diff options
819 files changed, 18099 insertions, 12396 deletions
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore index c298bab3d320..7d1b30aae874 100644 --- a/.get_maintainer.ignore +++ b/.get_maintainer.ignore @@ -1,4 +1,5 @@ Alan Cox <alan@lxorguk.ukuu.org.uk> Alan Cox <root@hraefn.swansea.linux.org.uk> Christoph Hellwig <hch@lst.de> +Jeff Kirsher <jeffrey.t.kirsher@intel.com> Marc Gonzalez <marc.w.gonzalez@free.fr> diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 5bff64d256c2..84aa25e0d14d 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -96,3 +96,26 @@ Description: Indicates the absolute minimum limit of bytes allowed to be queued on this network device transmit queue. Default value is 0. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_thrs +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Tx completion stall detection threshold in ms. Kernel will + guarantee to detect all stalls longer than this threshold but + may also detect stalls longer than half of the threshold. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_cnt +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Number of detected Tx completion stalls. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_max +Date: Jan 2024 +KernelVersion: 6.9 +Contact: netdev@vger.kernel.org +Description: + Longest detected Tx completion stall. Write 0 to clear. diff --git a/Documentation/devicetree/bindings/leds/leds-pwm-multicolor.yaml b/Documentation/devicetree/bindings/leds/leds-pwm-multicolor.yaml index 5edfbe347341..a31a202afe5c 100644 --- a/Documentation/devicetree/bindings/leds/leds-pwm-multicolor.yaml +++ b/Documentation/devicetree/bindings/leds/leds-pwm-multicolor.yaml @@ -41,6 +41,8 @@ properties: pwm-names: true + active-low: true + color: true required: diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index 890f7858d0dc..de7ba7f345a9 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -46,6 +46,7 @@ properties: - enum: - renesas,etheravb-r8a779a0 # R-Car V3U - renesas,etheravb-r8a779g0 # R-Car V4H + - renesas,etheravb-r8a779h0 # R-Car V4M - const: renesas,etheravb-rcar-gen4 # R-Car Gen4 - items: diff --git a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml index 475aff7714d6..ea35d19be829 100644 --- a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml @@ -65,9 +65,11 @@ properties: rx-internal-delay-ps: enum: [0, 1800] + default: 0 tx-internal-delay-ps: enum: [0, 2000] + default: 0 '#address-cells': const: 1 diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml index 8f23254c0458..784866ea392b 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -84,10 +84,10 @@ properties: description: | If present, select the RMII operation mode. Two modes are available: - - RMII master, where the PHY operates from a 25MHz clock reference, - provided by a crystal or a CMOS-level oscillator - - RMII slave, where the PHY operates from a 50MHz clock reference, - provided by a CMOS-level oscillator + - RMII master, where the PHY outputs a 50MHz reference clock which can + be connected to the MAC. + - RMII slave, where the PHY expects a 50MHz reference clock input + shared with the MAC. The RMII operation mode can also be configured by its straps. If the strap pin is not set correctly or not set at all, then this can be used to configure it. diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml index 252207adbc54..eabceb849537 100644 --- a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml +++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml @@ -19,9 +19,6 @@ description: | Alternatively, it can specify the wireless part of the MT7628/MT7688 or MT7622/MT7986 SoC. -allOf: - - $ref: ieee80211.yaml# - properties: compatible: enum: @@ -38,7 +35,12 @@ properties: MT7986 should contain 3 regions consys, dcm, and sku, in this order. interrupts: - maxItems: 1 + minItems: 1 + items: + - description: major interrupt for rings + - description: additional interrupt for ring 19 + - description: additional interrupt for ring 4 + - description: additional interrupt for ring 5 power-domains: maxItems: 1 @@ -217,6 +219,24 @@ required: - compatible - reg +allOf: + - $ref: ieee80211.yaml# + - if: + properties: + compatible: + contains: + enum: + - mediatek,mt7981-wmac + - mediatek,mt7986-wmac + then: + properties: + interrupts: + minItems: 4 + else: + properties: + interrupts: + maxItems: 1 + unevaluatedProperties: false examples: @@ -293,7 +313,10 @@ examples: reg = <0x18000000 0x1000000>, <0x10003000 0x1000>, <0x11d10000 0x1000>; - interrupts = <GIC_SPI 213 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 213 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 214 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 215 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 216 IRQ_TYPE_LEVEL_HIGH>; clocks = <&topckgen 50>, <&topckgen 62>; clock-names = "mcu", "ap2conn"; diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml index 7758a55dd328..9b3ef4bc3732 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml @@ -8,6 +8,7 @@ title: Qualcomm Technologies ath10k wireless devices maintainers: - Kalle Valo <kvalo@kernel.org> + - Jeff Johnson <jjohnson@kernel.org> description: Qualcomm Technologies, Inc. IEEE 802.11ac devices. diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml index 817f02a8b481..41d023797d7d 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml @@ -9,6 +9,7 @@ title: Qualcomm Technologies ath11k wireless devices (PCIe) maintainers: - Kalle Valo <kvalo@kernel.org> + - Jeff Johnson <jjohnson@kernel.org> description: | Qualcomm Technologies IEEE 802.11ax PCIe devices diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml index 7d5f982a3d09..672282cdfc2f 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml @@ -9,6 +9,7 @@ title: Qualcomm Technologies ath11k wireless devices maintainers: - Kalle Valo <kvalo@kernel.org> + - Jeff Johnson <jjohnson@kernel.org> description: | These are dt entries for Qualcomm Technologies, Inc. IEEE 802.11ax diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index e3d593841aa7..ea8d16600e16 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -545,7 +545,7 @@ In such scenario, dpll device input signal shall be also configurable to drive dpll with signal recovered from the PHY netdevice. This is done by exposing a pin to the netdevice - attaching pin to the netdevice itself with -``netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``. +``dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``. Exposed pin id handle ``DPLL_A_PIN_ID`` is then identifiable by the user as it is attached to rtnetlink respond to get ``RTM_NEWLINK`` command in nested attribute ``IFLA_DPLL_PIN``. diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index c58f7153fcf8..4dfd899a1661 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -11,7 +11,7 @@ $defs: minimum: 0 len-or-define: type: [ string, integer ] - pattern: ^[0-9A-Za-z_]+( - 1)?$ + pattern: ^[0-9A-Za-z_-]+( - 1)?$ minimum: 0 len-or-limit: # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. @@ -126,8 +126,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -208,6 +209,11 @@ properties: exact-len: description: Exact length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + unterminated-ok: + description: | + For string attributes, do not check whether attribute + contains the terminating null character. + type: boolean sub-type: *attr-type display-hint: &display-hint description: | @@ -261,14 +267,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] list: description: List of commands type: array @@ -370,3 +378,22 @@ properties: type: string # End genetlink-c flags: *cmd_flags + + kernel-family: + description: Additional global attributes used for kernel C code generation. + type: object + additionalProperties: False + properties: + headers: + description: | + List of extra headers which should be included in the source + of the generated code. + type: array + items: + type: string + sock-priv: + description: | + Literal name of the type which is used within the kernel + to store the socket state. The type / structure is internal + to the kernel, and is not defined in the spec. + type: string diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 938703088306..b48ad3b1cc32 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -11,7 +11,7 @@ $defs: minimum: 0 len-or-define: type: [ string, integer ] - pattern: ^[0-9A-Za-z_]+( - 1)?$ + pattern: ^[0-9A-Za-z_-]+( - 1)?$ minimum: 0 len-or-limit: # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. @@ -168,8 +168,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -251,6 +252,11 @@ properties: exact-len: description: Exact length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + unterminated-ok: + description: | + For string attributes, do not check whether attribute + contains the terminating null character. + type: boolean sub-type: *attr-type display-hint: *display-hint # Start genetlink-c @@ -304,14 +310,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] # Start genetlink-legacy fixed-header: &fixed-header description: | @@ -431,3 +439,22 @@ properties: type: string # End genetlink-c flags: *cmd_flags + + kernel-family: + description: Additional global attributes used for kernel C code generation. + type: object + additionalProperties: False + properties: + headers: + description: | + List of extra headers which should be included in the source + of the generated code. + type: array + items: + type: string + sock-priv: + description: | + Literal name of the type which is used within the kernel + to store the socket state. The type / structure is internal + to the kernel, and is not defined in the spec. + type: string diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 3283bf458ff1..ebd6ee743fcc 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -11,7 +11,7 @@ $defs: minimum: 0 len-or-define: type: [ string, integer ] - pattern: ^[0-9A-Za-z_]+( - 1)?$ + pattern: ^[0-9A-Za-z_-]+( - 1)?$ minimum: 0 len-or-limit: # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. @@ -328,3 +328,22 @@ properties: The name for the group, used to form the define and the value of the define. type: string flags: *cmd_flags + + kernel-family: + description: Additional global attributes used for kernel C code generation. + type: object + additionalProperties: False + properties: + headers: + description: | + List of extra headers which should be included in the source + of the generated code. + type: array + items: + type: string + sock-priv: + description: | + Literal name of the type which is used within the kernel + to store the socket state. The type / structure is internal + to the kernel, and is not defined in the spec. + type: string diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index ac4e05415f2f..a76e54cbadbc 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -11,7 +11,7 @@ $defs: minimum: 0 len-or-define: type: [ string, integer ] - pattern: ^[0-9A-Za-z_]+( - 1)?$ + pattern: ^[0-9A-Za-z_-]+( - 1)?$ minimum: 0 # Schema for specs @@ -189,8 +189,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -270,6 +271,11 @@ properties: exact-len: description: Exact length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + unterminated-ok: + description: | + For string attributes, do not check whether attribute + contains the terminating null character. + type: boolean sub-type: *attr-type display-hint: *display-hint # Start genetlink-c @@ -371,14 +377,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] # Start genetlink-legacy fixed-header: &fixed-header description: | diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 8dc1df5cfae7..95b0eb1486bf 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -312,6 +312,7 @@ attribute-sets: - name: capabilities type: u32 + enum: pin-capabilities - name: parent-device type: nest diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index 49f90cfb4698..af525ed29792 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -292,13 +292,14 @@ operations: - name: get-addr doc: Get endpoint information - attribute-set: endpoint + attribute-set: attr dont-validate: [ strict ] flags: [ uns-admin-perm ] do: &get-addr-attrs request: attributes: - addr + - token reply: attributes: - addr diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 3addac970680..76352dbd2be4 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -74,6 +74,10 @@ definitions: name: queue-type type: enum entries: [ rx, tx ] + - + name: qstats-scope + type: flags + entries: [ queue ] attribute-sets: - @@ -265,6 +269,73 @@ attribute-sets: doc: ID of the NAPI instance which services this queue. type: u32 + - + name: qstats + doc: | + Get device statistics, scoped to a device or a queue. + These statistics extend (and partially duplicate) statistics available + in struct rtnl_link_stats64. + Value of the `scope` attribute determines how statistics are + aggregated. When aggregated for the entire device the statistics + represent the total number of events since last explicit reset of + the device (i.e. not a reconfiguration like changing queue count). + When reported per-queue, however, the statistics may not add + up to the total number of events, will only be reported for currently + active objects, and will likely report the number of events since last + reconfiguration. + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which stats belong. + type: u32 + checks: + min: 1 + - + name: queue-type + doc: Queue type as rx, tx, for queue-id. + type: u32 + enum: queue-type + - + name: queue-id + doc: Queue ID, if stats are scoped to a single queue instance. + type: u32 + - + name: scope + doc: | + What object type should be used to iterate over the stats. + type: uint + enum: qstats-scope + - + name: rx-packets + doc: | + Number of wire packets successfully received and passed to the stack. + For drivers supporting XDP, XDP is considered the first layer + of the stack, so packets consumed by XDP are still counted here. + type: uint + value: 8 # reserve some attr ids in case we need more metadata later + - + name: rx-bytes + doc: Successfully received bytes, see `rx-packets`. + type: uint + - + name: tx-packets + doc: | + Number of wire packets successfully sent. Packet is considered to be + successfully sent once it is in device memory (usually this means + the device has issued a DMA completion for the packet). + type: uint + - + name: tx-bytes + doc: Successfully sent bytes, see `tx-packets`. + type: uint + - + name: rx-alloc-fail + doc: | + Number of times skb or buffer allocation failed on the Rx datapath. + Allocation failure may, or may not result in a packet drop, depending + on driver implementation and whether system recovers quickly. + type: uint + operations: list: - @@ -405,6 +476,26 @@ operations: attributes: - ifindex reply: *napi-get-op + - + name: qstats-get + doc: | + Get / dump fine grained statistics. Which statistics are reported + depends on the device and the driver, and whether the driver stores + software counters per-queue. + attribute-set: qstats + dump: + request: + attributes: + - scope + reply: + attributes: + - ifindex + - queue-type + - queue-id + - rx-packets + - rx-bytes + - tx-packets + - tx-bytes mcast-groups: list: diff --git a/Documentation/netlink/specs/nlctrl.yaml b/Documentation/netlink/specs/nlctrl.yaml new file mode 100644 index 000000000000..b1632b95f725 --- /dev/null +++ b/Documentation/netlink/specs/nlctrl.yaml @@ -0,0 +1,206 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: nlctrl +protocol: genetlink-legacy +uapi-header: linux/genetlink.h + +doc: | + genetlink meta-family that exposes information about all genetlink + families registered in the kernel (including itself). + +definitions: + - + name: op-flags + type: flags + enum-name: + entries: + - admin-perm + - cmd-cap-do + - cmd-cap-dump + - cmd-cap-haspol + - uns-admin-perm + - + name: attr-type + enum-name: netlink-attribute-type + type: enum + entries: + - invalid + - flag + - u8 + - u16 + - u32 + - u64 + - s8 + - s16 + - s32 + - s64 + - binary + - string + - nul-string + - nested + - nested-array + - bitfield32 + - sint + - uint + +attribute-sets: + - + name: ctrl-attrs + name-prefix: ctrl-attr- + attributes: + - + name: family-id + type: u16 + - + name: family-name + type: string + - + name: version + type: u32 + - + name: hdrsize + type: u32 + - + name: maxattr + type: u32 + - + name: ops + type: array-nest + nested-attributes: op-attrs + - + name: mcast-groups + type: array-nest + nested-attributes: mcast-group-attrs + - + name: policy + type: nest-type-value + type-value: [ policy-id, attr-id ] + nested-attributes: policy-attrs + - + name: op-policy + type: nest-type-value + type-value: [ op-id ] + nested-attributes: op-policy-attrs + - + name: op + type: u32 + - + name: mcast-group-attrs + name-prefix: ctrl-attr-mcast-grp- + enum-name: + attributes: + - + name: name + type: string + - + name: id + type: u32 + - + name: op-attrs + name-prefix: ctrl-attr-op- + enum-name: + attributes: + - + name: id + type: u32 + - + name: flags + type: u32 + enum: op-flags + enum-as-flags: true + - + name: policy-attrs + name-prefix: nl-policy-type-attr- + enum-name: + attributes: + - + name: type + type: u32 + enum: attr-type + - + name: min-value-s + type: s64 + - + name: max-value-s + type: s64 + - + name: min-value-u + type: u64 + - + name: max-value-u + type: u64 + - + name: min-length + type: u32 + - + name: max-length + type: u32 + - + name: policy-idx + type: u32 + - + name: policy-maxtype + type: u32 + - + name: bitfield32-mask + type: u32 + - + name: mask + type: u64 + - + name: pad + type: pad + - + name: op-policy-attrs + name-prefix: ctrl-attr-policy- + enum-name: + attributes: + - + name: do + type: u32 + - + name: dump + type: u32 + +operations: + enum-model: directional + name-prefix: ctrl-cmd- + list: + - + name: getfamily + doc: Get / dump genetlink families + attribute-set: ctrl-attrs + do: + request: + value: 3 + attributes: + - family-name + reply: &all-attrs + value: 1 + attributes: + - family-id + - family-name + - hdrsize + - maxattr + - mcast-groups + - ops + - version + dump: + reply: *all-attrs + - + name: getpolicy + doc: Get / dump genetlink policies + attribute-set: ctrl-attrs + dump: + request: + value: 10 + attributes: + - family-name + - family-id + - op + reply: + value: 10 + attributes: + - family-id + - op-policy + - policy diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index 5038e54586af..934752f675ba 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -368,15 +368,28 @@ more options for Receive Side Scaling (RSS) hash byte configuration. # ethtool -N <ethX> rx-flow-hash <type> <option> Where <type> is: - tcp4 signifying TCP over IPv4 - udp4 signifying UDP over IPv4 - tcp6 signifying TCP over IPv6 - udp6 signifying UDP over IPv6 + tcp4 signifying TCP over IPv4 + udp4 signifying UDP over IPv4 + gtpc4 signifying GTP-C over IPv4 + gtpc4t signifying GTP-C (include TEID) over IPv4 + gtpu4 signifying GTP-U over IPV4 + gtpu4e signifying GTP-U and Extension Header over IPV4 + gtpu4u signifying GTP-U PSC Uplink over IPV4 + gtpu4d signifying GTP-U PSC Downlink over IPV4 + tcp6 signifying TCP over IPv6 + udp6 signifying UDP over IPv6 + gtpc6 signifying GTP-C over IPv6 + gtpc6t signifying GTP-C (include TEID) over IPv6 + gtpu6 signifying GTP-U over IPV6 + gtpu6e signifying GTP-U and Extension Header over IPV6 + gtpu6u signifying GTP-U PSC Uplink over IPV6 + gtpu6d signifying GTP-U PSC Downlink over IPV6 And <option> is one or more of: s Hash on the IP source address of the Rx packet. d Hash on the IP destination address of the Rx packet. f Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet. n Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet. + e Hash on GTP Packet on TEID (4bytes) of the Rx packet. Accelerated Receive Flow Steering (aRFS) diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 69f3d6dcd9fd..473d72c36d61 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -74,6 +74,7 @@ Contents: mpls-sysctl mptcp-sysctl multiqueue + multi-pf-netdev napi net_cachelines/index netconsole diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst new file mode 100644 index 000000000000..be8e4bcadf11 --- /dev/null +++ b/Documentation/networking/multi-pf-netdev.rst @@ -0,0 +1,174 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +=============== +Multi-PF Netdev +=============== + +Contents +======== + +- `Background`_ +- `Overview`_ +- `mlx5 implementation`_ +- `Channels distribution`_ +- `Observability`_ +- `Steering`_ +- `Mutually exclusive features`_ + +Background +========== + +The Multi-PF NIC technology enables several CPUs within a multi-socket server to connect directly to +the network, each through its own dedicated PCIe interface. Through either a connection harness that +splits the PCIe lanes between two cards or by bifurcating a PCIe slot for a single card. This +results in eliminating the network traffic traversing over the internal bus between the sockets, +significantly reducing overhead and latency, in addition to reducing CPU utilization and increasing +network throughput. + +Overview +======== + +The feature adds support for combining multiple PFs of the same port in a Multi-PF environment under +one netdev instance. It is implemented in the netdev layer. Lower-layer instances like pci func, +sysfs entry, and devlink are kept separate. +Passing traffic through different devices belonging to different NUMA sockets saves cross-NUMA +traffic and allows apps running on the same netdev from different NUMAs to still feel a sense of +proximity to the device and achieve improved performance. + +mlx5 implementation +=================== + +Multi-PF or Socket-direct in mlx5 is achieved by grouping PFs together which belong to the same +NIC and has the socket-direct property enabled, once all PFs are probed, we create a single netdev +to represent all of them, symmetrically, we destroy the netdev whenever any of the PFs is removed. + +The netdev network channels are distributed between all devices, a proper configuration would utilize +the correct close NUMA node when working on a certain app/CPU. + +We pick one PF to be a primary (leader), and it fills a special role. The other devices +(secondaries) are disconnected from the network at the chip level (set to silent mode). In silent +mode, no south <-> north traffic flowing directly through a secondary PF. It needs the assistance of +the leader PF (east <-> west traffic) to function. All Rx/Tx traffic is steered through the primary +to/from the secondaries. + +Currently, we limit the support to PFs only, and up to two PFs (sockets). + +Channels distribution +===================== + +We distribute the channels between the different PFs to achieve local NUMA node performance +on multiple NUMA nodes. + +Each combined channel works against one specific PF, creating all its datapath queues against it. We +distribute channels to PFs in a round-robin policy. + +:: + + Example for 2 PFs and 5 channels: + +--------+--------+ + | ch idx | PF idx | + +--------+--------+ + | 0 | 0 | + | 1 | 1 | + | 2 | 0 | + | 3 | 1 | + | 4 | 0 | + +--------+--------+ + + +The reason we prefer round-robin is, it is less influenced by changes in the number of channels. The +mapping between a channel index and a PF is fixed, no matter how many channels the user configures. +As the channel stats are persistent across channel's closure, changing the mapping every single time +would turn the accumulative stats less representing of the channel's history. + +This is achieved by using the correct core device instance (mdev) in each channel, instead of them +all using the same instance under "priv->mdev". + +Observability +============= +The relation between PF, irq, napi, and queue can be observed via netlink spec: + +$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' +[{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'}, + {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}] + +$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' +[{'id': 543, 'ifindex': 13, 'irq': 42}, + {'id': 542, 'ifindex': 13, 'irq': 41}, + {'id': 541, 'ifindex': 13, 'irq': 40}, + {'id': 540, 'ifindex': 13, 'irq': 39}, + {'id': 539, 'ifindex': 13, 'irq': 36}] + +Here you can clearly observe our channels distribution policy: + +$ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 +/proc/irq/36/mlx5_comp1@pci:0000:08:00.0 +/proc/irq/39/mlx5_comp1@pci:0000:09:00.0 +/proc/irq/40/mlx5_comp2@pci:0000:08:00.0 +/proc/irq/41/mlx5_comp2@pci:0000:09:00.0 +/proc/irq/42/mlx5_comp3@pci:0000:08:00.0 + +Steering +======== +Secondary PFs are set to "silent" mode, meaning they are disconnected from the network. + +In Rx, the steering tables belong to the primary PF only, and it is its role to distribute incoming +traffic to other PFs, via cross-vhca steering capabilities. Still maintain a single default RSS table, +that is capable of pointing to the receive queues of a different PF. + +In Tx, the primary PF creates a new Tx flow table, which is aliased by the secondaries, so they can +go out to the network through it. + +In addition, we set default XPS configuration that, based on the CPU, selects an SQ belonging to the +PF on the same node as the CPU. + +XPS default config example: + +NUMA node(s): 2 +NUMA node0 CPU(s): 0-11 +NUMA node1 CPU(s): 12-23 + +PF0 on node0, PF1 on node1. + +- /sys/class/net/eth2/queues/tx-0/xps_cpus:000001 +- /sys/class/net/eth2/queues/tx-1/xps_cpus:001000 +- /sys/class/net/eth2/queues/tx-2/xps_cpus:000002 +- /sys/class/net/eth2/queues/tx-3/xps_cpus:002000 +- /sys/class/net/eth2/queues/tx-4/xps_cpus:000004 +- /sys/class/net/eth2/queues/tx-5/xps_cpus:004000 +- /sys/class/net/eth2/queues/tx-6/xps_cpus:000008 +- /sys/class/net/eth2/queues/tx-7/xps_cpus:008000 +- /sys/class/net/eth2/queues/tx-8/xps_cpus:000010 +- /sys/class/net/eth2/queues/tx-9/xps_cpus:010000 +- /sys/class/net/eth2/queues/tx-10/xps_cpus:000020 +- /sys/class/net/eth2/queues/tx-11/xps_cpus:020000 +- /sys/class/net/eth2/queues/tx-12/xps_cpus:000040 +- /sys/class/net/eth2/queues/tx-13/xps_cpus:040000 +- /sys/class/net/eth2/queues/tx-14/xps_cpus:000080 +- /sys/class/net/eth2/queues/tx-15/xps_cpus:080000 +- /sys/class/net/eth2/queues/tx-16/xps_cpus:000100 +- /sys/class/net/eth2/queues/tx-17/xps_cpus:100000 +- /sys/class/net/eth2/queues/tx-18/xps_cpus:000200 +- /sys/class/net/eth2/queues/tx-19/xps_cpus:200000 +- /sys/class/net/eth2/queues/tx-20/xps_cpus:000400 +- /sys/class/net/eth2/queues/tx-21/xps_cpus:400000 +- /sys/class/net/eth2/queues/tx-22/xps_cpus:000800 +- /sys/class/net/eth2/queues/tx-23/xps_cpus:800000 + +Mutually exclusive features +=========================== + +The nature of Multi-PF, where different channels work with different PFs, conflicts with +stateful features where the state is maintained in one of the PFs. +For example, in the TLS device-offload feature, special context objects are created per connection +and maintained in the PF. Transitioning between different RQs/SQs would break the feature. Hence, +we disable this combination for now. diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index b28c525e5d1e..d55c2a22ec7a 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -180,7 +180,7 @@ Custom user data can be appended to the end of messages with netconsole dynamic configuration enabled. User data entries can be modified without changing the "enabled" attribute of a target. -Directories (keys) under `userdata` are limited to 54 character length, and +Directories (keys) under `userdata` are limited to 53 character length, and data in `userdata/<key>/value` are limited to 200 bytes:: cd /sys/kernel/config/netconsole && mkdir cmdline0 @@ -197,8 +197,8 @@ Messages will now include this additional user data:: Sends:: 12,607,22085407756,-;This is a message - foo=bar - qux=baz + foo=bar + qux=baz Preview the userdata that will be appended with:: @@ -218,7 +218,7 @@ The `qux` key is omitted since it has no value:: echo "This is a message" > /dev/kmsg 12,607,22085407756,-;This is a message - foo=bar + foo=bar Delete `userdata` entries with `rmdir`:: diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst index 8054d33f449f..5bf285d73e8a 100644 --- a/Documentation/networking/sfp-phylink.rst +++ b/Documentation/networking/sfp-phylink.rst @@ -231,16 +231,136 @@ this documentation. For further information on these methods, please see the inline documentation in :c:type:`struct phylink_mac_ops <phylink_mac_ops>`. -9. Remove calls to of_parse_phandle() for the PHY, - of_phy_register_fixed_link() for fixed links etc. from the probe - function, and replace with: +9. Fill-in the :c:type:`struct phylink_config <phylink_config>` fields with + a reference to the :c:type:`struct device <device>` associated to your + :c:type:`struct net_device <net_device>`: .. code-block:: c - struct phylink *phylink; priv->phylink_config.dev = &dev.dev; priv->phylink_config.type = PHYLINK_NETDEV; + Fill-in the various speeds, pause and duplex modes your MAC can handle: + + .. code-block:: c + + priv->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + +10. Some Ethernet controllers work in pair with a PCS (Physical Coding Sublayer) + block, that can handle among other things the encoding/decoding, link + establishment detection and autonegotiation. While some MACs have internal + PCS whose operation is transparent, some other require dedicated PCS + configuration for the link to become functional. In that case, phylink + provides a PCS abstraction through :c:type:`struct phylink_pcs <phylink_pcs>`. + + Identify if your driver has one or more internal PCS blocks, and/or if + your controller can use an external PCS block that might be internally + connected to your controller. + + If your controller doesn't have any internal PCS, you can go to step 11. + + If your Ethernet controller contains one or several PCS blocks, create + one :c:type:`struct phylink_pcs <phylink_pcs>` instance per PCS block within + your driver's private data structure: + + .. code-block:: c + + struct phylink_pcs pcs; + + Populate the relevant :c:type:`struct phylink_pcs_ops <phylink_pcs_ops>` to + configure your PCS. Create a :c:func:`pcs_get_state` function that reports + the inband link state, a :c:func:`pcs_config` function to configure your + PCS according to phylink-provided parameters, and a :c:func:`pcs_validate` + function that report to phylink all accepted configuration parameters for + your PCS: + + .. code-block:: c + + struct phylink_pcs_ops foo_pcs_ops = { + .pcs_validate = foo_pcs_validate, + .pcs_get_state = foo_pcs_get_state, + .pcs_config = foo_pcs_config, + }; + + Arrange for PCS link state interrupts to be forwarded into + phylink, via: + + .. code-block:: c + + phylink_pcs_change(pcs, link_is_up); + + where ``link_is_up`` is true if the link is currently up or false + otherwise. If a PCS is unable to provide these interrupts, then + it should set ``pcs->pcs_poll = true;`` when creating the PCS. + +11. If your controller relies on, or accepts the presence of an external PCS + controlled through its own driver, add a pointer to a phylink_pcs instance + in your driver private data structure: + + .. code-block:: c + + struct phylink_pcs *pcs; + + The way of getting an instance of the actual PCS depends on the platform, + some PCS sit on an MDIO bus and are grabbed by passing a pointer to the + corresponding :c:type:`struct mii_bus <mii_bus>` and the PCS's address on + that bus. In this example, we assume the controller attaches to a Lynx PCS + instance: + + .. code-block:: c + + priv->pcs = lynx_pcs_create_mdiodev(bus, 0); + + Some PCS can be recovered based on firmware information: + + .. code-block:: c + + priv->pcs = lynx_pcs_create_fwnode(of_fwnode_handle(node)); + +12. Populate the :c:func:`mac_select_pcs` callback and add it to your + :c:type:`struct phylink_mac_ops <phylink_mac_ops>` set of ops. This function + must return a pointer to the relevant :c:type:`struct phylink_pcs <phylink_pcs>` + that will be used for the requested link configuration: + + .. code-block:: c + + static struct phylink_pcs *foo_select_pcs(struct phylink_config *config, + phy_interface_t interface) + { + struct foo_priv *priv = container_of(config, struct foo_priv, + phylink_config); + + if ( /* 'interface' needs a PCS to function */ ) + return priv->pcs; + + return NULL; + } + + See :c:func:`mvpp2_select_pcs` for an example of a driver that has multiple + internal PCS. + +13. Fill-in all the :c:type:`phy_interface_t <phy_interface_t>` (i.e. all MAC to + PHY link modes) that your MAC can output. The following example shows a + configuration for a MAC that can handle all RGMII modes, SGMII and 1000BaseX. + You must adjust these according to what your MAC and all PCS associated + with this MAC are capable of, and not just the interface you wish to use: + + .. code-block:: c + + phy_interface_set_rgmii(priv->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + priv->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + priv->phylink_config.supported_interfaces); + +14. Remove calls to of_parse_phandle() for the PHY, + of_phy_register_fixed_link() for fixed links etc. from the probe + function, and replace with: + + .. code-block:: c + + struct phylink *phylink; + phylink = phylink_create(&priv->phylink_config, node, phy_mode, &phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); @@ -249,14 +369,14 @@ this documentation. priv->phylink = phylink; - and arrange to destroy the phylink in the probe failure path as - appropriate and the removal path too by calling: + and arrange to destroy the phylink in the probe failure path as + appropriate and the removal path too by calling: - .. code-block:: c + .. code-block:: c phylink_destroy(priv->phylink); -10. Arrange for MAC link state interrupts to be forwarded into +15. Arrange for MAC link state interrupts to be forwarded into phylink, via: .. code-block:: c @@ -264,17 +384,16 @@ this documentation. phylink_mac_change(priv->phylink, link_is_up); where ``link_is_up`` is true if the link is currently up or false - otherwise. If a MAC is unable to provide these interrupts, then - it should set ``priv->phylink_config.pcs_poll = true;`` in step 9. + otherwise. -11. Verify that the driver does not call:: +16. Verify that the driver does not call:: netif_carrier_on() netif_carrier_off() - as these will interfere with phylink's tracking of the link state, - and cause phylink to omit calls via the :c:func:`mac_link_up` and - :c:func:`mac_link_down` methods. + as these will interfere with phylink's tracking of the link state, + and cause phylink to omit calls via the :c:func:`mac_link_up` and + :c:func:`mac_link_down` methods. Network drivers should call phylink_stop() and phylink_start() via their suspend/resume paths, which ensures that the appropriate diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 551b3cc29a41..75e017dfa825 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -41,6 +41,15 @@ If `-s` is specified once the detailed errors won't be shown. `ip` supports JSON formatting via the `-j` option. +Queue statistics +~~~~~~~~~~~~~~~~ + +Queue statistics are accessible via the netdev netlink family. + +Currently no widely distributed CLI exists to access those statistics. +Kernel development tools (ynl) can be used to experiment with them, +see `Documentation/userspace-api/netlink/intro-specs.rst`. + Protocol-specific statistics ---------------------------- @@ -147,6 +156,12 @@ Statistics are reported both in the responses to link information requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`, when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request). +netdev (netlink) +~~~~~~~~~~~~~~~~ + +`netdev` generic netlink family allows accessing page pool and per queue +statistics. + ethtool ------- diff --git a/Documentation/virt/hyperv/index.rst b/Documentation/virt/hyperv/index.rst index 4a7a1b738bbe..de447e11b4a5 100644 --- a/Documentation/virt/hyperv/index.rst +++ b/Documentation/virt/hyperv/index.rst @@ -10,3 +10,4 @@ Hyper-V Enlightenments overview vmbus clocks + vpci diff --git a/Documentation/virt/hyperv/vpci.rst b/Documentation/virt/hyperv/vpci.rst new file mode 100644 index 000000000000..b65b2126ede3 --- /dev/null +++ b/Documentation/virt/hyperv/vpci.rst @@ -0,0 +1,316 @@ +.. SPDX-License-Identifier: GPL-2.0 + +PCI pass-thru devices +========================= +In a Hyper-V guest VM, PCI pass-thru devices (also called +virtual PCI devices, or vPCI devices) are physical PCI devices +that are mapped directly into the VM's physical address space. +Guest device drivers can interact directly with the hardware +without intermediation by the host hypervisor. This approach +provides higher bandwidth access to the device with lower +latency, compared with devices that are virtualized by the +hypervisor. The device should appear to the guest just as it +would when running on bare metal, so no changes are required +to the Linux device drivers for the device. + +Hyper-V terminology for vPCI devices is "Discrete Device +Assignment" (DDA). Public documentation for Hyper-V DDA is +available here: `DDA`_ + +.. _DDA: https://learn.microsoft.com/en-us/windows-server/virtualization/hyper-v/plan/plan-for-deploying-devices-using-discrete-device-assignment + +DDA is typically used for storage controllers, such as NVMe, +and for GPUs. A similar mechanism for NICs is called SR-IOV +and produces the same benefits by allowing a guest device +driver to interact directly with the hardware. See Hyper-V +public documentation here: `SR-IOV`_ + +.. _SR-IOV: https://learn.microsoft.com/en-us/windows-hardware/drivers/network/overview-of-single-root-i-o-virtualization--sr-iov- + +This discussion of vPCI devices includes DDA and SR-IOV +devices. + +Device Presentation +------------------- +Hyper-V provides full PCI functionality for a vPCI device when +it is operating, so the Linux device driver for the device can +be used unchanged, provided it uses the correct Linux kernel +APIs for accessing PCI config space and for other integration +with Linux. But the initial detection of the PCI device and +its integration with the Linux PCI subsystem must use Hyper-V +specific mechanisms. Consequently, vPCI devices on Hyper-V +have a dual identity. They are initially presented to Linux +guests as VMBus devices via the standard VMBus "offer" +mechanism, so they have a VMBus identity and appear under +/sys/bus/vmbus/devices. The VMBus vPCI driver in Linux at +drivers/pci/controller/pci-hyperv.c handles a newly introduced +vPCI device by fabricating a PCI bus topology and creating all +the normal PCI device data structures in Linux that would +exist if the PCI device were discovered via ACPI on a bare- +metal system. Once those data structures are set up, the +device also has a normal PCI identity in Linux, and the normal +Linux device driver for the vPCI device can function as if it +were running in Linux on bare-metal. Because vPCI devices are +presented dynamically through the VMBus offer mechanism, they +do not appear in the Linux guest's ACPI tables. vPCI devices +may be added to a VM or removed from a VM at any time during +the life of the VM, and not just during initial boot. + +With this approach, the vPCI device is a VMBus device and a +PCI device at the same time. In response to the VMBus offer +message, the hv_pci_probe() function runs and establishes a +VMBus connection to the vPCI VSP on the Hyper-V host. That +connection has a single VMBus channel. The channel is used to +exchange messages with the vPCI VSP for the purpose of setting +up and configuring the vPCI device in Linux. Once the device +is fully configured in Linux as a PCI device, the VMBus +channel is used only if Linux changes the vCPU to be interrupted +in the guest, or if the vPCI device is removed from +the VM while the VM is running. The ongoing operation of the +device happens directly between the Linux device driver for +the device and the hardware, with VMBus and the VMBus channel +playing no role. + +PCI Device Setup +---------------- +PCI device setup follows a sequence that Hyper-V originally +created for Windows guests, and that can be ill-suited for +Linux guests due to differences in the overall structure of +the Linux PCI subsystem compared with Windows. Nonetheless, +with a bit of hackery in the Hyper-V virtual PCI driver for +Linux, the virtual PCI device is setup in Linux so that +generic Linux PCI subsystem code and the Linux driver for the +device "just work". + +Each vPCI device is set up in Linux to be in its own PCI +domain with a host bridge. The PCI domainID is derived from +bytes 4 and 5 of the instance GUID assigned to the VMBus vPCI +device. The Hyper-V host does not guarantee that these bytes +are unique, so hv_pci_probe() has an algorithm to resolve +collisions. The collision resolution is intended to be stable +across reboots of the same VM so that the PCI domainIDs don't +change, as the domainID appears in the user space +configuration of some devices. + +hv_pci_probe() allocates a guest MMIO range to be used as PCI +config space for the device. This MMIO range is communicated +to the Hyper-V host over the VMBus channel as part of telling +the host that the device is ready to enter d0. See +hv_pci_enter_d0(). When the guest subsequently accesses this +MMIO range, the Hyper-V host intercepts the accesses and maps +them to the physical device PCI config space. + +hv_pci_probe() also gets BAR information for the device from +the Hyper-V host, and uses this information to allocate MMIO +space for the BARs. That MMIO space is then setup to be +associated with the host bridge so that it works when generic +PCI subsystem code in Linux processes the BARs. + +Finally, hv_pci_probe() creates the root PCI bus. At this +point the Hyper-V virtual PCI driver hackery is done, and the +normal Linux PCI machinery for scanning the root bus works to +detect the device, to perform driver matching, and to +initialize the driver and device. + +PCI Device Removal +------------------ +A Hyper-V host may initiate removal of a vPCI device from a +guest VM at any time during the life of the VM. The removal +is instigated by an admin action taken on the Hyper-V host and +is not under the control of the guest OS. + +A guest VM is notified of the removal by an unsolicited +"Eject" message sent from the host to the guest over the VMBus +channel associated with the vPCI device. Upon receipt of such +a message, the Hyper-V virtual PCI driver in Linux +asynchronously invokes Linux kernel PCI subsystem calls to +shutdown and remove the device. When those calls are +complete, an "Ejection Complete" message is sent back to +Hyper-V over the VMBus channel indicating that the device has +been removed. At this point, Hyper-V sends a VMBus rescind +message to the Linux guest, which the VMBus driver in Linux +processes by removing the VMBus identity for the device. Once +that processing is complete, all vestiges of the device having +been present are gone from the Linux kernel. The rescind +message also indicates to the guest that Hyper-V has stopped +providing support for the vPCI device in the guest. If the +guest were to attempt to access that device's MMIO space, it +would be an invalid reference. Hypercalls affecting the device +return errors, and any further messages sent in the VMBus +channel are ignored. + +After sending the Eject message, Hyper-V allows the guest VM +60 seconds to cleanly shutdown the device and respond with +Ejection Complete before sending the VMBus rescind +message. If for any reason the Eject steps don't complete +within the allowed 60 seconds, the Hyper-V host forcibly +performs the rescind steps, which will likely result in +cascading errors in the guest because the device is now no +longer present from the guest standpoint and accessing the +device MMIO space will fail. + +Because ejection is asynchronous and can happen at any point +during the guest VM lifecycle, proper synchronization in the +Hyper-V virtual PCI driver is very tricky. Ejection has been +observed even before a newly offered vPCI device has been +fully setup. The Hyper-V virtual PCI driver has been updated +several times over the years to fix race conditions when +ejections happen at inopportune times. Care must be taken when +modifying this code to prevent re-introducing such problems. +See comments in the code. + +Interrupt Assignment +-------------------- +The Hyper-V virtual PCI driver supports vPCI devices using +MSI, multi-MSI, or MSI-X. Assigning the guest vCPU that will +receive the interrupt for a particular MSI or MSI-X message is +complex because of the way the Linux setup of IRQs maps onto +the Hyper-V interfaces. For the single-MSI and MSI-X cases, +Linux calls hv_compse_msi_msg() twice, with the first call +containing a dummy vCPU and the second call containing the +real vCPU. Furthermore, hv_irq_unmask() is finally called +(on x86) or the GICD registers are set (on arm64) to specify +the real vCPU again. Each of these three calls interact +with Hyper-V, which must decide which physical CPU should +receive the interrupt before it is forwarded to the guest VM. +Unfortunately, the Hyper-V decision-making process is a bit +limited, and can result in concentrating the physical +interrupts on a single CPU, causing a performance bottleneck. +See details about how this is resolved in the extensive +comment above the function hv_compose_msi_req_get_cpu(). + +The Hyper-V virtual PCI driver implements the +irq_chip.irq_compose_msi_msg function as hv_compose_msi_msg(). +Unfortunately, on Hyper-V the implementation requires sending +a VMBus message to the Hyper-V host and awaiting an interrupt +indicating receipt of a reply message. Since +irq_chip.irq_compose_msi_msg can be called with IRQ locks +held, it doesn't work to do the normal sleep until awakened by +the interrupt. Instead hv_compose_msi_msg() must send the +VMBus message, and then poll for the completion message. As +further complexity, the vPCI device could be ejected/rescinded +while the polling is in progress, so this scenario must be +detected as well. See comments in the code regarding this +very tricky area. + +Most of the code in the Hyper-V virtual PCI driver (pci- +hyperv.c) applies to Hyper-V and Linux guests running on x86 +and on arm64 architectures. But there are differences in how +interrupt assignments are managed. On x86, the Hyper-V +virtual PCI driver in the guest must make a hypercall to tell +Hyper-V which guest vCPU should be interrupted by each +MSI/MSI-X interrupt, and the x86 interrupt vector number that +the x86_vector IRQ domain has picked for the interrupt. This +hypercall is made by hv_arch_irq_unmask(). On arm64, the +Hyper-V virtual PCI driver manages the allocation of an SPI +for each MSI/MSI-X interrupt. The Hyper-V virtual PCI driver +stores the allocated SPI in the architectural GICD registers, +which Hyper-V emulates, so no hypercall is necessary as with +x86. Hyper-V does not support using LPIs for vPCI devices in +arm64 guest VMs because it does not emulate a GICv3 ITS. + +The Hyper-V virtual PCI driver in Linux supports vPCI devices +whose drivers create managed or unmanaged Linux IRQs. If the +smp_affinity for an unmanaged IRQ is updated via the /proc/irq +interface, the Hyper-V virtual PCI driver is called to tell +the Hyper-V host to change the interrupt targeting and +everything works properly. However, on x86 if the x86_vector +IRQ domain needs to reassign an interrupt vector due to +running out of vectors on a CPU, there's no path to inform the +Hyper-V host of the change, and things break. Fortunately, +guest VMs operate in a constrained device environment where +using all the vectors on a CPU doesn't happen. Since such a +problem is only a theoretical concern rather than a practical +concern, it has been left unaddressed. + +DMA +--- +By default, Hyper-V pins all guest VM memory in the host +when the VM is created, and programs the physical IOMMU to +allow the VM to have DMA access to all its memory. Hence +it is safe to assign PCI devices to the VM, and allow the +guest operating system to program the DMA transfers. The +physical IOMMU prevents a malicious guest from initiating +DMA to memory belonging to the host or to other VMs on the +host. From the Linux guest standpoint, such DMA transfers +are in "direct" mode since Hyper-V does not provide a virtual +IOMMU in the guest. + +Hyper-V assumes that physical PCI devices always perform +cache-coherent DMA. When running on x86, this behavior is +required by the architecture. When running on arm64, the +architecture allows for both cache-coherent and +non-cache-coherent devices, with the behavior of each device +specified in the ACPI DSDT. But when a PCI device is assigned +to a guest VM, that device does not appear in the DSDT, so the +Hyper-V VMBus driver propagates cache-coherency information +from the VMBus node in the ACPI DSDT to all VMBus devices, +including vPCI devices (since they have a dual identity as a VMBus +device and as a PCI device). See vmbus_dma_configure(). +Current Hyper-V versions always indicate that the VMBus is +cache coherent, so vPCI devices on arm64 always get marked as +cache coherent and the CPU does not perform any sync +operations as part of dma_map/unmap_*() calls. + +vPCI protocol versions +---------------------- +As previously described, during vPCI device setup and teardown +messages are passed over a VMBus channel between the Hyper-V +host and the Hyper-v vPCI driver in the Linux guest. Some +messages have been revised in newer versions of Hyper-V, so +the guest and host must agree on the vPCI protocol version to +be used. The version is negotiated when communication over +the VMBus channel is first established. See +hv_pci_protocol_negotiation(). Newer versions of the protocol +extend support to VMs with more than 64 vCPUs, and provide +additional information about the vPCI device, such as the +guest virtual NUMA node to which it is most closely affined in +the underlying hardware. + +Guest NUMA node affinity +------------------------ +When the vPCI protocol version provides it, the guest NUMA +node affinity of the vPCI device is stored as part of the Linux +device information for subsequent use by the Linux driver. See +hv_pci_assign_numa_node(). If the negotiated protocol version +does not support the host providing NUMA affinity information, +the Linux guest defaults the device NUMA node to 0. But even +when the negotiated protocol version includes NUMA affinity +information, the ability of the host to provide such +information depends on certain host configuration options. If +the guest receives NUMA node value "0", it could mean NUMA +node 0, or it could mean "no information is available". +Unfortunately it is not possible to distinguish the two cases +from the guest side. + +PCI config space access in a CoCo VM +------------------------------------ +Linux PCI device drivers access PCI config space using a +standard set of functions provided by the Linux PCI subsystem. +In Hyper-V guests these standard functions map to functions +hv_pcifront_read_config() and hv_pcifront_write_config() +in the Hyper-V virtual PCI driver. In normal VMs, +these hv_pcifront_*() functions directly access the PCI config +space, and the accesses trap to Hyper-V to be handled. +But in CoCo VMs, memory encryption prevents Hyper-V +from reading the guest instruction stream to emulate the +access, so the hv_pcifront_*() functions must invoke +hypercalls with explicit arguments describing the access to be +made. + +Config Block back-channel +------------------------- +The Hyper-V host and Hyper-V virtual PCI driver in Linux +together implement a non-standard back-channel communication +path between the host and guest. The back-channel path uses +messages sent over the VMBus channel associated with the vPCI +device. The functions hyperv_read_cfg_blk() and +hyperv_write_cfg_blk() are the primary interfaces provided to +other parts of the Linux kernel. As of this writing, these +interfaces are used only by the Mellanox mlx5 driver to pass +diagnostic data to a Hyper-V host running in the Azure public +cloud. The functions hyperv_read_cfg_blk() and +hyperv_write_cfg_blk() are implemented in a separate module +(pci-hyperv-intf.c, under CONFIG_PCI_HYPERV_INTERFACE) that +effectively stubs them out when running in non-Hyper-V +environments. diff --git a/MAINTAINERS b/MAINTAINERS index 04e5f7c20e30..fd66be5046f9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1395,6 +1395,7 @@ F: drivers/hwmon/max31760.c ANALOGBITS PLL LIBRARIES M: Paul Walmsley <paul.walmsley@sifive.com> +M: Samuel Holland <samuel.holland@sifive.com> S: Supported F: drivers/clk/analogbits/* F: include/linux/clk/analogbits* @@ -2156,7 +2157,7 @@ M: Shawn Guo <shawnguo@kernel.org> M: Sascha Hauer <s.hauer@pengutronix.de> R: Pengutronix Kernel Team <kernel@pengutronix.de> R: Fabio Estevam <festevam@gmail.com> -R: NXP Linux Team <linux-imx@nxp.com> +L: imx@lists.linux.dev L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git @@ -8505,7 +8506,7 @@ FREESCALE IMX / MXC FEC DRIVER M: Wei Fang <wei.fang@nxp.com> R: Shenwei Wang <shenwei.wang@nxp.com> R: Clark Wang <xiaoning.wang@nxp.com> -R: NXP Linux Team <linux-imx@nxp.com> +L: imx@lists.linux.dev L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/fsl,fec.yaml @@ -8540,7 +8541,7 @@ F: drivers/i2c/busses/i2c-imx.c FREESCALE IMX LPI2C DRIVER M: Dong Aisheng <aisheng.dong@nxp.com> L: linux-i2c@vger.kernel.org -L: linux-imx@nxp.com +L: imx@lists.linux.dev S: Maintained F: Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml F: drivers/i2c/busses/i2c-imx-lpi2c.c @@ -8600,6 +8601,13 @@ F: Documentation/devicetree/bindings/soc/fsl/cpm_qe/fsl,cpm1-scc-qmc.yaml F: drivers/soc/fsl/qe/qmc.c F: include/soc/fsl/qe/qmc.h +FREESCALE QUICC ENGINE QMC HDLC DRIVER +M: Herve Codina <herve.codina@bootlin.com> +L: netdev@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Maintained +F: drivers/net/wan/fsl_qmc_hdlc.c + FREESCALE QUICC ENGINE TSA DRIVER M: Herve Codina <herve.codina@bootlin.com> L: linuxppc-dev@lists.ozlabs.org @@ -15747,7 +15755,7 @@ F: drivers/iio/gyro/fxas21002c_spi.c NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER M: Haibo Chen <haibo.chen@nxp.com> L: linux-iio@vger.kernel.org -L: linux-imx@nxp.com +L: imx@lists.linux.dev S: Maintained F: Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml F: Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml @@ -15784,7 +15792,7 @@ F: drivers/gpu/drm/imx/dcss/ NXP i.MX 8QXP ADC DRIVER M: Cai Huoqing <cai.huoqing@linux.dev> M: Haibo Chen <haibo.chen@nxp.com> -L: linux-imx@nxp.com +L: imx@lists.linux.dev L: linux-iio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml @@ -15792,7 +15800,7 @@ F: drivers/iio/adc/imx8qxp-adc.c NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER M: Mirela Rabulea <mirela.rabulea@nxp.com> -R: NXP Linux Team <linux-imx@nxp.com> +L: imx@lists.linux.dev L: linux-media@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml @@ -15802,7 +15810,7 @@ NXP i.MX CLOCK DRIVERS M: Abel Vesa <abelvesa@kernel.org> R: Peng Fan <peng.fan@nxp.com> L: linux-clk@vger.kernel.org -L: linux-imx@nxp.com +L: imx@lists.linux.dev S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx F: Documentation/devicetree/bindings/clock/imx* @@ -16763,6 +16771,7 @@ F: drivers/pci/controller/dwc/*layerscape* PCI DRIVER FOR FU740 M: Paul Walmsley <paul.walmsley@sifive.com> M: Greentime Hu <greentime.hu@sifive.com> +M: Samuel Holland <samuel.holland@sifive.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml @@ -19680,7 +19689,7 @@ F: drivers/mmc/host/sdhci-of-at91.c SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER M: Haibo Chen <haibo.chen@nxp.com> -L: linux-imx@nxp.com +L: imx@lists.linux.dev L: linux-mmc@vger.kernel.org S: Maintained F: drivers/mmc/host/sdhci-esdhc-imx.c @@ -20015,36 +20024,15 @@ S: Maintained F: drivers/watchdog/simatic-ipc-wdt.c SIFIVE DRIVERS -M: Palmer Dabbelt <palmer@dabbelt.com> M: Paul Walmsley <paul.walmsley@sifive.com> +M: Samuel Holland <samuel.holland@sifive.com> L: linux-riscv@lists.infradead.org S: Supported +F: drivers/dma/sf-pdma/ N: sifive +K: fu[57]40 K: [^@]sifive -SIFIVE CACHE DRIVER -M: Conor Dooley <conor@kernel.org> -L: linux-riscv@lists.infradead.org -S: Maintained -F: Documentation/devicetree/bindings/cache/sifive,ccache0.yaml -F: drivers/cache/sifive_ccache.c - -SIFIVE FU540 SYSTEM-ON-CHIP -M: Paul Walmsley <paul.walmsley@sifive.com> -M: Palmer Dabbelt <palmer@dabbelt.com> -L: linux-riscv@lists.infradead.org -S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git -N: fu540 -K: fu540 - -SIFIVE PDMA DRIVER -M: Green Wan <green.wan@sifive.com> -S: Maintained -F: Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml -F: drivers/dma/sf-pdma/ - - SILEAD TOUCHSCREEN DRIVER M: Hans de Goede <hdegoede@redhat.com> L: linux-input@vger.kernel.org @@ -20253,8 +20241,8 @@ F: Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml F: drivers/net/ethernet/socionext/sni_ave.c SOCIONEXT (SNI) NETSEC NETWORK DRIVER -M: Jassi Brar <jaswinder.singh@linaro.org> M: Ilias Apalodimas <ilias.apalodimas@linaro.org> +M: Masahisa Kojima <kojima.masahisa@socionext.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/socionext,synquacer-netsec.yaml @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi index ebf7befcc11e..9c81c6baa2d3 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi @@ -834,16 +834,6 @@ <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>; clock-names = "pix", "axi"; status = "disabled"; - - port { - #address-cells = <1>; - #size-cells = <0>; - - lcdif_out_mipi_dsi: endpoint@0 { - reg = <0>; - remote-endpoint = <&mipi_dsi_in_lcdif>; - }; - }; }; mipi_csi: mipi-csi@30750000 { @@ -895,22 +885,6 @@ samsung,esc-clock-frequency = <20000000>; samsung,pll-clock-frequency = <24000000>; status = "disabled"; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - #address-cells = <1>; - #size-cells = <0>; - - mipi_dsi_in_lcdif: endpoint@0 { - reg = <0>; - remote-endpoint = <&lcdif_out_mipi_dsi>; - }; - }; - }; }; }; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0a90583f9f01..8f9dbe8d9029 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -297,6 +297,7 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_L4F00242T03=y CONFIG_LCD_PLATFORM=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_GPIO=y CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile index 91d505b385de..1f1f8d865d0e 100644 --- a/arch/arm64/boot/dts/allwinner/Makefile +++ b/arch/arm64/boot/dts/allwinner/Makefile @@ -42,5 +42,6 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-cb1-manta.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero2w.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 4ae4fdab461e..43f1d45ccc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -255,7 +255,7 @@ <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-rates = <13000000>, <13000000>, <156000000>; - reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 76c73daf546b..39a550c1cd26 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1820,7 +1820,7 @@ compatible = "fsl,imx8mp-ldb"; reg = <0x5c 0x4>, <0x128 0x4>; reg-names = "ldb", "lvds"; - clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; + clocks = <&clk IMX8MP_CLK_MEDIA_LDB_ROOT>; clock-names = "ldb"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index ea13c4a7027c..81a82933e350 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -175,7 +175,7 @@ status = "okay"; phy-handle = <&mgbe0_phy>; - phy-mode = "usxgmii"; + phy-mode = "10gbase-r"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 3f16595d099c..d1bd328892af 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -1459,7 +1459,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEAWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEA>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; status = "disabled"; }; @@ -1493,7 +1493,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEBWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF1>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; status = "disabled"; }; @@ -1527,7 +1527,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBECWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF2>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBED>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 8d41ed261adf..ee6f87c828ae 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -457,25 +457,6 @@ }; }; - mpm: interrupt-controller { - compatible = "qcom,mpm"; - qcom,rpm-msg-ram = <&apss_mpm>; - interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>; - mboxes = <&apcs_glb 1>; - interrupt-controller; - #interrupt-cells = <2>; - #power-domain-cells = <0>; - interrupt-parent = <&intc>; - qcom,mpm-pin-count = <96>; - qcom,mpm-pin-map = <2 184>, /* TSENS1 upper_lower_int */ - <52 243>, /* DWC3_PRI ss_phy_irq */ - <79 347>, /* DWC3_PRI hs_phy_irq */ - <80 352>, /* DWC3_SEC hs_phy_irq */ - <81 347>, /* QUSB2_PHY_PRI DP+DM */ - <82 352>, /* QUSB2_PHY_SEC DP+DM */ - <87 326>; /* SPMI */ - }; - psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -765,15 +746,8 @@ }; rpm_msg_ram: sram@68000 { - compatible = "qcom,rpm-msg-ram", "mmio-sram"; + compatible = "qcom,rpm-msg-ram"; reg = <0x00068000 0x6000>; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0x00068000 0x7000>; - - apss_mpm: sram@1b8 { - reg = <0x1b8 0x48>; - }; }; qfprom@74000 { @@ -856,8 +830,8 @@ reg = <0x004ad000 0x1000>, /* TM */ <0x004ac000 0x1000>; /* SROT */ #qcom,sensors = <8>; - interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "uplow", "critical"; #thermal-sensor-cells = <1>; }; @@ -1363,7 +1337,6 @@ interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; gpio-ranges = <&tlmm 0 0 150>; - wakeup-parent = <&mpm>; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -1891,7 +1864,7 @@ <0x0400a000 0x002100>; reg-names = "core", "chnls", "obsrvr", "intr", "cnfg"; interrupt-names = "periph_irq"; - interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>; qcom,ee = <0>; qcom,channel = <0>; #address-cells = <2>; @@ -3052,8 +3025,8 @@ #size-cells = <1>; ranges; - interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>, - <&mpm 52 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "ss_phy_irq"; clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts index ffc4406422ae..41215567b3ae 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts @@ -563,6 +563,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index def3976bd5bb..eb657e544961 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -722,6 +722,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 160e098f1075..f9849b8befbf 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -1304,6 +1304,9 @@ &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>, <&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts index 9d916edb1c73..be133a3d5cbe 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts @@ -622,7 +622,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; disp0_reset_n_active: disp0-reset-n-active-state { pins = "gpio133"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts index 592a67a47c78..b9151c2ddf2e 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts @@ -659,7 +659,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; bt_default: bt-default-state { bt-en-pins { diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 9bb2210c8d44..065ffd1b2f8a 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -69,7 +69,7 @@ enum rtas_function_index { RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE, RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2, RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW, - RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS, + RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW, RTAS_FNIDX__IBM_SCAN_LOG_DUMP, RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR, RTAS_FNIDX__IBM_SET_EEH_OPTION, @@ -164,7 +164,7 @@ typedef struct { #define RTAS_FN_IBM_READ_SLOT_RESET_STATE rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE) #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2 rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2) #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW) -#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS) +#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW) #define RTAS_FN_IBM_SCAN_LOG_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP) #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR) #define RTAS_FN_IBM_SET_EEH_OPTION rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 7e793b503e29..8064d9c3de86 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = { .name = "ibm,remove-pe-dma-window", }, - [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = { - .name = "ibm,reset-pe-dma-windows", + [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = { + /* + * Note: PAPR+ v2.13 7.3.31.4.1 spells this as + * "ibm,reset-pe-dma-windows" (plural), but RTAS + * implementations use the singular form in practice. + */ + .name = "ibm,reset-pe-dma-window", }, [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = { .name = "ibm,scan-log-dump", diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 496e16c588aa..e8c4129697b1 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb, struct iommu_table_ops iommu_table_lpar_multi_ops; -/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false; for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; + } + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; } - return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; } static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop; dn = pci_bus_to_OF_node(bus); pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); - if (dma_window == NULL) - pr_debug(" no ibm,dma-window property !\n"); + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + */ ppci = PCI_DN(pdn); @@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; } + /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..e3142ce531a0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -315,7 +315,6 @@ config AS_HAS_OPTION_ARCH # https://reviews.llvm.org/D123515 def_bool y depends on $(as-instr, .option arch$(comma) +m) - depends on !$(as-instr, .option arch$(comma) -i) source "arch/riscv/Kconfig.socs" source "arch/riscv/Kconfig.errata" diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 510014051f5d..2468c55933cd 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -424,6 +424,7 @@ # define CSR_STATUS CSR_MSTATUS # define CSR_IE CSR_MIE # define CSR_TVEC CSR_MTVEC +# define CSR_ENVCFG CSR_MENVCFG # define CSR_SCRATCH CSR_MSCRATCH # define CSR_EPC CSR_MEPC # define CSR_CAUSE CSR_MCAUSE @@ -448,6 +449,7 @@ # define CSR_STATUS CSR_SSTATUS # define CSR_IE CSR_SIE # define CSR_TVEC CSR_STVEC +# define CSR_ENVCFG CSR_SENVCFG # define CSR_SCRATCH CSR_SSCRATCH # define CSR_EPC CSR_SEPC # define CSR_CAUSE CSR_SCAUSE diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 329172122952..15055f9df4da 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 20f9c3ba2341..22deb7a2a6ec 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -11,8 +11,10 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h); #define arch_hugetlb_migration_supported arch_hugetlb_migration_supported +#endif #ifdef CONFIG_RISCV_ISA_SVNAPOT #define __HAVE_ARCH_HUGE_PTE_CLEAR diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 5340f818746b..1f2d2599c655 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -81,6 +81,8 @@ #define RISCV_ISA_EXT_ZTSO 72 #define RISCV_ISA_EXT_ZACAS 73 +#define RISCV_ISA_EXT_XLINUXENVCFG 127 + #define RISCV_ISA_EXT_MAX 128 #define RISCV_ISA_EXT_INVALID U32_MAX diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index d169a4f41a2e..c80bb9990d32 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -95,7 +95,13 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) __pud_free(mm, pud); } -#define __pud_free_tlb(tlb, pud, addr) pud_free((tlb)->mm, pud) +#define __pud_free_tlb(tlb, pud, addr) \ +do { \ + if (pgtable_l4_enabled) { \ + pagetable_pud_dtor(virt_to_ptdesc(pud)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \ + } \ +} while (0) #define p4d_alloc_one p4d_alloc_one static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -124,7 +130,11 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) __p4d_free(mm, p4d); } -#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#define __p4d_free_tlb(tlb, p4d, addr) \ +do { \ + if (pgtable_l5_enabled) \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ static inline void sync_kernel_mappings(pgd_t *pgd) @@ -149,7 +159,11 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #ifndef __PAGETABLE_PMD_FOLDED -#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) +#define __pmd_free_tlb(tlb, pmd, addr) \ +do { \ + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index b42017d76924..b99bd66107a6 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -136,7 +136,7 @@ enum napot_cont_order { * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable */ #define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) -#define _PAGE_NOCACHE_THEAD ((1UL < 61) | (1UL << 60)) +#define _PAGE_NOCACHE_THEAD ((1UL << 61) | (1UL << 60)) #define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60)) #define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 0c94260b5d0c..6066822e7396 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -84,7 +84,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -439,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/asm-generic/pgtable.h diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 02f87867389a..491296a335d0 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -14,6 +14,7 @@ struct suspend_context { struct pt_regs regs; /* Saved and restored by high-level functions */ unsigned long scratch; + unsigned long envcfg; unsigned long tvec; unsigned long ie; #ifdef CONFIG_MMU diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 924d01b56c9a..51f6dfe19745 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) return true; } -#ifdef CONFIG_RISCV_ISA_SVNAPOT -#include <linux/pgtable.h> +#endif -#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size -static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, - u64 pfn, unsigned int max_page_shift) -{ - unsigned long map_size = PAGE_SIZE; - unsigned long size, order; - - if (!has_svnapot()) - return map_size; - - for_each_napot_order_rev(order) { - if (napot_cont_shift(order) > max_page_shift) - continue; - - size = napot_cont_size(order); - if (end - addr < size) - continue; - - if (!IS_ALIGNED(addr, size)) - continue; - - if (!IS_ALIGNED(PFN_PHYS(pfn), size)) - continue; - - map_size = size; - break; - } - - return map_size; -} - -#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift -static inline int arch_vmap_pte_supported_shift(unsigned long size) -{ - int shift = PAGE_SHIFT; - unsigned long order; - - if (!has_svnapot()) - return shift; - - WARN_ON_ONCE(size >= PMD_SIZE); - - for_each_napot_order_rev(order) { - if (napot_cont_size(order) > size) - continue; - - if (!IS_ALIGNED(size, napot_cont_size(order))) - continue; - - shift = napot_cont_shift(order); - break; - } - - return shift; -} - -#endif /* CONFIG_RISCV_ISA_SVNAPOT */ -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* _ASM_RISCV_VMALLOC_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..604d6bf7e476 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -46,6 +47,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 89920f84d0a3..79a5a35fab96 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -24,6 +24,7 @@ #include <asm/hwprobe.h> #include <asm/patch.h> #include <asm/processor.h> +#include <asm/sbi.h> #include <asm/vector.h> #include "copy-unaligned.h" @@ -202,6 +203,16 @@ static const unsigned int riscv_zvbb_exts[] = { }; /* + * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V + * privileged ISA, the existence of the CSRs is implied by any extension which + * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the + * existence of the CSR, and treat it as a subset of those other extensions. + */ +static const unsigned int riscv_xlinuxenvcfg_exts[] = { + RISCV_ISA_EXT_XLINUXENVCFG +}; + +/* * The canonical order of ISA extension names in the ISA string is defined in * chapter 27 of the unprivileged specification. * @@ -250,8 +261,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), - __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), - __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts), + __RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts), __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), __RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND), __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), @@ -539,6 +550,20 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) } /* + * "V" in ISA strings is ambiguous in practice: it should mean + * just the standard V-1.0 but vendors aren't well behaved. + * Many vendors with T-Head CPU cores which implement the 0.7.1 + * version of the vector specification put "v" into their DTs. + * CPU cores with the ratified spec will contain non-zero + * marchid. + */ + if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID && + riscv_cached_marchid(cpu) == 0x0) { + this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; + clear_bit(RISCV_ISA_EXT_v, isainfo->isa); + } + + /* * All "okay" hart should have same isa. Set HWCAP based on * common capabilities of every "okay" hart, in case they don't * have. @@ -950,7 +975,7 @@ arch_initcall(check_unaligned_access_all_cpus); void riscv_user_isa_enable(void) { if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) - csr_set(CSR_SENVCFG, ENVCFG_CBZE); + csr_set(CSR_ENVCFG, ENVCFG_CBZE); } #ifdef CONFIG_RISCV_ALTERNATIVE diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 000000000000..c8115ec8fb30 --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 239509367e42..299795341e8a 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -15,6 +15,8 @@ void suspend_save_csrs(struct suspend_context *context) { context->scratch = csr_read(CSR_SCRATCH); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + context->envcfg = csr_read(CSR_ENVCFG); context->tvec = csr_read(CSR_TVEC); context->ie = csr_read(CSR_IE); @@ -36,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context) void suspend_restore_csrs(struct suspend_context *context) { csr_write(CSR_SCRATCH, context->scratch); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + csr_write(CSR_ENVCFG, context->envcfg); csr_write(CSR_TVEC, context->tvec); csr_write(CSR_IE, context->ie); diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 29c7606414d2..5ef2a6891158 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -426,10 +426,12 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return __hugetlb_valid_size(size); } +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { return __hugetlb_valid_size(huge_page_size(h)); } +#endif #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 96e6c51515f5..cf1b78cb2d04 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -16,6 +16,11 @@ extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 7dcbf153ad72..768d73de0d09 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -15,6 +15,7 @@ #include <asm/io.h> #include <asm/coco.h> #include <asm/mem_encrypt.h> +#include <asm/set_memory.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> @@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } /* + * When transitioning memory between encrypted and decrypted, the caller + * of set_memory_encrypted() or set_memory_decrypted() is responsible for + * ensuring that the memory isn't in use and isn't referenced while the + * transition is in progress. The transition has multiple steps, and the + * memory is in an inconsistent state until all steps are complete. A + * reference while the state is inconsistent could result in an exception + * that can't be cleanly fixed up. + * + * But the Linux kernel load_unaligned_zeropad() mechanism could cause a + * stray reference that can't be prevented by the caller, so Linux has + * specific code to handle this case. But when the #VC and #VE exceptions + * routed to a paravisor, the specific code doesn't work. To avoid this + * problem, mark the pages as "not present" while the transition is in + * progress. If load_unaligned_zeropad() causes a stray reference, a normal + * page fault is generated instead of #VC or #VE, and the page-fault-based + * handlers for load_unaligned_zeropad() resolve the reference. When the + * transition is complete, hv_vtom_set_host_visibility() marks the pages + * as "present" again. + */ +static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +{ + return !set_memory_np(kbuffer, pagecount); +} + +/* * hv_vtom_set_host_visibility - Set specified memory visible to host. * * In Isolation VM, all guest memory is encrypted from host and guest @@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; + phys_addr_t paddr; + void *vaddr; int ret = 0; bool result = true; int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); - if (!pfn_array) - return false; + if (!pfn_array) { + result = false; + goto err_set_memory_p; + } for (i = 0, pfn = 0; i < pagecount; i++) { - pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + /* + * Use slow_virt_to_phys() because the PRESENT bit has been + * temporarily cleared in the PTEs. slow_virt_to_phys() works + * without the PRESENT bit while virt_to_hvpfn() or similar + * does not. + */ + vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE); + paddr = slow_virt_to_phys(vaddr); + pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT; pfn++; if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { @@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo } } - err_free_pfn_array: +err_free_pfn_array: kfree(pfn_array); + +err_set_memory_p: + /* + * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present() + * did. Do this even if there is an error earlier in this function in + * order to avoid leaving the memory range in a "broken" state. Setting + * the PRESENT bits shouldn't fail, but return an error if it does. + */ + if (set_memory_p(kbuffer, pagecount)) + result = false; + return result; } static bool hv_vtom_tlb_flush_required(bool private) { - return true; + /* + * Since hv_vtom_clear_present() marks the PTEs as "not present" + * and flushes the TLB, they can't be in the TLB. That makes the + * flush controlled by this function redundant, so return "false". + */ + return false; } static bool hv_vtom_cache_flush_required(void) @@ -608,6 +662,7 @@ void __init hv_vtom_init(void) x86_platform.hyper.is_private_mmio = hv_is_private_mmio; x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required; + x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present; x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index a5e89641bd2d..9aee31862b4a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0b97bcde70c6..fbc4e60d027c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); if (this_cpu->c_early_init) @@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8fc9624..40dec9b56f87 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380d..b66f540de054 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index e9b448d1b1b7..102880404046 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address) * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * - * This could be optimized, but it is only intended to be - * used at initialization time, and keeping it - * unoptimized should increase the testing coverage for - * the more obscure platforms. + * Note that as long as the PTEs are well-formed with correct PFNs, this + * works without checking the PRESENT bit in the leaf PTE. This is unlike + * the similar vmalloc_to_page() and derivatives. Callers may depend on + * this behavior. + * + * This could be optimized, but it is only used in paths that are not perf + * sensitive, and keeping it unoptimized should increase the testing coverage + * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { @@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_p(unsigned long *addr, int numpages) -{ - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); -} - /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_p(&addr, 1); + return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ @@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages) CPA_NO_CHECK_ALIAS, NULL); } +int set_memory_p(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 50d8ce20ae5b..9fb1575f8d88 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -2550,14 +2550,12 @@ static int fore200e_sba_probe(struct platform_device *op) return 0; } -static int fore200e_sba_remove(struct platform_device *op) +static void fore200e_sba_remove(struct platform_device *op) { struct fore200e *fore200e = dev_get_drvdata(&op->dev); fore200e_shutdown(fore200e); kfree(fore200e); - - return 0; } static const struct of_device_id fore200e_sba_match[] = { @@ -2574,7 +2572,7 @@ static struct platform_driver fore200e_sba_driver = { .of_match_table = fore200e_sba_match, }, .probe = fore200e_sba_probe, - .remove = fore200e_sba_remove, + .remove_new = fore200e_sba_remove, }; #endif diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 0a5445ac5e1b..f9a7c790d7e2 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -11,6 +11,7 @@ #include <linux/firmware.h> #include <linux/dmi.h> #include <linux/of.h> +#include <linux/string.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -543,8 +544,6 @@ static const char *btbcm_get_board_name(struct device *dev) struct device_node *root; char *board_type; const char *tmp; - int len; - int i; root = of_find_node_by_path("/"); if (!root) @@ -554,13 +553,8 @@ static const char *btbcm_get_board_name(struct device *dev) return NULL; /* get rid of any '/' in the compatible string */ - len = strlen(tmp) + 1; - board_type = devm_kzalloc(dev, len, GFP_KERNEL); - strscpy(board_type, tmp, len); - for (i = 0; i < len; i++) { - if (board_type[i] == '/') - board_type[i] = '-'; - } + board_type = devm_kstrdup(dev, tmp, GFP_KERNEL); + strreplace(board_type, '/', '-'); of_node_put(root); return board_type; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index cdc5c08824a0..6ba7f5d1b837 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -441,7 +441,7 @@ int btintel_read_version(struct hci_dev *hdev, struct intel_version *ver) return PTR_ERR(skb); } - if (skb->len != sizeof(*ver)) { + if (!skb || skb->len != sizeof(*ver)) { bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; @@ -2670,6 +2670,119 @@ static void btintel_set_msft_opcode(struct hci_dev *hdev, u8 hw_variant) } } +static void btintel_print_fseq_info(struct hci_dev *hdev) +{ + struct sk_buff *skb; + u8 *p; + u32 val; + const char *str; + + skb = __hci_cmd_sync(hdev, 0xfcb3, 0, NULL, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_dbg(hdev, "Reading fseq status command failed (%ld)", + PTR_ERR(skb)); + return; + } + + if (skb->len < (sizeof(u32) * 16 + 2)) { + bt_dev_dbg(hdev, "Malformed packet of length %u received", + skb->len); + kfree_skb(skb); + return; + } + + p = skb_pull_data(skb, 1); + if (*p) { + bt_dev_dbg(hdev, "Failed to get fseq status (0x%2.2x)", *p); + kfree_skb(skb); + return; + } + + p = skb_pull_data(skb, 1); + switch (*p) { + case 0: + str = "Success"; + break; + case 1: + str = "Fatal error"; + break; + case 2: + str = "Semaphore acquire error"; + break; + default: + str = "Unknown error"; + break; + } + + if (*p) { + bt_dev_err(hdev, "Fseq status: %s (0x%2.2x)", str, *p); + kfree_skb(skb); + return; + } + + bt_dev_info(hdev, "Fseq status: %s (0x%2.2x)", str, *p); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Reason: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Global version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Installed version: 0x%8.8x", val); + + p = skb->data; + skb_pull_data(skb, 4); + bt_dev_info(hdev, "Fseq executed: %2.2u.%2.2u.%2.2u.%2.2u", p[0], p[1], + p[2], p[3]); + + p = skb->data; + skb_pull_data(skb, 4); + bt_dev_info(hdev, "Fseq BT Top: %2.2u.%2.2u.%2.2u.%2.2u", p[0], p[1], + p[2], p[3]); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq Top init version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq Cnvio init version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq MBX Wifi file version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq BT version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq Top reset address: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq MBX timeout: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq MBX ack: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq CNVi id: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq CNVr id: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq Error handle: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq Magic noalive indication: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq OTP version: 0x%8.8x", val); + + val = get_unaligned_le32(skb_pull_data(skb, 4)); + bt_dev_dbg(hdev, "Fseq MBX otp version: 0x%8.8x", val); + + kfree_skb(skb); +} + static int btintel_setup_combined(struct hci_dev *hdev) { const u8 param[1] = { 0xFF }; @@ -2902,6 +3015,7 @@ static int btintel_setup_combined(struct hci_dev *hdev) err = btintel_bootloader_setup_tlv(hdev, &ver_tlv); btintel_register_devcoredump_support(hdev); + btintel_print_fseq_info(hdev); break; default: bt_dev_err(hdev, "Unsupported Intel hw variant (%u)", diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index aaabb732082c..ac8ebccd3507 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -372,8 +372,10 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) struct btmediatek_data *data = hci_get_priv(hdev); int err; - if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) + if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { + kfree_skb(skb); return 0; + } switch (data->cd_info.state) { case HCI_DEVCOREDUMP_IDLE: @@ -420,5 +422,6 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_MT7622); MODULE_FIRMWARE(FIRMWARE_MT7663); MODULE_FIRMWARE(FIRMWARE_MT7668); +MODULE_FIRMWARE(FIRMWARE_MT7922); MODULE_FIRMWARE(FIRMWARE_MT7961); MODULE_FIRMWARE(FIRMWARE_MT7925); diff --git a/drivers/bluetooth/btmtk.h b/drivers/bluetooth/btmtk.h index 56f5502baadf..cbcdb99a22e6 100644 --- a/drivers/bluetooth/btmtk.h +++ b/drivers/bluetooth/btmtk.h @@ -4,6 +4,7 @@ #define FIRMWARE_MT7622 "mediatek/mt7622pr2h.bin" #define FIRMWARE_MT7663 "mediatek/mt7663pr2h.bin" #define FIRMWARE_MT7668 "mediatek/mt7668pr2h.bin" +#define FIRMWARE_MT7922 "mediatek/BT_RAM_CODE_MT7922_1_1_hdr.bin" #define FIRMWARE_MT7961 "mediatek/BT_RAM_CODE_MT7961_1_2_hdr.bin" #define FIRMWARE_MT7925 "mediatek/mt7925/BT_RAM_CODE_MT7925_1_1_hdr.bin" diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 1d592ac413d1..0b93c2ff29e4 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -126,6 +126,7 @@ struct ps_data { struct hci_dev *hdev; struct work_struct work; struct timer_list ps_timer; + struct mutex ps_lock; }; struct wakeup_cmd_payload { @@ -317,6 +318,9 @@ static void ps_start_timer(struct btnxpuart_dev *nxpdev) if (psdata->cur_psmode == PS_MODE_ENABLE) mod_timer(&psdata->ps_timer, jiffies + msecs_to_jiffies(psdata->h2c_ps_interval)); + + if (psdata->ps_state == PS_STATE_AWAKE && psdata->ps_cmd == PS_CMD_ENTER_PS) + cancel_work_sync(&psdata->work); } static void ps_cancel_timer(struct btnxpuart_dev *nxpdev) @@ -337,6 +341,7 @@ static void ps_control(struct hci_dev *hdev, u8 ps_state) !test_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state)) return; + mutex_lock(&psdata->ps_lock); switch (psdata->cur_h2c_wakeupmode) { case WAKEUP_METHOD_DTR: if (ps_state == PS_STATE_AWAKE) @@ -350,12 +355,15 @@ static void ps_control(struct hci_dev *hdev, u8 ps_state) status = serdev_device_break_ctl(nxpdev->serdev, 0); else status = serdev_device_break_ctl(nxpdev->serdev, -1); + msleep(20); /* Allow chip to detect UART-break and enter sleep */ bt_dev_dbg(hdev, "Set UART break: %s, status=%d", str_on_off(ps_state == PS_STATE_SLEEP), status); break; } if (!status) psdata->ps_state = ps_state; + mutex_unlock(&psdata->ps_lock); + if (ps_state == PS_STATE_AWAKE) btnxpuart_tx_wakeup(nxpdev); } @@ -391,17 +399,25 @@ static void ps_setup(struct hci_dev *hdev) psdata->hdev = hdev; INIT_WORK(&psdata->work, ps_work_func); + mutex_init(&psdata->ps_lock); timer_setup(&psdata->ps_timer, ps_timeout_func, 0); } -static void ps_wakeup(struct btnxpuart_dev *nxpdev) +static bool ps_wakeup(struct btnxpuart_dev *nxpdev) { struct ps_data *psdata = &nxpdev->psdata; + u8 ps_state; + + mutex_lock(&psdata->ps_lock); + ps_state = psdata->ps_state; + mutex_unlock(&psdata->ps_lock); - if (psdata->ps_state != PS_STATE_AWAKE) { + if (ps_state != PS_STATE_AWAKE) { psdata->ps_cmd = PS_CMD_EXIT_PS; schedule_work(&psdata->work); + return true; } + return false; } static int send_ps_cmd(struct hci_dev *hdev, void *data) @@ -1171,7 +1187,6 @@ static struct sk_buff *nxp_dequeue(void *data) { struct btnxpuart_dev *nxpdev = (struct btnxpuart_dev *)data; - ps_wakeup(nxpdev); ps_start_timer(nxpdev); return skb_dequeue(&nxpdev->txq); } @@ -1186,6 +1201,9 @@ static void btnxpuart_tx_work(struct work_struct *work) struct sk_buff *skb; int len; + if (ps_wakeup(nxpdev)) + return; + while ((skb = nxp_dequeue(nxpdev))) { len = serdev_device_write_buf(serdev, skb->data, skb->len); hdev->stat.byte_tx += len; @@ -1234,6 +1252,9 @@ static int btnxpuart_close(struct hci_dev *hdev) ps_wakeup(nxpdev); serdev_device_close(nxpdev->serdev); + skb_queue_purge(&nxpdev->txq); + kfree_skb(nxpdev->rx_skb); + nxpdev->rx_skb = NULL; clear_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state); return 0; } diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 277d039ecbb4..cc50de69e8dc 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -69,6 +69,7 @@ enum btrtl_chip_id { CHIP_ID_8852B = 20, CHIP_ID_8852C = 25, CHIP_ID_8851B = 36, + CHIP_ID_8852BT = 47, }; struct id_table { @@ -307,6 +308,15 @@ static const struct id_table ic_id_table[] = { .fw_name = "rtl_bt/rtl8851bu_fw", .cfg_name = "rtl_bt/rtl8851bu_config", .hw_info = "rtl8851bu" }, + + /* 8852BT/8852BE-VT */ + { IC_INFO(RTL_ROM_LMP_8852A, 0x87, 0xc, HCI_USB), + .config_needed = false, + .has_rom_version = true, + .has_msft_ext = true, + .fw_name = "rtl_bt/rtl8852btu_fw", + .cfg_name = "rtl_bt/rtl8852btu_config", + .hw_info = "rtl8852btu" }, }; static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev, @@ -645,6 +655,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, { RTL_ROM_LMP_8852A, 20 }, /* 8852B */ { RTL_ROM_LMP_8852A, 25 }, /* 8852C */ { RTL_ROM_LMP_8851B, 36 }, /* 8851B */ + { RTL_ROM_LMP_8852A, 47 }, /* 8852BT */ }; if (btrtl_dev->fw_len <= 8) @@ -1275,6 +1286,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) case CHIP_ID_8852B: case CHIP_ID_8852C: case CHIP_ID_8851B: + case CHIP_ID_8852BT: set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks); set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks); @@ -1505,6 +1517,8 @@ MODULE_FIRMWARE("rtl_bt/rtl8852bs_fw.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852bs_config.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852bu_fw.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852bu_config.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8852btu_fw.bin"); +MODULE_FIRMWARE("rtl_bt/rtl8852btu_config.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw_v2.bin"); MODULE_FIRMWARE("rtl_bt/rtl8852cu_config.bin"); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d31edad7a056..06e915b57283 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -553,6 +553,9 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x13d3, 0x3572), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8852BT/8852BE-VT Bluetooth devices */ + { USB_DEVICE(0x0bda, 0x8520), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), .driver_info = BTUSB_REALTEK }, @@ -655,6 +658,11 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + /* Additional MediaTek MT7925 Bluetooth devices */ + { USB_DEVICE(0x13d3, 0x3602), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, + /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3394), .driver_info = BTUSB_REALTEK }, @@ -3080,7 +3088,7 @@ static int btusb_mtk_setup(struct hci_dev *hdev) int err, status; u32 dev_id = 0; char fw_bin_name[64]; - u32 fw_version = 0; + u32 fw_version = 0, fw_flavor = 0; u8 param; struct btmediatek_data *mediatek; @@ -3103,6 +3111,11 @@ static int btusb_mtk_setup(struct hci_dev *hdev) bt_dev_err(hdev, "Failed to get fw version (%d)", err); return err; } + err = btusb_mtk_id_get(data, 0x70010020, &fw_flavor); + if (err < 0) { + bt_dev_err(hdev, "Failed to get fw flavor (%d)", err); + return err; + } } mediatek = hci_get_priv(hdev); @@ -3127,6 +3140,10 @@ static int btusb_mtk_setup(struct hci_dev *hdev) snprintf(fw_bin_name, sizeof(fw_bin_name), "mediatek/mt%04x/BT_RAM_CODE_MT%04x_1_%x_hdr.bin", dev_id & 0xffff, dev_id & 0xffff, (fw_version & 0xff) + 1); + else if (dev_id == 0x7961 && fw_flavor) + snprintf(fw_bin_name, sizeof(fw_bin_name), + "mediatek/BT_RAM_CODE_MT%04x_1a_%x_hdr.bin", + dev_id & 0xffff, (fw_version & 0xff) + 1); else snprintf(fw_bin_name, sizeof(fw_bin_name), "mediatek/BT_RAM_CODE_MT%04x_1_%x_hdr.bin", @@ -3273,7 +3290,6 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) { struct btusb_data *data = hci_get_drvdata(hdev); u16 handle = le16_to_cpu(hci_acl_hdr(skb)->handle); - struct sk_buff *skb_cd; switch (handle) { case 0xfc6f: /* Firmware dump from device */ @@ -3286,9 +3302,12 @@ static int btusb_recv_acl_mtk(struct hci_dev *hdev, struct sk_buff *skb) * for backward compatibility, so we have to clone the packet * extraly for the in-kernel coredump support. */ - skb_cd = skb_clone(skb, GFP_ATOMIC); - if (skb_cd) - btmtk_process_coredump(hdev, skb_cd); + if (IS_ENABLED(CONFIG_DEV_COREDUMP)) { + struct sk_buff *skb_cd = skb_clone(skb, GFP_ATOMIC); + + if (skb_cd) + btmtk_process_coredump(hdev, skb_cd); + } fallthrough; case 0x05ff: /* Firmware debug logging 1 */ @@ -4481,6 +4500,7 @@ static int btusb_probe(struct usb_interface *intf, set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks); } if (!reset) diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 71e748a9477e..c0436881a533 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -113,6 +113,7 @@ struct h5_vnd { int (*suspend)(struct h5 *h5); int (*resume)(struct h5 *h5); const struct acpi_gpio_mapping *acpi_gpio_map; + int sizeof_priv; }; struct h5_device_data { @@ -863,7 +864,8 @@ static int h5_serdev_probe(struct serdev_device *serdev) if (IS_ERR(h5->device_wake_gpio)) return PTR_ERR(h5->device_wake_gpio); - return hci_uart_register_device(&h5->serdev_hu, &h5p); + return hci_uart_register_device_priv(&h5->serdev_hu, &h5p, + h5->vnd->sizeof_priv); } static void h5_serdev_remove(struct serdev_device *serdev) @@ -1070,6 +1072,7 @@ static struct h5_vnd rtl_vnd = { .suspend = h5_btrtl_suspend, .resume = h5_btrtl_resume, .acpi_gpio_map = acpi_btrtl_gpios, + .sizeof_priv = sizeof(struct btrealtek_data), }; static const struct h5_device_data h5_data_rtl8822cs = { diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index edd2a81b4d5e..8a60ad7acd70 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2326,7 +2326,7 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en) && + if (IS_ERR(qcadev->bt_en) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855)) { dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); @@ -2335,7 +2335,7 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", GPIOD_IN); - if (IS_ERR_OR_NULL(qcadev->sw_ctrl) && + if (IS_ERR(qcadev->sw_ctrl) && (data->soc_type == QCA_WCN6750 || data->soc_type == QCA_WCN6855 || data->soc_type == QCA_WCN7850)) @@ -2357,7 +2357,7 @@ static int qca_serdev_probe(struct serdev_device *serdev) default: qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR_OR_NULL(qcadev->bt_en)) { + if (IS_ERR(qcadev->bt_en)) { dev_warn(&serdev->dev, "failed to acquire enable gpio\n"); power_ctrl_enabled = false; } diff --git a/drivers/bluetooth/hci_serdev.c b/drivers/bluetooth/hci_serdev.c index 39c8b567da3c..214fff876eae 100644 --- a/drivers/bluetooth/hci_serdev.c +++ b/drivers/bluetooth/hci_serdev.c @@ -300,8 +300,9 @@ static const struct serdev_device_ops hci_serdev_client_ops = { .write_wakeup = hci_uart_write_wakeup, }; -int hci_uart_register_device(struct hci_uart *hu, - const struct hci_uart_proto *p) +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv) { int err; struct hci_dev *hdev; @@ -325,7 +326,7 @@ int hci_uart_register_device(struct hci_uart *hu, set_bit(HCI_UART_PROTO_READY, &hu->flags); /* Initialize and register HCI device */ - hdev = hci_alloc_dev(); + hdev = hci_alloc_dev_priv(sizeof_priv); if (!hdev) { BT_ERR("Can't allocate HCI device"); err = -ENOMEM; @@ -394,7 +395,7 @@ err_rwsem: percpu_free_rwsem(&hu->proto_lock); return err; } -EXPORT_SYMBOL_GPL(hci_uart_register_device); +EXPORT_SYMBOL_GPL(hci_uart_register_device_priv); void hci_uart_unregister_device(struct hci_uart *hu) { diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h index fb4a2d0d8cc8..68c8c7e95d64 100644 --- a/drivers/bluetooth/hci_uart.h +++ b/drivers/bluetooth/hci_uart.h @@ -97,7 +97,17 @@ struct hci_uart { int hci_uart_register_proto(const struct hci_uart_proto *p); int hci_uart_unregister_proto(const struct hci_uart_proto *p); -int hci_uart_register_device(struct hci_uart *hu, const struct hci_uart_proto *p); + +int hci_uart_register_device_priv(struct hci_uart *hu, + const struct hci_uart_proto *p, + int sizeof_priv); + +static inline int hci_uart_register_device(struct hci_uart *hu, + const struct hci_uart_proto *p) +{ + return hci_uart_register_device_priv(hu, p, 0); +} + void hci_uart_unregister_device(struct hci_uart *hu); int hci_uart_tx_wakeup(struct hci_uart *hu); diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 1262a7773ef3..de50c00ba218 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -299,22 +299,6 @@ theend: return err; } -static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) -{ - struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); - struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); - struct sun8i_ce_dev *ce = op->ce; - struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); - int flow, err; - - flow = rctx->flow; - err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); - local_bh_disable(); - crypto_finalize_skcipher_request(engine, breq, err); - local_bh_enable(); -} - static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, void *async_req) { @@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); } +static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) +{ + struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); + struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); + struct sun8i_ce_dev *ce = op->ce; + struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); + int flow, err; + + flow = rctx->flow; + err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); + sun8i_ce_cipher_unprepare(engine, areq); + local_bh_disable(); + crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); +} + int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) { int err = sun8i_ce_cipher_prepare(engine, areq); @@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) return err; sun8i_ce_cipher_run(engine, areq); - sun8i_ce_cipher_unprepare(engine, areq); return 0; } diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 1b13b4aa16ec..a235e6c300f1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq) theend: pm_runtime_put_autosuspend(rkc->dev); + rk_hash_unprepare(engine, breq); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); local_bh_enable(); - rk_hash_unprepare(engine, breq); - return 0; } diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index b38786f0ad79..b75fdaffad9a 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote eDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, llp.msb, upper_32_bits(chunk->ll_region.paddr)); } + + dw_edma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_RW_32(dw, chan->dir, doorbell, FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id)); diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c index 00b735a0202a..10e8f0715114 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-core.c +++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c @@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw) static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir) { - u32 num_ch = 0; - int id; - - for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) { - if (GET_CH_32(dw, id, dir, ch_en) & BIT(0)) - num_ch++; - } - - if (num_ch > HDMA_V0_MAX_NR_CH) - num_ch = HDMA_V0_MAX_NR_CH; - - return (u16)num_ch; + /* + * The HDMA IP have no way to know the number of hardware channels + * available, we set it to maximum channels and let the platform + * set the right number of channels. + */ + return HDMA_V0_MAX_NR_CH; } static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan) @@ -228,6 +222,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote HDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -242,7 +250,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) /* Interrupt enable&unmask - done, abort */ tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) | HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK | - HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN; + HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN; + if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN; SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp); /* Channel control */ SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN); @@ -256,6 +266,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) /* Set consumer cycle */ SET_CH_32(dw, chan->dir, chan->id, cycle_sync, HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT); + + dw_hdma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START); } diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h index a974abdf8aaf..eab5fd7177e5 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h +++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h @@ -15,7 +15,7 @@ #define HDMA_V0_LOCAL_ABORT_INT_EN BIT(6) #define HDMA_V0_REMOTE_ABORT_INT_EN BIT(5) #define HDMA_V0_LOCAL_STOP_INT_EN BIT(4) -#define HDMA_V0_REMOTEL_STOP_INT_EN BIT(3) +#define HDMA_V0_REMOTE_STOP_INT_EN BIT(3) #define HDMA_V0_ABORT_INT_MASK BIT(2) #define HDMA_V0_STOP_INT_MASK BIT(0) #define HDMA_V0_LINKLIST_EN BIT(0) diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index b53f46245c37..793f1a7ad5e3 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -503,7 +503,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, if (fsl_chan->is_multi_fifo) { /* set mloff to support multiple fifo */ burst = cfg->direction == DMA_DEV_TO_MEM ? - cfg->src_addr_width : cfg->dst_addr_width; + cfg->src_maxburst : cfg->dst_maxburst; nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4)); /* enable DMLOE/SMLOE */ if (cfg->direction == DMA_MEM_TO_DEV) { diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index bb5221158a77..f5e216b157c7 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -30,8 +30,9 @@ #define EDMA_TCD_ATTR_SSIZE(x) (((x) & GENMASK(2, 0)) << 8) #define EDMA_TCD_ATTR_SMOD(x) (((x) & GENMASK(4, 0)) << 11) -#define EDMA_TCD_CITER_CITER(x) ((x) & GENMASK(14, 0)) -#define EDMA_TCD_BITER_BITER(x) ((x) & GENMASK(14, 0)) +#define EDMA_TCD_ITER_MASK GENMASK(14, 0) +#define EDMA_TCD_CITER_CITER(x) ((x) & EDMA_TCD_ITER_MASK) +#define EDMA_TCD_BITER_BITER(x) ((x) & EDMA_TCD_ITER_MASK) #define EDMA_TCD_CSR_START BIT(0) #define EDMA_TCD_CSR_INT_MAJOR BIT(1) diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 45cc419b1b4a..d36e28b9c767 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -10,6 +10,7 @@ */ #include <dt-bindings/dma/fsl-edma.h> +#include <linux/bitfield.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/clk.h> @@ -582,7 +583,8 @@ static int fsl_edma_probe(struct platform_device *pdev) DMAENGINE_ALIGN_32_BYTES; /* Per worst case 'nbytes = 1' take CITER as the max_seg_size */ - dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff); + dma_set_max_seg_size(fsl_edma->dma_dev.dev, + FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK)); fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index f405c77060ad..5005e138fc23 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17) /* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -160,6 +161,10 @@ struct fsl_qdma_format { u8 __reserved1[2]; u8 cfg8b_w1; } __packed; + struct { + __le32 __reserved2; + __le32 cmd; + } __packed; __le64 data; }; } __packed; @@ -354,7 +359,6 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan) static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, dma_addr_t dst, dma_addr_t src, u32 len) { - u32 cmd; struct fsl_qdma_format *sdf, *ddf; struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest; @@ -383,14 +387,11 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, /* This entry is the last entry. */ qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ - cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); - sdf->data = QDMA_SDDF_CMD(cmd); - - cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); - cmd |= cpu_to_le32(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET); - ddf->data = QDMA_SDDF_CMD(cmd); + sdf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF); + + ddf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) | + (FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET)); } /* @@ -624,7 +625,7 @@ static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma) static int fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma, - void *block, + __iomem void *block, int id) { bool duplicate; @@ -1196,10 +1197,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM; - ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1238,16 +1235,19 @@ static int fsl_qdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fsl_qdma); - ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; } - ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 77f8885cf407..e5a94a93a3cc 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -345,7 +345,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) spin_lock(&evl->lock); status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = status.tail; - h = evl->head; + h = status.head; size = evl->size; while (h != t) { diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c index 9cfbd9b14c4c..f3f25ee676f3 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -68,9 +68,9 @@ static int debugfs_evl_show(struct seq_file *s, void *d) spin_lock(&evl->lock); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; evl_size = evl->size; seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n", diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 47de3f93ff1e..d0f5db6cf1ed 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -300,7 +300,6 @@ struct idxd_evl { unsigned int log_size; /* The number of entries in the event log. */ u16 size; - u16 head; unsigned long *bmap; bool batch_fail[IDXD_MAX_BATCH_IDENT]; }; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 14df1f1347a8..4954adc6bb60 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -343,7 +343,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd) static int idxd_init_evl(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; + unsigned int evl_cache_size; struct idxd_evl *evl; + const char *idxd_name; if (idxd->hw.gen_cap.evl_support == 0) return 0; @@ -355,9 +357,16 @@ static int idxd_init_evl(struct idxd_device *idxd) spin_lock_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; - idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)), - sizeof(struct idxd_evl_fault) + evl_ent_size(idxd), - 0, 0, NULL); + idxd_name = dev_name(idxd_confdev(idxd)); + evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd); + /* + * Since completion record in evl_cache will be copied to user + * when handling completion record page fault, need to create + * the cache suitable for user copy. + */ + idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size, + 0, 0, 0, evl_cache_size, + NULL); if (!idxd->evl_cache) { kfree(evl); return -ENOMEM; diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index c8a0aa874b11..348aa21389a9 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -367,9 +367,9 @@ static void process_evl_entries(struct idxd_device *idxd) /* Clear interrupt pending bit */ iowrite32(evl_status.bits_upper32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; size = idxd->evl->size; while (h != t) { @@ -378,7 +378,6 @@ static void process_evl_entries(struct idxd_device *idxd) h = (h + 1) % size; } - evl->head = h; evl_status.head = h; iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); spin_unlock(&evl->lock); diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c index 1aa65e5de0f3..f79240734807 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/ptdma/ptdma-dmaengine.c @@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt) chan->vc.desc_free = pt_do_cleanup; vchan_init(&chan->vc, dma_dev); - dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64)); - ret = dma_async_device_register(dma_dev); if (ret) goto err_reg; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 12fcd420396e..6b2a6236f5e3 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -44,11 +44,6 @@ struct dpll_pin_registration { void *priv; }; -struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ - return rcu_dereference_rtnl(dev->dpll_pin); -} - struct dpll_device *dpll_device_get_by_id(int id) { if (xa_get_mark(&dpll_device_xa, id, DPLL_REGISTERED)) @@ -515,6 +510,26 @@ err_pin_prop: return ERR_PTR(ret); } +static void dpll_netdev_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + rtnl_lock(); + rcu_assign_pointer(dev->dpll_pin, dpll_pin); + rtnl_unlock(); +} + +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + WARN_ON(!dpll_pin); + dpll_netdev_pin_assign(dev, dpll_pin); +} +EXPORT_SYMBOL(dpll_netdev_pin_set); + +void dpll_netdev_pin_clear(struct net_device *dev) +{ + dpll_netdev_pin_assign(dev, NULL); +} +EXPORT_SYMBOL(dpll_netdev_pin_clear); + /** * dpll_pin_get - find existing or create new dpll pin * @clock_id: clock_id of creator diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 1419fd0d241c..98e6ad8528d3 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/netdevice.h> #include <net/genetlink.h> #include "dpll_core.h" #include "dpll_netlink.h" @@ -48,18 +49,6 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) } /** - * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin - * @pin: pin pointer - * - * Return: byte size of pin handle attribute for given pin. - */ -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) -{ - return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ -} -EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); - -/** * dpll_msg_add_pin_handle - attach pin handle attribute to a given message * @msg: pointer to sk_buff message to attach a pin handle * @pin: pin pointer @@ -68,7 +57,7 @@ EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); * * 0 - success * * -EMSGSIZE - no space in message to attach pin handle */ -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) { if (!pin) return 0; @@ -76,7 +65,28 @@ int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) return -EMSGSIZE; return 0; } -EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle); + +static struct dpll_pin *dpll_netdev_pin(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->dpll_pin); +} + +/** + * dpll_netdev_pin_handle_size - get size of pin handle attribute of a netdev + * @dev: netdev from which to get the pin + * + * Return: byte size of pin handle attribute, or 0 if @dev has no pin. + */ +size_t dpll_netdev_pin_handle_size(const struct net_device *dev) +{ + return dpll_netdev_pin(dev) ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ +} + +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev) +{ + return dpll_msg_add_pin_handle(msg, dpll_netdev_pin(dev)); +} static int dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll, diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 8aaa7fcb2630..401a77e3b5fa 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -500,7 +500,19 @@ static void bm_work(struct work_struct *work) fw_notice(card, "phy config: new root=%x, gap_count=%d\n", new_root_id, gap_count); fw_send_phy_config(card, new_root_id, generation, gap_count); - reset_bus(card, true); + /* + * Where possible, use a short bus reset to minimize + * disruption to isochronous transfers. But in the event + * of a gap count inconsistency, use a long bus reset. + * + * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus + * may set different gap counts after a bus reset. On a mixed + * 1394/1394a bus, a short bus reset can get doubled. Some + * nodes may treat the double reset as one bus reset and others + * may treat it as two, causing a gap count inconsistency + * again. Using a long bus reset prevents this. + */ + reset_bus(card, card->gap_count != 0); /* Will allocate broadcast channel after the reset. */ goto out; } diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a814..97bafb5f7038 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } - cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 682e417be5a3..fbeeaee4ac85 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -384,7 +384,8 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) u32 *response_msg; int ret; - response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg), + response_msg = devm_kzalloc(priv->dev, + AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg), GFP_KERNEL); if (!response_msg) return -ENOMEM; diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index e00c33310517..753e7be039e4 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe); - gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip); chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; } + gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e434e8cc1229..75be4a3ca7f8 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -968,11 +968,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -997,13 +997,13 @@ err_remove_irqchip: gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 2520db0b776e..c7edba18a6f0 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -199,7 +199,7 @@ config DRM_TTM config DRM_TTM_KUNIT_TEST tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS default n - depends on DRM && KUNIT && MMU + depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST) select DRM_TTM select DRM_EXPORT_FOR_TESTS if m select DRM_KUNIT_TEST_HELPERS @@ -207,7 +207,8 @@ config DRM_TTM_KUNIT_TEST help Enables unit tests for TTM, a GPU memory manager subsystem used to manage memory buffers. This option is mostly useful for kernel - developers. + developers. It depends on (UML || COMPILE_TEST) since no other driver + which uses TTM can be loaded while running the tests. If in doubt, say "N". diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index c64c01e2944a..1c614451dead 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev) return AMD_RESET_METHOD_MODE1; } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_asic_reset(struct amdgpu_device *adev) { /* original raven doesn't have full asic reset */ - if ((adev->apu_flags & AMD_APU_IS_RAVEN) || - (adev->apu_flags & AMD_APU_IS_RAVEN2)) + /* On the latest Raven, the GPU reset can be performed + * successfully. So now, temporarily enable it for the + * S3 suspend abort case. + */ + if (((adev->apu_flags & AMD_APU_IS_RAVEN) || + (adev->apu_flags & AMD_APU_IS_RAVEN2)) && + !soc15_need_reset_on_resume(adev)) return 0; switch (soc15_asic_reset_method(adev)) { @@ -1298,24 +1321,6 @@ static int soc15_common_suspend(void *handle) return soc15_common_hw_fini(adev); } -static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) -{ - u32 sol_reg; - - sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); - - /* Will reset for the following suspend abort cases. - * 1) Only reset limit on APU side, dGPU hasn't checked yet. - * 2) S3 suspend abort and TOS already launched. - */ - if (adev->flags & AMD_IS_APU && adev->in_s3 && - !adev->suspend_complete && - sol_reg) - return true; - - return false; -} - static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 85b7f58a7f35..c27063305a13 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -67,6 +67,8 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) /* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */ case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB): case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B): + case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A): + case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1): DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.remove_sink_ext_caps = true; break; @@ -120,6 +122,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; + apply_edid_quirks(edid_buf, edid_caps); + sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) return result; @@ -146,8 +150,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps( else edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION; - apply_edid_quirks(edid_buf, edid_caps); - kfree(sads); kfree(sadb); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 26307e599614..2a58a7687bdb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -76,6 +76,11 @@ static void map_hw_resources(struct dml2_context *dml2, in_out_display_cfg->hw.DLGRefClkFreqMHz = 50; } for (j = 0; j < mode_support_info->DPPPerSurface[i]; j++) { + if (i >= __DML2_WRAPPER_MAX_STREAMS_PLANES__) { + dml_print("DML::%s: Index out of bounds: i=%d, __DML2_WRAPPER_MAX_STREAMS_PLANES__=%d\n", + __func__, i, __DML2_WRAPPER_MAX_STREAMS_PLANES__); + break; + } dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_stream_id[i]; dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id_valid[num_pipes] = true; dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[i]; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index df4f20293c16..eb4da3666e05 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } +static int si_set_temperature_range(struct amdgpu_device *adev) +{ + int ret; + + ret = si_thermal_enable_alert(adev, false); + if (ret) + return ret; + ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); + if (ret) + return ret; + ret = si_thermal_enable_alert(adev, true); + if (ret) + return ret; + + return ret; +} + static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { + int ret; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (!adev->pm.dpm_enabled) + return 0; + + ret = si_set_temperature_range(adev); + if (ret) + return ret; +#if 0 //TODO ? + si_dpm_powergate_uvd(adev, true); +#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 4cd43bbec910..bcad42534da4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -1303,13 +1303,12 @@ static int arcturus_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 8d1d29ffb0f1..ed189a3878eb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2357,13 +2357,12 @@ static int navi10_get_power_limit(struct smu_context *smu, *default_power_limit = power_limit; if (smu->od_enabled && - navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { + navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 21fc033528fa..e2ad2b972ab0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -640,13 +640,12 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index a9954ffc02c5..9b80f18ea6c3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2369,13 +2369,12 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 0ffdb58af74e..3dc7b60cb075 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2333,13 +2333,12 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c index bb55f697a181..6886db2d9e00 100644 --- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c +++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c @@ -25,20 +25,18 @@ static void drm_aux_hpd_bridge_release(struct device *dev) ida_free(&drm_aux_hpd_bridge_ida, adev->id); of_node_put(adev->dev.platform_data); + of_node_put(adev->dev.of_node); kfree(adev); } -static void drm_aux_hpd_bridge_unregister_adev(void *_adev) +static void drm_aux_hpd_bridge_free_adev(void *_adev) { - struct auxiliary_device *adev = _adev; - - auxiliary_device_delete(adev); - auxiliary_device_uninit(adev); + auxiliary_device_uninit(_adev); } /** - * drm_dp_hpd_bridge_register - Create a simple HPD DisplayPort bridge + * devm_drm_dp_hpd_bridge_alloc - allocate a HPD DisplayPort bridge * @parent: device instance providing this bridge * @np: device node pointer corresponding to this bridge instance * @@ -46,11 +44,9 @@ static void drm_aux_hpd_bridge_unregister_adev(void *_adev) * DRM_MODE_CONNECTOR_DisplayPort, which terminates the bridge chain and is * able to send the HPD events. * - * Return: device instance that will handle created bridge or an error code - * encoded into the pointer. + * Return: bridge auxiliary device pointer or an error pointer */ -struct device *drm_dp_hpd_bridge_register(struct device *parent, - struct device_node *np) +struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np) { struct auxiliary_device *adev; int ret; @@ -74,18 +70,62 @@ struct device *drm_dp_hpd_bridge_register(struct device *parent, ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.platform_data); + of_node_put(adev->dev.of_node); ida_free(&drm_aux_hpd_bridge_ida, adev->id); kfree(adev); return ERR_PTR(ret); } - ret = auxiliary_device_add(adev); - if (ret) { - auxiliary_device_uninit(adev); + ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_free_adev, adev); + if (ret) return ERR_PTR(ret); - } - ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_unregister_adev, adev); + return adev; +} +EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_alloc); + +static void drm_aux_hpd_bridge_del_adev(void *_adev) +{ + auxiliary_device_delete(_adev); +} + +/** + * devm_drm_dp_hpd_bridge_add - register a HDP DisplayPort bridge + * @dev: struct device to tie registration lifetime to + * @adev: bridge auxiliary device to be registered + * + * Returns: zero on success or a negative errno + */ +int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev) +{ + int ret; + + ret = auxiliary_device_add(adev); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, drm_aux_hpd_bridge_del_adev, adev); +} +EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_add); + +/** + * drm_dp_hpd_bridge_register - allocate and register a HDP DisplayPort bridge + * @parent: device instance providing this bridge + * @np: device node pointer corresponding to this bridge instance + * + * Return: device instance that will handle created bridge or an error pointer + */ +struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np) +{ + struct auxiliary_device *adev; + int ret; + + adev = devm_drm_dp_hpd_bridge_alloc(parent, np); + if (IS_ERR(adev)) + return ERR_CAST(adev); + + ret = devm_drm_dp_hpd_bridge_add(parent, adev); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index c4222b886db7..5ebdd6f8f36e 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm, u64 start, u64 end, unsigned int order) { + u64 req_size = mm->chunk_size << order; struct drm_buddy_block *block; struct drm_buddy_block *buddy; LIST_HEAD(dfs); @@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm, if (drm_buddy_block_is_allocated(block)) continue; + if (block_start < start || block_end > end) { + u64 adjusted_start = max(block_start, start); + u64 adjusted_end = min(block_end, end); + + if (round_down(adjusted_end + 1, req_size) <= + round_up(adjusted_start, req_size)) + continue; + } + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { /* @@ -761,8 +771,12 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, return -EINVAL; /* Actual range allocation */ - if (start + size == end) + if (start + size == end) { + if (!IS_ALIGNED(start | end, min_block_size)) + return -EINVAL; + return __drm_buddy_alloc_range(mm, start, size, NULL, blocks); + } original_size = size; original_min_size = min_block_size; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index d37d599aec27..4c72124ffb5d 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -329,10 +329,26 @@ static const struct component_ops dp_display_comp_ops = { .unbind = dp_display_unbind, }; +static void dp_display_send_hpd_event(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + struct drm_connector *connector; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + connector = dp->dp_display.connector; + drm_helper_hpd_irq_event(connector->dev); +} + static int dp_display_send_hpd_notification(struct dp_display_private *dp, bool hpd) { - struct drm_bridge *bridge = dp->dp_display.bridge; + if ((hpd && dp->dp_display.link_ready) || + (!hpd && !dp->dp_display.link_ready)) { + drm_dbg_dp(dp->drm_dev, "HPD already %s\n", + (hpd ? "on" : "off")); + return 0; + } /* reset video pattern flag on disconnect */ if (!hpd) { @@ -348,7 +364,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp, drm_dbg_dp(dp->drm_dev, "type=%d hpd=%d\n", dp->dp_display.connector_type, hpd); - drm_bridge_hpd_notify(bridge, dp->dp_display.link_ready); + dp_display_send_hpd_event(&dp->dp_display); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index cd14f993bdd1..80f74ee0fc78 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -269,7 +269,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) break; case NOUVEAU_GETPARAM_VRAM_USED: { struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM); - getparam->value = (u64)ttm_resource_manager_usage(vram_mgr) << PAGE_SHIFT; + getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); break; } default: diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index a64c81385682..a73a5b589790 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1054,8 +1054,6 @@ r535_gsp_postinit(struct nvkm_gsp *gsp) /* Release the DMA buffers that were needed only for boot and init */ nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw); nvkm_gsp_mem_dtor(gsp, &gsp->libos); - nvkm_gsp_mem_dtor(gsp, &gsp->rmargs); - nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta); return ret; } @@ -2163,6 +2161,8 @@ r535_gsp_dtor(struct nvkm_gsp *gsp) r535_gsp_dtor_fws(gsp); + nvkm_gsp_mem_dtor(gsp, &gsp->rmargs); + nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta); nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem); nvkm_gsp_mem_dtor(gsp, &gsp->loginit); nvkm_gsp_mem_dtor(gsp, &gsp->logintr); diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index a73cff7a3070..03d1c76aec2d 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1243,9 +1243,26 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(&tegra_drm_driver); - if (err < 0) - goto hub; + /* + * Only take over from a potential firmware framebuffer if any CRTCs + * have been registered. This must not be a fatal error because there + * are other accelerators that are exposed via this driver. + * + * Another case where this happens is on Tegra234 where the display + * hardware is no longer part of the host1x complex, so this driver + * will not expose any modesetting features. + */ + if (drm->mode_config.num_crtc > 0) { + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); + if (err < 0) + goto hub; + } else { + /* + * Indicate to userspace that this doesn't expose any display + * capabilities. + */ + drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); + } err = drm_dev_register(drm, 0); if (err < 0) diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index 2f32fb2f12e7..be2d9d7764be 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -14,11 +14,216 @@ #include "../lib/drm_random.h" +static unsigned int random_seed; + static inline u64 get_size(int order, u64 chunk_size) { return (1 << order) * chunk_size; } +static void drm_test_buddy_alloc_range_bias(struct kunit *test) +{ + u32 mm_size, ps, bias_size, bias_start, bias_end, bias_rem; + DRM_RND_STATE(prng, random_seed); + unsigned int i, count, *order; + struct drm_buddy mm; + LIST_HEAD(allocated); + + bias_size = SZ_1M; + ps = roundup_pow_of_two(prandom_u32_state(&prng) % bias_size); + ps = max(SZ_4K, ps); + mm_size = (SZ_8M-1) & ~(ps-1); /* Multiple roots */ + + kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps); + + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps), + "buddy_init failed\n"); + + count = mm_size / bias_size; + order = drm_random_order(count, &prng); + KUNIT_EXPECT_TRUE(test, order); + + /* + * Idea is to split the address space into uniform bias ranges, and then + * in some random order allocate within each bias, using various + * patterns within. This should detect if allocations leak out from a + * given bias, for example. + */ + + for (i = 0; i < count; i++) { + LIST_HEAD(tmp); + u32 size; + + bias_start = order[i] * bias_size; + bias_end = bias_start + bias_size; + bias_rem = bias_size; + + /* internal round_up too big */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size + ps, bias_size, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size, bias_size); + + /* size too big */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size + ps, ps); + + /* bias range too small for size */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start + ps, + bias_end, bias_size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start + ps, bias_end, bias_size, ps); + + /* bias misaligned */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start + ps, + bias_end - ps, + bias_size >> 1, bias_size >> 1, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1); + + /* single big page */ + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size, bias_size, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size, bias_size); + drm_buddy_free_list(&mm, &tmp); + + /* single page with internal round_up */ + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, ps, bias_size, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, ps, bias_size); + drm_buddy_free_list(&mm, &tmp); + + /* random size within */ + size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + if (size) + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size, ps); + + bias_rem -= size; + /* too big for current avail */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_rem + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_rem + ps, ps); + + if (bias_rem) { + /* random fill of the remainder */ + size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + size = max(size, ps); + + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size, ps); + /* + * Intentionally allow some space to be left + * unallocated, and ideally not always on the bias + * boundaries. + */ + drm_buddy_free_list(&mm, &tmp); + } else { + list_splice_tail(&tmp, &allocated); + } + } + + kfree(order); + drm_buddy_free_list(&mm, &allocated); + drm_buddy_fini(&mm); + + /* + * Something more free-form. Idea is to pick a random starting bias + * range within the address space and then start filling it up. Also + * randomly grow the bias range in both directions as we go along. This + * should give us bias start/end which is not always uniform like above, + * and in some cases will require the allocator to jump over already + * allocated nodes in the middle of the address space. + */ + + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps), + "buddy_init failed\n"); + + bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps); + bias_end = round_up(bias_start + prandom_u32_state(&prng) % (mm_size - bias_start), ps); + bias_end = max(bias_end, bias_start + ps); + bias_rem = bias_end - bias_start; + + do { + u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size); + bias_rem -= size; + + /* + * Try to randomly grow the bias range in both directions, or + * only one, or perhaps don't grow at all. + */ + do { + u32 old_bias_start = bias_start; + u32 old_bias_end = bias_end; + + if (bias_start) + bias_start -= round_up(prandom_u32_state(&prng) % bias_start, ps); + if (bias_end != mm_size) + bias_end += round_up(prandom_u32_state(&prng) % (mm_size - bias_end), ps); + + bias_rem += old_bias_start - bias_start; + bias_rem += bias_end - old_bias_end; + } while (!bias_rem && (bias_start || bias_end != mm_size)); + } while (bias_rem); + + KUNIT_ASSERT_EQ(test, bias_start, 0); + KUNIT_ASSERT_EQ(test, bias_end, mm_size); + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, bias_end, + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc passed with bias(%x-%x), size=%u\n", + bias_start, bias_end, ps); + + drm_buddy_free_list(&mm, &allocated); + drm_buddy_fini(&mm); +} + static void drm_test_buddy_alloc_contiguous(struct kunit *test) { const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K; @@ -362,17 +567,30 @@ static void drm_test_buddy_alloc_limit(struct kunit *test) drm_buddy_fini(&mm); } +static int drm_buddy_suite_init(struct kunit_suite *suite) +{ + while (!random_seed) + random_seed = get_random_u32(); + + kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n", + random_seed); + + return 0; +} + static struct kunit_case drm_buddy_tests[] = { KUNIT_CASE(drm_test_buddy_alloc_limit), KUNIT_CASE(drm_test_buddy_alloc_optimistic), KUNIT_CASE(drm_test_buddy_alloc_pessimistic), KUNIT_CASE(drm_test_buddy_alloc_pathological), KUNIT_CASE(drm_test_buddy_alloc_contiguous), + KUNIT_CASE(drm_test_buddy_alloc_range_bias), {} }; static struct kunit_suite drm_buddy_test_suite = { .name = "drm_buddy", + .suite_init = drm_buddy_suite_init, .test_cases = drm_buddy_tests, }; diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 0b0e262e2166..4d3b80ec906d 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -28,6 +28,14 @@ #include "xe_ttm_stolen_mgr.h" #include "xe_vm.h" +const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES] = { + [XE_PL_SYSTEM] = "system", + [XE_PL_TT] = "gtt", + [XE_PL_VRAM0] = "vram0", + [XE_PL_VRAM1] = "vram1", + [XE_PL_STOLEN] = "stolen" +}; + static const struct ttm_place sys_placement_flags = { .fpfn = 0, .lpfn = 0, @@ -713,8 +721,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, migrate = xe->tiles[0].migrate; xe_assert(xe, migrate); - - trace_xe_bo_move(bo); + trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source); xe_device_mem_access_get(xe); if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) { diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 9b1279aca127..8be42ac6cd07 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -243,6 +243,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo); int xe_bo_restore_pinned(struct xe_bo *bo); extern struct ttm_device_funcs xe_ttm_funcs; +extern const char *const xe_mem_type_to_name[]; int xe_gem_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file); diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 82d1305e831f..6040e4d22b28 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -131,14 +131,6 @@ static void bo_meminfo(struct xe_bo *bo, static void show_meminfo(struct drm_printer *p, struct drm_file *file) { - static const char *const mem_type_to_name[TTM_NUM_MEM_TYPES] = { - [XE_PL_SYSTEM] = "system", - [XE_PL_TT] = "gtt", - [XE_PL_VRAM0] = "vram0", - [XE_PL_VRAM1] = "vram1", - [4 ... 6] = NULL, - [XE_PL_STOLEN] = "stolen" - }; struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {}; struct xe_file *xef = file->driver_priv; struct ttm_device *bdev = &xef->xe->ttm; @@ -171,7 +163,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) spin_unlock(&client->bos_lock); for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) { - if (!mem_type_to_name[mem_type]) + if (!xe_mem_type_to_name[mem_type]) continue; man = ttm_manager_type(bdev, mem_type); @@ -182,7 +174,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) DRM_GEM_OBJECT_RESIDENT | (mem_type != XE_PL_SYSTEM ? 0 : DRM_GEM_OBJECT_PURGEABLE), - mem_type_to_name[mem_type]); + xe_mem_type_to_name[mem_type]); } } } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 3acfd4f07666..49223026c89f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -309,85 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue * return q->ops->set_timeslice(q, value); } -static int exec_queue_set_preemption_timeout(struct xe_device *xe, - struct xe_exec_queue *q, u64 value, - bool create) -{ - u32 min = 0, max = 0; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_preempt_timeout(q, value); -} - -static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - u32 min = 0, max = 0; - - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_job_timeout(q, value); -} - -static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_trigger = value; - - return 0; -} - -static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_notify = value; - - return 0; -} - -static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - if (value > DRM_XE_ACC_GRANULARITY_64M) - return -EINVAL; - - q->usm.acc_granularity = value; - - return 0; -} - typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, struct xe_exec_queue *q, u64 value, bool create); @@ -395,11 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = { [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity, }; static int exec_queue_user_ext_set_property(struct xe_device *xe, @@ -418,7 +334,9 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe, if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(exec_queue_set_property_funcs)) || - XE_IOCTL_DBG(xe, ext.pad)) + XE_IOCTL_DBG(xe, ext.pad) || + XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY && + ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE)) return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs)); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 947bbc4b285d..36f4901d8d7e 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -150,16 +150,6 @@ struct xe_exec_queue { spinlock_t lock; } compute; - /** @usm: unified shared memory state */ - struct { - /** @acc_trigger: access counter trigger */ - u32 acc_trigger; - /** @acc_notify: access counter notify */ - u32 acc_notify; - /** @acc_granularity: access counter granularity */ - u32 acc_granularity; - } usm; - /** @ops: submission backend exec queue operations */ const struct xe_exec_queue_ops *ops; diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 42d01bbbf7d0..acb4d9f38fd7 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -212,7 +212,7 @@ static void xe_execlist_port_wake_locked(struct xe_execlist_port *port, static void xe_execlist_make_active(struct xe_execlist_exec_queue *exl) { struct xe_execlist_port *port = exl->port; - enum xe_exec_queue_priority priority = exl->active_priority; + enum xe_exec_queue_priority priority = exl->q->sched_props.priority; XE_WARN_ON(priority == XE_EXEC_QUEUE_PRIORITY_UNSET); XE_WARN_ON(priority < 0); diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 7eef23a00d77..f4c485289dbe 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -247,6 +247,14 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, xe_gt_assert(gt, vma); + /* Execlists not supported */ + if (gt_to_xe(gt)->info.force_execlist) { + if (fence) + __invalidation_fence_signal(fence); + + return 0; + } + action[len++] = XE_GUC_ACTION_TLB_INVALIDATION; action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */ if (!xe->info.has_range_tlb_invalidation) { @@ -317,6 +325,10 @@ int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno) struct drm_printer p = drm_err_printer(__func__); int ret; + /* Execlists not supported */ + if (gt_to_xe(gt)->info.force_execlist) + return 0; + /* * XXX: See above, this algorithm only works if seqno are always in * order diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 0ec5ad2539f1..b38319d2801e 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm) #define PVC_CTX_ASID (0x2e + 1) #define PVC_CTX_ACC_CTR_THOLD (0x2a + 1) -#define ACC_GRANULARITY_S 20 -#define ACC_NOTIFY_S 16 int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size) @@ -754,13 +752,7 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL, RING_CTL_SIZE(lrc->ring.size) | RING_VALID); if (xe->info.has_asid && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, - (q->usm.acc_granularity << - ACC_GRANULARITY_S) | vm->usm.asid); - if (xe->info.has_usm && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD, - (q->usm.acc_notify << ACC_NOTIFY_S) | - q->usm.acc_trigger); + xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid); lrc->desc = LRC_VALID; lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT; diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 5f6b53ea5528..02f7808f28ca 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -105,7 +105,7 @@ static void xe_resize_vram_bar(struct xe_device *xe) pci_bus_for_each_resource(root, root_res, i) { if (root_res && root_res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) && - root_res->start > 0x100000000ull) + (u64)root_res->start > 0x100000000ul) break; } diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index aab92bee1d7c..02c9577fe418 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -19,7 +19,7 @@ #include "xe_macros.h" #include "xe_sched_job_types.h" -struct user_fence { +struct xe_user_fence { struct xe_device *xe; struct kref refcount; struct dma_fence_cb cb; @@ -27,31 +27,32 @@ struct user_fence { struct mm_struct *mm; u64 __user *addr; u64 value; + int signalled; }; static void user_fence_destroy(struct kref *kref) { - struct user_fence *ufence = container_of(kref, struct user_fence, + struct xe_user_fence *ufence = container_of(kref, struct xe_user_fence, refcount); mmdrop(ufence->mm); kfree(ufence); } -static void user_fence_get(struct user_fence *ufence) +static void user_fence_get(struct xe_user_fence *ufence) { kref_get(&ufence->refcount); } -static void user_fence_put(struct user_fence *ufence) +static void user_fence_put(struct xe_user_fence *ufence) { kref_put(&ufence->refcount, user_fence_destroy); } -static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr, - u64 value) +static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr, + u64 value) { - struct user_fence *ufence; + struct xe_user_fence *ufence; ufence = kmalloc(sizeof(*ufence), GFP_KERNEL); if (!ufence) @@ -69,7 +70,7 @@ static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr, static void user_fence_worker(struct work_struct *w) { - struct user_fence *ufence = container_of(w, struct user_fence, worker); + struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker); if (mmget_not_zero(ufence->mm)) { kthread_use_mm(ufence->mm); @@ -80,10 +81,11 @@ static void user_fence_worker(struct work_struct *w) } wake_up_all(&ufence->xe->ufence_wq); + WRITE_ONCE(ufence->signalled, 1); user_fence_put(ufence); } -static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence) +static void kick_ufence(struct xe_user_fence *ufence, struct dma_fence *fence) { INIT_WORK(&ufence->worker, user_fence_worker); queue_work(ufence->xe->ordered_wq, &ufence->worker); @@ -92,7 +94,7 @@ static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence) static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { - struct user_fence *ufence = container_of(cb, struct user_fence, cb); + struct xe_user_fence *ufence = container_of(cb, struct xe_user_fence, cb); kick_ufence(ufence, fence); } @@ -340,3 +342,39 @@ err_out: return ERR_PTR(-ENOMEM); } + +/** + * xe_sync_ufence_get() - Get user fence from sync + * @sync: input sync + * + * Get a user fence reference from sync. + * + * Return: xe_user_fence pointer with reference + */ +struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync) +{ + user_fence_get(sync->ufence); + + return sync->ufence; +} + +/** + * xe_sync_ufence_put() - Put user fence reference + * @ufence: user fence reference + * + */ +void xe_sync_ufence_put(struct xe_user_fence *ufence) +{ + user_fence_put(ufence); +} + +/** + * xe_sync_ufence_get_status() - Get user fence status + * @ufence: user fence + * + * Return: 1 if signalled, 0 not signalled, <0 on error + */ +int xe_sync_ufence_get_status(struct xe_user_fence *ufence) +{ + return READ_ONCE(ufence->signalled); +} diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h index f43cdcaca6c5..0fd0d51208e6 100644 --- a/drivers/gpu/drm/xe/xe_sync.h +++ b/drivers/gpu/drm/xe/xe_sync.h @@ -38,4 +38,8 @@ static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync) return !!sync->ufence; } +struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync); +void xe_sync_ufence_put(struct xe_user_fence *ufence); +int xe_sync_ufence_get_status(struct xe_user_fence *ufence); + #endif diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h index 852db5e7884f..30ac3f51993b 100644 --- a/drivers/gpu/drm/xe/xe_sync_types.h +++ b/drivers/gpu/drm/xe/xe_sync_types.h @@ -18,7 +18,7 @@ struct xe_sync_entry { struct drm_syncobj *syncobj; struct dma_fence *fence; struct dma_fence_chain *chain_fence; - struct user_fence *ufence; + struct xe_user_fence *ufence; u64 addr; u64 timeline_value; u32 type; diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index 95163c303f3e..4ddc55527f9a 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -12,6 +12,7 @@ #include <linux/tracepoint.h> #include <linux/types.h> +#include "xe_bo.h" #include "xe_bo_types.h" #include "xe_exec_queue_types.h" #include "xe_gpu_scheduler_types.h" @@ -26,16 +27,16 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence, TP_ARGS(fence), TP_STRUCT__entry( - __field(u64, fence) + __field(struct xe_gt_tlb_invalidation_fence *, fence) __field(int, seqno) ), TP_fast_assign( - __entry->fence = (u64)fence; + __entry->fence = fence; __entry->seqno = fence->seqno; ), - TP_printk("fence=0x%016llx, seqno=%d", + TP_printk("fence=%p, seqno=%d", __entry->fence, __entry->seqno) ); @@ -82,16 +83,16 @@ DECLARE_EVENT_CLASS(xe_bo, TP_STRUCT__entry( __field(size_t, size) __field(u32, flags) - __field(u64, vm) + __field(struct xe_vm *, vm) ), TP_fast_assign( __entry->size = bo->size; __entry->flags = bo->flags; - __entry->vm = (unsigned long)bo->vm; + __entry->vm = bo->vm; ), - TP_printk("size=%zu, flags=0x%02x, vm=0x%016llx", + TP_printk("size=%zu, flags=0x%02x, vm=%p", __entry->size, __entry->flags, __entry->vm) ); @@ -100,9 +101,31 @@ DEFINE_EVENT(xe_bo, xe_bo_cpu_fault, TP_ARGS(bo) ); -DEFINE_EVENT(xe_bo, xe_bo_move, - TP_PROTO(struct xe_bo *bo), - TP_ARGS(bo) +TRACE_EVENT(xe_bo_move, + TP_PROTO(struct xe_bo *bo, uint32_t new_placement, uint32_t old_placement, + bool move_lacks_source), + TP_ARGS(bo, new_placement, old_placement, move_lacks_source), + TP_STRUCT__entry( + __field(struct xe_bo *, bo) + __field(size_t, size) + __field(u32, new_placement) + __field(u32, old_placement) + __array(char, device_id, 12) + __field(bool, move_lacks_source) + ), + + TP_fast_assign( + __entry->bo = bo; + __entry->size = bo->size; + __entry->new_placement = new_placement; + __entry->old_placement = old_placement; + strscpy(__entry->device_id, dev_name(xe_bo_device(__entry->bo)->drm.dev), 12); + __entry->move_lacks_source = move_lacks_source; + ), + TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s", + __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size, + xe_mem_type_to_name[__entry->old_placement], + xe_mem_type_to_name[__entry->new_placement], __entry->device_id) ); DECLARE_EVENT_CLASS(xe_exec_queue, @@ -327,16 +350,16 @@ DECLARE_EVENT_CLASS(xe_hw_fence, TP_STRUCT__entry( __field(u64, ctx) __field(u32, seqno) - __field(u64, fence) + __field(struct xe_hw_fence *, fence) ), TP_fast_assign( __entry->ctx = fence->dma.context; __entry->seqno = fence->dma.seqno; - __entry->fence = (unsigned long)fence; + __entry->fence = fence; ), - TP_printk("ctx=0x%016llx, fence=0x%016llx, seqno=%u", + TP_printk("ctx=0x%016llx, fence=%p, seqno=%u", __entry->ctx, __entry->fence, __entry->seqno) ); @@ -365,7 +388,7 @@ DECLARE_EVENT_CLASS(xe_vma, TP_ARGS(vma), TP_STRUCT__entry( - __field(u64, vma) + __field(struct xe_vma *, vma) __field(u32, asid) __field(u64, start) __field(u64, end) @@ -373,14 +396,14 @@ DECLARE_EVENT_CLASS(xe_vma, ), TP_fast_assign( - __entry->vma = (unsigned long)vma; + __entry->vma = vma; __entry->asid = xe_vma_vm(vma)->usm.asid; __entry->start = xe_vma_start(vma); __entry->end = xe_vma_end(vma) - 1; __entry->ptr = xe_vma_userptr(vma); ), - TP_printk("vma=0x%016llx, asid=0x%05x, start=0x%012llx, end=0x%012llx, ptr=0x%012llx,", + TP_printk("vma=%p, asid=0x%05x, start=0x%012llx, end=0x%012llx, userptr=0x%012llx,", __entry->vma, __entry->asid, __entry->start, __entry->end, __entry->ptr) ) @@ -465,16 +488,16 @@ DECLARE_EVENT_CLASS(xe_vm, TP_ARGS(vm), TP_STRUCT__entry( - __field(u64, vm) + __field(struct xe_vm *, vm) __field(u32, asid) ), TP_fast_assign( - __entry->vm = (unsigned long)vm; + __entry->vm = vm; __entry->asid = vm->usm.asid; ), - TP_printk("vm=0x%016llx, asid=0x%05x", __entry->vm, + TP_printk("vm=%p, asid=0x%05x", __entry->vm, __entry->asid) ); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 921ca28d49dd..3b21afe5b488 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -897,6 +897,11 @@ static void xe_vma_destroy_late(struct xe_vma *vma) struct xe_device *xe = vm->xe; bool read_only = xe_vma_read_only(vma); + if (vma->ufence) { + xe_sync_ufence_put(vma->ufence); + vma->ufence = NULL; + } + if (xe_vma_is_userptr(vma)) { struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr; @@ -1608,6 +1613,16 @@ xe_vm_unbind_vma(struct xe_vma *vma, struct xe_exec_queue *q, trace_xe_vma_unbind(vma); + if (vma->ufence) { + struct xe_user_fence * const f = vma->ufence; + + if (!xe_sync_ufence_get_status(f)) + return ERR_PTR(-EBUSY); + + vma->ufence = NULL; + xe_sync_ufence_put(f); + } + if (number_tiles > 1) { fences = kmalloc_array(number_tiles, sizeof(*fences), GFP_KERNEL); @@ -1741,6 +1756,21 @@ err_fences: return ERR_PTR(err); } +static struct xe_user_fence * +find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs) +{ + unsigned int i; + + for (i = 0; i < num_syncs; i++) { + struct xe_sync_entry *e = &syncs[i]; + + if (xe_sync_is_ufence(e)) + return xe_sync_ufence_get(e); + } + + return NULL; +} + static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma, struct xe_exec_queue *q, struct xe_sync_entry *syncs, u32 num_syncs, bool immediate, bool first_op, @@ -1748,9 +1778,16 @@ static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma, { struct dma_fence *fence; struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, q); + struct xe_user_fence *ufence; xe_vm_assert_held(vm); + ufence = find_ufence_get(syncs, num_syncs); + if (vma->ufence && ufence) + xe_sync_ufence_put(vma->ufence); + + vma->ufence = ufence ?: vma->ufence; + if (immediate) { fence = xe_vm_bind_vma(vma, q, syncs, num_syncs, first_op, last_op); @@ -2117,10 +2154,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, struct xe_vma_op *op = gpuva_op_to_vma_op(__op); if (__op->op == DRM_GPUVA_OP_MAP) { - op->map.immediate = - flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE; - op->map.read_only = - flags & DRM_XE_VM_BIND_FLAG_READONLY; op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; op->map.pat_index = pat_index; } else if (__op->op == DRM_GPUVA_OP_PREFETCH) { @@ -2313,8 +2346,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, switch (op->base.op) { case DRM_GPUVA_OP_MAP: { - flags |= op->map.read_only ? - VMA_CREATE_FLAG_READ_ONLY : 0; flags |= op->map.is_null ? VMA_CREATE_FLAG_IS_NULL : 0; @@ -2445,7 +2476,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm, case DRM_GPUVA_OP_MAP: err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma), op->syncs, op->num_syncs, - op->map.immediate || !xe_vm_in_fault_mode(vm), + !xe_vm_in_fault_mode(vm), op->flags & XE_VMA_OP_FIRST, op->flags & XE_VMA_OP_LAST); break; @@ -2720,14 +2751,11 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, return 0; } -#define SUPPORTED_FLAGS \ - (DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL) +#define SUPPORTED_FLAGS (DRM_XE_VM_BIND_FLAG_NULL | \ + DRM_XE_VM_BIND_FLAG_DUMPABLE) #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) -#define MAX_BINDS 512 /* FIXME: Picking random upper limit */ - static int vm_bind_ioctl_check_args(struct xe_device *xe, struct drm_xe_vm_bind *args, struct drm_xe_vm_bind_op **bind_ops) @@ -2739,16 +2767,16 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1])) return -EINVAL; - if (XE_IOCTL_DBG(xe, args->extensions) || - XE_IOCTL_DBG(xe, args->num_binds > MAX_BINDS)) + if (XE_IOCTL_DBG(xe, args->extensions)) return -EINVAL; if (args->num_binds > 1) { u64 __user *bind_user = u64_to_user_ptr(args->vector_of_binds); - *bind_ops = kmalloc(sizeof(struct drm_xe_vm_bind_op) * - args->num_binds, GFP_KERNEL); + *bind_ops = kvmalloc_array(args->num_binds, + sizeof(struct drm_xe_vm_bind_op), + GFP_KERNEL | __GFP_ACCOUNT); if (!