean; } return 0; + +err_clean: + kobject_put(auxo); + kobject_put(tko); + return ret; } late_initcall(tk_aux_sysfs_init); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 553fa469d7cc..d5ebb1d927ea 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1458,10 +1458,11 @@ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown) base = lock_timer_base(timer, &flags); - if (base->running_timer != timer) + if (base->running_timer != timer) { ret = detach_if_pending(timer, base, true); - if (shutdown) - timer->function = NULL; + if (shutdown) + timer->function = NULL; + } raw_spin_unlock_irqrestore(&base->lock, flags); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 42bd2ba68a82..59cfacb8a5bb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1971,7 +1971,8 @@ static void ftrace_hash_rec_enable_modify(struct ftrace_ops *ops) */ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, struct ftrace_hash *old_hash, - struct ftrace_hash *new_hash) + struct ftrace_hash *new_hash, + bool update_target) { struct ftrace_page *pg; struct dyn_ftrace *rec, *end = NULL; @@ -2006,10 +2007,13 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, if (rec->flags & FTRACE_FL_DISABLED) continue; - /* We need to update only differences of filter_hash */ + /* + * Unless we are updating the target of a direct function, + * we only need to update differences of filter_hash + */ in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); - if (in_old == in_new) + if (!update_target && (in_old == in_new)) continue; if (in_new) { @@ -2020,7 +2024,16 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, if (is_ipmodify) goto rollback; - FTRACE_WARN_ON(rec->flags & FTRACE_FL_DIRECT); + /* + * If this is called by __modify_ftrace_direct() + * then it is only changing where the direct + * pointer is jumping to, and the record already + * points to a direct trampoline. If it isn't, + * then it is a bug to update ipmodify on a direct + * caller. + */ + FTRACE_WARN_ON(!update_target && + (rec->flags & FTRACE_FL_DIRECT)); /* * Another ops with IPMODIFY is already @@ -2076,7 +2089,7 @@ static int ftrace_hash_ipmodify_enable(struct ftrace_ops *ops) if (ftrace_hash_empty(hash)) hash = NULL; - return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash); + return __ftrace_hash_update_ipmodify(ops, EMPTY_HASH, hash, false); } /* Disabling always succeeds */ @@ -2087,7 +2100,7 @@ static void ftrace_hash_ipmodify_disable(struct ftrace_ops *ops) if (ftrace_hash_empty(hash)) hash = NULL; - __ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH); + __ftrace_hash_update_ipmodify(ops, hash, EMPTY_HASH, false); } static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, @@ -2101,7 +2114,7 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, if (ftrace_hash_empty(new_hash)) new_hash = NULL; - return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash); + return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash, false); } static void print_ip_ins(const char *fmt, const unsigned char *p) @@ -5953,6 +5966,17 @@ static void register_ftrace_direct_cb(struct rcu_head *rhp) free_ftrace_hash(fhp); } +static void reset_direct(struct ftrace_ops *ops, unsigned long addr) +{ + struct ftrace_hash *hash = ops->func_hash->filter_hash; + + remove_direct_functions_hash(hash, addr); + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; +} + /** * register_ftrace_direct - Call a custom trampoline directly * for multiple functions registered in @ops @@ -6048,6 +6072,8 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) ops->direct_call = addr; err = register_ftrace_function_nolock(ops); + if (err) + reset_direct(ops, addr); out_unlock: mutex_unlock(&direct_mutex); @@ -6080,7 +6106,6 @@ EXPORT_SYMBOL_GPL(register_ftrace_direct); int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, bool free_filters) { - struct ftrace_hash *hash = ops->func_hash->filter_hash; int err; if (check_direct_multi(ops)) @@ -6090,13 +6115,9 @@ int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, mutex_lock(&direct_mutex); err = unregister_ftrace_function(ops); - remove_direct_functions_hash(hash, addr); + reset_direct(ops, addr); mutex_unlock(&direct_mutex); - /* cleanup for possible another register call */ - ops->func = NULL; - ops->trampoline = 0; - if (free_filters) ftrace_free_filter(ops); return err; @@ -6106,7 +6127,7 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_direct); static int __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { - struct ftrace_hash *hash; + struct ftrace_hash *hash = ops->func_hash->filter_hash; struct ftrace_func_entry *entry, *iter; static struct ftrace_ops tmp_ops = { .func = ftrace_stub, @@ -6127,12 +6148,20 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) return err; /* + * Call __ftrace_hash_update_ipmodify() here, so that we can call + * ops->ops_func for the ops. This is needed because the above + * register_ftrace_function_nolock() worked on tmp_ops. + */ + err = __ftrace_hash_update_ipmodify(ops, hash, hash, true); + if (err) + goto out; + + /* * Now the ftrace_ops_list_func() is called to do the direct callers. * We can safely change the direct functions attached to each entry. */ mutex_lock(&ftrace_lock); - hash = ops->func_hash->filter_hash; size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(iter, &hash->buckets[i], hlist) { @@ -6147,6 +6176,7 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) mutex_unlock(&ftrace_lock); +out: /* Removing the tmp_ops will add the updated direct callers to the functions */ unregister_ftrace_function(&tmp_ops); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d1e527cf2aae..304e93597126 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8781,8 +8781,18 @@ static void tracing_buffers_mmap_close(struct vm_area_struct *vma) put_snapshot_map(iter->tr); } +static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long addr) +{ + /* + * Trace buffer mappings require the complete buffer including + * the meta page. Partial mappings are not supported. + */ + return -EINVAL; +} + static const struct vm_operations_struct tracing_buffers_vmops = { .close = tracing_buffers_mmap_close, + .may_split = tracing_buffers_may_split, }; static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 3034e294d50d..713cc94caa02 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -445,8 +445,7 @@ config FRAME_WARN default 2048 if GCC_PLUGIN_LATENT_ENTROPY default 2048 if PARISC default 1536 if (!64BIT && XTENSA) - default 1280 if KASAN && !64BIT - default 1024 if !64BIT + default 1280 if !64BIT default 2048 if 64BIT help Tell the compiler to warn at build time for stack frames larger than this. diff --git a/lib/crypto/tests/sha256_kunit.c b/lib/crypto/tests/sha256_kunit.c index dcedfca06df6..5dccdee79693 100644 --- a/lib/crypto/tests/sha256_kunit.c +++ b/lib/crypto/tests/sha256_kunit.c @@ -68,6 +68,7 @@ static void test_sha256_finup_2x(struct kunit *test) rand_bytes(data1_buf, max_data_len); rand_bytes(data2_buf, max_data_len); rand_bytes(salt, sizeof(salt)); + memset(ctx, 0, sizeof(*ctx)); for (size_t i = 0; i < 500; i++) { size_t salt_len = rand_length(sizeof(salt)); diff --git a/lib/test_kho.c b/lib/test_kho.c index 60cd899ea745..fff018e5548d 100644 --- a/lib/test_kho.c +++ b/lib/test_kho.c @@ -301,6 +301,9 @@ static int __init kho_test_init(void) phys_addr_t fdt_phys; int err; + if (!kho_is_enabled()) + return 0; + err = kho_retrieve_subtree(KHO_TEST_FDT, &fdt_phys); if (!err) return kho_test_restore(fdt_phys); diff --git a/mm/Kconfig b/mm/Kconfig index 0e26f4fc8717..ca3f146bc705 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -908,6 +908,13 @@ config PAGE_MAPCOUNT config PGTABLE_HAS_HUGE_LEAVES def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE +# +# We can end up creating gigantic folio. +# +config HAVE_GIGANTIC_FOLIOS + def_bool (HUGETLB_PAGE && ARCH_HAS_GIGANTIC_PAGE) || \ + (ZONE_DEVICE && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + # TODO: Allow to be enabled without THP config ARCH_SUPPORTS_HUGE_PFNMAP def_bool n diff --git a/mm/filemap.c b/mm/filemap.c index 2f1e7e283a51..024b71da5224 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3682,8 +3682,9 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned short *mmap_miss, - bool can_map_large) + pgoff_t file_end) { + struct address_space *mapping = folio->mapping; unsigned int ref_from_caller = 1; vm_fault_t ret = 0; struct page *page = folio_page(folio, start); @@ -3692,12 +3693,16 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, unsigned long addr0; /* - * Map the large folio fully where possible. + * Map the large folio fully where possible: * - * The folio must not cross VMA or page table boundary. + * - The folio is fully within size of the file or belong + * to shmem/tmpfs; + * - The folio doesn't cross VMA boundary; + * - The folio doesn't cross page table boundary; */ addr0 = addr - start * PAGE_SIZE; - if (can_map_large && folio_within_vma(folio, vmf->vma) && + if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && + folio_within_vma(folio, vmf->vma) && (addr0 & PMD_MASK) == ((addr0 + folio_size(folio) - 1) & PMD_MASK)) { vmf->pte -= start; page -= start; @@ -3812,7 +3817,6 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, unsigned long rss = 0; unsigned int nr_pages = 0, folio_type; unsigned short mmap_miss = 0, mmap_miss_saved; - bool can_map_large; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); @@ -3823,16 +3827,14 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, end_pgoff = min(end_pgoff, file_end); /* - * Do not allow to map with PTEs beyond i_size and with PMD - * across i_size to preserve SIGBUS semantics. + * Do not allow to map with PMD across i_size to preserve + * SIGBUS semantics. * * Make an exception for shmem/tmpfs that for long time * intentionally mapped with PMDs across i_size. */ - can_map_large = shmem_mapping(mapping) || - file_end >= folio_next_index(folio); - - if (can_map_large && filemap_map_pmd(vmf, folio, start_pgoff)) { + if ((file_end >= folio_next_index(folio) || shmem_mapping(mapping)) && + filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } @@ -3861,8 +3863,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, - nr_pages, &rss, &mmap_miss, - can_map_large); + nr_pages, &rss, &mmap_miss, file_end); folio_unlock(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 323654fb4f8c..6cba1cb14b23 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3522,7 +3522,8 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, /* order-1 is not supported for anonymous THP. */ VM_WARN_ONCE(warns && new_order == 1, "Cannot split to order-1 folio"); - return new_order != 1; + if (new_order == 1) + return false; } else if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { /* @@ -3553,7 +3554,8 @@ bool uniform_split_supported(struct folio *folio, unsigned int new_order, if (folio_test_anon(folio)) { VM_WARN_ONCE(warns && new_order == 1, "Cannot split to order-1 folio"); - return new_order != 1; + if (new_order == 1) + return false; } else if (new_order) { if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { @@ -3617,6 +3619,16 @@ static int __folio_split(struct folio *folio, unsigned int new_order, if (folio != page_folio(split_at) || folio != page_folio(lock_at)) return -EINVAL; + /* + * Folios that just got truncated cannot get split. Signal to the + * caller that there was a race. + * + * TODO: this will also currently refuse shmem folios that are in the + * swapcache. + */ + if (!is_anon && !folio->mapping) + return -EBUSY; + if (new_order >= folio_order(folio)) return -EINVAL; @@ -3657,18 +3669,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order, gfp_t gfp; mapping = folio->mapping; - - /* Truncated ? */ - /* - * TODO: add support for large shmem folio in swap cache. - * When shmem is in swap cache, mapping is NULL and - * folio_test_swapcache() is true. - */ - if (!mapping) { - ret = -EBUSY; - goto out; - } - min_order = mapping_min_folio_order(folio->mapping); if (new_order < min_order) { ret = -EINVAL; diff --git a/mm/memblock.c b/mm/memblock.c index e23e16618e9b..f0f2dc66e9a2 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1826,7 +1826,8 @@ phys_addr_t __init_memblock memblock_reserved_kern_size(phys_addr_t limit, int n */ unsigned long __init memblock_estimated_nr_free_pages(void) { - return PHYS_PFN(memblock_phys_mem_size() - memblock_reserved_size()); + return PHYS_PFN(memblock_phys_mem_size() - + memblock_reserved_kern_size(MEMBLOCK_ALLOC_ANYWHERE, NUMA_NO_NODE)); } /* lowest address */ diff --git a/mm/memfd.c b/mm/memfd.c index 1d109c1acf21..a405eaa451ee 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -96,9 +96,36 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) NULL, gfp_mask); if (folio) { + u32 hash; + + /* + * Zero the folio to prevent information leaks to userspace. + * Use folio_zero_user() which is optimized for huge/gigantic + * pages. Pass 0 as addr_hint since this is not a faulting path + * and we don't have a user virtual address yet. + */ + folio_zero_user(folio, 0); + + /* + * Mark the folio uptodate before adding to page cache, + * as required by filemap.c and other hugetlb paths. + */ + __folio_mark_uptodate(folio); + + /* + * Serialize hugepage allocation and instantiation to prevent + * races with concurrent allocations, as required by all other + * callers of hugetlb_add_to_page_cache(). + */ + hash = hugetlb_fault_mutex_hash(memfd->f_mapping, idx); + mutex_lock(&hugetlb_fault_mutex_table[hash]); + err = hugetlb_add_to_page_cache(folio, memfd->f_mapping, idx); + + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + if (err) { folio_put(folio); goto err_unresv; diff --git a/mm/mempool.c b/mm/mempool.c index 1c38e873e546..d7bbf1189db9 100644 --- a/mm/mempool.c +++ b/mm/mempool.c @@ -68,10 +68,20 @@ static void check_element(mempool_t *pool, void *element) } else if (pool->free == mempool_free_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; - void *addr = kmap_local_page((struct page *)element); - __check_element(pool, addr, 1UL << (PAGE_SHIFT + order)); - kunmap_local(addr); +#ifdef CONFIG_HIGHMEM + for (int i = 0; i < (1 << order); i++) { + struct page *page = (struct page *)element; + void *addr = kmap_local_page(page + i); + + __check_element(pool, addr, PAGE_SIZE); + kunmap_local(addr); + } +#else + void *addr = page_address((struct page *)element); + + __check_element(pool, addr, PAGE_SIZE << order); +#endif } } @@ -97,10 +107,20 @@ static void poison_element(mempool_t *pool, void *element) } else if (pool->alloc == mempool_alloc_pages) { /* Mempools backed by page allocator */ int order = (int)(long)pool->pool_data; - void *addr = kmap_local_page((struct page *)element); - __poison_element(addr, 1UL << (PAGE_SHIFT + order)); - kunmap_local(addr); +#ifdef CONFIG_HIGHMEM + for (int i = 0; i < (1 << order); i++) { + struct page *page = (struct page *)element; + void *addr = kmap_local_page(page + i); + + __poison_element(addr, PAGE_SIZE); + kunmap_local(addr); + } +#else + void *addr = page_address((struct page *)element); + + __poison_element(addr, PAGE_SIZE << order); +#endif } } #else /* CONFIG_SLUB_DEBUG_ON */ diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 0a0db5849b8e..42e3dde73e74 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -241,6 +241,7 @@ retry: if (PTR_ERR(vma) == -EAGAIN) { count_vm_vma_lock_event(VMA_LOCK_MISS); /* The area was replaced with another one */ + mas_set(&mas, address); goto retry; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 600d9e981c23..ed82ee55e66a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1822,14 +1822,9 @@ inline void post_alloc_hook(struct page *page, unsigned int order, * If memory tags should be zeroed * (which happens only when memory should be initialized as well). */ - if (zero_tags) { - /* Initialize both memory and memory tags. */ - for (i = 0; i != 1 << order; ++i) - tag_clear_highpage(page + i); + if (zero_tags) + init = !tag_clear_highpages(page, 1 << order); - /* Take note that memory was initialized by the loop above. */ - init = false; - } if (!should_skip_kasan_unpoison(gfp_flags) && kasan_unpoison_pages(page, order, init)) { /* Take note that memory was initialized by KASAN. */ diff --git a/mm/shmem.c b/mm/shmem.c index 58701d14dd96..5a3f0f754dc0 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -131,8 +131,7 @@ struct shmem_options { #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 -#define SHMEM_SEEN_NOSWAP 16 -#define SHMEM_SEEN_QUOTA 32 +#define SHMEM_SEEN_QUOTA 16 }; #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -4680,7 +4679,6 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) "Turning off swap in unprivileged tmpfs mounts unsupported"); } ctx->noswap = true; - ctx->seen |= SHMEM_SEEN_NOSWAP; break; case Opt_quota: if (fc->user_ns != &init_user_ns) @@ -4830,14 +4828,15 @@ static int shmem_reconfigure(struct fs_context *fc) err = "Current inum too high to switch to 32-bit inums"; goto out; } - if ((ctx->seen & SHMEM_SEEN_NOSWAP) && ctx->noswap && !sbinfo->noswap) { + + /* + * "noswap" doesn't use fsparam_flag_no, i.e. there's no "swap" + * counterpart for (re-)enabling swap. + */ + if (ctx->noswap && !sbinfo->noswap) { err = "Cannot disable swap on remount"; goto out; } - if (!(ctx->seen & SHMEM_SEEN_NOSWAP) && !ctx->noswap && sbinfo->noswap) { - err = "Cannot enable swap on remount if it was disabled on first mount"; - goto out; - } if (ctx->seen & SHMEM_SEEN_QUOTA && !sb_any_quota_loaded(fc->root->d_sb)) { diff --git a/mm/slub.c b/mm/slub.c index 1bf65c421325..a0b905c2a557 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -6336,8 +6336,6 @@ next_remote_batch: if (unlikely(!slab_free_hook(s, p[i], init, false))) { p[i] = p[--size]; - if (!size) - goto flush_remote; continue; } @@ -6352,6 +6350,9 @@ next_remote_batch: i++; } + if (!size) + goto flush_remote; + next_batch: if (!local_trylock(&s->cpu_sheaves->lock)) goto fallback; @@ -6406,6 +6407,9 @@ do_free: goto next_batch; } + if (remote_nr) + goto flush_remote; + return; no_empty: diff --git a/mm/swap_state.c b/mm/swap_state.c index b13e9c4baa90..f4980dde5394 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -748,6 +748,8 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, blk_start_plug(&plug); for (addr = start; addr < end; ilx++, addr += PAGE_SIZE) { + struct swap_info_struct *si = NULL; + if (!pte++) { pte = pte_offset_map(vmf->pmd, addr); if (!pte) @@ -761,8 +763,19 @@ static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, continue; pte_unmap(pte); pte = NULL; + /* + * Readahead entry may come from a device that we are not + * holding a reference to, try to grab a reference, or skip. + */ + if (swp_type(entry) != swp_type(targ_entry)) { + si = get_swap_device(entry); + if (!si) + continue; + } folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, &page_allocated, false); + if (si) + put_swap_device(si); if (!folio) continue; if (page_allocated) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 10760240a3a2..a1b4b9d80e3b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2005,10 +2005,8 @@ swp_entry_t get_swap_page_of_type(int type) local_lock(&percpu_swap_cluster.lock); offset = cluster_alloc_swap_entry(si, 0, 1); local_unlock(&percpu_swap_cluster.lock); - if (offset) { + if (offset) entry = swp_entry(si->type, offset); - atomic_long_dec(&nr_swap_pages); - } } put_swap_device(si); } diff --git a/net/atm/common.c b/net/atm/common.c index cecc71a8bee1..fe77f51f6ce1 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -881,7 +881,7 @@ out_atmproc_exit: out_atmsvc_exit: atmsvc_exit(); out_atmpvc_exit: - atmsvc_exit(); + atmpvc_exit(); out_unregister_vcc_proto: proto_unregister(&vcc_proto); goto out; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 3418d7b964a1..8ccec73dce45 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -3832,13 +3832,14 @@ static void hci_tx_work(struct work_struct *work) static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_acl_hdr *hdr; - struct hci_conn *conn; __u16 handle, flags; + int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ACL packet too small"); - goto drop; + kfree_skb(skb); + return; } handle = __le16_to_cpu(hdr->handle); @@ -3850,36 +3851,27 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) hdev->stat.acl_rx++; - hci_dev_lock(hdev); - conn = hci_conn_hash_lookup_handle(hdev, handle); - hci_dev_unlock(hdev); - - if (conn) { - hci_conn_enter_active_mode(conn, BT_POWER_FORCE_ACTIVE_OFF); - - /* Send to upper protocol */ - l2cap_recv_acldata(conn, skb, flags); - return; - } else { + err = l2cap_recv_acldata(hdev, handle, skb, flags); + if (err == -ENOENT) bt_dev_err(hdev, "ACL packet for unknown connection handle %d", handle); - } - -drop: - kfree_skb(skb); + else if (err) + bt_dev_dbg(hdev, "ACL packet recv for handle %d failed: %d", + handle, err); } /* SCO data packet */ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_sco_hdr *hdr; - struct hci_conn *conn; __u16 handle, flags; + int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "SCO packet too small"); - goto drop; + kfree_skb(skb); + return; } handle = __le16_to_cpu(hdr->handle); @@ -3891,34 +3883,28 @@ static void hci_scodata_packet(struct hci_dev *hdev, struct sk_buff *skb) hdev->stat.sco_rx++; - hci_dev_lock(hdev); - conn = hci_conn_hash_lookup_handle(hdev, handle); - hci_dev_unlock(hdev); + hci_skb_pkt_status(skb) = flags & 0x03; - if (conn) { - /* Send to upper protocol */ - hci_skb_pkt_status(skb) = flags & 0x03; - sco_recv_scodata(conn, skb); - return; - } else { + err = sco_recv_scodata(hdev, handle, skb); + if (err == -ENOENT) bt_dev_err_ratelimited(hdev, "SCO packet for unknown connection handle %d", handle); - } - -drop: - kfree_skb(skb); + else if (err) + bt_dev_dbg(hdev, "SCO packet recv for handle %d failed: %d", + handle, err); } static void hci_isodata_packet(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_iso_hdr *hdr; - struct hci_conn *conn; __u16 handle, flags; + int err; hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) { bt_dev_err(hdev, "ISO packet too small"); - goto drop; + kfree_skb(skb); + return; } handle = __le16_to_cpu(hdr->handle); @@ -3928,22 +3914,13 @@ static void hci_isodata_packet(struct hci_dev *hdev, struct sk_buff *skb) bt_dev_dbg(hdev, "len %d handle 0x%4.4x flags 0x%4.4x", skb->len, handle, flags); - hci_dev_lock(hdev); - conn = hci_conn_hash_lookup_handle(hdev, handle); - hci_dev_unlock(hdev); - - if (!conn) { + err = iso_recv(hdev, handle, skb, flags); + if (err == -ENOENT) bt_dev_err(hdev, "ISO packet for unknown connection handle %d", handle); - goto drop; - } - - /* Send to upper protocol */ - iso_recv(conn, skb, flags); - return; - -drop: - kfree_skb(skb); + else if (err) + bt_dev_dbg(hdev, "ISO packet recv for handle %d failed: %d", + handle, err); } static bool hci_req_is_complete(struct hci_dev *hdev) @@ -4121,7 +4098,7 @@ static void hci_rx_work(struct work_struct *work) } } -static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) +static int hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) { int err; @@ -4133,16 +4110,19 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) if (!hdev->sent_cmd) { skb_queue_head(&hdev->cmd_q, skb); queue_work(hdev->workqueue, &hdev->cmd_work); - return; + return -EINVAL; } if (hci_skb_opcode(skb) != HCI_OP_NOP) { err = hci_send_frame(hdev, skb); if (err < 0) { hci_cmd_sync_cancel_sync(hdev, -err); - return; + return err; } atomic_dec(&hdev->cmd_cnt); + } else { + err = -ENODATA; + kfree_skb(skb); } if (hdev->req_status == HCI_REQ_PEND && @@ -4150,12 +4130,15 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); } + + return err; } static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); struct sk_buff *skb; + int err; BT_DBG("%s cmd_cnt %d cmd queued %d", hdev->name, atomic_read(&hdev->cmd_cnt), skb_queue_len(&hdev->cmd_q)); @@ -4166,7 +4149,9 @@ static void hci_cmd_work(struct work_struct *work) if (!skb) return; - hci_send_cmd_sync(hdev, skb); + err = hci_send_cmd_sync(hdev, skb); + if (err) + return; rcu_read_lock(); if (test_bit(HCI_RESET, &hdev->flags) || diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index ba9f48771e11..4e7bf63af9c5 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1311,7 +1311,9 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, goto done; } + hci_dev_lock(hdev); mgmt_index_removed(hdev); + hci_dev_unlock(hdev); err = hci_dev_open(hdev->id); if (err) { diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 243505b89733..5859ec1c04dd 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -2314,14 +2314,31 @@ static void iso_disconn_cfm(struct hci_conn *hcon, __u8 reason) iso_conn_del(hcon, bt_to_errno(reason)); } -void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) +int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) { - struct iso_conn *conn = hcon->iso_data; + struct hci_conn *hcon; + struct iso_conn *conn; struct skb_shared_hwtstamps *hwts; __u16 pb, ts, len, sn; - if (!conn) - goto drop; + hci_dev_lock(hdev); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon) { + hci_dev_unlock(hdev); + kfree_skb(skb); + return -ENOENT; + } + + conn = iso_conn_hold_unless_zero(hcon->iso_data); + hcon = NULL; + + hci_dev_unlock(hdev); + + if (!conn) { + kfree_skb(skb); + return -EINVAL; + } pb = hci_iso_flags_pb(flags); ts = hci_iso_flags_ts(flags); @@ -2377,7 +2394,7 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) hci_skb_pkt_status(skb) = flags & 0x03; hci_skb_pkt_seqnum(skb) = sn; iso_recv_frame(conn, skb); - return; + goto done; } if (pb == ISO_SINGLE) { @@ -2455,6 +2472,9 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) drop: kfree_skb(skb); +done: + iso_conn_put(conn); + return 0; } static struct hci_cb iso_cb = { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 35c57657bcf4..07b493331fd7 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7510,13 +7510,24 @@ struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *c) return c; } -void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) +int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb, u16 flags) { + struct hci_conn *hcon; struct l2cap_conn *conn; int len; - /* Lock hdev to access l2cap_data to avoid race with l2cap_conn_del */ - hci_dev_lock(hcon->hdev); + /* Lock hdev for hci_conn, and race on l2cap_data vs. l2cap_conn_del */ + hci_dev_lock(hdev); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon) { + hci_dev_unlock(hdev); + kfree_skb(skb); + return -ENOENT; + } + + hci_conn_enter_active_mode(hcon, BT_POWER_FORCE_ACTIVE_OFF); conn = hcon->l2cap_data; @@ -7524,12 +7535,13 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) conn = l2cap_conn_add(hcon); conn = l2cap_conn_hold_unless_zero(conn); + hcon = NULL; - hci_dev_unlock(hcon->hdev); + hci_dev_unlock(hdev); if (!conn) { kfree_skb(skb); - return; + return -EINVAL; } BT_DBG("conn %p len %u flags 0x%x", conn, skb->len, flags); @@ -7643,6 +7655,7 @@ drop: unlock: mutex_unlock(&conn->lock); l2cap_conn_put(conn); + return 0; } static struct hci_cb l2cap_cb = { diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 7afe65e7ff37..87ba90336e80 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1458,22 +1458,39 @@ static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) sco_conn_del(hcon, bt_to_errno(reason)); } -void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) +int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb) { - struct sco_conn *conn = hcon->sco_data; + struct hci_conn *hcon; + struct sco_conn *conn; - if (!conn) - goto drop; + hci_dev_lock(hdev); + + hcon = hci_conn_hash_lookup_handle(hdev, handle); + if (!hcon) { + hci_dev_unlock(hdev); + kfree_skb(skb); + return -ENOENT; + } + + conn = sco_conn_hold_unless_zero(hcon->sco_data); + hcon = NULL; + + hci_dev_unlock(hdev); + + if (!conn) { + kfree_skb(skb); + return -EINVAL; + } BT_DBG("conn %p len %u", conn, skb->len); - if (skb->len) { + if (skb->len) sco_recv_frame(conn, skb); - return; - } + else + kfree_skb(skb); -drop: - kfree_skb(skb); + sco_conn_put(conn); + return 0; } static struct hci_cb sco_cb = { diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 45512b2ba951..3a1ce04a7a53 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -2136,7 +2136,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_chan *smp = chan->data; struct hci_conn *hcon = conn->hcon; u8 *pkax, *pkbx, *na, *nb, confirm_hint; - u32 passkey; + u32 passkey = 0; int err; bt_dev_dbg(hcon->hdev, "conn %p", conn); @@ -2188,24 +2188,6 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); - - /* Only Just-Works pairing requires extra checks */ - if (smp->method != JUST_WORKS) - goto mackey_and_ltk; - - /* If there already exists long term key in local host, leave - * the decision to user space since the remote device could - * be legitimate or malicious. - */ - if (hci_find_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, - hcon->role)) { - /* Set passkey to 0. The value can be any number since - * it'll be ignored anyway. - */ - passkey = 0; - confirm_hint = 1; - goto confirm; - } } mackey_and_ltk: @@ -2226,11 +2208,12 @@ mackey_and_ltk: if (err) return SMP_UNSPECIFIED; - confirm_hint = 0; - -confirm: - if (smp->method == JUST_WORKS) - confirm_hint = 1; + /* Always require user confirmation for Just-Works pairing to prevent + * impersonation attacks, or in case of a legitimate device that is + * repairing use the confirmation as acknowledgment to proceed with the + * creation of new keys. + */ + confirm_hint = smp->method == JUST_WORKS ? 1 : 0; err = mgmt_user_confirm_request(hcon->hdev, &hcon->dst, hcon->type, hcon->dst_type, passkey, confirm_hint); diff --git a/net/can/raw.c b/net/can/raw.c index f36a83d3447c..be1ef7cf4204 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -892,20 +892,58 @@ static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) } } -static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +static inline bool raw_dev_cc_enabled(struct net_device *dev, + struct can_priv *priv) { - /* Classical CAN -> no checks for flags and device capabilities */ - if (can_is_can_skb(skb)) + /* The CANXL-only mode disables error-signalling on the CAN bus + * which is needed to send CAN CC/FD frames + */ + if (priv) + return !can_dev_in_xl_only_mode(priv); + + /* virtual CAN interfaces always support CAN CC */ + return true; +} + +static inline bool raw_dev_fd_enabled(struct net_device *dev, + struct can_priv *priv) +{ + /* check FD ctrlmode on real CAN interfaces */ + if (priv) + return (priv->ctrlmode & CAN_CTRLMODE_FD); + + /* check MTU for virtual CAN FD interfaces */ + return (READ_ONCE(dev->mtu) >= CANFD_MTU); +} + +static inline bool raw_dev_xl_enabled(struct net_device *dev, + struct can_priv *priv) +{ + /* check XL ctrlmode on real CAN interfaces */ + if (priv) + return (priv->ctrlmode & CAN_CTRLMODE_XL); + + /* check MTU for virtual CAN XL interfaces */ + return can_is_canxl_dev_mtu(READ_ONCE(dev->mtu)); +} + +static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, + struct net_device *dev) +{ + struct can_priv *priv = safe_candev_priv(dev); + + /* Classical CAN */ + if (can_is_can_skb(skb) && raw_dev_cc_enabled(dev, priv)) return CAN_MTU; - /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ + /* CAN FD */ if (ro->fd_frames && can_is_canfd_skb(skb) && - (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) + raw_dev_fd_enabled(dev, priv)) return CANFD_MTU; - /* CAN XL -> needs to be enabled and a CAN XL device */ + /* CAN XL */ if (ro->xl_frames && can_is_canxl_skb(skb) && - can_is_canxl_dev_mtu(mtu)) + raw_dev_xl_enabled(dev, priv)) return CANXL_MTU; return 0; @@ -961,7 +999,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) err = -EINVAL; /* check for valid CAN (CC/FD/XL) frame content */ - txmtu = raw_check_txframe(ro, skb, READ_ONCE(dev->mtu)); + txmtu = raw_check_txframe(ro, skb, dev); if (!txmtu) goto free_skb; diff --git a/net/core/dev.c b/net/core/dev.c index 69515edd17bc..9094c0fb8c68 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4069,17 +4069,23 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); -static void qdisc_pkt_len_init(struct sk_buff *skb) +static void qdisc_pkt_len_segs_init(struct sk_buff *skb) { - const struct skb_shared_info *shinfo = skb_shinfo(skb); + struct skb_shared_info *shinfo = skb_shinfo(skb); + u16 gso_segs; qdisc_skb_cb(skb)->pkt_len = skb->len; + if (!shinfo->gso_size) { + qdisc_skb_cb(skb)->pkt_segs = 1; + return; + } + + qdisc_skb_cb(skb)->pkt_segs = gso_segs = shinfo->gso_segs; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ - if (shinfo->gso_size && skb_transport_header_was_set(skb)) { - u16 gso_segs = shinfo->gso_segs; + if (skb_transport_header_was_set(skb)) { unsigned int hdr_len; /* mac layer + network layer */ @@ -4112,6 +4118,8 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) if (payload <= 0) return; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); + shinfo->gso_segs = gso_segs; + qdisc_skb_cb(skb)->pkt_segs = gso_segs; } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } @@ -4133,7 +4141,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { - struct sk_buff *next, *to_free = NULL; + struct sk_buff *next, *to_free = NULL, *to_free2 = NULL; spinlock_t *root_lock = qdisc_lock(q); struct llist_node *ll_list, *first_n; unsigned long defer_count = 0; @@ -4152,9 +4160,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); - qdisc_run_end(q); + to_free2 = qdisc_run_end(q); - goto no_lock_out; + goto free_skbs; } qdisc_bstats_cpu_update(q, skb); @@ -4162,18 +4170,14 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, !nolock_qdisc_is_empty(q)) __qdisc_run(q); - qdisc_run_end(q); - return NET_XMIT_SUCCESS; + to_free2 = qdisc_run_end(q); + rc = NET_XMIT_SUCCESS; + goto free_skbs; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); - qdisc_run(q); - -no_lock_out: - if (unlikely(to_free)) - kfree_skb_list_reason(to_free, - tcf_get_drop_reason(to_free)); - return rc; + to_free2 = qdisc_run(q); + goto free_skbs; } /* Open code llist_add(&skb->ll_node, &q->defer_list) + queue limit. @@ -4186,7 +4190,7 @@ no_lock_out: do { if (first_n && !defer_count) { defer_count = atomic_long_inc_return(&q->defer_count); - if (unlikely(defer_count > q->limit)) { + if (unlikely(defer_count > READ_ONCE(q->limit))) { kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP); return NET_XMIT_DROP; } @@ -4231,26 +4235,28 @@ no_lock_out: qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) __qdisc_run(q); - qdisc_run_end(q); + to_free2 = qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { int count = 0; llist_for_each_entry_safe(skb, next, ll_list, ll_node) { prefetch(next); + prefetch(&next->priority); skb_mark_not_on_list(skb); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); count++; } - qdisc_run(q); + to_free2 = qdisc_run(q); if (count != 1) rc = NET_XMIT_SUCCESS; } unlock: spin_unlock(root_lock); - if (unlikely(to_free)) - kfree_skb_list_reason(to_free, - tcf_get_drop_reason(to_free)); + +free_skbs: + tcf_kfree_skb_list(to_free); + tcf_kfree_skb_list(to_free2); return rc; } @@ -4355,7 +4361,7 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, return ret; tc_skb_cb(skb)->mru = 0; - tc_skb_cb(skb)->post_ct = false; + qdisc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); @@ -4426,7 +4432,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *pt_prev = NULL; } - qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_pkt_len_segs_init(skb); tcx_set_ingress(skb, true); if (static_branch_unlikely(&tcx_needed_key)) { @@ -4737,7 +4743,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) skb_update_prio(skb); - qdisc_pkt_len_init(skb); + qdisc_pkt_len_segs_init(skb); tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { @@ -5743,8 +5749,9 @@ static __latent_entropy void net_tx_action(void) rcu_read_lock(); while (head) { - struct Qdisc *q = head; spinlock_t *root_lock = NULL; + struct sk_buff *to_free; + struct Qdisc *q = head; head = head->next_sched; @@ -5771,9 +5778,10 @@ static __latent_entropy void net_tx_action(void) } clear_bit(__QDISC_STATE_SCHED, &q->state); - qdisc_run(q); + to_free = qdisc_run(q); if (root_lock) spin_unlock(root_lock); + tcf_kfree_skb_list(to_free); } rcu_read_unlock(); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b3ce0fb24a69..53a53357cfef 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -249,10 +249,11 @@ int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg) * * Helper for calling the default hardware provider timestamping. * - * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and - * there only exists a phydev->mii_ts->hwtstamp() method. So this will return - * -EOPNOTSUPP for phylib for now, which is still more accurate than letting - * the netdev handle the GET request. + * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), but + * phydev->mii_ts has both hwtstamp_get() and hwtstamp_set() methods. So this + * will return -EOPNOTSUPP for phylib only if hwtstamp_get() is not + * implemented for now, which is still more accurate than letting the netdev + * handle the GET request. */ int dev_get_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg) @@ -443,6 +444,9 @@ static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, struct ifreq ifrr; int err; + if (!kernel_cfg->ifr) + return -EINVAL; + strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; diff --git a/net/core/devmem.c b/net/core/devmem.c index 1d04754bc756..ec4217d6c0b4 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -97,9 +97,9 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) index = offset / PAGE_SIZE; niov = &owner->area.niovs[index]; - niov->pp_magic = 0; - niov->pp = NULL; - atomic_long_set(&niov->pp_ref_count, 0); + niov->desc.pp_magic = 0; + niov->desc.pp = NULL; + atomic_long_set(&niov->desc.pp_ref_count, 0); return niov; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index adcfef55a66f..dfad7c03b809 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -1223,15 +1223,13 @@ static void __init netns_ipv4_struct_check(void) sysctl_tcp_wmem); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_ip_fwd_use_pmtu); - CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); - - /* TXRX readonly hotpath cache lines */ - CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, - sysctl_tcp_moderate_rcvbuf); - CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); /* RX readonly hotpath cache line */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_moderate_rcvbuf); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, + sysctl_tcp_rcvbuf_low_rtt); + CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_ip_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_early_demux); @@ -1241,7 +1239,6 @@ static void __init netns_ipv4_struct_check(void) sysctl_tcp_reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_rmem); - CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 22); } #endif diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index ff20435c45d2..ba673e81716f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index cf3fad74511f..cffc08517a41 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_NETDEV_GEN_H #define _LINUX_NETDEV_GEN_H diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f34372666e67..a00808f7be6a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -223,9 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) skb_panic(skb, sz, addr, __func__); } -#define NAPI_SKB_CACHE_SIZE 64 -#define NAPI_SKB_CACHE_BULK 16 -#define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) +#define NAPI_SKB_CACHE_SIZE 128 +#define NAPI_SKB_CACHE_BULK 32 +#define NAPI_SKB_CACHE_FREE 32 struct napi_alloc_cache { local_lock_t bh_lock; @@ -280,17 +280,18 @@ EXPORT_SYMBOL(__netdev_alloc_frag_align); */ static u32 skbuff_cache_size __read_mostly; -static struct sk_buff *napi_skb_cache_get(void) +static struct sk_buff *napi_skb_cache_get(bool alloc) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, - GFP_ATOMIC | __GFP_NOWARN, - NAPI_SKB_CACHE_BULK, - nc->skb_cache); + if (alloc) + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN, + NAPI_SKB_CACHE_BULK, + nc->skb_cache); if (unlikely(!nc->skb_count)) { local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; @@ -298,6 +299,8 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; + if (nc->skb_count) + prefetch(nc->skb_cache[nc->skb_count - 1]); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); kasan_mempool_unpoison_object(skb, skbuff_cache_size); @@ -530,7 +533,7 @@ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = napi_skb_cache_get(); + skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; @@ -645,25 +648,38 @@ out: struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { + struct sk_buff *skb = NULL; struct kmem_cache *cache; - struct sk_buff *skb; bool pfmemalloc; u8 *data; - cache = (flags & SKB_ALLOC_FCLONE) - ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; - if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; - /* Get the HEAD */ - if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && - likely(node == NUMA_NO_NODE || node == numa_mem_id())) - skb = napi_skb_cache_get(); - else + if (flags & SKB_ALLOC_FCLONE) { + cache = net_hotdata.skbuff_fclone_cache; + goto fallback; + } + cache = net_hotdata.skbuff_cache; + if (unlikely(node != NUMA_NO_NODE && node != numa_mem_id())) + goto fallback; + + if (flags & SKB_ALLOC_NAPI) { + skb = napi_skb_cache_get(true); + if (unlikely(!skb)) + return NULL; + } else if (!in_hardirq() && !irqs_disabled()) { + local_bh_disable(); + skb = napi_skb_cache_get(false); + local_bh_enable(); + } + + if (!skb) { +fallback: skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); - if (unlikely(!skb)) - return NULL; + if (unlikely(!skb)) + return NULL; + } prefetchw(skb); /* We do our best to align skb_shared_info on a separate cache @@ -1431,7 +1447,6 @@ void __consume_stateless_skb(struct sk_buff *skb) static void napi_skb_cache_put(struct sk_buff *skb) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - u32 i; if (!kasan_mempool_poison_object(skb)) return; @@ -1440,13 +1455,16 @@ static void napi_skb_cache_put(struct sk_buff *skb) nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { - for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) + u32 i, remaining = NAPI_SKB_CACHE_SIZE - NAPI_SKB_CACHE_FREE; + + for (i = remaining; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], skbuff_cache_size); - kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, - nc->skb_cache + NAPI_SKB_CACHE_HALF); - nc->skb_count = NAPI_SKB_CACHE_HALF; + kmem_cache_free_bulk(net_hotdata.skbuff_cache, + NAPI_SKB_CACHE_FREE, + nc->skb_cache + remaining); + nc->skb_count = remaining; } local_unlock_nested_bh(&napi_alloc_cache.bh_lock); } @@ -1472,7 +1490,7 @@ void napi_skb_free_stolen_head(struct sk_buff *skb) void napi_consume_skb(struct sk_buff *skb, int budget) { /* Zero budget indicate non-NAPI context called us, like netpoll */ - if (unlikely(!budget)) { + if (unlikely(!budget || !skb)) { dev_consume_skb_any(skb); return; } diff --git a/net/core/sock.c b/net/core/sock.c index 3b74fc71f51c..45c98bf524b2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3448,6 +3448,24 @@ void __sk_mem_reclaim(struct sock *sk, int amount) } EXPORT_SYMBOL(__sk_mem_reclaim); +void __sk_charge(struct sock *sk, gfp_t gfp) +{ + int amt; + + gfp |= __GFP_NOFAIL; + if (mem_cgroup_from_sk(sk)) { + /* The socket has not been accepted yet, no need + * to look at newsk->sk_wmem_queued. + */ + amt = sk_mem_pages(sk->sk_forward_alloc + + atomic_read(&sk->sk_rmem_alloc)); + if (amt) + mem_cgroup_sk_charge(sk, amt, gfp); + } + + kmem_cache_charge(sk, gfp); +} + int sk_set_peek_off(struct sock *sk, int val) { WRITE_ONCE(sk->sk_peek_off, val); @@ -4501,14 +4519,14 @@ static int __init sock_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_send_head); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_write_pending); - CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_dst_pending_confirm); - CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_frag); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_timer); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_zckey); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_write_tx, sk_tskey); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_dst_pending_confirm); + CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_pacing_status); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_max_pacing_rate); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_sndtimeo); CACHELINE_ASSERT_GROUP_MEMBER(struct sock, sock_read_tx, sk_priority); diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 5ad435aee29d..f4c61c2b4f22 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/devlink.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> @@ -301,12 +302,13 @@ static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV }; /* DEVLINK_CMD_PARAM_SET - do */ -static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VALUE_CMODE + 1] = { +static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_RESET_DEFAULT + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_PARAM_TYPE] = NLA_POLICY_VALIDATE_FN(NLA_U8, &devlink_attr_param_type_validate), [DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2), + [DEVLINK_ATTR_PARAM_RESET_DEFAULT] = { .type = NLA_FLAG, }, }; /* DEVLINK_CMD_REGION_GET - do */ @@ -919,7 +921,7 @@ const struct genl_split_ops devlink_nl_ops[74] = { .doit = devlink_nl_param_set_doit, .post_doit = devlink_nl_post_doit, .policy = devlink_param_set_nl_policy, - .maxattr = DEVLINK_ATTR_PARAM_VALUE_CMODE, + .maxattr = DEVLINK_ATTR_PARAM_RESET_DEFAULT, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, { diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index 09cc6f264ccf..2817d53a0eba 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/devlink.