*bind_ops) return -ENOMEM; @@ -2838,7 +2866,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, free_bind_ops: if (args->num_binds > 1) - kfree(*bind_ops); + kvfree(*bind_ops); return err; } @@ -2926,13 +2954,15 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } if (args->num_binds) { - bos = kcalloc(args->num_binds, sizeof(*bos), GFP_KERNEL); + bos = kvcalloc(args->num_binds, sizeof(*bos), + GFP_KERNEL | __GFP_ACCOUNT); if (!bos) { err = -ENOMEM; goto release_vm_lock; } - ops = kcalloc(args->num_binds, sizeof(*ops), GFP_KERNEL); + ops = kvcalloc(args->num_binds, sizeof(*ops), + GFP_KERNEL | __GFP_ACCOUNT); if (!ops) { err = -ENOMEM; goto release_vm_lock; @@ -3073,10 +3103,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) for (i = 0; bos && i < args->num_binds; ++i) xe_bo_put(bos[i]); - kfree(bos); - kfree(ops); + kvfree(bos); + kvfree(ops); if (args->num_binds > 1) - kfree(bind_ops); + kvfree(bind_ops); return err; @@ -3100,10 +3130,10 @@ put_exec_queue: if (q) xe_exec_queue_put(q); free_objs: - kfree(bos); - kfree(ops); + kvfree(bos); + kvfree(ops); if (args->num_binds > 1) - kfree(bind_ops); + kvfree(bind_ops); return err; } diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index a603cc2eb56b..7300eea5394b 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -19,6 +19,7 @@ struct xe_bo; struct xe_sync_entry; +struct xe_user_fence; struct xe_vm; #define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS @@ -104,6 +105,12 @@ struct xe_vma { * @pat_index: The pat index to use when encoding the PTEs for this vma. */ u16 pat_index; + + /** + * @ufence: The user fence that was provided with MAP. + * Needs to be signalled before UNMAP can be processed. + */ + struct xe_user_fence *ufence; }; /** @@ -288,10 +295,6 @@ struct xe_vm { struct xe_vma_op_map { /** @vma: VMA to map */ struct xe_vma *vma; - /** @immediate: Immediate bind */ - bool immediate; - /** @read_only: Read only */ - bool read_only; /** @is_null: is NULL binding */ bool is_null; /** @pat_index: The pat index to use for this operation. */ diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 42fd504abbcd..89983d7d73ca 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -169,6 +169,7 @@ static const struct host1x_info host1x06_info = { .num_sid_entries = ARRAY_SIZE(tegra186_sid_table), .sid_table = tegra186_sid_table, .reserve_vblank_syncpts = false, + .skip_reset_assert = true, }; static const struct host1x_sid_entry tegra194_sid_table[] = { @@ -680,13 +681,15 @@ static int __maybe_unused host1x_runtime_suspend(struct device *dev) host1x_intr_stop(host); host1x_syncpt_save(host); - err = reset_control_bulk_assert(host->nresets, host->resets); - if (err) { - dev_err(dev, "failed to assert reset: %d\n", err); - goto resume_host1x; - } + if (!host->info->skip_reset_assert) { + err = reset_control_bulk_assert(host->nresets, host->resets); + if (err) { + dev_err(dev, "failed to assert reset: %d\n", err); + goto resume_host1x; + } - usleep_range(1000, 2000); + usleep_range(1000, 2000); + } clk_disable_unprepare(host->clk); reset_control_bulk_release(host->nresets, host->resets); diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index c8e302de7625..925a118db23f 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -116,6 +116,12 @@ struct host1x_info { * the display driver disables VBLANK increments. */ bool reserve_vblank_syncpts; + /* + * On Tegra186, secure world applications may require access to + * host1x during suspend/resume. To allow this, we need to leave + * host1x not in reset. + */ + bool skip_reset_assert; }; struct host1x { diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56f7e06c673e..adbf674355b2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer, pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT; - /* do we need a gpadl body msg */ pfnsize = MAX_SIZE_CHANNEL_MESSAGE - sizeof(struct vmbus_channel_gpadl_header) - sizeof(struct gpa_range); + pfncount = umin(pagecount, pfnsize / sizeof(u64)); + + msgsize = sizeof(struct vmbus_channel_msginfo) + + sizeof(struct vmbus_channel_gpadl_header) + + sizeof(struct gpa_range) + pfncount * sizeof(u64); + msgheader = kzalloc(msgsize, GFP_KERNEL); + if (!msgheader) + return -ENOMEM; + + INIT_LIST_HEAD(&msgheader->submsglist); + msgheader->msgsize = msgsize; + + gpadl_header = (struct vmbus_channel_gpadl_header *) + msgheader->msg; + gpadl_header->rangecount = 1; + gpadl_header->range_buflen = sizeof(struct gpa_range) + + pagecount * sizeof(u64); + gpadl_header->range[0].byte_offset = 0; + gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); + for (i = 0; i < pfncount; i++) + gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( + type, kbuffer, size, send_offset, i); + *msginfo = msgheader; + + pfnsum = pfncount; + pfnleft = pagecount - pfncount; + + /* how many pfns can we fit in a body message */ + pfnsize = MAX_SIZE_CHANNEL_MESSAGE - + sizeof(struct vmbus_channel_gpadl_body); pfncount = pfnsize / sizeof(u64); - if (pagecount > pfncount) { - /* we need a gpadl body */ - /* fill in the header */ + /* + * If pfnleft is zero, everything fits in the header and no body + * messages are needed + */ + while (pfnleft) { + pfncurr = umin(pfncount, pfnleft); msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pfncount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (!msgheader) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pfncount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - *msginfo = msgheader; - - pfnsum = pfncount; - pfnleft = pagecount - pfncount; - - /* how many pfns can we fit */ - pfnsize = MAX_SIZE_CHANNEL_MESSAGE - - sizeof(struct vmbus_channel_gpadl_body); - pfncount = pfnsize / sizeof(u64); - - /* fill in the body */ - while (pfnleft) { - if (pfnleft > pfncount) - pfncurr = pfncount; - else - pfncurr = pfnleft; - - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_body) + - pfncurr * sizeof(u64); - msgbody = kzalloc(msgsize, GFP_KERNEL); - - if (!msgbody) { - struct vmbus_channel_msginfo *pos = NULL; - struct vmbus_channel_msginfo *tmp = NULL; - /* - * Free up all the allocated messages. - */ - list_for_each_entry_safe(pos, tmp, - &msgheader->submsglist, - msglistentry) { - - list_del(&pos->msglistentry); - kfree(pos); - } - - goto nomem; - } - - msgbody->msgsize = msgsize; - gpadl_body = - (struct vmbus_channel_gpadl_body *)msgbody->msg; + sizeof(struct vmbus_channel_gpadl_body) + + pfncurr * sizeof(u64); + msgbody = kzalloc(msgsize, GFP_KERNEL); + if (!msgbody) { + struct vmbus_channel_msginfo *pos = NULL; + struct vmbus_channel_msginfo *tmp = NULL; /* - * Gpadl is u32 and we are using a pointer which could - * be 64-bit - * This is governed by the guest/host protocol and - * so the hypervisor guarantees that this is ok. + * Free up all the allocated messages. */ - for (i = 0; i < pfncurr; i++) - gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, - kbuffer, size, send_offset, pfnsum + i); - - /* add to msg header */ - list_add_tail(&msgbody->msglistentry, - &msgheader->submsglist); - pfnsum += pfncurr; - pfnleft -= pfncurr; + list_for_each_entry_safe(pos, tmp, + &msgheader->submsglist, + msglistentry) { + + list_del(&pos->msglistentry); + kfree(pos); + } + kfree(msgheader); + return -ENOMEM; } - } else { - /* everything fits in a header */ - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pagecount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (msgheader == NULL) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pagecount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - - *msginfo = msgheader; + + msgbody->msgsize = msgsize; + gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg; + + /* + * Gpadl is u32 and we are using a pointer which could + * be 64-bit + * This is governed by the guest/host protocol and + * so the hypervisor guarantees that this is ok. + */ + for (i = 0; i < pfncurr; i++) + gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, + kbuffer, size, send_offset, pfnsum + i); + + /* add to msg header */ + list_add_tail(&msgbody->msglistentry, &msgheader->submsglist); + pfnsum += pfncurr; + pfnleft -= pfncurr; } return 0; -nomem: - kfree(msgheader); - kfree(msgbody); - return -ENOMEM; } /* diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 42aec2c5606a..9c97c4065fe7 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -296,6 +296,11 @@ static struct { spinlock_t lock; } host_ts; +static bool timesync_implicit; + +module_param(timesync_implicit, bool, 0644); +MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind"); + static inline u64 reftime_to_ns(u64 reftime) { return (reftime - WLTIMEDELTA) * 100; @@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work) } /* + * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume. + * Force a sync if the guest is behind. + */ +static inline bool hv_implicit_sync(u64 host_time) +{ + struct timespec64 new_ts; + struct timespec64 threshold_ts; + + new_ts = ns_to_timespec64(reftime_to_ns(host_time)); + ktime_get_real_ts64(&threshold_ts); + + threshold_ts.tv_sec += 5; + + /* + * If guest behind the host by 5 or more seconds. + */ + if (timespec64_compare(&new_ts, &threshold_ts) >= 0) + return true; + + return false; +} + +/* * Synchronize time with host after reboot, restore, etc. * * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM. @@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags) spin_unlock_irqrestore(&host_ts.lock, flags); /* Schedule work to do do_settimeofday64() */ - if (adj_flags & ICTIMESYNCFLAG_SYNC) + if ((adj_flags & ICTIMESYNCFLAG_SYNC) || + (timesync_implicit && hv_implicit_sync(host_ts.host_time))) schedule_work(&adj_time_work); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b33d5abd9beb..7f7965f3d187 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = { }; /* The one and only one */ -static struct bus_type hv_bus = { +static const struct bus_type hv_bus = { .name = "vmbus", .match = vmbus_match, .shutdown = vmbus_shutdown, diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 7f91c8d0064b..65814cbc8402 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -117,11 +117,11 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm if (ret) goto out_free_domain; domain->users = 1; - refcount_set(&handle->users, 1); list_add(&domain->next, &mm->iommu_mm->sva_domains); - list_add(&handle->handle_item, &mm->iommu_mm->sva_handles); out: + refcount_set(&handle->users, 1); + list_add(&handle->handle_item, &mm->iommu_mm->sva_handles); mutex_unlock(&iommu_sva_lock); handle->dev = dev; handle->domain = domain; diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 504ac1b01b2d..05fd9d3abf1b 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1330,20 +1330,23 @@ out_unlock: int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access) { + u32 new_id; int rc; down_write(&iopt->domains_rwsem); down_write(&iopt->iova_rwsem); - rc = xa_alloc(&iopt->access_list, &access->iopt_access_list_id, access, - xa_limit_16b, GFP_KERNEL_ACCOUNT); + rc = xa_alloc(&iopt->access_list, &new_id, access, xa_limit_16b, + GFP_KERNEL_ACCOUNT); + if (rc) goto out_unlock; rc = iopt_calculate_iova_alignment(iopt); if (rc) { - xa_erase(&iopt->access_list, access->iopt_access_list_id); + xa_erase(&iopt->access_list, new_id); goto out_unlock; } + access->iopt_access_list_id = new_id; out_unlock: up_write(&iopt->iova_rwsem); diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 8abf9747773e..7a2199470f31 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -36,7 +36,7 @@ static struct mock_bus_type iommufd_mock_bus_type = { }, }; -static atomic_t mock_dev_num; +static DEFINE_IDA(mock_dev_ida); enum { MOCK_DIRTY_TRACK = 1, @@ -63,8 +63,8 @@ enum { * In syzkaller mode the 64 bit IOVA is converted into an nth area and offset * value. This has a much smaller randomization space and syzkaller can hit it. */ -static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt, - u64 *iova) +static unsigned long __iommufd_test_syz_conv_iova(struct io_pagetable *iopt, + u64 *iova) { struct syz_layout { __u32 nth_area; @@ -88,6 +88,21 @@ static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt, return 0; } +static unsigned long iommufd_test_syz_conv_iova(struct iommufd_access *access, + u64 *iova) +{ + unsigned long ret; + + mutex_lock(&access->ioas_lock); + if (!access->ioas) { + mutex_unlock(&access->ioas_lock); + return 0; + } + ret = __iommufd_test_syz_conv_iova(&access->ioas->iopt, iova); + mutex_unlock(&access->ioas_lock); + return ret; +} + void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, unsigned int ioas_id, u64 *iova, u32 *flags) { @@ -100,7 +115,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, ioas = iommufd_get_ioas(ucmd->ictx, ioas_id); if (IS_ERR(ioas)) return; - *iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova); + *iova = __iommufd_test_syz_conv_iova(&ioas->iopt, iova); iommufd_put_object(ucmd->ictx, &ioas->obj); } @@ -123,6 +138,7 @@ enum selftest_obj_type { struct mock_dev { struct device dev; unsigned long flags; + int id; }; struct selftest_obj { @@ -430,20 +446,27 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, /* * iommufd generates unmaps that must be a strict - * superset of the map's performend So every starting - * IOVA should have been an iova passed to map, and the + * superset of the map's performend So every + * starting/ending IOVA should have been an iova passed + * to map. * - * First IOVA must be present and have been a first IOVA - * passed to map_pages + * This simple logic doesn't work when the HUGE_PAGE is + * turned on since the core code will automatically + * switch between the two page sizes creating a break in + * the unmap calls. The break can land in the middle of + * contiguous IOVA. */ - if (first) { - WARN_ON(ent && !(xa_to_value(ent) & - MOCK_PFN_START_IOVA)); - first = false; + if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) { + if (first) { + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_START_IOVA)); + first = false; + } + if (pgcount == 1 && + cur + MOCK_IO_PAGE_SIZE == pgsize) + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_LAST_IOVA)); } - if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) - WARN_ON(ent && !(xa_to_value(ent) & - MOCK_PFN_LAST_IOVA)); iova += MOCK_IO_PAGE_SIZE; ret += MOCK_IO_PAGE_SIZE; @@ -631,7 +654,7 @@ static void mock_dev_release(struct device *dev) { struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); - atomic_dec(&mock_dev_num); + ida_free(&mock_dev_ida, mdev->id); kfree(mdev); } @@ -653,8 +676,12 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; - rc = dev_set_name(&mdev->dev, "iommufd_mock%u", - atomic_inc_return(&mock_dev_num)); + rc = ida_alloc(&mock_dev_ida, GFP_KERNEL); + if (rc < 0) + goto err_put; + mdev->id = rc; + + rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id); if (rc) goto err_put; @@ -1156,7 +1183,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd, } if (flags & MOCK_FLAGS_ACCESS_SYZ) - iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt, + iova = iommufd_test_syz_conv_iova(staccess->access, &cmd->access_pages.iova); npages = (ALIGN(iova + length, PAGE_SIZE) - @@ -1258,8 +1285,8 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd, } if (flags & MOCK_FLAGS_ACCESS_SYZ) - iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt, - &cmd->access_rw.iova); + iova = iommufd_test_syz_conv_iova(staccess->access, + &cmd->access_rw.iova); rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags); if (rc) diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 6e80d7bd3c4d..3ed257334562 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -49,7 +49,9 @@ MODULE_LICENSE("GPL"); /* -------- driver information -------------------------------------- */ static DEFINE_MUTEX(capi_mutex); -static struct class *capi_class; +static const struct class capi_class = { + .name = "capi", +}; static int capi_major = 68; /* allocated */ module_param_named(major, capi_major, uint, 0); @@ -1393,18 +1395,19 @@ static int __init capi_init(void) kcapi_exit(); return major_ret; } - capi_class = class_create("capi"); - if (IS_ERR(capi_class)) { + + ret = class_register(&capi_class); + if (ret) { unregister_chrdev(capi_major, "capi20"); kcapi_exit(); - return PTR_ERR(capi_class); + return ret; } - device_create(capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20"); + device_create(&capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20"); if (capinc_tty_init() < 0) { - device_destroy(capi_class, MKDEV(capi_major, 0)); - class_destroy(capi_class); + device_destroy(&capi_class, MKDEV(capi_major, 0)); + class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); kcapi_exit(); return -ENOMEM; @@ -1427,8 +1430,8 @@ static void __exit capi_exit(void) { proc_exit(); - device_destroy(capi_class, MKDEV(capi_major, 0)); - class_destroy(capi_class); + device_destroy(&capi_class, MKDEV(capi_major, 0)); + class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); capinc_tty_exit(); diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index 09b72f14d4b7..b4ed0bb8ddfb 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -31,7 +31,9 @@ struct dsp_element_entry { static LIST_HEAD(dsp_elements); /* sysfs */ -static struct class *elements_class; +static const struct class elements_class = { + .name = "dsp_pipeline", +}; static ssize_t attr_show_args(struct device *dev, struct device_attribute *attr, char *buf) @@ -80,7 +82,7 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem) INIT_LIST_HEAD(&entry->list); entry->elem = elem; - entry->dev.class = elements_class; + entry->dev.class = &elements_class; entry->dev.release = mISDN_dsp_dev_release; dev_set_drvdata(&entry->dev, elem); dev_set_name(&entry->dev, "%s", elem->name); @@ -131,9 +133,11 @@ EXPORT_SYMBOL(mISDN_dsp_element_unregister); int dsp_pipeline_module_init(void) { - elements_class = class_create("dsp_pipeline"); - if (IS_ERR(elements_class)) - return PTR_ERR(elements_class); + int err; + + err = class_register(&elements_class); + if (err) + return err; dsp_hwec_init(); @@ -146,7 +150,7 @@ void dsp_pipeline_module_exit(void) dsp_hwec_exit(); - class_destroy(elements_class); + class_unregister(&elements_class); list_for_each_entry_safe(entry, n, &dsp_elements, list) { list_del(&entry->list); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index f410bee50132..58ed7193a3ca 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1015,10 +1015,12 @@ static int mmc_select_bus_width(struct mmc_card *card) static unsigned ext_csd_bits[] = { EXT_CSD_BUS_WIDTH_8, EXT_CSD_BUS_WIDTH_4, + EXT_CSD_BUS_WIDTH_1, }; static unsigned bus_widths[] = { MMC_BUS_WIDTH_8, MMC_BUS_WIDTH_4, + MMC_BUS_WIDTH_1, }; struct mmc_host *host = card->host; unsigned idx, bus_width = 0; diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 35067e1e6cd8..f5da7f9baa52 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -225,6 +225,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i; + host->dma_in_progress = true; + if (!host->variant->dma_lli || data->sg_len == 1 || idma->use_bounce_buffer) { u32 dma_addr; @@ -263,9 +265,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) return 0; } +static void sdmmc_idma_error(struct mmci_host *host) +{ + struct mmc_data *data = host->data; + struct sdmmc_idma *idma = host->dma_priv; + + if (!dma_inprogress(host)) + return; + + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; + data->host_cookie = 0; + + if (!idma->use_bounce_buffer) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); +} + static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data) { + if (!dma_inprogress(host)) + return; + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; if (!data->host_cookie) sdmmc_idma_unprep_data(host, data, 0); @@ -676,6 +699,7 @@ static struct mmci_host_ops sdmmc_variant_ops = { .dma_setup = sdmmc_idma_setup, .dma_start = sdmmc_idma_start, .dma_finalize = sdmmc_idma_finalize, + .dma_error = sdmmc_idma_error, .set_clkreg = mmci_sdmmc_set_clkreg, .set_pwrreg = mmci_sdmmc_set_pwrreg, .busy_complete = sdmmc_busy_complete, diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index 8cf3a375de65..cc9d28b75eb9 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/ktime.h> +#include <linux/iopoll.h> #include <linux/of_address.h> #include "sdhci-pltfm.h" @@ -109,6 +110,8 @@ #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST (XENON_EMMC_PHY_REG_BASE + 0x18) #define XENON_LOGIC_TIMING_VALUE 0x00AA8977 +#define XENON_MAX_PHY_TIMEOUT_LOOPS 100 + /* * List offset of PHY registers and some special register values * in eMMC PHY 5.0 or eMMC PHY 5.1 @@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host) return 0; } +static int xenon_check_stability_internal_clk(struct sdhci_host *host) +{ + u32 reg; + int err; + + err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE, + 1100, 20000, false, host, SDHCI_CLOCK_CONTROL); + if (err) + dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n"); + + return err; +} + /* * eMMC 5.0/5.1 PHY init/re-init. * eMMC PHY init should be executed after: @@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs; + int ret = xenon_check_stability_internal_clk(host); + + if (ret) + return ret; + reg = sdhci_readl(host, phy_regs->timing_adj); reg |= XENON_PHY_INITIALIZAION; sdhci_writel(host, reg, phy_regs->timing_adj); @@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) /* get the wait time */ wait /= clock; wait++; - /* wait for host eMMC PHY init completes */ - udelay(wait); - reg = sdhci_readl(host, phy_regs->timing_adj); - reg &= XENON_PHY_INITIALIZAION; - if (reg) { + /* + * AC5X spec says bit must be polled until zero. + * We see cases in which timeout can take longer + * than the standard calculation on AC5X, which is + * expected following the spec comment above. + * According to the spec, we must wait as long as + * it takes for that bit to toggle on AC5X. + * Cap that with 100 delay loops so we won't get + * stuck here forever: + */ + + ret = read_poll_timeout(sdhci_readl, reg, + !(reg & XENON_PHY_INITIALIZAION), + wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait, + false, host, phy_regs->timing_adj); + if (ret) dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n", - wait); - return -ETIMEDOUT; - } + wait * XENON_MAX_PHY_TIMEOUT_LOOPS); - return 0; + return ret; } #define ARMADA_3700_SOC_PAD_1_8V 0x1 diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 68e79b1272f6..6d15ab3bfbbc 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3063,15 +3063,10 @@ static int amt_dev_init(struct net_device *dev) int err; amt->dev = dev; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; err = gro_cells_init(&amt->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } return 0; } @@ -3081,7 +3076,6 @@ static void amt_dev_uninit(struct net_device *dev) struct amt_dev *amt = netdev_priv(dev); gro_cells_destroy(&amt->gro_cells); - free_percpu(dev->tstats); } static const struct net_device_ops amt_netdev_ops = { @@ -3090,7 +3084,6 @@ static const struct net_device_ops amt_netdev_ops = { .ndo_open = amt_dev_open, .ndo_stop = amt_dev_stop, .ndo_start_xmit = amt_dev_xmit, - .ndo_get_stats64 = dev_get_tstats64, }; static void amt_link_setup(struct net_device *dev) @@ -3111,6 +3104,7 @@ static void amt_link_setup(struct net_device *dev) dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM; dev->hw_features |= NETIF_F_FRAGLIST | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; eth_hw_addr_random(dev); eth_zero_addr(dev->broadcast); ether_setup(dev); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 4db6122c9b43..339db6e4a1d5 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -194,15 +194,10 @@ static int bareudp_init(struct net_device *dev) struct bareudp_dev *bareudp = netdev_priv(dev); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&bareudp->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } + return 0; } @@ -211,7 +206,6 @@ static void bareudp_uninit(struct net_device *dev) struct bareudp_dev *bareudp = netdev_priv(dev); gro_cells_destroy(&bareudp->gro_cells); - free_percpu(dev->tstats); } static struct socket *bareudp_create_sock(struct net *net, __be16 port) @@ -529,7 +523,6 @@ static const struct net_device_ops bareudp_netdev_ops = { .ndo_open = bareudp_open, .ndo_stop = bareudp_stop, .ndo_start_xmit = bareudp_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_fill_metadata_dst = bareudp_fill_metadata_dst, }; @@ -567,6 +560,7 @@ static void bareudp_setup(struct net_device *dev) netif_keep_dst(dev); dev->priv_flags |= IFF_NO_QUEUE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ae1a561c4a0f..2c5ed0a7cb18 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev) ASSERT_RTNL(); - if (!bond_xdp_check(bond)) { + if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index 620766eb6bc1..2e31db55d927 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -169,6 +169,7 @@ config CAN_KVASER_PCIEFD Kvaser Mini PCI Express 1xCAN v3 Kvaser Mini PCI Express 2xCAN v3 Kvaser M.2 PCIe 4xCAN + Kvaser PCIe 8xCAN config CAN_SLCAN tristate "Serial / USB serial CAN Adaptors (slcan)" diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 416f10480b40..f81b598147b3 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -27,7 +27,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_BEC_POLL_FREQ (jiffies + msecs_to_jiffies(200)) #define KVASER_PCIEFD_MAX_ERR_REP 256U #define KVASER_PCIEFD_CAN_TX_MAX_COUNT 17U -#define KVASER_PCIEFD_MAX_CAN_CHANNELS 4UL +#define KVASER_PCIEFD_MAX_CAN_CHANNELS 8UL #define KVASER_PCIEFD_DMA_COUNT 2U #define KVASER_PCIEFD_DMA_SIZE (4U * 1024U) @@ -49,6 +49,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); /* Xilinx based devices */ #define KVASER_PCIEFD_M2_4CAN_DEVICE_ID 0x0017 +#define KVASER_PCIEFD_8CAN_DEVICE_ID 0x0019 /* Altera SerDes Enable 64-bit DMA address translation */ #define KVASER_PCIEFD_ALTERA_DMA_64BIT BIT(0) @@ -497,6 +498,10 @@ static struct pci_device_id kvaser_pciefd_id_table[] = { .driver_data = (kernel_ulong_t)&kvaser_pciefd_xilinx_driver_data, }, { + PCI_DEVICE(KVASER_PCIEFD_VENDOR, KVASER_PCIEFD_8CAN_DEVICE_ID), + .driver_data = (kernel_ulong_t)&kvaser_pciefd_xilinx_driver_data, + }, + { 0, }, }; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index eebf967f4711..1d9057dc44f2 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -837,7 +837,7 @@ static int __mcp251xfd_get_berr_counter(const struct net_device *ndev, return err; if (trec & MCP251XFD_REG_TREC_TXBO) - bec->txerr = 256; + bec->txerr = CAN_BUS_OFF_THRESHOLD; else bec->txerr = FIELD_GET(MCP251XFD_REG_TREC_TEC_MASK, trec); bec->rxerr = FIELD_GET(MCP251XFD_REG_TREC_REC_MASK, trec); diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index d1450722cb3c..bd58c636d465 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -100,6 +100,7 @@ config CAN_KVASER_USB - Scania VCI2 (if you have the Kvaser logo on top) - Kvaser BlackBird v2 - Kvaser Leaf Pro HS v2 + - Kvaser Leaf v3 - Kvaser Hybrid CAN/LIN - Kvaser Hybrid 2xCAN/LIN - Kvaser Hybrid Pro CAN/LIN diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 95b0fdb602c8..65c962f76898 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -385,7 +385,7 @@ static struct gs_tx_context *gs_get_tx_context(struct gs_can *dev, static int gs_cmd_reset(struct gs_can *dev) { struct gs_device_mode dm = { - .mode = GS_CAN_MODE_RESET, + .mode = cpu_to_le32(GS_CAN_MODE_RESET), }; return usb_control_msg_send(dev->udev, 0, GS_USB_BREQ_MODE, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 71ef4db5c09f..8faf8a462c05 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -88,6 +88,7 @@ #define USB_USBCAN_PRO_4HS_PRODUCT_ID 0x0114 #define USB_HYBRID_CANLIN_PRODUCT_ID 0x0115 #define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 0x0116 +#define USB_LEAF_V3_PRODUCT_ID 0x0117 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = { .quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP, @@ -235,6 +236,8 @@ static const struct usb_device_id kvaser_usb_table[] = { .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID), .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_V3_PRODUCT_ID), + .driver_info = (kernel_ulong_t)&kvaser_usb_driver_info_hydra }, { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 50351cef6ca5..14923535ca7e 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) mutex_lock(&dev->alu_mutex); ctrl_addr = IND_ACC_TABLE(table) | addr; - ret = ksz_write8(dev, regs[REG_IND_BYTE], data); + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); if (!ret) - ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + ret = ksz_write8(dev, regs[REG_IND_BYTE], data); mutex_unlock(&dev->alu_mutex); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 03d966fa67b2..678b51f9cea6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -966,18 +966,10 @@ mt753x_trap_frames(struct mt7530_priv *priv) MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY)); } -static int +static void mt753x_cpu_port_enable(struct dsa_switch *ds, int port) { struct mt7530_priv *priv = ds->priv; - int ret; - - /* Setup max capability of CPU port at first */ - if (priv->info->cpu_port_config) { - ret = priv->info->cpu_port_config(ds, port); - if (ret) - return ret; - } /* Enable Mediatek header mode on the cpu port */ mt7530_write(priv, MT7530_PVC_P(port), @@ -1003,8 +995,6 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) /* Set to fallback mode for independent VLAN learning */ mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK, MT7530_PORT_FALLBACK_MODE); - - return 0; } static int @@ -1028,7 +1018,6 @@ mt7530_port_enable(struct dsa_switch *ds, int port, priv->ports[port].enable = true; mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, priv->ports[port].pm); - mt7530_clear(priv, MT7530_PMCR_P(port), PMCR_LINK_SETTINGS_MASK); mutex_unlock(&priv->reg_mutex); @@ -1048,7 +1037,6 @@ mt7530_port_disable(struct dsa_switch *ds, int port) priv->ports[port].enable = false; mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, PCR_MATRIX_CLR); - mt7530_clear(priv, MT7530_PMCR_P(port), PMCR_LINK_SETTINGS_MASK); mutex_unlock(&priv->reg_mutex); } @@ -2055,7 +2043,7 @@ mt7530_setup_irq(struct mt7530_priv *priv) } /* This register must be set for MT7530 to properly fire interrupts */ - if (priv->id != ID_MT7531) + if (priv->id == ID_MT7530 || priv->id == ID_MT7621) mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL); ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn, @@ -2204,6 +2192,12 @@ mt7530_setup(struct dsa_switch *ds) } } + /* Disable LEDs before reset to prevent the MT7530 sampling a + * potentially incorrect HT_XTAL_FSEL value. + */ + mt7530_write(priv, MT7530_LED_EN, 0); + usleep_range(1000, 1100); + /* Reset whole chip through gpio pin or memory-mapped registers for * different type of hardware */ @@ -2261,14 +2255,18 @@ mt7530_setup(struct dsa_switch *ds) val |= MHWTRAP_MANUAL; mt7530_write(priv, MT7530_MHWTRAP, val); - priv->p6_interface = PHY_INTERFACE_MODE_NA; - mt753x_trap_frames(priv); /* Enable and reset MIB counters */ mt7530_mib_reset(ds); for (i = 0; i < MT7530_NUM_PORTS; i++) { + /* Clear link settings and enable force mode to force link down + * on all ports until they're enabled later. + */ + mt7530_rmw(priv, MT7530_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | + PMCR_FORCE_MODE, PMCR_FORCE_MODE); + /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, PCR_MATRIX_CLR); @@ -2277,9 +2275,7 @@ mt7530_setup(struct dsa_switch *ds) mt7530_set(priv, MT7530_PSC_P(i), SA_DIS); if (dsa_is_cpu_port(ds, i)) { - ret = mt753x_cpu_port_enable(ds, i); - if (ret) - return ret; + mt753x_cpu_port_enable(ds, i); } else { mt7530_port_disable(ds, i); @@ -2373,6 +2369,12 @@ mt7531_setup_common(struct dsa_switch *ds) UNU_FFP_MASK); for (i = 0; i < MT7530_NUM_PORTS; i++) { + /* Clear link settings and enable force mode to force link down + * on all ports until they're enabled later. + */ + mt7530_rmw(priv, MT7530_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | + MT7531_FORCE_MODE, MT7531_FORCE_MODE); + /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, PCR_MATRIX_CLR); @@ -2383,9 +2385,7 @@ mt7531_setup_common(struct dsa_switch *ds) mt7530_set(priv, MT7531_DBG_CNT(i), MT7531_DIS_CLR); if (dsa_is_cpu_port(ds, i)) { - ret = mt753x_cpu_port_enable(ds, i); - if (ret) - return ret; + mt753x_cpu_port_enable(ds, i); } else { mt7530_port_disable(ds, i); @@ -2451,14 +2451,12 @@ mt7531_setup(struct dsa_switch *ds) val = mt7530_read(priv, MT7531_TOP_SIG_SR); priv->p5_sgmii = !!(val & PAD_DUAL_SGMII_EN); - /* all MACs must be forced link-down before sw reset */ + /* Force link down on all ports before internal reset */ for (i = 0; i < MT7530_NUM_PORTS; i++) mt7530_write(priv, MT7530_PMCR_P(i), MT7531_FORCE_LNK); /* Reset the switch through internal reset */ - mt7530_write(priv, MT7530_SYS_CTRL, - SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST | - SYS_CTRL_REG_RST); + mt7530_write(priv, MT7530_SYS_CTRL, SYS_CTRL_SW_RST | SYS_CTRL_REG_RST); if (!priv->p5_sgmii) { mt7531_pll_setup(priv); @@ -2476,10 +2474,6 @@ mt7531_setup(struct dsa_switch *ds) mt7530_rmw(priv, MT7531_GPIO_MODE0, MT7531_GPIO0_MASK, MT7531_GPIO0_INTERRUPT); - /* Let phylink decide the interface later. */ - priv->p5_interface = PHY_INTERFACE_MODE_NA; - priv->p6_interface = PHY_INTERFACE_MODE_NA; - /* Enable PHY core PLL, since phy_device has not yet been created * provided for phy_[read,write]_mmd_indirect is called, we provide * our own mt7531_ind_mmd_phy_[read,write] to complete this @@ -2589,7 +2583,7 @@ static void mt7988_mac_port_get_caps(struct dsa_switch *ds, int port, } } -static int +static void mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { @@ -2599,22 +2593,14 @@ mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode, mt7530_setup_port5(priv->ds, interface); else if (port == 6) mt7530_setup_port6(priv->ds, interface); - - return 0; } -static int mt7531_rgmii_setup(struct mt7530_priv *priv, u32 port, - phy_interface_t interface, - struct phy_device *phydev) +static void mt7531_rgmii_setup(struct mt7530_priv *priv, u32 port, + phy_interface_t interface, + struct phy_device *phydev) { u32 val; - if (priv->p5_sgmii) { - dev_err(priv->dev, "RGMII mode is not available for port %d\n", - port); - return -EINVAL; - } - val = mt7530_read(priv, MT7531_CLKGEN_CTRL); val |= GP_CLK_EN; val &= ~GP_MODE_MASK; @@ -2642,31 +2628,14 @@ static int mt7531_rgmii_setup(struct mt7530_priv *priv, u32 port, case PHY_INTERFACE_MODE_RGMII_ID: break; default: - return -EINVAL; + break; } } - mt7530_write(priv, MT7531_CLKGEN_CTRL, val); - - return 0; -} -static bool mt753x_is_mac_port(u32 port) -{ - return (port == 5 || port == 6); -} - -static int -mt7988_mac_config(struct dsa_switch *ds, int port, unsigned int mode, - phy_interface_t interface) -{ - if (dsa_is_cpu_port(ds, port) && - interface == PHY_INTERFACE_MODE_INTERNAL) - return 0; - - return -EINVAL; + mt7530_write(priv, MT7531_CLKGEN_CTRL, val); } -static int +static void mt7531_mac_config(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) { @@ -2674,39 +2643,11 @@ mt7531_mac_config(struct dsa_switch *ds, int port, unsigned int mode, struct phy_device *phydev; struct dsa_port *dp; - if (!mt753x_is_mac_port(port)) { - dev_err(priv->dev, "port %d is not a MAC port\n", port); - return -EINVAL; - } - - switch (interface) { - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: + if (phy_interface_mode_is_rgmii(interface)) { dp = dsa_to_port(ds, port); phydev = dp->user->phydev; - return mt7531_rgmii_setup(priv, port, interface, phydev); - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_NA: - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_2500BASEX: - /* handled in SGMII PCS driver */ - return 0; - default: - return -EINVAL; + mt7531_rgmii_setup(priv, port, interface, phydev); } - - return -EINVAL; -} - -static int -mt753x_mac_config(struct dsa_switch *ds, int port, unsigned int mode, - const struct phylink_link_state *state) -{ - struct mt7530_priv *priv = ds->priv; - - return priv->info->mac_port_config(ds, port, mode, state->interface); } static struct phylink_pcs * @@ -2732,52 +2673,13 @@ mt753x_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { struct mt7530_priv *priv = ds->priv; - u32 mcr_cur, mcr_new; - switch (port) { - case 0 ... 4: - if (state->interface != PHY_INTERFACE_MODE_GMII && - state->interface != PHY_INTERFACE_MODE_INTERNAL) - goto unsupported; - break; - case 5: - if (priv->p5_interface == state->interface) - break; - - if (mt753x_mac_config(ds, port, mode, state) < 0) - goto unsupported; - - if (priv->p5_intf_sel != P5_DISABLED) - priv->p5_interface = state->interface; - break; - case 6: - if (priv->p6_interface == state->interface) - break; - - if (mt753x_mac_config(ds, port, mode, state) < 0) - goto unsupported; - - priv->p6_interface = state->interface; - break; - default: -unsupported: - dev_err(ds->dev, "%s: unsupported %s port: %i\n", - __func__, phy_modes(state->interface), port); - return; - } - - mcr_cur = mt7530_read(priv, MT7530_PMCR_P(port)); - mcr_new = mcr_cur; - mcr_new &= ~PMCR_LINK_SETTINGS_MASK; - mcr_new |= PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | PMCR_BACKOFF_EN | - PMCR_BACKPR_EN | PMCR_FORCE_MODE_ID(priv->id); + if ((port == 5 || port == 6) && priv->info->mac_port_config) + priv->info->mac_port_config(ds, port, mode, state->interface); /* Are we connected to external phy */ if (port == 5 && dsa_is_user_port(ds, 5)) - mcr_new |= PMCR_EXT_PHY; - - if (mcr_new != mcr_cur) - mt7530_write(priv, MT7530_PMCR_P(port), mcr_new); + mt7530_set(priv, MT7530_PMCR_P(port), PMCR_EXT_PHY); } static void mt753x_phylink_mac_link_down(struct dsa_switch *ds, int port, @@ -2801,17 +2703,10 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, mcr = PMCR_RX_EN | PMCR_TX_EN | PMCR_FORCE_LNK; - /* MT753x MAC works in 1G full duplex mode for all up-clocked - * variants. - */ - if (interface == PHY_INTERFACE_MODE_TRGMII || - (phy_interface_mode_is_8023z(interface))) { - speed = SPEED_1000; - duplex = DUPLEX_FULL; - } - switch (speed) { case SPEED_1000: + case SPEED_2500: + case SPEED_10000: mcr |= PMCR_FORCE_SPEED_1000; break; case SPEED_100: @@ -2829,6 +2724,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) { switch (speed) { case SPEED_1000: + case SPEED_2500: mcr |= PMCR_FORCE_EEE1G; break; case SPEED_100: @@ -2840,63 +2736,6 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port, mt7530_set(priv, MT7530_PMCR_P(port), mcr); } -static int -mt7531_cpu_port_config(struct dsa_switch *ds, int port) -{ - struct mt7530_priv *priv = ds->priv; - phy_interface_t interface; - int speed; - int ret; - - switch (port) { - case 5: - if (!priv->p5_sgmii) - interface = PHY_INTERFACE_MODE_RGMII; - else - interface = PHY_INTERFACE_MODE_2500BASEX; - - priv->p5_interface = interface; - break; - case 6: - interface = PHY_INTERFACE_MODE_2500BASEX; - - priv->p6_interface = interface; - break; - default: - return -EINVAL; - } - - if (interface == PHY_INTERFACE_MODE_2500BASEX) - speed = SPEED_2500; - else - speed = SPEED_1000; - - ret = mt7531_mac_config(ds, port, MLO_AN_FIXED, interface); - if (ret) - return ret; - mt7530_write(priv, MT7530_PMCR_P(port), - PMCR_CPU_PORT_SETTING(priv->id)); - mt753x_phylink_mac_link_up(ds, port, MLO_AN_FIXED, interface, NULL, - speed, DUPLEX_FULL, true, true); - - return 0; -} - -static int -mt7988_cpu_port_config(struct dsa_switch *ds, int port) -{ - struct mt7530_priv *priv = ds->priv; - - mt7530_write(priv, MT7530_PMCR_P(port), - PMCR_CPU_PORT_SETTING(priv->id)); - - mt753x_phylink_mac_link_up(ds, port, MLO_AN_FIXED, - PHY_INTERFACE_MODE_INTERNAL, NULL, - SPEED_10000, DUPLEX_FULL, true, true); - - return 0; -} - static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port, struct phylink_config *config) { @@ -2979,17 +2818,9 @@ static int mt753x_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; - int i, ret; - - /* Initialise the PCS devices */ - for (i = 0; i < priv->ds->num_ports; i++) { - priv->pcs[i].pcs.ops = priv->info->pcs_ops; - priv->pcs[i].pcs.neg_mode = true; - priv->pcs[i].priv = priv; - priv->pcs[i].port = i; - } + int ret = priv->info->sw_setup(ds); + int i; - ret = priv->info->sw_setup(ds); if (ret) return ret; @@ -3001,6 +2832,14 @@ mt753x_setup(struct dsa_switch *ds) if (ret && priv->irq) mt7530_free_irq_common(priv); + /* Initialise the PCS devices */ + for (i = 0; i < priv->ds->num_ports; i++) { + priv->pcs[i].pcs.ops = priv->info->pcs_ops; + priv->pcs[i].pcs.neg_mode = true; + priv->pcs[i].priv = priv; + priv->pcs[i].port = i; + } + if (priv->create_sgmii) { ret = priv->create_sgmii(priv); if (ret && priv->irq) @@ -3155,7 +2994,6 @@ const struct mt753x_info mt753x_table[] = { .phy_write_c22 = mt7531_ind_c22_phy_write, .phy_read_c45 = mt7531_ind_c45_phy_read, .phy_write_c45 = mt7531_ind_c45_phy_write, - .cpu_port_config = mt7531_cpu_port_config, .mac_port_get_caps = mt7531_mac_port_get_caps, .mac_port_config = mt7531_mac_config, }, @@ -3167,9 +3005,7 @@ const struct mt753x_info mt753x_table[] = { .phy_write_c22 = mt7531_ind_c22_phy_write, .phy_read_c45 = mt7531_ind_c45_phy_read, .phy_write_c45 = mt7531_ind_c45_phy_write, - .cpu_port_config = mt7988_cpu_port_config, .mac_port_get_caps = mt7988_mac_port_get_caps, - .mac_port_config = mt7988_mac_config, }, }; EXPORT_SYMBOL_GPL(mt753x_table); @@ -3197,8 +3033,7 @@ mt7530_probe_common(struct mt7530_priv *priv) * properly. */ if (!priv->info->sw_setup || !priv->info->phy_read_c22 || - !priv->info->phy_write_c22 || !priv->info->mac_port_get_caps || - !priv->info->mac_port_config) + !priv->info->phy_write_c22 || !priv->info->mac_port_get_caps) return -EINVAL; priv->id = priv->info->id; diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 26a6d2160c08..a71166e0a7fc 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -304,20 +304,11 @@ enum mt7530_vlan_port_acc_frm { MT7531_FORCE_DPX | \ MT7531_FORCE_RX_FC | \ MT7531_FORCE_TX_FC) -#define PMCR_FORCE_MODE_ID(id) ((((id) == ID_MT7531) || ((id) == ID_MT7988)) ? \ - MT7531_FORCE_MODE : PMCR_FORCE_MODE) #define PMCR_LINK_SETTINGS_MASK (PMCR_TX_EN | PMCR_FORCE_SPEED_1000 | \ PMCR_RX_EN | PMCR_FORCE_SPEED_100 | \ PMCR_TX_FC_EN | PMCR_RX_FC_EN | \ PMCR_FORCE_FDX | PMCR_FORCE_LNK | \ PMCR_FORCE_EEE1G | PMCR_FORCE_EEE100) -#define PMCR_CPU_PORT_SETTING(id) (PMCR_FORCE_MODE_ID((id)) | \ - PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \ - PMCR_BACKOFF_EN | PMCR_BACKPR_EN | \ - PMCR_TX_EN | PMCR_RX_EN | \ - PMCR_TX_FC_EN | PMCR_RX_FC_EN | \ - PMCR_FORCE_SPEED_1000 | \ - PMCR_FORCE_FDX | PMCR_FORCE_LNK) #define MT7530_PMEEECR_P(x) (0x3004 + (x) * 0x100) #define WAKEUP_TIME_1000(x) (((x) & 0xFF) << 24) @@ -724,15 +715,14 @@ struct mt753x_info { int regnum); int (*phy_write_c45)(struct mt7530_priv *priv, int port, int devad, int regnum, u16 val); - int (*cpu_port_config)(struct dsa_switch *ds, int port); void (*mac_port_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); void (*mac_port_validate)(struct dsa_switch *ds, int port, phy_interface_t interface, unsigned long *supported); - int (*mac_port_config)(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface); + void (*mac_port_config)(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); }; /* struct mt7530_priv - This is the main data structure for holding the state @@ -750,7 +740,6 @@ struct mt753x_info { * @ports: Holding the state among ports * @reg_mutex: The lock for protecting among process accessing * registers - * @p6_interface Holding the current port 6 interface * @p5_intf_sel: Holding the current port 5 interface select * @p5_sgmii: Flag for distinguishing if port 5 of the MT7531 switch * has got SGMII @@ -772,8 +761,6 @@ struct mt7530_priv { const struct mt753x_info *info; unsigned int id; bool mcm; - phy_interface_t p6_interface; - phy_interface_t p5_interface; enum p5_interface_select p5_intf_sel; bool p5_sgmii; u8 mirror_rx; diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c index 4d677f836807..5a27d047a38e 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c @@ -95,7 +95,7 @@ static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs, } } -static int mv88e6185_pcs_config(struct phylink_pcs *pcs, unsigned int mode, +static int mv88e6185_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, bool permit_pause_to_mac) @@ -137,6 +137,7 @@ static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port) mpcs->chip = chip; mpcs->port = port; mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops; + mpcs->phylink_pcs.neg_mode = true; irq = mv88e6xxx_serdes_irq_mapping(chip, port); if (irq) { diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index a3c79848a69a..2babea110991 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -160,23 +160,19 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf, if (err < 0) { dev_warn(cf->dev, "auxiliary_device_init of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out; + kfree(padev); + return ERR_PTR(err); } err = auxiliary_device_add(aux_dev); if (err) { dev_warn(cf->dev, "auxiliary_device_add of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out_uninit; + auxiliary_device_uninit(aux_dev); + return ERR_PTR(err); } return padev; - -err_out_uninit: - auxiliary_device_uninit(aux_dev); -err_out: - kfree(padev); - return ERR_PTR(err); } int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 528441b28c4e..c9b6acd8c892 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3538,7 +3538,7 @@ static u8 bnx2x_set_pbd_csum_enc(struct bnx2x *bp, struct sk_buff *skb, u32 *parsing_data, u32 xmit_type) { *parsing_data |= - ((((u8 *)skb_inner_transport_header(skb) - skb->data) >> 1) << + ((skb_inner_transport_offset(skb) >> 1) << ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W_SHIFT) & ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W; @@ -3570,7 +3570,7 @@ static u8 bnx2x_set_pbd_csum_e2(struct bnx2x *bp, struct sk_buff *skb, u32 *parsing_data, u32 xmit_type) { *parsing_data |= - ((((u8 *)skb_transport_header(skb) - skb->data) >> 1) << + ((skb_transport_offset(skb) >> 1) << ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W_SHIFT) & ETH_TX_PARSE_BD_E2_L4_HDR_START_OFFSET_W; @@ -3613,7 +3613,7 @@ static u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb, struct eth_tx_parse_bd_e1x *pbd, u32 xmit_type) { - u8 hlen = (skb_network_header(skb) - skb->data) >> 1; + u8 hlen = skb_network_offset(skb) >> 1; /* for now NS flag is not used in Linux */ pbd->global_data = @@ -3621,8 +3621,7 @@ static u8 bnx2x_set_pbd_csum(struct bnx2x *bp, struct sk_buff *skb, ((skb->protocol == cpu_to_be16(ETH_P_8021Q)) << ETH_TX_PARSE_BD_E1X_LLC_SNAP_EN_SHIFT)); - pbd->ip_hlen_w = (skb_transport_header(skb) - - skb_network_header(skb)) >> 1; + pbd->ip_hlen_w = skb_network_header_len(skb) >> 1; hlen += pbd->ip_hlen_w; @@ -3667,8 +3666,7 @@ static void bnx2x_update_pbds_gso_enc(struct sk_buff *skb, u8 outerip_off, outerip_len = 0; /* from outer IP to transport */ - hlen_w = (skb_inner_transport_header(skb) - - skb_network_header(skb)) >> 1; + hlen_w = skb_inner_transport_offset(skb) >> 1; /* transport len */ hlen_w += inner_tcp_hdrlen(skb) >> 1; @@ -3714,7 +3712,7 @@ static void bnx2x_update_pbds_gso_enc(struct sk_buff *skb, 0, IPPROTO_TCP, 0)); } - outerip_off = (skb_network_header(skb) - skb->data) >> 1; + outerip_off = (skb_network_offset(skb)) >> 1; *global_data |= outerip_off | diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a15e6d31fc22..493b724848c8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14523,6 +14523,70 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_bridge_setlink = bnxt_bridge_setlink, }; +static void bnxt_get_queue_stats_rx(struct net_device *dev, int i, + struct netdev_queue_stats_rx *stats) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_cp_ring_info *cpr; + u64 *sw; + + cpr = &bp->bnapi[i]->cp_ring; + sw = cpr->stats.sw_stats; + + stats->packets = 0; + stats->packets += BNXT_GET_RING_STATS64(sw, rx_ucast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, rx_bcast_pkts); + + stats->bytes = 0; + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_ucast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes); + + stats->alloc_fail = cpr->sw_stats.rx.rx_oom_discards; +} + +static void bnxt_get_queue_stats_tx(struct net_device *dev, int i, + struct netdev_queue_stats_tx *stats) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_napi *bnapi; + u64 *sw; + + bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi; + sw = bnapi->cp_ring.stats.sw_stats; + + stats->packets = 0; + stats->packets += BNXT_GET_RING_STATS64(sw, tx_ucast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, tx_mcast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, tx_bcast_pkts); + + stats->bytes = 0; + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_ucast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_mcast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_bcast_bytes); +} + +static void bnxt_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct bnxt *bp = netdev_priv(dev); + + rx->packets = bp->net_stats_prev.rx_packets; + rx->bytes = bp->net_stats_prev.rx_bytes; + rx->alloc_fail = bp->ring_err_stats_prev.rx_total_oom_discards; + + tx->packets = bp->net_stats_prev.tx_packets; + tx->bytes = bp->net_stats_prev.tx_bytes; +} + +static const struct netdev_stat_ops bnxt_stat_ops = { + .get_queue_stats_rx = bnxt_get_queue_stats_rx, + .get_queue_stats_tx = bnxt_get_queue_stats_tx, + .get_base_stats = bnxt_get_base_stats, +}; + static void bnxt_remove_one(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); @@ -14970,6 +15034,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_err_free; dev->netdev_ops = &bnxt_netdev_ops; + dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; pci_set_drvdata(pdev, dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b5ff2e1a9975..49d5808b7d11 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -804,20 +804,6 @@ static inline unsigned int calc_tx_flits(const struct sk_buff *skb, } /** - * calc_tx_descs - calculate the number of Tx descriptors for a packet - * @skb: the packet - * @chip_ver: chip version - * - * Returns the number of Tx descriptors needed for the given Ethernet - * packet, including the needed WR and CPL headers. - */ -static inline unsigned int calc_tx_descs(const struct sk_buff *skb, - unsigned int chip_ver) -{ - return flits_to_desc(calc_tx_flits(skb, chip_ver)); -} - -/** * cxgb4_write_sgl - populate a scatter/gather list for a packet * @skb: the packet * @q: the Tx queue we are writing into diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 207f1f66c117..d7693fdf640d 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2017,6 +2017,37 @@ static int fec_get_mac(struct net_device *ndev) /* * Phy section */ + +/* LPI Sleep Ts count base on tx clk (clk_ref). + * The lpi sleep cnt value = X us / (cycle_ns). + */ +static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + return us * (fep->clk_ref_rate / 1000) / 1000; +} + +static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + struct ethtool_keee *p = &fep->eee; + unsigned int sleep_cycle, wake_cycle; + + if (enable) { + sleep_cycle = fec_enet_us_to_tx_cycle(ndev, p->tx_lpi_timer); + wake_cycle = sleep_cycle; + } else { + sleep_cycle = 0; + wake_cycle = 0; + } + + writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP); + writel(wake_cycle, fep->hwp + FEC_LPI_WAKE); + + return 0; +} + static void fec_enet_adjust_link(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); @@ -2056,6 +2087,8 @@ static void fec_enet_adjust_link(struct net_device *ndev) netif_tx_unlock_bh(ndev); napi_enable(&fep->napi); } + if (fep->quirks & FEC_QUIRK_HAS_EEE) + fec_enet_eee_mode_set(ndev, phy_dev->enable_tx_lpi); } else { if (fep->link) { netif_stop_queue(ndev); @@ -2415,6 +2448,9 @@ static int fec_enet_mii_probe(struct net_device *ndev) else phy_set_max_speed(phy_dev, 100); + if (fep->quirks & FEC_QUIRK_HAS_EEE) + phy_support_eee(phy_dev); + fep->link = 0; fep->full_duplex = 0; @@ -3121,43 +3157,6 @@ static int fec_enet_set_coalesce(struct net_device *ndev, return 0; } -/* LPI Sleep Ts count base on tx clk (clk_ref). - * The lpi sleep cnt value = X us / (cycle_ns). - */ -static int fec_enet_us_to_tx_cycle(struct net_device *ndev, int us) -{ - struct fec_enet_private *fep = netdev_priv(ndev); - - return us * (fep->clk_ref_rate / 1000) / 1000; -} - -static int fec_enet_eee_mode_set(struct net_device *ndev, bool enable) -{ - struct fec_enet_private *fep = netdev_priv(ndev); - struct ethtool_keee *p = &fep->eee; - unsigned int sleep_cycle, wake_cycle; - int ret = 0; - - if (enable) { - ret = phy_init_eee(ndev->phydev, false); - if (ret) - return ret; - - sleep_cycle = fec_enet_us_to_tx_cycle(ndev, p->tx_lpi_timer); - wake_cycle = sleep_cycle; - } else { - sleep_cycle = 0; - wake_cycle = 0; - } - - p->tx_lpi_enabled = enable; - - writel(sleep_cycle, fep->hwp + FEC_LPI_SLEEP); - writel(wake_cycle, fep->hwp + FEC_LPI_WAKE); - - return 0; -} - static int fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata) { @@ -3171,7 +3170,6 @@ fec_enet_get_eee(struct net_device *ndev, struct ethtool_keee *edata) return -ENETDOWN; edata->tx_lpi_timer = p->tx_lpi_timer; - edata->tx_lpi_enabled = p->tx_lpi_enabled; return phy_ethtool_get_eee(ndev->phydev, edata); } @@ -3181,7 +3179,6 @@ fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata) { struct fec_enet_private *fep = netdev_priv(ndev); struct ethtool_keee *p = &fep->eee; - int ret = 0; if (!(fep->quirks & FEC_QUIRK_HAS_EEE)) return -EOPNOTSUPP; @@ -3191,15 +3188,6 @@ fec_enet_set_eee(struct net_device *ndev, struct ethtool_keee *edata) p->tx_lpi_timer = edata->tx_lpi_timer; - if (!edata->eee_enabled || !edata->tx_lpi_enabled || - !edata->tx_lpi_timer) - ret = fec_enet_eee_mode_set(ndev, false); - else - ret = fec_enet_eee_mode_set(ndev, true); - - if (ret) - return ret; - return phy_ethtool_set_eee(ndev->phydev, edata); } diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index fd290f3ad6ec..4814c96d5fe7 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -9,6 +9,7 @@ #include <linux/dma-mapping.h> #include <linux/dmapool.h> +#include <linux/ethtool_netlink.h> #include <linux/netdevice.h> #include <linux/pci.h> #include <linux/u64_stats_sync.h> @@ -51,12 +52,16 @@ #define GVE_DEFAULT_RX_BUFFER_SIZE 2048 +#define GVE_MAX_RX_BUFFER_SIZE 4096 + #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048 #define GVE_XDP_ACTIONS 5 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182 +#define GVE_DEFAULT_HEADER_BUFFER_SIZE 128 + #define DQO_QPL_DEFAULT_TX_PAGES 512 #define DQO_QPL_DEFAULT_RX_PAGES 2048 @@ -150,6 +155,11 @@ struct gve_rx_compl_queue_dqo { u32 mask; /* Mask for indices to the size of the ring */ }; +struct gve_header_buf { + u8 *data; + dma_addr_t addr; +}; + /* Stores state for tracking buffers posted to HW */ struct gve_rx_buf_state_dqo { /* The page posted to HW. */ @@ -252,19 +262,26 @@ struct gve_rx_ring { /* track number of used buffers */ u16 used_buf_states_cnt; + + /* Address info of the buffers for header-split */ + struct gve_header_buf hdr_bufs; } dqo; }; u64 rbytes; /* free-running bytes received */ + u64 rx_hsplit_bytes; /* free-running header bytes received */ u64 rpackets; /* free-running packets received */ u32 cnt; /* free-running total number of completed packets */ u32 fill_cnt; /* free-running total number of descs and buffs posted */ u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ + u64 rx_hsplit_pkt; /* free-running packets with headers split */ u64 rx_copybreak_pkt; /* free-running count of copybreak packets */ u64 rx_copied_pkt; /* free-running total number of copied packets */ u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */ u64 rx_buf_alloc_fail; /* free-running count of buffer alloc fails */ u64 rx_desc_err_dropped_pkt; /* free-running count of packets dropped by descriptor error */ + /* free-running count of unsplit packets due to header buffer overflow or hdr_len is 0 */ + u64 rx_hsplit_unsplit_pkt; u64 rx_cont_packet_cnt; /* free-running multi-fragment packets received */ u64 rx_frag_flip_cnt; /* free-running count of rx segments where page_flip was used */ u64 rx_frag_copy_cnt; /* free-running count of rx segments copied */ @@ -664,6 +681,7 @@ struct gve_rx_alloc_rings_cfg { struct gve_qpl_config *qpl_cfg; u16 ring_size; + u16 packet_buffer_size; bool raw_addressing; bool enable_header_split; @@ -778,13 +796,17 @@ struct gve_priv { struct gve_ptype_lut *ptype_lut_dqo; /* Must be a power of two. */ - int data_buffer_size_dqo; + u16 data_buffer_size_dqo; + u16 max_rx_buffer_size; /* device limit */ enum gve_queue_format queue_format; /* Interrupt coalescing settings */ u32 tx_coalesce_usecs; u32 rx_coalesce_usecs; + + u16 header_buf_size; /* device configured, header-split supported if non-zero */ + bool header_split_enabled; /* True if the header split is enabled by the user */ }; enum gve_service_task_flags_bit { @@ -1122,6 +1144,9 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *cfg); void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx); void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx); +u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hplit); +bool gve_header_split_supported(const struct gve_priv *priv); +int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split); /* Reset */ void gve_schedule_reset(struct gve_priv *priv); int gve_reset(struct gve_priv *priv, bool attempt_teardown); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 12fbd723ecc6..ae12ac38e18b 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -40,7 +40,8 @@ void gve_parse_device_option(struct gve_priv *priv, struct gve_device_option_gqi_qpl **dev_op_gqi_qpl, struct gve_device_option_dqo_rda **dev_op_dqo_rda, struct gve_device_option_jumbo_frames **dev_op_jumbo_frames, - struct gve_device_option_dqo_qpl **dev_op_dqo_qpl) + struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, + struct gve_device_option_buffer_sizes **dev_op_buffer_sizes) { u32 req_feat_mask = be32_to_cpu(option->required_features_mask); u16 option_length = be16_to_cpu(option->option_length); @@ -147,6 +148,23 @@ void gve_parse_device_option(struct gve_priv *priv, } *dev_op_jumbo_frames = (void *)(option + 1); break; + case GVE_DEV_OPT_ID_BUFFER_SIZES: + if (option_length < sizeof(**dev_op_buffer_sizes) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "Buffer Sizes", + (int)sizeof(**dev_op_buffer_sizes), + GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_buffer_sizes)) + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, + "Buffer Sizes"); + *dev_op_buffer_sizes = (void *)(option + 1); + break; default: /* If we don't recognize the option just continue * without doing anything. @@ -164,7 +182,8 @@ gve_process_device_options(struct gve_priv *priv, struct gve_device_option_gqi_qpl **dev_op_gqi_qpl, struct gve_device_option_dqo_rda **dev_op_dqo_rda, struct gve_device_option_jumbo_frames **dev_op_jumbo_frames, - struct gve_device_option_dqo_qpl **dev_op_dqo_qpl) + struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, + struct gve_device_option_buffer_sizes **dev_op_buffer_sizes) { const int num_options = be16_to_cpu(descriptor->num_device_options); struct gve_device_option *dev_opt; @@ -185,7 +204,7 @@ gve_process_device_options(struct gve_priv *priv, gve_parse_device_option(priv, descriptor, dev_opt, dev_op_gqi_rda, dev_op_gqi_qpl, dev_op_dqo_rda, dev_op_jumbo_frames, - dev_op_dqo_qpl); + dev_op_dqo_qpl, dev_op_buffer_sizes); dev_opt = next_opt; } @@ -640,6 +659,9 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) cpu_to_be16(rx_buff_ring_entries); cmd.create_rx_queue.enable_rsc = !!(priv->dev->features & NETIF_F_LRO); + if (priv->header_split_enabled) + cmd.create_rx_queue.header_buffer_size = + cpu_to_be16(priv->header_buf_size); } return gve_adminq_issue_cmd(priv, &cmd); @@ -755,7 +777,9 @@ static void gve_enable_supported_features(struct gve_priv *priv, const struct gve_device_option_jumbo_frames *dev_op_jumbo_frames, const struct gve_device_option_dqo_qpl - *dev_op_dqo_qpl) + *dev_op_dqo_qpl, + const struct gve_device_option_buffer_sizes + *dev_op_buffer_sizes) { /* Before control reaches this point, the page-size-capped max MTU from * the gve_device_descriptor field has already been stored in @@ -779,10 +803,22 @@ static void gve_enable_supported_features(struct gve_priv *priv, if (priv->rx_pages_per_qpl == 0) priv->rx_pages_per_qpl = DQO_QPL_DEFAULT_RX_PAGES; } + + if (dev_op_buffer_sizes && + (supported_features_mask & GVE_SUP_BUFFER_SIZES_MASK)) { + priv->max_rx_buffer_size = + be16_to_cpu(dev_op_buffer_sizes->packet_buffer_size); + priv->header_buf_size = + be16_to_cpu(dev_op_buffer_sizes->header_buffer_size); + dev_info(&priv->pdev->dev, + "BUFFER SIZES device option enabled with max_rx_buffer_size of %u, header_buf_size of %u.\n", + priv->max_rx_buffer_size, priv->header_buf_size); + } } int gve_adminq_describe_device(struct gve_priv *priv) { + struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL; struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL; struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL; struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL; @@ -816,7 +852,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) err = gve_process_device_options(priv, descriptor, &dev_op_gqi_rda, &dev_op_gqi_qpl, &dev_op_dqo_rda, &dev_op_jumbo_frames, - &dev_op_dqo_qpl); + &dev_op_dqo_qpl, + &dev_op_buffer_sizes); if (err) goto free_device_descriptor; @@ -885,7 +922,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues); gve_enable_supported_features(priv, supported_features_mask, - dev_op_jumbo_frames, dev_op_dqo_qpl); + dev_op_jumbo_frames, dev_op_dqo_qpl, + dev_op_buffer_sizes); free_device_descriptor: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 5865ccdccbd0..5ac972e45ff8 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -125,6 +125,15 @@ struct gve_device_option_jumbo_frames { static_assert(sizeof(struct gve_device_option_jumbo_frames) == 8); +struct gve_device_option_buffer_sizes { + /* GVE_SUP_BUFFER_SIZES_MASK bit should be set */ + __be32 supported_features_mask; + __be16 packet_buffer_size; + __be16 header_buffer_size; +}; + +static_assert(sizeof(struct gve_device_option_buffer_sizes) == 8); + /* Terminology: * * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA @@ -140,6 +149,7 @@ enum gve_dev_opt_id { GVE_DEV_OPT_ID_DQO_RDA = 0x4, GVE_DEV_OPT_ID_DQO_QPL = 0x7, GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8, + GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa, }; enum gve_dev_opt_req_feat_mask { @@ -149,10 +159,12 @@ enum gve_dev_opt_req_feat_mask { GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_JUMBO_FRAMES = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_DQO_QPL = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES = 0x0, }; enum gve_sup_feature_mask { GVE_SUP_JUMBO_FRAMES_MASK = 1 << 2, + GVE_SUP_BUFFER_SIZES_MASK = 1 << 4, }; #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 @@ -165,6 +177,7 @@ enum gve_driver_capbility { gve_driver_capability_dqo_qpl = 2, /* reserved for future use */ gve_driver_capability_dqo_rda = 3, gve_driver_capability_alt_miss_compl = 4, + gve_driver_capability_flexible_buffer_size = 5, }; #define GVE_CAP1(a) BIT((int)a) @@ -176,7 +189,8 @@ enum gve_driver_capbility { (GVE_CAP1(gve_driver_capability_gqi_qpl) | \ GVE_CAP1(gve_driver_capability_gqi_rda) | \ GVE_CAP1(gve_driver_capability_dqo_rda) | \ - GVE_CAP1(gve_driver_capability_alt_miss_compl)) + GVE_CAP1(gve_driver_capability_alt_miss_compl) | \ + GVE_CAP1(gve_driver_capability_flexible_buffer_size)) #define GVE_DRIVER_CAPABILITY_FLAGS2 0x0 #define GVE_DRIVER_CAPABILITY_FLAGS3 0x0 @@ -260,7 +274,9 @@ struct gve_adminq_create_rx_queue { __be16 packet_buffer_size; __be16 rx_buff_ring_size; u8 enable_rsc; - u8 padding[5]; + u8 padding1; + __be16 header_buffer_size; + u8 padding2[2]; }; static_assert(sizeof(struct gve_adminq_create_rx_queue) == 56); diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index e5397aa1e48f..9aebfb843d9d 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -4,7 +4,6 @@ * Copyright (C) 2015-2021 Google, Inc. */ -#include <linux/ethtool.h> #include <linux/rtnetlink.h> #include "gve.h" #include "gve_adminq.h" @@ -40,17 +39,18 @@ static u32 gve_get_msglevel(struct net_device *netdev) * as declared in enum xdp_action inside file uapi/linux/bpf.h . */ static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = { - "rx_packets", "tx_packets", "rx_bytes", "tx_bytes", - "rx_dropped", "tx_dropped", "tx_timeouts", + "rx_packets", "rx_hsplit_pkt", "tx_packets", "rx_bytes", + "tx_bytes", "rx_dropped", "tx_dropped", "tx_timeouts", "rx_skb_alloc_fail", "rx_buf_alloc_fail", "rx_desc_err_dropped_pkt", + "rx_hsplit_unsplit_pkt", "interface_up_cnt", "interface_down_cnt", "reset_cnt", "page_alloc_fail", "dma_mapping_error", "stats_report_trigger_cnt", }; static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { - "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_consumed_desc[%u]", "rx_bytes[%u]", - "rx_cont_packet_cnt[%u]", "rx_frag_flip_cnt[%u]", "rx_frag_copy_cnt[%u]", - "rx_frag_alloc_cnt[%u]", + "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_consumed_desc[%u]", + "rx_bytes[%u]", "rx_hsplit_bytes[%u]", "rx_cont_packet_cnt[%u]", + "rx_frag_flip_cnt[%u]", "rx_frag_copy_cnt[%u]", "rx_frag_alloc_cnt[%u]", "rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]", "rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]", "rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]", @@ -154,11 +154,13 @@ static void gve_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - u64 tmp_rx_pkts, tmp_rx_bytes, tmp_rx_skb_alloc_fail, - tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt, + u64 tmp_rx_pkts, tmp_rx_hsplit_pkt, tmp_rx_bytes, tmp_rx_hsplit_bytes, + tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, + tmp_rx_desc_err_dropped_pkt, tmp_rx_hsplit_unsplit_pkt, tmp_tx_pkts, tmp_tx_bytes; - u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_pkts, - rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, tx_dropped; + u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_hsplit_unsplit_pkt, + rx_pkts, rx_hsplit_pkt, rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, + tx_dropped; int stats_idx, base_stats_idx, max_stats_idx; struct stats *report_stats; int *rx_qid_to_stats_idx; @@ -185,8 +187,10 @@ gve_get_ethtool_stats(struct net_device *netdev, kfree(rx_qid_to_stats_idx); return; } - for (rx_pkts = 0, rx_bytes = 0, rx_skb_alloc_fail = 0, - rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, ring = 0; + for (rx_pkts = 0, rx_bytes = 0, rx_hsplit_pkt = 0, + rx_skb_alloc_fail = 0, rx_buf_alloc_fail = 0, + rx_desc_err_dropped_pkt = 0, rx_hsplit_unsplit_pkt = 0, + ring = 0; ring < priv->rx_cfg.num_queues; ring++) { if (priv->rx) { do { @@ -195,18 +199,23 @@ gve_get_ethtool_stats(struct net_device *netdev, start = u64_stats_fetch_begin(&priv->rx[ring].statss); tmp_rx_pkts = rx->rpackets; + tmp_rx_hsplit_pkt = rx->rx_hsplit_pkt; tmp_rx_bytes = rx->rbytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; + tmp_rx_hsplit_unsplit_pkt = + rx->rx_hsplit_unsplit_pkt; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; + rx_hsplit_pkt += tmp_rx_hsplit_pkt; rx_bytes += tmp_rx_bytes; rx_skb_alloc_fail += tmp_rx_skb_alloc_fail; rx_buf_alloc_fail += tmp_rx_buf_alloc_fail; rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; + rx_hsplit_unsplit_pkt += tmp_rx_hsplit_unsplit_pkt; } } for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; @@ -227,6 +236,7 @@ gve_get_ethtool_stats(struct net_device *netdev, i = 0; data[i++] = rx_pkts; + data[i++] = rx_hsplit_pkt; data[i++] = tx_pkts; data[i++] = rx_bytes; data[i++] = tx_bytes; @@ -238,6 +248,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx_skb_alloc_fail; data[i++] = rx_buf_alloc_fail; data[i++] = rx_desc_err_dropped_pkt; + data[i++] = rx_hsplit_unsplit_pkt; data[i++] = priv->interface_up_cnt; data[i++] = priv->interface_down_cnt; data[i++] = priv->reset_cnt; @@ -277,6 +288,7 @@ gve_get_ethtool_stats(struct net_device *netdev, start = u64_stats_fetch_begin(&priv->rx[ring].statss); tmp_rx_bytes = rx->rbytes; + tmp_rx_hsplit_bytes = rx->rx_hsplit_bytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = @@ -284,6 +296,7 @@ gve_get_ethtool_stats(struct net_device *netdev, } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; + data[i++] = tmp_rx_hsplit_bytes; data[i++] = rx->rx_cont_packet_cnt; data[i++] = rx->rx_frag_flip_cnt; data[i++] = rx->rx_frag_copy_cnt; @@ -480,6 +493,29 @@ static void gve_get_ringparam(struct net_device *netdev, cmd->tx_max_pending = priv->tx_desc_cnt; cmd->rx_pending = priv->rx_desc_cnt; cmd->tx_pending = priv->tx_desc_cnt; + + if (!gve_header_split_supported(priv)) + kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_UNKNOWN; + else if (priv->header_split_enabled) + kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; + else + kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED; +} + +static int gve_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *cmd, + struct kernel_ethtool_ringparam *kernel_cmd, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (priv->tx_desc_cnt != cmd->tx_pending || + priv->rx_desc_cnt != cmd->rx_pending) { + dev_info(&priv->pdev->dev, "Modify ring size is not supported.\n"); + return -EOPNOTSUPP; + } + + return gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split); } static int gve_user_reset(struct net_device *netdev, u32 *flags) @@ -655,6 +691,7 @@ static int gve_set_coalesce(struct net_device *netdev, const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, .get_drvinfo = gve_get_drvinfo, .get_strings = gve_get_strings, .get_sset_count = gve_get_sset_count, @@ -667,6 +704,7 @@ const struct ethtool_ops gve_ethtool_ops = { .get_coalesce = gve_get_coalesce, .set_coalesce = gve_set_coalesce, .get_ringparam = gve_get_ringparam, + .set_ringparam = gve_set_ringparam, .reset = gve_user_reset, .get_tunable = gve_get_tunable, .set_tunable = gve_set_tunable, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index db6d9ae7cd78..166bd827a6d7 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1276,17 +1276,10 @@ static void gve_unreg_xdp_info(struct gve_priv *priv) static void gve_drain_page_cache(struct gve_priv *priv) { - struct page_frag_cache *nc; int i; - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - nc = &priv->rx[i].page_cache; - if (nc->va) { - __page_frag_cache_drain(virt_to_page(nc->va), - nc->pagecnt_bias); - nc->va = NULL; - } - } + for (i = 0; i < priv->rx_cfg.num_queues; i++) + page_frag_cache_drain(&priv->rx[i].page_cache); } static void gve_qpls_get_curr_alloc_cfg(struct gve_priv *priv, @@ -1307,9 +1300,13 @@ static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv, cfg->qcfg = &priv->rx_cfg; cfg->qcfg_tx = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); + cfg->enable_header_split = priv->header_split_enabled; cfg->qpls = priv->qpls; cfg->qpl_cfg = &priv->qpl_cfg; cfg->ring_size = priv->rx_desc_cnt; + cfg->packet_buffer_size = gve_is_gqi(priv) ? + GVE_DEFAULT_RX_BUFFER_SIZE : + priv->data_buffer_size_dqo; cfg->rx = priv->rx; } @@ -1448,12 +1445,9 @@ static int gve_queues_start(struct gve_priv *priv, if (err) goto reset; - if (!gve_is_gqi(priv)) { - /* Hard code this for now. This may be tuned in the future for - * performance. - */ - priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE; - } + priv->header_split_enabled = rx_alloc_cfg->enable_header_split; + priv->data_buffer_size_dqo = rx_alloc_cfg->packet_buffer_size; + err = gve_create_rings(priv); if (err) goto reset; @@ -2065,6 +2059,56 @@ out: priv->tx_timeo_cnt++; } +u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hsplit) +{ + if (enable_hsplit && priv->max_rx_buffer_size >= GVE_MAX_RX_BUFFER_SIZE) + return GVE_MAX_RX_BUFFER_SIZE; + else + return GVE_DEFAULT_RX_BUFFER_SIZE; +} + +/* header-split is not supported on non-DQO_RDA yet even if device advertises it */ +bool gve_header_split_supported(const struct gve_priv *priv) +{ + return priv->header_buf_size && priv->queue_format == GVE_DQO_RDA_FORMAT; +} + +int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split) +{ + struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; + struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; + struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0}; + bool enable_hdr_split; + int err = 0; + + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + return 0; + + if (!gve_header_split_supported(priv)) { + dev_err(&priv->pdev->dev, "Header-split not supported\n"); + return -EOPNOTSUPP; + } + + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED) + enable_hdr_split = true; + else + enable_hdr_split = false; + + if (enable_hdr_split == priv->header_split_enabled) + return 0; + + gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg, + &tx_alloc_cfg, &rx_alloc_cfg); + + rx_alloc_cfg.enable_header_split = enable_hdr_split; + rx_alloc_cfg.packet_buffer_size = gve_get_pkt_buf_size(priv, enable_hdr_split); + + if (netif_running(priv->dev)) + err = gve_adjust_config(priv, &qpls_alloc_cfg, + &tx_alloc_cfg, &rx_alloc_cfg); + return err; +} + static int gve_set_features(struct net_device *netdev, netdev_features_t features) { @@ -2511,6 +2555,8 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) priv->service_task_flags = 0x0; priv->state_flags = 0x0; priv->ethtool_flags = 0x0; + priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE; + priv->max_rx_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE; gve_set_probe_in_progress(priv); priv->gve_wq = alloc_ordered_workqueue("gve", 0); diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 8e6aeb5b3ed4..8e8071308aeb 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -199,6 +199,18 @@ static int gve_alloc_page_dqo(struct gve_rx_ring *rx, return 0; } +static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx) +{ + struct device *hdev = &priv->pdev->dev; + int buf_count = rx->dqo.bufq.mask + 1; + + if (rx->dqo.hdr_bufs.data) { + dma_free_coherent(hdev, priv->header_buf_size * buf_count, + rx->dqo.hdr_bufs.data, rx->dqo.hdr_bufs.addr); + rx->dqo.hdr_bufs.data = NULL; + } +} + void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); @@ -258,9 +270,24 @@ static void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, kvfree(rx->dqo.buf_states); rx->dqo.buf_states = NULL; + gve_rx_free_hdr_bufs(priv, rx); + netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx); } +static int gve_rx_alloc_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx) +{ + struct device *hdev = &priv->pdev->dev; + int buf_count = rx->dqo.bufq.mask + 1; + + rx->dqo.hdr_bufs.data = dma_alloc_coherent(hdev, priv->header_buf_size * buf_count, + &rx->dqo.hdr_bufs.addr, GFP_KERNEL); + if (!rx->dqo.hdr_bufs.data) + return -ENOMEM; + + return 0; +} + void gve_rx_start_ring_dqo(struct gve_priv *priv, int idx) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); @@ -302,6 +329,11 @@ static int gve_rx_alloc_ring_dqo(struct gve_priv *priv, if (!rx->dqo.buf_states) return -ENOMEM; + /* Allocate header buffers for header-split */ + if (cfg->enable_header_split) + if (gve_rx_alloc_hdr_bufs(priv, rx)) + goto err; + /* Set up linked list of buffer IDs */ for (i = 0; i < rx->dqo.num_buf_states - 1; i++) rx->dqo.buf_states[i].next = i + 1; @@ -443,6 +475,10 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx) desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states); desc->buf_addr = cpu_to_le64(buf_state->addr + buf_state->page_info.page_offset); + if (rx->dqo.hdr_bufs.data) + desc->header_buf_addr = + cpu_to_le64(rx->dqo.hdr_bufs.addr + + priv->header_buf_size * bufq->tail); bufq->tail = (bufq->tail + 1) & bufq->mask; complq->num_free_slots--; @@ -458,7 +494,7 @@ void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx) static void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx, struct gve_rx_buf_state_dqo *buf_state) { - const int data_buffer_size = priv->data_buffer_size_dqo; + const u16 data_buffer_size = priv->data_buffer_size_dqo; int pagecount; /* Can't reuse if we only fit one buffer per page */ @@ -645,13 +681,16 @@ static int gve_rx_append_frags(struct napi_struct *napi, */ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, const struct gve_rx_compl_desc_dqo *compl_desc, - int queue_idx) + u32 desc_idx, int queue_idx) { const u16 buffer_id = le16_to_cpu(compl_desc->buf_id); + const bool hbo = compl_desc->header_buffer_overflow; const bool eop = compl_desc->end_of_packet != 0; + const bool hsplit = compl_desc->split_header; struct gve_rx_buf_state_dqo *buf_state; struct gve_priv *priv = rx->gve; u16 buf_len; + u16 hdr_len; if (unlikely(buffer_id >= rx->dqo.num_buf_states)) { net_err_ratelimited("%s: Invalid RX buffer_id=%u\n", @@ -672,12 +711,35 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, } buf_len = compl_desc->packet_len; + hdr_len = compl_desc->header_len; /* Page might have not been used for awhile and was likely last written * by a different thread. */ prefetch(buf_state->page_info.page); + /* Copy the header into the skb in the case of header split */ + if (hsplit) { + int unsplit = 0; + + if (hdr_len && !hbo) { + rx->ctx.skb_head = gve_rx_copy_data(priv->dev, napi, + rx->dqo.hdr_bufs.data + + desc_idx * priv->header_buf_size, + hdr_len); + if (unlikely(!rx->ctx.skb_head)) + goto error; + rx->ctx.skb_tail = rx->ctx.skb_head; + } else { + unsplit = 1; + } + u64_stats_update_begin(&rx->statss); + rx->rx_hsplit_pkt++; + rx->rx_hsplit_unsplit_pkt += unsplit; + rx->rx_hsplit_bytes += hdr_len; + u64_stats_update_end(&rx->statss); + } + /* Sync the portion of dma buffer for CPU to read. */ dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr, buf_state->page_info.page_offset, @@ -820,7 +882,7 @@ int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) /* Do not read data until we own the descriptor */ dma_rmb(); - err = gve_rx_dqo(napi, rx, compl_desc, rx->q_num); + err = gve_rx_dqo(napi, rx, compl_desc, complq->head, rx->q_num); if (err < 0) { gve_rx_free_skb(rx); u64_stats_update_begin(&rx->statss); diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index 535b1796b91d..2349750075a5 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -64,11 +64,9 @@ void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) rx->ntfy_id = ntfy_idx; } -struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, - struct gve_rx_slot_page_info *page_info, u16 len) +struct sk_buff *gve_rx_copy_data(struct net_device *dev, struct napi_struct *napi, + u8 *data, u16 len) { - void *va = page_info->page_address + page_info->page_offset + - page_info->pad; struct sk_buff *skb; skb = napi_alloc_skb(napi, len); @@ -76,12 +74,21 @@ struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, return NULL; __skb_put(skb, len); - skb_copy_to_linear_data_offset(skb, 0, va, len); + skb_copy_to_linear_data_offset(skb, 0, data, len); skb->protocol = eth_type_trans(skb, dev); return skb; } +struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, + struct gve_rx_slot_page_info *page_info, u16 len) +{ + void *va = page_info->page_address + page_info->page_offset + + page_info->pad; + + return gve_rx_copy_data(dev, napi, va, len); +} + void gve_dec_pagecnt_bias(struct gve_rx_slot_page_info *page_info) { page_info->pagecnt_bias--; diff --git a/drivers/net/ethernet/google/gve/gve_utils.h b/drivers/net/ethernet/google/gve/gve_utils.h index 277921a629f7..bf2e9a0adb36 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.h +++ b/drivers/net/ethernet/google/gve/gve_utils.h @@ -19,6 +19,9 @@ bool gve_rx_was_added_to_block(struct gve_priv *priv, int queue_idx); void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx); void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx); +struct sk_buff *gve_rx_copy_data(struct net_device *dev, struct napi_struct *napi, + u8 *data, u16 len); + struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 8a1027ad340d..d4293f76d69d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -12,7 +12,9 @@ #define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev) -static struct class *hnae_class; +static const struct class hnae_class = { + .name = "hnae", +}; static void hnae_list_add(spinlock_t *lock, struct list_head *node, struct list_head *head) @@ -111,7 +113,7 @@ static struct hnae_ae_dev *find_ae(const struct fwnode_handle *fwnode) WARN_ON(!fwnode); - dev = class_find_device(hnae_class, NULL, fwnode, __ae_match); + dev = class_find_device(&hnae_class, NULL, fwnode, __ae_match); return dev ? cls_to_ae_dev(dev) : NULL; } @@ -415,7 +417,7 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) hdev->owner = owner; hdev->id = (int)atomic_inc_return(&id); hdev->cls_dev.parent = hdev->dev; - hdev->cls_dev.class = hnae_class; + hdev->cls_dev.class = &hnae_class; hdev->cls_dev.release = hnae_release; (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); ret = device_register(&hdev->cls_dev); @@ -448,13 +450,12 @@ EXPORT_SYMBOL(hnae_ae_unregister); static int __init hnae_init(void) { - hnae_class = class_create("hnae"); - return PTR_ERR_OR_ZERO(hnae_class); + return class_register(&hnae_class); } static void __exit hnae_exit(void) { - class_destroy(hnae_class); + class_unregister(&hnae_class); } subsys_initcall(hnae_init); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index d7e175a9cb49..f19f1e1d1f9f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -388,6 +388,7 @@ struct hnae3_dev_specs { u16 mc_mac_size; u32 mac_stats_num; u8 tnl_num; + u8 hilink_version; }; struct hnae3_client_ops { @@ -819,6 +820,7 @@ struct hnae3_tc_info { u8 max_tc; /* Total number of TCs */ u8 num_tc; /* Total number of enabled TCs */ bool mqprio_active; + bool mqprio_destroy; bool dcb_ets_active; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c index d92ad6082d8e..652d71326231 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c @@ -351,7 +351,7 @@ static int hclge_comm_cmd_csq_done(struct hclge_comm_hw *hw) static u32 hclge_get_cmdq_tx_timeout(u16 opcode, u32 tx_timeout) { static const struct hclge_cmdq_tx_timeout_map cmdq_tx_timeout_map[] = { - {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS}, + {HCLGE_OPC_CFG_RST_TRIGGER, HCLGE_COMM_CMDQ_CFG_RST_TIMEOUT}, }; u32 i; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h index 533c19d25e4f..552396518e08 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.h @@ -55,7 +55,7 @@ #define HCLGE_COMM_NIC_CMQ_DESC_NUM_S 3 #define HCLGE_COMM_NIC_CMQ_DESC_NUM 1024 #define HCLGE_COMM_CMDQ_TX_TIMEOUT_DEFAULT 30000 -#define HCLGE_COMM_CMDQ_TX_TIMEOUT_500MS 500000 +#define HCLGE_COMM_CMDQ_CFG_RST_TIMEOUT 1000000 enum hclge_opcode_type { /* Generic commands */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c index 3b6dbf158b98..f72dc0cee30e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c @@ -76,7 +76,7 @@ static int hns3_dcbnl_ieee_delapp(struct net_device *ndev, struct dcb_app *app) if (hns3_nic_resetting(ndev)) return -EBUSY; - if (h->kinfo.dcb_ops->ieee_setapp) + if (h->kinfo.dcb_ops->ieee_delapp) return h->kinfo.dcb_ops->ieee_delapp(h, app); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index c083d1d10767..807eb3bbb11c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1097,6 +1097,8 @@ hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos) *pos += scnprintf(buf + *pos, len - *pos, "TX timeout threshold: %d seconds\n", dev->watchdog_timeo / HZ); + *pos += scnprintf(buf + *pos, len - *pos, "Hilink Version: %u\n", + dev_specs->hilink_version); } static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index f1695c889d3a..19668a8d22f7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2473,9 +2473,9 @@ static netdev_features_t hns3_features_check(struct sk_buff *skb, return features; if (skb->encapsulation) - len = skb_inner_transport_header(skb) - skb->data; + len = skb_inner_transport_offset(skb); else - len = skb_transport_header(skb) - skb->data; + len = skb_transport_offset(skb); /* Assume L4 is 60 byte as TCP is the only protocol with a * a flexible value, and it's max len is 60 bytes. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 4d15eb73b972..9bb708fa42f2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -828,7 +828,8 @@ struct hclge_dev_specs_1_cmd { __le16 mc_mac_size; u8 rsv1[6]; u8 tnl_num; - u8 rsv2[5]; + u8 hilink_version; + u8 rsv2[4]; }; /* mac speed type defined in firmware command */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index b98301e205f7..eabbacb1c714 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -619,6 +619,8 @@ static int hclge_setup_tc(struct hnae3_handle *h, return ret; } + kinfo->tc_info.mqprio_destroy = !tc; + ret = hclge_notify_down_uinit(hdev); if (ret) return ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5ea9e59569ef..b4afb66efe5c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -645,8 +645,12 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) handle->flags |= HNAE3_SUPPORT_APP_LOOPBACK; } - count += 1; - handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK; + if (hdev->ae_dev->dev_specs.hilink_version != + HCLGE_HILINK_H60) { + count += 1; + handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK; + } + count += 1; handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK; count += 1; @@ -884,7 +888,7 @@ static const struct hclge_speed_bit_map speed_bit_map[] = { {HCLGE_MAC_SPEED_40G, HCLGE_SUPPORT_40G_BIT}, {HCLGE_MAC_SPEED_50G, HCLGE_SUPPORT_50G_BITS}, {HCLGE_MAC_SPEED_100G, HCLGE_SUPPORT_100G_BITS}, - {HCLGE_MAC_SPEED_200G, HCLGE_SUPPORT_200G_BIT}, + {HCLGE_MAC_SPEED_200G, HCLGE_SUPPORT_200G_BITS}, }; static int hclge_get_speed_bit(u32 speed, u32 *speed_bit) @@ -940,7 +944,7 @@ static void hclge_update_fec_support(struct hclge_mac *mac) mac->supported); } -static const struct hclge_link_mode_bmap hclge_sr_link_mode_bmap[8] = { +static const struct hclge_link_mode_bmap hclge_sr_link_mode_bmap[] = { {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseSR_Full_BIT}, {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT}, {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT}, @@ -948,10 +952,12 @@ static const struct hclge_link_mode_bmap hclge_sr_link_mode_bmap[8] = { {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseSR_Full_BIT}, {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT}, {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT}, - {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_EXT_BIT, + ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_BIT, ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT}, }; -static const struct hclge_link_mode_bmap hclge_lr_link_mode_bmap[6] = { +static const struct hclge_link_mode_bmap hclge_lr_link_mode_bmap[] = { {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseLR_Full_BIT}, {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT}, {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT}, @@ -959,11 +965,13 @@ static const struct hclge_link_mode_bmap hclge_lr_link_mode_bmap[6] = { ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT}, {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT}, - {HCLGE_SUPPORT_200G_BIT, + {HCLGE_SUPPORT_200G_R4_EXT_BIT, + ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_BIT, ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT}, }; -static const struct hclge_link_mode_bmap hclge_cr_link_mode_bmap[8] = { +static const struct hclge_link_mode_bmap hclge_cr_link_mode_bmap[] = { {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseCR_Full_BIT}, {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT}, {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT}, @@ -971,10 +979,12 @@ static const struct hclge_link_mode_bmap hclge_cr_link_mode_bmap[8] = { {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseCR_Full_BIT}, {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT}, {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT}, - {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_EXT_BIT, + ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_BIT, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT}, }; -static const struct hclge_link_mode_bmap hclge_kr_link_mode_bmap[9] = { +static const struct hclge_link_mode_bmap hclge_kr_link_mode_bmap[] = { {HCLGE_SUPPORT_1G_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT}, {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT}, @@ -983,7 +993,9 @@ static const struct hclge_link_mode_bmap hclge_kr_link_mode_bmap[9] = { {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseKR_Full_BIT}, {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT}, {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT}, - {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_EXT_BIT, + ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT}, + {HCLGE_SUPPORT_200G_R4_BIT, ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT}, }; static void hclge_convert_setting_sr(u16 speed_ability, @@ -1154,7 +1166,7 @@ static void hclge_parse_link_mode(struct hclge_dev *hdev, u16 speed_ability) static u32 hclge_get_max_speed(u16 speed_ability) { - if (speed_ability & HCLGE_SUPPORT_200G_BIT) + if (speed_ability & HCLGE_SUPPORT_200G_BITS) return HCLGE_MAC_SPEED_200G; if (speed_ability & HCLGE_SUPPORT_100G_BITS) @@ -1350,6 +1362,7 @@ static void hclge_parse_dev_specs(struct hclge_dev *hdev, ae_dev->dev_specs.umv_size = le16_to_cpu(req1->umv_size); ae_dev->dev_specs.mc_mac_size = le16_to_cpu(req1->mc_mac_size); ae_dev->dev_specs.tnl_num = req1->tnl_num; + ae_dev->dev_specs.hilink_version = req1->hilink_version; } static void hclge_check_dev_specs(struct hclge_dev *hdev) @@ -2890,7 +2903,10 @@ static int hclge_mac_init(struct hclge_dev *hdev) int ret; hdev->support_sfp_query = true; - hdev->hw.mac.duplex = HCLGE_MAC_FULL; + + if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + hdev->hw.mac.duplex = HCLGE_MAC_FULL; + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, hdev->hw.mac.duplex, hdev->hw.mac.lane_num); if (ret) @@ -12092,6 +12108,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + hclge_reset_tc_config(hdev); + ret = hclge_tm_init_hw(hdev, true); if (ret) { dev_err(&pdev->dev, "tm init hw fail, ret =%d\n", ret); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 51979cf71262..e821dd2f1528 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -191,9 +191,10 @@ enum HLCGE_PORT_TYPE { #define HCLGE_SUPPORT_40G_BIT BIT(5) #define HCLGE_SUPPORT_100M_BIT BIT(6) #define HCLGE_SUPPORT_10M_BIT BIT(7) -#define HCLGE_SUPPORT_200G_BIT BIT(8) +#define HCLGE_SUPPORT_200G_R4_EXT_BIT BIT(8) #define HCLGE_SUPPORT_50G_R1_BIT BIT(9) #define HCLGE_SUPPORT_100G_R2_BIT BIT(10) +#define HCLGE_SUPPORT_200G_R4_BIT BIT(11) #define HCLGE_SUPPORT_GE \ (HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT) @@ -201,6 +202,8 @@ enum HLCGE_PORT_TYPE { (HCLGE_SUPPORT_50G_R2_BIT | HCLGE_SUPPORT_50G_R1_BIT) #define HCLGE_SUPPORT_100G_BITS \ (HCLGE_SUPPORT_100G_R4_BIT | HCLGE_SUPPORT_100G_R2_BIT) +#define HCLGE_SUPPORT_200G_BITS \ + (HCLGE_SUPPORT_200G_R4_EXT_BIT | HCLGE_SUPPORT_200G_R4_BIT) enum HCLGE_DEV_STATE { HCLGE_STATE_REINITING, @@ -253,6 +256,12 @@ enum HCLGE_MAC_DUPLEX { HCLGE_MAC_FULL }; +/* hilink version */ +enum hclge_hilink_version { + HCLGE_HILINK_H32 = 0, + HCLGE_HILINK_H60 = 1, +}; + #define QUERY_SFP_SPEED 0 #define QUERY_ACTIVE_SPEED 1 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 4b0d07ca2505..d4a0e0be7a72 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -1123,10 +1123,11 @@ void hclge_mbx_handler(struct hclge_dev *hdev) req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data; flag = le16_to_cpu(crq->desc[crq->next_to_use].flag); - if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) { + if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B) || + req->mbx_src_vfid > hdev->num_req_vfs)) { dev_warn(&hdev->pdev->dev, - "dropped invalid mailbox message, code = %u\n", - req->msg.code); + "dropped invalid mailbox message, code = %u, vfid = %u\n", + req->msg.code, req->mbx_src_vfid); /* dropping/not processing this invalid message */ crq->desc[crq->next_to_use].flag = 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 80a2a0073d97..507d7ce26d83 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -108,7 +108,7 @@ void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, u64 ns = nsec; u32 sec_h; - if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) + if (!hdev->ptp || !test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) return; /* Since the BD does not have enough space for the higher 16 bits of diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index c58c31221762..00c3f2548bf6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -2143,3 +2143,19 @@ int hclge_tm_flush_cfg(struct hclge_dev *hdev, bool enable) return ret; } + +void hclge_reset_tc_config(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_knic_private_info *kinfo; + + kinfo = &vport->nic.kinfo; + + if (!kinfo->tc_info.mqprio_destroy) + return; + + /* clear tc info, including mqprio_destroy and mqprio_active */ + memset(&kinfo->tc_info, 0, sizeof(kinfo->tc_info)); + hclge_tm_schd_info_update(hdev, 0); + hclge_comm_rss_indir_init_cfg(hdev->ae_dev, &hdev->rss_cfg); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 53eec6df5194..0985916629d3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -277,4 +277,5 @@ int hclge_tm_get_port_shaper(struct hclge_dev *hdev, int hclge_up_to_tc_map(struct hclge_dev *hdev); int hclge_dscp_to_tc_map(struct hclge_dev *hdev); int hclge_tm_flush_cfg(struct hclge_dev *hdev, bool enable); +void hclge_reset_tc_config(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 767358b60507..639fbb12bd35 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -372,6 +372,7 @@ config IGC config IGC_LEDS def_bool LEDS_TRIGGER_NETDEV depends on IGC && LEDS_CLASS + depends on LEDS_CLASS=y || IGC=m help Optional support for controlling the NIC LED's with the netdev LED trigger. diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 01f0f12035ca..3fcb8daaa243 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -171,8 +171,8 @@ static int debug = 3; static int eeprom_bad_csum_allow = 0; static int use_io = 0; module_param(debug, int, 0); -module_param(eeprom_bad_csum_allow, int, 0); -module_param(use_io, int, 0); +module_param(eeprom_bad_csum_allow, int, 0444); +module_param(use_io, int, 0444); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); MODULE_PARM_DESC(eeprom_bad_csum_allow, "Allow bad eeprom checksums"); MODULE_PARM_DESC(use_io, "Force use of i/o access mode"); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index a2788fd5f8bb..19e450a5bd31 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2559,7 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw) hw->phy.ops.write_reg_page(hw, BM_RAR_H(i), (u16)(mac_reg & 0xFFFF)); hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i), - FIELD_GET(E1000_RAH_AV, mac_reg)); + (u16)((mac_reg & E1000_RAH_AV) >> 16)); } e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index af5d9d97a0d6..cc8c531ec3df 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6688,14 +6688,14 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); } else if (hw->mac.type >= e1000_pch_lpt) { - if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) { /* ULP does not support wake from unicast, multicast * or broadcast. */ retval = e1000_enable_ulp_lpt_lp(hw, !runtime); - - if (retval) - return retval; + if (retval) + return retval; + } } /* Ensure that the appropriate bits are set in LPI_CTRL diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 306758428aef..b32071ee84af 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -148,8 +148,6 @@ static void i40e_client_release_qvlist(struct i40e_info *ldev) u32 reg_idx; qv_info = &qvlist_info->qv_info[i]; - if (!qv_info) - continue; reg_idx = I40E_PFINT_LNKLSTN(qv_info->v_idx - 1); wr32(&pf->hw, reg_idx, I40E_PFINT_LNKLSTN_FIRSTQ_INDX_MASK); } @@ -576,8 +574,6 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev, for (i = 0; i < qvlist_info->num_vectors; i++) { qv_info = &qvlist_info->qv_info[i]; - if (!qv_info) - continue; v_idx = qv_info->v_idx; /* Validate vector id belongs to this client */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f12092cdb1f0..f86578857e8a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13208,12 +13208,12 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, features &= ~NETIF_F_GSO_MASK; /* MACLEN can support at most 63 words */ - len = skb_network_header(skb) - skb->data; + len = skb_network_offset(skb); if (len & ~(63 * 2)) goto out_err; /* IPLEN and EIPLEN can support at most 127 dwords */ - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len & ~(127 * 4)) goto out_err; @@ -13523,9 +13523,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) return err; i40e_queue_pair_disable_irq(vsi, queue_pair); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); - i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index af4269330581..ce1f11b8ad65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -567,8 +567,7 @@ static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min) **/ static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min) { - return (hw->aq.fw_maj_ver > maj || - (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min)); + return (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min); } #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b34c71770887..83a34e98bdc7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -491,8 +491,6 @@ static void i40e_release_rdma_qvlist(struct i40e_vf *vf) u32 v_idx, reg_idx, reg; qv_info = &qvlist_info->qv_info[i]; - if (!qv_info) - continue; v_idx = qv_info->v_idx; if (qv_info->ceq_idx != I40E_QUEUE_INVALID_IDX) { /* Figure out the queue after CEQ and make that the @@ -562,8 +560,6 @@ i40e_config_rdma_qvlist(struct i40e_vf *vf, msix_vf = pf->hw.func_caps.num_msix_vectors_vf; for (i = 0; i < qvlist_info->num_vectors; i++) { qv_info = &qvlist_info->qv_info[i]; - if (!qv_info) - continue; /* Validate vector id belongs to this vf */ if (!i40e_vc_isvalid_vector_id(vf, qv_info->v_idx)) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 335fd13e86f7..ef2440f3abf8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2170,19 +2170,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_add_cloud_filter(adapter); return 0; } - - if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { - iavf_del_cloud_filter(adapter); - return 0; - } if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { iavf_del_cloud_filter(adapter); return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) { - iavf_add_cloud_filter(adapter); - return 0; - } if (adapter->aq_required & IAVF_FLAG_AQ_ADD_FDIR_FILTER) { iavf_add_fdir_filter(adapter); return IAVF_SUCCESS; @@ -4423,12 +4414,12 @@ static netdev_features_t iavf_features_check(struct sk_buff *skb, features &= ~NETIF_F_GSO_MASK; /* MACLEN can support at most 63 words */ - len = skb_network_header(skb) - skb->data; + len = skb_network_offset(skb); if (len & ~(63 * 2)) goto out_err; /* IPLEN and EIPLEN can support at most 127 dwords */ - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len & ~(127 * 4)) goto out_err; diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index cca0e753f38f..7cee365cc7d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2018-2020, Intel Corporation. */ #include "ice.h" +#include <net/rps.h> /** * ice_is_arfs_active - helper to check is aRFS is active diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 9266f25a9978..4d8111aeb0ff 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1002,9 +1002,9 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) */ int ice_init_hw(struct ice_hw *hw) { - struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); + void *mac_buf __free(kfree); u16 mac_buf_len; - void *mac_buf; int status; /* Set MAC type based on DeviceID */ @@ -1082,7 +1082,7 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) { status = -ENOMEM; goto err_unroll_sched; @@ -1092,7 +1092,6 @@ int ice_init_hw(struct ice_hw *hw) status = ice_aq_get_phy_caps(hw->port_info, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); - devm_kfree(ice_hw_to_dev(hw), pcaps); if (status) dev_warn(ice_hw_to_dev(hw), "Get PHY capabilities failed status = %d, continuing anyway\n", status); @@ -1119,18 +1118,15 @@ int ice_init_hw(struct ice_hw *hw) /* Get MAC information */ /* A single port can report up to two (LAN and WoL) addresses */ - mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, - sizeof(struct ice_aqc_manage_mac_read_resp), - GFP_KERNEL); - mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); - + mac_buf = kcalloc(2, sizeof(struct ice_aqc_manage_mac_read_resp), + GFP_KERNEL); if (!mac_buf) { status = -ENOMEM; goto err_unroll_fltr_mgmt_struct; } + mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); status = ice_aq_manage_mac_read(hw, mac_buf, mac_buf_len, NULL); - devm_kfree(ice_hw_to_dev(hw), mac_buf); if (status) goto err_unroll_fltr_mgmt_struct; @@ -1399,9 +1395,8 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * it to HW register space and enables the hardware to prefetch descriptors * instead of only fetching them on demand */ -int -ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, - u32 rxq_index) +int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, + u32 rxq_index) { u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; @@ -3277,19 +3272,14 @@ int ice_update_link_info(struct ice_port_info *pi) return status; if (li->link_info & ICE_AQ_MEDIA_AVAILABLE) { - struct ice_aqc_get_phy_caps_data *pcaps; - struct ice_hw *hw; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); - hw = pi->hw; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), - GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); - - devm_kfree(ice_hw_to_dev(hw), pcaps); } return status; @@ -3430,8 +3420,8 @@ ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, int ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); struct ice_aqc_set_phy_cfg_data cfg = { 0 }; - struct ice_aqc_get_phy_caps_data *pcaps; struct ice_hw *hw; int status; @@ -3441,7 +3431,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) *aq_failures = 0; hw = pi->hw; - pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; @@ -3493,7 +3483,6 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) } out: - devm_kfree(ice_hw_to_dev(hw), pcaps); return status; } @@ -3572,7 +3561,7 @@ int ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec) { - struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_get_phy_caps_data *pcaps __free(kfree); struct ice_hw *hw; int status; @@ -3641,8 +3630,6 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, } out: - kfree(pcaps); - return status; } @@ -4362,13 +4349,13 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, /* End of FW Admin Queue command wrappers */ /** - * ice_write_byte - write a byte to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * ice_pack_ctx_byte - write a byte to a packed context structure + * @src_ctx: unpacked source context structure + * @dest_ctx: packed destination context data + * @ce_info: context element description */ -static void -ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +static void ice_pack_ctx_byte(u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { u8 src_byte, dest_byte, mask; u8 *from, *dest; @@ -4379,14 +4366,11 @@ ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - mask = (u8)(BIT(ce_info->width) - 1); + mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); src_byte = *from; - src_byte &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_byte <<= shift_width; + src_byte &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4401,13 +4385,13 @@ ice_write_byte(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_word - write a word to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * ice_pack_ctx_word - write a word to a packed context structure + * @src_ctx: unpacked source context structure + * @dest_ctx: packed destination context data + * @ce_info: context element description */ -static void -ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +static void ice_pack_ctx_word(u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { u16 src_word, mask; __le16 dest_word; @@ -4419,17 +4403,14 @@ ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - mask = BIT(ce_info->width) - 1; + mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); /* don't swizzle the bits until after the mask because the mask bits * will be in a different bit position on big endian machines */ src_word = *(u16 *)from; - src_word &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_word <<= shift_width; + src_word &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4444,13 +4425,13 @@ ice_write_word(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_dword - write a dword to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * ice_pack_ctx_dword - write a dword to a packed context structure + * @src_ctx: unpacked source context structure + * @dest_ctx: packed destination context data + * @ce_info: context element description */ -static void -ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +static void ice_pack_ctx_dword(u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { u32 src_dword, mask; __le32 dest_dword; @@ -4462,25 +4443,14 @@ ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - - /* if the field width is exactly 32 on an x86 machine, then the shift - * operation will not work because the SHL instructions count is masked - * to 5 bits so the shift will do nothing - */ - if (ce_info->width < 32) - mask = BIT(ce_info->width) - 1; - else - mask = (u32)~0; + mask = GENMASK(ce_info->width - 1 + shift_width, shift_width); /* don't swizzle the bits until after the mask because the mask bits * will be in a different bit position on big endian machines */ src_dword = *(u32 *)from; - src_dword &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_dword <<= shift_width; + src_dword &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4495,13 +4465,13 @@ ice_write_dword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) } /** - * ice_write_qword - write a qword to a packed context structure - * @src_ctx: the context structure to read from - * @dest_ctx: the context to be written to - * @ce_info: a description of the struct to be filled + * ice_pack_ctx_qword - write a qword to a packed context structure + * @src_ctx: unpacked source context structure + * @dest_ctx: packed destination context data + * @ce_info: context element description */ -static void -ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) +static void ice_pack_ctx_qword(u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { u64 src_qword, mask; __le64 dest_qword; @@ -4513,25 +4483,14 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) /* prepare the bits and mask */ shift_width = ce_info->lsb % 8; - - /* if the field width is exactly 64 on an x86 machine, then the shift - * operation will not work because the SHL instructions count is masked - * to 6 bits so the shift will do nothing - */ - if (ce_info->width < 64) - mask = BIT_ULL(ce_info->width) - 1; - else - mask = (u64)~0; + mask = GENMASK_ULL(ce_info->width - 1 + shift_width, shift_width); /* don't swizzle the bits until after the mask because the mask bits * will be in a different bit position on big endian machines */ src_qword = *(u64 *)from; - src_qword &= mask; - - /* shift to correct alignment */ - mask <<= shift_width; src_qword <<= shift_width; + src_qword &= mask; /* get the current bits from the target bit string */ dest = dest_ctx + (ce_info->lsb / 8); @@ -4550,11 +4509,10 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) * @hw: pointer to the hardware structure * @src_ctx: pointer to a generic non-packed context structure * @dest_ctx: pointer to memory for the packed structure - * @ce_info: a description of the structure to be transformed + * @ce_info: List of Rx context elements */ -int -ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info) +int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info) { int f; @@ -4570,16 +4528,16 @@ ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, } switch (ce_info[f].size_of) { case sizeof(u8): - ice_write_byte(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_byte(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u16): - ice_write_word(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_word(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u32): - ice_write_dword(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_dword(src_ctx, dest_ctx, &ce_info[f]); break; case sizeof(u64): - ice_write_qword(src_ctx, dest_ctx, &ce_info[f]); + ice_pack_ctx_qword(src_ctx, dest_ctx, &ce_info[f]); break; default: return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 32fd10de620c..ffb22c7ce28b 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -53,9 +53,8 @@ int ice_get_caps(struct ice_hw *hw); void ice_set_safe_mode_caps(struct ice_hw *hw); -int -ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, - u32 rxq_index); +int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, + u32 rxq_index); int ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params); @@ -72,9 +71,8 @@ bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); extern const struct ice_ctx_ele ice_tlan_ctx_info[]; -int -ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, - const struct ice_ctx_ele *ce_info); +int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, + const struct ice_ctx_ele *ce_info); extern struct mutex ice_global_cfg_lock_sw; diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 2bceee6d30f3..e92be6f130a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1599,7 +1599,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) } if (WARN_ON_ONCE(!vsi || !vsi->netdev)) return; - netdev_dpll_pin_clear(vsi->netdev); + dpll_netdev_pin_clear(vsi->netdev); dpll_pin_put(rclk->pin); } @@ -1643,7 +1643,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (WARN_ON((!vsi || !vsi->netdev))) return -EINVAL; - netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin); return 0; @@ -2122,6 +2122,7 @@ void ice_dpll_init(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; int err = 0; + mutex_init(&d->lock); err = ice_dpll_init_info(pf, cgu); if (err) goto err_exit; @@ -2134,7 +2135,6 @@ void ice_dpll_init(struct ice_pf *pf) err = ice_dpll_init_pins(pf, cgu); if (err) goto deinit_pps; - mutex_init(&d->lock); if (cgu) { err = ice_dpll_init_worker(pf); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 3cc364a4d682..255a9c8151b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -802,7 +802,7 @@ static int ice_lbtest_create_frame(struct ice_pf *pf, u8 **ret_data, u16 size) if (!pf) return -EINVAL; - data = devm_kzalloc(ice_pf_to_dev(pf), size, GFP_KERNEL); + data = kzalloc(size, GFP_KERNEL); if (!data) return -ENOMEM; @@ -945,11 +945,9 @@ static u64 ice_loopback_test(struct net_device *netdev) int num_frames, valid_frames; struct ice_tx_ring *tx_ring; struct ice_rx_ring *rx_ring; - struct device *dev; - u8 *tx_frame; + u8 *tx_frame __free(kfree); int i; - dev = ice_pf_to_dev(pf); netdev_info(netdev, "loopback test\n"); test_vsi = ice_lb_vsi_setup(pf, pf->hw.port_info); @@ -994,7 +992,7 @@ static u64 ice_loopback_test(struct net_device *netdev) for (i = 0; i < num_frames; i++) { if (ice_diag_send(tx_ring, tx_frame, ICE_LB_FRAME_SIZE)) { ret = 8; - goto lbtest_free_frame; + goto remove_mac_filters; } } @@ -1004,8 +1002,6 @@ static u64 ice_loopback_test(struct net_device *netdev) else if (valid_frames != num_frames) ret = 10; -lbtest_free_frame: - devm_kfree(dev, tx_frame); remove_mac_filters: if (ice_fltr_remove_mac(test_vsi, broadcast, ICE_FWD_TO_VSI)) netdev_err(netdev, "Could not remove MAC filter for the test VSI\n"); @@ -2487,6 +2483,24 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) case SCTP_V4_FLOW: hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4; break; + case GTPU_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPC_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPC_TEID_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_EH_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_UL_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4; + break; + case GTPU_DL_V4_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4; + break; case TCP_V6_FLOW: hdrs |= ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6; break; @@ -2496,6 +2510,24 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc) case SCTP_V6_FLOW: hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6; break; + case GTPU_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPC_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPC_TEID_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_EH_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_UL_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6; + break; + case GTPU_DL_V6_FLOW: + hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6; + break; default: break; } @@ -2519,6 +2551,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) case TCP_V4_FLOW: case UDP_V4_FLOW: case SCTP_V4_FLOW: + case GTPU_V4_FLOW: + case GTPC_V4_FLOW: + case GTPC_TEID_V4_FLOW: + case GTPU_EH_V4_FLOW: + case GTPU_UL_V4_FLOW: + case GTPU_DL_V4_FLOW: if (nfc->data & RXH_IP_SRC) hfld |= ICE_FLOW_HASH_FLD_IPV4_SA; if (nfc->data & RXH_IP_DST) @@ -2527,6 +2565,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) case TCP_V6_FLOW: case UDP_V6_FLOW: case SCTP_V6_FLOW: + case GTPU_V6_FLOW: + case GTPC_V6_FLOW: + case GTPC_TEID_V6_FLOW: + case GTPU_EH_V6_FLOW: + case GTPU_UL_V6_FLOW: + case GTPU_DL_V6_FLOW: if (nfc->data & RXH_IP_SRC) hfld |= ICE_FLOW_HASH_FLD_IPV6_SA; if (nfc->data & RXH_IP_DST) @@ -2565,6 +2609,33 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm) } } + if (nfc->data & RXH_GTP_TEID) { + switch (nfc->flow_type) { + case GTPC_TEID_V4_FLOW: + case GTPC_TEID_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPC_TEID; + break; + case GTPU_V4_FLOW: + case GTPU_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_IP_TEID; + break; + case GTPU_EH_V4_FLOW: + case GTPU_EH_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_EH_TEID; + break; + case GTPU_UL_V4_FLOW: + case GTPU_UL_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_UP_TEID; + break; + case GTPU_DL_V4_FLOW: + case GTPU_DL_V6_FLOW: + hfld |= ICE_FLOW_HASH_FLD_GTPU_DWN_TEID; + break; + default: + break; + } + } + return hfld; } @@ -2677,6 +2748,13 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) hash_flds & ICE_FLOW_HASH_FLD_UDP_DST_PORT || hash_flds & ICE_FLOW_HASH_FLD_SCTP_DST_PORT) nfc->data |= (u64)RXH_L4_B_2_3; + + if (hash_flds & ICE_FLOW_HASH_FLD_GTPC_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_IP_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_EH_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_UP_TEID || + hash_flds & ICE_FLOW_HASH_FLD_GTPU_DWN_TEID) + nfc->data |= (u64)RXH_GTP_TEID; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index ff82915ab497..2fd2e0cb483d 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -37,13 +37,13 @@ #define ICE_HASH_SCTP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT) #define ICE_HASH_SCTP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT) -#define ICE_FLOW_HASH_GTP_TEID \ +#define ICE_FLOW_HASH_GTP_C_TEID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)) -#define ICE_FLOW_HASH_GTP_IPV4_TEID \ - (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID) -#define ICE_FLOW_HASH_GTP_IPV6_TEID \ - (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID) +#define ICE_FLOW_HASH_GTP_C_IPV4_TEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_C_TEID) +#define ICE_FLOW_HASH_GTP_C_IPV6_TEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_C_TEID) #define ICE_FLOW_HASH_GTP_U_TEID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)) @@ -66,6 +66,20 @@ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_EH_TEID | \ ICE_FLOW_HASH_GTP_U_EH_QFI) +#define ICE_FLOW_HASH_GTP_U_UP \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID)) +#define ICE_FLOW_HASH_GTP_U_DWN \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID)) + +#define ICE_FLOW_HASH_GTP_U_IPV4_UP \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_UP) +#define ICE_FLOW_HASH_GTP_U_IPV6_UP \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_UP) +#define ICE_FLOW_HASH_GTP_U_IPV4_DWN \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_DWN) +#define ICE_FLOW_HASH_GTP_U_IPV6_DWN \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_DWN) + #define ICE_FLOW_HASH_PPPOE_SESS_ID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)) @@ -242,6 +256,13 @@ enum ice_flow_field { #define ICE_FLOW_HASH_FLD_SCTP_DST_PORT \ BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT) +#define ICE_FLOW_HASH_FLD_GTPC_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_IP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_EH_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_EH_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_UP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID) +#define ICE_FLOW_HASH_FLD_GTPU_DWN_TEID \ + BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID) + /* Flow headers and fields for AVF support */ enum ice_flow_avf_hdr_field { /* Values 0 - 28 are reserved for future use */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 59e8a2572985..ee3f0d3e3f6d 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1618,6 +1618,25 @@ static const struct ice_rss_hash_cfg default_rss_cfgs[] = { */ {ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4, ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_IPV4, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc4t with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_C_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4 with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4e with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4u with input set IPv4 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu4d with input set IPv4 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4, + ICE_FLOW_HASH_GTP_U_IPV4_DWN, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ {ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6, ICE_HASH_TCP_IPV6, ICE_RSS_ANY_HEADERS, false}, @@ -1632,6 +1651,24 @@ static const struct ice_rss_hash_cfg default_rss_cfgs[] = { /* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */ {ICE_FLOW_SEG_HDR_ESP, ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_IPV6, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpc6t with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_C_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6 with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6e with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_EH, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6u with input set IPv6 src/dst */ + { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_UP, ICE_RSS_OUTER_HEADERS, false}, + /* configure RSS for gtpu6d with input set IPv6 src/dst */ + {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6, + ICE_FLOW_HASH_GTP_U_IPV6_DWN, ICE_RSS_OUTER_HEADERS, false}, }; /** @@ -2720,61 +2757,6 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) } /** - * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI - * @vsi: the VSI being un-configured - */ -void ice_vsi_dis_irq(struct ice_vsi *vsi) -{ - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; - u32 val; - int i; - - /* disable interrupt causation from each queue */ - if (vsi->tx_rings) { - ice_for_each_txq(vsi, i) { - if (vsi->tx_rings[i]) { - u16 reg; - - reg = vsi->tx_rings[i]->reg_idx; - val = rd32(hw, QINT_TQCTL(reg)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(reg), val); - } - } - } - - if (vsi->rx_rings) { - ice_for_each_rxq(vsi, i) { - if (vsi->rx_rings[i]) { - u16 reg; - - reg = vsi->rx_rings[i]->reg_idx; - val = rd32(hw, QINT_RQCTL(reg)); - val &= ~QINT_RQCTL_CAUSE_ENA_M; - wr32(hw, QINT_RQCTL(reg), val); - } - } - } - - /* disable each interrupt */ - ice_for_each_q_vector(vsi, i) { - if (!vsi->q_vectors[i]) - continue; - wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); - } - - ice_flush(hw); - - /* don't call synchronize_irq() for VF's from the host */ - if (vsi->type == ICE_VSI_VF) - return; - - ice_for_each_q_vector(vsi, i) - synchronize_irq(vsi->q_vectors[i]->irq.virq); -} - -/** * __ice_queue_set_napi - Set the napi instance for the queue * @dev: device to which NAPI and queue belong * @queue_index: Index of queue @@ -3063,7 +3045,7 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) } } - tx_ring_stats = vsi_stat->rx_ring_stats; + tx_ring_stats = vsi_stat->tx_ring_stats; vsi_stat->tx_ring_stats = krealloc_array(vsi_stat->tx_ring_stats, req_txq, sizeof(*vsi_stat->tx_ring_stats), diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index b5a1ed7cc4b1..9cd23afe5f15 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -110,8 +110,6 @@ void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, bool ena_ts); -void ice_vsi_dis_irq(struct ice_vsi *vsi); - void ice_vsi_free_irq(struct ice_vsi *vsi); void ice_vsi_free_rx_rings(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8f73ba77e835..5d7660bc8846 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7002,6 +7002,50 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) } /** + * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI + * @vsi: the VSI being un-configured + */ +static void ice_vsi_dis_irq(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + u32 val; + int i; + + /* disable interrupt causation from each Rx queue; Tx queues are + * handled in ice_vsi_stop_tx_ring() + */ + if (vsi->rx_rings) { + ice_for_each_rxq(vsi, i) { + if (vsi->rx_rings[i]) { + u16 reg; + + reg = vsi->rx_rings[i]->reg_idx; + val = rd32(hw, QINT_RQCTL(reg)); + val &= ~QINT_RQCTL_CAUSE_ENA_M; + wr32(hw, QINT_RQCTL(reg), val); + } + } + } + + /* disable each interrupt */ + ice_for_each_q_vector(vsi, i) { + if (!vsi->q_vectors[i]) + continue; + wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); + } + + ice_flush(hw); + + /* don't call synchronize_irq() for VF's from the host */ + if (vsi->type == ICE_VSI_VF) + return; + + ice_for_each_q_vector(vsi, i) + synchronize_irq(vsi->q_vectors[i]->irq.virq); +} + +/** * ice_down - Shutdown the connection * @vsi: The VSI being stopped * @@ -7954,6 +7998,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index a94a1c48c3de..a958fcf3e6be 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -240,7 +240,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) } vf->lan_vsi_idx = vsi->idx; - vf->lan_vsi_num = vsi->vsi_num; return vsi; } @@ -1068,6 +1067,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) struct ice_pf *pf = pci_get_drvdata(pdev); u16 prev_msix, prev_queues, queues; bool needs_rebuild = false; + struct ice_vsi *vsi; struct ice_vf *vf; int id; @@ -1102,6 +1102,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (!vf) return -ENOENT; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -ENOENT; + prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; @@ -1122,7 +1126,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (vf->first_vector_idx < 0) goto unroll; - if (ice_vf_reconfig_vsi(vf)) { + if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) { /* Try to rebuild with previous values */ needs_rebuild = true; goto unroll; @@ -1148,8 +1152,10 @@ unroll: if (vf->first_vector_idx < 0) return -EINVAL; - if (needs_rebuild) + if (needs_rebuild) { ice_vf_reconfig_vsi(vf); + ice_vf_init_host_cfg(vf, vsi); + } ice_ena_vf_mappings(vf); ice_put_vf(vf); diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 2ffdae9a82df..21d26e19338a 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -280,12 +280,6 @@ int ice_vf_reconfig_vsi(struct ice_vf *vf) return err; } - /* Update the lan_vsi_num field since it might have been changed. The - * PF lan_vsi_idx number remains the same so we don't need to change - * that. - */ - vf->lan_vsi_num = vsi->vsi_num; - return 0; } @@ -315,7 +309,6 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) * vf->lan_vsi_idx */ vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); - vf->lan_vsi_num = vsi->vsi_num; return 0; } @@ -1315,13 +1308,12 @@ int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi) } /** - * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access + * ice_vf_invalidate_vsi - invalidate vsi_idx to remove VSI access * @vf: VF to remove access to VSI for */ void ice_vf_invalidate_vsi(struct ice_vf *vf) { vf->lan_vsi_idx = ICE_NO_VSI; - vf->lan_vsi_num = ICE_NO_VSI; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 0cc9034065c5..fec16919ec19 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -109,11 +109,6 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ - /* VSI indices - actual VSI pointers are maintained in the PF structure - * When assigned, these will be non-zero, because VSI 0 is always - * the main LAN VSI for the PF. - */ - u16 lan_vsi_num; /* ID as used by firmware */ unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index c925813ec9ca..1ff9818b4c84 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vf->driver_caps = *(u32 *)msg; else vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; @@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, vf->driver_caps); - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; @@ -506,7 +499,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); - vfres->vsi_res[0].vsi_id = vf->lan_vsi_num; + vfres->vsi_res[0].vsi_id = ICE_VF_VSI_ID; vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, @@ -552,27 +545,20 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf) */ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { - struct ice_pf *pf = vf->pf; - struct ice_vsi *vsi; - - vsi = ice_find_vsi(pf, vsi_id); - - return (vsi && (vsi->vf == vf)); + return vsi_id == ICE_VF_VSI_ID; } /** * ice_vc_isvalid_q_id - * @vf: pointer to the VF info - * @vsi_id: VSI ID + * @vsi: VSI to check queue ID against * @qid: VSI relative queue ID * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) { - struct ice_vsi *vsi = ice_find_vsi(vf->pf, vsi_id); /* allocated Tx and Rx queues should be always equal for VF VSI */ - return (vsi && (qid < vsi->alloc_txq)); + return qid < vsi->alloc_txq; } /** @@ -1330,7 +1316,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) */ q_map = vqs->rx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1352,7 +1338,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1457,7 +1443,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) q_map = vqs->tx_queues; for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1483,7 +1469,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) bitmap_zero(vf->rxq_ena, ICE_MAX_RSS_QS_PER_VF); } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_RSS_QS_PER_VF) { - if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + if (!ice_vc_isvalid_q_id(vsi, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1539,7 +1525,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_rx++; @@ -1553,7 +1539,7 @@ ice_cfg_interrupt(struct ice_vf *vf, struct ice_vsi *vsi, u16 vector_id, for_each_set_bit(vsi_q_id_idx, &qmap, ICE_MAX_RSS_QS_PER_VF) { vsi_q_id = vsi_q_id_idx; - if (!ice_vc_isvalid_q_id(vf, vsi->vsi_num, vsi_q_id)) + if (!ice_vc_isvalid_q_id(vsi, vsi_q_id)) return VIRTCHNL_STATUS_ERR_PARAM; q_vector->num_ring_tx++; @@ -1710,7 +1696,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) qpi->txq.headwb_enabled || !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || - !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { + !ice_vc_isvalid_q_id(vsi, qpi->txq.queue_id)) { goto error_param; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 60dfbe05980a..3a4115869153 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -19,6 +19,15 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* VFs only get a single VSI. For ice hardware, the VF does not need to know + * its VSI index. However, the virtchnl interface requires a VSI number, + * mainly due to legacy hardware. + * + * Since the VF doesn't need this information, report a static value to the VF + * instead of leaking any information about the PF or hardware setup. + */ +#define ICE_VF_VSI_ID 1 + struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5e19d48a05b4..d796dbd2a440 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -13,8 +13,6 @@ * - opcodes needed by VF when caps are activated * * Caps that don't use new opcodes (no opcodes should be allowed): - * - VIRTCHNL_VF_OFFLOAD_RSS_AQ - * - VIRTCHNL_VF_OFFLOAD_RSS_REG * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR * - VIRTCHNL_VF_OFFLOAD_CRC * - VIRTCHNL_VF_OFFLOAD_RX_POLLING diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index f001553e1a1a..8e4ff3af86c6 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -94,9 +94,6 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)) return -EINVAL; - if (vsi_id != vf->lan_vsi_num) - return -EINVAL; - if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8a051420fa19..1857220d27fe 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) return -EBUSY; usleep_range(1000, 2000); } + + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + ice_qvec_toggle_napi(vsi, q_vector, false); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_fill_txq_meta(vsi, tx_ring, &txq_meta); @@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -245,11 +246,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) return err; - clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + clear_bit(ICE_CFG_BUSY, vsi->state); return 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index 0acc125decb3..e7a036538246 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -37,8 +37,6 @@ struct idpf_vport_max_q; #define IDPF_MB_MAX_ERR 20 #define IDPF_NUM_CHUNKS_PER_MSG(struct_sz, chunk_sz) \ ((IDPF_CTLQ_MAX_BUF_LEN - (struct_sz)) / (chunk_sz)) -#define IDPF_WAIT_FOR_EVENT_TIMEO_MIN 2000 -#define IDPF_WAIT_FOR_EVENT_TIMEO 60000 #define IDPF_MAX_WAIT 500 @@ -66,14 +64,12 @@ struct idpf_mac_filter { /** * enum idpf_state - State machine to handle bring up - * @__IDPF_STARTUP: Start the state machine * @__IDPF_VER_CHECK: Negotiate virtchnl version * @__IDPF_GET_CAPS: Negotiate capabilities * @__IDPF_INIT_SW: Init based on given capabilities * @__IDPF_STATE_LAST: Must be last, used to determine size */ enum idpf_state { - __IDPF_STARTUP, __IDPF_VER_CHECK, __IDPF_GET_CAPS, __IDPF_INIT_SW, @@ -87,6 +83,7 @@ enum idpf_state { * @IDPF_HR_RESET_IN_PROG: Reset in progress * @IDPF_REMOVE_IN_PROG: Driver remove in progress * @IDPF_MB_INTR_MODE: Mailbox in interrupt mode + * @IDPF_VC_CORE_INIT: virtchnl core has been init * @IDPF_FLAGS_NBITS: Must be last */ enum idpf_flags { @@ -95,6 +92,7 @@ enum idpf_flags { IDPF_HR_RESET_IN_PROG, IDPF_REMOVE_IN_PROG, IDPF_MB_INTR_MODE, + IDPF_VC_CORE_INIT, IDPF_FLAGS_NBITS, }; @@ -209,71 +207,6 @@ struct idpf_dev_ops { struct idpf_reg_ops reg_ops; }; -/* These macros allow us to generate an enum and a matching char * array of - * stringified enums that are always in sync. Checkpatch issues a bogus warning - * about this being a complex macro; but it's wrong, these are never used as a - * statement and instead only used to define the enum and array. - */ -#define IDPF_FOREACH_VPORT_VC_STATE(STATE) \ - STATE(IDPF_VC_CREATE_VPORT) \ - STATE(IDPF_VC_CREATE_VPORT_ERR) \ - STATE(IDPF_VC_ENA_VPORT) \ - STATE(IDPF_VC_ENA_VPORT_ERR) \ - STATE(IDPF_VC_DIS_VPORT) \ - STATE(IDPF_VC_DIS_VPORT_ERR) \ - STATE(IDPF_VC_DESTROY_VPORT) \ - STATE(IDPF_VC_DESTROY_VPORT_ERR) \ - STATE(IDPF_VC_CONFIG_TXQ) \ - STATE(IDPF_VC_CONFIG_TXQ_ERR) \ - STATE(IDPF_VC_CONFIG_RXQ) \ - STATE(IDPF_VC_CONFIG_RXQ_ERR) \ - STATE(IDPF_VC_ENA_QUEUES) \ - STATE(IDPF_VC_ENA_QUEUES_ERR) \ - STATE(IDPF_VC_DIS_QUEUES) \ - STATE(IDPF_VC_DIS_QUEUES_ERR) \ - STATE(IDPF_VC_MAP_IRQ) \ - STATE(IDPF_VC_MAP_IRQ_ERR) \ - STATE(IDPF_VC_UNMAP_IRQ) \ - STATE(IDPF_VC_UNMAP_IRQ_ERR) \ - STATE(IDPF_VC_ADD_QUEUES) \ - STATE(IDPF_VC_ADD_QUEUES_ERR) \ - STATE(IDPF_VC_DEL_QUEUES) \ - STATE(IDPF_VC_DEL_QUEUES_ERR) \ - STATE(IDPF_VC_ALLOC_VECTORS) \ - STATE(IDPF_VC_ALLOC_VECTORS_ERR) \ - STATE(IDPF_VC_DEALLOC_VECTORS) \ - STATE(IDPF_VC_DEALLOC_VECTORS_ERR) \ - STATE(IDPF_VC_SET_SRIOV_VFS) \ - STATE(IDPF_VC_SET_SRIOV_VFS_ERR) \ - STATE(IDPF_VC_GET_RSS_LUT) \ - STATE(IDPF_VC_GET_RSS_LUT_ERR) \ - STATE(IDPF_VC_SET_RSS_LUT) \ - STATE(IDPF_VC_SET_RSS_LUT_ERR) \ - STATE(IDPF_VC_GET_RSS_KEY) \ - STATE(IDPF_VC_GET_RSS_KEY_ERR) \ - STATE(IDPF_VC_SET_RSS_KEY) \ - STATE(IDPF_VC_SET_RSS_KEY_ERR) \ - STATE(IDPF_VC_GET_STATS) \ - STATE(IDPF_VC_GET_STATS_ERR) \ - STATE(IDPF_VC_ADD_MAC_ADDR) \ - STATE(IDPF_VC_ADD_MAC_ADDR_ERR) \ - STATE(IDPF_VC_DEL_MAC_ADDR) \ - STATE(IDPF_VC_DEL_MAC_ADDR_ERR) \ - STATE(IDPF_VC_GET_PTYPE_INFO) \ - STATE(IDPF_VC_GET_PTYPE_INFO_ERR) \ - STATE(IDPF_VC_LOOPBACK_STATE) \ - STATE(IDPF_VC_LOOPBACK_STATE_ERR) \ - STATE(IDPF_VC_NBITS) - -#define IDPF_GEN_ENUM(ENUM) ENUM, -#define IDPF_GEN_STRING(STRING) #STRING, - -enum idpf_vport_vc_state { - IDPF_FOREACH_VPORT_VC_STATE(IDPF_GEN_ENUM) -}; - -extern const char * const idpf_vport_vc_state_str[]; - /** * enum idpf_vport_reset_cause - Vport soft reset causes * @IDPF_SR_Q_CHANGE: Soft reset queue change @@ -358,11 +291,7 @@ struct idpf_port_stats { * @port_stats: per port csum, header split, and other offload stats * @link_up: True if link is up * @link_speed_mbps: Link speed in mbps - * @vc_msg: Virtchnl message buffer - * @vc_state: Virtchnl message state - * @vchnl_wq: Wait queue for virtchnl messages * @sw_marker_wq: workqueue for marker packets - * @vc_buf_lock: Lock to protect virtchnl buffer */ struct idpf_vport { u16 num_txq; @@ -408,12 +337,7 @@ struct idpf_vport { bool link_up; u32 link_speed_mbps; - char vc_msg[IDPF_CTLQ_MAX_BUF_LEN]; - DECLARE_BITMAP(vc_state, IDPF_VC_NBITS); - - wait_queue_head_t vchnl_wq; wait_queue_head_t sw_marker_wq; - struct mutex vc_buf_lock; }; /** @@ -476,15 +400,11 @@ struct idpf_vport_user_config_data { * enum idpf_vport_config_flags - Vport config flags * @IDPF_VPORT_REG_NETDEV: Register netdev * @IDPF_VPORT_UP_REQUESTED: Set if interface up is requested on core reset - * @IDPF_VPORT_ADD_MAC_REQ: Asynchronous add ether address in flight - * @IDPF_VPORT_DEL_MAC_REQ: Asynchronous delete ether address in flight * @IDPF_VPORT_CONFIG_FLAGS_NBITS: Must be last */ enum idpf_vport_config_flags { IDPF_VPORT_REG_NETDEV, IDPF_VPORT_UP_REQUESTED, - IDPF_VPORT_ADD_MAC_REQ, - IDPF_VPORT_DEL_MAC_REQ, IDPF_VPORT_CONFIG_FLAGS_NBITS, }; @@ -555,11 +475,13 @@ struct idpf_vector_lifo { struct idpf_vport_config { struct idpf_vport_user_config_data user_config; struct idpf_vport_max_q max_q; - void *req_qs_chunks; + struct virtchnl2_add_queues *req_qs_chunks; spinlock_t mac_filter_list_lock; DECLARE_BITMAP(flags, IDPF_VPORT_CONFIG_FLAGS_NBITS); }; +struct idpf_vc_xn_manager; + /** * struct idpf_adapter - Device data struct generated on probe * @pdev: PCI device struct given on probe @@ -601,9 +523,7 @@ struct idpf_vport_config { * @stats_task: Periodic statistics retrieval task * @stats_wq: Workqueue for statistics task * @caps: Negotiated capabilities with device - * @vchnl_wq: Wait queue for virtchnl messages - * @vc_state: Virtchnl message state - * @vc_msg: Virtchnl message buffer + * @vcxn_mngr: Virtchnl transaction manager * @dev_ops: See idpf_dev_ops * @num_vfs: Number of allocated VFs through sysfs. PF does not directly talk * to VFs but is used to initialize them @@ -659,10 +579,8 @@ struct idpf_adapter { struct delayed_work stats_task; struct workqueue_struct *stats_wq; struct virtchnl2_get_capabilities caps; + struct idpf_vc_xn_manager *vcxn_mngr; - wait_queue_head_t vchnl_wq; - DECLARE_BITMAP(vc_state, IDPF_VC_NBITS); - char vc_msg[IDPF_CTLQ_MAX_BUF_LEN]; struct idpf_dev_ops dev_ops; int num_vfs; bool crc_enable; @@ -903,68 +821,18 @@ void idpf_mbx_task(struct work_struct *work); void idpf_vc_event_task(struct work_struct *work); void idpf_dev_ops_init(struct idpf_adapter *adapter); void idpf_vf_dev_ops_init(struct idpf_adapter *adapter); -int idpf_vport_adjust_qs(struct idpf_vport *vport); -int idpf_init_dflt_mbx(struct idpf_adapter *adapter); -void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter); -int idpf_vc_core_init(struct idpf_adapter *adapter); -void idpf_vc_core_deinit(struct idpf_adapter *adapter); int idpf_intr_req(struct idpf_adapter *adapter); void idpf_intr_rel(struct idpf_adapter *adapter); -int idpf_get_reg_intr_vecs(struct idpf_vport *vport, - struct idpf_vec_regs *reg_vals); u16 idpf_get_max_tx_hdr_size(struct idpf_adapter *adapter); -int idpf_send_delete_queues_msg(struct idpf_vport *vport); -int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, - u16 num_complq, u16 num_rx_q, u16 num_rx_bufq); int idpf_initiate_soft_reset(struct idpf_vport *vport, enum idpf_vport_reset_cause reset_cause); -int idpf_send_enable_vport_msg(struct idpf_vport *vport); -int idpf_send_disable_vport_msg(struct idpf_vport *vport); -int idpf_send_destroy_vport_msg(struct idpf_vport *vport); -int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport); -int idpf_send_ena_dis_loopback_msg(struct idpf_vport *vport); -int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get); -int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get); -int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter); -int idpf_send_alloc_vectors_msg(struct idpf_adapter *adapter, u16 num_vectors); void idpf_deinit_task(struct idpf_adapter *adapter); int idpf_req_rel_vector_indexes(struct idpf_adapter *adapter, u16 *q_vector_idxs, struct idpf_vector_info *vec_info); -int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport); -int idpf_send_get_stats_msg(struct idpf_vport *vport); -int idpf_get_vec_ids(struct idpf_adapter *adapter, - u16 *vecids, int num_vecids, - struct virtchnl2_vector_chunks *chunks); -int idpf_recv_mb_msg(struct idpf_adapter *adapter, u32 op, - void *msg, int msg_size); -int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, - u16 msg_size, u8 *msg); void idpf_set_ethtool_ops(struct net_device *netdev); -int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter, - struct idpf_vport_max_q *max_q); -void idpf_vport_dealloc_max_qs(struct idpf_adapter *adapter, - struct idpf_vport_max_q *max_q); -int idpf_add_del_mac_filters(struct idpf_vport *vport, - struct idpf_netdev_priv *np, - bool add, bool async); -int idpf_set_promiscuous(struct idpf_adapter *adapter, - struct idpf_vport_user_config_data *config_data, - u32 vport_id); -int idpf_send_disable_queues_msg(struct idpf_vport *vport); -void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q); -u32 idpf_get_vport_id(struct idpf_vport *vport); -int idpf_vport_queue_ids_init(struct idpf_vport *vport); -int idpf_queue_reg_init(struct idpf_vport *vport); -int idpf_send_config_queues_msg(struct idpf_vport *vport); -int idpf_send_enable_queues_msg(struct idpf_vport *vport); -int idpf_send_create_vport_msg(struct idpf_adapter *adapter, - struct idpf_vport_max_q *max_q); -int idpf_check_supported_desc_ids(struct idpf_vport *vport); void idpf_vport_intr_write_itr(struct idpf_q_vector *q_vector, u16 itr, bool tx); -int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map); -int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs); int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs); u8 idpf_vport_get_hsplit(const struct idpf_vport *vport); diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index c7f43d2fcd13..4849590a5591 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -516,6 +516,8 @@ post_buffs_out: /* Wrap to end of end ring since current ntp is 0 */ cq->next_to_post = cq->ring_size - 1; + dma_wmb(); + wr32(hw, cq->reg.tail, cq->next_to_post); } @@ -546,11 +548,6 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, int err = 0; u16 i; - if (*num_q_msg == 0) - return 0; - else if (*num_q_msg > cq->ring_size) - return -EBADR; - /* take the lock before we start messing with the ring */ mutex_lock(&cq->cq_lock); diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h index 8dee098bbfb0..e8e046ef2f0d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h @@ -69,6 +69,11 @@ struct idpf_ctlq_msg { u8 context[IDPF_INDIRECT_CTX_SIZE]; struct idpf_dma_mem *payload; } indirect; + struct { + u32 rsvd; + u16 data; + u16 flags; + } sw_cookie; } ctx; }; diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c index 34ad1ac46b78..3df9935685e9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c @@ -3,6 +3,7 @@ #include "idpf.h" #include "idpf_lan_pf_regs.h" +#include "idpf_virtchnl.h" #define IDPF_PF_ITR_IDX_SPACING 0x4 diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 58179bd733ff..5d3532c27d57 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -2,14 +2,11 @@ /* Copyright (C) 2023 Intel Corporation */ #include "idpf.h" +#include "idpf_virtchnl.h" static const struct net_device_ops idpf_netdev_ops_splitq; static const struct net_device_ops idpf_netdev_ops_singleq; -const char * const idpf_vport_vc_state_str[] = { - IDPF_FOREACH_VPORT_VC_STATE(IDPF_GEN_STRING) -}; - /** * idpf_init_vector_stack - Fill the MSIX vector stack with vector index * @adapter: private data struct @@ -82,19 +79,12 @@ static void idpf_mb_intr_rel_irq(struct idpf_adapter *adapter) */ void idpf_intr_rel(struct idpf_adapter *adapter) { - int err; - if (!adapter->msix_entries) return; idpf_mb_intr_rel_irq(adapter); pci_free_irq_vectors(adapter->pdev); - - err = idpf_send_dealloc_vectors_msg(adapter); - if (err) - dev_err(&adapter->pdev->dev, - "Failed to deallocate vectors: %d\n", err); - + idpf_send_dealloc_vectors_msg(adapter); idpf_deinit_vector_stack(adapter); kfree(adapter->msix_entries); adapter->msix_entries = NULL; @@ -975,7 +965,6 @@ static void idpf_vport_rel(struct idpf_vport *vport) struct idpf_rss_data *rss_data; struct idpf_vport_max_q max_q; u16 idx = vport->idx; - int i; vport_config = adapter->vport_config[vport->idx]; idpf_deinit_rss(vport); @@ -985,20 +974,6 @@ static void idpf_vport_rel(struct idpf_vport *vport) idpf_send_destroy_vport_msg(vport); - /* Set all bits as we dont know on which vc_state the vport vhnl_wq - * is waiting on and wakeup the virtchnl workqueue even if it is - * waiting for the response as we are going down - */ - for (i = 0; i < IDPF_VC_NBITS; i++) - set_bit(i, vport->vc_state); - wake_up(&vport->vchnl_wq); - - mutex_destroy(&vport->vc_buf_lock); - - /* Clear all the bits */ - for (i = 0; i < IDPF_VC_NBITS; i++) - clear_bit(i, vport->vc_state); - /* Release all max queues allocated to the adapter's pool */ max_q.max_rxq = vport_config->max_q.max_rxq; max_q.max_txq = vport_config->max_q.max_txq; @@ -1253,7 +1228,7 @@ void idpf_mbx_task(struct work_struct *work) queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, msecs_to_jiffies(300)); - idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_UNKNOWN, NULL, 0); + idpf_recv_mb_msg(adapter); } /** @@ -1543,9 +1518,7 @@ void idpf_init_task(struct work_struct *work) vport_config = adapter->vport_config[index]; init_waitqueue_head(&vport->sw_marker_wq); - init_waitqueue_head(&vport->vchnl_wq); - mutex_init(&vport->vc_buf_lock); spin_lock_init(&vport_config->mac_filter_list_lock); INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list); @@ -1823,6 +1796,8 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter) goto unlock_mutex; } + queue_delayed_work(adapter->mbx_wq, &adapter->mbx_task, 0); + /* Initialize the state machine, also allocate memory and request * resources */ @@ -1902,7 +1877,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, * mess with. Nothing below should use those variables from new_vport * and should instead always refer to them in vport if they need to. */ - memcpy(new_vport, vport, offsetof(struct idpf_vport, vc_state)); + memcpy(new_vport, vport, offsetof(struct idpf_vport, link_speed_mbps)); /* Adjust resource parameters prior to reallocating resources */ switch (reset_cause) { @@ -1951,7 +1926,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport, /* Same comment as above regarding avoiding copying the wait_queues and * mutexes applies here. We do not want to mess with those if possible. */ - memcpy(vport, new_vport, offsetof(struct idpf_vport, vc_state)); + memcpy(vport, new_vport, offsetof(struct idpf_vport, link_speed_mbps)); /* Since idpf_vport_queues_alloc was called with new_port, the queue * back pointers are currently pointing to the local new_vport. Reset diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index e1febc74cefd..f784eea044bd 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -3,6 +3,7 @@ #include "idpf.h" #include "idpf_devids.h" +#include "idpf_virtchnl.h" #define DRV_SUMMARY "Intel(R) Infrastructure Data Path Function Linux Driver" @@ -30,6 +31,7 @@ static void idpf_remove(struct pci_dev *pdev) idpf_sriov_configure(pdev, 0); idpf_vc_core_deinit(adapter); + /* Be a good citizen and leave the device clean on exit */ adapter->dev_ops.reg_ops.trigger_reset(adapter, IDPF_HR_FUNC_RESET); idpf_deinit_dflt_mbx(adapter); @@ -66,6 +68,8 @@ destroy_wqs: adapter->vport_config = NULL; kfree(adapter->netdevs); adapter->netdevs = NULL; + kfree(adapter->vcxn_mngr); + adapter->vcxn_mngr = NULL; mutex_destroy(&adapter->vport_ctrl_lock); mutex_destroy(&adapter->vector_lock); @@ -229,8 +233,6 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&adapter->queue_lock); mutex_init(&adapter->vc_buf_lock); - init_waitqueue_head(&adapter->vchnl_wq); - INIT_DELAYED_WORK(&adapter->init_task, idpf_init_task); INIT_DELAYED_WORK(&adapter->serv_task, idpf_service_task); INIT_DELAYED_WORK(&adapter->mbx_task, idpf_mbx_task); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 2f8ad79ae3f0..6dd7a66bb897 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2,6 +2,7 @@ /* Copyright (C) 2023 Intel Corporation */ #include "idpf.h" +#include "idpf_virtchnl.h" /** * idpf_buf_lifo_push - push a buffer pointer onto stack diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c index 8ade4e3a9fe1..629cb5cb7c9f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c +++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c @@ -3,6 +3,7 @@ #include "idpf.h" #include "idpf_lan_vf_regs.h" +#include "idpf_virtchnl.h" #define IDPF_VF_ITR_IDX_SPACING 0x40 @@ -137,7 +138,7 @@ static void idpf_vf_trigger_reset(struct idpf_adapter *adapter, /* Do not send VIRTCHNL2_OP_RESET_VF message on driver unload */ if (trig_cause == IDPF_HR_FUNC_RESET && !test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) - idpf_send_mb_msg(adapter, VIRTCHNL2_OP_RESET_VF, 0, NULL); + idpf_send_mb_msg(adapter, VIRTCHNL2_OP_RESET_VF, 0, NULL, 0); } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d0cdd63b3d5b..a5f9b7a5effe 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -2,46 +2,192 @@ /* Copyright (C) 2023 Intel Corporation */ #include "idpf.h" +#include "idpf_virtchnl.h" + +#define IDPF_VC_XN_MIN_TIMEOUT_MSEC 2000 +#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC (60 * 1000) +#define IDPF_VC_XN_IDX_M GENMASK(7, 0) +#define IDPF_VC_XN_SALT_M GENMASK(15, 8) +#define IDPF_VC_XN_RING_LEN U8_MAX + +/** + * enum idpf_vc_xn_state - Virtchnl transaction status + * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used + * @IDPF_VC_XN_WAITING: expecting a reply, not yet received + * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, + * buffer updated + * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there + * was an error, buffer not updated + * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down + * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the + * return context; a callback may be provided to handle + * return + */ +enum idpf_vc_xn_state { + IDPF_VC_XN_IDLE = 1, + IDPF_VC_XN_WAITING, + IDPF_VC_XN_COMPLETED_SUCCESS, + IDPF_VC_XN_COMPLETED_FAILED, + IDPF_VC_XN_SHUTDOWN, + IDPF_VC_XN_ASYNC, +}; + +struct idpf_vc_xn; +/* Callback for asynchronous messages */ +typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *, + const struct idpf_ctlq_msg *); + +/** + * struct idpf_vc_xn - Data structure representing virtchnl transactions + * @completed: virtchnl event loop uses that to signal when a reply is + * available, uses kernel completion API + * @state: virtchnl event loop stores the data below, protected by the + * completion's lock. + * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be + * truncated on its way to the receiver thread according to + * reply_buf.iov_len. + * @reply: Reference to the buffer(s) where the reply data should be written + * to. May be 0-length (then NULL address permitted) if the reply data + * should be ignored. + * @async_handler: if sent asynchronously, a callback can be provided to handle + * the reply when it's received + * @vc_op: corresponding opcode sent with this transaction + * @idx: index used as retrieval on reply receive, used for cookie + * @salt: changed every message to make unique, used for cookie + */ +struct idpf_vc_xn { + struct completion completed; + enum idpf_vc_xn_state state; + size_t reply_sz; + struct kvec reply; + async_vc_cb async_handler; + u32 vc_op; + u8 idx; + u8 salt; +}; + +/** + * struct idpf_vc_xn_params - Parameters for executing transaction + * @send_buf: kvec for send buffer + * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length + * @timeout_ms: timeout to wait for reply + * @async: send message asynchronously, will not wait on completion + * @async_handler: If sent asynchronously, optional callback handler. The user + * must be careful when using async handlers as the memory for + * the recv_buf _cannot_ be on stack if this is async. + * @vc_op: virtchnl op to send + */ +struct idpf_vc_xn_params { + struct kvec send_buf; + struct kvec recv_buf; + int timeout_ms; + bool async; + async_vc_cb async_handler; + u32 vc_op; +}; + +/** + * struct idpf_vc_xn_manager - Manager for tracking transactions + * @ring: backing and lookup for transactions + * @free_xn_bm: bitmap for free transactions + * @xn_bm_lock: make bitmap access synchronous where necessary + * @salt: used to make cookie unique every message + */ +struct idpf_vc_xn_manager { + struct idpf_vc_xn ring[IDPF_VC_XN_RING_LEN]; + DECLARE_BITMAP(free_xn_bm, IDPF_VC_XN_RING_LEN); + spinlock_t xn_bm_lock; + u8 salt; +}; + +/** + * idpf_vid_to_vport - Translate vport id to vport pointer + * @adapter: private data struct + * @v_id: vport id to translate + * + * Returns vport matching v_id, NULL if not found. + */ +static +struct idpf_vport *idpf_vid_to_vport(struct idpf_adapter *adapter, u32 v_id) +{ + u16 num_max_vports = idpf_get_max_vports(adapter); + int i; + + for (i = 0; i < num_max_vports; i++) + if (adapter->vport_ids[i] == v_id) + return adapter->vports[i]; + + return NULL; +} + +/** + * idpf_handle_event_link - Handle link event message + * @adapter: private data struct + * @v2e: virtchnl event message + */ +static void idpf_handle_event_link(struct idpf_adapter *adapter, + const struct virtchnl2_event *v2e) +{ + struct idpf_netdev_priv *np; + struct idpf_vport *vport; + + vport = idpf_vid_to_vport(adapter, le32_to_cpu(v2e->vport_id)); + if (!vport) { + dev_err_ratelimited(&adapter->pdev->dev, "Failed to find vport_id %d for link event\n", + v2e->vport_id); + return; + } + np = netdev_priv(vport->netdev); + + vport->link_speed_mbps = le32_to_cpu(v2e->link_speed); + + if (vport->link_up == v2e->link_status) + return; + + vport->link_up = v2e->link_status; + + if (np->state != __IDPF_VPORT_UP) + return; + + if (vport->link_up) { + netif_tx_start_all_queues(vport->netdev); + netif_carrier_on(vport->netdev); + } else { + netif_tx_stop_all_queues(vport->netdev); + netif_carrier_off(vport->netdev); + } +} /** * idpf_recv_event_msg - Receive virtchnl event message - * @vport: virtual port structure + * @adapter: Driver specific private structure * @ctlq_msg: message to copy from * * Receive virtchnl event message */ -static void idpf_recv_event_msg(struct idpf_vport *vport, +static void idpf_recv_event_msg(struct idpf_adapter *adapter, struct idpf_ctlq_msg *ctlq_msg) { - struct idpf_netdev_priv *np = netdev_priv(vport->netdev); + int payload_size = ctlq_msg->ctx.indirect.payload->size; struct virtchnl2_event *v2e; - bool link_status; u32 event; + if (payload_size < sizeof(*v2e)) { + dev_err_ratelimited(&adapter->pdev->dev, "Failed to receive valid payload for event msg (op %d len %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode, + payload_size); + return; + } + v2e = (struct virtchnl2_event *)ctlq_msg->ctx.indirect.payload->va; event = le32_to_cpu(v2e->event); switch (event) { case VIRTCHNL2_EVENT_LINK_CHANGE: - vport->link_speed_mbps = le32_to_cpu(v2e->link_speed); - link_status = v2e->link_status; - - if (vport->link_up == link_status) - break; - - vport->link_up = link_status; - if (np->state == __IDPF_VPORT_UP) { - if (vport->link_up) { - netif_carrier_on(vport->netdev); - netif_tx_start_all_queues(vport->netdev); - } else { - netif_tx_stop_all_queues(vport->netdev); - netif_carrier_off(vport->netdev); - } - } - break; + idpf_handle_event_link(adapter, v2e); + return; default: - dev_err(&vport->adapter->pdev->dev, + dev_err(&adapter->pdev->dev, "Unknown event %d from PF\n", event); break; } @@ -93,13 +239,14 @@ err_kfree: * @op: virtchnl opcode * @msg_size: size of the payload * @msg: pointer to buffer holding the payload + * @cookie: unique SW generated cookie per message * * Will prepare the control queue message and initiates the send api * * Returns 0 on success, negative on failure */ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, - u16 msg_size, u8 *msg) + u16 msg_size, u8 *msg, u16 cookie) { struct idpf_ctlq_msg *ctlq_msg; struct idpf_dma_mem *dma_mem; @@ -139,8 +286,12 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, err = -ENOMEM; goto dma_alloc_error; } - memcpy(dma_mem->va, msg, msg_size); + + /* It's possible we're just sending an opcode but no buffer */ + if (msg && msg_size) + memcpy(dma_mem->va, msg, msg_size); ctlq_msg->ctx.indirect.payload = dma_mem; + ctlq_msg->ctx.sw_cookie.data = cookie; err = idpf_ctlq_send(&adapter->hw, adapter->hw.asq, 1, ctlq_msg); if (err) @@ -159,592 +310,432 @@ dma_mem_error: return err; } -/** - * idpf_find_vport - Find vport pointer from control queue message - * @adapter: driver specific private structure - * @vport: address of vport pointer to copy the vport from adapters vport list - * @ctlq_msg: control queue message +/* API for virtchnl "transaction" support ("xn" for short). * - * Return 0 on success, error value on failure. Also this function does check - * for the opcodes which expect to receive payload and return error value if - * it is not the case. + * We are reusing the completion lock to serialize the accesses to the + * transaction state for simplicity, but it could be its own separate synchro + * as well. For now, this API is only used from within a workqueue context; + * raw_spin_lock() is enough. */ -static int idpf_find_vport(struct idpf_adapter *adapter, - struct idpf_vport **vport, - struct idpf_ctlq_msg *ctlq_msg) -{ - bool no_op = false, vid_found = false; - int i, err = 0; - char *vc_msg; - u32 v_id; +/** + * idpf_vc_xn_lock - Request exclusive access to vc transaction + * @xn: struct idpf_vc_xn* to access + */ +#define idpf_vc_xn_lock(xn) \ + raw_spin_lock(&(xn)->completed.wait.lock) - vc_msg = kcalloc(IDPF_CTLQ_MAX_BUF_LEN, sizeof(char), GFP_KERNEL); - if (!vc_msg) - return -ENOMEM; +/** + * idpf_vc_xn_unlock - Release exclusive access to vc transaction + * @xn: struct idpf_vc_xn* to access + */ +#define idpf_vc_xn_unlock(xn) \ + raw_spin_unlock(&(xn)->completed.wait.lock) - if (ctlq_msg->data_len) { - size_t payload_size = ctlq_msg->ctx.indirect.payload->size; +/** + * idpf_vc_xn_release_bufs - Release reference to reply buffer(s) and + * reset the transaction state. + * @xn: struct idpf_vc_xn to update + */ +static void idpf_vc_xn_release_bufs(struct idpf_vc_xn *xn) +{ + xn->reply.iov_base = NULL; + xn->reply.iov_len = 0; - if (!payload_size) { - dev_err(&adapter->pdev->dev, "Failed to receive payload buffer\n"); - kfree(vc_msg); + if (xn->state != IDPF_VC_XN_SHUTDOWN) + xn->state = IDPF_VC_XN_IDLE; +} - return -EINVAL; - } +/** + * idpf_vc_xn_init - Initialize virtchnl transaction object + * @vcxn_mngr: pointer to vc transaction manager struct + */ +static void idpf_vc_xn_init(struct idpf_vc_xn_manager *vcxn_mngr) +{ + int i; - memcpy(vc_msg, ctlq_msg->ctx.indirect.payload->va, - min_t(size_t, payload_size, IDPF_CTLQ_MAX_BUF_LEN)); - } - - switch (ctlq_msg->cookie.mbx.chnl_opcode) { - case VIRTCHNL2_OP_VERSION: - case VIRTCHNL2_OP_GET_CAPS: - case VIRTCHNL2_OP_CREATE_VPORT: - case VIRTCHNL2_OP_SET_SRIOV_VFS: - case VIRTCHNL2_OP_ALLOC_VECTORS: - case VIRTCHNL2_OP_DEALLOC_VECTORS: - case VIRTCHNL2_OP_GET_PTYPE_INFO: - goto free_vc_msg; - case VIRTCHNL2_OP_ENABLE_VPORT: - case VIRTCHNL2_OP_DISABLE_VPORT: - case VIRTCHNL2_OP_DESTROY_VPORT: - v_id = le32_to_cpu(((struct virtchnl2_vport *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_CONFIG_TX_QUEUES: - v_id = le32_to_cpu(((struct virtchnl2_config_tx_queues *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_CONFIG_RX_QUEUES: - v_id = le32_to_cpu(((struct virtchnl2_config_rx_queues *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_ENABLE_QUEUES: - case VIRTCHNL2_OP_DISABLE_QUEUES: - case VIRTCHNL2_OP_DEL_QUEUES: - v_id = le32_to_cpu(((struct virtchnl2_del_ena_dis_queues *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_ADD_QUEUES: - v_id = le32_to_cpu(((struct virtchnl2_add_queues *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_MAP_QUEUE_VECTOR: - case VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR: - v_id = le32_to_cpu(((struct virtchnl2_queue_vector_maps *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_GET_STATS: - v_id = le32_to_cpu(((struct virtchnl2_vport_stats *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_GET_RSS_LUT: - case VIRTCHNL2_OP_SET_RSS_LUT: - v_id = le32_to_cpu(((struct virtchnl2_rss_lut *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_GET_RSS_KEY: - case VIRTCHNL2_OP_SET_RSS_KEY: - v_id = le32_to_cpu(((struct virtchnl2_rss_key *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_EVENT: - v_id = le32_to_cpu(((struct virtchnl2_event *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_LOOPBACK: - v_id = le32_to_cpu(((struct virtchnl2_loopback *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE: - v_id = le32_to_cpu(((struct virtchnl2_promisc_info *)vc_msg)->vport_id); - break; - case VIRTCHNL2_OP_ADD_MAC_ADDR: - case VIRTCHNL2_OP_DEL_MAC_ADDR: - v_id = le32_to_cpu(((struct virtchnl2_mac_addr_list *)vc_msg)->vport_id); - break; - default: - no_op = true; - break; - } + spin_lock_init(&vcxn_mngr->xn_bm_lock); - if (no_op) - goto free_vc_msg; + for (i = 0; i < ARRAY_SIZE(vcxn_mngr->ring); i++) { + struct idpf_vc_xn *xn = &vcxn_mngr->ring[i]; - for (i = 0; i < idpf_get_max_vports(adapter); i++) { - if (adapter->vport_ids[i] == v_id) { - vid_found = true; - break; - } + xn->state = IDPF_VC_XN_IDLE; + xn->idx = i; + idpf_vc_xn_release_bufs(xn); + init_completion(&xn->completed); } - if (vid_found) - *vport = adapter->vports[i]; - else - err = -EINVAL; - -free_vc_msg: - kfree(vc_msg); - - return err; + bitmap_fill(vcxn_mngr->free_xn_bm, IDPF_VC_XN_RING_LEN); } /** - * idpf_copy_data_to_vc_buf - Copy the virtchnl response data into the buffer. - * @adapter: driver specific private structure - * @vport: virtual port structure - * @ctlq_msg: msg to copy from - * @err_enum: err bit to set on error + * idpf_vc_xn_shutdown - Uninitialize virtchnl transaction object + * @vcxn_mngr: pointer to vc transaction manager struct * - * Copies the payload from ctlq_msg into virtchnl buffer. Returns 0 on success, - * negative on failure. + * All waiting threads will be woken-up and their transaction aborted. Further + * operations on that object will fail. */ -static int idpf_copy_data_to_vc_buf(struct idpf_adapter *adapter, - struct idpf_vport *vport, - struct idpf_ctlq_msg *ctlq_msg, - enum idpf_vport_vc_state err_enum) +static void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr) { - if (ctlq_msg->cookie.mbx.chnl_retval) { - if (vport) - set_bit(err_enum, vport->vc_state); - else - set_bit(err_enum, adapter->vc_state); + int i; - return -EINVAL; - } + spin_lock_bh(&vcxn_mngr->xn_bm_lock); + bitmap_zero(vcxn_mngr->free_xn_bm, IDPF_VC_XN_RING_LEN); + spin_unlock_bh(&vcxn_mngr->xn_bm_lock); - if (vport) - memcpy(vport->vc_msg, ctlq_msg->ctx.indirect.payload->va, - min_t(int, ctlq_msg->ctx.indirect.payload->size, - IDPF_CTLQ_MAX_BUF_LEN)); - else - memcpy(adapter->vc_msg, ctlq_msg->ctx.indirect.payload->va, - min_t(int, ctlq_msg->ctx.indirect.payload->size, - IDPF_CTLQ_MAX_BUF_LEN)); + for (i = 0; i < ARRAY_SIZE(vcxn_mngr->ring); i++) { + struct idpf_vc_xn *xn = &vcxn_mngr->ring[i]; - return 0; + idpf_vc_xn_lock(xn); + xn->state = IDPF_VC_XN_SHUTDOWN; + idpf_vc_xn_release_bufs(xn); + idpf_vc_xn_unlock(xn); + complete_all(&xn->completed); + } } /** - * idpf_recv_vchnl_op - helper function with common logic when handling the - * reception of VIRTCHNL OPs. - * @adapter: driver specific private structure - * @vport: virtual port structure - * @ctlq_msg: msg to copy from - * @state: state bit used on timeout check - * @err_state: err bit to set on error + * idpf_vc_xn_pop_free - Pop a free transaction from free list + * @vcxn_mngr: transaction manager to pop from + * + * Returns NULL if no free transactions */ -static void idpf_recv_vchnl_op(struct idpf_adapter *adapter, - struct idpf_vport *vport, - struct idpf_ctlq_msg *ctlq_msg, - enum idpf_vport_vc_state state, - enum idpf_vport_vc_state err_state) +static +struct idpf_vc_xn *idpf_vc_xn_pop_free(struct idpf_vc_xn_manager *vcxn_mngr) { - wait_queue_head_t *vchnl_wq; - int err; + struct idpf_vc_xn *xn = NULL; + unsigned long free_idx; - if (vport) - vchnl_wq = &vport->vchnl_wq; - else - vchnl_wq = &adapter->vchnl_wq; + spin_lock_bh(&vcxn_mngr->xn_bm_lock); + free_idx = find_first_bit(vcxn_mngr->free_xn_bm, IDPF_VC_XN_RING_LEN); + if (free_idx == IDPF_VC_XN_RING_LEN) + goto do_unlock; - err = idpf_copy_data_to_vc_buf(adapter, vport, ctlq_msg, err_state); - if (wq_has_sleeper(vchnl_wq)) { - if (vport) - set_bit(state, vport->vc_state); - else - set_bit(state, adapter->vc_state); + clear_bit(free_idx, vcxn_mngr->free_xn_bm); + xn = &vcxn_mngr->ring[free_idx]; + xn->salt = vcxn_mngr->salt++; - wake_up(vchnl_wq); - } else { - if (!err) { - dev_warn(&adapter->pdev->dev, "opcode %d received without waiting thread\n", - ctlq_msg->cookie.mbx.chnl_opcode); - } else { - /* Clear the errors since there is no sleeper to pass - * them on - */ - if (vport) - clear_bit(err_state, vport->vc_state); - else - clear_bit(err_state, adapter->vc_state); - } - } +do_unlock: + spin_unlock_bh(&vcxn_mngr->xn_bm_lock); + + return xn; } /** - * idpf_recv_mb_msg - Receive message over mailbox - * @adapter: Driver specific private structure - * @op: virtchannel operation code - * @msg: Received message holding buffer - * @msg_size: message size - * - * Will receive control queue message and posts the receive buffer. Returns 0 - * on success and negative on failure. + * idpf_vc_xn_push_free - Push a free transaction to free list + * @vcxn_mngr: transaction manager to push to + * @xn: transaction to push */ -int idpf_recv_mb_msg(struct idpf_adapter *adapter, u32 op, - void *msg, int msg_size) +static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr, + struct idpf_vc_xn *xn) { - struct idpf_vport *vport = NULL; - struct idpf_ctlq_msg ctlq_msg; - struct idpf_dma_mem *dma_mem; - bool work_done = false; - int num_retry = 2000; - u16 num_q_msg; - int err; - - while (1) { - struct idpf_vport_config *vport_config; - int payload_size = 0; - - /* Try to get one message */ - num_q_msg = 1; - dma_mem = NULL; - err = idpf_ctlq_recv(adapter->hw.arq, &num_q_msg, &ctlq_msg); - /* If no message then decide if we have to retry based on - * opcode - */ - if (err || !num_q_msg) { - /* Increasing num_retry to consider the delayed - * responses because of large number of VF's mailbox - * messages. If the mailbox message is received from - * the other side, we come out of the sleep cycle - * immediately else we wait for more time. - */ - if (!op || !num_retry--) - break; - if (test_bit(IDPF_REMOVE_IN_PROG, adapter->flags)) { - err = -EIO; - break; - } - msleep(20); - continue; - } + idpf_vc_xn_release_bufs(xn); + set_bit(xn->idx, vcxn_mngr->free_xn_bm); +} - /* If we are here a message is received. Check if we are looking - * for a specific message based on opcode. If it is different - * ignore and post buffers +/** + * idpf_vc_xn_exec - Perform a send/recv virtchnl transaction + * @adapter: driver specific private structure with vcxn_mngr + * @params: parameters for this particular transaction including + * -vc_op: virtchannel operation to send + * -send_buf: kvec iov for send buf and len + * -recv_buf: kvec iov for recv buf and len (ignored if NULL) + * -timeout_ms: timeout waiting for a reply (milliseconds) + * -async: don't wait for message reply, will lose caller context + * -async_handler: callback to handle async replies + * + * @returns >= 0 for success, the size of the initial reply (may or may not be + * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for + * error. + */ +static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, + const struct idpf_vc_xn_params *params) +{ + const struct kvec *send_buf = ¶ms->send_buf; + struct idpf_vc_xn *xn; + ssize_t retval; + u16 cookie; + + xn = idpf_vc_xn_pop_free(adapter->vcxn_mngr); + /* no free transactions available */ + if (!xn) + return -ENOSPC; + + idpf_vc_xn_lock(xn); + if (xn->state == IDPF_VC_XN_SHUTDOWN) { + retval = -ENXIO; + goto only_unlock; + } else if (xn->state != IDPF_VC_XN_IDLE) { + /* We're just going to clobber this transaction even though + * it's not IDLE. If we don't reuse it we could theoretically + * eventually leak all the free transactions and not be able to + * send any messages. At least this way we make an attempt to + * remain functional even though something really bad is + * happening that's corrupting what was supposed to be free + * transactions. */ - if (op && ctlq_msg.cookie.mbx.chnl_opcode != op) - goto post_buffs; + WARN_ONCE(1, "There should only be idle transactions in free list (idx %d op %d)\n", + xn->idx, xn->vc_op); + } - err = idpf_find_vport(adapter, &vport, &ctlq_msg); - if (err) - goto post_buffs; + xn->reply = params->recv_buf; + xn->reply_sz = 0; + xn->state = params->async ? IDPF_VC_XN_ASYNC : IDPF_VC_XN_WAITING; + xn->vc_op = params->vc_op; + xn->async_handler = params->async_handler; + idpf_vc_xn_unlock(xn); - if (ctlq_msg.data_len) - payload_size = ctlq_msg.ctx.indirect.payload->size; + if (!params->async) + reinit_completion(&xn->completed); + cookie = FIELD_PREP(IDPF_VC_XN_SALT_M, xn->salt) | + FIELD_PREP(IDPF_VC_XN_IDX_M, xn->idx); - /* All conditions are met. Either a message requested is - * received or we received a message to be processed - */ - switch (ctlq_msg.cookie.mbx.chnl_opcode) { - case VIRTCHNL2_OP_VERSION: - case VIRTCHNL2_OP_GET_CAPS: - if (ctlq_msg.cookie.mbx.chnl_retval) { - dev_err(&adapter->pdev->dev, "Failure initializing, vc op: %u retval: %u\n", - ctlq_msg.cookie.mbx.chnl_opcode, - ctlq_msg.cookie.mbx.chnl_retval); - err = -EBADMSG; - } else if (msg) { - memcpy(msg, ctlq_msg.ctx.indirect.payload->va, - min_t(int, payload_size, msg_size)); - } - work_done = true; - break; - case VIRTCHNL2_OP_CREATE_VPORT: - idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, - IDPF_VC_CREATE_VPORT, - IDPF_VC_CREATE_VPORT_ERR); - break; - case VIRTCHNL2_OP_ENABLE_VPORT: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_ENA_VPORT, - IDPF_VC_ENA_VPORT_ERR); - break; - case VIRTCHNL2_OP_DISABLE_VPORT: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_DIS_VPORT, - IDPF_VC_DIS_VPORT_ERR); - break; - case VIRTCHNL2_OP_DESTROY_VPORT: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_DESTROY_VPORT, - IDPF_VC_DESTROY_VPORT_ERR); - break; - case VIRTCHNL2_OP_CONFIG_TX_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_CONFIG_TXQ, - IDPF_VC_CONFIG_TXQ_ERR); - break; - case VIRTCHNL2_OP_CONFIG_RX_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_CONFIG_RXQ, - IDPF_VC_CONFIG_RXQ_ERR); - break; - case VIRTCHNL2_OP_ENABLE_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_ENA_QUEUES, - IDPF_VC_ENA_QUEUES_ERR); - break; - case VIRTCHNL2_OP_DISABLE_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_DIS_QUEUES, - IDPF_VC_DIS_QUEUES_ERR); - break; - case VIRTCHNL2_OP_ADD_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_ADD_QUEUES, - IDPF_VC_ADD_QUEUES_ERR); - break; - case VIRTCHNL2_OP_DEL_QUEUES: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_DEL_QUEUES, - IDPF_VC_DEL_QUEUES_ERR); - break; - case VIRTCHNL2_OP_MAP_QUEUE_VECTOR: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_MAP_IRQ, - IDPF_VC_MAP_IRQ_ERR); - break; - case VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_UNMAP_IRQ, - IDPF_VC_UNMAP_IRQ_ERR); - break; - case VIRTCHNL2_OP_GET_STATS: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_GET_STATS, - IDPF_VC_GET_STATS_ERR); - break; - case VIRTCHNL2_OP_GET_RSS_LUT: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_GET_RSS_LUT, - IDPF_VC_GET_RSS_LUT_ERR); - break; - case VIRTCHNL2_OP_SET_RSS_LUT: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_SET_RSS_LUT, - IDPF_VC_SET_RSS_LUT_ERR); - break; - case VIRTCHNL2_OP_GET_RSS_KEY: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_GET_RSS_KEY, - IDPF_VC_GET_RSS_KEY_ERR); - break; - case VIRTCHNL2_OP_SET_RSS_KEY: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_SET_RSS_KEY, - IDPF_VC_SET_RSS_KEY_ERR); - break; - case VIRTCHNL2_OP_SET_SRIOV_VFS: - idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, - IDPF_VC_SET_SRIOV_VFS, - IDPF_VC_SET_SRIOV_VFS_ERR); - break; - case VIRTCHNL2_OP_ALLOC_VECTORS: - idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, - IDPF_VC_ALLOC_VECTORS, - IDPF_VC_ALLOC_VECTORS_ERR); - break; - case VIRTCHNL2_OP_DEALLOC_VECTORS: - idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, - IDPF_VC_DEALLOC_VECTORS, - IDPF_VC_DEALLOC_VECTORS_ERR); - break; - case VIRTCHNL2_OP_GET_PTYPE_INFO: - idpf_recv_vchnl_op(adapter, NULL, &ctlq_msg, - IDPF_VC_GET_PTYPE_INFO, - IDPF_VC_GET_PTYPE_INFO_ERR); - break; - case VIRTCHNL2_OP_LOOPBACK: - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_LOOPBACK_STATE, - IDPF_VC_LOOPBACK_STATE_ERR); - break; - case VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE: - /* This message can only be sent asynchronously. As - * such we'll have lost the context in which it was - * called and thus can only really report if it looks - * like an error occurred. Don't bother setting ERR bit - * or waking chnl_wq since no work queue will be waiting - * to read the message. - */ - if (ctlq_msg.cookie.mbx.chnl_retval) { - dev_err(&adapter->pdev->dev, "Failed to set promiscuous mode: %d\n", - ctlq_msg.cookie.mbx.chnl_retval); - } - break; - case VIRTCHNL2_OP_ADD_MAC_ADDR: - vport_config = adapter->vport_config[vport->idx]; - if (test_and_clear_bit(IDPF_VPORT_ADD_MAC_REQ, - vport_config->flags)) { - /* Message was sent asynchronously. We don't - * normally print errors here, instead - * prefer to handle errors in the function - * calling wait_for_event. However, if - * asynchronous, the context in which the - * message was sent is lost. We can't really do - * anything about at it this point, but we - * should at a minimum indicate that it looks - * like something went wrong. Also don't bother - * setting ERR bit or waking vchnl_wq since no - * one will be waiting to read the async - * message. - */ - if (ctlq_msg.cookie.mbx.chnl_retval) - dev_err(&adapter->pdev->dev, "Failed to add MAC address: %d\n", - ctlq_msg.cookie.mbx.chnl_retval); - break; - } - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_ADD_MAC_ADDR, - IDPF_VC_ADD_MAC_ADDR_ERR); - break; - case VIRTCHNL2_OP_DEL_MAC_ADDR: - vport_config = adapter->vport_config[vport->idx]; - if (test_and_clear_bit(IDPF_VPORT_DEL_MAC_REQ, - vport_config->flags)) { - /* Message was sent asynchronously like the - * VIRTCHNL2_OP_ADD_MAC_ADDR - */ - if (ctlq_msg.cookie.mbx.chnl_retval) - dev_err(&adapter->pdev->dev, "Failed to delete MAC address: %d\n", - ctlq_msg.cookie.mbx.chnl_retval); - break; - } - idpf_recv_vchnl_op(adapter, vport, &ctlq_msg, - IDPF_VC_DEL_MAC_ADDR, - IDPF_VC_DEL_MAC_ADDR_ERR); - break; - case VIRTCHNL2_OP_EVENT: - idpf_recv_event_msg(vport, &ctlq_msg); - break; - default: - dev_warn(&adapter->pdev->dev, - "Unhandled virtchnl response %d\n", - ctlq_msg.cookie.mbx.chnl_opcode); - break; - } + retval = idpf_send_mb_msg(adapter, params->vc_op, + send_buf->iov_len, send_buf->iov_base, + cookie); + if (retval) { + idpf_vc_xn_lock(xn); + goto release_and_unlock; + } -post_buffs: - if (ctlq_msg.data_len) - dma_mem = ctlq_msg.ctx.indirect.payload; - else - num_q_msg = 0; + if (params->async) + return 0; - err = idpf_ctlq_post_rx_buffs(&adapter->hw, adapter->hw.arq, - &num_q_msg, &dma_mem); - /* If post failed clear the only buffer we supplied */ - if (err && dma_mem) - dma_free_coherent(&adapter->pdev->dev, dma_mem->size, - dma_mem->va, dma_mem->pa); + wait_for_completion_timeout(&xn->completed, + msecs_to_jiffies(params->timeout_ms)); - /* Applies only if we are looking for a specific opcode */ - if (work_done) - break; + /* No need to check the return value; we check the final state of the + * transaction below. It's possible the transaction actually gets more + * timeout than specified if we get preempted here but after + * wait_for_completion_timeout returns. This should be non-issue + * however. + */ + idpf_vc_xn_lock(xn); + switch (xn->state) { + case IDPF_VC_XN_SHUTDOWN: + retval = -ENXIO; + goto only_unlock; + case IDPF_VC_XN_WAITING: + dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n", + params->vc_op, params->timeout_ms); + retval = -ETIME; + break; + case IDPF_VC_XN_COMPLETED_SUCCESS: + retval = xn->reply_sz; + break; + case IDPF_VC_XN_COMPLETED_FAILED: + dev_notice_ratelimited(&adapter->pdev->dev, "Transaction failed (op %d)\n", + params->vc_op); + retval = -EIO; + break; + default: + /* Invalid state. */ + WARN_ON_ONCE(1); + retval = -EIO; + break; } - return err; +release_and_unlock: + idpf_vc_xn_push_free(adapter->vcxn_mngr, xn); + /* If we receive a VC reply after here, it will be dropped. */ +only_unlock: + idpf_vc_xn_unlock(xn); + + return retval; } /** - * __idpf_wait_for_event - wrapper function for wait on virtchannel response - * @adapter: Driver private data structure - * @vport: virtual port structure - * @state: check on state upon timeout - * @err_check: check if this specific error bit is set - * @timeout: Max time to wait + * idpf_vc_xn_forward_async - Handle async reply receives + * @adapter: private data struct + * @xn: transaction to handle + * @ctlq_msg: corresponding ctlq_msg * - * Checks if state is set upon expiry of timeout. Returns 0 on success, - * negative on failure. + * For async sends we're going to lose the caller's context so, if an + * async_handler was provided, it can deal with the reply, otherwise we'll just + * check and report if there is an error. */ -static int __idpf_wait_for_event(struct idpf_adapter *adapter, - struct idpf_vport *vport, - enum idpf_vport_vc_state state, - enum idpf_vport_vc_state err_check, - int timeout) +static int +idpf_vc_xn_forward_async(struct idpf_adapter *adapter, struct idpf_vc_xn *xn, + const struct idpf_ctlq_msg *ctlq_msg) { - int time_to_wait, num_waits; - wait_queue_head_t *vchnl_wq; - unsigned long *vc_state; + int err = 0; - time_to_wait = ((timeout <= IDPF_MAX_WAIT) ? timeout : IDPF_MAX_WAIT); - num_waits = ((timeout <= IDPF_MAX_WAIT) ? 1 : timeout / IDPF_MAX_WAIT); + if (ctlq_msg->cookie.mbx.chnl_opcode != xn->vc_op) { + dev_err_ratelimited(&adapter->pdev->dev, "Async message opcode does not match transaction opcode (msg: %d) (xn: %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode, xn->vc_op); + xn->reply_sz = 0; + err = -EINVAL; + goto release_bufs; + } - if (vport) { - vchnl_wq = &vport->vchnl_wq; - vc_state = vport->vc_state; - } else { - vchnl_wq = &adapter->vchnl_wq; - vc_state = adapter->vc_state; + if (xn->async_handler) { + err = xn->async_handler(adapter, xn, ctlq_msg); + goto release_bufs; + } + + if (ctlq_msg->cookie.mbx.chnl_retval) { + xn->reply_sz = 0; + dev_err_ratelimited(&adapter->pdev->dev, "Async message failure (op %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode); + err = -EINVAL; } - while (num_waits) { - int event; +release_bufs: + idpf_vc_xn_push_free(adapter->vcxn_mngr, xn); + + return err; +} + +/** + * idpf_vc_xn_forward_reply - copy a reply back to receiving thread + * @adapter: driver specific private structure with vcxn_mngr + * @ctlq_msg: controlq message to send back to receiving thread + */ +static int +idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, + const struct idpf_ctlq_msg *ctlq_msg) +{ + const void *payload = NULL; + size_t payload_size = 0; + struct idpf_vc_xn *xn; + u16 msg_info; + int err = 0; + u16 xn_idx; + u16 salt; + + msg_info = ctlq_msg->ctx.sw_cookie.data; + xn_idx = FIELD_GET(IDPF_VC_XN_IDX_M, msg_info); + if (xn_idx >= ARRAY_SIZE(adapter->vcxn_mngr->ring)) { + dev_err_ratelimited(&adapter->pdev->dev, "Out of bounds cookie received: %02x\n", + xn_idx); + return -EINVAL; + } + xn = &adapter->vcxn_mngr->ring[xn_idx]; + salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info); + if (xn->salt != salt) { + dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n", + xn->salt, salt); + return -EINVAL; + } - /* If we are here and a reset is detected do not wait but - * return. Reset timing is out of drivers control. So - * while we are cleaning resources as part of reset if the - * underlying HW mailbox is gone, wait on mailbox messages - * is not meaningful + idpf_vc_xn_lock(xn); + switch (xn->state) { + case IDPF_VC_XN_WAITING: + /* success */ + break; + case IDPF_VC_XN_IDLE: + dev_err_ratelimited(&adapter->pdev->dev, "Unexpected or belated VC reply (op %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode); + err = -EINVAL; + goto out_unlock; + case IDPF_VC_XN_SHUTDOWN: + /* ENXIO is a bit special here as the recv msg loop uses that + * know if it should stop trying to clean the ring if we lost + * the virtchnl. We need to stop playing with registers and + * yield. */ - if (idpf_is_reset_detected(adapter)) - return 0; + err = -ENXIO; + goto out_unlock; + case IDPF_VC_XN_ASYNC: + err = idpf_vc_xn_forward_async(adapter, xn, ctlq_msg); + idpf_vc_xn_unlock(xn); + return err; + default: + dev_err_ratelimited(&adapter->pdev->dev, "Overwriting VC reply (op %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode); + err = -EBUSY; + goto out_unlock; + } - event = wait_event_timeout(*vchnl_wq, - test_and_clear_bit(state, vc_state), - msecs_to_jiffies(time_to_wait)); - if (event) { - if (test_and_clear_bit(err_check, vc_state)) { - dev_err(&adapter->pdev->dev, "VC response error %s\n", - idpf_vport_vc_state_str[err_check]); + if (ctlq_msg->cookie.mbx.chnl_opcode != xn->vc_op) { + dev_err_ratelimited(&adapter->pdev->dev, "Message opcode does not match transaction opcode (msg: %d) (xn: %d)\n", + ctlq_msg->cookie.mbx.chnl_opcode, xn->vc_op); + xn->reply_sz = 0; + xn->state = IDPF_VC_XN_COMPLETED_FAILED; + err = -EINVAL; + goto out_unlock; + } - return -EINVAL; - } + if (ctlq_msg->cookie.mbx.chnl_retval) { + xn->reply_sz = 0; + xn->state = IDPF_VC_XN_COMPLETED_FAILED; + err = -EINVAL; + goto out_unlock; + } - return 0; - } - num_waits--; + if (ctlq_msg->data_len) { + payload = ctlq_msg->ctx.indirect.payload->va; + payload_size = ctlq_msg->ctx.indirect.payload->size; } - /* Timeout occurred */ - dev_err(&adapter->pdev->dev, "VC timeout, state = %s\n", - idpf_vport_vc_state_str[state]); + xn->reply_sz = payload_size; + xn->state = IDPF_VC_XN_COMPLETED_SUCCESS; - return -ETIMEDOUT; + if (xn->reply.iov_base && xn->reply.iov_len && payload_size) + memcpy(xn->reply.iov_base, payload, + min_t(size_t, xn->reply.iov_len, payload_size)); + +out_unlock: + idpf_vc_xn_unlock(xn); + /* we _cannot_ hold lock while calling complete */ + complete(&xn->completed); + + return err; } /** - * idpf_min_wait_for_event - wait for virtchannel response - * @adapter: Driver private data structure - * @vport: virtual port structure - * @state: check on state upon timeout - * @err_check: check if this specific error bit is set + * idpf_recv_mb_msg - Receive message over mailbox + * @adapter: Driver specific private structure * - * Returns 0 on success, negative on failure. + * Will receive control queue message and posts the receive buffer. Returns 0 + * on success and negative on failure. */ -static int idpf_min_wait_for_event(struct idpf_adapter *adapter, - struct idpf_vport *vport, - enum idpf_vport_vc_state state, - enum idpf_vport_vc_state err_check) +int idpf_recv_mb_msg(struct idpf_adapter *adapter) { - return __idpf_wait_for_event(adapter, vport, state, err_check, - IDPF_WAIT_FOR_EVENT_TIMEO_MIN); -} + struct idpf_ctlq_msg ctlq_msg; + struct idpf_dma_mem *dma_mem; + int post_err, err; + u16 num_recv; -/** - * idpf_wait_for_event - wait for virtchannel response - * @adapter: Driver private data structure - * @vport: virtual port structure - * @state: check on state upon timeout after 500ms - * @err_check: check if this specific error bit is set - * - * Returns 0 on success, negative on failure. - */ -static int idpf_wait_for_event(struct idpf_adapter *adapter, - struct idpf_vport *vport, - enum idpf_vport_vc_state state, - enum idpf_vport_vc_state err_check) -{ - /* Increasing the timeout in __IDPF_INIT_SW flow to consider large - * number of VF's mailbox message responses. When a message is received - * on mailbox, this thread is woken up by the idpf_recv_mb_msg before - * the timeout expires. Only in the error case i.e. if no message is - * received on mailbox, we wait for the complete timeout which is - * less likely to happen. - */ - return __idpf_wait_for_event(adapter, vport, state, err_check, - IDPF_WAIT_FOR_EVENT_TIMEO); + while (1) { + /* This will get <= num_recv messages and output how many + * actually received on num_recv. + */ + num_recv = 1; + err = idpf_ctlq_recv(adapter->hw.arq, &num_recv, &ctlq_msg); + if (err || !num_recv) + break; + + if (ctlq_msg.data_len) { + dma_mem = ctlq_msg.ctx.indirect.payload; + } else { + dma_mem = NULL; + num_recv = 0; + } + + if (ctlq_msg.cookie.mbx.chnl_opcode == VIRTCHNL2_OP_EVENT) + idpf_recv_event_msg(adapter, &ctlq_msg); + else + err = idpf_vc_xn_forward_reply(adapter, &ctlq_msg); + + post_err = idpf_ctlq_post_rx_buffs(&adapter->hw, + adapter->hw.arq, + &num_recv, &dma_mem); + + /* If post failed clear the only buffer we supplied */ + if (post_err) { + if (dma_mem) + dmam_free_coherent(&adapter->pdev->dev, + dma_mem->size, dma_mem->va, + dma_mem->pa); + break; + } + + /* virtchnl trying to shutdown, stop cleaning */ + if (err == -ENXIO) + break; + } + + return err; } /** @@ -785,7 +776,11 @@ static int idpf_wait_for_marker_event(struct idpf_vport *vport) */ static int idpf_send_ver_msg(struct idpf_adapter *adapter) { + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_version_info vvi; + ssize_t reply_sz; + u32 major, minor; + int err = 0; if (adapter->virt_ver_maj) { vvi.major = cpu_to_le32(adapter->virt_ver_maj); @@ -795,43 +790,29 @@ static int idpf_send_ver_msg(struct idpf_adapter *adapter) vvi.minor = cpu_to_le32(IDPF_VIRTCHNL_VERSION_MINOR); } - return idpf_send_mb_msg(adapter, VIRTCHNL2_OP_VERSION, sizeof(vvi), - (u8 *)&vvi); -} - -/** - * idpf_recv_ver_msg - Receive virtchnl version message - * @adapter: Driver specific private structure - * - * Receive virtchnl version message. Returns 0 on success, -EAGAIN if we need - * to send version message again, otherwise negative on failure. - */ -static int idpf_recv_ver_msg(struct idpf_adapter *adapter) -{ - struct virtchnl2_version_info vvi; - u32 major, minor; - int err; + xn_params.vc_op = VIRTCHNL2_OP_VERSION; + xn_params.send_buf.iov_base = &vvi; + xn_params.send_buf.iov_len = sizeof(vvi); + xn_params.recv_buf = xn_params.send_buf; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; - err = idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_VERSION, &vvi, - sizeof(vvi)); - if (err) - return err; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz < sizeof(vvi)) + return -EIO; major = le32_to_cpu(vvi.major); minor = le32_to_cpu(vvi.minor); if (major > IDPF_VIRTCHNL_VERSION_MAJOR) { - dev_warn(&adapter->pdev->dev, - "Virtchnl major version (%d) greater than supported\n", - major); - + dev_warn(&adapter->pdev->dev, "Virtchnl major version greater than supported\n"); return -EINVAL; } if (major == IDPF_VIRTCHNL_VERSION_MAJOR && minor > IDPF_VIRTCHNL_VERSION_MINOR) - dev_warn(&adapter->pdev->dev, - "Virtchnl minor version (%d) didn't match\n", minor); + dev_warn(&adapter->pdev->dev, "Virtchnl minor version didn't match\n"); /* If we have a mismatch, resend version to update receiver on what * version we will use. @@ -856,7 +837,9 @@ static int idpf_recv_ver_msg(struct idpf_adapter *adapter) */ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter) { - struct virtchnl2_get_capabilities caps = { }; + struct virtchnl2_get_capabilities caps = {}; + struct idpf_vc_xn_params xn_params = {}; + ssize_t reply_sz; caps.csum_caps = cpu_to_le32(VIRTCHNL2_CAP_TX_CSUM_L3_IPV4 | @@ -913,21 +896,20 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter) VIRTCHNL2_CAP_PROMISC | VIRTCHNL2_CAP_LOOPBACK); - return idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_CAPS, sizeof(caps), - (u8 *)&caps); -} + xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS; + xn_params.send_buf.iov_base = ∩︀ + xn_params.send_buf.iov_len = sizeof(caps); + xn_params.recv_buf.iov_base = &adapter->caps; + xn_params.recv_buf.iov_len = sizeof(adapter->caps); + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; -/** - * idpf_recv_get_caps_msg - Receive virtchnl get capabilities message - * @adapter: Driver specific private structure - * - * Receive virtchnl get capabilities message. Returns 0 on success, negative on - * failure. - */ -static int idpf_recv_get_caps_msg(struct idpf_adapter *adapter) -{ - return idpf_recv_mb_msg(adapter, VIRTCHNL2_OP_GET_CAPS, &adapter->caps, - sizeof(struct virtchnl2_get_capabilities)); + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz < sizeof(adapter->caps)) + return -EIO; + + return 0; } /** @@ -1254,8 +1236,10 @@ int idpf_send_create_vport_msg(struct idpf_adapter *adapter, struct idpf_vport_max_q *max_q) { struct virtchnl2_create_vport *vport_msg; + struct idpf_vc_xn_params xn_params = {}; u16 idx = adapter->next_vport; int err, buf_size; + ssize_t reply_sz; buf_size = sizeof(struct virtchnl2_create_vport); if (!adapter->vport_params_reqd[idx]) { @@ -1286,35 +1270,38 @@ int idpf_send_create_vport_msg(struct idpf_adapter *adapter, return err; } - mutex_lock(&adapter->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_CREATE_VPORT, buf_size, - (u8 *)vport_msg); - if (err) - goto rel_lock; - - err = idpf_wait_for_event(adapter, NULL, IDPF_VC_CREATE_VPORT, - IDPF_VC_CREATE_VPORT_ERR); - if (err) { - dev_err(&adapter->pdev->dev, "Failed to receive create vport message"); - - goto rel_lock; - } - if (!adapter->vport_params_recvd[idx]) { adapter->vport_params_recvd[idx] = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); if (!adapter->vport_params_recvd[idx]) { err = -ENOMEM; - goto rel_lock; + goto free_vport_params; } } - vport_msg = adapter->vport_params_recvd[idx]; - memcpy(vport_msg, adapter->vc_msg, IDPF_CTLQ_MAX_BUF_LEN); + xn_params.vc_op = VIRTCHNL2_OP_CREATE_VPORT; + xn_params.send_buf.iov_base = vport_msg; + xn_params.send_buf.iov_len = buf_size; + xn_params.recv_buf.iov_base = adapter->vport_params_recvd[idx]; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) { + err = reply_sz; + goto free_vport_params; + } + if (reply_sz < IDPF_CTLQ_MAX_BUF_LEN) { + err = -EIO; + goto free_vport_params; + } -rel_lock: - mutex_unlock(&adapter->vc_buf_lock); + return 0; + +free_vport_params: + kfree(adapter->vport_params_recvd[idx]); + adapter->vport_params_recvd[idx] = NULL; + kfree(adapter->vport_params_reqd[idx]); + adapter->vport_params_reqd[idx] = NULL; return err; } @@ -1366,26 +1353,19 @@ int idpf_check_supported_desc_ids(struct idpf_vport *vport) */ int idpf_send_destroy_vport_msg(struct idpf_vport *vport) { - struct idpf_adapter *adapter = vport->adapter; + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_vport v_id; - int err; + ssize_t reply_sz; v_id.vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_DESTROY_VPORT; + xn_params.send_buf.iov_base = &v_id; + xn_params.send_buf.iov_len = sizeof(v_id); + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DESTROY_VPORT, - sizeof(v_id), (u8 *)&v_id); - if (err) - goto rel_lock; - - err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DESTROY_VPORT, - IDPF_VC_DESTROY_VPORT_ERR); - -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -1397,26 +1377,19 @@ rel_lock: */ int idpf_send_enable_vport_msg(struct idpf_vport *vport) { - struct idpf_adapter *adapter = vport->adapter; + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_vport v_id; - int err; + ssize_t reply_sz; v_id.vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ENABLE_VPORT, - sizeof(v_id), (u8 *)&v_id); - if (err) - goto rel_lock; - - err = idpf_wait_for_event(adapter, vport, IDPF_VC_ENA_VPORT, - IDPF_VC_ENA_VPORT_ERR); + xn_params.vc_op = VIRTCHNL2_OP_ENABLE_VPORT; + xn_params.send_buf.iov_base = &v_id; + xn_params.send_buf.iov_len = sizeof(v_id); + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -1428,26 +1401,19 @@ rel_lock: */ int idpf_send_disable_vport_msg(struct idpf_vport *vport) { - struct idpf_adapter *adapter = vport->adapter; + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_vport v_id; - int err; + ssize_t reply_sz; v_id.vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_DISABLE_VPORT; + xn_params.send_buf.iov_base = &v_id; + xn_params.send_buf.iov_len = sizeof(v_id); + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DISABLE_VPORT, - sizeof(v_id), (u8 *)&v_id); - if (err) - goto rel_lock; - - err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DIS_VPORT, - IDPF_VC_DIS_VPORT_ERR); - -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -1459,11 +1425,13 @@ rel_lock: */ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) { - struct virtchnl2_config_tx_queues *ctq; + struct virtchnl2_config_tx_queues *ctq __free(kfree) = NULL; + struct virtchnl2_txq_info *qi __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; u32 config_sz, chunk_sz, buf_sz; int totqs, num_msgs, num_chunks; - struct virtchnl2_txq_info *qi; - int err = 0, i, k = 0; + ssize_t reply_sz; + int i, k = 0; totqs = vport->num_txq + vport->num_complq; qi = kcalloc(totqs, sizeof(struct virtchnl2_txq_info), GFP_KERNEL); @@ -1524,10 +1492,8 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) } /* Make sure accounting agrees */ - if (k != totqs) { - err = -EINVAL; - goto error; - } + if (k != totqs) + return -EINVAL; /* Chunk up the queue contexts into multiple messages to avoid * sending a control queue message buffer that is too large @@ -1541,12 +1507,11 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) buf_sz = struct_size(ctq, qinfo, num_chunks); ctq = kzalloc(buf_sz, GFP_KERNEL); - if (!ctq) { - err = -ENOMEM; - goto error; - } + if (!ctq) + return -ENOMEM; - mutex_lock(&vport->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_CONFIG_TX_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; for (i = 0, k = 0; i < num_msgs; i++) { memset(ctq, 0, buf_sz); @@ -1554,17 +1519,11 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) ctq->num_qinfo = cpu_to_le16(num_chunks); memcpy(ctq->qinfo, &qi[k], chunk_sz * num_chunks); - err = idpf_send_mb_msg(vport->adapter, - VIRTCHNL2_OP_CONFIG_TX_QUEUES, - buf_sz, (u8 *)ctq); - if (err) - goto mbx_error; - - err = idpf_wait_for_event(vport->adapter, vport, - IDPF_VC_CONFIG_TXQ, - IDPF_VC_CONFIG_TXQ_ERR); - if (err) - goto mbx_error; + xn_params.send_buf.iov_base = ctq; + xn_params.send_buf.iov_len = buf_sz; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; k += num_chunks; totqs -= num_chunks; @@ -1573,13 +1532,7 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) buf_sz = struct_size(ctq, qinfo, num_chunks); } -mbx_error: - mutex_unlock(&vport->vc_buf_lock); - kfree(ctq); -error: - kfree(qi); - - return err; + return 0; } /** @@ -1591,11 +1544,13 @@ error: */ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport) { - struct virtchnl2_config_rx_queues *crq; + struct virtchnl2_config_rx_queues *crq __free(kfree) = NULL; + struct virtchnl2_rxq_info *qi __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; u32 config_sz, chunk_sz, buf_sz; int totqs, num_msgs, num_chunks; - struct virtchnl2_rxq_info *qi; - int err = 0, i, k = 0; + ssize_t reply_sz; + int i, k = 0; totqs = vport->num_rxq + vport->num_bufq; qi = kcalloc(totqs, sizeof(struct virtchnl2_rxq_info), GFP_KERNEL); @@ -1676,10 +1631,8 @@ common_qi_fields: } /* Make sure accounting agrees */ - if (k != totqs) { - err = -EINVAL; - goto error; - } + if (k != totqs) + return -EINVAL; /* Chunk up the queue contexts into multiple messages to avoid * sending a control queue message buffer that is too large @@ -1693,12 +1646,11 @@ common_qi_fields: buf_sz = struct_size(crq, qinfo, num_chunks); crq = kzalloc(buf_sz, GFP_KERNEL); - if (!crq) { - err = -ENOMEM; - goto error; - } + if (!crq) + return -ENOMEM; - mutex_lock(&vport->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_CONFIG_RX_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; for (i = 0, k = 0; i < num_msgs; i++) { memset(crq, 0, buf_sz); @@ -1706,17 +1658,11 @@ common_qi_fields: crq->num_qinfo = cpu_to_le16(num_chunks); memcpy(crq->qinfo, &qi[k], chunk_sz * num_chunks); - err = idpf_send_mb_msg(vport->adapter, - VIRTCHNL2_OP_CONFIG_RX_QUEUES, - buf_sz, (u8 *)crq); - if (err) - goto mbx_error; - - err = idpf_wait_for_event(vport->adapter, vport, - IDPF_VC_CONFIG_RXQ, - IDPF_VC_CONFIG_RXQ_ERR); - if (err) - goto mbx_error; + xn_params.send_buf.iov_base = crq; + xn_params.send_buf.iov_len = buf_sz; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; k += num_chunks; totqs -= num_chunks; @@ -1725,42 +1671,28 @@ common_qi_fields: buf_sz = struct_size(crq, qinfo, num_chunks); } -mbx_error: - mutex_unlock(&vport->vc_buf_lock); - kfree(crq); -error: - kfree(qi); - - return err; + return 0; } /** * idpf_send_ena_dis_queues_msg - Send virtchnl enable or disable * queues message * @vport: virtual port data structure - * @vc_op: virtchnl op code to send + * @ena: if true enable, false disable * * Send enable or disable queues virtchnl message. Returns 0 on success, * negative on failure. */ -static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, u32 vc_op) +static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena) { + struct virtchnl2_del_ena_dis_queues *eq __free(kfree) = NULL; + struct virtchnl2_queue_chunk *qc __free(kfree) = NULL; u32 num_msgs, num_chunks, num_txq, num_rxq, num_q; - struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_del_ena_dis_queues *eq; + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_queue_chunks *qcs; - struct virtchnl2_queue_chunk *qc; u32 config_sz, chunk_sz, buf_sz; - int i, j, k = 0, err = 0; - - /* validate virtchnl op */ - switch (vc_op) { - case VIRTCHNL2_OP_ENABLE_QUEUES: - case VIRTCHNL2_OP_DISABLE_QUEUES: - break; - default: - return -EINVAL; - } + ssize_t reply_sz; + int i, j, k = 0; num_txq = vport->num_txq + vport->num_complq; num_rxq = vport->num_rxq + vport->num_bufq; @@ -1779,10 +1711,8 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, u32 vc_op) qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } } - if (vport->num_txq != k) { - err = -EINVAL; - goto error; - } + if (vport->num_txq != k) + return -EINVAL; if (!idpf_is_queue_model_split(vport->txq_model)) goto setup_rx; @@ -1794,10 +1724,8 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, u32 vc_op) qc[k].start_queue_id = cpu_to_le32(tx_qgrp->complq->q_id); qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } - if (vport->num_complq != (k - vport->num_txq)) { - err = -EINVAL; - goto error; - } + if (vport->num_complq != (k - vport->num_txq)) + return -EINVAL; setup_rx: for (i = 0; i < vport->num_rxq_grp; i++) { @@ -1823,10 +1751,8 @@ setup_rx: qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK); } } - if (vport->num_rxq != k - (vport->num_txq + vport->num_complq)) { - err = -EINVAL; - goto error; - } + if (vport->num_rxq != k - (vport->num_txq + vport->num_complq)) + return -EINVAL; if (!idpf_is_queue_model_split(vport->rxq_model)) goto send_msg; @@ -1845,10 +1771,8 @@ setup_rx: } if (vport->num_bufq != k - (vport->num_txq + vport->num_complq + - vport->num_rxq)) { - err = -EINVAL; - goto error; - } + vport->num_rxq)) + return -EINVAL; send_msg: /* Chunk up the queue info into multiple messages */ @@ -1861,12 +1785,16 @@ send_msg: buf_sz = struct_size(eq, chunks.chunks, num_chunks); eq = kzalloc(buf_sz, GFP_KERNEL); - if (!eq) { - err = -ENOMEM; - goto error; - } + if (!eq) + return -ENOMEM; - mutex_lock(&vport->vc_buf_lock); + if (ena) { + xn_params.vc_op = VIRTCHNL2_OP_ENABLE_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + } else { + xn_params.vc_op = VIRTCHNL2_OP_DISABLE_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + } for (i = 0, k = 0; i < num_msgs; i++) { memset(eq, 0, buf_sz); @@ -1875,20 +1803,11 @@ send_msg: qcs = &eq->chunks; memcpy(qcs->chunks, &qc[k], chunk_sz * num_chunks); - err = idpf_send_mb_msg(adapter, vc_op, buf_sz, (u8 *)eq); - if (err) - goto mbx_error; - - if (vc_op == VIRTCHNL2_OP_ENABLE_QUEUES) - err = idpf_wait_for_event(adapter, vport, - IDPF_VC_ENA_QUEUES, - IDPF_VC_ENA_QUEUES_ERR); - else - err = idpf_min_wait_for_event(adapter, vport, - IDPF_VC_DIS_QUEUES, - IDPF_VC_DIS_QUEUES_ERR); - if (err) - goto mbx_error; + xn_params.send_buf.iov_base = eq; + xn_params.send_buf.iov_len = buf_sz; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; k += num_chunks; num_q -= num_chunks; @@ -1897,13 +1816,7 @@ send_msg: buf_sz = struct_size(eq, chunks.chunks, num_chunks); } -mbx_error: - mutex_unlock(&vport->vc_buf_lock); - kfree(eq); -error: - kfree(qc); - - return err; + return 0; } /** @@ -1917,12 +1830,13 @@ error: */ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) { - struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_queue_vector_maps *vqvm; - struct virtchnl2_queue_vector *vqv; + struct virtchnl2_queue_vector_maps *vqvm __free(kfree) = NULL; + struct virtchnl2_queue_vector *vqv __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; u32 config_sz, chunk_sz, buf_sz; u32 num_msgs, num_chunks, num_q; - int i, j, k = 0, err = 0; + ssize_t reply_sz; + int i, j, k = 0; num_q = vport->num_txq + vport->num_rxq; @@ -1952,10 +1866,8 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) } } - if (vport->num_txq != k) { - err = -EINVAL; - goto error; - } + if (vport->num_txq != k) + return -EINVAL; for (i = 0; i < vport->num_rxq_grp; i++) { struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i]; @@ -1982,15 +1894,11 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) } if (idpf_is_queue_model_split(vport->txq_model)) { - if (vport->num_rxq != k - vport->num_complq) { - err = -EINVAL; - goto error; - } + if (vport->num_rxq != k - vport->num_complq) + return -EINVAL; } else { - if (vport->num_rxq != k - vport->num_txq) { - err = -EINVAL; - goto error; - } + if (vport->num_rxq != k - vport->num_txq) + return -EINVAL; } /* Chunk up the vector info into multiple messages */ @@ -2003,39 +1911,28 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) buf_sz = struct_size(vqvm, qv_maps, num_chunks); vqvm = kzalloc(buf_sz, GFP_KERNEL); - if (!vqvm) { - err = -ENOMEM; - goto error; - } + if (!vqvm) + return -ENOMEM; - mutex_lock(&vport->vc_buf_lock); + if (map) { + xn_params.vc_op = VIRTCHNL2_OP_MAP_QUEUE_VECTOR; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + } else { + xn_params.vc_op = VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR; + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + } for (i = 0, k = 0; i < num_msgs; i++) { memset(vqvm, 0, buf_sz); + xn_params.send_buf.iov_base = vqvm; + xn_params.send_buf.iov_len = buf_sz; vqvm->vport_id = cpu_to_le32(vport->vport_id); vqvm->num_qv_maps = cpu_to_le16(num_chunks); memcpy(vqvm->qv_maps, &vqv[k], chunk_sz * num_chunks); - if (map) { - err = idpf_send_mb_msg(adapter, - VIRTCHNL2_OP_MAP_QUEUE_VECTOR, - buf_sz, (u8 *)vqvm); - if (!err) - err = idpf_wait_for_event(adapter, vport, - IDPF_VC_MAP_IRQ, - IDPF_VC_MAP_IRQ_ERR); - } else { - err = idpf_send_mb_msg(adapter, - VIRTCHNL2_OP_UNMAP_QUEUE_VECTOR, - buf_sz, (u8 *)vqvm); - if (!err) - err = - idpf_min_wait_for_event(adapter, vport, - IDPF_VC_UNMAP_IRQ, - IDPF_VC_UNMAP_IRQ_ERR); - } - if (err) - goto mbx_error; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; k += num_chunks; num_q -= num_chunks; @@ -2044,13 +1941,7 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map) buf_sz = struct_size(vqvm, qv_maps, num_chunks); } -mbx_error: - mutex_unlock(&vport->vc_buf_lock); - kfree(vqvm); -error: - kfree(vqv); - - return err; + return 0; } /** @@ -2062,7 +1953,7 @@ error: */ int idpf_send_enable_queues_msg(struct idpf_vport *vport) { - return idpf_send_ena_dis_queues_msg(vport, VIRTCHNL2_OP_ENABLE_QUEUES); + return idpf_send_ena_dis_queues_msg(vport, true); } /** @@ -2076,7 +1967,7 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport) { int err, i; - err = idpf_send_ena_dis_queues_msg(vport, VIRTCHNL2_OP_DISABLE_QUEUES); + err = idpf_send_ena_dis_queues_msg(vport, false); if (err) return err; @@ -2087,8 +1978,10 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport) set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); /* schedule the napi to receive all the marker packets */ + local_bh_disable(); for (i = 0; i < vport->num_q_vectors; i++) napi_schedule(&vport->q_vectors[i].napi); + local_bh_enable(); return idpf_wait_for_marker_event(vport); } @@ -2122,22 +2015,21 @@ static void idpf_convert_reg_to_queue_chunks(struct virtchnl2_queue_chunk *dchun */ int idpf_send_delete_queues_msg(struct idpf_vport *vport) { - struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_del_ena_dis_queues *eq __free(kfree) = NULL; struct virtchnl2_create_vport *vport_params; struct virtchnl2_queue_reg_chunks *chunks; - struct virtchnl2_del_ena_dis_queues *eq; + struct idpf_vc_xn_params xn_params = {}; struct idpf_vport_config *vport_config; u16 vport_idx = vport->idx; - int buf_size, err; + ssize_t reply_sz; u16 num_chunks; + int buf_size; - vport_config = adapter->vport_config[vport_idx]; + vport_config = vport->adapter->vport_config[vport_idx]; if (vport_config->req_qs_chunks) { - struct virtchnl2_add_queues *vc_aq = - (struct virtchnl2_add_queues *)vport_config->req_qs_chunks; - chunks = &vc_aq->chunks; + chunks = &vport_config->req_qs_chunks->chunks; } else { - vport_params = adapter->vport_params_recvd[vport_idx]; + vport_params = vport->adapter->vport_params_recvd[vport_idx]; chunks = &vport_params->chunks; } @@ -2154,21 +2046,13 @@ int idpf_send_delete_queues_msg(struct idpf_vport *vport) idpf_convert_reg_to_queue_chunks(eq->chunks.chunks, chunks->chunks, num_chunks); - mutex_lock(&vport->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DEL_QUEUES, - buf_size, (u8 *)eq); - if (err) - goto rel_lock; - - err = idpf_min_wait_for_event(adapter, vport, IDPF_VC_DEL_QUEUES, - IDPF_VC_DEL_QUEUES_ERR); - -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - kfree(eq); + xn_params.vc_op = VIRTCHNL2_OP_DEL_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = eq; + xn_params.send_buf.iov_len = buf_size; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -2203,14 +2087,21 @@ int idpf_send_config_queues_msg(struct idpf_vport *vport) int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, u16 num_complq, u16 num_rx_q, u16 num_rx_bufq) { - struct idpf_adapter *adapter = vport->adapter; + struct virtchnl2_add_queues *vc_msg __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; struct idpf_vport_config *vport_config; - struct virtchnl2_add_queues aq = { }; - struct virtchnl2_add_queues *vc_msg; + struct virtchnl2_add_queues aq = {}; u16 vport_idx = vport->idx; - int size, err; + ssize_t reply_sz; + int size; + + vc_msg = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!vc_msg) + return -ENOMEM; - vport_config = adapter->vport_config[vport_idx]; + vport_config = vport->adapter->vport_config[vport_idx]; + kfree(vport_config->req_qs_chunks); + vport_config->req_qs_chunks = NULL; aq.vport_id = cpu_to_le32(vport->vport_id); aq.num_tx_q = cpu_to_le16(num_tx_q); @@ -2218,47 +2109,33 @@ int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, aq.num_rx_q = cpu_to_le16(num_rx_q); aq.num_rx_bufq = cpu_to_le16(num_rx_bufq); - mutex_lock(&((struct idpf_vport *)vport)->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ADD_QUEUES, - sizeof(struct virtchnl2_add_queues), (u8 *)&aq); - if (err) - goto rel_lock; - - /* We want vport to be const to prevent incidental code changes making - * changes to the vport config. We're making a special exception here - * to discard const to use the virtchnl. - */ - err = idpf_wait_for_event(adapter, (struct idpf_vport *)vport, - IDPF_VC_ADD_QUEUES, IDPF_VC_ADD_QUEUES_ERR); - if (err) - goto rel_lock; - - kfree(vport_config->req_qs_chunks); - vport_config->req_qs_chunks = NULL; + xn_params.vc_op = VIRTCHNL2_OP_ADD_QUEUES; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = &aq; + xn_params.send_buf.iov_len = sizeof(aq); + xn_params.recv_buf.iov_base = vc_msg; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; - vc_msg = (struct virtchnl2_add_queues *)vport->vc_msg; /* compare vc_msg num queues with vport num queues */ if (le16_to_cpu(vc_msg->num_tx_q) != num_tx_q || le16_to_cpu(vc_msg->num_rx_q) != num_rx_q || le16_to_cpu(vc_msg->num_tx_complq) != num_complq || - le16_to_cpu(vc_msg->num_rx_bufq) != num_rx_bufq) { - err = -EINVAL; - goto rel_lock; - } + le16_to_cpu(vc_msg->num_rx_bufq) != num_rx_bufq) + return -EINVAL; size = struct_size(vc_msg, chunks.chunks, le16_to_cpu(vc_msg->chunks.num_chunks)); - vport_config->req_qs_chunks = kmemdup(vc_msg, size, GFP_KERNEL); - if (!vport_config->req_qs_chunks) { - err = -ENOMEM; - goto rel_lock; - } + if (reply_sz < size) + return -EIO; -rel_lock: - mutex_unlock(&((struct idpf_vport *)vport)->vc_buf_lock); + vport_config->req_qs_chunks = kmemdup(vc_msg, size, GFP_KERNEL); + if (!vport_config->req_qs_chunks) + return -ENOMEM; - return err; + return 0; } /** @@ -2270,53 +2147,49 @@ rel_lock: */ int idpf_send_alloc_vectors_msg(struct idpf_adapter *adapter, u16 num_vectors) { - struct virtchnl2_alloc_vectors *alloc_vec, *rcvd_vec; - struct virtchnl2_alloc_vectors ac = { }; + struct virtchnl2_alloc_vectors *rcvd_vec __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; + struct virtchnl2_alloc_vectors ac = {}; + ssize_t reply_sz; u16 num_vchunks; - int size, err; + int size; ac.num_vectors = cpu_to_le16(num_vectors); - mutex_lock(&adapter->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_ALLOC_VECTORS, - sizeof(ac), (u8 *)&ac); - if (err) - goto rel_lock; + rcvd_vec = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!rcvd_vec) + return -ENOMEM; - err = idpf_wait_for_event(adapter, NULL, IDPF_VC_ALLOC_VECTORS, - IDPF_VC_ALLOC_VECTORS_ERR); - if (err) - goto rel_lock; + xn_params.vc_op = VIRTCHNL2_OP_ALLOC_VECTORS; + xn_params.send_buf.iov_base = ∾ + xn_params.send_buf.iov_len = sizeof(ac); + xn_params.recv_buf.iov_base = rcvd_vec; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; - rcvd_vec = (struct virtchnl2_alloc_vectors *)adapter->vc_msg; num_vchunks = le16_to_cpu(rcvd_vec->vchunks.num_vchunks); - size = struct_size(rcvd_vec, vchunks.vchunks, num_vchunks); - if (size > sizeof(adapter->vc_msg)) { - err = -EINVAL; - goto rel_lock; - } + if (reply_sz < size) + return -EIO; + + if (size > IDPF_CTLQ_MAX_BUF_LEN) + return -EINVAL; kfree(adapter->req_vec_chunks); - adapter->req_vec_chunks = NULL; - adapter->req_vec_chunks = kmemdup(adapter->vc_msg, size, GFP_KERNEL); - if (!adapter->req_vec_chunks) { - err = -ENOMEM; - goto rel_lock; - } + adapter->req_vec_chunks = kmemdup(rcvd_vec, size, GFP_KERNEL); + if (!adapter->req_vec_chunks) + return -ENOMEM; - alloc_vec = adapter->req_vec_chunks; - if (le16_to_cpu(alloc_vec->num_vectors) < num_vectors) { + if (le16_to_cpu(adapter->req_vec_chunks->num_vectors) < num_vectors) { kfree(adapter->req_vec_chunks); adapter->req_vec_chunks = NULL; - err = -EINVAL; + return -EINVAL; } -rel_lock: - mutex_unlock(&adapter->vc_buf_lock); - - return err; + return 0; } /** @@ -2329,29 +2202,24 @@ int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter) { struct virtchnl2_alloc_vectors *ac = adapter->req_vec_chunks; struct virtchnl2_vector_chunks *vcs = &ac->vchunks; - int buf_size, err; + struct idpf_vc_xn_params xn_params = {}; + ssize_t reply_sz; + int buf_size; buf_size = struct_size(vcs, vchunks, le16_to_cpu(vcs->num_vchunks)); - mutex_lock(&adapter->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_DEALLOC_VECTORS, buf_size, - (u8 *)vcs); - if (err) - goto rel_lock; - - err = idpf_min_wait_for_event(adapter, NULL, IDPF_VC_DEALLOC_VECTORS, - IDPF_VC_DEALLOC_VECTORS_ERR); - if (err) - goto rel_lock; + xn_params.vc_op = VIRTCHNL2_OP_DEALLOC_VECTORS; + xn_params.send_buf.iov_base = vcs; + xn_params.send_buf.iov_len = buf_size; + xn_params.timeout_ms = IDPF_VC_XN_MIN_TIMEOUT_MSEC; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; kfree(adapter->req_vec_chunks); adapter->req_vec_chunks = NULL; -rel_lock: - mutex_unlock(&adapter->vc_buf_lock); - - return err; + return 0; } /** @@ -2374,25 +2242,18 @@ static int idpf_get_max_vfs(struct idpf_adapter *adapter) */ int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs) { - struct virtchnl2_sriov_vfs_info svi = { }; - int err; + struct virtchnl2_sriov_vfs_info svi = {}; + struct idpf_vc_xn_params xn_params = {}; + ssize_t reply_sz; svi.num_vfs = cpu_to_le16(num_vfs); + xn_params.vc_op = VIRTCHNL2_OP_SET_SRIOV_VFS; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = &svi; + xn_params.send_buf.iov_len = sizeof(svi); + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); - mutex_lock(&adapter->vc_buf_lock); - - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_SRIOV_VFS, - sizeof(svi), (u8 *)&svi); - if (err) - goto rel_lock; - - err = idpf_wait_for_event(adapter, NULL, IDPF_VC_SET_SRIOV_VFS, - IDPF_VC_SET_SRIOV_VFS_ERR); - -rel_lock: - mutex_unlock(&adapter->vc_buf_lock); - - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -2405,10 +2266,10 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) { struct idpf_netdev_priv *np = netdev_priv(vport->netdev); struct rtnl_link_stats64 *netstats = &np->netstats; - struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_vport_stats stats_msg = { }; - struct virtchnl2_vport_stats *stats; - int err; + struct virtchnl2_vport_stats stats_msg = {}; + struct idpf_vc_xn_params xn_params = {}; + ssize_t reply_sz; + /* Don't send get_stats message if the link is down */ if (np->state <= __IDPF_VPORT_DOWN) @@ -2416,46 +2277,38 @@ int idpf_send_get_stats_msg(struct idpf_vport *vport) stats_msg.vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_GET_STATS; + xn_params.send_buf.iov_base = &stats_msg; + xn_params.send_buf.iov_len = sizeof(stats_msg); + xn_params.recv_buf = xn_params.send_buf; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_STATS, - sizeof(struct virtchnl2_vport_stats), - (u8 *)&stats_msg); - if (err) - goto rel_lock; - - err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_STATS, - IDPF_VC_GET_STATS_ERR); - if (err) - goto rel_lock; - - stats = (struct virtchnl2_vport_stats *)vport->vc_msg; + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz < sizeof(stats_msg)) + return -EIO; spin_lock_bh(&np->stats_lock); - netstats->rx_packets = le64_to_cpu(stats->rx_unicast) + - le64_to_cpu(stats->rx_multicast) + - le64_to_cpu(stats->rx_broadcast); - netstats->rx_bytes = le64_to_cpu(stats->rx_bytes); - netstats->rx_dropped = le64_to_cpu(stats->rx_discards); - netstats->rx_over_errors = le64_to_cpu(stats->rx_overflow_drop); - netstats->rx_length_errors = le64_to_cpu(stats->rx_invalid_frame_length); - - netstats->tx_packets = le64_to_cpu(stats->tx_unicast) + - le64_to_cpu(stats->tx_multicast) + - le64_to_cpu(stats->tx_broadcast); - netstats->tx_bytes = le64_to_cpu(stats->tx_bytes); - netstats->tx_errors = le64_to_cpu(stats->tx_errors); - netstats->tx_dropped = le64_to_cpu(stats->tx_discards); - - vport->port_stats.vport_stats = *stats; + netstats->rx_packets = le64_to_cpu(stats_msg.rx_unicast) + + le64_to_cpu(stats_msg.rx_multicast) + + le64_to_cpu(stats_msg.rx_broadcast); + netstats->tx_packets = le64_to_cpu(stats_msg.tx_unicast) + + le64_to_cpu(stats_msg.tx_multicast) + + le64_to_cpu(stats_msg.tx_broadcast); + netstats->rx_bytes = le64_to_cpu(stats_msg.rx_bytes); + netstats->tx_bytes = le64_to_cpu(stats_msg.tx_bytes); + netstats->rx_errors = le64_to_cpu(stats_msg.rx_errors); + netstats->tx_errors = le64_to_cpu(stats_msg.tx_errors); + netstats->rx_dropped = le64_to_cpu(stats_msg.rx_discards); + netstats->tx_dropped = le64_to_cpu(stats_msg.tx_discards); + + vport->port_stats.vport_stats = stats_msg; spin_unlock_bh(&np->stats_lock); -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - - return err; + return 0; } /** @@ -2467,70 +2320,70 @@ rel_lock: */ int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get) { - struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_rss_lut *recv_rl; + struct virtchnl2_rss_lut *recv_rl __free(kfree) = NULL; + struct virtchnl2_rss_lut *rl __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; struct idpf_rss_data *rss_data; - struct virtchnl2_rss_lut *rl; int buf_size, lut_buf_size; - int i, err; + ssize_t reply_sz; + int i; - rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + rss_data = + &vport->adapter->vport_config[vport->idx]->user_config.rss_data; buf_size = struct_size(rl, lut, rss_data->rss_lut_size); rl = kzalloc(buf_size, GFP_KERNEL); if (!rl) return -ENOMEM; rl->vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); - if (!get) { + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = rl; + xn_params.send_buf.iov_len = buf_size; + + if (get) { + recv_rl = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!recv_rl) + return -ENOMEM; + xn_params.vc_op = VIRTCHNL2_OP_GET_RSS_LUT; + xn_params.recv_buf.iov_base = recv_rl; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; + } else { rl->lut_entries = cpu_to_le16(rss_data->rss_lut_size); for (i = 0; i < rss_data->rss_lut_size; i++) rl->lut[i] = cpu_to_le32(rss_data->rss_lut[i]); - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_RSS_LUT, - buf_size, (u8 *)rl); - if (err) - goto free_mem; - - err = idpf_wait_for_event(adapter, vport, IDPF_VC_SET_RSS_LUT, - IDPF_VC_SET_RSS_LUT_ERR); - - goto free_mem; + xn_params.vc_op = VIRTCHNL2_OP_SET_RSS_LUT; } + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (!get) + return 0; + if (reply_sz < sizeof(struct virtchnl2_rss_lut)) + return -EIO; - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_RSS_LUT, - buf_size, (u8 *)rl); - if (err) - goto free_mem; + lut_buf_size = le16_to_cpu(recv_rl->lut_entries) * sizeof(u32); + if (reply_sz < lut_buf_size) + return -EIO; - err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_RSS_LUT, - IDPF_VC_GET_RSS_LUT_ERR); - if (err) - goto free_mem; - - recv_rl = (struct virtchnl2_rss_lut *)vport->vc_msg; + /* size didn't change, we can reuse existing lut buf */ if (rss_data->rss_lut_size == le16_to_cpu(recv_rl->lut_entries)) goto do_memcpy; rss_data->rss_lut_size = le16_to_cpu(recv_rl->lut_entries); kfree(rss_data->rss_lut); - lut_buf_size = rss_data->rss_lut_size * sizeof(u32); rss_data->rss_lut = kzalloc(lut_buf_size, GFP_KERNEL); if (!rss_data->rss_lut) { rss_data->rss_lut_size = 0; - err = -ENOMEM; - goto free_mem; + return -ENOMEM; } do_memcpy: - memcpy(rss_data->rss_lut, vport->vc_msg, rss_data->rss_lut_size); -free_mem: - mutex_unlock(&vport->vc_buf_lock); - kfree(rl); + memcpy(rss_data->rss_lut, recv_rl->lut, rss_data->rss_lut_size); - return err; + return 0; } /** @@ -2542,68 +2395,70 @@ free_mem: */ int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get) { - struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_rss_key *recv_rk; + struct virtchnl2_rss_key *recv_rk __free(kfree) = NULL; + struct virtchnl2_rss_key *rk __free(kfree) = NULL; + struct idpf_vc_xn_params xn_params = {}; struct idpf_rss_data *rss_data; - struct virtchnl2_rss_key *rk; - int i, buf_size, err; + ssize_t reply_sz; + int i, buf_size; + u16 key_size; - rss_data = &adapter->vport_config[vport->idx]->user_config.rss_data; + rss_data = + &vport->adapter->vport_config[vport->idx]->user_config.rss_data; buf_size = struct_size(rk, key_flex, rss_data->rss_key_size); rk = kzalloc(buf_size, GFP_KERNEL); if (!rk) return -ENOMEM; rk->vport_id = cpu_to_le32(vport->vport_id); - mutex_lock(&vport->vc_buf_lock); - + xn_params.send_buf.iov_base = rk; + xn_params.send_buf.iov_len = buf_size; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; if (get) { - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_RSS_KEY, - buf_size, (u8 *)rk); - if (err) - goto error; - - err = idpf_wait_for_event(adapter, vport, IDPF_VC_GET_RSS_KEY, - IDPF_VC_GET_RSS_KEY_ERR); - if (err) - goto error; - - recv_rk = (struct virtchnl2_rss_key *)vport->vc_msg; - if (rss_data->rss_key_size != - le16_to_cpu(recv_rk->key_len)) { - rss_data->rss_key_size = - min_t(u16, NETDEV_RSS_KEY_LEN, - le16_to_cpu(recv_rk->key_len)); - kfree(rss_data->rss_key); - rss_data->rss_key = kzalloc(rss_data->rss_key_size, - GFP_KERNEL); - if (!rss_data->rss_key) { - rss_data->rss_key_size = 0; - err = -ENOMEM; - goto error; - } - } - memcpy(rss_data->rss_key, recv_rk->key_flex, - rss_data->rss_key_size); + recv_rk = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); + if (!recv_rk) + return -ENOMEM; + + xn_params.vc_op = VIRTCHNL2_OP_GET_RSS_KEY; + xn_params.recv_buf.iov_base = recv_rk; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; } else { rk->key_len = cpu_to_le16(rss_data->rss_key_size); for (i = 0; i < rss_data->rss_key_size; i++) rk->key_flex[i] = rss_data->rss_key[i]; - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_SET_RSS_KEY, - buf_size, (u8 *)rk); - if (err) - goto error; + xn_params.vc_op = VIRTCHNL2_OP_SET_RSS_KEY; + } + + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (!get) + return 0; + if (reply_sz < sizeof(struct virtchnl2_rss_key)) + return -EIO; + + key_size = min_t(u16, NETDEV_RSS_KEY_LEN, + le16_to_cpu(recv_rk->key_len)); + if (reply_sz < key_size) + return -EIO; - err = idpf_wait_for_event(adapter, vport, IDPF_VC_SET_RSS_KEY, - IDPF_VC_SET_RSS_KEY_ERR); + /* key len didn't change, reuse existing buf */ + if (rss_data->rss_key_size == key_size) + goto do_memcpy; + + rss_data->rss_key_size = key_size; + kfree(rss_data->rss_key); + rss_data->rss_key = kzalloc(key_size, GFP_KERNEL); + if (!rss_data->rss_key) { + rss_data->rss_key_size = 0; + return -ENOMEM; } -error: - mutex_unlock(&vport->vc_buf_lock); - kfree(rk); +do_memcpy: + memcpy(rss_data->rss_key, recv_rk->key_flex, rss_data->rss_key_size); - return err; + return 0; } /** @@ -2655,13 +2510,15 @@ static void idpf_fill_ptype_lookup(struct idpf_rx_ptype_decoded *ptype, */ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) { + struct virtchnl2_get_ptype_info *get_ptype_info __free(kfree) = NULL; + struct virtchnl2_get_ptype_info *ptype_info __free(kfree) = NULL; struct idpf_rx_ptype_decoded *ptype_lkup = vport->rx_ptype_lkup; - struct virtchnl2_get_ptype_info get_ptype_info; int max_ptype, ptypes_recvd = 0, ptype_offset; struct idpf_adapter *adapter = vport->adapter; - struct virtchnl2_get_ptype_info *ptype_info; + struct idpf_vc_xn_params xn_params = {}; u16 next_ptype_id = 0; - int err = 0, i, j, k; + ssize_t reply_sz; + int i, j, k; if (idpf_is_queue_model_split(vport->rxq_model)) max_ptype = IDPF_RX_MAX_PTYPE; @@ -2670,43 +2527,44 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) memset(vport->rx_ptype_lkup, 0, sizeof(vport->rx_ptype_lkup)); + get_ptype_info = kzalloc(sizeof(*get_ptype_info), GFP_KERNEL); + if (!get_ptype_info) + return -ENOMEM; + ptype_info = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL); if (!ptype_info) return -ENOMEM; - mutex_lock(&adapter->vc_buf_lock); + xn_params.vc_op = VIRTCHNL2_OP_GET_PTYPE_INFO; + xn_params.send_buf.iov_base = get_ptype_info; + xn_params.send_buf.iov_len = sizeof(*get_ptype_info); + xn_params.recv_buf.iov_base = ptype_info; + xn_params.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; while (next_ptype_id < max_ptype) { - get_ptype_info.start_ptype_id = cpu_to_le16(next_ptype_id); + get_ptype_info->start_ptype_id = cpu_to_le16(next_ptype_id); if ((next_ptype_id + IDPF_RX_MAX_PTYPES_PER_BUF) > max_ptype) - get_ptype_info.num_ptypes = + get_ptype_info->num_ptypes = cpu_to_le16(max_ptype - next_ptype_id); else - get_ptype_info.num_ptypes = + get_ptype_info->num_ptypes = cpu_to_le16(IDPF_RX_MAX_PTYPES_PER_BUF); - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_GET_PTYPE_INFO, - sizeof(struct virtchnl2_get_ptype_info), - (u8 *)&get_ptype_info); - if (err) - goto vc_buf_unlock; - - err = idpf_wait_for_event(adapter, NULL, IDPF_VC_GET_PTYPE_INFO, - IDPF_VC_GET_PTYPE_INFO_ERR); - if (err) - goto vc_buf_unlock; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; - memcpy(ptype_info, adapter->vc_msg, IDPF_CTLQ_MAX_BUF_LEN); + if (reply_sz < IDPF_CTLQ_MAX_BUF_LEN) + return -EIO; ptypes_recvd += le16_to_cpu(ptype_info->num_ptypes); - if (ptypes_recvd > max_ptype) { - err = -EINVAL; - goto vc_buf_unlock; - } + if (ptypes_recvd > max_ptype) + return -EINVAL; - next_ptype_id = le16_to_cpu(get_ptype_info.start_ptype_id) + - le16_to_cpu(get_ptype_info.num_ptypes); + next_ptype_id = le16_to_cpu(get_ptype_info->start_ptype_id) + + le16_to_cpu(get_ptype_info->num_ptypes); ptype_offset = IDPF_RX_PTYPE_HDR_SZ; @@ -2719,17 +2577,13 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) ((u8 *)ptype_info + ptype_offset); ptype_offset += IDPF_GET_PTYPE_SIZE(ptype); - if (ptype_offset > IDPF_CTLQ_MAX_BUF_LEN) { - err = -EINVAL; - goto vc_buf_unlock; - } + if (ptype_offset > IDPF_CTLQ_MAX_BUF_LEN) + return -EINVAL; /* 0xFFFF indicates end of ptypes */ if (le16_to_cpu(ptype->ptype_id_10) == - IDPF_INVALID_PTYPE_ID) { - err = 0; - goto vc_buf_unlock; - } + IDPF_INVALID_PTYPE_ID) + return 0; if (idpf_is_queue_model_split(vport->rxq_model)) k = le16_to_cpu(ptype->ptype_id_10); @@ -2857,11 +2711,7 @@ int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport) } } -vc_buf_unlock: - mutex_unlock(&adapter->vc_buf_lock); - kfree(ptype_info); - - return err; + return 0; } /** @@ -2873,27 +2723,20 @@ vc_buf_unlock: */ int idpf_send_ena_dis_loopback_msg(struct idpf_vport *vport) { + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_loopback loopback; - int err; + ssize_t reply_sz; loopback.vport_id = cpu_to_le32(vport->vport_id); loopback.enable = idpf_is_feature_ena(vport, NETIF_F_LOOPBACK); - mutex_lock(&vport->vc_buf_lock); - - err = idpf_send_mb_msg(vport->adapter, VIRTCHNL2_OP_LOOPBACK, - sizeof(loopback), (u8 *)&loopback); - if (err) - goto rel_lock; + xn_params.vc_op = VIRTCHNL2_OP_LOOPBACK; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = &loopback; + xn_params.send_buf.iov_len = sizeof(loopback); + reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params); - err = idpf_wait_for_event(vport->adapter, vport, - IDPF_VC_LOOPBACK_STATE, - IDPF_VC_LOOPBACK_STATE_ERR); - -rel_lock: - mutex_unlock(&vport->vc_buf_lock); - - return err; + return reply_sz < 0 ? reply_sz : 0; } /** @@ -2958,7 +2801,7 @@ int idpf_init_dflt_mbx(struct idpf_adapter *adapter) return -ENOENT; } - adapter->state = __IDPF_STARTUP; + adapter->state = __IDPF_VER_CHECK; return 0; } @@ -3055,35 +2898,42 @@ int idpf_vc_core_init(struct idpf_adapter *adapter) u16 num_max_vports; int err = 0; + if (!adapter->vcxn_mngr) { + adapter->vcxn_mngr = kzalloc(sizeof(*adapter->vcxn_mngr), GFP_KERNEL); + if (!adapter->vcxn_mngr) { + err = -ENOMEM; + goto init_failed; + } + } + idpf_vc_xn_init(adapter->vcxn_mngr); + while (adapter->state != __IDPF_INIT_SW) { switch (adapter->state) { - case __IDPF_STARTUP: - if (idpf_send_ver_msg(adapter)) - goto init_failed; - adapter->state = __IDPF_VER_CHECK; - goto restart; case __IDPF_VER_CHECK: - err = idpf_recv_ver_msg(adapter); - if (err == -EIO) { - return err; - } else if (err == -EAGAIN) { - adapter->state = __IDPF_STARTUP; + err = idpf_send_ver_msg(adapter); + switch (err) { + case 0: + /* success, move state machine forward */ + adapter->state = __IDPF_GET_CAPS; + fallthrough; + case -EAGAIN: goto restart; - } else if (err) { + default: + /* Something bad happened, try again but only a + * few times. + */ goto init_failed; } - if (idpf_send_get_caps_msg(adapter)) - goto init_failed; - adapter->state = __IDPF_GET_CAPS; - goto restart; case __IDPF_GET_CAPS: - if (idpf_recv_get_caps_msg(adapter)) + err = idpf_send_get_caps_msg(adapter); + if (err) goto init_failed; adapter->state = __IDPF_INIT_SW; break; default: dev_err(&adapter->pdev->dev, "Device is in bad state: %d\n", adapter->state); + err = -EINVAL; goto init_failed; } break; @@ -3142,7 +2992,9 @@ restart: queue_delayed_work(adapter->init_wq, &adapter->init_task, msecs_to_jiffies(5 * (adapter->pdev->devfn & 0x07))); - goto no_err; + set_bit(IDPF_VC_CORE_INIT, adapter->flags); + + return 0; err_intr_req: cancel_delayed_work_sync(&adapter->serv_task); @@ -3151,7 +3003,6 @@ err_intr_req: err_netdev_alloc: kfree(adapter->vports); adapter->vports = NULL; -no_err: return err; init_failed: @@ -3168,7 +3019,9 @@ init_failed: * register writes might not have taken effect. Retry to initialize * the mailbox again */ - adapter->state = __IDPF_STARTUP; + adapter->state = __IDPF_VER_CHECK; + if (adapter->vcxn_mngr) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); idpf_deinit_dflt_mbx(adapter); set_bit(IDPF_HR_DRV_LOAD, adapter->flags); queue_delayed_work(adapter->vc_event_wq, &adapter->vc_event_task, @@ -3184,29 +3037,22 @@ init_failed: */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { - int i; + if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) + return; + idpf_vc_xn_shutdown(adapter->vcxn_mngr); idpf_deinit_task(adapter); idpf_intr_rel(adapter); - /* Set all bits as we dont know on which vc_state the vhnl_wq is - * waiting on and wakeup the virtchnl workqueue even if it is waiting - * for the response as we are going down - */ - for (i = 0; i < IDPF_VC_NBITS; i++) - set_bit(i, adapter->vc_state); - wake_up(&adapter->vchnl_wq); cancel_delayed_work_sync(&adapter->serv_task); cancel_delayed_work_sync(&adapter->mbx_task); idpf_vport_params_buf_rel(adapter); - /* Clear all the bits */ - for (i = 0; i < IDPF_VC_NBITS; i++) - clear_bit(i, adapter->vc_state); - kfree(adapter->vports); adapter->vports = NULL; + + clear_bit(IDPF_VC_CORE_INIT, adapter->flags); } /** @@ -3622,6 +3468,75 @@ u32 idpf_get_vport_id(struct idpf_vport *vport) } /** + * idpf_mac_filter_async_handler - Async callback for mac filters + * @adapter: private data struct + * @xn: transaction for message + * @ctlq_msg: received message + * + * In some scenarios driver can't sleep and wait for a reply (e.g.: stack is + * holding rtnl_lock) when adding a new mac filter. It puts us in a difficult + * situation to deal with errors returned on the reply. The best we can + * ultimately do is remove it from our list of mac filters and report the + * error. + */ +static int idpf_mac_filter_async_handler(struct idpf_adapter *adapter, + struct idpf_vc_xn *xn, + const struct idpf_ctlq_msg *ctlq_msg) +{ + struct virtchnl2_mac_addr_list *ma_list; + struct idpf_vport_config *vport_config; + struct virtchnl2_mac_addr *mac_addr; + struct idpf_mac_filter *f, *tmp; + struct list_head *ma_list_head; + struct idpf_vport *vport; + u16 num_entries; + int i; + + /* if success we're done, we're only here if something bad happened */ + if (!ctlq_msg->cookie.mbx.chnl_retval) + return 0; + + /* make sure at least struct is there */ + if (xn->reply_sz < sizeof(*ma_list)) + goto invalid_payload; + + ma_list = ctlq_msg->ctx.indirect.payload->va; + mac_addr = ma_list->mac_addr_list; + num_entries = le16_to_cpu(ma_list->num_mac_addr); + /* we should have received a buffer at least this big */ + if (xn->reply_sz < struct_size(ma_list, mac_addr_list, num_entries)) + goto invalid_payload; + + vport = idpf_vid_to_vport(adapter, le32_to_cpu(ma_list->vport_id)); + if (!vport) + goto invalid_payload; + + vport_config = adapter->vport_config[le32_to_cpu(ma_list->vport_id)]; + ma_list_head = &vport_config->user_config.mac_filter_list; + + /* We can't do much to reconcile bad filters at this point, however we + * should at least remove them from our list one way or the other so we + * have some idea what good filters we have. + */ + spin_lock_bh(&vport_config->mac_filter_list_lock); + list_for_each_entry_safe(f, tmp, ma_list_head, list) + for (i = 0; i < num_entries; i++) + if (ether_addr_equal(mac_addr[i].addr, f->macaddr)) + list_del(&f->list); + spin_unlock_bh(&vport_config->mac_filter_list_lock); + dev_err_ratelimited(&adapter->pdev->dev, "Received error sending MAC filter request (op %d)\n", + xn->vc_op); + + return 0; + +invalid_payload: + dev_err_ratelimited(&adapter->pdev->dev, "Received invalid MAC filter payload (op %d) (len %zd)\n", + xn->vc_op, xn->reply_sz); + + return -EINVAL; +} + +/** * idpf_add_del_mac_filters - Add/del mac filters * @vport: Virtual port data structure * @np: Netdev private structure @@ -3634,17 +3549,21 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, struct idpf_netdev_priv *np, bool add, bool async) { - struct virtchnl2_mac_addr_list *ma_list = NULL; + struct virtchnl2_mac_addr_list *ma_list __free(kfree) = NULL; + struct virtchnl2_mac_addr *mac_addr __free(kfree) = NULL; struct idpf_adapter *adapter = np->adapter; + struct idpf_vc_xn_params xn_params = {}; struct idpf_vport_config *vport_config; - enum idpf_vport_config_flags mac_flag; - struct pci_dev *pdev = adapter->pdev; - enum idpf_vport_vc_state vc, vc_err; - struct virtchnl2_mac_addr *mac_addr; - struct idpf_mac_filter *f, *tmp; u32 num_msgs, total_filters = 0; - int i = 0, k, err = 0; - u32 vop; + struct idpf_mac_filter *f; + ssize_t reply_sz; + int i = 0, k; + + xn_params.vc_op = add ? VIRTCHNL2_OP_ADD_MAC_ADDR : + VIRTCHNL2_OP_DEL_MAC_ADDR; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.async = async; + xn_params.async_handler = idpf_mac_filter_async_handler; vport_config = adapter->vport_config[np->vport_idx]; spin_lock_bh(&vport_config->mac_filter_list_lock); @@ -3668,13 +3587,13 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, mac_addr = kcalloc(total_filters, sizeof(struct virtchnl2_mac_addr), GFP_ATOMIC); if (!mac_addr) { - err = -ENOMEM; spin_unlock_bh(&vport_config->mac_filter_list_lock); - goto error; + + return -ENOMEM; } - list_for_each_entry_safe(f, tmp, &vport_config->user_config.mac_filter_list, - list) { + list_for_each_entry(f, &vport_config->user_config.mac_filter_list, + list) { if (add && f->add) { ether_addr_copy(mac_addr[i].addr, f->macaddr); i++; @@ -3693,26 +3612,11 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, spin_unlock_bh(&vport_config->mac_filter_list_lock); - if (add) { - vop = VIRTCHNL2_OP_ADD_MAC_ADDR; - vc = IDPF_VC_ADD_MAC_ADDR; - vc_err = IDPF_VC_ADD_MAC_ADDR_ERR; - mac_flag = IDPF_VPORT_ADD_MAC_REQ; - } else { - vop = VIRTCHNL2_OP_DEL_MAC_ADDR; - vc = IDPF_VC_DEL_MAC_ADDR; - vc_err = IDPF_VC_DEL_MAC_ADDR_ERR; - mac_flag = IDPF_VPORT_DEL_MAC_REQ; - } - /* Chunk up the filters into multiple messages to avoid * sending a control queue message buffer that is too large */ num_msgs = DIV_ROUND_UP(total_filters, IDPF_NUM_FILTERS_PER_MSG); - if (!async) - mutex_lock(&vport->vc_buf_lock); - for (i = 0, k = 0; i < num_msgs; i++) { u32 entries_size, buf_size, num_entries; @@ -3724,10 +3628,8 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, if (!ma_list || num_entries != IDPF_NUM_FILTERS_PER_MSG) { kfree(ma_list); ma_list = kzalloc(buf_size, GFP_ATOMIC); - if (!ma_list) { - err = -ENOMEM; - goto list_prep_error; - } + if (!ma_list) + return -ENOMEM; } else { memset(ma_list, 0, buf_size); } @@ -3736,34 +3638,17 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, ma_list->num_mac_addr = cpu_to_le16(num_entries); memcpy(ma_list->mac_addr_list, &mac_addr[k], entries_size); - if (async) - set_bit(mac_flag, vport_config->flags); - - err = idpf_send_mb_msg(adapter, vop, buf_size, (u8 *)ma_list); - if (err) - goto mbx_error; - - if (!async) { - err = idpf_wait_for_event(adapter, vport, vc, vc_err); - if (err) - goto mbx_error; - } + xn_params.send_buf.iov_base = ma_list; + xn_params.send_buf.iov_len = buf_size; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; k += num_entries; total_filters -= num_entries; } -mbx_error: - if (!async) - mutex_unlock(&vport->vc_buf_lock); - kfree(ma_list); -list_prep_error: - kfree(mac_addr); -error: - if (err) - dev_err(&pdev->dev, "Failed to add or del mac filters %d", err); - - return err; + return 0; } /** @@ -3780,9 +3665,10 @@ int idpf_set_promiscuous(struct idpf_adapter *adapter, struct idpf_vport_user_config_data *config_data, u32 vport_id) { + struct idpf_vc_xn_params xn_params = {}; struct virtchnl2_promisc_info vpi; + ssize_t reply_sz; u16 flags = 0; - int err; if (test_bit(__IDPF_PROMISC_UC, config_data->user_flags)) flags |= VIRTCHNL2_UNICAST_PROMISC; @@ -3792,9 +3678,13 @@ int idpf_set_promiscuous(struct idpf_adapter *adapter, vpi.vport_id = cpu_to_le32(vport_id); vpi.flags = cpu_to_le16(flags); - err = idpf_send_mb_msg(adapter, VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE, - sizeof(struct virtchnl2_promisc_info), - (u8 *)&vpi); + xn_params.vc_op = VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.send_buf.iov_base = &vpi; + xn_params.send_buf.iov_len = sizeof(vpi); + /* setting promiscuous is only ever done asynchronously */ + xn_params.async = true; + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); - return err; + return reply_sz < 0 ? reply_sz : 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h new file mode 100644 index 000000000000..83da5d8da56b --- /dev/null +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef _IDPF_VIRTCHNL_H_ +#define _IDPF_VIRTCHNL_H_ + +struct idpf_adapter; +struct idpf_netdev_priv; +struct idpf_vec_regs; +struct idpf_vport; +struct idpf_vport_max_q; +struct idpf_vport_user_config_data; + +int idpf_init_dflt_mbx(struct idpf_adapter *adapter); +void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter); +int idpf_vc_core_init(struct idpf_adapter *adapter); +void idpf_vc_core_deinit(struct idpf_adapter *adapter); + +int idpf_get_reg_intr_vecs(struct idpf_vport *vport, + struct idpf_vec_regs *reg_vals); +int idpf_queue_reg_init(struct idpf_vport *vport); +int idpf_vport_queue_ids_init(struct idpf_vport *vport); + +int idpf_recv_mb_msg(struct idpf_adapter *adapter); +int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, + u16 msg_size, u8 *msg, u16 cookie); + +void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q); +u32 idpf_get_vport_id(struct idpf_vport *vport); +int idpf_send_create_vport_msg(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +int idpf_send_destroy_vport_msg(struct idpf_vport *vport); +int idpf_send_enable_vport_msg(struct idpf_vport *vport); +int idpf_send_disable_vport_msg(struct idpf_vport *vport); + +int idpf_vport_adjust_qs(struct idpf_vport *vport); +int idpf_vport_alloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +void idpf_vport_dealloc_max_qs(struct idpf_adapter *adapter, + struct idpf_vport_max_q *max_q); +int idpf_send_add_queues_msg(const struct idpf_vport *vport, u16 num_tx_q, + u16 num_complq, u16 num_rx_q, u16 num_rx_bufq); +int idpf_send_delete_queues_msg(struct idpf_vport *vport); +int idpf_send_enable_queues_msg(struct idpf_vport *vport); +int idpf_send_disable_queues_msg(struct idpf_vport *vport); +int idpf_send_config_queues_msg(struct idpf_vport *vport); + +int idpf_vport_alloc_vec_indexes(struct idpf_vport *vport); +int idpf_get_vec_ids(struct idpf_adapter *adapter, + u16 *vecids, int num_vecids, + struct virtchnl2_vector_chunks *chunks); +int idpf_send_alloc_vectors_msg(struct idpf_adapter *adapter, u16 num_vectors); +int idpf_send_dealloc_vectors_msg(struct idpf_adapter *adapter); +int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map); + +int idpf_add_del_mac_filters(struct idpf_vport *vport, + struct idpf_netdev_priv *np, + bool add, bool async); +int idpf_set_promiscuous(struct idpf_adapter *adapter, + struct idpf_vport_user_config_data *config_data, + u32 vport_id); +int idpf_check_supported_desc_ids(struct idpf_vport *vport); +int idpf_send_get_rx_ptype_msg(struct idpf_vport *vport); +int idpf_send_ena_dis_loopback_msg(struct idpf_vport *vport); +int idpf_send_get_stats_msg(struct idpf_vport *vport); +int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs); +int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get); +int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get); + +#endif /* _IDPF_VIRTCHNL_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index cebb44f51d5f..518298bbdadc 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -202,7 +202,7 @@ static struct notifier_block dca_notifier = { #endif #ifdef CONFIG_PCI_IOV static unsigned int max_vfs; -module_param(max_vfs, uint, 0); +module_param(max_vfs, uint, 0444); MODULE_PARM_DESC(max_vfs, "Maximum number of virtual functions to allocate per physical function"); #endif /* CONFIG_PCI_IOV */ @@ -2538,7 +2538,7 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IGB_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index a4d4f00e6a87..b0cf310e6f7b 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2655,7 +2655,7 @@ igbvf_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IGBVF_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index cfa6baccec55..90316dc58630 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -570,7 +570,6 @@ struct igc_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; - struct net_device poll_dev; /* for dynamic allocation of rings associated with this q_vector */ struct igc_ring ring[] ____cacheline_internodealigned_in_smp; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 3af52d238f3b..14924dd8a4b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5277,7 +5277,7 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | @@ -6488,7 +6488,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; @@ -6504,16 +6504,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6521,7 +6520,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index e0c300fe5cee..cdaf087b4e85 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -334,7 +334,9 @@ static int ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core1) { *speed = IXGBE_LINK_SPEED_1GB_FULL; *autoneg = true; return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 633bac1543dd..6e6e6f1847b6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -349,6 +349,8 @@ static int ixgbe_get_link_ksettings(struct net_device *netdev, case ixgbe_sfp_type_1g_sx_core1: case ixgbe_sfp_type_1g_lx_core0: case ixgbe_sfp_type_1g_lx_core1: + case ixgbe_sfp_type_1g_bx_core0: + case ixgbe_sfp_type_1g_bx_core1: ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); ethtool_link_ksettings_add_link_mode(cmd, advertising, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index e23c3614fb10..f985252c8c8d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -153,7 +153,7 @@ MODULE_PARM_DESC(max_vfs, #endif /* CONFIG_PCI_IOV */ static bool allow_unsupported_sfp; -module_param(allow_unsupported_sfp, bool, 0); +module_param(allow_unsupported_sfp, bool, 0444); MODULE_PARM_DESC(allow_unsupported_sfp, "Allow unsupported and untested SFP+ modules on 82599-based adapters"); @@ -1106,6 +1106,44 @@ static int ixgbe_tx_maxrate(struct net_device *netdev, } /** + * ixgbe_update_tx_ring_stats - Update Tx ring specific counters + * @tx_ring: ring to update + * @q_vector: queue vector ring belongs to + * @pkts: number of processed packets + * @bytes: number of processed bytes + */ +void ixgbe_update_tx_ring_stats(struct ixgbe_ring *tx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes) +{ + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += bytes; + tx_ring->stats.packets += pkts; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += bytes; + q_vector->tx.total_packets += pkts; +} + +/** + * ixgbe_update_rx_ring_stats - Update Rx ring specific counters + * @rx_ring: ring to update + * @q_vector: queue vector ring belongs to + * @pkts: number of processed packets + * @bytes: number of processed bytes + */ +void ixgbe_update_rx_ring_stats(struct ixgbe_ring *rx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes) +{ + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.bytes += bytes; + rx_ring->stats.packets += pkts; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_bytes += bytes; + q_vector->rx.total_packets += pkts; +} + +/** * ixgbe_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: structure containing interrupt and ring information * @tx_ring: tx ring to clean @@ -1207,12 +1245,8 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->stats.bytes += total_bytes; - tx_ring->stats.packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; + ixgbe_update_tx_ring_stats(tx_ring, q_vector, total_packets, + total_bytes); adapter->tx_ipsec += total_ipsec; if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { @@ -2429,12 +2463,8 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, ixgbe_xdp_ring_update_tail_locked(ring); } - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->stats.packets += total_rx_packets; - rx_ring->stats.bytes += total_rx_bytes; - u64_stats_update_end(&rx_ring->syncp); - q_vector->rx.total_packets += total_rx_packets; - q_vector->rx.total_bytes += total_rx_bytes; + ixgbe_update_rx_ring_stats(rx_ring, q_vector, total_rx_packets, + total_rx_bytes); return total_rx_packets; } @@ -2939,8 +2969,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -10205,7 +10235,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | @@ -10525,6 +10555,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) } /** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + +/** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure * @ring: ring index @@ -10540,6 +10608,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10548,9 +10621,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10578,9 +10648,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10589,6 +10656,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 75e9453331ed..07eaa3c3f4d3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1532,6 +1532,7 @@ int ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; struct ixgbe_adapter *adapter = hw->back; u8 oui_bytes[3] = {0, 0, 0}; + u8 bitrate_nominal = 0; u8 comp_codes_10g = 0; u8 comp_codes_1g = 0; u16 enforce_sfp = 0; @@ -1576,7 +1577,12 @@ int ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_CABLE_TECHNOLOGY, &cable_tech); + if (status) + goto err_read_i2c_eeprom; + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_BITRATE_NOMINAL, + &bitrate_nominal); if (status) goto err_read_i2c_eeprom; @@ -1659,6 +1665,18 @@ int ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) else hw->phy.sfp_type = ixgbe_sfp_type_1g_lx_core1; + /* Support only Ethernet 1000BASE-BX10, checking the Bit Rate + * Nominal Value as per SFF-8472 by convention 1.25 Gb/s should + * be rounded up to 0Dh (13 in units of 100 MBd) for 1000BASE-BX + */ + } else if ((comp_codes_1g & IXGBE_SFF_BASEBX10_CAPABLE) && + (bitrate_nominal == 0xD)) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_bx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_bx_core1; } else { hw->phy.sfp_type = ixgbe_sfp_type_unknown; } @@ -1747,7 +1765,9 @@ int ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core1)) { hw->phy.type = ixgbe_phy_sfp_unsupported; return -EOPNOTSUPP; } @@ -1763,7 +1783,9 @@ int ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_bx_core1)) { /* Make sure we're a supported PHY type */ if (hw->phy.type == ixgbe_phy_sfp_intel) return 0; @@ -1999,12 +2021,14 @@ int ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, if (sfp_type == ixgbe_sfp_type_da_act_lmt_core0 || sfp_type == ixgbe_sfp_type_1g_lx_core0 || sfp_type == ixgbe_sfp_type_1g_cu_core0 || - sfp_type == ixgbe_sfp_type_1g_sx_core0) + sfp_type == ixgbe_sfp_type_1g_sx_core0 || + sfp_type == ixgbe_sfp_type_1g_bx_core0) sfp_type = ixgbe_sfp_type_srlr_core0; else if (sfp_type == ixgbe_sfp_type_da_act_lmt_core1 || sfp_type == ixgbe_sfp_type_1g_lx_core1 || sfp_type == ixgbe_sfp_type_1g_cu_core1 || - sfp_type == ixgbe_sfp_type_1g_sx_core1) + sfp_type == ixgbe_sfp_type_1g_sx_core1 || + sfp_type == ixgbe_sfp_type_1g_bx_core1) sfp_type = ixgbe_sfp_type_srlr_core1; /* Read offset to PHY init contents */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index beedcb7bec0d..14aa2ca51f70 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -17,6 +17,7 @@ #define IXGBE_SFF_1GBE_COMP_CODES 0x6 #define IXGBE_SFF_10GBE_COMP_CODES 0x3 #define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 +#define IXGBE_SFF_BITRATE_NOMINAL 0xC #define IXGBE_SFF_CABLE_SPEC_COMP 0x3C #define IXGBE_SFF_SFF_8472_SWAP 0x5C #define IXGBE_SFF_SFF_8472_COMP 0x5E @@ -39,6 +40,7 @@ #define IXGBE_SFF_1GBASESX_CAPABLE 0x1 #define IXGBE_SFF_1GBASELX_CAPABLE 0x2 #define IXGBE_SFF_1GBASET_CAPABLE 0x8 +#define IXGBE_SFF_BASEBX10_CAPABLE 0x64 #define IXGBE_SFF_10GBASESR_CAPABLE 0x10 #define IXGBE_SFF_10GBASELR_CAPABLE 0x20 #define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index f1f69ce67420..78deea5ec536 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -46,4 +46,11 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); +void ixgbe_update_tx_ring_stats(struct ixgbe_ring *tx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes); +void ixgbe_update_rx_ring_stats(struct ixgbe_ring *rx_ring, + struct ixgbe_q_vector *q_vector, u64 pkts, + u64 bytes); + #endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index d44c58130be2..ed440dd0c4f9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3210,6 +3210,9 @@ enum ixgbe_sfp_type { ixgbe_sfp_type_1g_sx_core1 = 12, ixgbe_sfp_type_1g_lx_core0 = 13, ixgbe_sfp_type_1g_lx_core1 = 14, + ixgbe_sfp_type_1g_bx_core0 = 15, + ixgbe_sfp_type_1g_bx_core1 = 16, + ixgbe_sfp_type_not_present = 0xFFFE, ixgbe_sfp_type_unknown = 0xFFFF }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 59798bc33298..d34d715c59eb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -359,12 +359,8 @@ construct_skb: ixgbe_xdp_ring_update_tail_locked(ring); } - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->stats.packets += total_rx_packets; - rx_ring->stats.bytes += total_rx_bytes; - u64_stats_update_end(&rx_ring->syncp); - q_vector->rx.total_packets += total_rx_packets; - q_vector->rx.total_bytes += total_rx_bytes; + ixgbe_update_rx_ring_stats(rx_ring, q_vector, total_rx_packets, + total_rx_bytes); if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) @@ -499,13 +495,8 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, } tx_ring->next_to_clean = ntc; - - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->stats.bytes += total_bytes; - tx_ring->stats.packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; + ixgbe_update_tx_ring_stats(tx_ring, q_vector, total_packets, + total_bytes); if (xsk_frames) xsk_tx_completed(pool, xsk_frames); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index a44e4bd56142..9c960017a6de 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4413,7 +4413,7 @@ ixgbevf_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IXGBEVF_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index d5c4f810da61..61ab7f66f053 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1556,6 +1556,7 @@ struct flow_msg { u32 mpls_lse[4]; u8 icmp_type; u8 icmp_code; + __be16 tcp_flags; }; struct npc_install_flow_req { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 3e6de9d7dde3..d883157393ea 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -217,6 +217,7 @@ enum key_fields { NPC_MPLS4_TTL, NPC_TYPE_ICMP, NPC_CODE_ICMP, + NPC_TCP_FLAGS, NPC_HEADER_FIELDS_MAX, NPC_CHAN = NPC_HEADER_FIELDS_MAX, /* Valid when Rx */ NPC_PF_FUNC, /* Valid when Tx */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index edd12d09dc89..07d4859de53a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -817,6 +817,8 @@ static int rvu_fwdata_init(struct rvu *rvu) err = cgx_get_fwdata_base(&fwdbase); if (err) goto fail; + + BUILD_BUG_ON(offsetof(struct rvu_fwdata, cgx_fw_data) > FWDATA_CGX_LMAC_OFFSET); rvu->fwdata = ioremap_wc(fwdbase, sizeof(struct rvu_fwdata)); if (!rvu->fwdata) goto fail; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index de8eba902276..f390525a6217 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -469,11 +469,12 @@ struct rvu_fwdata { u32 ptp_ext_clk_rate; u32 ptp_ext_tstamp; struct channel_fwdata channel_data; -#define FWDATA_RESERVED_MEM 1014 +#define FWDATA_RESERVED_MEM 958 u64 reserved[FWDATA_RESERVED_MEM]; #define CGX_MAX 9 #define CGX_LMACS_MAX 4 #define CGX_LMACS_USX 8 +#define FWDATA_CGX_LMAC_OFFSET 10536 union { struct cgx_lmac_fwdata_s cgx_fw_data[CGX_MAX][CGX_LMACS_MAX]; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index e6d7914ce61c..2500f5ba4f5a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2870,6 +2870,10 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s, seq_printf(s, "%d ", ntohs(rule->packet.dport)); seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.dport)); break; + case NPC_TCP_FLAGS: + seq_printf(s, "%d ", rule->packet.tcp_flags); + seq_printf(s, "mask 0x%x\n", rule->mask.tcp_flags); + break; case NPC_IPSEC_SPI: seq_printf(s, "0x%x ", ntohl(rule->packet.spi)); seq_printf(s, "mask 0x%x\n", ntohl(rule->mask.spi)); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index c75669c8fde7..c181e7aa9eb6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -53,6 +53,7 @@ static const char * const npc_flow_names[] = { [NPC_MPLS4_TTL] = "lse depth 4", [NPC_TYPE_ICMP] = "icmp type", [NPC_CODE_ICMP] = "icmp code", + [NPC_TCP_FLAGS] = "tcp flags", [NPC_UNKNOWN] = "unknown", }; @@ -530,6 +531,7 @@ do { \ NPC_SCAN_HDR(NPC_DPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 2, 2); NPC_SCAN_HDR(NPC_TYPE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 0, 1); NPC_SCAN_HDR(NPC_CODE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 1, 1); + NPC_SCAN_HDR(NPC_TCP_FLAGS, NPC_LID_LD, NPC_LT_LD_TCP, 12, 2); NPC_SCAN_HDR(NPC_ETYPE_ETHER, NPC_LID_LA, NPC_LT_LA_ETHER, 12, 2); NPC_SCAN_HDR(NPC_ETYPE_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 4, 2); NPC_SCAN_HDR(NPC_ETYPE_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 8, 2); @@ -574,7 +576,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) BIT_ULL(NPC_DPORT_TCP) | BIT_ULL(NPC_DPORT_UDP) | BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) | BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) | - BIT_ULL(NPC_TYPE_ICMP) | BIT_ULL(NPC_CODE_ICMP); + BIT_ULL(NPC_TYPE_ICMP) | BIT_ULL(NPC_CODE_ICMP) | + BIT_ULL(NPC_TCP_FLAGS); /* for tcp/udp/sctp corresponding layer type should be in the key */ if (*features & proto_flags) { @@ -982,7 +985,8 @@ do { \ mask->icmp_type, 0); NPC_WRITE_FLOW(NPC_CODE_ICMP, icmp_code, pkt->icmp_code, 0, mask->icmp_code, 0); - + NPC_WRITE_FLOW(NPC_TCP_FLAGS, tcp_flags, ntohs(pkt->tcp_flags), 0, + ntohs(mask->tcp_flags), 0); NPC_WRITE_FLOW(NPC_IPSEC_SPI, spi, ntohl(pkt->spi), 0, ntohl(mask->spi), 0); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 4fd44b6eecea..87bdb93cb066 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -638,6 +638,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, BIT(FLOW_DISSECTOR_KEY_IPSEC) | BIT_ULL(FLOW_DISSECTOR_KEY_MPLS) | BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | BIT_ULL(FLOW_DISSECTOR_KEY_IP)))) { netdev_info(nic->netdev, "unsupported flow used key 0x%llx", dissector->used_keys); @@ -857,6 +858,16 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match; + + flow_rule_match_tcp(rule, &match); + + flow_spec->tcp_flags = match.key->flags; + flow_mask->tcp_flags = match.mask->flags; + req->features |= BIT_ULL(NPC_TCP_FLAGS); + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_match_mpls match; u8 bit; diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index d58b07e7e123..7063c78bd35f 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -286,7 +286,6 @@ mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) static void mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; int i; for (i = 0; i < q->n_desc; i++) { @@ -301,19 +300,12 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) entry->buf = NULL; } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; - for (;;) { void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); @@ -323,12 +315,7 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) skb_free_frag(buf); } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index d7da62cda821..5d3fde63b273 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -42,6 +42,7 @@ #include <net/ip.h> #include <net/vxlan.h> #include <net/devlink.h> +#include <net/rps.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index c44870b175f9..76dc5a9b9648 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \ en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \ - lib/crypto.o + lib/crypto.o lib/sd.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3e064234f6fe..98d4306929f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE && + !dev->priv.fw_reset) { + NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function"); + return -EOPNOTSUPP; + } + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index c9c7fddb246f..904e08de852e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -285,7 +285,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll, { if (mdpll->tracking_netdev) return; - netdev_dpll_pin_set(netdev, mdpll->dpll_pin); + dpll_netdev_pin_set(netdev, mdpll->dpll_pin); mdpll->tracking_netdev = netdev; } @@ -293,7 +293,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll) { if (!mdpll->tracking_netdev) return; - netdev_dpll_pin_clear(mdpll->tracking_netdev); + dpll_netdev_pin_clear(mdpll->tracking_netdev); mdpll->tracking_netdev = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 55c6ace0acd5..84db05fb9389 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -60,6 +60,7 @@ #include "lib/clock.h" #include "en/rx_res.h" #include "en/selq.h" +#include "lib/sd.h" extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; @@ -791,6 +792,8 @@ struct mlx5e_channel { struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; + int vec_ix; + int sd_ix; int cpu; /* Sync between icosq recovery and XSK enable/disable. */ struct mutex icosq_recovery_lock; @@ -914,7 +917,7 @@ struct mlx5e_priv { bool tx_ptp_opened; bool rx_ptp_opened; struct hwtstamp_config tstamp; - u16 q_counter; + u16 q_counter[MLX5_SD_MAX_GROUP_SZ]; u16 drop_rq_q_counter; struct notifier_block events_nb; struct notifier_block blocking_events_nb; @@ -1029,12 +1032,12 @@ struct mlx5e_xsk_param; struct mlx5e_rq_param; int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq); #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); void mlx5e_close_rq(struct mlx5e_rq *rq); -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param); +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter); void mlx5e_destroy_rq(struct mlx5e_rq *rq); struct mlx5e_sq_param; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c index 48581ea3adcb..874a1016623c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c @@ -23,20 +23,26 @@ bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix) return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); } -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); *rqn = c->rq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)); *rqn = c->xskrq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h index 637ca90daaa8..6715aa9383b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h @@ -10,8 +10,10 @@ struct mlx5e_channels; unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs); bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix); -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn); #endif /* __MLX5_EN_CHANNELS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 40c8df111754..e2d8d2754be0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -20,10 +20,8 @@ #define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 #define NUM_REQ_Q_COUNTERS_S1 MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1 -int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev) { - struct mlx5_core_dev *mdev = priv->mdev; - if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters)) return false; if (MLX5_CAP_PCAM_REG(mdev, ppcnt) && @@ -36,24 +34,38 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) return true; } -static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv) +int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (!mlx5e_monitor_counter_cap(pos)) + return false; + return true; +} + +static void mlx5e_monitor_counter_arm(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {}; MLX5_SET(arm_monitor_counter_in, in, opcode, MLX5_CMD_OP_ARM_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in); + mlx5_cmd_exec_in(mdev, arm_monitor_counter, in); } static void mlx5e_monitor_counters_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, monitor_counters_work); + struct mlx5_core_dev *pos; + int i; mutex_lock(&priv->state_lock); mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) + mlx5e_monitor_counter_arm(pos); } static int mlx5e_monitor_event_handler(struct notifier_block *nb, @@ -97,15 +109,13 @@ static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in) } /* check if mlx5e_monitor_counter_supported before calling this function*/ -static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) +static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter) { - struct mlx5_core_dev *mdev = priv->mdev; int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters); int num_q_counters = MLX5_CAP_GEN(mdev, num_q_monitor_counters); int num_ppcnt_counters = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 : MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters); u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; - int q_counter = priv->q_counter; int cnt = 0; if (num_ppcnt_counters >= NUM_REQ_PPCNT_COUNTER_S1 && @@ -127,13 +137,17 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) /* check if mlx5e_monitor_counter_supported before calling this function*/ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) { + struct mlx5_core_dev *pos; + int i; + INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work); MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler, MONITOR_COUNTER); - mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb); - - mlx5e_set_monitor_counter(priv); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_eq_notifier_register(pos, &priv->monitor_counters_nb); + mlx5e_set_monitor_counter(pos, priv->q_counter[i]); + mlx5e_monitor_counter_arm(pos); + } queue_work(priv->wq, &priv->update_stats_work); } @@ -141,11 +155,15 @@ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(set_monitor_counter_in, in, opcode, MLX5_CMD_OP_SET_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in); - mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_cmd_exec_in(pos, set_monitor_counter, in); + mlx5_eq_notifier_unregister(pos, &priv->monitor_counters_nb); + } cancel_work_sync(&priv->monitor_counters_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 5757f4f10c12..a3f31d9d527e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -688,7 +688,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e .napi = &c->napi, .ch_stats = c->stats, .node = cpu_to_node(c->cpu), - .ix = c->ix, + .ix = c->vec_ix, }; } @@ -959,7 +959,6 @@ static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *param int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1021,7 +1020,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); @@ -1032,7 +1030,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1041,7 +1038,6 @@ void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1)); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); } @@ -1306,13 +1302,12 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam) { u8 icosq_log_wq_sz, async_icosq_log_wq_sz; int err; - err = mlx5e_build_rq_param(mdev, params, NULL, q_counter, &cparam->rq); + err = mlx5e_build_rq_param(mdev, params, NULL, &cparam->rq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 6800949dafbc..9a781f18b57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -130,10 +130,8 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_sq_param_common(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); @@ -149,7 +147,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam); u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index fd4ef6431142..d0af7271da34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad WARN_ON_ONCE(tracker->inuse); tracker->inuse = true; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_add_tail(&tracker->entry, &list->tracker_list_head); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } static void @@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me WARN_ON_ONCE(!tracker->inuse); tracker->inuse = false; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_del(&tracker->entry); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata) @@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n; - spin_lock(&cqe_list->tracker_list_lock); + spin_lock_bh(&cqe_list->tracker_list_lock); list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) { struct sk_buff *skb = mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id); @@ -170,7 +170,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, pos->inuse = false; list_del(&pos->entry); } - spin_unlock(&cqe_list->tracker_list_lock); + spin_unlock_bh(&cqe_list->tracker_list_lock); } #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) @@ -646,7 +646,6 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev, static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, struct net_device *netdev, - u16 q_counter, struct mlx5e_ptp_params *ptp_params) { struct mlx5e_rq_param *rq_params = &ptp_params->rq_param; @@ -655,7 +654,7 @@ static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = netdev->max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, rq_params); + mlx5e_build_rq_param(mdev, params, NULL, rq_params); } static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, @@ -681,7 +680,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, /* RQ */ if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { params->vlan_strip_disable = orig->vlan_strip_disable; - mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams); + mlx5e_ptp_build_rq_param(c->mdev, c->netdev, cparams); } } @@ -714,13 +713,16 @@ static int mlx5e_ptp_open_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param) { int node = dev_to_node(c->mdev->device); - int err; + int err, sd_ix; + u16 q_counter; err = mlx5e_init_ptp_rq(c, params, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_param, NULL, node, &c->rq); + sd_ix = mlx5_sd_ch_ix_get_dev_ix(c->mdev, MLX5E_PTP_CHANNEL_IX); + q_counter = c->priv->q_counter[sd_ix]; + return mlx5e_open_rq(params, rq_param, NULL, node, q_counter, &c->rq); } static int mlx5e_ptp_open_queues(struct mlx5e_ptp *c, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 34adf8c3f81a..e87e26f2c669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -122,8 +122,8 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, memset(¶m_sq, 0, sizeof(param_sq)); memset(¶m_cq, 0, sizeof(param_cq)); - mlx5e_build_sq_param(priv->mdev, params, ¶m_sq); - mlx5e_build_tx_cq_param(priv->mdev, params, ¶m_cq); + mlx5e_build_sq_param(c->mdev, params, ¶m_sq); + mlx5e_build_tx_cq_param(c->mdev, params, ¶m_cq); err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, ¶m_cq, &ccp, &sq->cq); if (err) goto err_free_sq; @@ -176,7 +176,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id) */ smp_wmb(); - qos_dbg(priv->mdev, "Activate QoS SQ qid %u\n", node_qid); + qos_dbg(sq->mdev, "Activate QoS SQ qid %u\n", node_qid); mlx5e_activate_txqsq(sq); return 0; @@ -190,7 +190,7 @@ void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) if (!sq) /* Handle the case when the SQ failed to open. */ return; - qos_dbg(priv->mdev, "Deactivate QoS SQ qid %u\n", qid); + qos_dbg(sq->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 4358798d6ce1..25d751eba99b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -294,8 +294,8 @@ static void mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq, params = &priv->channels.params; rq_sz = mlx5e_rqwq_get_size(rq); - real_time = mlx5_is_real_time_rq(priv->mdev); - rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL)); + real_time = mlx5_is_real_time_rq(rq->mdev); + rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(rq->mdev, params, NULL)); mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 6b44ddce14e9..0ab9db319530 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -219,7 +219,6 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq, int tc) { bool stopped = netif_xmit_stopped(sq->txq); - struct mlx5e_priv *priv = sq->priv; u8 state; int err; @@ -227,7 +226,7 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + err = mlx5_core_query_sq_state(sq->mdev, sq->sqn, &state); if (!err) devlink_fmsg_u8_pair_put(fmsg, "HW state", state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c index 7b8ff7a71003..bcafb4bf9415 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c @@ -4,6 +4,33 @@ #include "rqt.h" #include <linux/mlx5/transobj.h> +static bool verify_num_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + unsigned int max_num_vhca_id = MLX5_CAP_GEN_2(mdev, max_rqt_vhca_id); + int i; + + /* Verify that all vhca_ids are in range [0, max_num_vhca_ids - 1] */ + for (i = 0; i < size; i++) + if (vhca_ids[i] >= max_num_vhca_id) + return false; + return true; +} + +static bool rqt_verify_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + if (!vhca_ids) + return true; + + if (!MLX5_CAP_GEN(mdev, cross_vhca_rqt)) + return false; + if (!verify_num_vhca_ids(mdev, vhca_ids, size)) + return false; + + return true; +} + void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels) { @@ -13,19 +40,38 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, indir->table[i] = i % num_channels; } +static void fill_rqn_list(void *rqtc, u32 *rqns, u32 *vhca_ids, unsigned int size) +{ + unsigned int i; + + if (vhca_ids) { + MLX5_SET(rqtc, rqtc, rq_vhca_id_format, 1); + for (i = 0; i < size; i++) { + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_num, rqns[i]); + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_vhca_id, vhca_ids[i]); + } + } else { + for (i = 0; i < size; i++) + MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + } +} static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u16 max_size, u32 *init_rqns, u16 init_size) + u16 max_size, u32 *init_rqns, u32 *init_vhca_ids, u16 init_size) { + int entry_sz; void *rqtc; int inlen; int err; u32 *in; - int i; + + if (!rqt_verify_vhca_ids(mdev, init_vhca_ids, init_size)) + return -EOPNOTSUPP; rqt->mdev = mdev; rqt->size = max_size; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size; + entry_sz = init_vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + entry_sz * init_size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -33,10 +79,9 @@ static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size); - MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size); - for (i = 0; i < init_size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]); + + fill_rqn_list(rqtc, init_rqns, init_vhca_ids, init_size); err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn); @@ -49,7 +94,7 @@ int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, { u16 max_size = indir_enabled ? indir_table_size : 1; - return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1); + return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, NULL, 1); } static int mlx5e_bits_invert(unsigned long a, int size) @@ -63,7 +108,8 @@ static int mlx5e_bits_invert(unsigned long a, int size) return inv; } -static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns, +static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, u32 *rss_vhca_ids, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { unsigned int i; @@ -82,30 +128,42 @@ static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns */ return -EINVAL; rss_rqns[i] = rqns[ix]; + if (vhca_ids) + rss_vhca_ids[i] = vhca_ids[ix]; } return 0; } int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; rss_rqns = kvmalloc_array(indir->actual_table_size, sizeof(*rss_rqns), GFP_KERNEL); if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, + err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } @@ -126,15 +184,20 @@ void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt) mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn); } -static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size) +static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int size) { - unsigned int i; + int entry_sz; void *rqtc; int inlen; u32 *in; int err; - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, size)) + return -EINVAL; + + entry_sz = vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + entry_sz * size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -143,8 +206,8 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1); MLX5_SET(rqtc, rqtc, rqt_actual_size, size); - for (i = 0; i < size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + + fill_rqn_list(rqtc, rqns, vhca_ids, size); err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen); @@ -152,17 +215,21 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz return err; } -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn) +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id) { - return mlx5e_rqt_redirect(rqt, &rqn, 1); + return mlx5e_rqt_redirect(rqt, &rqn, vhca_id, 1); } -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, num_rqns)) + return -EINVAL; + if (WARN_ON(rqt->size != indir->max_table_size)) return -EINVAL; @@ -170,13 +237,23 @@ int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_ if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_redirect(rqt, rss_rqns, indir->actual_table_size); + err = mlx5e_rqt_redirect(rqt, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h index 77fba3ebd18d..e0bc30308c77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h @@ -20,7 +20,7 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels); struct mlx5e_rqt { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 rqtn; u16 size; }; @@ -28,7 +28,7 @@ struct mlx5e_rqt { int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, bool indir_enabled, u32 init_rqn, u32 indir_table_size); int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt); @@ -38,8 +38,9 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt) } u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels); -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn); -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id); +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); #endif /* __MLX5_EN_RQT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index c1545a2e8d6d..5f742f896600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -74,7 +74,7 @@ struct mlx5e_rss { struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_rqt rqt; - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 drop_rqn; bool inner_ft_support; bool enabled; @@ -473,21 +473,22 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, return 0; } -static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { int err; - err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir); + err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, vhca_ids, num_rqns, rss->hash.hfunc, + &rss->indir); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), err); return err; } -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { rss->enabled = true; - mlx5e_rss_apply(rss, rqns, num_rqns); + mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); } void mlx5e_rss_disable(struct mlx5e_rss *rss) @@ -495,7 +496,7 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss) int err; rss->enabled = false; - err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn); + err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn, NULL); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); @@ -568,7 +569,7 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc) int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns) + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { bool changed_indir = false; bool changed_hash = false; @@ -608,7 +609,7 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, } if (changed_indir && rss->enabled) { - err = mlx5e_rss_apply(rss, rqns, num_rqns); + err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); if (err) { mlx5e_rss_copy(rss, old_rss); goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index d1d0bc350e92..d0df98963c8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -39,7 +39,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn); -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); void mlx5e_rss_disable(struct mlx5e_rss *rss); int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, @@ -47,7 +47,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns); + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss); u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt); int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index b23e224e3763..a86eade9a9e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -8,7 +8,7 @@ #define MLX5E_MAX_NUM_RSS 16 struct mlx5e_rx_res { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ enum mlx5e_rx_res_features features; unsigned int max_nch; u32 drop_rqn; @@ -19,6 +19,7 @@ struct mlx5e_rx_res { struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS]; bool rss_active; u32 *rss_rqns; + u32 *rss_vhca_ids; unsigned int rss_nch; struct { @@ -34,6 +35,13 @@ struct mlx5e_rx_res { /* API for rx_res_rss_* */ +static u32 *get_vhca_ids(struct mlx5e_rx_res *res, int offset) +{ + bool multi_vhca = res->features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; + + return multi_vhca ? res->rss_vhca_ids + offset : NULL; +} + void mlx5e_rx_res_rss_update_num_channels(struct mlx5e_rx_res *res, u32 nch) { int i; @@ -85,8 +93,11 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int i return PTR_ERR(rss); mlx5e_rss_set_indir_uniform(rss, init_nch); - if (res->rss_active) - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + if (res->rss_active) { + u32 *vhca_ids = get_vhca_ids(res, 0); + + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); + } res->rss[i] = rss; *rss_idx = i; @@ -153,10 +164,12 @@ static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res) for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { struct mlx5e_rss *rss = res->rss[i]; + u32 *vhca_ids; if (!rss) continue; - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + vhca_ids = get_vhca_ids(res, 0); + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); } } @@ -200,6 +213,7 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, const u32 *indir, const u8 *key, const u8 *hfunc) { + u32 *vhca_ids = get_vhca_ids(res, 0); struct mlx5e_rss *rss; if (rss_idx >= MLX5E_MAX_NUM_RSS) @@ -209,7 +223,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, if (!rss) return -ENOENT; - return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch); + return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids, + res->rss_nch); } int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx, @@ -280,11 +295,13 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx) static void mlx5e_rx_res_free(struct mlx5e_rx_res *res) { + kvfree(res->rss_vhca_ids); kvfree(res->rss_rqns); kvfree(res); } -static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch) +static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch, + bool multi_vhca) { struct mlx5e_rx_res *rx_res; @@ -298,6 +315,15 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig return NULL; } + if (multi_vhca) { + rx_res->rss_vhca_ids = kvcalloc(max_nch, sizeof(*rx_res->rss_vhca_ids), GFP_KERNEL); + if (!rx_res->rss_vhca_ids) { + kvfree(rx_res->rss_rqns); + kvfree(rx_res); + return NULL; + } + } + return rx_res; } @@ -424,10 +450,11 @@ mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features featu const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { + bool multi_vhca = features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; struct mlx5e_rx_res *res; int err; - res = mlx5e_rx_res_alloc(mdev, max_nch); + res = mlx5e_rx_res_alloc(mdev, max_nch, multi_vhca); if (!res) return ERR_PTR(-ENOMEM); @@ -504,10 +531,11 @@ static void mlx5e_rx_res_channel_activate_direct(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix) { + u32 *vhca_id = get_vhca_ids(res, ix); u32 rqn = res->rss_rqns[ix]; int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn, vhca_id); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -519,7 +547,7 @@ static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res, { int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -534,10 +562,12 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann nch = mlx5e_channels_get_num(chs); for (ix = 0; ix < chs->num; ix++) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (mlx5e_channels_is_xsk(chs, ix)) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); } res->rss_nch = chs->num; @@ -554,7 +584,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann if (!mlx5e_channels_get_ptp_rqn(chs, &rqn)) rqn = res->drop_rqn; - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -573,7 +603,7 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) mlx5e_rx_res_channel_deactivate_direct(res, ix); if (res->features & MLX5E_RX_RES_FEATURE_PTP) { - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -584,10 +614,12 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix, bool xsk) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (xsk) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); mlx5e_rx_res_rss_enable(res); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 82aaba8a82b3..7b1a9f0f1874 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -18,6 +18,7 @@ struct mlx5e_rss_params_hash; enum mlx5e_rx_res_features { MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0), MLX5E_RX_RES_FEATURE_PTP = BIT(1), + MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2), }; /* Setup */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 86bf007fd05b..b500cc2c9689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) { if (priv->mdev->coredev_type == MLX5_COREDEV_PF) - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n"); err = -EOPNOTSUPP; goto err_check; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index ac458a8d10e0..53ca16cb9c41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -63,10 +63,12 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) struct mlx5e_create_cq_param ccp = {}; struct dim_cq_moder trap_moder = {}; struct mlx5e_rq *rq = &t->rq; + u16 q_counter; int node; int err; node = dev_to_node(mdev->device); + q_counter = priv->q_counter[0]; ccp.netdev = priv->netdev; ccp.wq = priv->wq; @@ -79,7 +81,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) return err; mlx5e_init_trap_rq(t, &t->params, rq); - err = mlx5e_open_rq(&t->params, rq_param, NULL, node, rq); + err = mlx5e_open_rq(&t->params, rq_param, NULL, node, q_counter, rq); if (err) goto err_destroy_cq; @@ -116,15 +118,14 @@ static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct ml } static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev, - int max_mtu, u16 q_counter, - struct mlx5e_trap *t) + int max_mtu, struct mlx5e_trap *t) { struct mlx5e_params *params = &t->params; params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, &t->rq_param); + mlx5e_build_rq_param(mdev, params, NULL, &t->rq_param); } static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) @@ -138,7 +139,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) if (!t) return ERR_PTR(-ENOMEM); - mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, priv->q_counter, t); + mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, t); t->priv = priv; t->mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index ebada0c5af3c..db776e515b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -6,10 +6,10 @@ #include "setup.h" #include "en/params.h" -static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, +static int mlx5e_xsk_map_pool(struct mlx5_core_dev *mdev, struct xsk_buff_pool *pool) { - struct device *dev = mlx5_core_dma_dev(priv->mdev); + struct device *dev = mlx5_core_dma_dev(mdev); return xsk_pool_dma_map(pool, dev, DMA_ATTR_SKIP_CPU_SYNC); } @@ -89,7 +89,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, if (unlikely(!mlx5e_xsk_is_pool_sane(pool))) return -EINVAL; - err = mlx5e_xsk_map_pool(priv, pool); + err = mlx5e_xsk_map_pool(mlx5_sd_ch_ix_get_dev(priv->mdev, ix), pool); if (unlikely(err)) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 82e6abbc1734..06592b9f0424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -49,10 +49,9 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_channel_param *cparam) { - mlx5e_build_rq_param(mdev, params, xsk, q_counter, &cparam->rq); + mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq); mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq); } @@ -93,6 +92,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param struct mlx5e_rq_param *rq_params, struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; struct mlx5e_rq *xskrq = &c->xskrq; int err; @@ -100,7 +100,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param if (err) return err; - err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), xskrq); + err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), q_counter, xskrq); if (err) return err; @@ -125,7 +125,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (!cparam) return -ENOMEM; - mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam); + mlx5e_build_xsk_cparam(priv->mdev, params, xsk, cparam); err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index 984fa04bd331..e3e57c849436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -96,7 +96,7 @@ bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev) { u8 max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); - if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx)) + if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx) || mlx5_get_sd(mdev)) return false; /* Check the possibility to post the required ICOSQ WQEs. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index f11075e67658..adc6d8ea0960 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -11,6 +11,7 @@ #ifdef CONFIG_MLX5_EN_TLS #include "lib/crypto.h" +#include "lib/mlx5.h" struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool, struct tls_crypto_info *crypto_info); @@ -61,7 +62,8 @@ void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_ static inline bool mlx5e_is_ktls_tx(struct mlx5_core_dev *mdev) { - return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx); + return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx) && + !mlx5_get_sd(mdev); } bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 9b597cb24598..65ccb33edafb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -267,7 +267,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, goto err_out; } - pdev = mlx5_core_dma_dev(sq->channel->priv->mdev); + pdev = mlx5_core_dma_dev(sq->channel->mdev); buf->dma_addr = dma_map_single(pdev, &buf->progress, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { @@ -425,14 +425,12 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, { struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf; struct mlx5e_ktls_offload_context_rx *priv_rx; - struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; - resync = &priv_rx->resync; - dev = mlx5_core_dma_dev(resync->priv->mdev); + dev = mlx5_core_dma_dev(sq->channel->mdev); if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index d4ebd8743114..b2cabd6ab86c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); } -static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, - struct mlx5e_macsec_sa *sa, - bool is_tx, struct net_device *netdev, u32 fs_id) +static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) { int action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : MLX5_ACCEL_MACSEC_ACTION_DECRYPT; @@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev, fs_id); - mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); sa->macsec_rule = NULL; } +static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) +{ + mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id); + mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); +} + +static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, + struct mlx5e_macsec_sa *sa, bool encrypt, + bool is_tx, u32 *fs_id) +{ + struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); + struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + struct mlx5_macsec_rule_attrs rule_attrs; + union mlx5_macsec_rule *macsec_rule; + + rule_attrs.macsec_obj_id = sa->macsec_obj_id; + rule_attrs.sci = sa->sci; + rule_attrs.assoc_num = sa->assoc_num; + rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : + MLX5_ACCEL_MACSEC_ACTION_DECRYPT; + + macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id); + if (!macsec_rule) + return -ENOMEM; + + sa->macsec_rule = macsec_rule; + + return 0; +} + static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5e_macsec_sa *sa, bool encrypt, bool is_tx, u32 *fs_id) { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5e_macsec *macsec = priv->macsec; - struct mlx5_macsec_rule_attrs rule_attrs; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; - union mlx5_macsec_rule *macsec_rule; int err; obj_attrs.next_pn = sa->next_pn; @@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, if (err) return err; - rule_attrs.macsec_obj_id = sa->macsec_obj_id; - rule_attrs.sci = sa->sci; - rule_attrs.assoc_num = sa->assoc_num; - rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : - MLX5_ACCEL_MACSEC_ACTION_DECRYPT; - - macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id); - if (!macsec_rule) { - err = -ENOMEM; - goto destroy_macsec_object; + if (sa->active) { + err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id); + if (err) + goto destroy_macsec_object; } - sa->macsec_rule = macsec_rule; - return 0; destroy_macsec_object: @@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) goto destroy_sa; macsec_device->tx_sa[assoc_num] = tx_sa; - if (!secy->operational || - assoc_num != tx_sc->encoding_sa || - !tx_sa->active) + if (!secy->operational) goto out; err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); @@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; if (ctx_tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } else { @@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } out: mutex_unlock(&macsec->lock); @@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + if (rx_sa->active) + mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); kfree(rx_sa); rx_sc->rx_sa[assoc_num] = NULL; @@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, if (!rx_sa || !rx_sa->macsec_rule) continue; - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); } } @@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, - &rx_sc->sc_xarray_element->fs_id); + err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false, + &rx_sc->sc_xarray_element->fs_id); if (err) goto out; } @@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) if (!tx_sa) continue; - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } for (i = 0; i < MACSEC_NUM_AN; ++i) { @@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) continue; if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index e66f486faafe..c7f542d0b8f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -34,6 +34,7 @@ #include <linux/mlx5/fs.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/rps.h> #include "en.h" #define ARFS_HASH_SHIFT BITS_PER_BYTE diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index be809556b2e1..91848eae4565 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -70,6 +70,7 @@ #include "qos.h" #include "en/trap.h" #include "lib/devcom.h" +#include "lib/sd.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode) @@ -1024,7 +1025,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) mlx5_wq_destroy(&rq->wq_ctrl); } -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter) { struct mlx5_core_dev *mdev = rq->mdev; u8 ts_format; @@ -1051,6 +1052,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); MLX5_SET(rqc, rqc, ts_format, ts_format); + MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); @@ -1274,7 +1276,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) } int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1287,7 +1289,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, if (err) return err; - err = mlx5e_create_rq(rq, param); + err = mlx5e_create_rq(rq, param, q_counter); if (err) goto err_free_rq; @@ -2335,13 +2337,14 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_params) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; int err; err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), &c->rq); + return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), q_counter, &c->rq); } static int mlx5e_open_queues(struct mlx5e_channel *c, @@ -2528,14 +2531,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { - int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix); struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev; struct mlx5e_xsk_param xsk; struct mlx5e_channel *c; unsigned int irq; + int vec_ix; + int cpu; int err; - err = mlx5_comp_irqn_get(priv->mdev, ix, &irq); + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); + cpu = mlx5_comp_vector_get_cpu(mdev, vec_ix); + + err = mlx5_comp_irqn_get(mdev, vec_ix, &irq); if (err) return err; @@ -2548,18 +2557,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, return -ENOMEM; c->priv = priv; - c->mdev = priv->mdev; + c->mdev = mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->vec_ix = vec_ix; + c->sd_ix = mlx5_sd_ch_ix_get_dev_ix(mdev, ix); c->cpu = cpu; - c->pdev = mlx5_core_dma_dev(priv->mdev); + c->pdev = mlx5_core_dma_dev(mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); + c->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix]->ch; c->aff_mask = irq_get_effective_affinity_mask(irq); - c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); + c->lag_port = mlx5e_enumerate_lag_port(mdev, ix); netif_napi_add(netdev, &c->napi, mlx5e_napi_poll); netif_napi_set_irq(&c->napi, irq); @@ -2654,7 +2665,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, if (!chs->c || !cparam) goto err_free; - err = mlx5e_build_channel_param(priv->mdev, &chs->params, priv->q_counter, cparam); + err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam); if (err) goto err_free; @@ -2942,15 +2953,18 @@ static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues); static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); @@ -3342,7 +3356,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, struct mlx5e_cq *cq = &drop_rq->cq; int err; - mlx5e_build_drop_rq_param(mdev, priv->drop_rq_q_counter, &rq_param); + mlx5e_build_drop_rq_param(mdev, &rq_param); err = mlx5e_alloc_drop_cq(priv, cq, &cq_param); if (err) @@ -3356,7 +3370,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, if (err) goto err_destroy_cq; - err = mlx5e_create_rq(drop_rq, &rq_param); + err = mlx5e_create_rq(drop_rq, &rq_param, priv->drop_rq_q_counter); if (err) goto err_free_rq; @@ -5271,13 +5285,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {}; struct mlx5_core_dev *mdev = priv->mdev; - int err; + struct mlx5_core_dev *pos; + int err, i; MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER); - err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); - if (!err) - priv->q_counter = - MLX5_GET(alloc_q_counter_out, out, counter_set_id); + + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5_cmd_exec_inout(pos, alloc_q_counter, in, out); + if (!err) + priv->q_counter[i] = + MLX5_GET(alloc_q_counter_out, out, counter_set_id); + } err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); if (!err) @@ -5288,13 +5306,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(dealloc_q_counter_in, in, opcode, MLX5_CMD_OP_DEALLOC_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(dealloc_q_counter_in, in, counter_set_id, - priv->q_counter); - mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(dealloc_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + mlx5_cmd_exec_in(pos, dealloc_q_counter, in); + } } if (priv->drop_rq_q_counter) { @@ -5378,6 +5400,8 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) features = MLX5E_RX_RES_FEATURE_PTP; if (mlx5_tunnel_inner_ft_supported(mdev)) features |= MLX5E_RX_RES_FEATURE_INNER_FT; + if (mlx5_get_sd(priv->mdev)) + features |= MLX5E_RX_RES_FEATURE_MULTI_VHCA; priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch, priv->drop_rq.rqn, &priv->channels.params.packet_merge, @@ -5987,28 +6011,52 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) free_netdev(netdev); } -static int mlx5e_resume(struct auxiliary_device *adev) +static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = edev->mdev; - int err; + struct mlx5_core_dev *pos, *to; + int err, i; if (netif_device_present(netdev)) return 0; - err = mlx5e_create_mdev_resources(mdev, true); - if (err) - return err; + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5e_create_mdev_resources(pos, true); + if (err) + goto err_destroy_mdev_res; + } err = mlx5e_attach_netdev(priv); - if (err) { - mlx5e_destroy_mdev_resources(mdev); + if (err) + goto err_destroy_mdev_res; + + return 0; + +err_destroy_mdev_res: + to = pos; + mlx5_sd_for_each_dev_to(i, mdev, to, pos) + mlx5e_destroy_mdev_resources(pos); + return err; +} + +static int mlx5e_resume(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) return err; - } + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_resume(actual_adev); return 0; } @@ -6018,21 +6066,36 @@ static int _mlx5e_suspend(struct auxiliary_device *adev) struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_dev *pos; + int i; if (!netif_device_present(netdev)) { if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); return -ENODEV; } mlx5e_detach_netdev(priv); - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + return 0; } static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - return _mlx5e_suspend(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err = 0; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + err = _mlx5e_suspend(actual_adev); + + mlx5_sd_cleanup(mdev); + return err; } static int _mlx5e_probe(struct auxiliary_device *adev) @@ -6078,9 +6141,9 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_destroy_netdev; } - err = mlx5e_resume(adev); + err = _mlx5e_resume(adev); if (err) { - mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); + mlx5_core_err(mdev, "_mlx5e_resume failed, %d\n", err); goto err_profile_cleanup; } @@ -6111,15 +6174,29 @@ err_devlink_unregister: static int mlx5e_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { - return _mlx5e_probe(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) + return err; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_probe(actual_adev); + return 0; } -static void mlx5e_remove(struct auxiliary_device *adev) +static void _mlx5e_remove(struct auxiliary_device *adev) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; + struct mlx5_core_dev *mdev = edev->mdev; - mlx5_core_uplink_netdev_set(priv->mdev, NULL); + mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); _mlx5e_suspend(adev); @@ -6129,6 +6206,19 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_destroy_devlink(mlx5e_dev); } +static void mlx5e_remove(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + _mlx5e_remove(actual_adev); + + mlx5_sd_cleanup(mdev); +} + static const struct auxiliary_device_id mlx5e_id_table[] = { { .name = MLX5_ADEV_NAME ".eth", }, {}, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 4b96ad657145..f3d0898bdbc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -561,11 +561,23 @@ static const struct counter_desc drop_rq_stats_desc[] = { #define NUM_Q_COUNTERS ARRAY_SIZE(q_stats_desc) #define NUM_DROP_RQ_COUNTERS ARRAY_SIZE(drop_rq_stats_desc) +static bool q_counter_any(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (priv->q_counter[i++]) + return true; + + return false; +} + static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt) { int num_stats = 0; - if (priv->q_counter) + if (q_counter_any(priv)) num_stats += NUM_Q_COUNTERS; if (priv->drop_rq_q_counter) @@ -578,7 +590,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format); @@ -593,7 +605,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt, q_stats_desc, i); for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++) @@ -607,18 +619,23 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt) struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt; u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; - int ret; + struct mlx5_core_dev *pos; + u32 rx_out_of_buffer = 0; + int ret, i; MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(query_q_counter_in, in, counter_set_id, - priv->q_counter); - ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out); - if (!ret) - qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, - out, out_of_buffer); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(query_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + ret = mlx5_cmd_exec_inout(pos, query_q_counter, in, out); + if (!ret) + rx_out_of_buffer += MLX5_GET(query_q_counter_out, + out, out_of_buffer); + } } + qcnt->rx_out_of_buffer = rx_out_of_buffer; if (priv->drop_rq_q_counter) { MLX5_SET(query_q_counter_in, in, counter_set_id, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9fb2c057bd78..31ed26cac9bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -766,7 +766,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) return err; mlx5e_rss_params_indir_init_uniform(&indir, hp->num_channels); - err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels, + err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, NULL, hp->num_channels, mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc, &indir); @@ -1169,7 +1169,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); - params.q_counter = priv->q_counter; + params.q_counter = priv->q_counter[0]; err = devl_param_driverinit_value_get( devlink, MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES, &val); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5c166d9d2dca..2fa076b23fbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -401,6 +401,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + /* ensure skb is put on metadata_map before tracking the index */ + wmb(); mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 190f10aba170..5a0047bdcb51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) + if (!rpriv || !rpriv->netdev) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b0455134c98e..baaae628b0a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -535,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) } static bool -esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest) +esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest) { - bool vf_dest = false, pf_dest = false; + bool internal_dest = false, external_dest = false; int i; for (i = 0; i < max_dest; i++) { - if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) + if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT && + dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK) continue; - if (dests[i].vport.num == MLX5_VPORT_UPLINK) - pf_dest = true; + /* Uplink dest is external, but considered as internal + * if there is reformat because firmware uses LB+hairpin to support it. + */ + if (dests[i].vport.num == MLX5_VPORT_UPLINK && + !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)) + external_dest = true; else - vf_dest = true; + internal_dest = true; - if (vf_dest && pf_dest) + if (internal_dest && external_dest) return true; } @@ -695,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, /* Header rewrite with combined wire+loopback in FDB is not allowed */ if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) && - esw_dests_to_vf_pf_vports(dest, i)) { + esw_dests_to_int_external(dest, i)) { esw_warn(esw->dev, - "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n"); + "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n"); rule = ERR_PTR(-EINVAL); goto err_esw_get; } @@ -3658,22 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) return 0; } -static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - struct net *devl_net, *netdev_net; - bool ret = false; - - mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); - if (dev->mlx5e_res.uplink_netdev) { - netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); - ret = net_eq(devl_net, netdev_net); - } - mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); - return ret; -} - int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -3718,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && - !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) { - NL_SET_ERR_MSG_MOD(extack, - "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's."); - return -EPERM; - } - mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index f27eab6e4929..2911aa34a5be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -703,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT); mlx5_eq_notifier_register(dev, &fw_reset->nb); } void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) { - mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return; + + mlx5_eq_notifier_unregister(dev, &fw_reset->nb); } void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); cancel_work_sync(&fw_reset->fw_live_patch_work); cancel_work_sync(&fw_reset->reset_request_work); @@ -733,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = { int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { - struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); + struct mlx5_fw_reset *fw_reset; int err; + if (!MLX5_CAP_MCAM_REG(dev, mfrl)) + return 0; + + fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); if (!fw_reset) return -ENOMEM; fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events"); @@ -771,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + devl_params_unregister(priv_to_devlink(dev), mlx5_fw_reset_devlink_params, ARRAY_SIZE(mlx5_fw_reset_devlink_params)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9463ede84d8d..ad38e31822df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct health_buffer __iomem *h = health->health; u8 synd = ioread8(&h->synd); + devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); if (!synd) return 0; - devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index ec32b686f586..d58032dd0df7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -10,6 +10,7 @@ enum mlx5_devcom_component { MLX5_DEVCOM_ESW_OFFLOADS, MLX5_DEVCOM_MPV, MLX5_DEVCOM_HCA_PORTS, + MLX5_DEVCOM_SD_GROUP, MLX5_DEVCOM_NUM_COMPONENTS, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 2b5826a785c4..37d5f445598c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -54,4 +54,16 @@ static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *md { return mdev->mlx5e_res.uplink_netdev; } + +struct mlx5_sd; + +static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev) +{ + return dev->sd; +} + +static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd) +{ + dev->sd = sd; +} #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c new file mode 100644 index 000000000000..5b28084e8a03 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -0,0 +1,524 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "lib/sd.h" +#include "mlx5_core.h" +#include "lib/mlx5.h" +#include "fs_cmd.h" +#include <linux/mlx5/vport.h> +#include <linux/debugfs.h> + +#define sd_info(__dev, format, ...) \ + dev_info((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) +#define sd_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) + +struct mlx5_sd { + u32 group_id; + u8 host_buses; + struct mlx5_devcom_comp_dev *devcom; + struct dentry *dfs; + bool primary; + union { + struct { /* primary */ + struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1]; + struct mlx5_flow_table *tx_ft; + }; + struct { /* secondary */ + struct mlx5_core_dev *primary_dev; + u32 alias_obj_id; + }; + }; +}; + +static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return 1; + + return sd->host_buses; +} + +static struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return dev; + + return sd->primary ? dev : sd->primary_dev; +} + +struct mlx5_core_dev * +mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx) +{ + struct mlx5_sd *sd; + + if (idx == 0) + return primary; + + if (idx >= mlx5_sd_get_host_buses(primary)) + return NULL; + + sd = mlx5_get_sd(primary); + return sd->secondaries[idx - 1]; +} + +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix % mlx5_sd_get_host_buses(dev); +} + +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix / mlx5_sd_get_host_buses(dev); +} + +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix) +{ + int mdev_idx = mlx5_sd_ch_ix_get_dev_ix(primary, ch_ix); + + return mlx5_sd_primary_get_peer(primary, mdev_idx); +} + +static bool ft_create_alias_supported(struct mlx5_core_dev *dev) +{ + u64 obj_allowed = MLX5_CAP_GEN_2_64(dev, allowed_object_for_other_vhca_access); + u32 obj_supp = MLX5_CAP_GEN_2(dev, cross_vhca_object_to_object_supported); + + if (!(obj_supp & + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE)) + return false; + + if (!(obj_allowed & MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE)) + return false; + + return true; +} + +static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) +{ + /* Feature is currently implemented for PFs only */ + if (!mlx5_core_is_pf(dev)) + return false; + + /* Honor the SW implementation limit */ + if (host_buses > MLX5_SD_MAX_GROUP_SZ) + return false; + + /* Disconnect secondaries from the network */ + if (!MLX5_CAP_GEN(dev, eswitch_manager)) + return false; + if (!MLX5_CAP_GEN(dev, silent_mode)) + return false; + + /* RX steering from primary to secondaries */ + if (!MLX5_CAP_GEN(dev, cross_vhca_rqt)) + return false; + if (host_buses > MLX5_CAP_GEN_2(dev, max_rqt_vhca_id)) + return false; + + /* TX steering from secondaries to primary */ + if (!ft_create_alias_supported(dev)) + return false; + if (!MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + return false; + + return true; +} + +static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, + u8 *host_buses, u8 *sd_group) +{ + u32 out[MLX5_ST_SZ_DW(mpir_reg)]; + int err; + + err = mlx5_query_mpir_reg(dev, out); + if (err) + return err; + + err = mlx5_query_nic_vport_sd_group(dev, sd_group); + if (err) + return err; + + *sdm = MLX5_GET(mpir_reg, out, sdm); + *host_buses = MLX5_GET(mpir_reg, out, host_buses); + + return 0; +} + +static u32 mlx5_sd_group_id(struct mlx5_core_dev *dev, u8 sd_group) +{ + return (u32)((MLX5_CAP_GEN(dev, native_port_num) << 8) | sd_group); +} + +static int sd_init(struct mlx5_core_dev *dev) +{ + u8 host_buses, sd_group; + struct mlx5_sd *sd; + u32 group_id; + bool sdm; + int err; + + if (!MLX5_CAP_MCAM_REG(dev, mpir)) + return 0; + + err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + if (err) + return err; + + if (!sdm) + return 0; + + if (!sd_group) + return 0; + + group_id = mlx5_sd_group_id(dev, sd_group); + + if (!mlx5_sd_is_supported(dev, host_buses)) { + sd_warn(dev, "can't support requested netdev combining for group id 0x%x), skipping\n", + group_id); + return 0; + } + + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) + return -ENOMEM; + + sd->host_buses = host_buses; + sd->group_id = group_id; + + mlx5_set_sd(dev, sd); + + return 0; +} + +static void sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_set_sd(dev, NULL); + kfree(sd); +} + +static int sd_register(struct mlx5_core_dev *dev) +{ + struct mlx5_devcom_comp_dev *devcom, *pos; + struct mlx5_core_dev *peer, *primary; + struct mlx5_sd *sd, *primary_sd; + int err, i; + + sd = mlx5_get_sd(dev); + devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, + sd->group_id, NULL, dev); + if (!devcom) + return -ENOMEM; + + sd->devcom = devcom; + + if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses) + return 0; + + mlx5_devcom_comp_lock(devcom); + mlx5_devcom_comp_set_ready(devcom, true); + mlx5_devcom_comp_unlock(devcom); + + if (!mlx5_devcom_for_each_peer_begin(devcom)) { + err = -ENODEV; + goto err_devcom_unreg; + } + + primary = dev; + mlx5_devcom_for_each_peer_entry(devcom, peer, pos) + if (peer->pdev->bus->number < primary->pdev->bus->number) + primary = peer; + + primary_sd = mlx5_get_sd(primary); + primary_sd->primary = true; + i = 0; + /* loop the secondaries */ + mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) { + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + + primary_sd->secondaries[i++] = peer; + peer_sd->primary = false; + peer_sd->primary_dev = primary; + } + + mlx5_devcom_for_each_peer_end(devcom); + return 0; + +err_devcom_unreg: + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); + return err; +} + +static void sd_unregister(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); +} + +static int sd_cmd_set_primary(struct mlx5_core_dev *primary, u8 *alias_key) +{ + struct mlx5_cmd_allow_other_vhca_access_attr allow_attr = {}; + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *nic_ns; + struct mlx5_flow_table *ft; + int err; + + nic_ns = mlx5_get_flow_namespace(primary, MLX5_FLOW_NAMESPACE_EGRESS); + if (!nic_ns) + return -EOPNOTSUPP; + + ft = mlx5_create_flow_table(nic_ns, &ft_attr); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + return err; + } + sd->tx_ft = ft; + memcpy(allow_attr.access_key, alias_key, ACCESS_KEY_LEN); + allow_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + allow_attr.obj_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + + err = mlx5_cmd_allow_other_vhca_access(primary, &allow_attr); + if (err) { + mlx5_core_err(primary, "Failed to allow other vhca access err=%d\n", + err); + mlx5_destroy_flow_table(ft); + return err; + } + + return 0; +} + +static void sd_cmd_unset_primary(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + + mlx5_destroy_flow_table(sd->tx_ft); +} + +static int sd_secondary_create_alias_ft(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + struct mlx5_flow_table *ft, + u32 *obj_id, u8 *alias_key) +{ + u32 aliased_object_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + u16 vhca_id_to_be_accessed = MLX5_CAP_GEN(primary, vhca_id); + struct mlx5_cmd_alias_obj_create_attr alias_attr = {}; + int ret; + + memcpy(alias_attr.access_key, alias_key, ACCESS_KEY_LEN); + alias_attr.obj_id = aliased_object_id; + alias_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + alias_attr.vhca_id = vhca_id_to_be_accessed; + ret = mlx5_cmd_alias_obj_create(secondary, &alias_attr, obj_id); + if (ret) { + mlx5_core_err(secondary, "Failed to create alias object err=%d\n", + ret); + return ret; + } + + return 0; +} + +static void sd_secondary_destroy_alias_ft(struct mlx5_core_dev *secondary) +{ + struct mlx5_sd *sd = mlx5_get_sd(secondary); + + mlx5_cmd_alias_obj_destroy(secondary, sd->alias_obj_id, + MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS); +} + +static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + u8 *alias_key) +{ + struct mlx5_sd *primary_sd = mlx5_get_sd(primary); + struct mlx5_sd *sd = mlx5_get_sd(secondary); + int err; + + err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1); + if (err) + return err; + + err = sd_secondary_create_alias_ft(secondary, primary, primary_sd->tx_ft, + &sd->alias_obj_id, alias_key); + if (err) + goto err_unset_silent; + + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, false); + if (err) + goto err_destroy_alias_ft; + + return 0; + +err_destroy_alias_ft: + sd_secondary_destroy_alias_ft(secondary); +err_unset_silent: + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); + return err; +} + +static void sd_cmd_unset_secondary(struct mlx5_core_dev *secondary) +{ + mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true); + sd_secondary_destroy_alias_ft(secondary); + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); +} + +static void sd_print_group(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_core_dev *pos; + int i; + + sd_info(primary, "group id %#x, primary %s, vhca %#x\n", + sd->group_id, pci_name(primary->pdev), + MLX5_CAP_GEN(primary, vhca_id)); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_info(primary, "group id %#x, secondary_%d %s, vhca %#x\n", + sd->group_id, i - 1, pci_name(pos->pdev), + MLX5_CAP_GEN(pos, vhca_id)); +} + +static ssize_t dev_read(struct file *filp, char __user *buf, size_t count, + loff_t *pos) +{ + struct mlx5_core_dev *dev; + char tbuf[32]; + int ret; + + dev = filp->private_data; + ret = snprintf(tbuf, sizeof(tbuf), "%s vhca %#x\n", pci_name(dev->pdev), + MLX5_CAP_GEN(dev, vhca_id)); + + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static const struct file_operations dev_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = dev_read, +}; + +int mlx5_sd_init(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *primary, *pos, *to; + struct mlx5_sd *sd = mlx5_get_sd(dev); + u8 alias_key[ACCESS_KEY_LEN]; + int err, i; + + err = sd_init(dev); + if (err) + return err; + + sd = mlx5_get_sd(dev); + if (!sd) + return 0; + + err = sd_register(dev); + if (err) + goto err_sd_cleanup; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return 0; + + primary = mlx5_sd_get_primary(dev); + + for (i = 0; i < ACCESS_KEY_LEN; i++) + alias_key[i] = get_random_u8(); + + err = sd_cmd_set_primary(primary, alias_key); + if (err) + goto err_sd_unregister; + + sd->dfs = debugfs_create_dir("multi-pf", mlx5_debugfs_get_dev_root(primary)); + debugfs_create_x32("group_id", 0400, sd->dfs, &sd->group_id); + debugfs_create_file("primary", 0400, sd->dfs, primary, &dev_fops); + + mlx5_sd_for_each_secondary(i, primary, pos) { + char name[32]; + + err = sd_cmd_set_secondary(pos, primary, alias_key); + if (err) + goto err_unset_secondaries; + + snprintf(name, sizeof(name), "secondary_%d", i - 1); + debugfs_create_file(name, 0400, sd->dfs, pos, &dev_fops); + + } + + sd_info(primary, "group id %#x, size %d, combined\n", + sd->group_id, mlx5_devcom_comp_get_size(sd->devcom)); + sd_print_group(primary); + + return 0; + +err_unset_secondaries: + to = pos; + mlx5_sd_for_each_secondary_to(i, primary, to, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); + debugfs_remove_recursive(sd->dfs); +err_sd_unregister: + sd_unregister(dev); +err_sd_cleanup: + sd_cleanup(dev); + return err; +} + +void mlx5_sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary, *pos; + int i; + + if (!sd) + return; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + goto out; + + primary = mlx5_sd_get_primary(dev); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); + debugfs_remove_recursive(sd->dfs); + + sd_info(primary, "group id %#x, uncombined\n", sd->group_id); +out: + sd_unregister(dev); + sd_cleanup(dev); +} + +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary; + + if (!sd) + return adev; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return NULL; + + primary = mlx5_sd_get_primary(dev); + if (dev == primary) + return adev; + + return &primary->priv.adev[idx]->adev; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h new file mode 100644 index 000000000000..137efaf9aabc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_LIB_SD_H__ +#define __MLX5_LIB_SD_H__ + +#define MLX5_SD_MAX_GROUP_SZ 2 + +struct mlx5_sd; + +struct mlx5_core_dev *mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx); +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix); +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix); +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix); +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx); + +int mlx5_sd_init(struct mlx5_core_dev *dev); +void mlx5_sd_cleanup(struct mlx5_core_dev *dev); + +#define mlx5_sd_for_each_dev_from_to(i, primary, ix_from, to, pos) \ + for (i = ix_from; \ + (pos = mlx5_sd_primary_get_peer(primary, i)) && pos != (to); i++) + +#define mlx5_sd_for_each_dev(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, NULL, pos) + +#define mlx5_sd_for_each_dev_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, to, pos) + +#define mlx5_sd_for_each_secondary(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, NULL, pos) + +#define mlx5_sd_for_each_secondary_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, to, pos) + +#endif /* __MLX5_LIB_SD_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c index 253d7ad9b809..8b63968bbee9 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c @@ -124,6 +124,41 @@ static void mlxbf_gige_get_pauseparam(struct net_device *netdev, pause->tx_pause = 1; } +static bool mlxbf_gige_llu_counters_enabled(struct mlxbf_gige *priv) +{ + u32 data; + + if (priv->hw_version == MLXBF_GIGE_VERSION_BF2) { + data = readl(priv->llu_base + MLXBF_GIGE_BF2_LLU_GENERAL_CONFIG); + if (data & MLXBF_GIGE_BF2_LLU_COUNTERS_EN) + return true; + } else { + data = readl(priv->llu_base + MLXBF_GIGE_BF3_LLU_GENERAL_CONFIG); + if (data & MLXBF_GIGE_BF3_LLU_COUNTERS_EN) + return true; + } + + return false; +} + +static void mlxbf_gige_get_pause_stats(struct net_device *netdev, + struct ethtool_pause_stats *pause_stats) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + u64 data_lo, data_hi; + + /* Read LLU counters to provide stats only if counters are enabled */ + if (mlxbf_gige_llu_counters_enabled(priv)) { + data_lo = readl(priv->llu_base + MLXBF_GIGE_TX_PAUSE_CNT_LO); + data_hi = readl(priv->llu_base + MLXBF_GIGE_TX_PAUSE_CNT_HI); + pause_stats->tx_pause_frames = (data_hi << 32) | data_lo; + + data_lo = readl(priv->llu_base + MLXBF_GIGE_RX_PAUSE_CNT_LO); + data_hi = readl(priv->llu_base + MLXBF_GIGE_RX_PAUSE_CNT_HI); + pause_stats->rx_pause_frames = (data_hi << 32) | data_lo; + } +} + const struct ethtool_ops mlxbf_gige_ethtool_ops = { .get_link = ethtool_op_get_link, .get_ringparam = mlxbf_gige_get_ringparam, @@ -134,6 +169,7 @@ const struct ethtool_ops mlxbf_gige_ethtool_ops = { .get_ethtool_stats = mlxbf_gige_get_ethtool_stats, .nway_reset = phy_ethtool_nway_reset, .get_pauseparam = mlxbf_gige_get_pauseparam, + .get_pause_stats = mlxbf_gige_get_pause_stats, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index cd0973229c9b..98a8681c21b9 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -99,4 +99,34 @@ #define MLXBF_GIGE_100M_IPG_SIZE 119 #define MLXBF_GIGE_10M_IPG_SIZE 1199 +/* Offsets into OOB LLU block for pause frame counters */ +#define MLXBF_GIGE_BF2_TX_PAUSE_CNT_HI 0x33d8 +#define MLXBF_GIGE_BF2_TX_PAUSE_CNT_LO 0x33dc +#define MLXBF_GIGE_BF2_RX_PAUSE_CNT_HI 0x3210 +#define MLXBF_GIGE_BF2_RX_PAUSE_CNT_LO 0x3214 + +#define MLXBF_GIGE_BF3_TX_PAUSE_CNT_HI 0x3a88 +#define MLXBF_GIGE_BF3_TX_PAUSE_CNT_LO 0x3a8c +#define MLXBF_GIGE_BF3_RX_PAUSE_CNT_HI 0x38c0 +#define MLXBF_GIGE_BF3_RX_PAUSE_CNT_LO 0x38c4 + +#define MLXBF_GIGE_TX_PAUSE_CNT_HI ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_TX_PAUSE_CNT_HI : \ + MLXBF_GIGE_BF3_TX_PAUSE_CNT_HI) +#define MLXBF_GIGE_TX_PAUSE_CNT_LO ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_TX_PAUSE_CNT_LO : \ + MLXBF_GIGE_BF3_TX_PAUSE_CNT_LO) +#define MLXBF_GIGE_RX_PAUSE_CNT_HI ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_RX_PAUSE_CNT_HI : \ + MLXBF_GIGE_BF3_RX_PAUSE_CNT_HI) +#define MLXBF_GIGE_RX_PAUSE_CNT_LO ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_RX_PAUSE_CNT_LO : \ + MLXBF_GIGE_BF3_RX_PAUSE_CNT_LO) + +#define MLXBF_GIGE_BF2_LLU_GENERAL_CONFIG 0x2110 +#define MLXBF_GIGE_BF3_LLU_GENERAL_CONFIG 0x2030 + +#define MLXBF_GIGE_BF2_LLU_COUNTERS_EN BIT(0) +#define MLXBF_GIGE_BF3_LLU_COUNTERS_EN BIT(4) + #endif /* !defined(__MLXBF_GIGE_REGS_H__) */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ecde2086c703..bb642e9bb6cf 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -176,13 +176,15 @@ MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16); MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, - unsigned int counter_index, u64 *packets, - u64 *bytes) + unsigned int counter_index, bool clear, + u64 *packets, u64 *bytes) { + enum mlxsw_reg_mgpc_opcode op = clear ? MLXSW_REG_MGPC_OPCODE_CLEAR : + MLXSW_REG_MGPC_OPCODE_NOP; char mgpc_pl[MLXSW_REG_MGPC_LEN]; int err; - mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP, + mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, op, MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 898d24232935..3beb5d0847ab 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -706,8 +706,8 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool is_member, bool untagged); int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, - unsigned int counter_index, u64 *packets, - u64 *bytes); + unsigned int counter_index, bool clear, + u64 *packets, u64 *bytes); int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int *p_counter_index); void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index b01b000bc71c..3e70cee4d2f3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -1024,7 +1024,7 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, rulei = mlxsw_sp_acl_rule_rulei(rule); if (rulei->counter_valid) { err = mlxsw_sp_flow_counter_get(mlxsw_sp, rulei->counter_index, - ¤t_packets, + false, ¤t_packets, ¤t_bytes); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index c8a356accdf8..ca80af06465f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -1181,9 +1181,11 @@ static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable) char ratr_pl[MLXSW_REG_RATR_LEN]; struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_nexthop *nh; + unsigned int n_done = 0; u32 adj_hash_index = 0; u32 adj_index = 0; u32 adj_size = 0; + int err; mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { if (!mlxsw_sp_nexthop_is_forward(nh) || @@ -1192,15 +1194,27 @@ static int mlxsw_sp_dpipe_table_adj_counters_update(void *priv, bool enable) mlxsw_sp_nexthop_indexes(nh, &adj_index, &adj_size, &adj_hash_index); - if (enable) - mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); - else - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + if (enable) { + err = mlxsw_sp_nexthop_counter_enable(mlxsw_sp, nh); + if (err) + goto err_counter_enable; + } else { + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); + } mlxsw_sp_nexthop_eth_update(mlxsw_sp, adj_index + adj_hash_index, nh, true, ratr_pl); + n_done++; } return 0; + +err_counter_enable: + mlxsw_sp_nexthop_for_each(nh, mlxsw_sp->router) { + if (!n_done--) + break; + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); + } + return err; } static u64 diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c index 221aa6a474eb..01d81ae3662a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c @@ -361,7 +361,7 @@ static int mlxsw_sp_mr_tcam_route_stats(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_mr_tcam_route *route = route_priv; return mlxsw_sp_flow_counter_get(mlxsw_sp, route->counter_index, - packets, bytes); + false, packets, bytes); } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 87617df694ab..40ba314fbc72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -19,6 +19,7 @@ #include <linux/net_namespace.h> #include <linux/mutex.h> #include <linux/genalloc.h> +#include <linux/xarray.