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_DEVLINK_GEN_H #define _LINUX_DEVLINK_GEN_H diff --git a/net/devlink/param.c b/net/devlink/param.c index 6b233b13b69a..e0ea93eded43 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -174,11 +174,12 @@ devlink_param_cmode_is_supported(const struct devlink_param *param, static int devlink_param_get(struct devlink *devlink, const struct devlink_param *param, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { if (!param->get) return -EOPNOTSUPP; - return param->get(devlink, param->id, ctx); + return param->get(devlink, param->id, ctx, extack); } static int devlink_param_set(struct devlink *devlink, @@ -191,68 +192,121 @@ static int devlink_param_set(struct devlink *devlink, return param->set(devlink, param->id, ctx, extack); } -static int -devlink_nl_param_value_fill_one(struct sk_buff *msg, - enum devlink_param_type type, - enum devlink_param_cmode cmode, - union devlink_param_value val) +static int devlink_param_get_default(struct devlink *devlink, + const struct devlink_param *param, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { - struct nlattr *param_value_attr; + if (!param->get_default) + return -EOPNOTSUPP; - param_value_attr = nla_nest_start_noflag(msg, - DEVLINK_ATTR_PARAM_VALUE); - if (!param_value_attr) - goto nla_put_failure; + return param->get_default(devlink, param->id, ctx, extack); +} - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode)) - goto value_nest_cancel; +static int devlink_param_reset_default(struct devlink *devlink, + const struct devlink_param *param, + enum devlink_param_cmode cmode, + struct netlink_ext_ack *extack) +{ + if (!param->reset_default) + return -EOPNOTSUPP; + return param->reset_default(devlink, param->id, cmode, extack); +} + +static int +devlink_nl_param_value_put(struct sk_buff *msg, enum devlink_param_type type, + int nla_type, union devlink_param_value val, + bool flag_as_u8) +{ switch (type) { case DEVLINK_PARAM_TYPE_U8: - if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8)) - goto value_nest_cancel; + if (nla_put_u8(msg, nla_type, val.vu8)) + return -EMSGSIZE; break; case DEVLINK_PARAM_TYPE_U16: - if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16)) - goto value_nest_cancel; + if (nla_put_u16(msg, nla_type, val.vu16)) + return -EMSGSIZE; break; case DEVLINK_PARAM_TYPE_U32: - if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32)) - goto value_nest_cancel; + if (nla_put_u32(msg, nla_type, val.vu32)) + return -EMSGSIZE; break; case DEVLINK_PARAM_TYPE_U64: - if (devlink_nl_put_u64(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, - val.vu64)) - goto value_nest_cancel; + if (devlink_nl_put_u64(msg, nla_type, val.vu64)) + return -EMSGSIZE; break; case DEVLINK_PARAM_TYPE_STRING: - if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, - val.vstr)) - goto value_nest_cancel; + if (nla_put_string(msg, nla_type, val.vstr)) + return -EMSGSIZE; break; case DEVLINK_PARAM_TYPE_BOOL: - if (val.vbool && - nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA)) - goto value_nest_cancel; + /* default values of type bool are encoded with u8, so that + * false can be distinguished from not present + */ + if (flag_as_u8) { + if (nla_put_u8(msg, nla_type, val.vbool)) + return -EMSGSIZE; + } else { + if (val.vbool && nla_put_flag(msg, nla_type)) + return -EMSGSIZE; + } break; } + return 0; +} + +static int +devlink_nl_param_value_fill_one(struct sk_buff *msg, + enum devlink_param_type type, + enum devlink_param_cmode cmode, + union devlink_param_value val, + union devlink_param_value default_val, + bool has_default) +{ + struct nlattr *param_value_attr; + int err = -EMSGSIZE; + + param_value_attr = nla_nest_start_noflag(msg, + DEVLINK_ATTR_PARAM_VALUE); + if (!param_value_attr) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode)) + goto value_nest_cancel; + + err = devlink_nl_param_value_put(msg, type, + DEVLINK_ATTR_PARAM_VALUE_DATA, + val, false); + if (err) + goto value_nest_cancel; + + if (has_default) { + err = devlink_nl_param_value_put(msg, type, + DEVLINK_ATTR_PARAM_VALUE_DEFAULT, + default_val, true); + if (err) + goto value_nest_cancel; + } nla_nest_end(msg, param_value_attr); return 0; value_nest_cancel: nla_nest_cancel(msg, param_value_attr); -nla_put_failure: - return -EMSGSIZE; + return err; } static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd, - u32 portid, u32 seq, int flags) + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) { + union devlink_param_value default_value[DEVLINK_PARAM_CMODE_MAX + 1]; union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; + bool default_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; const struct devlink_param *param = param_item->param; struct devlink_param_gset_ctx ctx; @@ -273,12 +327,26 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, param_value[i] = param_item->driverinit_value; else return -EOPNOTSUPP; + + if (param_item->driverinit_value_valid) { + default_value[i] = param_item->driverinit_default; + default_value_set[i] = true; + } } else { ctx.cmode = i; - err = devlink_param_get(devlink, param, &ctx); + err = devlink_param_get(devlink, param, &ctx, extack); if (err) return err; param_value[i] = ctx.val; + + err = devlink_param_get_default(devlink, param, &ctx, + extack); + if (!err) { + default_value[i] = ctx.val; + default_value_set[i] = true; + } else if (err != -EOPNOTSUPP) { + return err; + } } param_value_set[i] = true; } @@ -315,7 +383,9 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (!param_value_set[i]) continue; err = devlink_nl_param_value_fill_one(msg, param->type, - i, param_value[i]); + i, param_value[i], + default_value[i], + default_value_set[i]); if (err) goto values_list_nest_cancel; } @@ -357,7 +427,7 @@ static void devlink_param_notify(struct devlink *devlink, if (!msg) return; err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, - 0, 0, 0); + 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; @@ -400,7 +470,8 @@ static int devlink_nl_param_get_dump_one(struct sk_buff *msg, err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, flags); + cb->nlh->nlmsg_seq, flags, + cb->extack); if (err == -EOPNOTSUPP) { err = 0; } else if (err) { @@ -509,8 +580,8 @@ int devlink_nl_param_get_doit(struct sk_buff *skb, return -ENOMEM; err = devlink_nl_param_fill(msg, devlink, 0, param_item, - DEVLINK_CMD_PARAM_GET, - info->snd_portid, info->snd_seq, 0); + DEVLINK_CMD_PARAM_GET, info->snd_portid, + info->snd_seq, 0, info->extack); if (err) { nlmsg_free(msg); return err; @@ -531,6 +602,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, struct devlink_param_item *param_item; const struct devlink_param *param; union devlink_param_value value; + bool reset_default; int err = 0; param_item = devlink_param_get_from_info(params, info); @@ -542,13 +614,18 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return err; if (param_type != param->type) return -EINVAL; - err = devlink_param_value_get_from_info(param, info, &value); - if (err) - return err; - if (param->validate) { - err = param->validate(devlink, param->id, value, info->extack); + + reset_default = info->attrs[DEVLINK_ATTR_PARAM_RESET_DEFAULT]; + if (!reset_default) { + err = devlink_param_value_get_from_info(param, info, &value); if (err) return err; + if (param->validate) { + err = param->validate(devlink, param->id, value, + info->extack); + if (err) + return err; + } } if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_PARAM_VALUE_CMODE)) @@ -558,6 +635,15 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return -EOPNOTSUPP; if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) { + if (reset_default) { + if (!param_item->driverinit_value_valid) { + NL_SET_ERR_MSG(info->extack, + "Default value not available"); + return -EOPNOTSUPP; + } + value = param_item->driverinit_default; + } + param_item->driverinit_value_new = value; param_item->driverinit_value_new_valid = true; } else { @@ -565,7 +651,12 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return -EOPNOTSUPP; ctx.val = value; ctx.cmode = cmode; - err = devlink_param_set(devlink, param, &ctx, info->extack); + if (reset_default) + err = devlink_param_reset_default(devlink, param, cmode, + info->extack); + else + err = devlink_param_set(devlink, param, &ctx, + info->extack); if (err) return err; } @@ -813,6 +904,7 @@ void devl_param_driverinit_value_set(struct devlink *devlink, u32 param_id, param_item->driverinit_value = init_val; param_item->driverinit_value_valid = true; + param_item->driverinit_default = init_val; devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); } diff --git a/net/devlink/rate.c b/net/devlink/rate.c index 264fb82cba19..d157a8419bca 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -828,13 +828,15 @@ void devl_rate_nodes_destroy(struct devlink *devlink) if (!devlink_rate->parent) continue; - refcount_dec(&devlink_rate->parent->refcnt); if (devlink_rate_is_leaf(devlink_rate)) ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); else if (devlink_rate_is_node(devlink_rate)) ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, NULL, NULL); + + refcount_dec(&devlink_rate->parent->refcnt); + devlink_rate->parent = NULL; } list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { if (devlink_rate_is_node(devlink_rate)) { diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c index 4ae255cfb23f..a1b044467bd6 100644 --- a/net/dsa/conduit.c +++ b/net/dsa/conduit.c @@ -26,7 +26,7 @@ static int dsa_conduit_get_regs_len(struct net_device *dev) int ret = 0; int len; - if (ops->get_regs_len) { + if (ops && ops->get_regs_len) { netdev_lock_ops(dev); len = ops->get_regs_len(dev); netdev_unlock_ops(dev); @@ -59,7 +59,7 @@ static void dsa_conduit_get_regs(struct net_device *dev, int port = cpu_dp->index; int len; - if (ops->get_regs_len && ops->get_regs) { + if (ops && ops->get_regs_len && ops->get_regs) { netdev_lock_ops(dev); len = ops->get_regs_len(dev); if (len < 0) { @@ -87,30 +87,56 @@ static void dsa_conduit_get_regs(struct net_device *dev, } } +static ssize_t dsa_conduit_append_port_stats(struct dsa_switch *ds, int port, + u64 *data, size_t start) +{ + int count; + + if (!ds->ops->get_sset_count) + return 0; + + count = ds->ops->get_sset_count(ds, port, ETH_SS_STATS); + if (count < 0) + return count; + + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, port, data + start); + + return count; +} + static void dsa_conduit_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, - uint64_t *data) + u64 *data) { - struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int count = 0; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; - if (ops->get_sset_count && ops->get_ethtool_stats) { + if (ops && ops->get_sset_count && ops->get_ethtool_stats) { netdev_lock_ops(dev); - count = ops->get_sset_count(dev, ETH_SS_STATS); + mcount = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); netdev_unlock_ops(dev); } - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, port, data + count); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_stats(dp->ds, dp->index, + data, mcount); + if (count < 0) + return; + + mcount += count; + } } static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, struct ethtool_stats *stats, - uint64_t *data) + u64 *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -118,11 +144,11 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, int port = cpu_dp->index; int count = 0; - if (dev->phydev && !ops->get_ethtool_phy_stats) { + if (dev->phydev && (!ops || !ops->get_ethtool_phy_stats)) { count = phy_ethtool_get_sset_count(dev->phydev); if (count >= 0) phy_ethtool_get_stats(dev->phydev, stats, data); - } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) { + } else if (ops && ops->get_sset_count && ops->get_ethtool_phy_stats) { netdev_lock_ops(dev); count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); ops->get_ethtool_phy_stats(dev, stats, data); @@ -136,45 +162,82 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, ds->ops->get_ethtool_phy_stats(ds, port, data + count); } +static void dsa_conduit_append_port_sset_count(struct dsa_switch *ds, int port, + int sset, int *count) +{ + if (ds->ops->get_sset_count) + *count += ds->ops->get_sset_count(ds, port, sset); +} + static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) { - struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; + struct dsa_switch_tree *dst = cpu_dp->dst; int count = 0; netdev_lock_ops(dev); if (sset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) + (!ops || !ops->get_ethtool_phy_stats)) count = phy_ethtool_get_sset_count(dev->phydev); - else if (ops->get_sset_count) + else if (ops && ops->get_sset_count) count = ops->get_sset_count(dev, sset); netdev_unlock_ops(dev); if (count < 0) count = 0; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, cpu_dp->index, sset); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + dsa_conduit_append_port_sset_count(dp->ds, dp->index, sset, + &count); + } return count; } -static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) +static ssize_t dsa_conduit_append_port_strings(struct dsa_switch *ds, int port, + u32 stringset, u8 *data, + size_t start) { - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; int len = ETH_GSTRING_LEN; - int mcount = 0, count, i; - uint8_t pfx[4]; - uint8_t *ndata; + u8 pfx[8], *ndata; + int count, i; + + if (!ds->ops->get_strings) + return 0; - snprintf(pfx, sizeof(pfx), "p%.2d", port); + snprintf(pfx, sizeof(pfx), "s%.2d_p%.2d", ds->index, port); /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; + ndata = data + start * len; + /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle + * the output after to prepend our CPU port prefix we + * constructed earlier + */ + ds->ops->get_strings(ds, port, stringset, ndata); + count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return count; + + for (i = 0; i < count; i++) { + memmove(ndata + (i * len + sizeof(pfx)), + ndata + i * len, len - sizeof(pfx)); + memcpy(ndata + i * len, pfx, sizeof(pfx)); + } + + return count; +} + +static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, + u8 *data) +{ + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; netdev_lock_ops(dev); if (stringset == ETH_SS_PHY_STATS && dev->phydev && @@ -192,21 +255,17 @@ static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, } netdev_unlock_ops(dev); - if (ds->ops->get_strings) { - ndata = data + mcount * len; - /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle - * the output after to prepend our CPU port prefix we - * constructed earlier - */ - ds->ops->get_strings(ds, port, stringset, ndata); - count = ds->ops->get_sset_count(ds, port, stringset); + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_strings(dp->ds, dp->index, + stringset, data, + mcount); if (count < 0) return; - for (i = 0; i < count; i++) { - memmove(ndata + (i * len + sizeof(pfx)), - ndata + i * len, len - sizeof(pfx)); - memcpy(ndata + i * len, pfx, sizeof(pfx)); - } + + mcount += count; } } diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c index f41f9fc2194e..ed342f345692 100644 --- a/net/dsa/devlink.c +++ b/net/dsa/devlink.c @@ -182,7 +182,8 @@ static const struct devlink_ops dsa_devlink_ops = { }; int dsa_devlink_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dsa_devlink_to_ds(dl); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 43e211e611b1..13a63b48b7ee 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -154,9 +154,9 @@ EXPORT_SYMBOL(eth_get_headlen); */ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) { - unsigned short _service_access_point; const unsigned short *sap; const struct ethhdr *eth; + __be16 res; skb->dev = dev; skb_reset_mac_header(skb); @@ -181,15 +181,15 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) * the protocol design and runs IPX over 802.3 without an 802.2 LLC * layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This * won't work for fault tolerant netware but does for the rest. + * We use skb->dev as temporary storage to not hit + * CONFIG_STACKPROTECTOR_STRONG=y costs on some platforms. */ - sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point); - if (sap && *sap == 0xFFFF) - return htons(ETH_P_802_3); + sap = skb_header_pointer(skb, 0, sizeof(*sap), &skb->dev); + res = (sap && *sap == 0xFFFF) ? htons(ETH_P_802_3) : htons(ETH_P_802_2); - /* - * Real 802.2 LLC - */ - return htons(ETH_P_802_2); + /* restore skb->dev in case it was mangled by skb_header_pointer(). */ + skb->dev = dev; + return res; } EXPORT_SYMBOL(eth_type_trans); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 55223ebc2a7e..369c05cf8163 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -233,6 +233,10 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(800000, DR4_2, Full), __DEFINE_LINK_MODE_NAME(800000, SR4, Full), __DEFINE_LINK_MODE_NAME(800000, VR4, Full), + __DEFINE_LINK_MODE_NAME(1600000, CR8, Full), + __DEFINE_LINK_MODE_NAME(1600000, KR8, Full), + __DEFINE_LINK_MODE_NAME(1600000, DR8, Full), + __DEFINE_LINK_MODE_NAME(1600000, DR8_2, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -422,6 +426,10 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(800000, DR4_2, Full), __DEFINE_LINK_MODE_PARAMS(800000, SR4, Full), __DEFINE_LINK_MODE_PARAMS(800000, VR4, Full), + __DEFINE_LINK_MODE_PARAMS(1600000, CR8, Full), + __DEFINE_LINK_MODE_PARAMS(1600000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(1600000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(1600000, DR8_2, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); EXPORT_SYMBOL_GPL(link_mode_params); diff --git a/net/handshake/genl.c b/net/handshake/genl.c index f55d14d7b726..870612609491 100644 --- a/net/handshake/genl.c +++ b/net/handshake/genl.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/handshake.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/handshake/genl.h b/net/handshake/genl.h index ae72a596f6cc..8d3e18672daf 100644 --- a/net/handshake/genl.h +++ b/net/handshake/genl.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/handshake.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_HANDSHAKE_GEN_H #define _LINUX_HANDSHAKE_GEN_H diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a31b94ce8968..08d811f11896 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -756,23 +756,8 @@ EXPORT_SYMBOL(inet_stream_connect); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) { if (mem_cgroup_sockets_enabled) { - gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; - mem_cgroup_sk_alloc(newsk); - - if (mem_cgroup_from_sk(newsk)) { - int amt; - - /* The socket has not been accepted yet, no need - * to look at newsk->sk_wmem_queued. - */ - amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&newsk->sk_rmem_alloc)); - if (amt) - mem_cgroup_sk_charge(newsk, amt, gfp); - } - - kmem_cache_charge(newsk, gfp); + __sk_charge(newsk, GFP_KERNEL); } sock_rps_record_flow(newsk); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index e0d94270da28..05828d4cb6cd 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -122,8 +122,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6) - : htons(ETH_P_IP); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6) + : htons(ETH_P_IP); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 506260b4a4dc..7a99639204b1 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index 63a6c4ed803d..438342dc8507 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_FOU_GEN_H #define _LINUX_FOU_GEN_H diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index b4eae731c9ba..97d57c52b9ad 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -737,9 +737,9 @@ void inet_csk_init_xmit_timers(struct sock *sk, { struct inet_connection_sock *icsk = inet_csk(sk); - timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); + timer_setup(&sk->tcp_retransmit_timer, retransmit_handler, 0); timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); - timer_setup(&sk->sk_timer, keepalive_handler, 0); + timer_setup(&icsk->icsk_keepalive_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } @@ -750,9 +750,9 @@ void inet_csk_clear_xmit_timers(struct sock *sk) smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer(sk, &sk->tcp_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer(sk, &icsk->icsk_keepalive_timer); } void inet_csk_clear_xmit_timers_sync(struct sock *sk) @@ -765,9 +765,9 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk) smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); - sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &sk->tcp_retransmit_timer); sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); - sk_stop_timer_sync(sk, &sk->sk_timer); + sk_stop_timer_sync(sk, &icsk->icsk_keepalive_timer); } struct dst_entry *inet_csk_route_req(const struct sock *sk, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f0b6c5a411a2..3f5b1418a610 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -287,17 +287,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 1; r->idiag_retrans = READ_ONCE(icsk->icsk_retransmits); r->idiag_expires = - jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies); + jiffies_delta_to_msecs(tcp_timeout_expires(sk) - jiffies); } else if (icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out); r->idiag_expires = - jiffies_delta_to_msecs(icsk_timeout(icsk) - jiffies); - } else if (timer_pending(&sk->sk_timer)) { + jiffies_delta_to_msecs(tcp_timeout_expires(sk) - jiffies); + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { r->idiag_timer = 2; r->idiag_retrans = READ_ONCE(icsk->icsk_probes_out); r->idiag_expires = - jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); + jiffies_delta_to_msecs(icsk->icsk_keepalive_timer.expires - jiffies); } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 35367f8e2da3..a1a50a5c80dc 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1343,6 +1343,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, }, { + .procname = "tcp_rcvbuf_low_rtt", + .data = &init_net.ipv4.sysctl_tcp_rcvbuf_low_rtt, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { .procname = "tcp_tso_win_divisor", .data = &init_net.ipv4.sysctl_tcp_tso_win_divisor, .maxlen = sizeof(u8), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dee578aad690..f035440c475a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2587,7 +2587,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, if (err) goto out; - atomic_long_inc(&niov->pp_ref_count); + atomic_long_inc(&niov->desc.pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); sent += copy; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9df5d7515605..198f8a0d37be 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -896,6 +896,7 @@ void tcp_rcvbuf_grow(struct sock *sk, u32 newval) const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); u32 rcvwin, rcvbuf, cap, oldval; + u32 rtt_threshold, rtt_us; u64 grow; oldval = tp->rcvq_space.space; @@ -908,10 +909,19 @@ void tcp_rcvbuf_grow(struct sock *sk, u32 newval) /* DRS is always one RTT late. */ rcvwin = newval << 1; - /* slow start: allow the sender to double its rate. */ - grow = (u64)rcvwin * (newval - oldval); - do_div(grow, oldval); - rcvwin += grow << 1; + rtt_us = tp->rcv_rtt_est.rtt_us >> 3; + rtt_threshold = READ_ONCE(net->ipv4.sysctl_tcp_rcvbuf_low_rtt); + if (rtt_us < rtt_threshold) { + /* For small RTT, we set @grow to rcvwin * rtt_us/rtt_threshold. + * It might take few additional ms to reach 'line rate', + * but will avoid sk_rcvbuf inflation and poor cache use. + */ + grow = div_u64((u64)rcvwin * rtt_us, rtt_threshold); + } else { + /* slow start: allow the sender to double its rate. */ + grow = div_u64(((u64)rcvwin << 1) * (newval - oldval), oldval); + } + rcvwin += grow; if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7d9fec2950b..f8a9596e8f4d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2869,13 +2869,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk_timeout(icsk); + timer_expires = tcp_timeout_expires(sk); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk_timeout(icsk); - } else if (timer_pending(&sk->sk_timer)) { + timer_expires = tcp_timeout_expires(sk); + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sk->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = jiffies; @@ -3566,6 +3566,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; + net->ipv4.sysctl_tcp_rcvbuf_low_rtt = USEC_PER_MSEC; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -3593,7 +3594,7 @@ static int __net_init tcp_sk_init(struct net *net) sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; - net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; + net->ipv4.sysctl_tcp_comp_sack_slack_ns = 10 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_comp_sack_rtt_percent = 33; net->ipv4.sysctl_tcp_backlog_ack_defer = 1; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d8f4d813e8dd..bd5462154f97 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -337,7 +337,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); - tw->tw_transparent = inet_test_bit(TRANSPARENT, sk); tw->tw_mark = sk->sk_mark; tw->tw_priority = READ_ONCE(sk->sk_priority); tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 2cb93da93abc..fdda18b1abda 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -282,33 +282,6 @@ struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th) return NULL; } -struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) -{ - unsigned int thlen, hlen, off; - struct tcphdr *th; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*th); - th = skb_gro_header(skb, hlen, off); - if (unlikely(!th)) - return NULL; - - thlen = th->doff * 4; - if (thlen < sizeof(*th)) - return NULL; - - hlen = off + thlen; - if (!skb_gro_may_pull(skb, hlen)) { - th = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!th)) - return NULL; - } - - skb_gro_pull(skb, thlen); - - return th; -} - struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th) { diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0672c3d8f4f1..160080c9021d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -510,7 +510,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = icsk_timeout(icsk) - tp->rcv_tstamp; + rcv_delta = tcp_timeout_expires(sk) - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; @@ -697,9 +697,9 @@ void tcp_write_timer_handler(struct sock *sk) !icsk->icsk_pending) return; - if (time_after(icsk_timeout(icsk), jiffies)) { - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, - icsk_timeout(icsk)); + if (time_after(tcp_timeout_expires(sk), jiffies)) { + sk_reset_timer(sk, &sk->tcp_retransmit_timer, + tcp_timeout_expires(sk)); return; } tcp_mstamp_refresh(tcp_sk(sk)); @@ -725,12 +725,10 @@ void tcp_write_timer_handler(struct sock *sk) static void tcp_write_timer(struct timer_list *t) { - struct inet_connection_sock *icsk = - timer_container_of(icsk, t, icsk_retransmit_timer); - struct sock *sk = &icsk->icsk_inet.sk; + struct sock *sk = timer_container_of(sk, t, tcp_retransmit_timer); /* Avoid locking the socket when there is no pending event. */ - if (!smp_load_acquire(&icsk->icsk_pending)) + if (!smp_load_acquire(&inet_csk(sk)->icsk_pending)) goto out; bh_lock_sock(sk); @@ -755,12 +753,12 @@ void tcp_syn_ack_timeout(const struct request_sock *req) void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) { - sk_reset_timer(sk, &sk->sk_timer, jiffies + len); + sk_reset_timer(sk, &inet_csk(sk)->icsk_keepalive_timer, jiffies + len); } static void tcp_delete_keepalive_timer(struct sock *sk) { - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer(sk, &inet_csk(sk)->icsk_keepalive_timer); } void tcp_set_keepalive(struct sock *sk, int val) @@ -777,8 +775,9 @@ EXPORT_IPV6_MOD_GPL(tcp_set_keepalive); static void tcp_keepalive_timer(struct timer_list *t) { - struct sock *sk = timer_container_of(sk, t, sk_timer); - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + timer_container_of(icsk, t, icsk_keepalive_timer); + struct sock *sk = &icsk->icsk_inet.sk; struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 40e9c336f6c5..b66217d1b2f8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1324,7 +1324,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) __in6_ifa_put(ifp); } - if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); list_del_rcu(&ifp->if_list); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 7b41fb4f00b5..22410243ebe8 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -158,8 +158,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP) - : htons(ETH_P_IPV6); + const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x, + XFRM_MODE_SKB_CB(skb)->protocol); + __be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP) + : htons(ETH_P_IPV6); return skb_eth_gso_segment(skb, features, type); } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 02c16909f618..2111af022d94 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1138,6 +1138,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } + if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT))) { + iter->fib6_flags &= ~RTF_ADDRCONF; + iter->fib6_flags &= ~RTF_PREFIX_RT; + } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 08113f430124..280fe5978559 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2163,13 +2163,13 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk_timeout(icsk); + timer_expires = tcp_timeout_expires(sp); } else if (icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk_timeout(icsk); - } else if (timer_pending(&sp->sk_timer)) { + timer_expires = tcp_timeout_expires(sp); + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sp->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = jiffies; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a4f1df92417d..1e62fbc22cb7 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -10,8 +10,7 @@ * Ursula Braun <ursula.braun@de.ibm.com> */ -#define KMSG_COMPONENT "af_iucv" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "af_iucv: " fmt #include <linux/filter.h> #include <linux/module.h> diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 008be0abe3a5..da2af413c89d 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -20,8 +20,7 @@ * CP Programming Service, IBM document # SC24-5760 */ -#define KMSG_COMPONENT "iucv" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "iucv: " fmt #include <linux/kernel_stat.h> #include <linux/export.h> diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig index 16f39f2565d9..66660a06cacf 100644 --- a/net/kcm/Kconfig +++ b/net/kcm/Kconfig @@ -7,5 +7,5 @@ config AF_KCM select STREAM_PARSER help KCM (Kernel Connection Multiplexor) sockets provide a method - for multiplexing messages of a message based application - protocol over kernel connectons (e.g. TCP connections). + for multiplexing messages of a message-based application + protocol over kernel connections (e.g. TCP connections). diff --git a/net/key/af_key.c b/net/key/af_key.c index 2ebde0352245..571200433aa9 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3903,6 +3903,8 @@ static int __init ipsec_pfkey_init(void) { int err = proto_register(&key_proto, 0); + pr_warn_once("PFKEY is deprecated and scheduled to be removed in 2027, " + "please contact the netdev mailing list\n"); if (err != 0) goto out; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index c4f4a57cd67c..687c1366a4d0 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1246,9 +1246,9 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); - /* Reset skb netfilter state */ - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); + /* Reset control buffer */ + memset(skb->cb, 0, sizeof(skb->cb)); + nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by diff --git a/net/mctp/route.c b/net/mctp/route.c index 4d314e062ba9..2ac4011a953f 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -623,6 +623,7 @@ static int mctp_dst_output(struct mctp_dst *dst, struct sk_buff *skb) skb->protocol = htons(ETH_P_MCTP); skb->pkt_type = PACKET_OUTGOING; + skb->dev = dst->dev->dev; if (skb->len > dst->mtu) { kfree_skb(skb); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index b9e451197902..82ec15bcfd7f 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -32,7 +32,8 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf /* dequeue the skb from sk receive queue */ __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); - skb_orphan(skb); + + mptcp_subflow_lend_fwdmem(subflow, skb); /* We copy the fastopen data, but that don't belong to the mptcp sequence * space, need to offset it in the subflow sequence, see mptcp_subflow_get_map_offset() @@ -50,6 +51,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_lock(sk); DEBUG_NET_WARN_ON_ONCE(sock_owned_by_user_nocheck(sk)); + mptcp_borrow_fwdmem(sk, skb); skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); mptcp_sk(sk)->bytes_received += skb->len; diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 171643815076..f23fda0c55a7 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -71,7 +71,6 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPFastcloseRx", MPTCP_MIB_MPFASTCLOSERX), SNMP_MIB_ITEM("MPRstTx", MPTCP_MIB_MPRSTTX), SNMP_MIB_ITEM("MPRstRx", MPTCP_MIB_MPRSTRX), - SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), SNMP_MIB_ITEM("SndWndShared", MPTCP_MIB_SNDWNDSHARED), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index a1d3e9369fbb..812218b5ed2b 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -70,7 +70,6 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPFASTCLOSERX, /* Received a MP_FASTCLOSE */ MPTCP_MIB_MPRSTTX, /* Transmit a MP_RST */ MPTCP_MIB_MPRSTRX, /* Received a MP_RST */ - MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ MPTCP_MIB_SUBFLOWSTALE, /* Subflows entered 'stale' status */ MPTCP_MIB_SUBFLOWRECOVER, /* Subflows returned to active status after being stale */ MPTCP_MIB_SNDWNDSHARED, /* Subflow snd wnd is overridden by msk's one */ diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index ac974299de71..136c2d05c0ee 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -195,7 +195,8 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_info *info = _info; - r->idiag_rqueue = sk_rmem_alloc_get(sk); + r->idiag_rqueue = sk_rmem_alloc_get(sk) + + READ_ONCE(mptcp_sk(sk)->backlog_len); r->idiag_wqueue = sk_wmem_alloc_get(sk); if (inet_sk_state_load(sk) == TCP_LISTEN) { diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index dcffd847af33..c180930a8e0e 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h index e24258f6f819..b9280bcb43f5 100644 --- a/net/mptcp/mptcp_pm_gen.h +++ b/net/mptcp/mptcp_pm_gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/mptcp_pm.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_MPTCP_PM_GEN_H #define _LINUX_MPTCP_PM_GEN_H diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1103b3341a70..f24ae7d40e88 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -838,8 +838,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, opts->suboptions = 0; + /* Force later mptcp_write_options(), but do not use any actual + * option space. + */ if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb))) - return false; + return true; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) || @@ -1041,6 +1044,31 @@ static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) WRITE_ONCE(msk->snd_una, new_snd_una); } +static void rwin_update(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + u64 mptcp_rcv_wnd; + + /* Avoid touching extra cachelines if TCP is going to accept this + * skb without filling the TCP-level window even with a possibly + * outdated mptcp-level rwin. + */ + if (!skb->len || skb->len < tcp_receive_window(tp)) + return; + + mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent); + if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent)) + return; + + /* Some other subflow grew the mptcp-level rwin since rcv_wup, + * resync. + */ + tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent; + subflow->rcv_wnd_sent = mptcp_rcv_wnd; +} + static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) @@ -1208,6 +1236,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (mp_opt.use_ack) ack_update_msk(msk, sk, &mp_opt); + rwin_update(msk, sk, skb); /* Zero-data-length packets are dropped by the caller and not * propagated to the MPTCP layer, so the skb extension does not @@ -1294,6 +1323,10 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) if (rcv_wnd_new != rcv_wnd_old) { raise_win: + /* The msk-level rcv wnd is after the tcp level one, + * sync the latter. + */ + rcv_wnd_new = rcv_wnd_old; win = rcv_wnd_old - ack_seq; tp->rcv_wnd = min_t(u64, win, U32_MAX); new_win = tp->rcv_wnd; @@ -1317,6 +1350,21 @@ raise_win: update_wspace: WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); + subflow->rcv_wnd_sent = rcv_wnd_new; +} + +static void mptcp_track_rwin(struct tcp_sock *tp) +{ + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk; + + if (!ssk) + return; + + subflow = mptcp_subflow_ctx(ssk); + msk = mptcp_sk(subflow->conn); + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) @@ -1611,6 +1659,10 @@ mp_rst: opts->reset_transient, opts->reset_reason); return; + } else if (unlikely(!opts->suboptions)) { + /* Fallback to TCP */ + mptcp_track_rwin(tp); + return; } if (OPTION_MPTCP_PRIO & opts->suboptions) { diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 2ff1b9499568..e2040c327af6 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -18,6 +18,7 @@ struct mptcp_pm_add_entry { u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; + struct rcu_head rcu; }; static DEFINE_SPINLOCK(mptcp_pm_list_lock); @@ -155,7 +156,7 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); ret = entry; - kfree(entry); + kfree_rcu(entry, rcu); return ret; } @@ -345,22 +346,27 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; - struct timer_list *add_timer = NULL; + bool stop_timer = false; + + rcu_read_lock(); spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; - add_timer = &entry->add_timer; + stop_timer = true; } if (!check_id && entry) list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - /* no lock, because sk_stop_timer_sync() is calling timer_delete_sync() */ - if (add_timer) - sk_stop_timer_sync(sk, add_timer); + /* Note: entry might have been removed by another thread. + * We hold rcu_read_lock() to ensure it is not freed under us. + */ + if (stop_timer) + sk_stop_timer_sync(sk, &entry->add_timer); + rcu_read_unlock(); return entry; } @@ -415,7 +421,7 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk) list_for_each_entry_safe(entry, tmp, &free_list, list) { sk_stop_timer_sync(sk, &entry->add_timer); - kfree(entry); + kfree_rcu(entry, rcu); } } @@ -588,6 +594,7 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk) void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, const struct mptcp_subflow_context *subflow) { + struct sock *sk = (struct sock *)msk; struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; @@ -611,7 +618,8 @@ void mptcp_pm_subflow_check_next(struct mptcp_sock *msk, /* Even if this subflow is not really established, tell the PM to try * to pick the next ones, if possible. */ - if (mptcp_pm_nl_check_work_pending(msk)) + if (mptcp_is_fully_established(sk) && + mptcp_pm_nl_check_work_pending(msk)) mptcp_pm_schedule_work(msk, MPTCP_PM_SUBFLOW_ESTABLISHED); spin_unlock_bh(&pm->lock); diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 598f01a573c1..57570a44e418 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -337,6 +337,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) struct mptcp_pm_local local; mptcp_mpc_endpoint_setup(msk); + if (!mptcp_is_fully_established(sk)) + return; pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", msk->pm.local_addr_used, endp_subflow_max, @@ -680,7 +682,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id) { - if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + if (rm_id && !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4cd5df01446e..e212c1374bd0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -61,11 +61,13 @@ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { + unsigned short family = READ_ONCE(sk->sk_family); + #if IS_ENABLED(CONFIG_MPTCP_IPV6) - if (sk->sk_prot == &tcpv6_prot) + if (family == AF_INET6) return &inet6_stream_ops; #endif - WARN_ON_ONCE(sk->sk_prot != &tcp_prot); + WARN_ON_ONCE(family != AF_INET); return &inet_stream_ops; } @@ -76,6 +78,13 @@ bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) if (__mptcp_check_fallback(msk)) return true; + /* The caller possibly is not holding the msk socket lock, but + * in the fallback case only the current subflow is touching + * the OoO queue. + */ + if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) + return false; + spin_lock_bh(&msk->fallback_lock); if (!msk->allow_infinite_fallback) { spin_unlock_bh(&msk->fallback_lock); @@ -349,7 +358,7 @@ end: static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, int copy_len) { - const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* the skb map_seq accounts for the skb offset: @@ -374,11 +383,7 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb) struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *tail; - /* try to fetch required memory from subflow */ - if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); - goto drop; - } + mptcp_borrow_fwdmem(sk, skb); if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ @@ -400,16 +405,13 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb) * will retransmit as needed, if needed. */ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); -drop: mptcp_drop(sk, skb); return false; } static void mptcp_stop_rtx_timer(struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); - - sk_stop_timer(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer(sk, &sk->mptcp_retransmit_timer); mptcp_sk(sk)->timer_ival = 0; } @@ -515,7 +517,7 @@ static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subfl const struct sock *ssk = mptcp_subflow_tcp_sock(subflow); return inet_csk(ssk)->icsk_pending && !subflow->stale_count ? - icsk_timeout(inet_csk(ssk)) - jiffies : 0; + tcp_timeout_expires(ssk) - jiffies : 0; } static void mptcp_set_timeout(struct sock *sk) @@ -655,8 +657,50 @@ static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) } } +static void __mptcp_add_backlog(struct sock *sk, + struct mptcp_subflow_context *subflow, + struct sk_buff *skb) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct sk_buff *tail = NULL; + struct sock *ssk = skb->sk; + bool fragstolen; + int delta; + + if (unlikely(sk->sk_state == TCP_CLOSE)) { + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); + return; + } + + /* Try to coalesce with the last skb in our backlog */ + if (!list_empty(&msk->backlog_list)) + tail = list_last_entry(&msk->backlog_list, struct sk_buff, list); + + if (tail && MPTCP_SKB_CB(skb)->map_seq == MPTCP_SKB_CB(tail)->end_seq && + ssk == tail->sk && + __mptcp_try_coalesce(sk, tail, skb, &fragstolen, &delta)) { + skb->truesize -= delta; + kfree_skb_partial(skb, fragstolen); + __mptcp_subflow_lend_fwdmem(subflow, delta); + goto account; + } + + list_add_tail(&skb->list, &msk->backlog_list); + mptcp_subflow_lend_fwdmem(subflow, skb); + delta = skb->truesize; + +account: + WRITE_ONCE(msk->backlog_len, msk->backlog_len + delta); + + /* Possibly not accept()ed yet, keep track of memory not CG + * accounted, mptcp_graft_subflows() will handle it. + */ + if (!mem_cgroup_from_sk(ssk)) + msk->backlog_unaccounted += delta; +} + static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, - struct sock *ssk) + struct sock *ssk, bool own_msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; @@ -672,9 +716,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sk_buff *skb; bool fin; - if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) - break; - /* try to move as much data as available */ map_remaining = subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); @@ -701,8 +742,13 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, size_t len = skb->len - offset; mptcp_init_skb(ssk, skb, offset, len); - skb_orphan(skb); - ret = __mptcp_move_skb(sk, skb) || ret; + + if (own_msk && sk_rmem_alloc_get(sk) < sk->sk_rcvbuf) { + mptcp_subflow_lend_fwdmem(subflow, skb); + ret |= __mptcp_move_skb(sk, skb); + } else { + __mptcp_add_backlog(sk, subflow, skb); + } seq += len; if (unlikely(map_remaining < len)) { @@ -821,7 +867,7 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) struct sock *sk = (struct sock *)msk; bool moved; - moved = __mptcp_move_skbs_from_subflow(msk, ssk); + moved = __mptcp_move_skbs_from_subflow(msk, ssk, true); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) __mptcp_subflow_error_report(sk, ssk); @@ -836,31 +882,26 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) return moved; } -static void __mptcp_data_ready(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - /* Wake-up the reader only for in-sequence data */ - if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) - sk->sk_data_ready(sk); -} - void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_sock *msk = mptcp_sk(sk); /* The peer can send data while we are shutting down this - * subflow at msk destruction time, but we must avoid enqueuing + * subflow at subflow destruction time, but we must avoid enqueuing * more data to the msk receive queue */ - if (unlikely(subflow->disposable)) + if (unlikely(subflow->closing)) return; mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_data_ready(sk, ssk); - else - __set_bit(MPTCP_DEQUEUE, &mptcp_sk(sk)->cb_flags); + if (!sock_owned_by_user(sk)) { + /* Wake-up the reader only for in-sequence data */ + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); + } else { + __mptcp_move_skbs_from_subflow(msk, ssk, false); + } mptcp_data_unlock(sk); } @@ -886,12 +927,6 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_joined(msk, ssk); spin_unlock_bh(&msk->fallback_lock); - /* attach to msk socket only after we are sure we will deal with it - * at close time - */ - if (sk->sk_socket && !ssk->sk_socket) - mptcp_sock_graft(ssk, sk->sk_socket); - mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_stop_tout_timer(sk); @@ -917,12 +952,11 @@ static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list static bool mptcp_rtx_timer_pending(struct sock *sk) { - return timer_pending(&inet_csk(sk)->icsk_retransmit_timer); + return timer_pending(&sk->mptcp_retransmit_timer); } static void mptcp_reset_rtx_timer(struct sock *sk) { - struct inet_connection_sock *icsk = inet_csk(sk); unsigned long tout; /* prevent rescheduling on close */ @@ -930,19 +964,24 @@ static void mptcp_reset_rtx_timer(struct sock *sk) return; tout = mptcp_sk(sk)->timer_ival; - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout); + sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout); } bool mptcp_schedule_work(struct sock *sk) { - if (inet_sk_state_load(sk) != TCP_CLOSE && - schedule_work(&mptcp_sk(sk)->work)) { - /* each subflow already holds a reference to the sk, and the - * workqueue is invoked by a subflow, so sk can't go away here. - */ - sock_hold(sk); + if (inet_sk_state_load(sk) == TCP_CLOSE) + return false; + + /* Get a reference on this socket, mptcp_worker() will release it. + * As mptcp_worker() might complete before us, we can not avoid + * a sock_hold()/sock_put() if schedule_work() returns false. + */ + sock_hold(sk); + + if (schedule_work(&mptcp_sk(sk)->work)) return true; - } + + sock_put(sk); return false; } @@ -2100,60 +2139,80 @@ new_measure: msk->rcvq_space.time = mstamp; } -static struct mptcp_subflow_context * -__mptcp_first_ready_from(struct mptcp_sock *msk, - struct mptcp_subflow_context *subflow) +static bool __mptcp_move_skbs(struct sock *sk, struct list_head *skbs, u32 *delta) { - struct mptcp_subflow_context *start_subflow = subflow; + struct sk_buff *skb = list_first_entry(skbs, struct sk_buff, list); + struct mptcp_sock *msk = mptcp_sk(sk); + bool moved = false; + + *delta = 0; + while (1) { + /* If the msk recvbuf is full stop, don't drop */ + if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) + break; + + prefetch(skb->next); + list_del(&skb->list); + *delta += skb->truesize; - while (!READ_ONCE(subflow->data_avail)) { - subflow = mptcp_next_subflow(msk, subflow); - if (subflow == start_subflow) - return NULL; + moved |= __mptcp_move_skb(sk, skb); + if (list_empty(skbs)) + break; + + skb = list_first_entry(skbs, struct sk_buff, list); } - return subflow; + + __mptcp_ofo_queue(msk); + if (moved) + mptcp_check_data_fin((struct sock *)msk); + return moved; } -static bool __mptcp_move_skbs(struct sock *sk) +static bool mptcp_can_spool_backlog(struct sock *sk, struct list_head *skbs) { - struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - bool ret = false; - if (list_empty(&msk->conn_list)) + /* After CG initialization, subflows should never add skb before + * gaining the CG themself. + */ + DEBUG_NET_WARN_ON_ONCE(msk->backlog_unaccounted && sk->sk_socket && + mem_cgroup_from_sk(sk)); + + /* Don't spool the backlog if the rcvbuf is full. */ + if (list_empty(&msk->backlog_list) || + sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) return