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> @@ -2251,7 +2252,7 @@ int mlxsw_sp_neigh_counter_get(struct mlxsw_sp *mlxsw_sp, return -EINVAL; return mlxsw_sp_flow_counter_get(mlxsw_sp, neigh_entry->counter_index, - p_counter, NULL); + false, p_counter, NULL); } static struct mlxsw_sp_neigh_entry * @@ -3049,6 +3050,8 @@ struct mlxsw_sp_nexthop_key { struct fib_nh *fib_nh; }; +struct mlxsw_sp_nexthop_counter; + struct mlxsw_sp_nexthop { struct list_head neigh_list_node; /* member of neigh entry list */ struct list_head crif_list_node; @@ -3080,8 +3083,8 @@ struct mlxsw_sp_nexthop { struct mlxsw_sp_neigh_entry *neigh_entry; struct mlxsw_sp_ipip_entry *ipip_entry; }; - unsigned int counter_index; - bool counter_valid; + struct mlxsw_sp_nexthop_counter *counter; + u32 id; /* NH ID for members of a NH object group. */ }; static struct net_device * @@ -3106,8 +3109,10 @@ struct mlxsw_sp_nexthop_group_info { int sum_norm_weight; u8 adj_index_valid:1, gateway:1, /* routes using the group use a gateway */ - is_resilient:1; + is_resilient:1, + hw_stats:1; struct list_head list; /* member in nh_res_grp_list */ + struct xarray nexthop_counters; struct mlxsw_sp_nexthop nexthops[] __counted_by(count); }; @@ -3151,39 +3156,148 @@ struct mlxsw_sp_nexthop_group { bool can_destroy; }; -void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, +struct mlxsw_sp_nexthop_counter { + unsigned int counter_index; + refcount_t ref_count; +}; + +static struct mlxsw_sp_nexthop_counter * +mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_nexthop_counter *nhct; + int err; + + nhct = kzalloc(sizeof(*nhct), GFP_KERNEL); + if (!nhct) + return ERR_PTR(-ENOMEM); + + err = mlxsw_sp_flow_counter_alloc(mlxsw_sp, &nhct->counter_index); + if (err) + goto err_counter_alloc; + + refcount_set(&nhct->ref_count, 1); + return nhct; + +err_counter_alloc: + kfree(nhct); + return ERR_PTR(err); +} + +static void +mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_counter *nhct) +{ + mlxsw_sp_flow_counter_free(mlxsw_sp, nhct->counter_index); + kfree(nhct); +} + +static struct mlxsw_sp_nexthop_counter * +mlxsw_sp_nexthop_sh_counter_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_nexthop_group *nh_grp = nh->nhgi->nh_grp; + struct mlxsw_sp_nexthop_counter *nhct; + void *ptr; + int err; + + nhct = xa_load(&nh_grp->nhgi->nexthop_counters, nh->id); + if (nhct) { + refcount_inc(&nhct->ref_count); + return nhct; + } + + nhct = mlxsw_sp_nexthop_counter_alloc(mlxsw_sp); + if (IS_ERR(nhct)) + return nhct; + + ptr = xa_store(&nh_grp->nhgi->nexthop_counters, nh->id, nhct, + GFP_KERNEL); + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + goto err_store; + } + + return nhct; + +err_store: + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nhct); + return ERR_PTR(err); +} + +static void mlxsw_sp_nexthop_sh_counter_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_nexthop_group *nh_grp = nh->nhgi->nh_grp; + struct mlxsw_sp_nexthop_counter *nhct; + + nhct = xa_load(&nh_grp->nhgi->nexthop_counters, nh->id); + if (WARN_ON(!nhct)) + return; + + if (!refcount_dec_and_test(&nhct->ref_count)) + return; + + xa_erase(&nh_grp->nhgi->nexthop_counters, nh->id); + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nhct); +} + +int mlxsw_sp_nexthop_counter_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { + const char *table_adj = MLXSW_SP_DPIPE_TABLE_NAME_ADJ; + struct mlxsw_sp_nexthop_counter *nhct; struct devlink *devlink; + bool dpipe_stats; + + if (nh->counter) + return 0; devlink = priv_to_devlink(mlxsw_sp->core); - if (!devlink_dpipe_table_counter_enabled(devlink, - MLXSW_SP_DPIPE_TABLE_NAME_ADJ)) - return; + dpipe_stats = devlink_dpipe_table_counter_enabled(devlink, table_adj); + if (!(nh->nhgi->hw_stats || dpipe_stats)) + return 0; - if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &nh->counter_index)) - return; + if (nh->id) + nhct = mlxsw_sp_nexthop_sh_counter_get(mlxsw_sp, nh); + else + nhct = mlxsw_sp_nexthop_counter_alloc(mlxsw_sp); + if (IS_ERR(nhct)) + return PTR_ERR(nhct); - nh->counter_valid = true; + nh->counter = nhct; + return 0; } -void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +void mlxsw_sp_nexthop_counter_disable(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { - if (!nh->counter_valid) + if (!nh->counter) return; - mlxsw_sp_flow_counter_free(mlxsw_sp, nh->counter_index); - nh->counter_valid = false; + + if (nh->id) + mlxsw_sp_nexthop_sh_counter_put(mlxsw_sp, nh); + else + mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh->counter); + nh->counter = NULL; +} + +static int mlxsw_sp_nexthop_counter_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + if (nh->nhgi->hw_stats) + return mlxsw_sp_nexthop_counter_enable(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); + return 0; } int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, u64 *p_counter) { - if (!nh->counter_valid) + if (!nh->counter) return -EINVAL; - return mlxsw_sp_flow_counter_get(mlxsw_sp, nh->counter_index, - p_counter, NULL); + return mlxsw_sp_flow_counter_get(mlxsw_sp, nh->counter->counter_index, + true, p_counter, NULL); } struct mlxsw_sp_nexthop *mlxsw_sp_nexthop_next(struct mlxsw_sp_router *router, @@ -3656,8 +3770,9 @@ static int __mlxsw_sp_nexthop_eth_update(struct mlxsw_sp *mlxsw_sp, WARN_ON_ONCE(1); return -EINVAL; } - if (nh->counter_valid) - mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter_index, true); + if (nh->counter) + mlxsw_reg_ratr_counter_pack(ratr_pl, nh->counter->counter_index, + true); else mlxsw_reg_ratr_counter_pack(ratr_pl, 0, false); @@ -3744,6 +3859,7 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp, nh = &nhgi->nexthops[i]; if (!nh->should_offload) { + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); nh->offloaded = 0; continue; } @@ -3751,6 +3867,10 @@ mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp, if (nh->update || reallocate) { int err = 0; + err = mlxsw_sp_nexthop_counter_update(mlxsw_sp, nh); + if (err) + return err; + err = mlxsw_sp_nexthop_update(mlxsw_sp, adj_index, nh, true, ratr_pl); if (err) @@ -4507,7 +4627,10 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; - mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); + err = mlxsw_sp_nexthop_counter_enable(mlxsw_sp, nh); + if (err) + goto err_counter_enable; + list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); if (!dev) @@ -4531,7 +4654,8 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, err_nexthop_neigh_init: list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); +err_counter_enable: mlxsw_sp_nexthop_remove(mlxsw_sp, nh); return err; } @@ -4541,7 +4665,7 @@ static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); } @@ -5006,9 +5130,9 @@ mlxsw_sp_nexthop_obj_init(struct mlxsw_sp *mlxsw_sp, break; } - mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); nh->ifindex = dev->ifindex; + nh->id = nh_obj->id; err = mlxsw_sp_nexthop_type_init(mlxsw_sp, nh, dev); if (err) @@ -5030,7 +5154,6 @@ mlxsw_sp_nexthop_obj_init(struct mlxsw_sp *mlxsw_sp, err_type_init: list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); return err; } @@ -5041,7 +5164,7 @@ static void mlxsw_sp_nexthop_obj_fini(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop_obj_blackhole_fini(mlxsw_sp, nh); mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); nh->should_offload = 0; } @@ -5053,6 +5176,7 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group_info *nhgi; struct mlxsw_sp_nexthop *nh; bool is_resilient = false; + bool hw_stats = false; unsigned int nhs; int err, i; @@ -5062,9 +5186,11 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, break; case NH_NOTIFIER_INFO_TYPE_GRP: nhs = info->nh_grp->num_nh; + hw_stats = info->nh_grp->hw_stats; break; case NH_NOTIFIER_INFO_TYPE_RES_TABLE: nhs = info->nh_res_table->num_nh_buckets; + hw_stats = info->nh_res_table->hw_stats; is_resilient = true; break; default: @@ -5079,6 +5205,10 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, nhgi->gateway = mlxsw_sp_nexthop_obj_is_gateway(mlxsw_sp, info); nhgi->is_resilient = is_resilient; nhgi->count = nhs; + nhgi->hw_stats = hw_stats; + + xa_init_flags(&nhgi->nexthop_counters, XA_FLAGS_ALLOC1); + for (i = 0; i < nhgi->count; i++) { struct nh_notifier_single_info *nh_obj; int weight; @@ -5161,6 +5291,8 @@ mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); WARN_ON_ONCE(nhgi->adj_index_valid); + WARN_ON(!xa_empty(&nhgi->nexthop_counters)); + xa_destroy(&nhgi->nexthop_counters); kfree(nhgi); } @@ -5300,6 +5432,43 @@ err_out: return err; } +static int mlxsw_sp_nexthop_obj_res_group_pre(struct mlxsw_sp *mlxsw_sp, + struct nh_notifier_info *info) +{ + struct nh_notifier_grp_info *grp_info = info->nh_grp; + struct mlxsw_sp_nexthop_group_info *nhgi; + struct mlxsw_sp_nexthop_group *nh_grp; + int err; + int i; + + nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id); + if (!nh_grp) + return 0; + nhgi = nh_grp->nhgi; + + if (nhgi->hw_stats == grp_info->hw_stats) + return 0; + + nhgi->hw_stats = grp_info->hw_stats; + + for (i = 0; i < nhgi->count; i++) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; + + if (nh->offloaded) + nh->update = 1; + } + + err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + if (err) + goto err_group_refresh; + + return 0; + +err_group_refresh: + nhgi->hw_stats = !grp_info->hw_stats; + return err; +} + static int mlxsw_sp_nexthop_obj_new(struct mlxsw_sp *mlxsw_sp, struct nh_notifier_info *info) { @@ -5476,6 +5645,79 @@ err_nexthop_obj_init: return err; } +static void +mlxsw_sp_nexthop_obj_mp_hw_stats_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group_info *nhgi, + struct nh_notifier_grp_hw_stats_info *info) +{ + int nhi; + + for (nhi = 0; nhi < info->num_nh; nhi++) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[nhi]; + u64 packets; + int err; + + err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &packets); + if (err) + continue; + + nh_grp_hw_stats_report_delta(info, nhi, packets); + } +} + +static void +mlxsw_sp_nexthop_obj_res_hw_stats_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group_info *nhgi, + struct nh_notifier_grp_hw_stats_info *info) +{ + int nhi = -1; + int bucket; + + for (bucket = 0; bucket < nhgi->count; bucket++) { + struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[bucket]; + u64 packets; + int err; + + if (nhi == -1 || info->stats[nhi].id != nh->id) { + for (nhi = 0; nhi < info->num_nh; nhi++) + if (info->stats[nhi].id == nh->id) + break; + if (WARN_ON_ONCE(nhi == info->num_nh)) { + nhi = -1; + continue; + } + } + + err = mlxsw_sp_nexthop_counter_get(mlxsw_sp, nh, &packets); + if (err) + continue; + + nh_grp_hw_stats_report_delta(info, nhi, packets); + } +} + +static void mlxsw_sp_nexthop_obj_hw_stats_get(struct mlxsw_sp *mlxsw_sp, + struct nh_notifier_info *info) +{ + struct mlxsw_sp_nexthop_group_info *nhgi; + struct mlxsw_sp_nexthop_group *nh_grp; + + if (info->type != NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS) + return; + + nh_grp = mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, info->id); + if (!nh_grp) + return; + nhgi = nh_grp->nhgi; + + if (nhgi->is_resilient) + mlxsw_sp_nexthop_obj_res_hw_stats_get(mlxsw_sp, nhgi, + info->nh_grp_hw_stats); + else + mlxsw_sp_nexthop_obj_mp_hw_stats_get(mlxsw_sp, nhgi, + info->nh_grp_hw_stats); +} + static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -5491,6 +5733,10 @@ static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb, mutex_lock(&router->lock); switch (event) { + case NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE: + err = mlxsw_sp_nexthop_obj_res_group_pre(router->mlxsw_sp, + info); + break; case NEXTHOP_EVENT_REPLACE: err = mlxsw_sp_nexthop_obj_new(router->mlxsw_sp, info); break; @@ -5501,6 +5747,9 @@ static int mlxsw_sp_nexthop_obj_event(struct notifier_block *nb, err = mlxsw_sp_nexthop_obj_bucket_replace(router->mlxsw_sp, info); break; + case NEXTHOP_EVENT_HW_STATS_REPORT_DELTA: + mlxsw_sp_nexthop_obj_hw_stats_get(router->mlxsw_sp, info); + break; default: break; } @@ -6734,7 +6983,10 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, #if IS_ENABLED(CONFIG_IPV6) nh->neigh_tbl = &nd_tbl; #endif - mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); + + err = mlxsw_sp_nexthop_counter_enable(mlxsw_sp, nh); + if (err) + return err; list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -6750,7 +7002,7 @@ static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, err_nexthop_type_init: list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); return err; } @@ -6759,7 +7011,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); list_del(&nh->router_list_node); - mlxsw_sp_nexthop_counter_free(mlxsw_sp, nh); + mlxsw_sp_nexthop_counter_disable(mlxsw_sp, nh); } static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index ed3b628caafe..0432c7cc6b07 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -156,10 +156,10 @@ int mlxsw_sp_nexthop_counter_get(struct mlxsw_sp *mlxsw_sp, int mlxsw_sp_nexthop_eth_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, struct mlxsw_sp_nexthop *nh, bool force, char *ratr_pl); -void mlxsw_sp_nexthop_counter_alloc(struct mlxsw_sp *mlxsw_sp, +int mlxsw_sp_nexthop_counter_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh); -void mlxsw_sp_nexthop_counter_free(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh); +void mlxsw_sp_nexthop_counter_disable(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh); static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1, const union mlxsw_sp_l3addr *addr2) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 4af285918ea2..75868b3f548e 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5, list) { if ((vid == 0 || mact_entry->vid == vid) && ether_addr_equal(addr, mact_entry->mac)) { + sparx5_mact_forget(sparx5, addr, mact_entry->vid); + list_del(&mact_entry->list); devm_kfree(sparx5->dev, mact_entry); - - sparx5_mact_forget(sparx5, addr, mact_entry->vid); } } mutex_unlock(&sparx5->mact_lock); diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h index 9ffef2e06885..2ccc2c2a06e3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic.h +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -76,6 +76,8 @@ int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); int ionic_adminq_post_wait_nomsg(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); void ionic_adminq_netdev_err_print(struct ionic_lif *lif, u8 opcode, u8 status, int err); +bool ionic_notifyq_service(struct ionic_cq *cq); +bool ionic_adminq_service(struct ionic_cq *cq); int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); int ionic_dev_cmd_wait_nomsg(struct ionic *ionic, unsigned long max_wait); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 91327ef670c7..c3ae11a48024 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -113,8 +113,8 @@ static const struct debugfs_reg32 intr_ctrl_regs[] = { void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) { struct dentry *qcq_dentry, *q_dentry, *cq_dentry; - struct dentry *intr_dentry, *stats_dentry; struct ionic_dev *idev = &lif->ionic->idev; + struct dentry *intr_dentry, *stats_dentry; struct debugfs_regset32 *intr_ctrl_regset; struct ionic_intr_info *intr = &qcq->intr; struct debugfs_blob_wrapper *desc_blob; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 746072b4dbd0..874499337132 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -629,43 +629,25 @@ int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, cq->desc_size = desc_size; cq->tail_idx = 0; cq->done_color = 1; + cq->idev = &lif->ionic->idev; return 0; } -void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa) -{ - struct ionic_cq_info *cur; - unsigned int i; - - cq->base = base; - cq->base_pa = base_pa; - - for (i = 0, cur = cq->info; i < cq->num_descs; i++, cur++) - cur->cq_desc = base + (i * cq->desc_size); -} - -void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q) -{ - cq->bound_q = q; -} - unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, ionic_cq_cb cb, ionic_cq_done_cb done_cb, void *done_arg) { - struct ionic_cq_info *cq_info; unsigned int work_done = 0; if (work_to_do == 0) return 0; - cq_info = &cq->info[cq->tail_idx]; - while (cb(cq, cq_info)) { + while (cb(cq)) { if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; + cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1); - cq_info = &cq->info[cq->tail_idx]; if (++work_done >= work_to_do) break; @@ -692,7 +674,6 @@ int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, return -EINVAL; q->lif = lif; - q->idev = idev; q->index = index; q->num_descs = num_descs; q->desc_size = desc_size; @@ -706,53 +687,11 @@ int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, return 0; } -void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell) { - struct ionic_desc_info *cur; - unsigned int i; - - q->base = base; - q->base_pa = base_pa; - - for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) - cur->desc = base + (i * q->desc_size); -} - -void ionic_q_cmb_map(struct ionic_queue *q, void __iomem *base, dma_addr_t base_pa) -{ - struct ionic_desc_info *cur; - unsigned int i; - - q->cmb_base = base; - q->cmb_base_pa = base_pa; - - for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) - cur->cmb_desc = base + (i * q->desc_size); -} - -void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) -{ - struct ionic_desc_info *cur; - unsigned int i; - - q->sg_base = base; - q->sg_base_pa = base_pa; - - for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) - cur->sg_desc = base + (i * q->sg_desc_size); -} - -void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, - void *cb_arg) -{ - struct ionic_desc_info *desc_info; struct ionic_lif *lif = q->lif; struct device *dev = q->dev; - desc_info = &q->info[q->head_idx]; - desc_info->cb = cb; - desc_info->cb_arg = cb_arg; - q->head_idx = (q->head_idx + 1) & (q->num_descs - 1); dev_dbg(dev, "lif=%d qname=%s qid=%d qtype=%d p_index=%d ringdb=%d\n", @@ -771,7 +710,7 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, } } -static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) +bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) { unsigned int mask, tail, head; @@ -781,37 +720,3 @@ static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) return ((pos - tail) & mask) < ((head - tail) & mask); } - -void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, - unsigned int stop_index) -{ - struct ionic_desc_info *desc_info; - ionic_desc_cb cb; - void *cb_arg; - u16 index; - - /* check for empty queue */ - if (q->tail_idx == q->head_idx) - return; - - /* stop index must be for a descriptor that is not yet completed */ - if (unlikely(!ionic_q_is_posted(q, stop_index))) - dev_err(q->dev, - "ionic stop is not posted %s stop %u tail %u head %u\n", - q->name, stop_index, q->tail_idx, q->head_idx); - - do { - desc_info = &q->info[q->tail_idx]; - index = q->tail_idx; - q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - - cb = desc_info->cb; - cb_arg = desc_info->cb_arg; - - desc_info->cb = NULL; - desc_info->cb_arg = NULL; - - if (cb) - cb(q, desc_info, cq_info, cb_arg); - } while (index != stop_index); -} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index bfcfc2d7bcbd..f30eee4a5a80 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -16,9 +16,10 @@ #define IONIC_MAX_TX_DESC 8192 #define IONIC_MAX_RX_DESC 16384 #define IONIC_MIN_TXRX_DESC 64 -#define IONIC_DEF_TXRX_DESC 4096 +#define IONIC_DEF_TXRX_DESC 1024 #define IONIC_RX_FILL_THRESHOLD 16 #define IONIC_RX_FILL_DIV 8 +#define IONIC_TSO_DESCS_NEEDED 44 /* 64K TSO @1500B */ #define IONIC_LIFS_MAX 1024 #define IONIC_WATCHDOG_SECS 5 #define IONIC_ITR_COAL_USEC_DEFAULT 64 @@ -121,11 +122,13 @@ static_assert(sizeof(struct ionic_log_event) == 64); /* I/O */ static_assert(sizeof(struct ionic_txq_desc) == 16); static_assert(sizeof(struct ionic_txq_sg_desc) == 128); +static_assert(sizeof(struct ionic_txq_sg_desc_v1) == 256); static_assert(sizeof(struct ionic_txq_comp) == 16); static_assert(sizeof(struct ionic_rxq_desc) == 16); static_assert(sizeof(struct ionic_rxq_sg_desc) == 128); static_assert(sizeof(struct ionic_rxq_comp) == 16); +static_assert(sizeof(struct ionic_rxq_comp) == sizeof(struct ionic_txq_comp)); /* SR/IOV */ static_assert(sizeof(struct ionic_vf_setattr_cmd) == 64); @@ -174,21 +177,8 @@ struct ionic_dev { struct ionic_devinfo dev_info; }; -struct ionic_cq_info { - union { - void *cq_desc; - struct ionic_admin_comp *admincq; - struct ionic_notifyq_event *notifyq; - }; -}; - struct ionic_queue; struct ionic_qcq; -struct ionic_desc_info; - -typedef void (*ionic_desc_cb)(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - struct ionic_cq_info *cq_info, void *cb_arg); #define IONIC_MAX_BUF_LEN ((u16)-1) #define IONIC_PAGE_SIZE PAGE_SIZE @@ -208,28 +198,25 @@ struct ionic_buf_info { u32 len; }; -#define IONIC_MAX_FRAGS (1 + IONIC_TX_MAX_SG_ELEMS_V1) +#define IONIC_TX_MAX_FRAGS (1 + IONIC_TX_MAX_SG_ELEMS_V1) +#define IONIC_RX_MAX_FRAGS (1 + IONIC_RX_MAX_SG_ELEMS) -struct ionic_desc_info { - union { - void *desc; - struct ionic_txq_desc *txq_desc; - struct ionic_rxq_desc *rxq_desc; - struct ionic_admin_cmd *adminq_desc; - }; - void __iomem *cmb_desc; - union { - void *sg_desc; - struct ionic_txq_sg_desc *txq_sg_desc; - struct ionic_rxq_sg_desc *rxq_sgl_desc; - }; +struct ionic_tx_desc_info { unsigned int bytes; unsigned int nbufs; - struct ionic_buf_info bufs[MAX_SKB_FRAGS + 1]; - ionic_desc_cb cb; - void *cb_arg; + struct sk_buff *skb; struct xdp_frame *xdpf; enum xdp_action act; + struct ionic_buf_info bufs[MAX_SKB_FRAGS + 1]; +}; + +struct ionic_rx_desc_info { + unsigned int nbufs; + struct ionic_buf_info bufs[IONIC_RX_MAX_FRAGS]; +}; + +struct ionic_admin_desc_info { + void *ctx; }; #define IONIC_QUEUE_NAME_MAX_SZ 16 @@ -237,7 +224,12 @@ struct ionic_desc_info { struct ionic_queue { struct device *dev; struct ionic_lif *lif; - struct ionic_desc_info *info; + union { + void *info; + struct ionic_tx_desc_info *tx_info; + struct ionic_rx_desc_info *rx_info; + struct ionic_admin_desc_info *admin_info; + }; u64 dbval; unsigned long dbell_deadline; unsigned long dbell_jiffies; @@ -247,29 +239,33 @@ struct ionic_queue { unsigned int num_descs; unsigned int max_sg_elems; u64 features; - u64 drop; - struct ionic_dev *idev; unsigned int type; unsigned int hw_index; unsigned int hw_type; + bool xdp_flush; union { void *base; struct ionic_txq_desc *txq; struct ionic_rxq_desc *rxq; struct ionic_admin_cmd *adminq; }; - void __iomem *cmb_base; + union { + void __iomem *cmb_base; + struct ionic_txq_desc __iomem *cmb_txq; + struct ionic_rxq_desc __iomem *cmb_rxq; + }; union { void *sg_base; struct ionic_txq_sg_desc *txq_sgl; + struct ionic_txq_sg_desc_v1 *txq_sgl_v1; struct ionic_rxq_sg_desc *rxq_sgl; }; struct xdp_rxq_info *xdp_rxq_info; struct ionic_queue *partner; - bool xdp_flush; dma_addr_t base_pa; dma_addr_t cmb_base_pa; dma_addr_t sg_base_pa; + u64 drop; unsigned int desc_size; unsigned int sg_desc_size; unsigned int pid; @@ -291,7 +287,6 @@ struct ionic_intr_info { struct ionic_cq { struct ionic_lif *lif; - struct ionic_cq_info *info; struct ionic_queue *bound_q; struct ionic_intr_info *bound_intr; u16 tail_idx; @@ -300,6 +295,7 @@ struct ionic_cq { unsigned int desc_size; void *base; dma_addr_t base_pa; + struct ionic_dev *idev; } ____cacheline_aligned_in_smp; struct ionic; @@ -374,23 +370,20 @@ int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, unsigned int num_descs, size_t desc_size); void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa); void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q); -typedef bool (*ionic_cq_cb)(struct ionic_cq *cq, struct ionic_cq_info *cq_info); +typedef bool (*ionic_cq_cb)(struct ionic_cq *cq); typedef void (*ionic_cq_done_cb)(void *done_arg); unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, ionic_cq_cb cb, ionic_cq_done_cb done_cb, void *done_arg); +unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do); int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, struct ionic_queue *q, unsigned int index, const char *name, unsigned int num_descs, size_t desc_size, size_t sg_desc_size, unsigned int pid); -void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); -void ionic_q_cmb_map(struct ionic_queue *q, void __iomem *base, dma_addr_t base_pa); -void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); -void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, - void *cb_arg); -void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, - unsigned int stop_index); +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell); +bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos); + int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 1496893c28be..7f0c6cdc375e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -52,15 +52,20 @@ static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q); static void ionic_dim_work(struct work_struct *work) { struct dim *dim = container_of(work, struct dim, work); - struct ionic_intr_info *intr; struct dim_cq_moder cur_moder; + struct ionic_intr_info *intr; struct ionic_qcq *qcq; struct ionic_lif *lif; + struct ionic_queue *q; u32 new_coal; - cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); qcq = container_of(dim, struct ionic_qcq, dim); - lif = qcq->q.lif; + q = &qcq->q; + if (q->type == IONIC_QTYPE_RXQ) + cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + else + cur_moder = net_dim_get_tx_moderation(dim->mode, dim->profile_ix); + lif = q->lif; new_coal = ionic_coal_usec_to_hw(lif->ionic, cur_moder.usec); new_coal = new_coal ? new_coal : 1; @@ -428,8 +433,6 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) ionic_xdp_unregister_rxq_info(&qcq->q); ionic_qcq_intr_free(lif, qcq); - vfree(qcq->cq.info); - qcq->cq.info = NULL; vfree(qcq->q.info); qcq->q.info = NULL; } @@ -533,14 +536,11 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, unsigned int num_descs, unsigned int desc_size, unsigned int cq_desc_size, unsigned int sg_desc_size, + unsigned int desc_info_size, unsigned int pid, struct ionic_qcq **qcq) { struct ionic_dev *idev = &lif->ionic->idev; struct device *dev = lif->ionic->dev; - void *q_base, *cq_base, *sg_base; - dma_addr_t cq_base_pa = 0; - dma_addr_t sg_base_pa = 0; - dma_addr_t q_base_pa = 0; struct ionic_qcq *new; int err; @@ -556,7 +556,7 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, new->q.dev = dev; new->flags = flags; - new->q.info = vcalloc(num_descs, sizeof(*new->q.info)); + new->q.info = vcalloc(num_descs, desc_info_size); if (!new->q.info) { netdev_err(lif->netdev, "Cannot allocate queue info\n"); err = -ENOMEM; @@ -575,19 +575,12 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, err = ionic_alloc_qcq_interrupt(lif, new); if (err) - goto err_out; - - new->cq.info = vcalloc(num_descs, sizeof(*new->cq.info)); - if (!new->cq.info) { - netdev_err(lif->netdev, "Cannot allocate completion queue info\n"); - err = -ENOMEM; - goto err_out_free_irq; - } + goto err_out_free_q_info; err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size); if (err) { netdev_err(lif->netdev, "Cannot initialize completion queue\n"); - goto err_out_free_cq_info; + goto err_out_free_irq; } if (flags & IONIC_QCQ_F_NOTIFYQ) { @@ -605,16 +598,15 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, if (!new->q_base) { netdev_err(lif->netdev, "Cannot allocate qcq DMA memory\n"); err = -ENOMEM; - goto err_out_free_cq_info; + goto err_out_free_irq; } - q_base = PTR_ALIGN(new->q_base, PAGE_SIZE); - q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); - ionic_q_map(&new->q, q_base, q_base_pa); - - cq_base = PTR_ALIGN(q_base + q_size, PAGE_SIZE); - cq_base_pa = ALIGN(new->q_base_pa + q_size, PAGE_SIZE); - ionic_cq_map(&new->cq, cq_base, cq_base_pa); - ionic_cq_bind(&new->cq, &new->q); + new->q.base = PTR_ALIGN(new->q_base, PAGE_SIZE); + new->q.base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); + + /* Base the NotifyQ cq.base off of the ALIGNed q.base */ + new->cq.base = PTR_ALIGN(new->q.base + q_size, PAGE_SIZE); + new->cq.base_pa = ALIGN(new->q_base_pa + q_size, PAGE_SIZE); + new->cq.bound_q = &new->q; } else { /* regular DMA q descriptors */ new->q_size = PAGE_SIZE + (num_descs * desc_size); @@ -623,11 +615,10 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, if (!new->q_base) { netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n"); err = -ENOMEM; - goto err_out_free_cq_info; + goto err_out_free_irq; } - q_base = PTR_ALIGN(new->q_base, PAGE_SIZE); - q_base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); - ionic_q_map(&new->q, q_base, q_base_pa); + new->q.base = PTR_ALIGN(new->q_base, PAGE_SIZE); + new->q.base_pa = ALIGN(new->q_base_pa, PAGE_SIZE); if (flags & IONIC_QCQ_F_CMB_RINGS) { /* on-chip CMB q descriptors */ @@ -652,7 +643,8 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, } new->cmb_q_base_pa -= idev->phy_cmb_pages; - ionic_q_cmb_map(&new->q, new->cmb_q_base, new->cmb_q_base_pa); + new->q.cmb_base = new->cmb_q_base; + new->q.cmb_base_pa = new->cmb_q_base_pa; } /* cq DMA descriptors */ @@ -664,10 +656,9 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, err = -ENOMEM; goto err_out_free_q; } - cq_base = PTR_ALIGN(new->cq_base, PAGE_SIZE); - cq_base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE); - ionic_cq_map(&new->cq, cq_base, cq_base_pa); - ionic_cq_bind(&new->cq, &new->q); + new->cq.base = PTR_ALIGN(new->cq_base, PAGE_SIZE); + new->cq.base_pa = ALIGN(new->cq_base_pa, PAGE_SIZE); + new->cq.bound_q = &new->q; } if (flags & IONIC_QCQ_F_SG) { @@ -679,13 +670,12 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, err = -ENOMEM; goto err_out_free_cq; } - sg_base = PTR_ALIGN(new->sg_base, PAGE_SIZE); - sg_base_pa = ALIGN(new->sg_base_pa, PAGE_SIZE); - ionic_q_sg_map(&new->q, sg_base, sg_base_pa); + new->q.sg_base = PTR_ALIGN(new->sg_base, PAGE_SIZE); + new->q.sg_base_pa = ALIGN(new->sg_base_pa, PAGE_SIZE); } INIT_WORK(&new->dim.work, ionic_dim_work); - new->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + new->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_CQE; *qcq = new; @@ -699,8 +689,6 @@ err_out_free_q: ionic_put_cmb(lif, new->cmb_pgid, new->cmb_order); } dma_free_coherent(dev, new->q_size, new->q_base, new->q_base_pa); -err_out_free_cq_info: - vfree(new->cq.info); err_out_free_irq: if (flags & IONIC_QCQ_F_INTR) { devm_free_irq(dev, new->intr.vector, &new->napi); @@ -726,7 +714,9 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif) IONIC_ADMINQ_LENGTH, sizeof(struct ionic_admin_cmd), sizeof(struct ionic_admin_comp), - 0, lif->kern_pid, &lif->adminqcq); + 0, + sizeof(struct ionic_admin_desc_info), + lif->kern_pid, &lif->adminqcq); if (err) return err; ionic_debugfs_add_qcq(lif, lif->adminqcq); @@ -737,7 +727,9 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif) flags, IONIC_NOTIFYQ_LENGTH, sizeof(struct ionic_notifyq_cmd), sizeof(union ionic_notifyq_comp), - 0, lif->kern_pid, &lif->notifyqcq); + 0, + sizeof(struct ionic_admin_desc_info), + lif->kern_pid, &lif->notifyqcq); if (err) goto err_out; ionic_debugfs_add_qcq(lif, lif->notifyqcq); @@ -955,6 +947,7 @@ int ionic_lif_create_hwstamp_txq(struct ionic_lif *lif) err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, txq_i, "hwstamp_tx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_tx_desc_info), lif->kern_pid, &txq); if (err) goto err_qcq_alloc; @@ -1014,6 +1007,7 @@ int ionic_lif_create_hwstamp_rxq(struct ionic_lif *lif) err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, rxq_i, "hwstamp_rx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_rx_desc_info), lif->kern_pid, &rxq); if (err) goto err_qcq_alloc; @@ -1167,71 +1161,6 @@ int ionic_lif_set_hwstamp_rxfilt(struct ionic_lif *lif, u64 pkt_class) return ionic_lif_add_hwstamp_rxfilt(lif, pkt_class); } -static bool ionic_notifyq_service(struct ionic_cq *cq, - struct ionic_cq_info *cq_info) -{ - union ionic_notifyq_comp *comp = cq_info->cq_desc; - struct ionic_deferred_work *work; - struct net_device *netdev; - struct ionic_queue *q; - struct ionic_lif *lif; - u64 eid; - - q = cq->bound_q; - lif = q->info[0].cb_arg; - netdev = lif->netdev; - eid = le64_to_cpu(comp->event.eid); - - /* Have we run out of new completions to process? */ - if ((s64)(eid - lif->last_eid) <= 0) - return false; - - lif->last_eid = eid; - - dev_dbg(lif->ionic->dev, "notifyq event:\n"); - dynamic_hex_dump("event ", DUMP_PREFIX_OFFSET, 16, 1, - comp, sizeof(*comp), true); - - switch (le16_to_cpu(comp->event.ecode)) { - case IONIC_EVENT_LINK_CHANGE: - ionic_link_status_check_request(lif, CAN_NOT_SLEEP); - break; - case IONIC_EVENT_RESET: - if (lif->ionic->idev.fw_status_ready && - !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && - !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - netdev_err(lif->netdev, "Reset event dropped\n"); - clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); - } else { - work->type = IONIC_DW_TYPE_LIF_RESET; - ionic_lif_deferred_enqueue(&lif->deferred, work); - } - } - break; - default: - netdev_warn(netdev, "Notifyq event ecode=%d eid=%lld\n", - comp->event.ecode, eid); - break; - } - - return true; -} - -static bool ionic_adminq_service(struct ionic_cq *cq, - struct ionic_cq_info *cq_info) -{ - struct ionic_admin_comp *comp = cq_info->cq_desc; - - if (!color_match(comp->color, cq->done_color)) - return false; - - ionic_q_service(cq->bound_q, cq_info, le16_to_cpu(comp->comp_index)); - - return true; -} - static int ionic_adminq_napi(struct napi_struct *napi, int budget) { struct ionic_intr_info *intr = napi_to_cq(napi)->bound_intr; @@ -1262,8 +1191,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_rx_service, NULL, NULL); if (lif->hwstamp_txq) - tx_work = ionic_cq_service(&lif->hwstamp_txq->cq, budget, - ionic_tx_service, NULL, NULL); + tx_work = ionic_tx_cq_service(&lif->hwstamp_txq->cq, budget); work_done = max(max(n_work, a_work), max(rx_work, tx_work)); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -2106,6 +2034,7 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) for (i = 0; i < lif->nxqs; i++) { err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_tx_desc_info), lif->kern_pid, &lif->txqcqs[i]); if (err) goto err_out; @@ -2137,6 +2066,7 @@ static int ionic_txrx_alloc(struct ionic_lif *lif) for (i = 0; i < lif->nxqs; i++) { err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_rx_desc_info), lif->kern_pid, &lif->rxqcqs[i]); if (err) goto err_out; @@ -2954,7 +2884,6 @@ static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b) swap(a->cq.desc_size, b->cq.desc_size); swap(a->cq.base, b->cq.base); swap(a->cq.base_pa, b->cq.base_pa); - swap(a->cq.info, b->cq.info); swap(a->cq_base, b->cq_base); swap(a->cq_base_pa, b->cq_base_pa); swap(a->cq_size, b->cq_size); @@ -3018,6 +2947,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif, flags = IONIC_QCQ_F_TX_STATS | IONIC_QCQ_F_SG; err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, 4, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_tx_desc_info), lif->kern_pid, &lif->txqcqs[i]); if (err) goto err_out; @@ -3026,6 +2956,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif, flags = lif->txqcqs[i]->flags & ~IONIC_QCQ_F_INTR; err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_tx_desc_info), lif->kern_pid, &tx_qcqs[i]); if (err) goto err_out; @@ -3047,6 +2978,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif, flags = IONIC_QCQ_F_RX_STATS | IONIC_QCQ_F_SG; err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, 4, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_rx_desc_info), lif->kern_pid, &lif->rxqcqs[i]); if (err) goto err_out; @@ -3055,6 +2987,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif, flags = lif->rxqcqs[i]->flags & ~IONIC_QCQ_F_INTR; err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, num_desc, desc_sz, comp_sz, sg_desc_sz, + sizeof(struct ionic_rx_desc_info), lif->kern_pid, &rx_qcqs[i]); if (err) goto err_out; @@ -3629,7 +3562,7 @@ static int ionic_lif_notifyq_init(struct ionic_lif *lif) dev_dbg(dev, "notifyq->hw_index %d\n", q->hw_index); /* preset the callback info */ - q->info[0].cb_arg = lif; + q->admin_info[0].ctx = lif; qcq->flags |= IONIC_QCQ_F_INITED; @@ -3881,6 +3814,7 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif) union ionic_q_identity __iomem *q_ident; struct ionic *ionic = lif->ionic; struct ionic_dev *idev; + u16 max_frags; int qtype; int err; @@ -3948,17 +3882,16 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif) dev_dbg(ionic->dev, " qtype[%d].sg_desc_stride = %d\n", qtype, qti->sg_desc_stride); - if (qti->max_sg_elems >= IONIC_MAX_FRAGS) { - qti->max_sg_elems = IONIC_MAX_FRAGS - 1; - dev_dbg(ionic->dev, "limiting qtype %d max_sg_elems to IONIC_MAX_FRAGS-1 %d\n", - qtype, qti->max_sg_elems); - } + if (qtype == IONIC_QTYPE_TXQ) + max_frags = IONIC_TX_MAX_FRAGS; + else if (qtype == IONIC_QTYPE_RXQ) + max_frags = IONIC_RX_MAX_FRAGS; + else + max_frags = 1; - if (qti->max_sg_elems > MAX_SKB_FRAGS) { - qti->max_sg_elems = MAX_SKB_FRAGS; - dev_dbg(ionic->dev, "limiting qtype %d max_sg_elems to MAX_SKB_FRAGS %d\n", - qtype, qti->max_sg_elems); - } + qti->max_sg_elems = min_t(u16, max_frags - 1, MAX_SKB_FRAGS); + dev_dbg(ionic->dev, "qtype %d max_sg_elems %d\n", + qtype, qti->max_sg_elems); } } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 42006de8069d..08f4266fe2aa 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -71,25 +71,25 @@ struct ionic_qcq { void *q_base; dma_addr_t q_base_pa; u32 q_size; + u32 cq_size; void *cq_base; dma_addr_t cq_base_pa; - u32 cq_size; void *sg_base; dma_addr_t sg_base_pa; u32 sg_size; + unsigned int flags; void __iomem *cmb_q_base; phys_addr_t cmb_q_base_pa; u32 cmb_q_size; u32 cmb_pgid; u32 cmb_order; struct dim dim; + struct timer_list napi_deadline; struct ionic_queue q; struct ionic_cq cq; - struct ionic_intr_info intr; - struct timer_list napi_deadline; struct napi_struct napi; - unsigned int flags; struct ionic_qcq *napi_qcq; + struct ionic_intr_info intr; struct dentry *dentry; }; @@ -327,7 +327,7 @@ static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) static inline bool ionic_txq_hwstamp_enabled(struct ionic_queue *q) { - return unlikely(q->features & IONIC_TXQ_F_HWSTAMP); + return q->features & IONIC_TXQ_F_HWSTAMP; } void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 2f479de329fe..c1259324b0be 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -15,7 +15,7 @@ #include "ionic_debugfs.h" MODULE_DESCRIPTION(IONIC_DRV_DESCRIPTION); -MODULE_AUTHOR("Pensando Systems, Inc"); +MODULE_AUTHOR("Shannon Nelson <shannon.nelson@amd.com>"); MODULE_LICENSE("GPL"); static const char *ionic_error_to_str(enum ionic_status_code code) @@ -190,7 +190,8 @@ static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) static void ionic_adminq_flush(struct ionic_lif *lif) { - struct ionic_desc_info *desc_info; + struct ionic_admin_desc_info *desc_info; + struct ionic_admin_cmd *desc; unsigned long irqflags; struct ionic_queue *q; @@ -203,10 +204,10 @@ static void ionic_adminq_flush(struct ionic_lif *lif) q = &lif->adminqcq->q; while (q->tail_idx != q->head_idx) { - desc_info = &q->info[q->tail_idx]; - memset(desc_info->desc, 0, sizeof(union ionic_adminq_cmd)); - desc_info->cb = NULL; - desc_info->cb_arg = NULL; + desc = &q->adminq[q->tail_idx]; + desc_info = &q->admin_info[q->tail_idx]; + memset(desc, 0, sizeof(union ionic_adminq_cmd)); + desc_info->ctx = NULL; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); } spin_unlock_irqrestore(&lif->adminq_lock, irqflags); @@ -246,25 +247,93 @@ static int ionic_adminq_check_err(struct ionic_lif *lif, return err; } -static void ionic_adminq_cb(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - struct ionic_cq_info *cq_info, void *cb_arg) +bool ionic_notifyq_service(struct ionic_cq *cq) { - struct ionic_admin_ctx *ctx = cb_arg; + struct ionic_deferred_work *work; + union ionic_notifyq_comp *comp; + struct net_device *netdev; + struct ionic_queue *q; + struct ionic_lif *lif; + u64 eid; + + comp = &((union ionic_notifyq_comp *)cq->base)[cq->tail_idx]; + + q = cq->bound_q; + lif = q->admin_info[0].ctx; + netdev = lif->netdev; + eid = le64_to_cpu(comp->event.eid); + + /* Have we run out of new completions to process? */ + if ((s64)(eid - lif->last_eid) <= 0) + return false; + + lif->last_eid = eid; + + dev_dbg(lif->ionic->dev, "notifyq event:\n"); + dynamic_hex_dump("event ", DUMP_PREFIX_OFFSET, 16, 1, + comp, sizeof(*comp), true); + + switch (le16_to_cpu(comp->event.ecode)) { + case IONIC_EVENT_LINK_CHANGE: + ionic_link_status_check_request(lif, CAN_NOT_SLEEP); + break; + case IONIC_EVENT_RESET: + if (lif->ionic->idev.fw_status_ready && + !test_bit(IONIC_LIF_F_FW_RESET, lif->state) && + !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "Reset event dropped\n"); + clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state); + } else { + work->type = IONIC_DW_TYPE_LIF_RESET; + ionic_lif_deferred_enqueue(&lif->deferred, work); + } + } + break; + default: + netdev_warn(netdev, "Notifyq event ecode=%d eid=%lld\n", + comp->event.ecode, eid); + break; + } + + return true; +} + +bool ionic_adminq_service(struct ionic_cq *cq) +{ + struct ionic_admin_desc_info *desc_info; + struct ionic_queue *q = cq->bound_q; struct ionic_admin_comp *comp; + u16 index; - if (!ctx) - return; + comp = &((struct ionic_admin_comp *)cq->base)[cq->tail_idx]; + + if (!color_match(comp->color, cq->done_color)) + return false; + + /* check for empty queue */ + if (q->tail_idx == q->head_idx) + return false; - comp = cq_info->cq_desc; + do { + desc_info = &q->admin_info[q->tail_idx]; + index = q->tail_idx; + q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); + if (likely(desc_info->ctx)) { + struct ionic_admin_ctx *ctx = desc_info->ctx; - memcpy(&ctx->comp, comp, sizeof(*comp)); + memcpy(&ctx->comp, comp, sizeof(*comp)); - dev_dbg(q->dev, "comp admin queue command:\n"); - dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, - &ctx->comp, sizeof(ctx->comp), true); + dev_dbg(q->dev, "comp admin queue command:\n"); + dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx->comp, sizeof(ctx->comp), true); + complete_all(&ctx->work); + desc_info->ctx = NULL; + } + } while (index != le16_to_cpu(comp->comp_index)); - complete_all(&ctx->work); + return true; } bool ionic_adminq_poke_doorbell(struct ionic_queue *q) @@ -298,7 +367,8 @@ bool ionic_adminq_poke_doorbell(struct ionic_queue *q) int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { - struct ionic_desc_info *desc_info; + struct ionic_admin_desc_info *desc_info; + struct ionic_admin_cmd *desc; unsigned long irqflags; struct ionic_queue *q; int err = 0; @@ -320,14 +390,17 @@ int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) if (err) goto err_out; - desc_info = &q->info[q->head_idx]; - memcpy(desc_info->desc, &ctx->cmd, sizeof(ctx->cmd)); + desc_info = &q->admin_info[q->head_idx]; + desc_info->ctx = ctx; + + desc = &q->adminq[q->head_idx]; + memcpy(desc, &ctx->cmd, sizeof(ctx->cmd)); dev_dbg(&lif->netdev->dev, "post admin queue command:\n"); dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, &ctx->cmd, sizeof(ctx->cmd), true); - ionic_q_post(q, true, ionic_adminq_cb, ctx); + ionic_q_post(q, true); err_out: spin_unlock_irqrestore(&lif->adminq_lock, irqflags); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 56a7ad5bff17..5dba6d2d633c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -5,13 +5,12 @@ #include <linux/ipv6.h> #include <linux/if_vlan.h> #include <net/ip6_checksum.h> +#include <net/netdev_queues.h> #include "ionic.h" #include "ionic_lif.h" #include "ionic_txrx.h" -static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs); - static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t len); @@ -20,29 +19,26 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, size_t offset, size_t len); static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, - struct ionic_desc_info *desc_info); + struct ionic_tx_desc_info *desc_info); static void ionic_tx_clean(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - struct ionic_cq_info *cq_info, - void *cb_arg); + struct ionic_tx_desc_info *desc_info, + struct ionic_txq_comp *comp); -static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, - ionic_desc_cb cb_func, void *cb_arg) +static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell) { - ionic_q_post(q, ring_dbell, cb_func, cb_arg); + ionic_q_post(q, ring_dbell); } -static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, - ionic_desc_cb cb_func, void *cb_arg) +static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell) { - ionic_q_post(q, ring_dbell, cb_func, cb_arg); + ionic_q_post(q, ring_dbell); } bool ionic_txq_poke_doorbell(struct ionic_queue *q) { - unsigned long now, then, dif; struct netdev_queue *netdev_txq; + unsigned long now, then, dif; struct net_device *netdev; netdev = q->lif->netdev; @@ -100,9 +96,18 @@ bool ionic_rxq_poke_doorbell(struct ionic_queue *q) return true; } -static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) +static inline struct ionic_txq_sg_elem *ionic_tx_sg_elems(struct ionic_queue *q) +{ + if (likely(q->sg_desc_size == sizeof(struct ionic_txq_sg_desc_v1))) + return q->txq_sgl_v1[q->head_idx].elems; + else + return q->txq_sgl[q->head_idx].elems; +} + +static inline struct netdev_queue *q_to_ndq(struct net_device *netdev, + struct ionic_queue *q) { - return netdev_get_tx_queue(q->lif->netdev, q->index); + return netdev_get_tx_queue(netdev, q->index); } static void *ionic_rx_buf_va(struct ionic_buf_info *buf_info) @@ -123,38 +128,29 @@ static unsigned int ionic_rx_buf_size(struct ionic_buf_info *buf_info) static int ionic_rx_page_alloc(struct ionic_queue *q, struct ionic_buf_info *buf_info) { - struct net_device *netdev = q->lif->netdev; - struct ionic_rx_stats *stats; - struct device *dev; + struct device *dev = q->dev; + dma_addr_t dma_addr; struct page *page; - dev = q->dev; - stats = q_to_rx_stats(q); - - if (unlikely(!buf_info)) { - net_err_ratelimited("%s: %s invalid buf_info in alloc\n", - netdev->name, q->name); - return -EINVAL; - } - page = alloc_pages(IONIC_PAGE_GFP_MASK, 0); if (unlikely(!page)) { net_err_ratelimited("%s: %s page alloc failed\n", - netdev->name, q->name); - stats->alloc_err++; + dev_name(dev), q->name); + q_to_rx_stats(q)->alloc_err++; return -ENOMEM; } - buf_info->dma_addr = dma_map_page(dev, page, 0, - IONIC_PAGE_SIZE, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(dev, buf_info->dma_addr))) { + dma_addr = dma_map_page(dev, page, 0, + IONIC_PAGE_SIZE, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, dma_addr))) { __free_pages(page, 0); net_err_ratelimited("%s: %s dma map failed\n", - netdev->name, q->name); - stats->dma_map_err++; + dev_name(dev), q->name); + q_to_rx_stats(q)->dma_map_err++; return -EIO; } + buf_info->dma_addr = dma_addr; buf_info->page = page; buf_info->page_offset = 0; @@ -164,12 +160,11 @@ static int ionic_rx_page_alloc(struct ionic_queue *q, static void ionic_rx_page_free(struct ionic_queue *q, struct ionic_buf_info *buf_info) { - struct net_device *netdev = q->lif->netdev; struct device *dev = q->dev; if (unlikely(!buf_info)) { net_err_ratelimited("%s: %s invalid buf_info in free\n", - netdev->name, q->name); + dev_name(dev), q->name); return; } @@ -182,7 +177,7 @@ static void ionic_rx_page_free(struct ionic_queue *q, } static bool ionic_rx_buf_recycle(struct ionic_queue *q, - struct ionic_buf_info *buf_info, u32 used) + struct ionic_buf_info *buf_info, u32 len) { u32 size; @@ -194,7 +189,7 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q, if (page_to_nid(buf_info->page) != numa_mem_id()) return false; - size = ALIGN(used, q->xdp_rxq_info ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ); + size = ALIGN(len, q->xdp_rxq_info ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ); buf_info->page_offset += size; if (buf_info->page_offset >= IONIC_PAGE_SIZE) return false; @@ -204,95 +199,96 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q, return true; } -static struct sk_buff *ionic_rx_frags(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - unsigned int headroom, - unsigned int len, - unsigned int num_sg_elems, - bool synced) +static void ionic_rx_add_skb_frag(struct ionic_queue *q, + struct sk_buff *skb, + struct ionic_buf_info *buf_info, + u32 off, u32 len, + bool synced) +{ + if (!synced) + dma_sync_single_range_for_cpu(q->dev, ionic_rx_buf_pa(buf_info), + off, len, DMA_FROM_DEVICE); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + buf_info->page, buf_info->page_offset + off, + len, + IONIC_PAGE_SIZE); + + if (!ionic_rx_buf_recycle(q, buf_info, len)) { + dma_unmap_page(q->dev, buf_info->dma_addr, + IONIC_PAGE_SIZE, DMA_FROM_DEVICE); + buf_info->page = NULL; + } +} + +static struct sk_buff *ionic_rx_build_skb(struct ionic_queue *q, + struct ionic_rx_desc_info *desc_info, + unsigned int headroom, + unsigned int len, + unsigned int num_sg_elems, + bool synced) { - struct net_device *netdev = q->lif->netdev; struct ionic_buf_info *buf_info; - struct ionic_rx_stats *stats; - struct device *dev = q->dev; struct sk_buff *skb; unsigned int i; u16 frag_len; - stats = q_to_rx_stats(q); - buf_info = &desc_info->bufs[0]; - prefetchw(buf_info->page); skb = napi_get_frags(&q_to_qcq(q)->napi); if (unlikely(!skb)) { net_warn_ratelimited("%s: SKB alloc failed on %s!\n", - netdev->name, q->name); - stats->alloc_err++; + dev_name(q->dev), q->name); + q_to_rx_stats(q)->alloc_err++; return NULL; } - i = num_sg_elems + 1; - do { - if (unlikely(!buf_info->page)) { - dev_kfree_skb(skb); - return NULL; - } - - if (headroom) - frag_len = min_t(u16, len, IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN); - else - frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info)); - len -= frag_len; - - if (!synced) - dma_sync_single_range_for_cpu(dev, ionic_rx_buf_pa(buf_info), - headroom, frag_len, DMA_FROM_DEVICE); - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - buf_info->page, buf_info->page_offset + headroom, - frag_len, IONIC_PAGE_SIZE); - - if (!ionic_rx_buf_recycle(q, buf_info, frag_len)) { - dma_unmap_page(dev, buf_info->dma_addr, - IONIC_PAGE_SIZE, DMA_FROM_DEVICE); - buf_info->page = NULL; - } - - /* only needed on the first buffer */ - if (headroom) - headroom = 0; + if (headroom) + frag_len = min_t(u16, len, + IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN); + else + frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info)); - buf_info++; + if (unlikely(!buf_info->page)) + goto err_bad_buf_page; + ionic_rx_add_skb_frag(q, skb, buf_info, headroom, frag_len, synced); + len -= frag_len; + buf_info++; - i--; - } while (i > 0); + for (i = 0; i < num_sg_elems; i++, buf_info++) { + if (unlikely(!buf_info->page)) + goto err_bad_buf_page; + frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info)); + ionic_rx_add_skb_frag(q, skb, buf_info, 0, frag_len, synced); + len -= frag_len; + } return skb; + +err_bad_buf_page: + dev_kfree_skb(skb); + return NULL; } -static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q, - struct ionic_desc_info *desc_info, +static struct sk_buff *ionic_rx_copybreak(struct net_device *netdev, + struct ionic_queue *q, + struct ionic_rx_desc_info *desc_info, unsigned int headroom, unsigned int len, bool synced) { - struct net_device *netdev = q->lif->netdev; struct ionic_buf_info *buf_info; - struct ionic_rx_stats *stats; struct device *dev = q->dev; struct sk_buff *skb; - stats = q_to_rx_stats(q); - buf_info = &desc_info->bufs[0]; skb = napi_alloc_skb(&q_to_qcq(q)->napi, len); if (unlikely(!skb)) { net_warn_ratelimited("%s: SKB alloc failed on %s!\n", - netdev->name, q->name); - stats->alloc_err++; + dev_name(dev), q->name); + q_to_rx_stats(q)->alloc_err++; return NULL; } @@ -309,13 +305,13 @@ static struct sk_buff *ionic_rx_copybreak(struct ionic_queue *q, headroom, len, DMA_FROM_DEVICE); skb_put(skb, len); - skb->protocol = eth_type_trans(skb, q->lif->netdev); + skb->protocol = eth_type_trans(skb, netdev); return skb; } static void ionic_xdp_tx_desc_clean(struct ionic_queue *q, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { unsigned int nbufs = desc_info->nbufs; struct ionic_buf_info *buf_info; @@ -349,12 +345,11 @@ static void ionic_xdp_tx_desc_clean(struct ionic_queue *q, desc_info->act = 0; } -static int ionic_xdp_post_frame(struct net_device *netdev, - struct ionic_queue *q, struct xdp_frame *frame, +static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame, enum xdp_action act, struct page *page, int off, bool ring_doorbell) { - struct ionic_desc_info *desc_info; + struct ionic_tx_desc_info *desc_info; struct ionic_buf_info *buf_info; struct ionic_tx_stats *stats; struct ionic_txq_desc *desc; @@ -362,16 +357,14 @@ static int ionic_xdp_post_frame(struct net_device *netdev, dma_addr_t dma_addr; u64 cmd; - desc_info = &q->info[q->head_idx]; - desc = desc_info->txq_desc; + desc_info = &q->tx_info[q->head_idx]; + desc = &q->txq[q->head_idx]; buf_info = desc_info->bufs; stats = q_to_tx_stats(q); dma_addr = ionic_tx_map_single(q, frame->data, len); - if (dma_mapping_error(q->dev, dma_addr)) { - stats->dma_map_err++; + if (!dma_addr) return -EIO; - } buf_info->dma_addr = dma_addr; buf_info->len = len; buf_info->page = page; @@ -391,11 +384,10 @@ static int ionic_xdp_post_frame(struct net_device *netdev, bi = &buf_info[1]; sinfo = xdp_get_shared_info_from_frame(frame); frag = sinfo->frags; - elem = desc_info->txq_sg_desc->elems; + elem = ionic_tx_sg_elems(q); for (i = 0; i < sinfo->nr_frags; i++, frag++, bi++) { dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag)); - if (dma_mapping_error(q->dev, dma_addr)) { - stats->dma_map_err++; + if (!dma_addr) { ionic_tx_desc_unmap_bufs(q, desc_info); return -EIO; } @@ -422,7 +414,7 @@ static int ionic_xdp_post_frame(struct net_device *netdev, stats->pkts++; stats->bytes += len; - ionic_txq_post(q, ring_doorbell, ionic_tx_clean, NULL); + ionic_txq_post(q, ring_doorbell); return 0; } @@ -458,14 +450,16 @@ int ionic_xdp_xmit(struct net_device *netdev, int n, txq_trans_cond_update(nq); if (netif_tx_queue_stopped(nq) || - unlikely(ionic_maybe_stop_tx(txq, 1))) { + !netif_txq_maybe_stop(q_to_ndq(netdev, txq), + ionic_q_space_avail(txq), + 1, 1)) { __netif_tx_unlock(nq); return -EIO; } space = min_t(int, n, ionic_q_space_avail(txq)); for (nxmit = 0; nxmit < space ; nxmit++) { - if (ionic_xdp_post_frame(netdev, txq, xdp_frames[nxmit], + if (ionic_xdp_post_frame(txq, xdp_frames[nxmit], XDP_REDIRECT, virt_to_page(xdp_frames[nxmit]->data), 0, false)) { @@ -478,7 +472,9 @@ int ionic_xdp_xmit(struct net_device *netdev, int n, ionic_dbell_ring(lif->kern_dbpage, txq->hw_type, txq->dbval | txq->head_idx); - ionic_maybe_stop_tx(txq, 4); + netif_txq_maybe_stop(q_to_ndq(netdev, txq), + ionic_q_space_avail(txq), + 4, 4); __netif_tx_unlock(nq); return nxmit; @@ -571,7 +567,9 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, txq_trans_cond_update(nq); if (netif_tx_queue_stopped(nq) || - unlikely(ionic_maybe_stop_tx(txq, 1))) { + !netif_txq_maybe_stop(q_to_ndq(netdev, txq), + ionic_q_space_avail(txq), + 1, 1)) { __netif_tx_unlock(nq); goto out_xdp_abort; } @@ -579,7 +577,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats, dma_unmap_page(rxq->dev, buf_info->dma_addr, IONIC_PAGE_SIZE, DMA_FROM_DEVICE); - err = ionic_xdp_post_frame(netdev, txq, xdpf, XDP_TX, + err = ionic_xdp_post_frame(txq, xdpf, XDP_TX, buf_info->page, buf_info->page_offset, true); @@ -624,21 +622,19 @@ out_xdp_abort: } static void ionic_rx_clean(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - struct ionic_cq_info *cq_info, - void *cb_arg) + struct ionic_rx_desc_info *desc_info, + struct ionic_rxq_comp *comp) { struct net_device *netdev = q->lif->netdev; struct ionic_qcq *qcq = q_to_qcq(q); struct ionic_rx_stats *stats; - struct ionic_rxq_comp *comp; struct bpf_prog *xdp_prog; unsigned int headroom; struct sk_buff *skb; + bool synced = false; + bool use_copybreak; u16 len; - comp = cq_info->cq_desc + qcq->cq.desc_size - sizeof(*comp); - stats = q_to_rx_stats(q); if (comp->status) { @@ -651,16 +647,20 @@ static void ionic_rx_clean(struct ionic_queue *q, stats->bytes += len; xdp_prog = READ_ONCE(q->lif->xdp_prog); - if (xdp_prog && - ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len)) - return; + if (xdp_prog) { + if (ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len)) + return; + synced = true; + } headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0; - if (len <= q->lif->rx_copybreak) - skb = ionic_rx_copybreak(q, desc_info, headroom, len, !!xdp_prog); + use_copybreak = len <= q->lif->rx_copybreak; + if (use_copybreak) + skb = ionic_rx_copybreak(netdev, q, desc_info, + headroom, len, synced); else - skb = ionic_rx_frags(q, desc_info, headroom, len, - comp->num_sg_elems, !!xdp_prog); + skb = ionic_rx_build_skb(q, desc_info, headroom, len, + comp->num_sg_elems, synced); if (unlikely(!skb)) { stats->dropped++; @@ -712,7 +712,7 @@ static void ionic_rx_clean(struct ionic_queue *q, u64 hwstamp; cq_desc_hwstamp = - cq_info->cq_desc + + (void *)comp + qcq->cq.desc_size - sizeof(struct ionic_rxq_comp) - IONIC_HWSTAMP_CQ_NEGOFFSET; @@ -727,19 +727,19 @@ static void ionic_rx_clean(struct ionic_queue *q, } } - if (len <= q->lif->rx_copybreak) + if (use_copybreak) napi_gro_receive(&qcq->napi, skb); else napi_gro_frags(&qcq->napi); } -bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) +bool ionic_rx_service(struct ionic_cq *cq) { + struct ionic_rx_desc_info *desc_info; struct ionic_queue *q = cq->bound_q; - struct ionic_desc_info *desc_info; struct ionic_rxq_comp *comp; - comp = cq_info->cq_desc + cq->desc_size - sizeof(*comp); + comp = &((struct ionic_rxq_comp *)cq->base)[cq->tail_idx]; if (!color_match(comp->pkt_type_color, cq->done_color)) return false; @@ -751,31 +751,29 @@ bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) if (q->tail_idx != le16_to_cpu(comp->comp_index)) return false; - desc_info = &q->info[q->tail_idx]; + desc_info = &q->rx_info[q->tail_idx]; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); /* clean the related q entry, only one per qc completion */ - ionic_rx_clean(q, desc_info, cq_info, desc_info->cb_arg); - - desc_info->cb = NULL; - desc_info->cb_arg = NULL; + ionic_rx_clean(q, desc_info, comp); return true; } static inline void ionic_write_cmb_desc(struct ionic_queue *q, - void __iomem *cmb_desc, void *desc) { - if (q_to_qcq(q)->flags & IONIC_QCQ_F_CMB_RINGS) - memcpy_toio(cmb_desc, desc, q->desc_size); + /* Since Rx and Tx descriptors are the same size, we can + * save an instruction or two and skip the qtype check. + */ + if (unlikely(q_to_qcq(q)->flags & IONIC_QCQ_F_CMB_RINGS)) + memcpy_toio(&q->cmb_txq[q->head_idx], desc, sizeof(q->cmb_txq[0])); } void ionic_rx_fill(struct ionic_queue *q) { struct net_device *netdev = q->lif->netdev; - struct ionic_desc_info *desc_info; - struct ionic_rxq_sg_desc *sg_desc; + struct ionic_rx_desc_info *desc_info; struct ionic_rxq_sg_elem *sg_elem; struct ionic_buf_info *buf_info; unsigned int fill_threshold; @@ -803,8 +801,8 @@ void ionic_rx_fill(struct ionic_queue *q) nfrags = 0; remain_len = len; - desc_info = &q->info[q->head_idx]; - desc = desc_info->desc; + desc = &q->rxq[q->head_idx]; + desc_info = &q->rx_info[q->head_idx]; buf_info = &desc_info->bufs[0]; if (!buf_info->page) { /* alloc a new buffer? */ @@ -833,9 +831,8 @@ void ionic_rx_fill(struct ionic_queue *q) nfrags++; /* fill sg descriptors - buf[1..n] */ - sg_desc = desc_info->sg_desc; - for (j = 0; remain_len > 0 && j < q->max_sg_elems; j++) { - sg_elem = &sg_desc->elems[j]; + sg_elem = q->rxq_sgl[q->head_idx].elems; + for (j = 0; remain_len > 0 && j < q->max_sg_elems; j++, sg_elem++) { if (!buf_info->page) { /* alloc a new sg buffer? */ if (unlikely(ionic_rx_page_alloc(q, buf_info))) { sg_elem->addr = 0; @@ -853,18 +850,16 @@ void ionic_rx_fill(struct ionic_queue *q) } /* clear end sg element as a sentinel */ - if (j < q->max_sg_elems) { - sg_elem = &sg_desc->elems[j]; + if (j < q->max_sg_elems) memset(sg_elem, 0, sizeof(*sg_elem)); - } desc->opcode = (nfrags > 1) ? IONIC_RXQ_DESC_OPCODE_SG : IONIC_RXQ_DESC_OPCODE_SIMPLE; desc_info->nbufs = nfrags; - ionic_write_cmb_desc(q, desc_info->cmb_desc, desc); + ionic_write_cmb_desc(q, desc); - ionic_rxq_post(q, false, ionic_rx_clean, NULL); + ionic_rxq_post(q, false); } ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, @@ -879,21 +874,19 @@ void ionic_rx_fill(struct ionic_queue *q) void ionic_rx_empty(struct ionic_queue *q) { - struct ionic_desc_info *desc_info; + struct ionic_rx_desc_info *desc_info; struct ionic_buf_info *buf_info; unsigned int i, j; for (i = 0; i < q->num_descs; i++) { - desc_info = &q->info[i]; - for (j = 0; j < IONIC_RX_MAX_SG_ELEMS + 1; j++) { + desc_info = &q->rx_info[i]; + for (j = 0; j < ARRAY_SIZE(desc_info->bufs); j++) { buf_info = &desc_info->bufs[j]; if (buf_info->page) ionic_rx_page_free(q, buf_info); } desc_info->nbufs = 0; - desc_info->cb = NULL; - desc_info->cb_arg = NULL; } q->head_idx = 0; @@ -938,16 +931,10 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) { struct ionic_qcq *qcq = napi_to_qcq(napi); struct ionic_cq *cq = napi_to_cq(napi); - struct ionic_dev *idev; - struct ionic_lif *lif; u32 work_done = 0; u32 flags = 0; - lif = cq->bound_q->lif; - idev = &lif->ionic->idev; - - work_done = ionic_cq_service(cq, budget, - ionic_tx_service, NULL, NULL); + work_done = ionic_tx_cq_service(cq, budget); if (unlikely(!budget)) return budget; @@ -960,7 +947,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) if (work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; - ionic_intr_credits(idev->intr_ctrl, + ionic_intr_credits(cq->idev->intr_ctrl, cq->bound_intr->index, work_done, flags); } @@ -983,17 +970,12 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) { struct ionic_qcq *qcq = napi_to_qcq(napi); struct ionic_cq *cq = napi_to_cq(napi); - struct ionic_dev *idev; - struct ionic_lif *lif; u32 work_done = 0; u32 flags = 0; if (unlikely(!budget)) return budget; - lif = cq->bound_q->lif; - idev = &lif->ionic->idev; - work_done = ionic_cq_service(cq, budget, ionic_rx_service, NULL, NULL); @@ -1008,7 +990,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) if (work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; - ionic_intr_credits(idev->intr_ctrl, + ionic_intr_credits(cq->idev->intr_ctrl, cq->bound_intr->index, work_done, flags); } @@ -1025,7 +1007,6 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; struct ionic_qcq *txqcq; - struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; bool resched = false; @@ -1034,12 +1015,10 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) u32 flags = 0; lif = rxcq->bound_q->lif; - idev = &lif->ionic->idev; txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; - tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, - ionic_tx_service, NULL, NULL); + tx_work_done = ionic_tx_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT); if (unlikely(!budget)) return budget; @@ -1058,7 +1037,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) if (rx_work_done || flags) { flags |= IONIC_INTR_CRED_RESET_COALESCE; - ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, + ionic_intr_credits(rxcq->idev->intr_ctrl, rxcq->bound_intr->index, tx_work_done + rx_work_done, flags); } @@ -1075,15 +1054,14 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t len) { - struct ionic_tx_stats *stats = q_to_tx_stats(q); struct device *dev = q->dev; dma_addr_t dma_addr; dma_addr = dma_map_single(dev, data, len, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma_addr)) { net_warn_ratelimited("%s: DMA single map failed on %s!\n", - q->lif->netdev->name, q->name); - stats->dma_map_err++; + dev_name(dev), q->name); + q_to_tx_stats(q)->dma_map_err++; return 0; } return dma_addr; @@ -1093,24 +1071,23 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, const skb_frag_t *frag, size_t offset, size_t len) { - struct ionic_tx_stats *stats = q_to_tx_stats(q); struct device *dev = q->dev; dma_addr_t dma_addr; dma_addr = skb_frag_dma_map(dev, frag, offset, len, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma_addr)) { net_warn_ratelimited("%s: DMA frag map failed on %s!\n", - q->lif->netdev->name, q->name); - stats->dma_map_err++; + dev_name(dev), q->name); + q_to_tx_stats(q)->dma_map_err++; + return 0; } return dma_addr; } static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { struct ionic_buf_info *buf_info = desc_info->bufs; - struct ionic_tx_stats *stats = q_to_tx_stats(q); struct device *dev = q->dev; dma_addr_t dma_addr; unsigned int nfrags; @@ -1118,10 +1095,8 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb, int frag_idx; dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); - if (dma_mapping_error(dev, dma_addr)) { - stats->dma_map_err++; + if (!dma_addr) return -EIO; - } buf_info->dma_addr = dma_addr; buf_info->len = skb_headlen(skb); buf_info++; @@ -1130,10 +1105,8 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb, nfrags = skb_shinfo(skb)->nr_frags; for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) { dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag)); - if (dma_mapping_error(dev, dma_addr)) { - stats->dma_map_err++; + if (!dma_addr) goto dma_fail; - } buf_info->dma_addr = dma_addr; buf_info->len = skb_frag_size(frag); buf_info++; @@ -1151,12 +1124,13 @@ dma_fail: dma_unmap_page(dev, buf_info->dma_addr, buf_info->len, DMA_TO_DEVICE); } - dma_unmap_single(dev, buf_info->dma_addr, buf_info->len, DMA_TO_DEVICE); + dma_unmap_single(dev, desc_info->bufs[0].dma_addr, + desc_info->bufs[0].len, DMA_TO_DEVICE); return -EIO; } static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { struct ionic_buf_info *buf_info = desc_info->bufs; struct device *dev = q->dev; @@ -1165,25 +1139,23 @@ static void ionic_tx_desc_unmap_bufs(struct ionic_queue *q, if (!desc_info->nbufs) return; - dma_unmap_single(dev, (dma_addr_t)buf_info->dma_addr, + dma_unmap_single(dev, buf_info->dma_addr, buf_info->len, DMA_TO_DEVICE); buf_info++; for (i = 1; i < desc_info->nbufs; i++, buf_info++) - dma_unmap_page(dev, (dma_addr_t)buf_info->dma_addr, + dma_unmap_page(dev, buf_info->dma_addr, buf_info->len, DMA_TO_DEVICE); desc_info->nbufs = 0; } static void ionic_tx_clean(struct ionic_queue *q, - struct ionic_desc_info *desc_info, - struct ionic_cq_info *cq_info, - void *cb_arg) + struct ionic_tx_desc_info *desc_info, + struct ionic_txq_comp *comp) { struct ionic_tx_stats *stats = q_to_tx_stats(q); struct ionic_qcq *qcq = q_to_qcq(q); - struct sk_buff *skb = cb_arg; - u16 qi; + struct sk_buff *skb; if (desc_info->xdpf) { ionic_xdp_tx_desc_clean(q->partner, desc_info); @@ -1197,19 +1169,18 @@ static void ionic_tx_clean(struct ionic_queue *q, ionic_tx_desc_unmap_bufs(q, desc_info); + skb = desc_info->skb; if (!skb) return; - qi = skb_get_queue_mapping(skb); - - if (ionic_txq_hwstamp_enabled(q)) { - if (cq_info) { + if (unlikely(ionic_txq_hwstamp_enabled(q))) { + if (comp) { struct skb_shared_hwtstamps hwts = {}; __le64 *cq_desc_hwstamp; u64 hwstamp; cq_desc_hwstamp = - cq_info->cq_desc + + (void *)comp + qcq->cq.desc_size - sizeof(struct ionic_txq_comp) - IONIC_HWSTAMP_CQ_NEGOFFSET; @@ -1227,27 +1198,25 @@ static void ionic_tx_clean(struct ionic_queue *q, stats->hwstamp_invalid++; } } - - } else if (unlikely(__netif_subqueue_stopped(q->lif->netdev, qi))) { - netif_wake_subqueue(q->lif->netdev, qi); } desc_info->bytes = skb->len; stats->clean++; - dev_consume_skb_any(skb); + napi_consume_skb(skb, 1); } -bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) +static bool ionic_tx_service(struct ionic_cq *cq, + unsigned int *total_pkts, unsigned int *total_bytes) { + struct ionic_tx_desc_info *desc_info; struct ionic_queue *q = cq->bound_q; - struct ionic_desc_info *desc_info; struct ionic_txq_comp *comp; - int bytes = 0; - int pkts = 0; + unsigned int bytes = 0; + unsigned int pkts = 0; u16 index; - comp = cq_info->cq_desc + cq->desc_size - sizeof(*comp); + comp = &((struct ionic_txq_comp *)cq->base)[cq->tail_idx]; if (!color_match(comp->color, cq->done_color)) return false; @@ -1256,59 +1225,90 @@ bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) * several q entries completed for each cq completion */ do { - desc_info = &q->info[q->tail_idx]; + desc_info = &q->tx_info[q->tail_idx]; desc_info->bytes = 0; index = q->tail_idx; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - ionic_tx_clean(q, desc_info, cq_info, desc_info->cb_arg); - if (desc_info->cb_arg) { + ionic_tx_clean(q, desc_info, comp); + if (desc_info->skb) { pkts++; bytes += desc_info->bytes; + desc_info->skb = NULL; } - desc_info->cb = NULL; - desc_info->cb_arg = NULL; } while (index != le16_to_cpu(comp->comp_index)); - if (pkts && bytes && !ionic_txq_hwstamp_enabled(q)) - netdev_tx_completed_queue(q_to_ndq(q), pkts, bytes); + (*total_pkts) += pkts; + (*total_bytes) += bytes; return true; } +unsigned int ionic_tx_cq_service(struct ionic_cq *cq, unsigned int work_to_do) +{ + unsigned int work_done = 0; + unsigned int bytes = 0; + unsigned int pkts = 0; + + if (work_to_do == 0) + return 0; + + while (ionic_tx_service(cq, &pkts, &bytes)) { + if (cq->tail_idx == cq->num_descs - 1) + cq->done_color = !cq->done_color; + cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1); + + if (++work_done >= work_to_do) + break; + } + + if (work_done) { + struct ionic_queue *q = cq->bound_q; + + if (likely(!ionic_txq_hwstamp_enabled(q))) + netif_txq_completed_wake(q_to_ndq(q->lif->netdev, q), + pkts, bytes, + ionic_q_space_avail(q), + IONIC_TSO_DESCS_NEEDED); + } + + return work_done; +} + void ionic_tx_flush(struct ionic_cq *cq) { - struct ionic_dev *idev = &cq->lif->ionic->idev; u32 work_done; - work_done = ionic_cq_service(cq, cq->num_descs, - ionic_tx_service, NULL, NULL); + work_done = ionic_tx_cq_service(cq, cq->num_descs); if (work_done) - ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + ionic_intr_credits(cq->idev->intr_ctrl, cq->bound_intr->index, work_done, IONIC_INTR_CRED_RESET_COALESCE); } void ionic_tx_empty(struct ionic_queue *q) { - struct ionic_desc_info *desc_info; + struct ionic_tx_desc_info *desc_info; int bytes = 0; int pkts = 0; /* walk the not completed tx entries, if any */ while (q->head_idx != q->tail_idx) { - desc_info = &q->info[q->tail_idx]; + desc_info = &q->tx_info[q->tail_idx]; desc_info->bytes = 0; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - ionic_tx_clean(q, desc_info, NULL, desc_info->cb_arg); - if (desc_info->cb_arg) { + ionic_tx_clean(q, desc_info, NULL); + if (desc_info->skb) { pkts++; bytes += desc_info->bytes; + desc_info->skb = NULL; } - desc_info->cb = NULL; - desc_info->cb_arg = NULL; } - if (pkts && bytes && !ionic_txq_hwstamp_enabled(q)) - netdev_tx_completed_queue(q_to_ndq(q), pkts, bytes); + if (likely(!ionic_txq_hwstamp_enabled(q))) { + struct netdev_queue *ndq = q_to_ndq(q->lif->netdev, q); + + netdev_tx_completed_queue(ndq, pkts, bytes); + netdev_tx_reset_queue(ndq); + } } static int ionic_tx_tcp_inner_pseudo_csum(struct sk_buff *skb) @@ -1356,8 +1356,8 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) return 0; } -static void ionic_tx_tso_post(struct ionic_queue *q, - struct ionic_desc_info *desc_info, +static void ionic_tx_tso_post(struct net_device *netdev, struct ionic_queue *q, + struct ionic_tx_desc_info *desc_info, struct sk_buff *skb, dma_addr_t addr, u8 nsge, u16 len, unsigned int hdrlen, unsigned int mss, @@ -1365,7 +1365,7 @@ static void ionic_tx_tso_post(struct ionic_queue *q, u16 vlan_tci, bool has_vlan, bool start, bool done) { - struct ionic_txq_desc *desc = desc_info->desc; + struct ionic_txq_desc *desc = &q->txq[q->head_idx]; u8 flags = 0; u64 cmd; @@ -1381,22 +1381,23 @@ static void ionic_tx_tso_post(struct ionic_queue *q, desc->hdr_len = cpu_to_le16(hdrlen); desc->mss = cpu_to_le16(mss); - ionic_write_cmb_desc(q, desc_info->cmb_desc, desc); + ionic_write_cmb_desc(q, desc); if (start) { skb_tx_timestamp(skb); - if (!ionic_txq_hwstamp_enabled(q)) - netdev_tx_sent_queue(q_to_ndq(q), skb->len); - ionic_txq_post(q, false, ionic_tx_clean, skb); + if (likely(!ionic_txq_hwstamp_enabled(q))) + netdev_tx_sent_queue(q_to_ndq(netdev, q), skb->len); + ionic_txq_post(q, false); } else { - ionic_txq_post(q, done, NULL, NULL); + ionic_txq_post(q, done); } } -static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) +static int ionic_tx_tso(struct net_device *netdev, struct ionic_queue *q, + struct sk_buff *skb) { struct ionic_tx_stats *stats = q_to_tx_stats(q); - struct ionic_desc_info *desc_info; + struct ionic_tx_desc_info *desc_info; struct ionic_buf_info *buf_info; struct ionic_txq_sg_elem *elem; struct ionic_txq_desc *desc; @@ -1418,8 +1419,7 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) bool encap; int err; - desc_info = &q->info[q->head_idx]; - buf_info = desc_info->bufs; + desc_info = &q->tx_info[q->head_idx]; if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) return -EIO; @@ -1456,6 +1456,8 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) else hdrlen = skb_tcp_all_headers(skb); + desc_info->skb = skb; + buf_info = desc_info->bufs; tso_rem = len; seg_rem = min(tso_rem, hdrlen + mss); @@ -1482,8 +1484,8 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) chunk_len = min(frag_rem, seg_rem); if (!desc) { /* fill main descriptor */ - desc = desc_info->txq_desc; - elem = desc_info->txq_sg_desc->elems; + desc = &q->txq[q->head_idx]; + elem = ionic_tx_sg_elems(q); desc_addr = frag_addr; desc_len = chunk_len; } else { @@ -1501,13 +1503,13 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) seg_rem = min(tso_rem, mss); done = (tso_rem == 0); /* post descriptor */ - ionic_tx_tso_post(q, desc_info, skb, + ionic_tx_tso_post(netdev, q, desc_info, skb, desc_addr, desc_nsge, desc_len, hdrlen, mss, outer_csum, vlan_tci, has_vlan, start, done); start = false; /* Buffer information is stored with the first tso descriptor */ - desc_info = &q->info[q->head_idx]; + desc_info = &q->tx_info[q->head_idx]; desc_info->nbufs = 0; } @@ -1520,9 +1522,9 @@ static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) } static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { - struct ionic_txq_desc *desc = desc_info->txq_desc; + struct ionic_txq_desc *desc = &q->txq[q->head_idx]; struct ionic_buf_info *buf_info = desc_info->bufs; struct ionic_tx_stats *stats = q_to_tx_stats(q); bool has_vlan; @@ -1550,7 +1552,7 @@ static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, desc->csum_start = cpu_to_le16(skb_checksum_start_offset(skb)); desc->csum_offset = cpu_to_le16(skb->csum_offset); - ionic_write_cmb_desc(q, desc_info->cmb_desc, desc); + ionic_write_cmb_desc(q, desc); if (skb_csum_is_sctp(skb)) stats->crc32_csum++; @@ -1559,9 +1561,9 @@ static void ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb, } static void ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { - struct ionic_txq_desc *desc = desc_info->txq_desc; + struct ionic_txq_desc *desc = &q->txq[q->head_idx]; struct ionic_buf_info *buf_info = desc_info->bufs; struct ionic_tx_stats *stats = q_to_tx_stats(q); bool has_vlan; @@ -1589,20 +1591,20 @@ static void ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb, desc->csum_start = 0; desc->csum_offset = 0; - ionic_write_cmb_desc(q, desc_info->cmb_desc, desc); + ionic_write_cmb_desc(q, desc); stats->csum_none++; } static void ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, - struct ionic_desc_info *desc_info) + struct ionic_tx_desc_info *desc_info) { - struct ionic_txq_sg_desc *sg_desc = desc_info->txq_sg_desc; struct ionic_buf_info *buf_info = &desc_info->bufs[1]; - struct ionic_txq_sg_elem *elem = sg_desc->elems; struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_sg_elem *elem; unsigned int i; + elem = ionic_tx_sg_elems(q); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, buf_info++, elem++) { elem->addr = cpu_to_le64(buf_info->dma_addr); elem->len = cpu_to_le16(buf_info->len); @@ -1611,14 +1613,18 @@ static void ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb, stats->frags += skb_shinfo(skb)->nr_frags; } -static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) +static int ionic_tx(struct net_device *netdev, struct ionic_queue *q, + struct sk_buff *skb) { - struct ionic_desc_info *desc_info = &q->info[q->head_idx]; + struct ionic_tx_desc_info *desc_info = &q->tx_info[q->head_idx]; struct ionic_tx_stats *stats = q_to_tx_stats(q); + bool ring_dbell = true; if (unlikely(ionic_tx_map_skb(q, skb, desc_info))) return -EIO; + desc_info->skb = skb; + /* set up the initial descriptor */ if (skb->ip_summed == CHECKSUM_PARTIAL) ionic_tx_calc_csum(q, skb, desc_info); @@ -1632,16 +1638,22 @@ static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) stats->pkts++; stats->bytes += skb->len; - if (!ionic_txq_hwstamp_enabled(q)) - netdev_tx_sent_queue(q_to_ndq(q), skb->len); - ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb); + if (likely(!ionic_txq_hwstamp_enabled(q))) { + struct netdev_queue *ndq = q_to_ndq(netdev, q); + + if (unlikely(!ionic_q_has_space(q, MAX_SKB_FRAGS + 1))) + netif_tx_stop_queue(ndq); + ring_dbell = __netdev_tx_sent_queue(ndq, skb->len, + netdev_xmit_more()); + } + ionic_txq_post(q, ring_dbell); return 0; } static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) { - struct ionic_tx_stats *stats = q_to_tx_stats(q); + int nr_frags = skb_shinfo(skb)->nr_frags; bool too_many_frags = false; skb_frag_t *frag; int desc_bufs; @@ -1657,17 +1669,20 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) /* Each desc is mss long max, so a descriptor for each gso_seg */ if (skb_is_gso(skb)) { ndescs = skb_shinfo(skb)->gso_segs; + if (!nr_frags) + return ndescs; } else { ndescs = 1; - if (skb_shinfo(skb)->nr_frags > q->max_sg_elems) { + if (!nr_frags) + return ndescs; + + if (unlikely(nr_frags > q->max_sg_elems)) { too_many_frags = true; goto linearize; } - } - /* If non-TSO, or no frags to check, we're done */ - if (!skb_is_gso(skb) || !skb_shinfo(skb)->nr_frags) return ndescs; + } /* We need to scan the skb to be sure that none of the MTU sized * packets in the TSO will require more sgs per descriptor than we @@ -1718,36 +1733,17 @@ linearize: err = skb_linearize(skb); if (err) return err; - stats->linearize++; + q_to_tx_stats(q)->linearize++; } return ndescs; } -static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs) -{ - int stopped = 0; - - if (unlikely(!ionic_q_has_space(q, ndescs))) { - netif_stop_subqueue(q->lif->netdev, q->index); - stopped = 1; - - /* Might race with ionic_tx_clean, check again */ - smp_rmb(); - if (ionic_q_has_space(q, ndescs)) { - netif_wake_subqueue(q->lif->netdev, q->index); - stopped = 0; - } - } - - return stopped; -} - static netdev_tx_t ionic_start_hwstamp_xmit(struct sk_buff *skb, struct net_device *netdev) { struct ionic_lif *lif = netdev_priv(netdev); - struct ionic_queue *q = &lif->hwstamp_txq->q; + struct ionic_queue *q; int err, ndescs; /* Does not stop/start txq, because we post to a separate tx queue @@ -1755,6 +1751,7 @@ static netdev_tx_t ionic_start_hwstamp_xmit(struct sk_buff *skb, * the timestamping queue, it is dropped. */ + q = &lif->hwstamp_txq->q; ndescs = ionic_tx_descs_needed(q, skb); if (unlikely(ndescs < 0)) goto err_out_drop; @@ -1764,9 +1761,9 @@ static netdev_tx_t ionic_start_hwstamp_xmit(struct sk_buff *skb, skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP; if (skb_is_gso(skb)) - err = ionic_tx_tso(q, skb); + err = ionic_tx_tso(netdev, q, skb); else - err = ionic_tx(q, skb); + err = ionic_tx(netdev, q, skb); if (err) goto err_out_drop; @@ -1804,23 +1801,19 @@ netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) if (ndescs < 0) goto err_out_drop; - if (unlikely(ionic_maybe_stop_tx(q, ndescs))) + if (!netif_txq_maybe_stop(q_to_ndq(netdev, q), + ionic_q_space_avail(q), + ndescs, ndescs)) return NETDEV_TX_BUSY; if (skb_is_gso(skb)) - err = ionic_tx_tso(q, skb); + err = ionic_tx_tso(netdev, q, skb); else - err = ionic_tx(q, skb); + err = ionic_tx(netdev, q, skb); if (err) goto err_out_drop; - /* Stop the queue if there aren't descriptors for the next packet. - * Since our SG lists per descriptor take care of most of the possible - * fragmentation, we don't need to have many descriptors available. - */ - ionic_maybe_stop_tx(q, 4); - return NETDEV_TX_OK; err_out_drop: diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h index 82fc38e0f573..9e73e324e7a1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h @@ -14,8 +14,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget); int ionic_txrx_napi(struct napi_struct *napi, int budget); netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev); -bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info); -bool ionic_tx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info); +bool ionic_rx_service(struct ionic_cq *cq); int ionic_xdp_xmit(struct net_device *netdev, int n, struct xdp_frame **xdp, u32 flags); #endif /* _IONIC_TXRX_H_ */ diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index cb1746bc0e0c..847fa62c80df 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -215,7 +215,7 @@ static void qede_set_params_for_ipv6_ext(struct sk_buff *skb, bd2_bits1 |= (1 << ETH_TX_DATA_2ND_BD_IPV6_EXT_SHIFT); - bd2_bits2 |= ((((u8 *)skb_transport_header(skb) - skb->data) >> 1) & + bd2_bits2 |= ((skb_transport_offset(skb) >> 1) & ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_MASK) << ETH_TX_DATA_2ND_BD_L4_HDR_START_OFFSET_W_SHIFT; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 41894d154013..b9dc0071c5de 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -446,8 +446,7 @@ static int qlcnic_tx_encap_pkt(struct qlcnic_adapter *adapter, encap_descr |= skb_network_offset(skb) << 10; first_desc->encap_descr = cpu_to_le16(encap_descr); - first_desc->tcp_hdr_offset = skb_inner_transport_header(skb) - - skb->data; + first_desc->tcp_hdr_offset = skb_inner_transport_offset(skb); first_desc->ip_hdr_offset = skb_inner_network_offset(skb); qlcnic_set_tx_flags_opcode(first_desc, flags, opcode); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0d2cbb32c870..5c879a5c86d7 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2079,7 +2079,6 @@ static int rtl8169_get_eee(struct net_device *dev, struct ethtool_keee *data) return ret; data->tx_lpi_timer = r8169_get_tx_lpi_timer_us(tp); - data->tx_lpi_enabled = data->tx_lpi_timer ? data->eee_enabled : false; return 0; } @@ -5174,7 +5173,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp) tp->phydev->mac_managed_pm = true; if (rtl_supports_eee(tp)) - phy_advertise_eee_all(tp->phydev); + phy_support_eee(tp->phydev); phy_support_asym_pause(tp->phydev); /* PHY will be woken up in rtl_open() */ diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 35e642fc4b2a..b48935ec7e28 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1015,11 +1015,6 @@ enum CSR2_BIT { #define NUM_RX_QUEUE 2 #define NUM_TX_QUEUE 2 -#define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) - -#define GBETH_RX_BUFF_MAX 8192 -#define GBETH_RX_DESC_DATA_SIZE 4080 - struct ravb_tstamp_skb { struct list_head list; struct sk_buff *skb; @@ -1044,9 +1039,6 @@ struct ravb_ptp { }; struct ravb_hw_info { - void (*rx_ring_free)(struct net_device *ndev, int q); - void (*rx_ring_format)(struct net_device *ndev, int q); - void *(*alloc_rx_desc)(struct net_device *ndev, int q); bool (*receive)(struct net_device *ndev, int *quota, int q); void (*set_rate)(struct net_device *ndev); int (*set_feature)(struct net_device *ndev, netdev_features_t features); @@ -1057,9 +1049,10 @@ struct ravb_hw_info { netdev_features_t net_hw_features; netdev_features_t net_features; int stats_len; - size_t max_rx_len; u32 tccr_mask; - u32 rx_max_buf_size; + u32 rx_max_frame_size; + u32 rx_max_desc_use; + u32 rx_desc_size; unsigned aligned_tx: 1; /* hardware features */ @@ -1092,8 +1085,11 @@ struct ravb_private { struct ravb_desc *desc_bat; dma_addr_t rx_desc_dma[NUM_RX_QUEUE]; dma_addr_t tx_desc_dma[NUM_TX_QUEUE]; - struct ravb_rx_desc *gbeth_rx_ring; - struct ravb_ex_rx_desc *rx_ring[NUM_RX_QUEUE]; + union { + struct ravb_rx_desc *desc; + struct ravb_ex_rx_desc *ex_desc; + void *raw; + } rx_ring[NUM_RX_QUEUE]; struct ravb_tx_desc *tx_ring[NUM_TX_QUEUE]; void *tx_align[NUM_TX_QUEUE]; struct sk_buff *rx_1st_skb; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index f9fb772b05c7..d1be030c8848 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -113,12 +113,23 @@ static void ravb_set_rate_rcar(struct net_device *ndev) } } -static void ravb_set_buffer_align(struct sk_buff *skb) +static struct sk_buff * +ravb_alloc_skb(struct net_device *ndev, const struct ravb_hw_info *info, + gfp_t gfp_mask) { - u32 reserve = (unsigned long)skb->data & (RAVB_ALIGN - 1); + struct sk_buff *skb; + u32 reserve; + + skb = __netdev_alloc_skb(ndev, info->rx_max_frame_size + RAVB_ALIGN - 1, + gfp_mask); + if (!skb) + return NULL; + reserve = (unsigned long)skb->data & (RAVB_ALIGN - 1); if (reserve) skb_reserve(skb, RAVB_ALIGN - reserve); + + return skb; } /* Get MAC address from the MAC address registers @@ -191,6 +202,13 @@ static const struct mdiobb_ops bb_ops = { .get_mdio_data = ravb_get_mdio_data, }; +static struct ravb_rx_desc * +ravb_rx_get_desc(struct ravb_private *priv, unsigned int q, + unsigned int i) +{ + return priv->rx_ring[q].raw + priv->info->rx_desc_size * i; +} + /* Free TX skb function for AVB-IP */ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) { @@ -235,67 +253,40 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) return free_num; } -static void ravb_rx_ring_free_gbeth(struct net_device *ndev, int q) +static void ravb_rx_ring_free(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; unsigned int i; - if (!priv->gbeth_rx_ring) + if (!priv->rx_ring[q].raw) return; for (i = 0; i < priv->num_rx_ring[q]; i++) { - struct ravb_rx_desc *desc = &priv->gbeth_rx_ring[i]; + struct ravb_rx_desc *desc = ravb_rx_get_desc(priv, q, i); if (!dma_mapping_error(ndev->dev.parent, le32_to_cpu(desc->dptr))) dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - GBETH_RX_BUFF_MAX, + priv->info->rx_max_frame_size, DMA_FROM_DEVICE); } - ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); - dma_free_coherent(ndev->dev.parent, ring_size, priv->gbeth_rx_ring, + ring_size = priv->info->rx_desc_size * (priv->num_rx_ring[q] + 1); + dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q].raw, priv->rx_desc_dma[q]); - priv->gbeth_rx_ring = NULL; -} - -static void ravb_rx_ring_free_rcar(struct net_device *ndev, int q) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned int ring_size; - unsigned int i; - - if (!priv->rx_ring[q]) - return; - - for (i = 0; i < priv->num_rx_ring[q]; i++) { - struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; - - if (!dma_mapping_error(ndev->dev.parent, - le32_to_cpu(desc->dptr))) - dma_unmap_single(ndev->dev.parent, - le32_to_cpu(desc->dptr), - RX_BUF_SZ, - DMA_FROM_DEVICE); - } - ring_size = sizeof(struct ravb_ex_rx_desc) * - (priv->num_rx_ring[q] + 1); - dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], - priv->rx_desc_dma[q]); - priv->rx_ring[q] = NULL; + priv->rx_ring[q].raw = NULL; } /* Free skb's and DMA buffers for Ethernet AVB */ static void ravb_ring_free(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); - const struct ravb_hw_info *info = priv->info; unsigned int num_tx_desc = priv->num_tx_desc; unsigned int ring_size; unsigned int i; - info->rx_ring_free(ndev, q); + ravb_rx_ring_free(ndev, q); if (priv->tx_ring[q]) { ravb_tx_free(ndev, q, false); @@ -326,7 +317,7 @@ static void ravb_ring_free(struct net_device *ndev, int q) priv->tx_skb[q] = NULL; } -static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) +static void ravb_rx_ring_format(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); struct ravb_rx_desc *rx_desc; @@ -334,15 +325,15 @@ static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) dma_addr_t dma_addr; unsigned int i; - rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; - memset(priv->gbeth_rx_ring, 0, rx_ring_size); + rx_ring_size = priv->info->rx_desc_size * priv->num_rx_ring[q]; + memset(priv->rx_ring[q].raw, 0, rx_ring_size); /* Build RX ring buffer */ for (i = 0; i < priv->num_rx_ring[q]; i++) { /* RX descriptor */ - rx_desc = &priv->gbeth_rx_ring[i]; - rx_desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + rx_desc = ravb_rx_get_desc(priv, q, i); + rx_desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use); dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - GBETH_RX_BUFF_MAX, + priv->info->rx_max_frame_size, DMA_FROM_DEVICE); /* We just set the data size to 0 for a failed mapping which * should prevent DMA from happening... @@ -352,37 +343,7 @@ static void ravb_rx_ring_format_gbeth(struct net_device *ndev, int q) rx_desc->dptr = cpu_to_le32(dma_addr); rx_desc->die_dt = DT_FEMPTY; } - rx_desc = &priv->gbeth_rx_ring[i]; - rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); - rx_desc->die_dt = DT_LINKFIX; /* type */ -} - -static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) -{ - struct ravb_private *priv = netdev_priv(ndev); - struct ravb_ex_rx_desc *rx_desc; - unsigned int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; - dma_addr_t dma_addr; - unsigned int i; - - memset(priv->rx_ring[q], 0, rx_ring_size); - /* Build RX ring buffer */ - for (i = 0; i < priv->num_rx_ring[q]; i++) { - /* RX descriptor */ - rx_desc = &priv->rx_ring[q][i]; - rx_desc->ds_cc = cpu_to_le16(RX_BUF_SZ); - dma_addr = dma_map_single(ndev->dev.parent, priv->rx_skb[q][i]->data, - RX_BUF_SZ, - DMA_FROM_DEVICE); - /* We just set the data size to 0 for a failed mapping which - * should prevent DMA from happening... - */ - if (dma_mapping_error(ndev->dev.parent, dma_addr)) - rx_desc->ds_cc = cpu_to_le16(0); - rx_desc->dptr = cpu_to_le32(dma_addr); - rx_desc->die_dt = DT_FEMPTY; - } - rx_desc = &priv->rx_ring[q][i]; + rx_desc = ravb_rx_get_desc(priv, q, i); rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); rx_desc->die_dt = DT_LINKFIX; /* type */ } @@ -391,7 +352,6 @@ static void ravb_rx_ring_format_rcar(struct net_device *ndev, int q) static void ravb_ring_format(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); - const struct ravb_hw_info *info = priv->info; unsigned int num_tx_desc = priv->num_tx_desc; struct ravb_tx_desc *tx_desc; struct ravb_desc *desc; @@ -404,7 +364,7 @@ static void ravb_ring_format(struct net_device *ndev, int q) priv->dirty_rx[q] = 0; priv->dirty_tx[q] = 0; - info->rx_ring_format(ndev, q); + ravb_rx_ring_format(ndev, q); memset(priv->tx_ring[q], 0, tx_ring_size); /* Build TX ring buffer */ @@ -430,30 +390,18 @@ static void ravb_ring_format(struct net_device *ndev, int q) desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]); } -static void *ravb_alloc_rx_desc_gbeth(struct net_device *ndev, int q) +static void *ravb_alloc_rx_desc(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); unsigned int ring_size; - ring_size = sizeof(struct ravb_rx_desc) * (priv->num_rx_ring[q] + 1); - - priv->gbeth_rx_ring = dma_alloc_coherent(ndev->dev.parent, ring_size, - &priv->rx_desc_dma[q], - GFP_KERNEL); - return priv->gbeth_rx_ring; -} + ring_size = priv->info->rx_desc_size * (priv->num_rx_ring[q] + 1); -static void *ravb_alloc_rx_desc_rcar(struct net_device *ndev, int q) -{ - struct ravb_private *priv = netdev_priv(ndev); - unsigned int ring_size; + priv->rx_ring[q].raw = dma_alloc_coherent(ndev->dev.parent, ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); - ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); - - priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size, - &priv->rx_desc_dma[q], - GFP_KERNEL); - return priv->rx_ring[q]; + return priv->rx_ring[q].raw; } /* Init skb and descriptor buffer for Ethernet AVB */ @@ -475,10 +423,9 @@ static int ravb_ring_init(struct net_device *ndev, int q) goto error; for (i = 0; i < priv->num_rx_ring[q]; i++) { - skb = __netdev_alloc_skb(ndev, info->max_rx_len, GFP_KERNEL); + skb = ravb_alloc_skb(ndev, info, GFP_KERNEL); if (!skb) goto error; - ravb_set_buffer_align(skb); priv->rx_skb[q][i] = skb; } @@ -491,7 +438,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) } /* Allocate all RX descriptors. */ - if (!info->alloc_rx_desc(ndev, q)) + if (!ravb_alloc_rx_desc(ndev, q)) goto error; priv->dirty_rx[q] = 0; @@ -557,7 +504,7 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) } /* Receive frame limit set register */ - ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR); + ravb_write(ndev, priv->info->rx_max_frame_size + ETH_FCS_LEN, RFLR); /* EMAC Mode: PAUSE prohibition; Duplex; TX; RX; CRC Pass Through */ ravb_write(ndev, ECMR_ZPF | ((priv->duplex > 0) ? ECMR_DM : 0) | @@ -618,6 +565,7 @@ static void ravb_emac_init(struct net_device *ndev) static int ravb_dmac_init_gbeth(struct net_device *ndev) { + struct ravb_private *priv = netdev_priv(ndev); int error; error = ravb_ring_init(ndev, RAVB_BE); @@ -631,7 +579,7 @@ static int ravb_dmac_init_gbeth(struct net_device *ndev) ravb_write(ndev, 0x60000000, RCR); /* Set Max Frame Length (RTC) */ - ravb_write(ndev, 0x7ffc0000 | GBETH_RX_BUFF_MAX, RTC); + ravb_write(ndev, 0x7ffc0000 | priv->info->rx_max_frame_size, RTC); /* Set FIFO size */ ravb_write(ndev, 0x00222200, TGC); @@ -804,7 +752,8 @@ static struct sk_buff *ravb_get_skb_gbeth(struct net_device *ndev, int entry, skb = priv->rx_skb[RAVB_BE][entry]; priv->rx_skb[RAVB_BE][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - ALIGN(GBETH_RX_BUFF_MAX, 16), DMA_FROM_DEVICE); + ALIGN(priv->info->rx_max_frame_size, 16), + DMA_FROM_DEVICE); return skb; } @@ -830,7 +779,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) limit = priv->dirty_rx[q] + priv->num_rx_ring[q] - priv->cur_rx[q]; stats = &priv->stats[q]; - desc = &priv->gbeth_rx_ring[entry]; + desc = &priv->rx_ring[q].desc[entry]; for (i = 0; i < limit && rx_packets < *quota && desc->die_dt != DT_FEMPTY; i++) { /* Descriptor type must be checked before all other reads */ dma_rmb(); @@ -901,23 +850,22 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) } entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; + desc = &priv->rx_ring[q].desc[entry]; } /* Refill the RX ring buffers. */ for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; - desc = &priv->gbeth_rx_ring[entry]; - desc->ds_cc = cpu_to_le16(GBETH_RX_DESC_DATA_SIZE); + desc = &priv->rx_ring[q].desc[entry]; + desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use); if (!priv->rx_skb[q][entry]) { - skb = netdev_alloc_skb(ndev, info->max_rx_len); + skb = ravb_alloc_skb(ndev, info, GFP_ATOMIC); if (!skb) break; - ravb_set_buffer_align(skb); dma_addr = dma_map_single(ndev->dev.parent, skb->data, - GBETH_RX_BUFF_MAX, + priv->info->rx_max_frame_size, DMA_FROM_DEVICE); skb_checksum_none_assert(skb); /* We just set the data size to 0 for a failed mapping @@ -957,7 +905,7 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) boguscnt = min(boguscnt, *quota); limit = boguscnt; - desc = &priv->rx_ring[q][entry]; + desc = &priv->rx_ring[q].ex_desc[entry]; while (desc->die_dt != DT_FEMPTY) { /* Descriptor type must be checked before all other reads */ dma_rmb(); @@ -991,7 +939,7 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) skb = priv->rx_skb[q][entry]; priv->rx_skb[q][entry] = NULL; dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr), - RX_BUF_SZ, + priv->info->rx_max_frame_size, DMA_FROM_DEVICE); get_ts &= (q == RAVB_NC) ? RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : @@ -1017,22 +965,21 @@ static bool ravb_rx_rcar(struct net_device *ndev, int *quota, int q) } entry = (++priv->cur_rx[q]) % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q][entry]; + desc = &priv->rx_ring[q].ex_desc[entry]; } /* Refill the RX ring buffers. */ for (; priv->cur_rx[q] - priv->dirty_rx[q] > 0; priv->dirty_rx[q]++) { entry = priv->dirty_rx[q] % priv->num_rx_ring[q]; - desc = &priv->rx_ring[q][entry]; - desc->ds_cc = cpu_to_le16(RX_BUF_SZ); + desc = &priv->rx_ring[q].ex_desc[entry]; + desc->ds_cc = cpu_to_le16(priv->info->rx_max_desc_use); if (!priv->rx_skb[q][entry]) { - skb = netdev_alloc_skb(ndev, info->max_rx_len); + skb = ravb_alloc_skb(ndev, info, GFP_ATOMIC); if (!skb) break; /* Better luck next round. */ - ravb_set_buffer_align(skb); dma_addr = dma_map_single(ndev->dev.parent, skb->data, - le16_to_cpu(desc->ds_cc), + priv->info->rx_max_frame_size, DMA_FROM_DEVICE); skb_checksum_none_assert(skb); /* We just set the data size to 0 for a failed mapping @@ -2668,9 +2615,6 @@ static int ravb_mdio_release(struct ravb_private *priv) } static const struct ravb_hw_info ravb_gen3_hw_info = { - .rx_ring_free = ravb_rx_ring_free_rcar, - .rx_ring_format = ravb_rx_ring_format_rcar, - .alloc_rx_desc = ravb_alloc_rx_desc_rcar, .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, @@ -2681,9 +2625,10 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .net_hw_features = NETIF_F_RXCSUM, .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), - .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, - .rx_max_buf_size = SZ_2K, + .rx_max_frame_size = SZ_2K, + .rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16), + .rx_desc_size = sizeof(struct ravb_ex_rx_desc), .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, @@ -2694,9 +2639,6 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { }; static const struct ravb_hw_info ravb_gen2_hw_info = { - .rx_ring_free = ravb_rx_ring_free_rcar, - .rx_ring_format = ravb_rx_ring_format_rcar, - .alloc_rx_desc = ravb_alloc_rx_desc_rcar, .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, @@ -2707,9 +2649,10 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .net_hw_features = NETIF_F_RXCSUM, .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), - .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, - .rx_max_buf_size = SZ_2K, + .rx_max_frame_size = SZ_2K, + .rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16), + .rx_desc_size = sizeof(struct ravb_ex_rx_desc), .aligned_tx = 1, .gptp = 1, .nc_queues = 1, @@ -2717,9 +2660,6 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { }; static const struct ravb_hw_info ravb_rzv2m_hw_info = { - .rx_ring_free = ravb_rx_ring_free_rcar, - .rx_ring_format = ravb_rx_ring_format_rcar, - .alloc_rx_desc = ravb_alloc_rx_desc_rcar, .receive = ravb_rx_rcar, .set_rate = ravb_set_rate_rcar, .set_feature = ravb_set_features_rcar, @@ -2730,9 +2670,10 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = { .net_hw_features = NETIF_F_RXCSUM, .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), - .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, - .rx_max_buf_size = SZ_2K, + .rx_max_frame_size = SZ_2K, + .rx_max_desc_use = SZ_2K - ETH_FCS_LEN + sizeof(__sum16), + .rx_desc_size = sizeof(struct ravb_ex_rx_desc), .multi_irqs = 1, .err_mgmt_irqs = 1, .gptp = 1, @@ -2742,9 +2683,6 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = { }; static const struct ravb_hw_info gbeth_hw_info = { - .rx_ring_free = ravb_rx_ring_free_gbeth, - .rx_ring_format = ravb_rx_ring_format_gbeth, - .alloc_rx_desc = ravb_alloc_rx_desc_gbeth, .receive = ravb_rx_gbeth, .set_rate = ravb_set_rate_gbeth, .set_feature = ravb_set_features_gbeth, @@ -2755,9 +2693,10 @@ static const struct ravb_hw_info gbeth_hw_info = { .net_hw_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM, .net_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats_gbeth), - .max_rx_len = ALIGN(GBETH_RX_BUFF_MAX, RAVB_ALIGN), .tccr_mask = TCCR_TSRQ0, - .rx_max_buf_size = SZ_8K, + .rx_max_frame_size = SZ_8K, + .rx_max_desc_use = 4080, + .rx_desc_size = sizeof(struct ravb_rx_desc), .aligned_tx = 1, .tx_counters = 1, .carrier_counters = 1, @@ -2966,7 +2905,8 @@ static int ravb_probe(struct platform_device *pdev) priv->avb_link_active_low = of_property_read_bool(np, "renesas,ether-link-active-low"); - ndev->max_mtu = info->rx_max_buf_size - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); + ndev->max_mtu = info->rx_max_frame_size - + (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; /* FIXME: R-Car Gen2 has 4byte alignment restriction for tx buffer diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fac227d372db..dcd901eccfc8 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include <linux/module.h> #include <linux/iommu.h> +#include <net/rps.h> #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c index 4579f43484c3..219fb358a646 100644 --- a/drivers/net/ethernet/sfc/siena/rx_common.c +++ b/drivers/net/ethernet/sfc/siena/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include <linux/module.h> #include <linux/iommu.h> +#include <net/rps.h> #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/ethernet/sfc/siena/tx_common.c b/drivers/net/ethernet/sfc/siena/tx_common.c index a7a9ab304e13..71f9b5ec5ae4 100644 --- a/drivers/net/ethernet/sfc/siena/tx_common.c +++ b/drivers/net/ethernet/sfc/siena/tx_common.c @@ -317,11 +317,10 @@ static int efx_tx_tso_header_length(struct sk_buff *skb) size_t header_len; if (skb->encapsulation) - header_len = skb_inner_transport_header(skb) - - skb->data + + header_len = skb_inner_transport_offset(skb) + (inner_tcp_hdr(skb)->doff << 2u); else - header_len = skb_transport_header(skb) - skb->data + + header_len = skb_transport_offset(skb) + (tcp_hdr(skb)->doff << 2u); return header_len; } diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index 9f2393d34371..2adb132b2f7e 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -336,11 +336,10 @@ int efx_tx_tso_header_length(struct sk_buff *skb) size_t header_len; if (skb->encapsulation) - header_len = skb_inner_transport_header(skb) - - skb->data + + header_len = skb_inner_transport_offset(skb) + (inner_tcp_hdr(skb)->doff << 2u); else - header_len = skb_transport_header(skb) - skb->data + + header_len = skb_transport_offset(skb) + (tcp_hdr(skb)->doff << 2u); return header_len; } diff --git a/drivers/net/ethernet/sfc/tx_tso.c b/drivers/net/ethernet/sfc/tx_tso.c index 64a6768f75ea..ddf149db8180 100644 --- a/drivers/net/ethernet/sfc/tx_tso.c +++ b/drivers/net/ethernet/sfc/tx_tso.c @@ -174,8 +174,8 @@ static int tso_start(struct tso_state *st, struct efx_nic *efx, unsigned int header_len, in_len; dma_addr_t dma_addr; - st->ip_off = skb_network_header(skb) - skb->data; - st->tcp_off = skb_transport_header(skb) - skb->data; + st->ip_off = skb_network_offset(skb); + st->tcp_off = skb_transport_offset(skb); header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u); in_len = skb_headlen(skb) - header_len; st->header_len = header_len; diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index 3525d5c0d694..351609f4f011 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1144,9 +1144,9 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) nskb->protocol = skb->protocol; offset = skb_mac_header(skb) - skb->data; skb_set_mac_header(nskb, offset); - offset = skb_network_header(skb) - skb->data; + offset = skb_network_offset(skb); skb_set_network_header(nskb, offset); - offset = skb_transport_header(skb) - skb->data; + offset = skb_transport_offset(skb); skb_set_transport_header(nskb, offset); offset = 0; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 9d2f4ac783e4..2939a21ca74f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -294,7 +294,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev, txqueue, netif_tx_queue_stopped(netif_txq), jiffies_to_msecs(jiffies - trans_start), - dql_avail(&netif_txq->dql), + netdev_queue_dql_avail(netif_txq), k3_cppi_desc_pool_avail(tx_chn->desc_pool)); if (netif_tx_queue_stopped(netif_txq)) { diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 7cf02ab6de68..6dff2c85682d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1257,7 +1257,7 @@ static int wx_tso(struct wx_ring *tx_ring, struct wx_tx_buffer *first, /* compute header lengths */ l4len = enc ? inner_tcp_hdrlen(skb) : tcp_hdrlen(skb); - *hdr_len = enc ? (skb_inner_transport_header(skb) - skb->data) : + *hdr_len = enc ? skb_inner_transport_offset(skb) : skb_transport_offset(skb); *hdr_len += l4len; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index e67a21294158..bd4624d14ca0 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -81,6 +81,7 @@ static void txgbe_up_complete(struct wx *wx) { struct net_device *netdev = wx->netdev; + txgbe_reinit_gpio_intr(wx); wx_control_hw(wx, true); wx_configure_vectors(wx); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index bae0a8ee7014..93295916b1d2 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -475,8 +475,10 @@ irqreturn_t txgbe_gpio_irq_handler(int irq, void *data) gc = txgbe->gpio; for_each_set_bit(hwirq, &gpioirq, gc->ngpio) { int gpio = irq_find_mapping(gc->irq.domain, hwirq); + struct irq_data *d = irq_get_irq_data(gpio); u32 irq_type = irq_get_trigger_type(gpio); + txgbe_gpio_irq_ack(d); handle_nested_irq(gpio); if ((irq_type & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH) { @@ -489,6 +491,33 @@ irqreturn_t txgbe_gpio_irq_handler(int irq, void *data) return IRQ_HANDLED; } +void txgbe_reinit_gpio_intr(struct wx *wx) +{ + struct txgbe *txgbe = wx->priv; + irq_hw_number_t hwirq; + unsigned long gpioirq; + struct gpio_chip *gc; + unsigned long flags; + + /* for gpio interrupt pending before irq enable */ + gpioirq = rd32(wx, WX_GPIO_INTSTATUS); + + gc = txgbe->gpio; + for_each_set_bit(hwirq, &gpioirq, gc->ngpio) { + int gpio = irq_find_mapping(gc->irq.domain, hwirq); + struct irq_data *d = irq_get_irq_data(gpio); + u32 irq_type = irq_get_trigger_type(gpio); + + txgbe_gpio_irq_ack(d); + + if ((irq_type & IRQ_TYPE_SENSE_MASK) == IRQ_TYPE_EDGE_BOTH) { + raw_spin_lock_irqsave(&wx->gpio_lock, flags); + txgbe_toggle_trigger(gc, hwirq); + raw_spin_unlock_irqrestore(&wx->gpio_lock, flags); + } + } +} + static int txgbe_gpio_init(struct txgbe *txgbe) { struct gpio_irq_chip *girq; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h index 9855d44076cb..8a026d804fe2 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.h @@ -5,6 +5,7 @@ #define _TXGBE_PHY_H_ irqreturn_t txgbe_gpio_irq_handler(int irq, void *data); +void txgbe_reinit_gpio_intr(struct wx *wx); irqreturn_t txgbe_link_irq_handler(int irq, void *data); int txgbe_init_phy(struct txgbe *txgbe); void txgbe_remove_phy(struct txgbe *txgbe); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6f3f9b446b1d..2f6739fe78af 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; - int err = 0; + int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { @@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(geneve->dev, rx_length_errors); + DEV_STATS_INC(geneve->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -319,19 +333,12 @@ static int geneve_init(struct net_device *dev) struct geneve_dev *geneve = netdev_priv(dev); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&geneve->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { - free_percpu(dev->tstats); gro_cells_destroy(&geneve->gro_cells); return err; } @@ -345,7 +352,6 @@ static void geneve_uninit(struct net_device *dev) dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); - free_percpu(dev->tstats); } /* Callback from net/ipv4/udp.c to receive packets */ @@ -508,7 +514,7 @@ static struct sk_buff *geneve_gro_receive(struct sock *sk, gh_len = geneve_hlen(gh); hlen = off_gnv + gh_len; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { gh = skb_gro_header_slow(skb, hlen, off_gnv); if (unlikely(!gh)) goto out; @@ -1122,7 +1128,6 @@ static const struct net_device_ops geneve_netdev_ops = { .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, @@ -1189,6 +1194,7 @@ static void geneve_setup(struct net_device *dev) dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 2b46b7398ade..ba4704c2c640 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -711,25 +711,11 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) return ret; } -static int gtp_dev_init(struct net_device *dev) -{ - struct gtp_dev *gtp = netdev_priv(dev); - - gtp->dev = dev; - - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - - return 0; -} - static void gtp_dev_uninit(struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); gtp_encap_disable(gtp); - free_percpu(dev->tstats); } static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) @@ -942,10 +928,8 @@ tx_err: } static const struct net_device_ops gtp_netdev_ops = { - .ndo_init = gtp_dev_init, .ndo_uninit = gtp_dev_uninit, .ndo_start_xmit = gtp_dev_xmit, - .ndo_get_stats64 = dev_get_tstats64, }; static const struct device_type gtp_type = { @@ -957,6 +941,7 @@ static void gtp_link_setup(struct net_device *dev) unsigned int max_gtp_header_len = sizeof(struct iphdr) + sizeof(struct udphdr) + sizeof(struct gtp0_header); + struct gtp_dev *gtp = netdev_priv(dev); dev->netdev_ops = >p_netdev_ops; dev->needs_free_netdev = true; @@ -970,11 +955,13 @@ static void gtp_link_setup(struct net_device *dev) dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags |= IFF_NO_QUEUE; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); dev->needed_headroom = LL_MAX_HEADER + max_gtp_header_len; + gtp->dev = dev; } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 164c7f605af5..f632b0cfd5ae 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -11,17 +11,16 @@ */ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/gpio/consumer.h> #include <linux/hrtimer.h> #include <linux/jiffies.h> #include <linux/interrupt.h> #include <linux/irq.h> -#include <linux/gpio.h> #include <linux/delay.h> #include <linux/property.h> #include <linux/spi/spi.h> #include <linux/regmap.h> #include <linux/skbuff.h> -#include <linux/of_gpio.h> #include <linux/ieee802154.h> #include <net/mac802154.h> @@ -316,7 +315,7 @@ static const struct regmap_config at86rf230_regmap_spi_config = { .val_bits = 8, .write_flag_mask = CMD_REG | CMD_WRITE, .read_flag_mask = CMD_REG, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .max_register = AT86RF2XX_NUMREGS, .writeable_reg = at86rf230_reg_writeable, .readable_reg = at86rf230_reg_readable, diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 4ec0dab38872..f102f26cb0e3 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2857,19 +2857,13 @@ static int ca8210_interrupt_init(struct spi_device *spi) */ static int ca8210_dev_com_init(struct ca8210_priv *priv) { - priv->mlme_workqueue = alloc_ordered_workqueue( - "MLME work queue", - WQ_UNBOUND - ); + priv->mlme_workqueue = alloc_ordered_workqueue("MLME work queue", 0); if (!priv->mlme_workqueue) { dev_crit(&priv->spi->dev, "alloc of mlme_workqueue failed!\n"); return -ENOMEM; } - priv->irq_workqueue = alloc_ordered_workqueue( - "ca8210 irq worker", - WQ_UNBOUND - ); + priv->irq_workqueue = alloc_ordered_workqueue("ca8210 irq worker", 0); if (!priv->irq_workqueue) { dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n"); destroy_workqueue(priv->mlme_workqueue); diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 87abe3b46316..433fb5839203 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -12,7 +12,6 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/skbuff.h> -#include <linux/of_gpio.h> #include <linux/regmap.h> #include <linux/ieee802154.h> #include <linux/debugfs.h> @@ -251,7 +250,7 @@ static const struct regmap_config mcr20a_dar_regmap = { .val_bits = 8, .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE, .read_flag_mask = REGISTER_ACCESS | REGISTER_READ, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .writeable_reg = mcr20a_dar_writeable, .readable_reg = mcr20a_dar_readable, .volatile_reg = mcr20a_dar_volatile, @@ -387,7 +386,7 @@ static const struct regmap_config mcr20a_iar_regmap = { .val_bits = 8, .write_flag_mask = REGISTER_ACCESS | REGISTER_WRITE | IAR_INDEX, .read_flag_mask = REGISTER_ACCESS | REGISTER_READ | IAR_INDEX, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .writeable_reg = mcr20a_iar_writeable, .readable_reg = mcr20a_iar_readable, .volatile_reg = mcr20a_iar_volatile, diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index ee4cfbf2c5cc..d3f42efc5d1a 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -388,7 +388,7 @@ static const struct regmap_config mrf24j40_short_regmap = { .pad_bits = 1, .write_flag_mask = MRF24J40_SHORT_WRITE, .read_flag_mask = MRF24J40_SHORT_READ, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .max_register = MRF24J40_SHORT_NUMREGS, .writeable_reg = mrf24j40_short_reg_writeable, .readable_reg = mrf24j40_short_reg_readable, @@ -495,7 +495,7 @@ static const struct regmap_config mrf24j40_long_regmap = { .pad_bits = 5, .write_flag_mask = MRF24J40_LONG_ACCESS, .read_flag_mask = MRF24J40_LONG_ACCESS, - .cache_type = REGCACHE_RBTREE, + .cache_type = REGCACHE_MAPLE, .max_register = MRF24J40_LONG_NUMREGS, .writeable_reg = mrf24j40_long_reg_writeable, .readable_reg = mrf24j40_long_reg_readable, diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index f3355e040a9e..334cd62cf286 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -21,7 +21,6 @@ struct clk; struct icc_path; struct net_device; -struct platform_device; struct ipa_power; struct ipa_smp2p; @@ -31,7 +30,7 @@ struct ipa_interrupt; * struct ipa - IPA information * @gsi: Embedded GSI structure * @version: IPA hardware version - * @pdev: Platform device + * @dev: IPA device pointer * @completion: Used to signal pipeline clear transfer complete * @nb: Notifier block used for remoteproc SSR * @notifier: Remoteproc SSR notifier @@ -79,7 +78,7 @@ struct ipa_interrupt; struct ipa { struct gsi gsi; enum ipa_version version; - struct platform_device *pdev; + struct device *dev; struct completion completion; struct notifier_block nb; void *notifier; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index f1419fbd776c..39219963dbb3 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -174,7 +174,7 @@ bool ipa_cmd_table_init_valid(struct ipa *ipa, const struct ipa_mem *mem, u32 offset_max = field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK); u32 size_max = field_max(IP_FLTRT_FLAGS_NHASH_SIZE_FMASK); const char *table = route ? "route" : "filter"; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; u32 size; size = route ? ipa->route_count : ipa->filter_count + 1; @@ -204,7 +204,7 @@ bool ipa_cmd_table_init_valid(struct ipa *ipa, const struct ipa_mem *mem, /* Validate the memory region that holds headers */ static bool ipa_cmd_header_init_local_valid(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; const struct ipa_mem *mem; u32 offset_max; u32 size_max; @@ -256,7 +256,7 @@ static bool ipa_cmd_register_write_offset_valid(struct ipa *ipa, const char *name, u32 offset) { struct ipa_cmd_register_write *payload; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; u32 offset_max; u32 bit_count; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index afa1d56d9095..dd490941615e 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -233,8 +233,8 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data) { const struct ipa_gsi_endpoint_data *other_data; - struct device *dev = &ipa->pdev->dev; enum ipa_endpoint_name other_name; + struct device *dev = ipa->dev; if (ipa_gsi_endpoint_data_empty(data)) return true; @@ -388,7 +388,7 @@ static u32 ipa_endpoint_max(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data) { const struct ipa_gsi_endpoint_data *dp = data; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; enum ipa_endpoint_name name; u32 max; @@ -606,7 +606,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) count = ipa->modem_tx_count + ipa_cmd_pipeline_clear_count(); trans = ipa_cmd_trans_alloc(ipa, count); if (!trans) { - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "no transaction to reset modem exception endpoints\n"); return -EBUSY; } @@ -1498,8 +1498,7 @@ ipa_endpoint_status_tag_valid(struct ipa_endpoint *endpoint, const void *data) if (endpoint_id == command_endpoint->endpoint_id) { complete(&ipa->completion); } else { - dev_err(&ipa->pdev->dev, - "unexpected tagged packet from endpoint %u\n", + dev_err(ipa->dev, "unexpected tagged packet from endpoint %u\n", endpoint_id); } @@ -1536,6 +1535,7 @@ static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, void *data = page_address(page) + NET_SKB_PAD; u32 unused = buffer_size - total_len; struct ipa *ipa = endpoint->ipa; + struct device *dev = ipa->dev; u32 resid = total_len; while (resid) { @@ -1544,7 +1544,7 @@ static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, u32 len; if (resid < IPA_STATUS_SIZE) { - dev_err(&endpoint->ipa->pdev->dev, + dev_err(dev, "short message (%u bytes < %zu byte status)\n", resid, IPA_STATUS_SIZE); break; @@ -1666,8 +1666,8 @@ void ipa_endpoint_default_route_clear(struct ipa *ipa) */ static int ipa_endpoint_reset_rx_aggr(struct ipa_endpoint *endpoint) { - struct device *dev = &endpoint->ipa->pdev->dev; struct ipa *ipa = endpoint->ipa; + struct device *dev = ipa->dev; struct gsi *gsi = &ipa->gsi; bool suspended = false; dma_addr_t addr; @@ -1769,7 +1769,7 @@ static void ipa_endpoint_reset(struct ipa_endpoint *endpoint) gsi_channel_reset(&ipa->gsi, channel_id, true); if (ret) - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "error %d resetting channel %u for endpoint %u\n", ret, endpoint->channel_id, endpoint->endpoint_id); } @@ -1817,7 +1817,7 @@ int ipa_endpoint_enable_one(struct ipa_endpoint *endpoint) ret = gsi_channel_start(gsi, endpoint->channel_id); if (ret) { - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "error %d starting %cX channel %u for endpoint %u\n", ret, endpoint->toward_ipa ? 'T' : 'R', endpoint->channel_id, endpoint_id); @@ -1854,14 +1854,13 @@ void ipa_endpoint_disable_one(struct ipa_endpoint *endpoint) /* Note that if stop fails, the channel's state is not well-defined */ ret = gsi_channel_stop(gsi, endpoint->channel_id); if (ret) - dev_err(&ipa->pdev->dev, - "error %d attempting to stop endpoint %u\n", ret, - endpoint_id); + dev_err(ipa->dev, "error %d attempting to stop endpoint %u\n", + ret, endpoint_id); } void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint) { - struct device *dev = &endpoint->ipa->pdev->dev; + struct device *dev = endpoint->ipa->dev; struct gsi *gsi = &endpoint->ipa->gsi; int ret; @@ -1881,7 +1880,7 @@ void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint) void ipa_endpoint_resume_one(struct ipa_endpoint *endpoint) { - struct device *dev = &endpoint->ipa->pdev->dev; + struct device *dev = endpoint->ipa->dev; struct gsi *gsi = &endpoint->ipa->gsi; int ret; @@ -1983,7 +1982,7 @@ void ipa_endpoint_deconfig(struct ipa *ipa) int ipa_endpoint_config(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; const struct reg *reg; u32 endpoint_id; u32 hw_limit; diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index 4d80bf77a532..c3e8784d51d9 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -19,6 +19,7 @@ * time only these three are supported. */ +#include <linux/platform_device.h> #include <linux/types.h> #include <linux/interrupt.h> #include <linux/pm_runtime.h> @@ -109,14 +110,13 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) struct ipa_interrupt *interrupt = dev_id; struct ipa *ipa = interrupt->ipa; u32 enabled = interrupt->enabled; + struct device *dev = ipa->dev; const struct reg *reg; - struct device *dev; u32 pending; u32 offset; u32 mask; int ret; - dev = &ipa->pdev->dev; ret = pm_runtime_get_sync(dev); if (WARN_ON(ret < 0)) goto out_power_put; @@ -236,29 +236,17 @@ void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt) } /* Configure the IPA interrupt framework */ -struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) +int ipa_interrupt_config(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; - struct ipa_interrupt *interrupt; + struct ipa_interrupt *interrupt = ipa->interrupt; + unsigned int irq = interrupt->irq; + struct device *dev = ipa->dev; const struct reg *reg; - unsigned int irq; int ret; - ret = platform_get_irq_byname(ipa->pdev, "ipa"); - if (ret <= 0) { - dev_err(dev, "DT error %d getting \"ipa\" IRQ property\n", - ret); - return ERR_PTR(ret ? : -EINVAL); - } - irq = ret; - - interrupt = kzalloc(sizeof(*interrupt), GFP_KERNEL); - if (!interrupt) - return ERR_PTR(-ENOMEM); interrupt->ipa = ipa; - interrupt->irq = irq; - /* Start with all IPA interrupts disabled */ + /* Disable all IPA interrupt types */ reg = ipa_reg(ipa, IPA_IRQ_EN); iowrite32(0, ipa->reg_virt + reg_offset(reg)); @@ -271,26 +259,59 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) ret = dev_pm_set_wake_irq(dev, irq); if (ret) { - dev_err(dev, "error %d registering \"ipa\" IRQ as wakeirq\n", ret); + dev_err(dev, "error %d registering \"ipa\" IRQ as wakeirq\n", + ret); goto err_free_irq; } - return interrupt; + ipa->interrupt = interrupt; + + return 0; err_free_irq: free_irq(interrupt->irq, interrupt); err_kfree: kfree(interrupt); - return ERR_PTR(ret); + return ret; } /* Inverse of ipa_interrupt_config() */ -void ipa_interrupt_deconfig(struct ipa_interrupt *interrupt) +void ipa_interrupt_deconfig(struct ipa *ipa) { - struct device *dev = &interrupt->ipa->pdev->dev; + struct ipa_interrupt *interrupt = ipa->interrupt; + struct device *dev = ipa->dev; + + ipa->interrupt = NULL; dev_pm_clear_wake_irq(dev); free_irq(interrupt->irq, interrupt); +} + +/* Initialize the IPA interrupt structure */ +struct ipa_interrupt *ipa_interrupt_init(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct ipa_interrupt *interrupt; + int irq; + + irq = platform_get_irq_byname(pdev, "ipa"); + if (irq <= 0) { + dev_err(dev, "DT error %d getting \"ipa\" IRQ property\n", irq); + + return ERR_PTR(irq ? : -EINVAL); + } + + interrupt = kzalloc(sizeof(*interrupt), GFP_KERNEL); + if (!interrupt) + return ERR_PTR(-ENOMEM); + interrupt->irq = irq; + + return interrupt; +} + +/* Inverse of ipa_interrupt_init() */ +void ipa_interrupt_exit(struct ipa_interrupt *interrupt) +{ kfree(interrupt); } diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h index 53e1b71685c7..f3f4f4330a59 100644 --- a/drivers/net/ipa/ipa_interrupt.h +++ b/drivers/net/ipa/ipa_interrupt.h @@ -76,17 +76,31 @@ void ipa_interrupt_irq_enable(struct ipa *ipa); void ipa_interrupt_irq_disable(struct ipa *ipa); /** - * ipa_interrupt_config() - Configure the IPA interrupt framework + * ipa_interrupt_config() - Configure IPA interrupts * @ipa: IPA pointer * - * Return: Pointer to IPA SMP2P info, or a pointer-coded error + * Return: 0 if successful, or a negative error code */ -struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa); +int ipa_interrupt_config(struct ipa *ipa); /** * ipa_interrupt_deconfig() - Inverse of ipa_interrupt_config() + * @ipa: IPA pointer + */ +void ipa_interrupt_deconfig(struct ipa *ipa); + +/** + * ipa_interrupt_init() - Initialize the IPA interrupt structure + * @pdev: IPA platform device pointer + * + * Return: Pointer to an IPA interrupt structure, or a pointer-coded error + */ +struct ipa_interrupt *ipa_interrupt_init(struct platform_device *pdev); + +/** + * ipa_interrupt_exit() - Inverse of ipa_interrupt_init() * @interrupt: IPA interrupt structure */ -void ipa_interrupt_deconfig(struct ipa_interrupt *interrupt); +void ipa_interrupt_exit(struct ipa_interrupt *interrupt); #endif /* _IPA_INTERRUPT_H_ */ diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 00475fd7a205..57b241417e8c 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -7,7 +7,6 @@ #include <linux/types.h> #include <linux/atomic.h> #include <linux/bitfield.h> -#include <linux/device.h> #include <linux/bug.h> #include <linux/io.h> #include <linux/firmware.h> @@ -114,7 +113,7 @@ int ipa_setup(struct ipa *ipa) { struct ipa_endpoint *exception_endpoint; struct ipa_endpoint *command_endpoint; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; int ret; ret = gsi_setup(&ipa->gsi); @@ -542,12 +541,9 @@ static int ipa_config(struct ipa *ipa, const struct ipa_data *data) if (ret) goto err_hardware_deconfig; - ipa->interrupt = ipa_interrupt_config(ipa); - if (IS_ERR(ipa->interrupt)) { - ret = PTR_ERR(ipa->interrupt); - ipa->interrupt = NULL; + ret = ipa_interrupt_config(ipa); + if (ret) goto err_mem_deconfig; - } ipa_uc_config(ipa); @@ -572,8 +568,7 @@ err_endpoint_deconfig: ipa_endpoint_deconfig(ipa); err_uc_deconfig: ipa_uc_deconfig(ipa); - ipa_interrupt_deconfig(ipa->interrupt); - ipa->interrupt = NULL; + ipa_interrupt_deconfig(ipa); err_mem_deconfig: ipa_mem_deconfig(ipa); err_hardware_deconfig: @@ -591,8 +586,7 @@ static void ipa_deconfig(struct ipa *ipa) ipa_modem_deconfig(ipa); ipa_endpoint_deconfig(ipa); ipa_uc_deconfig(ipa); - ipa_interrupt_deconfig(ipa->interrupt); - ipa->interrupt = NULL; + ipa_interrupt_deconfig(ipa); ipa_mem_deconfig(ipa); ipa_hardware_deconfig(ipa); } @@ -808,6 +802,7 @@ out_self: static int ipa_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + struct ipa_interrupt *interrupt; enum ipa_firmware_loader loader; const struct ipa_data *data; struct ipa_power *power; @@ -839,12 +834,21 @@ static int ipa_probe(struct platform_device *pdev) if (loader == IPA_LOADER_DEFER) return -EPROBE_DEFER; - /* The clock and interconnects might not be ready when we're - * probed, so might return -EPROBE_DEFER. + /* The IPA interrupt might not be ready when we're probed, so this + * might return -EPROBE_DEFER. + */ + interrupt = ipa_interrupt_init(pdev); + if (IS_ERR(interrupt)) + return PTR_ERR(interrupt); + + /* The clock and interconnects might not be ready when we're probed, + * so this might return -EPROBE_DEFER. */ power = ipa_power_init(dev, data->power_data); - if (IS_ERR(power)) - return PTR_ERR(power); + if (IS_ERR(power)) { + ret = PTR_ERR(power); + goto err_interrupt_exit; + } /* No more EPROBE_DEFER. Allocate and initialize the IPA structure */ ipa = kzalloc(sizeof(*ipa), GFP_KERNEL); @@ -853,18 +857,19 @@ static int ipa_probe(struct platform_device *pdev) goto err_power_exit; } - ipa->pdev = pdev; + ipa->dev = dev; dev_set_drvdata(dev, ipa); + ipa->interrupt = interrupt; ipa->power = power; ipa->version = data->version; ipa->modem_route_count = data->modem_route_count; init_completion(&ipa->completion); - ret = ipa_reg_init(ipa); + ret = ipa_reg_init(ipa, pdev); if (ret) goto err_kfree_ipa; - ret = ipa_mem_init(ipa, data->mem_data); + ret = ipa_mem_init(ipa, pdev, data->mem_data); if (ret) goto err_reg_exit; @@ -882,7 +887,7 @@ static int ipa_probe(struct platform_device *pdev) if (ret) goto err_endpoint_exit; - ret = ipa_smp2p_init(ipa, loader == IPA_LOADER_MODEM); + ret = ipa_smp2p_init(ipa, pdev, loader == IPA_LOADER_MODEM); if (ret) goto err_table_exit; @@ -939,17 +944,27 @@ err_kfree_ipa: kfree(ipa); err_power_exit: ipa_power_exit(power); +err_interrupt_exit: + ipa_interrupt_exit(interrupt); return ret; } static void ipa_remove(struct platform_device *pdev) { - struct ipa *ipa = dev_get_drvdata(&pdev->dev); - struct ipa_power *power = ipa->power; - struct device *dev = &pdev->dev; + struct ipa_interrupt *interrupt; + struct ipa_power *power; + struct device *dev; + struct ipa *ipa; int ret; + ipa = dev_get_drvdata(&pdev->dev); + dev = ipa->dev; + WARN_ON(dev != &pdev->dev); + + power = ipa->power; + interrupt = ipa->interrupt; + /* Prevent the modem from triggering a call to ipa_setup(). This * also ensures a modem-initiated setup that's underway completes. */ @@ -991,6 +1006,7 @@ out_power_put: ipa_reg_exit(ipa); kfree(ipa); ipa_power_exit(power); + ipa_interrupt_exit(interrupt); dev_info(dev, "IPA driver removed"); } diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 694960537ecd..709f061ede61 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -9,6 +9,7 @@ #include <linux/bug.h> #include <linux/dma-mapping.h> #include <linux/iommu.h> +#include <linux/platform_device.h> #include <linux/io.h> #include <linux/soc/qcom/smem.h> @@ -75,9 +76,9 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, enum ipa_mem_id mem_id) int ipa_mem_setup(struct ipa *ipa) { dma_addr_t addr = ipa->zero_addr; - const struct reg *reg; const struct ipa_mem *mem; struct gsi_trans *trans; + const struct reg *reg; u32 offset; u16 size; u32 val; @@ -87,7 +88,7 @@ int ipa_mem_setup(struct ipa *ipa) */ trans = ipa_cmd_trans_alloc(ipa, 4); if (!trans) { - dev_err(&ipa->pdev->dev, "no transaction for memory setup\n"); + dev_err(ipa->dev, "no transaction for memory setup\n"); return -EBUSY; } @@ -217,8 +218,8 @@ static bool ipa_mem_id_required(struct ipa *ipa, enum ipa_mem_id mem_id) static bool ipa_mem_valid_one(struct ipa *ipa, const struct ipa_mem *mem) { - struct device *dev = &ipa->pdev->dev; enum ipa_mem_id mem_id = mem->id; + struct device *dev = ipa->dev; u16 size_multiple; /* Make sure the memory region is valid for this version of IPA */ @@ -254,7 +255,7 @@ static bool ipa_mem_valid_one(struct ipa *ipa, const struct ipa_mem *mem) static bool ipa_mem_valid(struct ipa *ipa, const struct ipa_mem_data *mem_data) { DECLARE_BITMAP(regions, IPA_MEM_COUNT) = { }; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; enum ipa_mem_id mem_id; u32 i; @@ -290,7 +291,7 @@ static bool ipa_mem_valid(struct ipa *ipa, const struct ipa_mem_data *mem_data) /* Do all memory regions fit within the IPA local memory? */ static bool ipa_mem_size_valid(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; u32 limit = ipa->mem_size; u32 i; @@ -317,7 +318,7 @@ static bool ipa_mem_size_valid(struct ipa *ipa) */ int ipa_mem_config(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; const struct ipa_mem *mem; const struct reg *reg; dma_addr_t addr; @@ -393,7 +394,7 @@ err_dma_free: /* Inverse of ipa_mem_config() */ void ipa_mem_deconfig(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; dma_free_coherent(dev, ipa->zero_size, ipa->zero_virt, ipa->zero_addr); ipa->zero_size = 0; @@ -420,8 +421,7 @@ int ipa_mem_zero_modem(struct ipa *ipa) */ trans = ipa_cmd_trans_alloc(ipa, 3); if (!trans) { - dev_err(&ipa->pdev->dev, - "no transaction to zero modem memory\n"); + dev_err(ipa->dev, "no transaction to zero modem memory\n"); return -EBUSY; } @@ -452,7 +452,7 @@ int ipa_mem_zero_modem(struct ipa *ipa) */ static int ipa_imem_init(struct ipa *ipa, unsigned long addr, size_t size) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; struct iommu_domain *domain; unsigned long iova; phys_addr_t phys; @@ -485,13 +485,12 @@ static int ipa_imem_init(struct ipa *ipa, unsigned long addr, size_t size) static void ipa_imem_exit(struct ipa *ipa) { + struct device *dev = ipa->dev; struct iommu_domain *domain; - struct device *dev; if (!ipa->imem_size) return; - dev = &ipa->pdev->dev; domain = iommu_get_domain_for_dev(dev); if (domain) { size_t size; @@ -527,7 +526,7 @@ static void ipa_imem_exit(struct ipa *ipa) */ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; struct iommu_domain *domain; unsigned long iova; phys_addr_t phys; @@ -594,7 +593,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) static void ipa_smem_exit(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; struct iommu_domain *domain; domain = iommu_get_domain_for_dev(dev); @@ -615,9 +614,10 @@ static void ipa_smem_exit(struct ipa *ipa) } /* Perform memory region-related initialization */ -int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) +int ipa_mem_init(struct ipa *ipa, struct platform_device *pdev, + const struct ipa_mem_data *mem_data) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = &pdev->dev; struct resource *res; int ret; @@ -634,14 +634,13 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) if (!ipa_table_mem_valid(ipa, true)) return -EINVAL; - ret = dma_set_mask_and_coherent(&ipa->pdev->dev, DMA_BIT_MASK(64)); + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); if (ret) { dev_err(dev, "error %d setting DMA mask\n", ret); return ret; } - res = platform_get_resource_byname(ipa->pdev, IORESOURCE_MEM, - "ipa-shared"); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ipa-shared"); if (!res) { dev_err(dev, "DT error getting \"ipa-shared\" memory property\n"); diff --git a/drivers/net/ipa/ipa_mem.h b/drivers/net/ipa/ipa_mem.h index 868e9c20e8c4..28aad00a151d 100644 --- a/drivers/net/ipa/ipa_mem.h +++ b/drivers/net/ipa/ipa_mem.h @@ -6,6 +6,8 @@ #ifndef _IPA_MEM_H_ #define _IPA_MEM_H_ +struct platform_device; + struct ipa; struct ipa_mem_data; @@ -100,7 +102,8 @@ int ipa_mem_setup(struct ipa *ipa); /* No ipa_mem_teardown() needed */ int ipa_mem_zero_modem(struct ipa *ipa); -int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data); +int ipa_mem_init(struct ipa *ipa, struct platform_device *pdev, + const struct ipa_mem_data *mem_data); void ipa_mem_exit(struct ipa *ipa); #endif /* _IPA_MEM_H_ */ diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index 1d1be92fbebc..c27ca3f27f7d 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -58,7 +58,7 @@ static int ipa_open(struct net_device *netdev) struct device *dev; int ret; - dev = &ipa->pdev->dev; + dev = ipa->dev; ret = pm_runtime_get_sync(dev); if (ret < 0) goto err_power_put; @@ -94,7 +94,7 @@ static int ipa_stop(struct net_device *netdev) struct device *dev; int ret; - dev = &ipa->pdev->dev; + dev = ipa->dev; ret = pm_runtime_get_sync(dev); if (ret < 0) goto out_power_put; @@ -158,7 +158,7 @@ ipa_start_xmit(struct sk_buff *skb, struct net_device *netdev) */ netif_stop_queue(netdev); - dev = &ipa->pdev->dev; + dev = ipa->dev; ret = pm_runtime_get(dev); if (ret < 1) { /* If a resume won't happen, just drop the packet */ @@ -322,7 +322,7 @@ int ipa_modem_start(struct ipa *ipa) goto out_set_state; } - SET_NETDEV_DEV(netdev, &ipa->pdev->dev); + SET_NETDEV_DEV(netdev, ipa->dev); priv = netdev_priv(netdev); priv->ipa = ipa; priv->tx = ipa->name_map[IPA_ENDPOINT_AP_MODEM_TX]; @@ -396,7 +396,7 @@ int ipa_modem_stop(struct ipa *ipa) /* Treat a "clean" modem stop the same as a crash */ static void ipa_modem_crashed(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; int ret; /* Prevent the modem from triggering a call to ipa_setup() */ @@ -443,7 +443,7 @@ static int ipa_modem_notify(struct notifier_block *nb, unsigned long action, { struct ipa *ipa = container_of(nb, struct ipa, nb); struct qcom_ssr_notify_data *notify_data = data; - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; switch (action) { case QCOM_SSR_BEFORE_POWERUP: @@ -492,7 +492,7 @@ int ipa_modem_config(struct ipa *ipa) void ipa_modem_deconfig(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; int ret; ret = qcom_unregister_ssr_notifier(ipa->notifier, &ipa->nb); diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index 0f635b8356bf..41ca7ef5e20f 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -238,7 +238,7 @@ int ipa_power_setup(struct ipa *ipa) ipa_interrupt_enable(ipa, IPA_IRQ_TX_SUSPEND); - ret = device_init_wakeup(&ipa->pdev->dev, true); + ret = device_init_wakeup(ipa->dev, true); if (ret) ipa_interrupt_disable(ipa, IPA_IRQ_TX_SUSPEND); @@ -247,7 +247,7 @@ int ipa_power_setup(struct ipa *ipa) void ipa_power_teardown(struct ipa *ipa) { - (void)device_init_wakeup(&ipa->pdev->dev, false); + (void)device_init_wakeup(ipa->dev, false); ipa_interrupt_disable(ipa, IPA_IRQ_TX_SUSPEND); } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index f70f0a1d1cda..65c40e207802 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -96,7 +96,7 @@ static void ipa_server_init_complete(struct ipa_qmi *ipa_qmi) IPA_QMI_INIT_COMPLETE_IND_SZ, ipa_init_complete_ind_ei, &ind); if (ret) - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "error %d sending init complete indication\n", ret); else ipa_qmi->indication_sent = true; @@ -148,7 +148,7 @@ static void ipa_qmi_ready(struct ipa_qmi *ipa_qmi) ipa = container_of(ipa_qmi, struct ipa, qmi); ret = ipa_modem_start(ipa); if (ret) - dev_err(&ipa->pdev->dev, "error %d starting modem\n", ret); + dev_err(ipa->dev, "error %d starting modem\n", ret); } /* All QMI clients from the modem node are gone (modem shut down or crashed). */ @@ -199,7 +199,7 @@ static void ipa_server_indication_register(struct qmi_handle *qmi, ipa_qmi->indication_requested = true; ipa_qmi_ready(ipa_qmi); /* We might be ready now */ } else { - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "error %d sending register indication response\n", ret); } } @@ -228,7 +228,7 @@ static void ipa_server_driver_init_complete(struct qmi_handle *qmi, ipa_qmi->uc_ready = true; ipa_qmi_ready(ipa_qmi); /* We might be ready now */ } else { - dev_err(&ipa->pdev->dev, + dev_err(ipa->dev, "error %d sending init complete response\n", ret); } } @@ -417,7 +417,7 @@ static void ipa_client_init_driver_work(struct work_struct *work) qmi = &ipa_qmi->client_handle; ipa = container_of(ipa_qmi, struct ipa, qmi); - dev = &ipa->pdev->dev; + dev = ipa->dev; ret = qmi_txn_init(qmi, &txn, NULL, NULL); if (ret < 0) { diff --git a/drivers/net/ipa/ipa_reg.c b/drivers/net/ipa/ipa_reg.c index 6a3203ae6f1e..98625956e0bb 100644 --- a/drivers/net/ipa/ipa_reg.c +++ b/drivers/net/ipa/ipa_reg.c @@ -4,6 +4,7 @@ * Copyright (C) 2019-2023 Linaro Ltd. */ +#include <linux/platform_device.h> #include <linux/io.h> #include "ipa.h" @@ -132,9 +133,9 @@ static const struct regs *ipa_regs(enum ipa_version version) } } -int ipa_reg_init(struct ipa *ipa) +int ipa_reg_init(struct ipa *ipa, struct platform_device *pdev) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = &pdev->dev; const struct regs *regs; struct resource *res; @@ -146,8 +147,7 @@ int ipa_reg_init(struct ipa *ipa) return -EINVAL; /* Setup IPA register memory */ - res = platform_get_resource_byname(ipa->pdev, IORESOURCE_MEM, - "ipa-reg"); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ipa-reg"); if (!res) { dev_err(dev, "DT error getting \"ipa-reg\" memory property\n"); return -ENODEV; diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h index 2998f115f12c..62c62495b796 100644 --- a/drivers/net/ipa/ipa_reg.h +++ b/drivers/net/ipa/ipa_reg.h @@ -12,6 +12,8 @@ #include "ipa_version.h" #include "reg.h" +struct platform_device; + struct ipa; /** @@ -643,7 +645,7 @@ extern const struct regs ipa_regs_v5_5; const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id); -int ipa_reg_init(struct ipa *ipa); +int ipa_reg_init(struct ipa *ipa, struct platform_device *pdev); void ipa_reg_exit(struct ipa *ipa); #endif /* _IPA_REG_H_ */ diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 5620dc271fac..aeccce9fab72 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -5,7 +5,7 @@ */ #include <linux/types.h> -#include <linux/device.h> +#include <linux/platform_device.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/panic_notifier.h> @@ -84,15 +84,13 @@ struct ipa_smp2p { */ static void ipa_smp2p_notify(struct ipa_smp2p *smp2p) { - struct device *dev; u32 value; u32 mask; if (smp2p->notified) return; - dev = &smp2p->ipa->pdev->dev; - smp2p->power_on = pm_runtime_get_if_active(dev, true) > 0; + smp2p->power_on = pm_runtime_get_if_active(smp2p->ipa->dev, true) > 0; /* Signal whether the IPA power is enabled */ mask = BIT(smp2p->enabled_bit); @@ -152,15 +150,16 @@ static void ipa_smp2p_panic_notifier_unregister(struct ipa_smp2p *smp2p) static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) { struct ipa_smp2p *smp2p = dev_id; + struct ipa *ipa = smp2p->ipa; struct device *dev; int ret; /* Ignore any (spurious) interrupts received after the first */ - if (smp2p->ipa->setup_complete) + if (ipa->setup_complete) return IRQ_HANDLED; /* Power needs to be active for setup */ - dev = &smp2p->ipa->pdev->dev; + dev = ipa->dev; ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "error %d getting power for setup\n", ret); @@ -168,7 +167,7 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) } /* An error here won't cause driver shutdown, so warn if one occurs */ - ret = ipa_setup(smp2p->ipa); + ret = ipa_setup(ipa); WARN(ret != 0, "error %d from ipa_setup()\n", ret); out_power_put: @@ -179,14 +178,15 @@ out_power_put: } /* Initialize SMP2P interrupts */ -static int ipa_smp2p_irq_init(struct ipa_smp2p *smp2p, const char *name, - irq_handler_t handler) +static int ipa_smp2p_irq_init(struct ipa_smp2p *smp2p, + struct platform_device *pdev, + const char *name, irq_handler_t handler) { - struct device *dev = &smp2p->ipa->pdev->dev; + struct device *dev = &pdev->dev; unsigned int irq; int ret; - ret = platform_get_irq_byname(smp2p->ipa->pdev, name); + ret = platform_get_irq_byname(pdev, name); if (ret <= 0) return ret ? : -EINVAL; irq = ret; @@ -208,7 +208,7 @@ static void ipa_smp2p_irq_exit(struct ipa_smp2p *smp2p, u32 irq) /* Drop the power reference if it was taken in ipa_smp2p_notify() */ static void ipa_smp2p_power_release(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; if (!ipa->smp2p->power_on) return; @@ -219,10 +219,11 @@ static void ipa_smp2p_power_release(struct ipa *ipa) } /* Initialize the IPA SMP2P subsystem */ -int ipa_smp2p_init(struct ipa *ipa, bool modem_init) +int +ipa_smp2p_init(struct ipa *ipa, struct platform_device *pdev, bool modem_init) { struct qcom_smem_state *enabled_state; - struct device *dev = &ipa->pdev->dev; + struct device *dev = &pdev->dev; struct qcom_smem_state *valid_state; struct ipa_smp2p *smp2p; u32 enabled_bit; @@ -261,7 +262,7 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init) /* We have enough information saved to handle notifications */ ipa->smp2p = smp2p; - ret = ipa_smp2p_irq_init(smp2p, "ipa-clock-query", + ret = ipa_smp2p_irq_init(smp2p, pdev, "ipa-clock-query", ipa_smp2p_modem_clk_query_isr); if (ret < 0) goto err_null_smp2p; @@ -273,7 +274,7 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init) if (modem_init) { /* Result will be non-zero (negative for error) */ - ret = ipa_smp2p_irq_init(smp2p, "ipa-setup-ready", + ret = ipa_smp2p_irq_init(smp2p, pdev, "ipa-setup-ready", ipa_smp2p_modem_setup_ready_isr); if (ret < 0) goto err_notifier_unregister; diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h index 9b969b03d1a4..2a3d8eefb13b 100644 --- a/drivers/net/ipa/ipa_smp2p.h +++ b/drivers/net/ipa/ipa_smp2p.h @@ -8,17 +8,20 @@ #include <linux/types.h> +struct platform_device; + struct ipa; /** * ipa_smp2p_init() - Initialize the IPA SMP2P subsystem * @ipa: IPA pointer + * @pdev: Platform device pointer * @modem_init: Whether the modem is responsible for GSI initialization * * Return: 0 if successful, or a negative error code - * */ -int ipa_smp2p_init(struct ipa *ipa, bool modem_init); +int ipa_smp2p_init(struct ipa *ipa, struct platform_device *pdev, + bool modem_init); /** * ipa_smp2p_exit() - Inverse of ipa_smp2p_init() diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 7b637bb8b41c..a24ac11b8893 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -163,7 +163,7 @@ ipa_table_mem(struct ipa *ipa, bool filter, bool hashed, bool ipv6) bool ipa_filtered_valid(struct ipa *ipa, u64 filtered) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; u32 count; if (!filtered) { @@ -236,8 +236,7 @@ ipa_filter_reset_table(struct ipa *ipa, bool hashed, bool ipv6, bool modem) trans = ipa_cmd_trans_alloc(ipa, hweight64(ep_mask)); if (!trans) { - dev_err(&ipa->pdev->dev, - "no transaction for %s filter reset\n", + dev_err(ipa->dev, "no transaction for %s filter reset\n", modem ? "modem" : "AP"); return -EBUSY; } @@ -298,8 +297,7 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) trans = ipa_cmd_trans_alloc(ipa, hash_support ? 4 : 2); if (!trans) { - dev_err(&ipa->pdev->dev, - "no transaction for %s route reset\n", + dev_err(ipa->dev, "no transaction for %s route reset\n", modem ? "modem" : "AP"); return -EBUSY; } @@ -327,7 +325,7 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) void ipa_table_reset(struct ipa *ipa, bool modem) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; const char *ee_name; int ret; @@ -356,7 +354,7 @@ int ipa_table_hash_flush(struct ipa *ipa) trans = ipa_cmd_trans_alloc(ipa, 1); if (!trans) { - dev_err(&ipa->pdev->dev, "no transaction for hash flush\n"); + dev_err(ipa->dev, "no transaction for hash flush\n"); return -EBUSY; } @@ -469,7 +467,7 @@ int ipa_table_setup(struct ipa *ipa) */ trans = ipa_cmd_trans_alloc(ipa, 8); if (!trans) { - dev_err(&ipa->pdev->dev, "no transaction for table setup\n"); + dev_err(ipa->dev, "no transaction for table setup\n"); return -EBUSY; } @@ -713,7 +711,7 @@ bool ipa_table_mem_valid(struct ipa *ipa, bool filter) */ int ipa_table_init(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; dma_addr_t addr; __le64 le_addr; __le64 *virt; @@ -763,7 +761,7 @@ int ipa_table_init(struct ipa *ipa) void ipa_table_exit(struct ipa *ipa) { u32 count = max_t(u32, 1 + ipa->filter_count, ipa->route_count); - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; size_t size; size = IPA_ZERO_RULE_SIZE + (1 + count) * sizeof(__le64); diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 7eaa0b4ebed9..bfd5dc6dab43 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -127,7 +127,7 @@ static struct ipa_uc_mem_area *ipa_uc_shared(struct ipa *ipa) static void ipa_uc_event_handler(struct ipa *ipa) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; if (shared->event == IPA_UC_EVENT_ERROR) dev_err(dev, "microcontroller error event\n"); @@ -141,7 +141,7 @@ static void ipa_uc_event_handler(struct ipa *ipa) static void ipa_uc_response_hdlr(struct ipa *ipa) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; /* An INIT_COMPLETED response message is sent to the AP by the * microcontroller when it is operational. Other than this, the AP @@ -191,7 +191,7 @@ void ipa_uc_config(struct ipa *ipa) /* Inverse of ipa_uc_config() */ void ipa_uc_deconfig(struct ipa *ipa) { - struct device *dev = &ipa->pdev->dev; + struct device *dev = ipa->dev; ipa_interrupt_disable(ipa, IPA_IRQ_UC_1); ipa_interrupt_disable(ipa, IPA_IRQ_UC_0); @@ -208,8 +208,8 @@ void ipa_uc_deconfig(struct ipa *ipa) /* Take a proxy power reference for the microcontroller */ void ipa_uc_power(struct ipa *ipa) { + struct device *dev = ipa->dev; static bool already; - struct device *dev; int ret; if (already) @@ -217,7 +217,6 @@ void ipa_uc_power(struct ipa *ipa) already = true; /* Only do this on first boot */ /* This power reference dropped in ipa_uc_response_hdlr() above */ - dev = &ipa->pdev->dev; ret = pm_runtime_get_sync(dev); if (ret < 0) { pm_runtime_put_noidle(dev); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 4b5513c9c2be..0206b84284ab 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3519,18 +3519,13 @@ static int macsec_dev_init(struct net_device *dev) struct net_device *real_dev = macsec->real_dev; int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&macsec->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; macsec_set_head_tail_room(dev); @@ -3550,7 +3545,6 @@ static void macsec_dev_uninit(struct net_device *dev) struct macsec_dev *macsec = macsec_priv(dev); gro_cells_destroy(&macsec->gro_cells); - free_percpu(dev->tstats); } static netdev_features_t macsec_fix_features(struct net_device *dev, diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 0de108a1c0c8..d7070dd4fe73 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -42,12 +42,14 @@ MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); -#define MAX_PARAM_LENGTH 256 -#define MAX_USERDATA_NAME_LENGTH 54 -#define MAX_USERDATA_VALUE_LENGTH 200 +#define MAX_PARAM_LENGTH 256 #define MAX_USERDATA_ENTRY_LENGTH 256 +#define MAX_USERDATA_VALUE_LENGTH 200 +/* The number 3 comes from userdata entry format characters (' ', '=', '\n') */ +#define MAX_USERDATA_NAME_LENGTH (MAX_USERDATA_ENTRY_LENGTH - \ + MAX_USERDATA_VALUE_LENGTH - 3) #define MAX_USERDATA_ITEMS 16 -#define MAX_PRINT_CHUNK 1000 +#define MAX_PRINT_CHUNK 1000 static char config[MAX_PARAM_LENGTH]; module_param_string(netconsole, config, MAX_PARAM_LENGTH, 0); @@ -671,7 +673,7 @@ static void update_userdata(struct netconsole_target *nt) * checked to not exceed MAX items with child_count above */ complete_idx += scnprintf(&nt->userdata_complete[complete_idx], - MAX_USERDATA_ENTRY_LENGTH, "%s=%s\n", + MAX_USERDATA_ENTRY_LENGTH, " %s=%s\n", item->ci_name, udm_item->value); } nt->userdata_length = strnlen(nt->userdata_complete, diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index 5e19a6839dea..e5a0987a263e 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -17,17 +17,6 @@ static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static int nlmon_dev_init(struct net_device *dev) -{ - dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); - return dev->lstats == NULL ? -ENOMEM : 0; -} - -static void nlmon_dev_uninit(struct net_device *dev) -{ - free_percpu(dev->lstats); -} - struct nlmon { struct netlink_tap nt; }; @@ -51,15 +40,7 @@ static int nlmon_close(struct net_device *dev) static void nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { - u64 packets, bytes; - - dev_lstats_read(dev, &packets, &bytes); - - stats->rx_packets = packets; - stats->tx_packets = 0; - - stats->rx_bytes = bytes; - stats->tx_bytes = 0; + dev_lstats_read(dev, &stats->rx_packets, &stats->rx_bytes); } static u32 always_on(struct net_device *dev) @@ -72,8 +53,6 @@ static const struct ethtool_ops nlmon_ethtool_ops = { }; static const struct net_device_ops nlmon_ops = { - .ndo_init = nlmon_dev_init, - .ndo_uninit = nlmon_dev_uninit, .ndo_open = nlmon_open, .ndo_stop = nlmon_close, .ndo_start_xmit = nlmon_xmit, @@ -92,6 +71,7 @@ static void nlmon_setup(struct net_device *dev) dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_LLTX; dev->flags = IFF_NOARP; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS; /* That's rather a softlimit here, which, of course, * can be altered. Not a real MTU, but what is to be diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index d93f84fbb1fd..4bd66fdde367 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -183,7 +183,7 @@ static void miic_converter_enable(struct miic *miic, int port, int enable) miic_reg_rmw(miic, MIIC_CONVRST, MIIC_CONVRST_PHYIF_RST(port), val); } -static int miic_config(struct phylink_pcs *pcs, unsigned int mode, +static int miic_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, bool permit) { @@ -234,7 +234,7 @@ static int miic_config(struct phylink_pcs *pcs, unsigned int mode, return 0; } -static void miic_link_up(struct phylink_pcs *pcs, unsigned int mode, +static void miic_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex) { struct miic_port *miic_port = phylink_pcs_to_miic_port(pcs); @@ -333,6 +333,7 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np) miic_port->miic = miic; miic_port->port = port - 1; miic_port->pcs.ops = &miic_phylink_ops; + miic_port->pcs.neg_mode = true; return &miic_port->pcs; } diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index e3aa30dad2e6..b88398e6872b 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -9,12 +9,10 @@ */ #include <linux/module.h> #include <linux/phy.h> -#include <linux/gpio.h> #include <linux/delay.h> #include <linux/mdio.h> #include <linux/marvell_phy.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/sfp.h> #include <linux/netdevice.h> diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 1faa22f58366..42ed013385bf 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -919,7 +919,10 @@ static int m88e1111_config_init_1000basex(struct phy_device *phydev) if (extsr < 0) return extsr; - /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled */ + /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled. + * FIXME: this does not actually enable 1000BaseX auto-negotiation if + * it was previously disabled in the Fiber BMCR! + */ mode = extsr & MII_M1111_HWCFG_MODE_MASK; if (mode == MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN) { err = phy_modify(phydev, MII_M1111_PHY_EXT_SR, diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index b765466e767f..8b9ead76e40e 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -13,7 +13,6 @@ #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include <linux/gpio.h> #include <linux/gpio/consumer.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -25,7 +24,6 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/of_mdio.h> #include <linux/phy.h> #include <linux/reset.h> diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 9b6973581989..8b8634600c51 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -114,6 +114,13 @@ #define LAN8814_INTR_CTRL_REG_POLARITY BIT(1) #define LAN8814_INTR_CTRL_REG_INTR_ENABLE BIT(0) +#define LAN8814_EEE_STATE 0x38 +#define LAN8814_EEE_STATE_MASK2P5P BIT(10) + +#define LAN8814_PD_CONTROLS 0x9d +#define LAN8814_PD_CONTROLS_PD_MEAS_TIME_MASK GENMASK(3, 0) +#define LAN8814_PD_CONTROLS_PD_MEAS_TIME_VAL 0xb + /* Represents 1ppm adjustment in 2^32 format with * each nsec contains 4 clock cycles. * The value is calculated as following: (1/1000000)/((2^-32)/4) @@ -3288,6 +3295,33 @@ static int lan8814_release_coma_mode(struct phy_device *phydev) return 0; } +static void lan8814_clear_2psp_bit(struct phy_device *phydev) +{ + u16 val; + + /* It was noticed that when traffic is passing through the PHY and the + * cable is removed then the LED was still one even though there is no + * link + */ + val = lanphy_read_page_reg(phydev, 2, LAN8814_EEE_STATE); + val &= ~LAN8814_EEE_STATE_MASK2P5P; + lanphy_write_page_reg(phydev, 2, LAN8814_EEE_STATE, val); +} + +static void lan8814_update_meas_time(struct phy_device *phydev) +{ + u16 val; + + /* By setting the measure time to a value of 0xb this will allow cables + * longer than 100m to be used. This configuration can be used + * regardless of the mode of operation of the PHY + */ + val = lanphy_read_page_reg(phydev, 1, LAN8814_PD_CONTROLS); + val &= ~LAN8814_PD_CONTROLS_PD_MEAS_TIME_MASK; + val |= LAN8814_PD_CONTROLS_PD_MEAS_TIME_VAL; + lanphy_write_page_reg(phydev, 1, LAN8814_PD_CONTROLS, val); +} + static int lan8814_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -3324,6 +3358,10 @@ static int lan8814_probe(struct phy_device *phydev) lan8814_ptp_init(phydev); + /* Errata workarounds */ + lan8814_clear_2psp_bit(phydev); + lan8814_update_meas_time(phydev); + return 0; } diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 3e95b8a15f44..5695935fdce9 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -1550,6 +1550,8 @@ EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); * advertised, but the previously advertised link modes are * retained. This allows EEE to be enabled/disabled in a * non-destructive way. + * Returns either error code, 0 if there was no change, or positive + * value if there was a change which triggered auto-neg. */ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data) @@ -1576,8 +1578,16 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, phydev->eee_enabled = data->eee_enabled; ret = genphy_c45_an_config_eee_aneg(phydev); - if (ret > 0) - return phy_restart_aneg(phydev); + if (ret > 0) { + ret = phy_restart_aneg(phydev); + if (ret < 0) + return ret; + + /* explicitly return 1, otherwise (ret > 0) value will be + * overwritten by phy_restart_aneg(). + */ + return 1; + } return ret; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 14224e06d69f..c4236564c1cd 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -983,9 +983,17 @@ static int phy_check_link_status(struct phy_device *phydev) if (phydev->link && phydev->state != PHY_RUNNING) { phy_check_downshift(phydev); phydev->state = PHY_RUNNING; + err = genphy_c45_eee_is_active(phydev, + NULL, NULL, NULL); + if (err <= 0) + phydev->enable_tx_lpi = false; + else + phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled; + phy_link_up(phydev); } else if (!phydev->link && phydev->state != PHY_NOLINK) { phydev->state = PHY_NOLINK; + phydev->enable_tx_lpi = false; phy_link_down(phydev); } @@ -1633,8 +1641,8 @@ EXPORT_SYMBOL(phy_get_eee_err); * @phydev: target phy_device struct * @data: ethtool_keee data * - * Description: it reportes the Supported/Advertisement/LP Advertisement - * capabilities. + * Description: reports the Supported/Advertisement/LP Advertisement + * capabilities, etc. */ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) { @@ -1645,6 +1653,7 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) mutex_lock(&phydev->lock); ret = genphy_c45_ethtool_get_eee(phydev, data); + eeecfg_to_eee(data, &phydev->eee_cfg); mutex_unlock(&phydev->lock); return ret; @@ -1652,6 +1661,36 @@ int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data) EXPORT_SYMBOL(phy_ethtool_get_eee); /** + * phy_ethtool_set_eee_noneg - Adjusts MAC LPI configuration without PHY + * renegotiation + * @phydev: pointer to the target PHY device structure + * @data: pointer to the ethtool_keee structure containing the new EEE settings + * + * This function updates the Energy Efficient Ethernet (EEE) configuration + * for cases where only the MAC's Low Power Idle (LPI) configuration changes, + * without triggering PHY renegotiation. It ensures that the MAC is properly + * informed of the new LPI settings by cycling the link down and up, which + * is necessary for the MAC to adopt the new configuration. This adjustment + * is done only if there is a change in the tx_lpi_enabled or tx_lpi_timer + * configuration. + */ +static void phy_ethtool_set_eee_noneg(struct phy_device *phydev, + struct ethtool_keee *data) +{ + if (phydev->eee_cfg.tx_lpi_enabled != data->tx_lpi_enabled || + phydev->eee_cfg.tx_lpi_timer != data->tx_lpi_timer) { + eee_to_eeecfg(&phydev->eee_cfg, data); + phydev->enable_tx_lpi = eeecfg_mac_can_tx_lpi(&phydev->eee_cfg); + if (phydev->link) { + phydev->link = false; + phy_link_down(phydev); + phydev->link = true; + phy_link_up(phydev); + } + } +} + +/** * phy_ethtool_set_eee - set EEE supported and status * @phydev: target phy_device struct * @data: ethtool_keee data @@ -1667,9 +1706,14 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data) mutex_lock(&phydev->lock); ret = genphy_c45_ethtool_set_eee(phydev, data); + if (ret >= 0) { + if (ret == 0) + phy_ethtool_set_eee_noneg(phydev, data); + eee_to_eeecfg(&phydev->eee_cfg, data); + } mutex_unlock(&phydev->lock); - return ret; + return ret < 0 ? ret : 0; } EXPORT_SYMBOL(phy_ethtool_set_eee); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2eefee970851..72452e6a478c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2911,6 +2911,34 @@ void phy_advertise_eee_all(struct phy_device *phydev) EXPORT_SYMBOL_GPL(phy_advertise_eee_all); /** + * phy_support_eee - Set initial EEE policy configuration + * @phydev: Target phy_device struct + * + * This function configures the initial policy for Energy Efficient Ethernet + * (EEE) on the specified PHY device, influencing that EEE capabilities are + * advertised before the link is established. It should be called during PHY + * registration by the MAC driver and/or the PHY driver (for SmartEEE PHYs) + * if MAC supports LPI or PHY is capable to compensate missing LPI functionality + * of the MAC. + * + * The function sets default EEE policy parameters, including preparing the PHY + * to advertise EEE capabilities based on hardware support. + * + * It also sets the expected configuration for Low Power Idle (LPI) in the MAC + * driver. If the PHY framework determines that both local and remote + * advertisements support EEE, and the negotiated link mode is compatible with + * EEE, it will set enable_tx_lpi = true. The MAC driver is expected to act on + * this setting by enabling the LPI timer if enable_tx_lpi is set. + */ +void phy_support_eee(struct phy_device *phydev) +{ + linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + phydev->eee_cfg.tx_lpi_enabled = true; + phydev->eee_cfg.eee_enabled = true; +} +EXPORT_SYMBOL(phy_support_eee); + +/** * phy_support_sym_pause - Enable support of symmetrical pause * @phydev: target phy_device struct * diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 780c28e2e4aa..672c6929119a 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -732,24 +732,24 @@ static int qca807x_probe(struct phy_device *phydev) priv->dac_disable_bias_current_tweak = of_property_read_bool(node, "qcom,dac-disable-bias-current-tweak"); - if (IS_ENABLED(CONFIG_GPIOLIB)) { - /* Make sure we don't have mixed leds node and gpio-controller - * to prevent registering leds and having gpio-controller usage - * conflicting with them. - */ - if (of_find_property(node, "leds", NULL) && - of_find_property(node, "gpio-controller", NULL)) { - phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); - return -EINVAL; - } +#if IS_ENABLED(CONFIG_GPIOLIB) + /* Make sure we don't have mixed leds node and gpio-controller + * to prevent registering leds and having gpio-controller usage + * conflicting with them. + */ + if (of_find_property(node, "leds", NULL) && + of_find_property(node, "gpio-controller", NULL)) { + phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); + return -EINVAL; + } - /* Do not register a GPIO controller unless flagged for it */ - if (of_property_read_bool(node, "gpio-controller")) { - ret = qca807x_gpio(phydev); - if (ret) - return ret; - } + /* Do not register a GPIO controller unless flagged for it */ + if (of_property_read_bool(node, "gpio-controller")) { + ret = qca807x_gpio(phydev); + if (ret) + return ret; } +#endif /* Attach SFP bus on combo port*/ if (phy_read(phydev, QCA807X_CHIP_CONFIGURATION)) { diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index db1d11ae817b..fe380fe196e7 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -295,7 +295,9 @@ static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; -static struct class *ppp_class; +static const struct class ppp_class = { + .name = "ppp", +}; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) @@ -1394,11 +1396,9 @@ static int __init ppp_init(void) goto out_net; } - ppp_class = class_create("ppp"); - if (IS_ERR(ppp_class)) { - err = PTR_ERR(ppp_class); + err = class_register(&ppp_class); + if (err) goto out_chrdev; - } err = rtnl_link_register(&ppp_link_ops); if (err) { @@ -1407,12 +1407,12 @@ static int __init ppp_init(void) } /* not a big deal if we fail here :-) */ - device_create(ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); + device_create(&ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: - class_destroy(ppp_class); + class_unregister(&ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: @@ -3549,8 +3549,8 @@ static void __exit ppp_cleanup(void) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); - device_destroy(ppp_class, MKDEV(PPP_MAJOR, 0)); - class_destroy(ppp_class); + device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); + class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index be37235af55d..0b3f21cba552 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -78,6 +78,7 @@ #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> @@ -977,20 +978,15 @@ static int tun_net_init(struct net_device *dev) struct ifreq *ifr = tun->ifr; int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - spin_lock_init(&tun->lock); err = security_tun_dev_alloc_security(&tun->security); - if (err < 0) { - free_percpu(dev->tstats); + if (err < 0) return err; - } tun_flow_init(tun); + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; @@ -1008,7 +1004,6 @@ static int tun_net_init(struct net_device *dev) if (err < 0) { tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); - free_percpu(dev->tstats); return err; } return 0; @@ -1344,7 +1339,6 @@ static const struct net_device_ops tap_netdev_ops = { .ndo_select_queue = tun_select_queue, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = tun_set_headroom, - .ndo_get_stats64 = dev_get_tstats64, .ndo_bpf = tun_xdp, .ndo_xdp_xmit = tun_xdp_xmit, .ndo_change_carrier = tun_net_change_carrier, @@ -2317,7 +2311,6 @@ static void tun_free_netdev(struct net_device *dev) BUG_ON(!(list_empty(&tun->disabled))); - free_percpu(dev->tstats); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 3ff430198512..80ee4fcdfb36 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3135,7 +3135,8 @@ static int lan78xx_open(struct net_device *net) done: mutex_unlock(&dev->dev_mutex); - usb_autopm_put_interface(dev->intf); + if (ret < 0) + usb_autopm_put_interface(dev->intf); return ret; } diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 143bd4ab160d..57947a5590cc 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -737,7 +737,9 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) data->eeprom_len = SR9800_EEPROM_LEN; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* LED Setting Rule : * AABB:CCDD diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index b21ebe24057f..e84efa661589 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1633,7 +1633,6 @@ void usbnet_disconnect (struct usb_interface *intf) usb_free_urb(dev->interrupt); kfree(dev->padding_pkt); - free_percpu(net->tstats); free_netdev(net); } EXPORT_SYMBOL_GPL(usbnet_disconnect); @@ -1645,7 +1644,6 @@ static const struct net_device_ops usbnet_netdev_ops = { .ndo_tx_timeout = usbnet_tx_timeout, .ndo_set_rx_mode = usbnet_set_rx_mode, .ndo_change_mtu = usbnet_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; @@ -1710,10 +1708,6 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->rx_speed = SPEED_UNSET; dev->tx_speed = SPEED_UNSET; - net->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!net->tstats) - goto out0; - dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK); init_waitqueue_head(&dev->wait); @@ -1743,6 +1737,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; net->ethtool_ops = &usbnet_ethtool_ops; + net->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; // allow device-specific bind/init procedures // NOTE net->name still not usable ... @@ -1861,8 +1856,6 @@ out1: */ cancel_work_sync(&dev->kevent); del_timer_sync(&dev->delay); - free_percpu(net->tstats); -out0: free_netdev(net); out: return status; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 386cbe4d3327..3495591a5c29 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2841,15 +2841,9 @@ static int vxlan_init(struct net_device *dev) if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_init(vxlan); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) { - err = -ENOMEM; - goto err_vnigroup_uninit; - } - err = gro_cells_init(&vxlan->gro_cells, dev); if (err) - goto err_free_percpu; + goto err_vnigroup_uninit; err = vxlan_mdb_init(vxlan); if (err) @@ -2860,8 +2854,6 @@ static int vxlan_init(struct net_device *dev) err_gro_cells_destroy: gro_cells_destroy(&vxlan->gro_cells); -err_free_percpu: - free_percpu(dev->tstats); err_vnigroup_uninit: if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) vxlan_vnigroup_uninit(vxlan); @@ -2892,8 +2884,6 @@ static void vxlan_uninit(struct net_device *dev) gro_cells_destroy(&vxlan->gro_cells); vxlan_fdb_delete_default(vxlan, vxlan->cfg.vni); - - free_percpu(dev->tstats); } /* Start ageing timer and join group when device is brought up */ @@ -3224,7 +3214,6 @@ static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_set_rx_mode = vxlan_set_multicast_list, .ndo_change_mtu = vxlan_change_mtu, .ndo_validate_addr = eth_validate_addr, @@ -3248,7 +3237,6 @@ static const struct net_device_ops vxlan_netdev_raw_ops = { .ndo_open = vxlan_open, .ndo_stop = vxlan_stop, .ndo_start_xmit = vxlan_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_change_mtu = vxlan_change_mtu, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, }; @@ -3316,6 +3304,7 @@ static void vxlan_setup(struct net_device *dev) dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = ETH_MAX_MTU; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; INIT_LIST_HEAD(&vxlan->next); timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE); diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig index 7dda87756d3f..31ab2136cdf1 100644 --- a/drivers/net/wan/Kconfig +++ b/drivers/net/wan/Kconfig @@ -197,6 +197,18 @@ config FARSYNC To compile this driver as a module, choose M here: the module will be called farsync. +config FSL_QMC_HDLC + tristate "Freescale QMC HDLC support" + depends on HDLC + depends on CPM_QMC + help + HDLC support using the Freescale QUICC Multichannel Controller (QMC). + + To compile this driver as a module, choose M here: the + module will be called fsl_qmc_hdlc. + + If unsure, say N. + config FSL_UCC_HDLC tristate "Freescale QUICC Engine HDLC support" depends on HDLC diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile index 8119b49d1da9..00e9b7ee1e01 100644 --- a/drivers/net/wan/Makefile +++ b/drivers/net/wan/Makefile @@ -25,6 +25,7 @@ obj-$(CONFIG_WANXL) += wanxl.o obj-$(CONFIG_PCI200SYN) += pci200syn.o obj-$(CONFIG_PC300TOO) += pc300too.o obj-$(CONFIG_IXP4XX_HSS) += ixp4xx_hss.o +obj-$(CONFIG_FSL_QMC_HDLC) += fsl_qmc_hdlc.o obj-$(CONFIG_FSL_UCC_HDLC) += fsl_ucc_hdlc.o obj-$(CONFIG_SLIC_DS26522) += slic_ds26522.o diff --git a/drivers/net/wan/framer/framer-core.c b/drivers/net/wan/framer/framer-core.c index 33b358b99f70..f547c22e26ac 100644 --- a/drivers/net/wan/framer/framer-core.c +++ b/drivers/net/wan/framer/framer-core.c @@ -18,7 +18,12 @@ #include <linux/regulator/consumer.h> #include <linux/slab.h> -static struct class *framer_class; +static void framer_release(struct device *dev); +static const struct class framer_class = { + .name = "framer", + .dev_release = framer_release, +}; + static DEFINE_MUTEX(framer_provider_mutex); static LIST_HEAD(framer_provider_list); static DEFINE_IDA(framer_ida); @@ -627,7 +632,7 @@ struct framer *framer_create(struct device *dev, struct device_node *node, INIT_DELAYED_WORK(&framer->polling_work, framer_polling_work); BLOCKING_INIT_NOTIFIER_HEAD(&framer->notifier_list); - framer->dev.class = framer_class; + framer->dev.class = &framer_class; framer->dev.parent = dev; framer->dev.of_node = node ? node : dev->of_node; framer->id = id; @@ -741,7 +746,7 @@ struct framer *framer_provider_simple_of_xlate(struct device *dev, struct class_dev_iter iter; struct framer *framer; - class_dev_iter_init(&iter, framer_class, NULL, NULL); + class_dev_iter_init(&iter, &framer_class, NULL, NULL); while ((dev = class_dev_iter_next(&iter))) { framer = dev_to_framer(dev); if (args->np != framer->dev.of_node) @@ -870,14 +875,6 @@ static void framer_release(struct device *dev) static int __init framer_core_init(void) { - framer_class = class_create("framer"); - if (IS_ERR(framer_class)) { - pr_err("failed to create framer class (%pe)\n", framer_class); - return PTR_ERR(framer_class); - } - - framer_class->dev_release = framer_release; - - return 0; + return class_register(&framer_class); } device_initcall(framer_core_init); diff --git a/drivers/net/wan/framer/pef2256/pef2256.c b/drivers/net/wan/framer/pef2256/pef2256.c index 4f81053ee4f0..413a3c1d15bb 100644 --- a/drivers/net/wan/framer/pef2256/pef2256.c +++ b/drivers/net/wan/framer/pef2256/pef2256.c @@ -838,7 +838,7 @@ static int pef2256_probe(struct platform_device *pdev) return 0; } -static int pef2256_remove(struct platform_device *pdev) +static void pef2256_remove(struct platform_device *pdev) { struct pef2256 *pef2256 = platform_get_drvdata(pdev); @@ -849,8 +849,6 @@ static int pef2256_remove(struct platform_device *pdev) pef2256_write8(pef2256, PEF2256_IMR3, 0xff); pef2256_write8(pef2256, PEF2256_IMR4, 0xff); pef2256_write8(pef2256, PEF2256_IMR5, 0xff); - - return 0; } static const struct of_device_id pef2256_id_table[] = { @@ -865,7 +863,7 @@ static struct platform_driver pef2256_driver = { .of_match_table = pef2256_id_table, }, .probe = pef2256_probe, - .remove = pef2256_remove, + .remove_new = pef2256_remove, }; module_platform_driver(pef2256_driver); diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c new file mode 100644 index 000000000000..960371df470a --- /dev/null +++ b/drivers/net/wan/fsl_qmc_hdlc.c @@ -0,0 +1,797 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Freescale QMC HDLC Device Driver + * + * Copyright 2023 CS GROUP France + * + * Author: Herve Codina <herve.codina@bootlin.com> + */ + +#include <linux/array_size.h> +#include <linux/bug.h> +#include <linux/cleanup.h> +#include <linux/bitmap.h> +#include <linux/dma-mapping.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/framer/framer.h> +#include <linux/hdlc.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <soc/fsl/qe/qmc.h> + +struct qmc_hdlc_desc { + struct net_device *netdev; + struct sk_buff *skb; /* NULL if the descriptor is not in use */ + dma_addr_t dma_addr; + size_t dma_size; +}; + +struct qmc_hdlc { + struct device *dev; + struct qmc_chan *qmc_chan; + struct net_device *netdev; + struct framer *framer; + spinlock_t carrier_lock; /* Protect carrier detection */ + struct notifier_block nb; + bool is_crc32; + spinlock_t tx_lock; /* Protect tx descriptors */ + struct qmc_hdlc_desc tx_descs[8]; + unsigned int tx_out; + struct qmc_hdlc_desc rx_descs[4]; + u32 slot_map; +}; + +static struct qmc_hdlc *netdev_to_qmc_hdlc(struct net_device *netdev) +{ + return dev_to_hdlc(netdev)->priv; +} + +static int qmc_hdlc_framer_set_carrier(struct qmc_hdlc *qmc_hdlc) +{ + struct framer_status framer_status; + int ret; + + if (!qmc_hdlc->framer) + return 0; + + guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock); + + ret = framer_get_status(qmc_hdlc->framer, &framer_status); + if (ret) { + dev_err(qmc_hdlc->dev, "get framer status failed (%d)\n", ret); + return ret; + } + if (framer_status.link_is_on) + netif_carrier_on(qmc_hdlc->netdev); + else + netif_carrier_off(qmc_hdlc->netdev); + + return 0; +} + +static int qmc_hdlc_framer_notifier(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct qmc_hdlc *qmc_hdlc = container_of(nb, struct qmc_hdlc, nb); + int ret; + + if (action != FRAMER_EVENT_STATUS) + return NOTIFY_DONE; + + ret = qmc_hdlc_framer_set_carrier(qmc_hdlc); + return ret ? NOTIFY_DONE : NOTIFY_OK; +} + +static int qmc_hdlc_framer_start(struct qmc_hdlc *qmc_hdlc) +{ + struct framer_status framer_status; + int ret; + + if (!qmc_hdlc->framer) + return 0; + + ret = framer_power_on(qmc_hdlc->framer); + if (ret) { + dev_err(qmc_hdlc->dev, "framer power-on failed (%d)\n", ret); + return ret; + } + + /* Be sure that get_status is supported */ + ret = framer_get_status(qmc_hdlc->framer, &framer_status); + if (ret) { + dev_err(qmc_hdlc->dev, "get framer status failed (%d)\n", ret); + goto framer_power_off; + } + + qmc_hdlc->nb.notifier_call = qmc_hdlc_framer_notifier; + ret = framer_notifier_register(qmc_hdlc->framer, &qmc_hdlc->nb); + if (ret) { + dev_err(qmc_hdlc->dev, "framer notifier register failed (%d)\n", ret); + goto framer_power_off; + } + + return 0; + +framer_power_off: + framer_power_off(qmc_hdlc->framer); + return ret; +} + +static void qmc_hdlc_framer_stop(struct qmc_hdlc *qmc_hdlc) +{ + if (!qmc_hdlc->framer) + return; + + framer_notifier_unregister(qmc_hdlc->framer, &qmc_hdlc->nb); + framer_power_off(qmc_hdlc->framer); +} + +static int qmc_hdlc_framer_set_iface(struct qmc_hdlc *qmc_hdlc, int if_iface, + const te1_settings *te1) +{ + struct framer_config config; + int ret; + + if (!qmc_hdlc->framer) + return 0; + + ret = framer_get_config(qmc_hdlc->framer, &config); + if (ret) + return ret; + + switch (if_iface) { + case IF_IFACE_E1: + config.iface = FRAMER_IFACE_E1; + break; + case IF_IFACE_T1: + config.iface = FRAMER_IFACE_T1; + break; + default: + return -EINVAL; + } + + switch (te1->clock_type) { + case CLOCK_DEFAULT: + /* Keep current value */ + break; + case CLOCK_EXT: + config.clock_type = FRAMER_CLOCK_EXT; + break; + case CLOCK_INT: + config.clock_type = FRAMER_CLOCK_INT; + break; + default: + return -EINVAL; + } + config.line_clock_rate = te1->clock_rate; + + return framer_set_config(qmc_hdlc->framer, &config); +} + +static int qmc_hdlc_framer_get_iface(struct qmc_hdlc *qmc_hdlc, int *if_iface, te1_settings *te1) +{ + struct framer_config config; + int ret; + + if (!qmc_hdlc->framer) { + *if_iface = IF_IFACE_E1; + return 0; + } + + ret = framer_get_config(qmc_hdlc->framer, &config); + if (ret) + return ret; + + switch (config.iface) { + case FRAMER_IFACE_E1: + *if_iface = IF_IFACE_E1; + break; + case FRAMER_IFACE_T1: + *if_iface = IF_IFACE_T1; + break; + } + + if (!te1) + return 0; /* Only iface type requested */ + + switch (config.clock_type) { + case FRAMER_CLOCK_EXT: + te1->clock_type = CLOCK_EXT; + break; + case FRAMER_CLOCK_INT: + te1->clock_type = CLOCK_INT; + break; + default: + return -EINVAL; + } + te1->clock_rate = config.line_clock_rate; + return 0; +} + +static int qmc_hdlc_framer_init(struct qmc_hdlc *qmc_hdlc) +{ + int ret; + + if (!qmc_hdlc->framer) + return 0; + + ret = framer_init(qmc_hdlc->framer); + if (ret) { + dev_err(qmc_hdlc->dev, "framer init failed (%d)\n", ret); + return ret; + } + + return 0; +} + +static void qmc_hdlc_framer_exit(struct qmc_hdlc *qmc_hdlc) +{ + if (!qmc_hdlc->framer) + return; + + framer_exit(qmc_hdlc->framer); +} + +static int qmc_hdlc_recv_queue(struct qmc_hdlc *qmc_hdlc, struct qmc_hdlc_desc *desc, size_t size); + +#define QMC_HDLC_RX_ERROR_FLAGS \ + (QMC_RX_FLAG_HDLC_OVF | QMC_RX_FLAG_HDLC_UNA | \ + QMC_RX_FLAG_HDLC_CRC | QMC_RX_FLAG_HDLC_ABORT) + +static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int flags) +{ + struct qmc_hdlc_desc *desc = context; + struct net_device *netdev; + struct qmc_hdlc *qmc_hdlc; + int ret; + + netdev = desc->netdev; + qmc_hdlc = netdev_to_qmc_hdlc(netdev); + + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, DMA_FROM_DEVICE); + + if (flags & QMC_HDLC_RX_ERROR_FLAGS) { + netdev->stats.rx_errors++; + if (flags & QMC_RX_FLAG_HDLC_OVF) /* Data overflow */ + netdev->stats.rx_over_errors++; + if (flags & QMC_RX_FLAG_HDLC_UNA) /* bits received not multiple of 8 */ + netdev->stats.rx_frame_errors++; + if (flags & QMC_RX_FLAG_HDLC_ABORT) /* Received an abort sequence */ + netdev->stats.rx_frame_errors++; + if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */ + netdev->stats.rx_crc_errors++; + kfree_skb(desc->skb); + } else { + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += length; + + skb_put(desc->skb, length); + desc->skb->protocol = hdlc_type_trans(desc->skb, netdev); + netif_rx(desc->skb); + } + + /* Re-queue a transfer using the same descriptor */ + ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size); + if (ret) { + dev_err(qmc_hdlc->dev, "queue recv desc failed (%d)\n", ret); + netdev->stats.rx_errors++; + } +} + +static int qmc_hdlc_recv_queue(struct qmc_hdlc *qmc_hdlc, struct qmc_hdlc_desc *desc, size_t size) +{ + int ret; + + desc->skb = dev_alloc_skb(size); + if (!desc->skb) + return -ENOMEM; + + desc->dma_size = size; + desc->dma_addr = dma_map_single(qmc_hdlc->dev, desc->skb->data, + desc->dma_size, DMA_FROM_DEVICE); + ret = dma_mapping_error(qmc_hdlc->dev, desc->dma_addr); + if (ret) + goto free_skb; + + ret = qmc_chan_read_submit(qmc_hdlc->qmc_chan, desc->dma_addr, desc->dma_size, + qmc_hcld_recv_complete, desc); + if (ret) + goto dma_unmap; + + return 0; + +dma_unmap: + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, DMA_FROM_DEVICE); +free_skb: + kfree_skb(desc->skb); + desc->skb = NULL; + return ret; +} + +static void qmc_hdlc_xmit_complete(void *context) +{ + struct qmc_hdlc_desc *desc = context; + struct net_device *netdev; + struct qmc_hdlc *qmc_hdlc; + struct sk_buff *skb; + + netdev = desc->netdev; + qmc_hdlc = netdev_to_qmc_hdlc(netdev); + + scoped_guard(spinlock_irqsave, &qmc_hdlc->tx_lock) { + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, DMA_TO_DEVICE); + skb = desc->skb; + desc->skb = NULL; /* Release the descriptor */ + if (netif_queue_stopped(netdev)) + netif_wake_queue(netdev); + } + + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += skb->len; + + dev_consume_skb_any(skb); +} + +static int qmc_hdlc_xmit_queue(struct qmc_hdlc *qmc_hdlc, struct qmc_hdlc_desc *desc) +{ + int ret; + + desc->dma_addr = dma_map_single(qmc_hdlc->dev, desc->skb->data, + desc->dma_size, DMA_TO_DEVICE); + ret = dma_mapping_error(qmc_hdlc->dev, desc->dma_addr); + if (ret) { + dev_err(qmc_hdlc->dev, "failed to map skb\n"); + return ret; + } + + ret = qmc_chan_write_submit(qmc_hdlc->qmc_chan, desc->dma_addr, desc->dma_size, + qmc_hdlc_xmit_complete, desc); + if (ret) { + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, DMA_TO_DEVICE); + dev_err(qmc_hdlc->dev, "qmc chan write returns %d\n", ret); + return ret; + } + + return 0; +} + +static netdev_tx_t qmc_hdlc_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct qmc_hdlc *qmc_hdlc = netdev_to_qmc_hdlc(netdev); + struct qmc_hdlc_desc *desc; + int err; + + guard(spinlock_irqsave)(&qmc_hdlc->tx_lock); + + desc = &qmc_hdlc->tx_descs[qmc_hdlc->tx_out]; + if (WARN_ONCE(desc->skb, "No tx descriptors available\n")) { + /* Should never happen. + * Previous xmit should have already stopped the queue. + */ + netif_stop_queue(netdev); + return NETDEV_TX_BUSY; + } + + desc->netdev = netdev; + desc->dma_size = skb->len; + desc->skb = skb; + err = qmc_hdlc_xmit_queue(qmc_hdlc, desc); + if (err) { + desc->skb = NULL; /* Release the descriptor */ + if (err == -EBUSY) { + netif_stop_queue(netdev); + return NETDEV_TX_BUSY; + } + dev_kfree_skb(skb); + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + qmc_hdlc->tx_out = (qmc_hdlc->tx_out + 1) % ARRAY_SIZE(qmc_hdlc->tx_descs); + + if (qmc_hdlc->tx_descs[qmc_hdlc->tx_out].skb) + netif_stop_queue(netdev); + + return NETDEV_TX_OK; +} + +static int qmc_hdlc_xlate_slot_map(struct qmc_hdlc *qmc_hdlc, + u32 slot_map, struct qmc_chan_ts_info *ts_info) +{ + DECLARE_BITMAP(ts_mask_avail, 64); + DECLARE_BITMAP(ts_mask, 64); + DECLARE_BITMAP(map, 64); + + /* Tx and Rx available masks must be identical */ + if (ts_info->rx_ts_mask_avail != ts_info->tx_ts_mask_avail) { + dev_err(qmc_hdlc->dev, "tx and rx available timeslots mismatch (0x%llx, 0x%llx)\n", + ts_info->rx_ts_mask_avail, ts_info->tx_ts_mask_avail); + return -EINVAL; + } + + bitmap_from_u64(ts_mask_avail, ts_info->rx_ts_mask_avail); + bitmap_from_u64(map, slot_map); + bitmap_scatter(ts_mask, map, ts_mask_avail, 64); + + if (bitmap_weight(ts_mask, 64) != bitmap_weight(map, 64)) { + dev_err(qmc_hdlc->dev, "Cannot translate timeslots %64pb -> (%64pb, %64pb)\n", + map, ts_mask_avail, ts_mask); + return -EINVAL; + } + + bitmap_to_arr64(&ts_info->tx_ts_mask, ts_mask, 64); + ts_info->rx_ts_mask = ts_info->tx_ts_mask; + return 0; +} + +static int qmc_hdlc_xlate_ts_info(struct qmc_hdlc *qmc_hdlc, + const struct qmc_chan_ts_info *ts_info, u32 *slot_map) +{ + DECLARE_BITMAP(ts_mask_avail, 64); + DECLARE_BITMAP(ts_mask, 64); + DECLARE_BITMAP(map, 64); + u32 slot_array[2]; + + /* Tx and Rx masks and available masks must be identical */ + if (ts_info->rx_ts_mask_avail != ts_info->tx_ts_mask_avail) { + dev_err(qmc_hdlc->dev, "tx and rx available timeslots mismatch (0x%llx, 0x%llx)\n", + ts_info->rx_ts_mask_avail, ts_info->tx_ts_mask_avail); + return -EINVAL; + } + if (ts_info->rx_ts_mask != ts_info->tx_ts_mask) { + dev_err(qmc_hdlc->dev, "tx and rx timeslots mismatch (0x%llx, 0x%llx)\n", + ts_info->rx_ts_mask, ts_info->tx_ts_mask); + return -EINVAL; + } + + bitmap_from_u64(ts_mask_avail, ts_info->rx_ts_mask_avail); + bitmap_from_u64(ts_mask, ts_info->rx_ts_mask); + bitmap_gather(map, ts_mask, ts_mask_avail, 64); + + if (bitmap_weight(ts_mask, 64) != bitmap_weight(map, 64)) { + dev_err(qmc_hdlc->dev, "Cannot translate timeslots (%64pb, %64pb) -> %64pb\n", + ts_mask_avail, ts_mask, map); + return -EINVAL; + } + + bitmap_to_arr32(slot_array, map, 64); + if (slot_array[1]) { + dev_err(qmc_hdlc->dev, "Slot map out of 32bit (%64pb, %64pb) -> %64pb\n", + ts_mask_avail, ts_mask, map); + return -EINVAL; + } + + *slot_map = slot_array[0]; + return 0; +} + +static int qmc_hdlc_set_iface(struct qmc_hdlc *qmc_hdlc, int if_iface, const te1_settings *te1) +{ + struct qmc_chan_ts_info ts_info; + int ret; + + ret = qmc_chan_get_ts_info(qmc_hdlc->qmc_chan, &ts_info); + if (ret) { + dev_err(qmc_hdlc->dev, "get QMC channel ts info failed %d\n", ret); + return ret; + } + ret = qmc_hdlc_xlate_slot_map(qmc_hdlc, te1->slot_map, &ts_info); + if (ret) + return ret; + + ret = qmc_chan_set_ts_info(qmc_hdlc->qmc_chan, &ts_info); + if (ret) { + dev_err(qmc_hdlc->dev, "set QMC channel ts info failed %d\n", ret); + return ret; + } + + qmc_hdlc->slot_map = te1->slot_map; + + ret = qmc_hdlc_framer_set_iface(qmc_hdlc, if_iface, te1); + if (ret) { + dev_err(qmc_hdlc->dev, "framer set iface failed %d\n", ret); + return ret; + } + + return 0; +} + +static int qmc_hdlc_ioctl(struct net_device *netdev, struct if_settings *ifs) +{ + struct qmc_hdlc *qmc_hdlc = netdev_to_qmc_hdlc(netdev); + te1_settings te1; + int ret; + + switch (ifs->type) { + case IF_GET_IFACE: + if (ifs->size < sizeof(te1)) { + /* Retrieve type only */ + ret = qmc_hdlc_framer_get_iface(qmc_hdlc, &ifs->type, NULL); + if (ret) + return ret; + + if (!ifs->size) + return 0; /* only type requested */ + + ifs->size = sizeof(te1); /* data size wanted */ + return -ENOBUFS; + } + + memset(&te1, 0, sizeof(te1)); + + /* Retrieve info from framer */ + ret = qmc_hdlc_framer_get_iface(qmc_hdlc, &ifs->type, &te1); + if (ret) + return ret; + + /* Update slot_map */ + te1.slot_map = qmc_hdlc->slot_map; + + if (copy_to_user(ifs->ifs_ifsu.te1, &te1, sizeof(te1))) + return -EFAULT; + return 0; + + case IF_IFACE_E1: + case IF_IFACE_T1: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (netdev->flags & IFF_UP) + return -EBUSY; + + if (copy_from_user(&te1, ifs->ifs_ifsu.te1, sizeof(te1))) + return -EFAULT; + + return qmc_hdlc_set_iface(qmc_hdlc, ifs->type, &te1); + + default: + return hdlc_ioctl(netdev, ifs); + } +} + +static int qmc_hdlc_open(struct net_device *netdev) +{ + struct qmc_hdlc *qmc_hdlc = netdev_to_qmc_hdlc(netdev); + struct qmc_chan_param chan_param; + struct qmc_hdlc_desc *desc; + int ret; + int i; + + ret = qmc_hdlc_framer_start(qmc_hdlc); + if (ret) + return ret; + + ret = hdlc_open(netdev); + if (ret) + goto framer_stop; + + /* Update carrier */ + qmc_hdlc_framer_set_carrier(qmc_hdlc); + + chan_param.mode = QMC_HDLC; + /* HDLC_MAX_MRU + 4 for the CRC + * HDLC_MAX_MRU + 4 + 8 for the CRC and some extraspace needed by the QMC + */ + chan_param.hdlc.max_rx_buf_size = HDLC_MAX_MRU + 4 + 8; + chan_param.hdlc.max_rx_frame_size = HDLC_MAX_MRU + 4; + chan_param.hdlc.is_crc32 = qmc_hdlc->is_crc32; + ret = qmc_chan_set_param(qmc_hdlc->qmc_chan, &chan_param); + if (ret) { + dev_err(qmc_hdlc->dev, "failed to set param (%d)\n", ret); + goto hdlc_close; + } + + /* Queue as many recv descriptors as possible */ + for (i = 0; i < ARRAY_SIZE(qmc_hdlc->rx_descs); i++) { + desc = &qmc_hdlc->rx_descs[i]; + + desc->netdev = netdev; + ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, chan_param.hdlc.max_rx_buf_size); + if (ret == -EBUSY && i != 0) + break; /* We use all the QMC chan capability */ + if (ret) + goto free_desc; + } + + ret = qmc_chan_start(qmc_hdlc->qmc_chan, QMC_CHAN_ALL); + if (ret) { + dev_err(qmc_hdlc->dev, "qmc chan start failed (%d)\n", ret); + goto free_desc; + } + + netif_start_queue(netdev); + + return 0; + +free_desc: + qmc_chan_reset(qmc_hdlc->qmc_chan, QMC_CHAN_ALL); + while (i--) { + desc = &qmc_hdlc->rx_descs[i]; + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, + DMA_FROM_DEVICE); + kfree_skb(desc->skb); + desc->skb = NULL; + } +hdlc_close: + hdlc_close(netdev); +framer_stop: + qmc_hdlc_framer_stop(qmc_hdlc); + return ret; +} + +static int qmc_hdlc_close(struct net_device *netdev) +{ + struct qmc_hdlc *qmc_hdlc = netdev_to_qmc_hdlc(netdev); + struct qmc_hdlc_desc *desc; + int i; + + qmc_chan_stop(qmc_hdlc->qmc_chan, QMC_CHAN_ALL); + qmc_chan_reset(qmc_hdlc->qmc_chan, QMC_CHAN_ALL); + + netif_stop_queue(netdev); + + for (i = 0; i < ARRAY_SIZE(qmc_hdlc->tx_descs); i++) { + desc = &qmc_hdlc->tx_descs[i]; + if (!desc->skb) + continue; + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, + DMA_TO_DEVICE); + kfree_skb(desc->skb); + desc->skb = NULL; + } + + for (i = 0; i < ARRAY_SIZE(qmc_hdlc->rx_descs); i++) { + desc = &qmc_hdlc->rx_descs[i]; + if (!desc->skb) + continue; + dma_unmap_single(qmc_hdlc->dev, desc->dma_addr, desc->dma_size, + DMA_FROM_DEVICE); + kfree_skb(desc->skb); + desc->skb = NULL; + } + + hdlc_close(netdev); + qmc_hdlc_framer_stop(qmc_hdlc); + return 0; +} + +static int qmc_hdlc_attach(struct net_device *netdev, unsigned short encoding, + unsigned short parity) +{ + struct qmc_hdlc *qmc_hdlc = netdev_to_qmc_hdlc(netdev); + + if (encoding != ENCODING_NRZ) + return -EINVAL; + + switch (parity) { + case PARITY_CRC16_PR1_CCITT: + qmc_hdlc->is_crc32 = false; + break; + case PARITY_CRC32_PR1_CCITT: + qmc_hdlc->is_crc32 = true; + break; + default: + dev_err(qmc_hdlc->dev, "unsupported parity %u\n", parity); + return -EINVAL; + } + + return 0; +} + +static const struct net_device_ops qmc_hdlc_netdev_ops = { + .ndo_open = qmc_hdlc_open, + .ndo_stop = qmc_hdlc_close, + .ndo_start_xmit = hdlc_start_xmit, + .ndo_siocwandev = qmc_hdlc_ioctl, +}; + +static int qmc_hdlc_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct qmc_chan_ts_info ts_info; + struct qmc_hdlc *qmc_hdlc; + struct qmc_chan_info info; + hdlc_device *hdlc; + int ret; + + qmc_hdlc = devm_kzalloc(dev, sizeof(*qmc_hdlc), GFP_KERNEL); + if (!qmc_hdlc) + return -ENOMEM; + + qmc_hdlc->dev = dev; + spin_lock_init(&qmc_hdlc->tx_lock); + spin_lock_init(&qmc_hdlc->carrier_lock); + + qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node); + if (IS_ERR(qmc_hdlc->qmc_chan)) + return dev_err_probe(dev, PTR_ERR(qmc_hdlc->qmc_chan), + "get QMC channel failed\n"); + + ret = qmc_chan_get_info(qmc_hdlc->qmc_chan, &info); + if (ret) + return dev_err_probe(dev, ret, "get QMC channel info failed\n"); + + if (info.mode != QMC_HDLC) + return dev_err_probe(dev, -EINVAL, "QMC chan mode %d is not QMC_HDLC\n", + info.mode); + + ret = qmc_chan_get_ts_info(qmc_hdlc->qmc_chan, &ts_info); + if (ret) + return dev_err_probe(dev, ret, "get QMC channel ts info failed\n"); + + ret = qmc_hdlc_xlate_ts_info(qmc_hdlc, &ts_info, &qmc_hdlc->slot_map); + if (ret) + return ret; + + qmc_hdlc->framer = devm_framer_optional_get(dev, "fsl,framer"); + if (IS_ERR(qmc_hdlc->framer)) + return PTR_ERR(qmc_hdlc->framer); + + ret = qmc_hdlc_framer_init(qmc_hdlc); + if (ret) + return ret; + + qmc_hdlc->netdev = alloc_hdlcdev(qmc_hdlc); + if (!qmc_hdlc->netdev) { + ret = -ENOMEM; + goto framer_exit; + } + + hdlc = dev_to_hdlc(qmc_hdlc->netdev); + hdlc->attach = qmc_hdlc_attach; + hdlc->xmit = qmc_hdlc_xmit; + SET_NETDEV_DEV(qmc_hdlc->netdev, dev); + qmc_hdlc->netdev->tx_queue_len = ARRAY_SIZE(qmc_hdlc->tx_descs); + qmc_hdlc->netdev->netdev_ops = &qmc_hdlc_netdev_ops; + ret = register_hdlc_device(qmc_hdlc->netdev); + if (ret) { + dev_err_probe(dev, ret, "failed to register hdlc device\n"); + goto free_netdev; + } + + platform_set_drvdata(pdev, qmc_hdlc); + return 0; + +free_netdev: + free_netdev(qmc_hdlc->netdev); +framer_exit: + qmc_hdlc_framer_exit(qmc_hdlc); + return ret; +} + +static int qmc_hdlc_remove(struct platform_device *pdev) +{ + struct qmc_hdlc *qmc_hdlc = platform_get_drvdata(pdev); + + unregister_hdlc_device(qmc_hdlc->netdev); + free_netdev(qmc_hdlc->netdev); + qmc_hdlc_framer_exit(qmc_hdlc); + + return 0; +} + +static const struct of_device_id qmc_hdlc_id_table[] = { + { .compatible = "fsl,qmc-hdlc" }, + {} /* sentinel */ +}; +MODULE_DEVICE_TABLE(of, qmc_hdlc_driver); + +static struct platform_driver qmc_hdlc_driver = { + .driver = { + .name = "fsl-qmc-hdlc", + .of_match_table = qmc_hdlc_id_table, + }, + .probe = qmc_hdlc_probe, + .remove = qmc_hdlc_remove, +}; +module_platform_driver(qmc_hdlc_driver); + +MODULE_AUTHOR("Herve Codina <herve.codina@bootlin.com>"); +MODULE_DESCRIPTION("QMC HDLC driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index a176653c8861..df275b4fccb6 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -263,7 +263,7 @@ static bool decrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) * call skb_cow_data, so that there's no chance that data is removed * from the skb, so that later we can extract the original endpoint. */ - offset = skb->data - skb_network_header(skb); + offset = -skb_network_offset(skb); skb_push(skb, offset); num_frags = skb_cow_data(skb, 0, &trailer); offset += sizeof(struct message_data); diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 922e67f8e04f..c78bce19bd75 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/module.h> @@ -1869,10 +1869,9 @@ static int ath11k_core_reconfigure_on_crash(struct ath11k_base *ab) mutex_lock(&ab->core_lock); ath11k_thermal_unregister(ab); - ath11k_hif_irq_disable(ab); ath11k_dp_pdev_free(ab); ath11k_spectral_deinit(ab); - ath11k_hif_stop(ab); + ath11k_ce_cleanup_pipes(ab); ath11k_wmi_detach(ab); ath11k_dp_pdev_reo_cleanup(ab); mutex_unlock(&ab->core_lock); @@ -2127,6 +2126,9 @@ static void ath11k_core_reset(struct work_struct *work) time_left = wait_for_completion_timeout(&ab->recovery_start, ATH11K_RECOVER_START_TIMEOUT_HZ); + ath11k_hif_irq_disable(ab); + ath11k_hif_ce_irq_disable(ab); + ath11k_hif_power_down(ab); ath11k_hif_power_up(ab); diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index b53659145fcf..fb4ecf9a103e 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -20,35 +20,7 @@ #define MHI_TIMEOUT_DEFAULT_MS 20000 #define RDDM_DUMP_SIZE 0x420000 -static struct mhi_channel_config ath11k_mhi_channels_qca6390[] = { - { - .num = 0, - .name = "LOOPBACK", - .num_elements = 32, - .event_ring = 0, - .dir = DMA_TO_DEVICE, - .ee_mask = 0x4, - .pollcfg = 0, - .doorbell = MHI_DB_BRST_DISABLE, - .lpm_notify = false, - .offload_channel = false, - .doorbell_mode_switch = false, - .auto_queue = false, - }, - { - .num = 1, - .name = "LOOPBACK", - .num_elements = 32, - .event_ring = 0, - .dir = DMA_FROM_DEVICE, - .ee_mask = 0x4, - .pollcfg = 0, - .doorbell = MHI_DB_BRST_DISABLE, - .lpm_notify = false, - .offload_channel = false, - .doorbell_mode_switch = false, - .auto_queue = false, - }, +static const struct mhi_channel_config ath11k_mhi_channels_qca6390[] = { { .num = 20, .name = "IPCR", @@ -102,46 +74,18 @@ static struct mhi_event_config ath11k_mhi_events_qca6390[] = { }, }; -static struct mhi_controller_config ath11k_mhi_config_qca6390 = { +static const struct mhi_controller_config ath11k_mhi_config_qca6390 = { .max_channels = 128, .timeout_ms = 2000, .use_bounce_buf = false, - .buf_len = 0, + .buf_len = 8192, .num_channels = ARRAY_SIZE(ath11k_mhi_channels_qca6390), .ch_cfg = ath11k_mhi_channels_qca6390, .num_events = ARRAY_SIZE(ath11k_mhi_events_qca6390), .event_cfg = ath11k_mhi_events_qca6390, }; -static struct mhi_channel_config ath11k_mhi_channels_qcn9074[] = { - { - .num = 0, - .name = "LOOPBACK", - .num_elements = 32, - .event_ring = 1, - .dir = DMA_TO_DEVICE, - .ee_mask = 0x14, - .pollcfg = 0, - .doorbell = MHI_DB_BRST_DISABLE, - .lpm_notify = false, - .offload_channel = false, - .doorbell_mode_switch = false, - .auto_queue = false, - }, - { - .num = 1, - .name = "LOOPBACK", - .num_elements = 32, - .event_ring = 1, - .dir = DMA_FROM_DEVICE, - .ee_mask = 0x14, - .pollcfg = 0, - .doorbell = MHI_DB_BRST_DISABLE, - .lpm_notify = false, - .offload_channel = false, - .doorbell_mode_switch = false, - .auto_queue = false, - }, +static const struct mhi_channel_config ath11k_mhi_channels_qcn9074[] = { { .num = 20, .name = "IPCR", @@ -195,7 +139,7 @@ static struct mhi_event_config ath11k_mhi_events_qcn9074[] = { }, }; -static struct mhi_controller_config ath11k_mhi_config_qcn9074 = { +static const struct mhi_controller_config ath11k_mhi_config_qcn9074 = { .max_channels = 30, .timeout_ms = 10000, .use_bounce_buf = false, @@ -384,7 +328,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci) { struct ath11k_base *ab = ab_pci->ab; struct mhi_controller *mhi_ctrl; - struct mhi_controller_config *ath11k_mhi_config; + const struct mhi_controller_config *ath11k_mhi_config; int ret; mhi_ctrl = mhi_alloc_controller(); diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index 2c7cab62b9bb..5006f81f779b 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/elf.h> @@ -3249,7 +3249,8 @@ static void ath11k_qmi_driver_event_work(struct work_struct *work) case ATH11K_QMI_EVENT_FW_INIT_DONE: clear_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags); if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags)) { - ath11k_hal_dump_srng_stats(ab); + if (ab->is_reset) + ath11k_hal_dump_srng_stats(ab); queue_work(ab->workqueue, &ab->restart_work); break; } diff --git a/drivers/net/wireless/ath/ath11k/thermal.c b/drivers/net/wireless/ath/ath11k/thermal.c index c29b11ab5bfa..41e7499f075f 100644 --- a/drivers/net/wireless/ath/ath11k/thermal.c +++ b/drivers/net/wireless/ath/ath11k/thermal.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2020 The Linux Foundation. All rights reserved. - * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/device.h> @@ -163,6 +163,9 @@ int ath11k_thermal_register(struct ath11k_base *ab) struct ath11k_pdev *pdev; int i, ret; + if (test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags)) + return 0; + for (i = 0; i < ab->num_radios; i++) { pdev = &ab->pdevs[i]; ar = pdev->ar; diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 90f1fdec9adc..34ab9631ff36 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/ctype.h> @@ -4857,6 +4857,7 @@ static void ath11k_wmi_free_dbring_caps(struct ath11k_base *ab) { kfree(ab->db_caps); ab->db_caps = NULL; + ab->num_db_cap = 0; } static int ath11k_wmi_tlv_dma_ring_caps(struct ath11k_base *ab, diff --git a/drivers/net/wireless/ath/ath12k/p2p.c b/drivers/net/wireless/ath/ath12k/p2p.c index 61e919b23b16..d334df720032 100644 --- a/drivers/net/wireless/ath/ath12k/p2p.c +++ b/drivers/net/wireless/ath/ath12k/p2p.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ISC +// SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. */ diff --git a/drivers/net/wireless/ath/ath12k/p2p.h b/drivers/net/wireless/ath/ath12k/p2p.h index b6f177fe4ff4..5768139a7844 100644 --- a/drivers/net/wireless/ath/ath12k/p2p.h +++ b/drivers/net/wireless/ath/ath12k/p2p.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: ISC */ +/* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.. */ diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 838161dd9098..9d69a1769926 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -6736,18 +6736,21 @@ static int ath12k_wmi_p2p_noa_event(struct ath12k_base *ab, "wmi tlv p2p noa vdev_id %i descriptors %u\n", vdev_id, le32_get_bits(noa->noa_attr, WMI_P2P_NOA_INFO_DESC_NUM)); + rcu_read_lock(); ar = ath12k_mac_get_ar_by_vdev_id(ab, vdev_id); if (!ar) { ath12k_warn(ab, "invalid vdev id %d in P2P NoA event\n", vdev_id); ret = -EINVAL; - goto out; + goto unlock; } ath12k_p2p_noa_update_by_vdev_id(ar, vdev_id, noa); ret = 0; +unlock: + rcu_read_unlock(); out: kfree(tb); return ret; diff --git a/drivers/net/wireless/broadcom/b43/phy_ht.c b/drivers/net/wireless/broadcom/b43/phy_ht.c index d050971d150a..26a226126bc4 100644 --- a/drivers/net/wireless/broadcom/b43/phy_ht.c +++ b/drivers/net/wireless/broadcom/b43/phy_ht.c @@ -322,8 +322,8 @@ static void b43_phy_ht_bphy_reset(struct b43_wldev *dev, bool reset) B43_PHY_B_BBCFG_RSTCCA | B43_PHY_B_BBCFG_RSTRX); else b43_phy_mask(dev, B43_PHY_B_BBCFG, - (u16)~(B43_PHY_B_BBCFG_RSTCCA | - B43_PHY_B_BBCFG_RSTRX)); + 0xffff & ~(B43_PHY_B_BBCFG_RSTCCA | + B43_PHY_B_BBCFG_RSTRX)); b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp); } @@ -551,7 +551,7 @@ static void b43_phy_ht_tx_power_ctl(struct b43_wldev *dev, bool enable) phy_ht->tx_pwr_idx[i] = b43_phy_read(dev, status_regs[i]); } - b43_phy_mask(dev, B43_PHY_HT_TXPCTL_CMD_C1, ~en_bits); + b43_phy_mask(dev, B43_PHY_HT_TXPCTL_CMD_C1, 0xffff & ~en_bits); } else { b43_phy_set(dev, B43_PHY_HT_TXPCTL_CMD_C1, en_bits); diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c index 2c0c019a815d..4bb005b93f2c 100644 --- a/drivers/net/wireless/broadcom/b43/phy_n.c +++ b/drivers/net/wireless/broadcom/b43/phy_n.c @@ -6246,7 +6246,7 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev, b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4); /* Take BPHY out of the reset */ b43_phy_mask(dev, B43_PHY_B_BBCFG, - (u16)~(B43_PHY_B_BBCFG_RSTCCA | B43_PHY_B_BBCFG_RSTRX)); + ~(B43_PHY_B_BBCFG_RSTCCA | B43_PHY_B_BBCFG_RSTRX) & 0xffff); b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16); } @@ -6377,7 +6377,7 @@ static int b43_nphy_set_channel(struct b43_wldev *dev, } else if (channel_type == NL80211_CHAN_HT40MINUS) { b43_phy_mask(dev, B43_NPHY_RXCTL, ~B43_NPHY_RXCTL_BSELU20); if (phy->rev >= 7) - b43_phy_mask(dev, 0x310, (u16)~0x8000); + b43_phy_mask(dev, 0x310, 0x7fff); } if (phy->rev >= 19) { diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index adf8a14feb49..b99aa66dc5a9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4308,6 +4308,9 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa, int ret; pmk_op = kzalloc(sizeof(*pmk_op), GFP_KERNEL); + if (!pmk_op) + return -ENOMEM; + pmk_op->version = cpu_to_le16(BRCMF_PMKSA_VER_3); if (!pmksa) { @@ -5101,6 +5104,7 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev, bool mbss; int is_11d; bool supports_11d; + bool closednet; brcmf_dbg(TRACE, "ctrlchn=%d, center=%d, bw=%d, beacon_interval=%d, dtim_period=%d,\n", settings->chandef.chan->hw_value, @@ -5270,12 +5274,12 @@ brcmf_cfg80211_start_ap(struct wiphy *wiphy, struct net_device *ndev, goto exit; } - err = brcmf_fil_iovar_int_set(ifp, "closednet", - settings->hidden_ssid); + closednet = + (settings->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); + err = brcmf_fil_iovar_int_set(ifp, "closednet", closednet); if (err) { bphy_err(drvr, "%s closednet error (%d)\n", - (settings->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE) ? - "enabled" : "disabled", + (closednet ? "enabled" : "disabled"), err); goto exit; } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index 0774f6c59226..f0b6a7607f16 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -497,12 +497,12 @@ void brcmf_fweh_process_event(struct brcmf_pub *drvr, return; event->code = fwevt_idx; + event->datalen = datalen; event->ifidx = event_packet->msg.ifidx; /* use memcpy to get aligned event message */ memcpy(&event->emsg, &event_packet->msg, sizeof(event->emsg)); memcpy(event->data, data, datalen); - event->datalen = datalen; memcpy(event->ifaddr, event_packet->eth.h_dest, ETH_ALEN); brcmf_fweh_queue_event(fweh, event); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c index 7717eb85a1db..aae2cf95fe95 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c @@ -3299,7 +3299,7 @@ wlc_lcnphy_run_samples(struct brcms_phy *pi, if (iqcalmode) { - and_phy_reg(pi, 0x453, (u16) ~(0x1 << 15)); + and_phy_reg(pi, 0x453, 0xffff & ~(0x1 << 15)); or_phy_reg(pi, 0x453, (0x1 << 15)); } else { write_phy_reg(pi, 0x63f, 1); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c index cd9b502a6a9f..d69879e1bd87 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c @@ -17582,7 +17582,7 @@ static void wlc_phy_txpwrctrl_pwr_setup_nphy(struct brcms_phy *pi) or_phy_reg(pi, 0x122, (0x1 << 0)); if (NREV_GE(pi->pubpi.phy_rev, 3)) - and_phy_reg(pi, 0x1e7, (u16) (~(0x1 << 15))); + and_phy_reg(pi, 0x1e7, 0x7fff); else or_phy_reg(pi, 0x1e7, (0x1 << 15)); @@ -18081,7 +18081,7 @@ wlc_phy_rfctrlintc_override_nphy(struct brcms_phy *pi, u8 field, u16 value, (0x1 << 10)); and_phy_reg(pi, 0x2ff, (u16) - ~(0x3 << 14)); + 0xffff & ~(0x3 << 14)); or_phy_reg(pi, 0x2ff, (0x1 << 13)); or_phy_reg(pi, 0x2ff, (0x1 << 0)); } else { @@ -21048,7 +21048,7 @@ wlc_phy_chanspec_nphy_setup(struct brcms_phy *pi, u16 chanspec, (val | MAC_PHY_FORCE_CLK)); and_phy_reg(pi, (NPHY_TO_BPHY_OFF + BPHY_BB_CONFIG), - (u16) (~(BBCFG_RESETCCA | BBCFG_RESETRX))); + 0xffff & ~(BBCFG_RESETCCA | BBCFG_RESETRX)); bcma_write16(pi->d11core, D11REGOFFS(psm_phy_hdr_param), val); } @@ -21282,7 +21282,8 @@ void wlc_phy_antsel_init(struct brcms_phy_pub *ppi, bool lut_init) bcma_set16(pi->d11core, D11REGOFFS(psm_gpio_oe), mask); - bcma_mask16(pi->d11core, D11REGOFFS(psm_gpio_out), ~mask); + bcma_mask16(pi->d11core, D11REGOFFS(psm_gpio_out), + 0xffff & ~mask); if (lut_init) { write_phy_reg(pi, 0xf8, 0x02d8); @@ -23192,7 +23193,7 @@ void wlc_phy_stopplayback_nphy(struct brcms_phy *pi) or_phy_reg(pi, 0xc3, NPHY_sampleCmd_STOP); else if (playback_status & 0x2) and_phy_reg(pi, 0xc2, - (u16) ~NPHY_iqloCalCmdGctl_IQLO_CAL_EN); + 0xffff & ~NPHY_iqloCalCmdGctl_IQLO_CAL_EN); and_phy_reg(pi, 0xc3, (u16) ~(0x1 << 2)); @@ -28197,8 +28198,9 @@ void wlc_phy_txpwrctrl_enable_nphy(struct brcms_phy *pi, u8 ctrl_type) if (NREV_GE(pi->pubpi.phy_rev, 3)) and_phy_reg(pi, 0x1e7, - (u16) (~((0x1 << 15) | - (0x1 << 14) | (0x1 << 13)))); + 0xffff & ~((0x1 << 15) | + (0x1 << 14) | + (0x1 << 13))); else and_phy_reg(pi, 0x1e7, (u16) (~((0x1 << 14) | (0x1 << 13)))); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c index 2e530fc928a4..25952d0bea99 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c @@ -299,3 +299,9 @@ MODULE_FIRMWARE(IWL_MA_B_HR_B_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_GF_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_GF4_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_B_MR_A_FW_MODULE_FIRMWARE(IWL_AX210_UCODE_API_MAX)); + +MODULE_FIRMWARE("iwlwifi-so-a0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-so-a0-gf4-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ty-a0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ma-b0-gf-a0.pnvm"); +MODULE_FIRMWARE("iwlwifi-ma-b0-gf4-a0.pnvm"); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index 18b1f2cf08cc..072b0a5827d1 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -176,3 +176,5 @@ MODULE_FIRMWARE(IWL_BZ_A_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_BZ_A_FM4_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_GL_B_FM_B_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_GL_C_FM_C_MODULE_FIRMWARE(IWL_BZ_UCODE_API_MAX)); + +MODULE_FIRMWARE("iwlwifi-gl-c0-fm-c0.pnvm"); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 70e03a9a937e..553c6fffc7c6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -1983,6 +1983,7 @@ static bool iwl_mvm_gtk_rekey(struct iwl_wowlan_status_data *status, } conf = { .conf.cipher = gtk_cipher, }; + int link_id = vif->active_links ? __ffs(vif->active_links) : -1; BUILD_BUG_ON(WLAN_KEY_LEN_CCMP != WLAN_KEY_LEN_GCMP); BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_CCMP); @@ -2016,7 +2017,7 @@ static bool iwl_mvm_gtk_rekey(struct iwl_wowlan_status_data *status, memcpy(conf.conf.key, status->gtk[i].key, sizeof(status->gtk[i].key)); - key = ieee80211_gtk_rekey_add(vif, &conf.conf); + key = ieee80211_gtk_rekey_add(vif, &conf.conf, link_id); if (IS_ERR(key)) return false; @@ -2047,6 +2048,7 @@ iwl_mvm_d3_igtk_bigtk_rekey_add(struct iwl_wowlan_status_data *status, .conf.keyidx = key_data->id, }; struct ieee80211_key_seq seq; + int link_id = vif->active_links ? __ffs(vif->active_links) : -1; if (!key_data->len) return true; @@ -2072,17 +2074,17 @@ iwl_mvm_d3_igtk_bigtk_rekey_add(struct iwl_wowlan_status_data *status, BUILD_BUG_ON(sizeof(conf.key) < sizeof(key_data->key)); memcpy(conf.conf.key, key_data->key, conf.conf.keylen); - key_config = ieee80211_gtk_rekey_add(vif, &conf.conf); + key_config = ieee80211_gtk_rekey_add(vif, &conf.conf, link_id); if (IS_ERR(key_config)) return false; ieee80211_set_key_rx_seq(key_config, 0, &seq); if (key_config->keyidx == 4 || key_config->keyidx == 5) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - int link_id = vif->active_links ? __ffs(vif->active_links) : 0; - struct iwl_mvm_vif_link_info *mvm_link = - mvmvif->link[link_id]; + struct iwl_mvm_vif_link_info *mvm_link; + link_id = link_id < 0 ? 0 : link_id; + mvm_link = mvmvif->link[link_id]; mvm_link->igtk = key_config; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 69f6a96b0cfb..1935630d3def 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1470,7 +1470,8 @@ out_unlock: } void iwl_mvm_abort_channel_switch(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); @@ -5551,8 +5552,16 @@ void iwl_mvm_channel_switch_rx_beacon(struct ieee80211_hw *hw, if (chsw->count >= mvmvif->csa_count && chsw->block_tx) { if (mvmvif->csa_misbehave) { + struct ieee80211_bss_conf *link_conf; + /* Second time, give up on this AP*/ - iwl_mvm_abort_channel_switch(hw, vif); + + link_conf = wiphy_dereference(hw->wiphy, + vif->link_conf[chsw->link_id]); + if (WARN_ON(!link_conf)) + return; + + iwl_mvm_abort_channel_switch(hw, vif, link_conf); ieee80211_chswitch_done(vif, false, 0); mvmvif->csa_misbehave = false; return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 5c316909cab2..a10b48947bca 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -2713,7 +2713,8 @@ int iwl_mvm_pre_channel_switch(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *chsw); void iwl_mvm_abort_channel_switch(struct ieee80211_hw *hw, - struct ieee80211_vif *vif); + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf); void iwl_mvm_channel_switch_rx_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *chsw); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index e502f4ee9e1f..782ddc8c296b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1015,8 +1015,7 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, netdev_features_t netdev_flags = NETIF_F_CSUM_MASK | NETIF_F_SG; u8 tid; - snap_ip_tcp = 8 + skb_transport_header(skb) - skb_network_header(skb) + - tcp_hdrlen(skb); + snap_ip_tcp = 8 + skb_network_header_len(skb) + tcp_hdrlen(skb); if (!mvmsta->max_amsdu_len || !ieee80211_is_data_qos(hdr->frame_control) || diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 6c2b37e56c78..fa8eba47dc4c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1331,7 +1331,7 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb, trans->txqs.tfd.size, &dev_cmd->hdr, IWL_FIRST_TB_SIZE + tb1_len, 0); - ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); + ip_hdrlen = skb_network_header_len(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len - iv_len; amsdu_pad = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/queue/tx.c b/drivers/net/wireless/intel/iwlwifi/queue/tx.c index d3bde2d010b7..33973a60d0bf 100644 --- a/drivers/net/wireless/intel/iwlwifi/queue/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/queue/tx.c @@ -353,7 +353,7 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans, trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr, start_len, 0); - ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb); + ip_hdrlen = skb_network_header_len(skb); snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb); total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len; amsdu_pad = 0; diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index d6575fe18c6b..f7f2d9a8ab0f 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_MT792x_USB) += mt792x-usb.o mt76-y := \ mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \ - tx.o agg-rx.o mcu.o + tx.o agg-rx.o mcu.o wed.o mt76-$(CONFIG_PCI) += pci.o mt76-$(CONFIG_NL80211_TESTMODE) += testmode.o diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c index 10cbd9e560e7..07c386c7b4d0 100644 --- a/drivers/net/wireless/mediatek/mt76/agg-rx.c +++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c @@ -122,7 +122,7 @@ mt76_rx_aggr_check_ctl(struct sk_buff *skb, struct sk_buff_head *frames) struct ieee80211_bar *bar = mt76_skb_get_hdr(skb); struct mt76_wcid *wcid = status->wcid; struct mt76_rx_tid *tid; - u8 tidno = status->qos_ctl & IEEE80211_QOS_CTL_TID_MASK; + u8 tidno; u16 seqno; if (!ieee80211_is_ctl(bar->frame_control)) diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 00230f106294..72a7bd5a8576 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -197,9 +197,8 @@ mt76_dma_sync_idx(struct mt76_dev *dev, struct mt76_queue *q) q->tail = q->head; } -static void -__mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q, - bool reset_idx) +void __mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q, + bool reset_idx) { if (!q || !q->ndesc) return; @@ -219,8 +218,7 @@ __mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q, mt76_dma_sync_idx(dev, q); } -static void -mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q) +void mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q) { __mt76_dma_queue_reset(dev, q, true); } @@ -632,9 +630,8 @@ free_skb: return ret; } -static int -mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, - bool allow_direct) +int mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, + bool allow_direct) { int len = SKB_WITH_OVERHEAD(q->buf_size); int frames = 0; @@ -681,81 +678,6 @@ done: return frames; } -int mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset) -{ -#ifdef CONFIG_NET_MEDIATEK_SOC_WED - int ret = 0, type, ring; - u16 flags; - - if (!q || !q->ndesc) - return -EINVAL; - - flags = q->flags; - if (!q->wed || !mtk_wed_device_active(q->wed)) - q->flags &= ~MT_QFLAG_WED; - - if (!(q->flags & MT_QFLAG_WED)) - return 0; - - type = FIELD_GET(MT_QFLAG_WED_TYPE, q->flags); - ring = FIELD_GET(MT_QFLAG_WED_RING, q->flags); - - switch (type) { - case MT76_WED_Q_TX: - ret = mtk_wed_device_tx_ring_setup(q->wed, ring, q->regs, - reset); - if (!ret) - q->wed_regs = q->wed->tx_ring[ring].reg_base; - break; - case MT76_WED_Q_TXFREE: - /* WED txfree queue needs ring to be initialized before setup */ - q->flags = 0; - mt76_dma_queue_reset(dev, q); - mt76_dma_rx_fill(dev, q, false); - - ret = mtk_wed_device_txfree_ring_setup(q->wed, q->regs); - if (!ret) - q->wed_regs = q->wed->txfree_ring.reg_base; - break; - case MT76_WED_Q_RX: - ret = mtk_wed_device_rx_ring_setup(q->wed, ring, q->regs, - reset); - if (!ret) - q->wed_regs = q->wed->rx_ring[ring].reg_base; - break; - case MT76_WED_RRO_Q_DATA: - q->flags &= ~MT_QFLAG_WED; - __mt76_dma_queue_reset(dev, q, false); - mtk_wed_device_rro_rx_ring_setup(q->wed, ring, q->regs); - q->head = q->ndesc - 1; - q->queued = q->head; - break; - case MT76_WED_RRO_Q_MSDU_PG: - q->flags &= ~MT_QFLAG_WED; - __mt76_dma_queue_reset(dev, q, false); - mtk_wed_device_msdu_pg_rx_ring_setup(q->wed, ring, q->regs); - q->head = q->ndesc - 1; - q->queued = q->head; - break; - case MT76_WED_RRO_Q_IND: - q->flags &= ~MT_QFLAG_WED; - mt76_dma_queue_reset(dev, q); - mt76_dma_rx_fill(dev, q, false); - mtk_wed_device_ind_rx_ring_setup(q->wed, q->regs); - break; - default: - ret = -EINVAL; - break; - } - q->flags = flags; - - return ret; -#else - return 0; -#endif -} -EXPORT_SYMBOL_GPL(mt76_dma_wed_setup); - static int mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q, int idx, int n_desc, int bufsize, @@ -800,7 +722,7 @@ mt76_dma_alloc_queue(struct mt76_dev *dev, struct mt76_queue *q, if (ret) return ret; - ret = mt76_dma_wed_setup(dev, q, false); + ret = mt76_wed_dma_setup(dev, q, false); if (ret) return ret; @@ -863,7 +785,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) mt76_dma_rx_cleanup(dev, q); /* reset WED rx queues */ - mt76_dma_wed_setup(dev, q, true); + mt76_wed_dma_setup(dev, q, true); if (mt76_queue_is_wed_tx_free(q)) return; @@ -1054,20 +976,6 @@ void mt76_dma_attach(struct mt76_dev *dev) } EXPORT_SYMBOL_GPL(mt76_dma_attach); -void mt76_dma_wed_reset(struct mt76_dev *dev) -{ - struct mt76_mmio *mmio = &dev->mmio; - - if (!test_bit(MT76_STATE_WED_RESET, &dev->phy.state)) - return; - - complete(&mmio->wed_reset); - - if (!wait_for_completion_timeout(&mmio->wed_reset_complete, 3 * HZ)) - dev_err(dev->dev, "wed reset complete timeout\n"); -} -EXPORT_SYMBOL_GPL(mt76_dma_wed_reset); - void mt76_dma_cleanup(struct mt76_dev *dev) { int i; diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h index c479cc6388ef..1de5a2b20f74 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.h +++ b/drivers/net/wireless/mediatek/mt76/dma.h @@ -79,15 +79,18 @@ enum mt76_dma_wed_ind_reason { int mt76_dma_rx_poll(struct napi_struct *napi, int budget); void mt76_dma_attach(struct mt76_dev *dev); void mt76_dma_cleanup(struct mt76_dev *dev); -int mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset); -void mt76_dma_wed_reset(struct mt76_dev *dev); +int mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, + bool allow_direct); +void __mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q, + bool reset_idx); +void mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q); static inline void mt76_dma_reset_tx_queue(struct mt76_dev *dev, struct mt76_queue *q) { dev->queue_ops->reset_q(dev, q); if (mtk_wed_device_active(&dev->mmio.wed)) - mt76_dma_wed_setup(dev, q, true); + mt76_wed_dma_setup(dev, q, true); } static inline void diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 758e380fdf1d..068206e48aec 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -579,13 +579,18 @@ EXPORT_SYMBOL_GPL(mt76_unregister_phy); int mt76_create_page_pool(struct mt76_dev *dev, struct mt76_queue *q) { + bool is_qrx = mt76_queue_is_rx(dev, q); struct page_pool_params pp_params = { .order = 0, .flags = 0, .nid = NUMA_NO_NODE, .dev = dev->dma_dev, }; - int idx = q - dev->q_rx; + int idx = is_qrx ? q - dev->q_rx : -1; + + /* Allocate page_pools just for rx/wed_tx_free queues */ + if (!is_qrx && !mt76_queue_is_wed_tx_free(q)) + return 0; switch (idx) { case MT_RXQ_MAIN: @@ -604,6 +609,9 @@ int mt76_create_page_pool(struct mt76_dev *dev, struct mt76_queue *q) pp_params.dma_dir = DMA_FROM_DEVICE; pp_params.max_len = PAGE_SIZE; pp_params.offset = 0; + /* NAPI is available just for rx queues */ + if (idx >= 0 && idx < ARRAY_SIZE(dev->napi)) + pp_params.napi = &dev->napi[idx]; } q->page_pool = page_pool_create(&pp_params); @@ -1854,19 +1862,3 @@ enum mt76_dfs_state mt76_phy_dfs_state(struct mt76_phy *phy) return MT_DFS_STATE_ACTIVE; } EXPORT_SYMBOL_GPL(mt76_phy_dfs_state); - -#ifdef CONFIG_NET_MEDIATEK_SOC_WED -int mt76_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct net_device *netdev, enum tc_setup_type type, - void *type_data) -{ - struct mt76_phy *phy = hw->priv; - struct mtk_wed_device *wed = &phy->dev->mmio.wed; - - if (!mtk_wed_device_active(wed)) - return -EOPNOTSUPP; - - return mtk_wed_device_setup_tc(wed, netdev, type, type_data); -} -EXPORT_SYMBOL_GPL(mt76_net_setup_tc); -#endif /* CONFIG_NET_MEDIATEK_SOC_WED */ diff --git a/drivers/net/wireless/mediatek/mt76/mmio.c b/drivers/net/wireless/mediatek/mt76/mmio.c index c3e0e23e0161..cd2e9737c3bf 100644 --- a/drivers/net/wireless/mediatek/mt76/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mmio.c @@ -85,113 +85,6 @@ void mt76_set_irq_mask(struct mt76_dev *dev, u32 addr, } EXPORT_SYMBOL_GPL(mt76_set_irq_mask); -#ifdef CONFIG_NET_MEDIATEK_SOC_WED -void mt76_mmio_wed_release_rx_buf(struct mtk_wed_device *wed) -{ - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); - int i; - - for (i = 0; i < dev->rx_token_size; i++) { - struct mt76_txwi_cache *t; - - t = mt76_rx_token_release(dev, i); - if (!t || !t->ptr) - continue; - - mt76_put_page_pool_buf(t->ptr, false); - t->ptr = NULL; - - mt76_put_rxwi(dev, t); - } - - mt76_free_pending_rxwi(dev); -} -EXPORT_SYMBOL_GPL(mt76_mmio_wed_release_rx_buf); - -u32 mt76_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size) -{ - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); - struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc; - struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN]; - int i, len = SKB_WITH_OVERHEAD(q->buf_size); - struct mt76_txwi_cache *t = NULL; - - for (i = 0; i < size; i++) { - enum dma_data_direction dir; - dma_addr_t addr; - u32 offset; - int token; - void *buf; - - t = mt76_get_rxwi(dev); - if (!t) - goto unmap; - - buf = mt76_get_page_pool_buf(q, &offset, q->buf_size); - if (!buf) - goto unmap; - - addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset; - dir = page_pool_get_dma_dir(q->page_pool); - dma_sync_single_for_device(dev->dma_dev, addr, len, dir); - - desc->buf0 = cpu_to_le32(addr); - token = mt76_rx_token_consume(dev, buf, t, addr); - if (token < 0) { - mt76_put_page_pool_buf(buf, false); - goto unmap; - } - - token = FIELD_PREP(MT_DMA_CTL_TOKEN, token); -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - token |= FIELD_PREP(MT_DMA_CTL_SDP0_H, addr >> 32); -#endif - desc->token |= cpu_to_le32(token); - desc++; - } - - return 0; - -unmap: - if (t) - mt76_put_rxwi(dev, t); - mt76_mmio_wed_release_rx_buf(wed); - - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(mt76_mmio_wed_init_rx_buf); - -int mt76_mmio_wed_offload_enable(struct mtk_wed_device *wed) -{ - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); - - spin_lock_bh(&dev->token_lock); - dev->token_size = wed->wlan.token_start; - spin_unlock_bh(&dev->token_lock); - - return !wait_event_timeout(dev->tx_wait, !dev->wed_token_count, HZ); -} -EXPORT_SYMBOL_GPL(mt76_mmio_wed_offload_enable); - -void mt76_mmio_wed_offload_disable(struct mtk_wed_device *wed) -{ - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); - - spin_lock_bh(&dev->token_lock); - dev->token_size = dev->drv->token_size; - spin_unlock_bh(&dev->token_lock); -} -EXPORT_SYMBOL_GPL(mt76_mmio_wed_offload_disable); - -void mt76_mmio_wed_reset_complete(struct mtk_wed_device *wed) -{ - struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); - - complete(&dev->mmio.wed_reset_complete); -} -EXPORT_SYMBOL_GPL(mt76_mmio_wed_reset_complete); -#endif /*CONFIG_NET_MEDIATEK_SOC_WED */ - void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs) { static const struct mt76_bus_ops mt76_mmio_ops = { diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index b20c34d5a0f7..a91f6ddacbd9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -210,6 +210,8 @@ struct mt76_queue { u16 first; u16 head; u16 tail; + u8 hw_idx; + u8 ep; int ndesc; int queued; int buf_size; @@ -217,7 +219,6 @@ struct mt76_queue { bool blocked; u8 buf_offset; - u8 hw_idx; u16 flags; struct mtk_wed_device *wed; @@ -1081,12 +1082,6 @@ bool ____mt76_poll_msec(struct mt76_dev *dev, u32 offset, u32 mask, u32 val, void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs); void mt76_pci_disable_aspm(struct pci_dev *pdev); -#ifdef CONFIG_NET_MEDIATEK_SOC_WED -int mt76_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct net_device *netdev, enum tc_setup_type type, - void *type_data); -#endif /*CONFIG_NET_MEDIATEK_SOC_WED */ - static inline u16 mt76_chip(struct mt76_dev *dev) { return dev->rev >> 16; @@ -1097,13 +1092,34 @@ static inline u16 mt76_rev(struct mt76_dev *dev) return dev->rev & 0xffff; } +void mt76_wed_release_rx_buf(struct mtk_wed_device *wed); +void mt76_wed_offload_disable(struct mtk_wed_device *wed); +void mt76_wed_reset_complete(struct mtk_wed_device *wed); +void mt76_wed_dma_reset(struct mt76_dev *dev); +int mt76_wed_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct net_device *netdev, enum tc_setup_type type, + void *type_data); #ifdef CONFIG_NET_MEDIATEK_SOC_WED -u32 mt76_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size); -void mt76_mmio_wed_release_rx_buf(struct mtk_wed_device *wed); -int mt76_mmio_wed_offload_enable(struct mtk_wed_device *wed); -void mt76_mmio_wed_offload_disable(struct mtk_wed_device *wed); -void mt76_mmio_wed_reset_complete(struct mtk_wed_device *wed); -#endif /*CONFIG_NET_MEDIATEK_SOC_WED */ +u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size); +int mt76_wed_offload_enable(struct mtk_wed_device *wed); +int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset); +#else +static inline u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size) +{ + return 0; +} + +static inline int mt76_wed_offload_enable(struct mtk_wed_device *wed) +{ + return 0; +} + +static inline int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, + bool reset) +{ + return 0; +} +#endif /* CONFIG_NET_MEDIATEK_SOC_WED */ #define mt76xx_chip(dev) mt76_chip(&((dev)->mt76)) #define mt76xx_rev(dev) mt76_rev(&((dev)->mt76)) @@ -1470,13 +1486,6 @@ static inline bool mt76u_urb_error(struct urb *urb) urb->status != -ENOENT; } -/* Map hardware queues to usb endpoints */ -static inline u8 q2ep(u8 qid) -{ - /* TODO: take management packets to queue 5 */ - return qid + 1; -} - static inline int mt76u_bulk_msg(struct mt76_dev *dev, void *data, int len, int *actual_len, int timeout, int ep) @@ -1598,6 +1607,18 @@ s8 mt76_get_rate_power_limits(struct mt76_phy *phy, struct mt76_power_limits *dest, s8 target_power); +static inline bool mt76_queue_is_rx(struct mt76_dev *dev, struct mt76_queue *q) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(dev->q_rx); i++) { + if (q == &dev->q_rx[i]) + return true; + } + + return false; +} + static inline bool mt76_queue_is_wed_tx_free(struct mt76_queue *q) { return (q->flags & MT_QFLAG_WED) && diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h index fdde3d70b300..98d64d3d2993 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h @@ -227,6 +227,11 @@ static inline bool is_mt7992(struct mt76_dev *dev) return mt76_chip(dev) == 0x7992; } +static inline bool is_mt799x(struct mt76_dev *dev) +{ + return is_mt7996(dev) || is_mt7992(dev); +} + static inline bool is_mt7622(struct mt76_dev *dev) { if (!IS_ENABLED(CONFIG_MT7622_WMAC)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h index bd2a92467a97..5f132115ebfc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h @@ -32,6 +32,11 @@ enum { MT_LMAC_PSMP0, }; +enum { + MT_TXS_MPDU_FMT = 0, + MT_TXS_PPDU_FMT = 2, +}; + #define MT_TX_FREE_MSDU_CNT GENMASK(9, 0) #define MT_TX_FREE_WLAN_ID GENMASK(23, 14) #define MT_TX_FREE_COUNT GENMASK(12, 0) diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index c7914643e9c0..b841bf628d02 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -544,7 +544,7 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, val = FIELD_PREP(MT_TXD5_PID, pid); if (pid >= MT_PACKET_ID_FIRST) { val |= MT_TXD5_TX_STATUS_HOST; - amsdu_en = amsdu_en && !is_mt7921(dev); + amsdu_en = 0; } txwi[5] = cpu_to_le32(val); @@ -579,6 +579,8 @@ void mt76_connac2_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi, spe_idx = 24 + phy_idx; txwi[7] |= cpu_to_le32(FIELD_PREP(MT_TXD7_SPE_IDX, spe_idx)); } + + txwi[7] &= ~cpu_to_le32(MT_TXD7_HW_AMSDU); } } EXPORT_SYMBOL_GPL(mt76_connac2_mac_write_txwi); @@ -714,6 +716,9 @@ bool mt76_connac2_mac_add_txs_skb(struct mt76_dev *dev, struct mt76_wcid *wcid, struct sk_buff_head list; struct sk_buff *skb; + if (le32_get_bits(txs_data[0], MT_TXS0_TXS_FORMAT) == MT_TXS_PPDU_FMT) + return false; + mt76_tx_status_lock(dev, &list); skb = mt76_tx_status_skb_get(dev, wcid, pid, &list); if (skb) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 3a20ba0d2492..af0c2b2aacb0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -66,7 +66,7 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len, if ((!is_connac_v1(dev) && addr == MCU_PATCH_ADDRESS) || (is_mt7921(dev) && addr == 0x900000) || - (is_mt7925(dev) && addr == 0x900000) || + (is_mt7925(dev) && (addr == 0x900000 || addr == 0xe0002800)) || (is_mt7996(dev) && addr == 0x900000) || (is_mt7992(dev) && addr == 0x900000)) cmd = MCU_CMD(PATCH_START_REQ); @@ -283,6 +283,9 @@ __mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif, }; struct sk_buff *skb; + if (is_mt799x(dev) && !wcid->sta) + hdr.muar_idx = 0xe; + mt76_connac_mcu_get_wlan_idx(dev, wcid, &hdr.wlan_idx_lo, &hdr.wlan_idx_hi); skb = mt76_mcu_msg_alloc(dev, NULL, len); @@ -2101,7 +2104,7 @@ mt76_connac_mcu_rate_txpower_band(struct mt76_phy *phy, int j, msg_len, num_ch; struct sk_buff *skb; - num_ch = i == batch_size - 1 ? n_chan % batch_len : batch_len; + num_ch = i == batch_size - 1 ? n_chan - i * batch_len : batch_len; msg_len = sizeof(tx_power_tlv) + num_ch * sizeof(sku_tlbv); skb = mt76_mcu_msg_alloc(dev, NULL, msg_len); if (!skb) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index ae6d0179727d..657a4d1f856b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -808,6 +808,7 @@ enum { STA_REC_MLD = 0x20, STA_REC_EHT = 0x22, STA_REC_PN_INFO = 0x26, + STA_REC_KEY_V3 = 0x27, STA_REC_HDRT = 0x28, STA_REC_HDR_TRANS = 0x2B, STA_REC_MAX_NUM @@ -935,6 +936,9 @@ enum { PHY_TYPE_INDEX_NUM }; +#define HR_DSSS_ERP_BASIC_RATE GENMASK(3, 0) +#define OFDM_BASIC_RATE (BIT(6) | BIT(8) | BIT(10)) + #define PHY_TYPE_BIT_HR_DSSS BIT(PHY_TYPE_HR_DSSS_INDEX) #define PHY_TYPE_BIT_ERP BIT(PHY_TYPE_ERP_INDEX) #define PHY_TYPE_BIT_OFDM BIT(PHY_TYPE_OFDM_INDEX) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c index 85a78dea4085..29b9a15f8dbe 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c @@ -67,7 +67,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data, struct mt76_tx_info *tx_info) { struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); - int pid, len = tx_info->skb->len, ep = q2ep(dev->mphy.q_tx[qid]->hw_idx); + int pid, len = tx_info->skb->len, ep = dev->mphy.q_tx[qid]->ep; struct mt76x02_txwi *txwi; bool ampdu = IEEE80211_SKB_CB(tx_info->skb)->flags & IEEE80211_TX_CTL_AMPDU; enum mt76_qsel qsel; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c index ca78e14251c2..e92bb871f231 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c @@ -18,6 +18,7 @@ static const struct usb_device_id mt76x2u_device_table[] = { { USB_DEVICE(0x7392, 0xb711) }, /* Edimax EW 7722 UAC */ { USB_DEVICE(0x0e8d, 0x7632) }, /* HC-M7662BU1 */ { USB_DEVICE(0x2c4e, 0x0103) }, /* Mercury UD13 */ + { USB_DEVICE(0x0846, 0x9014) }, /* Netgear WNDA3100v3 */ { USB_DEVICE(0x0846, 0x9053) }, /* Netgear A6210 */ { USB_DEVICE(0x045e, 0x02e6) }, /* XBox One Wireless Adapter */ { USB_DEVICE(0x045e, 0x02fe) }, /* XBox One Wireless Adapter */ diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c index c91a1c54027f..0baa82c8df5a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c @@ -614,7 +614,7 @@ int mt7915_dma_reset(struct mt7915_dev *dev, bool force) mtk_wed_device_dma_reset(wed); mt7915_dma_disable(dev, force); - mt76_dma_wed_reset(&dev->mt76); + mt76_wed_dma_reset(&dev->mt76); /* reset hw queues */ for (i = 0; i < __MT_TXQ_MAX; i++) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index b01edbed969c..e45361111f9b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -1520,12 +1520,6 @@ void mt7915_mac_reset_work(struct work_struct *work) if (!(READ_ONCE(dev->recovery.state) & MT_MCU_CMD_STOP_DMA)) return; - if (mtk_wed_device_active(&dev->mt76.mmio.wed)) { - mtk_wed_device_stop(&dev->mt76.mmio.wed); - if (!is_mt798x(&dev->mt76)) - mt76_wr(dev, MT_INT_WED_MASK_CSR, 0); - } - ieee80211_stop_queues(mt76_hw(dev)); if (ext_phy) ieee80211_stop_queues(ext_phy->hw); @@ -1545,6 +1539,9 @@ void mt7915_mac_reset_work(struct work_struct *work) mutex_lock(&dev->mt76.mutex); + if (mtk_wed_device_active(&dev->mt76.mmio.wed)) + mtk_wed_device_stop(&dev->mt76.mmio.wed); + mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_DMA_STOPPED); if (mt7915_wait_reset_state(dev, MT_MCU_CMD_RESET_DONE)) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index df2d4279790d..3709d18da0e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -1708,6 +1708,6 @@ const struct ieee80211_ops mt7915_ops = { .set_radar_background = mt7915_set_radar_background, #ifdef CONFIG_NET_MEDIATEK_SOC_WED .net_fill_forward_path = mt7915_net_fill_forward_path, - .net_setup_tc = mt76_net_setup_tc, + .net_setup_tc = mt76_wed_net_setup_tc, #endif }; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 3039f53e2245..d6ecd698cdcd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -490,6 +490,11 @@ static u32 __mt7915_reg_addr(struct mt7915_dev *dev, u32 addr) return dev->reg.map[i].maps + ofs; } + return 0; +} + +static u32 __mt7915_reg_remap_addr(struct mt7915_dev *dev, u32 addr) +{ if ((addr >= MT_INFRA_BASE && addr < MT_WFSYS0_PHY_START) || (addr >= MT_WFSYS0_PHY_START && addr < MT_WFSYS1_PHY_START) || (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END)) @@ -514,15 +519,30 @@ void mt7915_memcpy_fromio(struct mt7915_dev *dev, void *buf, u32 offset, { u32 addr = __mt7915_reg_addr(dev, offset); - memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + if (addr) { + memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + return; + } + + spin_lock_bh(&dev->reg_lock); + memcpy_fromio(buf, dev->mt76.mmio.regs + + __mt7915_reg_remap_addr(dev, offset), len); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7915_rr(struct mt76_dev *mdev, u32 offset) { struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); - u32 addr = __mt7915_reg_addr(dev, offset); + u32 addr = __mt7915_reg_addr(dev, offset), val; - return dev->bus_ops->rr(mdev, addr); + if (addr) + return dev->bus_ops->rr(mdev, addr); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rr(mdev, __mt7915_reg_remap_addr(dev, offset)); + spin_unlock_bh(&dev->reg_lock); + + return val; } static void mt7915_wr(struct mt76_dev *mdev, u32 offset, u32 val) @@ -530,7 +550,14 @@ static void mt7915_wr(struct mt76_dev *mdev, u32 offset, u32 val) struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); u32 addr = __mt7915_reg_addr(dev, offset); - dev->bus_ops->wr(mdev, addr, val); + if (addr) { + dev->bus_ops->wr(mdev, addr, val); + return; + } + + spin_lock_bh(&dev->reg_lock); + dev->bus_ops->wr(mdev, __mt7915_reg_remap_addr(dev, offset), val); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) @@ -538,7 +565,14 @@ static u32 mt7915_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); u32 addr = __mt7915_reg_addr(dev, offset); - return dev->bus_ops->rmw(mdev, addr, mask, val); + if (addr) + return dev->bus_ops->rmw(mdev, addr, mask, val); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rmw(mdev, __mt7915_reg_remap_addr(dev, offset), mask, val); + spin_unlock_bh(&dev->reg_lock); + + return val; } #ifdef CONFIG_NET_MEDIATEK_SOC_WED @@ -672,13 +706,13 @@ int mt7915_mmio_wed_init(struct mt7915_dev *dev, void *pdev_ptr, } wed->wlan.init_buf = mt7915_wed_init_buf; - wed->wlan.offload_enable = mt76_mmio_wed_offload_enable; - wed->wlan.offload_disable = mt76_mmio_wed_offload_disable; - wed->wlan.init_rx_buf = mt76_mmio_wed_init_rx_buf; - wed->wlan.release_rx_buf = mt76_mmio_wed_release_rx_buf; + wed->wlan.offload_enable = mt76_wed_offload_enable; + wed->wlan.offload_disable = mt76_wed_offload_disable; + wed->wlan.init_rx_buf = mt76_wed_init_rx_buf; + wed->wlan.release_rx_buf = mt76_wed_release_rx_buf; wed->wlan.update_wo_rx_stats = mt7915_mmio_wed_update_rx_stats; wed->wlan.reset = mt7915_mmio_wed_reset; - wed->wlan.reset_complete = mt76_mmio_wed_reset_complete; + wed->wlan.reset_complete = mt76_wed_reset_complete; dev->mt76.rx_token_size = wed->wlan.rx_npkt; @@ -707,6 +741,7 @@ static int mt7915_mmio_init(struct mt76_dev *mdev, dev = container_of(mdev, struct mt7915_dev, mt76); mt76_mmio_init(&dev->mt76, mem_base); + spin_lock_init(&dev->reg_lock); switch (device_id) { case 0x7915: diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index 4727d9c7b11d..6e79bc65f5a5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -287,6 +287,7 @@ struct mt7915_dev { struct list_head sta_rc_list; struct list_head twt_list; + spinlock_t reg_lock; u32 hw_pattern; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c index 8b4809703efc..f5b99917c08e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/soc.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/soc.c @@ -516,7 +516,8 @@ static int mt798x_wmac_adie_patch_7976(struct mt7915_dev *dev, u8 adie) if (ret) return ret; - if (version == 0x8a00 || version == 0x8a10 || version == 0x8b00) { + if (version == 0x8a00 || version == 0x8a10 || + version == 0x8b00 || version == 0x8c10) { rg_xo_01 = 0x1d59080f; rg_xo_03 = 0x34c00fe0; } else { diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index 48433c6d5e7d..ef0c721d26e3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -138,9 +138,14 @@ mt7921_regd_notifier(struct wiphy *wiphy, if (pm->suspended) return; + dev->regd_in_progress = true; + mt792x_mutex_acquire(dev); mt7921_regd_update(dev); mt792x_mutex_release(dev); + + dev->regd_in_progress = false; + wake_up(&dev->wait); } int mt7921_mac_init(struct mt792x_dev *dev) @@ -261,6 +266,7 @@ int mt7921_register_device(struct mt792x_dev *dev) spin_lock_init(&dev->pm.wake.lock); mutex_init(&dev->pm.mutex); init_waitqueue_head(&dev->pm.wait); + init_waitqueue_head(&dev->wait); if (mt76_is_sdio(&dev->mt76)) init_waitqueue_head(&dev->mt76.sdio.wait); spin_lock_init(&dev->pm.txq_lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 0d5adc5ddae3..ca36de34171b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -325,6 +325,19 @@ static void mt7921_roc_iter(void *priv, u8 *mac, mt7921_mcu_abort_roc(phy, mvif, phy->roc_token_id); } +void mt7921_roc_abort_sync(struct mt792x_dev *dev) +{ + struct mt792x_phy *phy = &dev->phy; + + del_timer_sync(&phy->roc_timer); + cancel_work_sync(&phy->roc_work); + if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state)) + ieee80211_iterate_active_interfaces(mt76_hw(dev), + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7921_roc_iter, (void *)phy); +} +EXPORT_SYMBOL_GPL(mt7921_roc_abort_sync); + void mt7921_roc_work(struct work_struct *work) { struct mt792x_phy *phy; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index f5582477c7e4..8b4ce32a2cd1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -1272,7 +1272,7 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2, .mtcl_conf = mt792x_acpi_get_mtcl_conf(&dev->phy, alpha2), }; int ret, valid_cnt = 0; - u16 buf_len = 0; + u32 buf_len = 0; u8 *pos; if (!clc) @@ -1283,7 +1283,7 @@ int __mt7921_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2, if (mt76_find_power_limits_node(&dev->mt76)) req.cap |= CLC_CAP_DTS_EN; - buf_len = le16_to_cpu(clc->len) - sizeof(*clc); + buf_len = le32_to_cpu(clc->len) - sizeof(*clc); pos = clc->data; while (buf_len > 16) { struct mt7921_clc_rule *rule = (struct mt7921_clc_rule *)pos; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h index 1cb21133992b..3016636d18c6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h @@ -322,4 +322,5 @@ int mt7921_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_vif *vif, enum mt7921_roc_req type, u8 token_id); int mt7921_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_vif *vif, u8 token_id); +void mt7921_roc_abort_sync(struct mt792x_dev *dev); #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index dde26f327478..cda853e86676 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/of.h> #include "mt7921.h" #include "../mt76_connac2_mac.h" @@ -369,6 +370,9 @@ static int mt7921_pci_probe(struct pci_dev *pdev, if (ret) goto err_free_irq; + if (of_property_read_bool(dev->mt76.dev->of_node, "wakeup-source")) + device_init_wakeup(dev->mt76.dev, true); + return 0; err_free_irq: @@ -386,7 +390,11 @@ static void mt7921_pci_remove(struct pci_dev *pdev) struct mt76_dev *mdev = pci_get_drvdata(pdev); struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); + if (of_property_read_bool(dev->mt76.dev->of_node, "wakeup-source")) + device_init_wakeup(dev->mt76.dev, false); + mt7921e_unregister_device(dev); + set_bit(MT76_REMOVED, &mdev->phy.state); devm_free_irq(&pdev->dev, pdev->irq, dev); mt76_free_device(&dev->mt76); pci_free_irq_vectors(pdev); @@ -405,10 +413,15 @@ static int mt7921_pci_suspend(struct device *device) cancel_delayed_work_sync(&pm->ps_work); cancel_work_sync(&pm->wake_work); + mt7921_roc_abort_sync(dev); + err = mt792x_mcu_drv_pmctrl(dev); if (err < 0) goto restore_suspend; + wait_event_timeout(dev->wait, + !dev->regd_in_progress, 5 * HZ); + err = mt76_connac_mcu_set_hif_suspend(mdev, true); if (err) goto restore_suspend; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c index a9ce1e746b95..004d942ee11a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c @@ -216,6 +216,8 @@ static int mt7921s_suspend(struct device *__dev) cancel_delayed_work_sync(&pm->ps_work); cancel_work_sync(&pm->wake_work); + mt7921_roc_abort_sync(dev); + err = mt792x_mcu_drv_pmctrl(dev); if (err < 0) goto restore_suspend; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c index 8f9b7a2f376c..c4cbc8976046 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c @@ -2,11 +2,61 @@ /* Copyright (C) 2023 MediaTek Inc. */ #include <linux/etherdevice.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> +#include <linux/thermal.h> #include <linux/firmware.h> #include "mt7925.h" #include "mac.h" #include "mcu.h" +static ssize_t mt7925_thermal_temp_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + switch (to_sensor_dev_attr(attr)->index) { + case 0: { + struct mt792x_phy *phy = dev_get_drvdata(dev); + struct mt792x_dev *mdev = phy->dev; + int temperature; + + mt792x_mutex_acquire(mdev); + temperature = mt7925_mcu_get_temperature(phy); + mt792x_mutex_release(mdev); + + if (temperature < 0) + return temperature; + /* display in millidegree Celsius */ + return sprintf(buf, "%u\n", temperature * 1000); + } + default: + return -EINVAL; + } +} +static SENSOR_DEVICE_ATTR_RO(temp1_input, mt7925_thermal_temp, 0); + +static struct attribute *mt7925_hwmon_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(mt7925_hwmon); + +static int mt7925_thermal_init(struct mt792x_phy *phy) +{ + struct wiphy *wiphy = phy->mt76->hw->wiphy; + struct device *hwmon; + const char *name; + + if (!IS_REACHABLE(CONFIG_HWMON)) + return 0; + + name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7925_%s", + wiphy_name(wiphy)); + + hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy, + mt7925_hwmon_groups); + return PTR_ERR_OR_ZERO(hwmon); +} static void mt7925_regd_notifier(struct wiphy *wiphy, struct regulatory_request *req) @@ -142,6 +192,12 @@ static void mt7925_init_work(struct work_struct *work) return; } + ret = mt7925_thermal_init(&dev->phy); + if (ret) { + dev_err(dev->mt76.dev, "thermal init failed\n"); + return; + } + /* we support chip reset now */ dev->hw_init_done = true; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index 125a1be3cb64..6179798a8845 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -359,6 +359,7 @@ mt7925_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->sta.wcid.phy_idx = mvif->mt76.band_idx; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; + mvif->sta.vif = mvif; mt76_wcid_init(&mvif->sta.wcid); mt7925_mac_wtbl_update(dev, idx, @@ -526,7 +527,7 @@ static int mt7925_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, if (cmd == SET_KEY && !mvif->mt76.cipher) { struct mt792x_phy *phy = mt792x_hw_phy(hw); - mvif->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher); + mvif->mt76.cipher = mt7925_mcu_get_cipher(key->cipher); mt7925_mcu_add_bss_info(phy, mvif->mt76.ctx, vif, sta, true); } @@ -710,7 +711,7 @@ static void mt7925_bss_info_changed(struct ieee80211_hw *hw, if (slottime != phy->slottime) { phy->slottime = slottime; - mt792x_mac_set_timeing(phy); + mt7925_mcu_set_timing(phy, vif); } } @@ -1274,6 +1275,25 @@ mt7925_channel_switch_beacon(struct ieee80211_hw *hw, } static int +mt7925_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, u16 queue, + const struct ieee80211_tx_queue_params *params) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + static const u8 mq_to_aci[] = { + [IEEE80211_AC_VO] = 3, + [IEEE80211_AC_VI] = 2, + [IEEE80211_AC_BE] = 0, + [IEEE80211_AC_BK] = 1, + }; + + /* firmware uses access class index */ + mvif->queue_params[mq_to_aci[queue]] = *params; + + return 0; +} + +static int mt7925_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf) { @@ -1396,7 +1416,7 @@ const struct ieee80211_ops mt7925_ops = { .add_interface = mt7925_add_interface, .remove_interface = mt792x_remove_interface, .config = mt7925_config, - .conf_tx = mt792x_conf_tx, + .conf_tx = mt7925_conf_tx, .configure_filter = mt7925_configure_filter, .bss_info_changed = mt7925_bss_info_changed, .start_ap = mt7925_start_ap, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index c5fd7116929b..bd37cb8d734b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -656,6 +656,42 @@ int mt7925_mcu_fw_log_2_host(struct mt792x_dev *dev, u8 ctrl) return ret; } +int mt7925_mcu_get_temperature(struct mt792x_phy *phy) +{ + struct { + u8 _rsv[4]; + + __le16 tag; + __le16 len; + u8 _rsv2[4]; + } __packed req = { + .tag = cpu_to_le16(0x0), + .len = cpu_to_le16(sizeof(req) - 4), + }; + struct mt7925_thermal_evt { + u8 rsv[4]; + __le32 temperature; + } __packed * evt; + struct mt792x_dev *dev = phy->dev; + int temperature, ret; + struct sk_buff *skb; + + ret = mt76_mcu_send_and_get_msg(&dev->mt76, + MCU_WM_UNI_CMD_QUERY(THERMAL), + &req, sizeof(req), true, &skb); + if (ret) + return ret; + + skb_pull(skb, 4 + sizeof(struct tlv)); + evt = (struct mt7925_thermal_evt *)skb->data; + + temperature = le32_to_cpu(evt->temperature); + + dev_kfree_skb(skb); + + return temperature; +} + static void mt7925_mcu_parse_phy_cap(struct mt792x_dev *dev, char *data) { @@ -814,6 +850,7 @@ mt7925_mcu_sta_hdr_trans_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; struct sta_rec_hdr_trans *hdr_trans; struct mt76_wcid *wcid; struct tlv *tlv; @@ -827,7 +864,11 @@ mt7925_mcu_sta_hdr_trans_tlv(struct sk_buff *skb, else hdr_trans->from_ds = true; - wcid = (struct mt76_wcid *)sta->drv_priv; + if (sta) + wcid = (struct mt76_wcid *)sta->drv_priv; + else + wcid = &mvif->sta.wcid; + if (!wcid) return; @@ -895,7 +936,7 @@ int mt7925_mcu_set_tx(struct mt792x_dev *dev, struct ieee80211_vif *vif) e = (struct edca *)tlv; e->set = WMM_PARAM_SET; - e->queue = ac + mvif->mt76.wmm_idx * MT76_CONNAC_MAX_WMM_SETS; + e->queue = ac; e->aifs = q->aifs; e->txop = cpu_to_le16(q->txop); @@ -921,61 +962,67 @@ mt7925_mcu_sta_key_tlv(struct mt76_wcid *wcid, struct ieee80211_key_conf *key, enum set_key_cmd cmd) { + struct mt792x_sta *msta = container_of(wcid, struct mt792x_sta, wcid); struct sta_rec_sec_uni *sec; + struct mt792x_vif *mvif = msta->vif; + struct ieee80211_sta *sta; + struct ieee80211_vif *vif; struct tlv *tlv; - tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V2, sizeof(*sec)); + sta = msta == &mvif->sta ? + NULL : + container_of((void *)msta, struct ieee80211_sta, drv_priv); + vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv); + + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_KEY_V3, sizeof(*sec)); sec = (struct sta_rec_sec_uni *)tlv; - sec->add = cmd; + sec->bss_idx = mvif->mt76.idx; + sec->is_authenticator = 0; + sec->mgmt_prot = 0; + sec->wlan_idx = (u8)wcid->idx; + + if (sta) { + sec->tx_key = 1; + sec->key_type = 1; + memcpy(sec->peer_addr, sta->addr, ETH_ALEN); + } else { + memcpy(sec->peer_addr, vif->bss_conf.bssid, ETH_ALEN); + } if (cmd == SET_KEY) { - struct sec_key_uni *sec_key; u8 cipher; - cipher = mt76_connac_mcu_get_cipher(key->cipher); - if (cipher == MCU_CIPHER_NONE) + sec->add = 1; + cipher = mt7925_mcu_get_cipher(key->cipher); + if (cipher == CONNAC3_CIPHER_NONE) return -EOPNOTSUPP; - sec_key = &sec->key[0]; - sec_key->cipher_len = sizeof(*sec_key); - - if (cipher == MCU_CIPHER_BIP_CMAC_128) { - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = MCU_CIPHER_AES_CCMP; - sec_key->key_id = sta_key_conf->keyidx; - sec_key->key_len = 16; - memcpy(sec_key->key, sta_key_conf->key, 16); - - sec_key = &sec->key[1]; - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; - sec_key->cipher_len = sizeof(*sec_key); - sec_key->key_len = 16; - memcpy(sec_key->key, key->key, 16); - sec->n_cipher = 2; + if (cipher == CONNAC3_CIPHER_BIP_CMAC_128) { + sec->cipher_id = CONNAC3_CIPHER_BIP_CMAC_128; + sec->key_id = sta_key_conf->keyidx; + sec->key_len = 32; + memcpy(sec->key, sta_key_conf->key, 16); + memcpy(sec->key + 16, key->key, 16); } else { - sec_key->wlan_idx = cpu_to_le16(wcid->idx); - sec_key->cipher_id = cipher; - sec_key->key_id = key->keyidx; - sec_key->key_len = key->keylen; - memcpy(sec_key->key, key->key, key->keylen); + sec->cipher_id = cipher; + sec->key_id = key->keyidx; + sec->key_len = key->keylen; + memcpy(sec->key, key->key, key->keylen); - if (cipher == MCU_CIPHER_TKIP) { + if (cipher == CONNAC3_CIPHER_TKIP) { /* Rx/Tx MIC keys are swapped */ - memcpy(sec_key->key + 16, key->key + 24, 8); - memcpy(sec_key->key + 24, key->key + 16, 8); + memcpy(sec->key + 16, key->key + 24, 8); + memcpy(sec->key + 24, key->key + 16, 8); } /* store key_conf for BIP batch update */ - if (cipher == MCU_CIPHER_AES_CCMP) { + if (cipher == CONNAC3_CIPHER_AES_CCMP) { memcpy(sta_key_conf->key, key->key, key->keylen); sta_key_conf->keyidx = key->keyidx; } - - sec->n_cipher = 1; } } else { - sec->n_cipher = 0; + sec->add = 0; } return 0; @@ -1460,12 +1507,10 @@ mt7925_mcu_sta_phy_tlv(struct sk_buff *skb, struct tlv *tlv; u8 af = 0, mm = 0; - if (!sta->deflink.ht_cap.ht_supported && !sta->deflink.he_6ghz_capa.capa) - return; - tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_PHY, sizeof(*phy)); phy = (struct sta_rec_phy *)tlv; phy->phy_type = mt76_connac_get_phy_mode_v2(mvif->phy->mt76, vif, chandef->chan->band, sta); + phy->basic_rate = cpu_to_le16((u16)vif->bss_conf.basic_rates); if (sta->deflink.ht_cap.ht_supported) { af = sta->deflink.ht_cap.ampdu_factor; mm = sta->deflink.ht_cap.ampdu_density; @@ -1573,8 +1618,6 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, { struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv; struct mt76_dev *dev = phy->dev; - struct wtbl_req_hdr *wtbl_hdr; - struct tlv *sta_wtbl; struct sk_buff *skb; skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid, @@ -1598,30 +1641,11 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, mt7925_mcu_sta_state_v2_tlv(phy, skb, info->sta, info->vif, info->rcpi, info->state); - mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->sta); mt7925_mcu_sta_mld_tlv(skb, info->vif, info->sta); } - sta_wtbl = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, - sizeof(struct tlv)); - - wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(dev, info->wcid, - WTBL_RESET_AND_SET, - sta_wtbl, &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - if (info->enable) { - mt76_connac_mcu_wtbl_generic_tlv(dev, skb, info->vif, - info->sta, sta_wtbl, - wtbl_hdr); - mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, info->vif, info->wcid, - sta_wtbl, wtbl_hdr); - if (info->sta) - mt76_connac_mcu_wtbl_ht_tlv(dev, skb, info->sta, - sta_wtbl, wtbl_hdr, - true, true); - } + if (info->enable) + mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->sta); return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); } @@ -2049,9 +2073,9 @@ mt7925_mcu_bss_basic_tlv(struct sk_buff *skb, struct cfg80211_chan_def *chandef = ctx ? &ctx->def : &phy->chandef; enum nl80211_band band = chandef->chan->band; struct mt76_connac_bss_basic_tlv *basic_req; - u8 idx, basic_phy; struct tlv *tlv; int conn_type; + u8 idx; tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_BASIC, sizeof(*basic_req)); basic_req = (struct mt76_connac_bss_basic_tlv *)tlv; @@ -2062,8 +2086,10 @@ mt7925_mcu_bss_basic_tlv(struct sk_buff *skb, basic_req->phymode_ext = mt7925_get_phy_mode_ext(phy, vif, band, sta); - basic_phy = mt76_connac_get_phy_mode_v2(phy, vif, band, sta); - basic_req->nonht_basic_phy = cpu_to_le16(basic_phy); + if (band == NL80211_BAND_2GHZ) + basic_req->nonht_basic_phy = cpu_to_le16(PHY_TYPE_ERP_INDEX); + else + basic_req->nonht_basic_phy = cpu_to_le16(PHY_TYPE_OFDM_INDEX); memcpy(basic_req->bssid, vif->bss_conf.bssid, ETH_ALEN); basic_req->phymode = mt76_connac_get_phy_mode(phy, vif, band, sta); @@ -2122,21 +2148,21 @@ mt7925_mcu_bss_sec_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) sec = (struct bss_sec_tlv *)tlv; switch (mvif->cipher) { - case MCU_CIPHER_GCMP_256: - case MCU_CIPHER_GCMP: + case CONNAC3_CIPHER_GCMP_256: + case CONNAC3_CIPHER_GCMP: sec->mode = MODE_WPA3_SAE; sec->status = 8; break; - case MCU_CIPHER_AES_CCMP: + case CONNAC3_CIPHER_AES_CCMP: sec->mode = MODE_WPA2_PSK; sec->status = 6; break; - case MCU_CIPHER_TKIP: + case CONNAC3_CIPHER_TKIP: sec->mode = MODE_WPA2_PSK; sec->status = 4; break; - case MCU_CIPHER_WEP104: - case MCU_CIPHER_WEP40: + case CONNAC3_CIPHER_WEP104: + case CONNAC3_CIPHER_WEP40: sec->mode = MODE_SHARED; sec->status = 0; break; @@ -2167,6 +2193,11 @@ mt7925_mcu_bss_bmc_tlv(struct sk_buff *skb, struct mt792x_phy *phy, bmc = (struct bss_rate_tlv *)tlv; + if (band == NL80211_BAND_2GHZ) + bmc->basic_rate = cpu_to_le16(HR_DSSS_ERP_BASIC_RATE); + else + bmc->basic_rate = cpu_to_le16(OFDM_BASIC_RATE); + bmc->short_preamble = (band == NL80211_BAND_2GHZ); bmc->bc_fixed_rate = idx; bmc->mc_fixed_rate = idx; @@ -2249,6 +2280,38 @@ mt7925_mcu_bss_color_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, vif->bss_conf.he_bss_color.color : 0; } +static void +mt7925_mcu_bss_ifs_tlv(struct sk_buff *skb, struct ieee80211_vif *vif) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_phy *phy = mvif->phy; + struct bss_ifs_time_tlv *ifs_time; + struct tlv *tlv; + + tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_IFS_TIME, sizeof(*ifs_time)); + ifs_time = (struct bss_ifs_time_tlv *)tlv; + ifs_time->slot_valid = true; + ifs_time->slot_time = cpu_to_le16(phy->slottime); +} + +int mt7925_mcu_set_timing(struct mt792x_phy *phy, + struct ieee80211_vif *vif) +{ + struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv; + struct mt792x_dev *dev = phy->dev; + struct sk_buff *skb; + + skb = __mt7925_mcu_alloc_bss_req(&dev->mt76, &mvif->mt76, + MT7925_BSS_UPDATE_MAX_SIZE); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + mt7925_mcu_bss_ifs_tlv(skb, vif); + + return mt76_mcu_skb_send_msg(&dev->mt76, skb, + MCU_UNI_CMD(BSS_INFO_UPDATE), true); +} + int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, struct ieee80211_chanctx_conf *ctx, struct ieee80211_vif *vif, @@ -2273,6 +2336,7 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, mt7925_mcu_bss_bmc_tlv(skb, phy, ctx, vif, sta); mt7925_mcu_bss_qos_tlv(skb, vif); mt7925_mcu_bss_mld_tlv(skb, vif, sta); + mt7925_mcu_bss_ifs_tlv(skb, vif); if (vif->bss_conf.he_support) { mt7925_mcu_bss_he_tlv(skb, vif, phy); @@ -2845,12 +2909,16 @@ int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb, if (cmd & __MCU_CMD_FIELD_UNI) { uni_txd = (struct mt76_connac2_mcu_uni_txd *)txd; uni_txd->len = cpu_to_le16(skb->len - sizeof(uni_txd->txd)); - uni_txd->option = MCU_CMD_UNI_EXT_ACK; uni_txd->cid = cpu_to_le16(mcu_cmd); uni_txd->s2d_index = MCU_S2D_H2N; uni_txd->pkt_type = MCU_PKT_ID; uni_txd->seq = seq; + if (cmd & __MCU_CMD_FIELD_QUERY) + uni_txd->option = MCU_CMD_UNI_QUERY_ACK; + else + uni_txd->option = MCU_CMD_UNI_EXT_ACK; + goto exit; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h index 3c41e21303b1..2a0bbfe7bfa5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h @@ -159,6 +159,20 @@ enum { UNI_EVENT_SCAN_DONE_NLO = 3, }; +enum connac3_mcu_cipher_type { + CONNAC3_CIPHER_NONE = 0, + CONNAC3_CIPHER_WEP40 = 1, + CONNAC3_CIPHER_TKIP = 2, + CONNAC3_CIPHER_AES_CCMP = 4, + CONNAC3_CIPHER_WEP104 = 5, + CONNAC3_CIPHER_BIP_CMAC_128 = 6, + CONNAC3_CIPHER_WEP128 = 7, + CONNAC3_CIPHER_WAPI = 8, + CONNAC3_CIPHER_CCMP_256 = 10, + CONNAC3_CIPHER_GCMP = 11, + CONNAC3_CIPHER_GCMP_256 = 12, +}; + struct mt7925_mcu_scan_chinfo_event { u8 nr_chan; u8 alpha2[3]; @@ -208,7 +222,7 @@ struct scan_req_tlv { __le16 channel_dwell_time; /* channel Dwell interval */ __le16 timeout_value; __le16 probe_delay_time; - u8 func_mask_ext; + __le32 func_mask_ext; }; struct scan_ssid_tlv { @@ -334,7 +348,8 @@ struct bss_req_hdr { struct bss_rate_tlv { __le16 tag; __le16 len; - u8 __rsv1[4]; + u8 __rsv1[2]; + __le16 basic_rate; __le16 bc_trans; __le16 mc_trans; u8 short_preamble; @@ -382,25 +397,22 @@ struct sta_rec_eht { u8 _rsv2[3]; } __packed; -struct sec_key_uni { - __le16 wlan_idx; - u8 mgmt_prot; - u8 cipher_id; - u8 cipher_len; - u8 key_id; - u8 key_len; - u8 need_resp; - u8 key[32]; -} __packed; - struct sta_rec_sec_uni { __le16 tag; __le16 len; u8 add; - u8 n_cipher; - u8 rsv[2]; - - struct sec_key_uni key[2]; + u8 tx_key; + u8 key_type; + u8 is_authenticator; + u8 peer_addr[6]; + u8 bss_idx; + u8 cipher_id; + u8 key_id; + u8 key_len; + u8 wlan_idx; + u8 mgmt_prot; + u8 key[32]; + u8 key_rsc[16]; } __packed; struct sta_rec_hdr_trans { @@ -428,6 +440,22 @@ struct sta_rec_mld { } __packed link[2]; } __packed; +struct bss_ifs_time_tlv { + __le16 tag; + __le16 len; + u8 slot_valid; + u8 sifs_valid; + u8 rifs_valid; + u8 eifs_valid; + __le16 slot_time; + __le16 sifs_time; + __le16 rifs_time; + __le16 eifs_time; + u8 eifs_cck_valid; + u8 rsv; + __le16 eifs_cck_time; +} __packed; + #define MT7925_STA_UPDATE_MAX_SIZE (sizeof(struct sta_req_hdr) + \ sizeof(struct sta_rec_basic) + \ sizeof(struct sta_rec_bf) + \ @@ -440,7 +468,7 @@ struct sta_rec_mld { sizeof(struct sta_rec_bfee) + \ sizeof(struct sta_rec_phy) + \ sizeof(struct sta_rec_ra) + \ - sizeof(struct sta_rec_sec) + \ + sizeof(struct sta_rec_sec_uni) + \ sizeof(struct sta_rec_ra_fixed) + \ sizeof(struct sta_rec_he_6g_capa) + \ sizeof(struct sta_rec_eht) + \ @@ -455,6 +483,7 @@ struct sta_rec_mld { sizeof(struct bss_mld_tlv) + \ sizeof(struct bss_info_uni_he) + \ sizeof(struct bss_info_uni_bss_color) + \ + sizeof(struct bss_ifs_time_tlv) + \ sizeof(struct tlv)) #define MT_CONNAC3_SKU_POWER_LIMIT 449 @@ -509,6 +538,33 @@ struct mt7925_wow_pattern_tlv { u8 rsv[4]; } __packed; +static inline enum connac3_mcu_cipher_type +mt7925_mcu_get_cipher(int cipher) +{ + switch (cipher) { + case WLAN_CIPHER_SUITE_WEP40: + return CONNAC3_CIPHER_WEP40; + case WLAN_CIPHER_SUITE_WEP104: + return CONNAC3_CIPHER_WEP104; + case WLAN_CIPHER_SUITE_TKIP: + return CONNAC3_CIPHER_TKIP; + case WLAN_CIPHER_SUITE_AES_CMAC: + return CONNAC3_CIPHER_BIP_CMAC_128; + case WLAN_CIPHER_SUITE_CCMP: + return CONNAC3_CIPHER_AES_CCMP; + case WLAN_CIPHER_SUITE_CCMP_256: + return CONNAC3_CIPHER_CCMP_256; + case WLAN_CIPHER_SUITE_GCMP: + return CONNAC3_CIPHER_GCMP; + case WLAN_CIPHER_SUITE_GCMP_256: + return CONNAC3_CIPHER_GCMP_256; + case WLAN_CIPHER_SUITE_SMS4: + return CONNAC3_CIPHER_WAPI; + default: + return CONNAC3_CIPHER_NONE; + } +} + int mt7925_mcu_set_dbdc(struct mt76_phy *phy); int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req); @@ -525,6 +581,8 @@ int mt7925_mcu_add_bss_info(struct mt792x_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, int enable); +int mt7925_mcu_set_timing(struct mt792x_phy *phy, + struct ieee80211_vif *vif); int mt7925_mcu_set_deep_sleep(struct mt792x_dev *dev, bool enable); int mt7925_mcu_set_channel_domain(struct mt76_phy *phy); int mt7925_mcu_set_radio_en(struct mt792x_phy *phy, bool enable); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h index 33785f526acf..8a4a71f6bcb6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h @@ -271,6 +271,7 @@ int mt7925_mcu_set_sniffer(struct mt792x_dev *dev, struct ieee80211_vif *vif, bool enable); int mt7925_mcu_config_sniffer(struct mt792x_vif *vif, struct ieee80211_chanctx_conf *ctx); +int mt7925_mcu_get_temperature(struct mt792x_phy *phy); int mt7925_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, enum mt76_txq_id qid, struct mt76_wcid *wcid, diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index 1fd99a856541..07b74d492ce1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -386,6 +386,8 @@ static int mt7925_pci_probe(struct pci_dev *pdev, dev_info(mdev->dev, "ASIC revision: %04x\n", mdev->rev); + mt76_rmw_field(dev, MT_HW_EMI_CTL, MT_HW_EMI_CTL_SLPPROT_EN, 1); + ret = mt792x_wfsys_reset(dev); if (ret) goto err_free_dev; @@ -425,6 +427,7 @@ static void mt7925_pci_remove(struct pci_dev *pdev) struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76); mt7925e_unregister_device(dev); + set_bit(MT76_REMOVED, &mdev->phy.state); devm_free_irq(&pdev->dev, pdev->irq, dev); mt76_free_device(&dev->mt76); pci_free_irq_vectors(pdev); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h index 3c897b34aaa7..a8556de3d480 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x.h +++ b/drivers/net/wireless/mediatek/mt76/mt792x.h @@ -186,6 +186,8 @@ struct mt792x_dev { bool hw_init_done:1; bool fw_assert:1; bool has_eht:1; + bool regd_in_progress:1; + wait_queue_head_t wait; struct work_struct init_work; diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c index e7afea87e82e..9317f8ff2070 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c @@ -66,13 +66,15 @@ free: } /* MTCL : Country List Table for 6G band */ -static void +static int mt792x_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version) { - if (mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL) < 0) - *version = 1; - else - *version = 2; + int ret; + + *version = ((ret = mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL)) < 0) + ? 1 : 2; + + return ret; } /* MTDS : Dynamic SAR Power Table */ @@ -166,16 +168,16 @@ int mt792x_init_acpi_sar(struct mt792x_dev *dev) if (!asar) return -ENOMEM; - mt792x_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver); + ret = mt792x_asar_acpi_read_mtcl(dev, (u8 **)&asar->countrylist, &asar->ver); + if (ret) { + devm_kfree(dev->mt76.dev, asar->countrylist); + asar->countrylist = NULL; + } - /* MTDS is mandatory. Return error if table is invalid */ ret = mt792x_asar_acpi_read_mtds(dev, (u8 **)&asar->dyn, asar->ver); if (ret) { devm_kfree(dev->mt76.dev, asar->dyn); - devm_kfree(dev->mt76.dev, asar->countrylist); - devm_kfree(dev->mt76.dev, asar); - - return ret; + asar->dyn = NULL; } /* MTGS is optional */ @@ -290,7 +292,7 @@ int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default) const struct cfg80211_sar_capa *capa = phy->mt76->hw->wiphy->sar_capa; int i; - if (!phy->acpisar) + if (!phy->acpisar || !((struct mt792x_acpi_sar *)phy->acpisar)->dyn) return 0; /* When ACPI SAR enabled in HW, we should apply rules for .frp @@ -353,11 +355,15 @@ static u8 mt792x_acpi_get_mtcl_map(int row, int column, struct mt792x_asar_cl *cl) { u8 config = 0; + u8 mode_6g, mode_5g9; + + mode_6g = (cl->mode_6g > 0x02) ? 0 : cl->mode_6g; + mode_5g9 = (cl->mode_5g9 > 0x01) ? 0 : cl->mode_5g9; - if (cl->cl6g[row] & BIT(column)) - config |= (cl->mode_6g & 0x3) << 2; + if ((cl->cl6g[row] & BIT(column)) || cl->mode_6g == 0x02) + config |= (mode_6g & 0x3) << 2; if (cl->version > 1 && cl->cl5g9[row] & BIT(column)) - config |= (cl->mode_5g9 & 0x3); + config |= (mode_5g9 & 0x3); return config; } @@ -374,7 +380,7 @@ u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2) "AT", "BE", "BG", "CY", "CZ", "HR", "DK", "EE", "FI", "FR", "DE", "GR", "HU", "IS", "IE", "IT", "LV", "LI", "LT", "LU", "MT", "NL", "NO", "PL", - "PT", "RO", "MT", "SK", "SI", "ES", "CH", + "PT", "RO", "SK", "SI", "ES", "SE", "CH", }; struct mt792x_acpi_sar *sar = phy->acpisar; struct mt792x_asar_cl *cl; diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index 7872fbae7252..a405af8d9052 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -354,6 +354,7 @@ static const char mt792x_gstrings_stats[][ETH_GSTRING_LEN] = { "v_tx_bw_40", "v_tx_bw_80", "v_tx_bw_160", + "v_tx_bw_320", "v_tx_mcs_0", "v_tx_mcs_1", "v_tx_mcs_2", diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c index 488326ce5ed4..5cc2d59b774a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c @@ -12,6 +12,8 @@ irqreturn_t mt792x_irq_handler(int irq, void *dev_instance) { struct mt792x_dev *dev = dev_instance; + if (test_bit(MT76_REMOVED, &dev->mt76.phy.state)) + return IRQ_NONE; mt76_wr(dev, dev->irq_map->host_irq_enable, 0); if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) @@ -123,14 +125,13 @@ static void mt792x_dma_prefetch(struct mt792x_dev *dev) int mt792x_dma_enable(struct mt792x_dev *dev) { - if (is_mt7925(&dev->mt76)) - mt76_rmw(dev, MT_UWFDMA0_GLO_CFG_EXT1, BIT(28), BIT(28)); - /* configure perfetch settings */ mt792x_dma_prefetch(dev); /* reset dma idx */ mt76_wr(dev, MT_WFDMA0_RST_DTX_PTR, ~0); + if (is_mt7925(&dev->mt76)) + mt76_wr(dev, MT_WFDMA0_RST_DRX_PTR, ~0); /* configure delay interrupt */ mt76_wr(dev, MT_WFDMA0_PRI_DLY_INT_CFG0, 0); @@ -140,12 +141,20 @@ int mt792x_dma_enable(struct mt792x_dev *dev) MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN | MT_WFDMA0_GLO_CFG_CLK_GAT_DIS | MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | + FIELD_PREP(MT_WFDMA0_GLO_CFG_DMA_SIZE, 3) | + MT_WFDMA0_GLO_CFG_FIFO_DIS_CHECK | + MT_WFDMA0_GLO_CFG_RX_WB_DDONE | MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN | MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); mt76_set(dev, MT_WFDMA0_GLO_CFG, MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN); + if (is_mt7925(&dev->mt76)) { + mt76_rmw(dev, MT_UWFDMA0_GLO_CFG_EXT1, BIT(28), BIT(28)); + mt76_set(dev, MT_WFDMA0_INT_RX_PRI, 0x0F00); + mt76_set(dev, MT_WFDMA0_INT_TX_PRI, 0x7F00); + } mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT); /* enable interrupts for TX/RX rings */ diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h index a99af23e4b56..458cfd0260b1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt792x_regs.h @@ -292,9 +292,12 @@ #define MT_WFDMA0_GLO_CFG_TX_DMA_BUSY BIT(1) #define MT_WFDMA0_GLO_CFG_RX_DMA_EN BIT(2) #define MT_WFDMA0_GLO_CFG_RX_DMA_BUSY BIT(3) +#define MT_WFDMA0_GLO_CFG_DMA_SIZE GENMASK(5, 4) #define MT_WFDMA0_GLO_CFG_TX_WB_DDONE BIT(6) #define MT_WFDMA0_GLO_CFG_FW_DWLD_BYPASS_DMASHDL BIT(9) +#define MT_WFDMA0_GLO_CFG_FIFO_DIS_CHECK BIT(11) #define MT_WFDMA0_GLO_CFG_FIFO_LITTLE_ENDIAN BIT(12) +#define MT_WFDMA0_GLO_CFG_RX_WB_DDONE BIT(13) #define MT_WFDMA0_GLO_CFG_CSR_DISP_BASE_PTR_CHAIN_EN BIT(15) #define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 BIT(21) #define MT_WFDMA0_GLO_CFG_OMIT_RX_INFO BIT(27) @@ -322,6 +325,8 @@ #define MT_WFDMA0_RST_DTX_PTR MT_WFDMA0(0x20c) #define MT_WFDMA0_RST_DRX_PTR MT_WFDMA0(0x280) +#define MT_WFDMA0_INT_RX_PRI MT_WFDMA0(0x298) +#define MT_WFDMA0_INT_TX_PRI MT_WFDMA0(0x29c) #define MT_WFDMA0_GLO_CFG_EXT0 MT_WFDMA0(0x2b0) #define MT_WFDMA0_CSR_TX_DMASHDL_ENABLE BIT(6) #define MT_WFDMA0_PRI_DLY_INT_CFG0 MT_WFDMA0(0x2f0) @@ -389,6 +394,9 @@ #define MT_HW_CHIPID 0x70010200 #define MT_HW_REV 0x70010204 +#define MT_HW_EMI_CTL 0x18011100 +#define MT_HW_EMI_CTL_SLPPROT_EN BIT(1) + #define MT_PCIE_MAC_BASE 0x10000 #define MT_PCIE_MAC(ofs) (MT_PCIE_MAC_BASE + (ofs)) #define MT_PCIE_MAC_INT_ENABLE MT_PCIE_MAC(0x188) diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c index 589a3efb9f8c..b49668a4b784 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_usb.c @@ -121,44 +121,25 @@ static void mt792xu_uhw_wr(struct mt76_dev *dev, u32 addr, u32 val) static void mt792xu_dma_prefetch(struct mt792x_dev *dev) { - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(0), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(0), - MT_WPDMA0_BASE_PTR_MASK, 0x80); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(1), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(1), - MT_WPDMA0_BASE_PTR_MASK, 0xc0); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(2), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(2), - MT_WPDMA0_BASE_PTR_MASK, 0x100); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(3), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(3), - MT_WPDMA0_BASE_PTR_MASK, 0x140); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(4), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(4), - MT_WPDMA0_BASE_PTR_MASK, 0x180); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(16), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(16), - MT_WPDMA0_BASE_PTR_MASK, 0x280); - - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(17), - MT_WPDMA0_MAX_CNT_MASK, 4); - mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL(17), - MT_WPDMA0_BASE_PTR_MASK, 0x2c0); +#define DMA_PREFETCH_CONF(_idx_, _cnt_, _base_) \ + mt76_rmw(dev, MT_UWFDMA0_TX_RING_EXT_CTRL((_idx_)), \ + MT_WPDMA0_MAX_CNT_MASK | MT_WPDMA0_BASE_PTR_MASK, \ + FIELD_PREP(MT_WPDMA0_MAX_CNT_MASK, (_cnt_)) | \ + FIELD_PREP(MT_WPDMA0_BASE_PTR_MASK, (_base_))) + + DMA_PREFETCH_CONF(0, 4, 0x080); + DMA_PREFETCH_CONF(1, 4, 0x0c0); + DMA_PREFETCH_CONF(2, 4, 0x100); + DMA_PREFETCH_CONF(3, 4, 0x140); + DMA_PREFETCH_CONF(4, 4, 0x180); + DMA_PREFETCH_CONF(16, 4, 0x280); + DMA_PREFETCH_CONF(17, 4, 0x2c0); } static void mt792xu_wfdma_init(struct mt792x_dev *dev) { + int i; + mt792xu_dma_prefetch(dev); mt76_clear(dev, MT_UWFDMA0_GLO_CFG, MT_WFDMA0_GLO_CFG_OMIT_RX_INFO); @@ -169,10 +150,27 @@ static void mt792xu_wfdma_init(struct mt792x_dev *dev) MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN); - /* disable dmashdl */ - mt76_clear(dev, MT_UWFDMA0_GLO_CFG_EXT0, - MT_WFDMA0_CSR_TX_DMASHDL_ENABLE); - mt76_set(dev, MT_DMASHDL_SW_CONTROL, MT_DMASHDL_DMASHDL_BYPASS); + mt76_rmw(dev, MT_DMASHDL_REFILL, MT_DMASHDL_REFILL_MASK, 0xffe00000); + mt76_clear(dev, MT_DMASHDL_PAGE, MT_DMASHDL_GROUP_SEQ_ORDER); + mt76_rmw(dev, MT_DMASHDL_PKT_MAX_SIZE, + MT_DMASHDL_PKT_MAX_SIZE_PLE | MT_DMASHDL_PKT_MAX_SIZE_PSE, + FIELD_PREP(MT_DMASHDL_PKT_MAX_SIZE_PLE, 1) | + FIELD_PREP(MT_DMASHDL_PKT_MAX_SIZE_PSE, 0)); + for (i = 0; i < 5; i++) + mt76_wr(dev, MT_DMASHDL_GROUP_QUOTA(i), + FIELD_PREP(MT_DMASHDL_GROUP_QUOTA_MIN, 0x3) | + FIELD_PREP(MT_DMASHDL_GROUP_QUOTA_MAX, 0xfff)); + for (i = 5; i < 16; i++) + mt76_wr(dev, MT_DMASHDL_GROUP_QUOTA(i), + FIELD_PREP(MT_DMASHDL_GROUP_QUOTA_MIN, 0x0) | + FIELD_PREP(MT_DMASHDL_GROUP_QUOTA_MAX, 0x0)); + mt76_wr(dev, MT_DMASHDL_Q_MAP(0), 0x32013201); + mt76_wr(dev, MT_DMASHDL_Q_MAP(1), 0x32013201); + mt76_wr(dev, MT_DMASHDL_Q_MAP(2), 0x55555444); + mt76_wr(dev, MT_DMASHDL_Q_MAP(3), 0x55555444); + + mt76_wr(dev, MT_DMASHDL_SCHED_SET(0), 0x76540132); + mt76_wr(dev, MT_DMASHDL_SCHED_SET(1), 0xFEDCBA98); mt76_set(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c index 483ad81b6eec..73e633d0d700 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c @@ -237,7 +237,8 @@ void mt7996_dma_start(struct mt7996_dev *dev, bool reset, bool wed_reset) MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN | MT_WFDMA0_GLO_CFG_OMIT_TX_INFO | - MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2); + MT_WFDMA0_GLO_CFG_OMIT_RX_INFO_PFET2 | + MT_WFDMA0_GLO_CFG_EXT_EN); if (dev->hif2) mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, @@ -694,7 +695,7 @@ void mt7996_dma_reset(struct mt7996_dev *dev, bool force) mtk_wed_device_dma_reset(&dev->mt76.mmio.wed); mt7996_dma_disable(dev, force); - mt76_dma_wed_reset(&dev->mt76); + mt76_wed_dma_reset(&dev->mt76); /* reset hw queues */ for (i = 0; i < __MT_TXQ_MAX; i++) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c index 0cf0d1fe420a..283df84f1b43 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c @@ -493,7 +493,7 @@ static void mt7996_mac_init_basic_rates(struct mt7996_dev *dev) void mt7996_mac_init(struct mt7996_dev *dev) { -#define HIF_TXD_V2_1 4 +#define HIF_TXD_V2_1 0x21 int i; mt76_clear(dev, MT_MDP_DCR2, MT_MDP_DCR2_RX_TRANS_SHORT); @@ -507,11 +507,6 @@ void mt7996_mac_init(struct mt7996_dev *dev) mt76_rmw_field(dev, i, MT_LED_GPIO_SEL_MASK, 4); } - /* txs report queue */ - mt76_rmw_field(dev, MT_DMA_TCRF1(0), MT_DMA_TCRF1_QIDX, 0); - mt76_rmw_field(dev, MT_DMA_TCRF1(1), MT_DMA_TCRF1_QIDX, 6); - mt76_rmw_field(dev, MT_DMA_TCRF1(2), MT_DMA_TCRF1_QIDX, 0); - /* rro module init */ if (is_mt7996(&dev->mt76)) mt7996_mcu_set_rro(dev, UNI_RRO_SET_PLATFORM_TYPE, 2); @@ -1012,11 +1007,12 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy, /* the maximum cap is 4 x 3, (Nr, Nc) = (3, 2) */ elem->phy_cap_info[7] |= min_t(int, sts - 1, 2) << 3; - if (vif != NL80211_IFTYPE_AP) + if (!(vif == NL80211_IFTYPE_AP || vif == NL80211_IFTYPE_STATION)) return; elem->phy_cap_info[3] |= IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER; - elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; + if (vif == NL80211_IFTYPE_AP) + elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; c = FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK, sts - 1) | diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 53258488d49f..0384fb059ddf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -732,6 +732,9 @@ mt7996_mac_write_txwi_8023(struct mt7996_dev *dev, __le32 *txwi, FIELD_PREP(MT_TXD2_SUB_TYPE, fc_stype); txwi[2] |= cpu_to_le32(val); + + if (wcid->amsdu) + txwi[3] |= cpu_to_le32(MT_TXD3_HW_AMSDU); } static void @@ -862,8 +865,6 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, val |= MT_TXD3_PROTECT_FRAME; if (info->flags & IEEE80211_TX_CTL_NO_ACK) val |= MT_TXD3_NO_ACK; - if (wcid->amsdu) - val |= MT_TXD3_HW_AMSDU; txwi[3] = cpu_to_le32(val); txwi[4] = 0; @@ -1188,25 +1189,28 @@ mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid, struct ieee80211_tx_info *info; struct sk_buff_head list; struct rate_info rate = {}; - struct sk_buff *skb; + struct sk_buff *skb = NULL; bool cck = false; u32 txrate, txs, mode, stbc; txs = le32_to_cpu(txs_data[0]); mt76_tx_status_lock(mdev, &list); - skb = mt76_tx_status_skb_get(mdev, wcid, pid, &list); - if (skb) { - info = IEEE80211_SKB_CB(skb); - if (!(txs & MT_TXS0_ACK_ERROR_MASK)) - info->flags |= IEEE80211_TX_STAT_ACK; + /* only report MPDU TXS */ + if (le32_get_bits(txs_data[0], MT_TXS0_TXS_FORMAT) == 0) { + skb = mt76_tx_status_skb_get(mdev, wcid, pid, &list); + if (skb) { + info = IEEE80211_SKB_CB(skb); + if (!(txs & MT_TXS0_ACK_ERROR_MASK)) + info->flags |= IEEE80211_TX_STAT_ACK; - info->status.ampdu_len = 1; - info->status.ampdu_ack_len = - !!(info->flags & IEEE80211_TX_STAT_ACK); + info->status.ampdu_len = 1; + info->status.ampdu_ack_len = + !!(info->flags & IEEE80211_TX_STAT_ACK); - info->status.rates[0].idx = -1; + info->status.rates[0].idx = -1; + } } if (mtk_wed_device_active(&dev->mt76.mmio.wed) && wcid->sta) { @@ -2527,6 +2531,34 @@ static int mt7996_mac_check_twt_req(struct ieee80211_twt_setup *twt) return 0; } +static bool +mt7996_mac_twt_param_equal(struct mt7996_sta *msta, + struct ieee80211_twt_params *twt_agrt) +{ + u16 type = le16_to_cpu(twt_agrt->req_type); + u8 exp; + int i; + + exp = FIELD_GET(IEEE80211_TWT_REQTYPE_WAKE_INT_EXP, type); + for (i = 0; i < MT7996_MAX_STA_TWT_AGRT; i++) { + struct mt7996_twt_flow *f; + + if (!(msta->twt.flowid_mask & BIT(i))) + continue; + + f = &msta->twt.flow[i]; + if (f->duration == twt_agrt->min_twt_dur && + f->mantissa == twt_agrt->mantissa && + f->exp == exp && + f->protection == !!(type & IEEE80211_TWT_REQTYPE_PROTECTION) && + f->flowtype == !!(type & IEEE80211_TWT_REQTYPE_FLOWTYPE) && + f->trigger == !!(type & IEEE80211_TWT_REQTYPE_TRIGGER)) + return true; + } + + return false; +} + void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, struct ieee80211_sta *sta, struct ieee80211_twt_setup *twt) @@ -2538,8 +2570,7 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, enum ieee80211_twt_setup_cmd sta_setup_cmd; struct mt7996_dev *dev = mt7996_hw_dev(hw); struct mt7996_twt_flow *flow; - int flowid, table_id; - u8 exp; + u8 flowid, table_id, exp; if (mt7996_mac_check_twt_req(twt)) goto out; @@ -2552,9 +2583,19 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, if (hweight8(msta->twt.flowid_mask) == ARRAY_SIZE(msta->twt.flow)) goto unlock; + if (twt_agrt->min_twt_dur < MT7996_MIN_TWT_DUR) { + setup_cmd = TWT_SETUP_CMD_DICTATE; + twt_agrt->min_twt_dur = MT7996_MIN_TWT_DUR; + goto unlock; + } + + if (mt7996_mac_twt_param_equal(msta, twt_agrt)) + goto unlock; + flowid = ffs(~msta->twt.flowid_mask) - 1; - le16p_replace_bits(&twt_agrt->req_type, flowid, - IEEE80211_TWT_REQTYPE_FLOWID); + twt_agrt->req_type &= ~cpu_to_le16(IEEE80211_TWT_REQTYPE_FLOWID); + twt_agrt->req_type |= le16_encode_bits(flowid, + IEEE80211_TWT_REQTYPE_FLOWID); table_id = ffs(~dev->twt.table_mask) - 1; exp = FIELD_GET(IEEE80211_TWT_REQTYPE_WAKE_INT_EXP, req_type); @@ -2601,10 +2642,10 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw, unlock: mutex_unlock(&dev->mt76.mutex); out: - le16p_replace_bits(&twt_agrt->req_type, setup_cmd, - IEEE80211_TWT_REQTYPE_SETUP_CMD); - twt->control = (twt->control & IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT) | - (twt->control & IEEE80211_TWT_CONTROL_RX_DISABLED); + twt_agrt->req_type &= ~cpu_to_le16(IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt_agrt->req_type |= + le16_encode_bits(setup_cmd, IEEE80211_TWT_REQTYPE_SETUP_CMD); + twt->control = twt->control & IEEE80211_TWT_CONTROL_RX_DISABLED; } void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 234e6495871b..f7da8d6dd903 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -350,9 +350,12 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_SMS4: + break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: - break; + if (key->keyidx == 6 || key->keyidx == 7) + break; + fallthrough; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: default: @@ -1499,6 +1502,6 @@ const struct ieee80211_ops mt7996_ops = { .set_radar_background = mt7996_set_radar_background, #ifdef CONFIG_NET_MEDIATEK_SOC_WED .net_fill_forward_path = mt7996_net_fill_forward_path, - .net_setup_tc = mt76_net_setup_tc, + .net_setup_tc = mt76_wed_net_setup_tc, #endif }; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 3ec813077dc2..b44abe2acc81 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -732,13 +732,10 @@ void mt7996_mcu_rx_event(struct mt7996_dev *dev, struct sk_buff *skb) static struct tlv * mt7996_mcu_add_uni_tlv(struct sk_buff *skb, u16 tag, u16 len) { - struct tlv *ptlv, tlv = { - .tag = cpu_to_le16(tag), - .len = cpu_to_le16(len), - }; + struct tlv *ptlv = skb_put(skb, len); - ptlv = skb_put(skb, len); - memcpy(ptlv, &tlv, sizeof(tlv)); + ptlv->tag = cpu_to_le16(tag); + ptlv->len = cpu_to_le16(len); return ptlv; } @@ -1240,6 +1237,9 @@ mt7996_mcu_sta_he_6g_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) static void mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) { + struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv; + struct ieee80211_vif *vif = container_of((void *)msta->vif, + struct ieee80211_vif, drv_priv); struct ieee80211_eht_mcs_nss_supp *mcs_map; struct ieee80211_eht_cap_elem_fixed *elem; struct sta_rec_eht *eht; @@ -1259,8 +1259,17 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) eht->phy_cap = cpu_to_le64(*(u64 *)elem->phy_cap_info); eht->phy_cap_ext = cpu_to_le64(elem->phy_cap_info[8]); - if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20) - memcpy(eht->mcs_map_bw20, &mcs_map->only_20mhz, sizeof(eht->mcs_map_bw20)); + if (vif->type != NL80211_IFTYPE_STATION && + (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] & + (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)) == 0) { + memcpy(eht->mcs_map_bw20, &mcs_map->only_20mhz, + sizeof(eht->mcs_map_bw20)); + return; + } + memcpy(eht->mcs_map_bw80, &mcs_map->bw._80, sizeof(eht->mcs_map_bw80)); memcpy(eht->mcs_map_bw160, &mcs_map->bw._160, sizeof(eht->mcs_map_bw160)); memcpy(eht->mcs_map_bw320, &mcs_map->bw._320, sizeof(eht->mcs_map_bw320)); @@ -2510,7 +2519,7 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, info = IEEE80211_SKB_CB(skb); info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->mt76->band_idx); - len = sizeof(*bcn) + MT_TXD_SIZE + skb->len; + len = ALIGN(sizeof(*bcn) + MT_TXD_SIZE + skb->len, 4); tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_BCN_CONTENT, len); bcn = (struct bss_bcn_content_tlv *)tlv; bcn->enable = en; @@ -2579,8 +2588,7 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev, info->band = band; info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->mt76->band_idx); - len = sizeof(*discov) + MT_TXD_SIZE + skb->len; - + len = ALIGN(sizeof(*discov) + MT_TXD_SIZE + skb->len, 4); tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_OFFLOAD, len); discov = (struct bss_inband_discovery_tlv *)tlv; @@ -3539,7 +3547,7 @@ int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset) u32 addr = le32_to_cpu(*(__le32 *)(skb->data + 12)); u8 *buf = (u8 *)dev->mt76.eeprom.data + addr; - skb_pull(skb, 64); + skb_pull(skb, 48); memcpy(buf, skb->data, MT7996_EEPROM_BLOCK_SIZE); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h index 36cacc495c75..43468bcaffc6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h @@ -800,10 +800,10 @@ enum { sizeof(struct sta_rec_hdr_trans) + \ sizeof(struct tlv)) -#define MT7996_MAX_BEACON_SIZE 1342 +#define MT7996_MAX_BEACON_SIZE 1338 #define MT7996_BEACON_UPDATE_SIZE (sizeof(struct bss_req_hdr) + \ sizeof(struct bss_bcn_content_tlv) + \ - MT_TXD_SIZE + \ + 4 + MT_TXD_SIZE + \ sizeof(struct bss_bcn_cntdwn_tlv) + \ sizeof(struct bss_bcn_mbss_tlv)) #define MT7996_MAX_BSS_OFFLOAD_SIZE (MT7996_MAX_BEACON_SIZE + \ diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c index 9f2abfa273c9..304e5fd14803 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c @@ -140,7 +140,6 @@ static u32 mt7996_reg_map_l1(struct mt7996_dev *dev, u32 addr) u32 offset = FIELD_GET(MT_HIF_REMAP_L1_OFFSET, addr); u32 base = FIELD_GET(MT_HIF_REMAP_L1_BASE, addr); - dev->reg_l1_backup = dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L1); dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L1, MT_HIF_REMAP_L1_MASK, FIELD_PREP(MT_HIF_REMAP_L1_MASK, base)); @@ -155,7 +154,6 @@ static u32 mt7996_reg_map_l2(struct mt7996_dev *dev, u32 addr) u32 offset = FIELD_GET(MT_HIF_REMAP_L2_OFFSET, addr); u32 base = FIELD_GET(MT_HIF_REMAP_L2_BASE, addr); - dev->reg_l2_backup = dev->bus_ops->rr(&dev->mt76, MT_HIF_REMAP_L2); dev->bus_ops->rmw(&dev->mt76, MT_HIF_REMAP_L2, MT_HIF_REMAP_L2_MASK, FIELD_PREP(MT_HIF_REMAP_L2_MASK, base)); @@ -165,26 +163,10 @@ static u32 mt7996_reg_map_l2(struct mt7996_dev *dev, u32 addr) return MT_HIF_REMAP_BASE_L2 + offset; } -static void mt7996_reg_remap_restore(struct mt7996_dev *dev) -{ - /* remap to ori status */ - if (unlikely(dev->reg_l1_backup)) { - dev->bus_ops->wr(&dev->mt76, MT_HIF_REMAP_L1, dev->reg_l1_backup); - dev->reg_l1_backup = 0; - } - - if (dev->reg_l2_backup) { - dev->bus_ops->wr(&dev->mt76, MT_HIF_REMAP_L2, dev->reg_l2_backup); - dev->reg_l2_backup = 0; - } -} - static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr) { int i; - mt7996_reg_remap_restore(dev); - if (addr < 0x100000) return addr; @@ -201,6 +183,11 @@ static u32 __mt7996_reg_addr(struct mt7996_dev *dev, u32 addr) return dev->reg.map[i].mapped + ofs; } + return 0; +} + +static u32 __mt7996_reg_remap_addr(struct mt7996_dev *dev, u32 addr) +{ if ((addr >= MT_INFRA_BASE && addr < MT_WFSYS0_PHY_START) || (addr >= MT_WFSYS0_PHY_START && addr < MT_WFSYS1_PHY_START) || (addr >= MT_WFSYS1_PHY_START && addr <= MT_WFSYS1_PHY_END)) @@ -225,28 +212,60 @@ void mt7996_memcpy_fromio(struct mt7996_dev *dev, void *buf, u32 offset, { u32 addr = __mt7996_reg_addr(dev, offset); - memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + if (addr) { + memcpy_fromio(buf, dev->mt76.mmio.regs + addr, len); + return; + } + + spin_lock_bh(&dev->reg_lock); + memcpy_fromio(buf, dev->mt76.mmio.regs + + __mt7996_reg_remap_addr(dev, offset), len); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7996_rr(struct mt76_dev *mdev, u32 offset) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset), val; + + if (addr) + return dev->bus_ops->rr(mdev, addr); - return dev->bus_ops->rr(mdev, __mt7996_reg_addr(dev, offset)); + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rr(mdev, __mt7996_reg_remap_addr(dev, offset)); + spin_unlock_bh(&dev->reg_lock); + + return val; } static void mt7996_wr(struct mt76_dev *mdev, u32 offset, u32 val) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset); - dev->bus_ops->wr(mdev, __mt7996_reg_addr(dev, offset), val); + if (addr) { + dev->bus_ops->wr(mdev, addr, val); + return; + } + + spin_lock_bh(&dev->reg_lock); + dev->bus_ops->wr(mdev, __mt7996_reg_remap_addr(dev, offset), val); + spin_unlock_bh(&dev->reg_lock); } static u32 mt7996_rmw(struct mt76_dev *mdev, u32 offset, u32 mask, u32 val) { struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76); + u32 addr = __mt7996_reg_addr(dev, offset); + + if (addr) + return dev->bus_ops->rmw(mdev, addr, mask, val); + + spin_lock_bh(&dev->reg_lock); + val = dev->bus_ops->rmw(mdev, __mt7996_reg_remap_addr(dev, offset), mask, val); + spin_unlock_bh(&dev->reg_lock); - return dev->bus_ops->rmw(mdev, __mt7996_reg_addr(dev, offset), mask, val); + return val; } #ifdef CONFIG_NET_MEDIATEK_SOC_WED @@ -391,13 +410,13 @@ int mt7996_mmio_wed_init(struct mt7996_dev *dev, void *pdev_ptr, wed->wlan.amsdu_max_len = 1536; wed->wlan.init_buf = mt7996_wed_init_buf; - wed->wlan.init_rx_buf = mt76_mmio_wed_init_rx_buf; - wed->wlan.release_rx_buf = mt76_mmio_wed_release_rx_buf; - wed->wlan.offload_enable = mt76_mmio_wed_offload_enable; - wed->wlan.offload_disable = mt76_mmio_wed_offload_disable; + wed->wlan.init_rx_buf = mt76_wed_init_rx_buf; + wed->wlan.release_rx_buf = mt76_wed_release_rx_buf; + wed->wlan.offload_enable = mt76_wed_offload_enable; + wed->wlan.offload_disable = mt76_wed_offload_disable; if (!hif2) { wed->wlan.reset = mt7996_mmio_wed_reset; - wed->wlan.reset_complete = mt76_mmio_wed_reset_complete; + wed->wlan.reset_complete = mt76_wed_reset_complete; } if (mtk_wed_device_attach(wed)) @@ -421,6 +440,7 @@ static int mt7996_mmio_init(struct mt76_dev *mdev, dev = container_of(mdev, struct mt7996_dev, mt76); mt76_mmio_init(&dev->mt76, mem_base); + spin_lock_init(&dev->reg_lock); switch (device_id) { case 0x7990: diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index bc73bcb47bf0..36d1f247d55a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -53,6 +53,7 @@ #define MT7996_MAX_TWT_AGRT 16 #define MT7996_MAX_STA_TWT_AGRT 8 +#define MT7996_MIN_TWT_DUR 64 #define MT7996_MAX_QUEUE (__MT_RXQ_MAX + __MT_MCUQ_MAX + 3) /* NOTE: used to map mt76_rates. idx may change if firmware expands table */ @@ -320,12 +321,11 @@ struct mt7996_dev { struct rchan *relay_fwlog; struct { - u8 table_mask; + u16 table_mask; u8 n_agrt; } twt; - u32 reg_l1_backup; - u32 reg_l2_backup; + spinlock_t reg_lock; u8 wtbl_size_group; }; diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 5a0bcb5071bd..342c3aea549d 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -767,7 +767,7 @@ static void mt76u_status_worker(struct mt76_worker *w) if (!test_bit(MT76_STATE_RUNNING, &dev->phy.state)) return; - for (i = 0; i < IEEE80211_NUM_ACS; i++) { + for (i = 0; i <= MT_TXQ_PSD; i++) { q = dev->phy.q_tx[i]; if (!q) continue; @@ -872,9 +872,8 @@ mt76u_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, if (err < 0) return err; - mt76u_fill_bulk_urb(dev, USB_DIR_OUT, q2ep(q->hw_idx), - q->entry[idx].urb, mt76u_complete_tx, - &q->entry[idx]); + mt76u_fill_bulk_urb(dev, USB_DIR_OUT, q->ep, q->entry[idx].urb, + mt76u_complete_tx, &q->entry[idx]); q->head = (q->head + 1) % q->ndesc; q->entry[idx].skb = tx_info.skb; @@ -906,9 +905,13 @@ static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q) } } -static u8 mt76u_ac_to_hwq(struct mt76_dev *dev, u8 ac) +static void +mt76u_ac_to_hwq(struct mt76_dev *dev, struct mt76_queue *q, u8 qid) { - if (mt76_chip(dev) == 0x7663) { + u8 ac = qid < IEEE80211_NUM_ACS ? qid : IEEE80211_AC_BE; + + switch (mt76_chip(dev)) { + case 0x7663: { static const u8 lmac_queue_map[] = { /* ac to lmac mapping */ [IEEE80211_AC_BK] = 0, @@ -917,33 +920,36 @@ static u8 mt76u_ac_to_hwq(struct mt76_dev *dev, u8 ac) [IEEE80211_AC_VO] = 4, }; - if (WARN_ON(ac >= ARRAY_SIZE(lmac_queue_map))) - return 1; /* BE */ - - return lmac_queue_map[ac]; + q->hw_idx = lmac_queue_map[ac]; + q->ep = q->hw_idx + 1; + break; + } + case 0x7961: + case 0x7925: + q->hw_idx = mt76_ac_to_hwq(ac); + q->ep = qid == MT_TXQ_PSD ? MT_EP_OUT_HCCA : q->hw_idx + 1; + break; + default: + q->hw_idx = mt76_ac_to_hwq(ac); + q->ep = q->hw_idx + 1; + break; } - - return mt76_ac_to_hwq(ac); } static int mt76u_alloc_tx(struct mt76_dev *dev) { - struct mt76_queue *q; - int i, j, err; + int i; for (i = 0; i <= MT_TXQ_PSD; i++) { - if (i >= IEEE80211_NUM_ACS) { - dev->phy.q_tx[i] = dev->phy.q_tx[0]; - continue; - } + struct mt76_queue *q; + int j, err; q = devm_kzalloc(dev->dev, sizeof(*q), GFP_KERNEL); if (!q) return -ENOMEM; spin_lock_init(&q->lock); - q->hw_idx = mt76u_ac_to_hwq(dev, i); - + mt76u_ac_to_hwq(dev, q, i); dev->phy.q_tx[i] = q; q->entry = devm_kcalloc(dev->dev, @@ -969,7 +975,7 @@ static void mt76u_free_tx(struct mt76_dev *dev) mt76_worker_teardown(&dev->usb.status_worker); - for (i = 0; i < IEEE80211_NUM_ACS; i++) { + for (i = 0; i <= MT_TXQ_PSD; i++) { struct mt76_queue *q; int j; @@ -999,7 +1005,7 @@ void mt76u_stop_tx(struct mt76_dev *dev) dev_err(dev->dev, "timed out waiting for pending tx\n"); - for (i = 0; i < IEEE80211_NUM_ACS; i++) { + for (i = 0; i <= MT_TXQ_PSD; i++) { q = dev->phy.q_tx[i]; if (!q) continue; @@ -1013,7 +1019,7 @@ void mt76u_stop_tx(struct mt76_dev *dev) /* On device removal we maight queue skb's, but mt76u_tx_kick() * will fail to submit urb, cleanup those skb's manually. */ - for (i = 0; i < IEEE80211_NUM_ACS; i++) { + for (i = 0; i <= MT_TXQ_PSD; i++) { q = dev->phy.q_tx[i]; if (!q) continue; diff --git a/drivers/net/wireless/mediatek/mt76/wed.c b/drivers/net/wireless/mediatek/mt76/wed.c new file mode 100644 index 000000000000..f89e4537555c --- /dev/null +++ b/drivers/net/wireless/mediatek/mt76/wed.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: ISC +/* + * Copyright (C) 2023 Lorenzo Bianconi <lorenzo@kernel.org> + */ + +#include "mt76.h" +#include "dma.h" + +void mt76_wed_release_rx_buf(struct mtk_wed_device *wed) +{ + struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + int i; + + for (i = 0; i < dev->rx_token_size; i++) { + struct mt76_txwi_cache *t; + + t = mt76_rx_token_release(dev, i); + if (!t || !t->ptr) + continue; + + mt76_put_page_pool_buf(t->ptr, false); + t->ptr = NULL; + + mt76_put_rxwi(dev, t); + } + + mt76_free_pending_rxwi(dev); +} +EXPORT_SYMBOL_GPL(mt76_wed_release_rx_buf); + +#ifdef CONFIG_NET_MEDIATEK_SOC_WED +u32 mt76_wed_init_rx_buf(struct mtk_wed_device *wed, int size) +{ + struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + struct mtk_wed_bm_desc *desc = wed->rx_buf_ring.desc; + struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN]; + int i, len = SKB_WITH_OVERHEAD(q->buf_size); + struct mt76_txwi_cache *t = NULL; + + for (i = 0; i < size; i++) { + enum dma_data_direction dir; + dma_addr_t addr; + u32 offset; + int token; + void *buf; + + t = mt76_get_rxwi(dev); + if (!t) + goto unmap; + + buf = mt76_get_page_pool_buf(q, &offset, q->buf_size); + if (!buf) + goto unmap; + + addr = page_pool_get_dma_addr(virt_to_head_page(buf)) + offset; + dir = page_pool_get_dma_dir(q->page_pool); + dma_sync_single_for_device(dev->dma_dev, addr, len, dir); + + desc->buf0 = cpu_to_le32(addr); + token = mt76_rx_token_consume(dev, buf, t, addr); + if (token < 0) { + mt76_put_page_pool_buf(buf, false); + goto unmap; + } + + token = FIELD_PREP(MT_DMA_CTL_TOKEN, token); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + token |= FIELD_PREP(MT_DMA_CTL_SDP0_H, addr >> 32); +#endif + desc->token |= cpu_to_le32(token); + desc++; + } + + return 0; + +unmap: + if (t) + mt76_put_rxwi(dev, t); + mt76_wed_release_rx_buf(wed); + + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(mt76_wed_init_rx_buf); + +int mt76_wed_offload_enable(struct mtk_wed_device *wed) +{ + struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + + spin_lock_bh(&dev->token_lock); + dev->token_size = wed->wlan.token_start; + spin_unlock_bh(&dev->token_lock); + + return !wait_event_timeout(dev->tx_wait, !dev->wed_token_count, HZ); +} +EXPORT_SYMBOL_GPL(mt76_wed_offload_enable); + +int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q, bool reset) +{ + int ret = 0, type, ring; + u16 flags; + + if (!q || !q->ndesc) + return -EINVAL; + + flags = q->flags; + if (!q->wed || !mtk_wed_device_active(q->wed)) + q->flags &= ~MT_QFLAG_WED; + + if (!(q->flags & MT_QFLAG_WED)) + return 0; + + type = FIELD_GET(MT_QFLAG_WED_TYPE, q->flags); + ring = FIELD_GET(MT_QFLAG_WED_RING, q->flags); + + switch (type) { + case MT76_WED_Q_TX: + ret = mtk_wed_device_tx_ring_setup(q->wed, ring, q->regs, + reset); + if (!ret) + q->wed_regs = q->wed->tx_ring[ring].reg_base; + break; + case MT76_WED_Q_TXFREE: + /* WED txfree queue needs ring to be initialized before setup */ + q->flags = 0; + mt76_dma_queue_reset(dev, q); + mt76_dma_rx_fill(dev, q, false); + + ret = mtk_wed_device_txfree_ring_setup(q->wed, q->regs); + if (!ret) + q->wed_regs = q->wed->txfree_ring.reg_base; + break; + case MT76_WED_Q_RX: + ret = mtk_wed_device_rx_ring_setup(q->wed, ring, q->regs, + reset); + if (!ret) + q->wed_regs = q->wed->rx_ring[ring].reg_base; + break; + case MT76_WED_RRO_Q_DATA: + q->flags &= ~MT_QFLAG_WED; + __mt76_dma_queue_reset(dev, q, false); + mtk_wed_device_rro_rx_ring_setup(q->wed, ring, q->regs); + q->head = q->ndesc - 1; + q->queued = q->head; + break; + case MT76_WED_RRO_Q_MSDU_PG: + q->flags &= ~MT_QFLAG_WED; + __mt76_dma_queue_reset(dev, q, false); + mtk_wed_device_msdu_pg_rx_ring_setup(q->wed, ring, q->regs); + q->head = q->ndesc - 1; + q->queued = q->head; + break; + case MT76_WED_RRO_Q_IND: + q->flags &= ~MT_QFLAG_WED; + mt76_dma_queue_reset(dev, q); + mt76_dma_rx_fill(dev, q, false); + mtk_wed_device_ind_rx_ring_setup(q->wed, q->regs); + break; + default: + ret = -EINVAL; + break; + } + q->flags = flags; + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_wed_dma_setup); +#endif /*CONFIG_NET_MEDIATEK_SOC_WED */ + +void mt76_wed_offload_disable(struct mtk_wed_device *wed) +{ + struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + + spin_lock_bh(&dev->token_lock); + dev->token_size = dev->drv->token_size; + spin_unlock_bh(&dev->token_lock); +} +EXPORT_SYMBOL_GPL(mt76_wed_offload_disable); + +void mt76_wed_reset_complete(struct mtk_wed_device *wed) +{ + struct mt76_dev *dev = container_of(wed, struct mt76_dev, mmio.wed); + + complete(&dev->mmio.wed_reset_complete); +} +EXPORT_SYMBOL_GPL(mt76_wed_reset_complete); + +int mt76_wed_net_setup_tc(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct net_device *netdev, enum tc_setup_type type, + void *type_data) +{ + struct mt76_phy *phy = hw->priv; + struct mtk_wed_device *wed = &phy->dev->mmio.wed; + + if (!mtk_wed_device_active(wed)) + return -EOPNOTSUPP; + + return mtk_wed_device_setup_tc(wed, netdev, type, type_data); +} +EXPORT_SYMBOL_GPL(mt76_wed_net_setup_tc); + +void mt76_wed_dma_reset(struct mt76_dev *dev) +{ + struct mt76_mmio *mmio = &dev->mmio; + + if (!test_bit(MT76_STATE_WED_RESET, &dev->phy.state)) + return; + + complete(&mmio->wed_reset); + + if (!wait_for_completion_timeout(&mmio->wed_reset_complete, 3 * HZ)) + dev_err(dev->dev, "wed reset complete timeout\n"); +} +EXPORT_SYMBOL_GPL(mt76_wed_dma_reset); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index aaf31857ae1e..3bb81bcff0ac 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -10946,13 +10946,13 @@ static void rt2800_efuse_read(struct rt2x00_dev *rt2x00dev, unsigned int i) /* Apparently the data is read from end to start */ reg = rt2800_register_read_lock(rt2x00dev, efuse_data3_reg); /* The returned value is in CPU order, but eeprom is le */ - *(u32 *)&rt2x00dev->eeprom[i] = cpu_to_le32(reg); + *(__le32 *)&rt2x00dev->eeprom[i] = cpu_to_le32(reg); reg = rt2800_register_read_lock(rt2x00dev, efuse_data2_reg); - *(u32 *)&rt2x00dev->eeprom[i + 2] = cpu_to_le32(reg); + *(__le32 *)&rt2x00dev->eeprom[i + 2] = cpu_to_le32(reg); reg = rt2800_register_read_lock(rt2x00dev, efuse_data1_reg); - *(u32 *)&rt2x00dev->eeprom[i + 4] = cpu_to_le32(reg); + *(__le32 *)&rt2x00dev->eeprom[i + 4] = cpu_to_le32(reg); reg = rt2800_register_read_lock(rt2x00dev, efuse_data0_reg); - *(u32 *)&rt2x00dev->eeprom[i + 6] = cpu_to_le32(reg); + *(__le32 *)&rt2x00dev->eeprom[i + 6] = cpu_to_le32(reg); mutex_unlock(&rt2x00dev->csr_mutex); } diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index efddbe402f0d..4a49f8f9d80f 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -4919,11 +4919,11 @@ static void rtl8xxxu_set_aifs(struct rtl8xxxu_priv *priv, u8 slot_time) int i; for (i = 0; i < ARRAY_SIZE(priv->vifs); i++) { + struct ieee80211_sta *sta; + if (!priv->vifs[i]) continue; - struct ieee80211_sta *sta; - rcu_read_lock(); sta = ieee80211_find_sta(priv->vifs[i], priv->vifs[i]->bss_conf.bssid); if (sta) diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c index d059cfe5a2a9..11709b6c83f1 100644 --- a/drivers/net/wireless/realtek/rtlwifi/pci.c +++ b/drivers/net/wireless/realtek/rtlwifi/pci.c @@ -2374,7 +2374,6 @@ EXPORT_SYMBOL(rtl_pci_resume); #endif /* CONFIG_PM_SLEEP */ const struct rtl_intf_ops rtl_pci_ops = { - .read_efuse_byte = read_efuse_byte, .adapter_start = rtl_pci_start, .adapter_stop = rtl_pci_stop, .check_buddy_priv = rtl_pci_check_buddy_priv, diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c index 743ac6871bf4..4ba42f6be3f2 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/hw.c @@ -1669,10 +1669,8 @@ static void _rtl92de_efuse_update_chip_version(struct ieee80211_hw *hw) u8 cutvalue[2]; u16 chipvalue; - rtlpriv->intf_ops->read_efuse_byte(hw, EEPROME_CHIP_VERSION_H, - &cutvalue[1]); - rtlpriv->intf_ops->read_efuse_byte(hw, EEPROME_CHIP_VERSION_L, - &cutvalue[0]); + read_efuse_byte(hw, EEPROME_CHIP_VERSION_H, &cutvalue[1]); + read_efuse_byte(hw, EEPROME_CHIP_VERSION_L, &cutvalue[0]); chipvalue = (cutvalue[1] << 8) | cutvalue[0]; switch (chipvalue) { case 0xAA55: diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h index f388d13e2ba8..9fabf597cfd6 100644 --- a/drivers/net/wireless/realtek/rtlwifi/wifi.h +++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h @@ -2289,7 +2289,6 @@ struct rtl_hal_ops { struct rtl_intf_ops { /*com */ - void (*read_efuse_byte)(struct ieee80211_hw *hw, u16 _offset, u8 *pbuf); int (*adapter_start)(struct ieee80211_hw *hw); void (*adapter_stop)(struct ieee80211_hw *hw); bool (*check_buddy_priv)(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c index 298663b03580..0c1c1ff31085 100644 --- a/drivers/net/wireless/realtek/rtw88/mac.c +++ b/drivers/net/wireless/realtek/rtw88/mac.c @@ -309,6 +309,13 @@ static int rtw_mac_power_switch(struct rtw_dev *rtwdev, bool pwr_on) pwr_seq = pwr_on ? chip->pwr_on_seq : chip->pwr_off_seq; ret = rtw_pwr_seq_parser(rtwdev, pwr_seq); + if (pwr_on && rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB) { + if (chip->id == RTW_CHIP_TYPE_8822C || + chip->id == RTW_CHIP_TYPE_8822B || + chip->id == RTW_CHIP_TYPE_8821C) + rtw_write8_clr(rtwdev, REG_SYS_STATUS1 + 1, BIT(0)); + } + if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_SDIO) rtw_write32(rtwdev, REG_SDIO_HIMR, imr); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index 6d22628129d0..ffba6b88f392 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -2032,8 +2032,6 @@ static int rtw_chip_board_info_setup(struct rtw_dev *rtwdev) rtw_phy_setup_phy_cond(rtwdev, hal->pkg_type); rtw_phy_init_tx_power(rtwdev); - if (rfe_def->agc_btg_tbl) - rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_table(rtwdev, rfe_def->phy_pg_tbl); rtw_load_table(rtwdev, rfe_def->txpwr_lmt_tbl); rtw_phy_tx_power_by_rate_config(hal); diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c index 128e75a81bf3..37ef80c9091d 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.c +++ b/drivers/net/wireless/realtek/rtw88/phy.c @@ -1761,12 +1761,15 @@ static void rtw_load_rfk_table(struct rtw_dev *rtwdev) void rtw_phy_load_tables(struct rtw_dev *rtwdev) { + const struct rtw_rfe_def *rfe_def = rtw_get_rfe_def(rtwdev); const struct rtw_chip_info *chip = rtwdev->chip; u8 rf_path; rtw_load_table(rtwdev, chip->mac_tbl); rtw_load_table(rtwdev, chip->bb_tbl); rtw_load_table(rtwdev, chip->agc_tbl); + if (rfe_def->agc_btg_tbl) + rtw_load_table(rtwdev, rfe_def->agc_btg_tbl); rtw_load_rfk_table(rtwdev); for (rf_path = 0; rf_path < rtwdev->hal.rf_path_num; rf_path++) { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index 429bb420b056..fe5d8e188350 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -773,9 +773,9 @@ static void rtw8821c_false_alarm_statistics(struct rtw_dev *rtwdev) dm_info->cck_fa_cnt = cck_fa_cnt; dm_info->ofdm_fa_cnt = ofdm_fa_cnt; + dm_info->total_fa_cnt = ofdm_fa_cnt; if (cck_enable) dm_info->total_fa_cnt += cck_fa_cnt; - dm_info->total_fa_cnt = ofdm_fa_cnt; crc32_cnt = rtw_read32(rtwdev, REG_CRC_CCK); dm_info->cck_ok_cnt = FIELD_GET(GENMASK(15, 0), crc32_cnt); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c index 7a5cbdc31ef7..e2c7d9f87683 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c @@ -9,24 +9,36 @@ #include "usb.h" static const struct usb_device_id rtw_8821cu_id_table[] = { - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8731, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xb82b, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc80c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc820, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc821, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82a, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8821CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8811, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* 8811CU */ - { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x2006, 0xff, 0xff, 0xff), - .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* TOTOLINK A650UA v3 */ + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ + { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xd811, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* Edimax */ {}, }; MODULE_DEVICE_TABLE(usb, rtw_8821cu_id_table); diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c index e6ab1ac6d709..a0188511099a 100644 --- a/drivers/net/wireless/realtek/rtw88/usb.c +++ b/drivers/net/wireless/realtek/rtw88/usb.c @@ -33,6 +33,36 @@ static void rtw_usb_fill_tx_checksum(struct rtw_usb *rtwusb, rtw_tx_fill_txdesc_checksum(rtwdev, &pkt_info, skb->data); } +static void rtw_usb_reg_sec(struct rtw_dev *rtwdev, u32 addr, __le32 *data) +{ + struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); + struct usb_device *udev = rtwusb->udev; + bool reg_on_section = false; + u16 t_reg = 0x4e0; + u8 t_len = 1; + int status; + + /* There are three sections: + * 1. on (0x00~0xFF; 0x1000~0x10FF): this section is always powered on + * 2. off (< 0xFE00, excluding "on" section): this section could be + * powered off + * 3. local (>= 0xFE00): usb specific registers section + */ + if (addr <= 0xff || (addr >= 0x1000 && addr <= 0x10ff)) + reg_on_section = true; + + if (!reg_on_section) + return; + + status = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), + RTW_USB_CMD_REQ, RTW_USB_CMD_WRITE, + t_reg, 0, data, t_len, 500); + + if (status != t_len && status != -ENODEV) + rtw_err(rtwdev, "%s: reg 0x%x, usb write %u fail, status: %d\n", + __func__, t_reg, t_len, status); +} + static u32 rtw_usb_read(struct rtw_dev *rtwdev, u32 addr, u16 len) { struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); @@ -58,6 +88,11 @@ static u32 rtw_usb_read(struct rtw_dev *rtwdev, u32 addr, u16 len) rtw_err(rtwdev, "read register 0x%x failed with %d\n", addr, ret); + if (rtwdev->chip->id == RTW_CHIP_TYPE_8822C || + rtwdev->chip->id == RTW_CHIP_TYPE_8822B || + rtwdev->chip->id == RTW_CHIP_TYPE_8821C) + rtw_usb_reg_sec(rtwdev, addr, data); + return le32_to_cpu(*data); } @@ -102,6 +137,11 @@ static void rtw_usb_write(struct rtw_dev *rtwdev, u32 addr, u32 val, int len) if (ret < 0 && ret != -ENODEV && count++ < 4) rtw_err(rtwdev, "write register 0x%x failed with %d\n", addr, ret); + + if (rtwdev->chip->id == RTW_CHIP_TYPE_8822C || + rtwdev->chip->id == RTW_CHIP_TYPE_8822B || + rtwdev->chip->id == RTW_CHIP_TYPE_8821C) + rtw_usb_reg_sec(rtwdev, addr, data); } static void rtw_usb_write8(struct rtw_dev *rtwdev, u32 addr, u8 val) diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c index f37afb4cbb63..d9b66d43f32e 100644 --- a/drivers/net/wireless/realtek/rtw89/coex.c +++ b/drivers/net/wireless/realtek/rtw89/coex.c @@ -129,68 +129,75 @@ static const u32 cxtbl[] = { static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = { /* firmware version must be in decreasing order for each chip */ + {RTL8922A, RTW89_FW_VER_CODE(0, 35, 8, 0), + .fcxbtcrpt = 8, .fcxtdma = 7, .fcxslots = 7, .fcxcysta = 7, + .fcxstep = 7, .fcxnullsta = 7, .fcxmreg = 7, .fcxgpiodbg = 7, + .fcxbtver = 7, .fcxbtscan = 7, .fcxbtafh = 7, .fcxbtdevinfo = 7, + .fwlrole = 2, .frptmap = 7, .fcxctrl = 7, .fcxinit = 7, + .drvinfo_type = 1, .info_buf = 1800, .max_role_num = 6, + }, {RTL8851B, RTW89_FW_VER_CODE(0, 29, 29, 0), .fcxbtcrpt = 105, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 5, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 2, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 2, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 2, .frptmap = 3, .fcxctrl = 1, - .info_buf = 1800, .max_role_num = 6, + .fwlrole = 2, .frptmap = 3, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1800, .max_role_num = 6, }, {RTL8852C, RTW89_FW_VER_CODE(0, 27, 57, 0), .fcxbtcrpt = 4, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 3, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, - .info_buf = 1280, .max_role_num = 5, + .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1280, .max_role_num = 5, }, {RTL8852C, RTW89_FW_VER_CODE(0, 27, 42, 0), .fcxbtcrpt = 4, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 3, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 2, .fcxctrl = 1, - .info_buf = 1280, .max_role_num = 5, + .fwlrole = 1, .frptmap = 2, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1280, .max_role_num = 5, }, {RTL8852C, RTW89_FW_VER_CODE(0, 27, 0, 0), .fcxbtcrpt = 4, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 3, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 1, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 2, .fcxctrl = 1, - .info_buf = 1280, .max_role_num = 5, + .fwlrole = 1, .frptmap = 2, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1280, .max_role_num = 5, }, {RTL8852B, RTW89_FW_VER_CODE(0, 29, 29, 0), .fcxbtcrpt = 105, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 5, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 2, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 2, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 2, .frptmap = 3, .fcxctrl = 1, - .info_buf = 1800, .max_role_num = 6, + .fwlrole = 2, .frptmap = 3, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1800, .max_role_num = 6, }, {RTL8852B, RTW89_FW_VER_CODE(0, 29, 14, 0), .fcxbtcrpt = 5, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 4, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, - .info_buf = 1800, .max_role_num = 6, + .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1800, .max_role_num = 6, }, {RTL8852B, RTW89_FW_VER_CODE(0, 27, 0, 0), .fcxbtcrpt = 4, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 3, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 1, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 1, .fcxctrl = 1, - .info_buf = 1280, .max_role_num = 5, + .fwlrole = 1, .frptmap = 1, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1280, .max_role_num = 5, }, {RTL8852A, RTW89_FW_VER_CODE(0, 13, 37, 0), .fcxbtcrpt = 4, .fcxtdma = 3, .fcxslots = 1, .fcxcysta = 3, .fcxstep = 3, .fcxnullsta = 2, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 2, .fcxbtdevinfo = 1, - .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, - .info_buf = 1280, .max_role_num = 5, + .fwlrole = 1, .frptmap = 3, .fcxctrl = 1, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1280, .max_role_num = 5, }, {RTL8852A, RTW89_FW_VER_CODE(0, 13, 0, 0), .fcxbtcrpt = 1, .fcxtdma = 1, .fcxslots = 1, .fcxcysta = 2, .fcxstep = 2, .fcxnullsta = 1, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 1, .fcxbtdevinfo = 1, - .fwlrole = 0, .frptmap = 0, .fcxctrl = 0, - .info_buf = 1024, .max_role_num = 5, + .fwlrole = 0, .frptmap = 0, .fcxctrl = 0, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1024, .max_role_num = 5, }, /* keep it to be the last as default entry */ @@ -198,8 +205,8 @@ static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = { .fcxbtcrpt = 1, .fcxtdma = 1, .fcxslots = 1, .fcxcysta = 2, .fcxstep = 2, .fcxnullsta = 1, .fcxmreg = 1, .fcxgpiodbg = 1, .fcxbtver = 1, .fcxbtscan = 1, .fcxbtafh = 1, .fcxbtdevinfo = 1, - .fwlrole = 0, .frptmap = 0, .fcxctrl = 0, - .info_buf = 1024, .max_role_num = 5, + .fwlrole = 0, .frptmap = 0, .fcxctrl = 0, .fcxinit = 0, + .drvinfo_type = 0, .info_buf = 1024, .max_role_num = 5, }, }; @@ -351,17 +358,26 @@ enum btc_cx_poicy_type { /* TDMA off + pri: WL_Rx = BT, BT_HI > WL_Tx > BT_Lo */ BTC_CXP_OFF_EQ3 = (BTC_CXP_OFF << 8) | 5, + /* TDMA off + pri: WL_Rx = BT, BT_HI > WL_Tx > BT_Lo */ + BTC_CXP_OFF_EQ4 = (BTC_CXP_OFF << 8) | 6, + + /* TDMA off + pri: WL_Rx = BT, BT_HI > WL_Tx > BT_Lo */ + BTC_CXP_OFF_EQ5 = (BTC_CXP_OFF << 8) | 7, + /* TDMA off + pri: BT_Hi > WL > BT_Lo */ - BTC_CXP_OFF_BWB0 = (BTC_CXP_OFF << 8) | 6, + BTC_CXP_OFF_BWB0 = (BTC_CXP_OFF << 8) | 8, /* TDMA off + pri: WL_Hi-Tx > BT_Hi_Rx, BT_Hi > WL > BT_Lo */ - BTC_CXP_OFF_BWB1 = (BTC_CXP_OFF << 8) | 7, + BTC_CXP_OFF_BWB1 = (BTC_CXP_OFF << 8) | 9, /* TDMA off + pri: WL_Hi-Tx > BT, BT_Hi > other-WL > BT_Lo */ - BTC_CXP_OFF_BWB2 = (BTC_CXP_OFF << 8) | 8, + BTC_CXP_OFF_BWB2 = (BTC_CXP_OFF << 8) | 10, /* TDMA off + pri: WL_Hi-Tx = BT */ - BTC_CXP_OFF_BWB3 = (BTC_CXP_OFF << 8) | 9, + BTC_CXP_OFF_BWB3 = (BTC_CXP_OFF << 8) | 11, + + /* TDMA off + pri: WL > BT, Block-BT*/ + BTC_CXP_OFF_WL2 = (BTC_CXP_OFF << 8) | 12, /* TDMA off+Bcn-Protect + pri: WL_Hi-Tx > BT_Hi_Rx, BT_Hi > WL > BT_Lo*/ BTC_CXP_OFFB_BWB0 = (BTC_CXP_OFFB << 8) | 0, @@ -676,20 +692,25 @@ static void _run_coex(struct rtw89_dev *rtwdev, static void _write_scbd(struct rtw89_dev *rtwdev, u32 val, bool state); static void _update_bt_scbd(struct rtw89_dev *rtwdev, bool only_update); -static void _send_fw_cmd(struct rtw89_dev *rtwdev, u8 h2c_class, u8 h2c_func, - void *param, u16 len) +static int _send_fw_cmd(struct rtw89_dev *rtwdev, u8 h2c_class, u8 h2c_func, + void *param, u16 len) { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo; struct rtw89_btc_cx *cx = &btc->cx; struct rtw89_btc_wl_info *wl = &cx->wl; + struct rtw89_btc_dm *dm = &btc->dm; int ret; - if (!wl->status.map.init_ok) { + if (len > BTC_H2C_MAXLEN || len == 0) { + btc->fwinfo.cnt_h2c_fail++; + dm->error.map.h2c_buffer_over = true; + return -EINVAL; + } else if (!wl->status.map.init_ok) { rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): return by btc not init!!\n", __func__); pfwinfo->cnt_h2c_fail++; - return; + return -EINVAL; } else if ((wl->status.map.rf_off_pre == BTC_LPS_RF_OFF && wl->status.map.rf_off == BTC_LPS_RF_OFF) || (wl->status.map.lps_pre == BTC_LPS_RF_OFF && @@ -697,20 +718,23 @@ static void _send_fw_cmd(struct rtw89_dev *rtwdev, u8 h2c_class, u8 h2c_func, rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): return by wl off!!\n", __func__); pfwinfo->cnt_h2c_fail++; - return; + return -EINVAL; } - pfwinfo->cnt_h2c++; - ret = rtw89_fw_h2c_raw_with_hdr(rtwdev, h2c_class, h2c_func, param, len, false, true); - if (ret != 0) + if (ret) pfwinfo->cnt_h2c_fail++; + else + pfwinfo->cnt_h2c++; + + return ret; } static void _reset_btc_var(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; + const struct rtw89_btc_ver *ver = btc->ver; struct rtw89_btc_cx *cx = &btc->cx; struct rtw89_btc_wl_info *wl = &btc->cx.wl; struct rtw89_btc_bt_info *bt = &btc->cx.bt; @@ -728,7 +752,9 @@ static void _reset_btc_var(struct rtw89_dev *rtwdev, u8 type) if (type & BTC_RESET_CTRL) { memset(&btc->ctrl, 0, sizeof(btc->ctrl)); - btc->ctrl.trace_step = FCXDEF_STEP; + btc->manual_ctrl = false; + if (ver->fcxctrl != 7) + btc->ctrl.ctrl.trace_step = FCXDEF_STEP; } /* Init Coex variables that are not zero */ @@ -777,22 +803,27 @@ static void _get_reg_status(struct rtw89_dev *rtwdev, u8 type, u8 *val) { struct rtw89_btc *btc = &rtwdev->btc; const struct rtw89_btc_ver *ver = btc->ver; - struct rtw89_btc_module *md = &btc->mdinfo; + union rtw89_btc_module_info *md = &btc->mdinfo; union rtw89_btc_fbtc_mreg_val *pmreg; u32 pre_agc_addr = R_BTC_BB_PRE_AGC_S1; u32 reg_val; - u8 idx; + u8 idx, switch_type; - if (md->ant.btg_pos == RF_PATH_A) + if (ver->fcxinit == 7) + switch_type = md->md_v7.switch_type; + else + switch_type = md->md.switch_type; + + if (btc->btg_pos == RF_PATH_A) pre_agc_addr = R_BTC_BB_PRE_AGC_S0; switch (type) { case BTC_CSTATUS_TXDIV_POS: - if (md->switch_type == BTC_SWITCH_INTERNAL) + if (switch_type == BTC_SWITCH_INTERNAL) *val = BTC_ANT_DIV_MAIN; break; case BTC_CSTATUS_RXDIV_POS: - if (md->switch_type == BTC_SWITCH_INTERNAL) + if (switch_type == BTC_SWITCH_INTERNAL) *val = BTC_ANT_DIV_MAIN; break; case BTC_CSTATUS_BB_GNT_MUX: @@ -1117,7 +1148,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev, void *rpt_content = NULL, *pfinfo = NULL; u8 rpt_type = 0; u16 wl_slot_set = 0, wl_slot_real = 0; - u32 trace_step = btc->ctrl.trace_step, rpt_len = 0, diff_t = 0; + u32 trace_step = 0, rpt_len = 0, diff_t = 0; u32 cnt_leak_slot, bt_slot_real, bt_slot_set, cnt_rx_imr; u8 i, val = 0; @@ -1207,6 +1238,9 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev, break; case BTC_RPT_TYPE_STEP: pcinfo = &pfwinfo->rpt_fbtc_step.cinfo; + if (ver->fcxctrl != 7) + trace_step = btc->ctrl.ctrl.trace_step; + if (ver->fcxstep == 2) { pfinfo = &pfwinfo->rpt_fbtc_step.finfo.v2; pcinfo->req_len = sizeof(pfwinfo->rpt_fbtc_step.finfo.v2.step[0]) * @@ -1920,6 +1954,7 @@ static void rtw89_btc_fw_en_rpt(struct rtw89_dev *rtwdev, struct rtw89_btc_btf_fwinfo *fwinfo = &btc->fwinfo; struct rtw89_btc_btf_set_report r = {0}; u32 val, bit_map; + int ret; if ((wl_smap->rf_off || wl_smap->lps != BTC_LPS_OFF) && rpt_state != 0) return; @@ -1938,13 +1973,13 @@ static void rtw89_btc_fw_en_rpt(struct rtw89_dev *rtwdev, if (val == fwinfo->rpt_en_map) return; - fwinfo->rpt_en_map = val; - r.fver = BTF_SET_REPORT_VER; r.enable = cpu_to_le32(val); r.para = cpu_to_le32(rpt_state); - _send_fw_cmd(rtwdev, BTFC_SET, SET_REPORT_EN, &r, sizeof(r)); + ret = _send_fw_cmd(rtwdev, BTFC_SET, SET_REPORT_EN, &r, sizeof(r)); + if (!ret) + fwinfo->rpt_en_map = val; } static void rtw89_btc_fw_set_slots(struct rtw89_dev *rtwdev, u8 num, @@ -2032,6 +2067,7 @@ static void _fw_set_policy(struct rtw89_dev *rtwdev, u16 policy_type, { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_dm *dm = &btc->dm; + int ret; dm->run_action = action; @@ -2060,11 +2096,12 @@ static void _fw_set_policy(struct rtw89_dev *rtwdev, u16 policy_type, if (btc->lps == 1) rtw89_set_coex_ctrl_lps(rtwdev, btc->lps); - _send_fw_cmd(rtwdev, BTFC_SET, SET_CX_POLICY, - btc->policy, btc->policy_len); - - memcpy(&dm->tdma_now, &dm->tdma, sizeof(dm->tdma_now)); - memcpy(&dm->slot_now, &dm->slot, sizeof(dm->slot_now)); + ret = _send_fw_cmd(rtwdev, BTFC_SET, SET_CX_POLICY, + btc->policy, btc->policy_len); + if (!ret) { + memcpy(&dm->tdma_now, &dm->tdma, sizeof(dm->tdma_now)); + memcpy(&dm->slot_now, &dm->slot, sizeof(dm->slot_now)); + } if (btc->update_policy_force) btc->update_policy_force = false; @@ -2083,20 +2120,32 @@ static void _fw_set_drv_info(struct rtw89_dev *rtwdev, u8 type) switch (type) { case CXDRVINFO_INIT: - rtw89_fw_h2c_cxdrv_init(rtwdev); + if (ver->fcxinit == 7) + rtw89_fw_h2c_cxdrv_init_v7(rtwdev, type); + else + rtw89_fw_h2c_cxdrv_init(rtwdev, type); break; case CXDRVINFO_ROLE: if (ver->fwlrole == 0) - rtw89_fw_h2c_cxdrv_role(rtwdev); + rtw89_fw_h2c_cxdrv_role(rtwdev, type); else if (ver->fwlrole == 1) - rtw89_fw_h2c_cxdrv_role_v1(rtwdev); + rtw89_fw_h2c_cxdrv_role_v1(rtwdev, type); else if (ver->fwlrole == 2) - rtw89_fw_h2c_cxdrv_role_v2(rtwdev); + rtw89_fw_h2c_cxdrv_role_v2(rtwdev, type); break; case CXDRVINFO_CTRL: - rtw89_fw_h2c_cxdrv_ctrl(rtwdev); + if (ver->drvinfo_type == 1) + type = 2; + + if (ver->fcxctrl == 7) + rtw89_fw_h2c_cxdrv_ctrl_v7(rtwdev, type); + else + rtw89_fw_h2c_cxdrv_ctrl(rtwdev, type); break; case CXDRVINFO_TRX: + if (ver->drvinfo_type == 1) + type = 3; + dm->trx_info.tx_power = u32_get_bits(rf_para.wl_tx_power, RTW89_BTC_WL_DEF_TX_PWR); dm->trx_info.rx_gain = u32_get_bits(rf_para.wl_rx_gain, @@ -2107,11 +2156,18 @@ static void _fw_set_drv_info(struct rtw89_dev *rtwdev, u8 type) RTW89_BTC_WL_DEF_TX_PWR); dm->trx_info.cn = wl->cn_report; dm->trx_info.nhm = wl->nhm.pwr; - rtw89_fw_h2c_cxdrv_trx(rtwdev); + rtw89_fw_h2c_cxdrv_trx(rtwdev, type); break; case CXDRVINFO_RFK: - rtw89_fw_h2c_cxdrv_rfk(rtwdev); + if (ver->drvinfo_type == 1) + return; + + rtw89_fw_h2c_cxdrv_rfk(rtwdev, type); break; + case CXDRVINFO_TXPWR: + case CXDRVINFO_FDDT: + case CXDRVINFO_MLO: + case CXDRVINFO_OSI: default: break; } @@ -2261,20 +2317,25 @@ static void _set_bt_tx_power(struct rtw89_dev *rtwdev, u8 level) { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_bt_info *bt = &btc->cx.bt; + int ret; u8 buf; - if (bt->rf_para.tx_pwr_freerun == level) + if (btc->cx.cnt_bt[BTC_BCNT_INFOUPDATE] == 0) return; - bt->rf_para.tx_pwr_freerun = level; - btc->dm.rf_trx_para.bt_tx_power = level; + if (bt->rf_para.tx_pwr_freerun == level) + return; rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): level = %d\n", __func__, level); buf = (s8)(-level); - _send_fw_cmd(rtwdev, BTFC_SET, SET_BT_TX_PWR, &buf, 1); + ret = _send_fw_cmd(rtwdev, BTFC_SET, SET_BT_TX_PWR, &buf, 1); + if (!ret) { + bt->rf_para.tx_pwr_freerun = level; + btc->dm.rf_trx_para.bt_tx_power = level; + } } #define BTC_BT_RX_NORMAL_LVL 7 @@ -2284,6 +2345,9 @@ static void _set_bt_rx_gain(struct rtw89_dev *rtwdev, u8 level) struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_bt_info *bt = &btc->cx.bt; + if (btc->cx.cnt_bt[BTC_BCNT_INFOUPDATE] == 0) + return; + if ((bt->rf_para.rx_gain_freerun == level || level > BTC_BT_RX_NORMAL_LVL) && (!rtwdev->chip->scbd || bt->lna_constrain == level)) @@ -2333,7 +2397,7 @@ static void _set_rf_trx_para(struct rtw89_dev *rtwdev) } /* decide trx_para_level */ - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { /* fix LNA2 + TIA gain not change by GNT_BT */ if ((btc->dm.wl_btg_rx && b->profile_cnt.now != 0) || dm->bt_only == 1) @@ -2435,7 +2499,7 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev) u8 en = 0, i, ch = 0, bw = 0; u8 mode, connect_cnt; - if (btc->ctrl.manual || wl->status.map.scan) + if (btc->manual_ctrl || wl->status.map.scan) return; if (ver->fwlrole == 0) { @@ -2560,8 +2624,16 @@ static bool _check_freerun(struct rtw89_dev *rtwdev) struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1; struct rtw89_btc_bt_link_info *bt_linfo = &bt->link_info; struct rtw89_btc_bt_hid_desc *hid = &bt_linfo->hid_desc; + union rtw89_btc_module_info *md = &btc->mdinfo; + const struct rtw89_btc_ver *ver = btc->ver; + u8 isolation; + + if (ver->fcxinit == 7) + isolation = md->md_v7.ant.isolation; + else + isolation = md->md.ant.isolation; - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { btc->dm.trx_para_level = 0; return false; } @@ -2584,7 +2656,7 @@ static bool _check_freerun(struct rtw89_dev *rtwdev) } /* TODO get isolation by BT psd */ - if (btc->mdinfo.ant.isolation >= BTC_FREERUN_ANTISO_MIN) { + if (isolation >= BTC_FREERUN_ANTISO_MIN) { btc->dm.trx_para_level = 5; return true; } @@ -2712,7 +2784,7 @@ void rtw89_btc_set_policy(struct rtw89_dev *rtwdev, u16 policy_type) u8 type; u32 tbl_w1, tbl_b1, tbl_b4; - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { if (btc->cx.wl.status.map._4way) tbl_w1 = cxtbl[1]; else @@ -3023,12 +3095,13 @@ void rtw89_btc_set_policy_v1(struct rtw89_dev *rtwdev, u16 policy_type) struct rtw89_btc_wl_role_info_v1 *wl_rinfo = &btc->cx.wl.role_info_v1; struct rtw89_btc_bt_hid_desc *hid = &btc->cx.bt.link_info.hid_desc; struct rtw89_btc_bt_hfp_desc *hfp = &btc->cx.bt.link_info.hfp_desc; + struct rtw89_btc_wl_info *wl = &btc->cx.wl; u8 type, null_role; u32 tbl_w1, tbl_b1, tbl_b4; type = FIELD_GET(BTC_CXP_MASK, policy_type); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { if (btc->cx.wl.status.map._4way) tbl_w1 = cxtbl[1]; else if (hid->exist && hid->type == BTC_HID_218) @@ -3048,9 +3121,16 @@ void rtw89_btc_set_policy_v1(struct rtw89_dev *rtwdev, u16 policy_type) tbl_b4 = cxtbl[2]; } } else { - tbl_w1 = cxtbl[16]; tbl_b1 = cxtbl[17]; tbl_b4 = cxtbl[17]; + + if (wl->bg_mode) + tbl_w1 = cxtbl[8]; + else if ((wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) && + hid->exist) + tbl_w1 = cxtbl[19]; + else + tbl_w1 = cxtbl[16]; } btc->bt_req_en = false; @@ -3615,7 +3695,7 @@ static void _action_bt_idle(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ switch (btc->cx.state_map) { case BTC_WBUSY_BNOSCAN: /*wl-busy + bt idle*/ case BTC_WSCAN_BNOSCAN: /* wl-scan + bt-idle */ @@ -3654,7 +3734,7 @@ static void _action_bt_hfp(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { if (btc->cx.wl.status.map._4way) { _set_policy(rtwdev, BTC_CXP_OFF_WL, BTC_ACT_BT_HFP); } else if (wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) { @@ -3664,7 +3744,12 @@ static void _action_bt_hfp(struct rtw89_dev *rtwdev) _set_policy(rtwdev, BTC_CXP_OFF_BWB1, BTC_ACT_BT_HFP); } } else { - _set_policy(rtwdev, BTC_CXP_OFF_EQ2, BTC_ACT_BT_HFP); + if (wl->bg_mode) + _set_policy(rtwdev, BTC_CXP_OFF_BWB1, BTC_ACT_BT_HFP); + else if (wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) + _set_policy(rtwdev, BTC_CXP_OFF_EQ5, BTC_ACT_BT_HFP); + else + _set_policy(rtwdev, BTC_CXP_OFF_EQ2, BTC_ACT_BT_HFP); } } @@ -3679,7 +3764,7 @@ static void _action_bt_hid(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ if (wl->status.map._4way) { policy_type = BTC_CXP_OFF_WL; } else if (wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) { @@ -3697,7 +3782,12 @@ static void _action_bt_hid(struct rtw89_dev *rtwdev) policy_type = BTC_CXP_OFF_BWB1; } } else { /* dedicated-antenna */ - policy_type = BTC_CXP_OFF_EQ3; + if (wl->bg_mode) + policy_type = BTC_CXP_OFF_BWB1; + else if (wl->status.map.traffic_dir & BIT(RTW89_TFC_UL)) + policy_type = BTC_CXP_OFF_EQ4; + else + policy_type = BTC_CXP_OFF_EQ3; } _set_policy(rtwdev, policy_type, BTC_ACT_BT_HID); @@ -3947,7 +4037,7 @@ static void _action_wl_other(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) + if (btc->ant_type == BTC_ANT_SHARED) _set_policy(rtwdev, BTC_CXP_OFFB_BWB0, BTC_ACT_WL_OTHER); else _set_policy(rtwdev, BTC_CXP_OFF_EQ0, BTC_ACT_WL_OTHER); @@ -3991,7 +4081,7 @@ static void _set_btg_ctrl(struct rtw89_dev *rtwdev) u32 is_btg; u8 i, val; - if (btc->ctrl.manual) + if (btc->manual_ctrl) return; if (ver->fwlrole == 0) @@ -4063,7 +4153,7 @@ static void _set_wl_preagc_ctrl(struct rtw89_dev *rtwdev) struct rtw89_btc_dm *dm = &btc->dm; u8 is_preagc, val; - if (btc->ctrl.manual) + if (btc->manual_ctrl) return; if (wl_rinfo->link_mode == BTC_WLINK_25G_MCC) @@ -4083,7 +4173,7 @@ static void _set_wl_preagc_ctrl(struct rtw89_dev *rtwdev) else if (ver->fwlrole == 2 && wl_rinfo->dbcc_en && wl_rinfo->dbcc_2g_phy != RTW89_PHY_1) is_preagc = BTC_PREAGC_DISABLE; - else if (btc->mdinfo.ant.type == BTC_ANT_SHARED) + else if (btc->ant_type == BTC_ANT_SHARED) is_preagc = BTC_PREAGC_DISABLE; else is_preagc = BTC_PREAGC_ENABLE; @@ -4187,13 +4277,12 @@ static void _set_wl_tx_limit(struct rtw89_dev *rtwdev) struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1; struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2; struct rtw89_txtime_data data = {.rtwdev = rtwdev}; - u8 mode; - u8 tx_retry; + u8 mode, igno_bt, tx_retry; u32 tx_time; u16 enable; bool reenable = false; - if (btc->ctrl.manual) + if (btc->manual_ctrl) return; if (ver->fwlrole == 0) @@ -4205,7 +4294,12 @@ static void _set_wl_tx_limit(struct rtw89_dev *rtwdev) else return; - if (btc->dm.freerun || btc->ctrl.igno_bt || b->profile_cnt.now == 0 || + if (ver->fcxctrl == 7) + igno_bt = btc->ctrl.ctrl_v7.igno_bt; + else + igno_bt = btc->ctrl.ctrl.igno_bt; + + if (btc->dm.freerun || igno_bt || b->profile_cnt.now == 0 || mode == BTC_WLINK_5G || mode == BTC_WLINK_NOLINK) { enable = 0; tx_time = BTC_MAX_TX_TIME_DEF; @@ -4402,7 +4496,7 @@ static void _action_wl_scan(struct rtw89_dev *rtwdev) if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) { _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W25G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) + if (btc->ant_type == BTC_ANT_SHARED) _set_policy(rtwdev, BTC_CXP_OFFE_DEF, BTC_RSN_NTFY_SCAN_START); else @@ -4430,7 +4524,7 @@ static void _action_wl_25g_mcc(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W25G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_25G_MCC); @@ -4447,7 +4541,7 @@ static void _action_wl_2g_mcc(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_2G_MCC); @@ -4465,7 +4559,7 @@ static void _action_wl_2g_scc(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_2G_SCC); @@ -4487,7 +4581,7 @@ static void _action_wl_2g_scc_v1(struct rtw89_dev *rtwdev) u16 policy_type = BTC_CXP_OFF_BT; u32 dur; - if (btc->mdinfo.ant.type == BTC_ANT_DEDICATED) { + if (btc->ant_type == BTC_ANT_DEDICATED) { policy_type = BTC_CXP_OFF_EQ0; } else { /* shared-antenna */ @@ -4549,7 +4643,7 @@ static void _action_wl_2g_scc_v2(struct rtw89_dev *rtwdev) u16 policy_type = BTC_CXP_OFF_BT; u32 dur; - if (btc->mdinfo.ant.type == BTC_ANT_DEDICATED) { + if (btc->ant_type == BTC_ANT_DEDICATED) { policy_type = BTC_CXP_OFF_EQ0; } else { /* shared-antenna */ @@ -4607,7 +4701,7 @@ static void _action_wl_2g_ap(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_2G_AP); @@ -4624,7 +4718,7 @@ static void _action_wl_2g_go(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_2G_GO); @@ -4642,7 +4736,7 @@ static void _action_wl_2g_gc(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ _action_by_bt(rtwdev); } else {/* dedicated-antenna */ _set_policy(rtwdev, BTC_CXP_OFF_EQ0, BTC_ACT_WL_2G_GC); @@ -4655,7 +4749,7 @@ static void _action_wl_2g_nan(struct rtw89_dev *rtwdev) _set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G); - if (btc->mdinfo.ant.type == BTC_ANT_SHARED) { /* shared-antenna */ + if (btc->ant_type == BTC_ANT_SHARED) { /* shared-antenna */ if (btc->cx.bt.link_info.profile_cnt.now == 0) _set_policy(rtwdev, BTC_CXP_OFFE_DEF2, BTC_ACT_WL_2G_NAN); @@ -5351,7 +5445,7 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason) struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info; struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1; struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2; - u8 mode; + u8 mode, igno_bt, always_freerun; lockdep_assert_held(&rtwdev->mutex); @@ -5368,20 +5462,28 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason) else return; + if (ver->fcxctrl == 7) { + igno_bt = btc->ctrl.ctrl_v7.igno_bt; + always_freerun = btc->ctrl.ctrl_v7.always_freerun; + } else { + igno_bt = btc->ctrl.ctrl.igno_bt; + always_freerun = btc->ctrl.ctrl.always_freerun; + } + rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): reason=%d, mode=%d\n", __func__, reason, mode); rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): wl_only=%d, bt_only=%d\n", __func__, dm->wl_only, dm->bt_only); /* Be careful to change the following function sequence!! */ - if (btc->ctrl.manual) { + if (btc->manual_ctrl) { rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): return for Manual CTRL!!