false; - subflow = list_first_entry(&msk->conn_list, - struct mptcp_subflow_context, node); - for (;;) { - struct sock *ssk; - bool slowpath; + INIT_LIST_HEAD(skbs); + list_splice_init(&msk->backlog_list, skbs); + return true; +} - /* - * As an optimization avoid traversing the subflows list - * and ev. acquiring the subflow socket lock before baling out - */ - if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) - break; +static void mptcp_backlog_spooled(struct sock *sk, u32 moved, + struct list_head *skbs) +{ + struct mptcp_sock *msk = mptcp_sk(sk); - subflow = __mptcp_first_ready_from(msk, subflow); - if (!subflow) - break; + WRITE_ONCE(msk->backlog_len, msk->backlog_len - moved); + list_splice(skbs, &msk->backlog_list); +} - ssk = mptcp_subflow_tcp_sock(subflow); - slowpath = lock_sock_fast(ssk); - ret = __mptcp_move_skbs_from_subflow(msk, ssk) || ret; - if (unlikely(ssk->sk_err)) - __mptcp_error_report(sk); - unlock_sock_fast(ssk, slowpath); +static bool mptcp_move_skbs(struct sock *sk) +{ + struct list_head skbs; + bool enqueued = false; + u32 moved; - subflow = mptcp_next_subflow(msk, subflow); - } + mptcp_data_lock(sk); + while (mptcp_can_spool_backlog(sk, &skbs)) { + mptcp_data_unlock(sk); + enqueued |= __mptcp_move_skbs(sk, &skbs, &moved); - __mptcp_ofo_queue(msk); - if (ret) - mptcp_check_data_fin((struct sock *)msk); - return ret; + mptcp_data_lock(sk); + mptcp_backlog_spooled(sk, moved, &skbs); + } + mptcp_data_unlock(sk); + return enqueued; } static unsigned int mptcp_inq_hint(const struct sock *sk) @@ -2219,7 +2278,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - if (skb_queue_empty(&sk->sk_receive_queue) && __mptcp_move_skbs(sk)) + if (!list_empty(&msk->backlog_list) && mptcp_move_skbs(sk)) continue; /* only the MPTCP socket status is relevant here. The exit @@ -2292,9 +2351,7 @@ out_err: static void mptcp_retransmit_timer(struct timer_list *t) { - struct inet_connection_sock *icsk = timer_container_of(icsk, t, - icsk_retransmit_timer); - struct sock *sk = &icsk->icsk_inet.sk; + struct sock *sk = timer_container_of(sk, t, mptcp_retransmit_timer); struct mptcp_sock *msk = mptcp_sk(sk); bh_lock_sock(sk); @@ -2312,7 +2369,9 @@ static void mptcp_retransmit_timer(struct timer_list *t) static void mptcp_tout_timer(struct timer_list *t) { - struct sock *sk = timer_container_of(sk, t, sk_timer); + struct inet_connection_sock *icsk = + timer_container_of(icsk, t, mptcp_tout_timer); + struct sock *sk = &icsk->icsk_inet.sk; mptcp_schedule_work(sk); sock_put(sk); @@ -2398,7 +2457,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) -#define MPTCP_CF_FASTCLOSE BIT(2) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches @@ -2409,7 +2467,7 @@ static void __mptcp_subflow_disconnect(struct sock *ssk, unsigned int flags) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || - (flags & MPTCP_CF_FASTCLOSE)) { + subflow->send_fastclose) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ @@ -2434,6 +2492,25 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, { struct mptcp_sock *msk = mptcp_sk(sk); bool dispose_it, need_push = false; + int fwd_remaining; + + /* Do not pass RX data to the msk, even if the subflow socket is not + * going to be freed (i.e. even for the first subflow on graceful + * subflow close. + */ + lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + subflow->closing = 1; + + /* Borrow the fwd allocated page left-over; fwd memory for the subflow + * could be negative at this point, but will be reach zero soon - when + * the data allocated using such fragment will be freed. + */ + if (subflow->lent_mem_frag) { + fwd_remaining = PAGE_SIZE - subflow->lent_mem_frag; + sk_forward_alloc_add(sk, fwd_remaining); + sk_forward_alloc_add(ssk, -fwd_remaining); + subflow->lent_mem_frag = 0; + } /* If the first subflow moved to a close state before accept, e.g. due * to an incoming reset or listener shutdown, the subflow socket is @@ -2445,7 +2522,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, /* ensure later check in mptcp_worker() will dispose the msk */ sock_set_flag(sk, SOCK_DEAD); mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); - lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; } @@ -2454,16 +2530,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (dispose_it) list_del(&subflow->node); - lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - - if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_close path - * to generate the egress reset - */ - ssk->sk_lingertime = 0; - sock_set_flag(ssk, SOCK_LINGER); - subflow->send_fastclose = 1; - } + if (subflow->send_fastclose && ssk->sk_state != TCP_CLOSE) + tcp_set_state(ssk, TCP_CLOSE); need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { @@ -2524,6 +2592,9 @@ out: void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + struct mptcp_sock *msk = mptcp_sk(sk); + struct sk_buff *skb; + /* The first subflow can already be closed and still in the list */ if (subflow->close_event_done) return; @@ -2533,6 +2604,17 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); + /* Remove any reference from the backlog to this ssk; backlog skbs consume + * space in the msk receive queue, no need to touch sk->sk_rmem_alloc + */ + list_for_each_entry(skb, &msk->backlog_list, list) { + if (skb->sk != ssk) + continue; + + atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc); + skb->sk = NULL; + } + /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ @@ -2559,7 +2641,8 @@ static void __mptcp_close_subflow(struct sock *sk) if (ssk_state != TCP_CLOSE && (ssk_state != TCP_CLOSE_WAIT || - inet_sk_state_load(sk) != TCP_ESTABLISHED)) + inet_sk_state_load(sk) != TCP_ESTABLISHED || + __mptcp_check_fallback(msk))) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2658,7 +2741,7 @@ static void __mptcp_retrans(struct sock *sk) } if (!mptcp_send_head(sk)) - return; + goto clear_scheduled; goto reset_timer; } @@ -2689,7 +2772,7 @@ static void __mptcp_retrans(struct sock *sk) if (__mptcp_check_fallback(msk)) { spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); - return; + goto clear_scheduled; } while (info.sent < info.limit) { @@ -2721,6 +2804,15 @@ reset_timer: if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); + +clear_scheduled: + /* If no rtx data was available or in case of fallback, there + * could be left-over scheduled subflows; clear them all + * or later xmit could use bad ones + */ + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->scheduled)) + mptcp_subflow_set_scheduled(subflow, false); } /* schedule the timeout timer for the relevant event: either close timeout @@ -2742,7 +2834,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) */ timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; - sk_reset_timer(sk, &sk->sk_timer, timeout); + sk_reset_timer(sk, &inet_csk(sk)->mptcp_tout_timer, timeout); } static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) @@ -2761,15 +2853,57 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) unlock_sock_fast(ssk, slow); } +static void mptcp_backlog_purge(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + struct sk_buff *tmp, *skb; + LIST_HEAD(backlog); + + mptcp_data_lock(sk); + list_splice_init(&msk->backlog_list, &backlog); + msk->backlog_len = 0; + mptcp_data_unlock(sk); + + list_for_each_entry_safe(skb, tmp, &backlog, list) { + mptcp_borrow_fwdmem(sk, skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); + } + sk_mem_reclaim(sk); +} + static void mptcp_do_fastclose(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); - mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), - subflow, MPTCP_CF_FASTCLOSE); + mptcp_backlog_purge(sk); + + /* Explicitly send the fastclose reset as need */ + if (__mptcp_check_fallback(msk)) + return; + + mptcp_for_each_subflow_safe(msk, subflow, tmp) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + + /* Some subflow socket states don't allow/need a reset.*/ + if ((1 << ssk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) + goto unlock; + + subflow->send_fastclose = 1; + + /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 + * issue in __tcp_select_window(), see tcp_disconnect(). + */ + inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; + + tcp_send_active_reset(ssk, ssk->sk_allocation, + SK_RST_REASON_TCP_ABORT_ON_CLOSE); +unlock: + release_sock(ssk); + } } static void mptcp_worker(struct work_struct *work) @@ -2796,7 +2930,11 @@ static void mptcp_worker(struct work_struct *work) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { + struct mptcp_subflow_context *subflow, *tmp; + mptcp_do_fastclose(sk); + mptcp_for_each_subflow_safe(msk, subflow, tmp) + __mptcp_close_ssk(sk, subflow->tcp_sock, subflow, 0); mptcp_close_wake_up(sk); } @@ -2824,11 +2962,13 @@ static void __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); + INIT_LIST_HEAD(&msk->backlog_list); INIT_WORK(&msk->work, mptcp_worker); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; + msk->backlog_len = 0; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -2845,8 +2985,8 @@ static void __mptcp_init_sock(struct sock *sk) spin_lock_init(&msk->fallback_lock); /* re-use the csk retrans timer for MPTCP-level retrans */ - timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0); - timer_setup(&sk->sk_timer, mptcp_tout_timer, 0); + timer_setup(&sk->mptcp_retransmit_timer, mptcp_retransmit_timer, 0); + timer_setup(&msk->sk.mptcp_tout_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) @@ -3048,7 +3188,7 @@ static void __mptcp_destroy_sock(struct sock *sk) might_sleep(); mptcp_stop_rtx_timer(sk); - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer(sk, &inet_csk(sk)->mptcp_tout_timer); msk->pm.status = 0; mptcp_release_sched(msk); @@ -3199,6 +3339,28 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; } +static void mptcp_destroy_common(struct mptcp_sock *msk) +{ + struct mptcp_subflow_context *subflow, *tmp; + struct sock *sk = (struct sock *)msk; + + __mptcp_clear_xmit(sk); + mptcp_backlog_purge(sk); + + /* join list will be eventually flushed (with rst) at sock lock release time */ + mptcp_for_each_subflow_safe(msk, subflow, tmp) + __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, 0); + + __skb_queue_purge(&sk->sk_receive_queue); + skb_rbtree_purge(&msk->out_of_order_queue); + + /* move all the rx fwd alloc into the sk_mem_reclaim_final in + * inet_sock_destruct() will dispose it + */ + mptcp_token_destroy(msk); + mptcp_pm_destroy(msk); +} + static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -3221,7 +3383,8 @@ static int mptcp_disconnect(struct sock *sk, int flags) /* msk->subflow is still intact, the following will not free the first * subflow */ - mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); + mptcp_do_fastclose(sk); + mptcp_destroy_common(msk); /* The first subflow is already in TCP_CLOSE status, the following * can't overlap with a fallback anymore @@ -3250,6 +3413,9 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->bytes_retrans = 0; msk->rcvspace_init = 0; + /* for fallback's sake */ + WRITE_ONCE(msk->ack_seq, 0); + WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; @@ -3400,34 +3566,13 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) -{ - struct mptcp_subflow_context *subflow, *tmp; - struct sock *sk = (struct sock *)msk; - - __mptcp_clear_xmit(sk); - - /* join list will be eventually flushed (with rst) at sock lock release time */ - mptcp_for_each_subflow_safe(msk, subflow, tmp) - __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); - - __skb_queue_purge(&sk->sk_receive_queue); - skb_rbtree_purge(&msk->out_of_order_queue); - - /* move all the rx fwd alloc into the sk_mem_reclaim_final in - * inet_sock_destruct() will dispose it - */ - mptcp_token_destroy(msk); - mptcp_pm_destroy(msk); -} - static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* allow the following to close even the initial subflow */ msk->free_first = 1; - mptcp_destroy_common(msk, 0); + mptcp_destroy_common(msk); sk_sockets_allocated_dec(sk); } @@ -3449,8 +3594,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ BIT(MPTCP_RETRANSMIT) | \ - BIT(MPTCP_FLUSH_JOIN_LIST) | \ - BIT(MPTCP_DEQUEUE)) + BIT(MPTCP_FLUSH_JOIN_LIST)) /* processes deferred events and flush wmem */ static void mptcp_release_cb(struct sock *sk) @@ -3460,9 +3604,12 @@ static void mptcp_release_cb(struct sock *sk) for (;;) { unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); - struct list_head join_list; + struct list_head join_list, skbs; + bool spool_bl; + u32 moved; - if (!flags) + spool_bl = mptcp_can_spool_backlog(sk, &skbs); + if (!flags && !spool_bl) break; INIT_LIST_HEAD(&join_list); @@ -3484,7 +3631,7 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); - if ((flags & BIT(MPTCP_DEQUEUE)) && __mptcp_move_skbs(sk)) { + if (spool_bl && __mptcp_move_skbs(sk, &skbs, &moved)) { /* notify ack seq update */ mptcp_cleanup_rbuf(msk, 0); sk->sk_data_ready(sk); @@ -3492,6 +3639,8 @@ static void mptcp_release_cb(struct sock *sk) cond_resched(); spin_lock_bh(&sk->sk_lock.slock); + if (spool_bl) + mptcp_backlog_spooled(sk, moved, &skbs); } if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) @@ -3617,6 +3766,23 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent) write_unlock_bh(&sk->sk_callback_lock); } +/* Can be called without holding the msk socket lock; use the callback lock + * to avoid {READ_,WRITE_}ONCE annotations on sk_socket. + */ +static void mptcp_sock_check_graft(struct sock *sk, struct sock *ssk) +{ + struct socket *sock; + + write_lock_bh(&sk->sk_callback_lock); + sock = sk->sk_socket; + write_unlock_bh(&sk->sk_callback_lock); + if (sock) { + mptcp_sock_graft(ssk, sock); + __mptcp_inherit_cgrp_data(sk, ssk); + __mptcp_inherit_memcg(sk, ssk, GFP_ATOMIC); + } +} + bool mptcp_finish_join(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -3632,7 +3798,9 @@ bool mptcp_finish_join(struct sock *ssk) return false; } - /* active subflow, already present inside the conn_list */ + /* Active subflow, already present inside the conn_list; is grafted + * either by __mptcp_subflow_connect() or accept. + */ if (!list_empty(&subflow->node)) { spin_lock_bh(&msk->fallback_lock); if (!msk->allow_subflows) { @@ -3659,11 +3827,17 @@ bool mptcp_finish_join(struct sock *ssk) if (ret) { sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); + mptcp_sock_check_graft(parent, ssk); } } else { sock_hold(ssk); list_add_tail(&subflow->node, &msk->join_list); __set_bit(MPTCP_FLUSH_JOIN_LIST, &msk->cb_flags); + + /* In case of later failures, __mptcp_flush_join_list() will + * properly orphan the ssk via mptcp_close_ssk(). + */ + mptcp_sock_check_graft(parent, ssk); } mptcp_data_unlock(parent); @@ -3724,7 +3898,7 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) return -EINVAL; lock_sock(sk); - if (__mptcp_move_skbs(sk)) + if (mptcp_move_skbs(sk)) mptcp_cleanup_rbuf(msk, 0); *karg = mptcp_inq_hint(sk); release_sock(sk); @@ -3924,6 +4098,69 @@ unlock: return err; } +static void mptcp_graft_subflows(struct sock *sk) +{ + struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); + + if (mem_cgroup_sockets_enabled) { + LIST_HEAD(join_list); + + /* Subflows joining after __inet_accept() will get the + * mem CG properly initialized at mptcp_finish_join() time, + * but subflows pending in join_list need explicit + * initialization before flushing `backlog_unaccounted` + * or MPTCP can later unexpectedly observe unaccounted memory. + */ + mptcp_data_lock(sk); + list_splice_init(&msk->join_list, &join_list); + mptcp_data_unlock(sk); + + __mptcp_flush_join_list(sk, &join_list); + } + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + lock_sock(ssk); + + /* Set ssk->sk_socket of accept()ed flows to mptcp socket. + * This is needed so NOSPACE flag can be set from tcp stack. + */ + if (!ssk->sk_socket) + mptcp_sock_graft(ssk, sk->sk_socket); + + if (!mem_cgroup_sk_enabled(sk)) + goto unlock; + + __mptcp_inherit_cgrp_data(sk, ssk); + __mptcp_inherit_memcg(sk, ssk, GFP_KERNEL); + +unlock: + release_sock(ssk); + } + + if (mem_cgroup_sk_enabled(sk)) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; + int amt; + + /* Account the backlog memory; prior accept() is aware of + * fwd and rmem only. + */ + mptcp_data_lock(sk); + amt = sk_mem_pages(sk->sk_forward_alloc + + msk->backlog_unaccounted + + atomic_read(&sk->sk_rmem_alloc)) - + sk_mem_pages(sk->sk_forward_alloc + + atomic_read(&sk->sk_rmem_alloc)); + msk->backlog_unaccounted = 0; + mptcp_data_unlock(sk); + + if (amt) + mem_cgroup_sk_charge(sk, amt, gfp); + } +} + static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { @@ -3971,26 +4208,17 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, msk = mptcp_sk(newsk); msk->in_accept_queue = 0; - /* set ssk->sk_socket of accept()ed flows to mptcp socket. - * This is needed so NOSPACE flag can be set from tcp stack. - */ - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - - if (!ssk->sk_socket) - mptcp_sock_graft(ssk, newsock); - } - + mptcp_graft_subflows(newsk); mptcp_rps_record_subflows(msk); /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */ if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { - __mptcp_close_ssk(newsk, msk->first, - mptcp_subflow_ctx(msk->first), 0); if (unlikely(list_is_singular(&msk->conn_list))) mptcp_set_state(newsk, TCP_CLOSE); + mptcp_close_ssk(newsk, msk->first, + mptcp_subflow_ctx(msk->first)); } } else { tcpfallback: diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9a3429175758..9c0d17876b22 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -124,7 +124,6 @@ #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_SYNC_STATE 6 #define MPTCP_SYNC_SNDBUF 7 -#define MPTCP_DEQUEUE 8 struct mptcp_skb_cb { u64 map_seq; @@ -357,6 +356,10 @@ struct mptcp_sock { * allow_infinite_fallback and * allow_join */ + + struct list_head backlog_list; /* protected by the data lock */ + u32 backlog_len; + u32 backlog_unaccounted; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) @@ -407,6 +410,7 @@ static inline int mptcp_space_from_win(const struct sock *sk, int win) static inline int __mptcp_space(const struct sock *sk) { return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - + READ_ONCE(mptcp_sk(sk)->backlog_len) - sk_rmem_alloc_get(sk)); } @@ -509,6 +513,7 @@ struct mptcp_subflow_context { u64 remote_key; u64 idsn; u64 map_seq; + u64 rcv_wnd_sent; u32 snd_isn; u32 token; u32 rel_write_seq; @@ -535,16 +540,18 @@ struct mptcp_subflow_context { send_infinite_map : 1, remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ + closing : 1, /* must not pass rx data to msk anymore */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ close_event_done : 1, /* has done the post-closed part */ mpc_drop : 1, /* the MPC option has been dropped in a rtx */ - __unused : 9; + __unused : 8; bool data_avail; bool scheduled; bool pm_listener; /* a listener managed by the kernel PM? */ bool fully_established; /* path validated */ + u32 lent_mem_frag; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -644,6 +651,42 @@ mptcp_send_active_reset_reason(struct sock *sk) tcp_send_active_reset(sk, GFP_ATOMIC, reason); } +/* Made the fwd mem carried by the given skb available to the msk, + * To be paired with a previous mptcp_subflow_lend_fwdmem() before freeing + * the skb or setting the skb ownership. + */ +static inline void mptcp_borrow_fwdmem(struct sock *sk, struct sk_buff *skb) +{ + struct sock *ssk = skb->sk; + + /* The subflow just lend the skb fwd memory; if the subflow meanwhile + * closed, mptcp_close_ssk() already released the ssk rcv memory. + */ + DEBUG_NET_WARN_ON_ONCE(skb->destructor); + sk_forward_alloc_add(sk, skb->truesize); + if (!ssk) + return; + + atomic_sub(skb->truesize, &ssk->sk_rmem_alloc); + skb->sk = NULL; +} + +static inline void +__mptcp_subflow_lend_fwdmem(struct mptcp_subflow_context *subflow, int size) +{ + int frag = (subflow->lent_mem_frag + size) & (PAGE_SIZE - 1); + + subflow->lent_mem_frag = frag; +} + +static inline void +mptcp_subflow_lend_fwdmem(struct mptcp_subflow_context *subflow, + struct sk_buff *skb) +{ + __mptcp_subflow_lend_fwdmem(subflow, skb->truesize); + skb->destructor = NULL; +} + static inline u64 mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow) { @@ -706,6 +749,9 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) return ret; } +void __mptcp_inherit_memcg(struct sock *sk, struct sock *ssk, gfp_t gfp); +void __mptcp_inherit_cgrp_data(struct sock *sk, struct sock *ssk); + int mptcp_is_enabled(const struct net *net); unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); @@ -846,7 +892,7 @@ static inline void mptcp_stop_tout_timer(struct sock *sk) if (!inet_csk(sk)->icsk_mtup.probe_timestamp) return; - sk_stop_timer(sk, &sk->sk_timer); + sk_stop_timer(sk, &inet_csk(sk)->mptcp_tout_timer); inet_csk(sk)->icsk_mtup.probe_timestamp = 0; } @@ -976,8 +1022,6 @@ static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) local_bh_enable(); } -void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags); - #define MPTCP_TOKEN_MAX_RETRIES 4 void __init mptcp_token_init(void); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 30961b3d1702..86ce58ae533d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -491,6 +491,9 @@ static void subflow_set_remote_key(struct mptcp_sock *msk, mptcp_crypto_key_sha(subflow->remote_key, NULL, &subflow->iasn); subflow->iasn++; + /* for fallback's sake */ + subflow->map_seq = subflow->iasn; + WRITE_ONCE(msk->remote_key, subflow->remote_key); WRITE_ONCE(msk->ack_seq, subflow->iasn); WRITE_ONCE(msk->can_ack, true); @@ -1285,6 +1288,7 @@ static bool subflow_is_done(const struct sock *sk) /* sched mptcp worker for subflow cleanup if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { + const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; if (likely(ssk->sk_state != TCP_CLOSE && @@ -1303,7 +1307,8 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss */ if (__mptcp_check_fallback(msk) && subflow_is_done(ssk) && msk->first == ssk && - mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) + mptcp_update_rcv_data_fin(msk, subflow->map_seq + + subflow->map_data_len, true)) mptcp_schedule_work(sk); } @@ -1433,9 +1438,12 @@ reset: skb = skb_peek(&ssk->sk_receive_queue); subflow->map_valid = 1; - subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; + subflow->map_seq = __mptcp_expand_seq(subflow->map_seq, + subflow->iasn + + TCP_SKB_CB(skb)->seq - + subflow->ssn_offset - 1); WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1712,21 +1720,35 @@ err_out: return err; } -static void mptcp_attach_cgroup(struct sock *parent, struct sock *child) +void __mptcp_inherit_memcg(struct sock *sk, struct sock *ssk, gfp_t gfp) +{ + /* Only if the msk has been accepted already (and not orphaned).*/ + if (!mem_cgroup_sockets_enabled || !sk->sk_socket) + return; + + mem_cgroup_sk_inherit(sk, ssk); + __sk_charge(ssk, gfp); +} + +void __mptcp_inherit_cgrp_data(struct sock *sk, struct sock *ssk) { #ifdef CONFIG_SOCK_CGROUP_DATA - struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data, - *child_skcd = &child->sk_cgrp_data; + struct sock_cgroup_data *sk_cd = &sk->sk_cgrp_data, + *ssk_cd = &ssk->sk_cgrp_data; /* only the additional subflows created by kworkers have to be modified */ - if (cgroup_id(sock_cgroup_ptr(parent_skcd)) != - cgroup_id(sock_cgroup_ptr(child_skcd))) { - cgroup_sk_free(child_skcd); - *child_skcd = *parent_skcd; - cgroup_sk_clone(child_skcd); + if (cgroup_id(sock_cgroup_ptr(sk_cd)) != + cgroup_id(sock_cgroup_ptr(ssk_cd))) { + cgroup_sk_free(ssk_cd); + *ssk_cd = *sk_cd; + cgroup_sk_clone(sk_cd); } #endif /* CONFIG_SOCK_CGROUP_DATA */ +} +static void mptcp_attach_cgroup(struct sock *parent, struct sock *child) +{ + __mptcp_inherit_cgrp_data(parent, child); if (mem_cgroup_sockets_enabled) mem_cgroup_sk_inherit(parent, child); } @@ -2144,6 +2166,10 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; tcp_prot_override.diag_destroy = tcp_abort_override; +#ifdef CONFIG_BPF_SYSCALL + /* Disable sockmap processing for subflows */ + tcp_prot_override.psock_update_sk_prot = NULL; +#endif #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -2180,6 +2206,10 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; tcpv6_prot_override.diag_destroy = tcp_abort_override; +#ifdef CONFIG_BPF_SYSCALL + /* Disable sockmap processing for subflows */ + tcpv6_prot_override.psock_update_sk_prot = NULL; +#endif #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index fdacbc3c15be..d54d7da58334 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -13,8 +13,7 @@ * Author: Juan Jose Ciarlante, <jjciarla@raiz.uncu.edu.ar> */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 37ebb0cb62b8..50cc492c7553 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -17,8 +17,7 @@ * Changes: */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/interrupt.h> #include <linux/in.h> diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 5ea7ab8bf4dc..90d56f92c0f6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -19,8 +19,7 @@ * Harald Welte don't use nfcache */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 4c8fa22be88a..068702894377 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -13,8 +13,7 @@ * Changes: */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/init.h> diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 75f4c231f4a0..bb7aca4601ff 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -30,8 +30,7 @@ * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 93a925f1ed9b..77f4f637ff67 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -12,8 +12,7 @@ * get_stats()) do the per cpu summing. */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/kernel.h> #include <linux/jiffies.h> diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c index ab117e5bc34e..d657b47c6511 100644 --- a/net/netfilter/ipvs/ip_vs_fo.c +++ b/net/netfilter/ipvs/ip_vs_fo.c @@ -8,8 +8,7 @@ * Kenny Mathis : added initial functionality based on weight */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 206c6700e200..b315c608fda4 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -16,8 +16,7 @@ * Author: Wouter Gadeyne */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/moduleparam.h> diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 156181a3bacd..e6c8ed0c92f6 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -34,8 +34,7 @@ * me to write this module. */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index a021e6aba3d7..a25cf7bb6185 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -32,8 +32,7 @@ * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/module.h> diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c index c2764505e380..38cc38c5d8bb 100644 --- a/net/netfilter/ipvs/ip_vs_lc.c +++ b/net/netfilter/ipvs/ip_vs_lc.c @@ -9,8 +9,7 @@ * Wensong Zhang : added any dest with weight=0 is quiesced */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c index e3d7f5c879ce..f61f54004c9e 100644 --- a/net/netfilter/ipvs/ip_vs_mh.c +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -17,8 +17,7 @@ https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 08adcb222986..81974f69e5bb 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -30,8 +30,7 @@ * PASV response can not be NAT-ed) but Active FTP should work */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/types.h> diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c index ed7f5c889b41..ada158c610ce 100644 --- a/net/netfilter/ipvs/ip_vs_nq.c +++ b/net/netfilter/ipvs/ip_vs_nq.c @@ -26,8 +26,7 @@ * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_ovf.c b/net/netfilter/ipvs/ip_vs_ovf.c index c7708b809700..c5c67df80a0b 100644 --- a/net/netfilter/ipvs/ip_vs_ovf.c +++ b/net/netfilter/ipvs/ip_vs_ovf.c @@ -12,8 +12,7 @@ * active connections */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 166c669f0763..3035079ebd99 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/spinlock.h> diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index e4ce1d9a63f9..85f31d71e29a 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index a9fd1d3fc2cb..fd9dbca24c85 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -8,8 +8,7 @@ * Changes: */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 89602c16f6b6..44e14acc187e 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -6,8 +6,7 @@ * Wensong Zhang <wensong@linuxvirtualserver.org> */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/in.h> #include <linux/ip.h> diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 7da51390cea6..f68a1533ee45 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -13,8 +13,7 @@ * protocol ip_vs_proto_data and is handled by netns */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/kernel.h> #include <linux/ip.h> diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 68260d91c988..0f0107c80dd2 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -9,8 +9,7 @@ * Network name space (netns) aware. */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/in.h> #include <linux/ip.h> diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c index 6baa34dff9f0..4125ee561cdc 100644 --- a/net/netfilter/ipvs/ip_vs_rr.c +++ b/net/netfilter/ipvs/ip_vs_rr.c @@ -14,8 +14,7 @@ * Wensong Zhang : added any dest with weight=0 is quiesced */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index d4903723be7e..c6e421c4e299 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -12,8 +12,7 @@ * Changes: */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/spinlock.h> diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c index a46f99a56618..245a323c84cd 100644 --- a/net/netfilter/ipvs/ip_vs_sed.c +++ b/net/netfilter/ipvs/ip_vs_sed.c @@ -30,8 +30,7 @@ * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 92e77d7a6b50..0e85e07e23b9 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -32,8 +32,7 @@ * */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/ip.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 5a0c6f42bd8f..54dd1514ac45 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -32,8 +32,7 @@ * Persistence support, fwmark and time-out. */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/slab.h> diff --git a/net/netfilter/ipvs/ip_vs_twos.c b/net/netfilter/ipvs/ip_vs_twos.c index 8d5419edde50..dbb7f5fd4688 100644 --- a/net/netfilter/ipvs/ip_vs_twos.c +++ b/net/netfilter/ipvs/ip_vs_twos.c @@ -4,8 +4,7 @@ * Authors: Darby Payne <darby.payne@applovin.com> */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/kernel.h> #include <linux/module.h> diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c index 9fa500927c0a..9da445ca09a1 100644 --- a/net/netfilter/ipvs/ip_vs_wlc.c +++ b/net/netfilter/ipvs/ip_vs_wlc.c @@ -14,8 +14,7 @@ * Wensong Zhang : added any dest with weight=0 is quiesced */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c index 85ce0d04afac..99f09cbf2d9b 100644 --- a/net/netfilter/ipvs/ip_vs_wrr.c +++ b/net/netfilter/ipvs/ip_vs_wrr.c @@ -13,8 +13,7 @@ * with weight 0 when all weights are zero */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 95af252b2939..3162ce3c2640 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -21,8 +21,7 @@ * - the only place where we can see skb->sk != NULL */ -#define KMSG_COMPONENT "IPVS" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "IPVS: " fmt #include <linux/kernel.h> #include <linux/slab.h> diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2832e0794197..792ca44a461d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -572,69 +572,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, - const struct nlattr *a) -{ - struct nshhdr *nh; - size_t length; - int err; - u8 flags; - u8 ttl; - int i; - - struct ovs_key_nsh key; - struct ovs_key_nsh mask; - - err = nsh_key_from_nlattr(a, &key, &mask); - if (err) - return err; - - /* Make sure the NSH base header is there */ - if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) - return -ENOMEM; - - nh = nsh_hdr(skb); - length = nsh_hdr_len(nh); - - /* Make sure the whole NSH header is there */ - err = skb_ensure_writable(skb, skb_network_offset(skb) + - length); - if (unlikely(err)) - return err; - - nh = nsh_hdr(skb); - skb_postpull_rcsum(skb, nh, length); - flags = nsh_get_flags(nh); - flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); - flow_key->nsh.base.flags = flags; - ttl = nsh_get_ttl(nh); - ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); - flow_key->nsh.base.ttl = ttl; - nsh_set_flags_and_ttl(nh, flags, ttl); - nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, - mask.base.path_hdr); - flow_key->nsh.base.path_hdr = nh->path_hdr; - switch (nh->mdtype) { - case NSH_M_TYPE1: - for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { - nh->md1.context[i] = - OVS_MASKED(nh->md1.context[i], key.context[i], - mask.context[i]); - } - memcpy(flow_key->nsh.context, nh->md1.context, - sizeof(nh->md1.context)); - break; - case NSH_M_TYPE2: - memset(flow_key->nsh.context, 0, - sizeof(flow_key->nsh.context)); - break; - default: - return -EINVAL; - } - skb_postpush_rcsum(skb, nh, length); - return 0; -} - /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1130,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; - case OVS_KEY_ATTR_NSH: - err = set_nsh(skb, flow_key, a); - break; - case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1170,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: + case OVS_KEY_ATTR_NSH: err = -EINVAL; break; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ad64bb9ab5e2..1cb4f97335d8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1305,6 +1305,11 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +/* + * Constructs NSH header 'nh' from attributes of OVS_ACTION_ATTR_PUSH_NSH, + * where 'nh' points to a memory block of 'size' bytes. It's assumed that + * attributes were previously validated with validate_push_nsh(). + */ int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size) { @@ -1314,8 +1319,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, u8 ttl = 0; int mdlen = 0; - /* validate_nsh has check this, so we needn't do duplicate check here - */ if (size < NSH_BASE_HDR_LEN) return -ENOBUFS; @@ -1359,46 +1362,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, return 0; } -int nsh_key_from_nlattr(const struct nlattr *attr, - struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) -{ - struct nlattr *a; - int rem; - - /* validate_nsh has check this, so we needn't do duplicate check here - */ - nla_for_each_nested(a, attr, rem) { - int type = nla_type(a); - - switch (type) { - case OVS_NSH_KEY_ATTR_BASE: { - const struct ovs_nsh_key_base *base = nla_data(a); - const struct ovs_nsh_key_base *base_mask = base + 1; - - nsh->base = *base; - nsh_mask->base = *base_mask; - break; - } - case OVS_NSH_KEY_ATTR_MD1: { - const struct ovs_nsh_key_md1 *md1 = nla_data(a); - const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; - - memcpy(nsh->context, md1->context, sizeof(*md1)); - memcpy(nsh_mask->context, md1_mask->context, - sizeof(*md1_mask)); - break; - } - case OVS_NSH_KEY_ATTR_MD2: - /* Not supported yet */ - return -ENOTSUPP; - default: - return -EINVAL; - } - } - - return 0; -} - static int nsh_key_put_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool is_push_nsh, bool log) @@ -2839,17 +2802,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_nsh(const struct nlattr *attr, bool is_mask, - bool is_push_nsh, bool log) +static bool validate_push_nsh(const struct nlattr *attr, bool log) { struct sw_flow_match match; struct sw_flow_key key; - int ret = 0; ovs_match_init(&match, &key, true, NULL); - ret = nsh_key_put_from_nlattr(attr, &match, is_mask, - is_push_nsh, log); - return !ret; + return !nsh_key_put_from_nlattr(attr, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -2997,13 +2956,6 @@ static int validate_set(const struct nlattr *a, break; - case OVS_KEY_ATTR_NSH: - if (eth_type != htons(ETH_P_NSH)) - return -EINVAL; - if (!validate_nsh(nla_data(a), masked, false, log)) - return -EINVAL; - break; - default: return -EINVAL; } @@ -3437,7 +3389,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_nsh(nla_data(a), false, true, true)) + if (!validate_push_nsh(nla_data(a), log)) return -EINVAL; break; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index fe7f77fc5f18..ff8cdecbe346 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -65,8 +65,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); -int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, - struct ovs_key_nsh *nsh_mask); int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size); diff --git a/net/psp/psp-nl-gen.c b/net/psp/psp-nl-gen.c index 73f8b06d66f0..22a48d0fa378 100644 --- a/net/psp/psp-nl-gen.c +++ b/net/psp/psp-nl-gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/psp.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/psp/psp-nl-gen.h b/net/psp/psp-nl-gen.h index 5bc3b5d5a53e..599c5f1c82f2 100644 --- a/net/psp/psp-nl-gen.h +++ b/net/psp/psp-nl-gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/psp.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_PSP_GEN_H #define _LINUX_PSP_GEN_H diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 396b576390d0..c2b5bc19e091 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -47,12 +47,10 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(filter, skb); + filter_res = bpf_prog_run_data_pointers(filter, skb); } if (unlikely(!skb->tstamp && skb->tstamp_type)) skb->tstamp_type = SKB_CLOCK_REALTIME; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 6749a4a9a9cd..2b6ac7069dc1 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -948,9 +948,9 @@ static int tcf_ct_act_nat(struct sk_buff *skb, return err & NF_VERDICT_MASK; if (action & BIT(NF_NAT_MANIP_SRC)) - tc_skb_cb(skb)->post_ct_snat = 1; + qdisc_skb_cb(skb)->post_ct_snat = 1; if (action & BIT(NF_NAT_MANIP_DST)) - tc_skb_cb(skb)->post_ct_dnat = 1; + qdisc_skb_cb(skb)->post_ct_dnat = 1; return err; #else @@ -986,7 +986,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, tcf_action_update_bstats(&c->common, skb); if (clear) { - tc_skb_cb(skb)->post_ct = false; + qdisc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { nf_ct_put(ct); @@ -1097,7 +1097,7 @@ do_nat: out_push: skb_push_rcsum(skb, nh_ofs); - tc_skb_cb(skb)->post_ct = true; + qdisc_skb_cb(skb)->post_ct = true; tc_skb_cb(skb)->zone = p->zone; out_clear: if (defrag) diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 7c6975632fc2..1dfdda6c2d4c 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -649,9 +649,9 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, memset(&opt, 0, sizeof(opt)); - opt.index = ife->tcf_index, - opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref, - opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, + opt.index = ife->tcf_index; + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind; spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index f751cd5eeac8..ebca4b926dcf 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1872,9 +1872,9 @@ int tcf_classify(struct sk_buff *skb, } 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->post_ct = qdisc_skb_cb(skb)->post_ct; + ext->post_ct_snat = qdisc_skb_cb(skb)->post_ct_snat; + ext->post_ct_dnat = qdisc_skb_cb(skb)->post_ct_dnat; ext->zone = cb->zone; } } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 7fbe42f0e5c2..a32754a2658b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -97,12 +97,10 @@ TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb, } else if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); __skb_pull(skb, skb->mac_len); } else { - bpf_compute_data_pointers(skb); - filter_res = bpf_prog_run(prog->filter, skb); + filter_res = bpf_prog_run_data_pointers(prog->filter, skb); } if (unlikely(!skb->tstamp && skb->tstamp_type)) skb->tstamp_type = SKB_CLOCK_REALTIME; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 099ff6a3e1f5..7669371c1354 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -326,7 +326,7 @@ TC_INDIRECT_SCOPE int fl_classify(struct sk_buff *skb, struct tcf_result *res) { struct cls_fl_head *head = rcu_dereference_bh(tp->root); - bool post_ct = tc_skb_cb(skb)->post_ct; + bool post_ct = qdisc_skb_cb(skb)->post_ct; u16 zone = tc_skb_cb(skb)->zone; struct fl_flow_key skb_key; struct fl_flow_mask *mask; diff --git a/net/sched/em_canid.c b/net/sched/em_canid.c index 5337bc462755..2d27f91d8441 100644 --- a/net/sched/em_canid.c +++ b/net/sched/em_canid.c @@ -99,6 +99,9 @@ static int em_canid_match(struct sk_buff *skb, struct tcf_ematch *m, int i; const struct can_filter *lp; + if (!pskb_may_pull(skb, CAN_MTU)) + return 0; + can_id = em_canid_get_id(skb); if (can_id & CAN_EFF_FLAG) { diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index 64b637f18bc7..48c1bce74f49 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -22,9 +22,12 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { struct tcf_em_cmp *cmp = (struct tcf_em_cmp *) em->data; - unsigned char *ptr = tcf_get_base_ptr(skb, cmp->layer) + cmp->off; + unsigned char *ptr = tcf_get_base_ptr(skb, cmp->layer); u32 val = 0; + if (!ptr) + return 0; + ptr += cmp->off; if (!tcf_valid_offset(skb, ptr, cmp->align)) return 0; diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 4f9f21a05d5e..c65ffa5fff94 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -42,6 +42,8 @@ static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em, struct nbyte_data *nbyte = (struct nbyte_data *) em->data; unsigned char *ptr = tcf_get_base_ptr(skb, nbyte->hdr.layer); + if (!ptr) + return 0; ptr += nbyte->hdr.off; if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len)) diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 6b3d0af72c39..692e2be1793e 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -29,12 +29,19 @@ static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m, struct tcf_pkt_info *info) { struct text_match *tm = EM_TEXT_PRIV(m); + unsigned char *ptr; int from, to; - from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data; + ptr = tcf_get_base_ptr(skb, tm->from_layer); + if (!ptr) + return 0; + from = ptr - skb->data; from += tm->from_offset; - to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data; + ptr = tcf_get_base_ptr(skb, tm->to_layer); + if (!ptr) + return 0; + to = ptr - skb->data; to += tm->to_offset; return skb_find_text(skb, from, to, tm->config) != UINT_MAX; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 32bacfc314c2..0ea9440f68c6 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1398,15 +1398,15 @@ static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int hdr_len, last_len = 0; u32 off = skb_network_offset(skb); + u16 segs = qdisc_pkt_segs(skb); u32 len = qdisc_pkt_len(skb); - u16 segs = 1; q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); - if (!shinfo->gso_size) + if (segs == 1) return cake_calc_overhead(q, len, off); - /* borrowed from qdisc_pkt_len_init() */ + /* borrowed from qdisc_pkt_len_segs_init() */ if (!skb->encapsulation) hdr_len = skb_transport_offset(skb); else @@ -1430,12 +1430,6 @@ static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) hdr_len += sizeof(struct udphdr); } - if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) - segs = DIV_ROUND_UP(skb->len - hdr_len, - shinfo->gso_size); - else - segs = shinfo->gso_segs; - len = shinfo->gso_size + hdr_len; last_len = skb->len - shinfo->gso_size * (segs - 1); @@ -1788,7 +1782,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(len > b->max_skblen)) b->max_skblen = len; - if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { + if (qdisc_pkt_segs(skb) > 1 && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); unsigned int slen = 0, numsegs = 0; @@ -1800,6 +1794,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; + qdisc_skb_cb(segs)->pkt_segs = 1; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, segs); @@ -2188,7 +2183,7 @@ retry: b->tin_dropped++; qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); - kfree_skb_reason(skb, reason); + qdisc_dequeue_drop(sch, skb, reason); if (q->rate_flags & CAKE_FLAG_INGRESS) goto retry; } @@ -2729,6 +2724,8 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, int i, j, err; sch->limit = 10240; + sch->flags |= TCQ_F_DEQUEUE_DROPS; + q->tin_mode = CAKE_DIFFSERV_DIFFSERV3; q->flow_mode = CAKE_FLOW_TRIPLE; diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index fa0314679e43..c6551578f1cf 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -52,7 +52,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_CONGESTED); + qdisc_dequeue_drop(sch, skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } @@ -182,6 +182,8 @@ static int codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; + sch->flags |= TCQ_F_DEQUEUE_DROPS; + return 0; } diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 4b975feb52b1..6d7e6389758d 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -475,6 +475,7 @@ static int dualpi2_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, * (3) Enqueue fragment & set ts in dualpi2_enqueue_skb */ qdisc_skb_cb(nskb)->pkt_len = nskb->len; + qdisc_skb_cb(nskb)->pkt_segs = 1; dualpi2_skb_cb(nskb)->classified = dualpi2_skb_cb(skb)->classified; dualpi2_skb_cb(nskb)->ect = dualpi2_skb_cb(skb)->ect; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index fee922da2f99..6e5f2f4f2415 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -480,7 +480,10 @@ static void fq_erase_head(struct Qdisc *sch, struct fq_flow *flow, struct sk_buff *skb) { if (skb == flow->head) { - flow->head = skb->next; + struct sk_buff *next = skb->next; + + prefetch(next); + flow->head = next; } else { rb_erase(&skb->rbnode, &flow->t_root); skb->dev = qdisc_dev(sch); @@ -497,6 +500,7 @@ static void fq_dequeue_skb(struct Qdisc *sch, struct fq_flow *flow, skb_mark_not_on_list(skb); qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; + qdisc_bstats_update(sch, skb); } static void flow_queue_add(struct fq_flow *flow, struct sk_buff *skb) @@ -711,6 +715,7 @@ begin: goto begin; } prefetch(&skb->end); + fq_dequeue_skb(sch, f, skb); if ((s64)(now - time_next_packet - q->ce_threshold) > 0) { INET_ECN_set_ce(skb); q->stat_ce_mark++; @@ -718,7 +723,6 @@ begin: if (--f->qlen == 0) q->inactive_flows++; q->band_pkt_count[fq_skb_cb(skb)->band]--; - fq_dequeue_skb(sch, f, skb); } else { head->first = f->next; /* force a pass through old_flows to prevent starvation */ @@ -776,7 +780,6 @@ begin: f->time_next_packet = now + len; } out: - qdisc_bstats_update(sch, skb); return skb; } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index a14142392939..dc187c7f06b1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -275,7 +275,7 @@ static void drop_func(struct sk_buff *skb, void *ctx) { struct Qdisc *sch = ctx; - kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_CONGESTED); + qdisc_dequeue_drop(sch, skb, SKB_DROP_REASON_QDISC_CONGESTED); qdisc_qstats_drop(sch); } @@ -519,6 +519,9 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; + + sch->flags |= TCQ_F_DEQUEUE_DROPS; + return 0; alloc_failure: diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index eafc316ae319..32a5f3304046 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -429,6 +429,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff *segs; netdev_features_t features = netif_skb_features(skb); + qdisc_skb_cb(skb)->pkt_segs = 1; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 2255355e51d3..d920f57dc6d7 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1250,7 +1250,7 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } } - gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; + gso_segs = qdisc_pkt_segs(skb); err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 39b735386996..300d577b3286 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -595,6 +595,7 @@ static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; + qdisc_skb_cb(segs)->pkt_segs = 1; slen += segs->len; /* FIXME: we should be segmenting to a smaller size diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 4c977f049670..f2340164f579 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -221,6 +221,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, skb_mark_not_on_list(segs); seg_len = segs->len; qdisc_skb_cb(segs)->pkt_len = seg_len; + qdisc_skb_cb(segs)->pkt_segs = 1; ret = qdisc_enqueue(segs, q->qdisc, to_free); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) diff --git a/net/shaper/shaper_nl_gen.c b/net/shaper/shaper_nl_gen.c index 204c8ae8c7b1..e8cccc4c1180 100644 --- a/net/shaper/shaper_nl_gen.c +++ b/net/shaper/shaper_nl_gen.c @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/net_shaper.yaml */ /* YNL-GEN kernel source */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #include <net/netlink.h> #include <net/genetlink.h> diff --git a/net/shaper/shaper_nl_gen.h b/net/shaper/shaper_nl_gen.h index cb7f9026fc23..ec41c90431a4 100644 --- a/net/shaper/shaper_nl_gen.h +++ b/net/shaper/shaper_nl_gen.