\n", __func__); return; } - if (btc->ctrl.igno_bt && + if (igno_bt && (reason == BTC_RSN_UPDATE_BT_INFO || reason == BTC_RSN_UPDATE_BT_SCBD)) { rtw89_debug(rtwdev, RTW89_DBG_BTC, @@ -5418,24 +5520,24 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason) dm->freerun = false; dm->cnt_dm[BTC_DCNT_RUN]++; dm->fddt_train = BTC_FDDT_DISABLE; - btc->ctrl.igno_bt = false; bt->scan_rx_low_pri = false; + igno_bt = false; - if (btc->ctrl.always_freerun) { + if (always_freerun) { _action_freerun(rtwdev); - btc->ctrl.igno_bt = true; + igno_bt = true; goto exit; } if (dm->wl_only) { _action_wl_only(rtwdev); - btc->ctrl.igno_bt = true; + igno_bt = true; goto exit; } if (wl->status.map.rf_off || wl->status.map.lps || dm->bt_only) { _action_wl_off(rtwdev, mode); - btc->ctrl.igno_bt = true; + igno_bt = true; goto exit; } @@ -5525,6 +5627,10 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason) exit: rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): exit\n", __func__); + if (ver->fcxctrl == 7) + btc->ctrl.ctrl_v7.igno_bt = igno_bt; + else + btc->ctrl.ctrl.igno_bt = igno_bt; _action_common(rtwdev); } @@ -5560,16 +5666,26 @@ static void _set_init_info(struct rtw89_dev *rtwdev) { const struct rtw89_chip_info *chip = rtwdev->chip; struct rtw89_btc *btc = &rtwdev->btc; + const struct rtw89_btc_ver *ver = btc->ver; struct rtw89_btc_dm *dm = &btc->dm; struct rtw89_btc_wl_info *wl = &btc->cx.wl; - dm->init_info.wl_only = (u8)dm->wl_only; - dm->init_info.bt_only = (u8)dm->bt_only; - dm->init_info.wl_init_ok = (u8)wl->status.map.init_ok; - dm->init_info.dbcc_en = rtwdev->dbcc_en; - dm->init_info.cx_other = btc->cx.other.type; - dm->init_info.wl_guard_ch = chip->afh_guard_ch; - dm->init_info.module = btc->mdinfo; + if (ver->fcxinit == 7) { + dm->init_info.init_v7.wl_only = (u8)dm->wl_only; + dm->init_info.init_v7.bt_only = (u8)dm->bt_only; + dm->init_info.init_v7.wl_init_ok = (u8)wl->status.map.init_ok; + dm->init_info.init_v7.cx_other = btc->cx.other.type; + dm->init_info.init_v7.wl_guard_ch = chip->afh_guard_ch; + dm->init_info.init_v7.module = btc->mdinfo.md_v7; + } else { + dm->init_info.init.wl_only = (u8)dm->wl_only; + dm->init_info.init.bt_only = (u8)dm->bt_only; + dm->init_info.init.wl_init_ok = (u8)wl->status.map.init_ok; + dm->init_info.init.dbcc_en = rtwdev->dbcc_en; + dm->init_info.init.cx_other = btc->cx.other.type; + dm->init_info.init.wl_guard_ch = chip->afh_guard_ch; + dm->init_info.init.module = btc->mdinfo.md; + } } void rtw89_btc_ntfy_init(struct rtw89_dev *rtwdev, u8 mode) @@ -5578,11 +5694,15 @@ void rtw89_btc_ntfy_init(struct rtw89_dev *rtwdev, u8 mode) struct rtw89_btc_dm *dm = &rtwdev->btc.dm; struct rtw89_btc_wl_info *wl = &btc->cx.wl; const struct rtw89_chip_info *chip = rtwdev->chip; + const struct rtw89_btc_ver *ver = btc->ver; _reset_btc_var(rtwdev, BTC_RESET_ALL); btc->dm.run_reason = BTC_RSN_NONE; btc->dm.run_action = BTC_ACT_NONE; - btc->ctrl.igno_bt = true; + if (ver->fcxctrl == 7) + btc->ctrl.ctrl_v7.igno_bt = true; + else + btc->ctrl.ctrl.igno_bt = true; rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): mode=%d\n", __func__, mode); @@ -6298,7 +6418,7 @@ static void rtw89_btc_ntfy_wl_sta_iter(void *data, struct ieee80211_sta *sta) if (BTC_RSSI_LOW(link_info->rssi_state[i])) rssi_map |= BIT(i); - if (btc->mdinfo.ant.type == BTC_ANT_DEDICATED && + if (btc->ant_type == BTC_ANT_DEDICATED && BTC_RSSI_CHANGE(link_info->rssi_state[i])) is_sta_change = true; } @@ -6489,13 +6609,16 @@ void rtw89_btc_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb, static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m) { + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; const struct rtw89_chip_info *chip = rtwdev->chip; + const struct rtw89_btc_ver *ver = rtwdev->btc.ver; struct rtw89_hal *hal = &rtwdev->hal; struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_dm *dm = &btc->dm; struct rtw89_btc_bt_info *bt = &btc->cx.bt; struct rtw89_btc_wl_info *wl = &btc->cx.wl; u32 ver_main = 0, ver_sub = 0, ver_hotfix = 0, id_branch = 0; + u8 cv, rfe, iso, ant_num, ant_single_pos; if (!(dm->coex_info_map & BTC_COEX_INFO_CX)) return; @@ -6545,11 +6668,24 @@ static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m) ver_main, ver_sub, ver_hotfix, id_branch, bt->ver_info.fw, bt->run_patch_code ? "patch" : "ROM"); + if (ver->fcxinit == 7) { + cv = md->md_v7.kt_ver; + rfe = md->md_v7.rfe_type; + iso = md->md_v7.ant.isolation; + ant_num = md->md_v7.ant.num; + ant_single_pos = md->md_v7.ant.single_pos; + } else { + cv = md->md.cv; + rfe = md->md.rfe_type; + iso = md->md.ant.isolation; + ant_num = md->md.ant.num; + ant_single_pos = md->md.ant.single_pos; + } + seq_printf(m, " %-15s : cv:%x, rfe_type:0x%x, ant_iso:%d, ant_pg:%d, %s", - "[hw_info]", btc->mdinfo.cv, btc->mdinfo.rfe_type, - btc->mdinfo.ant.isolation, btc->mdinfo.ant.num, - (btc->mdinfo.ant.num > 1 ? "" : (btc->mdinfo.ant.single_pos ? - "1Ant_Pos:S1, " : "1Ant_Pos:S0, "))); + "[hw_info]", cv, rfe, iso, ant_num, + ant_num > 1 ? "" : + ant_single_pos ? "1Ant_Pos:S1, " : "1Ant_Pos:S0, "); seq_printf(m, "3rd_coex:%d, dbcc:%d, tx_num:%d, rx_num:%d\n", btc->cx.other.type, rtwdev->dbcc_en, hal->tx_nss, @@ -6722,20 +6858,26 @@ static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m) struct rtw89_btc_cx *cx = &btc->cx; struct rtw89_btc_bt_info *bt = &cx->bt; struct rtw89_btc_wl_info *wl = &cx->wl; - struct rtw89_btc_module *module = &btc->mdinfo; struct rtw89_btc_bt_link_info *bt_linfo = &bt->link_info; + union rtw89_btc_module_info *md = &btc->mdinfo; u8 *afh = bt_linfo->afh_map; u8 *afh_le = bt_linfo->afh_map_le; + u8 bt_pos; if (!(btc->dm.coex_info_map & BTC_COEX_INFO_BT)) return; + if (ver->fcxinit == 7) + bt_pos = md->md_v7.bt_pos; + else + bt_pos = md->md.bt_pos; + seq_puts(m, "========== [BT Status] ==========\n"); seq_printf(m, " %-15s : enable:%s, btg:%s%s, connect:%s, ", "[status]", bt->enable.now ? "Y" : "N", bt->btg_type ? "Y" : "N", - (bt->enable.now && (bt->btg_type != module->bt_pos) ? + (bt->enable.now && (bt->btg_type != bt_pos) ? "(efuse-mismatch!!)" : ""), (bt_linfo->status.map.connect ? "Y" : "N")); @@ -6934,10 +7076,13 @@ static const char *steps_to_str(u16 step) CASE_BTC_POLICY_STR(OFF_EQ1); CASE_BTC_POLICY_STR(OFF_EQ2); CASE_BTC_POLICY_STR(OFF_EQ3); + CASE_BTC_POLICY_STR(OFF_EQ4); + CASE_BTC_POLICY_STR(OFF_EQ5); CASE_BTC_POLICY_STR(OFF_BWB0); CASE_BTC_POLICY_STR(OFF_BWB1); CASE_BTC_POLICY_STR(OFF_BWB2); CASE_BTC_POLICY_STR(OFF_BWB3); + CASE_BTC_POLICY_STR(OFF_WL2); CASE_BTC_POLICY_STR(OFFB_BWB0); CASE_BTC_POLICY_STR(OFFE_DEF); CASE_BTC_POLICY_STR(OFFE_DEF2); @@ -7123,21 +7268,22 @@ static void _show_dm_step(struct rtw89_dev *rtwdev, struct seq_file *m) static void _show_dm_info(struct rtw89_dev *rtwdev, struct seq_file *m) { struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; + const struct rtw89_btc_ver *ver = btc->ver; struct rtw89_btc_dm *dm = &btc->dm; struct rtw89_btc_wl_info *wl = &btc->cx.wl; struct rtw89_btc_bt_info *bt = &btc->cx.bt; + u8 igno_bt; if (!(dm->coex_info_map & BTC_COEX_INFO_DM)) return; seq_printf(m, "========== [Mechanism Status %s] ==========\n", - (btc->ctrl.manual ? "(Manual)" : "(Auto)")); + (btc->manual_ctrl ? "(Manual)" : "(Auto)")); seq_printf(m, " %-15s : type:%s, reason:%s(), action:%s(), ant_path:%s, init_mode:%s, run_cnt:%d\n", "[status]", - module->ant.type == BTC_ANT_SHARED ? "shared" : "dedicated", + btc->ant_type == BTC_ANT_SHARED ? "shared" : "dedicated", steps_to_str(dm->run_reason), steps_to_str(dm->run_action | BTC_ACT_EXT_BIT), id_to_ant(FIELD_GET(GENMASK(7, 0), dm->set_ant_path)), @@ -7146,8 +7292,13 @@ static void _show_dm_info(struct rtw89_dev *rtwdev, struct seq_file *m) _show_dm_step(rtwdev, m); + if (ver->fcxctrl == 7) + igno_bt = btc->ctrl.ctrl_v7.igno_bt; + else + igno_bt = btc->ctrl.ctrl.igno_bt; + seq_printf(m, " %-15s : wl_only:%d, bt_only:%d, igno_bt:%d, free_run:%d, wl_ps_ctrl:%d, wl_mimo_ps:%d, ", - "[dm_flag]", dm->wl_only, dm->bt_only, btc->ctrl.igno_bt, + "[dm_flag]", dm->wl_only, dm->bt_only, igno_bt, dm->freerun, btc->lps, dm->wl_mimo_ps); seq_printf(m, "leak_ap:%d, fw_offload:%s%s\n", dm->leak_ap, @@ -7888,10 +8039,11 @@ static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m) struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo; struct rtw89_btc_rpt_cmn_info *pcinfo = NULL; struct rtw89_btc_fbtc_steps_v2 *pstep = NULL; + const struct rtw89_btc_ver *ver = btc->ver; u8 type, val, cnt = 0, state = 0; bool outloop = false; u16 i, diff_t, n_start = 0, n_stop = 0; - u16 pos_old, pos_new; + u16 pos_old, pos_new, trace_step; pcinfo = &pfwinfo->rpt_fbtc_step.cinfo; if (!pcinfo->valid) @@ -7908,11 +8060,16 @@ static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m) do { switch (state) { case 0: + if (ver->fcxctrl == 7 || ver->fcxctrl == 1) + trace_step = 50; + else + trace_step = btc->ctrl.ctrl.trace_step; + n_start = pos_old; if (pos_new >= pos_old) n_stop = pos_new; else - n_stop = btc->ctrl.trace_step - 1; + n_stop = trace_step - 1; state = 1; break; @@ -8742,7 +8899,7 @@ void rtw89_btc_dump_info(struct rtw89_dev *rtwdev, struct seq_file *m) seq_printf(m, "WL FW / BT FW %d.%d.%d.%d / NA\n", fw_suit->major_ver, fw_suit->minor_ver, fw_suit->sub_ver, fw_suit->sub_idex); - seq_printf(m, "manual %d\n", btc->ctrl.manual); + seq_printf(m, "manual %d\n", btc->manual_ctrl); seq_puts(m, "=========================================\n"); diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h index 08121fd899e6..13303830684e 100644 --- a/drivers/net/wireless/realtek/rtw89/coex.h +++ b/drivers/net/wireless/realtek/rtw89/coex.h @@ -7,6 +7,8 @@ #include "core.h" +#define BTC_H2C_MAXLEN 2020 + enum btc_mode { BTC_MODE_NORMAL, BTC_MODE_WL, @@ -153,6 +155,10 @@ enum btc_lps_state { #define BTC_REG_NOTFOUND 0xff +#define R_BTC_ZB_COEX_TBL_0 0xE328 +#define R_BTC_ZB_COEX_TBL_1 0xE32c +#define R_BTC_ZB_BREAK_TBL 0xE350 + enum btc_ant_div_pos { BTC_ANT_DIV_MAIN = 0, BTC_ANT_DIV_AUX = 1, @@ -181,6 +187,20 @@ enum btc_btgctrl_type { BTC_BTGCTRL_BB_GNT_NOTFOUND, }; +enum btc_wa_type { + BTC_WA_5G_HI_CH_RX = BIT(0), + BTC_WA_NULL_AP = BIT(1), + BTC_WA_HFP_ZB = BIT(2), /* HFP PTA req bit4 define issue */ +}; + +enum btc_3cx_type { + BTC_3CX_NONE = 0, + BTC_3CX_BT2 = BIT(0), + BTC_3CX_ZB = BIT(1), + BTC_3CX_LTE = BIT(2), + BTC_3CX_MAX, +}; + void rtw89_btc_ntfy_poweron(struct rtw89_dev *rtwdev); void rtw89_btc_ntfy_poweroff(struct rtw89_dev *rtwdev); void rtw89_btc_ntfy_init(struct rtw89_dev *rtwdev, u8 mode); diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index f697e3d898e6..d474b8d5df3d 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -3801,7 +3801,7 @@ static void rtw89_init_eht_cap(struct rtw89_dev *rtwdev, struct ieee80211_sta_eht_cap *eht_cap; struct rtw89_hal *hal = &rtwdev->hal; bool support_320mhz = false; - int sts = 3; + int sts = 8; u8 val; if (chip->chip_gen == RTW89_CHIP_AX) @@ -3845,18 +3845,16 @@ static void rtw89_init_eht_cap(struct rtw89_dev *rtwdev, eht_cap_elem->phy_cap_info[2] = 0; eht_cap_elem->phy_cap_info[3] = - IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK | - IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK | IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK | - IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK; + IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK | + IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK; eht_cap_elem->phy_cap_info[4] = IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP | u8_encode_bits(1, IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK); eht_cap_elem->phy_cap_info[5] = - IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK | u8_encode_bits(IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US, IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK); @@ -4505,6 +4503,8 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev) hw->wiphy->max_remain_on_channel_duration = 1000; wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0); + wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_SCAN_RANDOM_SN); + wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL); ret = rtw89_core_set_supported_band(rtwdev); if (ret) { diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h index d62d23015c48..2e854c9af709 100644 --- a/drivers/net/wireless/realtek/rtw89/core.h +++ b/drivers/net/wireless/realtek/rtw89/core.h @@ -1151,9 +1151,15 @@ struct rtw89_mac_ax_gnt { u8 gnt_wl; } __packed; +struct rtw89_mac_ax_wl_act { + u8 wlan_act_en; + u8 wlan_act; +}; + #define RTW89_MAC_AX_COEX_GNT_NR 2 struct rtw89_mac_ax_coex_gnt { struct rtw89_mac_ax_gnt band[RTW89_MAC_AX_COEX_GNT_NR]; + struct rtw89_mac_ax_wl_act bt[RTW89_MAC_AX_COEX_GNT_NR]; }; enum rtw89_btc_ncnt { @@ -1271,6 +1277,18 @@ struct rtw89_btc_ant_info { u8 stream_cnt: 4; }; +struct rtw89_btc_ant_info_v7 { + u8 type; /* shared, dedicated(non-shared) */ + u8 num; /* antenna count */ + u8 isolation; + u8 single_pos;/* wifi 1ss-1ant at 0:S0 or 1:S1 */ + + u8 diversity; /* only for wifi use 1-antenna */ + u8 btg_pos; /* btg-circuit at 0:S0/1:S1/others:all */ + u8 stream_cnt; /* spatial_stream count */ + u8 rsvd; +} __packed; + enum rtw89_tfc_dir { RTW89_TFC_UL, RTW89_TFC_DL, @@ -1665,6 +1683,16 @@ struct rtw89_btc_dm_emap { u32 wl_e2g_hang: 1; u32 wl_ver_mismatch: 1; u32 bt_ver_mismatch: 1; + u32 rfe_type0: 1; + u32 h2c_buffer_over: 1; + u32 bt_tx_hang: 1; /* for SNR too low bug, BT has no Tx req*/ + u32 wl_no_sta_ntfy: 1; + + u32 h2c_bmap_mismatch: 1; + u32 c2h_bmap_mismatch: 1; + u32 h2c_struct_invalid: 1; + u32 c2h_struct_invalid: 1; + u32 h2c_c2h_buffer_mismatch: 1; }; union rtw89_btc_dm_error_map { @@ -1713,6 +1741,7 @@ struct rtw89_btc_wl_info { u8 cn_report; u8 coex_mode; + bool bg_mode; bool scbd_change; u32 scbd; }; @@ -1730,6 +1759,25 @@ struct rtw89_btc_module { u8 kt_ver_adie; }; +struct rtw89_btc_module_v7 { + u8 rfe_type; + u8 kt_ver; + u8 bt_solo; + u8 bt_pos; /* wl-end view: get from efuse, must compare bt.btg_type*/ + + u8 switch_type; /* WL/BT switch type: 0: internal, 1: external */ + u8 wa_type; /* WA type: 0:none, 1: 51B 5G_Hi-Ch_Rx */ + u8 kt_ver_adie; + u8 rsvd; + + struct rtw89_btc_ant_info_v7 ant; +} __packed; + +union rtw89_btc_module_info { + struct rtw89_btc_module md; + struct rtw89_btc_module_v7 md_v7; +}; + #define RTW89_BTC_DM_MAXSTEP 30 #define RTW89_BTC_DM_CNT_MAX (RTW89_BTC_DM_MAXSTEP * 8) @@ -1752,6 +1800,25 @@ struct rtw89_btc_init_info { u16 rsvd; }; +struct rtw89_btc_init_info_v7 { + u8 wl_guard_ch; + u8 wl_only; + u8 wl_init_ok; + u8 rsvd3; + + u8 cx_other; + u8 bt_only; + u8 pta_mode; + u8 pta_direction; + + struct rtw89_btc_module_v7 module; +} __packed; + +union rtw89_btc_init_info_u { + struct rtw89_btc_init_info init; + struct rtw89_btc_init_info_v7 init_v7; +}; + struct rtw89_btc_wl_tx_limit_para { u16 enable; u32 tx_time; /* unit: us */ @@ -2490,7 +2557,7 @@ struct rtw89_btc_dm { struct rtw89_btc_fbtc_tdma tdma; struct rtw89_btc_fbtc_tdma tdma_now; struct rtw89_mac_ax_coex_gnt gnt; - struct rtw89_btc_init_info init_info; /* pass to wl_fw if offload */ + union rtw89_btc_init_info_u init_info; /* pass to wl_fw if offload */ struct rtw89_btc_rf_trx_para rf_trx_para; struct rtw89_btc_wl_tx_limit_para wl_tx_limit; struct rtw89_btc_dm_step dm_step; @@ -2539,6 +2606,18 @@ struct rtw89_btc_ctrl { u32 rsvd: 12; }; +struct rtw89_btc_ctrl_v7 { + u8 manual; + u8 igno_bt; + u8 always_freerun; + u8 rsvd; +} __packed; + +union rtw89_btc_ctrl_list { + struct rtw89_btc_ctrl ctrl; + struct rtw89_btc_ctrl_v7 ctrl_v7; +}; + struct rtw89_btc_dbg { /* cmd "rb" */ bool rb_done; @@ -2711,7 +2790,9 @@ struct rtw89_btc_ver { u8 fwlrole; u8 frptmap; u8 fcxctrl; + u8 fcxinit; + u8 drvinfo_type; u16 info_buf; u8 max_role_num; }; @@ -2723,8 +2804,8 @@ struct rtw89_btc { struct rtw89_btc_cx cx; struct rtw89_btc_dm dm; - struct rtw89_btc_ctrl ctrl; - struct rtw89_btc_module mdinfo; + union rtw89_btc_ctrl_list ctrl; + union rtw89_btc_module_info mdinfo; struct rtw89_btc_btf_fwinfo fwinfo; struct rtw89_btc_dbg dbg; @@ -2736,11 +2817,14 @@ struct rtw89_btc { u32 bt_req_len; u8 policy[RTW89_BTC_POLICY_MAXLEN]; + u8 ant_type; + u8 btg_pos; u16 policy_len; u16 policy_type; bool bt_req_en; bool update_policy_force; bool lps; + bool manual_ctrl; }; enum rtw89_btc_hmsg { @@ -3118,7 +3202,7 @@ struct rtw89_hci_ops { void (*ctrl_txdma_ch)(struct rtw89_dev *rtwdev, bool enable); void (*ctrl_txdma_fw_ch)(struct rtw89_dev *rtwdev, bool enable); void (*ctrl_trxhci)(struct rtw89_dev *rtwdev, bool enable); - int (*poll_txdma_ch)(struct rtw89_dev *rtwdev); + int (*poll_txdma_ch_idle)(struct rtw89_dev *rtwdev); void (*clr_idx_all)(struct rtw89_dev *rtwdev); void (*clear)(struct rtw89_dev *rtwdev, struct pci_dev *pdev); void (*disable_intr)(struct rtw89_dev *rtwdev); @@ -3870,6 +3954,7 @@ struct rtw89_chip_info { const u32 *c2h_regs; struct rtw89_reg_def c2h_counter_reg; const struct rtw89_page_regs *page_regs; + u32 wow_reason_reg; bool cfo_src_fd; bool cfo_hw_comp; const struct rtw89_reg_def *dcfo_comp; @@ -5168,12 +5253,12 @@ static inline void rtw89_hci_ctrl_trxhci(struct rtw89_dev *rtwdev, bool enable) rtwdev->hci.ops->ctrl_trxhci(rtwdev, enable); } -static inline int rtw89_hci_poll_txdma_ch(struct rtw89_dev *rtwdev) +static inline int rtw89_hci_poll_txdma_ch_idle(struct rtw89_dev *rtwdev) { int ret = 0; - if (rtwdev->hci.ops->poll_txdma_ch) - ret = rtwdev->hci.ops->poll_txdma_ch(rtwdev); + if (rtwdev->hci.ops->poll_txdma_ch_idle) + ret = rtwdev->hci.ops->poll_txdma_ch_idle(rtwdev); return ret; } diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 44829a148185..affffc4092ba 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -3427,14 +3427,17 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp, struct rtw89_debugfs_priv *debugfs_priv = filp->private_data; struct rtw89_dev *rtwdev = debugfs_priv->rtwdev; struct rtw89_btc *btc = &rtwdev->btc; - bool btc_manual; + const struct rtw89_btc_ver *ver = btc->ver; int ret; - ret = kstrtobool_from_user(user_buf, count, &btc_manual); + ret = kstrtobool_from_user(user_buf, count, &btc->manual_ctrl); if (ret) return ret; - btc->ctrl.manual = btc_manual; + if (ver->fcxctrl == 7) + btc->ctrl.ctrl_v7.manual = btc->manual_ctrl; + else + btc->ctrl.ctrl.manual = btc->manual_ctrl; return count; } diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 63897351ca15..185cd339c085 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -3753,11 +3753,11 @@ fail: return ret; } -int rtw89_fw_h2c_cxdrv_init(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_init(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_dm *dm = &btc->dm; - struct rtw89_btc_init_info *init_info = &dm->init_info; + struct rtw89_btc_init_info *init_info = &dm->init_info.init; struct rtw89_btc_module *module = &init_info->module; struct rtw89_btc_ant_info *ant = &module->ant; struct rtw89_h2c_cxinit *h2c; @@ -3773,7 +3773,7 @@ int rtw89_fw_h2c_cxdrv_init(struct rtw89_dev *rtwdev) skb_put(skb, len); h2c = (struct rtw89_h2c_cxinit *)skb->data; - h2c->hdr.type = CXDRVINFO_INIT; + h2c->hdr.type = type; h2c->hdr.len = len - H2C_LEN_CXDRVHDR; h2c->ant_type = ant->type; @@ -3820,12 +3820,53 @@ fail: return ret; } +int rtw89_fw_h2c_cxdrv_init_v7(struct rtw89_dev *rtwdev, u8 type) +{ + struct rtw89_btc *btc = &rtwdev->btc; + struct rtw89_btc_dm *dm = &btc->dm; + struct rtw89_btc_init_info_v7 *init_info = &dm->init_info.init_v7; + struct rtw89_h2c_cxinit_v7 *h2c; + u32 len = sizeof(*h2c); + struct sk_buff *skb; + int ret; + + skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len); + if (!skb) { + rtw89_err(rtwdev, "failed to alloc skb for h2c cxdrv_init_v7\n"); + return -ENOMEM; + } + skb_put(skb, len); + h2c = (struct rtw89_h2c_cxinit_v7 *)skb->data; + + h2c->hdr.type = type; + h2c->hdr.ver = btc->ver->fcxinit; + h2c->hdr.len = len - H2C_LEN_CXDRVHDR_V7; + h2c->init = *init_info; + + rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, + H2C_CAT_OUTSRC, BTFC_SET, + SET_DRV_INFO, 0, 0, + len); + + ret = rtw89_h2c_tx(rtwdev, skb, false); + if (ret) { + rtw89_err(rtwdev, "failed to send h2c\n"); + goto fail; + } + + return 0; +fail: + dev_kfree_skb_any(skb); + + return ret; +} + #define PORT_DATA_OFFSET 4 #define H2C_LEN_CXDRVINFO_ROLE_DBCC_LEN 12 #define H2C_LEN_CXDRVINFO_ROLE_SIZE(max_role_num) \ (4 + 12 * (max_role_num) + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; const struct rtw89_btc_ver *ver = btc->ver; @@ -3850,7 +3891,7 @@ int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev) skb_put(skb, len); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_ROLE); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, len - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXROLE_CONNECT_CNT(cmd, role_info->connect_cnt); @@ -3906,7 +3947,7 @@ fail: #define H2C_LEN_CXDRVINFO_ROLE_SIZE_V1(max_role_num) \ (4 + 16 * (max_role_num) + H2C_LEN_CXDRVINFO_ROLE_DBCC_LEN + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; const struct rtw89_btc_ver *ver = btc->ver; @@ -3930,7 +3971,7 @@ int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev) skb_put(skb, len); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_ROLE); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, len - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXROLE_CONNECT_CNT(cmd, role_info->connect_cnt); @@ -3996,7 +4037,7 @@ fail: #define H2C_LEN_CXDRVINFO_ROLE_SIZE_V2(max_role_num) \ (4 + 8 * (max_role_num) + H2C_LEN_CXDRVINFO_ROLE_DBCC_LEN + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; const struct rtw89_btc_ver *ver = btc->ver; @@ -4020,7 +4061,7 @@ int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev) skb_put(skb, len); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_ROLE); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, len - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXROLE_CONNECT_CNT(cmd, role_info->connect_cnt); @@ -4080,11 +4121,11 @@ fail: } #define H2C_LEN_CXDRVINFO_CTRL (4 + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; const struct rtw89_btc_ver *ver = btc->ver; - struct rtw89_btc_ctrl *ctrl = &btc->ctrl; + struct rtw89_btc_ctrl *ctrl = &btc->ctrl.ctrl; struct sk_buff *skb; u8 *cmd; int ret; @@ -4097,7 +4138,7 @@ int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev) skb_put(skb, H2C_LEN_CXDRVINFO_CTRL); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_CTRL); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, H2C_LEN_CXDRVINFO_CTRL - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXCTRL_MANUAL(cmd, ctrl->manual); @@ -4124,8 +4165,47 @@ fail: return ret; } +int rtw89_fw_h2c_cxdrv_ctrl_v7(struct rtw89_dev *rtwdev, u8 type) +{ + struct rtw89_btc *btc = &rtwdev->btc; + struct rtw89_btc_ctrl_v7 *ctrl = &btc->ctrl.ctrl_v7; + struct rtw89_h2c_cxctrl_v7 *h2c; + u32 len = sizeof(*h2c); + struct sk_buff *skb; + int ret; + + skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len); + if (!skb) { + rtw89_err(rtwdev, "failed to alloc skb for h2c cxdrv_ctrl\n"); + return -ENOMEM; + } + skb_put(skb, len); + h2c = (struct rtw89_h2c_cxctrl_v7 *)skb->data; + + h2c->hdr.type = type; + h2c->hdr.ver = btc->ver->fcxctrl; + h2c->hdr.len = sizeof(*h2c) - H2C_LEN_CXDRVHDR_V7; + h2c->ctrl = *ctrl; + + rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C, + H2C_CAT_OUTSRC, BTFC_SET, + SET_DRV_INFO, 0, 0, len); + + ret = rtw89_h2c_tx(rtwdev, skb, false); + if (ret) { + rtw89_err(rtwdev, "failed to send h2c\n"); + goto fail; + } + + return 0; +fail: + dev_kfree_skb_any(skb); + + return ret; +} + #define H2C_LEN_CXDRVINFO_TRX (28 + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_trx(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_trx(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_trx_info *trx = &btc->dm.trx_info; @@ -4141,7 +4221,7 @@ int rtw89_fw_h2c_cxdrv_trx(struct rtw89_dev *rtwdev) skb_put(skb, H2C_LEN_CXDRVINFO_TRX); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_TRX); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, H2C_LEN_CXDRVINFO_TRX - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXTRX_TXLV(cmd, trx->tx_lvl); @@ -4181,7 +4261,7 @@ fail: } #define H2C_LEN_CXDRVINFO_RFK (4 + H2C_LEN_CXDRVHDR) -int rtw89_fw_h2c_cxdrv_rfk(struct rtw89_dev *rtwdev) +int rtw89_fw_h2c_cxdrv_rfk(struct rtw89_dev *rtwdev, u8 type) { struct rtw89_btc *btc = &rtwdev->btc; struct rtw89_btc_wl_info *wl = &btc->cx.wl; @@ -4198,7 +4278,7 @@ int rtw89_fw_h2c_cxdrv_rfk(struct rtw89_dev *rtwdev) skb_put(skb, H2C_LEN_CXDRVINFO_RFK); cmd = skb->data; - RTW89_SET_FWCMD_CXHDR_TYPE(cmd, CXDRVINFO_RFK); + RTW89_SET_FWCMD_CXHDR_TYPE(cmd, type); RTW89_SET_FWCMD_CXHDR_LEN(cmd, H2C_LEN_CXDRVINFO_RFK - H2C_LEN_CXDRVHDR); RTW89_SET_FWCMD_CXRFK_STATE(cmd, rfk_info->state); @@ -5739,7 +5819,7 @@ int rtw89_hw_scan_add_chan_list(struct rtw89_dev *rtwdev, goto out; } - if (req->duration_mandatory) + if (req->duration) ch_info->period = req->duration; else if (channel->band == NL80211_BAND_6GHZ) ch_info->period = RTW89_CHANNEL_TIME_6G + @@ -5817,7 +5897,7 @@ int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev, goto out; } - if (req->duration_mandatory) + if (req->duration) ch_info->period = req->duration; else if (channel->band == NL80211_BAND_6GHZ) ch_info->period = RTW89_CHANNEL_TIME_6G + RTW89_DWELL_TIME_6G; diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index 9c5464dcc081..44311f65b4fa 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -64,6 +64,8 @@ struct rtw89_h2creg_sch_tx_en { #define RTW89_H2CREG_SCH_TX_EN_W1_MASK GENMASK(15, 0) #define RTW89_H2CREG_SCH_TX_EN_W1_BAND BIT(16) +#define RTW89_H2CREG_WOW_CPUIO_RX_CTRL_EN GENMASK(23, 16) + #define RTW89_H2CREG_MAX 4 #define RTW89_C2HREG_MAX 4 #define RTW89_C2HREG_HDR_LEN 2 @@ -95,7 +97,9 @@ enum rtw89_mac_h2c_type { RTW89_FWCMD_H2CREG_FUNC_FWERR, RTW89_FWCMD_H2CREG_FUNC_GET_FEATURE, RTW89_FWCMD_H2CREG_FUNC_GETPKT_INFORM, - RTW89_FWCMD_H2CREG_FUNC_SCH_TX_EN + RTW89_FWCMD_H2CREG_FUNC_SCH_TX_EN, + RTW89_FWCMD_H2CREG_FUNC_WOW_TRX_STOP = 0x6, + RTW89_FWCMD_H2CREG_FUNC_WOW_CPUIO_RX_CTRL = 0xA, }; enum rtw89_mac_c2h_type { @@ -104,7 +108,8 @@ enum rtw89_mac_c2h_type { RTW89_FWCMD_C2HREG_FUNC_ERR_MSG, RTW89_FWCMD_C2HREG_FUNC_PHY_CAP, RTW89_FWCMD_C2HREG_FUNC_TX_PAUSE_RPT, - RTW89_FWCMD_C2HREG_FUNC_NULL = 0xFF + RTW89_FWCMD_C2HREG_FUNC_WOW_CPUIO_RX_ACK = 0xA, + RTW89_FWCMD_C2HREG_FUNC_NULL = 0xFF, }; enum rtw89_fw_c2h_category { @@ -2324,9 +2329,15 @@ enum rtw89_btc_btf_set { SET_BT_IGNORE_WLAN_ACT, SET_BT_TX_PWR, SET_BT_LNA_CONSTRAIN, - SET_BT_GOLDEN_RX_RANGE, + SET_BT_QUERY_DEV_LIST, + SET_BT_QUERY_DEV_INFO, SET_BT_PSD_REPORT, SET_H2C_TEST, + SET_IOFLD_RF, + SET_IOFLD_BB, + SET_IOFLD_MAC, + SET_IOFLD_SCBD, + SET_H2C_MACRO, SET_MAX1, }; @@ -2340,6 +2351,10 @@ enum rtw89_btc_cxdrvinfo { CXDRVINFO_CTRL, CXDRVINFO_SCAN, CXDRVINFO_TRX, /* WL traffic to WL fw */ + CXDRVINFO_TXPWR, + CXDRVINFO_FDDT, + CXDRVINFO_MLO, + CXDRVINFO_OSI, CXDRVINFO_MAX, }; @@ -2366,7 +2381,19 @@ struct rtw89_h2c_cxhdr { u8 len; } __packed; +struct rtw89_h2c_cxhdr_v7 { + u8 type; + u8 ver; + u8 len; +} __packed; + +struct rtw89_h2c_cxctrl_v7 { + struct rtw89_h2c_cxhdr_v7 hdr; + struct rtw89_btc_ctrl_v7 ctrl; +} __packed; + #define H2C_LEN_CXDRVHDR sizeof(struct rtw89_h2c_cxhdr) +#define H2C_LEN_CXDRVHDR_V7 sizeof(struct rtw89_h2c_cxhdr_v7) struct rtw89_h2c_cxinit { struct rtw89_h2c_cxhdr hdr; @@ -2400,6 +2427,11 @@ struct rtw89_h2c_cxinit { #define RTW89_H2C_CXINIT_INFO_CX_OTHER BIT(3) #define RTW89_H2C_CXINIT_INFO_BT_ONLY BIT(4) +struct rtw89_h2c_cxinit_v7 { + struct rtw89_h2c_cxhdr_v7 hdr; + struct rtw89_btc_init_info_v7 init; +} __packed; + static inline void RTW89_SET_FWCMD_CXROLE_CONNECT_CNT(void *cmd, u8 val) { u8p_replace_bits((u8 *)(cmd) + 2, val, GENMASK(7, 0)); @@ -4531,13 +4563,15 @@ int rtw89_fw_h2c_rssi_offload(struct rtw89_dev *rtwdev, struct rtw89_rx_phy_ppdu *phy_ppdu); int rtw89_fw_h2c_tp_offload(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif); int rtw89_fw_h2c_ra(struct rtw89_dev *rtwdev, struct rtw89_ra_info *ra, bool csi); -int rtw89_fw_h2c_cxdrv_init(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_trx(struct rtw89_dev *rtwdev); -int rtw89_fw_h2c_cxdrv_rfk(struct rtw89_dev *rtwdev); +int rtw89_fw_h2c_cxdrv_init(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_init_v7(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_ctrl_v7(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_trx(struct rtw89_dev *rtwdev, u8 type); +int rtw89_fw_h2c_cxdrv_rfk(struct rtw89_dev *rtwdev, u8 type); int rtw89_fw_h2c_del_pkt_offload(struct rtw89_dev *rtwdev, u8 id); int rtw89_fw_h2c_add_pkt_offload(struct rtw89_dev *rtwdev, u8 *id, struct sk_buff *skb_ofld); diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 908245ac46bd..aa5b396b5d2b 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2025,6 +2025,9 @@ void rtw89_mac_hw_mgnt_sec(struct rtw89_dev *rtwdev, bool enable) { u32 msk32 = B_AX_UC_MGNT_DEC | B_AX_BMC_MGNT_DEC; + if (rtwdev->chip->chip_gen != RTW89_CHIP_AX) + return; + if (enable) rtw89_write32_set(rtwdev, R_AX_SEC_ENG_CTRL, msk32); else @@ -5615,7 +5618,8 @@ int rtw89_mac_cfg_gnt_v1(struct rtw89_dev *rtwdev, } EXPORT_SYMBOL(rtw89_mac_cfg_gnt_v1); -int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) +static +int rtw89_mac_cfg_plt_ax(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) { u32 reg; u16 val; @@ -5711,7 +5715,7 @@ bool rtw89_mac_get_ctrl_path(struct rtw89_dev *rtwdev) return !!val; } -u16 rtw89_mac_get_plt_cnt(struct rtw89_dev *rtwdev, u8 band) +static u16 rtw89_mac_get_plt_cnt_ax(struct rtw89_dev *rtwdev, u8 band) { u32 reg; u16 cnt; @@ -6265,6 +6269,41 @@ int rtw89_mac_ptk_drop_by_band_and_wait(struct rtw89_dev *rtwdev, return ret; } +static int rtw89_wow_config_mac_ax(struct rtw89_dev *rtwdev, bool enable_wow) +{ + const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; + int ret; + + if (enable_wow) { + ret = rtw89_mac_resize_ple_rx_quota(rtwdev, true); + if (ret) { + rtw89_err(rtwdev, "[ERR]patch rx qta %d\n", ret); + return ret; + } + + rtw89_write32_set(rtwdev, R_AX_RX_FUNCTION_STOP, B_AX_HDR_RX_STOP); + rtw89_write32_clr(rtwdev, mac->rx_fltr, B_AX_SNIFFER_MODE); + rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false); + rtw89_write32(rtwdev, R_AX_ACTION_FWD0, 0); + rtw89_write32(rtwdev, R_AX_ACTION_FWD1, 0); + rtw89_write32(rtwdev, R_AX_TF_FWD, 0); + rtw89_write32(rtwdev, R_AX_HW_RPT_FWD, 0); + } else { + ret = rtw89_mac_resize_ple_rx_quota(rtwdev, false); + if (ret) { + rtw89_err(rtwdev, "[ERR]patch rx qta %d\n", ret); + return ret; + } + + rtw89_write32_clr(rtwdev, R_AX_RX_FUNCTION_STOP, B_AX_HDR_RX_STOP); + rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true); + rtw89_write32(rtwdev, R_AX_ACTION_FWD0, TRXCFG_MPDU_PROC_ACT_FRWD); + rtw89_write32(rtwdev, R_AX_TF_FWD, TRXCFG_MPDU_PROC_TF_FRWD); + } + + return 0; +} + static u8 rtw89_fw_get_rdy_ax(struct rtw89_dev *rtwdev, enum rtw89_fwdl_check_type type) { u8 val = rtw89_read8(rtwdev, R_AX_WCPU_FW_CTRL); @@ -6307,6 +6346,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = { .addr = R_AX_RXTRIG_TEST_USER_2, .mask = B_AX_RXTRIG_RU26_DIS, }, + .wow_ctrl = {.addr = R_AX_WOW_CTRL, .mask = B_AX_WOW_WOWEN,}, .check_mac_en = rtw89_mac_check_mac_en_ax, .sys_init = sys_init_ax, @@ -6340,6 +6380,9 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = { .parse_phycap_map = rtw89_parse_phycap_map_ax, .cnv_efuse_state = rtw89_cnv_efuse_state_ax, + .cfg_plt = rtw89_mac_cfg_plt_ax, + .get_plt_cnt = rtw89_mac_get_plt_cnt_ax, + .get_txpwr_cr = rtw89_mac_get_txpwr_cr_ax, .write_xtal_si = rtw89_mac_write_xtal_si_ax, @@ -6352,5 +6395,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = { .add_chan_list = rtw89_hw_scan_add_chan_list, .scan_offload = rtw89_fw_h2c_scan_offload, + + .wow_config_mac = rtw89_wow_config_mac_ax, }; EXPORT_SYMBOL(rtw89_mac_gen_ax); diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index db95509fad2f..6fb457153a11 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -169,6 +169,12 @@ enum rtw89_mac_ax_l0_to_l1_event { MAC_AX_L0_TO_L1_EVENT_MAX = 15, }; +enum rtw89_mac_wow_fw_status { + WOWLAN_NOT_READY = 0x00, + WOWLAN_SLEEP_READY = 0x01, + WOWLAN_RESUME_READY = 0x02, +}; + #define RTW89_PORT_OFFSET_TU_TO_32US(shift_tu) ((shift_tu) * 1024 / 32) enum rtw89_mac_dbg_port_sel { @@ -913,6 +919,7 @@ struct rtw89_mac_gen_def { struct rtw89_reg_def muedca_ctrl; struct rtw89_reg_def bfee_ctrl; struct rtw89_reg_def narrow_bw_ru_dis; + struct rtw89_reg_def wow_ctrl; int (*check_mac_en)(struct rtw89_dev *rtwdev, u8 band, enum rtw89_mac_hwmod_sel sel); @@ -958,6 +965,9 @@ struct rtw89_mac_gen_def { int (*parse_phycap_map)(struct rtw89_dev *rtwdev); int (*cnv_efuse_state)(struct rtw89_dev *rtwdev, bool idle); + int (*cfg_plt)(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt); + u16 (*get_plt_cnt)(struct rtw89_dev *rtwdev, u8 band); + bool (*get_txpwr_cr)(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u32 reg_base, u32 *cr); @@ -976,6 +986,8 @@ struct rtw89_mac_gen_def { int (*scan_offload)(struct rtw89_dev *rtwdev, struct rtw89_scan_option *option, struct rtw89_vif *rtwvif); + + int (*wow_config_mac)(struct rtw89_dev *rtwdev, bool enable_wow); }; extern const struct rtw89_mac_gen_def rtw89_mac_gen_ax; @@ -1185,13 +1197,31 @@ int rtw89_mac_cfg_gnt(struct rtw89_dev *rtwdev, const struct rtw89_mac_ax_coex_gnt *gnt_cfg); int rtw89_mac_cfg_gnt_v1(struct rtw89_dev *rtwdev, const struct rtw89_mac_ax_coex_gnt *gnt_cfg); -int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt); -u16 rtw89_mac_get_plt_cnt(struct rtw89_dev *rtwdev, u8 band); +int rtw89_mac_cfg_gnt_v2(struct rtw89_dev *rtwdev, + const struct rtw89_mac_ax_coex_gnt *gnt_cfg); + +static inline +int rtw89_mac_cfg_plt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) +{ + const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; + + return mac->cfg_plt(rtwdev, plt); +} + +static inline +u16 rtw89_mac_get_plt_cnt(struct rtw89_dev *rtwdev, u8 band) +{ + const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; + + return mac->get_plt_cnt(rtwdev, band); +} + void rtw89_mac_cfg_sb(struct rtw89_dev *rtwdev, u32 val); u32 rtw89_mac_get_sb(struct rtw89_dev *rtwdev); bool rtw89_mac_get_ctrl_path(struct rtw89_dev *rtwdev); int rtw89_mac_cfg_ctrl_path(struct rtw89_dev *rtwdev, bool wl); int rtw89_mac_cfg_ctrl_path_v1(struct rtw89_dev *rtwdev, bool wl); +int rtw89_mac_cfg_ctrl_path_v2(struct rtw89_dev *rtwdev, bool wl); void rtw89_mac_power_mode_change(struct rtw89_dev *rtwdev, bool enter); void rtw89_mac_notify_wake(struct rtw89_dev *rtwdev); diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c index 320e88229971..f16467377eab 100644 --- a/drivers/net/wireless/realtek/rtw89/mac_be.c +++ b/drivers/net/wireless/realtek/rtw89/mac_be.c @@ -1797,6 +1797,120 @@ static int trx_init_be(struct rtw89_dev *rtwdev) return 0; } +int rtw89_mac_cfg_gnt_v2(struct rtw89_dev *rtwdev, + const struct rtw89_mac_ax_coex_gnt *gnt_cfg) +{ + u32 val = 0; + + if (gnt_cfg->band[0].gnt_bt) + val |= B_BE_GNT_BT_BB0_VAL | B_BE_GNT_BT_RX_BB0_VAL | + B_BE_GNT_BT_TX_BB0_VAL; + + if (gnt_cfg->band[0].gnt_bt_sw_en) + val |= B_BE_GNT_BT_BB0_SWCTRL | B_BE_GNT_BT_RX_BB0_SWCTRL | + B_BE_GNT_BT_TX_BB0_SWCTRL; + + if (gnt_cfg->band[0].gnt_wl) + val |= B_BE_GNT_WL_BB0_VAL | B_BE_GNT_WL_RX_VAL | + B_BE_GNT_WL_TX_VAL | B_BE_GNT_WL_BB_PWR_VAL; + + if (gnt_cfg->band[0].gnt_wl_sw_en) + val |= B_BE_GNT_WL_BB0_SWCTRL | B_BE_GNT_WL_RX_SWCTRL | + B_BE_GNT_WL_TX_SWCTRL | B_BE_GNT_WL_BB_PWR_SWCTRL; + + if (gnt_cfg->band[1].gnt_bt) + val |= B_BE_GNT_BT_BB1_VAL | B_BE_GNT_BT_RX_BB1_VAL | + B_BE_GNT_BT_TX_BB1_VAL; + + if (gnt_cfg->band[1].gnt_bt_sw_en) + val |= B_BE_GNT_BT_BB1_SWCTRL | B_BE_GNT_BT_RX_BB1_SWCTRL | + B_BE_GNT_BT_TX_BB1_SWCTRL; + + if (gnt_cfg->band[1].gnt_wl) + val |= B_BE_GNT_WL_BB1_VAL | B_BE_GNT_WL_RX_VAL | + B_BE_GNT_WL_TX_VAL | B_BE_GNT_WL_BB_PWR_VAL; + + if (gnt_cfg->band[1].gnt_wl_sw_en) + val |= B_BE_GNT_WL_BB1_SWCTRL | B_BE_GNT_WL_RX_SWCTRL | + B_BE_GNT_WL_TX_SWCTRL | B_BE_GNT_WL_BB_PWR_SWCTRL; + + if (gnt_cfg->bt[0].wlan_act_en) + val |= B_BE_WL_ACT_SWCTRL; + if (gnt_cfg->bt[0].wlan_act) + val |= B_BE_WL_ACT_VAL; + if (gnt_cfg->bt[1].wlan_act_en) + val |= B_BE_WL_ACT2_SWCTRL; + if (gnt_cfg->bt[1].wlan_act) + val |= B_BE_WL_ACT2_VAL; + + rtw89_write32(rtwdev, R_BE_GNT_SW_CTRL, val); + + return 0; +} +EXPORT_SYMBOL(rtw89_mac_cfg_gnt_v2); + +int rtw89_mac_cfg_ctrl_path_v2(struct rtw89_dev *rtwdev, bool wl) +{ + struct rtw89_btc *btc = &rtwdev->btc; + struct rtw89_btc_dm *dm = &btc->dm; + struct rtw89_mac_ax_gnt *g = dm->gnt.band; + struct rtw89_mac_ax_wl_act *gbt = dm->gnt.bt; + int i; + + if (wl) + return 0; + + for (i = 0; i < RTW89_PHY_MAX; i++) { + g[i].gnt_bt_sw_en = 1; + g[i].gnt_bt = 1; + g[i].gnt_wl_sw_en = 1; + g[i].gnt_wl = 0; + gbt[i].wlan_act = 1; + gbt[i].wlan_act_en = 0; + } + + return rtw89_mac_cfg_gnt_v2(rtwdev, &dm->gnt); +} +EXPORT_SYMBOL(rtw89_mac_cfg_ctrl_path_v2); + +static +int rtw89_mac_cfg_plt_be(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_plt *plt) +{ + u32 reg; + u16 val; + int ret; + + ret = rtw89_mac_check_mac_en(rtwdev, plt->band, RTW89_CMAC_SEL); + if (ret) + return ret; + + reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_BT_PLT, plt->band); + val = (plt->tx & RTW89_MAC_AX_PLT_LTE_RX ? B_BE_TX_PLT_GNT_LTE_RX : 0) | + (plt->tx & RTW89_MAC_AX_PLT_GNT_BT_TX ? B_BE_TX_PLT_GNT_BT_TX : 0) | + (plt->tx & RTW89_MAC_AX_PLT_GNT_BT_RX ? B_BE_TX_PLT_GNT_BT_RX : 0) | + (plt->tx & RTW89_MAC_AX_PLT_GNT_WL ? B_BE_TX_PLT_GNT_WL : 0) | + (plt->rx & RTW89_MAC_AX_PLT_LTE_RX ? B_BE_RX_PLT_GNT_LTE_RX : 0) | + (plt->rx & RTW89_MAC_AX_PLT_GNT_BT_TX ? B_BE_RX_PLT_GNT_BT_TX : 0) | + (plt->rx & RTW89_MAC_AX_PLT_GNT_BT_RX ? B_BE_RX_PLT_GNT_BT_RX : 0) | + (plt->rx & RTW89_MAC_AX_PLT_GNT_WL ? B_BE_RX_PLT_GNT_WL : 0) | + B_BE_PLT_EN; + rtw89_write16(rtwdev, reg, val); + + return 0; +} + +static u16 rtw89_mac_get_plt_cnt_be(struct rtw89_dev *rtwdev, u8 band) +{ + u32 reg; + u16 cnt; + + reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_BT_PLT, band); + cnt = rtw89_read32_mask(rtwdev, reg, B_BE_BT_PLT_PKT_CNT_MASK); + rtw89_write16_set(rtwdev, reg, B_BE_BT_PLT_RST); + + return cnt; +} + static int rtw89_set_hw_sch_tx_en_v2(struct rtw89_dev *rtwdev, u8 mac_idx, u32 tx_en, u32 tx_en_mask) { @@ -2193,6 +2307,52 @@ static void rtw89_mac_dump_qta_lost_be(struct rtw89_dev *rtwdev) dump_err_status_dispatcher_be(rtwdev); } +static int rtw89_mac_cpu_io_rx(struct rtw89_dev *rtwdev, bool wow_enable) +{ + struct rtw89_mac_h2c_info h2c_info = {}; + struct rtw89_mac_c2h_info c2h_info = {}; + u32 ret; + + h2c_info.id = RTW89_FWCMD_H2CREG_FUNC_WOW_CPUIO_RX_CTRL; + h2c_info.content_len = sizeof(h2c_info.u.hdr); + h2c_info.u.hdr.w0 = u32_encode_bits(wow_enable, RTW89_H2CREG_WOW_CPUIO_RX_CTRL_EN); + + ret = rtw89_fw_msg_reg(rtwdev, &h2c_info, &c2h_info); + if (ret) + return ret; + + if (c2h_info.id != RTW89_FWCMD_C2HREG_FUNC_WOW_CPUIO_RX_ACK) + ret = -EINVAL; + + return ret; +} + +static int rtw89_wow_config_mac_be(struct rtw89_dev *rtwdev, bool enable_wow) +{ + if (enable_wow) { + rtw89_write32_set(rtwdev, R_BE_RX_STOP, B_BE_HOST_RX_STOP); + rtw89_write32_clr(rtwdev, R_BE_RX_FLTR_OPT, B_BE_SNIFFER_MODE); + rtw89_mac_cpu_io_rx(rtwdev, enable_wow); + rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false); + rtw89_write32(rtwdev, R_BE_FWD_ERR, 0); + rtw89_write32(rtwdev, R_BE_FWD_ACTN0, 0); + rtw89_write32(rtwdev, R_BE_FWD_ACTN1, 0); + rtw89_write32(rtwdev, R_BE_FWD_ACTN2, 0); + rtw89_write32(rtwdev, R_BE_FWD_TF0, 0); + rtw89_write32(rtwdev, R_BE_FWD_TF1, 0); + rtw89_write32(rtwdev, R_BE_FWD_ERR, 0); + rtw89_write32(rtwdev, R_BE_HW_PPDU_STATUS, 0); + rtw89_write8(rtwdev, R_BE_DBG_WOW_READY, WOWLAN_NOT_READY); + } else { + rtw89_mac_cpu_io_rx(rtwdev, enable_wow); + rtw89_write32_clr(rtwdev, R_BE_RX_STOP, B_BE_HOST_RX_STOP); + rtw89_write32_set(rtwdev, R_BE_RX_FLTR_OPT, R_BE_RX_FLTR_OPT); + rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true); + } + + return 0; +} + static void rtw89_mac_dump_cmac_err_status_be(struct rtw89_dev *rtwdev, u8 band) { @@ -2406,6 +2566,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = { .addr = R_BE_RXTRIG_TEST_USER_2, .mask = B_BE_RXTRIG_RU26_DIS, }, + .wow_ctrl = {.addr = R_BE_WOW_CTRL, .mask = B_BE_WOW_WOWEN,}, .check_mac_en = rtw89_mac_check_mac_en_be, .sys_init = sys_init_be, @@ -2439,6 +2600,9 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = { .parse_phycap_map = rtw89_parse_phycap_map_be, .cnv_efuse_state = rtw89_cnv_efuse_state_be, + .cfg_plt = rtw89_mac_cfg_plt_be, + .get_plt_cnt = rtw89_mac_get_plt_cnt_be, + .get_txpwr_cr = rtw89_mac_get_txpwr_cr_be, .write_xtal_si = rtw89_mac_write_xtal_si_be, @@ -2451,5 +2615,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = { .add_chan_list = rtw89_hw_scan_add_chan_list_be, .scan_offload = rtw89_fw_h2c_scan_offload_be, + + .wow_config_mac = rtw89_wow_config_mac_be, }; EXPORT_SYMBOL(rtw89_mac_gen_be); diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index 67d7294e488a..19001130ad94 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -218,7 +218,7 @@ int rtw89_pci_sync_skb_for_device_and_validate_rx_info(struct rtw89_dev *rtwdev, return ret; } -static void rtw89_pci_ctrl_txdma_ch_pcie(struct rtw89_dev *rtwdev, bool enable) +static void rtw89_pci_ctrl_txdma_ch_ax(struct rtw89_dev *rtwdev, bool enable) { const struct rtw89_pci_info *info = rtwdev->pci_info; const struct rtw89_reg_def *dma_stop1 = &info->dma_stop1; @@ -235,7 +235,7 @@ static void rtw89_pci_ctrl_txdma_ch_pcie(struct rtw89_dev *rtwdev, bool enable) } } -static void rtw89_pci_ctrl_txdma_fw_ch_pcie(struct rtw89_dev *rtwdev, bool enable) +static void rtw89_pci_ctrl_txdma_fw_ch_ax(struct rtw89_dev *rtwdev, bool enable) { const struct rtw89_pci_info *info = rtwdev->pci_info; const struct rtw89_reg_def *dma_stop1 = &info->dma_stop1; @@ -2524,7 +2524,7 @@ static void rtw89_pci_clr_idx_all_ax(struct rtw89_dev *rtwdev) B_AX_CLR_RXQ_IDX | B_AX_CLR_RPQ_IDX); } -static int rtw89_poll_txdma_ch_idle_pcie(struct rtw89_dev *rtwdev) +static int rtw89_pci_poll_txdma_ch_idle_ax(struct rtw89_dev *rtwdev) { const struct rtw89_pci_info *info = rtwdev->pci_info; u32 ret, check, dma_busy; @@ -2551,7 +2551,7 @@ static int rtw89_poll_txdma_ch_idle_pcie(struct rtw89_dev *rtwdev) return 0; } -static int rtw89_poll_rxdma_ch_idle_pcie(struct rtw89_dev *rtwdev) +static int rtw89_pci_poll_rxdma_ch_idle_ax(struct rtw89_dev *rtwdev) { const struct rtw89_pci_info *info = rtwdev->pci_info; u32 ret, check, dma_busy; @@ -2571,13 +2571,13 @@ static int rtw89_pci_poll_dma_all_idle(struct rtw89_dev *rtwdev) { u32 ret; - ret = rtw89_poll_txdma_ch_idle_pcie(rtwdev); + ret = rtw89_pci_poll_txdma_ch_idle_ax(rtwdev); if (ret) { rtw89_err(rtwdev, "txdma ch busy\n"); return ret; } - ret = rtw89_poll_rxdma_ch_idle_pcie(rtwdev); + ret = rtw89_pci_poll_rxdma_ch_idle_ax(rtwdev); if (ret) { rtw89_err(rtwdev, "rxdma ch busy\n"); return ret; @@ -2756,8 +2756,8 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev) } /* disable all channels except to FW CMD channel to download firmware */ - rtw89_pci_ctrl_txdma_ch_pcie(rtwdev, false); - rtw89_pci_ctrl_txdma_fw_ch_pcie(rtwdev, true); + rtw89_pci_ctrl_txdma_ch_ax(rtwdev, false); + rtw89_pci_ctrl_txdma_fw_ch_ax(rtwdev, true); /* start DMA activities */ rtw89_pci_ctrl_dma_all(rtwdev, true); @@ -2870,7 +2870,7 @@ static int rtw89_pci_ops_mac_post_init_ax(struct rtw89_dev *rtwdev) } /* enable DMA for all queues */ - rtw89_pci_ctrl_txdma_ch_pcie(rtwdev, true); + rtw89_pci_ctrl_txdma_ch_ax(rtwdev, true); /* Release PCI IO */ rtw89_write32_clr(rtwdev, info->dma_stop1.addr, @@ -3652,12 +3652,20 @@ static int rtw89_pci_filter_out(struct rtw89_dev *rtwdev) static void rtw89_pci_clkreq_set(struct rtw89_dev *rtwdev, bool enable) { - enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; - int ret; + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; if (rtw89_pci_disable_clkreq) return; + gen_def->clkreq_set(rtwdev, enable); +} + +static void rtw89_pci_clkreq_set_ax(struct rtw89_dev *rtwdev, bool enable) +{ + enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; + int ret; + ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_CLK_CTRL, PCIE_CLKDLY_HW_30US); if (ret) @@ -3689,24 +3697,31 @@ static void rtw89_pci_clkreq_set(struct rtw89_dev *rtwdev, bool enable) static void rtw89_pci_aspm_set(struct rtw89_dev *rtwdev, bool enable) { - enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; - u8 value = 0; - int ret; + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; if (rtw89_pci_disable_aspm_l1) return; + gen_def->aspm_set(rtwdev, enable); +} + +static void rtw89_pci_aspm_set_ax(struct rtw89_dev *rtwdev, bool enable) +{ + enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; + u8 value = 0; + int ret; + ret = rtw89_pci_read_config_byte(rtwdev, RTW89_PCIE_ASPM_CTRL, &value); if (ret) - rtw89_err(rtwdev, "failed to read ASPM Delay\n"); + rtw89_warn(rtwdev, "failed to read ASPM Delay\n"); - value &= ~(RTW89_L1DLY_MASK | RTW89_L0DLY_MASK); - value |= FIELD_PREP(RTW89_L1DLY_MASK, PCIE_L1DLY_16US) | - FIELD_PREP(RTW89_L0DLY_MASK, PCIE_L0SDLY_4US); + u8p_replace_bits(&value, PCIE_L1DLY_16US, RTW89_L1DLY_MASK); + u8p_replace_bits(&value, PCIE_L0SDLY_4US, RTW89_L0DLY_MASK); ret = rtw89_pci_write_config_byte(rtwdev, RTW89_PCIE_ASPM_CTRL, value); if (ret) - rtw89_err(rtwdev, "failed to read ASPM Delay\n"); + rtw89_warn(rtwdev, "failed to read ASPM Delay\n"); if (chip_id == RTL8852A || chip_id == RTL8852B || chip_id == RTL8851B) { if (enable) @@ -3793,6 +3808,17 @@ static void rtw89_pci_link_cfg(struct rtw89_dev *rtwdev) static void rtw89_pci_l1ss_set(struct rtw89_dev *rtwdev, bool enable) { + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; + + if (rtw89_pci_disable_l1ss) + return; + + gen_def->l1ss_set(rtwdev, enable); +} + +static void rtw89_pci_l1ss_set_ax(struct rtw89_dev *rtwdev, bool enable) +{ enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; int ret; @@ -4066,6 +4092,14 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_ax = { .lv1rst_stop_dma = rtw89_pci_lv1rst_stop_dma_ax, .lv1rst_start_dma = rtw89_pci_lv1rst_start_dma_ax, + + .ctrl_txdma_ch = rtw89_pci_ctrl_txdma_ch_ax, + .ctrl_txdma_fw_ch = rtw89_pci_ctrl_txdma_fw_ch_ax, + .poll_txdma_ch_idle = rtw89_pci_poll_txdma_ch_idle_ax, + + .aspm_set = rtw89_pci_aspm_set_ax, + .clkreq_set = rtw89_pci_clkreq_set_ax, + .l1ss_set = rtw89_pci_l1ss_set_ax, }; EXPORT_SYMBOL(rtw89_pci_gen_ax); @@ -4100,10 +4134,11 @@ static const struct rtw89_hci_ops rtw89_pci_ops = { .recovery_start = rtw89_pci_ops_recovery_start, .recovery_complete = rtw89_pci_ops_recovery_complete, - .ctrl_txdma_ch = rtw89_pci_ctrl_txdma_ch_pcie, - .ctrl_txdma_fw_ch = rtw89_pci_ctrl_txdma_fw_ch_pcie, + .ctrl_txdma_ch = rtw89_pci_ctrl_txdma_ch, + .ctrl_txdma_fw_ch = rtw89_pci_ctrl_txdma_fw_ch, .ctrl_trxhci = rtw89_pci_ctrl_dma_trx, - .poll_txdma_ch = rtw89_poll_txdma_ch_idle_pcie, + .poll_txdma_ch_idle = rtw89_pci_poll_txdma_ch_idle, + .clr_idx_all = rtw89_pci_clr_idx_all, .clear = rtw89_pci_clear_resource, .disable_intr = rtw89_pci_disable_intr_lock, diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index 532f78eaf6df..a63b6b7c9bfa 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -282,6 +282,21 @@ #define B_BE_PCIE_EN_SWENT_L23 BIT(1) #define B_BE_SEL_REQ_EXIT_L1 BIT(0) +#define R_BE_PCIE_MIX_CFG 0x300C +#define B_BE_L1SS_TIMEOUT_CTRL BIT(18) +#define B_BE_ASPM_CTRL_L1 BIT(17) +#define B_BE_ASPM_CTRL_L0 BIT(16) +#define B_BE_XFER_PENDING_FW BIT(11) +#define B_BE_XFER_PENDING BIT(10) +#define B_BE_REQ_EXIT_L1 BIT(9) +#define B_BE_REQ_ENTR_L1 BIT(8) +#define B_BE_L1SUB_ENABLE BIT(0) + +#define R_BE_L1_CLK_CTRL 0x3010 +#define B_BE_RAS_SD_HOLD_LTSSM BIT(12) +#define B_BE_CLK_REQ_N BIT(1) +#define B_BE_CLK_PM_EN BIT(0) + #define R_BE_PCIE_LAT_CTRL 0x3044 #define B_BE_ELBI_PHY_REMAP_MASK GENMASK(29, 24) #define B_BE_SYS_SUS_L12_EN BIT(17) @@ -290,6 +305,8 @@ #define B_BE_RTK_LDO_POWER_LATENCY_MASK GENMASK(11, 10) #define B_BE_RTK_LDO_BIAS_LATENCY_MASK GENMASK(9, 8) #define B_BE_CLK_REQ_LAT_MASK GENMASK(7, 4) +#define B_BE_RTK_PM_SEL_OPT BIT(1) +#define B_BE_CLK_REQ_SEL BIT(0) #define R_BE_PCIE_HIMR0 0x30B0 #define B_BE_PCIE_HB1_IND_INTA_IMR BIT(31) @@ -925,6 +942,8 @@ #define B_BE_SER_L1SUB_IMR BIT(1) #define B_BE_SER_PMU_IMR BIT(0) +#define R_BE_REG_PL1_ISR 0x34B4 + #define R_BE_RX_APPEND_MODE 0x8920 #define B_BE_APPEND_OFFSET_MASK GENMASK(23, 16) #define B_BE_APPEND_LEN_MASK GENMASK(15, 0) @@ -1066,6 +1085,15 @@ enum rtw89_pcie_clkdly_hw { PCIE_CLKDLY_HW_200US = 0x5, }; +enum rtw89_pcie_clkdly_hw_v1 { + PCIE_CLKDLY_HW_V1_0 = 0, + PCIE_CLKDLY_HW_V1_16US = 0x1, + PCIE_CLKDLY_HW_V1_32US = 0x2, + PCIE_CLKDLY_HW_V1_64US = 0x3, + PCIE_CLKDLY_HW_V1_80US = 0x4, + PCIE_CLKDLY_HW_V1_96US = 0x5, +}; + enum mac_ax_bd_trunc_mode { MAC_AX_BD_NORM, MAC_AX_BD_TRUNC, @@ -1216,6 +1244,14 @@ struct rtw89_pci_gen_def { int (*lv1rst_stop_dma)(struct rtw89_dev *rtwdev); int (*lv1rst_start_dma)(struct rtw89_dev *rtwdev); + + void (*ctrl_txdma_ch)(struct rtw89_dev *rtwdev, bool enable); + void (*ctrl_txdma_fw_ch)(struct rtw89_dev *rtwdev, bool enable); + int (*poll_txdma_ch_idle)(struct rtw89_dev *rtwdev); + + void (*aspm_set)(struct rtw89_dev *rtwdev, bool enable); + void (*clkreq_set)(struct rtw89_dev *rtwdev, bool enable); + void (*l1ss_set)(struct rtw89_dev *rtwdev, bool enable); }; struct rtw89_pci_info { @@ -1524,6 +1560,7 @@ static inline bool rtw89_pci_ltr_is_err_reg_val(u32 val) } extern const struct dev_pm_ops rtw89_pm_ops; +extern const struct dev_pm_ops rtw89_pm_ops_be; extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set; extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_v1; extern const struct rtw89_pci_ch_dma_addr_set rtw89_pci_ch_dma_addr_set_be; @@ -1679,4 +1716,27 @@ static inline int rtw89_pci_reset_bdram(struct rtw89_dev *rtwdev) return gen_def->rst_bdram(rtwdev); } +static inline void rtw89_pci_ctrl_txdma_ch(struct rtw89_dev *rtwdev, bool enable) +{ + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; + + return gen_def->ctrl_txdma_ch(rtwdev, enable); +} + +static inline void rtw89_pci_ctrl_txdma_fw_ch(struct rtw89_dev *rtwdev, bool enable) +{ + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; + + return gen_def->ctrl_txdma_fw_ch(rtwdev, enable); +} + +static inline int rtw89_pci_poll_txdma_ch_idle(struct rtw89_dev *rtwdev) +{ + const struct rtw89_pci_info *info = rtwdev->pci_info; + const struct rtw89_pci_gen_def *gen_def = info->gen_def; + + return gen_def->poll_txdma_ch_idle(rtwdev); +} #endif diff --git a/drivers/net/wireless/realtek/rtw89/pci_be.c b/drivers/net/wireless/realtek/rtw89/pci_be.c index 5c9e39357773..7cc328222965 100644 --- a/drivers/net/wireless/realtek/rtw89/pci_be.c +++ b/drivers/net/wireless/realtek/rtw89/pci_be.c @@ -19,6 +19,54 @@ enum pcie_rxbd_mode { #define PL0_TMR_MAC_1MS 0x27100 #define PL0_TMR_AUX_1MS 0x1E848 +static void rtw89_pci_aspm_set_be(struct rtw89_dev *rtwdev, bool enable) +{ + struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; + struct pci_dev *pdev = rtwpci->pdev; + u8 value = 0; + int ret; + + ret = pci_read_config_byte(pdev, RTW89_PCIE_ASPM_CTRL, &value); + if (ret) + rtw89_warn(rtwdev, "failed to read ASPM Delay\n"); + + u8p_replace_bits(&value, PCIE_L1DLY_16US, RTW89_L1DLY_MASK); + + ret = pci_write_config_byte(pdev, RTW89_PCIE_ASPM_CTRL, value); + if (ret) + rtw89_warn(rtwdev, "failed to write ASPM Delay\n"); + + if (enable) + rtw89_write32_set(rtwdev, R_AX_PCIE_MIX_CFG_V1, + B_BE_ASPM_CTRL_L1); + else + rtw89_write32_clr(rtwdev, R_AX_PCIE_MIX_CFG_V1, + B_BE_ASPM_CTRL_L1); +} + +static void rtw89_pci_l1ss_set_be(struct rtw89_dev *rtwdev, bool enable) +{ + if (enable) + rtw89_write32_set(rtwdev, R_BE_PCIE_MIX_CFG, + B_BE_L1SUB_ENABLE); + else + rtw89_write32_clr(rtwdev, R_BE_PCIE_MIX_CFG, + B_BE_L1SUB_ENABLE); +} + +static void rtw89_pci_clkreq_set_be(struct rtw89_dev *rtwdev, bool enable) +{ + rtw89_write32_mask(rtwdev, R_BE_PCIE_LAT_CTRL, B_BE_CLK_REQ_LAT_MASK, + PCIE_CLKDLY_HW_V1_0); + + if (enable) + rtw89_write32_set(rtwdev, R_BE_L1_CLK_CTRL, + B_BE_CLK_PM_EN); + else + rtw89_write32_clr(rtwdev, R_AX_L1_CLK_CTRL, + B_BE_CLK_PM_EN); +} + static void _patch_pcie_power_wake_be(struct rtw89_dev *rtwdev, bool power_up) { if (power_up) @@ -269,8 +317,7 @@ static void rtw89_pci_ser_setting_be(struct rtw89_dev *rtwdev) rtw89_write32(rtwdev, R_BE_REG_PL1_MASK, val32); } -static void rtw89_pci_ctrl_txdma_ch_be(struct rtw89_dev *rtwdev, bool all_en, - bool h2c_en) +static void rtw89_pci_ctrl_txdma_ch_be(struct rtw89_dev *rtwdev, bool enable) { u32 mask_all; u32 val; @@ -283,12 +330,19 @@ static void rtw89_pci_ctrl_txdma_ch_be(struct rtw89_dev *rtwdev, bool all_en, val = rtw89_read32(rtwdev, R_BE_HAXI_DMA_STOP1); val |= B_BE_STOP_CH13 | B_BE_STOP_CH14; - if (all_en) + if (enable) val &= ~mask_all; else val |= mask_all; - if (h2c_en) + rtw89_write32(rtwdev, R_BE_HAXI_DMA_STOP1, val); +} + +static void rtw89_pci_ctrl_txdma_fw_ch_be(struct rtw89_dev *rtwdev, bool enable) +{ + u32 val = rtw89_read32(rtwdev, R_BE_HAXI_DMA_STOP1); + + if (enable) val &= ~B_BE_STOP_CH12; else val |= B_BE_STOP_CH12; @@ -327,7 +381,8 @@ static int rtw89_pci_ops_mac_pre_init_be(struct rtw89_dev *rtwdev) rtw89_pci_pcie_setting_be(rtwdev); rtw89_pci_ser_setting_be(rtwdev); - rtw89_pci_ctrl_txdma_ch_be(rtwdev, false, true); + rtw89_pci_ctrl_txdma_ch_be(rtwdev, false); + rtw89_pci_ctrl_txdma_fw_ch_be(rtwdev, true); rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_ENABLE, MAC_AX_PCIE_ENABLE, MAC_AX_PCIE_ENABLE); @@ -437,7 +492,8 @@ static int rtw89_pci_ops_mac_post_init_be(struct rtw89_dev *rtwdev) rtw89_pci_ctrl_trxdma_pcie_be(rtwdev, MAC_AX_PCIE_IGNORE, MAC_AX_PCIE_IGNORE, MAC_AX_PCIE_ENABLE); rtw89_pci_ctrl_wpdma_pcie_be(rtwdev, true); - rtw89_pci_ctrl_txdma_ch_be(rtwdev, true, true); + rtw89_pci_ctrl_txdma_ch_be(rtwdev, true); + rtw89_pci_ctrl_txdma_fw_ch_be(rtwdev, true); rtw89_pci_configure_mit_be(rtwdev); return 0; @@ -494,6 +550,46 @@ static int rtw89_pci_lv1rst_start_dma_be(struct rtw89_dev *rtwdev) return 0; } +static int __maybe_unused rtw89_pci_suspend_be(struct device *dev) +{ + struct ieee80211_hw *hw = dev_get_drvdata(dev); + struct rtw89_dev *rtwdev = hw->priv; + + rtw89_write32_set(rtwdev, R_BE_RSV_CTRL, B_BE_WLOCK_1C_BIT6); + rtw89_write32_set(rtwdev, R_BE_RSV_CTRL, B_BE_R_DIS_PRST); + rtw89_write32_clr(rtwdev, R_BE_RSV_CTRL, B_BE_WLOCK_1C_BIT6); + rtw89_write32_set(rtwdev, R_BE_PCIE_FRZ_CLK, B_BE_PCIE_FRZ_REG_RST); + rtw89_write32_clr(rtwdev, R_BE_REG_PL1_MASK, B_BE_SER_PM_MASTER_IMR); + return 0; +} + +static int __maybe_unused rtw89_pci_resume_be(struct device *dev) +{ + struct ieee80211_hw *hw = dev_get_drvdata(dev); + struct rtw89_dev *rtwdev = hw->priv; + u32 polling; + int ret; + + rtw89_write32_set(rtwdev, R_BE_RSV_CTRL, B_BE_WLOCK_1C_BIT6); + rtw89_write32_clr(rtwdev, R_BE_RSV_CTRL, B_BE_R_DIS_PRST); + rtw89_write32_clr(rtwdev, R_BE_RSV_CTRL, B_BE_WLOCK_1C_BIT6); + rtw89_write32_clr(rtwdev, R_BE_PCIE_FRZ_CLK, B_BE_PCIE_FRZ_REG_RST); + rtw89_write32_clr(rtwdev, R_BE_SER_PL1_CTRL, B_BE_PL1_SER_PL1_EN); + + ret = read_poll_timeout_atomic(rtw89_read32, polling, !polling, 1, 1000, + false, rtwdev, R_BE_REG_PL1_ISR); + if (ret) + rtw89_warn(rtwdev, "[ERR] PCIE SER clear polling fail\n"); + + rtw89_write32_set(rtwdev, R_BE_SER_PL1_CTRL, B_BE_PL1_SER_PL1_EN); + rtw89_write32_set(rtwdev, R_BE_REG_PL1_MASK, B_BE_SER_PM_MASTER_IMR); + + return 0; +} + +SIMPLE_DEV_PM_OPS(rtw89_pm_ops_be, rtw89_pci_suspend_be, rtw89_pci_resume_be); +EXPORT_SYMBOL(rtw89_pm_ops_be); + const struct rtw89_pci_gen_def rtw89_pci_gen_be = { .isr_rdu = B_BE_RDU_CH1_INT | B_BE_RDU_CH0_INT, .isr_halt_c2h = B_BE_HALT_C2H_INT, @@ -510,5 +606,13 @@ const struct rtw89_pci_gen_def rtw89_pci_gen_be = { .lv1rst_stop_dma = rtw89_pci_lv1rst_stop_dma_be, .lv1rst_start_dma = rtw89_pci_lv1rst_start_dma_be, + + .ctrl_txdma_ch = rtw89_pci_ctrl_txdma_ch_be, + .ctrl_txdma_fw_ch = rtw89_pci_ctrl_txdma_fw_ch_be, + .poll_txdma_ch_idle = rtw89_pci_poll_txdma_ch_idle_be, + + .aspm_set = rtw89_pci_aspm_set_be, + .clkreq_set = rtw89_pci_clkreq_set_be, + .l1ss_set = rtw89_pci_l1ss_set_be, }; EXPORT_SYMBOL(rtw89_pci_gen_be); diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h index 37ccd8ffa87a..72e448e91b6f 100644 --- a/drivers/net/wireless/realtek/rtw89/reg.h +++ b/drivers/net/wireless/realtek/rtw89/reg.h @@ -3510,8 +3510,13 @@ #define B_AX_PTA_EDCCA_EN BIT(0) #define R_BTC_COEX_WL_REQ 0xDA24 +#define R_BTC_COEX_WL_REQ_BE 0xE324 +#define B_BTC_TX_NULL_HI BIT(23) #define B_BTC_TX_BCN_HI BIT(22) +#define B_BTC_TX_TRI_HI BIT(17) #define B_BTC_RSP_ACK_HI BIT(10) +#define B_BTC_PRI_MASK_TX_TIME GENMASK(4, 3) +#define B_BTC_PRI_MASK_RX_TIME_V1 GENMASK(2, 1) #define R_BTC_BREAK_TABLE 0xDA2C #define BTC_BREAK_PARAM 0xf0ffffff @@ -3759,6 +3764,19 @@ #define B_BE_SYM_PADPDN_WL_RFC1_1P3 BIT(6) #define B_BE_SYM_PADPDN_WL_RFC0_1P3 BIT(5) +#define R_BE_RSV_CTRL 0x001C +#define B_BE_HR_BE_DBG GENMASK(23, 12) +#define B_BE_R_SYM_DIS_PCIE_FLR BIT(9) +#define B_BE_R_EN_HRST_PWRON BIT(8) +#define B_BE_LOCK_ALL_EN BIT(7) +#define B_BE_R_DIS_PRST BIT(6) +#define B_BE_WLOCK_1C_BIT6 BIT(5) +#define B_BE_WLOCK_40 BIT(4) +#define B_BE_WLOCK_08 BIT(3) +#define B_BE_WLOCK_04 BIT(2) +#define B_BE_WLOCK_00 BIT(1) +#define B_BE_WLOCK_ALL BIT(0) + #define R_BE_AFE_LDO_CTRL 0x0020 #define B_BE_FORCE_MACBBBT_PWR_ON BIT(31) #define B_BE_R_SYM_WLPOFF_P4_PC_EN BIT(28) @@ -4451,6 +4469,9 @@ #define B_BE_HCI_RXDMA_EN BIT(1) #define B_BE_HCI_TXDMA_EN BIT(0) +#define R_BE_DBG_WOW_READY 0x815E +#define B_BE_DBG_WOW_READY GENMASK(7, 0) + #define R_BE_DMAC_FUNC_EN 0x8400 #define B_BE_DMAC_CRPRT BIT(31) #define B_BE_MAC_FUNC_EN BIT(30) @@ -5004,6 +5025,12 @@ B_BE_CR_WRFF_OVERFLOW_ERR_INT_EN | \ B_BE_CR_WRFF_UNDERFLOW_ERR_INT_EN) +#define R_BE_RX_STOP 0x8914 +#define B_BE_CPU_RX_STOP BIT(17) +#define B_BE_HOST_RX_STOP BIT(16) +#define B_BE_CPU_RX_CH_STOP_MSK GENMASK(15, 8) +#define B_BE_HOST_RX_CH_STOP_MSK GENMASK(5, 0) + #define R_BE_DISP_FWD_WLAN_0 0x8938 #define B_BE_FWD_WLAN_CPU_TYPE_13_MASK GENMASK(31, 30) #define B_BE_FWD_WLAN_CPU_TYPE_12_MASK GENMASK(29, 28) @@ -5519,6 +5546,13 @@ #define B_BE_DROP_NONDMA_PPDU BIT(2) #define B_BE_APPEND_FCS BIT(0) +#define R_BE_FWD_ERR 0x9C10 +#define R_BE_FWD_ACTN0 0x9C14 +#define R_BE_FWD_ACTN1 0x9C18 +#define R_BE_FWD_ACTN2 0x9C1C +#define R_BE_FWD_TF0 0x9C20 +#define R_BE_FWD_TF1 0x9C24 + #define R_BE_HW_PPDU_STATUS 0x9C30 #define B_BE_FWD_RPKTTYPE_MASK GENMASK(31, 26) #define B_BE_FWD_PPDU_PRTID_MASK GENMASK(25, 23) @@ -5535,6 +5569,12 @@ #define B_BE_CUT_AMSDU_CHKLEN_L_TH_MASK GENMASK(23, 16) #define B_BE_CUT_AMSDU_CHKLEN_H_TH_MASK GENMASK(15, 0) +#define R_BE_WOW_CTRL 0x9CB8 +#define B_BE_WOW_HCI BIT(5) +#define B_BE_WOW_DROP BIT(2) +#define B_BE_WOW_WOWEN BIT(1) +#define B_BE_WOW_FORCE_WAKEUP BIT(0) + #define R_BE_RX_HDRTRNS 0x9CC0 #define B_BE_RX_MGN_MLD_ADDR_EN BIT(6) #define B_BE_HDR_INFO_MASK GENMASK(5, 4) @@ -5932,6 +5972,36 @@ #define B_BE_MACID_ACQ_GRP0_CLR_P BIT(2) #define B_BE_R_MACID_ACQ_CHK_EN BIT(0) +#define R_BE_BT_BREAK_TABLE 0x0E344 + +#define R_BE_GNT_SW_CTRL 0x0E348 +#define B_BE_WL_ACT2_VAL BIT(25) +#define B_BE_WL_ACT2_SWCTRL BIT(24) +#define B_BE_WL_ACT_VAL BIT(23) +#define B_BE_WL_ACT_SWCTRL BIT(22) +#define B_BE_GNT_BT_RX_BB1_VAL BIT(21) +#define B_BE_GNT_BT_RX_BB1_SWCTRL BIT(20) +#define B_BE_GNT_BT_TX_BB1_VAL BIT(19) +#define B_BE_GNT_BT_TX_BB1_SWCTRL BIT(18) +#define B_BE_GNT_BT_RX_BB0_VAL BIT(17) +#define B_BE_GNT_BT_RX_BB0_SWCTRL BIT(16) +#define B_BE_GNT_BT_TX_BB0_VAL BIT(15) +#define B_BE_GNT_BT_TX_BB0_SWCTRL BIT(14) +#define B_BE_GNT_WL_RX_VAL BIT(13) +#define B_BE_GNT_WL_RX_SWCTRL BIT(12) +#define B_BE_GNT_WL_TX_VAL BIT(11) +#define B_BE_GNT_WL_TX_SWCTRL BIT(10) +#define B_BE_GNT_BT_BB1_VAL BIT(9) +#define B_BE_GNT_BT_BB1_SWCTRL BIT(8) +#define B_BE_GNT_WL_BB1_VAL BIT(7) +#define B_BE_GNT_WL_BB1_SWCTRL BIT(6) +#define B_BE_GNT_BT_BB0_VAL BIT(5) +#define B_BE_GNT_BT_BB0_SWCTRL BIT(4) +#define B_BE_GNT_WL_BB0_VAL BIT(3) +#define B_BE_GNT_WL_BB0_SWCTRL BIT(2) +#define B_BE_GNT_WL_BB_PWR_VAL BIT(1) +#define B_BE_GNT_WL_BB_PWR_SWCTRL BIT(0) + #define R_BE_PWR_MACID_PATH_BASE 0x0E500 #define R_BE_PWR_MACID_LMT_BASE 0x0ED00 @@ -6457,6 +6527,20 @@ #define B_BE_PORT_DROP_4_0_MASK GENMASK(20, 16) #define B_BE_MBSSID_DROP_15_0_MASK GENMASK(15, 0) +#define R_BE_BT_PLT 0x1087C +#define R_BE_BT_PLT_C1 0x1487C +#define B_BE_BT_PLT_PKT_CNT_MASK GENMASK(31, 16) +#define B_BE_BT_PLT_RST BIT(9) +#define B_BE_PLT_EN BIT(8) +#define B_BE_RX_PLT_GNT_LTE_RX BIT(7) +#define B_BE_RX_PLT_GNT_BT_RX BIT(6) +#define B_BE_RX_PLT_GNT_BT_TX BIT(5) +#define B_BE_RX_PLT_GNT_WL BIT(4) +#define B_BE_TX_PLT_GNT_LTE_RX BIT(3) +#define B_BE_TX_PLT_GNT_BT_RX BIT(2) +#define B_BE_TX_PLT_GNT_BT_TX BIT(1) +#define B_BE_TX_PLT_GNT_WL BIT(0) + #define R_BE_PTCL_BSS_COLOR_0 0x108A0 #define R_BE_PTCL_BSS_COLOR_0_C1 0x148A0 #define B_BE_BSS_COLOB_BE_PORT_3_MASK GENMASK(29, 24) diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c index 83db0a686ee2..51d3e61eaa1d 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c @@ -1921,41 +1921,81 @@ static u8 rtw8851b_get_thermal(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_p static void rtw8851b_btc_set_rfe(struct rtw89_dev *rtwdev) { - struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; - - module->rfe_type = rtwdev->efuse.rfe_type; - module->cv = rtwdev->hal.cv; - module->bt_solo = 0; - module->switch_type = BTC_SWITCH_INTERNAL; - module->ant.isolation = 10; - module->kt_ver_adie = rtwdev->hal.acv; - - if (module->rfe_type == 0) - return; - - /* rfe_type 3*n+1: 1-Ant(shared), - * 3*n+2: 2-Ant+Div(non-shared), - * 3*n+3: 2-Ant+no-Div(non-shared) - */ - module->ant.num = (module->rfe_type % 3 == 1) ? 1 : 2; - /* WL-1ss at S0, btg at s0 (On 1 WL RF) */ - module->ant.single_pos = RF_PATH_A; - module->ant.btg_pos = RF_PATH_A; - module->ant.stream_cnt = 1; - - if (module->ant.num == 1) { - module->ant.type = BTC_ANT_SHARED; - module->bt_pos = BTC_BT_BTG; - module->wa_type = 1; - module->ant.diversity = 0; - } else { /* ant.num == 2 */ - module->ant.type = BTC_ANT_DEDICATED; - module->bt_pos = BTC_BT_ALONE; - module->switch_type = BTC_SWITCH_EXTERNAL; - module->wa_type = 0; - if (module->rfe_type % 3 == 2) - module->ant.diversity = 1; + const struct rtw89_btc_ver *ver = rtwdev->btc.ver; + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; + + if (ver->fcxinit == 7) { + md->md_v7.rfe_type = rtwdev->efuse.rfe_type; + md->md_v7.kt_ver = rtwdev->hal.cv; + md->md_v7.bt_solo = 0; + md->md_v7.switch_type = BTC_SWITCH_INTERNAL; + md->md_v7.ant.isolation = 10; + md->md_v7.kt_ver_adie = rtwdev->hal.acv; + + if (md->md_v7.rfe_type == 0) + return; + + /* rfe_type 3*n+1: 1-Ant(shared), + * 3*n+2: 2-Ant+Div(non-shared), + * 3*n+3: 2-Ant+no-Div(non-shared) + */ + md->md_v7.ant.num = (md->md_v7.rfe_type % 3 == 1) ? 1 : 2; + /* WL-1ss at S0, btg at s0 (On 1 WL RF) */ + md->md_v7.ant.single_pos = RF_PATH_A; + md->md_v7.ant.btg_pos = RF_PATH_A; + md->md_v7.ant.stream_cnt = 1; + + if (md->md_v7.ant.num == 1) { + md->md_v7.ant.type = BTC_ANT_SHARED; + md->md_v7.bt_pos = BTC_BT_BTG; + md->md_v7.wa_type = 1; + md->md_v7.ant.diversity = 0; + } else { /* ant.num == 2 */ + md->md_v7.ant.type = BTC_ANT_DEDICATED; + md->md_v7.bt_pos = BTC_BT_ALONE; + md->md_v7.switch_type = BTC_SWITCH_EXTERNAL; + md->md_v7.wa_type = 0; + if (md->md_v7.rfe_type % 3 == 2) + md->md_v7.ant.diversity = 1; + } + rtwdev->btc.btg_pos = md->md_v7.ant.btg_pos; + rtwdev->btc.ant_type = md->md_v7.ant.type; + } else { + md->md.rfe_type = rtwdev->efuse.rfe_type; + md->md.cv = rtwdev->hal.cv; + md->md.bt_solo = 0; + md->md.switch_type = BTC_SWITCH_INTERNAL; + md->md.ant.isolation = 10; + md->md.kt_ver_adie = rtwdev->hal.acv; + + if (md->md.rfe_type == 0) + return; + + /* rfe_type 3*n+1: 1-Ant(shared), + * 3*n+2: 2-Ant+Div(non-shared), + * 3*n+3: 2-Ant+no-Div(non-shared) + */ + md->md.ant.num = (md->md.rfe_type % 3 == 1) ? 1 : 2; + /* WL-1ss at S0, btg at s0 (On 1 WL RF) */ + md->md.ant.single_pos = RF_PATH_A; + md->md.ant.btg_pos = RF_PATH_A; + md->md.ant.stream_cnt = 1; + + if (md->md.ant.num == 1) { + md->md.ant.type = BTC_ANT_SHARED; + md->md.bt_pos = BTC_BT_BTG; + md->md.wa_type = 1; + md->md.ant.diversity = 0; + } else { /* ant.num == 2 */ + md->md.ant.type = BTC_ANT_DEDICATED; + md->md.bt_pos = BTC_BT_ALONE; + md->md.switch_type = BTC_SWITCH_EXTERNAL; + md->md.wa_type = 0; + if (md->md.rfe_type % 3 == 2) + md->md.ant.diversity = 1; + } + rtwdev->btc.btg_pos = md->md.ant.btg_pos; + rtwdev->btc.ant_type = md->md.ant.type; } } @@ -1965,7 +2005,7 @@ void rtw8851b_set_trx_mask(struct rtw89_dev *rtwdev, u8 path, u8 group, u32 val) if (group > BTC_BT_SS_GROUP) group--; /* Tx-group=1, Rx-group=2 */ - if (rtwdev->btc.mdinfo.ant.type == BTC_ANT_SHARED) /* 1-Ant */ + if (rtwdev->btc.ant_type == BTC_ANT_SHARED) /* 1-Ant */ group += 3; rtw89_write_rf(rtwdev, path, RR_LUTWA, RFREG_MASK, group); @@ -1980,9 +2020,9 @@ static void rtw8851b_btc_init_cfg(struct rtw89_dev *rtwdev) }; const struct rtw89_chip_info *chip = rtwdev->chip; struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; - struct rtw89_btc_ant_info *ant = &module->ant; - u8 path, path_min, path_max; + union rtw89_btc_module_info *md = &btc->mdinfo; + const struct rtw89_btc_ver *ver = btc->ver; + u8 path, path_min, path_max, str_cnt, ant_sing_pos; /* PTA init */ rtw89_mac_coex_init(rtwdev, &coex_params); @@ -1991,9 +2031,17 @@ static void rtw8851b_btc_init_cfg(struct rtw89_dev *rtwdev) chip->ops->btc_set_wl_pri(rtwdev, BTC_PRI_MASK_TX_RESP, true); chip->ops->btc_set_wl_pri(rtwdev, BTC_PRI_MASK_BEACON, true); + if (ver->fcxinit == 7) { + str_cnt = md->md_v7.ant.stream_cnt; + ant_sing_pos = md->md_v7.ant.single_pos; + } else { + str_cnt = md->md.ant.stream_cnt; + ant_sing_pos = md->md.ant.single_pos; + } + /* for 1-Ant && 1-ss case: only 1-path */ - if (ant->stream_cnt == 1) { - path_min = ant->single_pos; + if (str_cnt == 1) { + path_min = ant_sing_pos; path_max = path_min; } else { path_min = RF_PATH_A; @@ -2016,7 +2064,7 @@ static void rtw8851b_btc_init_cfg(struct rtw89_dev *rtwdev) /* if GNT_WL = 0 && BT = Tx_group --> * Shared-Ant && BTG-path:WL mask(0x55f), others:WL THRU(0x5ff) */ - if (ant->type == BTC_ANT_SHARED && ant->btg_pos == path) + if (btc->ant_type == BTC_ANT_SHARED && btc->btg_pos == path) rtw8851b_set_trx_mask(rtwdev, path, BTC_BT_TX_GROUP, 0x55f); else rtw8851b_set_trx_mask(rtwdev, path, BTC_BT_TX_GROUP, 0x5ff); @@ -2148,19 +2196,18 @@ void rtw8851b_btc_update_bt_cnt(struct rtw89_dev *rtwdev) static void rtw8851b_btc_wl_s1_standby(struct rtw89_dev *rtwdev, bool state) { struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_ant_info *ant = &btc->mdinfo.ant; - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWE, RFREG_MASK, 0x80000); - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWA, RFREG_MASK, 0x1); - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWD1, RFREG_MASK, 0x110); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWE, RFREG_MASK, 0x80000); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWA, RFREG_MASK, 0x1); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWD1, RFREG_MASK, 0x110); /* set WL standby = Rx for GNT_BT_Tx = 1->0 settle issue */ if (state) - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWD0, RFREG_MASK, 0x179c); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWD0, RFREG_MASK, 0x179c); else - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWD0, RFREG_MASK, 0x208); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWD0, RFREG_MASK, 0x208); - rtw89_write_rf(rtwdev, ant->btg_pos, RR_LUTWE, RFREG_MASK, 0x0); + rtw89_write_rf(rtwdev, btc->btg_pos, RR_LUTWE, RFREG_MASK, 0x0); } #define LNA2_51B_MA 0x700 @@ -2175,7 +2222,6 @@ static void rtw8851b_btc_set_wl_rx_gain(struct rtw89_dev *rtwdev, u32 level) * level=1 Fix LNA2=5: TIA 1/0= (LNA2,TIAN6) = (5,0)/(5,1) = 18dB/12dB */ struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_ant_info *ant = &btc->mdinfo.ant; const struct rtw89_reg2_def *rf; u32 n, i, val; @@ -2203,10 +2249,10 @@ static void rtw8851b_btc_set_wl_rx_gain(struct rtw89_dev *rtwdev, u32 level) for (i = 0; i < n; i++, rf++) { val = rf->data; /* bit[10] = 1 if non-shared-ant for 8851b */ - if (btc->mdinfo.ant.type == BTC_ANT_DEDICATED) + if (btc->ant_type == BTC_ANT_DEDICATED) val |= 0x4; - rtw89_write_rf(rtwdev, ant->btg_pos, rf->addr, LNA2_51B_MA, val); + rtw89_write_rf(rtwdev, btc->btg_pos, rf->addr, LNA2_51B_MA, val); } } @@ -2460,6 +2506,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = { .c2h_counter_reg = {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8}, .c2h_regs = rtw8851b_c2h_regs, .page_regs = &rtw8851b_page_regs, + .wow_reason_reg = R_AX_C2HREG_DATA3 + 3, .cfo_src_fd = true, .cfo_hw_comp = true, .dcfo_comp = &rtw8851b_dcfo_comp, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c index 8e808ded5d52..2deadec715cf 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c @@ -1665,28 +1665,55 @@ static u8 rtw8852a_get_thermal(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_p static void rtw8852a_btc_set_rfe(struct rtw89_dev *rtwdev) { - struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; + const struct rtw89_btc_ver *ver = rtwdev->btc.ver; + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; - module->rfe_type = rtwdev->efuse.rfe_type; - module->cv = rtwdev->hal.cv; - module->bt_solo = 0; - module->switch_type = BTC_SWITCH_INTERNAL; + if (ver->fcxinit == 7) { + md->md_v7.rfe_type = rtwdev->efuse.rfe_type; + md->md_v7.kt_ver = rtwdev->hal.cv; + md->md_v7.bt_solo = 0; + md->md_v7.switch_type = BTC_SWITCH_INTERNAL; - if (module->rfe_type > 0) - module->ant.num = (module->rfe_type % 2 ? 2 : 3); - else - module->ant.num = 2; + if (md->md_v7.rfe_type > 0) + md->md_v7.ant.num = (md->md_v7.rfe_type % 2 ? 2 : 3); + else + md->md_v7.ant.num = 2; - module->ant.diversity = 0; - module->ant.isolation = 10; + md->md_v7.ant.diversity = 0; + md->md_v7.ant.isolation = 10; - if (module->ant.num == 3) { - module->ant.type = BTC_ANT_DEDICATED; - module->bt_pos = BTC_BT_ALONE; + if (md->md_v7.ant.num == 3) { + md->md_v7.ant.type = BTC_ANT_DEDICATED; + md->md_v7.bt_pos = BTC_BT_ALONE; + } else { + md->md_v7.ant.type = BTC_ANT_SHARED; + md->md_v7.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md_v7.ant.btg_pos; + rtwdev->btc.ant_type = md->md_v7.ant.type; } else { - module->ant.type = BTC_ANT_SHARED; - module->bt_pos = BTC_BT_BTG; + md->md.rfe_type = rtwdev->efuse.rfe_type; + md->md.cv = rtwdev->hal.cv; + md->md.bt_solo = 0; + md->md.switch_type = BTC_SWITCH_INTERNAL; + + if (md->md.rfe_type > 0) + md->md.ant.num = (md->md.rfe_type % 2 ? 2 : 3); + else + md->md.ant.num = 2; + + md->md.ant.diversity = 0; + md->md.ant.isolation = 10; + + if (md->md.ant.num == 3) { + md->md.ant.type = BTC_ANT_DEDICATED; + md->md.bt_pos = BTC_BT_ALONE; + } else { + md->md.ant.type = BTC_ANT_SHARED; + md->md.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md.ant.btg_pos; + rtwdev->btc.ant_type = md->md.ant.type; } } @@ -1717,7 +1744,6 @@ static void rtw8852a_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en, static void rtw8852a_btc_init_cfg(struct rtw89_dev *rtwdev) { struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; const struct rtw89_chip_info *chip = rtwdev->chip; const struct rtw89_mac_ax_coex coex_params = { .pta_mode = RTW89_MAC_AX_COEX_RTK_MODE, @@ -1736,7 +1762,7 @@ static void rtw8852a_btc_init_cfg(struct rtw89_dev *rtwdev) rtw89_write_rf(rtwdev, RF_PATH_B, RR_WLSEL, 0xfffff, 0x0); /* set WL Tx thru in TRX mask table if GNT_WL = 0 && BT_S1 = ss group */ - if (module->ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { rtw8852a_set_trx_mask(rtwdev, RF_PATH_A, BTC_BT_SS_GROUP, 0x5ff); rtw8852a_set_trx_mask(rtwdev, @@ -2197,6 +2223,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = { .c2h_regs = rtw8852a_c2h_regs, .c2h_counter_reg = {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8}, .page_regs = &rtw8852a_page_regs, + .wow_reason_reg = R_AX_C2HREG_DATA3 + 3, .cfo_src_fd = false, .cfo_hw_comp = false, .dcfo_comp = &rtw8852a_dcfo_comp, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c index 19454766f3de..d025c4135e1c 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c @@ -2125,28 +2125,55 @@ static u8 rtw8852b_get_thermal(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_p static void rtw8852b_btc_set_rfe(struct rtw89_dev *rtwdev) { - struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; + const struct rtw89_btc_ver *ver = rtwdev->btc.ver; + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; - module->rfe_type = rtwdev->efuse.rfe_type; - module->cv = rtwdev->hal.cv; - module->bt_solo = 0; - module->switch_type = BTC_SWITCH_INTERNAL; + if (ver->fcxinit == 7) { + md->md_v7.rfe_type = rtwdev->efuse.rfe_type; + md->md_v7.kt_ver = rtwdev->hal.cv; + md->md_v7.bt_solo = 0; + md->md_v7.switch_type = BTC_SWITCH_INTERNAL; - if (module->rfe_type > 0) - module->ant.num = module->rfe_type % 2 ? 2 : 3; - else - module->ant.num = 2; + if (md->md_v7.rfe_type > 0) + md->md_v7.ant.num = (md->md_v7.rfe_type % 2 ? 2 : 3); + else + md->md_v7.ant.num = 2; - module->ant.diversity = 0; - module->ant.isolation = 10; + md->md_v7.ant.diversity = 0; + md->md_v7.ant.isolation = 10; - if (module->ant.num == 3) { - module->ant.type = BTC_ANT_DEDICATED; - module->bt_pos = BTC_BT_ALONE; + if (md->md_v7.ant.num == 3) { + md->md_v7.ant.type = BTC_ANT_DEDICATED; + md->md_v7.bt_pos = BTC_BT_ALONE; + } else { + md->md_v7.ant.type = BTC_ANT_SHARED; + md->md_v7.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md_v7.ant.btg_pos; + rtwdev->btc.ant_type = md->md_v7.ant.type; } else { - module->ant.type = BTC_ANT_SHARED; - module->bt_pos = BTC_BT_BTG; + md->md.rfe_type = rtwdev->efuse.rfe_type; + md->md.cv = rtwdev->hal.cv; + md->md.bt_solo = 0; + md->md.switch_type = BTC_SWITCH_INTERNAL; + + if (md->md.rfe_type > 0) + md->md.ant.num = (md->md.rfe_type % 2 ? 2 : 3); + else + md->md.ant.num = 2; + + md->md.ant.diversity = 0; + md->md.ant.isolation = 10; + + if (md->md.ant.num == 3) { + md->md.ant.type = BTC_ANT_DEDICATED; + md->md.bt_pos = BTC_BT_ALONE; + } else { + md->md.ant.type = BTC_ANT_SHARED; + md->md.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md.ant.btg_pos; + rtwdev->btc.ant_type = md->md.ant.type; } } @@ -2162,7 +2189,6 @@ void rtw8852b_set_trx_mask(struct rtw89_dev *rtwdev, u8 path, u8 group, u32 val) static void rtw8852b_btc_init_cfg(struct rtw89_dev *rtwdev) { struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; const struct rtw89_chip_info *chip = rtwdev->chip; const struct rtw89_mac_ax_coex coex_params = { .pta_mode = RTW89_MAC_AX_COEX_RTK_MODE, @@ -2181,7 +2207,7 @@ static void rtw8852b_btc_init_cfg(struct rtw89_dev *rtwdev) rtw89_write_rf(rtwdev, RF_PATH_B, RR_WLSEL, RFREG_MASK, 0x0); /* set WL Tx thru in TRX mask table if GNT_WL = 0 && BT_S1 = ss group */ - if (module->ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { rtw8852b_set_trx_mask(rtwdev, RF_PATH_A, BTC_BT_SS_GROUP, 0x5ff); rtw8852b_set_trx_mask(rtwdev, RF_PATH_B, BTC_BT_SS_GROUP, 0x5ff); /* set path-A(S0) Tx/Rx no-mask if GNT_WL=0 && BT_S1=tx group */ @@ -2631,6 +2657,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = { .c2h_counter_reg = {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8}, .c2h_regs = rtw8852b_c2h_regs, .page_regs = &rtw8852b_page_regs, + .wow_reason_reg = R_AX_C2HREG_DATA3 + 3, .cfo_src_fd = true, .cfo_hw_comp = true, .dcfo_comp = &rtw8852b_dcfo_comp, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c index ca8547fbd70e..17e6164855fa 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c @@ -2365,28 +2365,55 @@ static u8 rtw8852c_get_thermal(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_p static void rtw8852c_btc_set_rfe(struct rtw89_dev *rtwdev) { - struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; + const struct rtw89_btc_ver *ver = rtwdev->btc.ver; + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; - module->rfe_type = rtwdev->efuse.rfe_type; - module->cv = rtwdev->hal.cv; - module->bt_solo = 0; - module->switch_type = BTC_SWITCH_INTERNAL; + if (ver->fcxinit == 7) { + md->md_v7.rfe_type = rtwdev->efuse.rfe_type; + md->md_v7.kt_ver = rtwdev->hal.cv; + md->md_v7.bt_solo = 0; + md->md_v7.switch_type = BTC_SWITCH_INTERNAL; - if (module->rfe_type > 0) - module->ant.num = (module->rfe_type % 2 ? 2 : 3); - else - module->ant.num = 2; + if (md->md_v7.rfe_type > 0) + md->md_v7.ant.num = (md->md_v7.rfe_type % 2 ? 2 : 3); + else + md->md_v7.ant.num = 2; - module->ant.diversity = 0; - module->ant.isolation = 10; + md->md_v7.ant.diversity = 0; + md->md_v7.ant.isolation = 10; - if (module->ant.num == 3) { - module->ant.type = BTC_ANT_DEDICATED; - module->bt_pos = BTC_BT_ALONE; + if (md->md_v7.ant.num == 3) { + md->md_v7.ant.type = BTC_ANT_DEDICATED; + md->md_v7.bt_pos = BTC_BT_ALONE; + } else { + md->md_v7.ant.type = BTC_ANT_SHARED; + md->md_v7.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md_v7.ant.btg_pos; + rtwdev->btc.ant_type = md->md_v7.ant.type; } else { - module->ant.type = BTC_ANT_SHARED; - module->bt_pos = BTC_BT_BTG; + md->md.rfe_type = rtwdev->efuse.rfe_type; + md->md.cv = rtwdev->hal.cv; + md->md.bt_solo = 0; + md->md.switch_type = BTC_SWITCH_INTERNAL; + + if (md->md.rfe_type > 0) + md->md.ant.num = (md->md.rfe_type % 2 ? 2 : 3); + else + md->md.ant.num = 2; + + md->md.ant.diversity = 0; + md->md.ant.isolation = 10; + + if (md->md.ant.num == 3) { + md->md.ant.type = BTC_ANT_DEDICATED; + md->md.bt_pos = BTC_BT_ALONE; + } else { + md->md.ant.type = BTC_ANT_SHARED; + md->md.bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = md->md.ant.btg_pos; + rtwdev->btc.ant_type = md->md.ant.type; } } @@ -2449,7 +2476,6 @@ void rtw8852c_set_trx_mask(struct rtw89_dev *rtwdev, u8 path, u8 group, u32 val) static void rtw8852c_btc_init_cfg(struct rtw89_dev *rtwdev) { struct rtw89_btc *btc = &rtwdev->btc; - struct rtw89_btc_module *module = &btc->mdinfo; const struct rtw89_chip_info *chip = rtwdev->chip; const struct rtw89_mac_ax_coex coex_params = { .pta_mode = RTW89_MAC_AX_COEX_RTK_MODE, @@ -2468,7 +2494,7 @@ static void rtw8852c_btc_init_cfg(struct rtw89_dev *rtwdev) rtw89_write_rf(rtwdev, RF_PATH_B, RR_WLSEL, RFREG_MASK, 0x0); /* set WL Tx thru in TRX mask table if GNT_WL = 0 && BT_S1 = ss group */ - if (module->ant.type == BTC_ANT_SHARED) { + if (btc->ant_type == BTC_ANT_SHARED) { rtw8852c_set_trx_mask(rtwdev, RF_PATH_A, BTC_BT_SS_GROUP, 0x5ff); rtw8852c_set_trx_mask(rtwdev, @@ -2971,6 +2997,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = { .c2h_counter_reg = {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8}, .c2h_regs = rtw8852c_c2h_regs, .page_regs = &rtw8852c_page_regs, + .wow_reason_reg = R_AX_C2HREG_DATA3_V1 + 3, .cfo_src_fd = false, .cfo_hw_comp = false, .dcfo_comp = &rtw8852c_dcfo_comp, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c index 823f0d840df9..367459bd1345 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c @@ -2150,6 +2150,113 @@ static u8 rtw8922a_get_thermal(struct rtw89_dev *rtwdev, enum rtw89_rf_path rf_p return clamp_t(int, th, 0, U8_MAX); } +static void rtw8922a_btc_set_rfe(struct rtw89_dev *rtwdev) +{ + union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo; + struct rtw89_btc_module_v7 *module = &md->md_v7; + + module->rfe_type = rtwdev->efuse.rfe_type; + module->kt_ver = rtwdev->hal.cv; + module->bt_solo = 0; + module->switch_type = BTC_SWITCH_INTERNAL; + module->wa_type = 0; + + module->ant.type = BTC_ANT_SHARED; + module->ant.num = 2; + module->ant.isolation = 10; + module->ant.diversity = 0; + module->ant.single_pos = RF_PATH_A; + module->ant.btg_pos = RF_PATH_B; + + if (module->kt_ver <= 1) + module->wa_type |= BTC_WA_HFP_ZB; + + rtwdev->btc.cx.other.type = BTC_3CX_NONE; + + if (module->rfe_type == 0) { + rtwdev->btc.dm.error.map.rfe_type0 = true; + return; + } + + module->ant.num = (module->rfe_type % 2) ? 2 : 3; + + if (module->kt_ver == 0) + module->ant.num = 2; + + if (module->ant.num == 3) { + module->ant.type = BTC_ANT_DEDICATED; + module->bt_pos = BTC_BT_ALONE; + } else { + module->ant.type = BTC_ANT_SHARED; + module->bt_pos = BTC_BT_BTG; + } + rtwdev->btc.btg_pos = module->ant.btg_pos; + rtwdev->btc.ant_type = module->ant.type; +} + +static +void rtw8922a_set_trx_mask(struct rtw89_dev *rtwdev, u8 path, u8 group, u32 val) +{ + rtw89_write_rf(rtwdev, path, RR_LUTWA, RFREG_MASK, group); + rtw89_write_rf(rtwdev, path, RR_LUTWD0, RFREG_MASK, val); +} + +static void rtw8922a_btc_init_cfg(struct rtw89_dev *rtwdev) +{ + struct rtw89_btc *btc = &rtwdev->btc; + struct rtw89_btc_ant_info_v7 *ant = &btc->mdinfo.md_v7.ant; + u32 wl_pri, path_min, path_max; + u8 path; + + /* for 1-Ant && 1-ss case: only 1-path */ + if (ant->num == 1) { + path_min = ant->single_pos; + path_max = path_min; + } else { + path_min = RF_PATH_A; + path_max = RF_PATH_B; + } + + path = path_min; + + for (path = path_min; path <= path_max; path++) { + /* set DEBUG_LUT_RFMODE_MASK = 1 to start trx-mask-setup */ + rtw89_write_rf(rtwdev, path, RR_LUTWE, RFREG_MASK, BIT(17)); + + /* if GNT_WL=0 && BT=SS_group --> WL Tx/Rx = THRU */ + rtw8922a_set_trx_mask(rtwdev, path, BTC_BT_SS_GROUP, 0x5ff); + + /* if GNT_WL=0 && BT=Rx_group --> WL-Rx = THRU + WL-Tx = MASK */ + rtw8922a_set_trx_mask(rtwdev, path, BTC_BT_RX_GROUP, 0x5df); + + /* if GNT_WL = 0 && BT = Tx_group --> + * Shared-Ant && BTG-path:WL mask(0x55f), others:WL THRU(0x5ff) + */ + if (btc->ant_type == BTC_ANT_SHARED && btc->btg_pos == path) + rtw8922a_set_trx_mask(rtwdev, path, BTC_BT_TX_GROUP, 0x5ff); + else + rtw8922a_set_trx_mask(rtwdev, path, BTC_BT_TX_GROUP, 0x5ff); + + rtw89_write_rf(rtwdev, path, RR_LUTWE, RFREG_MASK, 0); + } + + /* set WL PTA Hi-Pri: Ack-Tx, beacon-tx, Trig-frame-Tx, Null-Tx*/ + wl_pri = B_BTC_RSP_ACK_HI | B_BTC_TX_BCN_HI | B_BTC_TX_TRI_HI | + B_BTC_TX_NULL_HI; + rtw89_write32(rtwdev, R_BTC_COEX_WL_REQ_BE, wl_pri); + + /* set PTA break table */ + rtw89_write32(rtwdev, R_BE_BT_BREAK_TABLE, BTC_BREAK_PARAM); + + /* ZB coex table init for HFP PTA req-cmd bit-4 define issue COEX-900*/ + rtw89_write32(rtwdev, R_BTC_ZB_COEX_TBL_0, 0xda5a5a5a); + + rtw89_write32(rtwdev, R_BTC_ZB_COEX_TBL_1, 0xda5a5a5a); + + rtw89_write32(rtwdev, R_BTC_ZB_BREAK_TBL, 0xf0ffffff); + btc->cx.wl.status.map.init_ok = true; +} + static void rtw8922a_fill_freq_with_ppdu(struct rtw89_dev *rtwdev, struct rtw89_rx_phy_ppdu *phy_ppdu, struct ieee80211_rx_status *status) @@ -2246,6 +2353,8 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = { .query_rxdesc = rtw89_core_query_rxdesc_v2, .fill_txdesc = rtw89_core_fill_txdesc_v2, .fill_txdesc_fwcmd = rtw89_core_fill_txdesc_fwcmd_v2, + .cfg_ctrl_path = rtw89_mac_cfg_ctrl_path_v2, + .mac_cfg_gnt = rtw89_mac_cfg_gnt_v2, .stop_sch_tx = rtw89_mac_stop_sch_tx_v2, .resume_sch_tx = rtw89_mac_resume_sch_tx_v2, .h2c_dctl_sec_cam = rtw89_fw_h2c_dctl_sec_cam_v2, @@ -2255,6 +2364,9 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = { .h2c_default_dmac_tbl = rtw89_fw_h2c_default_dmac_tbl_v2, .h2c_update_beacon = rtw89_fw_h2c_update_beacon_be, .h2c_ba_cam = rtw89_fw_h2c_ba_cam_v1, + + .btc_set_rfe = rtw8922a_btc_set_rfe, + .btc_init_cfg = rtw8922a_btc_init_cfg, }; const struct rtw89_chip_info rtw8922a_chip_info = { @@ -2341,6 +2453,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = { .c2h_counter_reg = {R_BE_UDM1 + 1, B_BE_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8}, .c2h_regs = rtw8922a_c2h_regs, .page_regs = &rtw8922a_page_regs, + .wow_reason_reg = R_AX_C2HREG_DATA3_V1 + 3, .cfo_src_fd = true, .cfo_hw_comp = true, .dcfo_comp = NULL, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c index 9f46fb166105..4981b657bd7b 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8922ae.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8922ae.c @@ -80,7 +80,7 @@ static struct pci_driver rtw89_8922ae_driver = { .id_table = rtw89_8922ae_id_table, .probe = rtw89_pci_probe, .remove = rtw89_pci_remove, - .driver.pm = &rtw89_pm_ops, + .driver.pm = &rtw89_pm_ops_be, }; module_pci_driver(rtw89_8922ae_driver); diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c index 4c17936795b6..ccad026defb5 100644 --- a/drivers/net/wireless/realtek/rtw89/wow.c +++ b/drivers/net/wireless/realtek/rtw89/wow.c @@ -41,34 +41,8 @@ static void rtw89_wow_leave_lps(struct rtw89_dev *rtwdev) static int rtw89_wow_config_mac(struct rtw89_dev *rtwdev, bool enable_wow) { const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; - int ret; - - if (enable_wow) { - ret = rtw89_mac_resize_ple_rx_quota(rtwdev, true); - if (ret) { - rtw89_err(rtwdev, "[ERR]patch rx qta %d\n", ret); - return ret; - } - rtw89_write32_set(rtwdev, R_AX_RX_FUNCTION_STOP, B_AX_HDR_RX_STOP); - rtw89_write32_clr(rtwdev, mac->rx_fltr, B_AX_SNIFFER_MODE); - rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false); - rtw89_write32(rtwdev, R_AX_ACTION_FWD0, 0); - rtw89_write32(rtwdev, R_AX_ACTION_FWD1, 0); - rtw89_write32(rtwdev, R_AX_TF_FWD, 0); - rtw89_write32(rtwdev, R_AX_HW_RPT_FWD, 0); - } else { - ret = rtw89_mac_resize_ple_rx_quota(rtwdev, false); - if (ret) { - rtw89_err(rtwdev, "[ERR]patch rx qta %d\n", ret); - return ret; - } - rtw89_write32_clr(rtwdev, R_AX_RX_FUNCTION_STOP, B_AX_HDR_RX_STOP); - rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true); - rtw89_write32(rtwdev, R_AX_ACTION_FWD0, TRXCFG_MPDU_PROC_ACT_FRWD); - rtw89_write32(rtwdev, R_AX_TF_FWD, TRXCFG_MPDU_PROC_TF_FRWD); - } - return 0; + return mac->wow_config_mac(rtwdev, enable_wow); } static void rtw89_wow_set_rx_filter(struct rtw89_dev *rtwdev, bool enable) @@ -85,21 +59,14 @@ static void rtw89_wow_set_rx_filter(struct rtw89_dev *rtwdev, bool enable) static void rtw89_wow_show_wakeup_reason(struct rtw89_dev *rtwdev) { - enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id; + u32 wow_reason_reg = rtwdev->chip->wow_reason_reg; struct cfg80211_wowlan_nd_info nd_info; struct cfg80211_wowlan_wakeup wakeup = { .pattern_idx = -1, }; - u32 wow_reason_reg; u8 reason; - if (chip_id == RTL8852A || chip_id == RTL8852B || chip_id == RTL8851B) - wow_reason_reg = R_AX_C2HREG_DATA3 + 3; - else - wow_reason_reg = R_AX_C2HREG_DATA3_V1 + 3; - reason = rtw89_read8(rtwdev, wow_reason_reg); - switch (reason) { case RTW89_WOW_RSN_RX_DEAUTH: wakeup.disconnect = true; @@ -470,13 +437,14 @@ static int rtw89_wow_cfg_wake(struct rtw89_dev *rtwdev, bool wow) static int rtw89_wow_check_fw_status(struct rtw89_dev *rtwdev, bool wow_enable) { + const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def; u8 polling; int ret; ret = read_poll_timeout_atomic(rtw89_read8_mask, polling, wow_enable == !!polling, 50, 50000, false, rtwdev, - R_AX_WOW_CTRL, B_AX_WOW_WOWEN); + mac->wow_ctrl.addr, mac->wow_ctrl.mask); if (ret) rtw89_err(rtwdev, "failed to check wow status %s\n", wow_enable ? "enabled" : "disabled"); @@ -566,7 +534,7 @@ static int rtw89_wow_enable_trx_pre(struct rtw89_dev *rtwdev) rtw89_mac_ptk_drop_by_band_and_wait(rtwdev, RTW89_MAC_0); - ret = rtw89_hci_poll_txdma_ch(rtwdev); + ret = rtw89_hci_poll_txdma_ch_idle(rtwdev); if (ret) { rtw89_err(rtwdev, "txdma ch busy\n"); return ret; @@ -589,7 +557,7 @@ static int rtw89_wow_enable_trx_post(struct rtw89_dev *rtwdev) rtw89_hci_disable_intr(rtwdev); rtw89_hci_ctrl_trxhci(rtwdev, false); - ret = rtw89_hci_poll_txdma_ch(rtwdev); + ret = rtw89_hci_poll_txdma_ch_idle(rtwdev); if (ret) { rtw89_err(rtwdev, "failed to poll txdma ch idle pcie\n"); return ret; @@ -699,14 +667,14 @@ static int rtw89_wow_fw_stop(struct rtw89_dev *rtwdev) goto out; } + rtw89_fw_release_general_pkt_list(rtwdev, true); + ret = rtw89_wow_cfg_wake(rtwdev, false); if (ret) { rtw89_err(rtwdev, "wow: failed to disable config wake\n"); goto out; } - rtw89_fw_release_general_pkt_list(rtwdev, true); - ret = rtw89_wow_check_fw_status(rtwdev, false); if (ret) { rtw89_err(rtwdev, "wow: failed to check disable fw ready\n"); diff --git a/drivers/net/wireless/st/cw1200/cw1200_spi.c b/drivers/net/wireless/st/cw1200/cw1200_spi.c index fb3aafcafe18..4f346fb977a9 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_spi.c +++ b/drivers/net/wireless/st/cw1200/cw1200_spi.c @@ -81,6 +81,9 @@ static int cw1200_spi_memcpy_fromio(struct hwbus_priv *self, pr_info("READ : %04d from 0x%02x (%04x)\n", count, addr, regaddr); #endif + /* Header is LE16 */ + regaddr = (__force u16)cpu_to_le16(regaddr); + /* We have to byteswap if the SPI bus is limited to 8b operation or we are running on a Big Endian system */ @@ -143,6 +146,9 @@ static int cw1200_spi_memcpy_toio(struct hwbus_priv *self, pr_info("WRITE: %04d to 0x%02x (%04x)\n", count, addr, regaddr); #endif + /* Header is LE16 */ + regaddr = (__force u16)cpu_to_le16(regaddr); + /* We have to byteswap if the SPI bus is limited to 8b operation or we are running on a Big Endian system */ diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 966edb39ad9e..92fb5b8dcdae 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -74,8 +74,8 @@ static int __must_check wl12xx_sdio_raw_read(struct device *child, int addr, sdio_release_host(func); - if (WARN_ON(ret)) - dev_err(child->parent, "sdio read failed (%d)\n", ret); + if (ret) + dev_err_ratelimited(child->parent, "sdio read failed (%d)\n", ret); if (unlikely(dump)) { printk(KERN_DEBUG "wlcore_sdio: READ from 0x%04x\n", addr); @@ -119,8 +119,8 @@ static int __must_check wl12xx_sdio_raw_write(struct device *child, int addr, sdio_release_host(func); - if (WARN_ON(ret)) - dev_err(child->parent, "sdio write failed (%d)\n", ret); + if (ret) + dev_err_ratelimited(child->parent, "sdio write failed (%d)\n", ret); return ret; } diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c index 8505d84eeed6..f3b567a13ded 100644 --- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c @@ -380,7 +380,7 @@ static inline void handle_regs_int(struct urb *urb) spin_lock_irqsave(&intr->lock, flags); int_num = le16_to_cpu(*(__le16 *)(urb->transfer_buffer+2)); - if (int_num == CR_INTERRUPT) { + if (int_num == (u16)CR_INTERRUPT) { struct zd_mac *mac = zd_hw_mac(zd_usb_to_hw(urb->context)); spin_lock(&mac->lock); memcpy(&mac->intr_buffer, urb->transfer_buffer, @@ -416,7 +416,8 @@ out: spin_unlock_irqrestore(&intr->lock, flags); /* CR_INTERRUPT might override read_reg too. */ - if (int_num == CR_INTERRUPT && atomic_read(&intr->read_regs_enabled)) + if (int_num == (u16)CR_INTERRUPT && + atomic_read(&intr->read_regs_enabled)) handle_regs_int_override(urb); } diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index b0030f3ed0f0..17431f1b1a0c 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -26,7 +26,9 @@ static DEFINE_MUTEX(wwan_register_lock); /* WWAN device create|remove lock */ static DEFINE_IDA(minors); /* minors for WWAN port chardevs */ static DEFINE_IDA(wwan_dev_ids); /* for unique WWAN device IDs */ -static struct class *wwan_class; +static const struct class wwan_class = { + .name = "wwan", +}; static int wwan_major; static struct dentry *wwan_debugfs_dir; @@ -130,7 +132,7 @@ static struct wwan_device *wwan_dev_get_by_parent(struct device *parent) { struct device *dev; - dev = class_find_device(wwan_class, NULL, parent, wwan_dev_parent_match); + dev = class_find_device(&wwan_class, NULL, parent, wwan_dev_parent_match); if (!dev) return ERR_PTR(-ENODEV); @@ -147,7 +149,7 @@ static struct wwan_device *wwan_dev_get_by_name(const char *name) { struct device *dev; - dev = class_find_device(wwan_class, NULL, name, wwan_dev_name_match); + dev = class_find_device(&wwan_class, NULL, name, wwan_dev_name_match); if (!dev) return ERR_PTR(-ENODEV); @@ -183,7 +185,7 @@ static struct wwan_device *wwan_dev_get_by_debugfs(struct dentry *dir) { struct device *dev; - dev = class_find_device(wwan_class, NULL, dir, wwan_dev_debugfs_match); + dev = class_find_device(&wwan_class, NULL, dir, wwan_dev_debugfs_match); if (!dev) return ERR_PTR(-ENODEV); @@ -239,7 +241,7 @@ static struct wwan_device *wwan_create_dev(struct device *parent) } wwandev->dev.parent = parent; - wwandev->dev.class = wwan_class; + wwandev->dev.class = &wwan_class; wwandev->dev.type = &wwan_dev_type; wwandev->id = id; dev_set_name(&wwandev->dev, "wwan%d", wwandev->id); @@ -265,7 +267,7 @@ done_unlock: static int is_wwan_child(struct device *dev, void *data) { - return dev->class == wwan_class; + return dev->class == &wwan_class; } static void wwan_remove_dev(struct wwan_device *wwandev) @@ -375,7 +377,7 @@ static struct wwan_port *wwan_port_get_by_minor(unsigned int minor) { struct device *dev; - dev = class_find_device(wwan_class, NULL, &minor, wwan_port_minor_match); + dev = class_find_device(&wwan_class, NULL, &minor, wwan_port_minor_match); if (!dev) return ERR_PTR(-ENODEV); @@ -405,7 +407,7 @@ static int __wwan_port_dev_assign_name(struct wwan_port *port, const char *fmt) return -ENOMEM; /* Collect ids of same name format ports */ - class_dev_iter_init(&iter, wwan_class, NULL, &wwan_port_dev_type); + class_dev_iter_init(&iter, &wwan_class, NULL, &wwan_port_dev_type); while ((dev = class_dev_iter_next(&iter))) { if (dev->parent != &wwandev->dev) continue; @@ -477,7 +479,7 @@ struct wwan_port *wwan_create_port(struct device *parent, mutex_init(&port->data_lock); port->dev.parent = &wwandev->dev; - port->dev.class = wwan_class; + port->dev.class = &wwan_class; port->dev.type = &wwan_port_dev_type; port->dev.devt = MKDEV(wwan_major, minor); dev_set_drvdata(&port->dev, drvdata); @@ -1212,11 +1214,9 @@ static int __init wwan_init(void) if (err) return err; - wwan_class = class_create("wwan"); - if (IS_ERR(wwan_class)) { - err = PTR_ERR(wwan_class); + err = class_register(&wwan_class); + if (err) goto unregister; - } /* chrdev used for wwan ports */ wwan_major = __register_chrdev(0, 0, WWAN_MAX_MINORS, "wwan_port", @@ -1233,7 +1233,7 @@ static int __init wwan_init(void) return 0; destroy: - class_destroy(wwan_class); + class_unregister(&wwan_class); unregister: rtnl_link_unregister(&wwan_rtnl_link_ops); return err; @@ -1244,7 +1244,7 @@ static void __exit wwan_exit(void) debugfs_remove_recursive(wwan_debugfs_dir); __unregister_chrdev(wwan_major, 0, WWAN_MAX_MINORS, "wwan_port"); rtnl_link_unregister(&wwan_rtnl_link_ops); - class_destroy(wwan_class); + class_unregister(&wwan_class); } module_init(wwan_init); diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index ff3dd24ddb33..b02befd1b6fb 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -25,7 +25,9 @@ static int wwan_hwsim_devsnum = 2; module_param_named(devices, wwan_hwsim_devsnum, int, 0444); MODULE_PARM_DESC(devices, "Number of simulated devices"); -static struct class *wwan_hwsim_class; +static const struct class wwan_hwsim_class = { + .name = "wwan_hwsim", +}; static struct dentry *wwan_hwsim_debugfs_topdir; static struct dentry *wwan_hwsim_debugfs_devcreate; @@ -277,7 +279,7 @@ static struct wwan_hwsim_dev *wwan_hwsim_dev_new(void) spin_unlock(&wwan_hwsim_devs_lock); dev->dev.release = wwan_hwsim_dev_release; - dev->dev.class = wwan_hwsim_class; + dev->dev.class = &wwan_hwsim_class; dev_set_name(&dev->dev, "hwsim%u", dev->id); spin_lock_init(&dev->ports_lock); @@ -511,11 +513,9 @@ static int __init wwan_hwsim_init(void) if (!wwan_wq) return -ENOMEM; - wwan_hwsim_class = class_create("wwan_hwsim"); - if (IS_ERR(wwan_hwsim_class)) { - err = PTR_ERR(wwan_hwsim_class); + err = class_register(&wwan_hwsim_class); + if (err) goto err_wq_destroy; - } wwan_hwsim_debugfs_topdir = debugfs_create_dir("wwan_hwsim", NULL); wwan_hwsim_debugfs_devcreate = @@ -534,7 +534,7 @@ err_clean_devs: wwan_hwsim_free_devs(); flush_workqueue(wwan_wq); /* Wait deletion works completion */ debugfs_remove(wwan_hwsim_debugfs_topdir); - class_destroy(wwan_hwsim_class); + class_unregister(&wwan_hwsim_class); err_wq_destroy: destroy_workqueue(wwan_wq); @@ -547,7 +547,7 @@ static void __exit wwan_hwsim_exit(void) wwan_hwsim_free_devs(); flush_workqueue(wwan_wq); /* Wait deletion works completion */ debugfs_remove(wwan_hwsim_debugfs_topdir); - class_destroy(wwan_hwsim_class); + class_unregister(&wwan_hwsim_class); destroy_workqueue(wwan_wq); } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index a6d596e05602..3692b56cb58d 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1344,7 +1344,6 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { - struct page *page; struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; unsigned int noreclaim_flag; @@ -1355,11 +1354,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) if (queue->hdr_digest || queue->data_digest) nvme_tcp_free_crypto(queue); - if (queue->pf_cache.va) { - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); - queue->pf_cache.va = NULL; - } + page_frag_cache_drain(&queue->pf_cache); noreclaim_flag = memalloc_noreclaim_save(); /* ->sock will be released by fput() */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index c8655fc5aa5b..2aa5762e9f50 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1591,7 +1591,6 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) static void nvmet_tcp_release_queue_work(struct work_struct *w) { - struct page *page; struct nvmet_tcp_queue *queue = container_of(w, struct nvmet_tcp_queue, release_work); @@ -1615,8 +1614,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) if (queue->hdr_digest || queue->data_digest) nvmet_tcp_free_crypto(queue); ida_free(&nvmet_tcp_queue_ida, queue->idx); - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); + page_frag_cache_drain(&queue->pf_cache); kfree(queue); } diff --git a/drivers/of/property.c b/drivers/of/property.c index b71267c6667c..fa8cd33be131 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1304,7 +1304,7 @@ static struct device_node *parse_remote_endpoint(struct device_node *np, int index) { /* Return NULL for index > 0 to signify end of remote-endpoints. */ - if (!index || strcmp(prop_name, "remote-endpoint")) + if (index > 0 || strcmp(prop_name, "remote-endpoint")) return NULL; return of_graph_get_remote_port_parent(np); diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 0dda70e1ef90..c78a6fd6c57f 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -150,19 +150,11 @@ u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event) struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - if (!rvpmu->ctr_get_width) - /** - * If the pmu driver doesn't support counter width, set it to default - * maximum allowed by the specification. - */ - cwidth = 63; - else { - if (hwc->idx == -1) - /* Handle init case where idx is not initialized yet */ - cwidth = rvpmu->ctr_get_width(0); - else - cwidth = rvpmu->ctr_get_width(hwc->idx); - } + if (hwc->idx == -1) + /* Handle init case where idx is not initialized yet */ + cwidth = rvpmu->ctr_get_width(0); + else + cwidth = rvpmu->ctr_get_width(hwc->idx); return GENMASK_ULL(cwidth, 0); } diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 79fdd667922e..fa0bccf4edf2 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -37,6 +37,12 @@ static int pmu_legacy_event_map(struct perf_event *event, u64 *config) return pmu_legacy_ctr_get_idx(event); } +/* cycle & instret are always 64 bit, one bit less according to SBI spec */ +static int pmu_legacy_ctr_get_width(int idx) +{ + return 63; +} + static u64 pmu_legacy_read_ctr(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -111,12 +117,14 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; pmu->ctr_get_idx = pmu_legacy_ctr_get_idx; - pmu->ctr_get_width = NULL; + pmu->ctr_get_width = pmu_legacy_ctr_get_width; pmu->ctr_clear_idx = NULL; pmu->ctr_read = pmu_legacy_read_ctr; pmu->event_mapped = pmu_legacy_event_mapped; pmu->event_unmapped = pmu_legacy_event_unmapped; pmu->csr_index = pmu_legacy_csr_index; + pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW); } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 16acd4dcdb96..452aab49db1e 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -512,7 +512,7 @@ static void pmu_sbi_set_scounteren(void *arg) if (event->hw.idx != -1) csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event))); + csr_read(CSR_SCOUNTEREN) | BIT(pmu_sbi_csr_index(event))); } static void pmu_sbi_reset_scounteren(void *arg) @@ -521,7 +521,7 @@ static void pmu_sbi_reset_scounteren(void *arg) if (event->hw.idx != -1) csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event))); + csr_read(CSR_SCOUNTEREN) & ~BIT(pmu_sbi_csr_index(event))); } static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) @@ -731,14 +731,14 @@ 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 */ - if (!(overflow & (1 << hidx))) + if (!(overflow & BIT(hidx))) continue; /* * Keep a track of overflowed counters so that they can be started * with updated initial value. */ - overflowed_ctrs |= 1 << lidx; + overflowed_ctrs |= BIT(lidx); hw_evt = &event->hw; riscv_pmu_event_update(event); perf_sample_data_init(&data, 0, hw_evt->last_period); diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c index e625b32889bf..0928a526e2ab 100644 --- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c +++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c @@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev) return ret; } - priv->id = of_alias_get_id(np, "mipi_dphy"); + priv->id = of_alias_get_id(np, "mipi-dphy"); if (priv->id < 0) { dev_err(dev, "Failed to get phy node alias id: %d\n", priv->id); diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index a623f092b11f..a43e20abb10d 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -37,56 +37,28 @@ #define EUSB2_TUNE_EUSB_EQU 0x5A #define EUSB2_TUNE_EUSB_HS_COMP_CUR 0x5B -#define QCOM_EUSB2_REPEATER_INIT_CFG(r, v) \ - { \ - .reg = r, \ - .val = v, \ - } - -enum reg_fields { - F_TUNE_EUSB_HS_COMP_CUR, - F_TUNE_EUSB_EQU, - F_TUNE_EUSB_SLEW, - F_TUNE_USB2_HS_COMP_CUR, - F_TUNE_USB2_PREEM, - F_TUNE_USB2_EQU, - F_TUNE_USB2_SLEW, - F_TUNE_SQUELCH_U, - F_TUNE_HSDISC, - F_TUNE_RES_FSDIF, - F_TUNE_IUSB2, - F_TUNE_USB2_CROSSOVER, - F_NUM_TUNE_FIELDS, - - F_FORCE_VAL_5 = F_NUM_TUNE_FIELDS, - F_FORCE_EN_5, - - F_EN_CTL1, - - F_RPTR_STATUS, - F_NUM_FIELDS, -}; - -static struct reg_field eusb2_repeater_tune_reg_fields[F_NUM_FIELDS] = { - [F_TUNE_EUSB_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_EUSB_HS_COMP_CUR, 0, 1), - [F_TUNE_EUSB_EQU] = REG_FIELD(EUSB2_TUNE_EUSB_EQU, 0, 1), - [F_TUNE_EUSB_SLEW] = REG_FIELD(EUSB2_TUNE_EUSB_SLEW, 0, 1), - [F_TUNE_USB2_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_USB2_HS_COMP_CUR, 0, 1), - [F_TUNE_USB2_PREEM] = REG_FIELD(EUSB2_TUNE_USB2_PREEM, 0, 2), - [F_TUNE_USB2_EQU] = REG_FIELD(EUSB2_TUNE_USB2_EQU, 0, 1), - [F_TUNE_USB2_SLEW] = REG_FIELD(EUSB2_TUNE_USB2_SLEW, 0, 1), - [F_TUNE_SQUELCH_U] = REG_FIELD(EUSB2_TUNE_SQUELCH_U, 0, 2), - [F_TUNE_HSDISC] = REG_FIELD(EUSB2_TUNE_HSDISC, 0, 2), - [F_TUNE_RES_FSDIF] = REG_FIELD(EUSB2_TUNE_RES_FSDIF, 0, 2), - [F_TUNE_IUSB2] = REG_FIELD(EUSB2_TUNE_IUSB2, 0, 3), - [F_TUNE_USB2_CROSSOVER] = REG_FIELD(EUSB2_TUNE_USB2_CROSSOVER, 0, 2), - - [F_FORCE_VAL_5] = REG_FIELD(EUSB2_FORCE_VAL_5, 0, 7), - [F_FORCE_EN_5] = REG_FIELD(EUSB2_FORCE_EN_5, 0, 7), - - [F_EN_CTL1] = REG_FIELD(EUSB2_EN_CTL1, 0, 7), - - [F_RPTR_STATUS] = REG_FIELD(EUSB2_RPTR_STATUS, 0, 7), +enum eusb2_reg_layout { + TUNE_EUSB_HS_COMP_CUR, + TUNE_EUSB_EQU, + TUNE_EUSB_SLEW, + TUNE_USB2_HS_COMP_CUR, + TUNE_USB2_PREEM, + TUNE_USB2_EQU, + TUNE_USB2_SLEW, + TUNE_SQUELCH_U, + TUNE_HSDISC, + TUNE_RES_FSDIF, + TUNE_IUSB2, + TUNE_USB2_CROSSOVER, + NUM_TUNE_FIELDS, + + FORCE_VAL_5 = NUM_TUNE_FIELDS, + FORCE_EN_5, + + EN_CTL1, + + RPTR_STATUS, + LAYOUT_SIZE, }; struct eusb2_repeater_cfg { @@ -98,10 +70,11 @@ struct eusb2_repeater_cfg { struct eusb2_repeater { struct device *dev; - struct regmap_field *regs[F_NUM_FIELDS]; + struct regmap *regmap; struct phy *phy; struct regulator_bulk_data *vregs; const struct eusb2_repeater_cfg *cfg; + u32 base; enum phy_mode mode; }; @@ -109,10 +82,10 @@ static const char * const pm8550b_vreg_l[] = { "vdd18", "vdd3", }; -static const u32 pm8550b_init_tbl[F_NUM_TUNE_FIELDS] = { - [F_TUNE_IUSB2] = 0x8, - [F_TUNE_SQUELCH_U] = 0x3, - [F_TUNE_USB2_PREEM] = 0x5, +static const u32 pm8550b_init_tbl[NUM_TUNE_FIELDS] = { + [TUNE_IUSB2] = 0x8, + [TUNE_SQUELCH_U] = 0x3, + [TUNE_USB2_PREEM] = 0x5, }; static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = { @@ -140,47 +113,42 @@ static int eusb2_repeater_init_vregs(struct eusb2_repeater *rptr) static int eusb2_repeater_init(struct phy *phy) { - struct reg_field *regfields = eusb2_repeater_tune_reg_fields; struct eusb2_repeater *rptr = phy_get_drvdata(phy); struct device_node *np = rptr->dev->of_node; - u32 init_tbl[F_NUM_TUNE_FIELDS] = { 0 }; - u8 override; + struct regmap *regmap = rptr->regmap; + const u32 *init_tbl = rptr->cfg->init_tbl; + u8 tune_usb2_preem = init_tbl[TUNE_USB2_PREEM]; + u8 tune_hsdisc = init_tbl[TUNE_HSDISC]; + u8 tune_iusb2 = init_tbl[TUNE_IUSB2]; + u32 base = rptr->base; u32 val; int ret; - int i; + + of_property_read_u8(np, "qcom,tune-usb2-amplitude", &tune_iusb2); + of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &tune_hsdisc); + of_property_read_u8(np, "qcom,tune-usb2-preem", &tune_usb2_preem); ret = regulator_bulk_enable(rptr->cfg->num_vregs, rptr->vregs); if (ret) return ret; - regmap_field_update_bits(rptr->regs[F_EN_CTL1], EUSB2_RPTR_EN, EUSB2_RPTR_EN); + regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN); - for (i = 0; i < F_NUM_TUNE_FIELDS; i++) { - if (init_tbl[i]) { - regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]); - } else { - /* Write 0 if there's no value set */ - u32 mask = GENMASK(regfields[i].msb, regfields[i].lsb); - - regmap_field_update_bits(rptr->regs[i], mask, 0); - } - } - memcpy(init_tbl, rptr->cfg->init_tbl, sizeof(init_tbl)); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_HS_COMP_CUR, init_tbl[TUNE_EUSB_HS_COMP_CUR]); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_EQU, init_tbl[TUNE_EUSB_EQU]); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_SLEW, init_tbl[TUNE_EUSB_SLEW]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_HS_COMP_CUR, init_tbl[TUNE_USB2_HS_COMP_CUR]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_EQU, init_tbl[TUNE_USB2_EQU]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_SLEW, init_tbl[TUNE_USB2_SLEW]); + regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, init_tbl[TUNE_SQUELCH_U]); + regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, init_tbl[TUNE_RES_FSDIF]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_CROSSOVER, init_tbl[TUNE_USB2_CROSSOVER]); - if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &override)) - init_tbl[F_TUNE_IUSB2] = override; + regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, tune_usb2_preem); + regmap_write(regmap, base + EUSB2_TUNE_HSDISC, tune_hsdisc); + regmap_write(regmap, base + EUSB2_TUNE_IUSB2, tune_iusb2); - if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &override)) - init_tbl[F_TUNE_HSDISC] = override; - - if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &override)) - init_tbl[F_TUNE_USB2_PREEM] = override; - - for (i = 0; i < F_NUM_TUNE_FIELDS; i++) - regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]); - - ret = regmap_field_read_poll_timeout(rptr->regs[F_RPTR_STATUS], - val, val & RPTR_OK, 10, 5); + ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, val, val & RPTR_OK, 10, 5); if (ret) dev_err(rptr->dev, "initialization timed-out\n"); @@ -191,6 +159,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, enum phy_mode mode, int submode) { struct eusb2_repeater *rptr = phy_get_drvdata(phy); + struct regmap *regmap = rptr->regmap; + u32 base = rptr->base; switch (mode) { case PHY_MODE_USB_HOST: @@ -199,10 +169,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, * per eUSB 1.2 Spec. Below implement software workaround until * PHY and controller is fixing seen observation. */ - regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], - F_CLK_19P2M_EN, F_CLK_19P2M_EN); - regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], - V_CLK_19P2M_EN, V_CLK_19P2M_EN); + regmap_write(regmap, base + EUSB2_FORCE_EN_5, F_CLK_19P2M_EN); + regmap_write(regmap, base + EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN); break; case PHY_MODE_USB_DEVICE: /* @@ -211,10 +179,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, * repeater doesn't clear previous value due to shared * regulators (say host <-> device mode switch). */ - regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], - F_CLK_19P2M_EN, 0); - regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], - V_CLK_19P2M_EN, 0); + regmap_write(regmap, base + EUSB2_FORCE_EN_5, 0); + regmap_write(regmap, base + EUSB2_FORCE_VAL_5, 0); break; default: return -EINVAL; @@ -243,9 +209,8 @@ static int eusb2_repeater_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct phy_provider *phy_provider; struct device_node *np = dev->of_node; - struct regmap *regmap; - int i, ret; u32 res; + int ret; rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL); if (!rptr) @@ -258,22 +223,15 @@ static int eusb2_repeater_probe(struct platform_device *pdev) if (!rptr->cfg) return -EINVAL; - regmap = dev_get_regmap(dev->parent, NULL); - if (!regmap) + rptr->regmap = dev_get_regmap(dev->parent, NULL); + if (!rptr->regmap) return -ENODEV; ret = of_property_read_u32(np, "reg", &res); if (ret < 0) return ret; - for (i = 0; i < F_NUM_FIELDS; i++) - eusb2_repeater_tune_reg_fields[i].reg += res; - - ret = devm_regmap_field_bulk_alloc(dev, regmap, rptr->regs, - eusb2_repeater_tune_reg_fields, - F_NUM_FIELDS); - if (ret) - return ret; + rptr->base = res; ret = eusb2_repeater_init_vregs(rptr); if (ret < 0) { diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c index c2590579190a..03fb0d4b75d7 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -299,7 +299,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) qphy->vreg = devm_regulator_get(dev, "vdda-phy"); if (IS_ERR(qphy->vreg)) - return dev_err_probe(dev, PTR_ERR(qphy->phy), + return dev_err_probe(dev, PTR_ERR(qphy->vreg), "failed to get vreg\n"); phy_set_drvdata(qphy->phy, qphy); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 6621246e4ddf..5c003988c35d 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1556,7 +1556,7 @@ static const char * const qmp_phy_vreg_l[] = { "vdda-phy", "vdda-pll", }; -static const struct qmp_usb_offsets qmp_usb_offsets_ipq8074 = { +static const struct qmp_usb_offsets qmp_usb_offsets_v3 = { .serdes = 0, .pcs = 0x800, .pcs_misc = 0x600, @@ -1572,7 +1572,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = { .rx = 0x400, }; -static const struct qmp_usb_offsets qmp_usb_offsets_v3 = { +static const struct qmp_usb_offsets qmp_usb_offsets_v3_msm8996 = { .serdes = 0, .pcs = 0x600, .tx = 0x200, @@ -1624,7 +1624,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v7 = { static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_ipq8074, + .offsets = &qmp_usb_offsets_v3, .serdes_tbl = ipq9574_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(ipq9574_usb3_serdes_tbl), @@ -1642,7 +1642,7 @@ static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = { static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_ipq8074, + .offsets = &qmp_usb_offsets_v3, .serdes_tbl = ipq8074_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(ipq8074_usb3_serdes_tbl), @@ -1678,7 +1678,7 @@ static const struct qmp_phy_cfg ipq9574_usb3phy_cfg = { static const struct qmp_phy_cfg msm8996_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_v3, + .offsets = &qmp_usb_offsets_v3_msm8996, .serdes_tbl = msm8996_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(msm8996_usb3_serdes_tbl), diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 8527dca9cf56..dcbe8f85e122 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -458,8 +458,10 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) amd_pmf_hex_dump_pb(dev); dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); - if (!dev->prev_data) + if (!dev->prev_data) { + ret = -ENOMEM; goto error; + } ret = amd_pmf_start_policy_engine(dev); if (ret) diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 6bd14d0132db..3d66e1d4eb1f 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -20,9 +20,11 @@ #define P2SBC_HIDE BIT(8) #define P2SB_DEVFN_DEFAULT PCI_DEVFN(31, 1) +#define P2SB_DEVFN_GOLDMONT PCI_DEVFN(13, 0) +#define SPI_DEVFN_GOLDMONT PCI_DEVFN(13, 2) static const struct x86_cpu_id p2sb_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, PCI_DEVFN(13, 0)), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT), {} }; @@ -98,21 +100,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { - unsigned int slot, fn; - - if (PCI_FUNC(devfn) == 0) { - /* - * When function number of the P2SB device is zero, scan it and - * other function numbers, and if devices are available, cache - * their BAR0s. - */ - slot = PCI_SLOT(devfn); - for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++) - p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn)); - } else { - /* Scan the P2SB device and cache its BAR0 */ - p2sb_scan_and_cache_devfn(bus, devfn); - } + /* Scan the P2SB device and cache its BAR0 */ + p2sb_scan_and_cache_devfn(bus, devfn); + + /* On Goldmont p2sb_bar() also gets called for the SPI controller */ + if (devfn == P2SB_DEVFN_GOLDMONT) + p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c index 709bbc448fad..d7ef46ccd9b8 100644 --- a/drivers/pmdomain/arm/scmi_perf_domain.c +++ b/drivers/pmdomain/arm/scmi_perf_domain.c @@ -159,6 +159,9 @@ static void scmi_perf_domain_remove(struct scmi_device *sdev) struct genpd_onecell_data *scmi_pd_data = dev_get_drvdata(dev); int i; + if (!scmi_pd_data) + return; + of_genpd_del_provider(dev->of_node); for (i = 0; i < scmi_pd_data->num_domains; i++) diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 3078896b1300..47df910645f6 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -692,6 +692,7 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) unsigned int active_corner, sleep_corner; unsigned int this_active_corner = 0, this_sleep_corner = 0; unsigned int peer_active_corner = 0, peer_sleep_corner = 0; + unsigned int peer_enabled_corner; if (pd->state_synced) { to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner); @@ -701,9 +702,11 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) this_sleep_corner = pd->level_count - 1; } - if (peer && peer->enabled) - to_active_sleep(peer, peer->corner, &peer_active_corner, + if (peer && peer->enabled) { + peer_enabled_corner = max(peer->corner, peer->enable_corner); + to_active_sleep(peer, peer_enabled_corner, &peer_active_corner, &peer_sleep_corner); + } active_corner = max(this_active_corner, peer_active_corner); diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index f21cb05815ec..3e31375491d5 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -978,6 +978,7 @@ config CHARGER_QCOM_SMB2 config FUEL_GAUGE_MM8013 tristate "Mitsumi MM8013 fuel gauge driver" depends on I2C + select REGMAP_I2C help Say Y here to enable the Mitsumi MM8013 fuel gauge driver. It enables the monitoring of many battery parameters, including diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 3a1798b0c1a7..9910c600743e 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); - free_irq(client->irq, di); + if (client->irq) + free_irq(client->irq, di); + bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 3aaf1a3430c5..c56cd0f63909 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -4,7 +4,6 @@ * * Copyright (C) 2010 OMICRON electronics GmbH */ -#include <linux/idr.h> #include <linux/device.h> #include <linux/err.h> #include <linux/init.h> @@ -16,6 +15,7 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/debugfs.h> +#include <linux/xarray.h> #include <uapi/linux/sched/types.h> #include "ptp_private.h" @@ -25,13 +25,16 @@ #define PTP_PPS_EVENT PPS_CAPTUREASSERT #define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC) -struct class *ptp_class; +const struct class ptp_class = { + .name = "ptp", + .dev_groups = ptp_groups +}; /* private globals */ static dev_t ptp_devt; -static DEFINE_IDA(ptp_clocks_map); +static DEFINE_XARRAY_ALLOC(ptp_clocks_map); /* time stamp event queue operations */ @@ -201,7 +204,7 @@ static void ptp_clock_release(struct device *dev) bitmap_free(tsevq->mask); kfree(tsevq); debugfs_remove(ptp->debugfs_root); - ida_free(&ptp_clocks_map, ptp->index); + xa_erase(&ptp_clocks_map, ptp->index); kfree(ptp); } @@ -233,7 +236,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, { struct ptp_clock *ptp; struct timestamp_event_queue *queue = NULL; - int err = 0, index, major = MAJOR(ptp_devt); + int err, index, major = MAJOR(ptp_devt); char debugfsname[16]; size_t size; @@ -241,16 +244,16 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, return ERR_PTR(-EINVAL); /* Initialize a clock structure. */ - err = -ENOMEM; ptp = kzalloc(sizeof(struct ptp_clock), GFP_KERNEL); - if (ptp == NULL) + if (!ptp) { + err = -ENOMEM; goto no_memory; + } - index = ida_alloc_max(&ptp_clocks_map, MINORMASK, GFP_KERNEL); - if (index < 0) { - err = index; + err = xa_alloc(&ptp_clocks_map, &index, ptp, xa_limit_31b, + GFP_KERNEL); + if (err) goto no_slot; - } ptp->clock.ops = ptp_clock_ops; ptp->info = info; @@ -258,13 +261,17 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, ptp->index = index; INIT_LIST_HEAD(&ptp->tsevqs); queue = kzalloc(sizeof(*queue), GFP_KERNEL); - if (!queue) + if (!queue) { + err = -ENOMEM; goto no_memory_queue; + } list_add_tail(&queue->qlist, &ptp->tsevqs); spin_lock_init(&ptp->tsevqs_lock); queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL); - if (!queue->mask) + if (!queue->mask) { + err = -ENOMEM; goto no_memory_bitmap; + } bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS); spin_lock_init(&queue->lock); mutex_init(&ptp->pincfg_mux); @@ -335,7 +342,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, /* Initialize a new device of our class in our clock structure. */ device_initialize(&ptp->dev); ptp->dev.devt = ptp->devid; - ptp->dev.class = ptp_class; + ptp->dev.class = &ptp_class; ptp->dev.parent = parent; ptp->dev.groups = ptp->pin_attr_groups; ptp->dev.release = ptp_clock_release; @@ -378,7 +385,7 @@ no_memory_bitmap: list_del(&queue->qlist); kfree(queue); no_memory_queue: - ida_free(&ptp_clocks_map, index); + xa_erase(&ptp_clocks_map, index); no_slot: kfree(ptp); no_memory: @@ -509,19 +516,19 @@ EXPORT_SYMBOL(ptp_cancel_worker_sync); static void __exit ptp_exit(void) { - class_destroy(ptp_class); + class_unregister(&ptp_class); unregister_chrdev_region(ptp_devt, MINORMASK + 1); - ida_destroy(&ptp_clocks_map); + xa_destroy(&ptp_clocks_map); } static int __init ptp_init(void) { int err; - ptp_class = class_create("ptp"); - if (IS_ERR(ptp_class)) { + err = class_register(&ptp_class); + if (err) { pr_err("ptp: failed to allocate class\n"); - return PTR_ERR(ptp_class); + return err; } err = alloc_chrdev_region(&ptp_devt, 0, MINORMASK + 1, "ptp"); @@ -530,12 +537,11 @@ static int __init ptp_init(void) goto no_region; } - ptp_class->dev_groups = ptp_groups; pr_info("PTP clock support registered\n"); return 0; no_region: - class_destroy(ptp_class); + class_unregister(&ptp_class); return err; } diff --git a/drivers/ptp/ptp_fc3.c b/drivers/ptp/ptp_fc3.c index 0e2286ba088a..6ef982862e27 100644 --- a/drivers/ptp/ptp_fc3.c +++ b/drivers/ptp/ptp_fc3.c @@ -996,13 +996,11 @@ static int idtfc3_probe(struct platform_device *pdev) return 0; } -static int idtfc3_remove(struct platform_device *pdev) +static void idtfc3_remove(struct platform_device *pdev) { struct idtfc3 *idtfc3 = platform_get_drvdata(pdev); ptp_clock_unregister(idtfc3->ptp_clock); - - return 0; } static struct platform_driver idtfc3_driver = { @@ -1010,7 +1008,7 @@ static struct platform_driver idtfc3_driver = { .name = "rc38xxx-phc", }, .probe = idtfc3_probe, - .remove = idtfc3_remove, + .remove_new = idtfc3_remove, }; module_platform_driver(idtfc3_driver); diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 45f9002a5dca..18934e28469e 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -120,7 +120,7 @@ static inline bool ptp_clock_freerun(struct ptp_clock *ptp) return ptp_vclock_in_use(ptp); } -extern struct class *ptp_class; +extern const struct class ptp_class; /* * see ptp_chardev.c diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index dcf752c9e045..7febfdcbde8b 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -241,7 +241,7 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index) return num; snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", pclock_index); - dev = class_find_device_by_name(ptp_class, name); + dev = class_find_device_by_name(&ptp_class, name); if (!dev) return num; diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index c0c8ab586957..d32ad46318cb 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1671,7 +1671,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port, void mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) { - struct host_port h_port[64]; + struct host_port *h_port = NULL; int i, j, found, host_port_count = 0, port_idx; u16 sz, attached_handle, ioc_status; struct mpi3_sas_io_unit_page0 *sas_io_unit_pg0 = NULL; @@ -1685,6 +1685,10 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) sas_io_unit_pg0 = kzalloc(sz, GFP_KERNEL); if (!sas_io_unit_pg0) return; + h_port = kcalloc(64, sizeof(struct host_port), GFP_KERNEL); + if (!h_port) + goto out; + if (mpi3mr_cfg_get_sas_io_unit_pg0(mrioc, sas_io_unit_pg0, sz)) { ioc_err(mrioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); @@ -1814,6 +1818,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) } } out: + kfree(h_port); kfree(sas_io_unit_pg0); } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 8761bc58d965..b8120ca93c79 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7378,7 +7378,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout) return -EFAULT; } - issue_diag_reset: + return 0; + +issue_diag_reset: rc = _base_diag_reset(ioc); return rc; } diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index f4bfd24386f1..f913e9bd57ed 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -265,10 +265,17 @@ static int pmic_glink_probe(struct platform_device *pdev) pg->client_mask = *match_data; + pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg); + if (IS_ERR(pg->pdr)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), + "failed to initialize pdr\n"); + return ret; + } + if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) { ret = pmic_glink_add_aux_device(pg, &pg->ucsi_aux, "ucsi"); if (ret) - return ret; + goto out_release_pdr_handle; } if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_ALTMODE)) { ret = pmic_glink_add_aux_device(pg, &pg->altmode_aux, "altmode"); @@ -281,17 +288,11 @@ static int pmic_glink_probe(struct platform_device *pdev) goto out_release_altmode_aux; } - pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg); - if (IS_ERR(pg->pdr)) { - ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), "failed to initialize pdr\n"); - goto out_release_aux_devices; - } - service = pdr_add_lookup(pg->pdr, "tms/servreg", "msm/adsp/charger_pd"); if (IS_ERR(service)) { ret = dev_err_probe(&pdev->dev, PTR_ERR(service), "failed adding pdr lookup for charger_pd\n"); - goto out_release_pdr_handle; + goto out_release_aux_devices; } mutex_lock(&__pmic_glink_lock); @@ -300,8 +301,6 @@ static int pmic_glink_probe(struct platform_device *pdev) return 0; -out_release_pdr_handle: - pdr_handle_release(pg->pdr); out_release_aux_devices: if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_BATT)) pmic_glink_del_aux_device(pg, &pg->ps_aux); @@ -311,6 +310,8 @@ out_release_altmode_aux: out_release_ucsi_aux: if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) pmic_glink_del_aux_device(pg, &pg->ucsi_aux); +out_release_pdr_handle: + pdr_handle_release(pg->pdr); return ret; } diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 5fcd0fdd2faa..b3808fc24c69 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -76,7 +76,7 @@ struct pmic_glink_altmode_port { struct work_struct work; - struct device *bridge; + struct auxiliary_device *bridge; enum typec_orientation orientation; u16 svid; @@ -230,7 +230,7 @@ static void pmic_glink_altmode_worker(struct work_struct *work) else pmic_glink_altmode_enable_usb(altmode, alt_port); - drm_aux_hpd_bridge_notify(alt_port->bridge, + drm_aux_hpd_bridge_notify(&alt_port->bridge->dev, alt_port->hpd_state ? connector_status_connected : connector_status_disconnected); @@ -454,7 +454,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, alt_port->index = port; INIT_WORK(&alt_port->work, pmic_glink_altmode_worker); - alt_port->bridge = drm_dp_hpd_bridge_register(dev, to_of_node(fwnode)); + alt_port->bridge = devm_drm_dp_hpd_bridge_alloc(dev, to_of_node(fwnode)); if (IS_ERR(alt_port->bridge)) { fwnode_handle_put(fwnode); return PTR_ERR(alt_port->bridge); @@ -510,6 +510,16 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, } } + for (port = 0; port < ARRAY_SIZE(altmode->ports); port++) { + alt_port = &altmode->ports[port]; + if (!alt_port->bridge) + continue; + + ret = devm_drm_dp_hpd_bridge_add(dev, alt_port->bridge); + if (ret) + return ret; + } + altmode->client = devm_pmic_glink_register_client(dev, altmode->owner_id, pmic_glink_altmode_callback, diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 4b1092127694..1892e49a8e6a 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f2ed7167c848..4b2fcb228a0a 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -141,10 +141,8 @@ struct vhost_net { unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; - /* Private page frag */ - struct page_frag page_frag; - /* Refcount bias of page frag */ - int refcnt_bias; + /* Private page frag cache */ + struct page_frag_cache pf_cache; }; static unsigned vhost_net_zcopy_mask __read_mostly; @@ -655,41 +653,6 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } -static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, - struct page_frag *pfrag, gfp_t gfp) -{ - if (pfrag->page) { - if (pfrag->offset + sz <= pfrag->size) - return true; - __page_frag_cache_drain(pfrag->page, net->refcnt_bias); - } - - pfrag->offset = 0; - net->refcnt_bias = 0; - if (SKB_FRAG_PAGE_ORDER) { - /* Avoid direct reclaim but allow kswapd to wake */ - pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | - __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, - SKB_FRAG_PAGE_ORDER); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; - goto done; - } - } - pfrag->page = alloc_page(gfp); - if (likely(pfrag->page)) { - pfrag->size = PAGE_SIZE; - goto done; - } - return false; - -done: - net->refcnt_bias = USHRT_MAX; - page_ref_add(pfrag->page, USHRT_MAX - 1); - return true; -} - #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, @@ -699,7 +662,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); struct socket *sock = vhost_vq_get_backend(vq); - struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; @@ -710,6 +672,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, int sock_hlen = nvq->sock_hlen; void *buf; int copied; + int ret; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; @@ -719,18 +682,17 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); - alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!vhost_net_page_frag_refill(net, buflen, - alloc_frag, GFP_KERNEL))) + buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); + if (unlikely(!buf)) return -ENOMEM; - buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + - offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied != sock_hlen) - return -EFAULT; + copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied != sock_hlen) { + ret = -EFAULT; + goto err; + } hdr = buf; gso = &hdr->gso; @@ -743,27 +705,30 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); - if (vhost16_to_cpu(vq, gso->hdr_len) > len) - return -EINVAL; + if (vhost16_to_cpu(vq, gso->hdr_len) > len) { + ret = -EINVAL; + goto err; + } } len -= sock_hlen; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + pad, - len, from); - if (copied != len) - return -EFAULT; + copied = copy_from_iter(buf + pad, len, from); + if (copied != len) { + ret = -EFAULT; + goto err; + } xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; - --net->refcnt_bias; - alloc_frag->offset += buflen; - ++nvq->batched_xdp; return 0; + +err: + page_frag_free(buf); + return ret; } static void handle_tx_copy(struct vhost_net *net, struct socket *sock) @@ -1353,8 +1318,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) vqs[VHOST_NET_VQ_RX]); f->private_data = n; - n->page_frag.page = NULL; - n->refcnt_bias = 0; + n->pf_cache.va = NULL; return 0; } @@ -1422,8 +1386,7 @@ static int vhost_net_release(struct inode *inode, struct file *f) kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); - if (n->page_frag.page) - __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias); + page_frag_cache_drain(&n->pf_cache); kvfree(n); return 0; } diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 1183e7a871f8..46823c2e2ba1 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2399,11 +2399,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; - char *old_data = NULL; + u8 *old_data = vc->vc_font.data; resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); - if (p->userfont) - old_data = vc->vc_font.data; vc->vc_font.data = (void *)(p->fontdata = data); old_userfont = p->userfont; if ((p->userfont = userfont)) @@ -2437,13 +2435,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, update_screen(vc); } - if (old_data && (--REFCOUNT(old_data) == 0)) + if (old_userfont && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0; err_out: p->fontdata = old_data; - vc->vc_font.data = (void *)old_data; + vc->vc_font.data = old_data; if (userfont) { p->userfont = old_userfont; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index c26ee6fd73c9..8fdccf033b2d 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1010,8 +1010,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) goto getmem_done; } pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n"); - } else { - goto err1; } /* diff --git a/fs/afs/dir.c b/fs/afs/dir.c index b5b8de521f99..8a67fc427e74 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -479,8 +479,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, dire->u.name[0] == '.' && ctx->actor != afs_lookup_filldir && ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) + memcmp(dire->u.name, ".__afs", 6) == 0) { + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + } /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, @@ -589,8 +589,8 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; /* @@ -600,9 +600,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) if (!(iocb->ki_flags & IOCB_AIO_RW)) return; + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e71ef97d0a7c..c843563914ca 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1307,12 +1307,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, - * pass 0 for new allocation. + * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev, + u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; @@ -1342,9 +1342,9 @@ again: * that common but still possible. In that case, we just need * to free the anon_dev. */ - if (unlikely(anon_dev)) { - free_anon_bdev(anon_dev); - anon_dev = 0; + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; } if (check_ref && btrfs_root_refs(&root->root_item) == 0) { @@ -1366,7 +1366,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root, anon_dev); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; @@ -1402,7 +1402,7 @@ fail: * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ - if (anon_dev) + if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); @@ -1418,7 +1418,7 @@ fail: struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { - return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* @@ -1426,11 +1426,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, * the anonymous block device id * * @objectid: tree objectid - * @anon_dev: if zero, allocate a new anonymous block device or use the - * parameter value + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev) + u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 9413726b329b..eb3473d1c1ac 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -61,7 +61,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev); + u64 objectid, dev_t *anon_dev); struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e19a2475ab3..8b4bef05e222 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2480,6 +2480,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache, u64 offset, u64 phys, u64 len, u32 flags) { + u64 cache_end; int ret = 0; /* Set at the end of extent_fiemap(). */ @@ -2489,15 +2490,102 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, goto assign; /* - * Sanity check, extent_fiemap() should have ensured that new - * fiemap extent won't overlap with cached one. - * Not recoverable. + * When iterating the extents of the inode, at extent_fiemap(), we may + * find an extent that starts at an offset behind the end offset of the + * previous extent we processed. This happens if fiemap is called + * without FIEMAP_FLAG_SYNC and there are ordered extents completing + * while we call btrfs_next_leaf() (through fiemap_next_leaf_item()). * - * NOTE: Physical address can overlap, due to compression + * For example we are in leaf X processing its last item, which is the + * file extent item for file range [512K, 1M[, and after + * btrfs_next_leaf() releases the path, there's an ordered extent that + * completes for the file range [768K, 2M[, and that results in trimming + * the file extent item so that it now corresponds to the file range + * [512K, 768K[ and a new file extent item is inserted for the file + * range [768K, 2M[, which may end up as the last item of leaf X or as + * the first item of the next leaf - in either case btrfs_next_leaf() + * will leave us with a path pointing to the new extent item, for the + * file range [768K, 2M[, since that's the first key that follows the + * last one we processed. So in order not to report overlapping extents + * to user space, we trim the length of the previously cached extent and + * emit it. + * + * Upon calling btrfs_next_leaf() we may also find an extent with an + * offset smaller than or equals to cache->offset, and this happens + * when we had a hole or prealloc extent with several delalloc ranges in + * it, but after btrfs_next_leaf() released the path, delalloc was + * flushed and the resulting ordered extents were completed, so we can + * now have found a file extent item for an offset that is smaller than + * or equals to what we have in cache->offset. We deal with this as + * described below. */ - if (cache->offset + cache->len > offset) { - WARN_ON(1); - return -EINVAL; + cache_end = cache->offset + cache->len; + if (cache_end > offset) { + if (offset == cache->offset) { + /* + * We cached a dealloc range (found in the io tree) for + * a hole or prealloc extent and we have now found a + * file extent item for the same offset. What we have + * now is more recent and up to date, so discard what + * we had in the cache and use what we have just found. + */ + goto assign; + } else if (offset > cache->offset) { + /* + * The extent range we previously found ends after the + * offset of the file extent item we found and that + * offset falls somewhere in the middle of that previous + * extent range. So adjust the range we previously found + * to end at the offset of the file extent item we have + * just found, since this extent is more up to date. + * Emit that adjusted range and cache the file extent + * item we have just found. This corresponds to the case + * where a previously found file extent item was split + * due to an ordered extent completing. + */ + cache->len = offset - cache->offset; + goto emit; + } else { + const u64 range_end = offset + len; + + /* + * The offset of the file extent item we have just found + * is behind the cached offset. This means we were + * processing a hole or prealloc extent for which we + * have found delalloc ranges (in the io tree), so what + * we have in the cache is the last delalloc range we + * found while the file extent item we found can be + * either for a whole delalloc range we previously + * emmitted or only a part of that range. + * + * We have two cases here: + * + * 1) The file extent item's range ends at or behind the + * cached extent's end. In this case just ignore the + * current file extent item because we don't want to + * overlap with previous ranges that may have been + * emmitted already; + * + * 2) The file extent item starts behind the currently + * cached extent but its end offset goes beyond the + * end offset of the cached extent. We don't want to + * overlap with a previous range that may have been + * emmitted already, so we emit the currently cached + * extent and then partially store the current file + * extent item's range in the cache, for the subrange + * going the cached extent's end to the end of the + * file extent item. + */ + if (range_end <= cache_end) + return 0; + + if (!(flags & (FIEMAP_EXTENT_ENCODED | FIEMAP_EXTENT_DELALLOC))) + phys += cache_end - offset; + + offset = cache_end; + len = range_end - cache_end; + goto emit; + } } /* @@ -2517,6 +2605,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, return 0; } +emit: /* Not mergeable, need to submit cached one */ ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); @@ -2907,17 +2996,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, range_end = round_up(start + len, sectorsize); prev_extent_end = range_start; - btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) - goto out_unlock; + goto out; btrfs_release_path(path); path->reada = READA_FORWARD; ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* * No file extent item found, but we may have delalloc between @@ -2964,7 +3051,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, backref_ctx, 0, 0, 0, prev_extent_end, hole_end); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; @@ -3020,7 +3107,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, extent_gen, backref_ctx); if (ret < 0) - goto out_unlock; + goto out; else if (ret > 0) flags |= FIEMAP_EXTENT_SHARED; } @@ -3031,7 +3118,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; @@ -3042,12 +3129,12 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, next_item: if (fatal_signal_pending(current)) { ret = -EINTR; - goto out_unlock; + goto out; } ret = fiemap_next_leaf_item(inode, path); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* No more file extent items for this inode. */ break; @@ -3071,7 +3158,7 @@ check_eof_delalloc: &delalloc_cached_state, backref_ctx, 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) - goto out_unlock; + goto out; prev_extent_end = range_end; } @@ -3109,9 +3196,6 @@ check_eof_delalloc: } ret = emit_last_fiemap_cache(fieinfo, &cache); - -out_unlock: - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); out: free_extent_state(delalloc_cached_state); btrfs_free_backref_share_ctx(backref_ctx); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f88e0ca8331d..4795738d5785 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7835,6 +7835,7 @@ struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { + struct btrfs_inode *btrfs_inode = BTRFS_I(inode); int ret; ret = fiemap_prep(inode, fieinfo, start, &len, 0); @@ -7860,7 +7861,26 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return ret; } - return extent_fiemap(BTRFS_I(inode), fieinfo, start, len); + btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED); + + /* + * We did an initial flush to avoid holding the inode's lock while + * triggering writeback and waiting for the completion of IO and ordered + * extents. Now after we locked the inode we do it again, because it's + * possible a new write may have happened in between those two steps. + */ + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) { + ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX); + if (ret) { + btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); + return ret; + } + } + + ret = extent_fiemap(btrfs_inode, fieinfo, start, len); + btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); + + return ret; } static int btrfs_writepages(struct address_space *mapping, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ac3316e0d11c..9d1eac15e09e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -721,7 +721,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, free_extent_buffer(leaf); leaf = NULL; - new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c52807d97efa..bf8e64c766b6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1834,7 +1834,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); pending->snap = NULL; diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index fae97c25ce58..8109aba66e02 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -380,10 +380,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, ceph_decode_skip_8(p, end, bad_ext); /* required_client_features */ ceph_decode_skip_set(p, end, 64, bad_ext); + /* bal_rank_mask */ + ceph_decode_skip_string(p, end, bad_ext); + } + if (mdsmap_ev >= 18) { ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); - } else { - /* This forces the usage of the (sync) SETXATTR Op */ - m->m_max_xattr_size = 0; } bad_ext: doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h index 89f1931f1ba6..1f2171dd01bf 100644 --- a/fs/ceph/mdsmap.h +++ b/fs/ceph/mdsmap.h @@ -27,7 +27,11 @@ struct ceph_mdsmap { u32 m_session_timeout; /* seconds */ u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; - u64 m_max_xattr_size; /* maximum size for xattrs blob */ + /* + * maximum size for xattrs blob. + * Zeroed by default to force the usage of the (sync) SETXATTR Op. + */ + u64 m_max_xattr_size; u32 m_max_mds; /* expected up:active mds number */ u32 m_num_active_mds; /* actual up:active mds number */ u32 possible_max_rank; /* possible max rank index */ diff --git a/fs/coredump.c b/fs/coredump.c index f258c17c1841..be6403b4b14b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -872,6 +872,9 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) loff_t pos; ssize_t n; + if (!page) + return 0; + if (cprm->to_skip) { if (!__dump_skip(cprm, cprm->to_skip)) return 0; @@ -884,7 +887,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) pos = file->f_pos; bvec_set_page(&bvec, page, PAGE_SIZE, 0); iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); - iov_iter_set_copy_mc(&iter); n = __kernel_write_iter(cprm->file, &iter, &pos); if (n != PAGE_SIZE) return 0; @@ -895,10 +897,44 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) return 1; } +/* + * If we might get machine checks from kernel accesses during the + * core dump, let's get those errors early rather than during the + * IO. This is not performance-critical enough to warrant having + * all the machine check logic in the iovec paths. + */ +#ifdef copy_mc_to_kernel + +#define dump_page_alloc() alloc_page(GFP_KERNEL) +#define dump_page_free(x) __free_page(x) +static struct page *dump_page_copy(struct page *src, struct page *dst) +{ + void *buf = kmap_local_page(src); + size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE); + kunmap_local(buf); + return left ? NULL : dst; +} + +#else + +/* We just want to return non-NULL; it's never used. */ +#define dump_page_alloc() ERR_PTR(-EINVAL) +#define dump_page_free(x) ((void)(x)) +static inline struct page *dump_page_copy(struct page *src, struct page *dst) +{ + return src; +} +#endif + int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len) { unsigned long addr; + struct page *dump_page; + + dump_page = dump_page_alloc(); + if (!dump_page) + return 0; for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page; @@ -912,14 +948,17 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, */ page = get_dump_page(addr); if (page) { - int stop = !dump_emit_page(cprm, page); + int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page)); put_page(page); - if (stop) + if (stop) { + dump_page_free(dump_page); return 0; + } } else { dump_skip(cprm, PAGE_SIZE); } } + dump_page_free(dump_page); return 1; } #endif diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index 169252e6dc46..f7206158ee81 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -38,7 +38,7 @@ struct efivar_entry { int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, struct list_head *), - void *data, bool duplicates, struct list_head *head); + void *data, struct list_head *head); int efivar_entry_add(struct efivar_entry *entry, struct list_head *head); void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6038dd39367a..bb14462f6d99 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -343,12 +343,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - err = efivar_init(efivarfs_callback, (void *)sb, true, - &sfi->efivarfs_list); - if (err) - efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL); - - return err; + return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list); } static int efivarfs_get_tree(struct fs_context *fc) diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 114ff0fd4e55..4d722af1014f 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -361,7 +361,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, * efivar_init - build the initial list of EFI variables * @func: callback function to invoke for every variable * @data: function-specific data to pass to @func - * @duplicates: error if we encounter duplicates on @head? * @head: initialised head of variable list * * Get every EFI variable from the firmware and invoke @func. @func @@ -371,9 +370,9 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, */ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, struct list_head *), - void *data, bool duplicates, struct list_head *head) + void *data, struct list_head *head) { - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -390,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, goto free; /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = efivar_get_next_variable(&variable_name_size, variable_name, @@ -413,8 +413,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, * we'll ever see a different variable name, * and may end up looping here forever. */ - if (duplicates && - variable_is_present(variable_name, &vendor_guid, + if (variable_is_present(variable_name, &vendor_guid, head)) { dup_variable_bug(variable_name, &vendor_guid, variable_name_size); @@ -432,9 +431,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index d25a96a148af..cc00f1a7a1e1 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -35,13 +35,18 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) if (new_num_clusters == num_clusters) goto out; - exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags); - ret = exfat_find_last_cluster(sb, &clu, &last_clu); - if (ret) - return ret; + if (num_clusters) { + exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags); + ret = exfat_find_last_cluster(sb, &clu, &last_clu); + if (ret) + return ret; + + clu.dir = last_clu + 1; + } else { + last_clu = EXFAT_EOF_CLUSTER; + clu.dir = EXFAT_EOF_CLUSTER; + } - clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ? - EXFAT_EOF_CLUSTER : last_clu + 1; clu.size = 0; clu.flags = ei->flags; @@ -51,17 +56,19 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) return ret; /* Append new clusters to chain */ - if (clu.flags != ei->flags) { - exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters); - ei->flags = ALLOC_FAT_CHAIN; - } - if (clu.flags == ALLOC_FAT_CHAIN) - if (exfat_ent_set(sb, last_clu, clu.dir)) - goto free_clu; - - if (num_clusters == 0) + if (num_clusters) { + if (clu.flags != ei->flags) + if (exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters)) + goto free_clu; + + if (clu.flags == ALLOC_FAT_CHAIN) + if (exfat_ent_set(sb, last_clu, clu.dir)) + goto free_clu; + } else ei->start_clu = clu.dir; + ei->flags = clu.flags; + out: inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); /* Expanded range not zeroed, do not update valid_size */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 5a2512d20bd0..98401de832ee 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -350,7 +350,6 @@ xfs_setup_dax_always( return -EINVAL; } - xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); return 0; disable_dax: diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h index c4c423e97f06..4453906105ca 100644 --- a/include/drm/bridge/aux-bridge.h +++ b/include/drm/bridge/aux-bridge.h @@ -9,6 +9,8 @@ #include <drm/drm_connector.h> +struct auxiliary_device; + #if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE) int drm_aux_bridge_register(struct device *parent); #else @@ -19,10 +21,23 @@ static inline int drm_aux_bridge_register(struct device *parent) #endif #if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE) +struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np); +int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev); struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np); void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status); #else +static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, + struct device_node *np) +{ + return NULL; +} + +static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev) +{ + return 0; +} + static inline struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np) { diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index ebfa12f69501..63928f173223 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -66,7 +66,8 @@ _pfx "mask is not constant"); \ BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ - ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ + ~((_mask) >> __bf_shf(_mask)) & \ + (0 + (_val)) : 0, \ _pfx "value too large for the field"); \ BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ __bf_cast_unsigned(_reg, ~0ull), \ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5814e9ee40ba..00b8c6d4355c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -63,6 +63,8 @@ struct device; * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest * bitmap_replace(dst, old, new, mask, nbits) *dst = (*old & ~(*mask)) | (*new & *mask) + * bitmap_scatter(dst, src, mask, nbits) *dst = map(dense, sparse)(src) + * bitmap_gather(dst, src, mask, nbits) *dst = map(sparse, dense)(src) * bitmap_remap(dst, src, old, new, nbits) *dst = map(old, new)(src) * bitmap_bitremap(oldbit, old, new, nbits) newbit = map(old, new)(oldbit) * bitmap_onto(dst, orig, relmap, nbits) *dst = orig relative to relmap @@ -499,6 +501,105 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } +/** + * bitmap_scatter - Scatter a bitmap according to the given mask + * @dst: scattered bitmap + * @src: gathered bitmap + * @mask: mask representing bits to assign to in the scattered bitmap + * @nbits: number of bits in each of these bitmaps + * + * Scatters bitmap with sequential bits according to the given @mask. + * + * Example: + * If @src bitmap = 0x005a, with @mask = 0x1313, @dst will be 0x0302. + * + * Or in binary form + * @src @mask @dst + * 0000000001011010 0001001100010011 0000001100000010 + * + * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12) + * + * A more 'visual' description of the operation: + * src: 0000000001011010 + * |||||| + * +------+||||| + * | +----+|||| + * | |+----+||| + * | || +-+|| + * | || | || + * mask: ...v..vv...v..vv + * ...0..11...0..10 + * dst: 0000001100000010 + * + * A relationship exists between bitmap_scatter() and bitmap_gather(). + * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation. + * See bitmap_scatter() for details related to this relationship. + */ +static inline void bitmap_scatter(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int n = 0; + unsigned int bit; + + bitmap_zero(dst, nbits); + + for_each_set_bit(bit, mask, nbits) + __assign_bit(bit, dst, test_bit(n++, src)); +} + +/** + * bitmap_gather - Gather a bitmap according to given mask + * @dst: gathered bitmap + * @src: scattered bitmap + * @mask: mask representing bits to extract from in the scattered bitmap + * @nbits: number of bits in each of these bitmaps + * + * Gathers bitmap with sparse bits according to the given @mask. + * + * Example: + * If @src bitmap = 0x0302, with @mask = 0x1313, @dst will be 0x001a. + * + * Or in binary form + * @src @mask @dst + * 0000001100000010 0001001100010011 0000000000011010 + * + * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5) + * + * A more 'visual' description of the operation: + * mask: ...v..vv...v..vv + * src: 0000001100000010 + * ^ ^^ ^ 0 + * | || | 10 + * | || > 010 + * | |+--> 1010 + * | +--> 11010 + * +----> 011010 + * dst: 0000000000011010 + * + * A relationship exists between bitmap_gather() and bitmap_scatter(). See + * bitmap_scatter() for the bitmap scatter detailed operations. + * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n). + * The operation bitmap_gather(result, scattered, mask, n) leads to a result + * equal or equivalent to src. + * + * The result can be 'equivalent' because bitmap_scatter() and bitmap_gather() + * are not bijective. + * The result and src values are equivalent in that sense that a call to + * bitmap_scatter(res, src, mask, n) and a call to + * bitmap_scatter(res, result, mask, n) will lead to the same res value. + */ +static inline void bitmap_gather(unsigned long *dst, const unsigned long *src, + const unsigned long *mask, unsigned int nbits) +{ + unsigned int n = 0; + unsigned int bit; + + bitmap_zero(dst, nbits); + + for_each_set_bit(bit, mask, nbits) + __assign_bit(n++, dst, test_bit(bit, src)); +} + static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 555aae5448ae..bd1e361b351c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -83,7 +83,7 @@ struct bvec_iter { unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -} __packed; +} __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index e3abde993244..d275736230b3 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -123,15 +123,24 @@ struct dpll_pin_properties { }; #if IS_ENABLED(CONFIG_DPLL) -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void dpll_netdev_pin_clear(struct net_device *dev); + +size_t dpll_netdev_pin_handle_size(const struct net_device *dev); +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev); #else -static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +static inline void +dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { } +static inline void dpll_netdev_pin_clear(struct net_device *dev) { } + +static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev) { return 0; } -static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static inline int +dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev) { return 0; } @@ -170,13 +179,4 @@ int dpll_device_change_ntf(struct dpll_device *dpll); int dpll_pin_change_ntf(struct dpll_pin *pin); -#if !IS_ENABLED(CONFIG_DPLL) -static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ - return NULL; -} -#else -struct dpll_pin *netdev_dpll_pin(const struct net_device *dev); -#endif - #endif diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 407c2f281b64..5693a4be0d9a 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -38,14 +38,22 @@ #ifdef __KERNEL__ +#include <linux/bitops.h> #include <asm/bug.h> +#define DQL_HIST_LEN 4 +#define DQL_HIST_ENT(dql, idx) ((dql)->history[(idx) % DQL_HIST_LEN]) + struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + unsigned long history_head; /* top 58 bits of jiffies */ + /* stall entries, a bit per entry */ + unsigned long history[DQL_HIST_LEN]; + /* Fields accessed only by completion path (dql_completed) */ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */ @@ -62,6 +70,13 @@ struct dql { unsigned int max_limit; /* Max limit */ unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ + + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + /* Longest stall detected, reported to user */ + unsigned short stall_max; + unsigned long last_reap; /* Last reap (in jiffies) */ + unsigned long stall_cnt; /* Number of stalls */ }; /* Set some static maximums */ @@ -74,6 +89,8 @@ struct dql { */ static inline void dql_queued(struct dql *dql, unsigned int count) { + unsigned long map, now, now_hi, i; + BUG_ON(count > DQL_MAX_OBJECT); dql->last_obj_cnt = count; @@ -86,6 +103,34 @@ static inline void dql_queued(struct dql *dql, unsigned int count) barrier(); dql->num_queued += count; + + now = jiffies; + now_hi = now / BITS_PER_LONG; + + /* The following code set a bit in the ring buffer, where each + * bit trackes time the packet was queued. The dql->history buffer + * tracks DQL_HIST_LEN * BITS_PER_LONG time (jiffies) slot + */ + if (unlikely(now_hi != dql->history_head)) { + /* About to reuse slots, clear them */ + for (i = 0; i < DQL_HIST_LEN; i++) { + /* Multiplication masks high bits */ + if (now_hi * BITS_PER_LONG == + (dql->history_head + i) * BITS_PER_LONG) + break; + DQL_HIST_ENT(dql, dql->history_head + i + 1) = 0; + } + /* pairs with smp_rmb() in dql_check_stall() */ + smp_wmb(); + WRITE_ONCE(dql->history_head, now_hi); + } + + /* __set_bit() does not guarantee WRITE_ONCE() semantics */ + map = DQL_HIST_ENT(dql, now_hi); + + /* Populate the history with an entry (bit) per queued */ + if (!(map & BIT_MASK(now))) + WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } /* Returns how many objects can be queued, < 0 indicates over limit. */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index de292a007138..6cef1c241180 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -311,15 +311,23 @@ extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; +void page_frag_cache_drain(struct page_frag_cache *nc); extern void __page_frag_cache_drain(struct page *page, unsigned int count); -extern void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} static inline void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask) { - return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); } extern void page_frag_free(void *addr); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2b00faf98017..6ef0557b4bff 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41f03b352401..bf9324a31ae9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -823,6 +823,7 @@ struct mlx5_core_dev { struct blocking_notifier_head macsec_nh; #endif u64 num_ipsec_offloads; + struct mlx5_sd *sd; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 628a3aa7a7e0..49f660563e49 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10253,7 +10253,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcqi[0x1]; u8 mcqs[0x1]; - u8 regs_95_to_87[0x9]; + u8 regs_95_to_90[0x6]; + u8 mpir[0x1]; + u8 regs_88_to_87[0x2]; u8 mpegc[0x1]; u8 mtutc[0x1]; u8 regs_84_to_68[0x11]; @@ -10261,7 +10263,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_63_to_46[0x12]; u8 mrtc[0x1]; - u8 regs_44_to_32[0xd]; + u8 regs_44_to_41[0x4]; + u8 mfrl[0x1]; + u8 regs_39_to_32[0x8]; u8 regs_31_to_10[0x16]; u8 mtmp[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c41019f34179..c6f6ac779b34 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,8 +79,6 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; -/* DPLL specific */ -struct dpll_pin; typedef u32 xdp_features_t; @@ -227,12 +225,6 @@ struct net_device_core_stats { #include <linux/cache.h> #include <linux/skbuff.h> -#ifdef CONFIG_RPS -#include <linux/static_key.h> -extern struct static_key_false rps_needed; -extern struct static_key_false rfs_needed; -#endif - struct neighbour; struct neigh_parms; struct sk_buff; @@ -732,86 +724,10 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node #endif } -#ifdef CONFIG_RPS -/* - * This structure holds an RPS map which can be of variable length. The - * map is an array of CPUs. - */ -struct rps_map { - unsigned int len; - struct rcu_head rcu; - u16 cpus[]; -}; -#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) - -/* - * The rps_dev_flow structure contains the mapping of a flow to a CPU, the - * tail pointer for that CPU's input queue at the time of last enqueue, and - * a hardware filter index. - */ -struct rps_dev_flow { - u16 cpu; - u16 filter; - unsigned int last_qtail; -}; -#define RPS_NO_FILTER 0xffff - -/* - * The rps_dev_flow_table structure contains a table of flow mappings. - */ -struct rps_dev_flow_table { - unsigned int mask; - struct rcu_head rcu; - struct rps_dev_flow flows[]; -}; -#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ - ((_num) * sizeof(struct rps_dev_flow))) - -/* - * The rps_sock_flow_table contains mappings of flows to the last CPU - * on which they were processed by the application (set in recvmsg). - * Each entry is a 32bit value. Upper part is the high-order bits - * of flow hash, lower part is CPU number. - * rps_cpu_mask is used to partition the space, depending on number of - * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 - * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, - * meaning we use 32-6=26 bits for the hash. - */ -struct rps_sock_flow_table { - u32 mask; - - u32 ents[] ____cacheline_aligned_in_smp; -}; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) - -#define RPS_NO_CPU 0xffff - -extern u32 rps_cpu_mask; -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - -static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) { - unsigned int index = hash & table->mask; - u32 val = hash & ~rps_cpu_mask; - - /* We only give a hint, preemption can change CPU under us */ - val |= raw_smp_processor_id(); - - /* The following WRITE_ONCE() is paired with the READ_ONCE() - * here, and another one in get_rps_cpu(). - */ - if (READ_ONCE(table->ents[index]) != val) - WRITE_ONCE(table->ents[index], val); - } -} - #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif -#endif /* CONFIG_RPS */ /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { @@ -2039,6 +1955,7 @@ enum netdev_reg_state { * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops + * @stat_ops: Optional ops for queue-aware statistics * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2419,6 +2336,8 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; + const struct netdev_stat_ops *stat_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -3500,6 +3419,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue #endif } +static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) +{ +#ifdef CONFIG_BQL + /* Non-BQL migrated drivers will return 0, too. */ + return dql_avail(&txq->dql); +#else + return 0; +#endif +} + /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue @@ -3972,8 +3901,6 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); -struct packet_offload *gro_find_receive_by_type(__be16 type); -struct packet_offload *gro_find_complete_by_type(__be16 type); static inline void napi_free_frags(struct napi_struct *napi) { @@ -4033,8 +3960,6 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); -void netdev_dpll_pin_clear(struct net_device *dev); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -4787,11 +4712,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); -extern int netdev_max_backlog; -extern int dev_rx_weight; -extern int dev_tx_weight; -extern int gro_normal_batch; - enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, @@ -5301,7 +5221,6 @@ static inline const char *netdev_reg_state(const struct net_device *dev) #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) -extern struct list_head ptype_all __read_mostly; extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; diff --git a/include/linux/phy.h b/include/linux/phy.h index e3ab2c347a59..3f68b8239bb1 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -30,6 +30,7 @@ #include <linux/refcount.h> #include <linux/atomic.h> +#include <net/eee.h> #define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ @@ -594,6 +595,8 @@ struct macsec_ops; * @supported_eee: supported PHY EEE linkmodes * @advertising_eee: Currently advertised EEE linkmodes * @eee_enabled: Flag indicating whether the EEE feature is enabled + * @enable_tx_lpi: When True, MAC should transmit LPI to PHY + * @eee_cfg: User configuration of EEE * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited @@ -703,7 +706,7 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); - /* used for eee validation */ + /* used for eee validation and configuration*/ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); bool eee_enabled; @@ -713,6 +716,8 @@ struct phy_device { /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; + bool enable_tx_lpi; + struct eee_config eee_cfg; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; @@ -1968,6 +1973,7 @@ void phy_advertise_supported(struct phy_device *phydev); void phy_advertise_eee_all(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); +void phy_support_eee(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 6ba411732a0d..9a57deefcb07 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -480,9 +480,6 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. - * - * When present, this overrides pcs_get_state() in &struct - * phylink_pcs_ops. */ void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1470b74fb6d2..3023bc2be6a1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -822,9 +822,9 @@ typedef unsigned char *sk_buff_data_t; * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * delivery_time in mono clock base (i.e., EDT) or a clock base chosen + * by SO_TXTIME. If zero, skb->tstamp has the (rcv) timestamp at + * ingress. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -1237,6 +1237,24 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } +static inline bool skb_data_unref(const struct sk_buff *skb, + struct skb_shared_info *shinfo) +{ + int bias; + + if (!skb->cloned) + return true; + + bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; + + if (atomic_read(&shinfo->dataref) == bias) + smp_rmb(); + else if (atomic_sub_return(bias, &shinfo->dataref)) + return false; + + return true; +} + void __fix_address kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); @@ -1271,7 +1289,6 @@ static inline void consume_skb(struct sk_buff *skb) void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); -extern struct kmem_cache *skbuff_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, @@ -3036,6 +3053,7 @@ static inline int skb_transport_offset(const struct sk_buff *skb) static inline u32 skb_network_header_len(const struct sk_buff *skb) { + DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 988a30ef6bfe..55399ee2a57e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -304,7 +304,7 @@ struct tcp_sock { __cacheline_group_end(tcp_sock_write_txrx); /* RX read-write hotpath cache lines */ - __cacheline_group_begin(tcp_sock_write_rx); + __cacheline_group_begin(tcp_sock_write_rx) __aligned(8); u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived * sum(delta(rcv_nxt)), or how many bytes diff --git a/include/linux/uio.h b/include/linux/uio.h index bea9c89922d9..00cebe2b70de 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -40,7 +40,6 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; - bool copy_mc; bool nofault; bool data_source; size_t iov_offset; @@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); -static inline void iov_iter_set_copy_mc(struct iov_iter *i) -{ - i->copy_mc = true; -} - -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return i->copy_mc; -} #else #define _copy_mc_to_iter _copy_to_iter -static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return false; -} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, - .copy_mc = false, .data_source = direction, .ubuf = buf, .count = count, diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 7ffa8c192c3f..9fe95a22abeb 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -164,6 +164,8 @@ struct bt_voice { #define BT_ISO_QOS_BIG_UNSET 0xff #define BT_ISO_QOS_BIS_UNSET 0xff +#define BT_ISO_SYNC_TIMEOUT 0x07d0 /* 20 secs */ + struct bt_iso_io_qos { __u32 interval; __u16 latency; diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index bdee5d649cc6..8701ca5f31ee 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -330,6 +330,14 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_LE_CODED, + + /* + * When this quirk is set, the HCI_OP_READ_ENC_KEY_SIZE command is + * skipped during an HCI_EV_ENCRYPT_CHANGE event. This is required + * for Actions Semiconductor ATS2851 based controllers, which erroneously + * claim to support it. + */ + HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, }; /* HCI device flags */ @@ -372,6 +380,7 @@ enum { HCI_SETUP, HCI_CONFIG, HCI_DEBUGFS_CREATED, + HCI_POWERING_DOWN, HCI_AUTO_OFF, HCI_RFKILLED, HCI_MGMT, @@ -393,7 +402,6 @@ enum { HCI_LIMITED_PRIVACY, HCI_RPA_EXPIRED, HCI_RPA_RESOLVING, - HCI_HS_ENABLED, HCI_LE_ENABLED, HCI_ADVERTISING, HCI_ADVERTISING_CONNECTABLE, @@ -437,7 +445,7 @@ enum { #define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ -#define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */ +#define HCI_ACL_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_CONN_TIMEOUT msecs_to_jiffies(20000) /* 20 seconds */ #define HCI_LE_AUTOCONN_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ @@ -653,6 +661,7 @@ enum { #define HCI_ERROR_PIN_OR_KEY_MISSING 0x06 #define HCI_ERROR_MEMORY_EXCEEDED 0x07 #define HCI_ERROR_CONNECTION_TIMEOUT 0x08 +#define HCI_ERROR_COMMAND_DISALLOWED 0x0c #define HCI_ERROR_REJ_LIMITED_RESOURCES 0x0d #define HCI_ERROR_REJ_BAD_ADDR 0x0f #define HCI_ERROR_INVALID_PARAMETERS 0x12 @@ -661,6 +670,7 @@ enum { #define HCI_ERROR_REMOTE_POWER_OFF 0x15 #define HCI_ERROR_LOCAL_HOST_TERM 0x16 #define HCI_ERROR_PAIRING_NOT_ALLOWED 0x18 +#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE 0x1e #define HCI_ERROR_INVALID_LL_PARAMS 0x1e #define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c @@ -2035,6 +2045,7 @@ struct hci_cp_le_set_per_adv_params { } __packed; #define HCI_MAX_PER_AD_LENGTH 252 +#define HCI_MAX_PER_AD_TOT_LEN 1650 #define HCI_OP_LE_SET_PER_ADV_DATA 0x203f struct hci_cp_le_set_per_adv_data { @@ -2795,6 +2806,10 @@ struct hci_ev_le_per_adv_report { __u8 data[]; } __packed; +#define LE_PA_DATA_COMPLETE 0x00 +#define LE_PA_DATA_MORE_TO_COME 0x01 +#define LE_PA_DATA_TRUNCATED 0x02 + #define HCI_EV_LE_EXT_ADV_SET_TERM 0x12 struct hci_evt_le_ext_adv_set_term { __u8 status; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8f8dd9173714..56fb42df44a3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> @@ -552,6 +552,7 @@ struct hci_dev { __u32 req_status; __u32 req_result; struct sk_buff *req_skb; + struct sk_buff *req_rsp; void *smp_data; void *smp_bredr_data; @@ -734,8 +735,9 @@ struct hci_conn { __u16 le_supv_timeout; __u8 le_adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 le_adv_data_len; - __u8 le_per_adv_data[HCI_MAX_PER_AD_LENGTH]; - __u8 le_per_adv_data_len; + __u8 le_per_adv_data[HCI_MAX_PER_AD_TOT_LEN]; + __u16 le_per_adv_data_len; + __u16 le_per_adv_data_offset; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -1083,6 +1085,24 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) return c->acl_num + c->amp_num + c->sco_num + c->le_num + c->iso_num; } +static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c == conn) { + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); + + return false; +} + static inline __u8 hci_conn_lookup_type(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; @@ -1480,7 +1500,6 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); -void hci_conn_check_pending(struct hci_dev *hdev); struct hci_chan *hci_chan_create(struct hci_conn *conn); void hci_chan_del(struct hci_chan *chan); @@ -1494,11 +1513,13 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role); +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason); + enum conn_reasons conn_reason, u16 timeout); struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec); + __u16 setting, struct bt_codec *codec, + u16 timeout); struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos); struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, @@ -1509,8 +1530,8 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, __u8 data_len, __u8 *data); -int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, - __u8 sid, struct bt_iso_qos *qos); +struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, __u8 sid, struct bt_iso_qos *qos); int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 6efbc2152146..6a9d063e9f47 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -42,12 +42,24 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, void hci_cmd_sync_init(struct hci_dev *hdev); void hci_cmd_sync_clear(struct hci_dev *hdev); void hci_cmd_sync_cancel(struct hci_dev *hdev, int err); -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err); +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err); int hci_cmd_sync_submit(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, void *data, hci_cmd_sync_work_destroy_t destroy); +int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +struct hci_cmd_sync_work_entry * +hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry); +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, void *data, + hci_cmd_sync_work_destroy_t destroy); int hci_update_eir_sync(struct hci_dev *hdev); int hci_update_class_sync(struct hci_dev *hdev); @@ -127,8 +139,6 @@ struct hci_conn; int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason); -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); - int hci_le_create_cis_sync(struct hci_dev *hdev); int hci_le_remove_cig_sync(struct hci_dev *hdev, u8 handle); @@ -138,3 +148,9 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason); int hci_le_big_terminate_sync(struct hci_dev *hdev, u8 handle); int hci_le_pa_terminate_sync(struct hci_dev *hdev, u16 handle); + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn); + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index cf393e72d6ed..a4278aa618ab 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -59,8 +59,6 @@ #define L2CAP_WAIT_ACK_POLL_PERIOD msecs_to_jiffies(200) #define L2CAP_WAIT_ACK_TIMEOUT msecs_to_jiffies(10000) -#define L2CAP_A2MP_DEFAULT_MTU 670 - /* L2CAP socket address */ struct sockaddr_l2 { sa_family_t l2_family; @@ -109,12 +107,6 @@ struct l2cap_conninfo { #define L2CAP_ECHO_RSP 0x09 #define L2CAP_INFO_REQ 0x0a #define L2CAP_INFO_RSP 0x0b -#define L2CAP_CREATE_CHAN_REQ 0x0c -#define L2CAP_CREATE_CHAN_RSP 0x0d -#define L2CAP_MOVE_CHAN_REQ 0x0e -#define L2CAP_MOVE_CHAN_RSP 0x0f -#define L2CAP_MOVE_CHAN_CFM 0x10 -#define L2CAP_MOVE_CHAN_CFM_RSP 0x11 #define L2CAP_CONN_PARAM_UPDATE_REQ 0x12 #define L2CAP_CONN_PARAM_UPDATE_RSP 0x13 #define L2CAP_LE_CONN_REQ 0x14 @@ -144,7 +136,6 @@ struct l2cap_conninfo { /* L2CAP fixed channels */ #define L2CAP_FC_SIG_BREDR 0x02 #define L2CAP_FC_CONNLESS 0x04 -#define L2CAP_FC_A2MP 0x08 #define L2CAP_FC_ATT 0x10 #define L2CAP_FC_SIG_LE 0x20 #define L2CAP_FC_SMP_LE 0x40 @@ -267,7 +258,6 @@ struct l2cap_conn_rsp { /* channel identifier */ #define L2CAP_CID_SIGNALING 0x0001 #define L2CAP_CID_CONN_LESS 0x0002 -#define L2CAP_CID_A2MP 0x0003 #define L2CAP_CID_ATT 0x0004 #define L2CAP_CID_LE_SIGNALING 0x0005 #define L2CAP_CID_SMP 0x0006 @@ -282,7 +272,6 @@ struct l2cap_conn_rsp { #define L2CAP_CR_BAD_PSM 0x0002 #define L2CAP_CR_SEC_BLOCK 0x0003 #define L2CAP_CR_NO_MEM 0x0004 -#define L2CAP_CR_BAD_AMP 0x0005 #define L2CAP_CR_INVALID_SCID 0x0006 #define L2CAP_CR_SCID_IN_USE 0x0007 @@ -404,29 +393,6 @@ struct l2cap_info_rsp { __u8 data[]; } __packed; -struct l2cap_create_chan_req { - __le16 psm; - __le16 scid; - __u8 amp_id; -} __packed; - -struct l2cap_create_chan_rsp { - __le16 dcid; - __le16 scid; - __le16 result; - __le16 status; -} __packed; - -struct l2cap_move_chan_req { - __le16 icid; - __u8 dest_amp_id; -} __packed; - -struct l2cap_move_chan_rsp { - __le16 icid; - __le16 result; -} __packed; - #define L2CAP_MR_SUCCESS 0x0000 #define L2CAP_MR_PEND 0x0001 #define L2CAP_MR_BAD_ID 0x0002 @@ -539,8 +505,6 @@ struct l2cap_seq_list { struct l2cap_chan { struct l2cap_conn *conn; - struct hci_conn *hs_hcon; - struct hci_chan *hs_hchan; struct kref kref; atomic_t nesting; @@ -591,12 +555,6 @@ struct l2cap_chan { unsigned long conn_state; unsigned long flags; - __u8 remote_amp_id; - __u8 local_amp_id; - __u8 move_id; - __u8 move_state; - __u8 move_role; - __u16 next_tx_seq; __u16 expected_ack_seq; __u16 expected_tx_seq; @@ -981,7 +939,7 @@ int l2cap_add_scid(struct l2cap_chan *chan, __u16 scid); struct l2cap_chan *l2cap_chan_create(void); void l2cap_chan_close(struct l2cap_chan *chan, int reason); int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type); + bdaddr_t *dst, u8 dst_type, u16 timeout); int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu); int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len); void l2cap_chan_busy(struct l2cap_chan *chan, int busy); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f9eada2a26ec..2e2be4fd2bb6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6871,13 +6871,45 @@ cfg80211_find_vendor_ie(unsigned int oui, int oui_type, } /** + * enum cfg80211_rnr_iter_ret - reduced neighbor report iteration state + * @RNR_ITER_CONTINUE: continue iterating with the next entry + * @RNR_ITER_BREAK: break iteration and return success + * @RNR_ITER_ERROR: break iteration and return error + */ +enum cfg80211_rnr_iter_ret { + RNR_ITER_CONTINUE, + RNR_ITER_BREAK, + RNR_ITER_ERROR, +}; + +/** + * cfg80211_iter_rnr - iterate reduced neighbor report entries + * @elems: the frame elements to iterate RNR elements and then + * their entries in + * @elems_len: length of the elements + * @iter: iteration function, see also &enum cfg80211_rnr_iter_ret + * for the return value + * @iter_data: additional data passed to the iteration function + * Return: %true on success (after successfully iterating all entries + * or if the iteration function returned %RNR_ITER_BREAK), + * %false on error (iteration function returned %RNR_ITER_ERROR + * or elements were malformed.) + */ +bool cfg80211_iter_rnr(const u8 *elems, size_t elems_len, + enum cfg80211_rnr_iter_ret + (*iter)(void *data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len), + void *iter_data); + +/** * cfg80211_defragment_element - Defrag the given element data into a buffer * * @elem: the element to defragment * @ies: elements where @elem is contained * @ieslen: length of @ies - * @data: buffer to store element data - * @data_len: length of @data + * @data: buffer to store element data, or %NULL to just determine size + * @data_len: length of @data, or 0 * @frag_id: the element ID of fragments * * Return: length of @data, or -EINVAL on error diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index cd95711b12b8..76d2cd2e2b30 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -401,6 +401,7 @@ struct ieee802154_llsec_key { struct ieee802154_llsec_key_entry { struct list_head list; + struct rcu_head rcu; struct ieee802154_llsec_key_id id; struct ieee802154_llsec_key *key; diff --git a/include/net/eee.h b/include/net/eee.h new file mode 100644 index 000000000000..84837aba3cd9 --- /dev/null +++ b/include/net/eee.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _EEE_H +#define _EEE_H + +#include <linux/types.h> + +struct eee_config { + u32 tx_lpi_timer; + bool tx_lpi_enabled; + bool eee_enabled; +}; + +static inline bool eeecfg_mac_can_tx_lpi(const struct eee_config *eeecfg) +{ + /* eee_enabled is the master on/off */ + if (!eeecfg->eee_enabled || !eeecfg->tx_lpi_enabled) + return false; + + return true; +} + +static inline void eeecfg_to_eee(struct ethtool_keee *eee, + const struct eee_config *eeecfg) +{ + eee->tx_lpi_timer = eeecfg->tx_lpi_timer; + eee->tx_lpi_enabled = eeecfg->tx_lpi_enabled; + eee->eee_enabled = eeecfg->eee_enabled; +} + +static inline void eee_to_eeecfg(struct eee_config *eeecfg, + const struct ethtool_keee *eee) +{ + eeecfg->tx_lpi_timer = eee->tx_lpi_timer; + eeecfg->tx_lpi_enabled = eee->tx_lpi_enabled; + eeecfg->eee_enabled = eee->eee_enabled; +} + +#endif diff --git a/include/net/gro.h b/include/net/gro.h index b435f0ddbf64..50f1e403dbbb 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -#ifndef _NET_IPV6_GRO_H -#define _NET_IPV6_GRO_H +#ifndef _NET_GRO_H +#define _NET_GRO_H #include <linux/indirect_call_wrapper.h> #include <linux/ip.h> @@ -9,6 +9,7 @@ #include <net/ip6_checksum.h> #include <linux/skbuff.h> #include <net/udp.h> +#include <net/hotdata.h> struct napi_gro_cb { union { @@ -139,21 +140,16 @@ static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) NAPI_GRO_CB(skb)->data_offset += len; } -static inline void *skb_gro_header_fast(struct sk_buff *skb, +static inline void *skb_gro_header_fast(const struct sk_buff *skb, unsigned int offset) { return NAPI_GRO_CB(skb)->frag0 + offset; } -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) +static inline bool skb_gro_may_pull(const struct sk_buff *skb, + unsigned int hlen) { - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} - -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + return likely(hlen <= NAPI_GRO_CB(skb)->frag0_len); } static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, @@ -162,28 +158,30 @@ static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, if (!pskb_may_pull(skb, hlen)) return NULL; - skb_gro_frag0_invalidate(skb); return skb->data + offset; } -static inline void *skb_gro_header(struct sk_buff *skb, - unsigned int hlen, unsigned int offset) +static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen, + unsigned int offset) { void *ptr; ptr = skb_gro_header_fast(skb, offset); - if (skb_gro_header_hard(skb, hlen)) + if (!skb_gro_may_pull(skb, hlen)) ptr = skb_gro_header_slow(skb, hlen, offset); return ptr; } -static inline void *skb_gro_network_header(struct sk_buff *skb) +static inline void *skb_gro_network_header(const struct sk_buff *skb) { - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); + if (skb_gro_may_pull(skb, skb_gro_offset(skb))) + return skb_gro_header_fast(skb, skb_network_offset(skb)); + + return skb_network_header(skb); } -static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) +static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb, + int proto) { const struct iphdr *iph = skb_gro_network_header(skb); @@ -421,7 +419,8 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) return uh; } -static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) +static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb, + int proto) { const struct ipv6hdr *iph = skb_gro_network_header(skb); @@ -448,7 +447,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, { list_add_tail(&skb->list, &napi->rx_list); napi->rx_count += segs; - if (napi->rx_count >= READ_ONCE(gro_normal_batch)) + if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) gro_normal_list(napi); } @@ -495,6 +494,7 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * #endif } -extern struct list_head offload_base; +struct packet_offload *gro_find_receive_by_type(__be16 type); +struct packet_offload *gro_find_complete_by_type(__be16 type); -#endif /* _NET_IPV6_GRO_H */ +#endif /* _NET_GRO_H */ diff --git a/include/net/hotdata.h b/include/net/hotdata.h new file mode 100644 index 000000000000..003667a1efd6 --- /dev/null +++ b/include/net/hotdata.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_HOTDATA_H +#define _NET_HOTDATA_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <net/protocol.h> + +/* Read mostly data used in network fast paths. */ +struct net_hotdata { +#if IS_ENABLED(CONFIG_INET) + struct packet_offload ip_packet_offload; + struct net_offload tcpv4_offload; + struct net_protocol tcp_protocol; + struct net_offload udpv4_offload; + struct net_protocol udp_protocol; + struct packet_offload ipv6_packet_offload; + struct net_offload tcpv6_offload; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_protocol tcpv6_protocol; + struct inet6_protocol udpv6_protocol; +#endif + struct net_offload udpv6_offload; +#endif + struct list_head offload_base; + struct list_head ptype_all; + struct kmem_cache *skbuff_cache; + struct kmem_cache *skbuff_fclone_cache; + struct kmem_cache *skb_small_head_cache; +#ifdef CONFIG_RPS + struct rps_sock_flow_table __rcu *rps_sock_flow_table; + u32 rps_cpu_mask; +#endif + int gro_normal_batch; + int netdev_budget; + int netdev_budget_usecs; + int tstamp_prequeue; + int max_backlog; + int dev_tx_weight; + int dev_rx_weight; +}; + +#define inet_ehash_secret net_hotdata.tcp_protocol.secret +#define udp_ehash_secret net_hotdata.udp_protocol.secret +#define inet6_ehash_secret net_hotdata.tcpv6_protocol.secret +#define tcp_ipv6_hash_secret net_hotdata.tcpv6_offload.secret +#define udp6_ehash_secret net_hotdata.udpv6_protocol.secret +#define udp_ipv6_hash_secret net_hotdata.udpv6_offload.secret + +extern struct net_hotdata net_hotdata; + +#endif /* _NET_HOTDATA_H */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index d94c242eb3ed..f9ddd47dc4f8 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -274,6 +274,7 @@ enum { INET_FLAGS_REPFLOW = 27, INET_FLAGS_RTALERT_ISOLATE = 28, INET_FLAGS_SNDFLOW = 29, + INET_FLAGS_RTALERT = 30, }; /* cmsg flags for inet */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 56c6ecb2c10a..353488ab94a2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1763,8 +1763,9 @@ struct ieee80211_conf { * @chandef: the new channel to switch to * @count: the number of TBTT's until the channel switch event * @delay: maximum delay between the time the AP transmitted the last beacon in - * current channel and the expected time of the first beacon in the new - * channel, expressed in TU. + * current channel and the expected time of the first beacon in the new + * channel, expressed in TU. + * @link_id: the link ID of the link doing the channel switch, 0 for non-MLO */ struct ieee80211_channel_switch { u64 timestamp; @@ -1772,6 +1773,7 @@ struct ieee80211_channel_switch { bool block_tx; struct cfg80211_chan_def chandef; u8 count; + u8 link_id; u32 delay; }; @@ -2011,6 +2013,21 @@ static inline bool ieee80211_vif_is_mld(const struct ieee80211_vif *vif) return vif->valid_links != 0; } +/** + * ieee80211_vif_link_active - check if a given link is active + * @vif: the vif + * @link_id: the link ID to check + * Return: %true if the vif is an MLD and the link is active, or if + * the vif is not an MLD and the link ID is 0; %false otherwise. + */ +static inline bool ieee80211_vif_link_active(const struct ieee80211_vif *vif, + unsigned int link_id) +{ + if (!ieee80211_vif_is_mld(vif)) + return link_id == 0; + return vif->active_links & BIT(link_id); +} + #define for_each_vif_active_link(vif, link, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((vif)->link_conf); link_id++) \ if ((!(vif)->active_links || \ @@ -2761,6 +2778,11 @@ struct ieee80211_txq { * @IEEE80211_HW_DISALLOW_PUNCTURING: HW requires disabling puncturing in EHT * and connecting with a lower bandwidth instead * + * @IEEE80211_HW_HANDLES_QUIET_CSA: HW/driver handles quieting for CSA, so + * no need to stop queues. This really should be set by a driver that + * implements MLO, so operation can continue on other links when one + * link is switching. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2819,6 +2841,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_DETECTS_COLOR_COLLISION, IEEE80211_HW_MLO_MCAST_MULTI_LINK_TX, IEEE80211_HW_DISALLOW_PUNCTURING, + IEEE80211_HW_HANDLES_QUIET_CSA, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -4251,7 +4274,7 @@ struct ieee80211_prep_tx_info { * after a channel switch procedure is completed, allowing the * driver to go back to a normal configuration. * @abort_channel_switch: This is an optional callback that is called - * when channel switch procedure was completed, allowing the + * when channel switch procedure was aborted, allowing the * driver to go back to a normal configuration. * @channel_switch_rx_beacon: This is an optional callback that is called * when channel switch procedure is in progress and additional beacon with @@ -4647,7 +4670,8 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf); void (*abort_channel_switch)(struct ieee80211_hw *hw, - struct ieee80211_vif *vif); + struct ieee80211_vif *vif, + struct ieee80211_bss_conf *link_conf); void (*channel_switch_rx_beacon)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_channel_switch *ch_switch); @@ -5912,6 +5936,7 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); * ieee80211_gtk_rekey_add - add a GTK key from rekeying during WoWLAN * @vif: the virtual interface to add the key on * @keyconf: new key data + * @link_id: the link id of the key or -1 for non-MLO * * When GTK rekeying was done while the system was suspended, (a) new * key(s) will be available. These will be needed by mac80211 for proper @@ -5939,7 +5964,8 @@ void ieee80211_remove_key(struct ieee80211_key_conf *keyconf); */ struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, - struct ieee80211_key_conf *keyconf); + struct ieee80211_key_conf *keyconf, + int link_id); /** * ieee80211_gtk_rekey_notify - notify userspace supplicant of rekeying diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 8b8ed4e13d74..1ec408585373 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,62 @@ #include <linux/netdevice.h> +/* See the netdev.yaml spec for definition of each statistic */ +struct netdev_queue_stats_rx { + u64 bytes; + u64 packets; + u64 alloc_fail; +}; + +struct netdev_queue_stats_tx { + u64 bytes; + u64 packets; +}; + +/** + * struct netdev_stat_ops - netdev ops for fine grained stats + * @get_queue_stats_rx: get stats for a given Rx queue + * @get_queue_stats_tx: get stats for a given Tx queue + * @get_base_stats: get base stats (not belonging to any live instance) + * + * Query stats for a given object. The values of the statistics are undefined + * on entry (specifically they are *not* zero-initialized). Drivers should + * assign values only to the statistics they collect. Statistics which are not + * collected must be left undefined. + * + * Queue objects are not necessarily persistent, and only currently active + * queues are queried by the per-queue callbacks. This means that per-queue + * statistics will not generally add up to the total number of events for + * the device. The @get_base_stats callback allows filling in the delta + * between events for currently live queues and overall device history. + * When the statistics for the entire device are queried, first @get_base_stats + * is issued to collect the delta, and then a series of per-queue callbacks. + * Only statistics which are set in @get_base_stats will be reported + * at the device level, meaning that unlike in queue callbacks, setting + * a statistic to zero in @get_base_stats is a legitimate thing to do. + * This is because @get_base_stats has a second function of designating which + * statistics are in fact correct for the entire device (e.g. when history + * for some of the events is not maintained, and reliable "total" cannot + * be provided). + * + * Device drivers can assume that when collecting total device stats, + * the @get_base_stats and subsequent per-queue calls are performed + * "atomically" (without releasing the rtnl_lock). + * + * Device drivers are encouraged to reset the per-queue statistics when + * number of queues change. This is because the primary use case for + * per-queue statistics is currently to detect traffic imbalance. + */ +struct netdev_stat_ops { + void (*get_queue_stats_rx)(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *stats); + void (*get_queue_stats_tx)(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *stats); + void (*get_base_stats)(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 77e99cba60ad..7ca315ad500e 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -47,6 +47,8 @@ struct nh_config { bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; + bool nh_hw_stats; + struct nlattr *nh_encap; u16 nh_encap_type; @@ -95,8 +97,14 @@ struct nh_res_table { struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; +struct nh_grp_entry_stats { + u64_stats_t packets; + struct u64_stats_sync syncp; +}; + struct nh_grp_entry { struct nexthop *nh; + struct nh_grp_entry_stats __percpu *stats; u8 weight; union { @@ -114,6 +122,7 @@ struct nh_grp_entry { struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ + u64 packets_hw; }; struct nh_group { @@ -124,6 +133,7 @@ struct nh_group { bool resilient; bool fdb_nh; bool has_v4; + bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); @@ -157,6 +167,7 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { @@ -164,6 +175,7 @@ enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, + NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { @@ -173,6 +185,7 @@ struct nh_notifier_single_info { __be32 ipv4; struct in6_addr ipv6; }; + u32 id; u8 is_reject:1, is_fdb:1, has_encap:1; @@ -180,13 +193,13 @@ struct nh_notifier_single_info { struct nh_notifier_grp_entry_info { u8 weight; - u32 id; struct nh_notifier_single_info nh; }; struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; + bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; @@ -200,9 +213,21 @@ struct nh_notifier_res_bucket_info { struct nh_notifier_res_table_info { u16 num_nh_buckets; + bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; +struct nh_notifier_grp_hw_stats_entry_info { + u32 id; + u64 packets; +}; + +struct nh_notifier_grp_hw_stats_info { + u16 num_nh; + bool hw_stats_used; + struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); +}; + struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; @@ -213,6 +238,7 @@ struct nh_notifier_info { struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; + struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; @@ -225,6 +251,9 @@ void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 5dee575fbe86..3d07abacf08b 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -196,7 +196,7 @@ struct nfc_dev { }; #define to_nfc_dev(_dev) container_of(_dev, struct nfc_dev, dev) -extern struct class nfc_class; +extern const struct class nfc_class; struct nfc_dev *nfc_allocate_device(const struct nfc_ops *ops, u32 supported_protocols, diff --git a/include/net/protocol.h b/include/net/protocol.h index 6aef8cb11cc8..b2499f88f8f8 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -46,6 +46,7 @@ struct net_protocol { * socket lookup? */ icmp_strict_tag_validation:1; + u32 secret; }; #if IS_ENABLED(CONFIG_IPV6) @@ -59,6 +60,7 @@ struct inet6_protocol { __be32 info); unsigned int flags; /* INET6_PROTO_xxx */ + u32 secret; }; #define INET6_PROTO_NOPOLICY 0x1 @@ -68,6 +70,7 @@ struct inet6_protocol { struct net_offload { struct offload_callbacks callbacks; unsigned int flags; /* Flags used by IPv6 for now */ + u32 secret; }; /* This should be set for any extension header which is compatible with GSO. */ #define INET6_PROTO_GSO_EXTHDR 0x1 diff --git a/include/net/rps.h b/include/net/rps.h new file mode 100644 index 000000000000..7660243e905b --- /dev/null +++ b/include/net/rps.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_RPS_H +#define _NET_RPS_H + +#include <linux/types.h> +#include <linux/static_key.h> +#include <net/sock.h> +#include <net/hotdata.h> + +#ifdef CONFIG_RPS + +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; + +/* + * This structure holds an RPS map which can be of variable length. The + * map is an array of CPUs. + */ +struct rps_map { + unsigned int len; + struct rcu_head rcu; + u16 cpus[]; +}; +#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) + +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. + */ +struct rps_dev_flow { + u16 cpu; + u16 filter; + unsigned int last_qtail; +}; +#define RPS_NO_FILTER 0xffff + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct rps_dev_flow flows[]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + ((_num) * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high-order bits + * of flow hash, lower part is CPU number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. + */ +struct rps_sock_flow_table { + u32 mask; + + u32 ents[] ____cacheline_aligned_in_smp; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + unsigned int index = hash & table->mask; + u32 val = hash & ~net_hotdata.rps_cpu_mask; + + /* We only give a hint, preemption can change CPU under us */ + val |= raw_smp_processor_id(); + + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); +} + +#endif /* CONFIG_RPS */ + +static inline void sock_rps_record_flow_hash(__u32 hash) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + if (!hash) + return; + rcu_read_lock(); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); + if (sock_flow_table) + rps_record_sock_flow(sock_flow_table, hash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + if (static_branch_unlikely(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } + } +#endif +} + +#endif /* _NET_RPS_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 934fdb977551..cefe0c4bdae3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { -#ifdef CONFIG_BQL - /* Non-BQL migrated drivers will return 0, too. */ - return dql_avail(&txq->dql); -#else - return 0; -#endif + return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { diff --git a/include/net/sock.h b/include/net/sock.h index 09a0cde8bf52..b5e00702acc1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1117,41 +1117,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } -static inline void sock_rps_record_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - -static inline void sock_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - if (static_branch_unlikely(&rfs_needed)) { - /* Reading sk->sk_rxhash might incur an expensive cache line - * miss. - * - * TCP_ESTABLISHED does cover almost all states where RFS - * might be useful, and is cheaper [1] than testing : - * IPv4: inet_sk(sk)->inet_daddr - * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) - * OR an additional socket flag - * [1] : sk_state and sk_prot are in the same cache line. - */ - if (sk->sk_state == TCP_ESTABLISHED) { - /* This READ_ONCE() is paired with the WRITE_ONCE() - * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). - */ - sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); - } - } -#endif -} static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index ecc02e955279..1f4c39922d82 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -30,6 +30,8 @@ static inline void snd_soc_card_mutex_unlock(struct snd_soc_card *card) struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, const char *name); +struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card, + const char *name); int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type, struct snd_soc_jack *jack); int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id, diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 6678cf8b235b..dc03cf8e0369 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -36,6 +36,39 @@ TRACE_EVENT(napi_poll, __entry->work, __entry->budget) ); +TRACE_EVENT(dql_stall_detected, + + TP_PROTO(unsigned short thrs, unsigned int len, + unsigned long last_reap, unsigned long hist_head, + unsigned long now, unsigned long *hist), + + TP_ARGS(thrs, len, last_reap, hist_head, now, hist), + + TP_STRUCT__entry( + __field( unsigned short, thrs) + __field( unsigned int, len) + __field( unsigned long, last_reap) + __field( unsigned long, hist_head) + __field( unsigned long, now) + __array( unsigned long, hist, 4) + ), + + TP_fast_assign( + __entry->thrs = thrs; + __entry->len = len; + __entry->last_reap = last_reap; + __entry->hist_head = hist_head * BITS_PER_LONG; + __entry->now = now; + memcpy(__entry->hist, hist, sizeof(entry->hist)); + ), + + TP_printk("thrs %u len %u last_reap %lu hist_head %lu now %lu hist %016lx %016lx %016lx %016lx", + __entry->thrs, __entry->len, + __entry->last_reap, __entry->hist_head, __entry->now, + __entry->hist[0], __entry->hist[1], + __entry->hist[2], __entry->hist[3]) +); + #undef NO_DEV #endif /* _TRACE_NAPI_H */ diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index a3995925cb05..1f4258308b96 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; @@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 87b8de9b6c1c..a1b126a6b0d7 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -83,7 +83,7 @@ EM(rxrpc_badmsg_bad_abort, "bad-abort") \ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \ EM(rxrpc_badmsg_short_ack, "short-ack") \ - EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \ + EM(rxrpc_badmsg_short_ack_trailer, "short-ack-trailer") \ EM(rxrpc_badmsg_short_hdr, "short-hdr") \ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \ EM(rxrpc_badmsg_zero_call, "zero-call") \ @@ -119,6 +119,7 @@ EM(rxrpc_call_poke_complete, "Compl") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ + EM(rxrpc_call_poke_set_timeout, "Set-timo") \ EM(rxrpc_call_poke_start, "Start") \ EM(rxrpc_call_poke_timer, "Timer") \ E_(rxrpc_call_poke_timer_now, "Timer-now") @@ -340,35 +341,26 @@ E_(rxrpc_rtt_rx_requested_ack, "RACK") #define rxrpc_timer_traces \ - EM(rxrpc_timer_begin, "Begin ") \ - EM(rxrpc_timer_exp_ack, "ExpAck") \ - EM(rxrpc_timer_exp_hard, "ExpHrd") \ - EM(rxrpc_timer_exp_idle, "ExpIdl") \ - EM(rxrpc_timer_exp_keepalive, "ExpKA ") \ - EM(rxrpc_timer_exp_lost_ack, "ExpLoA") \ - EM(rxrpc_timer_exp_normal, "ExpNml") \ - EM(rxrpc_timer_exp_ping, "ExpPng") \ - EM(rxrpc_timer_exp_resend, "ExpRsn") \ - EM(rxrpc_timer_init_for_reply, "IniRpl") \ - EM(rxrpc_timer_init_for_send_reply, "SndRpl") \ - EM(rxrpc_timer_restart, "Restrt") \ - EM(rxrpc_timer_set_for_ack, "SetAck") \ - EM(rxrpc_timer_set_for_hard, "SetHrd") \ - EM(rxrpc_timer_set_for_idle, "SetIdl") \ - EM(rxrpc_timer_set_for_keepalive, "KeepAl") \ - EM(rxrpc_timer_set_for_lost_ack, "SetLoA") \ - EM(rxrpc_timer_set_for_normal, "SetNml") \ - EM(rxrpc_timer_set_for_ping, "SetPng") \ - EM(rxrpc_timer_set_for_resend, "SetRTx") \ - E_(rxrpc_timer_set_for_send, "SetSnd") + EM(rxrpc_timer_trace_delayed_ack, "DelayAck ") \ + EM(rxrpc_timer_trace_expect_rx, "ExpectRx ") \ + EM(rxrpc_timer_trace_hard, "HardLimit") \ + EM(rxrpc_timer_trace_idle, "IdleLimit") \ + EM(rxrpc_timer_trace_keepalive, "KeepAlive") \ + EM(rxrpc_timer_trace_lost_ack, "LostAck ") \ + EM(rxrpc_timer_trace_ping, "DelayPing") \ + EM(rxrpc_timer_trace_resend, "Resend ") \ + EM(rxrpc_timer_trace_resend_reset, "ResendRst") \ + E_(rxrpc_timer_trace_resend_tx, "ResendTx ") #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ + EM(rxrpc_propose_ack_delayed_ack, "DlydAck") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \ + EM(rxrpc_propose_ack_ping_for_0_retrans, "0-Retrn") \ EM(rxrpc_propose_ack_ping_for_old_rtt, "OldRtt ") \ EM(rxrpc_propose_ack_ping_for_params, "Params ") \ EM(rxrpc_propose_ack_ping_for_rtt, "Rtt ") \ @@ -1084,9 +1076,9 @@ TRACE_EVENT(rxrpc_tx_packet, TRACE_EVENT(rxrpc_tx_data, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, - rxrpc_serial_t serial, u8 flags, bool retrans, bool lose), + rxrpc_serial_t serial, unsigned int flags, bool lose), - TP_ARGS(call, seq, serial, flags, retrans, lose), + TP_ARGS(call, seq, serial, flags, lose), TP_STRUCT__entry( __field(unsigned int, call) @@ -1094,8 +1086,7 @@ TRACE_EVENT(rxrpc_tx_data, __field(rxrpc_serial_t, serial) __field(u32, cid) __field(u32, call_id) - __field(u8, flags) - __field(bool, retrans) + __field(u16, flags) __field(bool, lose) ), @@ -1106,7 +1097,6 @@ TRACE_EVENT(rxrpc_tx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->retrans = retrans; __entry->lose = lose; ), @@ -1116,8 +1106,8 @@ TRACE_EVENT(rxrpc_tx_data, __entry->call_id, __entry->serial, __entry->seq, - __entry->flags, - __entry->retrans ? " *RETRANS*" : "", + __entry->flags & RXRPC_TXBUF_WIRE_FLAGS, + __entry->flags & RXRPC_TXBUF_RESENT ? " *RETRANS*" : "", __entry->lose ? " *LOSE*" : "") ); @@ -1314,90 +1304,112 @@ TRACE_EVENT(rxrpc_rtt_rx, __entry->rto) ); -TRACE_EVENT(rxrpc_timer, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why, - unsigned long now), +TRACE_EVENT(rxrpc_timer_set, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, + enum rxrpc_timer_trace why), - TP_ARGS(call, why, now), + TP_ARGS(call, delay, why), TP_STRUCT__entry( __field(unsigned int, call) __field(enum rxrpc_timer_trace, why) - __field(long, now) - __field(long, ack_at) - __field(long, ack_lost_at) - __field(long, resend_at) - __field(long, ping_at) - __field(long, expect_rx_by) - __field(long, expect_req_by) - __field(long, expect_term_by) - __field(long, timer) + __field(ktime_t, delay) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->now = now; - __entry->ack_at = call->delay_ack_at; - __entry->ack_lost_at = call->ack_lost_at; - __entry->resend_at = call->resend_at; - __entry->expect_rx_by = call->expect_rx_by; - __entry->expect_req_by = call->expect_req_by; - __entry->expect_term_by = call->expect_term_by; - __entry->timer = call->timer.expires; + __entry->delay = delay; ), - TP_printk("c=%08x %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", + TP_printk("c=%08x %s to=%lld", __entry->call, __print_symbolic(__entry->why, rxrpc_timer_traces), - __entry->ack_at - __entry->now, - __entry->ack_lost_at - __entry->now, - __entry->resend_at - __entry->now, - __entry->expect_rx_by - __entry->now, - __entry->expect_req_by - __entry->now, - __entry->expect_term_by - __entry->now, - __entry->timer - __entry->now) + ktime_to_us(__entry->delay)) + ); + +TRACE_EVENT(rxrpc_timer_exp, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, + enum rxrpc_timer_trace why), + + TP_ARGS(call, delay, why), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(enum rxrpc_timer_trace, why) + __field(ktime_t, delay) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->delay = delay; + ), + + TP_printk("c=%08x %s to=%lld", + __entry->call, + __print_symbolic(__entry->why, rxrpc_timer_traces), + ktime_to_us(__entry->delay)) + ); + +TRACE_EVENT(rxrpc_timer_can, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why), + + TP_ARGS(call, why), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(enum rxrpc_timer_trace, why) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + ), + + TP_printk("c=%08x %s", + __entry->call, + __print_symbolic(__entry->why, rxrpc_timer_traces)) + ); + +TRACE_EVENT(rxrpc_timer_restart, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, unsigned long delayj), + + TP_ARGS(call, delay, delayj), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(unsigned long, delayj) + __field(ktime_t, delay) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->delayj = delayj; + __entry->delay = delay; + ), + + TP_printk("c=%08x to=%lld j=%ld", + __entry->call, + ktime_to_us(__entry->delay), + __entry->delayj) ); TRACE_EVENT(rxrpc_timer_expired, - TP_PROTO(struct rxrpc_call *call, unsigned long now), + TP_PROTO(struct rxrpc_call *call), - TP_ARGS(call, now), + TP_ARGS(call), TP_STRUCT__entry( __field(unsigned int, call) - __field(long, now) - __field(long, ack_at) - __field(long, ack_lost_at) - __field(long, resend_at) - __field(long, ping_at) - __field(long, expect_rx_by) - __field(long, expect_req_by) - __field(long, expect_term_by) - __field(long, timer) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->now = now; - __entry->ack_at = call->delay_ack_at; - __entry->ack_lost_at = call->ack_lost_at; - __entry->resend_at = call->resend_at; - __entry->expect_rx_by = call->expect_rx_by; - __entry->expect_req_by = call->expect_req_by; - __entry->expect_term_by = call->expect_term_by; - __entry->timer = call->timer.expires; ), - TP_printk("c=%08x EXPIRED a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", - __entry->call, - __entry->ack_at - __entry->now, - __entry->ack_lost_at - __entry->now, - __entry->resend_at - __entry->now, - __entry->expect_rx_by - __entry->now, - __entry->expect_req_by - __entry->now, - __entry->expect_term_by - __entry->now, - __entry->timer - __entry->now) + TP_printk("c=%08x EXPIRED", + __entry->call) ); TRACE_EVENT(rxrpc_rx_lose, @@ -1506,26 +1518,30 @@ TRACE_EVENT(rxrpc_drop_ack, ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, s64 expiry), + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, + rxrpc_serial_t serial, ktime_t expiry), - TP_ARGS(call, seq, expiry), + TP_ARGS(call, seq, serial, expiry), TP_STRUCT__entry( __field(unsigned int, call) __field(rxrpc_seq_t, seq) - __field(s64, expiry) + __field(rxrpc_serial_t, serial) + __field(ktime_t, expiry) ), TP_fast_assign( __entry->call = call->debug_id; __entry->seq = seq; + __entry->serial = serial; __entry->expiry = expiry; ), - TP_printk("c=%08x q=%x xp=%lld", + TP_printk("c=%08x q=%x r=%x xp=%lld", __entry->call, __entry->seq, - __entry->expiry) + __entry->serial, + ktime_to_us(__entry->expiry)) ); TRACE_EVENT(rxrpc_congest, diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 7b1ddffa3dfc..699dafd204ea 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -88,7 +88,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), - TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", + TP_printk("skbaddr=%p skaddr=%p family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", + __entry->skbaddr, __entry->skaddr, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, @@ -258,6 +259,8 @@ TRACE_EVENT(tcp_probe, __field(__u32, srtt) __field(__u32, rcv_wnd) __field(__u64, sock_cookie) + __field(const void *, skbaddr) + __field(const void *, skaddr) ), TP_fast_assign( @@ -285,14 +288,18 @@ TRACE_EVENT(tcp_probe, __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; __entry->sock_cookie = sock_gen_cookie(sk); + + __entry->skbaddr = skb; + __entry->skaddr = sk; ), - TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", + TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx skbaddr=%p skaddr=%p", show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, - __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie) + __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie, + __entry->skbaddr, __entry->skaddr) ); #define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \ @@ -361,7 +368,8 @@ DECLARE_EVENT_CLASS(tcp_event_skb, TP_STORE_ADDR_PORTS_SKB(__entry, skb); ), - TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr) + TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", + __entry->skbaddr, __entry->saddr, __entry->daddr) ); DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 6d11ee9e571a..bb0c8a994116 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -831,11 +831,6 @@ struct drm_xe_vm_destroy { * - %DRM_XE_VM_BIND_OP_PREFETCH * * and the @flags can be: - * - %DRM_XE_VM_BIND_FLAG_READONLY - * - %DRM_XE_VM_BIND_FLAG_ASYNC - * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the - * MAP operation immediately rather than deferring the MAP to the page - * fault handler. * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page * tables are setup with a special bit which indicates writes are * dropped and all reads return zero. In the future, the NULL flags @@ -928,9 +923,8 @@ struct drm_xe_vm_bind_op { /** @op: Bind operation to perform */ __u32 op; -#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) -#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) #define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) +#define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) /** @flags: Bind flags */ __u32 flags; @@ -1045,19 +1039,6 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7 -/* Monitor 128KB contiguous region with 4K sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_128K 0 -/* Monitor 2MB contiguous region with 64KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_2M 1 -/* Monitor 16MB contiguous region with 512KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_16M 2 -/* Monitor 64MB contiguous region with 2M sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_64M 3 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 130cae0d3e20..2da0c7eb6710 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -614,7 +614,10 @@ enum devlink_attr { DEVLINK_ATTR_REGION_DIRECT, /* flag */ - /* add new attributes above here, update the policy in devlink.c */ + /* Add new attributes above here, update the spec in + * Documentation/netlink/specs/devlink.yaml and re-generate + * net/devlink/netlink_gen.c. + */ __DEVLINK_ATTR_MAX, DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1 diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 06ef6b78b7de..11fc18988bc2 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2023,6 +2023,53 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define IPV4_FLOW 0x10 /* hash only */ #define IPV6_FLOW 0x11 /* hash only */ #define ETHER_FLOW 0x12 /* spec only (ether_spec) */ + +/* Used for GTP-U IPv4 and IPv6. + * The format of GTP packets only includes + * elements such as TEID and GTP version. + * It is primarily intended for data communication of the UE. + */ +#define GTPU_V4_FLOW 0x13 /* hash only */ +#define GTPU_V6_FLOW 0x14 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * The format of these GTP packets does not include TEID. + * Primarily expected to be used for communication + * to create sessions for UE data communication, + * commonly referred to as CSR (Create Session Request). + */ +#define GTPC_V4_FLOW 0x15 /* hash only */ +#define GTPC_V6_FLOW 0x16 /* hash only */ + +/* Use for GTP-C IPv4 and v6. + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID. + * After session creation, it becomes this packet. + * This is mainly used for requests to realize UE handover. + */ +#define GTPC_TEID_V4_FLOW 0x17 /* hash only */ +#define GTPC_TEID_V6_FLOW 0x18 /* hash only */ + +/* Use for GTP-U and extended headers for the PSC (PDU Session Container). + * The format of these GTP packets includes TEID and QFI. + * In 5G communication using UPF (User Plane Function), + * data communication with this extended header is performed. + */ +#define GTPU_EH_V4_FLOW 0x19 /* hash only */ +#define GTPU_EH_V6_FLOW 0x1a /* hash only */ + +/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers. + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by + * UL/DL included in the PSC. + * There are differences in the data included based on Downlink/Uplink, + * and can be used to distinguish packets. + * The functions described so far are useful when you want to + * handle communication from the mobile network in UPF, PGW, etc. + */ +#define GTPU_UL_V4_FLOW 0x1b /* hash only */ +#define GTPU_UL_V6_FLOW 0x1c /* hash only */ +#define GTPU_DL_V4_FLOW 0x1d /* hash only */ +#define GTPU_DL_V6_FLOW 0x1e /* hash only */ + /* Flag to enable additional fields in struct ethtool_rx_flow_spec */ #define FLOW_EXT 0x80000000 #define FLOW_MAC_EXT 0x40000000 @@ -2037,6 +2084,7 @@ static inline int ethtool_validate_duplex(__u8 duplex) #define RXH_IP_DST (1 << 5) #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ +#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */ #define RXH_DISCARD (1 << 31) #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 93cb411adf72..bb65ee840cda 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -133,6 +137,21 @@ enum { }; enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -144,6 +163,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index d8ffa8c9ca78..dd8787f9cf39 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -30,6 +30,9 @@ enum { #define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) +#define NHA_OP_FLAG_DUMP_STATS BIT(0) +#define NHA_OP_FLAG_DUMP_HW_STATS BIT(1) + enum { NHA_UNSPEC, NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ @@ -60,6 +63,18 @@ enum { /* nested; nexthop bucket attributes */ NHA_RES_BUCKET, + /* u32; operation-specific flags */ + NHA_OP_FLAGS, + + /* nested; nexthop group stats */ + NHA_GROUP_STATS, + + /* u32; nexthop hardware stats enable */ + NHA_HW_STATS_ENABLE, + + /* u32; read-only; whether any driver collects HW stats */ + NHA_HW_STATS_USED, + __NHA_MAX, }; @@ -101,4 +116,34 @@ enum { #define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1) +enum { + NHA_GROUP_STATS_UNSPEC, + + /* nested; nexthop group entry stats */ + NHA_GROUP_STATS_ENTRY, + + __NHA_GROUP_STATS_MAX, +}; + +#define NHA_GROUP_STATS_MAX (__NHA_GROUP_STATS_MAX - 1) + +enum { + NHA_GROUP_STATS_ENTRY_UNSPEC, + + /* u32; nexthop id of the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_ID, + + /* uint; number of packets forwarded via the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_PACKETS, + + /* uint; number of packets forwarded via the nexthop group entry in + * hardware + */ + NHA_GROUP_STATS_ENTRY_PACKETS_HW, + + __NHA_GROUP_STATS_ENTRY_MAX, +}; + +#define NHA_GROUP_STATS_ENTRY_MAX (__NHA_GROUP_STATS_ENTRY_MAX - 1) + #endif diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index d5b9cfbd9cea..628d46a0da92 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 5a568bbbeaeb..82243cb6c54d 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1358,7 +1358,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype) { - unsigned int offset = skb->data - skb_network_header(skb); + unsigned int offset = -skb_network_offset(skb); struct sock *save_sk; void *saved_data_end; struct cgroup *cgrp; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8a0bb80fe48a..9ee8da477465 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,6 +24,7 @@ #include <linux/filter.h> #include <linux/ptr_ring.h> #include <net/xdp.h> +#include <net/hotdata.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -178,7 +179,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; @@ -326,7 +327,8 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d501c90f8ab5..63749ad5ac6b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16827,6 +16827,9 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat { int i; + if (old->callback_depth > cur->callback_depth) + return false; + for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ba36c073304a..927bef3a598a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2562,7 +2562,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, update_partition_sd_lb(cs, old_prs); out_free: free_cpumasks(NULL, &tmp); - return 0; + return retval; } /** @@ -2598,9 +2598,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus)) return 0; - if (alloc_cpumasks(NULL, &tmp)) - return -ENOMEM; - if (*buf) compute_effective_exclusive_cpumask(trialcs, NULL); @@ -2615,6 +2612,9 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval) return retval; + if (alloc_cpumasks(NULL, &tmp)) + return -ENOMEM; + if (old_prs) { if (cpumask_empty(trialcs->effective_xcpus)) { invalidate = true; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 6cd2a4e3afb8..9ff018245840 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -189,9 +189,6 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) { int size; - if (num <= 0) - return -EINVAL; - if (!fp->exit_handler) { fp->rethook = NULL; return 0; @@ -199,15 +196,16 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) /* Initialize rethook if needed */ if (fp->nr_maxactive) - size = fp->nr_maxactive; + num = fp->nr_maxactive; else - size = num * num_possible_cpus() * 2; - if (size <= 0) + num *= num_possible_cpus() * 2; + if (num <= 0) return -EINVAL; + size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, - sizeof(struct fprobe_rethook_node), size); + fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); if (IS_ERR(fp->rethook)) return PTR_ERR(fp->rethook); diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index fde0aa244148..a1389db1c30a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -10,10 +10,77 @@ #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> +#include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) +static void dql_check_stall(struct dql *dql) +{ + unsigned short stall_thrs; + unsigned long now; + + stall_thrs = READ_ONCE(dql->stall_thrs); + if (!stall_thrs) + return; + + now = jiffies; + /* Check for a potential stall */ + if (time_after_eq(now, dql->last_reap + stall_thrs)) { + unsigned long hist_head, t, start, end; + + /* We are trying to detect a period of at least @stall_thrs + * jiffies without any Tx completions, but during first half + * of which some Tx was posted. + */ +dqs_again: + hist_head = READ_ONCE(dql->history_head); + /* pairs with smp_wmb() in dql_queued() */ + smp_rmb(); + + /* Get the previous entry in the ring buffer, which is the + * oldest sample. + */ + start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; + + /* Advance start to continue from the last reap time */ + if (time_before(start, dql->last_reap + 1)) + start = dql->last_reap + 1; + + /* Newest sample we should have already seen a completion for */ + end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); + + /* Shrink the search space to [start, (now - start_thrs/2)] if + * `end` is beyond the stall zone + */ + if (time_before(now, end + stall_thrs / 2)) + end = now - stall_thrs / 2; + + /* Search for the queued time in [t, end] */ + for (t = start; time_before_eq(t, end); t++) + if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), + dql->history)) + break; + + /* Variable t contains the time of the queue */ + if (!time_before_eq(t, end)) + goto no_stall; + + /* The ring buffer was modified in the meantime, retry */ + if (hist_head != READ_ONCE(dql->history_head)) + goto dqs_again; + + dql->stall_cnt++; + dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); + + trace_dql_stall_detected(dql->stall_thrs, now - t, + dql->last_reap, dql->history_head, + now, dql->history); + } +no_stall: + dql->last_reap = now; +} + /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { @@ -110,6 +177,8 @@ void dql_completed(struct dql *dql, unsigned int count) dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; + + dql_check_stall(dql); } EXPORT_SYMBOL(dql_completed); @@ -125,6 +194,10 @@ void dql_reset(struct dql *dql) dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; + + dql->last_reap = jiffies; + dql->history_head = jiffies / BITS_PER_LONG; + memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); @@ -133,6 +206,7 @@ void dql_init(struct dql *dql, unsigned int hold_time) dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; + dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e0aa6b440ca5..cf2eb2b2f983 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -166,7 +166,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, - .copy_mc = false, .nofault = false, .data_source = direction, .__iov = iov, @@ -245,26 +244,8 @@ EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ static __always_inline -size_t memcpy_from_iter_mc(void *iter_from, size_t progress, - size_t len, void *to, void *priv2) -{ - return copy_mc_to_kernel(to + progress, iter_from, len); -} - -static size_t __copy_from_iter_mc(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(i->count < bytes)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - return iterate_bvec(i, bytes, addr, NULL, memcpy_from_iter_mc); -} - -static __always_inline size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(iov_iter_is_copy_mc(i))) - return __copy_from_iter_mc(addr, bytes, i); return iterate_and_advance(i, bytes, addr, copy_from_user_iter, memcpy_from_iter); } @@ -633,7 +614,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, - .copy_mc = false, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, @@ -650,7 +630,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, - .copy_mc = false, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, @@ -679,7 +658,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, - .copy_mc = false, .data_source = direction, .xarray = xarray, .xarray_start = start, @@ -703,7 +681,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, - .copy_mc = false, .data_source = false, .count = count, .iov_offset = 0 diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 65f22c2578b0..6b2b33579f56 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -380,6 +380,47 @@ static void __init test_replace(void) expect_eq_bitmap(bmap, exp3_1_0, nbits); } +static const unsigned long sg_mask[] __initconst = { + BITMAP_FROM_U64(0x000000000000035aULL), +}; + +static const unsigned long sg_src[] __initconst = { + BITMAP_FROM_U64(0x0000000000000667ULL), +}; + +static const unsigned long sg_gather_exp[] __initconst = { + BITMAP_FROM_U64(0x0000000000000029ULL), +}; + +static const unsigned long sg_scatter_exp[] __initconst = { + BITMAP_FROM_U64(0x000000000000021aULL), +}; + +static void __init test_bitmap_sg(void) +{ + unsigned int nbits = 64; + DECLARE_BITMAP(bmap_gather, 100); + DECLARE_BITMAP(bmap_scatter, 100); + DECLARE_BITMAP(bmap_tmp, 100); + DECLARE_BITMAP(bmap_res, 100); + + /* Simple gather call */ + bitmap_zero(bmap_gather, 100); + bitmap_gather(bmap_gather, sg_src, sg_mask, nbits); + expect_eq_bitmap(sg_gather_exp, bmap_gather, nbits); + + /* Simple scatter call */ + bitmap_zero(bmap_scatter, 100); + bitmap_scatter(bmap_scatter, sg_src, sg_mask, nbits); + expect_eq_bitmap(sg_scatter_exp, bmap_scatter, nbits); + + /* Scatter/gather relationship */ + bitmap_zero(bmap_tmp, 100); + bitmap_gather(bmap_tmp, bmap_scatter, sg_mask, nbits); + bitmap_scatter(bmap_res, bmap_tmp, sg_mask, nbits); + expect_eq_bitmap(bmap_scatter, bmap_res, nbits); +} + #define PARSE_TIME 0x1 #define NO_LEN 0x2 @@ -1252,6 +1293,7 @@ static void __init selftest(void) test_copy(); test_bitmap_region(); test_replace(); + test_bitmap_sg(); test_bitmap_arr32(); test_bitmap_arr64(); test_bitmap_parse(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 150d4f23b010..06aa1ebbd21c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4685,8 +4685,8 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp = gfp_mask; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | - __GFP_NOMEMALLOC; + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER); nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; @@ -4699,6 +4699,16 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, return page; } +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); @@ -4708,9 +4718,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) } EXPORT_SYMBOL(__page_frag_cache_drain); -void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) { unsigned int size = PAGE_SIZE; struct page *page; @@ -4779,7 +4789,7 @@ refill: return nc->va + offset; } -EXPORT_SYMBOL(page_frag_alloc_align); +EXPORT_SYMBOL(__page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4eb1b3ced0d2..27520a8a486f 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -572,7 +572,7 @@ static void netdev_setup(struct net_device *dev) dev->needs_free_netdev = true; } -static struct device_type bt_type = { +static const struct device_type bt_type = { .name = "bluetooth", }; @@ -892,7 +892,7 @@ static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) chan->ops = &bt_6lowpan_chan_ops; err = l2cap_chan_connect(chan, cpu_to_le16(L2CAP_PSM_IPSP), 0, - addr, dst_type); + addr, dst_type, L2CAP_CONN_TIMEOUT); BT_DBG("chan %p err %d", chan, err); if (err < 0) diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index da7cac0a1b71..6b2b65a66700 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -62,14 +62,6 @@ source "net/bluetooth/cmtp/Kconfig" source "net/bluetooth/hidp/Kconfig" -config BT_HS - bool "Bluetooth High Speed (HS) features" - depends on BT_BREDR - help - Bluetooth High Speed includes support for off-loading - Bluetooth connections via 802.11 (wifi) physical layer - available with Bluetooth version 3.0 or later. - config BT_LE bool "Bluetooth Low Energy (LE) features" depends on BT diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 141ac1fda0bf..628d448d78be 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -21,7 +21,6 @@ bluetooth-$(CONFIG_DEV_COREDUMP) += coredump.o bluetooth-$(CONFIG_BT_BREDR) += sco.o bluetooth-$(CONFIG_BT_LE) += iso.o -bluetooth-$(CONFIG_BT_HS) += a2mp.o amp.o bluetooth-$(CONFIG_BT_LEDS) += leds.o bluetooth-$(CONFIG_BT_MSFTEXT) += msft.o bluetooth-$(CONFIG_BT_AOSPEXT) += aosp.o diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c deleted file mode 100644 index e7adb8a98cf9..000000000000 --- a/net/bluetooth/a2mp.c +++ /dev/null @@ -1,1054 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include <net/bluetooth/bluetooth.h> -#include <net/bluetooth/hci_core.h> -#include <net/bluetooth/l2cap.h> - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -#define A2MP_FEAT_EXT 0x8000 - -/* Global AMP Manager list */ -static LIST_HEAD(amp_mgr_list); -static DEFINE_MUTEX(amp_mgr_list_lock); - -/* A2MP build & send command helper functions */ -static struct a2mp_cmd *__a2mp_build(u8 code, u8 ident, u16 len, void *data) -{ - struct a2mp_cmd *cmd; - int plen; - - plen = sizeof(*cmd) + len; - cmd = kzalloc(plen, GFP_KERNEL); - if (!cmd) - return NULL; - - cmd->code = code; - cmd->ident = ident; - cmd->len = cpu_to_le16(len); - - memcpy(cmd->data, data, len); - - return cmd; -} - -static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) -{ - struct l2cap_chan *chan = mgr->a2mp_chan; - struct a2mp_cmd *cmd; - u16 total_len = len + sizeof(*cmd); - struct kvec iv; - struct msghdr msg; - - cmd = __a2mp_build(code, ident, len, data); - if (!cmd) - return; - - iv.iov_base = cmd; - iv.iov_len = total_len; - - memset(&msg, 0, sizeof(msg)); - - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, total_len); - - l2cap_chan_send(chan, &msg, total_len); - - kfree(cmd); -} - -static u8 __next_ident(struct amp_mgr *mgr) -{ - if (++mgr->ident == 0) - mgr->ident = 1; - - return mgr->ident; -} - -static struct amp_mgr *amp_mgr_lookup_by_state(u8 state) -{ - struct amp_mgr *mgr; - - mutex_lock(&_mgr_list_lock); - list_for_each_entry(mgr, &_mgr_list, list) { - if (test_and_clear_bit(state, &mgr->state)) { - amp_mgr_get(mgr); - mutex_unlock(&_mgr_list_lock); - return mgr; - } - } - mutex_unlock(&_mgr_list_lock); - - return NULL; -} - -/* hci_dev_list shall be locked */ -static void __a2mp_add_cl(struct amp_mgr *mgr, struct a2mp_cl *cl) -{ - struct hci_dev *hdev; - int i = 1; - - cl[0].id = AMP_ID_BREDR; - cl[0].type = AMP_TYPE_BREDR; - cl[0].status = AMP_STATUS_BLUETOOTH_ONLY; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) { - cl[i].id = hdev->id; - cl[i].type = hdev->amp_type; - if (test_bit(HCI_UP, &hdev->flags)) - cl[i].status = hdev->amp_status; - else - cl[i].status = AMP_STATUS_POWERED_DOWN; - i++; - } - } -} - -/* Processing A2MP messages */ -static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cmd_rej *rej = (void *) skb->data; - - if (le16_to_cpu(hdr->len) < sizeof(*rej)) - return -EINVAL; - - BT_DBG("ident %u reason %d", hdr->ident, le16_to_cpu(rej->reason)); - - skb_pull(skb, sizeof(*rej)); - - return 0; -} - -static int a2mp_discover_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_req *req = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_discov_rsp *rsp; - u16 ext_feat; - u8 num_ctrl; - struct hci_dev *hdev; - - if (len < sizeof(*req)) - return -EINVAL; - - skb_pull(skb, sizeof(*req)); - - ext_feat = le16_to_cpu(req->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(req->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - read_lock(&hci_dev_list_lock); - - /* at minimum the BR/EDR needs to be listed */ - num_ctrl = 1; - - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->dev_type == HCI_AMP) - num_ctrl++; - } - - len = struct_size(rsp, cl, num_ctrl); - rsp = kmalloc(len, GFP_ATOMIC); - if (!rsp) { - read_unlock(&hci_dev_list_lock); - return -ENOMEM; - } - - rsp->mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - rsp->ext_feat = 0; - - __a2mp_add_cl(mgr, rsp->cl); - - read_unlock(&hci_dev_list_lock); - - a2mp_send(mgr, A2MP_DISCOVER_RSP, hdr->ident, len, rsp); - - kfree(rsp); - return 0; -} - -static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_discov_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct a2mp_cl *cl; - u16 ext_feat; - bool found = false; - - if (len < sizeof(*rsp)) - return -EINVAL; - - len -= sizeof(*rsp); - skb_pull(skb, sizeof(*rsp)); - - ext_feat = le16_to_cpu(rsp->ext_feat); - - BT_DBG("mtu %d efm 0x%4.4x", le16_to_cpu(rsp->mtu), ext_feat); - - /* check that packet is not broken for now */ - while (ext_feat & A2MP_FEAT_EXT) { - if (len < sizeof(ext_feat)) - return -EINVAL; - - ext_feat = get_unaligned_le16(skb->data); - BT_DBG("efm 0x%4.4x", ext_feat); - len -= sizeof(ext_feat); - skb_pull(skb, sizeof(ext_feat)); - } - - cl = (void *) skb->data; - while (len >= sizeof(*cl)) { - BT_DBG("Remote AMP id %u type %u status %u", cl->id, cl->type, - cl->status); - - if (cl->id != AMP_ID_BREDR && cl->type != AMP_TYPE_BREDR) { - struct a2mp_info_req req; - - found = true; - - memset(&req, 0, sizeof(req)); - - req.id = cl->id; - a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr), - sizeof(req), &req); - } - - len -= sizeof(*cl); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* Fall back to L2CAP init sequence */ - if (!found) { - struct l2cap_conn *conn = mgr->l2cap_conn; - struct l2cap_chan *chan; - - mutex_lock(&conn->chan_lock); - - list_for_each_entry(chan, &conn->chan_l, list) { - - BT_DBG("chan %p state %s", chan, - state_to_string(chan->state)); - - if (chan->scid == L2CAP_CID_A2MP) - continue; - - l2cap_chan_lock(chan); - - if (chan->state == BT_CONNECT) - l2cap_send_conn_req(chan); - - l2cap_chan_unlock(chan); - } - - mutex_unlock(&conn->chan_lock); - } - - return 0; -} - -static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_cl *cl = (void *) skb->data; - - while (skb->len >= sizeof(*cl)) { - BT_DBG("Controller id %u type %u status %u", cl->id, cl->type, - cl->status); - cl = skb_pull(skb, sizeof(*cl)); - } - - /* TODO send A2MP_CHANGE_RSP */ - - return 0; -} - -static void read_local_amp_info_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - a2mp_send_getinfo_rsp(hdev); -} - -static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct hci_request hreq; - int err = 0; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->dev_type != HCI_AMP) { - struct a2mp_info_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = req->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - a2mp_send(mgr, A2MP_GETINFO_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - set_bit(READ_LOC_AMP_INFO, &mgr->state); - hci_req_init(&hreq, hdev); - hci_req_add(&hreq, HCI_OP_READ_LOCAL_AMP_INFO, 0, NULL); - err = hci_req_run(&hreq, read_local_amp_info_complete); - if (err < 0) - a2mp_send_getinfo_rsp(hdev); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_info_rsp *rsp = (struct a2mp_info_rsp *) skb->data; - struct a2mp_amp_assoc_req req; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*rsp)) - return -EINVAL; - - BT_DBG("id %u status 0x%2.2x", rsp->id, rsp->status); - - if (rsp->status) - return -EINVAL; - - ctrl = amp_ctrl_add(mgr, rsp->id); - if (!ctrl) - return -ENOMEM; - - memset(&req, 0, sizeof(req)); - - req.id = rsp->id; - a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req), - &req); - - skb_pull(skb, sizeof(*rsp)); - return 0; -} - -static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_req *req = (void *) skb->data; - struct hci_dev *hdev; - struct amp_mgr *tmp; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("id %u", req->id); - - /* Make sure that other request is not processed */ - tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - - hdev = hci_dev_get(req->id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR || tmp) { - struct a2mp_amp_assoc_rsp rsp; - - memset(&rsp, 0, sizeof(rsp)); - rsp.id = req->id; - - if (tmp) { - rsp.status = A2MP_STATUS_COLLISION_OCCURED; - amp_mgr_put(tmp); - } else { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, hdr->ident, sizeof(rsp), - &rsp); - - goto done; - } - - amp_read_loc_assoc(hdev, mgr); - -done: - if (hdev) - hci_dev_put(hdev); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_amp_assoc_rsp *rsp = (void *) skb->data; - u16 len = le16_to_cpu(hdr->len); - struct hci_dev *hdev; - struct amp_ctrl *ctrl; - struct hci_conn *hcon; - size_t assoc_len; - - if (len < sizeof(*rsp)) - return -EINVAL; - - assoc_len = len - sizeof(*rsp); - - BT_DBG("id %u status 0x%2.2x assoc len %zu", rsp->id, rsp->status, - assoc_len); - - if (rsp->status) - return -EINVAL; - - /* Save remote ASSOC data */ - ctrl = amp_ctrl_lookup(mgr, rsp->id); - if (ctrl) { - u8 *assoc; - - assoc = kmemdup(rsp->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - /* Create Phys Link */ - hdev = hci_dev_get(rsp->id); - if (!hdev) - return -EINVAL; - - hcon = phylink_add(hdev, mgr, rsp->id, true); - if (!hcon) - goto done; - - BT_DBG("Created hcon %p: loc:%u -> rem:%u", hcon, hdev->id, rsp->id); - - mgr->bredr_chan->remote_amp_id = rsp->id; - - amp_create_phylink(hdev, mgr, hcon); - -done: - hci_dev_put(hdev); - skb_pull(skb, len); - return 0; -} - -static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - struct amp_ctrl *ctrl; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u, remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - - hdev = hci_dev_get(req->remote_id); - if (!hdev || hdev->amp_type == AMP_TYPE_BREDR) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - ctrl = amp_ctrl_lookup(mgr, rsp.remote_id); - if (!ctrl) { - ctrl = amp_ctrl_add(mgr, rsp.remote_id); - if (ctrl) { - amp_ctrl_get(ctrl); - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - goto send_rsp; - } - } - - if (ctrl) { - size_t assoc_len = le16_to_cpu(hdr->len) - sizeof(*req); - u8 *assoc; - - assoc = kmemdup(req->amp_assoc, assoc_len, GFP_KERNEL); - if (!assoc) { - amp_ctrl_put(ctrl); - hci_dev_put(hdev); - return -ENOMEM; - } - - ctrl->assoc = assoc; - ctrl->assoc_len = assoc_len; - ctrl->assoc_rem_len = assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - } - - hcon = phylink_add(hdev, mgr, req->local_id, false); - if (hcon) { - amp_accept_phylink(hdev, mgr, hcon); - rsp.status = A2MP_STATUS_SUCCESS; - } else { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } - -send_rsp: - if (hdev) - hci_dev_put(hdev); - - /* Reply error now and success after HCI Write Remote AMP Assoc - command complete with success status - */ - if (rsp.status != A2MP_STATUS_SUCCESS) { - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, hdr->ident, - sizeof(rsp), &rsp); - } else { - set_bit(WRITE_REMOTE_AMP_ASSOC, &mgr->state); - mgr->ident = hdr->ident; - } - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - struct a2mp_physlink_req *req = (void *) skb->data; - struct a2mp_physlink_rsp rsp; - struct hci_dev *hdev; - struct hci_conn *hcon; - - if (le16_to_cpu(hdr->len) < sizeof(*req)) - return -EINVAL; - - BT_DBG("local_id %u remote_id %u", req->local_id, req->remote_id); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.local_id = req->remote_id; - rsp.remote_id = req->local_id; - rsp.status = A2MP_STATUS_SUCCESS; - - hdev = hci_dev_get(req->remote_id); - if (!hdev) { - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - goto send_rsp; - } - - hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &mgr->l2cap_conn->hcon->dst); - if (!hcon) { - bt_dev_err(hdev, "no phys link exist"); - rsp.status = A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS; - goto clean; - } - - /* TODO Disconnect Phys Link here */ - -clean: - hci_dev_put(hdev); - -send_rsp: - a2mp_send(mgr, A2MP_DISCONNPHYSLINK_RSP, hdr->ident, sizeof(rsp), &rsp); - - skb_pull(skb, sizeof(*req)); - return 0; -} - -static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, - struct a2mp_cmd *hdr) -{ - BT_DBG("ident %u code 0x%2.2x", hdr->ident, hdr->code); - - skb_pull(skb, le16_to_cpu(hdr->len)); - return 0; -} - -/* Handle A2MP signalling */ -static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) -{ - struct a2mp_cmd *hdr; - struct amp_mgr *mgr = chan->data; - int err = 0; - - amp_mgr_get(mgr); - - while (skb->len >= sizeof(*hdr)) { - u16 len; - - hdr = (void *) skb->data; - len = le16_to_cpu(hdr->len); - - BT_DBG("code 0x%2.2x id %u len %u", hdr->code, hdr->ident, len); - - skb_pull(skb, sizeof(*hdr)); - - if (len > skb->len || !hdr->ident) { - err = -EINVAL; - break; - } - - mgr->ident = hdr->ident; - - switch (hdr->code) { - case A2MP_COMMAND_REJ: - a2mp_command_rej(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_REQ: - err = a2mp_discover_req(mgr, skb, hdr); - break; - - case A2MP_CHANGE_NOTIFY: - err = a2mp_change_notify(mgr, skb, hdr); - break; - - case A2MP_GETINFO_REQ: - err = a2mp_getinfo_req(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_REQ: - err = a2mp_getampassoc_req(mgr, skb, hdr); - break; - - case A2MP_CREATEPHYSLINK_REQ: - err = a2mp_createphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCONNPHYSLINK_REQ: - err = a2mp_discphyslink_req(mgr, skb, hdr); - break; - - case A2MP_DISCOVER_RSP: - err = a2mp_discover_rsp(mgr, skb, hdr); - break; - - case A2MP_GETINFO_RSP: - err = a2mp_getinfo_rsp(mgr, skb, hdr); - break; - - case A2MP_GETAMPASSOC_RSP: - err = a2mp_getampassoc_rsp(mgr, skb, hdr); - break; - - case A2MP_CHANGE_RSP: - case A2MP_CREATEPHYSLINK_RSP: - case A2MP_DISCONNPHYSLINK_RSP: - err = a2mp_cmd_rsp(mgr, skb, hdr); - break; - - default: - BT_ERR("Unknown A2MP sig cmd 0x%2.2x", hdr->code); - err = -EINVAL; - break; - } - } - - if (err) { - struct a2mp_cmd_rej rej; - - memset(&rej, 0, sizeof(rej)); - - rej.reason = cpu_to_le16(0); - hdr = (void *) skb->data; - - BT_DBG("Send A2MP Rej: cmd 0x%2.2x err %d", hdr->code, err); - - a2mp_send(mgr, A2MP_COMMAND_REJ, hdr->ident, sizeof(rej), - &rej); - } - - /* Always free skb and return success error code to prevent - from sending L2CAP Disconnect over A2MP channel */ - kfree_skb(skb); - - amp_mgr_put(mgr); - - return 0; -} - -static void a2mp_chan_close_cb(struct l2cap_chan *chan) -{ - l2cap_chan_put(chan); -} - -static void a2mp_chan_state_change_cb(struct l2cap_chan *chan, int state, - int err) -{ - struct amp_mgr *mgr = chan->data; - - if (!mgr) - return; - - BT_DBG("chan %p state %s", chan, state_to_string(state)); - - chan->state = state; - - switch (state) { - case BT_CLOSED: - if (mgr) - amp_mgr_put(mgr); - break; - } -} - -static struct sk_buff *a2mp_chan_alloc_skb_cb(struct l2cap_chan *chan, - unsigned long hdr_len, - unsigned long len, int nb) -{ - struct sk_buff *skb; - - skb = bt_skb_alloc(hdr_len + len, GFP_KERNEL); - if (!skb) - return ERR_PTR(-ENOMEM); - - return skb; -} - -static const struct l2cap_ops a2mp_chan_ops = { - .name = "L2CAP A2MP channel", - .recv = a2mp_chan_recv_cb, - .close = a2mp_chan_close_cb, - .state_change = a2mp_chan_state_change_cb, - .alloc_skb = a2mp_chan_alloc_skb_cb, - - /* Not implemented for A2MP */ - .new_connection = l2cap_chan_no_new_connection, - .teardown = l2cap_chan_no_teardown, - .ready = l2cap_chan_no_ready, - .defer = l2cap_chan_no_defer, - .resume = l2cap_chan_no_resume, - .set_shutdown = l2cap_chan_no_set_shutdown, - .get_sndtimeo = l2cap_chan_no_get_sndtimeo, -}; - -static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) -{ - struct l2cap_chan *chan; - int err; - - chan = l2cap_chan_create(); - if (!chan) - return NULL; - - BT_DBG("chan %p", chan); - - chan->chan_type = L2CAP_CHAN_FIXED; - chan->scid = L2CAP_CID_A2MP; - chan->dcid = L2CAP_CID_A2MP; - chan->omtu = L2CAP_A2MP_DEFAULT_MTU; - chan->imtu = L2CAP_A2MP_DEFAULT_MTU; - chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; - - chan->ops = &a2mp_chan_ops; - - l2cap_chan_set_defaults(chan); - chan->remote_max_tx = chan->max_tx; - chan->remote_tx_win = chan->tx_win; - - chan->retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; - chan->monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; - - skb_queue_head_init(&chan->tx_q); - - chan->mode = L2CAP_MODE_ERTM; - - err = l2cap_ertm_init(chan); - if (err < 0) { - l2cap_chan_del(chan, 0); - return NULL; - } - - chan->conf_state = 0; - - if (locked) - __l2cap_chan_add(conn, chan); - else - l2cap_chan_add(conn, chan); - - chan->remote_mps = chan->omtu; - chan->mps = chan->omtu; - - chan->state = BT_CONNECTED; - - return chan; -} - -/* AMP Manager functions */ -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - kref_get(&mgr->kref); - - return mgr; -} - -static void amp_mgr_destroy(struct kref *kref) -{ - struct amp_mgr *mgr = container_of(kref, struct amp_mgr, kref); - - BT_DBG("mgr %p", mgr); - - mutex_lock(&_mgr_list_lock); - list_del(&mgr->list); - mutex_unlock(&_mgr_list_lock); - - amp_ctrl_list_flush(mgr); - kfree(mgr); -} - -int amp_mgr_put(struct amp_mgr *mgr) -{ - BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref)); - - return kref_put(&mgr->kref, &_mgr_destroy); -} - -static struct amp_mgr *amp_mgr_create(struct l2cap_conn *conn, bool locked) -{ - struct amp_mgr *mgr; - struct l2cap_chan *chan; - - mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); - if (!mgr) - return NULL; - - BT_DBG("conn %p mgr %p", conn, mgr); - - mgr->l2cap_conn = conn; - - chan = a2mp_chan_open(conn, locked); - if (!chan) { - kfree(mgr); - return NULL; - } - - mgr->a2mp_chan = chan; - chan->data = mgr; - - conn->hcon->amp_mgr = mgr; - - kref_init(&mgr->kref); - - /* Remote AMP ctrl list initialization */ - INIT_LIST_HEAD(&mgr->amp_ctrls); - mutex_init(&mgr->amp_ctrls_lock); - - mutex_lock(&_mgr_list_lock); - list_add(&mgr->list, &_mgr_list); - mutex_unlock(&_mgr_list_lock); - - return mgr; -} - -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - struct amp_mgr *mgr; - - if (conn->hcon->type != ACL_LINK) - return NULL; - - mgr = amp_mgr_create(conn, false); - if (!mgr) { - BT_ERR("Could not create AMP manager"); - return NULL; - } - - BT_DBG("mgr: %p chan %p", mgr, mgr->a2mp_chan); - - return mgr->a2mp_chan; -} - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev) -{ - struct amp_mgr *mgr; - struct a2mp_info_rsp rsp; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_INFO); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - memset(&rsp, 0, sizeof(rsp)); - - rsp.id = hdev->id; - rsp.status = A2MP_STATUS_INVALID_CTRL_ID; - - if (hdev->amp_type != AMP_TYPE_BREDR) { - rsp.status = 0; - rsp.total_bw = cpu_to_le32(hdev->amp_total_bw); - rsp.max_bw = cpu_to_le32(hdev->amp_max_bw); - rsp.min_latency = cpu_to_le32(hdev->amp_min_latency); - rsp.pal_cap = cpu_to_le16(hdev->amp_pal_cap); - rsp.assoc_size = cpu_to_le16(hdev->amp_assoc_size); - } - - a2mp_send(mgr, A2MP_GETINFO_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_amp_assoc_rsp *rsp; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); - if (!mgr) - return; - - BT_DBG("%s mgr %p", hdev->name, mgr); - - len = sizeof(struct a2mp_amp_assoc_rsp) + loc_assoc->len; - rsp = kzalloc(len, GFP_KERNEL); - if (!rsp) { - amp_mgr_put(mgr); - return; - } - - rsp->id = hdev->id; - - if (status) { - rsp->status = A2MP_STATUS_INVALID_CTRL_ID; - } else { - rsp->status = A2MP_STATUS_SUCCESS; - memcpy(rsp->amp_assoc, loc_assoc->data, loc_assoc->len); - } - - a2mp_send(mgr, A2MP_GETAMPASSOC_RSP, mgr->ident, len, rsp); - amp_mgr_put(mgr); - kfree(rsp); -} - -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct a2mp_physlink_req *req; - struct l2cap_chan *bredr_chan; - size_t len; - - mgr = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC_FINAL); - if (!mgr) - return; - - len = sizeof(*req) + loc_assoc->len; - - BT_DBG("%s mgr %p assoc_len %zu", hdev->name, mgr, len); - - req = kzalloc(len, GFP_KERNEL); - if (!req) { - amp_mgr_put(mgr); - return; - } - - bredr_chan = mgr->bredr_chan; - if (!bredr_chan) - goto clean; - - req->local_id = hdev->id; - req->remote_id = bredr_chan->remote_amp_id; - memcpy(req->amp_assoc, loc_assoc->data, loc_assoc->len); - - a2mp_send(mgr, A2MP_CREATEPHYSLINK_REQ, __next_ident(mgr), len, req); - -clean: - amp_mgr_put(mgr); - kfree(req); -} - -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status) -{ - struct amp_mgr *mgr; - struct a2mp_physlink_rsp rsp; - struct hci_conn *hs_hcon; - - mgr = amp_mgr_lookup_by_state(WRITE_REMOTE_AMP_ASSOC); - if (!mgr) - return; - - memset(&rsp, 0, sizeof(rsp)); - - hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT); - if (!hs_hcon) { - rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION; - } else { - rsp.remote_id = hs_hcon->remote_id; - rsp.status = A2MP_STATUS_SUCCESS; - } - - BT_DBG("%s mgr %p hs_hcon %p status %u", hdev->name, mgr, hs_hcon, - status); - - rsp.local_id = hdev->id; - a2mp_send(mgr, A2MP_CREATEPHYSLINK_RSP, mgr->ident, sizeof(rsp), &rsp); - amp_mgr_put(mgr); -} - -void a2mp_discover_amp(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct a2mp_discov_req req; - - BT_DBG("chan %p conn %p mgr %p", chan, conn, mgr); - - if (!mgr) { - mgr = amp_mgr_create(conn, true); - if (!mgr) - return; - } - - mgr->bredr_chan = chan; - - memset(&req, 0, sizeof(req)); - - req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU); - req.ext_feat = 0; - a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req); -} diff --git a/net/bluetooth/a2mp.h b/net/bluetooth/a2mp.h deleted file mode 100644 index 2fd253a61a2a..000000000000 --- a/net/bluetooth/a2mp.h +++ /dev/null @@ -1,154 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2010,2011 Code Aurora Forum. All rights reserved. - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __A2MP_H -#define __A2MP_H - -#include <net/bluetooth/l2cap.h> - -enum amp_mgr_state { - READ_LOC_AMP_INFO, - READ_LOC_AMP_ASSOC, - READ_LOC_AMP_ASSOC_FINAL, - WRITE_REMOTE_AMP_ASSOC, -}; - -struct amp_mgr { - struct list_head list; - struct l2cap_conn *l2cap_conn; - struct l2cap_chan *a2mp_chan; - struct l2cap_chan *bredr_chan; - struct kref kref; - __u8 ident; - __u8 handle; - unsigned long state; - unsigned long flags; - - struct list_head amp_ctrls; - struct mutex amp_ctrls_lock; -}; - -struct a2mp_cmd { - __u8 code; - __u8 ident; - __le16 len; - __u8 data[]; -} __packed; - -/* A2MP command codes */ -#define A2MP_COMMAND_REJ 0x01 -struct a2mp_cmd_rej { - __le16 reason; - __u8 data[]; -} __packed; - -#define A2MP_DISCOVER_REQ 0x02 -struct a2mp_discov_req { - __le16 mtu; - __le16 ext_feat; -} __packed; - -struct a2mp_cl { - __u8 id; - __u8 type; - __u8 status; -} __packed; - -#define A2MP_DISCOVER_RSP 0x03 -struct a2mp_discov_rsp { - __le16 mtu; - __le16 ext_feat; - struct a2mp_cl cl[]; -} __packed; - -#define A2MP_CHANGE_NOTIFY 0x04 -#define A2MP_CHANGE_RSP 0x05 - -#define A2MP_GETINFO_REQ 0x06 -struct a2mp_info_req { - __u8 id; -} __packed; - -#define A2MP_GETINFO_RSP 0x07 -struct a2mp_info_rsp { - __u8 id; - __u8 status; - __le32 total_bw; - __le32 max_bw; - __le32 min_latency; - __le16 pal_cap; - __le16 assoc_size; -} __packed; - -#define A2MP_GETAMPASSOC_REQ 0x08 -struct a2mp_amp_assoc_req { - __u8 id; -} __packed; - -#define A2MP_GETAMPASSOC_RSP 0x09 -struct a2mp_amp_assoc_rsp { - __u8 id; - __u8 status; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_REQ 0x0A -#define A2MP_DISCONNPHYSLINK_REQ 0x0C -struct a2mp_physlink_req { - __u8 local_id; - __u8 remote_id; - __u8 amp_assoc[]; -} __packed; - -#define A2MP_CREATEPHYSLINK_RSP 0x0B -#define A2MP_DISCONNPHYSLINK_RSP 0x0D -struct a2mp_physlink_rsp { - __u8 local_id; - __u8 remote_id; - __u8 status; -} __packed; - -/* A2MP response status */ -#define A2MP_STATUS_SUCCESS 0x00 -#define A2MP_STATUS_INVALID_CTRL_ID 0x01 -#define A2MP_STATUS_UNABLE_START_LINK_CREATION 0x02 -#define A2MP_STATUS_NO_PHYSICAL_LINK_EXISTS 0x02 -#define A2MP_STATUS_COLLISION_OCCURED 0x03 -#define A2MP_STATUS_DISCONN_REQ_RECVD 0x04 -#define A2MP_STATUS_PHYS_LINK_EXISTS 0x05 -#define A2MP_STATUS_SECURITY_VIOLATION 0x06 - -struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr); - -#if IS_ENABLED(CONFIG_BT_HS) -int amp_mgr_put(struct amp_mgr *mgr); -struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb); -void a2mp_discover_amp(struct l2cap_chan *chan); -#else -static inline int amp_mgr_put(struct amp_mgr *mgr) -{ - return 0; -} - -static inline struct l2cap_chan *a2mp_channel_create(struct l2cap_conn *conn, - struct sk_buff *skb) -{ - return NULL; -} - -static inline void a2mp_discover_amp(struct l2cap_chan *chan) -{ -} -#endif - -void a2mp_send_getinfo_rsp(struct hci_dev *hdev); -void a2mp_send_getampassoc_rsp(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_req(struct hci_dev *hdev, u8 status); -void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status); - -#endif /* __A2MP_H */ diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index b93464ac3517..67604ccec2f4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,14 +309,11 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; - lock_sock(sk); - skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - release_sock(sk); return err; } @@ -346,8 +343,6 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); - release_sock(sk); - if (flags & MSG_TRUNC) copied = skblen; @@ -570,10 +565,11 @@ int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) if (sk->sk_state == BT_LISTEN) return -EINVAL; - lock_sock(sk); + spin_lock(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; - release_sock(sk); + spin_unlock(&sk->sk_receive_queue.lock); + err = put_user(amount, (int __user *)arg); break; diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c deleted file mode 100644 index 5d698f19868c..000000000000 --- a/net/bluetooth/amp.c +++ /dev/null @@ -1,590 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#include <net/bluetooth/bluetooth.h> -#include <net/bluetooth/hci.h> -#include <net/bluetooth/hci_core.h> -#include <crypto/hash.h> - -#include "hci_request.h" -#include "a2mp.h" -#include "amp.h" - -/* Remote AMP Controllers interface */ -void amp_ctrl_get(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - kref_get(&ctrl->kref); -} - -static void amp_ctrl_destroy(struct kref *kref) -{ - struct amp_ctrl *ctrl = container_of(kref, struct amp_ctrl, kref); - - BT_DBG("ctrl %p", ctrl); - - kfree(ctrl->assoc); - kfree(ctrl); -} - -int amp_ctrl_put(struct amp_ctrl *ctrl) -{ - BT_DBG("ctrl %p orig refcnt %d", ctrl, - kref_read(&ctrl->kref)); - - return kref_put(&ctrl->kref, &_ctrl_destroy); -} - -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); - if (!ctrl) - return NULL; - - kref_init(&ctrl->kref); - ctrl->id = id; - - mutex_lock(&mgr->amp_ctrls_lock); - list_add(&ctrl->list, &mgr->amp_ctrls); - mutex_unlock(&mgr->amp_ctrls_lock); - - BT_DBG("mgr %p ctrl %p", mgr, ctrl); - - return ctrl; -} - -void amp_ctrl_list_flush(struct amp_mgr *mgr) -{ - struct amp_ctrl *ctrl, *n; - - BT_DBG("mgr %p", mgr); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry_safe(ctrl, n, &mgr->amp_ctrls, list) { - list_del(&ctrl->list); - amp_ctrl_put(ctrl); - } - mutex_unlock(&mgr->amp_ctrls_lock); -} - -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) -{ - struct amp_ctrl *ctrl; - - BT_DBG("mgr %p id %u", mgr, id); - - mutex_lock(&mgr->amp_ctrls_lock); - list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { - if (ctrl->id == id) { - amp_ctrl_get(ctrl); - mutex_unlock(&mgr->amp_ctrls_lock); - return ctrl; - } - } - mutex_unlock(&mgr->amp_ctrls_lock); - - return NULL; -} - -/* Physical Link interface */ -static u8 __next_handle(struct amp_mgr *mgr) -{ - if (++mgr->handle == 0) - mgr->handle = 1; - - return mgr->handle; -} - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out) -{ - bdaddr_t *dst = &mgr->l2cap_conn->hcon->dst; - struct hci_conn *hcon; - u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - - hcon = hci_conn_add(hdev, AMP_LINK, dst, role, __next_handle(mgr)); - if (!hcon) - return NULL; - - BT_DBG("hcon %p dst %pMR", hcon, dst); - - hcon->state = BT_CONNECT; - hcon->attempt++; - hcon->remote_id = remote_id; - hcon->amp_mgr = amp_mgr_get(mgr); - - return hcon; -} - -/* AMP crypto key generation interface */ -static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output) -{ - struct crypto_shash *tfm; - struct shash_desc *shash; - int ret; - - if (!ksize) - return -EINVAL; - - tfm = crypto_alloc_shash("hmac(sha256)", 0, 0); - if (IS_ERR(tfm)) { - BT_DBG("crypto_alloc_ahash failed: err %ld", PTR_ERR(tfm)); - return PTR_ERR(tfm); - } - - ret = crypto_shash_setkey(tfm, key, ksize); - if (ret) { - BT_DBG("crypto_ahash_setkey failed: err %d", ret); - goto failed; - } - - shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(tfm), - GFP_KERNEL); - if (!shash) { - ret = -ENOMEM; - goto failed; - } - - shash->tfm = tfm; - - ret = crypto_shash_digest(shash, plaintext, psize, output); - - kfree(shash); - -failed: - crypto_free_shash(tfm); - return ret; -} - -int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) -{ - struct hci_dev *hdev = conn->hdev; - struct link_key *key; - u8 keybuf[HCI_AMP_LINK_KEY_SIZE]; - u8 gamp_key[HCI_AMP_LINK_KEY_SIZE]; - int err; - - if (!hci_conn_check_link_mode(conn)) - return -EACCES; - - BT_DBG("conn %p key_type %d", conn, conn->key_type); - - /* Legacy key */ - if (conn->key_type < 3) { - bt_dev_err(hdev, "legacy key type %u", conn->key_type); - return -EACCES; - } - - *type = conn->key_type; - *len = HCI_AMP_LINK_KEY_SIZE; - - key = hci_find_link_key(hdev, &conn->dst); - if (!key) { - BT_DBG("No Link key for conn %p dst %pMR", conn, &conn->dst); - return -EACCES; - } - - /* BR/EDR Link Key concatenated together with itself */ - memcpy(&keybuf[0], key->val, HCI_LINK_KEY_SIZE); - memcpy(&keybuf[HCI_LINK_KEY_SIZE], key->val, HCI_LINK_KEY_SIZE); - - /* Derive Generic AMP Link Key (gamp) */ - err = hmac_sha256(keybuf, HCI_AMP_LINK_KEY_SIZE, "gamp", 4, gamp_key); - if (err) { - bt_dev_err(hdev, "could not derive Generic AMP Key: err %d", err); - return err; - } - - if (conn->key_type == HCI_LK_DEBUG_COMBINATION) { - BT_DBG("Use Generic AMP Key (gamp)"); - memcpy(data, gamp_key, HCI_AMP_LINK_KEY_SIZE); - return err; - } - - /* Derive Dedicated AMP Link Key: "802b" is 802.11 PAL keyID */ - return hmac_sha256(gamp_key, HCI_AMP_LINK_KEY_SIZE, "802b", 4, data); -} - -static void read_local_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_read_local_amp_assoc *rp = (void *)skb->data; - struct amp_assoc *assoc = &hdev->loc_assoc; - size_t rem_len, frag_len; - - BT_DBG("%s status 0x%2.2x", hdev->name, rp->status); - - if (rp->status) - goto send_rsp; - - frag_len = skb->len - sizeof(*rp); - rem_len = __le16_to_cpu(rp->rem_len); - - if (rem_len > frag_len) { - BT_DBG("frag_len %zu rem_len %zu", frag_len, rem_len); - - memcpy(assoc->data + assoc->offset, rp->frag, frag_len); - assoc->offset += frag_len; - - /* Read other fragments */ - amp_read_loc_assoc_frag(hdev, rp->phy_handle); - - return; - } - - memcpy(assoc->data + assoc->offset, rp->frag, rem_len); - assoc->len = assoc->offset + rem_len; - assoc->offset = 0; - -send_rsp: - /* Send A2MP Rsp when all fragments are received */ - a2mp_send_getampassoc_rsp(hdev, rp->status); - a2mp_send_create_phy_link_req(hdev, rp->status); -} - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_assoc *loc_assoc = &hdev->loc_assoc; - struct hci_request req; - int err; - - BT_DBG("%s handle %u", hdev->name, phy_handle); - - cp.phy_handle = phy_handle; - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - cp.len_so_far = cpu_to_le16(loc_assoc->offset); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr) -{ - struct hci_cp_read_local_amp_assoc cp; - struct hci_request req; - int err; - - memset(&hdev->loc_assoc, 0, sizeof(struct amp_assoc)); - memset(&cp, 0, sizeof(cp)); - - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC, &mgr->state); - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_read_local_amp_assoc cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct hci_request req; - int err; - - if (!mgr) - return; - - cp.phy_handle = hcon->handle; - cp.len_so_far = cpu_to_le16(0); - cp.max_len = cpu_to_le16(hdev->amp_assoc_size); - - set_bit(READ_LOC_AMP_ASSOC_FINAL, &mgr->state); - - /* Read Local AMP Assoc final link information data */ - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_READ_LOCAL_AMP_ASSOC, sizeof(cp), &cp); - err = hci_req_run_skb(&req, read_local_amp_assoc_complete); - if (err < 0) - a2mp_send_getampassoc_rsp(hdev, A2MP_STATUS_INVALID_CTRL_ID); -} - -static void write_remote_amp_assoc_complete(struct hci_dev *hdev, u8 status, - u16 opcode, struct sk_buff *skb) -{ - struct hci_rp_write_remote_amp_assoc *rp = (void *)skb->data; - - BT_DBG("%s status 0x%2.2x phy_handle 0x%2.2x", - hdev->name, rp->status, rp->phy_handle); - - if (rp->status) - return; - - amp_write_rem_assoc_continue(hdev, rp->phy_handle); -} - -/* Write AMP Assoc data fragments, returns true with last fragment written*/ -static bool amp_write_rem_assoc_frag(struct hci_dev *hdev, - struct hci_conn *hcon) -{ - struct hci_cp_write_remote_amp_assoc *cp; - struct amp_mgr *mgr = hcon->amp_mgr; - struct amp_ctrl *ctrl; - struct hci_request req; - u16 frag_len, len; - - ctrl = amp_ctrl_lookup(mgr, hcon->remote_id); - if (!ctrl) - return false; - - if (!ctrl->assoc_rem_len) { - BT_DBG("all fragments are written"); - ctrl->assoc_rem_len = ctrl->assoc_len; - ctrl->assoc_len_so_far = 0; - - amp_ctrl_put(ctrl); - return true; - } - - frag_len = min_t(u16, 248, ctrl->assoc_rem_len); - len = frag_len + sizeof(*cp); - - cp = kzalloc(len, GFP_KERNEL); - if (!cp) { - amp_ctrl_put(ctrl); - return false; - } - - BT_DBG("hcon %p ctrl %p frag_len %u assoc_len %u rem_len %u", - hcon, ctrl, frag_len, ctrl->assoc_len, ctrl->assoc_rem_len); - - cp->phy_handle = hcon->handle; - cp->len_so_far = cpu_to_le16(ctrl->assoc_len_so_far); - cp->rem_len = cpu_to_le16(ctrl->assoc_rem_len); - memcpy(cp->frag, ctrl->assoc, frag_len); - - ctrl->assoc_len_so_far += frag_len; - ctrl->assoc_rem_len -= frag_len; - - amp_ctrl_put(ctrl); - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_WRITE_REMOTE_AMP_ASSOC, len, cp); - hci_req_run_skb(&req, write_remote_amp_assoc_complete); - - kfree(cp); - - return false; -} - -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - /* Send A2MP create phylink rsp when all fragments are written */ - if (amp_write_rem_assoc_frag(hdev, hcon)) - a2mp_send_create_phy_link_rsp(hdev, 0); -} - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle) -{ - struct hci_conn *hcon; - - BT_DBG("%s phy handle 0x%2.2x", hdev->name, handle); - - hcon = hci_conn_hash_lookup_handle(hdev, handle); - if (!hcon) - return; - - BT_DBG("%s phy handle 0x%2.2x hcon %p", hdev->name, handle, hcon); - - amp_write_rem_assoc_frag(hdev, hcon); -} - -static void create_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_create_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - cp = hci_sent_cmd_data(hdev, HCI_OP_CREATE_PHY_LINK); - if (!cp) - return; - - hci_dev_lock(hdev); - - if (status) { - struct hci_conn *hcon; - - hcon = hci_conn_hash_lookup_handle(hdev, cp->phy_handle); - if (hcon) - hci_conn_del(hcon); - } else { - amp_write_remote_assoc(hdev, cp->phy_handle); - } - - hci_dev_unlock(hdev); -} - -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_create_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_CREATE_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, create_phylink_complete); -} - -static void accept_phylink_complete(struct hci_dev *hdev, u8 status, - u16 opcode) -{ - struct hci_cp_accept_phy_link *cp; - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - cp = hci_sent_cmd_data(hdev, HCI_OP_ACCEPT_PHY_LINK); - if (!cp) - return; - - amp_write_remote_assoc(hdev, cp->phy_handle); -} - -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon) -{ - struct hci_cp_accept_phy_link cp; - struct hci_request req; - - cp.phy_handle = hcon->handle; - - BT_DBG("%s hcon %p phy handle 0x%2.2x", hdev->name, hcon, - hcon->handle); - - if (phylink_gen_key(mgr->l2cap_conn->hcon, cp.key, &cp.key_len, - &cp.key_type)) { - BT_DBG("Cannot create link key"); - return; - } - - hci_req_init(&req, hdev); - hci_req_add(&req, HCI_OP_ACCEPT_PHY_LINK, sizeof(cp), &cp); - hci_req_run(&req, accept_phylink_complete); -} - -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon) -{ - struct hci_dev *bredr_hdev = hci_dev_hold(bredr_hcon->hdev); - struct amp_mgr *mgr = hs_hcon->amp_mgr; - struct l2cap_chan *bredr_chan; - - BT_DBG("bredr_hcon %p hs_hcon %p mgr %p", bredr_hcon, hs_hcon, mgr); - - if (!bredr_hdev || !mgr || !mgr->bredr_chan) - return; - - bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - set_bit(FLAG_EFS_ENABLE, &bredr_chan->flags); - bredr_chan->remote_amp_id = hs_hcon->remote_id; - bredr_chan->local_amp_id = hs_hcon->hdev->id; - bredr_chan->hs_hcon = hs_hcon; - bredr_chan->conn->mtu = hs_hcon->hdev->block_mtu; - - __l2cap_physical_cfm(bredr_chan, 0); - - l2cap_chan_unlock(bredr_chan); - - hci_dev_put(bredr_hdev); -} - -void amp_create_logical_link(struct l2cap_chan *chan) -{ - struct hci_conn *hs_hcon = chan->hs_hcon; - struct hci_cp_create_accept_logical_link cp; - struct hci_dev *hdev; - - BT_DBG("chan %p hs_hcon %p dst %pMR", chan, hs_hcon, - &chan->conn->hcon->dst); - - if (!hs_hcon) - return; - - hdev = hci_dev_hold(chan->hs_hcon->hdev); - if (!hdev) - return; - - cp.phy_handle = hs_hcon->handle; - - cp.tx_flow_spec.id = chan->local_id; - cp.tx_flow_spec.stype = chan->local_stype; - cp.tx_flow_spec.msdu = cpu_to_le16(chan->local_msdu); - cp.tx_flow_spec.sdu_itime = cpu_to_le32(chan->local_sdu_itime); - cp.tx_flow_spec.acc_lat = cpu_to_le32(chan->local_acc_lat); - cp.tx_flow_spec.flush_to = cpu_to_le32(chan->local_flush_to); - - cp.rx_flow_spec.id = chan->remote_id; - cp.rx_flow_spec.stype = chan->remote_stype; - cp.rx_flow_spec.msdu = cpu_to_le16(chan->remote_msdu); - cp.rx_flow_spec.sdu_itime = cpu_to_le32(chan->remote_sdu_itime); - cp.rx_flow_spec.acc_lat = cpu_to_le32(chan->remote_acc_lat); - cp.rx_flow_spec.flush_to = cpu_to_le32(chan->remote_flush_to); - - if (hs_hcon->out) - hci_send_cmd(hdev, HCI_OP_CREATE_LOGICAL_LINK, sizeof(cp), - &cp); - else - hci_send_cmd(hdev, HCI_OP_ACCEPT_LOGICAL_LINK, sizeof(cp), - &cp); - - hci_dev_put(hdev); -} - -void amp_disconnect_logical_link(struct hci_chan *hchan) -{ - struct hci_conn *hcon = hchan->conn; - struct hci_cp_disconn_logical_link cp; - - if (hcon->state != BT_CONNECTED) { - BT_DBG("hchan %p not connected", hchan); - return; - } - - cp.log_handle = cpu_to_le16(hchan->handle); - hci_send_cmd(hcon->hdev, HCI_OP_DISCONN_LOGICAL_LINK, sizeof(cp), &cp); -} - -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason) -{ - BT_DBG("hchan %p", hchan); - - hci_chan_del(hchan); -} diff --git a/net/bluetooth/amp.h b/net/bluetooth/amp.h deleted file mode 100644 index 97c87abd129f..000000000000 --- a/net/bluetooth/amp.h +++ /dev/null @@ -1,60 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - Copyright (c) 2011,2012 Intel Corp. - -*/ - -#ifndef __AMP_H -#define __AMP_H - -struct amp_ctrl { - struct list_head list; - struct kref kref; - __u8 id; - __u16 assoc_len_so_far; - __u16 assoc_rem_len; - __u16 assoc_len; - __u8 *assoc; -}; - -int amp_ctrl_put(struct amp_ctrl *ctrl); -void amp_ctrl_get(struct amp_ctrl *ctrl); -struct amp_ctrl *amp_ctrl_add(struct amp_mgr *mgr, u8 id); -struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id); -void amp_ctrl_list_flush(struct amp_mgr *mgr); - -struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, - u8 remote_id, bool out); - -int phylink_gen_key(struct hci_conn *hcon, u8 *data, u8 *len, u8 *type); - -void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle); -void amp_read_loc_assoc(struct hci_dev *hdev, struct amp_mgr *mgr); -void amp_read_loc_assoc_final_data(struct hci_dev *hdev, - struct hci_conn *hcon); -void amp_create_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); -void amp_accept_phylink(struct hci_dev *hdev, struct amp_mgr *mgr, - struct hci_conn *hcon); - -#if IS_ENABLED(CONFIG_BT_HS) -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -#else -static inline void amp_create_logical_link(struct l2cap_chan *chan) -{ -} - -static inline void amp_disconnect_logical_link(struct hci_chan *hchan) -{ -} -#endif - -void amp_write_remote_assoc(struct hci_dev *hdev, u8 handle); -void amp_write_rem_assoc_continue(struct hci_dev *hdev, u8 handle); -void amp_physical_cfm(struct hci_conn *bredr_hcon, struct hci_conn *hs_hcon); -void amp_create_logical_link(struct l2cap_chan *chan); -void amp_disconnect_logical_link(struct hci_chan *hchan); -void amp_destroy_logical_link(struct hci_chan *hchan, u8 reason); - -#endif /* __AMP_H */ diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 5a6a49885ab6..ec45f77fce21 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -385,7 +385,8 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb) case BNEP_COMPRESSED_DST_ONLY: __skb_put_data(nskb, skb_mac_header(skb), ETH_ALEN); - __skb_put_data(nskb, s->eh.h_source, ETH_ALEN + 2); + __skb_put_data(nskb, s->eh.h_source, ETH_ALEN); + put_unaligned(s->eh.h_proto, (__be16 *)__skb_put(nskb, 2)); break; case BNEP_GENERAL: @@ -549,7 +550,7 @@ static struct device *bnep_get_device(struct bnep_session *session) return &conn->hcon->dev; } -static struct device_type bnep_type = { +static const struct device_type bnep_type = { .name = "bluetooth", }; diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 9214189279e8..1bc51e2b05a3 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -13,48 +13,33 @@ #define PNP_INFO_SVCLASS_ID 0x1200 -static u8 eir_append_name(u8 *eir, u16 eir_len, u8 type, u8 *data, u8 data_len) -{ - u8 name[HCI_MAX_SHORT_NAME_LENGTH + 1]; - - /* If data is already NULL terminated just pass it directly */ - if (data[data_len - 1] == '\0') - return eir_append_data(eir, eir_len, type, data, data_len); - - memcpy(name, data, HCI_MAX_SHORT_NAME_LENGTH); - name[HCI_MAX_SHORT_NAME_LENGTH] = '\0'; - - return eir_append_data(eir, eir_len, type, name, sizeof(name)); -} - u8 eir_append_local_name(struct hci_dev *hdev, u8 *ptr, u8 ad_len) { size_t short_len; size_t complete_len; - /* no space left for name (+ NULL + type + len) */ - if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 3) + /* no space left for name (+ type + len) */ + if ((max_adv_len(hdev) - ad_len) < HCI_MAX_SHORT_NAME_LENGTH + 2) return ad_len; /* use complete name if present and fits */ complete_len = strnlen(hdev->dev_name, sizeof(hdev->dev_name)); if (complete_len && complete_len <= HCI_MAX_SHORT_NAME_LENGTH) - return eir_append_name(ptr, ad_len, EIR_NAME_COMPLETE, - hdev->dev_name, complete_len + 1); + return eir_append_data(ptr, ad_len, EIR_NAME_COMPLETE, + hdev->dev_name, complete_len); /* use short name if present */ short_len = strnlen(hdev->short_name, sizeof(hdev->short_name)); if (short_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->short_name, - short_len == HCI_MAX_SHORT_NAME_LENGTH ? - short_len : short_len + 1); + short_len); /* use shortened full name if present, we already know that name * is longer then HCI_MAX_SHORT_NAME_LENGTH */ if (complete_len) - return eir_append_name(ptr, ad_len, EIR_NAME_SHORT, + return eir_append_data(ptr, ad_len, EIR_NAME_SHORT, hdev->dev_name, HCI_MAX_SHORT_NAME_LENGTH); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index a41d2693f4d8..3ad74f76983b 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1,7 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. - Copyright 2023 NXP + Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> @@ -36,7 +36,6 @@ #include "hci_request.h" #include "smp.h" -#include "a2mp.h" #include "eir.h" struct sco_param { @@ -69,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) +void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -179,64 +178,6 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_dev_put(hdev); } -static void hci_acl_create_connection(struct hci_conn *conn) -{ - struct hci_dev *hdev = conn->hdev; - struct inquiry_entry *ie; - struct hci_cp_create_conn cp; - - BT_DBG("hcon %p", conn); - - /* Many controllers disallow HCI Create Connection while it is doing - * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create - * Connection. This may cause the MGMT discovering state to become false - * without user space's request but it is okay since the MGMT Discovery - * APIs do not promise that discovery should be done forever. Instead, - * the user space monitors the status of MGMT discovering and it may - * request for discovery again when this flag becomes false. - */ - if (test_bit(HCI_INQUIRY, &hdev->flags)) { - /* Put this connection to "pending" state so that it will be - * executed after the inquiry cancel command complete event. - */ - conn->state = BT_CONNECT2; - hci_send_cmd(hdev, HCI_OP_INQUIRY_CANCEL, 0, NULL); - return; - } - - conn->state = BT_CONNECT; - conn->out = true; - conn->role = HCI_ROLE_MASTER; - - conn->attempt++; - - conn->link_policy = hdev->link_policy; - - memset(&cp, 0, sizeof(cp)); - bacpy(&cp.bdaddr, &conn->dst); - cp.pscan_rep_mode = 0x02; - - ie = hci_inquiry_cache_lookup(hdev, &conn->dst); - if (ie) { - if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { - cp.pscan_rep_mode = ie->data.pscan_rep_mode; - cp.pscan_mode = ie->data.pscan_mode; - cp.clock_offset = ie->data.clock_offset | - cpu_to_le16(0x8000); - } - - memcpy(conn->dev_class, ie->data.dev_class, 3); - } - - cp.pkt_type = cpu_to_le16(conn->pkt_type); - if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) - cp.role_switch = 0x01; - else - cp.role_switch = 0x00; - - hci_send_cmd(hdev, HCI_OP_CREATE_CONN, sizeof(cp), &cp); -} - int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); @@ -1175,9 +1116,6 @@ void hci_conn_del(struct hci_conn *conn) } } - if (conn->amp_mgr) - amp_mgr_put(conn->amp_mgr); - skb_queue_purge(&conn->data_q); /* Remove the connection from the list and cleanup its remaining @@ -1186,6 +1124,9 @@ void hci_conn_del(struct hci_conn *conn) * rest of hci_conn_del. */ hci_conn_cleanup(conn); + + /* Dequeue callbacks using connection pointer as data */ + hci_cmd_sync_dequeue(hdev, NULL, conn, NULL); } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) @@ -1320,53 +1261,6 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) return 0; } -static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return; - - bt_dev_dbg(hdev, "err %d", err); - - hci_dev_lock(hdev); - - if (!err) { - hci_connect_le_scan_cleanup(conn, 0x00); - goto done; - } - - /* Check if connection is still pending */ - if (conn != hci_lookup_le_connect(hdev)) - goto done; - - /* Flush to make sure we send create conn cancel command if needed */ - flush_delayed_work(&conn->le_conn_timeout); - hci_conn_failed(conn, bt_status(err)); - -done: - hci_dev_unlock(hdev); -} - -static int hci_connect_le_sync(struct hci_dev *hdev, void *data) -{ - struct hci_conn *conn; - u16 handle = PTR_UINT(data); - - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; - - bt_dev_dbg(hdev, "conn %p", conn); - - clear_bit(HCI_CONN_SCANNING, &conn->flags); - conn->state = BT_CONNECT; - - return hci_le_create_conn_sync(hdev, conn); -} - struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role) @@ -1433,9 +1327,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; - err = hci_cmd_sync_queue(hdev, hci_connect_le_sync, - UINT_PTR(conn->handle), - create_le_conn_complete); + err = hci_connect_le_sync(hdev, conn); if (err) { hci_conn_del(conn); return ERR_PTR(err); @@ -1669,7 +1561,7 @@ done: struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, - enum conn_reasons conn_reason) + enum conn_reasons conn_reason, u16 timeout) { struct hci_conn *acl; @@ -1700,10 +1592,18 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { + int err; + acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; acl->auth_type = auth_type; - hci_acl_create_connection(acl); + acl->conn_timeout = timeout; + + err = hci_connect_acl_sync(hdev, acl); + if (err) { + hci_conn_del(acl); + return ERR_PTR(err); + } } return acl; @@ -1738,14 +1638,15 @@ static struct hci_link *hci_conn_link(struct hci_conn *parent, } struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, - __u16 setting, struct bt_codec *codec) + __u16 setting, struct bt_codec *codec, + u16 timeout) { struct hci_conn *acl; struct hci_conn *sco; struct hci_link *link; acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, - CONN_REASON_SCO_CONNECT); + CONN_REASON_SCO_CONNECT, timeout); if (IS_ERR(acl)) return acl; @@ -2156,18 +2057,31 @@ static int create_pa_sync(struct hci_dev *hdev, void *data) return hci_update_passive_scan_sync(hdev); } -int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, - __u8 sid, struct bt_iso_qos *qos) +struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, + __u8 dst_type, __u8 sid, + struct bt_iso_qos *qos) { struct hci_cp_le_pa_create_sync *cp; + struct hci_conn *conn; + int err; if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC)) - return -EBUSY; + return ERR_PTR(-EBUSY); + + conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_SLAVE); + if (!conn) + return ERR_PTR(-ENOMEM); + + conn->iso_qos = *qos; + conn->state = BT_LISTEN; + + hci_conn_hold(conn); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) { hci_dev_clear_flag(hdev, HCI_PA_SYNC); - return -ENOMEM; + hci_conn_drop(conn); + return ERR_PTR(-ENOMEM); } cp->options = qos->bcast.options; @@ -2179,7 +2093,14 @@ int hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, cp->sync_cte_type = qos->bcast.sync_cte_type; /* Queue start pa_create_sync and scan */ - return hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + err = hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); + if (err < 0) { + hci_conn_drop(conn); + kfree(cp); + return ERR_PTR(err); + } + + return conn; } int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, @@ -2647,22 +2568,6 @@ void hci_conn_hash_flush(struct hci_dev *hdev) } } -/* Check pending connect attempts */ -void hci_conn_check_pending(struct hci_dev *hdev) -{ - struct hci_conn *conn; - - BT_DBG("hdev %s", hdev->name); - - hci_dev_lock(hdev); - - conn = hci_conn_hash_lookup_state(hdev, ACL_LINK, BT_CONNECT2); - if (conn) - hci_acl_create_connection(conn); - - hci_dev_unlock(hdev); -} - static u32 get_link_mode(struct hci_conn *conn) { u32 link_mode = 0; @@ -2978,12 +2883,10 @@ u32 hci_conn_get_phy(struct hci_conn *conn) static int abort_conn_sync(struct hci_dev *hdev, void *data) { - struct hci_conn *conn; - u16 handle = PTR_UINT(data); + struct hci_conn *conn = data; - conn = hci_conn_hash_lookup_handle(hdev, handle); - if (!conn) - return 0; + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } @@ -3011,14 +2914,17 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) */ if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { + case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: case HCI_EV_LE_ENHANCED_CONN_COMPLETE: case HCI_EVT_LE_CIS_ESTABLISHED: - hci_cmd_sync_cancel(hdev, -ECANCELED); + hci_cmd_sync_cancel(hdev, ECANCELED); break; } + /* Cancel connect attempt if still queued/pending */ + } else if (!hci_cancel_connect_sync(hdev, conn)) { + return 0; } - return hci_cmd_sync_queue(hdev, abort_conn_sync, UINT_PTR(conn->handle), - NULL); + return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2821a42cefdc..1690ae57a09d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -908,7 +908,7 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; @@ -940,20 +940,51 @@ int hci_get_dev_info(void __user *arg) /* ---- Interface to HCI drivers ---- */ +static int hci_dev_do_poweroff(struct hci_dev *hdev) +{ + int err; + + BT_DBG("%s %p", hdev->name, hdev); + + hci_req_sync_lock(hdev); + + err = hci_set_powered_sync(hdev, false); + + hci_req_sync_unlock(hdev); + + return err; +} + static int hci_rfkill_set_block(void *data, bool blocked) { struct hci_dev *hdev = data; + int err; BT_DBG("%p name %s blocked %d", hdev, hdev->name, blocked); if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) return -EBUSY; + if (blocked == hci_dev_test_flag(hdev, HCI_RFKILLED)) + return 0; + if (blocked) { hci_dev_set_flag(hdev, HCI_RFKILLED); + if (!hci_dev_test_flag(hdev, HCI_SETUP) && - !hci_dev_test_flag(hdev, HCI_CONFIG)) - hci_dev_do_close(hdev); + !hci_dev_test_flag(hdev, HCI_CONFIG)) { + err = hci_dev_do_poweroff(hdev); + if (err) { + bt_dev_err(hdev, "Error when powering off device on rfkill (%d)", + err); + + /* Make sure the device is still closed even if + * anything during power off sequence (eg. + * disconnecting devices) failed. + */ + hci_dev_do_close(hdev); + } + } } else { hci_dev_clear_flag(hdev, HCI_RFKILLED); } @@ -1491,11 +1522,12 @@ static void hci_cmd_timeout(struct work_struct *work) struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_timer.work); - if (hdev->sent_cmd) { - struct hci_command_hdr *sent = (void *) hdev->sent_cmd->data; - u16 opcode = __le16_to_cpu(sent->opcode); + if (hdev->req_skb) { + u16 opcode = hci_skb_opcode(hdev->req_skb); bt_dev_err(hdev, "command 0x%4.4x tx timeout", opcode); + + hci_cmd_sync_cancel_sync(hdev, ETIMEDOUT); } else { bt_dev_err(hdev, "command tx timeout"); } @@ -2608,10 +2640,11 @@ int hci_register_dev(struct hci_dev *hdev) */ switch (hdev->dev_type) { case HCI_PRIMARY: - id = ida_simple_get(&hci_index_ida, 0, HCI_MAX_ID, GFP_KERNEL); + id = ida_alloc_max(&hci_index_ida, HCI_MAX_ID - 1, GFP_KERNEL); break; case HCI_AMP: - id = ida_simple_get(&hci_index_ida, 1, HCI_MAX_ID, GFP_KERNEL); + id = ida_alloc_range(&hci_index_ida, 1, HCI_MAX_ID - 1, + GFP_KERNEL); break; default: return -EINVAL; @@ -2710,7 +2743,7 @@ err_wqueue: destroy_workqueue(hdev->workqueue); destroy_workqueue(hdev->req_workqueue); err: - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); return error; } @@ -2793,8 +2826,9 @@ void hci_release_dev(struct hci_dev *hdev) hci_dev_unlock(hdev); ida_destroy(&hdev->unset_handle_ida); - ida_simple_remove(&hci_index_ida, hdev->id); + ida_free(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); + kfree_skb(hdev->req_skb); kfree_skb(hdev->recv_event); kfree(hdev); } @@ -2826,6 +2860,23 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) return ret; } +/* Cancel ongoing command synchronously: + * + * - Cancel command timer + * - Reset command counter + * - Cancel command request + */ +static void hci_cancel_cmd_sync(struct hci_dev *hdev, int err) +{ + bt_dev_dbg(hdev, "err 0x%2.2x", err); + + cancel_delayed_work_sync(&hdev->cmd_timer); + cancel_delayed_work_sync(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + + hci_cmd_sync_cancel_sync(hdev, -err); +} + /* Suspend HCI device */ int hci_suspend_dev(struct hci_dev *hdev) { @@ -2843,7 +2894,7 @@ int hci_suspend_dev(struct hci_dev *hdev) return 0; /* Cancel potentially blocking sync operation before suspend */ - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cancel_cmd_sync(hdev, -EHOSTDOWN); hci_req_sync_lock(hdev); ret = hci_suspend_sync(hdev); @@ -3107,21 +3158,33 @@ int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, EXPORT_SYMBOL(__hci_cmd_send); /* Get data from the previously sent command */ -void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +static void *hci_cmd_data(struct sk_buff *skb, __u16 opcode) { struct hci_command_hdr *hdr; - if (!hdev->sent_cmd) + if (!skb || skb->len < HCI_COMMAND_HDR_SIZE) return NULL; - hdr = (void *) hdev->sent_cmd->data; + hdr = (void *)skb->data; if (hdr->opcode != cpu_to_le16(opcode)) return NULL; - BT_DBG("%s opcode 0x%4.4x", hdev->name, opcode); + return skb->data + HCI_COMMAND_HDR_SIZE; +} - return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; +/* Get data from the previously sent command */ +void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) +{ + void *data; + + /* Check if opcode matches last sent command */ + data = hci_cmd_data(hdev->sent_cmd, opcode); + if (!data) + /* Check if opcode matches last request */ + data = hci_cmd_data(hdev->req_skb, opcode); + + return data; } /* Get data from last received event */ @@ -4022,17 +4085,19 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, if (!status && !hci_req_is_complete(hdev)) return; + skb = hdev->req_skb; + /* If this was the last command in a request the complete - * callback would be found in hdev->sent_cmd instead of the + * callback would be found in hdev->req_skb instead of the * command queue (hdev->cmd_q). */ - if (bt_cb(hdev->sent_cmd)->hci.req_flags & HCI_REQ_SKB) { - *req_complete_skb = bt_cb(hdev->sent_cmd)->hci.req_complete_skb; + if (skb && bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) { + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; return; } - if (bt_cb(hdev->sent_cmd)->hci.req_complete) { - *req_complete = bt_cb(hdev->sent_cmd)->hci.req_complete; + if (skb && bt_cb(skb)->hci.req_complete) { + *req_complete = bt_cb(skb)->hci.req_complete; return; } @@ -4128,6 +4193,36 @@ static void hci_rx_work(struct work_struct *work) } } +static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) +{ + int err; + + bt_dev_dbg(hdev, "skb %p", skb); + + kfree_skb(hdev->sent_cmd); + + hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); + if (!hdev->sent_cmd) { + skb_queue_head(&hdev->cmd_q, skb); + queue_work(hdev->workqueue, &hdev->cmd_work); + return; + } + + err = hci_send_frame(hdev, skb); + if (err < 0) { + hci_cmd_sync_cancel_sync(hdev, err); + return; + } + + if (hci_req_status_pend(hdev) && + !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { + kfree_skb(hdev->req_skb); + hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); + } + + atomic_dec(&hdev->cmd_cnt); +} + static void hci_cmd_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_work); @@ -4142,30 +4237,15 @@ static void hci_cmd_work(struct work_struct *work) if (!skb) return; - kfree_skb(hdev->sent_cmd); - - hdev->sent_cmd = skb_clone(skb, GFP_KERNEL); - if (hdev->sent_cmd) { - int res; - if (hci_req_status_pend(hdev)) - hci_dev_set_flag(hdev, HCI_CMD_PENDING); - atomic_dec(&hdev->cmd_cnt); + hci_send_cmd_sync(hdev, skb); - res = hci_send_frame(hdev, skb); - if (res < 0) - __hci_cmd_sync_cancel(hdev, -res); - - rcu_read_lock(); - if (test_bit(HCI_RESET, &hdev->flags) || - hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) - cancel_delayed_work(&hdev->cmd_timer); - else - queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, - HCI_CMD_TIMEOUT); - rcu_read_unlock(); - } else { - skb_queue_head(&hdev->cmd_q, skb); - queue_work(hdev->workqueue, &hdev->cmd_work); - } + rcu_read_lock(); + if (test_bit(HCI_RESET, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) + cancel_delayed_work(&hdev->cmd_timer); + else + queue_delayed_work(hdev->workqueue, &hdev->cmd_timer, + HCI_CMD_TIMEOUT); + rcu_read_unlock(); } } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2a5f5a7d2412..4ae224824012 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -36,8 +36,6 @@ #include "hci_request.h" #include "hci_debugfs.h" #include "hci_codec.h" -#include "a2mp.h" -#include "amp.h" #include "smp.h" #include "msft.h" #include "eir.h" @@ -95,11 +93,11 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, /* It is possible that we receive Inquiry Complete event right * before we receive Inquiry Cancel Command Complete event, in * which case the latter event should have status of Command - * Disallowed (0x0c). This should not be treated as error, since + * Disallowed. This should not be treated as error, since * we actually achieve what Inquiry Cancel wants to achieve, * which is to end the last Inquiry session. */ - if (rp->status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + if (rp->status == HCI_ERROR_COMMAND_DISALLOWED && !test_bit(HCI_INQUIRY, &hdev->flags)) { bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); rp->status = 0x00; } @@ -120,8 +118,6 @@ static u8 hci_cc_inquiry_cancel(struct hci_dev *hdev, void *data, hci_discovery_set_state(hdev, DISCOVERY_STOPPED); hci_dev_unlock(hdev); - hci_conn_check_pending(hdev); - return rp->status; } @@ -152,8 +148,6 @@ static u8 hci_cc_exit_periodic_inq(struct hci_dev *hdev, void *data, hci_dev_clear_flag(hdev, HCI_PERIODIC_INQ); - hci_conn_check_pending(hdev); - return rp->status; } @@ -2314,10 +2308,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { bt_dev_dbg(hdev, "status 0x%2.2x", status); - if (status) { - hci_conn_check_pending(hdev); + if (status) return; - } if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) set_bit(HCI_INQUIRY, &hdev->flags); @@ -2342,12 +2334,9 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) if (status) { if (conn && conn->state == BT_CONNECT) { - if (status != 0x0c || conn->attempt > 2) { - conn->state = BT_CLOSED; - hci_connect_cfm(conn, status); - hci_conn_del(conn); - } else - conn->state = BT_CONNECT2; + conn->state = BT_CLOSED; + hci_connect_cfm(conn, status); + hci_conn_del(conn); } } else { if (!conn) { @@ -2526,9 +2515,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, * Only those in BT_CONFIG or BT_CONNECTED states can be * considered connected. */ - if (conn && - (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) && - !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED)) mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) @@ -3039,8 +3026,6 @@ static void hci_inquiry_complete_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags)) return; @@ -3262,8 +3247,6 @@ done: unlock: hci_dev_unlock(hdev); - - hci_conn_check_pending(hdev); } static void hci_reject_conn(struct hci_dev *hdev, bdaddr_t *bdaddr) @@ -3556,8 +3539,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -3660,7 +3641,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, * controller really supports it. If it doesn't, assume * the default size (16). */ - if (!(hdev->commands[20] & 0x10)) { + if (!(hdev->commands[20] & 0x10) || + test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) { conn->enc_key_size = HCI_LINK_KEY_SIZE; goto notify; } @@ -3762,8 +3744,9 @@ static void hci_remote_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); - } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -3936,6 +3919,11 @@ static u8 hci_cc_le_setup_iso_path(struct hci_dev *hdev, void *data, * last. */ hci_connect_cfm(conn, rp->status); + + /* Notify device connected in case it is a BIG Sync */ + if (!rp->status && test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) + mgmt_device_connected(hdev, conn, NULL, 0); + break; } @@ -4381,7 +4369,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, void *data, * (since for this kind of commands there will not be a command * complete event). */ - if (ev->status || (hdev->sent_cmd && !hci_skb_event(hdev->sent_cmd))) { + if (ev->status || (hdev->req_skb && !hci_skb_event(hdev->req_skb))) { hci_req_cmd_complete(hdev, *opcode, ev->status, req_complete, req_complete_skb); if (hci_dev_test_flag(hdev, HCI_CMD_PENDING)) { @@ -5010,8 +4998,9 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, void *data, bacpy(&cp.bdaddr, &conn->dst); cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); - } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + } else { mgmt_device_connected(hdev, conn, NULL, 0); + } if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -5675,150 +5664,6 @@ unlock: hci_dev_unlock(hdev); } -#if IS_ENABLED(CONFIG_BT_HS) -static void hci_chan_selected_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_channel_selected *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x", ev->phy_handle); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - amp_read_loc_assoc_final_data(hdev, hcon); -} - -static void hci_phy_link_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_phy_link_complete *ev = data; - struct hci_conn *hcon, *bredr_hcon; - - bt_dev_dbg(hdev, "handle 0x%2.2x status 0x%2.2x", ev->phy_handle, - ev->status); - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - goto unlock; - - if (!hcon->amp_mgr) - goto unlock; - - if (ev->status) { - hci_conn_del(hcon); - goto unlock; - } - - bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon; - - hcon->state = BT_CONNECTED; - bacpy(&hcon->dst, &bredr_hcon->dst); - - hci_conn_hold(hcon); - hcon->disc_timeout = HCI_DISCONN_TIMEOUT; - hci_conn_drop(hcon); - - hci_debugfs_create_conn(hcon); - hci_conn_add_sysfs(hcon); - - amp_physical_cfm(bredr_hcon, hcon); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_logical_link_complete *ev = data; - struct hci_conn *hcon; - struct hci_chan *hchan; - struct amp_mgr *mgr; - - bt_dev_dbg(hdev, "log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->phy_handle, ev->status); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (!hcon) - return; - - /* Create AMP hchan */ - hchan = hci_chan_create(hcon); - if (!hchan) - return; - - hchan->handle = le16_to_cpu(ev->handle); - hchan->amp = true; - - BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); - - mgr = hcon->amp_mgr; - if (mgr && mgr->bredr_chan) { - struct l2cap_chan *bredr_chan = mgr->bredr_chan; - - l2cap_chan_lock(bredr_chan); - - bredr_chan->conn->mtu = hdev->block_mtu; - l2cap_logical_cfm(bredr_chan, hchan, 0); - hci_conn_hold(hcon); - - l2cap_chan_unlock(bredr_chan); - } -} - -static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_logical_link_complete *ev = data; - struct hci_chan *hchan; - - bt_dev_dbg(hdev, "handle 0x%4.4x status 0x%2.2x", - le16_to_cpu(ev->handle), ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); - if (!hchan || !hchan->amp) - goto unlock; - - amp_destroy_logical_link(hchan, ev->reason); - -unlock: - hci_dev_unlock(hdev); -} - -static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_ev_disconn_phy_link_complete *ev = data; - struct hci_conn *hcon; - - bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); - - if (ev->status) - return; - - hci_dev_lock(hdev); - - hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); - if (hcon && hcon->type == AMP_LINK) { - hcon->state = BT_CLOSED; - hci_disconn_cfm(hcon, ev->reason); - hci_conn_del(hcon); - } - - hci_dev_unlock(hdev); -} -#endif - static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *local_rpa) { @@ -5984,8 +5829,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, goto unlock; } - if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->state = BT_CONFIG; @@ -6684,7 +6528,7 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, void *data, * transition into connected state and mark it as * successful. */ - if (!conn->out && ev->status == 0x1a && + if (!conn->out && ev->status == HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE && (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else @@ -7214,6 +7058,9 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, /* Notify iso layer */ hci_connect_cfm(pa_sync, 0x00); + /* Notify MGMT layer */ + mgmt_device_connected(hdev, pa_sync, NULL, 0); + unlock: hci_dev_unlock(hdev); } @@ -7324,10 +7171,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "subevent 0x%2.2x", ev->subevent); /* Only match event if command OGF is for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) == 0x08 && - hci_skb_event(hdev->sent_cmd) == ev->subevent) { - *opcode = hci_skb_opcode(hdev->sent_cmd); + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) == 0x08 && + hci_skb_event(hdev->req_skb) == ev->subevent) { + *opcode = hci_skb_opcode(hdev->req_skb); hci_req_cmd_complete(hdev, *opcode, 0x00, req_complete, req_complete_skb); } @@ -7626,25 +7473,6 @@ static const struct hci_ev { /* [0x3e = HCI_EV_LE_META] */ HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), -#if IS_ENABLED(CONFIG_BT_HS) - /* [0x40 = HCI_EV_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_PHY_LINK_COMPLETE, hci_phy_link_complete_evt, - sizeof(struct hci_ev_phy_link_complete)), - /* [0x41 = HCI_EV_CHANNEL_SELECTED] */ - HCI_EV(HCI_EV_CHANNEL_SELECTED, hci_chan_selected_evt, - sizeof(struct hci_ev_channel_selected)), - /* [0x42 = HCI_EV_DISCONN_PHY_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE, - hci_disconn_loglink_complete_evt, - sizeof(struct hci_ev_disconn_logical_link_complete)), - /* [0x45 = HCI_EV_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_LOGICAL_LINK_COMPLETE, hci_loglink_complete_evt, - sizeof(struct hci_ev_logical_link_complete)), - /* [0x46 = HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE] */ - HCI_EV(HCI_EV_DISCONN_PHY_LINK_COMPLETE, - hci_disconn_phylink_complete_evt, - sizeof(struct hci_ev_disconn_phy_link_complete)), -#endif /* [0x48 = HCI_EV_NUM_COMP_BLOCKS] */ HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, sizeof(struct hci_ev_num_comp_blocks)), @@ -7714,10 +7542,10 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) } /* Only match event if command OGF is not for LE */ - if (hdev->sent_cmd && - hci_opcode_ogf(hci_skb_opcode(hdev->sent_cmd)) != 0x08 && - hci_skb_event(hdev->sent_cmd) == event) { - hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->sent_cmd), + if (hdev->req_skb && + hci_opcode_ogf(hci_skb_opcode(hdev->req_skb)) != 0x08 && + hci_skb_event(hdev->req_skb) == event) { + hci_req_cmd_complete(hdev, hci_skb_opcode(hdev->req_skb), status, &req_complete, &req_complete_skb); req_evt = event; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 6e023b0104b0..00e02138003e 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -895,7 +895,7 @@ void hci_request_setup(struct hci_dev *hdev) void hci_request_cancel_all(struct hci_dev *hdev) { - __hci_cmd_sync_cancel(hdev, ENODEV); + hci_cmd_sync_cancel_sync(hdev, ENODEV); cancel_interleave_scan(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 3e7cd330d731..4ee1b976678b 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -101,7 +101,7 @@ static bool hci_sock_gen_cookie(struct sock *sk) int id = hci_pi(sk)->cookie; if (!id) { - id = ida_simple_get(&sock_cookie_ida, 1, 0, GFP_KERNEL); + id = ida_alloc_min(&sock_cookie_ida, 1, GFP_KERNEL); if (id < 0) id = 0xffffffff; @@ -119,7 +119,7 @@ static void hci_sock_free_cookie(struct sock *sk) if (id) { hci_pi(sk)->cookie = 0xffffffff; - ida_simple_remove(&sock_cookie_ida, id); + ida_free(&sock_cookie_ida, id); } } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5716345a26df..f6b662369322 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -32,6 +32,10 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; + /* Free the request command so it is not used as response */ + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + if (skb) { struct sock *sk = hci_skb_sk(skb); @@ -39,7 +43,7 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (sk) sock_put(sk); - hdev->req_skb = skb_get(skb); + hdev->req_rsp = skb_get(skb); } wake_up_interruptible(&hdev->req_wait_q); @@ -187,8 +191,8 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, hdev->req_status = 0; hdev->req_result = 0; - skb = hdev->req_skb; - hdev->req_skb = NULL; + skb = hdev->req_rsp; + hdev->req_rsp = NULL; bt_dev_dbg(hdev, "end: err %d", err); @@ -566,6 +570,17 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire); } +static void _hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry, + int err) +{ + if (entry->destroy) + entry->destroy(hdev, entry->data, err); + + list_del(&entry->list); + kfree(entry); +} + void hci_cmd_sync_clear(struct hci_dev *hdev) { struct hci_cmd_sync_work_entry *entry, *tmp; @@ -574,17 +589,12 @@ void hci_cmd_sync_clear(struct hci_dev *hdev) cancel_work_sync(&hdev->reenable_adv_work); mutex_lock(&hdev->cmd_sync_work_lock); - list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { - if (entry->destroy) - entry->destroy(hdev, entry->data, -ECANCELED); - - list_del(&entry->list); - kfree(entry); - } + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); mutex_unlock(&hdev->cmd_sync_work_lock); } -void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -592,15 +602,17 @@ void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - cancel_delayed_work_sync(&hdev->cmd_timer); - cancel_delayed_work_sync(&hdev->ncmd_timer); - atomic_set(&hdev->cmd_cnt, 1); - - wake_up_interruptible(&hdev->req_wait_q); + queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); } } +EXPORT_SYMBOL(hci_cmd_sync_cancel); -void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) +/* Cancel ongoing command request synchronously: + * + * - Set result and mark status to HCI_REQ_CANCELED + * - Wakeup command sync thread + */ +void hci_cmd_sync_cancel_sync(struct hci_dev *hdev, int err) { bt_dev_dbg(hdev, "err 0x%2.2x", err); @@ -608,10 +620,10 @@ void hci_cmd_sync_cancel(struct hci_dev *hdev, int err) hdev->req_result = err; hdev->req_status = HCI_REQ_CANCELED; - queue_work(hdev->workqueue, &hdev->cmd_sync_cancel_work); + wake_up_interruptible(&hdev->req_wait_q); } } -EXPORT_SYMBOL(hci_cmd_sync_cancel); +EXPORT_SYMBOL(hci_cmd_sync_cancel_sync); /* Submit HCI command to be run in as cmd_sync_work: * @@ -667,6 +679,115 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue); +static struct hci_cmd_sync_work_entry * +_hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->cmd_sync_work_list, list) { + if (func && entry->func != func) + continue; + + if (data && entry->data != data) + continue; + + if (destroy && entry->destroy != destroy) + continue; + + return entry; + } + + return NULL; +} + +/* Queue HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and queue it. + */ +int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_queue(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_queue_once); + +/* Lookup HCI command entry: + * + * - Return first entry that matches by function callback or data or + * destroy callback. + */ +struct hci_cmd_sync_work_entry * +hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + mutex_lock(&hdev->cmd_sync_work_lock); + entry = _hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + mutex_unlock(&hdev->cmd_sync_work_lock); + + return entry; +} +EXPORT_SYMBOL(hci_cmd_sync_lookup_entry); + +/* Cancel HCI command entry */ +void hci_cmd_sync_cancel_entry(struct hci_dev *hdev, + struct hci_cmd_sync_work_entry *entry) +{ + mutex_lock(&hdev->cmd_sync_work_lock); + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + mutex_unlock(&hdev->cmd_sync_work_lock); +} +EXPORT_SYMBOL(hci_cmd_sync_cancel_entry); + +/* Dequeue one HCI command entry: + * + * - Lookup and cancel first entry that matches. + */ +bool hci_cmd_sync_dequeue_once(struct hci_dev *hdev, + hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + + entry = hci_cmd_sync_lookup_entry(hdev, func, data, destroy); + if (!entry) + return false; + + hci_cmd_sync_cancel_entry(hdev, entry); + + return true; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue_once); + +/* Dequeue HCI command entry: + * + * - Lookup and cancel any entry that matches by function callback or data or + * destroy callback. + */ +bool hci_cmd_sync_dequeue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + struct hci_cmd_sync_work_entry *entry; + bool ret = false; + + mutex_lock(&hdev->cmd_sync_work_lock); + while ((entry = _hci_cmd_sync_lookup_entry(hdev, func, data, + destroy))) { + _hci_cmd_sync_cancel_entry(hdev, entry, -ECANCELED); + ret = true; + } + mutex_unlock(&hdev->cmd_sync_work_lock); + + return ret; +} +EXPORT_SYMBOL(hci_cmd_sync_dequeue); + int hci_update_eir_sync(struct hci_dev *hdev) { struct hci_cp_write_eir cp; @@ -2445,6 +2566,16 @@ static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) return p; } +/* Clear LE Accept List */ +static int hci_le_clear_accept_list_sync(struct hci_dev *hdev) +{ + if (!(hdev->commands[26] & 0x80)) + return 0; + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL, + HCI_CMD_TIMEOUT); +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2493,6 +2624,31 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) goto done; } + /* Force address filtering if PA Sync is in progress */ + if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { + struct hci_cp_le_pa_create_sync *sent; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_PA_CREATE_SYNC); + if (sent) { + struct conn_params pa; + + memset(&pa, 0, sizeof(pa)); + + bacpy(&pa.addr, &sent->addr); + pa.addr_type = sent->addr_type; + + /* Clear first since there could be addresses left + * behind. + */ + hci_le_clear_accept_list_sync(hdev); + + num_entries = 1; + err = hci_le_add_accept_list_sync(hdev, &pa, + &num_entries); + goto done; + } + } + /* Go through the current accept list programmed into the * controller one by one and check if that address is connected or is * still in the list of pending connections or list of devices to @@ -2602,6 +2758,14 @@ done: return filter_policy; } +static void hci_le_scan_phy_params(struct hci_cp_le_scan_phy_params *cp, + u8 type, u16 interval, u16 window) +{ + cp->type = type; + cp->interval = cpu_to_le16(interval); + cp->window = cpu_to_le16(window); +} + static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy) @@ -2609,7 +2773,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, struct hci_cp_le_set_ext_scan_params *cp; struct hci_cp_le_scan_phy_params *phy; u8 data[sizeof(*cp) + sizeof(*phy) * 2]; - u8 num_phy = 0; + u8 num_phy = 0x00; cp = (void *)data; phy = (void *)cp->data; @@ -2619,28 +2783,64 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type, cp->own_addr_type = own_addr_type; cp->filter_policy = filter_policy; + /* Check if PA Sync is in progress then select the PHY based on the + * hci_conn.iso_qos. + */ + if (hci_dev_test_flag(hdev, HCI_PA_SYNC)) { + struct hci_cp_le_add_to_accept_list *sent; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); + if (sent) { + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_ba(hdev, ISO_LINK, + &sent->bdaddr); + if (conn) { + struct bt_iso_qos *qos = &conn->iso_qos; + + if (qos->bcast.in.phy & BT_ISO_PHY_1M || + qos->bcast.in.phy & BT_ISO_PHY_2M) { + cp->scanning_phys |= LE_SCAN_PHY_1M; + hci_le_scan_phy_params(phy, type, + interval, + window); + num_phy++; + phy++; + } + + if (qos->bcast.in.phy & BT_ISO_PHY_CODED) { + cp->scanning_phys |= LE_SCAN_PHY_CODED; + hci_le_scan_phy_params(phy, type, + interval, + window); + num_phy++; + phy++; + } + + if (num_phy) + goto done; + } + } + } + if (scan_1m(hdev) || scan_2m(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_1M; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval, window); num_phy++; phy++; } if (scan_coded(hdev)) { cp->scanning_phys |= LE_SCAN_PHY_CODED; - - phy->type = type; - phy->interval = cpu_to_le16(interval); - phy->window = cpu_to_le16(window); - + hci_le_scan_phy_params(phy, type, interval, window); num_phy++; phy++; } +done: + if (!num_phy) + return -EINVAL; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS, sizeof(*cp) + sizeof(*phy) * num_phy, data, HCI_CMD_TIMEOUT); @@ -2879,7 +3079,8 @@ int hci_update_passive_scan(struct hci_dev *hdev) hci_dev_test_flag(hdev, HCI_UNREGISTER)) return 0; - return hci_cmd_sync_queue(hdev, update_passive_scan_sync, NULL, NULL); + return hci_cmd_sync_queue_once(hdev, update_passive_scan_sync, NULL, + NULL); } int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val) @@ -4098,16 +4299,6 @@ static int hci_le_read_accept_list_size_sync(struct hci_dev *hdev) 0, NULL, HCI_CMD_TIMEOUT); } -/* Clear LE Accept List */ -static int hci_le_clear_accept_list_sync(struct hci_dev *hdev) -{ - if (!(hdev->commands[26] & 0x80)) - return 0; - - return __hci_cmd_sync_status(hdev, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL, - HCI_CMD_TIMEOUT); -} - /* Read LE Resolving List Size */ static int hci_le_read_resolv_list_size_sync(struct hci_dev *hdev) { @@ -4834,6 +5025,11 @@ int hci_dev_open_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -4994,6 +5190,12 @@ int hci_dev_close_sync(struct hci_dev *hdev) hdev->sent_cmd = NULL; } + /* Drop last request */ + if (hdev->req_skb) { + kfree_skb(hdev->req_skb); + hdev->req_skb = NULL; + } + clear_bit(HCI_RUNNING, &hdev->flags); hci_sock_dev_event(hdev, HCI_DEV_CLOSE); @@ -5403,27 +5605,33 @@ static int hci_power_off_sync(struct hci_dev *hdev) if (!test_bit(HCI_UP, &hdev->flags)) return 0; + hci_dev_set_flag(hdev, HCI_POWERING_DOWN); + if (test_bit(HCI_ISCAN, &hdev->flags) || test_bit(HCI_PSCAN, &hdev->flags)) { err = hci_write_scan_enable_sync(hdev, 0x00); if (err) - return err; + goto out; } err = hci_clear_adv_sync(hdev, NULL, false); if (err) - return err; + goto out; err = hci_stop_discovery_sync(hdev); if (err) - return err; + goto out; /* Terminated due to Power Off */ err = hci_disconnect_all_sync(hdev, HCI_ERROR_REMOTE_POWER_OFF); if (err) - return err; + goto out; + + err = hci_dev_close_sync(hdev); - return hci_dev_close_sync(hdev); +out: + hci_dev_clear_flag(hdev, HCI_POWERING_DOWN); + return err; } int hci_set_powered_sync(struct hci_dev *hdev, u8 val) @@ -6161,12 +6369,21 @@ static int hci_le_ext_create_conn_sync(struct hci_dev *hdev, conn->conn_timeout, NULL); } -int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) +static int hci_le_create_conn_sync(struct hci_dev *hdev, void *data) { struct hci_cp_le_create_conn cp; struct hci_conn_params *params; u8 own_addr_type; int err; + struct hci_conn *conn = data; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + bt_dev_dbg(hdev, "conn %p", conn); + + clear_bit(HCI_CONN_SCANNING, &conn->flags); + conn->state = BT_CONNECT; /* If requested to connect as peripheral use directed advertising */ if (conn->role == HCI_ROLE_SLAVE) { @@ -6484,3 +6701,125 @@ int hci_update_adv_data(struct hci_dev *hdev, u8 instance) return hci_cmd_sync_queue(hdev, _update_adv_data_sync, UINT_PTR(instance), NULL); } + +static int hci_acl_create_conn_sync(struct hci_dev *hdev, void *data) +{ + struct hci_conn *conn = data; + struct inquiry_entry *ie; + struct hci_cp_create_conn cp; + int err; + + if (!hci_conn_valid(hdev, conn)) + return -ECANCELED; + + /* Many controllers disallow HCI Create Connection while it is doing + * HCI Inquiry. So we cancel the Inquiry first before issuing HCI Create + * Connection. This may cause the MGMT discovering state to become false + * without user space's request but it is okay since the MGMT Discovery + * APIs do not promise that discovery should be done forever. Instead, + * the user space monitors the status of MGMT discovering and it may + * request for discovery again when this flag becomes false. + */ + if (test_bit(HCI_INQUIRY, &hdev->flags)) { + err = __hci_cmd_sync_status(hdev, HCI_OP_INQUIRY_CANCEL, 0, + NULL, HCI_CMD_TIMEOUT); + if (err) + bt_dev_warn(hdev, "Failed to cancel inquiry %d", err); + } + + conn->state = BT_CONNECT; + conn->out = true; + conn->role = HCI_ROLE_MASTER; + + conn->attempt++; + + conn->link_policy = hdev->link_policy; + + memset(&cp, 0, sizeof(cp)); + bacpy(&cp.bdaddr, &conn->dst); + cp.pscan_rep_mode = 0x02; + + ie = hci_inquiry_cache_lookup(hdev, &conn->dst); + if (ie) { + if (inquiry_entry_age(ie) <= INQUIRY_ENTRY_AGE_MAX) { + cp.pscan_rep_mode = ie->data.pscan_rep_mode; + cp.pscan_mode = ie->data.pscan_mode; + cp.clock_offset = ie->data.clock_offset | + cpu_to_le16(0x8000); + } + + memcpy(conn->dev_class, ie->data.dev_class, 3); + } + + cp.pkt_type = cpu_to_le16(conn->pkt_type); + if (lmp_rswitch_capable(hdev) && !(hdev->link_mode & HCI_LM_MASTER)) + cp.role_switch = 0x01; + else + cp.role_switch = 0x00; + + return __hci_cmd_sync_status_sk(hdev, HCI_OP_CREATE_CONN, + sizeof(cp), &cp, + HCI_EV_CONN_COMPLETE, + conn->conn_timeout, NULL); +} + +int hci_connect_acl_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_acl_create_conn_sync, conn, + NULL); +} + +static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) +{ + struct hci_conn *conn = data; + + bt_dev_dbg(hdev, "err %d", err); + + if (err == -ECANCELED) + return; + + hci_dev_lock(hdev); + + if (!hci_conn_valid(hdev, conn)) + goto done; + + if (!err) { + hci_connect_le_scan_cleanup(conn, 0x00); + goto done; + } + + /* Check if connection is still pending */ + if (conn != hci_lookup_le_connect(hdev)) + goto done; + + /* Flush to make sure we send create conn cancel command if needed */ + flush_delayed_work(&conn->le_conn_timeout); + hci_conn_failed(conn, bt_status(err)); + +done: + hci_dev_unlock(hdev); +} + +int hci_connect_le_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + return hci_cmd_sync_queue_once(hdev, hci_le_create_conn_sync, conn, + create_le_conn_complete); +} + +int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) +{ + if (conn->state != BT_OPEN) + return -EINVAL; + + switch (conn->type) { + case ACL_LINK: + return !hci_cmd_sync_dequeue_once(hdev, + hci_acl_create_conn_sync, + conn, NULL); + case LE_LINK: + return !hci_cmd_sync_dequeue_once(hdev, hci_le_create_conn_sync, + conn, create_le_conn_complete); + } + + return -ENOENT; +} diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 04f6572d35f1..c8793e57f4b5 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -3,7 +3,7 @@ * BlueZ - Bluetooth protocol stack for Linux * * Copyright (C) 2022 Intel Corporation - * Copyright 2023 NXP + * Copyright 2023-2024 NXP */ #include <linux/module.h> @@ -690,11 +690,8 @@ static void iso_sock_cleanup_listen(struct sock *parent) iso_sock_kill(sk); } - /* If listening socket stands for a PA sync connection, - * properly disconnect the hcon and socket. - */ - if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon && - test_bit(HCI_CONN_PA_SYNC, &iso_pi(parent)->conn->hcon->flags)) { + /* If listening socket has a hcon, properly disconnect it */ + if (iso_pi(parent)->conn && iso_pi(parent)->conn->hcon) { iso_sock_disconn(parent); return; } @@ -837,10 +834,10 @@ static struct bt_iso_qos default_qos = { .bcode = {0x00}, .options = 0x00, .skip = 0x0000, - .sync_timeout = 0x4000, + .sync_timeout = BT_ISO_SYNC_TIMEOUT, .sync_cte_type = 0x00, .mse = 0x00, - .timeout = 0x4000, + .timeout = BT_ISO_SYNC_TIMEOUT, }, }; @@ -1076,6 +1073,8 @@ static int iso_listen_bis(struct sock *sk) { struct hci_dev *hdev; int err = 0; + struct iso_conn *conn; + struct hci_conn *hcon; BT_DBG("%pMR -> %pMR (SID 0x%2.2x)", &iso_pi(sk)->src, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid); @@ -1096,18 +1095,40 @@ static int iso_listen_bis(struct sock *sk) if (!hdev) return -EHOSTUNREACH; + hci_dev_lock(hdev); + /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { iso_pi(sk)->qos = default_qos; - return -EINVAL; + err = -EINVAL; + goto unlock; + } + + hcon = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, + le_addr_type(iso_pi(sk)->dst_type), + iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; } - err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, - le_addr_type(iso_pi(sk)->dst_type), - iso_pi(sk)->bc_sid, &iso_pi(sk)->qos); + conn = iso_conn_add(hcon); + if (!conn) { + hci_conn_drop(hcon); + err = -ENOMEM; + goto unlock; + } + + err = iso_chan_add(conn, sk, NULL); + if (err) { + hci_conn_drop(hcon); + goto unlock; + } hci_dev_put(hdev); +unlock: + hci_dev_unlock(hdev); return err; } @@ -1889,7 +1910,6 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) struct hci_evt_le_big_info_adv_report *ev2; struct hci_ev_le_per_adv_report *ev3; struct sock *sk; - int lm = 0; bt_dev_dbg(hdev, "bdaddr %pMR", bdaddr); @@ -1933,7 +1953,7 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) if (sk && test_bit(BT_SK_PA_SYNC_TERM, &iso_pi(sk)->flags)) - return lm; + return 0; } if (sk) { @@ -1961,16 +1981,58 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { - size_t base_len = ev3->length; + size_t base_len = 0; u8 *base; + struct hci_conn *hcon; sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sync_handle_pa_report, ev3); - base = eir_get_service_data(ev3->data, ev3->length, - EIR_BAA_SERVICE_UUID, &base_len); - if (base && sk && base_len <= sizeof(iso_pi(sk)->base)) { + if (!sk) + goto done; + + hcon = iso_pi(sk)->conn->hcon; + if (!hcon) + goto done; + + if (ev3->data_status == LE_PA_DATA_TRUNCATED) { + /* The controller was unable to retrieve PA data. */ + memset(hcon->le_per_adv_data, 0, + HCI_MAX_PER_AD_TOT_LEN); + hcon->le_per_adv_data_len = 0; + hcon->le_per_adv_data_offset = 0; + goto done; + } + + if (hcon->le_per_adv_data_offset + ev3->length > + HCI_MAX_PER_AD_TOT_LEN) + goto done; + + memcpy(hcon->le_per_adv_data + hcon->le_per_adv_data_offset, + ev3->data, ev3->length); + hcon->le_per_adv_data_offset += ev3->length; + + if (ev3->data_status == LE_PA_DATA_COMPLETE) { + /* All PA data has been received. */ + hcon->le_per_adv_data_len = + hcon->le_per_adv_data_offset; + hcon->le_per_adv_data_offset = 0; + + /* Extract BASE */ + base = eir_get_service_data(hcon->le_per_adv_data, + hcon->le_per_adv_data_len, + EIR_BAA_SERVICE_UUID, + &base_len); + + if (!base || base_len > BASE_MAX_LENGTH) + goto done; + memcpy(iso_pi(sk)->base, base, base_len); iso_pi(sk)->base_len = base_len; + } else { + /* This is a PA data fragment. Keep pa_data_len set to 0 + * until all data has been reassembled. + */ + hcon->le_per_adv_data_len = 0; } } else { sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); @@ -1978,16 +2040,14 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) done: if (!sk) - return lm; - - lm |= HCI_LM_ACCEPT; + return 0; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; sock_put(sk); - return lm; + return HCI_LM_ACCEPT; } static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 656f49b299d2..467b242d8be0 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -39,8 +39,6 @@ #include <net/bluetooth/l2cap.h> #include "smp.h" -#include "a2mp.h" -#include "amp.h" #define LE_FLOWCTL_MAX_CREDITS 65535 @@ -167,24 +165,6 @@ static struct l2cap_chan *__l2cap_get_chan_by_ident(struct l2cap_conn *conn, return NULL; } -static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, - u8 ident) -{ - struct l2cap_chan *c; - - mutex_lock(&conn->chan_lock); - c = __l2cap_get_chan_by_ident(conn, ident); - if (c) { - /* Only lock if chan reference is not 0 */ - c = l2cap_chan_hold_unless_zero(c); - if (c) - l2cap_chan_lock(c); - } - mutex_unlock(&conn->chan_lock); - - return c; -} - static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src, u8 src_type) { @@ -651,7 +631,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) chan->ops->teardown(chan, err); if (conn) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; /* Delete from channel list */ list_del(&chan->list); @@ -666,16 +645,6 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) if (chan->chan_type != L2CAP_CHAN_FIXED || test_bit(FLAG_HOLD_HCI_CONN, &chan->flags)) hci_conn_drop(conn->hcon); - - if (mgr && mgr->bredr_chan == chan) - mgr->bredr_chan = NULL; - } - - if (chan->hs_hchan) { - struct hci_chan *hs_hchan = chan->hs_hchan; - - BT_DBG("chan %p disconnect hs_hchan %p", chan, hs_hchan); - amp_disconnect_logical_link(hs_hchan); } if (test_bit(CONF_NOT_COMPLETE, &chan->conf_state)) @@ -977,12 +946,6 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, hci_send_acl(conn->hchan, skb, flags); } -static bool __chan_is_moving(struct l2cap_chan *chan) -{ - return chan->move_state != L2CAP_MOVE_STABLE && - chan->move_state != L2CAP_MOVE_WAIT_PREPARE; -} - static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) { struct hci_conn *hcon = chan->conn->hcon; @@ -991,15 +954,6 @@ static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) BT_DBG("chan %p, skb %p len %d priority %u", chan, skb, skb->len, skb->priority); - if (chan->hs_hcon && !