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/net_shaper.yaml */ /* YNL-GEN kernel header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _LINUX_NET_SHAPER_GEN_H #define _LINUX_NET_SHAPER_GEN_H diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e388de8dca09..f97f77b041d9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -16,8 +16,7 @@ * based on prototype from Frank Blaschka */ -#define KMSG_COMPONENT "smc" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "smc: " fmt #include <linux/module.h> #include <linux/socket.h> diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3b44cadaed96..c627efc3698d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -733,8 +733,7 @@ static void unix_release_sock(struct sock *sk, int embrion) /* ---- Socket is dead now and most probably destroyed ---- */ - if (READ_ONCE(unix_tot_inflight)) - unix_gc(); /* Garbage collect fds */ + unix_schedule_gc(NULL); } struct unix_peercred { @@ -2099,8 +2098,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) return err; - wait_for_unix_gc(scm.fp); - if (msg->msg_flags & MSG_OOB) { err = -EOPNOTSUPP; goto out; @@ -2394,8 +2391,6 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) return err; - wait_for_unix_gc(scm.fp); - if (msg->msg_flags & MSG_OOB) { err = -EOPNOTSUPP; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) @@ -2943,6 +2938,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, u = unix_sk(sk); +redo: /* Lock the socket to prevent queue disordering * while sleeps in memcpy_tomsg */ @@ -2954,7 +2950,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, struct sk_buff *skb, *last; int chunk; -redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -3004,7 +2999,6 @@ again: goto out; } - mutex_lock(&u->iolock); goto redo; unlock: unix_state_unlock(sk); diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h index 59db179df9bb..c4f1b2da363d 100644 --- a/net/unix/af_unix.h +++ b/net/unix/af_unix.h @@ -24,14 +24,12 @@ struct unix_skb_parms { #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) /* GC for SCM_RIGHTS */ -extern unsigned int unix_tot_inflight; void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver); void unix_del_edges(struct scm_fp_list *fpl); void unix_update_edges(struct unix_sock *receiver); int unix_prepare_fpl(struct scm_fp_list *fpl); void unix_destroy_fpl(struct scm_fp_list *fpl); -void unix_gc(void); -void wait_for_unix_gc(struct scm_fp_list *fpl); +void unix_schedule_gc(struct user_struct *user); /* SOCK_DIAG */ long unix_inq_len(struct sock *sk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 65396a4e1b07..78323d43e63e 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -121,8 +121,13 @@ static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) return edge->successor->vertex; } -static bool unix_graph_maybe_cyclic; -static bool unix_graph_grouped; +enum { + UNIX_GRAPH_NOT_CYCLIC, + UNIX_GRAPH_MAYBE_CYCLIC, + UNIX_GRAPH_CYCLIC, +}; + +static unsigned char unix_graph_state; static void unix_update_graph(struct unix_vertex *vertex) { @@ -132,8 +137,7 @@ static void unix_update_graph(struct unix_vertex *vertex) if (!vertex) return; - unix_graph_maybe_cyclic = true; - unix_graph_grouped = false; + WRITE_ONCE(unix_graph_state, UNIX_GRAPH_MAYBE_CYCLIC); } static LIST_HEAD(unix_unvisited_vertices); @@ -196,7 +200,6 @@ static void unix_free_vertices(struct scm_fp_list *fpl) } static DEFINE_SPINLOCK(unix_gc_lock); -unsigned int unix_tot_inflight; void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { @@ -222,7 +225,6 @@ void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) } while (i < fpl->count_unix); receiver->scm_stat.nr_unix_fds += fpl->count_unix; - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); @@ -253,7 +255,6 @@ void unix_del_edges(struct scm_fp_list *fpl) receiver = fpl->edges[0].successor; receiver->scm_stat.nr_unix_fds -= fpl->count_unix; } - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); @@ -299,6 +300,8 @@ int unix_prepare_fpl(struct scm_fp_list *fpl) if (!fpl->edges) goto err; + unix_schedule_gc(fpl->user); + return 0; err: @@ -404,9 +407,11 @@ static bool unix_scc_cyclic(struct list_head *scc) static LIST_HEAD(unix_visited_vertices); static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; -static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, - struct sk_buff_head *hitlist) +static unsigned long __unix_walk_scc(struct unix_vertex *vertex, + unsigned long *last_index, + struct sk_buff_head *hitlist) { + unsigned long cyclic_sccs = 0; LIST_HEAD(vertex_stack); struct unix_edge *edge; LIST_HEAD(edge_stack); @@ -497,8 +502,8 @@ prev_vertex: if (unix_vertex_max_scc_index < vertex->scc_index) unix_vertex_max_scc_index = vertex->scc_index; - if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + if (unix_scc_cyclic(&scc)) + cyclic_sccs++; } list_del(&scc); @@ -507,13 +512,17 @@ prev_vertex: /* Need backtracking ? */ if (!list_empty(&edge_stack)) goto prev_vertex; + + return cyclic_sccs; } +static unsigned long unix_graph_cyclic_sccs; + static void unix_walk_scc(struct sk_buff_head *hitlist) { unsigned long last_index = UNIX_VERTEX_INDEX_START; + unsigned long cyclic_sccs = 0; - unix_graph_maybe_cyclic = false; unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; /* Visit every vertex exactly once. @@ -523,18 +532,20 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) struct unix_vertex *vertex; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); - __unix_walk_scc(vertex, &last_index, hitlist); + cyclic_sccs += __unix_walk_scc(vertex, &last_index, hitlist); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); - unix_graph_grouped = true; + WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs); + WRITE_ONCE(unix_graph_state, + cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC); } static void unix_walk_scc_fast(struct sk_buff_head *hitlist) { - unix_graph_maybe_cyclic = false; + unsigned long cyclic_sccs = unix_graph_cyclic_sccs; while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; @@ -551,34 +562,38 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) scc_dead = unix_vertex_dead(vertex); } - if (scc_dead) + if (scc_dead) { + cyclic_sccs--; unix_collect_skb(&scc, hitlist); - else if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } list_del(&scc); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + + WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs); + WRITE_ONCE(unix_graph_state, + cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC); } static bool gc_in_progress; -static void __unix_gc(struct work_struct *work) +static void unix_gc(struct work_struct *work) { struct sk_buff_head hitlist; struct sk_buff *skb; spin_lock(&unix_gc_lock); - if (!unix_graph_maybe_cyclic) { + if (unix_graph_state == UNIX_GRAPH_NOT_CYCLIC) { spin_unlock(&unix_gc_lock); goto skip_gc; } __skb_queue_head_init(&hitlist); - if (unix_graph_grouped) + if (unix_graph_state == UNIX_GRAPH_CYCLIC) unix_walk_scc_fast(&hitlist); else unix_walk_scc(&hitlist); @@ -595,36 +610,27 @@ skip_gc: WRITE_ONCE(gc_in_progress, false); } -static DECLARE_WORK(unix_gc_work, __unix_gc); +static DECLARE_WORK(unix_gc_work, unix_gc); -void unix_gc(void) -{ - WRITE_ONCE(gc_in_progress, true); - queue_work(system_dfl_wq, &unix_gc_work); -} +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) -#define UNIX_INFLIGHT_TRIGGER_GC 16000 -#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) - -void wait_for_unix_gc(struct scm_fp_list *fpl) +void unix_schedule_gc(struct user_struct *user) { - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight(), and __unix_gc(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); + if (READ_ONCE(unix_graph_state) == UNIX_GRAPH_NOT_CYCLIC) + return; /* Penalise users who want to send AF_UNIX sockets * but whose sockets have not been received yet. */ - if (!fpl || !fpl->count_unix || - READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + if (user && + READ_ONCE(user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) return; - if (READ_ONCE(gc_in_progress)) + if (!READ_ONCE(gc_in_progress)) { + WRITE_ONCE(gc_in_progress, true); + queue_work(system_dfl_wq, &unix_gc_work); + } + + if (user && READ_ONCE(unix_graph_cyclic_sccs)) flush_work(&unix_gc_work); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 72bb6b7ed386..adcba1b7bf74 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1661,18 +1661,40 @@ static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr, timeout = schedule_timeout(timeout); lock_sock(sk); - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; - sock->state = SS_UNCONNECTED; - vsock_transport_cancel_pkt(vsk); - vsock_remove_connected(vsk); - goto out_wait; - } else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) { - err = -ETIMEDOUT; + /* Connection established. Whatever happens to socket once we + * release it, that's not connect()'s concern. No need to go + * into signal and timeout handling. Call it a day. + * + * Note that allowing to "reset" an already established socket + * here is racy and insecure. + */ + if (sk->sk_state == TCP_ESTABLISHED) + break; + + /* If connection was _not_ established and a signal/timeout came + * to be, we want the socket's state reset. User space may want + * to retry. + * + * sk_state != TCP_ESTABLISHED implies that socket is not on + * vsock_connected_table. We keep the binding and the transport + * assigned. + */ + if (signal_pending(current) || timeout == 0) { + err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout); + + /* Listener might have already responded with + * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our + * sk_state == TCP_SYN_SENT, which hereby we break. + * In such case VIRTIO_VSOCK_OP_RST will follow. + */ sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; + + /* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by + * transport->connect(). + */ vsock_transport_cancel_pkt(vsk); + goto out_wait; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index bcfd400e9cf8..f093c3453f64 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,20 +36,13 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET 32 -struct xsk_addr_node { - u64 addr; - struct list_head addr_node; -}; - -struct xsk_addr_head { +struct xsk_addrs { u32 num_descs; - struct list_head addrs_list; + u64 addrs[MAX_SKB_FRAGS + 1]; }; static struct kmem_cache *xsk_tx_generic_cache; -#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb)) - void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -557,29 +550,68 @@ static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) return ret; } +static bool xsk_skb_destructor_is_addr(struct sk_buff *skb) +{ + return (uintptr_t)skb_shinfo(skb)->destructor_arg & 0x1UL; +} + +static u64 xsk_skb_destructor_get_addr(struct sk_buff *skb) +{ + return (u64)((uintptr_t)skb_shinfo(skb)->destructor_arg & ~0x1UL); +} + +static void xsk_skb_destructor_set_addr(struct sk_buff *skb, u64 addr) +{ + skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t)addr | 0x1UL); +} + +static void xsk_inc_num_desc(struct sk_buff *skb) +{ + struct xsk_addrs *xsk_addr; + + if (!xsk_skb_destructor_is_addr(skb)) { + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + xsk_addr->num_descs++; + } +} + +static u32 xsk_get_num_desc(struct sk_buff *skb) +{ + struct xsk_addrs *xsk_addr; + + if (xsk_skb_destructor_is_addr(skb)) + return 1; + + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + + return xsk_addr->num_descs; +} + static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, struct sk_buff *skb) { - struct xsk_addr_node *pos, *tmp; + u32 num_descs = xsk_get_num_desc(skb); + struct xsk_addrs *xsk_addr; u32 descs_processed = 0; unsigned long flags; - u32 idx; + u32 idx, i; spin_lock_irqsave(&pool->cq_prod_lock, flags); idx = xskq_get_prod(pool->cq); - xskq_prod_write_addr(pool->cq, idx, - (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg); - descs_processed++; + if (unlikely(num_descs > 1)) { + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; - if (unlikely(XSKCB(skb)->num_descs > 1)) { - list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + for (i = 0; i < num_descs; i++) { xskq_prod_write_addr(pool->cq, idx + descs_processed, - pos->addr); + xsk_addr->addrs[i]); descs_processed++; - list_del(&pos->addr_node); - kmem_cache_free(xsk_tx_generic_cache, pos); } + kmem_cache_free(xsk_tx_generic_cache, xsk_addr); + } else { + xskq_prod_write_addr(pool->cq, idx, + xsk_skb_destructor_get_addr(skb)); + descs_processed++; } xskq_prod_submit_n(pool->cq, descs_processed); spin_unlock_irqrestore(&pool->cq_prod_lock, flags); @@ -592,16 +624,6 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) spin_unlock(&pool->cq_cached_prod_lock); } -static void xsk_inc_num_desc(struct sk_buff *skb) -{ - XSKCB(skb)->num_descs++; -} - -static u32 xsk_get_num_desc(struct sk_buff *skb) -{ - return XSKCB(skb)->num_descs; -} - INDIRECT_CALLABLE_SCOPE void xsk_destruct_skb(struct sk_buff *skb) { @@ -619,27 +641,22 @@ void xsk_destruct_skb(struct sk_buff *skb) static void xsk_skb_init_misc(struct sk_buff *skb, struct xdp_sock *xs, u64 addr) { - BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb)); - INIT_LIST_HEAD(&XSKCB(skb)->addrs_list); skb->dev = xs->dev; skb->priority = READ_ONCE(xs->sk.sk_priority); skb->mark = READ_ONCE(xs->sk.sk_mark); - XSKCB(skb)->num_descs = 0; skb->destructor = xsk_destruct_skb; - skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr; + xsk_skb_destructor_set_addr(skb, addr); } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); u32 num_descs = xsk_get_num_desc(skb); - struct xsk_addr_node *pos, *tmp; + struct xsk_addrs *xsk_addr; if (unlikely(num_descs > 1)) { - list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { - list_del(&pos->addr_node); - kmem_cache_free(xsk_tx_generic_cache, pos); - } + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + kmem_cache_free(xsk_tx_generic_cache, xsk_addr); } skb->destructor = sock_wfree; @@ -699,7 +716,6 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; - struct xsk_addr_node *xsk_addr; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; @@ -725,16 +741,26 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, return ERR_PTR(err); } } else { - xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); - if (!xsk_addr) - return ERR_PTR(-ENOMEM); + struct xsk_addrs *xsk_addr; + + if (xsk_skb_destructor_is_addr(skb)) { + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, + GFP_KERNEL); + if (!xsk_addr) + return ERR_PTR(-ENOMEM); + + xsk_addr->num_descs = 1; + xsk_addr->addrs[0] = xsk_skb_destructor_get_addr(skb); + skb_shinfo(skb)->destructor_arg = (void *)xsk_addr; + } else { + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + } /* in case of -EOVERFLOW that could happen below, * xsk_consume_skb() will release this node as whole skb * would be dropped, which implies freeing all list elements */ - xsk_addr->addr = desc->addr; - list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); + xsk_addr->addrs[xsk_addr->num_descs] = desc->addr; } len = desc->len; @@ -811,10 +837,25 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, } } else { int nr_frags = skb_shinfo(skb)->nr_frags; - struct xsk_addr_node *xsk_addr; + struct xsk_addrs *xsk_addr; struct page *page; u8 *vaddr; + if (xsk_skb_destructor_is_addr(skb)) { + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, + GFP_KERNEL); + if (!xsk_addr) { + err = -ENOMEM; + goto free_err; + } + + xsk_addr->num_descs = 1; + xsk_addr->addrs[0] = xsk_skb_destructor_get_addr(skb); + skb_shinfo(skb)->destructor_arg = (void *)xsk_addr; + } else { + xsk_addr = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg; + } + if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { err = -EOVERFLOW; goto free_err; @@ -826,13 +867,6 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, goto free_err; } - xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); - if (!xsk_addr) { - __free_page(page); - err = -ENOMEM; - goto free_err; - } - vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); @@ -840,8 +874,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); - xsk_addr->addr = desc->addr; - list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); + xsk_addr->addrs[xsk_addr->num_descs] = desc->addr; } } @@ -1902,7 +1935,7 @@ static int __init xsk_init(void) goto out_pernet; xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache", - sizeof(struct xsk_addr_node), + sizeof(struct xsk_addrs), 0, SLAB_HWCACHE_ALIGN, NULL); if (!xsk_tx_generic_cache) { err = -ENOMEM; diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index f0157702718f..4a62817a88f8 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -110,14 +110,17 @@ config XFRM_IPCOMP select CRYPTO_DEFLATE config NET_KEY - tristate "PF_KEY sockets" + tristate "PF_KEY sockets (deprecated)" select XFRM_ALGO help PF_KEYv2 socket family, compatible to KAME ones. - They are required if you are going to use IPsec tools ported - from KAME. - Say Y unless you know what you are doing. + The PF_KEYv2 socket interface is deprecated and + scheduled for removal. All maintained IKE daemons + no longer need PF_KEY sockets. Please use the netlink + interface (XFRM_USER) to configure IPsec. + + If unsure, say N. config NET_KEY_MIGRATE bool "PF_KEY MIGRATE" diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 44b9de6e4e77..52ae0e034d29 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -438,7 +438,7 @@ ok: check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; - switch (x->inner_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: /* Check for IPv4 options */ if (ip_hdr(skb)->ihl != 5) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c9ddef869aa5..4ed346e682c7 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -505,6 +505,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) async = 1; dev_put(skb->dev); seq = XFRM_SKB_CB(skb)->seq.input.low; + spin_lock(&x->lock); goto resume; } /* GRO call */ @@ -541,9 +542,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } + + nexthdr = x->type_offload->input_tail(x, skb); } - goto lock; + goto process; } family = XFRM_SPI_SKB_CB(skb)->family; @@ -611,7 +614,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) goto drop; } -lock: +process: + seq_hi = htonl(xfrm_replay_seqhi(x, seq)); + + XFRM_SKB_CB(skb)->seq.input.low = seq; + XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; + spin_lock(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { @@ -638,21 +646,13 @@ lock: goto drop_unlock; } - spin_unlock(&x->lock); - if (xfrm_tunnel_check(skb, x, family)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); - goto drop; + goto drop_unlock; } - seq_hi = htonl(xfrm_replay_seqhi(x, seq)); - - XFRM_SKB_CB(skb)->seq.input.low = seq; - XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - - if (crypto_done) { - nexthdr = x->type_offload->input_tail(x, skb); - } else { + if (!crypto_done) { + spin_unlock(&x->lock); dev_hold(skb->dev); nexthdr = x->type->input(x, skb); @@ -660,9 +660,9 @@ lock: return 0; dev_put(skb->dev); + spin_lock(&x->lock); } resume: - spin_lock(&x->lock); if (nexthdr < 0) { if (nexthdr == -EBADMSG) { xfrm_audit_state_icvfail(x, skb, @@ -676,7 +676,7 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (xfrm_replay_recheck(x, skb, seq)) { + if (!crypto_done && xfrm_replay_recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9077730ff7d0..54222fcbd7fd 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -698,7 +698,7 @@ static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x) return; if (x->outer_mode.encap == XFRM_MODE_TUNNEL) { - switch (x->outer_mode.family) { + switch (skb_dst(skb)->ops->family) { case AF_INET: xo->inner_ipproto = ip_hdr(skb)->protocol; break; @@ -772,8 +772,12 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) /* Exclusive direct xmit for tunnel mode, as * some filtering or matching rules may apply * in transport mode. + * Locally generated packets also require + * the normal XFRM path for L2 header setup, + * as the hardware needs the L2 header to match + * for encryption, so skip direct output as well. */ - if (x->props.mode == XFRM_MODE_TUNNEL) + if (x->props.mode == XFRM_MODE_TUNNEL && !skb->sk) return xfrm_dev_direct_output(sk, x, skb); return xfrm_output_resume(sk, skb, 0); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d213ca3653a8..9e14e453b55c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -592,6 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) @@ -607,6 +608,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x->replay_esn); kfree(x->preplay_esn); xfrm_unset_type_offload(x); + xfrm_state_delete_tunnel(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -806,7 +808,6 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -2073,6 +2074,7 @@ static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, return x; error: + x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); out: return NULL; @@ -2157,11 +2159,15 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) - goto error; + goto error_add; } return xc; +error_add: + if (xuo) + xfrm_dev_state_delete(xc); error: + xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return NULL; } @@ -2191,14 +2197,18 @@ int xfrm_state_update(struct xfrm_state *x) } if (x1->km.state == XFRM_STATE_ACQ) { - if (x->dir && x1->dir != x->dir) + if (x->dir && x1->dir != x->dir) { + to_put = x1; goto out; + } __xfrm_state_insert(x); x = NULL; } else { - if (x1->dir != x->dir) + if (x1->dir != x->dir) { + to_put = x1; goto out; + } } err = 0; @@ -3298,6 +3308,7 @@ out_bydst: void xfrm_state_fini(struct net *net) { unsigned int sz; + int i; flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, 0, false); @@ -3305,14 +3316,17 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); + for (i = 0; i <= net->xfrm.state_hmask; i++) { + WARN_ON(!hlist_empty(net->xfrm.state_byseq + i)); + WARN_ON(!hlist_empty(net->xfrm.state_byspi + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i)); + WARN_ON(!hlist_empty(net->xfrm.state_bydst + i)); + } + sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); - WARN_ON(!hlist_empty(net->xfrm.state_byseq)); xfrm_hash_free(net->xfrm.state_byseq, sz); - WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); xfrm_hash_free(net->xfrm.state_bysrc, sz); - WARN_ON(!hlist_empty(net->xfrm.state_bydst)); xfrm_hash_free(net->xfrm.state_bydst, sz); free_percpu(net->xfrm.state_cache_input); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 010c9e6638c0..403b5ecac2c5 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -947,8 +947,11 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_PCPU]) { x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]); - if (x->pcpu_num >= num_possible_cpus()) + if (x->pcpu_num >= num_possible_cpus()) { + err = -ERANGE; + NL_SET_ERR_MSG(extack, "pCPU number too big"); goto error; + } } err = __xfrm_init_state(x, extack); @@ -3035,6 +3038,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } xfrm_state_free(x); + xfrm_dev_policy_delete(xp); + xfrm_dev_policy_free(xp); + security_xfrm_policy_free(xp->security); kfree(xp); return 0; diff --git a/samples/vfs/test-statx.c b/samples/vfs/test-statx.c index 49c7a46cee07..424a6fa15723 100644 --- a/samples/vfs/test-statx.c +++ b/samples/vfs/test-statx.c @@ -19,6 +19,12 @@ #include <time.h> #include <sys/syscall.h> #include <sys/types.h> + +// Work around glibc header silliness +#undef AT_RENAME_NOREPLACE +#undef AT_RENAME_EXCHANGE +#undef AT_RENAME_WHITEOUT + #include <linux/stat.h> #include <linux/fcntl.h> #define statx foo diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c index 8c6cb57d5cfc..24cf7d7a1972 100644 --- a/samples/watch_queue/watch_test.c +++ b/samples/watch_queue/watch_test.c @@ -16,6 +16,12 @@ #include <errno.h> #include <sys/ioctl.h> #include <limits.h> + +// Work around glibc header silliness +#undef AT_RENAME_NOREPLACE +#undef AT_RENAME_EXCHANGE +#undef AT_RENAME_WHITEOUT + #include <linux/watch_queue.h> #include <linux/unistd.h> #include <linux/keyctl.h> diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c index 08ae61eb327e..f5203d1640ee 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.c +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -138,7 +138,8 @@ int main(int argc, char **argv) error("no input files?"); } - symbol_read_exports(stdin); + if (!symbol_read_exports(stdin)) + return 0; if (symtypes_file) { symfile = fopen(symtypes_file, "w"); diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h index d9c06d2cb1df..32cec8f7695a 100644 --- a/scripts/gendwarfksyms/gendwarfksyms.h +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -123,7 +123,7 @@ struct symbol { typedef void (*symbol_callback_t)(struct symbol *, void *arg); bool is_symbol_ptr(const char *name); -void symbol_read_exports(FILE *file); +int symbol_read_exports(FILE *file); void symbol_read_symtab(int fd); struct symbol *symbol_get(const char *name); void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr); diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c index 35ed594f0749..ecddcb5ffcdf 100644 --- a/scripts/gendwarfksyms/symbols.c +++ b/scripts/gendwarfksyms/symbols.c @@ -128,7 +128,7 @@ static bool is_exported(const char *name) return for_each(name, NULL, NULL) > 0; } -void symbol_read_exports(FILE *file) +int symbol_read_exports(FILE *file) { struct symbol *sym; char *line = NULL; @@ -159,6 +159,8 @@ void symbol_read_exports(FILE *file) free(line); debug("%d exported symbols", nsym); + + return nsym; } static void get_symbol(struct symbol *sym, void *arg) diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 0bade2c5aa1d..d9c12b993fa7 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -1335,11 +1335,10 @@ static void hook_sb_delete(struct super_block *const sb) * At this point, we own the ihold() reference that was * originally set up by get_inode_object() and the * __iget() reference that we just set in this loop - * walk. Therefore the following call to iput() will - * not sleep nor drop the inode because there is now at - * least two references to it. + * walk. Therefore there are at least two references + * on the inode. */ - iput(inode); + iput_not_last(inode); } else { spin_unlock(&object->lock); rcu_read_unlock(); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index dfc22da42f30..e713291db873 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -210,12 +210,12 @@ static int selinux_lsm_notifier_avc_callback(u32 event) */ static void cred_init_security(void) { - struct task_security_struct *tsec; + struct cred_security_struct *crsec; /* NOTE: the lsm framework zeros out the buffer on allocation */ - tsec = selinux_cred(unrcu_pointer(current->real_cred)); - tsec->osid = tsec->sid = tsec->avdcache.sid = SECINITSID_KERNEL; + crsec = selinux_cred(unrcu_pointer(current->real_cred)); + crsec->osid = crsec->sid = SECINITSID_KERNEL; } /* @@ -223,10 +223,10 @@ static void cred_init_security(void) */ static inline u32 cred_sid(const struct cred *cred) { - const struct task_security_struct *tsec; + const struct cred_security_struct *crsec; - tsec = selinux_cred(cred); - return tsec->sid; + crsec = selinux_cred(cred); + return crsec->sid; } static void __ad_net_init(struct common_audit_data *ad, @@ -437,15 +437,15 @@ static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { - const struct task_security_struct *tsec = selinux_cred(cred); + const struct cred_security_struct *crsec = selinux_cred(cred); int rc; - rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, + rc = avc_has_perm(crsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; - rc = avc_has_perm(tsec->sid, sid, SECCLASS_FILESYSTEM, + rc = avc_has_perm(crsec->sid, sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELTO, NULL); return rc; } @@ -454,9 +454,9 @@ static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, const struct cred *cred) { - const struct task_security_struct *tsec = selinux_cred(cred); + const struct cred_security_struct *crsec = selinux_cred(cred); int rc; - rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, + rc = avc_has_perm(crsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); if (rc) return rc; @@ -1788,7 +1788,7 @@ out: * Determine the label for an inode that might be unioned. */ static int -selinux_determine_inode_label(const struct task_security_struct *tsec, +selinux_determine_inode_label(const struct cred_security_struct *crsec, struct inode *dir, const struct qstr *name, u16 tclass, u32 *_new_isid) @@ -1800,11 +1800,11 @@ selinux_determine_inode_label(const struct task_security_struct *tsec, (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) { *_new_isid = sbsec->mntpoint_sid; } else if ((sbsec->flags & SBLABEL_MNT) && - tsec->create_sid) { - *_new_isid = tsec->create_sid; + crsec->create_sid) { + *_new_isid = crsec->create_sid; } else { const struct inode_security_struct *dsec = inode_security(dir); - return security_transition_sid(tsec->sid, + return security_transition_sid(crsec->sid, dsec->sid, tclass, name, _new_isid); } @@ -1817,7 +1817,7 @@ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; u32 sid, newsid; @@ -1827,7 +1827,7 @@ static int may_create(struct inode *dir, dsec = inode_security(dir); sbsec = selinux_superblock(dir->i_sb); - sid = tsec->sid; + sid = crsec->sid; ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; @@ -1838,7 +1838,7 @@ static int may_create(struct inode *dir, if (rc) return rc; - rc = selinux_determine_inode_label(tsec, dir, &dentry->d_name, tclass, + rc = selinux_determine_inode_label(crsec, dir, &dentry->d_name, tclass, &newsid); if (rc) return rc; @@ -2251,8 +2251,8 @@ static u32 ptrace_parent_sid(void) } static int check_nnp_nosuid(const struct linux_binprm *bprm, - const struct task_security_struct *old_tsec, - const struct task_security_struct *new_tsec) + const struct cred_security_struct *old_crsec, + const struct cred_security_struct *new_crsec) { int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS); int nosuid = !mnt_may_suid(bprm->file->f_path.mnt); @@ -2262,7 +2262,7 @@ static int check_nnp_nosuid(const struct linux_binprm *bprm, if (!nnp && !nosuid) return 0; /* neither NNP nor nosuid */ - if (new_tsec->sid == old_tsec->sid) + if (new_crsec->sid == old_crsec->sid) return 0; /* No change in credentials */ /* @@ -2277,7 +2277,7 @@ static int check_nnp_nosuid(const struct linux_binprm *bprm, av |= PROCESS2__NNP_TRANSITION; if (nosuid) av |= PROCESS2__NOSUID_TRANSITION; - rc = avc_has_perm(old_tsec->sid, new_tsec->sid, + rc = avc_has_perm(old_crsec->sid, new_crsec->sid, SECCLASS_PROCESS2, av, NULL); if (!rc) return 0; @@ -2288,8 +2288,8 @@ static int check_nnp_nosuid(const struct linux_binprm *bprm, * i.e. SIDs that are guaranteed to only be allowed a subset * of the permissions of the current SID. */ - rc = security_bounded_transition(old_tsec->sid, - new_tsec->sid); + rc = security_bounded_transition(old_crsec->sid, + new_crsec->sid); if (!rc) return 0; @@ -2305,8 +2305,8 @@ static int check_nnp_nosuid(const struct linux_binprm *bprm, static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) { - const struct task_security_struct *old_tsec; - struct task_security_struct *new_tsec; + const struct cred_security_struct *old_crsec; + struct cred_security_struct *new_crsec; struct inode_security_struct *isec; struct common_audit_data ad; struct inode *inode = file_inode(bprm->file); @@ -2315,18 +2315,18 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) /* SELinux context only depends on initial program or script and not * the script interpreter */ - old_tsec = selinux_cred(current_cred()); - new_tsec = selinux_cred(bprm->cred); + old_crsec = selinux_cred(current_cred()); + new_crsec = selinux_cred(bprm->cred); isec = inode_security(inode); /* Default to the current task SID. */ - new_tsec->sid = old_tsec->sid; - new_tsec->osid = old_tsec->sid; + new_crsec->sid = old_crsec->sid; + new_crsec->osid = old_crsec->sid; /* Reset fs, key, and sock SIDs on execve. */ - new_tsec->create_sid = 0; - new_tsec->keycreate_sid = 0; - new_tsec->sockcreate_sid = 0; + new_crsec->create_sid = 0; + new_crsec->keycreate_sid = 0; + new_crsec->sockcreate_sid = 0; /* * Before policy is loaded, label any task outside kernel space @@ -2335,26 +2335,26 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL). */ if (!selinux_initialized()) { - new_tsec->sid = SECINITSID_INIT; + new_crsec->sid = SECINITSID_INIT; /* also clear the exec_sid just in case */ - new_tsec->exec_sid = 0; + new_crsec->exec_sid = 0; return 0; } - if (old_tsec->exec_sid) { - new_tsec->sid = old_tsec->exec_sid; + if (old_crsec->exec_sid) { + new_crsec->sid = old_crsec->exec_sid; /* Reset exec SID on execve. */ - new_tsec->exec_sid = 0; + new_crsec->exec_sid = 0; /* Fail on NNP or nosuid if not an allowed transition. */ - rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); + rc = check_nnp_nosuid(bprm, old_crsec, new_crsec); if (rc) return rc; } else { /* Check for a default transition on this program. */ - rc = security_transition_sid(old_tsec->sid, + rc = security_transition_sid(old_crsec->sid, isec->sid, SECCLASS_PROCESS, NULL, - &new_tsec->sid); + &new_crsec->sid); if (rc) return rc; @@ -2362,34 +2362,34 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) * Fallback to old SID on NNP or nosuid if not an allowed * transition. */ - rc = check_nnp_nosuid(bprm, old_tsec, new_tsec); + rc = check_nnp_nosuid(bprm, old_crsec, new_crsec); if (rc) - new_tsec->sid = old_tsec->sid; + new_crsec->sid = old_crsec->sid; } ad.type = LSM_AUDIT_DATA_FILE; ad.u.file = bprm->file; - if (new_tsec->sid == old_tsec->sid) { - rc = avc_has_perm(old_tsec->sid, isec->sid, + if (new_crsec->sid == old_crsec->sid) { + rc = avc_has_perm(old_crsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ - rc = avc_has_perm(old_tsec->sid, new_tsec->sid, + rc = avc_has_perm(old_crsec->sid, new_crsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; - rc = avc_has_perm(new_tsec->sid, isec->sid, + rc = avc_has_perm(new_crsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; /* Check for shared state */ if (bprm->unsafe & LSM_UNSAFE_SHARE) { - rc = avc_has_perm(old_tsec->sid, new_tsec->sid, + rc = avc_has_perm(old_crsec->sid, new_crsec->sid, SECCLASS_PROCESS, PROCESS__SHARE, NULL); if (rc) @@ -2401,7 +2401,7 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) if (bprm->unsafe & LSM_UNSAFE_PTRACE) { u32 ptsid = ptrace_parent_sid(); if (ptsid != 0) { - rc = avc_has_perm(ptsid, new_tsec->sid, + rc = avc_has_perm(ptsid, new_crsec->sid, SECCLASS_PROCESS, PROCESS__PTRACE, NULL); if (rc) @@ -2415,7 +2415,7 @@ static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm) /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ - rc = avc_has_perm(old_tsec->sid, new_tsec->sid, + rc = avc_has_perm(old_crsec->sid, new_crsec->sid, SECCLASS_PROCESS, PROCESS__NOATSECURE, NULL); bprm->secureexec |= !!rc; @@ -2483,12 +2483,12 @@ static inline void flush_unauthorized_files(const struct cred *cred, */ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) { - struct task_security_struct *new_tsec; + struct cred_security_struct *new_crsec; struct rlimit *rlim, *initrlim; int rc, i; - new_tsec = selinux_cred(bprm->cred); - if (new_tsec->sid == new_tsec->osid) + new_crsec = selinux_cred(bprm->cred); + if (new_crsec->sid == new_crsec->osid) return; /* Close files for which the new task SID is not authorized. */ @@ -2507,7 +2507,7 @@ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) * higher than the default soft limit for cases where the default is * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. */ - rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, + rc = avc_has_perm(new_crsec->osid, new_crsec->sid, SECCLASS_PROCESS, PROCESS__RLIMITINH, NULL); if (rc) { /* protect against do_prlimit() */ @@ -2529,12 +2529,12 @@ static void selinux_bprm_committing_creds(const struct linux_binprm *bprm) */ static void selinux_bprm_committed_creds(const struct linux_binprm *bprm) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); u32 osid, sid; int rc; - osid = tsec->osid; - sid = tsec->sid; + osid = crsec->osid; + sid = crsec->sid; if (sid == osid) return; @@ -2911,7 +2911,7 @@ static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, { u32 newsid; int rc; - struct task_security_struct *tsec; + struct cred_security_struct *crsec; rc = selinux_determine_inode_label(selinux_cred(old), d_inode(dentry->d_parent), name, @@ -2920,8 +2920,8 @@ static int selinux_dentry_create_files_as(struct dentry *dentry, int mode, if (rc) return rc; - tsec = selinux_cred(new); - tsec->create_sid = newsid; + crsec = selinux_cred(new); + crsec->create_sid = newsid; return 0; } @@ -2929,7 +2929,7 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, struct xattr *xattrs, int *xattr_count) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); struct superblock_security_struct *sbsec; struct xattr *xattr = lsm_get_xattr_slot(xattrs, xattr_count); u32 newsid, clen; @@ -2939,9 +2939,9 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir, sbsec = selinux_superblock(dir->i_sb); - newsid = tsec->create_sid; + newsid = crsec->create_sid; newsclass = inode_mode_to_security_class(inode->i_mode); - rc = selinux_determine_inode_label(tsec, dir, qstr, newsclass, &newsid); + rc = selinux_determine_inode_label(crsec, dir, qstr, newsclass, &newsid); if (rc) return rc; @@ -3113,7 +3113,7 @@ static noinline int audit_inode_permission(struct inode *inode, static inline void task_avdcache_reset(struct task_security_struct *tsec) { memset(&tsec->avdcache.dir, 0, sizeof(tsec->avdcache.dir)); - tsec->avdcache.sid = tsec->sid; + tsec->avdcache.sid = current_sid(); tsec->avdcache.seqno = avc_policy_seqno(); tsec->avdcache.dir_spot = TSEC_AVDC_DIR_SIZE - 1; } @@ -3137,7 +3137,7 @@ static inline int task_avdcache_search(struct task_security_struct *tsec, if (isec->sclass != SECCLASS_DIR) return -ENOENT; - if (unlikely(tsec->sid != tsec->avdcache.sid || + if (unlikely(current_sid() != tsec->avdcache.sid || tsec->avdcache.seqno != avc_policy_seqno())) { task_avdcache_reset(tsec); return -ENOENT; @@ -3201,6 +3201,7 @@ static int selinux_inode_permission(struct inode *inode, int requested) { int mask; u32 perms; + u32 sid = current_sid(); struct task_security_struct *tsec; struct inode_security_struct *isec; struct avdc_entry *avdc; @@ -3213,8 +3214,8 @@ static int selinux_inode_permission(struct inode *inode, int requested) if (!mask) return 0; - tsec = selinux_cred(current_cred()); - if (task_avdcache_permnoaudit(tsec)) + tsec = selinux_task(current); + if (task_avdcache_permnoaudit(tsec, sid)) return 0; isec = inode_security_rcu(inode, requested & MAY_NOT_BLOCK); @@ -3234,7 +3235,7 @@ static int selinux_inode_permission(struct inode *inode, int requested) struct av_decision avd; /* Cache miss. */ - rc = avc_has_perm_noaudit(tsec->sid, isec->sid, isec->sclass, + rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, (requested & MAY_ACCESS) ? FILE__AUDIT_ACCESS : 0, @@ -3285,9 +3286,9 @@ static int selinux_inode_getattr(const struct path *path) { struct task_security_struct *tsec; - tsec = selinux_cred(current_cred()); + tsec = selinux_task(current); - if (task_avdcache_permnoaudit(tsec)) + if (task_avdcache_permnoaudit(tsec, current_sid())) return 0; return path_has_perm(current_cred(), path, FILE__GETATTR); @@ -3659,7 +3660,7 @@ static void selinux_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop) static int selinux_inode_copy_up(struct dentry *src, struct cred **new) { struct lsm_prop prop; - struct task_security_struct *tsec; + struct cred_security_struct *crsec; struct cred *new_creds = *new; if (new_creds == NULL) { @@ -3668,10 +3669,10 @@ static int selinux_inode_copy_up(struct dentry *src, struct cred **new) return -ENOMEM; } - tsec = selinux_cred(new_creds); + crsec = selinux_cred(new_creds); /* Get label from overlay inode and set it in create_sid */ selinux_inode_getlsmprop(d_inode(src), &prop); - tsec->create_sid = prop.selinux.secid; + crsec->create_sid = prop.selinux.secid; *new = new_creds; return 0; } @@ -3697,7 +3698,7 @@ static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name) static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); u32 parent_sid, newsid, clen; int rc; char *context; @@ -3725,8 +3726,8 @@ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, if (rc) return rc; - if (tsec->create_sid) { - newsid = tsec->create_sid; + if (crsec->create_sid) { + newsid = crsec->create_sid; } else { u16 secclass = inode_mode_to_security_class(kn->mode); const char *kn_name; @@ -3737,7 +3738,7 @@ static int selinux_kernfs_init_security(struct kernfs_node *kn_dir, q.name = kn_name; q.hash_len = hashlen_string(kn_dir, kn_name); - rc = security_transition_sid(tsec->sid, + rc = security_transition_sid(crsec->sid, parent_sid, secclass, &q, &newsid); if (rc) @@ -4151,7 +4152,10 @@ static int selinux_task_alloc(struct task_struct *task, u64 clone_flags) { u32 sid = current_sid(); + struct task_security_struct *old_tsec = selinux_task(current); + struct task_security_struct *new_tsec = selinux_task(task); + *new_tsec = *old_tsec; return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL); } @@ -4161,10 +4165,10 @@ static int selinux_task_alloc(struct task_struct *task, static int selinux_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { - const struct task_security_struct *old_tsec = selinux_cred(old); - struct task_security_struct *tsec = selinux_cred(new); + const struct cred_security_struct *old_crsec = selinux_cred(old); + struct cred_security_struct *crsec = selinux_cred(new); - *tsec = *old_tsec; + *crsec = *old_crsec; return 0; } @@ -4173,10 +4177,10 @@ static int selinux_cred_prepare(struct cred *new, const struct cred *old, */ static void selinux_cred_transfer(struct cred *new, const struct cred *old) { - const struct task_security_struct *old_tsec = selinux_cred(old); - struct task_security_struct *tsec = selinux_cred(new); + const struct cred_security_struct *old_crsec = selinux_cred(old); + struct cred_security_struct *crsec = selinux_cred(new); - *tsec = *old_tsec; + *crsec = *old_crsec; } static void selinux_cred_getsecid(const struct cred *c, u32 *secid) @@ -4195,7 +4199,7 @@ static void selinux_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop) */ static int selinux_kernel_act_as(struct cred *new, u32 secid) { - struct task_security_struct *tsec = selinux_cred(new); + struct cred_security_struct *crsec = selinux_cred(new); u32 sid = current_sid(); int ret; @@ -4204,10 +4208,10 @@ static int selinux_kernel_act_as(struct cred *new, u32 secid) KERNEL_SERVICE__USE_AS_OVERRIDE, NULL); if (ret == 0) { - tsec->sid = secid; - tsec->create_sid = 0; - tsec->keycreate_sid = 0; - tsec->sockcreate_sid = 0; + crsec->sid = secid; + crsec->create_sid = 0; + crsec->keycreate_sid = 0; + crsec->sockcreate_sid = 0; } return ret; } @@ -4219,7 +4223,7 @@ static int selinux_kernel_act_as(struct cred *new, u32 secid) static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) { struct inode_security_struct *isec = inode_security(inode); - struct task_security_struct *tsec = selinux_cred(new); + struct cred_security_struct *crsec = selinux_cred(new); u32 sid = current_sid(); int ret; @@ -4229,7 +4233,7 @@ static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) NULL); if (ret == 0) - tsec->create_sid = isec->sid; + crsec->create_sid = isec->sid; return ret; } @@ -4744,15 +4748,15 @@ static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid) /* socket security operations */ -static int socket_sockcreate_sid(const struct task_security_struct *tsec, +static int socket_sockcreate_sid(const struct cred_security_struct *crsec, u16 secclass, u32 *socksid) { - if (tsec->sockcreate_sid > SECSID_NULL) { - *socksid = tsec->sockcreate_sid; + if (crsec->sockcreate_sid > SECSID_NULL) { + *socksid = crsec->sockcreate_sid; return 0; } - return security_transition_sid(tsec->sid, tsec->sid, + return security_transition_sid(crsec->sid, crsec->sid, secclass, NULL, socksid); } @@ -4797,7 +4801,7 @@ static int sock_has_perm(struct sock *sk, u32 perms) static int selinux_socket_create(int family, int type, int protocol, int kern) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); u32 newsid; u16 secclass; int rc; @@ -4806,17 +4810,17 @@ static int selinux_socket_create(int family, int type, return 0; secclass = socket_type_to_security_class(family, type, protocol); - rc = socket_sockcreate_sid(tsec, secclass, &newsid); + rc = socket_sockcreate_sid(crsec, secclass, &newsid); if (rc) return rc; - return avc_has_perm(tsec->sid, newsid, secclass, SOCKET__CREATE, NULL); + return avc_has_perm(crsec->sid, newsid, secclass, SOCKET__CREATE, NULL); } static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock)); struct sk_security_struct *sksec; u16 sclass = socket_type_to_security_class(family, type, protocol); @@ -4824,7 +4828,7 @@ static int selinux_socket_post_create(struct socket *sock, int family, int err = 0; if (!kern) { - err = socket_sockcreate_sid(tsec, sclass, &sid); + err = socket_sockcreate_sid(crsec, sclass, &sid); if (err) return err; } @@ -6526,37 +6530,37 @@ static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p, char **value) { - const struct task_security_struct *tsec; + const struct cred_security_struct *crsec; int error; u32 sid; u32 len; rcu_read_lock(); - tsec = selinux_cred(__task_cred(p)); + crsec = selinux_cred(__task_cred(p)); if (p != current) { - error = avc_has_perm(current_sid(), tsec->sid, + error = avc_has_perm(current_sid(), crsec->sid, SECCLASS_PROCESS, PROCESS__GETATTR, NULL); if (error) goto err_unlock; } switch (attr) { case LSM_ATTR_CURRENT: - sid = tsec->sid; + sid = crsec->sid; break; case LSM_ATTR_PREV: - sid = tsec->osid; + sid = crsec->osid; break; case LSM_ATTR_EXEC: - sid = tsec->exec_sid; + sid = crsec->exec_sid; break; case LSM_ATTR_FSCREATE: - sid = tsec->create_sid; + sid = crsec->create_sid; break; case LSM_ATTR_KEYCREATE: - sid = tsec->keycreate_sid; + sid = crsec->keycreate_sid; break; case LSM_ATTR_SOCKCREATE: - sid = tsec->sockcreate_sid; + sid = crsec->sockcreate_sid; break; default: error = -EOPNOTSUPP; @@ -6581,7 +6585,7 @@ err_unlock: static int selinux_lsm_setattr(u64 attr, void *value, size_t size) { - struct task_security_struct *tsec; + struct cred_security_struct *crsec; struct cred *new; u32 mysid = current_sid(), sid = 0, ptsid; int error; @@ -6667,11 +6671,11 @@ static int selinux_lsm_setattr(u64 attr, void *value, size_t size) operation. See selinux_bprm_creds_for_exec for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ - tsec = selinux_cred(new); + crsec = selinux_cred(new); if (attr == LSM_ATTR_EXEC) { - tsec->exec_sid = sid; + crsec->exec_sid = sid; } else if (attr == LSM_ATTR_FSCREATE) { - tsec->create_sid = sid; + crsec->create_sid = sid; } else if (attr == LSM_ATTR_KEYCREATE) { if (sid) { error = avc_has_perm(mysid, sid, @@ -6679,22 +6683,22 @@ static int selinux_lsm_setattr(u64 attr, void *value, size_t size) if (error) goto abort_change; } - tsec->keycreate_sid = sid; + crsec->keycreate_sid = sid; } else if (attr == LSM_ATTR_SOCKCREATE) { - tsec->sockcreate_sid = sid; + crsec->sockcreate_sid = sid; } else if (attr == LSM_ATTR_CURRENT) { error = -EINVAL; if (sid == 0) goto abort_change; if (!current_is_single_threaded()) { - error = security_bounded_transition(tsec->sid, sid); + error = security_bounded_transition(crsec->sid, sid); if (error) goto abort_change; } /* Check permissions for the transition. */ - error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, + error = avc_has_perm(crsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) goto abort_change; @@ -6709,7 +6713,7 @@ static int selinux_lsm_setattr(u64 attr, void *value, size_t size) goto abort_change; } - tsec->sid = sid; + crsec->sid = sid; } else { error = -EINVAL; goto abort_change; @@ -6876,14 +6880,14 @@ static int selinux_inode_getsecctx(struct inode *inode, struct lsm_context *cp) static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { - const struct task_security_struct *tsec; + const struct cred_security_struct *crsec; struct key_security_struct *ksec = selinux_key(k); - tsec = selinux_cred(cred); - if (tsec->keycreate_sid) - ksec->sid = tsec->keycreate_sid; + crsec = selinux_cred(cred); + if (crsec->keycreate_sid) + ksec->sid = crsec->keycreate_sid; else - ksec->sid = tsec->sid; + ksec->sid = crsec->sid; return 0; } @@ -7137,7 +7141,8 @@ static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *att #endif struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = { - .lbs_cred = sizeof(struct task_security_struct), + .lbs_cred = sizeof(struct cred_security_struct), + .lbs_task = sizeof(struct task_security_struct), .lbs_file = sizeof(struct file_security_struct), .lbs_inode = sizeof(struct inode_security_struct), .lbs_ipc = sizeof(struct ipc_security_struct), diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 2d5139c6d45b..8fc3de5234ac 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -37,13 +37,16 @@ struct avdc_entry { bool permissive; /* AVC permissive flag */ }; -struct task_security_struct { +struct cred_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ +} __randomize_layout; + +struct task_security_struct { #define TSEC_AVDC_DIR_SIZE (1 << 2) struct { u32 sid; /* current SID for cached entries */ @@ -54,10 +57,11 @@ struct task_security_struct { } avdcache; } __randomize_layout; -static inline bool task_avdcache_permnoaudit(struct task_security_struct *tsec) +static inline bool task_avdcache_permnoaudit(struct task_security_struct *tsec, + u32 sid) { return (tsec->avdcache.permissive_neveraudit && - tsec->sid == tsec->avdcache.sid && + sid == tsec->avdcache.sid && tsec->avdcache.seqno == avc_policy_seqno()); } @@ -172,11 +176,17 @@ struct perf_event_security_struct { }; extern struct lsm_blob_sizes selinux_blob_sizes; -static inline struct task_security_struct *selinux_cred(const struct cred *cred) +static inline struct cred_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } +static inline struct task_security_struct * +selinux_task(const struct task_struct *task) +{ + return task->security + selinux_blob_sizes.lbs_task; +} + static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; @@ -207,9 +217,9 @@ selinux_ipc(const struct kern_ipc_perm *ipc) */ static inline u32 current_sid(void) { - const struct task_security_struct *tsec = selinux_cred(current_cred()); + const struct cred_security_struct *crsec = selinux_cred(current_cred()); - return tsec->sid; + return crsec->sid; } static inline struct superblock_security_struct * diff --git a/sound/hda/codecs/cirrus/cs420x.c b/sound/hda/codecs/cirrus/cs420x.c index 823220d5cada..13f5f1711fa4 100644 --- a/sound/hda/codecs/cirrus/cs420x.c +++ b/sound/hda/codecs/cirrus/cs420x.c @@ -585,6 +585,7 @@ static const struct hda_quirk cs4208_mac_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x6c00, "MacMini 7,1", CS4208_MACMINI), SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6), SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6), + SND_PCI_QUIRK(0x106b, 0x7800, "MacPro 6,1", CS4208_MACMINI), SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11), {} /* terminator */ }; diff --git a/sound/hda/codecs/hdmi/nvhdmi-mcp.c b/sound/hda/codecs/hdmi/nvhdmi-mcp.c index 8fd8d76fa72f..1c5fdfe872f2 100644 --- a/sound/hda/codecs/hdmi/nvhdmi-mcp.c +++ b/sound/hda/codecs/hdmi/nvhdmi-mcp.c @@ -350,8 +350,8 @@ static int nvhdmi_mcp_probe(struct hda_codec *codec, static const struct hda_codec_ops nvhdmi_mcp_codec_ops = { .probe = nvhdmi_mcp_probe, .remove = snd_hda_hdmi_simple_remove, - .build_controls = nvhdmi_mcp_build_pcms, - .build_pcms = nvhdmi_mcp_build_controls, + .build_pcms = nvhdmi_mcp_build_pcms, + .build_controls = nvhdmi_mcp_build_controls, .init = nvhdmi_mcp_init, .unsol_event = snd_hda_hdmi_simple_unsol_event, }; diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 4aec5067c59d..b45fcc9a3785 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6525,6 +6525,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8a4f, "HP Victus 15-fa0xxx (MB 8A4F)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a6e, "HP EDNA 360", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x103c, 0x8a74, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8a75, "HP ProBook 450 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x8aa0, "HP ProBook 440 G9 (MB 8A9E)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), @@ -6572,6 +6573,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bd4, "HP Victus 16-s0xxx (MB 8BD4)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), + SND_PCI_QUIRK(0x103c, 0x8bd6, "HP Pavilion Aero Laptop 13z-be200", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8bdd, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bde, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bdf, "HP Envy 15", ALC287_FIXUP_CS35L41_I2C_2), @@ -6694,6 +6696,15 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8ed5, "HP Merino13X", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8ed6, "HP Merino13", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8ed7, "HP Merino14", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8ed8, "HP Merino16", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8ed9, "HP Merino14W", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8eda, "HP Merino16W", ALC245_FIXUP_TAS2781_SPI_2), + SND_PCI_QUIRK(0x103c, 0x8f40, "HP Lampas14", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x103c, 0x8f41, "HP Lampas16", ALC287_FIXUP_TXNW2781_I2C), + SND_PCI_QUIRK(0x103c, 0x8f42, "HP LampasW14", ALC287_FIXUP_TXNW2781_I2C), SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), diff --git a/sound/pci/au88x0/au88x0.c b/sound/pci/au88x0/au88x0.c index de56e83d8e10..bb02945793f0 100644 --- a/sound/pci/au88x0/au88x0.c +++ b/sound/pci/au88x0/au88x0.c @@ -280,11 +280,11 @@ __snd_vortex_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) // (5) err = pci_read_config_word(pci, PCI_DEVICE_ID, &chip->device); - if (err < 0) - return err; + if (err) + return pcibios_err_to_errno(err); err = pci_read_config_word(pci, PCI_VENDOR_ID, &chip->vendor); - if (err < 0) - return err; + if (err) + return pcibios_err_to_errno(err); chip->rev = pci->revision; #ifdef CHIP_AU8830 if ((chip->rev) != 0xfe && (chip->rev) != 0xfa) { diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c index 6a3cca3d26c7..ead447a5da7f 100644 --- a/sound/soc/codecs/cs4271.c +++ b/sound/soc/codecs/cs4271.c @@ -581,17 +581,17 @@ static int cs4271_component_probe(struct snd_soc_component *component) ret = regcache_sync(cs4271->regmap); if (ret < 0) - return ret; + goto err_disable_regulator; ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2, CS4271_MODE2_PDN | CS4271_MODE2_CPEN, CS4271_MODE2_PDN | CS4271_MODE2_CPEN); if (ret < 0) - return ret; + goto err_disable_regulator; ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2, CS4271_MODE2_PDN, 0); if (ret < 0) - return ret; + goto err_disable_regulator; /* Power-up sequence requires 85 uS */ udelay(85); @@ -601,6 +601,10 @@ static int cs4271_component_probe(struct snd_soc_component *component) CS4271_MODE2_MUTECAEQUB); return 0; + +err_disable_regulator: + regulator_bulk_disable(ARRAY_SIZE(cs4271->supplies), cs4271->supplies); + return ret; } static void cs4271_component_remove(struct snd_soc_component *component) diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index ae89260ca215..3420011da444 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -2124,11 +2124,50 @@ static int da7213_probe(struct snd_soc_component *component) return 0; } +static int da7213_runtime_suspend(struct device *dev) +{ + struct da7213_priv *da7213 = dev_get_drvdata(dev); + + regcache_cache_only(da7213->regmap, true); + regcache_mark_dirty(da7213->regmap); + regulator_bulk_disable(DA7213_NUM_SUPPLIES, da7213->supplies); + + return 0; +} + +static int da7213_runtime_resume(struct device *dev) +{ + struct da7213_priv *da7213 = dev_get_drvdata(dev); + int ret; + + ret = regulator_bulk_enable(DA7213_NUM_SUPPLIES, da7213->supplies); + if (ret < 0) + return ret; + regcache_cache_only(da7213->regmap, false); + return regcache_sync(da7213->regmap); +} + +static int da7213_suspend(struct snd_soc_component *component) +{ + struct da7213_priv *da7213 = snd_soc_component_get_drvdata(component); + + return da7213_runtime_suspend(da7213->dev); +} + +static int da7213_resume(struct snd_soc_component *component) +{ + struct da7213_priv *da7213 = snd_soc_component_get_drvdata(component); + + return da7213_runtime_resume(da7213->dev); +} + static const struct snd_soc_component_driver soc_component_dev_da7213 = { .probe = da7213_probe, .set_bias_level = da7213_set_bias_level, .controls = da7213_snd_controls, .num_controls = ARRAY_SIZE(da7213_snd_controls), + .suspend = da7213_suspend, + .resume = da7213_resume, .dapm_widgets = da7213_dapm_widgets, .num_dapm_widgets = ARRAY_SIZE(da7213_dapm_widgets), .dapm_routes = da7213_audio_map, @@ -2175,6 +2214,8 @@ static int da7213_i2c_probe(struct i2c_client *i2c) if (!da7213->fin_min_rate) return -EINVAL; + da7213->dev = &i2c->dev; + i2c_set_clientdata(i2c, da7213); /* Get required supplies */ @@ -2224,31 +2265,9 @@ static void da7213_i2c_remove(struct i2c_client *i2c) pm_runtime_disable(&i2c->dev); } -static int da7213_runtime_suspend(struct device *dev) -{ - struct da7213_priv *da7213 = dev_get_drvdata(dev); - - regcache_cache_only(da7213->regmap, true); - regcache_mark_dirty(da7213->regmap); - regulator_bulk_disable(DA7213_NUM_SUPPLIES, da7213->supplies); - - return 0; -} - -static int da7213_runtime_resume(struct device *dev) -{ - struct da7213_priv *da7213 = dev_get_drvdata(dev); - int ret; - - ret = regulator_bulk_enable(DA7213_NUM_SUPPLIES, da7213->supplies); - if (ret < 0) - return ret; - regcache_cache_only(da7213->regmap, false); - return regcache_sync(da7213->regmap); -} - -static DEFINE_RUNTIME_DEV_PM_OPS(da7213_pm, da7213_runtime_suspend, - da7213_runtime_resume, NULL); +static const struct dev_pm_ops da7213_pm = { + RUNTIME_PM_OPS(da7213_runtime_suspend, da7213_runtime_resume, NULL) +}; static const struct i2c_device_id da7213_i2c_id[] = { { "da7213" }, diff --git a/sound/soc/codecs/da7213.h b/sound/soc/codecs/da7213.h index b9ab791d6b88..29cbf0eb6124 100644 --- a/sound/soc/codecs/da7213.h +++ b/sound/soc/codecs/da7213.h @@ -595,6 +595,7 @@ enum da7213_supplies { /* Codec private data */ struct da7213_priv { struct regmap *regmap; + struct device *dev; struct mutex ctrl_lock; struct regulator_bulk_data supplies[DA7213_NUM_SUPPLIES]; struct clk *mclk; diff --git a/sound/soc/codecs/lpass-va-macro.c b/sound/soc/codecs/lpass-va-macro.c index 2e1b77973a3e..92c177b82a02 100644 --- a/sound/soc/codecs/lpass-va-macro.c +++ b/sound/soc/codecs/lpass-va-macro.c @@ -1638,7 +1638,7 @@ static int va_macro_probe(struct platform_device *pdev) if (ret) goto err_clkout; - va->fsgen = clk_hw_get_clk(&va->hw, "fsgen"); + va->fsgen = devm_clk_hw_get_clk(dev, &va->hw, "fsgen"); if (IS_ERR(va->fsgen)) { ret = PTR_ERR(va->fsgen); goto err_clkout; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index ba880b5de7e8..8f37aa00e62e 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -1957,7 +1957,8 @@ static void tasdevice_parse_dt(struct tasdevice_priv *tas_priv) { struct i2c_client *client = (struct i2c_client *)tas_priv->client; unsigned int dev_addrs[TASDEVICE_MAX_CHANNELS]; - int i, ndev = 0; + int ndev = 0; + int i, rc; if (tas_priv->isacpi) { ndev = device_property_read_u32_array(&client->dev, @@ -1968,8 +1969,12 @@ static void tasdevice_parse_dt(struct tasdevice_priv *tas_priv) } else { ndev = (ndev < ARRAY_SIZE(dev_addrs)) ? ndev : ARRAY_SIZE(dev_addrs); - ndev = device_property_read_u32_array(&client->dev, + rc = device_property_read_u32_array(&client->dev, "ti,audio-slots", dev_addrs, ndev); + if (rc != 0) { + ndev = 1; + dev_addrs[0] = client->addr; + } } tas_priv->irq = diff --git a/sound/soc/codecs/tas2783-sdw.c b/sound/soc/codecs/tas2783-sdw.c index 1fb4227b711e..e273b80d033e 100644 --- a/sound/soc/codecs/tas2783-sdw.c +++ b/sound/soc/codecs/tas2783-sdw.c @@ -762,10 +762,17 @@ static void tas2783_fw_ready(const struct firmware *fmw, void *context) goto out; } - mutex_lock(&tas_dev->pde_lock); img_sz = fmw->size; buf = fmw->data; offset += FW_DL_OFFSET; + if (offset >= (img_sz - FW_FL_HDR)) { + dev_err(tas_dev->dev, + "firmware is too small"); + ret = -EINVAL; + goto out; + } + + mutex_lock(&tas_dev->pde_lock); while (offset < (img_sz - FW_FL_HDR)) { memset(&hdr, 0, sizeof(hdr)); offset += read_header(&buf[offset], &hdr); @@ -776,6 +783,14 @@ static void tas2783_fw_ready(const struct firmware *fmw, void *context) /* size also includes the header */ file_blk_size = hdr.length - FW_FL_HDR; + /* make sure that enough data is there */ + if (offset + file_blk_size > img_sz) { + ret = -EINVAL; + dev_err(tas_dev->dev, + "corrupt firmware file"); + break; + } + switch (hdr.file_id) { case 0: ret = sdw_nwrite_no_pm(tas_dev->sdw_peripheral, @@ -808,7 +823,8 @@ static void tas2783_fw_ready(const struct firmware *fmw, void *context) break; } mutex_unlock(&tas_dev->pde_lock); - tas2783_update_calibdata(tas_dev); + if (!ret) + tas2783_update_calibdata(tas_dev); out: if (!ret) diff --git a/sound/soc/renesas/rcar/ssiu.c b/sound/soc/renesas/rcar/ssiu.c index faf351126d57..244fb833292a 100644 --- a/sound/soc/renesas/rcar/ssiu.c +++ b/sound/soc/renesas/rcar/ssiu.c @@ -509,7 +509,7 @@ void rsnd_parse_connect_ssiu(struct rsnd_dai *rdai, int rsnd_ssiu_probe(struct rsnd_priv *priv) { struct device *dev = rsnd_priv_to_dev(priv); - struct device_node *node; + struct device_node *node __free(device_node) = rsnd_ssiu_of_node(priv); struct rsnd_ssiu *ssiu; struct rsnd_mod_ops *ops; const int *list = NULL; @@ -522,7 +522,6 @@ int rsnd_ssiu_probe(struct rsnd_priv *priv) * see * rsnd_ssiu_bufsif_to_id() */ - node = rsnd_ssiu_of_node(priv); if (node) nr = rsnd_node_count(priv, node, SSIU_NAME); else diff --git a/sound/soc/sdca/sdca_functions.c b/sound/soc/sdca/sdca_functions.c index 13f68f7b6dd6..0ccb6775f4de 100644 --- a/sound/soc/sdca/sdca_functions.c +++ b/sound/soc/sdca/sdca_functions.c @@ -894,7 +894,8 @@ static int find_sdca_entity_control(struct device *dev, struct sdca_entity *enti return ret; } - control->values = devm_kzalloc(dev, hweight64(control->cn_list), GFP_KERNEL); + control->values = devm_kcalloc(dev, hweight64(control->cn_list), + sizeof(int), GFP_KERNEL); if (!control->values) return -ENOMEM; diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c index f7c8c16308de..3848c7df1916 100644 --- a/sound/soc/sdw_utils/soc_sdw_utils.c +++ b/sound/soc/sdw_utils/soc_sdw_utils.c @@ -1277,7 +1277,7 @@ static int is_sdca_endpoint_present(struct device *dev, struct sdw_slave *slave; struct device *sdw_dev; const char *sdw_codec_name; - int i; + int ret, i; dlc = kzalloc(sizeof(*dlc), GFP_KERNEL); if (!dlc) @@ -1307,13 +1307,16 @@ static int is_sdca_endpoint_present(struct device *dev, } slave = dev_to_sdw_dev(sdw_dev); - if (!slave) - return -EINVAL; + if (!slave) { + ret = -EINVAL; + goto put_device; + } /* Make sure BIOS provides SDCA properties */ if (!slave->sdca_data.interface_revision) { dev_warn(&slave->dev, "SDCA properties not found in the BIOS\n"); - return 1; + ret = 1; + goto put_device; } for (i = 0; i < slave->sdca_data.num_functions; i++) { @@ -1322,7 +1325,8 @@ static int is_sdca_endpoint_present(struct device *dev, if (dai_type == dai_info->dai_type) { dev_dbg(&slave->dev, "DAI type %d sdca function %s found\n", dai_type, slave->sdca_data.function[i].name); - return 1; + ret = 1; + goto put_device; } } @@ -1330,7 +1334,11 @@ static int is_sdca_endpoint_present(struct device *dev, "SDCA device function for DAI type %d not supported, skip endpoint\n", dai_info->dai_type); - return 0; + ret = 0; + +put_device: + put_device(sdw_dev); + return ret; } int asoc_sdw_parse_sdw_endpoints(struct snd_soc_card *card, diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 880f5afcce60..cc15624ecaff 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1362,6 +1362,11 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, ep->sample_rem = ep->cur_rate % ep->pps; ep->packsize[0] = ep->cur_rate / ep->pps; ep->packsize[1] = (ep->cur_rate + (ep->pps - 1)) / ep->pps; + if (ep->packsize[1] > ep->maxpacksize) { + usb_audio_dbg(chip, "Too small maxpacksize %u for rate %u / pps %u\n", + ep->maxpacksize, ep->cur_rate, ep->pps); + return -EINVAL; + } /* calculate the frequency in 16.16 format */ ep->freqm = ep->freqn; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 6f00e0d52382..3af71d42b9b9 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -921,7 +921,7 @@ static int parse_term_uac2_clock_source(struct mixer_build *state, { struct uac_clock_source_descriptor *d = p1; - term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */ + term->type = UAC2_CLOCK_SOURCE << 16; /* virtual type */ term->id = id; term->name = d->iClockSource; return 0; @@ -3086,6 +3086,8 @@ static int snd_usb_mixer_controls_badd(struct usb_mixer_interface *mixer, int i; assoc = usb_ifnum_to_if(dev, ctrlif)->intf_assoc; + if (!assoc) + return -EINVAL; /* Detect BADD capture/playback channels from AS EP descriptors */ for (i = 0; i < assoc->bInterfaceCount; i++) { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 71638e6dfb20..61bd61ffb1b2 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2022,12 +2022,15 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case USB_ID(0x16d0, 0x09d8): /* NuPrime IDA-8 */ case USB_ID(0x16d0, 0x09db): /* NuPrime Audio DAC-9 */ case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ + case USB_ID(0x16d0, 0x0ab1): /* PureAudio APA DAC */ + case USB_ID(0x16d0, 0xeca1): /* PureAudio Lotus DAC5, DAC5 SE, DAC5 Pro */ case USB_ID(0x1db5, 0x0003): /* Bryston BDA3 */ case USB_ID(0x20a0, 0x4143): /* WaveIO USB Audio 2.0 */ case USB_ID(0x22e1, 0xca01): /* HDTA Serenade DSD */ case USB_ID(0x249c, 0x9326): /* M2Tech Young MkIII */ case USB_ID(0x2616, 0x0106): /* PS Audio NuWave DAC */ case USB_ID(0x2622, 0x0041): /* Audiolab M-DAC+ */ + case USB_ID(0x2622, 0x0061): /* LEAK Stereo 230 */ case USB_ID(0x278b, 0x5100): /* Rotel RC-1590 */ case USB_ID(0x27f7, 0x3002): /* W4S DAC-2v2SE */ case USB_ID(0x29a2, 0x0086): /* Mutec MC3+ USB */ @@ -2267,6 +2270,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0fd9, 0x0008, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x1038, 0x1294, /* SteelSeries Arctis Pro Wireless */ + QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE), DEVICE_FLG(0x1101, 0x0003, /* Audioengine D1 */ QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x12d1, 0x3a07, /* Huawei Technologies Co., Ltd. */ @@ -2297,6 +2302,10 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_IGNORE_CLOCK_SOURCE), DEVICE_FLG(0x1686, 0x00dd, /* Zoom R16/24 */ QUIRK_FLAG_TX_LENGTH | QUIRK_FLAG_CTL_MSG_DELAY_1M), + DEVICE_FLG(0x16d0, 0x0ab1, /* PureAudio APA DAC */ + QUIRK_FLAG_DSD_RAW), + DEVICE_FLG(0x16d0, 0xeca1, /* PureAudio Lotus DAC5, DAC5 SE and DAC5 Pro */ + QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x17aa, 0x1046, /* Lenovo ThinkStation P620 Rear Line-in, Line-out and Microphone */ QUIRK_FLAG_DISABLE_AUTOSUSPEND), DEVICE_FLG(0x17aa, 0x104d, /* Lenovo ThinkStation P620 Internal Speaker + Front Headset */ @@ -2420,6 +2429,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x25ce, /* Mytek devices */ QUIRK_FLAG_DSD_RAW), + VENDOR_FLG(0x2622, /* IAG Limited devices */ + QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x278b, /* Rotel? */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x292b, /* Gustard/Ess based devices */ diff --git a/tools/arch/riscv/include/asm/csr.h b/tools/arch/riscv/include/asm/csr.h index 56d7367ee344..21d8cee04638 100644 --- a/tools/arch/riscv/include/asm/csr.h +++ b/tools/arch/riscv/include/asm/csr.h @@ -167,7 +167,8 @@ #define VSIP_TO_HVIP_SHIFT (IRQ_VS_SOFT - IRQ_S_SOFT) #define VSIP_VALID_MASK ((_AC(1, UL) << IRQ_S_SOFT) | \ (_AC(1, UL) << IRQ_S_TIMER) | \ - (_AC(1, UL) << IRQ_S_EXT)) + (_AC(1, UL) << IRQ_S_EXT) | \ + (_AC(1, UL) << IRQ_PMU_OVF)) /* AIA CSR bits */ #define TOPI_IID_SHIFT 16 @@ -280,7 +281,7 @@ #define CSR_HPMCOUNTER30H 0xc9e #define CSR_HPMCOUNTER31H 0xc9f -#define CSR_SSCOUNTOVF 0xda0 +#define CSR_SCOUNTOVF 0xda0 #define CSR_SSTATUS 0x100 #define CSR_SIE 0x104 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 9792e329343e..1baa86dfe029 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -93,6 +93,7 @@ #define EXIT_REASON_TPAUSE 68 #define EXIT_REASON_BUS_LOCK 74 #define EXIT_REASON_NOTIFY 75 +#define EXIT_REASON_SEAMCALL 76 #define EXIT_REASON_TDCALL 77 #define EXIT_REASON_MSR_READ_IMM 84 #define EXIT_REASON_MSR_WRITE_IMM 85 diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 009633294b09..35aeeaf5f711 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -182,7 +182,7 @@ bpftool prog tracelog bpftool prog tracelog { stdout | stderr } *PROG* Dump the BPF stream of the program. BPF programs can write to these streams - at runtime with the **bpf_stream_vprintk**\ () kfunc. The kernel may write + at runtime with the **bpf_stream_vprintk_impl**\ () kfunc. The kernel may write error messages to the standard error stream. This facility should be used only for debugging purposes. diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 49b0add392b1..95646290cb89 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -107,7 +107,7 @@ all: $(FILES) __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl - BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd + BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -ldl -lz -llzma -lzstd __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 @@ -115,7 +115,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ############################### $(OUTPUT)test-all.bin: - $(BUILD_ALL) || $(BUILD_ALL) -lopcodes -liberty + $(BUILD_ALL) $(OUTPUT)test-hello.bin: $(BUILD) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 048c8de1a130..e0b579a1df4f 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -2,6 +2,7 @@ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ #ifndef _UAPI_LINUX_NETDEV_H #define _UAPI_LINUX_NETDEV_H diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 80c028540656..d4e4e388e625 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -315,20 +315,20 @@ enum libbpf_tristate { ___param, sizeof(___param)); \ }) -extern int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, - __u32 len__sz, void *aux__prog) __weak __ksym; - -#define bpf_stream_printk(stream_id, fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_stream_vprintk(stream_id, ___fmt, ___param, sizeof(___param), NULL);\ +extern int bpf_stream_vprintk_impl(int stream_id, const char *fmt__str, const void *args, + __u32 len__sz, void *aux__prog) __weak __ksym; + +#define bpf_stream_printk(stream_id, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_stream_vprintk_impl(stream_id, ___fmt, ___param, sizeof(___param), NULL); \ }) /* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index 31ed20c0f3f8..a40591e513b7 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -12,7 +12,7 @@ endif libdir ?= $(prefix)/$(libdir_relative) includedir ?= $(prefix)/include -SUBDIRS = lib generated samples ynltool +SUBDIRS = lib generated samples ynltool tests all: $(SUBDIRS) libynl.a @@ -49,5 +49,9 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install + @make -C tests install -.PHONY: all clean distclean install $(SUBDIRS) +run_tests: + @$(MAKE) -C tests run_tests + +.PHONY: all clean distclean install run_tests $(SUBDIRS) diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py index 8c192e900bd3..ff81ff083764 100755 --- a/tools/net/ynl/pyynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -7,6 +7,7 @@ import os import pathlib import pprint import sys +import textwrap sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily, Netlink, NlError @@ -39,6 +40,60 @@ class YnlEncoder(json.JSONEncoder): return json.JSONEncoder.default(self, obj) +def print_attr_list(ynl, attr_names, attr_set, indent=2): + """Print a list of attributes with their types and documentation.""" + prefix = ' ' * indent + for attr_name in attr_names: + if attr_name in attr_set.attrs: + attr = attr_set.attrs[attr_name] + attr_info = f'{prefix}- {attr_name}: {attr.type}' + if 'enum' in attr.yaml: + enum_name = attr.yaml['enum'] + attr_info += f" (enum: {enum_name})" + # Print enum values if available + if enum_name in ynl.consts: + const = ynl.consts[enum_name] + enum_values = list(const.entries.keys()) + attr_info += f"\n{prefix} {const.type.capitalize()}: {', '.join(enum_values)}" + + # Show nested attributes reference and recursively display them + nested_set_name = None + if attr.type == 'nest' and 'nested-attributes' in attr.yaml: + nested_set_name = attr.yaml['nested-attributes'] + attr_info += f" -> {nested_set_name}" + + if attr.yaml.get('doc'): + doc_text = textwrap.indent(attr.yaml['doc'], prefix + ' ') + attr_info += f"\n{doc_text}" + print(attr_info) + + # Recursively show nested attributes + if nested_set_name in ynl.attr_sets: + nested_set = ynl.attr_sets[nested_set_name] + # Filter out 'unspec' and other unused attrs + nested_names = [n for n in nested_set.attrs.keys() + if nested_set.attrs[n].type != 'unused'] + if nested_names: + print_attr_list(ynl, nested_names, nested_set, indent + 4) + + +def print_mode_attrs(ynl, mode, mode_spec, attr_set, print_request=True): + """Print a given mode (do/dump/event/notify).""" + mode_title = mode.capitalize() + + if print_request and 'request' in mode_spec and 'attributes' in mode_spec['request']: + print(f'\n{mode_title} request attributes:') + print_attr_list(ynl, mode_spec['request']['attributes'], attr_set) + + if 'reply' in mode_spec and 'attributes' in mode_spec['reply']: + print(f'\n{mode_title} reply attributes:') + print_attr_list(ynl, mode_spec['reply']['attributes'], attr_set) + + if 'attributes' in mode_spec: + print(f'\n{mode_title} attributes:') + print_attr_list(ynl, mode_spec['attributes'], attr_set) + + def main(): description = """ YNL CLI utility - a general purpose netlink utility that uses YAML @@ -70,6 +125,8 @@ def main(): group.add_argument('--dump', dest='dump', metavar='DUMP-OPERATION', type=str) group.add_argument('--list-ops', action='store_true') group.add_argument('--list-msgs', action='store_true') + group.add_argument('--list-attrs', dest='list_attrs', metavar='OPERATION', type=str, + help='List attributes for an operation') parser.add_argument('--duration', dest='duration', type=int, help='when subscribed, watch for DURATION seconds') @@ -135,6 +192,28 @@ def main(): for op_name, op in ynl.msgs.items(): print(op_name, " [", ", ".join(op.modes), "]") + if args.list_attrs: + op = ynl.msgs.get(args.list_attrs) + if not op: + print(f'Operation {args.list_attrs} not found') + exit(1) + + print(f'Operation: {op.name}') + print(op.yaml['doc']) + + for mode in ['do', 'dump', 'event']: + if mode in op.yaml: + print_mode_attrs(ynl, mode, op.yaml[mode], op.attr_set, True) + + if 'notify' in op.yaml: + mode_spec = op.yaml['notify'] + ref_spec = ynl.msgs.get(mode_spec).yaml.get('do') + if ref_spec: + print_mode_attrs(ynl, 'notify', ref_spec, op.attr_set, False) + + if 'mcgrp' in op.yaml: + print(f"\nMulticast group: {op.yaml['mcgrp']}") + try: if args.do: reply = ynl.do(args.do, attrs, args.flags) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 225baad3c8f8..36d36eb7e3b8 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -985,6 +985,15 @@ class YnlFamily(SpecFamily): raw = bytes.fromhex(string) else: raw = int(string, 16) + elif attr_spec.display_hint == 'mac': + # Parse MAC address in format "00:11:22:33:44:55" or "001122334455" + if ':' in string: + mac_bytes = [int(x, 16) for x in string.split(':')] + else: + if len(string) % 2 != 0: + raise Exception(f"Invalid MAC address format: {string}") + mac_bytes = [int(string[i:i+2], 16) for i in range(0, len(string), 2)] + raw = bytes(mac_bytes) else: raise Exception(f"Display hint '{attr_spec.display_hint}' not implemented" f" when parsing '{attr_spec['name']}'") diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index aadeb3abcad8..b517d0c605ad 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -1205,7 +1205,7 @@ class SubMessage(SpecSubMessage): class Family(SpecFamily): - def __init__(self, file_name, exclude_ops): + def __init__(self, file_name, exclude_ops, fn_prefix): # Added by resolve: self.c_name = None delattr(self, "c_name") @@ -1237,6 +1237,8 @@ class Family(SpecFamily): else: self.uapi_header_name = self.ident_name + self.fn_prefix = fn_prefix if fn_prefix else f'{self.ident_name}-nl' + def resolve(self): self.resolve_up(super()) @@ -2911,12 +2913,12 @@ def print_kernel_op_table_fwd(family, cw, terminate): continue if 'do' in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-doit") + name = c_lower(f"{family.fn_prefix}-{op_name}-doit") cw.write_func_prot('int', name, ['struct sk_buff *skb', 'struct genl_info *info'], suffix=';') if 'dump' in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-dumpit") + name = c_lower(f"{family.fn_prefix}-{op_name}-dumpit") cw.write_func_prot('int', name, ['struct sk_buff *skb', 'struct netlink_callback *cb'], suffix=';') cw.nl() @@ -2942,7 +2944,7 @@ def print_kernel_op_table(family, cw): for x in op['dont-validate']])), ) for op_mode in ['do', 'dump']: if op_mode in op: - name = c_lower(f"{family.ident_name}-nl-{op_name}-{op_mode}it") + name = c_lower(f"{family.fn_prefix}-{op_name}-{op_mode}it") members.append((op_mode + 'it', name)) if family.kernel_policy == 'per-op': struct = Struct(family, op['attribute-set'], @@ -2980,7 +2982,7 @@ def print_kernel_op_table(family, cw): members.append(('validate', ' | '.join([c_upper('genl-dont-validate-' + x) for x in dont_validate])), ) - name = c_lower(f"{family.ident_name}-nl-{op_name}-{op_mode}it") + name = c_lower(f"{family.fn_prefix}-{op_name}-{op_mode}it") if 'pre' in op[op_mode]: members.append((cb_names[op_mode]['pre'], c_lower(op[op_mode]['pre']))) members.append((op_mode + 'it', name)) @@ -3402,6 +3404,7 @@ def main(): help='Do not overwrite the output file if the new output is identical to the old') parser.add_argument('--exclude-op', action='append', default=[]) parser.add_argument('-o', dest='out_file', type=str, default=None) + parser.add_argument('--function-prefix', dest='fn_prefix', type=str) args = parser.parse_args() if args.header is None: @@ -3410,7 +3413,7 @@ def main(): exclude_ops = [re.compile(expr) for expr in args.exclude_op] try: - parsed = Family(args.spec, exclude_ops) + parsed = Family(args.spec, exclude_ops, args.fn_prefix) if parsed.license != '((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)': print('Spec license:', parsed.license) print('License must be: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)') @@ -3430,11 +3433,16 @@ def main(): cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") - if args.exclude_op or args.user_header: + if args.exclude_op or args.user_header or args.fn_prefix: line = '' - line += ' --user-header '.join([''] + args.user_header) - line += ' --exclude-op '.join([''] + args.exclude_op) + if args.user_header: + line += ' --user-header '.join([''] + args.user_header) + if args.exclude_op: + line += ' --exclude-op '.join([''] + args.exclude_op) + if args.fn_prefix: + line += f' --function-prefix {args.fn_prefix}' cw.p(f'/* YNL-ARG{line} */') + cw.p('/* To regenerate run: tools/net/ynl/ynl-regen.sh */') cw.nl() if args.mode == 'uapi': diff --git a/tools/net/ynl/samples/.gitignore b/tools/net/ynl/samples/.gitignore index 7f5fca7682d7..05087ee323ba 100644 --- a/tools/net/ynl/samples/.gitignore +++ b/tools/net/ynl/samples/.gitignore @@ -7,3 +7,4 @@ rt-addr rt-link rt-route tc +tc-filter-add diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile index c9494a564da4..d76cbd41cbb1 100644 --- a/tools/net/ynl/samples/Makefile +++ b/tools/net/ynl/samples/Makefile @@ -19,6 +19,7 @@ include $(wildcard *.d) all: $(BINS) CFLAGS_page-pool=$(CFLAGS_netdev) +CFLAGS_tc-filter-add:=$(CFLAGS_tc) $(BINS): ../lib/ynl.a ../generated/protos.a $(SRCS) @echo -e '\tCC sample $@' diff --git a/tools/net/ynl/samples/tc-filter-add.c b/tools/net/ynl/samples/tc-filter-add.c new file mode 100644 index 000000000000..1f9cd3f62df6 --- /dev/null +++ b/tools/net/ynl/samples/tc-filter-add.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <string.h> +#include <stdlib.h> +#include <arpa/inet.h> +#include <linux/pkt_sched.h> +#include <linux/tc_act/tc_vlan.h> +#include <linux/tc_act/tc_gact.h> +#include <linux/if_ether.h> +#include <net/if.h> + +#include <ynl.h> + +#include "tc-user.h" + +#define TC_HANDLE (0xFFFF << 16) + +const char *vlan_act_name(struct tc_vlan *p) +{ + switch (p->v_action) { + case TCA_VLAN_ACT_POP: + return "pop"; + case TCA_VLAN_ACT_PUSH: + return "push"; + case TCA_VLAN_ACT_MODIFY: + return "modify"; + default: + break; + } + + return "not supported"; +} + +const char *gact_act_name(struct tc_gact *p) +{ + switch (p->action) { + case TC_ACT_SHOT: + return "drop"; + case TC_ACT_OK: + return "ok"; + case TC_ACT_PIPE: + return "pipe"; + default: + break; + } + + return "not supported"; +} + +static void print_vlan(struct tc_act_vlan_attrs *vlan) +{ + printf("%s ", vlan_act_name(vlan->parms)); + if (vlan->_present.push_vlan_id) + printf("id %u ", vlan->push_vlan_id); + if (vlan->_present.push_vlan_protocol) + printf("protocol %#x ", ntohs(vlan->push_vlan_protocol)); + if (vlan->_present.push_vlan_priority) + printf("priority %u ", vlan->push_vlan_priority); +} + +static void print_gact(struct tc_act_gact_attrs *gact) +{ + struct tc_gact *p = gact->parms; + + printf("%s ", gact_act_name(p)); +} + +static void flower_print(struct tc_flower_attrs *flower, const char *kind) +{ + struct tc_act_attrs *a; + unsigned int i; + + printf("%s:\n", kind); + + if (flower->_present.key_vlan_id) + printf(" vlan_id: %u\n", flower->key_vlan_id); + if (flower->_present.key_vlan_prio) + printf(" vlan_prio: %u\n", flower->key_vlan_prio); + if (flower->_present.key_num_of_vlans) + printf(" num_of_vlans: %u\n", flower->key_num_of_vlans); + + for (i = 0; i < flower->_count.act; i++) { + a = &flower->act[i]; + printf("action order: %i %s ", i + 1, a->kind); + if (a->options._present.vlan) + print_vlan(&a->options.vlan); + else if (a->options._present.gact) + print_gact(&a->options.gact); + printf("\n"); + } + printf("\n"); +} + +static void tc_filter_print(struct tc_gettfilter_rsp *f) +{ + struct tc_options_msg *opt = &f->options; + + if (opt->_present.flower) + flower_print(&opt->flower, f->kind); + else if (f->_len.kind) + printf("%s pref %u proto: %#x\n", f->kind, + (f->_hdr.tcm_info >> 16), + ntohs(TC_H_MIN(f->_hdr.tcm_info))); +} + +static int tc_filter_add(struct ynl_sock *ys, int ifi) +{ + struct tc_newtfilter_req *req; + struct tc_act_attrs *acts; + struct tc_vlan p = { + .action = TC_ACT_PIPE, + .v_action = TCA_VLAN_ACT_PUSH + }; + __u16 flags = NLM_F_REQUEST | NLM_F_EXCL | NLM_F_CREATE; + int ret; + + req = tc_newtfilter_req_alloc(); + if (!req) { + fprintf(stderr, "tc_newtfilter_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + acts = tc_act_attrs_alloc(3); + if (!acts) { + fprintf(stderr, "tc_act_attrs_alloc\n"); + tc_newtfilter_req_free(req); + return -1; + } + memset(acts, 0, sizeof(*acts) * 3); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_hdr.tcm_info = TC_H_MAKE(1 << 16, htons(ETH_P_8021Q)); + req->chain = 0; + + tc_newtfilter_req_set_nlflags(req, flags); + tc_newtfilter_req_set_kind(req, "flower"); + tc_newtfilter_req_set_options_flower_key_vlan_id(req, 100); + tc_newtfilter_req_set_options_flower_key_vlan_prio(req, 5); + tc_newtfilter_req_set_options_flower_key_num_of_vlans(req, 3); + + __tc_newtfilter_req_set_options_flower_act(req, acts, 3); + + /* Skip action at index 0 because in TC, the action array + * index starts at 1, with each index defining the action's + * order. In contrast, in YNL indexed arrays start at index 0. + */ + tc_act_attrs_set_kind(&acts[1], "vlan"); + tc_act_attrs_set_options_vlan_parms(&acts[1], &p, sizeof(p)); + tc_act_attrs_set_options_vlan_push_vlan_id(&acts[1], 200); + tc_act_attrs_set_kind(&acts[2], "vlan"); + tc_act_attrs_set_options_vlan_parms(&acts[2], &p, sizeof(p)); + tc_act_attrs_set_options_vlan_push_vlan_id(&acts[2], 300); + + tc_newtfilter_req_set_options_flower_flags(req, 0); + tc_newtfilter_req_set_options_flower_key_eth_type(req, htons(0x8100)); + + ret = tc_newtfilter(ys, req); + if (ret) + fprintf(stderr, "tc_newtfilter: %s\n", ys->err.msg); + + tc_newtfilter_req_free(req); + + return ret; +} + +static int tc_filter_show(struct ynl_sock *ys, int ifi) +{ + struct tc_gettfilter_req_dump *req; + struct tc_gettfilter_list *rsp; + + req = tc_gettfilter_req_dump_alloc(); + if (!req) { + fprintf(stderr, "tc_gettfilter_req_dump_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_present.chain = 1; + req->chain = 0; + + rsp = tc_gettfilter_dump(ys, req); + tc_gettfilter_req_dump_free(req); + if (!rsp) { + fprintf(stderr, "YNL: %s\n", ys->err.msg); + return -1; + } + + if (ynl_dump_empty(rsp)) + fprintf(stderr, "Error: no filters reported\n"); + else + ynl_dump_foreach(rsp, flt) tc_filter_print(flt); + + tc_gettfilter_list_free(rsp); + + return 0; +} + +static int tc_filter_del(struct ynl_sock *ys, int ifi) +{ + struct tc_deltfilter_req *req; + __u16 flags = NLM_F_REQUEST; + int ret; + + req = tc_deltfilter_req_alloc(); + if (!req) { + fprintf(stderr, "tc_deltfilter_req_alloc failedq\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + req->_hdr.tcm_info = TC_H_MAKE(1 << 16, htons(ETH_P_8021Q)); + tc_deltfilter_req_set_nlflags(req, flags); + + ret = tc_deltfilter(ys, req); + if (ret) + fprintf(stderr, "tc_deltfilter failed: %s\n", ys->err.msg); + + tc_deltfilter_req_free(req); + + return ret; +} + +static int tc_clsact_add(struct ynl_sock *ys, int ifi) +{ + struct tc_newqdisc_req *req; + __u16 flags = NLM_F_REQUEST | NLM_F_EXCL | NLM_F_CREATE; + int ret; + + req = tc_newqdisc_req_alloc(); + if (!req) { + fprintf(stderr, "tc_newqdisc_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_CLSACT; + req->_hdr.tcm_handle = TC_HANDLE; + tc_newqdisc_req_set_nlflags(req, flags); + tc_newqdisc_req_set_kind(req, "clsact"); + + ret = tc_newqdisc(ys, req); + if (ret) + fprintf(stderr, "tc_newqdisc failed: %s\n", ys->err.msg); + + tc_newqdisc_req_free(req); + + return ret; +} + +static int tc_clsact_del(struct ynl_sock *ys, int ifi) +{ + struct tc_delqdisc_req *req; + __u16 flags = NLM_F_REQUEST; + int ret; + + req = tc_delqdisc_req_alloc(); + if (!req) { + fprintf(stderr, "tc_delqdisc_req_alloc failed\n"); + return -1; + } + memset(req, 0, sizeof(*req)); + + req->_hdr.tcm_ifindex = ifi; + req->_hdr.tcm_parent = TC_H_CLSACT; + req->_hdr.tcm_handle = TC_HANDLE; + tc_delqdisc_req_set_nlflags(req, flags); + + ret = tc_delqdisc(ys, req); + if (ret) + fprintf(stderr, "tc_delqdisc failed: %s\n", ys->err.msg); + + tc_delqdisc_req_free(req); + + return ret; +} + +static int tc_filter_config(struct ynl_sock *ys, int ifi) +{ + int ret = 0; + + if (tc_filter_add(ys, ifi)) + return -1; + + ret = tc_filter_show(ys, ifi); + + if (tc_filter_del(ys, ifi)) + return -1; + + return ret; +} + +int main(int argc, char **argv) +{ + struct ynl_error yerr; + struct ynl_sock *ys; + int ifi, ret = 0; + + if (argc < 2) { + fprintf(stderr, "Usage: %s <interface_name>\n", argv[0]); + return 1; + } + ifi = if_nametoindex(argv[1]); + if (!ifi) { + perror("if_nametoindex"); + return 1; + } + + ys = ynl_sock_create(&ynl_tc_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return 1; + } + + if (tc_clsact_add(ys, ifi)) { + ret = 2; + goto err_destroy; + } + + if (tc_filter_config(ys, ifi)) + ret = 3; + + if (tc_clsact_del(ys, ifi)) + ret = 4; + +err_destroy: + ynl_sock_destroy(ys); + return ret; +} diff --git a/tools/net/ynl/tests/Makefile b/tools/net/ynl/tests/Makefile new file mode 100644 index 000000000000..c1df2e001255 --- /dev/null +++ b/tools/net/ynl/tests/Makefile @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for YNL tests + +TESTS := \ + test_ynl_cli.sh \ + test_ynl_ethtool.sh \ +# end of TESTS + +all: $(TESTS) + +run_tests: + @for test in $(TESTS); do \ + ./$$test; \ + done + +install: $(TESTS) + @mkdir -p $(DESTDIR)/usr/bin + @mkdir -p $(DESTDIR)/usr/share/kselftest + @cp ../../../testing/selftests/kselftest/ktap_helpers.sh $(DESTDIR)/usr/share/kselftest/ + @for test in $(TESTS); do \ + name=$$(basename $$test .sh); \ + sed -e 's|^ynl=.*|ynl="ynl"|' \ + -e 's|^ynl_ethtool=.*|ynl_ethtool="ynl-ethtool"|' \ + -e 's|KSELFTEST_KTAP_HELPERS=.*|KSELFTEST_KTAP_HELPERS="/usr/share/kselftest/ktap_helpers.sh"|' \ + $$test > $(DESTDIR)/usr/bin/$$name; \ + chmod +x $(DESTDIR)/usr/bin/$$name; \ + done + +clean distclean: + @# Nothing to clean + +.PHONY: all install clean run_tests diff --git a/tools/net/ynl/tests/config b/tools/net/ynl/tests/config new file mode 100644 index 000000000000..339f1309c03f --- /dev/null +++ b/tools/net/ynl/tests/config @@ -0,0 +1,6 @@ +CONFIG_DUMMY=m +CONFIG_INET_DIAG=y +CONFIG_IPV6=y +CONFIG_NET_NS=y +CONFIG_NETDEVSIM=m +CONFIG_VETH=m diff --git a/tools/net/ynl/tests/test_ynl_cli.sh b/tools/net/ynl/tests/test_ynl_cli.sh new file mode 100755 index 000000000000..7c0722a08117 --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_cli.sh @@ -0,0 +1,327 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL CLI functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck source=../../../testing/selftests/kselftest/ktap_helpers.sh +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl path for direct execution, can be overridden by make install +ynl="../pyynl/cli.py" + +readonly NSIM_ID="1338" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-$(mktemp -u XXXXXX)" +TESTS_NO=0 + +# Test listing available families +cli_list_families() +{ + if $ynl --list-families &>/dev/null; then + ktap_test_pass "YNL CLI list families" + else + ktap_test_fail "YNL CLI list families" + fi +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test netdev family operations (dev-get, queue-get) +cli_netdev_ops() +{ + local dev_output + local ifindex + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + dev_output=$(ip netns exec "$testns" $ynl --family netdev \ + --do dev-get --json "{\"ifindex\": $ifindex}" 2>/dev/null) + + if ! echo "$dev_output" | grep -q "ifindex"; then + ktap_test_fail "YNL CLI netdev operations (netdev dev-get output missing ifindex)" + return + fi + + if ! ip netns exec "$testns" $ynl --family netdev \ + --dump queue-get --json "{\"ifindex\": $ifindex}" &>/dev/null; then + ktap_test_fail "YNL CLI netdev operations (failed to get netdev queue info)" + return + fi + + ktap_test_pass "YNL CLI netdev operations" +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test ethtool family operations (rings-get, linkinfo-get) +cli_ethtool_ops() +{ + local rings_output + local linkinfo_output + + rings_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do rings-get --json "{\"header\": {\"dev-name\": \"$NSIM_DEV_NAME\"}}" 2>/dev/null) + + if ! echo "$rings_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool rings-get output missing header)" + return + fi + + linkinfo_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do linkinfo-get --json "{\"header\": {\"dev-name\": \"$VETH_A\"}}" 2>/dev/null) + + if ! echo "$linkinfo_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool linkinfo-get output missing header)" + return + fi + + ktap_test_pass "YNL CLI ethtool operations" +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-route family operations +cli_rt_route_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-route"; then + ktap_test_skip "YNL CLI rt-route operations (rt-route family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add route: 192.0.2.0/24 dev $dev scope link + if ! ip netns exec "$testns" $ynl --family rt-route --do newroute --create \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-route operations (failed to add route)" + return + fi + + local route_output + route_output=$(ip netns exec "$testns" $ynl --family rt-route --dump getroute 2>/dev/null) + if echo "$route_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-route operations" + else + ktap_test_fail "YNL CLI rt-route operations (failed to verify route)" + fi + + ip netns exec "$testns" $ynl --family rt-route --do delroute \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-addr family operations +cli_rt_addr_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-addr"; then + ktap_test_skip "YNL CLI rt-addr operations (rt-addr family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + if ! ip netns exec "$testns" $ynl --family rt-addr --do newaddr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-addr operations (failed to add address)" + return + fi + + local addr_output + addr_output=$(ip netns exec "$testns" $ynl --family rt-addr --dump getaddr 2>/dev/null) + if echo "$addr_output" | grep -q "192.0.2.100"; then + ktap_test_pass "YNL CLI rt-addr operations" + else + ktap_test_fail "YNL CLI rt-addr operations (failed to verify address)" + fi + + ip netns exec "$testns" $ynl --family rt-addr --do deladdr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-link family operations +cli_rt_link_ops() +{ + if ! $ynl --list-families 2>/dev/null | grep -q "rt-link"; then + ktap_test_skip "YNL CLI rt-link operations (rt-link family not available)" + return + fi + + if ! ip netns exec "$testns" $ynl --family rt-link --do newlink --create \ + --json "{\"ifname\": \"dummy0\", \"linkinfo\": {\"kind\": \"dummy\"}}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-link operations (failed to add link)" + return + fi + + local link_output + link_output=$(ip netns exec "$testns" $ynl --family rt-link --dump getlink 2>/dev/null) + if echo "$link_output" | grep -q "$NSIM_DEV_NAME" && echo "$link_output" | grep -q "dummy0"; then + ktap_test_pass "YNL CLI rt-link operations" + else + ktap_test_fail "YNL CLI rt-link operations (failed to verify link)" + fi + + ip netns exec "$testns" $ynl --family rt-link --do dellink \ + --json "{\"ifname\": \"dummy0\"}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-neigh family operations +cli_rt_neigh_ops() +{ + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-neigh"; then + ktap_test_skip "YNL CLI rt-neigh operations (rt-neigh family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add neighbor: 192.0.2.1 dev nsim1338 lladdr 11:22:33:44:55:66 PERMANENT + if ! ip netns exec "$testns" $ynl --family rt-neigh --do newneigh --create \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2, \"ndm-state\": 128}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-neigh operations (failed to add neighbor)" + fi + + local neigh_output + neigh_output=$(ip netns exec "$testns" $ynl --family rt-neigh --dump getneigh 2>/dev/null) + if echo "$neigh_output" | grep -q "192.0.2.1"; then + ktap_test_pass "YNL CLI rt-neigh operations" + else + ktap_test_fail "YNL CLI rt-neigh operations (failed to verify neighbor)" + fi + + ip netns exec "$testns" $ynl --family rt-neigh --do delneigh \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test rt-rule family operations +cli_rt_rule_ops() +{ + if ! $ynl --list-families 2>/dev/null | grep -q "rt-rule"; then + ktap_test_skip "YNL CLI rt-rule operations (rt-rule family not available)" + return + fi + + # Add rule: from 192.0.2.0/24 lookup 100 none + if ! ip netns exec "$testns" $ynl --family rt-rule --do newrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-rule operations (failed to add rule)" + return + fi + + local rule_output + rule_output=$(ip netns exec "$testns" $ynl --family rt-rule --dump getrule 2>/dev/null) + if echo "$rule_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-rule operations" + else + ktap_test_fail "YNL CLI rt-rule operations (failed to verify rule)" + fi + + ip netns exec "$testns" $ynl --family rt-rule --do delrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null +} +TESTS_NO=$((TESTS_NO + 1)) + +# Test nlctrl family operations +cli_nlctrl_ops() +{ + local family_output + + if ! family_output=$($ynl --family nlctrl \ + --do getfamily --json "{\"family-name\": \"netdev\"}" 2>/dev/null); then + ktap_test_fail "YNL CLI nlctrl getfamily (failed to get nlctrl family info)" + return + fi + + if ! echo "$family_output" | grep -q "family-name"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-name)" + return + fi + + if ! echo "$family_output" | grep -q "family-id"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-id)" + return + fi + + ktap_test_pass "YNL CLI nlctrl getfamily" +} +TESTS_NO=$((TESTS_NO + 1)) + +setup() +{ + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() +{ + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true +} + +# Check if ynl command is available +if ! command -v $ynl &>/dev/null && [[ ! -x $ynl ]]; then + ktap_skip_all "ynl command not found: $ynl" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +setup +ktap_set_plan "${TESTS_NO}" + +cli_list_families +cli_netdev_ops +cli_ethtool_ops +cli_rt_route_ops +cli_rt_addr_ops +cli_rt_link_ops +cli_rt_neigh_ops +cli_rt_rule_ops +cli_nlctrl_ops + +ktap_finished diff --git a/tools/net/ynl/tests/test_ynl_ethtool.sh b/tools/net/ynl/tests/test_ynl_ethtool.sh new file mode 100755 index 000000000000..b826269017f4 --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_ethtool.sh @@ -0,0 +1,222 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL ethtool functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck source=../../../testing/selftests/kselftest/ktap_helpers.sh +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl-ethtool path for direct execution, can be overridden by make install +ynl_ethtool="../pyynl/ethtool.py" + +readonly NSIM_ID="1337" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-ethtool-$(mktemp -u XXXXXX)" +TESTS_NO=0 + +# Uses veth device as netdevsim doesn't support basic ethtool device info +ethtool_device_info() +{ + local info_output + + info_output=$(ip netns exec "$testns" $ynl_ethtool "$VETH_A" 2>/dev/null) + + if ! echo "$info_output" | grep -q "Settings for"; then + ktap_test_fail "YNL ethtool device info (device info output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool device info" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_statistics() +{ + local stats_output + + stats_output=$(ip netns exec "$testns" $ynl_ethtool --statistics "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$stats_output" | grep -q -E "(NIC statistics|packets|bytes)"; then + ktap_test_fail "YNL ethtool statistics (statistics output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool statistics" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_ring_params() +{ + local ring_output + + ring_output=$(ip netns exec "$testns" $ynl_ethtool --show-ring "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ring_output" | grep -q -E "(Ring parameters|RX|TX)"; then + ktap_test_fail "YNL ethtool ring parameters (ring parameters output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-ring "$NSIM_DEV_NAME" rx 64 2>/dev/null; then + ktap_test_fail "YNL ethtool ring parameters (set-ring command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool ring parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_coalesce_params() +{ + if ! ip netns exec "$testns" $ynl_ethtool --show-coalesce "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (failed to get coalesce parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-coalesce "$NSIM_DEV_NAME" rx-usecs 50 2>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (set-coalesce command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool coalesce parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_pause_params() +{ + if ! ip netns exec "$testns" $ynl_ethtool --show-pause "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (failed to get pause parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-pause "$NSIM_DEV_NAME" tx 1 rx 1 2>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (set-pause command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool pause parameters (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_features_info() +{ + local features_output + + features_output=$(ip netns exec "$testns" $ynl_ethtool --show-features "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$features_output" | grep -q -E "(Features|offload)"; then + ktap_test_fail "YNL ethtool features info (features output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool features info (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_channels_info() +{ + local channels_output + + channels_output=$(ip netns exec "$testns" $ynl_ethtool --show-channels "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$channels_output" | grep -q -E "(Channel|Combined|RX|TX)"; then + ktap_test_fail "YNL ethtool channels info (channels output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-channels "$NSIM_DEV_NAME" combined-count 1 2>/dev/null; then + ktap_test_fail "YNL ethtool channels info (set-channels command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool channels info (show/set)" +} +TESTS_NO=$((TESTS_NO + 1)) + +ethtool_time_stamping() +{ + local ts_output + + ts_output=$(ip netns exec "$testns" $ynl_ethtool --show-time-stamping "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ts_output" | grep -q -E "(Time stamping|timestamping|SOF_TIMESTAMPING)"; then + ktap_test_fail "YNL ethtool time stamping (time stamping output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool time stamping" +} +TESTS_NO=$((TESTS_NO + 1)) + +setup() +{ + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() +{ + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true +} + +# Check if ynl-ethtool command is available +if ! command -v $ynl_ethtool &>/dev/null && [[ ! -x $ynl_ethtool ]]; then + ktap_skip_all "ynl-ethtool command not found: $ynl_ethtool" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +setup +ktap_set_plan "${TESTS_NO}" + +ethtool_device_info +ethtool_statistics +ethtool_ring_params +ethtool_coalesce_params +ethtool_pause_params +ethtool_features_info +ethtool_channels_info +ethtool_time_stamping + +ktap_finished diff --git a/tools/net/ynl/ynltool/.gitignore b/tools/net/ynl/ynltool/.gitignore index f38848dbb0d3..690d399c921a 100644 --- a/tools/net/ynl/ynltool/.gitignore +++ b/tools/net/ynl/ynltool/.gitignore @@ -1 +1,2 @@ ynltool +*.d diff --git a/tools/net/ynl/ynltool/Makefile b/tools/net/ynl/ynltool/Makefile index 5edaa0f93237..f5b1de32daa5 100644 --- a/tools/net/ynl/ynltool/Makefile +++ b/tools/net/ynl/ynltool/Makefile @@ -31,7 +31,7 @@ Q = @ $(YNLTOOL): ../libynl.a $(OBJS) $(Q)echo -e "\tLINK $@" - $(Q)$(CC) $(CFLAGS) -o $@ $(OBJS) ../libynl.a -lmnl -lm + $(Q)$(CC) $(CFLAGS) -o $@ $(OBJS) ../libynl.a -lm %.o: %.c ../libynl.a $(Q)echo -e "\tCC $@" diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 5700516aa84a..2dd5f5a60568 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -354,9 +354,6 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt -FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl -FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl - CORE_CFLAGS += -fno-omit-frame-pointer CORE_CFLAGS += -Wall CORE_CFLAGS += -Wextra @@ -930,6 +927,8 @@ ifdef BUILD_NONDISTRO ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd -lopcodes + FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl + FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl else # we are on a system that requires -liberty and (maybe) -lz # to link against -lbfd; test each case individually here diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index 078634461df2..e8962c985d34 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -1867,6 +1867,7 @@ static int __cmd_report(bool display_info) eops.sample = process_sample_event; eops.comm = perf_event__process_comm; eops.mmap = perf_event__process_mmap; + eops.mmap2 = perf_event__process_mmap2; eops.namespaces = perf_event__process_namespaces; eops.tracing_data = perf_event__process_tracing_data; session = perf_session__new(&data, &eops); @@ -2023,6 +2024,7 @@ static int __cmd_contention(int argc, const char **argv) eops.sample = process_sample_event; eops.comm = perf_event__process_comm; eops.mmap = perf_event__process_mmap; + eops.mmap2 = perf_event__process_mmap2; eops.tracing_data = perf_event__process_tracing_data; perf_env__init(&host_env); diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index 7248a74ca2a3..6dd90519f45c 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -13,15 +13,18 @@ cleanup() { rm -f ${perfdata} rm -f ${result} rm -f ${errout} - trap - EXIT TERM INT + trap - EXIT TERM INT ERR } trap_cleanup() { + if (( $? == 139 )); then #SIGSEGV + err=1 + fi echo "Unexpected signal in ${FUNCNAME[1]}" cleanup exit ${err} } -trap trap_cleanup EXIT TERM INT +trap trap_cleanup EXIT TERM INT ERR check() { if [ "$(id -u)" != 0 ]; then @@ -145,7 +148,7 @@ test_aggr_cgroup() fi # the perf lock contention output goes to the stderr - perf lock con -a -b -g -E 1 -q -- perf bench sched messaging -p > /dev/null 2> ${result} + perf lock con -a -b --lock-cgroup -E 1 -q -- perf bench sched messaging -p > /dev/null 2> ${result} if [ "$(cat "${result}" | wc -l)" != "1" ]; then echo "[Fail] BPF result count is not 1:" "$(cat "${result}" | wc -l)" err=1 @@ -271,7 +274,7 @@ test_cgroup_filter() return fi - perf lock con -a -b -g -E 1 -F wait_total -q -- perf bench sched messaging -p > /dev/null 2> ${result} + perf lock con -a -b --lock-cgroup -E 1 -F wait_total -q -- perf bench sched messaging -p > /dev/null 2> ${result} if [ "$(cat "${result}" | wc -l)" != "1" ]; then echo "[Fail] BPF result should have a cgroup result:" "$(cat "${result}")" err=1 @@ -279,7 +282,7 @@ test_cgroup_filter() fi cgroup=$(cat "${result}" | awk '{ print $3 }') - perf lock con -a -b -g -E 1 -G "${cgroup}" -q -- perf bench sched messaging -p > /dev/null 2> ${result} + perf lock con -a -b --lock-cgroup -E 1 -G "${cgroup}" -q -- perf bench sched messaging -p > /dev/null 2> ${result} if [ "$(cat "${result}" | wc -l)" != "1" ]; then echo "[Fail] BPF result should have a result with cgroup filter:" "$(cat "${cgroup}")" err=1 @@ -338,4 +341,5 @@ test_aggr_task_stack_filter test_cgroup_filter test_csv_output +cleanup exit ${err} diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 4f2a6e10ed5c..4e12be579140 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1022,12 +1022,9 @@ static int write_bpf_prog_info(struct feat_fd *ff, down_read(&env->bpf_progs.lock); - if (env->bpf_progs.infos_cnt == 0) - goto out; - ret = do_write(ff, &env->bpf_progs.infos_cnt, sizeof(env->bpf_progs.infos_cnt)); - if (ret < 0) + if (ret < 0 || env->bpf_progs.infos_cnt == 0) goto out; root = &env->bpf_progs.infos; @@ -1067,13 +1064,10 @@ static int write_bpf_btf(struct feat_fd *ff, down_read(&env->bpf_progs.lock); - if (env->bpf_progs.btfs_cnt == 0) - goto out; - ret = do_write(ff, &env->bpf_progs.btfs_cnt, sizeof(env->bpf_progs.btfs_cnt)); - if (ret < 0) + if (ret < 0 || env->bpf_progs.btfs_cnt == 0) goto out; root = &env->bpf_progs.btfs; diff --git a/tools/perf/util/libbfd.c b/tools/perf/util/libbfd.c index 01147fbf73b3..6434c2dccd4a 100644 --- a/tools/perf/util/libbfd.c +++ b/tools/perf/util/libbfd.c @@ -38,6 +38,39 @@ struct a2l_data { asymbol **syms; }; +static bool perf_bfd_lock(void *bfd_mutex) +{ + mutex_lock(bfd_mutex); + return true; +} + +static bool perf_bfd_unlock(void *bfd_mutex) +{ + mutex_unlock(bfd_mutex); + return true; +} + +static void perf_bfd_init(void) +{ + static struct mutex bfd_mutex; + + mutex_init_recursive(&bfd_mutex); + + if (bfd_init() != BFD_INIT_MAGIC) { + pr_err("Error initializing libbfd\n"); + return; + } + if (!bfd_thread_init(perf_bfd_lock, perf_bfd_unlock, &bfd_mutex)) + pr_err("Error initializing libbfd threading\n"); +} + +static void ensure_bfd_init(void) +{ + static pthread_once_t bfd_init_once = PTHREAD_ONCE_INIT; + + pthread_once(&bfd_init_once, perf_bfd_init); +} + static int bfd_error(const char *string) { const char *errmsg; @@ -132,6 +165,7 @@ static struct a2l_data *addr2line_init(const char *path) bfd *abfd; struct a2l_data *a2l = NULL; + ensure_bfd_init(); abfd = bfd_openr(path, NULL); if (abfd == NULL) return NULL; @@ -288,6 +322,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) bfd *abfd; u64 start, len; + ensure_bfd_init(); abfd = bfd_openr(debugfile, NULL); if (!abfd) return -1; @@ -393,6 +428,7 @@ int libbfd__read_build_id(const char *filename, struct build_id *bid, bool block if (fd < 0) return -1; + ensure_bfd_init(); abfd = bfd_fdopenr(filename, /*target=*/NULL, fd); if (!abfd) return -1; @@ -421,6 +457,7 @@ int libbfd_filename__read_debuglink(const char *filename, char *debuglink, asection *section; bfd *abfd; + ensure_bfd_init(); abfd = bfd_openr(filename, NULL); if (!abfd) return -1; @@ -480,6 +517,7 @@ int symbol__disassemble_bpf_libbfd(struct symbol *sym __maybe_unused, memset(tpath, 0, sizeof(tpath)); perf_exe(tpath, sizeof(tpath)); + ensure_bfd_init(); bfdf = bfd_openr(tpath, NULL); if (bfdf == NULL) abort(); diff --git a/tools/perf/util/mutex.c b/tools/perf/util/mutex.c index bca7f0717f35..7aa1f3f55a7d 100644 --- a/tools/perf/util/mutex.c +++ b/tools/perf/util/mutex.c @@ -17,7 +17,7 @@ static void check_err(const char *fn, int err) #define CHECK_ERR(err) check_err(__func__, err) -static void __mutex_init(struct mutex *mtx, bool pshared) +static void __mutex_init(struct mutex *mtx, bool pshared, bool recursive) { pthread_mutexattr_t attr; @@ -27,21 +27,27 @@ static void __mutex_init(struct mutex *mtx, bool pshared) /* In normal builds enable error checking, such as recursive usage. */ CHECK_ERR(pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ERRORCHECK)); #endif + if (recursive) + CHECK_ERR(pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)); if (pshared) CHECK_ERR(pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED)); - CHECK_ERR(pthread_mutex_init(&mtx->lock, &attr)); CHECK_ERR(pthread_mutexattr_destroy(&attr)); } void mutex_init(struct mutex *mtx) { - __mutex_init(mtx, /*pshared=*/false); + __mutex_init(mtx, /*pshared=*/false, /*recursive=*/false); } void mutex_init_pshared(struct mutex *mtx) { - __mutex_init(mtx, /*pshared=*/true); + __mutex_init(mtx, /*pshared=*/true, /*recursive=*/false); +} + +void mutex_init_recursive(struct mutex *mtx) +{ + __mutex_init(mtx, /*pshared=*/false, /*recursive=*/true); } void mutex_destroy(struct mutex *mtx) diff --git a/tools/perf/util/mutex.h b/tools/perf/util/mutex.h index 38458f00846f..70232d8d094f 100644 --- a/tools/perf/util/mutex.h +++ b/tools/perf/util/mutex.h @@ -104,6 +104,8 @@ void mutex_init(struct mutex *mtx); * process-private attribute. */ void mutex_init_pshared(struct mutex *mtx); +/* Initializes a mutex that may be recursively held on the same thread. */ +void mutex_init_recursive(struct mutex *mtx); void mutex_destroy(struct mutex *mtx); void mutex_lock(struct mutex *mtx) EXCLUSIVE_LOCK_FUNCTION(*mtx); diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index fcd2f9bf78c9..558839e3c185 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -50,6 +50,7 @@ CONFIG_IPV6_SIT=y CONFIG_IPV6_TUNNEL=y CONFIG_KEYS=y CONFIG_LIRC=y +CONFIG_LIVEPATCH=y CONFIG_LWTUNNEL=y CONFIG_MODULE_SIG=y CONFIG_MODULE_SRCVERSION_ALL=y @@ -111,6 +112,8 @@ CONFIG_IP6_NF_FILTER=y CONFIG_NF_NAT=y CONFIG_PACKET=y CONFIG_RC_CORE=y +CONFIG_SAMPLES=y +CONFIG_SAMPLE_LIVEPATCH=m CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_SYN_COOKIES=y diff --git a/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c b/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c new file mode 100644 index 000000000000..72aa5376c30e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "testing_helpers.h" +#include "livepatch_trampoline.skel.h" + +static int load_livepatch(void) +{ + char path[4096]; + + /* CI will set KBUILD_OUTPUT */ + snprintf(path, sizeof(path), "%s/samples/livepatch/livepatch-sample.ko", + getenv("KBUILD_OUTPUT") ? : "../../../.."); + + return load_module(path, env_verbosity > VERBOSE_NONE); +} + +static void unload_livepatch(void) +{ + /* Disable the livepatch before unloading the module */ + system("echo 0 > /sys/kernel/livepatch/livepatch_sample/enabled"); + + unload_module("livepatch_sample", env_verbosity > VERBOSE_NONE); +} + +static void read_proc_cmdline(void) +{ + char buf[4096]; + int fd, ret; + + fd = open("/proc/cmdline", O_RDONLY); + if (!ASSERT_OK_FD(fd, "open /proc/cmdline")) + return; + + ret = read(fd, buf, sizeof(buf)); + if (!ASSERT_GT(ret, 0, "read /proc/cmdline")) + goto out; + + ASSERT_OK(strncmp(buf, "this has been live patched", 26), "strncmp"); + +out: + close(fd); +} + +static void __test_livepatch_trampoline(bool fexit_first) +{ + struct livepatch_trampoline *skel = NULL; + int err; + + skel = livepatch_trampoline__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + goto out; + + skel->bss->my_pid = getpid(); + + if (!fexit_first) { + /* fentry program is loaded first by default */ + err = livepatch_trampoline__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + } else { + /* Manually load fexit program first. */ + skel->links.fexit_cmdline = bpf_program__attach(skel->progs.fexit_cmdline); + if (!ASSERT_OK_PTR(skel->links.fexit_cmdline, "attach_fexit")) + goto out; + + skel->links.fentry_cmdline = bpf_program__attach(skel->progs.fentry_cmdline); + if (!ASSERT_OK_PTR(skel->links.fentry_cmdline, "attach_fentry")) + goto out; + } + + read_proc_cmdline(); + + ASSERT_EQ(skel->bss->fentry_hit, 1, "fentry_hit"); + ASSERT_EQ(skel->bss->fexit_hit, 1, "fexit_hit"); +out: + livepatch_trampoline__destroy(skel); +} + +void test_livepatch_trampoline(void) +{ + int retry_cnt = 0; + +retry: + if (load_livepatch()) { + if (retry_cnt) { + ASSERT_OK(1, "load_livepatch"); + goto out; + } + /* + * Something else (previous run of the same test?) loaded + * the KLP module. Unload the KLP module and retry. + */ + unload_livepatch(); + retry_cnt++; + goto retry; + } + + if (test__start_subtest("fentry_first")) + __test_livepatch_trampoline(false); + + if (test__start_subtest("fexit_first")) + __test_livepatch_trampoline(true); +out: + unload_livepatch(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c index f8eb7f9d4fd2..8fade8bdc451 100644 --- a/tools/testing/selftests/bpf/prog_tests/mptcp.c +++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c @@ -6,11 +6,13 @@ #include <netinet/in.h> #include <test_progs.h> #include <unistd.h> +#include <errno.h> #include "cgroup_helpers.h" #include "network_helpers.h" #include "mptcp_sock.skel.h" #include "mptcpify.skel.h" #include "mptcp_subflow.skel.h" +#include "mptcp_sockmap.skel.h" #define NS_TEST "mptcp_ns" #define ADDR_1 "10.0.1.1" @@ -436,6 +438,142 @@ close_cgroup: close(cgroup_fd); } +/* Test sockmap on MPTCP server handling non-mp-capable clients. */ +static void test_sockmap_with_mptcp_fallback(struct mptcp_sockmap *skel) +{ + int listen_fd = -1, client_fd1 = -1, client_fd2 = -1; + int server_fd1 = -1, server_fd2 = -1, sent, recvd; + char snd[9] = "123456789"; + char rcv[10]; + + /* start server with MPTCP enabled */ + listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0); + if (!ASSERT_OK_FD(listen_fd, "sockmap-fb:start_mptcp_server")) + return; + + skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd)); + skel->bss->sk_index = 0; + /* create client without MPTCP enabled */ + client_fd1 = connect_to_fd_opts(listen_fd, NULL); + if (!ASSERT_OK_FD(client_fd1, "sockmap-fb:connect_to_fd")) + goto end; + + server_fd1 = accept(listen_fd, NULL, 0); + skel->bss->sk_index = 1; + client_fd2 = connect_to_fd_opts(listen_fd, NULL); + if (!ASSERT_OK_FD(client_fd2, "sockmap-fb:connect_to_fd")) + goto end; + + server_fd2 = accept(listen_fd, NULL, 0); + /* test normal redirect behavior: data sent by client_fd1 can be + * received by client_fd2 + */ + skel->bss->redirect_idx = 1; + sent = send(client_fd1, snd, sizeof(snd), 0); + if (!ASSERT_EQ(sent, sizeof(snd), "sockmap-fb:send(client_fd1)")) + goto end; + + /* try to recv more bytes to avoid truncation check */ + recvd = recv(client_fd2, rcv, sizeof(rcv), 0); + if (!ASSERT_EQ(recvd, sizeof(snd), "sockmap-fb:recv(client_fd2)")) + goto end; + +end: + if (client_fd1 >= 0) + close(client_fd1); + if (client_fd2 >= 0) + close(client_fd2); + if (server_fd1 >= 0) + close(server_fd1); + if (server_fd2 >= 0) + close(server_fd2); + close(listen_fd); +} + +/* Test sockmap rejection of MPTCP sockets - both server and client sides. */ +static void test_sockmap_reject_mptcp(struct mptcp_sockmap *skel) +{ + int listen_fd = -1, server_fd = -1, client_fd1 = -1; + int err, zero = 0; + + /* start server with MPTCP enabled */ + listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0); + if (!ASSERT_OK_FD(listen_fd, "start_mptcp_server")) + return; + + skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd)); + skel->bss->sk_index = 0; + /* create client with MPTCP enabled */ + client_fd1 = connect_to_fd(listen_fd, 0); + if (!ASSERT_OK_FD(client_fd1, "connect_to_fd client_fd1")) + goto end; + + /* bpf_sock_map_update() called from sockops should reject MPTCP sk */ + if (!ASSERT_EQ(skel->bss->helper_ret, -EOPNOTSUPP, "should reject")) + goto end; + + server_fd = accept(listen_fd, NULL, 0); + err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map), + &zero, &server_fd, BPF_NOEXIST); + if (!ASSERT_EQ(err, -EOPNOTSUPP, "server should be disallowed")) + goto end; + + /* MPTCP client should also be disallowed */ + err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map), + &zero, &client_fd1, BPF_NOEXIST); + if (!ASSERT_EQ(err, -EOPNOTSUPP, "client should be disallowed")) + goto end; +end: + if (client_fd1 >= 0) + close(client_fd1); + if (server_fd >= 0) + close(server_fd); + close(listen_fd); +} + +static void test_mptcp_sockmap(void) +{ + struct mptcp_sockmap *skel; + struct netns_obj *netns; + int cgroup_fd, err; + + cgroup_fd = test__join_cgroup("/mptcp_sockmap"); + if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_sockmap")) + return; + + skel = mptcp_sockmap__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_sockmap")) + goto close_cgroup; + + skel->links.mptcp_sockmap_inject = + bpf_program__attach_cgroup(skel->progs.mptcp_sockmap_inject, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.mptcp_sockmap_inject, "attach sockmap")) + goto skel_destroy; + + err = bpf_prog_attach(bpf_program__fd(skel->progs.mptcp_sockmap_redirect), + bpf_map__fd(skel->maps.sock_map), + BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach stream verdict")) + goto skel_destroy; + + netns = netns_new(NS_TEST, true); + if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_sockmap")) + goto skel_destroy; + + if (endpoint_init("subflow") < 0) + goto close_netns; + + test_sockmap_with_mptcp_fallback(skel); + test_sockmap_reject_mptcp(skel); + +close_netns: + netns_free(netns); +skel_destroy: + mptcp_sockmap__destroy(skel); +close_cgroup: + close(cgroup_fd); +} + void test_mptcp(void) { if (test__start_subtest("base")) @@ -444,4 +582,6 @@ void test_mptcp(void) test_mptcpify(); if (test__start_subtest("subflow")) test_subflow(); + if (test__start_subtest("sockmap")) + test_mptcp_sockmap(); } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c new file mode 100644 index 000000000000..c9efdd2a5b18 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "stacktrace_ips.skel.h" + +#ifdef __x86_64__ +static int check_stacktrace_ips(int fd, __u32 key, int cnt, ...) +{ + __u64 ips[PERF_MAX_STACK_DEPTH]; + struct ksyms *ksyms = NULL; + int i, err = 0; + va_list args; + + /* sorted by addr */ + ksyms = load_kallsyms_local(); + if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_local")) + return -1; + + /* unlikely, but... */ + if (!ASSERT_LT(cnt, PERF_MAX_STACK_DEPTH, "check_max")) + return -1; + + err = bpf_map_lookup_elem(fd, &key, ips); + if (err) + goto out; + + /* + * Compare all symbols provided via arguments with stacktrace ips, + * and their related symbol addresses.t + */ + va_start(args, cnt); + + for (i = 0; i < cnt; i++) { + unsigned long val; + struct ksym *ksym; + + val = va_arg(args, unsigned long); + ksym = ksym_search_local(ksyms, ips[i]); + if (!ASSERT_OK_PTR(ksym, "ksym_search_local")) + break; + ASSERT_EQ(ksym->addr, val, "stack_cmp"); + } + + va_end(args); + +out: + free_kallsyms_local(ksyms); + return err; +} + +static void test_stacktrace_ips_kprobe_multi(bool retprobe) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts, + .retprobe = retprobe + ); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct stacktrace_ips *skel; + + skel = stacktrace_ips__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load")) + return; + + if (!skel->kconfig->CONFIG_UNWINDER_ORC) { + test__skip(); + goto cleanup; + } + + skel->links.kprobe_multi_test = bpf_program__attach_kprobe_multi_opts( + skel->progs.kprobe_multi_test, + "bpf_testmod_stacktrace_test", &opts); + if (!ASSERT_OK_PTR(skel->links.kprobe_multi_test, "bpf_program__attach_kprobe_multi_opts")) + goto cleanup; + + trigger_module_test_read(1); + + load_kallsyms(); + + check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4, + ksym_get_addr("bpf_testmod_stacktrace_test_3"), + ksym_get_addr("bpf_testmod_stacktrace_test_2"), + ksym_get_addr("bpf_testmod_stacktrace_test_1"), + ksym_get_addr("bpf_testmod_test_read")); + +cleanup: + stacktrace_ips__destroy(skel); +} + +static void test_stacktrace_ips_raw_tp(void) +{ + __u32 info_len = sizeof(struct bpf_prog_info); + LIBBPF_OPTS(bpf_test_run_opts, topts); + struct bpf_prog_info info = {}; + struct stacktrace_ips *skel; + __u64 bpf_prog_ksym = 0; + int err; + + skel = stacktrace_ips__open_and_load(); + if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load")) + return; + + if (!skel->kconfig->CONFIG_UNWINDER_ORC) { + test__skip(); + goto cleanup; + } + + skel->links.rawtp_test = bpf_program__attach_raw_tracepoint( + skel->progs.rawtp_test, + "bpf_testmod_test_read"); + if (!ASSERT_OK_PTR(skel->links.rawtp_test, "bpf_program__attach_raw_tracepoint")) + goto cleanup; + + /* get bpf program address */ + info.jited_ksyms = ptr_to_u64(&bpf_prog_ksym); + info.nr_jited_ksyms = 1; + err = bpf_prog_get_info_by_fd(bpf_program__fd(skel->progs.rawtp_test), + &info, &info_len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + goto cleanup; + + trigger_module_test_read(1); + + load_kallsyms(); + + check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 2, + bpf_prog_ksym, + ksym_get_addr("bpf_trace_run2")); + +cleanup: + stacktrace_ips__destroy(skel); +} + +static void __test_stacktrace_ips(void) +{ + if (test__start_subtest("kprobe_multi")) + test_stacktrace_ips_kprobe_multi(false); + if (test__start_subtest("kretprobe_multi")) + test_stacktrace_ips_kprobe_multi(true); + if (test__start_subtest("raw_tp")) + test_stacktrace_ips_raw_tp(); +} +#else +static void __test_stacktrace_ips(void) +{ + test__skip(); +} +#endif + +void test_stacktrace_ips(void) +{ + __test_stacktrace_ips(); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 164640db3a29..b1e509b231cd 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -99,13 +99,13 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_retransmit_timer.expires; + timer_expires = sp->tcp_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_retransmit_timer.expires; - } else if (timer_pending(&sp->sk_timer)) { + timer_expires = sp->tcp_retransmit_timer.expires; + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sp->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = bpf_jiffies64(); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index 591c703f5032..dbc7166aee91 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -99,13 +99,13 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp, icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; - timer_expires = icsk->icsk_retransmit_timer.expires; + timer_expires = sp->tcp_retransmit_timer.expires; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; - timer_expires = icsk->icsk_retransmit_timer.expires; - } else if (timer_pending(&sp->sk_timer)) { + timer_expires = sp->tcp_retransmit_timer.expires; + } else if (timer_pending(&icsk->icsk_keepalive_timer)) { timer_active = 2; - timer_expires = sp->sk_timer.expires; + timer_expires = icsk->icsk_keepalive_timer.expires; } else { timer_active = 0; timer_expires = bpf_jiffies64(); diff --git a/tools/testing/selftests/bpf/progs/iters_looping.c b/tools/testing/selftests/bpf/progs/iters_looping.c index 05fa5ce7fc59..d00fd570255a 100644 --- a/tools/testing/selftests/bpf/progs/iters_looping.c +++ b/tools/testing/selftests/bpf/progs/iters_looping.c @@ -161,3 +161,56 @@ int simplest_loop(void *ctx) return 0; } + +__used +static void iterator_with_diff_stack_depth(int x) +{ + struct bpf_iter_num iter; + + asm volatile ( + "if r1 == 42 goto 0f;" + "*(u64 *)(r10 - 128) = 0;" + "0:" + /* create iterator */ + "r1 = %[iter];" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + /* consume next item */ + "r1 = %[iter];" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "goto 1b;" + "2:" + /* destroy iterator */ + "r1 = %[iter];" + "call %[bpf_iter_num_destroy];" + : + : __imm_ptr(iter), ITER_HELPERS + : __clobber_common, "r6" + ); +} + +SEC("socket") +__success +__naked int widening_stack_size_bug(void *ctx) +{ + /* + * Depending on iterator_with_diff_stack_depth() parameter value, + * subprogram stack depth is either 8 or 128 bytes. Arrange values so + * that it is 128 on a first call and 8 on a second. This triggered a + * bug in verifier's widen_imprecise_scalars() logic. + */ + asm volatile ( + "r6 = 0;" + "r1 = 0;" + "1:" + "call iterator_with_diff_stack_depth;" + "r1 = 42;" + "r6 += 1;" + "if r6 < 2 goto 1b;" + "r0 = 0;" + "exit;" + ::: __clobber_all); +} diff --git a/tools/testing/selftests/bpf/progs/livepatch_trampoline.c b/tools/testing/selftests/bpf/progs/livepatch_trampoline.c new file mode 100644 index 000000000000..15579d5bcd91 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/livepatch_trampoline.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int fentry_hit; +int fexit_hit; +int my_pid; + +SEC("fentry/cmdline_proc_show") +int BPF_PROG(fentry_cmdline) +{ + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + fentry_hit = 1; + return 0; +} + +SEC("fexit/cmdline_proc_show") +int BPF_PROG(fexit_cmdline) +{ + if (my_pid != (bpf_get_current_pid_tgid() >> 32)) + return 0; + + fexit_hit = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/mptcp_sockmap.c b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c new file mode 100644 index 000000000000..d4eef0cbadb9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +int sk_index; +int redirect_idx; +int trace_port; +int helper_ret; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); + __uint(max_entries, 100); +} sock_map SEC(".maps"); + +SEC("sockops") +int mptcp_sockmap_inject(struct bpf_sock_ops *skops) +{ + struct bpf_sock *sk; + + /* only accept specified connection */ + if (skops->local_port != trace_port || + skops->op != BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) + return 1; + + sk = skops->sk; + if (!sk) + return 1; + + /* update sk handler */ + helper_ret = bpf_sock_map_update(skops, &sock_map, &sk_index, BPF_NOEXIST); + + return 1; +} + +SEC("sk_skb/stream_verdict") +int mptcp_sockmap_redirect(struct __sk_buff *skb) +{ + /* redirect skb to the sk under sock_map[redirect_idx] */ + return bpf_sk_redirect_map(skb, &sock_map, redirect_idx, 0); +} diff --git a/tools/testing/selftests/bpf/progs/stacktrace_ips.c b/tools/testing/selftests/bpf/progs/stacktrace_ips.c new file mode 100644 index 000000000000..a96c8150d7f5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/stacktrace_ips.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef PERF_MAX_STACK_DEPTH +#define PERF_MAX_STACK_DEPTH 127 +#endif + +typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH]; + +struct { + __uint(type, BPF_MAP_TYPE_STACK_TRACE); + __uint(max_entries, 16384); + __type(key, __u32); + __type(value, stack_trace_t); +} stackmap SEC(".maps"); + +extern bool CONFIG_UNWINDER_ORC __kconfig __weak; + +/* + * This function is here to have CONFIG_UNWINDER_ORC + * used and added to object BTF. + */ +int unused(void) +{ + return CONFIG_UNWINDER_ORC ? 0 : 1; +} + +__u32 stack_key; + +SEC("kprobe.multi") +int kprobe_multi_test(struct pt_regs *ctx) +{ + stack_key = bpf_get_stackid(ctx, &stackmap, 0); + return 0; +} + +SEC("raw_tp/bpf_testmod_test_read") +int rawtp_test(void *ctx) +{ + /* Skip ebpf program entry in the stack. */ + stack_key = bpf_get_stackid(ctx, &stackmap, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/stream_fail.c b/tools/testing/selftests/bpf/progs/stream_fail.c index b4a0d0cc8ec8..3662515f0107 100644 --- a/tools/testing/selftests/bpf/progs/stream_fail.c +++ b/tools/testing/selftests/bpf/progs/stream_fail.c @@ -10,7 +10,7 @@ SEC("syscall") __failure __msg("Possibly NULL pointer passed") int stream_vprintk_null_arg(void *ctx) { - bpf_stream_vprintk(BPF_STDOUT, "", NULL, 0, NULL); + bpf_stream_vprintk_impl(BPF_STDOUT, "", NULL, 0, NULL); return 0; } @@ -18,7 +18,7 @@ SEC("syscall") __failure __msg("R3 type=scalar expected=") int stream_vprintk_scalar_arg(void *ctx) { - bpf_stream_vprintk(BPF_STDOUT, "", (void *)46, 0, NULL); + bpf_stream_vprintk_impl(BPF_STDOUT, "", (void *)46, 0, NULL); return 0; } @@ -26,7 +26,7 @@ SEC("syscall") __failure __msg("arg#1 doesn't point to a const string") int stream_vprintk_string_arg(void *ctx) { - bpf_stream_vprintk(BPF_STDOUT, ctx, NULL, 0, NULL); + bpf_stream_vprintk_impl(BPF_STDOUT, ctx, NULL, 0, NULL); return 0; } diff --git a/tools/testing/selftests/bpf/progs/task_work.c b/tools/testing/selftests/bpf/progs/task_work.c index 23217f06a3ec..663a80990f8f 100644 --- a/tools/testing/selftests/bpf/progs/task_work.c +++ b/tools/testing/selftests/bpf/progs/task_work.c @@ -66,7 +66,7 @@ int oncpu_hash_map(struct pt_regs *args) if (!work) return 0; - bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL); return 0; } @@ -80,7 +80,7 @@ int oncpu_array_map(struct pt_regs *args) work = bpf_map_lookup_elem(&arrmap, &key); if (!work) return 0; - bpf_task_work_schedule_signal(task, &work->tw, &arrmap, process_work, NULL); + bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, process_work, NULL); return 0; } @@ -102,6 +102,6 @@ int oncpu_lru_map(struct pt_regs *args) work = bpf_map_lookup_elem(&lrumap, &key); if (!work || work->data[0]) return 0; - bpf_task_work_schedule_resume(task, &work->tw, &lrumap, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, &work->tw, &lrumap, process_work, NULL); return 0; } diff --git a/tools/testing/selftests/bpf/progs/task_work_fail.c b/tools/testing/selftests/bpf/progs/task_work_fail.c index 77fe8f28facd..1270953fd092 100644 --- a/tools/testing/selftests/bpf/progs/task_work_fail.c +++ b/tools/testing/selftests/bpf/progs/task_work_fail.c @@ -53,7 +53,7 @@ int mismatch_map(struct pt_regs *args) work = bpf_map_lookup_elem(&arrmap, &key); if (!work) return 0; - bpf_task_work_schedule_resume(task, &work->tw, &hmap, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL); return 0; } @@ -65,7 +65,7 @@ int no_map_task_work(struct pt_regs *args) struct bpf_task_work tw; task = bpf_get_current_task_btf(); - bpf_task_work_schedule_resume(task, &tw, &hmap, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, &tw, &hmap, process_work, NULL); return 0; } @@ -76,7 +76,7 @@ int task_work_null(struct pt_regs *args) struct task_struct *task; task = bpf_get_current_task_btf(); - bpf_task_work_schedule_resume(task, NULL, &hmap, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, NULL, &hmap, process_work, NULL); return 0; } @@ -91,6 +91,6 @@ int map_null(struct pt_regs *args) work = bpf_map_lookup_elem(&arrmap, &key); if (!work) return 0; - bpf_task_work_schedule_resume(task, &work->tw, NULL, process_work, NULL); + bpf_task_work_schedule_resume_impl(task, &work->tw, NULL, process_work, NULL); return 0; } diff --git a/tools/testing/selftests/bpf/progs/task_work_stress.c b/tools/testing/selftests/bpf/progs/task_work_stress.c index 90fca06fff56..55e555f7f41b 100644 --- a/tools/testing/selftests/bpf/progs/task_work_stress.c +++ b/tools/testing/selftests/bpf/progs/task_work_stress.c @@ -51,8 +51,8 @@ int schedule_task_work(void *ctx) if (!work) return 0; } - err = bpf_task_work_schedule_signal(bpf_get_current_task_btf(), &work->tw, &hmap, - process_work, NULL); + err = bpf_task_work_schedule_signal_impl(bpf_get_current_task_btf(), &work->tw, &hmap, + process_work, NULL); if (err) __sync_fetch_and_add(&schedule_error, 1); else diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index 8eeebaa951f0..1669a7eeda26 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -417,6 +417,30 @@ noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d, return a + (long)b + c + d + (long)e + f + g + h + i + j + k; } +noinline void bpf_testmod_stacktrace_test(void) +{ + /* used for stacktrace test as attach function */ + asm volatile (""); +} + +noinline void bpf_testmod_stacktrace_test_3(void) +{ + bpf_testmod_stacktrace_test(); + asm volatile (""); +} + +noinline void bpf_testmod_stacktrace_test_2(void) +{ + bpf_testmod_stacktrace_test_3(); + asm volatile (""); +} + +noinline void bpf_testmod_stacktrace_test_1(void) +{ + bpf_testmod_stacktrace_test_2(); + asm volatile (""); +} + int bpf_testmod_fentry_ok; noinline ssize_t @@ -497,6 +521,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, 21, 22, 23, 24, 25, 26) != 231) goto out; + bpf_testmod_stacktrace_test_1(); + bpf_testmod_fentry_ok = 1; out: return -EIO; /* always fail */ diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore index 585ecb4d5dc4..3633c7a3ed65 100644 --- a/tools/testing/selftests/drivers/net/.gitignore +++ b/tools/testing/selftests/drivers/net/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only +gro napi_id_helper psp_responder diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 33f4816216ec..f5c71d993750 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -6,10 +6,12 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \ ../../net/lib.sh \ TEST_GEN_FILES := \ + gro \ napi_id_helper \ # end of TEST_GEN_FILES TEST_PROGS := \ + gro.py \ hds.py \ napi_id.py \ napi_threaded.py \ diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index cfc39f70635d..995b492f5bcb 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -57,7 +57,8 @@ #include <string.h> #include <unistd.h> -#include "../kselftest.h" +#include "../../kselftest.h" +#include "../../net/lib/ksft.h" #define DPORT 8000 #define SPORT 1500 @@ -1127,6 +1128,8 @@ static void gro_receiver(void) set_timeout(rxfd); bind_packetsocket(rxfd); + ksft_ready(); + memset(correct_payload, 0, sizeof(correct_payload)); if (strcmp(testname, "data") == 0) { diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py new file mode 100755 index 000000000000..ba83713bf7b5 --- /dev/null +++ b/tools/testing/selftests/drivers/net/gro.py @@ -0,0 +1,164 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +GRO (Generic Receive Offload) conformance tests. + +Validates that GRO coalescing works correctly by running the gro +binary in different configurations and checking for correct packet +coalescing behavior. + +Test cases: + - data: Data packets with same size/headers and correct seq numbers coalesce + - ack: Pure ACK packets do not coalesce + - flags: Packets with PSH, SYN, URG, RST flags do not coalesce + - tcp: Packets with incorrect checksum, non-consecutive seqno don't coalesce + - ip: Packets with different ECN, TTL, TOS, or IP options don't coalesce + - large: Packets larger than GRO_MAX_SIZE don't coalesce +""" + +import os +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import NetDrvEpEnv, KsftXfailEx +from lib.py import cmd, defer, bkg, ip +from lib.py import ksft_variants + + +def _resolve_dmac(cfg, ipver): + """ + Find the destination MAC address remote host should use to send packets + towards the local host. It may be a router / gateway address. + """ + + attr = "dmac" + ipver + # Cache the response across test cases + if hasattr(cfg, attr): + return getattr(cfg, attr) + + route = ip(f"-{ipver} route get {cfg.addr_v[ipver]}", + json=True, host=cfg.remote)[0] + gw = route.get("gateway") + # Local L2 segment, address directly + if not gw: + setattr(cfg, attr, cfg.dev['address']) + return getattr(cfg, attr) + + # ping to make sure neighbor is resolved, + # bind to an interface, for v6 the GW is likely link local + cmd(f"ping -c1 -W0 -I{cfg.remote_ifname} {gw}", host=cfg.remote) + + neigh = ip(f"neigh get {gw} dev {cfg.remote_ifname}", + json=True, host=cfg.remote)[0] + setattr(cfg, attr, neigh['lladdr']) + return getattr(cfg, attr) + + +def _write_defer_restore(cfg, path, val, defer_undo=False): + with open(path, "r", encoding="utf-8") as fp: + orig_val = fp.read().strip() + if str(val) == orig_val: + return + with open(path, "w", encoding="utf-8") as fp: + fp.write(val) + if defer_undo: + defer(_write_defer_restore, cfg, path, orig_val) + + +def _set_mtu_restore(dev, mtu, host): + if dev['mtu'] < mtu: + ip(f"link set dev {dev['ifname']} mtu {mtu}", host=host) + defer(ip, f"link set dev {dev['ifname']} mtu {dev['mtu']}", host=host) + + +def _setup(cfg, test_name): + """ Setup hardware loopback mode for GRO testing. """ + + if not hasattr(cfg, "bin_remote"): + cfg.bin_local = cfg.test_dir / "gro" + cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) + + # "large" test needs at least 4k MTU + if test_name == "large": + _set_mtu_restore(cfg.dev, 4096, None) + _set_mtu_restore(cfg.remote_dev, 4096, cfg.remote) + + flush_path = f"/sys/class/net/{cfg.ifname}/gro_flush_timeout" + irq_path = f"/sys/class/net/{cfg.ifname}/napi_defer_hard_irqs" + + _write_defer_restore(cfg, flush_path, "200000", defer_undo=True) + _write_defer_restore(cfg, irq_path, "10", defer_undo=True) + + try: + # Disable TSO for local tests + cfg.require_nsim() # will raise KsftXfailEx if not running on nsim + + cmd(f"ethtool -K {cfg.ifname} gro on tso off") + cmd(f"ethtool -K {cfg.remote_ifname} gro on tso off", host=cfg.remote) + except KsftXfailEx: + pass + +def _gro_variants(): + """Generator that yields all combinations of protocol and test types.""" + + for protocol in ["ipv4", "ipv6", "ipip"]: + for test_name in ["data", "ack", "flags", "tcp", "ip", "large"]: + yield protocol, test_name + + +@ksft_variants(_gro_variants()) +def test(cfg, protocol, test_name): + """Run a single GRO test with retries.""" + + ipver = "6" if protocol[-1] == "6" else "4" + cfg.require_ipver(ipver) + + _setup(cfg, test_name) + + base_cmd_args = [ + f"--{protocol}", + f"--dmac {_resolve_dmac(cfg, ipver)}", + f"--smac {cfg.remote_dev['address']}", + f"--daddr {cfg.addr_v[ipver]}", + f"--saddr {cfg.remote_addr_v[ipver]}", + f"--test {test_name}", + "--verbose" + ] + base_args = " ".join(base_cmd_args) + + # Each test is run 6 times to deflake, because given the receive timing, + # not all packets that should coalesce will be considered in the same flow + # on every try. + max_retries = 6 + for attempt in range(max_retries): + rx_cmd = f"{cfg.bin_local} {base_args} --rx --iface {cfg.ifname}" + tx_cmd = f"{cfg.bin_remote} {base_args} --iface {cfg.remote_ifname}" + + fail_now = attempt >= max_retries - 1 + + with bkg(rx_cmd, ksft_ready=True, exit_wait=True, + fail=fail_now) as rx_proc: + cmd(tx_cmd, host=cfg.remote) + + if rx_proc.ret == 0: + return + + ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# ')) + ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# ')) + + if test_name == "large" and os.environ.get("KSFT_MACHINE_SLOW"): + ksft_pr(f"Ignoring {protocol}/{test_name} failure due to slow environment") + return + + ksft_pr(f"Attempt {attempt + 1}/{max_retries} failed, retrying...") + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEpEnv(__file__) as cfg: + ksft_run(cases=[test], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore index 6942bf575497..46540468a775 100644 --- a/tools/testing/selftests/drivers/net/hw/.gitignore +++ b/tools/testing/selftests/drivers/net/hw/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only iou-zcrx ncdevmem +toeplitz diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 8133d1a0051c..7c819fdfa107 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -1,6 +1,21 @@ # SPDX-License-Identifier: GPL-2.0+ OR MIT -TEST_GEN_FILES = iou-zcrx +# Check if io_uring supports zero-copy receive +HAS_IOURING_ZCRX := $(shell \ + echo -e '#include <liburing.h>\n' \ + 'void *func = (void *)io_uring_register_ifq;\n' \ + 'int main() {return 0;}' | \ + $(CC) -luring -x c - -o /dev/null 2>&1 && echo y) + +ifeq ($(HAS_IOURING_ZCRX),y) +COND_GEN_FILES += iou-zcrx +else +$(warning excluding iouring tests, liburing not installed or too old) +endif + +TEST_GEN_FILES := \ + $(COND_GEN_FILES) \ +# end of TEST_GEN_FILES TEST_PROGS = \ csum.py \ @@ -21,6 +36,7 @@ TEST_PROGS = \ rss_ctx.py \ rss_flow_label.py \ rss_input_xfrm.py \ + toeplitz.py \ tso.py \ xsk_reconfig.py \ # @@ -38,7 +54,10 @@ TEST_INCLUDES := \ # # YNL files, must be before "include ..lib.mk" -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := \ + ncdevmem \ + toeplitz \ +# end of YNL_GEN_FILES TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) @@ -54,4 +73,6 @@ include ../../../net/ynl.mk include ../../../net/bpf.mk +ifeq ($(HAS_IOURING_ZCRX),y) $(OUTPUT)/iou-zcrx: LDLIBS += -luring +endif diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index fb010a48a5a1..0c61debf86fb 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -25,7 +25,7 @@ try: fd_read_timeout, ip, rand_port, wait_port_listen, wait_file from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ - ksft_setup + ksft_setup, ksft_variants, KsftNamedVariant from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none from drivers.net.lib.py import GenerateTraffic, Remote @@ -40,7 +40,7 @@ try: "wait_port_listen", "wait_file", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", - "ksft_setup", + "ksft_setup", "ksft_variants", "KsftNamedVariant", "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", "ksft_not_none", "ksft_not_none", diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index 9ba03164d73a..a4d04438c313 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -52,7 +52,11 @@ #include <sys/types.h> #include <unistd.h> -#include "../kselftest.h" +#include <ynl.h> +#include "ethtool-user.h" + +#include "../../../kselftest.h" +#include "../../../net/lib/ksft.h" #define TOEPLITZ_KEY_MIN_LEN 40 #define TOEPLITZ_KEY_MAX_LEN 60 @@ -64,6 +68,7 @@ #define FOUR_TUPLE_MAX_LEN ((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2)) #define RSS_MAX_CPUS (1 << 16) /* real constraint is PACKET_FANOUT_MAX */ +#define RSS_MAX_INDIR (1 << 16) #define RPS_MAX_CPUS 16UL /* must be a power of 2 */ @@ -101,6 +106,8 @@ struct ring_state { static unsigned int rx_irq_cpus[RSS_MAX_CPUS]; /* map from rxq to cpu */ static int rps_silo_to_cpu[RPS_MAX_CPUS]; static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN]; +static unsigned int rss_indir_tbl[RSS_MAX_INDIR]; +static unsigned int rss_indir_tbl_size; static struct ring_state rings[RSS_MAX_CPUS]; static inline uint32_t toeplitz(const unsigned char *four_tuple, @@ -129,7 +136,12 @@ static inline uint32_t toeplitz(const unsigned char *four_tuple, /* Compare computed cpu with arrival cpu from packet_fanout_cpu */ static void verify_rss(uint32_t rx_hash, int cpu) { - int queue = rx_hash % cfg_num_queues; + int queue; + + if (rss_indir_tbl_size) + queue = rss_indir_tbl[rx_hash % rss_indir_tbl_size]; + else + queue = rx_hash % cfg_num_queues; log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]); if (rx_irq_cpus[queue] != cpu) { @@ -482,6 +494,56 @@ static void parse_rps_bitmap(const char *arg) rps_silo_to_cpu[cfg_num_rps_cpus++] = i; } +static void read_rss_dev_info_ynl(void) +{ + struct ethtool_rss_get_req *req; + struct ethtool_rss_get_rsp *rsp; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_ethtool_family, NULL); + if (!ys) + error(1, errno, "ynl_sock_create failed"); + + req = ethtool_rss_get_req_alloc(); + if (!req) + error(1, errno, "ethtool_rss_get_req_alloc failed"); + + ethtool_rss_get_req_set_header_dev_name(req, cfg_ifname); + + rsp = ethtool_rss_get(ys, req); + if (!rsp) + error(1, ys->err.code, "YNL: %s", ys->err.msg); + + if (!rsp->_len.hkey) + error(1, 0, "RSS key not available for %s", cfg_ifname); + + if (rsp->_len.hkey < TOEPLITZ_KEY_MIN_LEN || + rsp->_len.hkey > TOEPLITZ_KEY_MAX_LEN) + error(1, 0, "RSS key length %u out of bounds [%u, %u]", + rsp->_len.hkey, TOEPLITZ_KEY_MIN_LEN, + TOEPLITZ_KEY_MAX_LEN); + + memcpy(toeplitz_key, rsp->hkey, rsp->_len.hkey); + + if (rsp->_count.indir > RSS_MAX_INDIR) + error(1, 0, "RSS indirection table too large (%u > %u)", + rsp->_count.indir, RSS_MAX_INDIR); + + /* If indir table not available we'll fallback to simple modulo math */ + if (rsp->_count.indir) { + memcpy(rss_indir_tbl, rsp->indir, + rsp->_count.indir * sizeof(rss_indir_tbl[0])); + rss_indir_tbl_size = rsp->_count.indir; + + log_verbose("RSS indirection table size: %u\n", + rss_indir_tbl_size); + } + + ethtool_rss_get_rsp_free(rsp); + ethtool_rss_get_req_free(req); + ynl_sock_destroy(ys); +} + static void parse_opts(int argc, char **argv) { static struct option long_options[] = { @@ -550,7 +612,7 @@ static void parse_opts(int argc, char **argv) } if (!have_toeplitz) - error(1, 0, "Must supply rss key ('-k')"); + read_rss_dev_info_ynl(); num_cpus = get_nprocs(); if (num_cpus > RSS_MAX_CPUS) @@ -576,6 +638,10 @@ int main(int argc, char **argv) fd_sink = setup_sink(); setup_rings(); + + /* Signal to test framework that we're ready to receive */ + ksft_ready(); + process_rings(); cleanup_rings(); diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py new file mode 100755 index 000000000000..d2db5ee9e358 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -0,0 +1,211 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Toeplitz Rx hashing test: + - rxhash (the hash value calculation itself); + - RSS mapping from rxhash to rx queue; + - RPS mapping from rxhash to cpu. +""" + +import glob +import os +import socket +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import NetDrvEpEnv, EthtoolFamily, NetdevFamily +from lib.py import cmd, bkg, rand_port, defer +from lib.py import ksft_in +from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx + +# "define" for the ID of the Toeplitz hash function +ETH_RSS_HASH_TOP = 1 + + +def _check_rps_and_rfs_not_configured(cfg): + """Verify that RPS is not already configured.""" + + for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): + with open(rps_file, "r", encoding="utf-8") as fp: + val = fp.read().strip() + if set(val) - {"0", ","}: + raise KsftSkipEx(f"RPS already configured on {rps_file}: {val}") + + rfs_file = "/proc/sys/net/core/rps_sock_flow_entries" + with open(rfs_file, "r", encoding="utf-8") as fp: + val = fp.read().strip() + if val != "0": + raise KsftSkipEx(f"RFS already configured {rfs_file}: {val}") + + +def _get_cpu_for_irq(irq): + with open(f"/proc/irq/{irq}/smp_affinity_list", "r", + encoding="utf-8") as fp: + data = fp.read().strip() + if "," in data or "-" in data: + raise KsftFailEx(f"IRQ{irq} is not mapped to a single core: {data}") + return int(data) + + +def _get_irq_cpus(cfg): + """ + Read the list of IRQs for the device Rx queues. + """ + queues = cfg.netnl.queue_get({"ifindex": cfg.ifindex}, dump=True) + napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True) + + # Remap into ID-based dicts + napis = {n["id"]: n for n in napis} + queues = {f"{q['type']}{q['id']}": q for q in queues} + + cpus = [] + for rx in range(9999): + name = f"rx{rx}" + if name not in queues: + break + cpus.append(_get_cpu_for_irq(napis[queues[name]["napi-id"]]["irq"])) + + return cpus + + +def _get_unused_cpus(cfg, count=2): + """ + Get CPUs that are not used by Rx queues. + Returns a list of at least 'count' CPU numbers. + """ + + # Get CPUs used by Rx queues + rx_cpus = set(_get_irq_cpus(cfg)) + + # Get total number of CPUs + num_cpus = os.cpu_count() + + # Find unused CPUs + unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus] + + if len(unused_cpus) < count: + raise KsftSkipEx(f"Need at {count} CPUs not used by Rx queues, found {len(unused_cpus)}") + + return unused_cpus[:count] + + +def _configure_rps(cfg, rps_cpus): + """Configure RPS for all Rx queues.""" + + mask = 0 + for cpu in rps_cpus: + mask |= (1 << cpu) + mask = hex(mask)[2:] + + # Set RPS bitmap for all rx queues + for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"): + with open(rps_file, "w", encoding="utf-8") as fp: + fp.write(mask) + + return mask + + +def _send_traffic(cfg, proto_flag, ipver, port): + """Send 20 packets of requested type.""" + + # Determine protocol and IP version for socat + if proto_flag == "-u": + proto = "UDP" + else: + proto = "TCP" + + baddr = f"[{cfg.addr_v['6']}]" if ipver == "6" else cfg.addr_v["4"] + + # Run socat in a loop to send traffic periodically + # Use sh -c with a loop similar to toeplitz_client.sh + socat_cmd = f""" + for i in `seq 20`; do + echo "msg $i" | socat -{ipver} -t 0.1 - {proto}:{baddr}:{port}; + sleep 0.001; + done + """ + + cmd(socat_cmd, shell=True, host=cfg.remote) + + +def _test_variants(): + for grp in ["", "rss", "rps"]: + for l4 in ["tcp", "udp"]: + for l3 in ["4", "6"]: + name = f"{l4}_ipv{l3}" + if grp: + name = f"{grp}_{name}" + yield KsftNamedVariant(name, "-" + l4[0], l3, grp) + + +@ksft_variants(_test_variants()) +def test(cfg, proto_flag, ipver, grp): + """Run a single toeplitz test.""" + + cfg.require_ipver(ipver) + + # Check that rxhash is enabled + ksft_in("receive-hashing: on", cmd(f"ethtool -k {cfg.ifname}").stdout) + + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # Make sure NIC is configured to use Toeplitz hash, and no key xfrm. + if rss.get('hfunc') != ETH_RSS_HASH_TOP or rss.get('input-xfrm'): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hfunc": ETH_RSS_HASH_TOP, + "input-xfrm": {}}) + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex}, + "hfunc": rss.get('hfunc'), + "input-xfrm": rss.get('input-xfrm', {}) + }) + + port = rand_port(socket.SOCK_DGRAM) + + toeplitz_path = cfg.test_dir / "toeplitz" + rx_cmd = [ + str(toeplitz_path), + "-" + ipver, + proto_flag, + "-d", str(port), + "-i", cfg.ifname, + "-T", "4000", + "-s", + "-v" + ] + + if grp: + _check_rps_and_rfs_not_configured(cfg) + if grp == "rss": + irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)]) + rx_cmd += ["-C", irq_cpus] + ksft_pr(f"RSS using CPUs: {irq_cpus}") + elif grp == "rps": + # Get CPUs not used by Rx queues and configure them for RPS + rps_cpus = _get_unused_cpus(cfg, count=2) + rps_mask = _configure_rps(cfg, rps_cpus) + defer(_configure_rps, cfg, []) + rx_cmd += ["-r", rps_mask] + ksft_pr(f"RPS using CPUs: {rps_cpus}, mask: {rps_mask}") + + # Run rx in background, it will exit once it has seen enough packets + with bkg(" ".join(rx_cmd), ksft_ready=True, exit_wait=True) as rx_proc: + while rx_proc.proc.poll() is None: + _send_traffic(cfg, proto_flag, ipver, port) + + # Check rx result + ksft_pr("Receiver output:") + ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# ')) + if rx_proc.stderr: + ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# ')) + + +def main() -> None: + """Ksft boilerplate main.""" + + with NetDrvEpEnv(__file__) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() + ksft_run(cases=[test], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py index b0c6300150fb..d9d035634a31 100644 --- a/tools/testing/selftests/drivers/net/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py @@ -25,7 +25,7 @@ try: fd_read_timeout, ip, rand_port, wait_port_listen, wait_file from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \ - ksft_setup + ksft_setup, ksft_variants, KsftNamedVariant from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \ ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none @@ -38,7 +38,7 @@ try: "wait_port_listen", "wait_file", "KsftSkipEx", "KsftFailEx", "KsftXfailEx", "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run", - "ksft_setup", + "ksft_setup", "ksft_variants", "KsftNamedVariant", "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt", "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt", "ksft_not_none", "ksft_not_none"] diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 01be3d9b9720..8b644fd84ff2 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -168,6 +168,8 @@ class NetDrvEpEnv(NetDrvEnvBase): # resolve remote interface name self.remote_ifname = self.resolve_remote_ifc() + self.remote_dev = ip("-d link show dev " + self.remote_ifname, + host=self.remote, json=True)[0] self._required_cmd = {} diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh index a3446b569976..2022f3061738 100755 --- a/tools/testing/selftests/drivers/net/netcons_basic.sh +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -28,8 +28,6 @@ OUTPUT_FILE="/tmp/${TARGET}" # Check for basic system dependency and exit if not found check_for_dependencies -# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) -echo "6 5" > /proc/sys/kernel/printk # Remove the namespace, interfaces and netconsole target on exit trap cleanup EXIT @@ -39,6 +37,9 @@ do for IP_VERSION in "ipv6" "ipv4" do echo "Running with target mode: ${FORMAT} (${IP_VERSION})" + # Set current loglevel to KERN_INFO(6), and default to + # KERN_NOTICE(5) + echo "6 5" > /proc/sys/kernel/printk # Create one namespace and two interfaces set_network "${IP_VERSION}" # Create a dynamic target for netconsole diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netcons_overflow.sh index 29bad56448a2..06089643b771 100755 --- a/tools/testing/selftests/drivers/net/netcons_overflow.sh +++ b/tools/testing/selftests/drivers/net/netcons_overflow.sh @@ -15,7 +15,7 @@ SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh # This is coming from netconsole code. Check for it in drivers/net/netconsole.c -MAX_USERDATA_ITEMS=16 +MAX_USERDATA_ITEMS=256 # Function to create userdata entries function create_userdata_max_entries() { diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 030762b203d7..1b529ccaf050 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -3,7 +3,8 @@ lib_dir=$(dirname $0)/../../../net/forwarding -ALL_TESTS="fw_flash_test params_test regions_test reload_test \ +ALL_TESTS="fw_flash_test params_test \ + params_default_test regions_test reload_test \ netns_reload_test resource_test dev_info_test \ empty_reporter_test dummy_reporter_test rate_test" NUM_NETIFS=0 @@ -78,17 +79,28 @@ fw_flash_test() param_get() { local name=$1 + local attr=${2:-value} + local cmode=${3:-driverinit} cmd_jq "devlink dev param show $DL_HANDLE name $name -j" \ - '.[][][].values[] | select(.cmode == "driverinit").value' + '.[][][].values[] | select(.cmode == "'"$cmode"'").'"$attr" } param_set() { local name=$1 local value=$2 + local cmode=${3:-driverinit} - devlink dev param set $DL_HANDLE name $name cmode driverinit value $value + devlink dev param set $DL_HANDLE name $name cmode $cmode value $value +} + +param_set_default() +{ + local name=$1 + local cmode=${2:-driverinit} + + devlink dev param set $DL_HANDLE name $name default cmode $cmode } check_value() @@ -97,12 +109,18 @@ check_value() local phase_name=$2 local expected_param_value=$3 local expected_debugfs_value=$4 + local cmode=${5:-driverinit} local value + local attr="value" - value=$(param_get $name) - check_err $? "Failed to get $name param value" + if [[ "$phase_name" == *"default"* ]]; then + attr="default" + fi + + value=$(param_get $name $attr $cmode) + check_err $? "Failed to get $name param $attr" [ "$value" == "$expected_param_value" ] - check_err $? "Unexpected $phase_name $name param value" + check_err $? "Unexpected $phase_name $name param $attr" value=$(<$DEBUGFS_DIR/$name) check_err $? "Failed to get $name debugfs value" [ "$value" == "$expected_debugfs_value" ] @@ -135,6 +153,92 @@ params_test() log_test "params test" } +value_to_debugfs() +{ + local value=$1 + + case "$value" in + true) + echo "Y" + ;; + false) + echo "N" + ;; + *) + echo "$value" + ;; + esac +} + +test_default() +{ + local param_name=$1 + local new_value=$2 + local expected_default=$3 + local cmode=${4:-driverinit} + local default_debugfs + local new_debugfs + local expected_debugfs + + default_debugfs=$(value_to_debugfs $expected_default) + new_debugfs=$(value_to_debugfs $new_value) + + expected_debugfs=$default_debugfs + check_value $param_name initial-default $expected_default $expected_debugfs $cmode + + param_set $param_name $new_value $cmode + check_err $? "Failed to set $param_name to $new_value" + + expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$new_debugfs" || echo "$default_debugfs") + check_value $param_name post-set $new_value $expected_debugfs $cmode + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device" + + expected_debugfs=$new_debugfs + check_value $param_name post-reload-new-value $new_value $expected_debugfs $cmode + + param_set_default $param_name $cmode + check_err $? "Failed to set $param_name to default" + + expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$default_debugfs" || echo "$new_debugfs") + check_value $param_name post-set-default $expected_default $expected_debugfs $cmode + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device" + + expected_debugfs=$default_debugfs + check_value $param_name post-reload-default $expected_default $expected_debugfs $cmode +} + +params_default_test() +{ + RET=0 + + if ! devlink dev param help 2>&1 | grep -q "value VALUE | default"; then + echo "SKIP: devlink cli missing default feature" + return + fi + + # Remove side effects of previous tests. Use plain param_set, because + # param_set_default is a feature under test here. + param_set max_macs 32 driverinit + check_err $? "Failed to reset max_macs to default value" + param_set test1 true driverinit + check_err $? "Failed to reset test1 to default value" + param_set test2 1234 runtime + check_err $? "Failed to reset test2 to default value" + + devlink dev reload $DL_HANDLE + check_err $? "Failed to reload device for clean state" + + test_default max_macs 16 32 driverinit + test_default test1 false true driverinit + test_default test2 100 1234 runtime + + log_test "params default test" +} + check_region_size() { local name=$1 diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py index a148004e1c36..e54df158dfe9 100755 --- a/tools/testing/selftests/drivers/net/xdp.py +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -12,6 +12,7 @@ from dataclasses import dataclass from enum import Enum from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_ne, ksft_pr +from lib.py import KsftNamedVariant, ksft_variants from lib.py import KsftFailEx, NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import bkg, cmd, rand_port, wait_port_listen @@ -672,7 +673,18 @@ def test_xdp_native_adjst_head_shrnk_data(cfg): _validate_res(res, offset_lst, pkt_sz_lst) -def _test_xdp_native_ifc_stats(cfg, act): +@ksft_variants([ + KsftNamedVariant("pass", XDPAction.PASS), + KsftNamedVariant("drop", XDPAction.DROP), + KsftNamedVariant("tx", XDPAction.TX), +]) +def test_xdp_native_qstats(cfg, act): + """ + Send 1000 messages. Expect XDP action specified in @act. + Make sure the packets were counted to interface level qstats + (Rx, and Tx if act is TX). + """ + cfg.require_cmd("socat") bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) @@ -687,9 +699,12 @@ def _test_xdp_native_ifc_stats(cfg, act): "/dev/null" # Listener runs on "remote" in case of XDP_TX rx_host = cfg.remote if act == XDPAction.TX else None - # We want to spew 2000 packets quickly, bash seems to do a good enough job - tx_udp = f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ - "for i in `seq 2000`; do echo a >&5; done; exec 5>&-" + # We want to spew 1000 packets quickly, bash seems to do a good enough job + # Each reopening of the socket gives us a differenot local port (for RSS) + tx_udp = "for _ in `seq 20`; do " \ + f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ + "for i in `seq 50`; do echo a >&5; done; " \ + "exec 5>&-; done" cfg.wait_hw_stats_settle() # Qstats have more clearly defined semantics than rtnetlink. @@ -704,11 +719,11 @@ def _test_xdp_native_ifc_stats(cfg, act): cfg.wait_hw_stats_settle() after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] - ksft_ge(after['rx-packets'] - before['rx-packets'], 2000) + expected_pkts = 1000 + ksft_ge(after['rx-packets'] - before['rx-packets'], expected_pkts) if act == XDPAction.TX: - ksft_ge(after['tx-packets'] - before['tx-packets'], 2000) + ksft_ge(after['tx-packets'] - before['tx-packets'], expected_pkts) - expected_pkts = 2000 stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) ksft_eq(stats[XDPStats.RX.value], expected_pkts, "XDP RX stats mismatch") if act == XDPAction.TX: @@ -730,30 +745,6 @@ def _test_xdp_native_ifc_stats(cfg, act): ksft_ge(after['tx-packets'], before['tx-packets']) -def test_xdp_native_qstats_pass(cfg): - """ - Send 2000 messages, expect XDP_PASS, make sure the packets were counted - to interface level qstats (Rx). - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.PASS) - - -def test_xdp_native_qstats_drop(cfg): - """ - Send 2000 messages, expect XDP_DROP, make sure the packets were counted - to interface level qstats (Rx). - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.DROP) - - -def test_xdp_native_qstats_tx(cfg): - """ - Send 2000 messages, expect XDP_TX, make sure the packets were counted - to interface level qstats (Rx and Tx) - """ - _test_xdp_native_ifc_stats(cfg, XDPAction.TX) - - def main(): """ Main function to execute the XDP tests. @@ -778,9 +769,7 @@ def main(): test_xdp_native_adjst_tail_shrnk_data, test_xdp_native_adjst_head_grow_data, test_xdp_native_adjst_head_shrnk_data, - test_xdp_native_qstats_pass, - test_xdp_native_qstats_drop, - test_xdp_native_qstats_tx, + test_xdp_native_qstats, ], args=(cfg,)) ksft_exit() diff --git a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc index c62165fabd0c..cfa16aa1f39a 100644 --- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -20,6 +20,10 @@ sample_events() { echo 0 > tracing_on echo 0 > events/enable +# Clear functions caused by page cache; run sample_events twice +sample_events +sample_events + echo "Get the most frequently calling function" echo > trace sample_events diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index 9e3be2ee7f1b..f917b4c4c943 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1758,10 +1758,15 @@ int main(int argc, char *argv[]) uffd_test_ops = mem_type->mem_ops; uffd_test_case_ops = test->test_case_ops; - if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) { gopts.page_size = default_huge_page_size(); - else + if (gopts.page_size == 0) { + uffd_test_skip("huge page size is 0, feature missing?"); + continue; + } + } else { gopts.page_size = psize(); + } /* Ensure we have at least 2 pages */ gopts.nr_pages = MAX(UFFD_TEST_MEM_SIZE, gopts.page_size * 2) @@ -1776,12 +1781,6 @@ int main(int argc, char *argv[]) continue; uffd_test_start("%s on %s", test->name, mem_type->name); - if ((mem_type->mem_flag == MEM_HUGETLB || - mem_type->mem_flag == MEM_HUGETLB_PRIVATE) && - (default_huge_page_size() == 0)) { - uffd_test_skip("huge page size is 0, feature missing?"); - continue; - } if (!uffd_feature_supported(test)) { uffd_test_skip("feature missing"); continue; diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 439101b518ee..6930fe926c58 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -4,10 +4,8 @@ bind_timewait bind_wildcard busy_poller cmsg_sender -diag_uid epoll_busy_poll fin_ack_lat -gro hwtstamp_config io_uring_zerocopy_tx ioam6_parser @@ -18,7 +16,6 @@ ipv6_flowlabel ipv6_flowlabel_mgr ipv6_fragmentation log.txt -msg_oob msg_zerocopy netlink-dumps nettest @@ -35,9 +32,6 @@ reuseport_bpf_numa reuseport_dualstack rxtimestamp sctp_hello -scm_inq -scm_pidfd -scm_rights sk_bind_sendto_listen sk_connect_zero_addr sk_so_peek_off @@ -56,7 +50,6 @@ tcp_port_share tfo timestamping tls -toeplitz tools tun txring_overwrite @@ -64,4 +57,3 @@ txtimestamp udpgso udpgso_bench_rx udpgso_bench_tx -unix_connect diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b5127e968108..b66ba04f19d9 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -38,7 +38,6 @@ TEST_PROGS := \ fq_band_pktlimit.sh \ gre_gso.sh \ gre_ipv6_lladdr.sh \ - gro.sh \ icmp.sh \ icmp_redirect.sh \ io_uring_zerocopy_tx.sh \ @@ -121,8 +120,6 @@ TEST_PROGS := \ # end of TEST_PROGS TEST_PROGS_EXTENDED := \ - toeplitz.sh \ - toeplitz_client.sh \ xfrm_policy_add_speed.sh \ # end of TEST_PROGS_EXTENDED @@ -130,7 +127,6 @@ TEST_GEN_FILES := \ bind_bhash \ cmsg_sender \ fin_ack_lat \ - gro \ hwtstamp_config \ io_uring_zerocopy_tx \ ioam6_parser \ @@ -159,7 +155,6 @@ TEST_GEN_FILES := \ tcp_mmap \ tfo \ timestamping \ - toeplitz \ txring_overwrite \ txtimestamp \ udpgso \ @@ -193,8 +188,6 @@ TEST_FILES := \ in_netns.sh \ lib.sh \ settings \ - setup_loopback.sh \ - setup_veth.sh \ # end of TEST_FILES # YNL files, must be before "include ..lib.mk" diff --git a/tools/testing/selftests/net/af_unix/.gitignore b/tools/testing/selftests/net/af_unix/.gitignore new file mode 100644 index 000000000000..240b26740c9e --- /dev/null +++ b/tools/testing/selftests/net/af_unix/.gitignore @@ -0,0 +1,8 @@ +diag_uid +msg_oob +scm_inq +scm_pidfd +scm_rights +so_peek_off +unix_connect +unix_connreset diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index de805cbbdf69..3cd677b72072 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -6,7 +6,9 @@ TEST_GEN_PROGS := \ scm_inq \ scm_pidfd \ scm_rights \ + so_peek_off \ unix_connect \ + unix_connreset \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/so_peek_off.c b/tools/testing/selftests/net/af_unix/so_peek_off.c new file mode 100644 index 000000000000..86e7b0fb522d --- /dev/null +++ b/tools/testing/selftests/net/af_unix/so_peek_off.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include <stdlib.h> +#include <unistd.h> + +#include <sys/socket.h> + +#include "../../kselftest_harness.h" + +FIXTURE(so_peek_off) +{ + int fd[2]; /* 0: sender, 1: receiver */ +}; + +FIXTURE_VARIANT(so_peek_off) +{ + int type; +}; + +FIXTURE_VARIANT_ADD(so_peek_off, stream) +{ + .type = SOCK_STREAM, +}; + +FIXTURE_VARIANT_ADD(so_peek_off, dgram) +{ + .type = SOCK_DGRAM, +}; + +FIXTURE_VARIANT_ADD(so_peek_off, seqpacket) +{ + .type = SOCK_SEQPACKET, +}; + +FIXTURE_SETUP(so_peek_off) +{ + struct timeval timeout = { + .tv_sec = 5, + .tv_usec = 0, + }; + int ret; + + ret = socketpair(AF_UNIX, variant->type, 0, self->fd); + ASSERT_EQ(0, ret); + + ret = setsockopt(self->fd[1], SOL_SOCKET, SO_RCVTIMEO_NEW, + &timeout, sizeof(timeout)); + ASSERT_EQ(0, ret); + + ret = setsockopt(self->fd[1], SOL_SOCKET, SO_PEEK_OFF, + &(int){0}, sizeof(int)); + ASSERT_EQ(0, ret); +} + +FIXTURE_TEARDOWN(so_peek_off) +{ + close_range(self->fd[0], self->fd[1], 0); +} + +#define sendeq(fd, str, flags) \ + do { \ + int bytes, len = strlen(str); \ + \ + bytes = send(fd, str, len, flags); \ + ASSERT_EQ(len, bytes); \ + } while (0) + +#define recveq(fd, str, buflen, flags) \ + do { \ + char buf[(buflen) + 1] = {}; \ + int bytes; \ + \ + bytes = recv(fd, buf, buflen, flags); \ + ASSERT_NE(-1, bytes); \ + ASSERT_STREQ(str, buf); \ + } while (0) + +#define async \ + for (pid_t pid = (pid = fork(), \ + pid < 0 ? \ + __TH_LOG("Failed to start async {}"), \ + _metadata->exit_code = KSFT_FAIL, \ + __bail(1, _metadata), \ + 0xdead : \ + pid); \ + !pid; exit(0)) + +TEST_F(so_peek_off, single_chunk) +{ + sendeq(self->fd[0], "aaaabbbb", 0); + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks) +{ + sendeq(self->fd[0], "aaaa", 0); + sendeq(self->fd[0], "bbbb", 0); + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks_blocking) +{ + async { + usleep(1000); + sendeq(self->fd[0], "aaaa", 0); + } + + recveq(self->fd[1], "aaaa", 4, MSG_PEEK); + + async { + usleep(1000); + sendeq(self->fd[0], "bbbb", 0); + } + + /* goto again; -> goto redo; in unix_stream_read_generic(). */ + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_F(so_peek_off, two_chunks_overlap) +{ + sendeq(self->fd[0], "aaaa", 0); + recveq(self->fd[1], "aa", 2, MSG_PEEK); + + sendeq(self->fd[0], "bbbb", 0); + + if (variant->type == SOCK_STREAM) { + /* SOCK_STREAM tries to fill the buffer. */ + recveq(self->fd[1], "aabb", 4, MSG_PEEK); + recveq(self->fd[1], "bb", 100, MSG_PEEK); + } else { + /* SOCK_DGRAM and SOCK_SEQPACKET returns at the skb boundary. */ + recveq(self->fd[1], "aa", 100, MSG_PEEK); + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); + } +} + +TEST_F(so_peek_off, two_chunks_overlap_blocking) +{ + async { + usleep(1000); + sendeq(self->fd[0], "aaaa", 0); + } + + recveq(self->fd[1], "aa", 2, MSG_PEEK); + + async { + usleep(1000); + sendeq(self->fd[0], "bbbb", 0); + } + + /* Even SOCK_STREAM does not wait if at least one byte is read. */ + recveq(self->fd[1], "aa", 100, MSG_PEEK); + + recveq(self->fd[1], "bbbb", 100, MSG_PEEK); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/af_unix/unix_connreset.c b/tools/testing/selftests/net/af_unix/unix_connreset.c new file mode 100644 index 000000000000..08c1de8f5a98 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_connreset.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Selftest for AF_UNIX socket close and ECONNRESET behaviour. + * + * This test verifies: + * 1. SOCK_STREAM returns EOF when the peer closes normally. + * 2. SOCK_STREAM returns ECONNRESET if peer closes with unread data. + * 3. SOCK_SEQPACKET returns EOF when the peer closes normally. + * 4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data. + * 5. SOCK_DGRAM does not return ECONNRESET when the peer closes. + * + * These tests document the intended Linux behaviour. + * + */ + +#define _GNU_SOURCE +#include <string.h> +#include <fcntl.h> +#include <unistd.h> +#include <errno.h> +#include <sys/socket.h> +#include <sys/un.h> +#include "../../kselftest_harness.h" + +#define SOCK_PATH "/tmp/af_unix_connreset.sock" + +static void remove_socket_file(void) +{ + unlink(SOCK_PATH); +} + +FIXTURE(unix_sock) +{ + int server; + int client; + int child; +}; + +FIXTURE_VARIANT(unix_sock) +{ + int socket_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(unix_sock, stream) { + .socket_type = SOCK_STREAM, + .name = "SOCK_STREAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, dgram) { + .socket_type = SOCK_DGRAM, + .name = "SOCK_DGRAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, seqpacket) { + .socket_type = SOCK_SEQPACKET, + .name = "SOCK_SEQPACKET", +}; + +FIXTURE_SETUP(unix_sock) +{ + struct sockaddr_un addr = {}; + int err; + + addr.sun_family = AF_UNIX; + strcpy(addr.sun_path, SOCK_PATH); + remove_socket_file(); + + self->server = socket(AF_UNIX, variant->socket_type, 0); + ASSERT_LT(-1, self->server); + + err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0); + ASSERT_LT(-1, self->client); + + err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(unix_sock) +{ + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) + close(self->child); + + close(self->client); + close(self->server); + remove_socket_file(); +} + +/* Test 1: peer closes normally */ +TEST_F(unix_sock, eof) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + close(self->child); + } else { + close(self->server); + } + + n = recv(self->client, buf, sizeof(buf), 0); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(0, n); + } else { + ASSERT_EQ(-1, n); + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 2: peer closes with unread data */ +TEST_F(unix_sock, reset_unread_behavior) +{ + char buf[16] = {}; + ssize_t n; + + /* Send data that will remain unread */ + send(self->client, "hello", 5, 0); + + if (variant->socket_type == SOCK_DGRAM) { + /* No real connection, just close the server */ + close(self->server); + } else { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + /* Peer closes before client reads */ + close(self->child); + } + + n = recv(self->client, buf, sizeof(buf), 0); + ASSERT_EQ(-1, n); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(ECONNRESET, errno); + } else { + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 3: closing unaccepted (embryo) server socket should reset client. */ +TEST_F(unix_sock, reset_closed_embryo) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_DGRAM) { + snprintf(_metadata->results->reason, + sizeof(_metadata->results->reason), + "Test only applies to SOCK_STREAM and SOCK_SEQPACKET"); + exit(KSFT_XFAIL); + } + + /* Close server without accept()ing */ + close(self->server); + + n = recv(self->client, buf, sizeof(buf), 0); + + ASSERT_EQ(-1, n); + ASSERT_EQ(ECONNRESET, errno); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a94b73a53f72..a88f797c549a 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -11,7 +11,8 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ - ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance" + ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance \ + fib6_ra_to_static" VERBOSE=0 PAUSE_ON_FAIL=no @@ -1476,6 +1477,68 @@ ipv6_route_metrics_test() route_cleanup } +fib6_ra_to_static() +{ + setup + + echo + echo "Fib6 route promotion from RA-learned to static test" + set -e + + # ra6 is required for the test. (ipv6toolkit) + if [ ! -x "$(command -v ra6)" ]; then + echo "SKIP: ra6 not found." + set +e + cleanup &> /dev/null + return + fi + + # Create a pair of veth devices to send a RA message from one + # device to another. + $IP link add veth1 type veth peer name veth2 + $IP link set dev veth1 up + $IP link set dev veth2 up + $IP -6 address add 2001:10::1/64 dev veth1 nodad + $IP -6 address add 2001:10::2/64 dev veth2 nodad + + # Make veth1 ready to receive RA messages. + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra=2 + + # Send a RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + + # Wait for the RA message. + sleep 1 + + # systemd may mess up the test. Make sure that + # systemd-networkd.service and systemd-networkd.socket are stopped. + check_rt_num_clean 2 $($IP -6 route list|grep expires|wc -l) || return + + # Configure static address on the same prefix + $IP -6 address add 2001:12::dead/64 dev veth1 nodad + + # On-link route won't expire anymore, default route still owned by RA + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + # Send a second RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + sleep 1 + + # Expire is not back, on-link route is still static + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + $IP -6 address del 2001:12::dead/64 dev veth1 nodad + + # Expire is back, on-link route is now owned by RA again + check_rt_num 2 $($IP -6 route list |grep expires|wc -l) + + log_test $ret 0 "ipv6 promote RA route to static" + + set +e + + cleanup &> /dev/null +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -2798,6 +2861,7 @@ do ipv6_mpath_list) ipv6_mpath_list_test;; ipv4_mpath_balance) ipv4_mpath_balance_test;; ipv6_mpath_balance) ipv6_mpath_balance_test;; + fib6_ra_to_static) fib6_ra_to_static;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/lib_sh_test.sh b/tools/testing/selftests/net/forwarding/lib_sh_test.sh index ff2accccaf4d..b4eda6c6199e 100755 --- a/tools/testing/selftests/net/forwarding/lib_sh_test.sh +++ b/tools/testing/selftests/net/forwarding/lib_sh_test.sh @@ -30,6 +30,11 @@ tfail() do_test "tfail" false } +tfail2() +{ + do_test "tfail2" false +} + txfail() { FAIL_TO_XFAIL=yes do_test "txfail" false @@ -132,6 +137,8 @@ test_ret() ret_subtest $ksft_fail "tfail" txfail tfail ret_subtest $ksft_xfail "txfail" txfail txfail + + ret_subtest $ksft_fail "tfail2" tfail2 tfail } exit_status_tests_run() diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh deleted file mode 100755 index 4c5144c6f652..000000000000 --- a/tools/testing/selftests/net/gro.sh +++ /dev/null @@ -1,105 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly SERVER_MAC="aa:00:00:00:00:02" -readonly CLIENT_MAC="aa:00:00:00:00:01" -readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large") -readonly PROTOS=("ipv4" "ipv6" "ipip") -dev="" -test="all" -proto="ipv4" - -run_test() { - local server_pid=0 - local exit_code=0 - local protocol=$1 - local test=$2 - local ARGS=( "--${protocol}" "--dmac" "${SERVER_MAC}" \ - "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" ) - - setup_ns - # Each test is run 6 times to deflake, because given the receive timing, - # not all packets that should coalesce will be considered in the same flow - # on every try. - for tries in {1..6}; do - # Actual test starts here - ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \ - 1>>log.txt & - server_pid=$! - sleep 0.5 # to allow for socket init - ip netns exec $client_ns ./gro "${ARGS[@]}" "--iface" "client" \ - 1>>log.txt - wait "${server_pid}" - exit_code=$? - if [[ ${test} == "large" && -n "${KSFT_MACHINE_SLOW}" && \ - ${exit_code} -ne 0 ]]; then - echo "Ignoring errors due to slow environment" 1>&2 - exit_code=0 - fi - if [[ "${exit_code}" -eq 0 ]]; then - break; - fi - done - cleanup_ns - echo ${exit_code} -} - -run_all_tests() { - local failed_tests=() - for proto in "${PROTOS[@]}"; do - for test in "${TESTS[@]}"; do - echo "running test ${proto} ${test}" >&2 - exit_code=$(run_test $proto $test) - if [[ "${exit_code}" -ne 0 ]]; then - failed_tests+=("${proto}_${test}") - fi; - done; - done - if [[ ${#failed_tests[@]} -ne 0 ]]; then - echo "failed tests: ${failed_tests[*]}. \ - Please see log.txt for more logs" - exit 1 - else - echo "All Tests Succeeded!" - fi; -} - -usage() { - echo "Usage: $0 \ - [-i <DEV>] \ - [-t data|ack|flags|tcp|ip|large] \ - [-p <ipv4|ipv6>]" 1>&2; - exit 1; -} - -while getopts "i:t:p:" opt; do - case "${opt}" in - i) - dev="${OPTARG}" - ;; - t) - test="${OPTARG}" - ;; - p) - proto="${OPTARG}" - ;; - *) - usage - ;; - esac -done - -if [ -n "$dev" ]; then - source setup_loopback.sh -else - source setup_veth.sh -fi - -setup -trap cleanup EXIT -if [[ "${test}" == "all" ]]; then - run_all_tests -else - exit_code=$(run_test "${proto}" "${test}") - exit $exit_code -fi; diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index feba4ef69a54..f448bafb3f20 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -43,7 +43,7 @@ __ksft_status_merge() weights[$i]=$((weight++)) done - if [[ ${weights[$a]} > ${weights[$b]} ]]; then + if [[ ${weights[$a]} -ge ${weights[$b]} ]]; then echo "$a" return 0 else diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index ce795bc0a1af..5339f56329e1 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -8,6 +8,7 @@ CFLAGS += -I../../ TEST_FILES := \ ../../../../net/ynl \ ../../../../../Documentation/netlink/specs \ + ksft_setup_loopback.sh \ # end of TEST_FILES TEST_GEN_FILES := \ diff --git a/tools/testing/selftests/net/lib/ksft_setup_loopback.sh b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh new file mode 100755 index 000000000000..3defbb1919c5 --- /dev/null +++ b/tools/testing/selftests/net/lib/ksft_setup_loopback.sh @@ -0,0 +1,111 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Setup script for running ksft tests over a real interface in loopback mode. +# This scripts replaces the historical setup_loopback.sh. It puts +# a (presumably) real hardware interface into loopback mode, creates macvlan +# interfaces on top and places them in a network namespace for isolation. +# +# NETIF env variable must be exported to indicate the real target device. +# Note that the test will override NETIF with one of the macvlans, the +# actual ksft test will only see the macvlans. +# +# Example use: +# export NETIF=eth0 +# ./net/lib/ksft_setup_loopback.sh ./drivers/net/gro.py + +if [ -z "$NETIF" ]; then + echo "Error: NETIF variable not set" + exit 1 +fi +if ! [ -d "/sys/class/net/$NETIF" ]; then + echo "Error: Can't find $NETIF, invalid netdevice" + exit 1 +fi + +# Save original settings for cleanup +readonly FLUSH_PATH="/sys/class/net/${NETIF}/gro_flush_timeout" +readonly IRQ_PATH="/sys/class/net/${NETIF}/napi_defer_hard_irqs" +FLUSH_TIMEOUT="$(< "${FLUSH_PATH}")" +readonly FLUSH_TIMEOUT +HARD_IRQS="$(< "${IRQ_PATH}")" +readonly HARD_IRQS + +SERVER_NS=$(mktemp -u server-XXXXXXXX) +readonly SERVER_NS +CLIENT_NS=$(mktemp -u client-XXXXXXXX) +readonly CLIENT_NS +readonly SERVER_MAC="aa:00:00:00:00:02" +readonly CLIENT_MAC="aa:00:00:00:00:01" + +# ksft expects addresses to communicate with remote +export LOCAL_V6=2001:db8:1::1 +export REMOTE_V6=2001:db8:1::2 + +cleanup() { + local exit_code=$? + + echo "Cleaning up..." + + # Remove macvlan interfaces and namespaces + ip -netns "${SERVER_NS}" link del dev server 2>/dev/null || true + ip netns del "${SERVER_NS}" 2>/dev/null || true + ip -netns "${CLIENT_NS}" link del dev client 2>/dev/null || true + ip netns del "${CLIENT_NS}" 2>/dev/null || true + + # Disable loopback + ethtool -K "${NETIF}" loopback off 2>/dev/null || true + sleep 1 + + echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" + echo "${HARD_IRQS}" >"${IRQ_PATH}" + + exit $exit_code +} + +trap cleanup EXIT INT TERM + +# Enable loopback mode +echo "Enabling loopback on ${NETIF}..." +ethtool -K "${NETIF}" loopback on || { + echo "Failed to enable loopback mode" + exit 1 +} +# The interface may need time to get carrier back, but selftests +# will wait for carrier, so no need to wait / sleep here. + +# Use timer on host to trigger the network stack +# Also disable device interrupt to not depend on NIC interrupt +# Reduce test flakiness caused by unexpected interrupts +echo 100000 >"${FLUSH_PATH}" +echo 50 >"${IRQ_PATH}" + +# Create server namespace with macvlan +ip netns add "${SERVER_NS}" +ip link add link "${NETIF}" dev server address "${SERVER_MAC}" type macvlan +ip link set dev server netns "${SERVER_NS}" +ip -netns "${SERVER_NS}" link set dev server up +ip -netns "${SERVER_NS}" addr add $LOCAL_V6/64 dev server +ip -netns "${SERVER_NS}" link set dev lo up + +# Create client namespace with macvlan +ip netns add "${CLIENT_NS}" +ip link add link "${NETIF}" dev client address "${CLIENT_MAC}" type macvlan +ip link set dev client netns "${CLIENT_NS}" +ip -netns "${CLIENT_NS}" link set dev client up +ip -netns "${CLIENT_NS}" addr add $REMOTE_V6/64 dev client +ip -netns "${CLIENT_NS}" link set dev lo up + +echo "Setup complete!" +echo " Device: ${NETIF}" +echo " Server NS: ${SERVER_NS}" +echo " Client NS: ${CLIENT_NS}" +echo "" + +# Setup environment variables for tests +export NETIF=server +export REMOTE_TYPE=netns +export REMOTE_ARGS="${CLIENT_NS}" + +# Run the command +ip netns exec "${SERVER_NS}" "$@" diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 97b7cf2b20eb..40f9ce307dd1 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -8,7 +8,8 @@ from .consts import KSRC from .ksft import KsftFailEx, KsftSkipEx, KsftXfailEx, ksft_pr, ksft_eq, \ ksft_ne, ksft_true, ksft_not_none, ksft_in, ksft_not_in, ksft_is, \ ksft_ge, ksft_gt, ksft_lt, ksft_raises, ksft_busy_wait, \ - ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit + ktap_result, ksft_disruptive, ksft_setup, ksft_run, ksft_exit, \ + ksft_variants, KsftNamedVariant from .netns import NetNS, NetNSEnter from .nsim import NetdevSim, NetdevSimDev from .utils import CmdExitFailure, fd_read_timeout, cmd, bkg, defer, \ @@ -21,7 +22,7 @@ __all__ = ["KSRC", "ksft_ne", "ksft_true", "ksft_not_none", "ksft_in", "ksft_not_in", "ksft_is", "ksft_ge", "ksft_gt", "ksft_lt", "ksft_raises", "ksft_busy_wait", "ktap_result", "ksft_disruptive", "ksft_setup", - "ksft_run", "ksft_exit", + "ksft_run", "ksft_exit", "ksft_variants", "KsftNamedVariant", "NetNS", "NetNSEnter", "CmdExitFailure", "fd_read_timeout", "cmd", "bkg", "defer", "bpftool", "ip", "ethtool", "bpftrace", "rand_port", diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 83b1574f7719..ebd82940ee50 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,12 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -import builtins import functools import inspect import signal import sys import time import traceback +from collections import namedtuple from .consts import KSFT_MAIN_NAME from .utils import global_defer_queue @@ -136,7 +136,7 @@ def ksft_busy_wait(cond, sleep=0.005, deadline=1, comment=""): time.sleep(sleep) -def ktap_result(ok, cnt=1, case="", comment=""): +def ktap_result(ok, cnt=1, case_name="", comment=""): global KSFT_RESULT_ALL KSFT_RESULT_ALL = KSFT_RESULT_ALL and ok @@ -146,8 +146,8 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "ok " res += str(cnt) + " " res += KSFT_MAIN_NAME - if case: - res += "." + str(case.__name__) + if case_name: + res += "." + case_name if comment: res += " # " + comment print(res, flush=True) @@ -163,7 +163,7 @@ def ksft_flush_defer(): entry = global_defer_queue.pop() try: entry.exec_only() - except: + except BaseException: ksft_pr(f"Exception while handling defer / cleanup (callback {i} of {qlen_start})!") tb = traceback.format_exc() for line in tb.strip().split('\n'): @@ -171,6 +171,10 @@ def ksft_flush_defer(): KSFT_RESULT = False +KsftCaseFunction = namedtuple("KsftCaseFunction", + ['name', 'original_func', 'variants']) + + def ksft_disruptive(func): """ Decorator that marks the test as disruptive (e.g. the test @@ -181,11 +185,47 @@ def ksft_disruptive(func): @functools.wraps(func) def wrapper(*args, **kwargs): if not KSFT_DISRUPTIVE: - raise KsftSkipEx(f"marked as disruptive") + raise KsftSkipEx("marked as disruptive") return func(*args, **kwargs) return wrapper +class KsftNamedVariant: + """ Named string name + argument list tuple for @ksft_variants """ + + def __init__(self, name, *params): + self.params = params + self.name = name or "_".join([str(x) for x in self.params]) + + +def ksft_variants(params): + """ + Decorator defining the sets of inputs for a test. + The parameters will be included in the name of the resulting sub-case. + Parameters can be either single object, tuple or a KsftNamedVariant. + The argument can be a list or a generator. + + Example: + + @ksft_variants([ + (1, "a"), + (2, "b"), + KsftNamedVariant("three", 3, "c"), + ]) + def my_case(cfg, a, b): + pass # ... + + ksft_run(cases=[my_case], args=(cfg, )) + + Will generate cases: + my_case.1_a + my_case.2_b + my_case.three + """ + + return lambda func: KsftCaseFunction(func.__name__, func, params) + + def ksft_setup(env): """ Setup test framework global state from the environment. @@ -199,7 +239,7 @@ def ksft_setup(env): return False try: return bool(int(value)) - except: + except Exception: raise Exception(f"failed to parse {name}") if "DISRUPTIVE" in env: @@ -220,9 +260,13 @@ def _ksft_intr(signum, frame): ksft_pr(f"Ignoring SIGTERM (cnt: {term_cnt}), already exiting...") -def ksft_run(cases=None, globs=None, case_pfx=None, args=()): +def _ksft_generate_test_cases(cases, globs, case_pfx, args): + """Generate a flat list of (func, args, name) tuples""" + cases = cases or [] + test_cases = [] + # If using the globs method find all relevant functions if globs and case_pfx: for key, value in globs.items(): if not callable(value): @@ -232,6 +276,27 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): cases.append(value) break + for func in cases: + if isinstance(func, KsftCaseFunction): + # Parametrized test - create case for each param + for param in func.variants: + if not isinstance(param, KsftNamedVariant): + if not isinstance(param, tuple): + param = (param, ) + param = KsftNamedVariant(None, *param) + + test_cases.append((func.original_func, + (*args, *param.params), + func.name + "." + param.name)) + else: + test_cases.append((func, args, func.__name__)) + + return test_cases + + +def ksft_run(cases=None, globs=None, case_pfx=None, args=()): + test_cases = _ksft_generate_test_cases(cases, globs, case_pfx, args) + global term_cnt term_cnt = 0 prev_sigterm = signal.signal(signal.SIGTERM, _ksft_intr) @@ -239,19 +304,19 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} print("TAP version 13", flush=True) - print("1.." + str(len(cases)), flush=True) + print("1.." + str(len(test_cases)), flush=True) global KSFT_RESULT cnt = 0 stop = False - for case in cases: + for func, args, name in test_cases: KSFT_RESULT = True cnt += 1 comment = "" cnt_key = "" try: - case(*args) + func(*args) except KsftSkipEx as e: comment = "SKIP " + str(e) cnt_key = 'skip' @@ -273,7 +338,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): if not cnt_key: cnt_key = 'pass' if KSFT_RESULT else 'fail' - ktap_result(KSFT_RESULT, cnt, case, comment=comment) + ktap_result(KSFT_RESULT, cnt, name, comment=comment) totals[cnt_key] += 1 if stop: diff --git a/tools/testing/selftests/net/lib/py/nsim.py b/tools/testing/selftests/net/lib/py/nsim.py index 1a8cbe9acc48..7c640ed64c0b 100644 --- a/tools/testing/selftests/net/lib/py/nsim.py +++ b/tools/testing/selftests/net/lib/py/nsim.py @@ -27,7 +27,7 @@ class NetdevSim: self.port_index = port_index self.ns = ns self.dfs_dir = "%s/ports/%u/" % (nsimdev.dfs_dir, port_index) - ret = ip("-j link show dev %s" % ifname, ns=ns) + ret = ip("-d -j link show dev %s" % ifname, ns=ns) self.dev = json.loads(ret.stdout)[0] self.ifindex = self.dev["ifindex"] diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index cb40ecef9456..106ee1f2df86 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -32,7 +32,7 @@ class cmd: Use bkg() instead to run a command in the background. """ def __init__(self, comm, shell=None, fail=True, ns=None, background=False, - host=None, timeout=5, ksft_wait=None): + host=None, timeout=5, ksft_ready=None, ksft_wait=None): if ns: comm = f'ip netns exec {ns} ' + comm @@ -52,21 +52,25 @@ class cmd: # ksft_wait lets us wait for the background process to fully start, # we pass an FD to the child process, and wait for it to write back. # Similarly term_fd tells child it's time to exit. - pass_fds = () + pass_fds = [] env = os.environ.copy() if ksft_wait is not None: - rfd, ready_fd = os.pipe() wait_fd, self.ksft_term_fd = os.pipe() - pass_fds = (ready_fd, wait_fd, ) - env["KSFT_READY_FD"] = str(ready_fd) + pass_fds.append(wait_fd) env["KSFT_WAIT_FD"] = str(wait_fd) + ksft_ready = True # ksft_wait implies ready + if ksft_ready is not None: + rfd, ready_fd = os.pipe() + pass_fds.append(ready_fd) + env["KSFT_READY_FD"] = str(ready_fd) self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE, stderr=subprocess.PIPE, pass_fds=pass_fds, env=env) if ksft_wait is not None: - os.close(ready_fd) os.close(wait_fd) + if ksft_ready is not None: + os.close(ready_fd) msg = fd_read_timeout(rfd, ksft_wait) os.close(rfd) if not msg: @@ -116,10 +120,10 @@ class bkg(cmd): with bkg("my_binary", ksft_wait=5): """ def __init__(self, comm, shell=None, fail=None, ns=None, host=None, - exit_wait=False, ksft_wait=None): + exit_wait=False, ksft_ready=None, ksft_wait=None): super().__init__(comm, background=True, shell=shell, fail=fail, ns=ns, host=host, - ksft_wait=ksft_wait) + ksft_ready=ksft_ready, ksft_wait=ksft_wait) self.terminate = not exit_wait and not ksft_wait self._exit_wait = exit_wait self.check_fail = fail diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index c368fc045f4b..64f05229ab24 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -332,7 +332,7 @@ static __u16 csum_fold_helper(__u32 csum) } static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, - __u32 hdr_len) + unsigned long hdr_len) { char tmp_buff[MAX_ADJST_OFFSET]; __u32 buff_pos, udp_csum = 0; @@ -422,8 +422,9 @@ static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) { struct udphdr *udph = NULL; __s32 *adjust_offset, *val; - __u32 key, hdr_len; + unsigned long hdr_len; void *offset_ptr; + __u32 key; __u8 tag; int ret; diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 9b7b93f8eb0c..a6447f7a31fe 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -375,81 +375,75 @@ do_transfer() local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" local capopt="-i any -s 65535 -B 32768 ${capuser}" - ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + ip netns exec ${listener_ns} tcpdump ${capopt} \ + -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & local cappid_listener=$! - ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & - local cappid_connector=$! + if [ ${listener_ns} != ${connector_ns} ]; then + ip netns exec ${connector_ns} tcpdump ${capopt} \ + -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + fi sleep 1 fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - fi - - local stat_synrx_last_l - local stat_ackrx_last_l - local stat_cookietx_last - local stat_cookierx_last - local stat_csum_err_s - local stat_csum_err_c - local stat_tcpfb_last_l - stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_args $local_addr < "$sin" > "$sout" & + mptcp_lib_nstat_init "${connector_ns}" + fi + + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args $local_addr < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start start=$(date +%s%3N) - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + local stop stop=$(date +%s%3N) if $capture; then sleep 1 kill ${cappid_listener} - kill ${cappid_connector} + if [ ${listener_ns} != ${connector_ns} ]; then + kill ${cappid_connector} + fi fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out + mptcp_lib_nstat_get "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${connector_ns}" fi local duration duration=$((stop-start)) printf "(duration %05sms) " "${duration}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" echo cat "$capout" @@ -463,38 +457,38 @@ do_transfer() rets=$? local extra="" - local stat_synrx_now_l - local stat_ackrx_now_l - local stat_cookietx_now - local stat_cookierx_now - local stat_ooo_now - local stat_tcpfb_now_l - stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") - stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - expect_synrx=$((stat_synrx_last_l)) - expect_ackrx=$((stat_ackrx_last_l)) + local stat_synrx + local stat_ackrx + local stat_cookietx + local stat_cookierx + local stat_ooo + local stat_tcpfb + stat_synrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") + + expect_synrx=0 + expect_ackrx=0 cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) + expect_synrx=${connect_per_transfer} + expect_ackrx=${connect_per_transfer} fi - if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then - mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx_now_l})" \ + if [ ${stat_synrx} -lt ${expect_synrx} ]; then + mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx})" \ "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - if [ ${stat_ooo_now} -eq 0 ]; then - mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ + if [ ${stat_ackrx} -lt ${expect_ackrx} ]; then + if [ ${stat_ooo} -eq 0 ]; then + mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx})" \ "than expected (${expect_ackrx})" rets=1 else @@ -508,47 +502,45 @@ do_transfer() csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) - if [ $csum_err_s_nr -gt 0 ]; then - mptcp_lib_pr_fail "server got ${csum_err_s_nr} data checksum error[s]" + if [ $csum_err_s -gt 0 ]; then + mptcp_lib_pr_fail "server got ${csum_err_s} data checksum error[s]" rets=1 fi - local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) - if [ $csum_err_c_nr -gt 0 ]; then - mptcp_lib_pr_fail "client got ${csum_err_c_nr} data checksum error[s]" + if [ $csum_err_c -gt 0 ]; then + mptcp_lib_pr_fail "client got ${csum_err_c} data checksum error[s]" retc=1 fi fi - if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + if [ ${stat_ooo} -eq 0 ] && [ ${stat_tcpfb} -gt 0 ]; then mptcp_lib_pr_fail "unexpected fallback to TCP" rets=1 fi if [ $cookies -eq 2 ];then - if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + if [ $stat_cookietx -eq 0 ] ;then extra+=" WARN: CookieSent: did not advance" fi - if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + if [ $stat_cookierx -eq 0 ] ;then extra+=" WARN: CookieRecv: did not advance" fi else - if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + if [ $stat_cookietx -gt 0 ] ;then extra+=" WARN: CookieSent: changed" fi - if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + if [ $stat_cookierx -gt 0 ] ;then extra+=" WARN: CookieRecv: changed" fi fi - if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then + if [ ${stat_synrx} -gt ${expect_synrx} ]; then extra+=" WARN: SYNRX: expect ${expect_synrx}," - extra+=" got ${stat_synrx_now_l} (probably retransmissions)" + extra+=" got ${stat_synrx} (probably retransmissions)" fi - if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then + if [ ${stat_ackrx} -gt ${expect_ackrx} ]; then extra+=" WARN: ACKRX: expect ${expect_ackrx}," - extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + extra+=" got ${stat_ackrx} (probably retransmissions)" fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index f0efbf985625..b2e6e548f796 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -983,10 +983,8 @@ do_transfer() cond_start_capture ${listener_ns} - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" local extra_args if [ $speed = "fast" ]; then @@ -1026,38 +1024,38 @@ do_transfer() if [ "$test_linkfail" -gt 1 ];then listener_in="${sinfail}" fi - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p ${port} -s ${srv_proto} \ - ${extra_srv_args} "${bind_addr}" < "${listener_in}" > "${sout}" & + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p ${port} -s ${srv_proto} \ + ${extra_srv_args} "${bind_addr}" < "${listener_in}" > "${sout}" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" extra_cl_args="$extra_args $extra_cl_args" if [ "$test_linkfail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then connector_in="${cinsent}" ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ - timeout ${timeout_test} \ ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_cl_args $connect_addr > "$cout" & else connector_in="${cinsent}" tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & fi local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr check_cestab $listener_ns $connector_ns @@ -1066,17 +1064,20 @@ do_transfer() wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + cond_stop_capture - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" return 1 fi @@ -1151,12 +1152,20 @@ run_tests() do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} } +_dump_stats() +{ + local ns="${1}" + local side="${2}" + + mptcp_lib_print_err "${side} ns stats (${ns2})" + mptcp_lib_pr_nstat "${ns}" + echo +} + dump_stats() { - echo Server ns stats - ip netns exec $ns1 nstat -as | grep Tcp - echo Client ns stats - ip netns exec $ns2 nstat -as | grep Tcp + _dump_stats "${ns1}" "Server" + _dump_stats "${ns2}" "Client" } chk_csum_nr() @@ -3646,7 +3655,6 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then - MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 @@ -3655,7 +3663,6 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then - MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 join_rst_nr=1 \ @@ -3952,7 +3959,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 2 2 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -3985,7 +3992,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -4013,7 +4020,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -4034,7 +4041,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns2 pm_nl_set_limits $ns1 0 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns2 @@ -4058,7 +4065,7 @@ userspace_tests() continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then set_userspace_pm $ns1 pm_nl_set_limits $ns2 1 1 - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! wait_mpj $ns1 @@ -4089,7 +4096,7 @@ endpoint_tests() 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 - { test_linkfail=128 speed=slow \ + { timeout_test=120 test_linkfail=128 speed=slow \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4116,7 +4123,7 @@ endpoint_tests() pm_nl_set_limits $ns2 0 3 pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4194,7 +4201,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal - { test_linkfail=128 speed=5 \ + { timeout_test=120 test_linkfail=128 speed=5 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! @@ -4203,38 +4210,45 @@ endpoint_tests() $ns1 10.0.2.1 id 1 flags signal chk_subflow_nr "before delete" 2 chk_mptcp_info subflows 1 subflows 1 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 1 pm_nl_del_endpoint $ns1 1 10.0.2.1 pm_nl_del_endpoint $ns1 2 224.0.0.1 sleep 0.5 chk_subflow_nr "after delete" 1 chk_mptcp_info subflows 0 subflows 0 + chk_mptcp_info add_addr_signal 0 add_addr_accepted 0 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal wait_mpj $ns2 chk_subflow_nr "after re-add" 3 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj $ns2 chk_subflow_nr "after re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 + chk_mptcp_info add_addr_signal 3 add_addr_accepted 2 pm_nl_del_endpoint $ns1 99 10.0.1.1 sleep 0.5 chk_subflow_nr "after re-delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 + chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal wait_mpj $ns2 chk_subflow_nr "after re-re-add ID 0" 3 chk_mptcp_info subflows 3 subflows 3 + chk_mptcp_info add_addr_signal 3 add_addr_accepted 2 mptcp_lib_kill_group_wait $tests_pid kill_events_pids @@ -4267,7 +4281,7 @@ endpoint_tests() # broadcast IP: no packet for this address will be received on ns1 pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow - { test_linkfail=128 speed=20 \ + { timeout_test=120 test_linkfail=128 speed=20 \ run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null local tests_pid=$! diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f4388900016a..5fea7e7df628 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -106,23 +106,32 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } -# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_nstat() { + local ns="${1}" + local hist="/tmp/${ns}.out" + + if [ -f "${hist}" ]; then + awk '$2 != 0 { print " "$0 }' "${hist}" + else + ip netns exec "${ns}" nstat -as | grep Tcp + fi +} + +# $1-2: listener/connector ns ; $3 port mptcp_lib_pr_err_stats() { local lns="${1}" local cns="${2}" local port="${3}" - local lstat="${4}" - local cstat="${5}" echo -en "${MPTCP_LIB_COLOR_RED}" { printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" - cat "${lstat}" + mptcp_lib_pr_nstat "${lns}" printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" - [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + [ "${lns}" != "${cns}" ] && mptcp_lib_pr_nstat "${cns}" } 1>&2 echo -en "${MPTCP_LIB_COLOR_RESET}" } @@ -341,6 +350,19 @@ mptcp_lib_evts_get_info() { mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } +mptcp_lib_wait_timeout() { + local timeout_test="${1}" + local listener_ns="${2}" + local connector_ns="${3}" + local port="${4}" + shift 4 # rest are PIDs + + sleep "${timeout_test}" + mptcp_lib_print_err "timeout" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" + kill "${@}" 2>/dev/null +} + # $1: PID mptcp_lib_kill_wait() { [ "${1}" -eq 0 ] && return 0 @@ -376,14 +398,36 @@ mptcp_lib_is_v6() { [ -z "${1##*:*}" ] } +mptcp_lib_nstat_init() { + local ns="${1}" + + rm -f "/tmp/${ns}."{nstat,out} + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -n +} + +mptcp_lib_nstat_get() { + local ns="${1}" + + # filter out non-*TCP stats, and the rate (last column) + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -sz | + grep -o ".*Tcp\S\+\s\+[0-9]\+" > "/tmp/${ns}.out" +} + # $1: ns, $2: MIB counter +# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" + local hist="/tmp/${ns}.out" local count - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + else + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" return 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index f01989be6e9b..ab8bce06b262 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,41 +169,44 @@ do_transfer() cmsg+=",TCPINQ" fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ - ${local_addr} < "$sin" > "$sout" & + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" + + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ + ${local_addr} < "$sin" > "$sout" & local spid=$! - sleep 1 + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ - $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ + $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" print_title "Transfer ${ip:2}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 1903e8e84a31..806aaa7d2d61 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,48 +155,53 @@ do_transfer() sleep 1 fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat -n - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${ns3} \ - ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ - 0.0.0.0 < "$sin" > "$sout" & + mptcp_lib_nstat_init "${ns3}" + mptcp_lib_nstat_init "${ns1}" + + ip netns exec ${ns3} \ + ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ + 0.0.0.0 < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${ns3}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${ns1} \ - ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ - 10.0.3.3 < "$cin" > "$cout" & + ip netns exec ${ns1} \ + ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ + 10.0.3.3 < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${ns3}" "${ns1}" "${port}" \ + "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + if $capture; then sleep 1 kill ${cappid_listener} kill ${cappid_connector} fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat | grep Tcp > /tmp/${ns3}.out - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat | grep Tcp > /tmp/${ns1}.out + mptcp_lib_nstat_get "${ns3}" + mptcp_lib_nstat_get "${ns1}" cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ - [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + if [ $retc -eq 0 ] && [ $rets -eq 0 ] && + [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && + [ $timeout_pid -eq 0 ]; then printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" @@ -204,8 +209,7 @@ do_transfer() fi mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ - "/tmp/${ns3}.out" "/tmp/${ns1}.out" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 87323942cb8a..e9ae1806ab07 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -211,7 +211,8 @@ make_connection() ip netns exec "$ns1" \ ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - sleep 0.5 + + mptcp_lib_wait_local_port_listen "${ns1}" "${port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt index b2b2cdf27e20..454441e7ecff 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_syscall_bad_arg_sendmsg-empty-iov.pkt @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 // Test that we correctly skip zero-length IOVs. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` + 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt index a82c8899d36b..0a0700afdaa3 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt @@ -4,6 +4,8 @@ // send a packet with MSG_ZEROCOPY and receive the notification ID // repeat and verify IDs are consecutive +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt index c01915e7f4a1..df91675d2991 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt @@ -3,6 +3,8 @@ // // send multiple packets, then read one range of all notifications. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt index 6509882932e9..2963cfcb14df 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 // Minimal client-side zerocopy test +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt index 2cd78755cb2a..ea0c2fa73c2d 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt @@ -7,6 +7,8 @@ // First send on a closed socket and wait for (absent) notification. // Then connect and send and verify that notification nr. is zero. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt index 7671c20e01cf..4df978a9b82e 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt @@ -7,6 +7,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt index fadc480fdb7f..36b6edc4858c 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt @@ -8,6 +8,9 @@ // fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR // is correctly fired only once, when EPOLLET is set. send another packet with // MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt index 5bfa0d1d2f4a..1bea6f3b4558 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt @@ -8,6 +8,9 @@ // is correctly fired only once, when EPOLLONESHOT is set. send another packet // with MSG_ZEROCOPY. confirm that EPOLLERR is not fired. Rearm the FD and // confirm that EPOLLERR is correctly set. + +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt index 4a73bbf46961..e27c21ff5d18 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt @@ -8,6 +8,8 @@ // one will have no data in the initial send. On return 0 the // zerocopy notification counter is not incremented. Verify this too. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` // Send a FastOpen request, no cookie yet so no data in SYN diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt index 36086c5877ce..b1fa77c77dfa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt @@ -4,6 +4,8 @@ // send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the // kernel returns the notification ID. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x207` diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt index 672f817faca0..2f5317d0a9fa 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt @@ -7,6 +7,8 @@ // because each iovec element becomes a frag // 3) the PSH bit is set on an skb when it runs out of fragments +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt index a9a1ac0aea4f..9d5272c6b207 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt @@ -4,6 +4,8 @@ // verify that SO_EE_CODE_ZEROCOPY_COPIED is set on zerocopy // packets of all sizes, including the smallest payload, 1B. +--send_omit_free // do not reuse send buffers with zerocopy + `./defaults.sh` 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 163a084d525d..248c2b91fe42 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -8,6 +8,7 @@ ALL_TESTS=" kci_test_polrouting kci_test_route_get kci_test_addrlft + kci_test_addrlft_route_cleanup kci_test_promote_secondaries kci_test_tc kci_test_gre @@ -323,6 +324,25 @@ kci_test_addrlft() end_test "PASS: preferred_lft addresses have expired" } +kci_test_addrlft_route_cleanup() +{ + local ret=0 + local test_addr="2001:db8:99::1/64" + local test_prefix="2001:db8:99::/64" + + run_cmd ip -6 addr add $test_addr dev "$devdummy" valid_lft 300 preferred_lft 300 + run_cmd_grep "$test_prefix proto kernel" ip -6 route show dev "$devdummy" + run_cmd ip -6 addr del $test_addr dev "$devdummy" + run_cmd_grep_fail "$test_prefix" ip -6 route show dev "$devdummy" + + if [ $ret -ne 0 ]; then + end_test "FAIL: route not cleaned up when address with valid_lft deleted" + return 1 + fi + + end_test "PASS: route cleaned up when address with valid_lft deleted" +} + kci_test_promote_secondaries() { run_cmd ifconfig "$devdummy" diff --git a/tools/testing/selftests/net/setup_loopback.sh b/tools/testing/selftests/net/setup_loopback.sh deleted file mode 100644 index 2070b57849de..000000000000 --- a/tools/testing/selftests/net/setup_loopback.sh +++ /dev/null @@ -1,120 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly FLUSH_PATH="/sys/class/net/${dev}/gro_flush_timeout" -readonly IRQ_PATH="/sys/class/net/${dev}/napi_defer_hard_irqs" -readonly FLUSH_TIMEOUT="$(< ${FLUSH_PATH})" -readonly HARD_IRQS="$(< ${IRQ_PATH})" -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -netdev_check_for_carrier() { - local -r dev="$1" - - for i in {1..5}; do - carrier="$(cat /sys/class/net/${dev}/carrier)" - if [[ "${carrier}" -ne 1 ]] ; then - echo "carrier not ready yet..." >&2 - sleep 1 - else - echo "carrier ready" >&2 - break - fi - done - echo "${carrier}" -} - -# Assumes that there is no existing ipvlan device on the physical device -setup_loopback_environment() { - local dev="$1" - - # Fail hard if cannot turn on loopback mode for current NIC - ethtool -K "${dev}" loopback on || exit 1 - sleep 1 - - # Check for the carrier - carrier=$(netdev_check_for_carrier ${dev}) - if [[ "${carrier}" -ne 1 ]] ; then - echo "setup_loopback_environment failed" - exit 1 - fi -} - -setup_macvlan_ns(){ - local -r link_dev="$1" - local -r ns_name="$2" - local -r ns_dev="$3" - local -r ns_mac="$4" - local -r addr="$5" - - ip link add link "${link_dev}" dev "${ns_dev}" \ - address "${ns_mac}" type macvlan - exit_code=$? - if [[ "${exit_code}" -ne 0 ]]; then - echo "setup_macvlan_ns failed" - exit $exit_code - fi - - [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - ip link set dev "${ns_dev}" netns "${ns_name}" - ip -netns "${ns_name}" link set dev "${ns_dev}" up - if [[ -n "${addr}" ]]; then - ip -netns "${ns_name}" addr add dev "${ns_dev}" "${addr}" - fi - - sleep 1 -} - -cleanup_macvlan_ns(){ - while (( $# >= 2 )); do - ns_name="$1" - ns_dev="$2" - ip -netns "${ns_name}" link del dev "${ns_dev}" - ip netns del "${ns_name}" - shift 2 - done -} - -cleanup_loopback(){ - local -r dev="$1" - - ethtool -K "${dev}" loopback off - sleep 1 - - # Check for the carrier - carrier=$(netdev_check_for_carrier ${dev}) - if [[ "${carrier}" -ne 1 ]] ; then - echo "setup_loopback_environment failed" - exit 1 - fi -} - -setup_interrupt() { - # Use timer on host to trigger the network stack - # Also disable device interrupt to not depend on NIC interrupt - # Reduce test flakiness caused by unexpected interrupts - echo 100000 >"${FLUSH_PATH}" - echo 50 >"${IRQ_PATH}" -} - -setup_ns() { - # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${dev}" ${server_ns} server "${SERVER_MAC}" - setup_macvlan_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" -} - -cleanup_ns() { - cleanup_macvlan_ns ${server_ns} server ${client_ns} client -} - -setup() { - setup_loopback_environment "${dev}" - setup_interrupt -} - -cleanup() { - cleanup_loopback "${dev}" - - echo "${FLUSH_TIMEOUT}" >"${FLUSH_PATH}" - echo "${HARD_IRQS}" >"${IRQ_PATH}" -} diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh deleted file mode 100644 index 152bf4c65747..000000000000 --- a/tools/testing/selftests/net/setup_veth.sh +++ /dev/null @@ -1,45 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -readonly server_ns=$(mktemp -u server-XXXXXXXX) -readonly client_ns=$(mktemp -u client-XXXXXXXX) - -setup_veth_ns() { - local -r link_dev="$1" - local -r ns_name="$2" - local -r ns_dev="$3" - local -r ns_mac="$4" - - [[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}" - echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout" - echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs" - ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535 - ip -netns "${ns_name}" link set dev "${ns_dev}" up - - ip netns exec "${ns_name}" ethtool -K "${ns_dev}" gro on tso off -} - -setup_ns() { - # Set up server_ns namespace and client_ns namespace - ip link add name server type veth peer name client - - setup_veth_ns "${dev}" ${server_ns} server "${SERVER_MAC}" - setup_veth_ns "${dev}" ${client_ns} client "${CLIENT_MAC}" -} - -cleanup_ns() { - local ns_name - - for ns_name in ${client_ns} ${server_ns}; do - [[ -e /var/run/netns/"${ns_name}" ]] && ip netns del "${ns_name}" - done -} - -setup() { - # no global init setup step needed - : -} - -cleanup() { - cleanup_ns -} diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c index 8457b7ccbc09..b76df1efc2ef 100644 --- a/tools/testing/selftests/net/so_txtime.c +++ b/tools/testing/selftests/net/so_txtime.c @@ -174,7 +174,7 @@ static int do_recv_errqueue_timeout(int fdt) msg.msg_controllen = sizeof(control); while (1) { - const char *reason; + const char *reason = NULL; ret = recvmsg(fdt, &msg, MSG_ERRQUEUE); if (ret == -1 && errno == EAGAIN) diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh deleted file mode 100755 index 8ff172f7bb1b..000000000000 --- a/tools/testing/selftests/net/toeplitz.sh +++ /dev/null @@ -1,199 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# extended toeplitz test: test rxhash plus, optionally, either (1) rss mapping -# from rxhash to rx queue ('-rss') or (2) rps mapping from rxhash to cpu -# ('-rps <rps_map>') -# -# irq-pattern-prefix can be derived from /sys/kernel/irq/*/action, -# which is a driver-specific encoding. -# -# invoke as ./toeplitz.sh (-i <iface>) -u|-t -4|-6 \ -# [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)] - -source setup_loopback.sh -readonly SERVER_IP4="192.168.1.200/24" -readonly SERVER_IP6="fda8::1/64" -readonly SERVER_MAC="aa:00:00:00:00:02" - -readonly CLIENT_IP4="192.168.1.100/24" -readonly CLIENT_IP6="fda8::2/64" -readonly CLIENT_MAC="aa:00:00:00:00:01" - -PORT=8000 -KEY="$(</proc/sys/net/core/netdev_rss_key)" -TEST_RSS=false -RPS_MAP="" -PROTO_FLAG="" -IP_FLAG="" -DEV="eth0" - -# Return the number of rxqs among which RSS is configured to spread packets. -# This is determined by reading the RSS indirection table using ethtool. -get_rss_cfg_num_rxqs() { - echo $(ethtool -x "${DEV}" | - grep -E [[:space:]]+[0-9]+:[[:space:]]+ | - cut -d: -f2- | - awk '{$1=$1};1' | - tr ' ' '\n' | - sort -u | - wc -l) -} - -# Return a list of the receive irq handler cpus. -# The list is ordered by the irqs, so first rxq-0 cpu, then rxq-1 cpu, etc. -# Reads /sys/kernel/irq/ in order, so algorithm depends on -# irq_{rxq-0} < irq_{rxq-1}, etc. -get_rx_irq_cpus() { - CPUS="" - # sort so that irq 2 is read before irq 10 - SORTED_IRQS=$(for i in /sys/kernel/irq/*; do echo $i; done | sort -V) - # Consider only as many queues as RSS actually uses. We assume that - # if RSS_CFG_NUM_RXQS=N, then RSS uses rxqs 0-(N-1). - RSS_CFG_NUM_RXQS=$(get_rss_cfg_num_rxqs) - RXQ_COUNT=0 - - for i in ${SORTED_IRQS} - do - [[ "${RXQ_COUNT}" -lt "${RSS_CFG_NUM_RXQS}" ]] || break - # lookup relevant IRQs by action name - [[ -e "$i/actions" ]] || continue - cat "$i/actions" | grep -q "${IRQ_PATTERN}" || continue - irqname=$(<"$i/actions") - - # does the IRQ get called - irqcount=$(cat "$i/per_cpu_count" | tr -d '0,') - [[ -n "${irqcount}" ]] || continue - - # lookup CPU - irq=$(basename "$i") - cpu=$(cat "/proc/irq/$irq/smp_affinity_list") - - if [[ -z "${CPUS}" ]]; then - CPUS="${cpu}" - else - CPUS="${CPUS},${cpu}" - fi - RXQ_COUNT=$((RXQ_COUNT+1)) - done - - echo "${CPUS}" -} - -get_disable_rfs_cmd() { - echo "echo 0 > /proc/sys/net/core/rps_sock_flow_entries;" -} - -get_set_rps_bitmaps_cmd() { - CMD="" - for i in /sys/class/net/${DEV}/queues/rx-*/rps_cpus - do - CMD="${CMD} echo $1 > ${i};" - done - - echo "${CMD}" -} - -get_disable_rps_cmd() { - echo "$(get_set_rps_bitmaps_cmd 0)" -} - -die() { - echo "$1" - exit 1 -} - -check_nic_rxhash_enabled() { - local -r pattern="receive-hashing:\ on" - - ethtool -k "${DEV}" | grep -q "${pattern}" || die "rxhash must be enabled" -} - -parse_opts() { - local prog=$0 - shift 1 - - while [[ "$1" =~ "-" ]]; do - if [[ "$1" = "-irq_prefix" ]]; then - shift - IRQ_PATTERN="^$1-[0-9]*$" - elif [[ "$1" = "-u" || "$1" = "-t" ]]; then - PROTO_FLAG="$1" - elif [[ "$1" = "-4" ]]; then - IP_FLAG="$1" - SERVER_IP="${SERVER_IP4}" - CLIENT_IP="${CLIENT_IP4}" - elif [[ "$1" = "-6" ]]; then - IP_FLAG="$1" - SERVER_IP="${SERVER_IP6}" - CLIENT_IP="${CLIENT_IP6}" - elif [[ "$1" = "-rss" ]]; then - TEST_RSS=true - elif [[ "$1" = "-rps" ]]; then - shift - RPS_MAP="$1" - elif [[ "$1" = "-i" ]]; then - shift - DEV="$1" - else - die "Usage: ${prog} (-i <iface>) -u|-t -4|-6 \ - [(-rss -irq_prefix <irq-pattern-prefix>)|(-rps <rps_map>)]" - fi - shift - done -} - -setup() { - setup_loopback_environment "${DEV}" - - # Set up server_ns namespace and client_ns namespace - setup_macvlan_ns "${DEV}" $server_ns server \ - "${SERVER_MAC}" "${SERVER_IP}" - setup_macvlan_ns "${DEV}" $client_ns client \ - "${CLIENT_MAC}" "${CLIENT_IP}" -} - -cleanup() { - cleanup_macvlan_ns $server_ns server $client_ns client - cleanup_loopback "${DEV}" -} - -parse_opts $0 $@ - -setup -trap cleanup EXIT - -check_nic_rxhash_enabled - -# Actual test starts here -if [[ "${TEST_RSS}" = true ]]; then - # RPS/RFS must be disabled because they move packets between cpus, - # which breaks the PACKET_FANOUT_CPU identification of RSS decisions. - eval "$(get_disable_rfs_cmd) $(get_disable_rps_cmd)" \ - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ - -C "$(get_rx_irq_cpus)" -s -v & -elif [[ ! -z "${RPS_MAP}" ]]; then - eval "$(get_disable_rfs_cmd) $(get_set_rps_bitmaps_cmd ${RPS_MAP})" \ - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 \ - -r "0x${RPS_MAP}" -s -v & -else - ip netns exec $server_ns ./toeplitz "${IP_FLAG}" "${PROTO_FLAG}" \ - -d "${PORT}" -i "${DEV}" -k "${KEY}" -T 1000 -s -v & -fi - -server_pid=$! - -ip netns exec $client_ns ./toeplitz_client.sh "${PROTO_FLAG}" \ - "${IP_FLAG}" "${SERVER_IP%%/*}" "${PORT}" & - -client_pid=$! - -wait "${server_pid}" -exit_code=$? -kill -9 "${client_pid}" -if [[ "${exit_code}" -eq 0 ]]; then - echo "Test Succeeded!" -fi -exit "${exit_code}" diff --git a/tools/testing/selftests/net/toeplitz_client.sh b/tools/testing/selftests/net/toeplitz_client.sh deleted file mode 100755 index 2fef34f4aba1..000000000000 --- a/tools/testing/selftests/net/toeplitz_client.sh +++ /dev/null @@ -1,28 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# A simple program for generating traffic for the toeplitz test. -# -# This program sends packets periodically for, conservatively, 20 seconds. The -# intent is for the calling program to kill this program once it is no longer -# needed, rather than waiting for the 20 second expiration. - -send_traffic() { - expiration=$((SECONDS+20)) - while [[ "${SECONDS}" -lt "${expiration}" ]] - do - if [[ "${PROTO}" == "-u" ]]; then - echo "msg $i" | nc "${IPVER}" -u -w 0 "${ADDR}" "${PORT}" - else - echo "msg $i" | nc "${IPVER}" -w 0 "${ADDR}" "${PORT}" - fi - sleep 0.001 - done -} - -PROTO=$1 -IPVER=$2 -ADDR=$3 -PORT=$4 - -send_traffic diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index dae91eb97d69..bcc14688661d 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -217,7 +217,7 @@ static void print_timestamp_usr(void) static void print_timestamp(struct scm_timestamping *tss, int tstype, int tskey, int payload_len) { - const char *tsname; + const char *tsname = NULL; validate_key(tskey, tstype); diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 5288e768b207..68625362add2 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -236,7 +236,7 @@ TEST_F(user, perf_empty_events) { ASSERT_EQ(1 << reg.enable_bit, self->check); /* Ensure write shows up at correct offset */ - ASSERT_NE(-1, write(self->data_fd, ®.write_index, + ASSERT_NE(-1, write(self->data_fd, (void *)®.write_index, sizeof(reg.write_index))); val = (void *)(((char *)perf_page) + perf_page->data_offset); ASSERT_EQ(PERF_RECORD_SAMPLE, *val); diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index 240409bf5f8a..69ec0c856481 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -4,9 +4,12 @@ #include <fcntl.h> #include <string.h> -#include <linux/vfio.h> + +#include <uapi/linux/types.h> +#include <linux/iommufd.h> #include <linux/list.h> #include <linux/pci_regs.h> +#include <linux/vfio.h> #include "../../../kselftest.h" @@ -185,6 +188,13 @@ struct vfio_pci_device { struct vfio_pci_driver driver; }; +struct iova_allocator { + struct iommu_iova_range *ranges; + u32 nranges; + u32 range_idx; + u64 range_offset; +}; + /* * Return the BDF string of the device that the test should use. * @@ -206,6 +216,13 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_ void vfio_pci_device_cleanup(struct vfio_pci_device *device); void vfio_pci_device_reset(struct vfio_pci_device *device); +struct iommu_iova_range *vfio_pci_iova_ranges(struct vfio_pci_device *device, + u32 *nranges); + +struct iova_allocator *iova_allocator_init(struct vfio_pci_device *device); +void iova_allocator_cleanup(struct iova_allocator *allocator); +iova_t iova_allocator_alloc(struct iova_allocator *allocator, size_t size); + int __vfio_pci_dma_map(struct vfio_pci_device *device, struct vfio_dma_region *region); int __vfio_pci_dma_unmap(struct vfio_pci_device *device, diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index a381fd253aa7..b479a359da12 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -12,11 +12,12 @@ #include <sys/mman.h> #include <uapi/linux/types.h> +#include <linux/iommufd.h> #include <linux/limits.h> #include <linux/mman.h> +#include <linux/overflow.h> #include <linux/types.h> #include <linux/vfio.h> -#include <linux/iommufd.h> #include "../../../kselftest.h" #include <vfio_util.h> @@ -29,6 +30,249 @@ VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \ } while (0) +static struct vfio_info_cap_header *next_cap_hdr(void *buf, u32 bufsz, + u32 *cap_offset) +{ + struct vfio_info_cap_header *hdr; + + if (!*cap_offset) + return NULL; + + VFIO_ASSERT_LT(*cap_offset, bufsz); + VFIO_ASSERT_GE(bufsz - *cap_offset, sizeof(*hdr)); + + hdr = (struct vfio_info_cap_header *)((u8 *)buf + *cap_offset); + *cap_offset = hdr->next; + + return hdr; +} + +static struct vfio_info_cap_header *vfio_iommu_info_cap_hdr(struct vfio_iommu_type1_info *info, + u16 cap_id) +{ + struct vfio_info_cap_header *hdr; + u32 cap_offset = info->cap_offset; + u32 max_depth; + u32 depth = 0; + + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) + return NULL; + + if (cap_offset) + VFIO_ASSERT_GE(cap_offset, sizeof(*info)); + + max_depth = (info->argsz - sizeof(*info)) / sizeof(*hdr); + + while ((hdr = next_cap_hdr(info, info->argsz, &cap_offset))) { + depth++; + VFIO_ASSERT_LE(depth, max_depth, "Capability chain contains a cycle\n"); + + if (hdr->id == cap_id) + return hdr; + } + + return NULL; +} + +/* Return buffer including capability chain, if present. Free with free() */ +static struct vfio_iommu_type1_info *vfio_iommu_get_info(struct vfio_pci_device *device) +{ + struct vfio_iommu_type1_info *info; + + info = malloc(sizeof(*info)); + VFIO_ASSERT_NOT_NULL(info); + + *info = (struct vfio_iommu_type1_info) { + .argsz = sizeof(*info), + }; + + ioctl_assert(device->container_fd, VFIO_IOMMU_GET_INFO, info); + VFIO_ASSERT_GE(info->argsz, sizeof(*info)); + + info = realloc(info, info->argsz); + VFIO_ASSERT_NOT_NULL(info); + + ioctl_assert(device->container_fd, VFIO_IOMMU_GET_INFO, info); + VFIO_ASSERT_GE(info->argsz, sizeof(*info)); + + return info; +} + +/* + * Return iova ranges for the device's container. Normalize vfio_iommu_type1 to + * report iommufd's iommu_iova_range. Free with free(). + */ +static struct iommu_iova_range *vfio_iommu_iova_ranges(struct vfio_pci_device *device, + u32 *nranges) +{ + struct vfio_iommu_type1_info_cap_iova_range *cap_range; + struct vfio_iommu_type1_info *info; + struct vfio_info_cap_header *hdr; + struct iommu_iova_range *ranges = NULL; + + info = vfio_iommu_get_info(device); + hdr = vfio_iommu_info_cap_hdr(info, VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE); + VFIO_ASSERT_NOT_NULL(hdr); + + cap_range = container_of(hdr, struct vfio_iommu_type1_info_cap_iova_range, header); + VFIO_ASSERT_GT(cap_range->nr_iovas, 0); + + ranges = calloc(cap_range->nr_iovas, sizeof(*ranges)); + VFIO_ASSERT_NOT_NULL(ranges); + + for (u32 i = 0; i < cap_range->nr_iovas; i++) { + ranges[i] = (struct iommu_iova_range){ + .start = cap_range->iova_ranges[i].start, + .last = cap_range->iova_ranges[i].end, + }; + } + + *nranges = cap_range->nr_iovas; + + free(info); + return ranges; +} + +/* Return iova ranges of the device's IOAS. Free with free() */ +static struct iommu_iova_range *iommufd_iova_ranges(struct vfio_pci_device *device, + u32 *nranges) +{ + struct iommu_iova_range *ranges; + int ret; + + struct iommu_ioas_iova_ranges query = { + .size = sizeof(query), + .ioas_id = device->ioas_id, + }; + + ret = ioctl(device->iommufd, IOMMU_IOAS_IOVA_RANGES, &query); + VFIO_ASSERT_EQ(ret, -1); + VFIO_ASSERT_EQ(errno, EMSGSIZE); + VFIO_ASSERT_GT(query.num_iovas, 0); + + ranges = calloc(query.num_iovas, sizeof(*ranges)); + VFIO_ASSERT_NOT_NULL(ranges); + + query.allowed_iovas = (uintptr_t)ranges; + + ioctl_assert(device->iommufd, IOMMU_IOAS_IOVA_RANGES, &query); + *nranges = query.num_iovas; + + return ranges; +} + +static int iova_range_comp(const void *a, const void *b) +{ + const struct iommu_iova_range *ra = a, *rb = b; + + if (ra->start < rb->start) + return -1; + + if (ra->start > rb->start) + return 1; + + return 0; +} + +/* Return sorted IOVA ranges of the device. Free with free(). */ +struct iommu_iova_range *vfio_pci_iova_ranges(struct vfio_pci_device *device, + u32 *nranges) +{ + struct iommu_iova_range *ranges; + + if (device->iommufd) + ranges = iommufd_iova_ranges(device, nranges); + else + ranges = vfio_iommu_iova_ranges(device, nranges); + + if (!ranges) + return NULL; + + VFIO_ASSERT_GT(*nranges, 0); + + /* Sort and check that ranges are sane and non-overlapping */ + qsort(ranges, *nranges, sizeof(*ranges), iova_range_comp); + VFIO_ASSERT_LT(ranges[0].start, ranges[0].last); + + for (u32 i = 1; i < *nranges; i++) { + VFIO_ASSERT_LT(ranges[i].start, ranges[i].last); + VFIO_ASSERT_LT(ranges[i - 1].last, ranges[i].start); + } + + return ranges; +} + +struct iova_allocator *iova_allocator_init(struct vfio_pci_device *device) +{ + struct iova_allocator *allocator; + struct iommu_iova_range *ranges; + u32 nranges; + + ranges = vfio_pci_iova_ranges(device, &nranges); + VFIO_ASSERT_NOT_NULL(ranges); + + allocator = malloc(sizeof(*allocator)); + VFIO_ASSERT_NOT_NULL(allocator); + + *allocator = (struct iova_allocator){ + .ranges = ranges, + .nranges = nranges, + .range_idx = 0, + .range_offset = 0, + }; + + return allocator; +} + +void iova_allocator_cleanup(struct iova_allocator *allocator) +{ + free(allocator->ranges); + free(allocator); +} + +iova_t iova_allocator_alloc(struct iova_allocator *allocator, size_t size) +{ + VFIO_ASSERT_GT(size, 0, "Invalid size arg, zero\n"); + VFIO_ASSERT_EQ(size & (size - 1), 0, "Invalid size arg, non-power-of-2\n"); + + for (;;) { + struct iommu_iova_range *range; + iova_t iova, last; + + VFIO_ASSERT_LT(allocator->range_idx, allocator->nranges, + "IOVA allocator out of space\n"); + + range = &allocator->ranges[allocator->range_idx]; + iova = range->start + allocator->range_offset; + + /* Check for sufficient space at the current offset */ + if (check_add_overflow(iova, size - 1, &last) || + last > range->last) + goto next_range; + + /* Align iova to size */ + iova = last & ~(size - 1); + + /* Check for sufficient space at the aligned iova */ + if (check_add_overflow(iova, size - 1, &last) || + last > range->last) + goto next_range; + + if (last == range->last) { + allocator->range_idx++; + allocator->range_offset = 0; + } else { + allocator->range_offset = last - range->start + 1; + } + + return iova; + +next_range: + allocator->range_idx++; + allocator->range_offset = 0; + } +} + iova_t __to_iova(struct vfio_pci_device *device, void *vaddr) { struct vfio_dma_region *region; diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 4f1ea79a200c..102603d4407d 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -3,6 +3,8 @@ #include <sys/mman.h> #include <unistd.h> +#include <uapi/linux/types.h> +#include <linux/iommufd.h> #include <linux/limits.h> #include <linux/mman.h> #include <linux/sizes.h> @@ -93,6 +95,7 @@ static int iommu_mapping_get(const char *bdf, u64 iova, FIXTURE(vfio_dma_mapping_test) { struct vfio_pci_device *device; + struct iova_allocator *iova_allocator; }; FIXTURE_VARIANT(vfio_dma_mapping_test) { @@ -117,10 +120,12 @@ FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous_hugetlb_1gb, SZ_1G, MAP_HUGETLB | FIXTURE_SETUP(vfio_dma_mapping_test) { self->device = vfio_pci_device_init(device_bdf, variant->iommu_mode); + self->iova_allocator = iova_allocator_init(self->device); } FIXTURE_TEARDOWN(vfio_dma_mapping_test) { + iova_allocator_cleanup(self->iova_allocator); vfio_pci_device_cleanup(self->device); } @@ -142,7 +147,7 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) else ASSERT_NE(region.vaddr, MAP_FAILED); - region.iova = (u64)region.vaddr; + region.iova = iova_allocator_alloc(self->iova_allocator, size); region.size = size; vfio_pci_dma_map(self->device, ®ion); @@ -219,7 +224,10 @@ FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(); FIXTURE_SETUP(vfio_dma_map_limit_test) { struct vfio_dma_region *region = &self->region; + struct iommu_iova_range *ranges; u64 region_size = getpagesize(); + iova_t last_iova; + u32 nranges; /* * Over-allocate mmap by double the size to provide enough backing vaddr @@ -232,8 +240,13 @@ FIXTURE_SETUP(vfio_dma_map_limit_test) MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); ASSERT_NE(region->vaddr, MAP_FAILED); - /* One page prior to the end of address space */ - region->iova = ~(iova_t)0 & ~(region_size - 1); + ranges = vfio_pci_iova_ranges(self->device, &nranges); + VFIO_ASSERT_NOT_NULL(ranges); + last_iova = ranges[nranges - 1].last; + free(ranges); + + /* One page prior to the last iova */ + region->iova = last_iova & ~(region_size - 1); region->size = region_size; } @@ -276,6 +289,7 @@ TEST_F(vfio_dma_map_limit_test, overflow) struct vfio_dma_region *region = &self->region; int rc; + region->iova = ~(iova_t)0 & ~(region->size - 1); region->size = self->mmap_size; rc = __vfio_pci_dma_map(self->device, region); diff --git a/tools/testing/selftests/vfio/vfio_pci_driver_test.c b/tools/testing/selftests/vfio/vfio_pci_driver_test.c index 2dbd70b7db62..f69eec8b928d 100644 --- a/tools/testing/selftests/vfio/vfio_pci_driver_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_driver_test.c @@ -19,6 +19,7 @@ static const char *device_bdf; } while (0) static void region_setup(struct vfio_pci_device *device, + struct iova_allocator *iova_allocator, struct vfio_dma_region *region, u64 size) { const int flags = MAP_SHARED | MAP_ANONYMOUS; @@ -29,7 +30,7 @@ static void region_setup(struct vfio_pci_device *device, VFIO_ASSERT_NE(vaddr, MAP_FAILED); region->vaddr = vaddr; - region->iova = (u64)vaddr; + region->iova = iova_allocator_alloc(iova_allocator, size); region->size = size; vfio_pci_dma_map(device, region); @@ -44,6 +45,7 @@ static void region_teardown(struct vfio_pci_device *device, FIXTURE(vfio_pci_driver_test) { struct vfio_pci_device *device; + struct iova_allocator *iova_allocator; struct vfio_dma_region memcpy_region; void *vaddr; int msi_fd; @@ -72,14 +74,15 @@ FIXTURE_SETUP(vfio_pci_driver_test) struct vfio_pci_driver *driver; self->device = vfio_pci_device_init(device_bdf, variant->iommu_mode); + self->iova_allocator = iova_allocator_init(self->device); driver = &self->device->driver; - region_setup(self->device, &self->memcpy_region, SZ_1G); - region_setup(self->device, &driver->region, SZ_2M); + region_setup(self->device, self->iova_allocator, &self->memcpy_region, SZ_1G); + region_setup(self->device, self->iova_allocator, &driver->region, SZ_2M); /* Any IOVA that doesn't overlap memcpy_region and driver->region. */ - self->unmapped_iova = 8UL * SZ_1G; + self->unmapped_iova = iova_allocator_alloc(self->iova_allocator, SZ_1G); vfio_pci_driver_init(self->device); self->msi_fd = self->device->msi_eventfds[driver->msi]; @@ -108,6 +111,7 @@ FIXTURE_TEARDOWN(vfio_pci_driver_test) region_teardown(self->device, &self->memcpy_region); region_teardown(self->device, &driver->region); + iova_allocator_cleanup(self->iova_allocator); vfio_pci_device_cleanup(self->device); } diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index d4517386e551..9e1250790f33 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -2015,6 +2015,11 @@ static void test_stream_transport_change_client(const struct test_opts *opts) exit(EXIT_FAILURE); } + /* Although setting SO_LINGER does not affect the original test + * for null-ptr-deref, it may trigger a lockdep warning. + */ + enable_so_linger(s, 1); + ret = connect(s, (struct sockaddr *)&sa, sizeof(sa)); /* The connect can fail due to signals coming from the thread, * or because the receiver connection queue is full. @@ -2352,7 +2357,7 @@ static struct test_case test_cases[] = { .run_server = test_stream_nolinger_server, }, { - .name = "SOCK_STREAM transport change null-ptr-deref", + .name = "SOCK_STREAM transport change null-ptr-deref, lockdep warn", .run_client = test_stream_transport_change_client, .run_server = test_stream_transport_change_server, }, |