__chan_is_moving(chan)) { - if (chan->hs_hchan) - hci_send_acl(chan->hs_hchan, skb, ACL_COMPLETE); - else - kfree_skb(skb); - - return; - } - /* Use NO_FLUSH for LE links (where this is the only option) or * if the BR/EDR link supports it and flushing has not been * explicitly requested (through FLAG_FLUSHABLE). @@ -1180,9 +1134,6 @@ static void l2cap_send_sframe(struct l2cap_chan *chan, if (!control->sframe) return; - if (__chan_is_moving(chan)) - return; - if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state) && !control->poll) control->final = 1; @@ -1237,40 +1188,6 @@ static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) return !test_bit(CONF_CONNECT_PEND, &chan->conf_state); } -static bool __amp_capable(struct l2cap_chan *chan) -{ - struct l2cap_conn *conn = chan->conn; - struct hci_dev *hdev; - bool amp_available = false; - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return false; - - if (!(conn->remote_fixed_chan & L2CAP_FC_A2MP)) - return false; - - read_lock(&hci_dev_list_lock); - list_for_each_entry(hdev, &hci_dev_list, list) { - if (hdev->amp_type != AMP_TYPE_BREDR && - test_bit(HCI_UP, &hdev->flags)) { - amp_available = true; - break; - } - } - read_unlock(&hci_dev_list_lock); - - if (chan->chan_policy == BT_CHANNEL_POLICY_AMP_PREFERRED) - return amp_available; - - return false; -} - -static bool l2cap_check_efs(struct l2cap_chan *chan) -{ - /* Check EFS parameters */ - return true; -} - void l2cap_send_conn_req(struct l2cap_chan *chan) { struct l2cap_conn *conn = chan->conn; @@ -1286,76 +1203,6 @@ void l2cap_send_conn_req(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); } -static void l2cap_send_create_chan_req(struct l2cap_chan *chan, u8 amp_id) -{ - struct l2cap_create_chan_req req; - req.scid = cpu_to_le16(chan->scid); - req.psm = chan->psm; - req.amp_id = amp_id; - - chan->ident = l2cap_get_ident(chan->conn); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_REQ, - sizeof(req), &req); -} - -static void l2cap_move_setup(struct l2cap_chan *chan) -{ - struct sk_buff *skb; - - BT_DBG("chan %p", chan); - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - __clear_retrans_timer(chan); - __clear_monitor_timer(chan); - __clear_ack_timer(chan); - - chan->retry_count = 0; - skb_queue_walk(&chan->tx_q, skb) { - if (bt_cb(skb)->l2cap.retries) - bt_cb(skb)->l2cap.retries = 1; - else - break; - } - - chan->expected_tx_seq = chan->buffer_seq; - - clear_bit(CONN_REJ_ACT, &chan->conn_state); - clear_bit(CONN_SREJ_ACT, &chan->conn_state); - l2cap_seq_list_clear(&chan->retrans_list); - l2cap_seq_list_clear(&chan->srej_list); - skb_queue_purge(&chan->srej_q); - - chan->tx_state = L2CAP_TX_STATE_XMIT; - chan->rx_state = L2CAP_RX_STATE_MOVE; - - set_bit(CONN_REMOTE_BUSY, &chan->conn_state); -} - -static void l2cap_move_done(struct l2cap_chan *chan) -{ - u8 move_role = chan->move_role; - BT_DBG("chan %p", chan); - - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - - if (chan->mode != L2CAP_MODE_ERTM) - return; - - switch (move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_tx(chan, NULL, NULL, L2CAP_EV_EXPLICIT_POLL); - chan->rx_state = L2CAP_RX_STATE_WAIT_F; - break; - case L2CAP_MOVE_ROLE_RESPONDER: - chan->rx_state = L2CAP_RX_STATE_WAIT_P; - break; - } -} - static void l2cap_chan_ready(struct l2cap_chan *chan) { /* The channel may have already been flagged as connected in @@ -1505,10 +1352,7 @@ static void l2cap_le_start(struct l2cap_chan *chan) static void l2cap_start_connection(struct l2cap_chan *chan) { - if (__amp_capable(chan)) { - BT_DBG("chan %p AMP capable: discover AMPs", chan); - a2mp_discover_amp(chan); - } else if (chan->conn->hcon->type == LE_LINK) { + if (chan->conn->hcon->type == LE_LINK) { l2cap_le_start(chan); } else { l2cap_send_conn_req(chan); @@ -1611,11 +1455,6 @@ static void l2cap_send_disconn_req(struct l2cap_chan *chan, int err) __clear_ack_timer(chan); } - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_state_change(chan, BT_DISCONN); - return; - } - req.dcid = cpu_to_le16(chan->dcid); req.scid = cpu_to_le16(chan->scid); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_DISCONN_REQ, @@ -1754,11 +1593,6 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_lock(chan); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (hcon->type == LE_LINK) { l2cap_le_start(chan); } else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { @@ -2067,9 +1901,6 @@ static void l2cap_streaming_send(struct l2cap_chan *chan, BT_DBG("chan %p, skbs %p", chan, skbs); - if (__chan_is_moving(chan)) - return; - skb_queue_splice_tail_init(skbs, &chan->tx_q); while (!skb_queue_empty(&chan->tx_q)) { @@ -2112,9 +1943,6 @@ static int l2cap_ertm_send(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return 0; - if (__chan_is_moving(chan)) - return 0; - while (chan->tx_send_head && chan->unacked_frames < chan->remote_tx_win && chan->tx_state == L2CAP_TX_STATE_XMIT) { @@ -2180,9 +2008,6 @@ static void l2cap_ertm_resend(struct l2cap_chan *chan) if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) return; - if (__chan_is_moving(chan)) - return; - while (chan->retrans_list.head != L2CAP_SEQ_LIST_CLEAR) { seq = l2cap_seq_list_pop(&chan->retrans_list); @@ -2522,8 +2347,7 @@ static int l2cap_segment_sdu(struct l2cap_chan *chan, pdu_len = chan->conn->mtu; /* Constrain PDU size for BR/EDR connections */ - if (!chan->hs_hcon) - pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); + pdu_len = min_t(size_t, pdu_len, L2CAP_BREDR_MAX_PAYLOAD); /* Adjust for largest possible L2CAP overhead. */ if (chan->fcs) @@ -3287,11 +3111,6 @@ int l2cap_ertm_init(struct l2cap_chan *chan) skb_queue_head_init(&chan->tx_q); - chan->local_amp_id = AMP_ID_BREDR; - chan->move_id = AMP_ID_BREDR; - chan->move_state = L2CAP_MOVE_STABLE; - chan->move_role = L2CAP_MOVE_ROLE_NONE; - if (chan->mode != L2CAP_MODE_ERTM) return 0; @@ -3326,52 +3145,19 @@ static inline __u8 l2cap_select_mode(__u8 mode, __u16 remote_feat_mask) static inline bool __l2cap_ews_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_WINDOW); } static inline bool __l2cap_efs_supported(struct l2cap_conn *conn) { - return ((conn->local_fixed_chan & L2CAP_FC_A2MP) && - (conn->feat_mask & L2CAP_FEAT_EXT_FLOW)); + return (conn->feat_mask & L2CAP_FEAT_EXT_FLOW); } static void __l2cap_set_ertm_timeouts(struct l2cap_chan *chan, struct l2cap_conf_rfc *rfc) { - if (chan->local_amp_id != AMP_ID_BREDR && chan->hs_hcon) { - u64 ertm_to = chan->hs_hcon->hdev->amp_be_flush_to; - - /* Class 1 devices have must have ERTM timeouts - * exceeding the Link Supervision Timeout. The - * default Link Supervision Timeout for AMP - * controllers is 10 seconds. - * - * Class 1 devices use 0xffffffff for their - * best-effort flush timeout, so the clamping logic - * will result in a timeout that meets the above - * requirement. ERTM timeouts are 16-bit values, so - * the maximum timeout is 65.535 seconds. - */ - - /* Convert timeout to milliseconds and round */ - ertm_to = DIV_ROUND_UP_ULL(ertm_to, 1000); - - /* This is the recommended formula for class 2 devices - * that start ERTM timers when packets are sent to the - * controller. - */ - ertm_to = 3 * ertm_to + 500; - - if (ertm_to > 0xffff) - ertm_to = 0xffff; - - rfc->retrans_timeout = cpu_to_le16((u16) ertm_to); - rfc->monitor_timeout = rfc->retrans_timeout; - } else { - rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); - rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); - } + rfc->retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc->monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); } static inline void l2cap_txwin_setup(struct l2cap_chan *chan) @@ -3623,13 +3409,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data case L2CAP_CONF_EWS: if (olen != 2) break; - if (!(chan->conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -ECONNREFUSED; - set_bit(FLAG_EXT_CTRL, &chan->flags); - set_bit(CONF_EWS_RECV, &chan->conf_state); - chan->tx_win_max = L2CAP_DEFAULT_EXT_WINDOW; - chan->remote_tx_win = val; - break; + return -ECONNREFUSED; default: if (hint) @@ -4027,11 +3807,7 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) rsp.dcid = cpu_to_le16(chan->scid); rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - - if (chan->hs_hcon) - rsp_code = L2CAP_CREATE_CHAN_RSP; - else - rsp_code = L2CAP_CONN_RSP; + rsp_code = L2CAP_CONN_RSP; BT_DBG("chan %p rsp_code %u", chan, rsp_code); @@ -4190,7 +3966,6 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, chan->dst_type = bdaddr_dst_type(conn->hcon); chan->psm = psm; chan->dcid = scid; - chan->local_amp_id = amp_id; __l2cap_chan_add(conn, chan); @@ -4516,10 +4291,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, /* check compatibility */ /* Send rsp for BR/EDR channel */ - if (!chan->hs_hcon) - l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); - else - chan->ident = cmd->ident; + l2cap_send_efs_conf_rsp(chan, rsp, cmd->ident, flags); } unlock: @@ -4571,15 +4343,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, goto done; } - if (!chan->hs_hcon) { - l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, - 0); - } else { - if (l2cap_check_efs(chan)) { - amp_create_logical_link(chan); - chan->ident = cmd->ident; - } - } + l2cap_send_efs_conf_rsp(chan, buf, cmd->ident, 0); } goto done; @@ -4750,9 +4514,6 @@ static inline int l2cap_information_req(struct l2cap_conn *conn, if (!disable_ertm) feat_mask |= L2CAP_FEAT_ERTM | L2CAP_FEAT_STREAMING | L2CAP_FEAT_FCS; - if (conn->local_fixed_chan & L2CAP_FC_A2MP) - feat_mask |= L2CAP_FEAT_EXT_FLOW - | L2CAP_FEAT_EXT_WINDOW; put_unaligned_le32(feat_mask, rsp->data); l2cap_send_cmd(conn, cmd->ident, L2CAP_INFO_RSP, sizeof(buf), @@ -4841,751 +4602,6 @@ static inline int l2cap_information_rsp(struct l2cap_conn *conn, return 0; } -static int l2cap_create_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_create_chan_req *req = data; - struct l2cap_create_chan_rsp rsp; - struct l2cap_chan *chan; - struct hci_dev *hdev; - u16 psm, scid; - - if (cmd_len != sizeof(*req)) - return -EPROTO; - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -EINVAL; - - psm = le16_to_cpu(req->psm); - scid = le16_to_cpu(req->scid); - - BT_DBG("psm 0x%2.2x, scid 0x%4.4x, amp_id %d", psm, scid, req->amp_id); - - /* For controller id 0 make BR/EDR connection */ - if (req->amp_id == AMP_ID_BREDR) { - l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - return 0; - } - - /* Validate AMP controller id */ - hdev = hci_dev_get(req->amp_id); - if (!hdev) - goto error; - - if (hdev->dev_type != HCI_AMP || !test_bit(HCI_UP, &hdev->flags)) { - hci_dev_put(hdev); - goto error; - } - - chan = l2cap_connect(conn, cmd, data, L2CAP_CREATE_CHAN_RSP, - req->amp_id); - if (chan) { - struct amp_mgr *mgr = conn->hcon->amp_mgr; - struct hci_conn *hs_hcon; - - hs_hcon = hci_conn_hash_lookup_ba(hdev, AMP_LINK, - &conn->hcon->dst); - if (!hs_hcon) { - hci_dev_put(hdev); - cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, - chan->dcid); - return 0; - } - - BT_DBG("mgr %p bredr_chan %p hs_hcon %p", mgr, chan, hs_hcon); - - mgr->bredr_chan = chan; - chan->hs_hcon = hs_hcon; - chan->fcs = L2CAP_FCS_NONE; - conn->mtu = hdev->block_mtu; - } - - hci_dev_put(hdev); - - return 0; - -error: - rsp.dcid = 0; - rsp.scid = cpu_to_le16(scid); - rsp.result = cpu_to_le16(L2CAP_CR_BAD_AMP); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - - l2cap_send_cmd(conn, cmd->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); - - return 0; -} - -static void l2cap_send_move_chan_req(struct l2cap_chan *chan, u8 dest_amp_id) -{ - struct l2cap_move_chan_req req; - u8 ident; - - BT_DBG("chan %p, dest_amp_id %d", chan, dest_amp_id); - - ident = l2cap_get_ident(chan->conn); - chan->ident = ident; - - req.icid = cpu_to_le16(chan->scid); - req.dest_amp_id = dest_amp_id; - - l2cap_send_cmd(chan->conn, ident, L2CAP_MOVE_CHAN_REQ, sizeof(req), - &req); - - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} - -static void l2cap_send_move_chan_rsp(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_rsp rsp; - - BT_DBG("chan %p, result 0x%4.4x", chan, result); - - rsp.icid = cpu_to_le16(chan->dcid); - rsp.result = cpu_to_le16(result); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); -} - -static void l2cap_send_move_chan_cfm(struct l2cap_chan *chan, u16 result) -{ - struct l2cap_move_chan_cfm cfm; - - BT_DBG("chan %p, result 0x%4.4x", chan, result); - - chan->ident = l2cap_get_ident(chan->conn); - - cfm.icid = cpu_to_le16(chan->scid); - cfm.result = cpu_to_le16(result); - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); - - __set_chan_timer(chan, L2CAP_MOVE_TIMEOUT); -} - -static void l2cap_send_move_chan_cfm_icid(struct l2cap_conn *conn, u16 icid) -{ - struct l2cap_move_chan_cfm cfm; - - BT_DBG("conn %p, icid 0x%4.4x", conn, icid); - - cfm.icid = cpu_to_le16(icid); - cfm.result = cpu_to_le16(L2CAP_MC_UNCONFIRMED); - - l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_MOVE_CHAN_CFM, - sizeof(cfm), &cfm); -} - -static void l2cap_send_move_chan_cfm_rsp(struct l2cap_conn *conn, u8 ident, - u16 icid) -{ - struct l2cap_move_chan_cfm_rsp rsp; - - BT_DBG("icid 0x%4.4x", icid); - - rsp.icid = cpu_to_le16(icid); - l2cap_send_cmd(conn, ident, L2CAP_MOVE_CHAN_CFM_RSP, sizeof(rsp), &rsp); -} - -static void __release_logical_link(struct l2cap_chan *chan) -{ - chan->hs_hchan = NULL; - chan->hs_hcon = NULL; - - /* Placeholder - release the logical link */ -} - -static void l2cap_logical_fail(struct l2cap_chan *chan) -{ - /* Logical link setup failed */ - if (chan->state != BT_CONNECTED) { - /* Create channel failure, disconnect */ - l2cap_send_disconn_req(chan, ECONNRESET); - return; - } - - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_move_done(chan); - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_SUPP); - break; - case L2CAP_MOVE_ROLE_INITIATOR: - if (chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_COMP || - chan->move_state == L2CAP_MOVE_WAIT_LOGICAL_CFM) { - /* Remote has only sent pending or - * success responses, clean up - */ - l2cap_move_done(chan); - } - - /* Other amp move states imply that the move - * has already aborted - */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } -} - -static void l2cap_logical_finish_create(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - struct l2cap_conf_rsp rsp; - - chan->hs_hchan = hchan; - chan->hs_hcon->l2cap_data = chan->conn; - - l2cap_send_efs_conf_rsp(chan, &rsp, chan->ident, 0); - - if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { - int err; - - set_default_fcs(chan); - - err = l2cap_ertm_init(chan); - if (err < 0) - l2cap_send_disconn_req(chan, -err); - else - l2cap_chan_ready(chan); - } -} - -static void l2cap_logical_finish_move(struct l2cap_chan *chan, - struct hci_chan *hchan) -{ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - BT_DBG("move_state %d", chan->move_state); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent after a success - * response is received - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - break; - case L2CAP_MOVE_WAIT_LOGICAL_CFM: - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - } - break; - default: - /* Move was not in expected state, free the channel */ - __release_logical_link(chan); - - chan->move_state = L2CAP_MOVE_STABLE; - } -} - -/* Call with chan locked */ -void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan, - u8 status) -{ - BT_DBG("chan %p, hchan %p, status %d", chan, hchan, status); - - if (status) { - l2cap_logical_fail(chan); - __release_logical_link(chan); - return; - } - - if (chan->state != BT_CONNECTED) { - /* Ignore logical link if channel is on BR/EDR */ - if (chan->local_amp_id != AMP_ID_BREDR) - l2cap_logical_finish_create(chan, hchan); - } else { - l2cap_logical_finish_move(chan, hchan); - } -} - -void l2cap_move_start(struct l2cap_chan *chan) -{ - BT_DBG("chan %p", chan); - - if (chan->local_amp_id == AMP_ID_BREDR) { - if (chan->chan_policy != BT_CHANNEL_POLICY_AMP_PREFERRED) - return; - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - start physical link setup */ - } else { - chan->move_role = L2CAP_MOVE_ROLE_INITIATOR; - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - chan->move_id = 0; - l2cap_move_setup(chan); - l2cap_send_move_chan_req(chan, 0); - } -} - -static void l2cap_do_create(struct l2cap_chan *chan, int result, - u8 local_amp_id, u8 remote_amp_id) -{ - BT_DBG("chan %p state %s %u -> %u", chan, state_to_string(chan->state), - local_amp_id, remote_amp_id); - - chan->fcs = L2CAP_FCS_NONE; - - /* Outgoing channel on AMP */ - if (chan->state == BT_CONNECT) { - if (result == L2CAP_CR_SUCCESS) { - chan->local_amp_id = local_amp_id; - l2cap_send_create_chan_req(chan, remote_amp_id); - } else { - /* Revert to BR/EDR connect */ - l2cap_send_conn_req(chan); - } - - return; - } - - /* Incoming channel on AMP */ - if (__l2cap_no_conn_pending(chan)) { - struct l2cap_conn_rsp rsp; - char buf[128]; - rsp.scid = cpu_to_le16(chan->dcid); - rsp.dcid = cpu_to_le16(chan->scid); - - if (result == L2CAP_CR_SUCCESS) { - /* Send successful response */ - rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } else { - /* Send negative response */ - rsp.result = cpu_to_le16(L2CAP_CR_NO_MEM); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - } - - l2cap_send_cmd(chan->conn, chan->ident, L2CAP_CREATE_CHAN_RSP, - sizeof(rsp), &rsp); - - if (result == L2CAP_CR_SUCCESS) { - l2cap_state_change(chan, BT_CONFIG); - set_bit(CONF_REQ_SENT, &chan->conf_state); - l2cap_send_cmd(chan->conn, l2cap_get_ident(chan->conn), - L2CAP_CONF_REQ, - l2cap_build_conf_req(chan, buf, sizeof(buf)), buf); - chan->num_conf_req++; - } - } -} - -static void l2cap_do_move_initiate(struct l2cap_chan *chan, u8 local_amp_id, - u8 remote_amp_id) -{ - l2cap_move_setup(chan); - chan->move_id = local_amp_id; - chan->move_state = L2CAP_MOVE_WAIT_RSP; - - l2cap_send_move_chan_req(chan, remote_amp_id); -} - -static void l2cap_do_move_respond(struct l2cap_chan *chan, int result) -{ - struct hci_chan *hchan = NULL; - - /* Placeholder - get hci_chan for logical link */ - - if (hchan) { - if (hchan->state == BT_CONNECTED) { - /* Logical link is ready to go */ - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - l2cap_send_move_chan_rsp(chan, L2CAP_MR_SUCCESS); - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - } else { - /* Wait for logical link to be ready */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } - } else { - /* Logical link not available */ - l2cap_send_move_chan_rsp(chan, L2CAP_MR_NOT_ALLOWED); - } -} - -static void l2cap_do_move_cancel(struct l2cap_chan *chan, int result) -{ - if (chan->move_role == L2CAP_MOVE_ROLE_RESPONDER) { - u8 rsp_result; - if (result == -EINVAL) - rsp_result = L2CAP_MR_BAD_ID; - else - rsp_result = L2CAP_MR_NOT_ALLOWED; - - l2cap_send_move_chan_rsp(chan, rsp_result); - } - - chan->move_role = L2CAP_MOVE_ROLE_NONE; - chan->move_state = L2CAP_MOVE_STABLE; - - /* Restart data transmission */ - l2cap_ertm_send(chan); -} - -/* Invoke with locked chan */ -void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) -{ - u8 local_amp_id = chan->local_amp_id; - u8 remote_amp_id = chan->remote_amp_id; - - BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", - chan, result, local_amp_id, remote_amp_id); - - if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) - return; - - if (chan->state != BT_CONNECTED) { - l2cap_do_create(chan, result, local_amp_id, remote_amp_id); - } else if (result != L2CAP_MR_SUCCESS) { - l2cap_do_move_cancel(chan, result); - } else { - switch (chan->move_role) { - case L2CAP_MOVE_ROLE_INITIATOR: - l2cap_do_move_initiate(chan, local_amp_id, - remote_amp_id); - break; - case L2CAP_MOVE_ROLE_RESPONDER: - l2cap_do_move_respond(chan, result); - break; - default: - l2cap_do_move_cancel(chan, result); - break; - } - } -} - -static inline int l2cap_move_channel_req(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_req *req = data; - struct l2cap_move_chan_rsp rsp; - struct l2cap_chan *chan; - u16 icid = 0; - u16 result = L2CAP_MR_NOT_ALLOWED; - - if (cmd_len != sizeof(*req)) - return -EPROTO; - - icid = le16_to_cpu(req->icid); - - BT_DBG("icid 0x%4.4x, dest_amp_id %d", icid, req->dest_amp_id); - - if (!(conn->local_fixed_chan & L2CAP_FC_A2MP)) - return -EINVAL; - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - rsp.icid = cpu_to_le16(icid); - rsp.result = cpu_to_le16(L2CAP_MR_NOT_ALLOWED); - l2cap_send_cmd(conn, cmd->ident, L2CAP_MOVE_CHAN_RSP, - sizeof(rsp), &rsp); - return 0; - } - - chan->ident = cmd->ident; - - if (chan->scid < L2CAP_CID_DYN_START || - chan->chan_policy == BT_CHANNEL_POLICY_BREDR_ONLY || - (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING)) { - result = L2CAP_MR_NOT_ALLOWED; - goto send_move_response; - } - - if (chan->local_amp_id == req->dest_amp_id) { - result = L2CAP_MR_SAME_ID; - goto send_move_response; - } - - if (req->dest_amp_id != AMP_ID_BREDR) { - struct hci_dev *hdev; - hdev = hci_dev_get(req->dest_amp_id); - if (!hdev || hdev->dev_type != HCI_AMP || - !test_bit(HCI_UP, &hdev->flags)) { - if (hdev) - hci_dev_put(hdev); - - result = L2CAP_MR_BAD_ID; - goto send_move_response; - } - hci_dev_put(hdev); - } - - /* Detect a move collision. Only send a collision response - * if this side has "lost", otherwise proceed with the move. - * The winner has the larger bd_addr. - */ - if ((__chan_is_moving(chan) || - chan->move_role != L2CAP_MOVE_ROLE_NONE) && - bacmp(&conn->hcon->src, &conn->hcon->dst) > 0) { - result = L2CAP_MR_COLLISION; - goto send_move_response; - } - - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - l2cap_move_setup(chan); - chan->move_id = req->dest_amp_id; - - if (req->dest_amp_id == AMP_ID_BREDR) { - /* Moving to BR/EDR */ - if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - result = L2CAP_MR_PEND; - } else { - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM; - result = L2CAP_MR_SUCCESS; - } - } else { - chan->move_state = L2CAP_MOVE_WAIT_PREPARE; - /* Placeholder - uncomment when amp functions are available */ - /*amp_accept_physical(chan, req->dest_amp_id);*/ - result = L2CAP_MR_PEND; - } - -send_move_response: - l2cap_send_move_chan_rsp(chan, result); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) -{ - struct l2cap_chan *chan; - struct hci_chan *hchan = NULL; - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) { - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - if (result == L2CAP_MR_PEND) - __set_chan_timer(chan, L2CAP_MOVE_ERTX_TIMEOUT); - - switch (chan->move_state) { - case L2CAP_MOVE_WAIT_LOGICAL_COMP: - /* Move confirm will be sent when logical link - * is complete. - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - break; - case L2CAP_MOVE_WAIT_RSP_SUCCESS: - if (result == L2CAP_MR_PEND) { - break; - } else if (test_bit(CONN_LOCAL_BUSY, - &chan->conn_state)) { - chan->move_state = L2CAP_MOVE_WAIT_LOCAL_BUSY; - } else { - /* Logical link is up or moving to BR/EDR, - * proceed with move - */ - chan->move_state = L2CAP_MOVE_WAIT_CONFIRM_RSP; - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } - break; - case L2CAP_MOVE_WAIT_RSP: - /* Moving to AMP */ - if (result == L2CAP_MR_SUCCESS) { - /* Remote is ready, send confirm immediately - * after logical link is ready - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_CFM; - } else { - /* Both logical link and move success - * are required to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_LOGICAL_COMP; - } - - /* Placeholder - get hci_chan for logical link */ - if (!hchan) { - /* Logical link not available */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - break; - } - - /* If the logical link is not yet connected, do not - * send confirmation. - */ - if (hchan->state != BT_CONNECTED) - break; - - /* Logical link is already ready to go */ - - chan->hs_hcon = hchan->conn; - chan->hs_hcon->l2cap_data = chan->conn; - - if (result == L2CAP_MR_SUCCESS) { - /* Can confirm now */ - l2cap_send_move_chan_cfm(chan, L2CAP_MC_CONFIRMED); - } else { - /* Now only need move success - * to confirm - */ - chan->move_state = L2CAP_MOVE_WAIT_RSP_SUCCESS; - } - - l2cap_logical_cfm(chan, hchan, L2CAP_MR_SUCCESS); - break; - default: - /* Any other amp move state means the move failed. */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, - u16 result) -{ - struct l2cap_chan *chan; - - chan = l2cap_get_chan_by_ident(conn, ident); - if (!chan) { - /* Could not locate channel, icid is best guess */ - l2cap_send_move_chan_cfm_icid(conn, icid); - return; - } - - __clear_chan_timer(chan); - - if (chan->move_role == L2CAP_MOVE_ROLE_INITIATOR) { - if (result == L2CAP_MR_COLLISION) { - chan->move_role = L2CAP_MOVE_ROLE_RESPONDER; - } else { - /* Cleanup - cancel move */ - chan->move_id = chan->local_amp_id; - l2cap_move_done(chan); - } - } - - l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); -} - -static int l2cap_move_channel_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_rsp *rsp = data; - u16 icid, result; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - result = le16_to_cpu(rsp->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - if (result == L2CAP_MR_SUCCESS || result == L2CAP_MR_PEND) - l2cap_move_continue(conn, icid, result); - else - l2cap_move_fail(conn, cmd->ident, icid, result); - - return 0; -} - -static int l2cap_move_channel_confirm(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm *cfm = data; - struct l2cap_chan *chan; - u16 icid, result; - - if (cmd_len != sizeof(*cfm)) - return -EPROTO; - - icid = le16_to_cpu(cfm->icid); - result = le16_to_cpu(cfm->result); - - BT_DBG("icid 0x%4.4x, result 0x%4.4x", icid, result); - - chan = l2cap_get_chan_by_dcid(conn, icid); - if (!chan) { - /* Spec requires a response even if the icid was not found */ - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - return 0; - } - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM) { - if (result == L2CAP_MC_CONFIRMED) { - chan->local_amp_id = chan->move_id; - if (chan->local_amp_id == AMP_ID_BREDR) - __release_logical_link(chan); - } else { - chan->move_id = chan->local_amp_id; - } - - l2cap_move_done(chan); - } - - l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - -static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, - struct l2cap_cmd_hdr *cmd, - u16 cmd_len, void *data) -{ - struct l2cap_move_chan_cfm_rsp *rsp = data; - struct l2cap_chan *chan; - u16 icid; - - if (cmd_len != sizeof(*rsp)) - return -EPROTO; - - icid = le16_to_cpu(rsp->icid); - - BT_DBG("icid 0x%4.4x", icid); - - chan = l2cap_get_chan_by_scid(conn, icid); - if (!chan) - return 0; - - __clear_chan_timer(chan); - - if (chan->move_state == L2CAP_MOVE_WAIT_CONFIRM_RSP) { - chan->local_amp_id = chan->move_id; - - if (chan->local_amp_id == AMP_ID_BREDR && chan->hs_hchan) - __release_logical_link(chan); - - l2cap_move_done(chan); - } - - l2cap_chan_unlock(chan); - l2cap_chan_put(chan); - - return 0; -} - static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) @@ -5745,7 +4761,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, break; case L2CAP_CONN_RSP: - case L2CAP_CREATE_CHAN_RSP: l2cap_connect_create_rsp(conn, cmd, cmd_len, data); break; @@ -5780,26 +4795,6 @@ static inline int l2cap_bredr_sig_cmd(struct l2cap_conn *conn, l2cap_information_rsp(conn, cmd, cmd_len, data); break; - case L2CAP_CREATE_CHAN_REQ: - err = l2cap_create_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_REQ: - err = l2cap_move_channel_req(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_RSP: - l2cap_move_channel_rsp(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM: - err = l2cap_move_channel_confirm(conn, cmd, cmd_len, data); - break; - - case L2CAP_MOVE_CHAN_CFM_RSP: - l2cap_move_channel_confirm_rsp(conn, cmd, cmd_len, data); - break; - default: BT_ERR("Unknown BR/EDR signaling command 0x%2.2x", cmd->code); err = -EINVAL; @@ -7051,8 +6046,8 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, if (control->final) { clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state) && - !__chan_is_moving(chan)) { + if (!test_and_clear_bit(CONN_REJ_ACT, + &chan->conn_state)) { control->final = 0; l2cap_retransmit_all(chan, control); } @@ -7245,11 +6240,7 @@ static int l2cap_finish_move(struct l2cap_chan *chan) BT_DBG("chan %p", chan); chan->rx_state = L2CAP_RX_STATE_RECV; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; return l2cap_resegment(chan); } @@ -7316,11 +6307,7 @@ static int l2cap_rx_state_wait_f(struct l2cap_chan *chan, */ chan->next_tx_seq = control->reqseq; chan->unacked_frames = 0; - - if (chan->hs_hcon) - chan->conn->mtu = chan->hs_hcon->hdev->block_mtu; - else - chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; + chan->conn->mtu = chan->conn->hcon->hdev->acl_mtu; err = l2cap_resegment(chan); @@ -7672,21 +6659,10 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, chan = l2cap_get_chan_by_scid(conn, cid); if (!chan) { - if (cid == L2CAP_CID_A2MP) { - chan = a2mp_channel_create(conn, skb); - if (!chan) { - kfree_skb(skb); - return; - } - - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - } else { - BT_DBG("unknown cid 0x%4.4x", cid); - /* Drop packet and return */ - kfree_skb(skb); - return; - } + BT_DBG("unknown cid 0x%4.4x", cid); + /* Drop packet and return */ + kfree_skb(skb); + return; } BT_DBG("chan %p, len %d", chan, skb->len); @@ -7887,10 +6863,6 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->local_fixed_chan = L2CAP_FC_SIG_BREDR | L2CAP_FC_CONNLESS; - if (hcon->type == ACL_LINK && - hci_dev_test_flag(hcon->hdev, HCI_HS_ENABLED)) - conn->local_fixed_chan |= L2CAP_FC_A2MP; - if (hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED) && (bredr_sc_enabled(hcon->hdev) || hci_dev_test_flag(hcon->hdev, HCI_FORCE_BREDR_SMP))) @@ -7953,7 +6925,7 @@ static void l2cap_chan_by_pid(struct l2cap_chan *chan, void *data) } int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, - bdaddr_t *dst, u8 dst_type) + bdaddr_t *dst, u8 dst_type, u16 timeout) { struct l2cap_conn *conn; struct hci_conn *hcon; @@ -8046,19 +7018,17 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) hcon = hci_connect_le(hdev, dst, dst_type, false, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, + chan->sec_level, timeout, HCI_ROLE_SLAVE); else hcon = hci_connect_le_scan(hdev, dst, dst_type, - chan->sec_level, - HCI_LE_CONN_TIMEOUT, + chan->sec_level, timeout, CONN_REASON_L2CAP_CHAN); } else { u8 auth_type = l2cap_get_auth_type(chan); hcon = hci_connect_acl(hdev, dst, chan->sec_level, auth_type, - CONN_REASON_L2CAP_CHAN); + CONN_REASON_L2CAP_CHAN, timeout); } if (IS_ERR(hcon)) { @@ -8355,11 +7325,6 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("chan %p scid 0x%4.4x state %s", chan, chan->scid, state_to_string(chan->state)); - if (chan->scid == L2CAP_CID_A2MP) { - l2cap_chan_unlock(chan); - continue; - } - if (!status && encrypt) chan->sec_level = hcon->sec_level; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index e50d3d102078..4287aa6cc988 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -254,7 +254,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, chan->mode = L2CAP_MODE_LE_FLOWCTL; err = l2cap_chan_connect(chan, la.l2_psm, __le16_to_cpu(la.l2_cid), - &la.l2_bdaddr, la.l2_bdaddr_type); + &la.l2_bdaddr, la.l2_bdaddr_type, + sk->sk_sndtimeo); if (err) return err; @@ -1027,23 +1028,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (opt > BT_CHANNEL_POLICY_AMP_PREFERRED) { - err = -EINVAL; - break; - } - - if (chan->mode != L2CAP_MODE_ERTM && - chan->mode != L2CAP_MODE_STREAMING) { - err = -EOPNOTSUPP; - break; - } - - chan->chan_policy = (u8) opt; - - if (sk->sk_state == BT_CONNECTED && - chan->move_role == L2CAP_MOVE_ROLE_NONE) - l2cap_move_start(chan); - + err = -EOPNOTSUPP; break; case BT_SNDMTU: diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ee3b4aad8bd8..32ed6e9245a3 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -835,8 +835,6 @@ static u32 get_supported_settings(struct hci_dev *hdev) if (lmp_ssp_capable(hdev)) { settings |= MGMT_SETTING_SSP; - if (IS_ENABLED(CONFIG_BT_HS)) - settings |= MGMT_SETTING_HS; } if (lmp_sc_capable(hdev)) @@ -901,9 +899,6 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) settings |= MGMT_SETTING_SSP; - if (hci_dev_test_flag(hdev, HCI_HS_ENABLED)) - settings |= MGMT_SETTING_HS; - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) settings |= MGMT_SETTING_ADVERTISING; @@ -1390,6 +1385,14 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + if (!cp->val) { + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) { + err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, + MGMT_STATUS_BUSY); + goto failed; + } + } + if (pending_find(MGMT_OP_SET_POWERED, hdev)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_POWERED, MGMT_STATUS_BUSY); @@ -1409,7 +1412,7 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, /* Cancel potentially blocking sync operation before power off */ if (cp->val == 0x00) { - __hci_cmd_sync_cancel(hdev, -EHOSTDOWN); + hci_cmd_sync_cancel_sync(hdev, -EHOSTDOWN); err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, mgmt_set_powered_complete); } else { @@ -1704,8 +1707,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - if (cmd) - mgmt_pending_remove(cmd); + mgmt_pending_remove(cmd); hci_dev_unlock(hdev); } @@ -1930,7 +1932,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) if (enable && hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED)) { - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); new_settings(hdev, NULL); } @@ -1943,12 +1944,6 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) changed = !hci_dev_test_and_set_flag(hdev, HCI_SSP_ENABLED); } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match); @@ -2012,11 +2007,6 @@ static int set_ssp(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) } else { changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED); - if (!changed) - changed = hci_dev_test_and_clear_flag(hdev, - HCI_HS_ENABLED); - else - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } err = send_settings_rsp(sk, MGMT_OP_SET_SSP, hdev); @@ -2062,63 +2052,10 @@ failed: static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { - struct mgmt_mode *cp = data; - bool changed; - u8 status; - int err; - bt_dev_dbg(hdev, "sock %p", sk); - if (!IS_ENABLED(CONFIG_BT_HS)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, MGMT_STATUS_NOT_SUPPORTED); - - status = mgmt_bredr_support(hdev); - if (status) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status); - - if (!lmp_ssp_capable(hdev)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_NOT_SUPPORTED); - - if (!hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - - if (cp->val != 0x00 && cp->val != 0x01) - return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_INVALID_PARAMS); - - hci_dev_lock(hdev); - - if (pending_find(MGMT_OP_SET_SSP, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_BUSY); - goto unlock; - } - - if (cp->val) { - changed = !hci_dev_test_and_set_flag(hdev, HCI_HS_ENABLED); - } else { - if (hdev_is_powered(hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, - MGMT_STATUS_REJECTED); - goto unlock; - } - - changed = hci_dev_test_and_clear_flag(hdev, HCI_HS_ENABLED); - } - - err = send_settings_rsp(sk, MGMT_OP_SET_HS, hdev); - if (err < 0) - goto unlock; - - if (changed) - err = new_settings(hdev, sk); - -unlock: - hci_dev_unlock(hdev); - return err; } static void set_le_complete(struct hci_dev *hdev, void *data, int err) @@ -3188,6 +3125,7 @@ failed: static u8 link_to_bdaddr(u8 link_type, u8 addr_type) { switch (link_type) { + case ISO_LINK: case LE_LINK: switch (addr_type) { case ADDR_LE_DEV_PUBLIC: @@ -3505,7 +3443,8 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, if (cp->addr.type == BDADDR_BREDR) { conn = hci_connect_acl(hdev, &cp->addr.bdaddr, sec_level, - auth_type, CONN_REASON_PAIR_DEVICE); + auth_type, CONN_REASON_PAIR_DEVICE, + HCI_ACL_CONN_TIMEOUT); } else { u8 addr_type = le_addr_type(cp->addr.type); struct hci_conn_params *p; @@ -6766,7 +6705,6 @@ static int set_bredr(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) hci_dev_clear_flag(hdev, HCI_SSP_ENABLED); hci_dev_clear_flag(hdev, HCI_LINK_SECURITY); hci_dev_clear_flag(hdev, HCI_FAST_CONNECTABLE); - hci_dev_clear_flag(hdev, HCI_HS_ENABLED); } hci_dev_change_flag(hdev, HCI_BREDR_ENABLED); @@ -8470,7 +8408,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev, static u8 calculate_name_len(struct hci_dev *hdev) { - u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 3]; + u8 buf[HCI_MAX_SHORT_NAME_LENGTH + 2]; /* len + type + name */ return eir_append_local_name(hdev, buf, 0); } @@ -8829,8 +8767,7 @@ static void add_ext_adv_params_complete(struct hci_dev *hdev, void *data, } unlock: - if (cmd) - mgmt_pending_free(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); } @@ -9681,6 +9618,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, u16 eir_len = 0; u32 flags = 0; + if (test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) + return; + /* allocate buff for LE or BR/EDR adv */ if (conn->le_adv_data_len > 0) skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_CONNECTED, @@ -9748,6 +9688,9 @@ bool mgmt_powering_down(struct hci_dev *hdev) struct mgmt_pending_cmd *cmd; struct mgmt_mode *cp; + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) + return true; + cmd = pending_find(MGMT_OP_SET_POWERED, hdev); if (!cmd) return false; @@ -9766,14 +9709,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, struct mgmt_ev_device_disconnected ev; struct sock *sk = NULL; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - if (!mgmt_connected) return; @@ -9830,14 +9765,6 @@ void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, { struct mgmt_ev_connect_failed ev; - /* The connection is still in hci_conn_hash so test for 1 - * instead of 0 to know if this is the last one. - */ - if (mgmt_powering_down(hdev) && hci_conn_count(hdev) == 1) { - cancel_delayed_work(&hdev->power_off); - queue_work(hdev->req_workqueue, &hdev->power_off.work); - } - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.status = mgmt_status(status); @@ -10071,6 +9998,9 @@ void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status) /* If this is a HCI command related to powering on the * HCI dev don't send any mgmt signals. */ + if (hci_dev_test_flag(hdev, HCI_POWERING_DOWN)) + return; + if (pending_find(MGMT_OP_SET_POWERED, hdev)) return; } diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index 630e3023273b..9612c5d1b13f 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -875,6 +875,7 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) remove = true; goto done; } + cp->sub_opcode = MSFT_OP_LE_MONITOR_ADVERTISEMENT; cp->rssi_high = address_filter->rssi_high; cp->rssi_low = address_filter->rssi_low; @@ -887,6 +888,8 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, HCI_CMD_TIMEOUT); + kfree(cp); + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to enable address %pMR filter", &address_filter->bdaddr); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index c736186aba26..43daf965a01e 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -264,7 +264,8 @@ static int sco_connect(struct sock *sk) } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, - sco_pi(sk)->setting, &sco_pi(sk)->codec); + sco_pi(sk)->setting, &sco_pi(sk)->codec, + sk->sk_sndtimeo); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 5535f9adc658..61efeadaff8d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -12,6 +12,7 @@ #include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> +#include <net/hotdata.h> #include <net/sock.h> #include <net/tcp.h> #include <net/net_namespace.h> @@ -254,7 +255,8 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, nframes, + (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); diff --git a/net/core/Makefile b/net/core/Makefile index 821aec06abf1..6e6548011fae 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,6 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o +obj-y += hotdata.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/dev.c b/net/core/dev.c index fe054cbd41e9..0766a245816b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -155,13 +155,13 @@ #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -struct list_head ptype_all __read_mostly; /* Taps */ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, @@ -540,7 +540,7 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) - return pt->dev ? &pt->dev->ptype_all : &ptype_all; + return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; @@ -2226,7 +2226,8 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) */ bool dev_nit_active(struct net_device *dev) { - return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); + return !list_empty(&net_hotdata.ptype_all) || + !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); @@ -2237,10 +2238,9 @@ EXPORT_SYMBOL_GPL(dev_nit_active); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { - struct packet_type *ptype; + struct list_head *ptype_list = &net_hotdata.ptype_all; + struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; - struct packet_type *pt_prev = NULL; - struct list_head *ptype_list = &ptype_all; rcu_read_lock(); again: @@ -2286,7 +2286,7 @@ again: pt_prev = ptype; } - if (ptype_list == &ptype_all) { + if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } @@ -4405,19 +4405,10 @@ EXPORT_SYMBOL(__dev_direct_xmit); * Receiver routines *************************************************************************/ -int netdev_max_backlog __read_mostly = 1000; -EXPORT_SYMBOL(netdev_max_backlog); - -int netdev_tstamp_prequeue __read_mostly = 1; unsigned int sysctl_skb_defer_max __read_mostly = 64; -int netdev_budget __read_mostly = 300; -/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ -unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ -int dev_rx_weight __read_mostly = 64; -int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4459,12 +4450,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, #ifdef CONFIG_RPS -/* One global table that all flow-based protocols share. */ -struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; -EXPORT_SYMBOL(rps_sock_flow_table); -u32 rps_cpu_mask __read_mostly; -EXPORT_SYMBOL(rps_cpu_mask); - struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; @@ -4556,7 +4541,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (!hash) goto done; - sock_flow_table = rcu_dereference(rps_sock_flow_table); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; @@ -4566,10 +4551,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); - if ((ident ^ hash) & ~rps_cpu_mask) + if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; - next_cpu = ident & rps_cpu_mask; + next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table @@ -4718,7 +4703,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) + if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4766,7 +4751,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(net_hotdata.max_backlog) && + !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -5055,7 +5041,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); @@ -5347,7 +5333,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5391,7 +5377,7 @@ another_round: if (pfmemalloc) goto skip_taps; - list_for_each_entry_rcu(ptype, &ptype_all, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -5731,7 +5717,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5761,7 +5747,8 @@ void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), + skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5985,7 +5972,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = READ_ONCE(dev_rx_weight); + napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6790,8 +6777,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); - int budget = READ_ONCE(netdev_budget); + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); + int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -9122,28 +9109,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); -static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) -{ -#if IS_ENABLED(CONFIG_DPLL) - rtnl_lock(); - rcu_assign_pointer(dev->dpll_pin, dpll_pin); - rtnl_unlock(); -#endif -} - -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) -{ - WARN_ON(!dpll_pin); - netdev_dpll_pin_assign(dev, dpll_pin); -} -EXPORT_SYMBOL(netdev_dpll_pin_set); - -void netdev_dpll_pin_clear(struct net_device *dev) -{ - netdev_dpll_pin_assign(dev, NULL); -} -EXPORT_SYMBOL(netdev_dpll_pin_clear); - /** * dev_change_proto_down - set carrier according to proto_down. * @@ -11774,7 +11739,6 @@ static int __init net_dev_init(void) if (netdev_kobject_init()) goto out; - INIT_LIST_HEAD(&ptype_all); for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); diff --git a/net/core/dev.h b/net/core/dev.h index 45892267848d..2bcaf8eee50c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -38,10 +38,7 @@ int dev_addr_init(struct net_device *dev); void dev_addr_check(struct net_device *dev); /* sysctls not referred to from outside net/core/ */ -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; extern unsigned int sysctl_skb_defer_max; -extern int netdev_tstamp_prequeue; extern int netdev_unregister_timeout_secs; extern int weight_p; extern int dev_weight_rx_bias; diff --git a/net/core/gro.c b/net/core/gro.c index 0759277dc14e..ee30d4f0c038 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -10,9 +10,6 @@ #define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(offload_lock); -struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /** * dev_add_offload - register offload handlers @@ -31,7 +28,7 @@ void dev_add_offload(struct packet_offload *po) struct packet_offload *elem; spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { + list_for_each_entry(elem, &net_hotdata.offload_base, list) { if (po->priority < elem->priority) break; } @@ -55,7 +52,7 @@ EXPORT_SYMBOL(dev_add_offload); */ static void __dev_remove_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *po1; spin_lock(&offload_lock); @@ -235,9 +232,9 @@ done: static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; int err = -ENOENT; BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); @@ -369,15 +366,21 @@ static void gro_list_prepare(const struct list_head *head, static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) { - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; + const struct skb_shared_info *pinfo; + const skb_frag_t *frag0; + unsigned int headlen; NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + headlen = skb_headlen(skb); + NAPI_GRO_CB(skb)->frag0 = skb->data; + NAPI_GRO_CB(skb)->frag0_len = headlen; + if (headlen) + return; + + pinfo = skb_shinfo(skb); + frag0 = &pinfo->frags[0]; - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, @@ -438,7 +441,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; @@ -544,7 +547,7 @@ normal: struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -558,7 +561,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type); struct packet_offload *gro_find_complete_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -700,7 +703,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) skb_reset_mac_header(skb); skb_gro_reset_offset(skb, hlen); - if (unlikely(skb_gro_header_hard(skb, hlen))) { + if (unlikely(!skb_gro_may_pull(skb, hlen))) { eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { net_warn_ratelimited("%s: dropping impossible skb from %s\n", @@ -710,7 +713,10 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) } } else { eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); + + if (NAPI_GRO_CB(skb)->frag0 != skb->data) + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen; } diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index ed5ec5de47f6..ff8e5b64bf6b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <linux/netdevice.h> #include <net/gro_cells.h> +#include <net/hotdata.h> struct gro_cell { struct sk_buff_head napi_skbs; @@ -26,7 +27,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/gso.c b/net/core/gso.c index 9e1803bfc9c6..bcd156372f4d 100644 --- a/net/core/gso.c +++ b/net/core/gso.c @@ -17,7 +17,7 @@ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, struct packet_offload *ptype; rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; @@ -48,7 +48,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, __skb_pull(skb, vlan_depth); rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; diff --git a/net/core/hotdata.c b/net/core/hotdata.c new file mode 100644 index 000000000000..c8a7a451c18a --- /dev/null +++ b/net/core/hotdata.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <net/hotdata.h> +#include <linux/cache.h> +#include <linux/jiffies.h> +#include <linux/list.h> + + +struct net_hotdata net_hotdata __cacheline_aligned = { + .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), + .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all), + .gro_normal_batch = 8, + + .netdev_budget = 300, + /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ + .netdev_budget_usecs = 2 * USEC_PER_SEC / HZ, + + .tstamp_prequeue = 1, + .max_backlog = 1000, + .dev_tx_weight = 64, + .dev_rx_weight = 64, +}; +EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 2e4e96d30ee1..a97eceb84e61 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -3,6 +3,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> +#include <net/hotdata.h> #include "dev.h" @@ -183,7 +184,7 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) } } - list_for_each_entry_rcu(pt, &ptype_all, list) { + list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { if (i == pos) return pt; ++i; @@ -231,13 +232,13 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) } } - nxt = ptype_all.next; + nxt = net_hotdata.ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: - if (nxt != &ptype_all) + if (nxt != &net_hotdata.ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index af238026ac3c..e3d7a8cfa20b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -24,6 +24,7 @@ #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_rx_queue.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" @@ -1414,6 +1415,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); +static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); +} + +static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + value = msecs_to_jiffies(value); + if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) + return -ERANGE; + + if (!dql->stall_thrs && value) + dql->last_reap = jiffies; + /* Force last_reap to be live */ + smp_wmb(); + dql->stall_thrs = value; + + return len; +} + +static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = + __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); + +static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) +{ + return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); +} + +static ssize_t bql_set_stall_max(struct netdev_queue *queue, + const char *buf, size_t len) +{ + WRITE_ONCE(queue->dql.stall_max, 0); + return len; +} + +static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = + __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); + +static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%lu\n", dql->stall_cnt); +} + +static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = + __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); + static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { @@ -1452,6 +1512,9 @@ static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, + &bql_stall_thrs_attribute.attr, + &bql_stall_cnt_attribute.attr, + &bql_stall_max_attribute.attr, NULL }; diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..8d8ace9ef87f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_QSTATS_GET - dump */ +static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_QSTATS_GET, + .dumpit = netdev_nl_qstats_get_dumpit, + .policy = netdev_qstats_get_nl_policy, + .maxattr = NETDEV_A_QSTATS_SCOPE, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..4db40fd5b4a9 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index fd98936da3ae..7004b3399c2b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -8,6 +8,7 @@ #include <net/xdp.h> #include <net/xdp_sock.h> #include <net/netdev_rx_queue.h> +#include <net/netdev_queues.h> #include <net/busy_poll.h> #include "netdev-genl-gen.h" @@ -152,10 +153,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -287,10 +285,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; - - return skb->len; + return err; } static int @@ -463,10 +458,220 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) } rtnl_unlock(); - if (err != -EMSGSIZE) - return err; + return err; +} + +#define NETDEV_STAT_NOT_SET (~0ULL) + +static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) +{ + const u64 *add = _add; + u64 *sum = _sum; + + while (size) { + if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) + *sum += *add; + sum++; + add++; + size -= 8; + } +} + +static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) +{ + if (value == NETDEV_STAT_NOT_SET) + return 0; + return nla_put_uint(rsp, attr_id, value); +} + +static int +netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, + u32 q_type, int i, const struct genl_info *info) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + memset(&rx, 0xff, sizeof(rx)); + ops->get_queue_stats_rx(netdev, i, &rx); + if (!memchr_inv(&rx, 0xff, sizeof(rx))) + goto nla_cancel; + if (netdev_nl_stats_write_rx(rsp, &rx)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + memset(&tx, 0xff, sizeof(tx)); + ops->get_queue_stats_tx(netdev, i, &tx); + if (!memchr_inv(&tx, 0xff, sizeof(tx))) + goto nla_cancel; + if (netdev_nl_stats_write_tx(rsp, &tx)) + goto nla_put_failure; + break; + } + + genlmsg_end(rsp, hdr); + return 0; + +nla_cancel: + genlmsg_cancel(rsp, hdr); + return 0; +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int +netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + int i, err; + + if (!(netdev->flags & IFF_UP)) + return 0; + + i = ctx->rxq_idx; + while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, + i, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + i = ctx->txq_idx; + while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, + i, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + return 0; +} + +static int +netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info) +{ + struct netdev_queue_stats_rx rx_sum, rx; + struct netdev_queue_stats_tx tx_sum, tx; + const struct netdev_stat_ops *ops; + void *hdr; + int i; + + ops = netdev->stat_ops; + /* Netdev can't guarantee any complete counters */ + if (!ops->get_base_stats) + return 0; + + memset(&rx_sum, 0xff, sizeof(rx_sum)); + memset(&tx_sum, 0xff, sizeof(tx_sum)); + + ops->get_base_stats(netdev, &rx_sum, &tx_sum); + + /* The op was there, but nothing reported, don't bother */ + if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && + !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + for (i = 0; i < netdev->real_num_rx_queues; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); + } + for (i = 0; i < netdev->real_num_tx_queues; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); + } + + if (netdev_nl_stats_write_rx(rsp, &rx_sum) || + netdev_nl_stats_write_tx(rsp, &tx_sum)) + goto nla_put_failure; + + genlmsg_end(rsp, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + unsigned int scope; + int err = 0; + + scope = 0; + if (info->attrs[NETDEV_A_QSTATS_SCOPE]) + scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); + + rtnl_lock(); + for_each_netdev_dump(net, netdev, ctx->ifindex) { + if (!netdev->stat_ops) + continue; + + switch (scope) { + case 0: + err = netdev_nl_stats_by_netdev(netdev, skb, info); + break; + case NETDEV_QSTATS_SCOPE_QUEUE: + err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); + break; + } + if (err < 0) + break; + } + rtnl_unlock(); - return skb->len; + return err; } static int netdev_genl_netdevice_event(struct notifier_block *nb, diff --git a/net/core/page_pool.c b/net/core/page_pool.c index d706fe5548df..dd364d738c00 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -657,6 +657,11 @@ static bool page_pool_recycle_in_cache(struct page *page, return true; } +static bool __page_pool_page_can_be_recycled(const struct page *page) +{ + return page_ref_count(page) == 1 && !page_is_pfmemalloc(page); +} + /* If the page refcnt == 1, this will try to recycle the page. * if PP_FLAG_DMA_SYNC_DEV is set, we'll try to sync the DMA area for * the configured size min(dma_sync_size, pool->max_len). @@ -678,7 +683,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * page is NOT reusable when allocated when system is under * some pressure. (page_is_pfmemalloc) */ - if (likely(page_ref_count(page) == 1 && !page_is_pfmemalloc(page))) { + if (likely(__page_pool_page_can_be_recycled(page))) { /* Read barrier done in page_ref_count / READ_ONCE */ if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) @@ -793,7 +798,7 @@ static struct page *page_pool_drain_frag(struct page_pool *pool, if (likely(page_pool_unref_page(page, drain_count))) return NULL; - if (page_ref_count(page) == 1 && !page_is_pfmemalloc(page)) { + if (__page_pool_page_can_be_recycled(page)) { if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, -1); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index ffe5244e5597..3a3277ba167b 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -94,16 +94,15 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) - break; + goto out; } state->pp_id = 0; } +out: mutex_unlock(&page_pools_lock); rtnl_unlock(); - if (skb->len && err == -EMSGSIZE) - return skb->len; return err; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 780b330f8ef9..a3d7847ce69d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1056,7 +1056,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) { size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */ - size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev)); + size += dpll_netdev_pin_handle_size(dev); return size; } @@ -1793,7 +1793,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb, if (!dpll_pin_nest) return -EMSGSIZE; - ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev)); + ret = dpll_netdev_add_pin_handle(skb, dev); if (ret < 0) goto nest_cancel; @@ -2267,11 +2267,8 @@ walk_entries: nlh->nlmsg_seq, 0, flags, ext_filter_mask, 0, NULL, 0, netnsid, GFP_KERNEL); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) break; - } } cb->seq = tgt_net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1f918e602bc4..b99127712e67 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/sock.h> #include <net/checksum.h> #include <net/gso.h> +#include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> @@ -88,15 +89,10 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_cache __ro_after_init; -static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif - -static struct kmem_cache *skb_small_head_cache __ro_after_init; - #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. @@ -315,7 +311,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); - return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); @@ -327,13 +324,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); - data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + align_mask); } else { struct napi_alloc_cache *nc; local_bh_disable(); nc = this_cpu_ptr(&napi_alloc_cache); - data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); + data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, + align_mask); local_bh_enable(); } return data; @@ -346,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -355,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); + kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; } @@ -413,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -464,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -575,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { - obj = kmem_cache_alloc_node(skb_small_head_cache, + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; @@ -583,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node); + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out; } @@ -646,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_cache; + ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -1092,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb) static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) - kmem_cache_free(skb_small_head_cache, head); + kmem_cache_free(net_hotdata.skb_small_head_cache, head); else kfree(head); } @@ -1116,9 +1115,7 @@ static void skb_release_data(struct sk_buff *skb, enum skb_drop_reason reason, struct skb_shared_info *shinfo = skb_shinfo(skb); int i; - if (skb->cloned && - atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, - &shinfo->dataref)) + if (!skb_data_unref(skb, shinfo)) goto exit; if (skb_zcopy(skb)) { @@ -1159,7 +1156,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -1180,7 +1177,7 @@ static void kfree_skbmem(struct sk_buff *skb) if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: - kmem_cache_free(skbuff_fclone_cache, fclones); + kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) @@ -1277,7 +1274,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1302,7 +1299,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); + kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1464,9 +1461,9 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], - kmem_cache_size(skbuff_cache)); + kmem_cache_size(net_hotdata.skbuff_cache)); - kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, + 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; } @@ -2063,7 +2060,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_cache, gfp_mask); + n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; @@ -5002,7 +4999,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", + net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| @@ -5010,7 +5007,7 @@ void __init skb_init(void) offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", + net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -5019,7 +5016,7 @@ void __init skb_init(void) * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ - skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, @@ -5892,7 +5889,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } diff --git a/net/core/sock.c b/net/core/sock.c index df2ac54a8f74..43bf3818c19e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2053,8 +2053,9 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, - prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + prot->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see sk_prot_alloc() */); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 986f15e5d6c4..6973dda3abda 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -23,6 +23,8 @@ #include <net/net_ratelimit.h> #include <net/busy_poll.h> #include <net/pkt_sched.h> +#include <net/hotdata.h> +#include <net/rps.h> #include "dev.h" @@ -138,7 +140,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_lock(&sock_flow_mutex); - orig_sock_table = rcu_dereference_protected(rps_sock_flow_table, + orig_sock_table = rcu_dereference_protected( + net_hotdata.rps_sock_flow_table, lockdep_is_held(&sock_flow_mutex)); size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; @@ -159,7 +162,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_unlock(&sock_flow_mutex); return -ENOMEM; } - rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1; + net_hotdata.rps_cpu_mask = + roundup_pow_of_two(nr_cpu_ids) - 1; sock_table->mask = size - 1; } else sock_table = orig_sock_table; @@ -170,7 +174,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, sock_table = NULL; if (sock_table != orig_sock_table) { - rcu_assign_pointer(rps_sock_flow_table, sock_table); + rcu_assign_pointer(net_hotdata.rps_sock_flow_table, + sock_table); if (sock_table) { static_branch_inc(&rps_needed); static_branch_inc(&rfs_needed); @@ -300,8 +305,8 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); - WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); - WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); @@ -439,7 +444,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_max_backlog", - .data = &netdev_max_backlog, + .data = &net_hotdata.max_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -498,7 +503,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_tstamp_prequeue", - .data = &netdev_tstamp_prequeue, + .data = &net_hotdata.tstamp_prequeue, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -576,7 +581,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_budget", - .data = &netdev_budget, + .data = &net_hotdata.netdev_budget, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -599,7 +604,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_budget_usecs", - .data = &netdev_budget_usecs, + .data = &net_hotdata.netdev_budget_usecs, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -632,7 +637,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "gro_normal_batch", - .data = &gro_normal_batch, + .data = &net_hotdata.gro_normal_batch, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, diff --git a/net/core/xdp.c b/net/core/xdp.c index 0e3709a29175..41693154e426 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -16,6 +16,7 @@ #include <linux/bug.h> #include <net/page_pool/helpers.h> +#include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> @@ -589,7 +590,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -658,7 +659,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; diff --git a/net/dsa/user.c b/net/dsa/user.c index 9c42a6edcdc8..16d395bb1a1f 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2625,11 +2625,7 @@ int dsa_user_create(struct dsa_port *port) user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); - user_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!user_dev->tstats) { - free_netdev(user_dev); - return -ENOMEM; - } + user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) @@ -2695,7 +2691,6 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(user_dev->tstats); free_netdev(user_dev); port->user = NULL; return ret; @@ -2716,7 +2711,6 @@ void dsa_user_destroy(struct net_device *user_dev) dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); - free_percpu(user_dev->tstats); free_netdev(user_dev); } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index ce486cec346c..6b2a360dcdf0 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -712,8 +712,3 @@ ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) } } EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); - -bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee) -{ - return !linkmode_empty(eee->supported); -} diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 0f2b5f7eacee..28b8aaaf9bcb 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -55,6 +55,5 @@ int ethtool_get_module_eeprom_call(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data); bool __ethtool_dev_mm_supported(struct net_device *dev); -bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee); #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 317308bdbda9..5a55270aa86e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1514,17 +1514,12 @@ static void eee_to_keee(struct ethtool_keee *keee, { memset(keee, 0, sizeof(*keee)); - keee->eee_active = eee->eee_active; keee->eee_enabled = eee->eee_enabled; keee->tx_lpi_enabled = eee->tx_lpi_enabled; keee->tx_lpi_timer = eee->tx_lpi_timer; - ethtool_convert_legacy_u32_to_link_mode(keee->supported, - eee->supported); ethtool_convert_legacy_u32_to_link_mode(keee->advertised, eee->advertised); - ethtool_convert_legacy_u32_to_link_mode(keee->lp_advertised, - eee->lp_advertised); } static void keee_to_eee(struct ethtool_eee *eee, diff --git a/net/ieee802154/sysfs.c b/net/ieee802154/sysfs.c index d2903933805c..6708160ebf9f 100644 --- a/net/ieee802154/sysfs.c +++ b/net/ieee802154/sysfs.c @@ -93,7 +93,7 @@ static SIMPLE_DEV_PM_OPS(wpan_phy_pm_ops, wpan_phy_suspend, wpan_phy_resume); #define WPAN_PHY_PM_OPS NULL #endif -struct class wpan_phy_class = { +const struct class wpan_phy_class = { .name = "ieee802154", .dev_release = wpan_phy_release, .dev_groups = pmib_groups, diff --git a/net/ieee802154/sysfs.h b/net/ieee802154/sysfs.h index 337545b639e9..69961e166257 100644 --- a/net/ieee802154/sysfs.h +++ b/net/ieee802154/sysfs.h @@ -5,6 +5,6 @@ int wpan_phy_sysfs_init(void); void wpan_phy_sysfs_exit(void); -extern struct class wpan_phy_class; +extern const struct class wpan_phy_class; #endif /* __IEEE802154_SYSFS_H */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5daebdcbca32..55bd72997b31 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #endif #include <net/l3mdev.h> #include <net/compat.h> +#include <net/rps.h> #include <trace/events/sock.h> @@ -1751,19 +1752,6 @@ static const struct net_protocol igmp_protocol = { }; #endif -static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .no_policy = 1, - .icmp_strict_tag_validation = 1, -}; - -static const struct net_protocol udp_protocol = { - .handler = udp_rcv, - .err_handler = udp_err, - .no_policy = 1, -}; - static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, @@ -1904,14 +1892,6 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ -static struct packet_offload ip_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IP), - .callbacks = { - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, - }, -}; static const struct net_offload ipip_offload = { .callbacks = { @@ -1938,7 +1918,15 @@ static int __init ipv4_offload_init(void) if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); - dev_add_offload(&ip_packet_offload); + net_hotdata.ip_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } @@ -1992,9 +1980,22 @@ static int __init inet_init(void) if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); - if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) + + net_hotdata.udp_protocol = (struct net_protocol) { + .handler = udp_rcv, + .err_handler = udp_err, + .no_policy = 1, + }; + if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); - if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) + + net_hotdata.tcp_protocol = (struct net_protocol) { + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .no_policy = 1, + .icmp_strict_tag_validation = 1, + }; + if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 4daa8124f247..7a437f0d4190 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1900,8 +1900,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); @@ -2312,8 +2310,6 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, ctx->all_default++; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; rcu_read_unlock(); return err; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index bf3a2214fe29..48741352a88a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1026,8 +1026,6 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0 && skb->len) - err = skb->len; goto unlock; } @@ -1045,11 +1043,8 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) goto out; - } dumped = 1; next: e++; diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index 0c41076e31ed..a8494f796dca 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -351,7 +351,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, optlen = guehdr->hlen << 2; len += optlen; - if (skb_gro_header_hard(skb, len)) { + if (!skb_gro_may_pull(skb, len)) { guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 311e70bfce40..5028c72d494a 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -174,7 +174,7 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, grehlen += GRE_HEADER_SECTION; hlen = off + grehlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { greh = skb_gro_header_slow(skb, hlen, off); if (unlikely(!greh)) goto out; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 747ed7344cbe..7d8090f109ef 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,8 +906,9 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); - memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, - req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), + /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 308ff34002ea..7498af320164 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,6 +24,7 @@ #include <net/inet6_hashtables.h> #endif #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/ip.h> #include <net/tcp.h> #include <net/sock_reuseport.h> @@ -32,8 +33,6 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 inet_ehash_secret __read_mostly; - net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 1fe794967211..33f93dc730a3 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1458,6 +1458,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; skb->tstamp = cork->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 21d2ffa919e9..cf377377b52d 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -894,7 +894,7 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, { struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); - int val = 0, err; + int val = 0, err, retv; bool needs_rtnl = setsockopt_needs_rtnl(optname); switch (optname) { @@ -938,8 +938,12 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname, /* If optlen==0, it is equivalent to val == 0 */ - if (optname == IP_ROUTER_ALERT) - return ip_ra_control(sk, val ? 1 : 0, NULL); + if (optname == IP_ROUTER_ALERT) { + retv = ip_ra_control(sk, val ? 1 : 0, NULL); + if (retv == 0) + inet_assign_bit(RTALERT, sk, val); + return retv; + } if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); @@ -1575,6 +1579,9 @@ int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_BIND_ADDRESS_NO_PORT: val = inet_test_bit(BIND_ADDRESS_NO_PORT, sk); goto copyval; + case IP_ROUTER_ALERT: + val = inet_test_bit(RTALERT, sk); + goto copyval; case IP_TTL: val = READ_ONCE(inet->uc_ttl); if (val < 0) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 0708ac6f6c58..fd5c01c8489f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1603,9 +1603,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; + + olr = min_t(unsigned int, olr, sizeof(int)); + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, olr)) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 70509da4f080..73b849be6504 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,6 +26,9 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ + NHA_OP_FLAG_DUMP_HW_STATS) + static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, @@ -37,10 +40,17 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, + [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), +}; + +static const struct nla_policy rtm_nh_policy_del[] = { + [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { @@ -48,6 +58,8 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -92,6 +104,7 @@ __nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, else if (nh_info->gw_family == AF_INET6) nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; + nh_info->id = nhi->nh_parent->id; nh_info->is_reject = nhi->reject_nh; nh_info->is_fdb = nhi->fdb_nh; nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; @@ -131,13 +144,13 @@ static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; + info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; struct nh_info *nhi; nhi = rtnl_dereference(nhge->nh->nh_info); - info->nh_grp->nh_entries[i].id = nhge->nh->id; info->nh_grp->nh_entries[i].weight = nhge->weight; __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, nhi); @@ -162,6 +175,7 @@ static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; + info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; @@ -393,6 +407,7 @@ static int call_nexthop_res_table_notifiers(struct net *net, struct nexthop *nh, struct nh_notifier_info info = { .net = net, .extack = extack, + .id = nh->id, }; struct nh_group *nhg; int err; @@ -474,6 +489,7 @@ static void nexthop_free_group(struct nexthop *nh) struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); + free_percpu(nhge->stats); nexthop_put(nhge->nh); } @@ -654,8 +670,201 @@ nla_put_failure: return -EMSGSIZE; } -static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) +{ + struct nh_grp_entry_stats *cpu_stats; + + cpu_stats = this_cpu_ptr(nhge->stats); + u64_stats_update_begin(&cpu_stats->syncp); + u64_stats_inc(&cpu_stats->packets); + u64_stats_update_end(&cpu_stats->syncp); +} + +static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, + u64 *ret_packets) +{ + int i; + + *ret_packets = 0; + + for_each_possible_cpu(i) { + struct nh_grp_entry_stats *cpu_stats; + unsigned int start; + u64 packets; + + cpu_stats = per_cpu_ptr(nhge->stats, i); + do { + start = u64_stats_fetch_begin(&cpu_stats->syncp); + packets = u64_stats_read(&cpu_stats->packets); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + *ret_packets += packets; + } +} + +static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, + const struct nexthop *nh) { + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + info->id = nh->id; + info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; + info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, + stats, nhg->num_nh), + GFP_KERNEL); + if (!info->nh_grp_hw_stats) + return -ENOMEM; + + info->nh_grp_hw_stats->num_nh = nhg->num_nh; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; + } + + return 0; +} + +static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp_hw_stats); +} + +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets) +{ + info->hw_stats_used = true; + info->stats[nh_idx].packets += delta_packets; +} +EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); + +static void nh_grp_hw_stats_apply_update(struct nexthop *nh, + struct nh_notifier_info *info) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; + } +} + +static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) +{ + struct nh_notifier_info info = { + .net = nh->net, + }; + struct net *net = nh->net; + int err; + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_grp_hw_stats_init(&info, nh); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, + &info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + nh_grp_hw_stats_apply_update(nh, &info); + *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; + + nh_notifier_grp_hw_stats_fini(&info); + return notifier_to_errno(err); +} + +static int nla_put_nh_group_stats_entry(struct sk_buff *skb, + struct nh_grp_entry *nhge, + u32 op_flags) +{ + struct nlattr *nest; + u64 packets; + + nh_grp_entry_stats_read(nhge, &packets); + + nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, + packets + nhge->packets_hw)) + goto nla_put_failure; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, + nhge->packets_hw)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + struct nlattr *nest; + bool hw_stats_used; + int err; + int i; + + if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) + goto err_out; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nhg->hw_stats) { + err = nh_grp_hw_stats_update(nh, &hw_stats_used); + if (err) + goto out; + + if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) + goto err_out; + } + + nest = nla_nest_start(skb, NHA_GROUP_STATS); + if (!nest) + goto err_out; + + for (i = 0; i < nhg->num_nh; i++) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], + op_flags)) + goto cancel_out; + + nla_nest_end(skb, nest); + return 0; + +cancel_out: + nla_nest_cancel(skb, nest); +err_out: + err = -EMSGSIZE; +out: + return err; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; @@ -684,6 +893,11 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; + if (op_flags & NHA_OP_FLAG_DUMP_STATS && + (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || + nla_put_nh_group_stats(skb, nh, op_flags))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -691,7 +905,8 @@ nla_put_failure: } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, - int event, u32 portid, u32 seq, unsigned int nlflags) + int event, u32 portid, u32 seq, unsigned int nlflags, + u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; @@ -718,7 +933,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nhg)) + if (nla_put_nh_group(skb, nh, op_flags)) goto nla_put_failure; goto out; } @@ -849,7 +1064,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) if (!skb) goto errout; - err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1104,6 +1319,7 @@ static int nh_check_attr_group(struct net *net, if (!tb[i]) continue; switch (i) { + case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: @@ -1176,6 +1392,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1185,7 +1402,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { - struct nexthop *rc = NULL; + struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) @@ -1200,16 +1417,20 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) if (!nexthop_is_good_nh(nhge->nh)) continue; - if (!rc) - rc = nhge->nh; + if (!nhge0) + nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } - return rc ? : nhg->nh_entries[0].nh; + if (!nhge0) + nhge0 = &nhg->nh_entries[0]; + nh_grp_entry_stats_inc(nhge0); + return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) @@ -1225,6 +1446,7 @@ static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1798,6 +2020,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, newg->has_v4 = true; list_del(&nhges[i].nh_list); + new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; @@ -1813,6 +2036,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); + free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through @@ -2477,6 +2701,13 @@ static struct nexthop *nexthop_create_group(struct net *net, if (nhi->family == AF_INET) nhg->has_v4 = true; + nhg->nh_entries[i].stats = + netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); + if (!nhg->nh_entries[i].stats) { + err = -ENOMEM; + nexthop_put(nhe); + goto out_no_nh; + } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = entry[i].weight + 1; list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); @@ -2509,6 +2740,9 @@ static struct nexthop *nexthop_create_group(struct net *net, if (cfg->nh_fdb) nhg->fdb_nh = 1; + if (cfg->nh_hw_stats) + nhg->hw_stats = true; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -2516,6 +2750,7 @@ static struct nexthop *nexthop_create_group(struct net *net, out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); + free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } @@ -2850,6 +3085,9 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); + if (tb[NHA_HW_STATS_ENABLE]) + cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); + /* no other attributes should be set */ goto out; } @@ -2941,6 +3179,10 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } + if (tb[NHA_HW_STATS_ENABLE]) { + NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); + goto out; + } err = 0; out: @@ -2966,9 +3208,9 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, - struct nlattr **tb, u32 *id, - struct netlink_ext_ack *extack) +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, u32 *op_flags, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); @@ -2988,22 +3230,12 @@ static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } - return 0; -} - -static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; - int err; - - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get) - 1, - rtm_nh_policy_get, extack); - if (err < 0) - return err; + if (tb[NHA_OP_FLAGS]) + *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + *op_flags = 0; - return __nh_valid_get_del_req(nlh, tb, id, extack); + return 0; } /* rtnl */ @@ -3011,16 +3243,23 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[NHA_MAX + 1]; struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, + rtm_nh_policy_del, extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3038,12 +3277,19 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NHA_MAX + 1]; struct sk_buff *skb = NULL; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, + rtm_nh_policy_get, extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3058,7 +3304,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; @@ -3079,6 +3325,7 @@ struct nh_dump_filter { bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; + u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -3150,6 +3397,11 @@ static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, return -EINVAL; } + if (tb[NHA_OP_FLAGS]) + filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + filter->op_flags = 0; + return 0; } @@ -3157,11 +3409,10 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; + struct nlattr *tb[NHA_MAX + 1]; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_dump) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_dump, cb->extack); if (err < 0) return err; @@ -3223,7 +3474,7 @@ static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ @@ -3241,10 +3492,6 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) err = rtm_dump_walk_nexthops(skb, cb, root, ctx, &rtm_dump_nexthop_cb, &filter); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3300,11 +3547,10 @@ static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct netlink_callback *cb) { struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; + struct nlattr *tb[NHA_MAX + 1]; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_dump_bucket, NULL); if (err < 0) return err; @@ -3439,11 +3685,6 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, &rtm_dump_nexthop_bucket_cb, &dd); } - if (err < 0) { - if (likely(skb->len)) - err = skb->len; - } - cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3474,16 +3715,16 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, u32 *id, u16 *bucket_index, struct netlink_ext_ack *extack) { - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; + struct nlattr *tb[NHA_MAX + 1]; + u32 op_flags; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_get_bucket, extack); if (err < 0) return err; - err = __nh_valid_get_del_req(nlh, tb, id, extack); + err = nh_valid_get_del_req(nlh, tb, id, &op_flags, extack); if (err) return err; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 7d2bdfd7e7d7..42ac434cfcfa 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -175,6 +175,13 @@ static int raw_v4_input(struct net *net, struct sk_buff *skb, if (!raw_v4_match(net, sk, iph->protocol, iph->saddr, iph->daddr, dif, sdif)) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = 1; if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) && ip_mc_sf_allow(sk, iph->daddr, iph->saddr, @@ -310,7 +317,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); raw_rcv_skb(sk, skb); return 0; @@ -353,6 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c82dc42f57c6..d20b62d52171 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/rps.h> /* Track pending CMSGs. */ enum { @@ -974,7 +975,7 @@ int tcp_wmem_schedule(struct sock *sk, int copy) * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ - left = sock_net(sk)->ipv4.sysctl_tcp_wmem[0] - sk->sk_wmem_queued; + left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); @@ -4010,11 +4011,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; @@ -4651,7 +4652,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); - CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 113); + CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 105); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 8311c38267b5..ebe4722bb020 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -204,7 +204,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb) goto out; hlen = off + thlen; - if (skb_gro_header_hard(skb, hlen)) { + if (!skb_gro_may_pull(skb, hlen)) { th = skb_gro_header_slow(skb, hlen, off); if (unlikely(!th)) goto out; @@ -299,18 +299,20 @@ out: void tcp_gro_complete(struct sk_buff *skb) { struct tcphdr *th = tcp_hdr(skb); + struct skb_shared_info *shinfo; + + if (skb->encapsulation) + skb->inner_transport_header = skb->transport_header; skb->csum_start = (unsigned char *)th - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); skb->ip_summed = CHECKSUM_PARTIAL; - skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + shinfo = skb_shinfo(skb); + shinfo->gso_segs = NAPI_GRO_CB(skb)->count; if (th->cwr) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; - - if (skb->encapsulation) - skb->inner_transport_header = skb->transport_header; + shinfo->gso_type |= SKB_GSO_TCP_ECN; } EXPORT_SYMBOL(tcp_gro_complete); @@ -335,24 +337,22 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr, iph->daddr, 0); - skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; - if (NAPI_GRO_CB(skb)->is_atomic) - skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_FIXEDID; + skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 | + (NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID); tcp_gro_complete(skb); return 0; } -static const struct net_offload tcpv4_offload = { - .callbacks = { - .gso_segment = tcp4_gso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - }, -}; - int __init tcpv4_offload_init(void) { - return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); + net_hotdata.tcpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp4_gso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.tcpv4_offload, IPPROTO_TCP); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a8acea17b4e5..661d0e0d273f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -411,8 +411,6 @@ INDIRECT_CALLABLE_SCOPE u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 udp_ehash_secret __read_mostly; - net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, @@ -2570,11 +2568,12 @@ int udp_v4_early_demux(struct sk_buff *skb) uh->source, iph->saddr, dif, sdif); } - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return 0; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) @@ -2793,11 +2792,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = udp_test_bit(CORK, sk); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6c95d28d0c4a..b9880743765c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -737,15 +737,14 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } -static const struct net_offload udpv4_offload = { - .callbacks = { - .gso_segment = udp4_ufo_fragment, - .gro_receive = udp4_gro_receive, - .gro_complete = udp4_gro_complete, - }, -}; - int __init udpv4_offload_init(void) { - return inet_add_offload(&udpv4_offload, IPPROTO_UDP); + net_hotdata.udpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp4_ufo_fragment, + .gro_receive = udp4_gro_receive, + .gro_complete = udp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index c54676998eb6..dae35101d189 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -58,7 +58,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) return -iph->protocol; #endif - __skb_push(skb, skb->data - skb_network_header(skb)); + __skb_push(skb, -skb_network_offset(skb)); iph->tot_len = htons(skb->len); ip_send_check(iph); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f84e6ecf19f..247bd4d8ee45 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -717,7 +717,7 @@ errout: static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -793,8 +793,6 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, ctx->all_default++; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; rcu_read_unlock(); return err; } @@ -2730,7 +2728,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; - ifp->tstamp = now; + WRITE_ONCE(ifp->tstamp, now); flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); @@ -4898,13 +4896,13 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; - ifp->tstamp = jiffies; - ifp->valid_lft = cfg->valid_lft; - ifp->prefered_lft = cfg->preferred_lft; - ifp->ifa_proto = cfg->ifa_proto; + WRITE_ONCE(ifp->tstamp, jiffies); + WRITE_ONCE(ifp->valid_lft, cfg->valid_lft); + WRITE_ONCE(ifp->prefered_lft, cfg->preferred_lft); + WRITE_ONCE(ifp->ifa_proto, cfg->ifa_proto); if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) - ifp->rt_priority = cfg->rt_priority; + WRITE_ONCE(ifp->rt_priority, cfg->rt_priority); if (new_peer) ifp->peer_addr = *cfg->peer_pfx; @@ -5125,17 +5123,21 @@ struct inet6_fill_args { enum addr_type_t type; }; -static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, +static int inet6_fill_ifaddr(struct sk_buff *skb, + const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; + struct nlmsghdr *nlh; u32 preferred, valid; + u32 flags, priority; + u8 proto; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + flags = READ_ONCE(ifa->flags); put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); @@ -5143,13 +5145,14 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; - spin_lock_bh(&ifa->lock); - if (!((ifa->flags&IFA_F_PERMANENT) && - (ifa->prefered_lft == INFINITY_LIFE_TIME))) { - preferred = ifa->prefered_lft; - valid = ifa->valid_lft; + preferred = READ_ONCE(ifa->prefered_lft); + valid = READ_ONCE(ifa->valid_lft); + + if (!((flags & IFA_F_PERMANENT) && + (preferred == INFINITY_LIFE_TIME))) { if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->tstamp)/HZ; + long tval = (jiffies - READ_ONCE(ifa->tstamp)) / HZ; + if (preferred > tval) preferred -= tval; else @@ -5165,28 +5168,29 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } - spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; - } else + } else { if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; + } - if (ifa->rt_priority && - nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) + priority = READ_ONCE(ifa->rt_priority); + if (priority && nla_put_u32(skb, IFA_RT_PRIORITY, priority)) goto error; - if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + if (put_cacheinfo(skb, ifa->cstamp, READ_ONCE(ifa->tstamp), + preferred, valid) < 0) goto error; - if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + if (nla_put_u32(skb, IFA_FLAGS, flags) < 0) goto error; - if (ifa->ifa_proto && - nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + proto = READ_ONCE(ifa->ifa_proto); + if (proto && nla_put_u8(skb, IFA_PROTO, proto)) goto error; nlmsg_end(skb, nlh); @@ -5197,12 +5201,13 @@ error: return -EMSGSIZE; } -static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, +static int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; - u8 scope = RT_SCOPE_UNIVERSE; int ifindex = ifmca->idev->dev->ifindex; + u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5220,7 +5225,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || - put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5230,13 +5235,14 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return 0; } -static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, +static int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; - struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5254,7 +5260,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || - put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + put_cacheinfo(skb, ifaca->aca_cstamp, READ_ONCE(ifaca->aca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5265,24 +5271,23 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, } /* called with rcu_read_lock() */ -static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, +static int in6_dump_addrs(const struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, struct inet6_fill_args *fillargs) { - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; + const struct ifmcaddr6 *ifmca; + const struct ifacaddr6 *ifaca; int ip_idx = 0; - int err = 1; + int err = 0; - read_lock_bh(&idev->lock); switch (fillargs->type) { case UNICAST_ADDR: { - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ - list_for_each_entry(ifa, &idev->addr_list, if_list) { - if (ip_idx < s_ip_idx) + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { + if (ip_idx < *s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) @@ -5294,27 +5299,25 @@ next: break; } case MULTICAST_ADDR: - read_unlock_bh(&idev->lock); fillargs->event = RTM_GETMULTICAST; /* multicast address */ for (ifmca = rcu_dereference(idev->mc_list); ifmca; ifmca = rcu_dereference(ifmca->next), ip_idx++) { - if (ip_idx < s_ip_idx) + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } - read_lock_bh(&idev->lock); break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ for (ifaca = rcu_dereference(idev->ac_list); ifaca; ifaca = rcu_dereference(ifaca->aca_next), ip_idx++) { - if (ip_idx < s_ip_idx) + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) @@ -5324,8 +5327,7 @@ next: default: break; } - read_unlock_bh(&idev->lock); - cb->args[2] = ip_idx; + *s_ip_idx = err ? ip_idx : 0; return err; } @@ -5388,6 +5390,7 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *tgt_net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, @@ -5396,72 +5399,52 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .netnsid = -1, .type = type, }; - struct net *tgt_net = sock_net(skb->sk); - int idx, s_idx, s_ip_idx; - int h, s_h; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - rcu_read_lock(); if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) { - err = -ENODEV; - goto put_tgt_net; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) + goto done; idev = __in6_dev_get(dev); - if (idev) { - err = in6_dump_addrs(idev, skb, cb, s_ip_idx, + if (idev) + err = in6_dump_addrs(idev, skb, cb, + &ctx->ip_idx, &fillargs); - if (err > 0) - err = 0; - } - goto put_tgt_net; + goto done; } } cb->seq = inet6_base_seq(tgt_net); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (in6_dump_addrs(idev, skb, cb, s_ip_idx, - &fillargs) < 0) - goto done; -cont: - idx++; - } + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; } done: - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: rcu_read_unlock(); if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len ? : err; + return err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -6158,11 +6141,8 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) break; - } } rcu_read_unlock(); @@ -7474,15 +7454,18 @@ int __init addrconf_init(void) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST, - NULL, inet6_dump_ifmcaddr, 0); + NULL, inet6_dump_ifmcaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST, - NULL, inet6_dump_ifacaddr, 0); + NULL, inet6_dump_ifacaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b90d46533cdc..8041dc181bd4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,7 @@ #include <net/xfrm.h> #include <net/ioam6.h> #include <net/rawv6.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/mroute6.h> diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 26f1e4a5ade0..6789623b2b0d 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -804,7 +804,7 @@ looped_back: ip6_route_input(skb); if (skb_dst(skb)->error) { - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; } @@ -821,7 +821,7 @@ looped_back: goto looped_back; } - skb_push(skb, skb->data - skb_network_header(skb)); + skb_push(skb, -skb_network_offset(skb)); dst_input(skb); return -1; @@ -883,14 +883,6 @@ void ipv6_exthdrs_exit(void) Hop-by-hop options. **********************************/ -/* - * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input(). - */ -static inline struct net *ipv6_skb_net(struct sk_buff *skb) -{ - return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev); -} - /* Router Alert as of RFC 2711 */ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) @@ -941,7 +933,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) goto drop; /* Ignore if the IOAM namespace is unknown */ - ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id); + ns = ioam6_namespace(dev_net(skb->dev), trace->namespace_id); if (!ns) goto ignore; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b0e8d278e8a9..2e81383b663b 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -14,6 +14,7 @@ #include <linux/random.h> #include <net/addrconf.h> +#include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -25,16 +26,13 @@ u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { - static u32 inet6_ehash_secret __read_mostly; - static u32 ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); - net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); + net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; - fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cca64c7809be..b41e35af69ea 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -419,14 +419,6 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) return inet_gro_complete(skb, nhoff); } -static struct packet_offload ipv6_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IPV6), - .callbacks = { - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, - }, -}; static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -486,7 +478,15 @@ static int __init ipv6_offload_init(void) if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); - dev_add_offload(&ipv6_packet_offload); + net_hotdata.ipv6_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index b9dd3a66e423..02eeca5492cd 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1925,7 +1925,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; skb->tstamp = cork->base.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5fd07581efaf..e9cc315832cb 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -247,7 +247,6 @@ static void ip6_dev_free(struct net_device *dev) gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); - free_percpu(dev->tstats); } static int ip6_tnl_create2(struct net_device *dev) @@ -1848,6 +1847,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->features |= NETIF_F_LLTX; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; @@ -1873,13 +1873,10 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t->dev = dev; t->net = dev_net(dev); - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) - goto free_stats; + return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) @@ -1903,9 +1900,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) destroy_dst: dst_cache_destroy(&t->dst_cache); -free_stats: - free_percpu(dev->tstats); - dev->tstats = NULL; return ret; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index f61d977ac052..d4c28ec1bc51 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -948,6 +948,8 @@ done: if (optlen < sizeof(int)) goto e_inval; retv = ip6_ra_control(sk, val); + if (retv == 0) + inet6_assign_bit(RTALERT, sk, valbool); break; case IPV6_FLOWLABEL_MGR: retv = ipv6_flowlabel_opt(sk, optval, optlen); @@ -1445,6 +1447,10 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->rxopt.bits.recvfragsize; break; + case IPV6_ROUTER_ALERT: + val = inet6_test_bit(RTALERT, sk); + break; + case IPV6_ROUTER_ALERT_ISOLATE: val = inet6_test_bit(RTALERT_ISOLATE, sk); break; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b2dd48911c8d..1a51a44571c3 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -327,9 +327,9 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto err; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 76e6eb3b643d..ca49e6617afa 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -160,6 +160,13 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) if (!raw_v6_match(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb))) continue; + + if (atomic_read(&sk->sk_rmem_alloc) >= + READ_ONCE(sk->sk_rcvbuf)) { + atomic_inc(&sk->sk_drops); + continue; + } + delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: @@ -615,7 +622,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5ebc47da1000..acb4f119e11f 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -272,9 +272,9 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, if (!reasm_data) goto out_oom; - payload_len = ((skb->data - skb_network_header(skb)) - + payload_len = -skb_network_offset(skb) - sizeof(struct ipv6hdr) + fq->q.len - - sizeof(struct frag_hdr)); + sizeof(struct frag_hdr); if (payload_len > IPV6_MAXPLEN) goto out_oversize; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2cecb1c5a58f..1f4b935a0e57 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5343,19 +5343,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5363,6 +5351,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5423,8 +5417,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f677f0fa5196..3f4cba49e9ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -58,6 +58,7 @@ #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/busy_poll.h> #include <linux/proc_fs.h> @@ -2367,11 +2368,6 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -static const struct inet6_protocol tcpv6_protocol = { - .handler = tcp_v6_rcv, - .err_handler = tcp_v6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, @@ -2408,7 +2404,12 @@ int __init tcpv6_init(void) { int ret; - ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); + net_hotdata.tcpv6_protocol = (struct inet6_protocol) { + .handler = tcp_v6_rcv, + .err_handler = tcp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; @@ -2433,7 +2434,7 @@ out_tcpv6_pernet_subsys: out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } @@ -2441,5 +2442,5 @@ void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index bf0c957e4b5e..4b07d1e6c952 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,15 +66,15 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, return tcp_gso_segment(skb, features); } -static const struct net_offload tcpv6_offload = { - .callbacks = { - .gso_segment = tcp6_gso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, - }, -}; int __init tcpv6_offload_init(void) { - return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); + net_hotdata.tcpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp6_gso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.tcpv6_offload, IPPROTO_TCP); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3f2249b4cd5f..7c1e6469d091 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,9 +79,6 @@ u32 udp6_ehashfn(const struct net *net, const struct in6_addr *faddr, const __be16 fport) { - static u32 udp6_ehash_secret __read_mostly; - static u32 udp_ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, @@ -1101,11 +1098,12 @@ void udp_v6_early_demux(struct sk_buff *skb) else return; - if (!sk || !refcount_inc_not_zero(&sk->sk_refcnt)) + if (!sk) return; skb->sk = sk; - skb->destructor = sock_efree; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; dst = rcu_dereference(sk->sk_rx_dst); if (dst) @@ -1702,11 +1700,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -static const struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1803,7 +1796,12 @@ int __init udpv6_init(void) { int ret; - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + net_hotdata.udpv6_protocol = (struct inet6_protocol) { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; @@ -1814,12 +1812,12 @@ out: return ret; out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6b95ba241ebe..312bcaeea96f 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -192,20 +192,19 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } -static const struct net_offload udpv6_offload = { - .callbacks = { - .gso_segment = udp6_ufo_fragment, - .gro_receive = udp6_gro_receive, - .gro_complete = udp6_gro_complete, - }, -}; - -int udpv6_offload_init(void) +int __init udpv6_offload_init(void) { - return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); + net_hotdata.udpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp6_ufo_fragment, + .gro_receive = udp6_gro_receive, + .gro_complete = udp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { - return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); + return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 6e36e5047fba..a17d783dc7c0 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -43,7 +43,7 @@ static int xfrm6_transport_finish2(struct net *net, struct sock *sk, int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); - int nhlen = skb->data - skb_network_header(skb); + int nhlen = -skb_network_offset(skb); skb_network_header(skb)[IP6CB(skb)->nhoff] = XFRM_MODE_SKB_CB(skb)->protocol; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f6cb94f82cc3..bf140ef781c1 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -355,10 +355,7 @@ static int __init xfrm6_tunnel_init(void) { int rv; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL); + xfrm6_tunnel_spi_kmem = KMEM_CACHE(xfrm6_tunnel_spi, SLAB_HWCACHE_ALIGN); if (!xfrm6_tunnel_spi_kmem) return -ENOMEM; rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index dc46f17a3187..2f191e50d4fc 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1153,10 +1153,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f011af6601c9..6146e4e67bbb 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1356,11 +1356,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 0744113f3535..f03452dc716d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1241,6 +1241,30 @@ ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, return 0; } +static u8 ieee80211_num_beaconing_links(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_link_data *link; + u8 link_id, num = 0; + + if (sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_P2P_GO) + return num; + + if (!sdata->vif.valid_links) + return num; + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + + if (sdata_dereference(link->u.ap.beacon, sdata)) + num++; + } + + return num; +} + static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { @@ -1470,7 +1494,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_SSID); ieee80211_link_info_change_notify(sdata, link, changed); - netif_carrier_on(dev); + if (ieee80211_num_beaconing_links(sdata) <= 1) + netif_carrier_on(dev); + list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_on(vlan->dev); @@ -1563,6 +1589,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct ieee80211_bss_conf *link_conf = link->conf; + LIST_HEAD(keys); lockdep_assert_wiphy(local->hw.wiphy); @@ -1580,10 +1607,10 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, /* abort any running channel switch or color change */ link_conf->csa_active = false; link_conf->color_change_active = false; - if (link->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link->csa_block_tx = false; + sdata->csa_blocked_tx = false; } ieee80211_free_next_beacon(link); @@ -1591,7 +1618,9 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); - netif_carrier_off(dev); + + if (ieee80211_num_beaconing_links(sdata) <= 1) + netif_carrier_off(dev); /* remove beacon and probe response */ sdata->u.ap.active = false; @@ -1617,7 +1646,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, link_conf->bssid_indicator = 0; __sta_info_flush(sdata, true, link_id); - ieee80211_free_keys(sdata, true); + + ieee80211_remove_link_keys(link, &keys); + if (!list_empty(&keys)) { + synchronize_net(); + ieee80211_free_key_list(local, &keys); + } link_conf->enable_beacon = false; sdata->beacon_rate_set = false; @@ -1867,7 +1901,7 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } - ieee80211_sta_set_rx_nss(link_sta); + ieee80211_sta_init_nss(link_sta); return ret; } @@ -3155,8 +3189,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return -EINVAL; - if (ieee80211_vif_is_mld(&sdata->vif) && - !(sdata->vif.active_links & BIT(link->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; old_req = link->u.mgd.req_smps; @@ -3209,7 +3242,7 @@ int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, if (err) link->u.mgd.req_smps = old_req; else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) - ieee80211_teardown_tdls_peers(sdata); + ieee80211_teardown_tdls_peers(link); return err; } @@ -3256,33 +3289,57 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, return 0; } +static void ieee80211_set_cqm_rssi_link(struct ieee80211_sub_if_data *sdata, + struct ieee80211_link_data *link, + s32 rssi_thold, u32 rssi_hyst, + s32 rssi_low, s32 rssi_high) +{ + struct ieee80211_bss_conf *conf; + + if (!link || !link->conf) + return; + + conf = link->conf; + + if (rssi_thold && rssi_hyst && + rssi_thold == conf->cqm_rssi_thold && + rssi_hyst == conf->cqm_rssi_hyst) + return; + + conf->cqm_rssi_thold = rssi_thold; + conf->cqm_rssi_hyst = rssi_hyst; + conf->cqm_rssi_low = rssi_low; + conf->cqm_rssi_high = rssi_high; + link->u.mgd.last_cqm_event_signal = 0; + + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) + return; + + if (sdata->u.mgd.associated && + (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_CQM); +} + static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; - struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; - - if (rssi_thold == bss_conf->cqm_rssi_thold && - rssi_hyst == bss_conf->cqm_rssi_hyst) - return 0; + int link_id; - if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER && - !(sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) + if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER && + !(vif->driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) return -EOPNOTSUPP; - bss_conf->cqm_rssi_thold = rssi_thold; - bss_conf->cqm_rssi_hyst = rssi_hyst; - bss_conf->cqm_rssi_low = 0; - bss_conf->cqm_rssi_high = 0; - sdata->deflink.u.mgd.last_cqm_event_signal = 0; + /* For MLD, handle CQM change on all the active links */ + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct ieee80211_link_data *link = + sdata_dereference(sdata->link[link_id], sdata); - /* tell the driver upon association, unless already associated */ - if (sdata->u.mgd.associated && - sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_CQM); + ieee80211_set_cqm_rssi_link(sdata, link, rssi_thold, rssi_hyst, + 0, 0); + } return 0; } @@ -3293,22 +3350,19 @@ static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; - struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; + int link_id; - if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER) + if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER) return -EOPNOTSUPP; - bss_conf->cqm_rssi_low = rssi_low; - bss_conf->cqm_rssi_high = rssi_high; - bss_conf->cqm_rssi_thold = 0; - bss_conf->cqm_rssi_hyst = 0; - sdata->deflink.u.mgd.last_cqm_event_signal = 0; + /* For MLD, handle CQM change on all the active links */ + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct ieee80211_link_data *link = + sdata_dereference(sdata->link[link_id], sdata); - /* tell the driver upon association, unless already associated */ - if (sdata->u.mgd.associated && - sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI) - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_CQM); + ieee80211_set_cqm_rssi_link(sdata, link, 0, 0, + rssi_low, rssi_high); + } return 0; } @@ -3595,7 +3649,7 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_t struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - sdata->deflink.csa_block_tx = block_tx; + sdata->csa_blocked_tx = block_tx; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } @@ -3681,10 +3735,10 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) ieee80211_link_info_change_notify(sdata, link_data, changed); - if (link_data->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link_data->csa_block_tx = false; + sdata->csa_blocked_tx = false; } err = drv_post_channel_switch(link_data); @@ -3877,7 +3931,9 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = params->chandef }; struct ieee80211_local *local = sdata->local; - struct ieee80211_channel_switch ch_switch; + struct ieee80211_channel_switch ch_switch = { + .link_id = params->link_id, + }; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; struct ieee80211_bss_conf *link_conf; @@ -3958,12 +4014,14 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, } link_data->csa_chanreq = chanreq; - link_data->csa_block_tx = params->block_tx; link_conf->csa_active = true; - if (link_data->csa_block_tx) + if (params->block_tx && + !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = true; + } cfg80211_ch_switch_started_notify(sdata->dev, &link_data->csa_chanreq.oper, 0, diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 38acdc458c7c..80e4b9784131 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1701,8 +1701,7 @@ int ieee80211_link_use_channel(struct ieee80211_link_data *link, lockdep_assert_wiphy(local->hw.wiphy); - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link->link_id))) { + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) { ieee80211_link_update_chanreq(link, chanreq); return 0; } diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 74be49191e70..2f68e92a7404 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019, 2021-2023 Intel Corporation + * Copyright (C) 2018 - 2019, 2021-2024 Intel Corporation */ #include <linux/debugfs.h> @@ -498,6 +498,7 @@ static const char *hw_flag_names[] = { FLAG(DETECTS_COLOR_COLLISION), FLAG(MLO_MCAST_MULTI_LINK_TX), FLAG(DISALLOW_PUNCTURING), + FLAG(HANDLES_QUIET_CSA), #undef FLAG }; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 3b7f70073fc3..dce37ba8ebe3 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2015 Intel Deutschland GmbH - * Copyright (C) 2022-2023 Intel Corporation + * Copyright (C) 2022-2024 Intel Corporation */ #include <net/mac80211.h> #include "ieee80211_i.h" @@ -214,8 +214,7 @@ int drv_conf_tx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; if (params->cw_min == 0 || params->cw_min > params->cw_max) { @@ -315,8 +314,7 @@ int drv_assign_vif_chanctx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_conf->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_conf->link_id)) return 0; trace_drv_assign_vif_chanctx(local, sdata, link_conf, ctx); @@ -343,8 +341,7 @@ void drv_unassign_vif_chanctx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_conf->link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_conf->link_id)) return; trace_drv_unassign_vif_chanctx(local, sdata, link_conf, ctx); @@ -461,8 +458,7 @@ void drv_link_info_changed(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return; - if (sdata->vif.active_links && - !(sdata->vif.active_links & BIT(link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_id)) return; trace_drv_link_info_changed(local, sdata, info, changed); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index e20c64edb880..5d078c0a2323 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016 Intel Deutschland GmbH -* Copyright (C) 2018 - 2019, 2021 - 2023 Intel Corporation +* Copyright (C) 2018-2019, 2021-2024 Intel Corporation */ #ifndef __MAC80211_DRIVER_OPS @@ -1180,8 +1180,9 @@ drv_post_channel_switch(struct ieee80211_link_data *link) } static inline void -drv_abort_channel_switch(struct ieee80211_sub_if_data *sdata) +drv_abort_channel_switch(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; might_sleep(); @@ -1193,7 +1194,8 @@ drv_abort_channel_switch(struct ieee80211_sub_if_data *sdata) trace_drv_abort_channel_switch(local, sdata); if (local->ops->abort_channel_switch) - local->ops->abort_channel_switch(&local->hw, &sdata->vif); + local->ops->abort_channel_switch(&local->hw, &sdata->vif, + link->conf); } static inline void diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4bec625a84d1..b6fead612b66 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1034,7 +1034,6 @@ struct ieee80211_link_data { struct ieee80211_key __rcu *default_beacon_key; struct wiphy_work csa_finalize_work; - bool csa_block_tx; bool operating_11g_mode; @@ -1093,6 +1092,8 @@ struct ieee80211_sub_if_data { unsigned long state; + bool csa_blocked_tx; + char name[IFNAMSIZ]; struct ieee80211_fragment_cache frags; @@ -1766,12 +1767,6 @@ struct ieee802_11_elems { size_t ml_basic_len; size_t ml_reconf_len; - /* The basic Multi-Link element in the original IEs */ - const struct element *ml_basic_elem; - - /* The reconfiguration Multi-Link element in the original IEs */ - const struct element *ml_reconf_elem; - u8 ttlm_num; /* @@ -1784,14 +1779,6 @@ struct ieee802_11_elems { /* whether/which parse error occurred while retrieving these elements */ u8 parse_error; - - /* - * scratch buffer that can be used for various element parsing related - * tasks, e.g., element de-fragmentation etc. - */ - size_t scratch_len; - u8 *scratch_pos; - u8 scratch[] __counted_by(scratch_len); }; static inline struct ieee80211_local *hw_to_local( @@ -2153,7 +2140,7 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta); -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta); +void ieee80211_sta_init_nss(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); enum nl80211_chan_width @@ -2624,7 +2611,7 @@ int ieee80211_tdls_channel_switch(struct wiphy *wiphy, struct net_device *dev, void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); -void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata); +void ieee80211_teardown_tdls_peers(struct ieee80211_link_data *link); void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason); void diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b75b83a5142b..395de62d9cb2 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2024 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -544,10 +544,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do sdata->vif.bss_conf.csa_active = false; if (sdata->vif.type == NL80211_IFTYPE_STATION) sdata->deflink.u.mgd.csa_waiting_bcn = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa_finalize_work); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index a2cce62c97b7..eecdd2265eaa 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -6,7 +6,7 @@ * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright 2018-2020, 2022-2023 Intel Corporation + * Copyright 2018-2020, 2022-2024 Intel Corporation */ #include <crypto/utils.h> @@ -1372,12 +1372,19 @@ EXPORT_SYMBOL_GPL(ieee80211_remove_key); struct ieee80211_key_conf * ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, - struct ieee80211_key_conf *keyconf) + struct ieee80211_key_conf *keyconf, + int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; int err; + struct ieee80211_link_data *link_data = + link_id < 0 ? &sdata->deflink : + sdata_dereference(sdata->link[link_id], sdata); + + if (WARN_ON(!link_data)) + return ERR_PTR(-EINVAL); if (WARN_ON(!local->wowlan)) return ERR_PTR(-EINVAL); @@ -1394,8 +1401,9 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; - /* FIXME: this function needs to get a link ID */ - err = ieee80211_key_link(key, &sdata->deflink, NULL); + key->conf.link_id = link_id; + + err = ieee80211_key_link(key, link_data, NULL); if (err) return ERR_PTR(err); diff --git a/net/mac80211/link.c b/net/mac80211/link.c index 87a413374ece..685ec66b4264 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -356,7 +356,7 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, link = sdata_dereference(sdata->link[link_id], sdata); - /* FIXME: kill TDLS connections on the link */ + ieee80211_teardown_tdls_peers(link); ieee80211_link_release_channel(link); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 5f2e9f5e1779..47a2cba8313f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1319,7 +1319,8 @@ static size_t ieee80211_assoc_link_elems(struct ieee80211_sub_if_data *sdata, offset); if (sband->band != NL80211_BAND_6GHZ && - assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_VHT) { + assoc_data->link[link_id].conn.mode >= IEEE80211_CONN_MODE_VHT && + sband->vht_cap.vht_supported) { bool mu_mimo_owner = ieee80211_add_vht_ie(sdata, skb, sband, &assoc_data->link[link_id].ap_vht_cap, @@ -1925,19 +1926,14 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link) WARN_ON(!link->conf->csa_active); - if (link->csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - link->csa_block_tx = false; + sdata->csa_blocked_tx = false; } link->conf->csa_active = false; link->u.mgd.csa_waiting_bcn = false; - /* - * If the CSA IE is still present on the beacon after the switch, - * we need to consider it as a new CSA (possibly to self). - */ - link->u.mgd.beacon_crc_valid = false; ret = drv_post_channel_switch(link); if (ret) { @@ -1996,14 +1992,15 @@ ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link) ieee80211_link_unreserve_chanctx(link); - if (link->csa_block_tx) + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = false; + } - link->csa_block_tx = false; link->conf->csa_active = false; - drv_abort_channel_switch(sdata); + drv_abort_channel_switch(link); } static void @@ -2020,7 +2017,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, struct ieee80211_chanctx *chanctx; enum nl80211_band current_band; struct ieee80211_csa_ie csa_ie; - struct ieee80211_channel_switch ch_switch; + struct ieee80211_channel_switch ch_switch = { + .link_id = link->link_id, + }; struct ieee80211_bss *bss; unsigned long timeout; int res; @@ -2049,18 +2048,32 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, if (res < 0) goto drop_connection; - if (beacon && link->conf->csa_active && - !link->u.mgd.csa_waiting_bcn) { - if (res) + if (link->conf->csa_active) { + /* already processing - disregard action frames */ + if (!beacon) + return; + + if (link->u.mgd.csa_waiting_bcn) { + ieee80211_chswitch_post_beacon(link); + /* + * If the CSA IE is still present in the beacon after + * the switch, we need to consider it as a new CSA + * (possibly to self) - this happens by not returning + * here so we'll get to the check below. + */ + } else if (res) { ieee80211_sta_abort_chanswitch(link); - else + return; + } else { drv_channel_switch_rx_beacon(sdata, &ch_switch); - return; - } else if (link->conf->csa_active || res) { - /* disregard subsequent announcements if already processing */ - return; + return; + } } + /* nothing to do at all - no active CSA nor a new one */ + if (res) + return; + if (link->conf->chanreq.oper.chan->band != csa_ie.chanreq.oper.chan->band) { sdata_info(sdata, @@ -2102,12 +2115,13 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, } /* - * Drop all TDLS peers - either we disconnect or move to a different - * channel from this point on. There's no telling what our peer will do. + * Drop all TDLS peers on the affected link - either we disconnect or + * move to a different channel from this point on. There's no telling + * what our peer will do. * The TDLS WIDER_BW scenario is also problematic, as peers might now * have an incompatible wider chandef. */ - ieee80211_teardown_tdls_peers(sdata); + ieee80211_teardown_tdls_peers(link); conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); @@ -2142,13 +2156,15 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, link->conf->csa_active = true; link->csa_chanreq = csa_ie.chanreq; - link->csa_block_tx = csa_ie.mode; link->u.mgd.csa_ignored_same_chan = false; link->u.mgd.beacon_crc_valid = false; - if (link->csa_block_tx) + if (csa_ie.mode && + !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { ieee80211_stop_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_tx = true; + } cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chanreq.oper, link->link_id, csa_ie.count, @@ -2176,7 +2192,8 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, * reset when the disconnection worker runs. */ link->conf->csa_active = true; - link->csa_block_tx = csa_ie.mode; + sdata->csa_blocked_tx = + csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); @@ -3230,10 +3247,10 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.csa_active = false; sdata->deflink.u.mgd.csa_waiting_bcn = false; sdata->deflink.u.mgd.csa_ignored_same_chan = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } /* existing TX TSPEC sessions no longer exist */ @@ -3546,9 +3563,12 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) if (!ifmgd->associated) return; - /* in MLO assume we have a link where we can TX the frame */ - tx = ieee80211_vif_is_mld(&sdata->vif) || - !sdata->deflink.csa_block_tx; + /* + * MLO drivers should have HANDLES_QUIET_CSA, so that csa_blocked_tx + * is always false; if they don't then this may try to transmit the + * frame but queues will be stopped. + */ + tx = !sdata->csa_blocked_tx; if (!ifmgd->driver_disconnect) { unsigned int link_id; @@ -3581,10 +3601,10 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) /* the other links will be destroyed */ sdata->vif.bss_conf.csa_active = false; sdata->deflink.u.mgd.csa_waiting_bcn = false; - if (sdata->deflink.csa_block_tx) { + if (sdata->csa_blocked_tx) { ieee80211_wake_vif_queues(local, sdata, IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->deflink.csa_block_tx = false; + sdata->csa_blocked_tx = false; } ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, @@ -5751,9 +5771,7 @@ out: static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, struct ieee802_11_elems *elems) { - const struct ieee80211_multi_link_elem *ml; const struct element *sub; - ssize_t ml_len; unsigned long removed_links = 0; u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {}; u8 link_id; @@ -5762,24 +5780,11 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, if (!ieee80211_vif_is_mld(&sdata->vif) || !elems->ml_reconf) return; - ml_len = cfg80211_defragment_element(elems->ml_reconf_elem, - elems->ie_start, - elems->total_len, - elems->scratch_pos, - elems->scratch + elems->scratch_len - - elems->scratch_pos, - WLAN_EID_FRAGMENT); - if (ml_len < 0) - return; - - elems->ml_reconf = (const void *)elems->scratch_pos; - elems->ml_reconf_len = ml_len; - ml = elems->ml_reconf; - /* Directly parse the sub elements as the common information doesn't * hold any useful information. */ - for_each_mle_subelement(sub, (u8 *)ml, ml_len) { + for_each_mle_subelement(sub, (const u8 *)elems->ml_reconf, + elems->ml_reconf_len) { struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; u8 *pos = prof->variable; u16 control; @@ -6298,9 +6303,6 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, } } - if (link->u.mgd.csa_waiting_bcn) - ieee80211_chswitch_post_beacon(link); - /* * Update beacon timing and dtim count on every beacon appearance. This * will allow the driver to use the most updated values. Do it before @@ -8048,6 +8050,67 @@ ieee80211_setup_assoc_link(struct ieee80211_sub_if_data *sdata, } } +static int +ieee80211_mgd_get_ap_ht_vht_capa(struct ieee80211_sub_if_data *sdata, + struct ieee80211_mgd_assoc_data *assoc_data, + int link_id) +{ + struct cfg80211_bss *cbss = assoc_data->link[link_id].bss; + enum nl80211_band band = cbss->channel->band; + struct ieee80211_supported_band *sband; + const struct element *elem; + int err; + + /* neither HT nor VHT elements used on 6 GHz */ + if (band == NL80211_BAND_6GHZ) + return 0; + + if (assoc_data->link[link_id].conn.mode < IEEE80211_CONN_MODE_HT) + return 0; + + rcu_read_lock(); + elem = ieee80211_bss_get_elem(cbss, WLAN_EID_HT_OPERATION); + if (!elem || elem->datalen < sizeof(struct ieee80211_ht_operation)) { + mlme_link_id_dbg(sdata, link_id, "no HT operation on BSS %pM\n", + cbss->bssid); + err = -EINVAL; + goto out_rcu; + } + assoc_data->link[link_id].ap_ht_param = + ((struct ieee80211_ht_operation *)(elem->data))->ht_param; + rcu_read_unlock(); + + if (assoc_data->link[link_id].conn.mode < IEEE80211_CONN_MODE_VHT) + return 0; + + /* some drivers want to support VHT on 2.4 GHz even */ + sband = sdata->local->hw.wiphy->bands[band]; + if (!sband->vht_cap.vht_supported) + return 0; + + rcu_read_lock(); + elem = ieee80211_bss_get_elem(cbss, WLAN_EID_VHT_CAPABILITY); + /* but even then accept it not being present on the AP */ + if (!elem && band == NL80211_BAND_2GHZ) { + err = 0; + goto out_rcu; + } + if (!elem || elem->datalen < sizeof(struct ieee80211_vht_cap)) { + mlme_link_id_dbg(sdata, link_id, "no VHT capa on BSS %pM\n", + cbss->bssid); + err = -EINVAL; + goto out_rcu; + } + memcpy(&assoc_data->link[link_id].ap_vht_cap, elem->data, + sizeof(struct ieee80211_vht_cap)); + rcu_read_unlock(); + + return 0; +out_rcu: + rcu_read_unlock(); + return err; +} + int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, struct cfg80211_assoc_request *req) { @@ -8129,10 +8192,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, sizeof(ifmgd->s1g_capa_mask)); /* keep some setup (AP STA, channel, ...) if matching */ - if (ifmgd->auth_data) - match_auth = ether_addr_equal(ifmgd->auth_data->ap_addr, - assoc_data->ap_addr) && - ifmgd->auth_data->link_id == req->link_id; + match_auth = ifmgd->auth_data && + ether_addr_equal(ifmgd->auth_data->ap_addr, + assoc_data->ap_addr) && + ifmgd->auth_data->link_id == req->link_id; if (req->ap_mld_addr) { uapsd_supported = true; @@ -8173,7 +8236,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, eth_random_addr(assoc_data->link[i].addr); sband = local->hw.wiphy->bands[link_cbss->channel->band]; - if (match_auth && i == assoc_link_id) + if (match_auth && i == assoc_link_id && link) assoc_data->link[i].conn = link->u.mgd.conn; else assoc_data->link[i].conn = @@ -8192,6 +8255,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, req->links[i].error = err; goto err_free; } + + err = ieee80211_mgd_get_ap_ht_vht_capa(sdata, + assoc_data, i); + if (err) { + err = -EINVAL; + req->links[i].error = err; + goto err_free; + } } assoc_data->wmm = true; @@ -8227,6 +8298,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, &assoc_data->link[0].conn); uapsd_supported = bss->uapsd_supported; + + err = ieee80211_mgd_get_ap_ht_vht_capa(sdata, assoc_data, 0); + if (err) + goto err_free; } assoc_data->spp_amsdu = req->flags & ASSOC_REQ_SPP_AMSDU; diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index 196a882e4c19..55e5497f8978 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -34,12 +34,32 @@ #include "led.h" #include "wep.h" +struct ieee80211_elems_parse { + /* must be first for kfree to work */ + struct ieee802_11_elems elems; + + /* The basic Multi-Link element in the original elements */ + const struct element *ml_basic_elem; + + /* The reconfiguration Multi-Link element in the original elements */ + const struct element *ml_reconf_elem; + + /* + * scratch buffer that can be used for various element parsing related + * tasks, e.g., element de-fragmentation etc. + */ + size_t scratch_len; + u8 *scratch_pos; + u8 scratch[] __counted_by(scratch_len); +}; + static void ieee80211_parse_extension_element(u32 *crc, const struct element *elem, - struct ieee802_11_elems *elems, + struct ieee80211_elems_parse *elems_parse, struct ieee80211_elems_parse_params *params) { + struct ieee802_11_elems *elems = &elems_parse->elems; const void *data = elem->data + 1; bool calc_crc = false; u8 len; @@ -129,19 +149,15 @@ ieee80211_parse_extension_element(u32 *crc, switch (le16_get_bits(mle->control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: - if (elems->ml_basic) { + if (elems_parse->ml_basic_elem) { elems->parse_error |= IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC; break; } - elems->ml_basic_elem = (void *)elem; - elems->ml_basic = data; - elems->ml_basic_len = len; + elems_parse->ml_basic_elem = elem; break; case IEEE80211_ML_CONTROL_TYPE_RECONF: - elems->ml_reconf_elem = (void *)elem; - elems->ml_reconf = data; - elems->ml_reconf_len = len; + elems_parse->ml_reconf_elem = elem; break; default: break; @@ -173,9 +189,10 @@ ieee80211_parse_extension_element(u32 *crc, static u32 _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, - struct ieee802_11_elems *elems, + struct ieee80211_elems_parse *elems_parse, const struct element *check_inherit) { + struct ieee802_11_elems *elems = &elems_parse->elems; const struct element *elem; bool calc_crc = params->filter != 0; DECLARE_BITMAP(seen_elems, 256); @@ -590,7 +607,8 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, case WLAN_EID_EXTENSION: ieee80211_parse_extension_element(calc_crc ? &crc : NULL, - elem, elems, params); + elem, elems_parse, + params); break; case WLAN_EID_S1G_CAPABILITIES: if (params->mode != IEEE80211_CONN_MODE_S1G) @@ -713,20 +731,15 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, return found ? profile_len : 0; } -static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems, - u8 link_id) +static void +ieee80211_mle_get_sta_prof(struct ieee80211_elems_parse *elems_parse, + u8 link_id) { + struct ieee802_11_elems *elems = &elems_parse->elems; const struct ieee80211_multi_link_elem *ml = elems->ml_basic; ssize_t ml_len = elems->ml_basic_len; const struct element *sub; - if (!ml || !ml_len) - return; - - if (le16_get_bits(ml->control, IEEE80211_ML_CONTROL_TYPE) != - IEEE80211_ML_CONTROL_TYPE_BASIC) - return; - for_each_mle_subelement(sub, (u8 *)ml, ml_len) { struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; ssize_t sta_prof_len; @@ -752,26 +765,27 @@ static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems, sta_prof_len = cfg80211_defragment_element(sub, (u8 *)ml, ml_len, - elems->scratch_pos, - elems->scratch + - elems->scratch_len - - elems->scratch_pos, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, IEEE80211_MLE_SUBELEM_FRAGMENT); if (sta_prof_len < 0) return; - elems->prof = (void *)elems->scratch_pos; + elems->prof = (void *)elems_parse->scratch_pos; elems->sta_prof_len = sta_prof_len; - elems->scratch_pos += sta_prof_len; + elems_parse->scratch_pos += sta_prof_len; return; } } -static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, +static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse, struct ieee80211_elems_parse_params *params) { + struct ieee802_11_elems *elems = &elems_parse->elems; struct ieee80211_mle_per_sta_profile *prof; struct ieee80211_elems_parse_params sub = { .mode = params->mode, @@ -783,25 +797,26 @@ static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, const struct element *non_inherit = NULL; const u8 *end; - if (params->link_id == -1) - return; - - ml_len = cfg80211_defragment_element(elems->ml_basic_elem, + ml_len = cfg80211_defragment_element(elems_parse->ml_basic_elem, elems->ie_start, elems->total_len, - elems->scratch_pos, - elems->scratch + - elems->scratch_len - - elems->scratch_pos, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, WLAN_EID_FRAGMENT); if (ml_len < 0) return; - elems->ml_basic = (const void *)elems->scratch_pos; + elems->ml_basic = (const void *)elems_parse->scratch_pos; elems->ml_basic_len = ml_len; + elems_parse->scratch_pos += ml_len; - ieee80211_mle_get_sta_prof(elems, params->link_id); + if (params->link_id == -1) + return; + + ieee80211_mle_get_sta_prof(elems_parse, params->link_id); prof = elems->prof; if (!prof) @@ -826,38 +841,66 @@ static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, sub.start, sub.len); - _ieee802_11_parse_elems_full(&sub, elems, non_inherit); + _ieee802_11_parse_elems_full(&sub, elems_parse, non_inherit); +} + +static void +ieee80211_mle_defrag_reconf(struct ieee80211_elems_parse *elems_parse) +{ + struct ieee802_11_elems *elems = &elems_parse->elems; + ssize_t ml_len; + + ml_len = cfg80211_defragment_element(elems_parse->ml_reconf_elem, + elems->ie_start, + elems->total_len, + elems_parse->scratch_pos, + elems_parse->scratch + + elems_parse->scratch_len - + elems_parse->scratch_pos, + WLAN_EID_FRAGMENT); + if (ml_len < 0) + return; + elems->ml_reconf = (void *)elems_parse->scratch_pos; + elems->ml_reconf_len = ml_len; + elems_parse->scratch_pos += ml_len; } struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) { + struct ieee80211_elems_parse *elems_parse; struct ieee802_11_elems *elems; const struct element *non_inherit = NULL; u8 *nontransmitted_profile; int nontransmitted_profile_len = 0; size_t scratch_len = 3 * params->len; - elems = kzalloc(struct_size(elems, scratch, scratch_len), GFP_ATOMIC); - if (!elems) + BUILD_BUG_ON(offsetof(typeof(*elems_parse), elems) != 0); + + elems_parse = kzalloc(struct_size(elems_parse, scratch, scratch_len), + GFP_ATOMIC); + if (!elems_parse) return NULL; + + elems_parse->scratch_len = scratch_len; + elems_parse->scratch_pos = elems_parse->scratch; + + elems = &elems_parse->elems; elems->ie_start = params->start; elems->total_len = params->len; - elems->scratch_len = scratch_len; - elems->scratch_pos = elems->scratch; - nontransmitted_profile = elems->scratch_pos; + nontransmitted_profile = elems_parse->scratch_pos; nontransmitted_profile_len = ieee802_11_find_bssid_profile(params->start, params->len, elems, params->bss, nontransmitted_profile); - elems->scratch_pos += nontransmitted_profile_len; - elems->scratch_len -= nontransmitted_profile_len; + elems_parse->scratch_pos += nontransmitted_profile_len; non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, nontransmitted_profile, nontransmitted_profile_len); - elems->crc = _ieee802_11_parse_elems_full(params, elems, non_inherit); + elems->crc = _ieee802_11_parse_elems_full(params, elems_parse, + non_inherit); /* Override with nontransmitted profile, if found */ if (nontransmitted_profile_len) { @@ -869,10 +912,12 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) .link_id = params->link_id, }; - _ieee802_11_parse_elems_full(&sub, elems, NULL); + _ieee802_11_parse_elems_full(&sub, elems_parse, NULL); } - ieee80211_mle_parse_link(elems, params); + ieee80211_mle_parse_link(elems_parse, params); + + ieee80211_mle_defrag_reconf(elems_parse); if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index cfc8eb70e966..23404b275457 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -37,7 +37,7 @@ void rate_control_rate_init(struct sta_info *sta) struct ieee80211_supported_band *sband; struct ieee80211_chanctx_conf *chanctx_conf; - ieee80211_sta_set_rx_nss(&sta->deflink); + ieee80211_sta_init_nss(&sta->deflink); if (!ref) return; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index bca2a259fda6..0429e59ba387 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -257,7 +257,6 @@ static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_sub_if_data *sdata1, *sdata2; struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; @@ -281,12 +280,6 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) if (skb->len < min_hdr_len) return; - sdata1 = rcu_dereference(local->scan_sdata); - sdata2 = rcu_dereference(local->sched_scan_sdata); - - if (likely(!sdata1 && !sdata2)) - return; - if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { /* * we were passive scanning because of radar/no-IR, but @@ -304,10 +297,17 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) return; if (ieee80211_is_probe_resp(mgmt->frame_control)) { + struct ieee80211_sub_if_data *sdata1, *sdata2; struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; u32 scan_req_flags = 0, sched_scan_req_flags = 0; + sdata1 = rcu_dereference(local->scan_sdata); + sdata2 = rcu_dereference(local->sched_scan_sdata); + + if (likely(!sdata1 && !sdata2)) + return; + scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); @@ -327,8 +327,16 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) sched_scan_req_flags, mgmt->da)) return; + } else { + /* Beacons are expected only with broadcast address */ + if (!is_broadcast_ether_addr(mgmt->da)) + return; } + /* Do not update the BSS table in case of only monitor interfaces */ + if (local->open_count == local->monitors) + return; + bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index f03731a5bbee..a52fb76386d0 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020-2023 Intel Corporation + * Copyright(c) 2020-2024 Intel Corporation */ #ifndef STA_INFO_H @@ -482,6 +482,8 @@ struct ieee80211_fragment_cache { * same for non-MLD STA. This is used as key for searching link STA * @link_id: Link ID uniquely identifying the link STA. This is 0 for non-MLD * and set to the corresponding vif LinkId for MLD STA + * @op_mode_nss: NSS limit as set by operating mode notification, or 0 + * @capa_nss: NSS limit as determined by local and peer capabilities * @link_hash_node: hash node for rhashtable * @sta: Points to the STA info * @gtk: group keys negotiated with this station, if any @@ -518,6 +520,8 @@ struct link_sta_info { u8 addr[ETH_ALEN]; u8 link_id; + u8 op_mode_nss, capa_nss; + struct rhlist_head link_hash_node; struct sta_info *sta; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index 42d9c06cbb84..f07b40916485 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -2028,8 +2028,9 @@ ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, } } -void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) +void ieee80211_teardown_tdls_peers(struct ieee80211_link_data *link) { + struct ieee80211_sub_if_data *sdata = link->sdata; struct sta_info *sta; u16 reason = WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED; @@ -2039,6 +2040,9 @@ void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; + if (sta->deflink.link_id != link->link_id) + continue; + ieee80211_tdls_oper_request(&sdata->vif, sta->sta.addr, NL80211_TDLS_TEARDOWN, reason, GFP_ATOMIC); diff --git a/net/mac80211/tests/elems.c b/net/mac80211/tests/elems.c index 30fc0acb7ac2..a413ba29f759 100644 --- a/net/mac80211/tests/elems.c +++ b/net/mac80211/tests/elems.c @@ -2,7 +2,7 @@ /* * KUnit tests for element parsing * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include <kunit/test.h> #include "../ieee80211_i.h" @@ -69,7 +69,7 @@ static void mle_defrag(struct kunit *test) if (IS_ERR_OR_NULL(parsed)) goto free_skb; - KUNIT_EXPECT_NOT_NULL(test, parsed->ml_basic_elem); + KUNIT_EXPECT_NOT_NULL(test, parsed->ml_basic); KUNIT_EXPECT_EQ(test, parsed->ml_basic_len, 2 /* control */ + diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 478b32d2520a..8e758b5074bd 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -1209,7 +1209,7 @@ DEFINE_EVENT(sta_event, drv_flush_sta, TP_ARGS(local, sdata, sta) ); -TRACE_EVENT(drv_channel_switch, +DECLARE_EVENT_CLASS(chanswitch_evt, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), @@ -1224,6 +1224,7 @@ TRACE_EVENT(drv_channel_switch, __field(u32, device_timestamp) __field(bool, block_tx) __field(u8, count) + __field(u8, link_id) ), TP_fast_assign( @@ -1234,14 +1235,24 @@ TRACE_EVENT(drv_channel_switch, __entry->device_timestamp = ch_switch->device_timestamp; __entry->block_tx = ch_switch->block_tx; __entry->count = ch_switch->count; + __entry->link_id = ch_switch->link_id; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " new " CHANDEF_PR_FMT " count:%d", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count + LOCAL_PR_FMT VIF_PR_FMT CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu device_ts:%u link_id:%d", + LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, + __entry->block_tx, __entry->timestamp, + __entry->device_timestamp, __entry->link_id ) ); +DEFINE_EVENT(chanswitch_evt, drv_channel_switch, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_channel_switch *ch_switch), + TP_ARGS(local, sdata, ch_switch) +); + TRACE_EVENT(drv_set_antenna, TP_PROTO(struct ieee80211_local *local, u32 tx_ant, u32 rx_ant, int ret), @@ -2121,39 +2132,11 @@ TRACE_EVENT(drv_channel_switch_beacon, ) ); -TRACE_EVENT(drv_pre_channel_switch, +DEFINE_EVENT(chanswitch_evt, drv_pre_channel_switch, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), - - TP_ARGS(local, sdata, ch_switch), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - CHANDEF_ENTRY - __field(u64, timestamp) - __field(u32, device_timestamp) - __field(bool, block_tx) - __field(u8, count) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - CHANDEF_ASSIGN(&ch_switch->chandef) - __entry->timestamp = ch_switch->timestamp; - __entry->device_timestamp = ch_switch->device_timestamp; - __entry->block_tx = ch_switch->block_tx; - __entry->count = ch_switch->count; - ), - - TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " prepare channel switch to " - CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, - __entry->block_tx, __entry->timestamp - ) + TP_ARGS(local, sdata, ch_switch) ); DEFINE_EVENT(local_sdata_evt, drv_post_channel_switch, @@ -2168,40 +2151,11 @@ DEFINE_EVENT(local_sdata_evt, drv_abort_channel_switch, TP_ARGS(local, sdata) ); -TRACE_EVENT(drv_channel_switch_rx_beacon, +DEFINE_EVENT(chanswitch_evt, drv_channel_switch_rx_beacon, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_switch *ch_switch), - - TP_ARGS(local, sdata, ch_switch), - - TP_STRUCT__entry( - LOCAL_ENTRY - VIF_ENTRY - CHANDEF_ENTRY - __field(u64, timestamp) - __field(u32, device_timestamp) - __field(bool, block_tx) - __field(u8, count) - ), - - TP_fast_assign( - LOCAL_ASSIGN; - VIF_ASSIGN; - CHANDEF_ASSIGN(&ch_switch->chandef) - __entry->timestamp = ch_switch->timestamp; - __entry->device_timestamp = ch_switch->device_timestamp; - __entry->block_tx = ch_switch->block_tx; - __entry->count = ch_switch->count; - ), - - TP_printk( - LOCAL_PR_FMT VIF_PR_FMT - " received a channel switch beacon to " - CHANDEF_PR_FMT " count:%d block_tx:%d timestamp:%llu", - LOCAL_PR_ARG, VIF_PR_ARG, CHANDEF_PR_ARG, __entry->count, - __entry->block_tx, __entry->timestamp - ) + TP_ARGS(local, sdata, ch_switch) ); TRACE_EVENT(drv_get_txpower, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 627bd5a8bda5..a237cbcf7b49 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1216,8 +1216,8 @@ static int ieee80211_put_preq_ies_band(struct sk_buff *skb, if (band == NL80211_BAND_S1GHZ) return ieee80211_put_s1g_cap(skb, &sband->s1g_cap); - err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, 0, - WLAN_EID_SUPP_RATES); + err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, + ~rate_mask, WLAN_EID_SUPP_RATES); if (err) return err; @@ -1238,8 +1238,8 @@ static int ieee80211_put_preq_ies_band(struct sk_buff *skb, *offset = noffset; } - err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, 0, - WLAN_EID_EXT_SUPP_RATES); + err = ieee80211_put_srates_elem(skb, sband, 0, rate_flags, + ~rate_mask, WLAN_EID_EXT_SUPP_RATES); if (err) return err; @@ -1935,8 +1935,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) for (link_id = 0; link_id < ARRAY_SIZE(sdata->vif.link_conf); link_id++) { - if (ieee80211_vif_is_mld(&sdata->vif) && - !(sdata->vif.active_links & BIT(link_id))) + if (!ieee80211_vif_link_active(&sdata->vif, link_id)) continue; link = sdata_dereference(sdata->link[link_id], sdata); diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 2c475c439ba9..642891cafbaf 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -4,7 +4,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2023 Intel Corporation + * Copyright (C) 2018 - 2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -541,15 +541,11 @@ ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) return bw; } -void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) +void ieee80211_sta_init_nss(struct link_sta_info *link_sta) { u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, eht_rx_nss = 0, rx_nss; bool support_160; - /* if we received a notification already don't overwrite it */ - if (link_sta->pub->rx_nss) - return; - if (link_sta->pub->eht_cap.has_eht) { int i; const u8 *rx_nss_mcs = (void *)&link_sta->pub->eht_cap.eht_mcs_nss_supp; @@ -627,7 +623,15 @@ void ieee80211_sta_set_rx_nss(struct link_sta_info *link_sta) rx_nss = max(vht_rx_nss, ht_rx_nss); rx_nss = max(he_rx_nss, rx_nss); rx_nss = max(eht_rx_nss, rx_nss); - link_sta->pub->rx_nss = max_t(u8, 1, rx_nss); + rx_nss = max_t(u8, 1, rx_nss); + link_sta->capa_nss = rx_nss; + + /* that shouldn't be set yet, but we can handle it anyway */ + if (link_sta->op_mode_nss) + link_sta->pub->rx_nss = + min_t(u8, rx_nss, link_sta->op_mode_nss); + else + link_sta->pub->rx_nss = rx_nss; } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -637,7 +641,7 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, enum ieee80211_sta_rx_bandwidth new_bw; struct sta_opmode_info sta_opmode = {}; u32 changed = 0; - u8 nss, cur_nss; + u8 nss; /* ignore - no support for BF yet */ if (opmode & IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF) @@ -647,23 +651,17 @@ u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, nss >>= IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT; nss += 1; - if (link_sta->pub->rx_nss != nss) { - cur_nss = link_sta->pub->rx_nss; - /* Reset rx_nss and call ieee80211_sta_set_rx_nss() which - * will set the same to max nss value calculated based on capability. - */ - link_sta->pub->rx_nss = 0; - ieee80211_sta_set_rx_nss(link_sta); - /* Do not allow an nss change to rx_nss greater than max_nss - * negotiated and capped to APs capability during association. - */ - if (nss <= link_sta->pub->rx_nss) { - link_sta->pub->rx_nss = nss; - sta_opmode.rx_nss = nss; - changed |= IEEE80211_RC_NSS_CHANGED; - sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + if (link_sta->op_mode_nss != nss) { + if (nss <= link_sta->capa_nss) { + link_sta->op_mode_nss = nss; + + if (nss != link_sta->pub->rx_nss) { + link_sta->pub->rx_nss = nss; + changed |= IEEE80211_RC_NSS_CHANGED; + sta_opmode.rx_nss = link_sta->pub->rx_nss; + sta_opmode.changed |= STA_OPMODE_N_SS_CHANGED; + } } else { - link_sta->pub->rx_nss = cur_nss; pr_warn_ratelimited("Ignoring NSS change in VHT Operating Mode Notification from %pM with invalid nss %d", link_sta->pub->addr, nss); } diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 8d2eabc71bbe..f13b07ebfb98 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index ef59e25dc482..8fc790f2a01b 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -55,8 +55,6 @@ static int mpls_xmit(struct sk_buff *skb) out_dev = dst->dev; net = dev_net(out_dev); - skb_orphan(skb); - if (!mpls_output_possible(out_dev) || !dst->lwtstate || skb_warn_if_lro(skb)) goto drop; diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 7017dd60659d..3ae46b545d2c 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int subflow_get_info(struct sock *sk, struct sk_buff *skb) diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index bd8ff5950c8d..0566dd793810 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c index 670da7822e6c..c30a2a90a192 100644 --- a/net/mptcp/mptcp_pm_gen.c +++ b/net/mptcp/mptcp_pm_gen.c @@ -32,8 +32,9 @@ const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] }; /* MPTCP_PM_CMD_GET_ADDR - do */ -const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { - [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, }; /* MPTCP_PM_CMD_FLUSH_ADDRS - do */ @@ -110,7 +111,7 @@ const struct genl_ops mptcp_pm_nl_ops[11] = { .doit = mptcp_pm_nl_get_addr_doit, .dumpit = mptcp_pm_nl_get_addr_dumpit, .policy = mptcp_pm_get_addr_nl_policy, - .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .maxattr = MPTCP_PM_ATTR_TOKEN, .flags = GENL_UNS_ADMIN_PERM, }, { diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h index ac9fc7225b6a..e24258f6f819 100644 --- a/net/mptcp/mptcp_pm_gen.h +++ b/net/mptcp/mptcp_pm_gen.h @@ -18,7 +18,7 @@ extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADD extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; -extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; +extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ATTR_TOKEN + 1]; extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 53e0b08b1123..55406720c607 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -6,7 +6,6 @@ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> -#include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" @@ -441,13 +440,27 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); } -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info) { - if (token) - return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup); - return mptcp_pm_nl_set_flags(net, loc, bkup); + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_get_addr(skb, info); + return mptcp_pm_nl_get_addr(skb, info); +} + +int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_dump_addr(msg, cb); + return mptcp_pm_nl_dump_addr(msg, cb); +} + +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_set_flags(skb, info); + return mptcp_pm_nl_set_flags(skb, info); } void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d5a942b9ab29..5c17d39146ea 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -8,19 +8,13 @@ #include <linux/inet.h> #include <linux/kernel.h> -#include <net/tcp.h> #include <net/inet_common.h> #include <net/netns/generic.h> #include <net/mptcp.h> -#include <net/genetlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" -/* forward declaration */ -static struct genl_family mptcp_genl_family; - static int pm_nl_pernet_id; struct mptcp_pm_add_entry { @@ -505,15 +499,12 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) } static struct mptcp_pm_addr_entry * -__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, - bool lookup_by_id) +__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, &pernet->local_addr_list, list) { - if ((!lookup_by_id && - mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) || - (lookup_by_id && entry->addr.id == info->id)) + if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; @@ -543,7 +534,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); - entry = __lookup_addr(pernet, &mpc_addr, false); + entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; @@ -1550,8 +1541,8 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) } } -void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, - struct list_head *rm_list) +static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, + struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; @@ -1636,8 +1627,8 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) return 0; } -static int mptcp_nl_fill_addr(struct sk_buff *skb, - struct mptcp_pm_addr_entry *entry) +int mptcp_nl_fill_addr(struct sk_buff *skb, + struct mptcp_pm_addr_entry *entry) { struct mptcp_addr_info *addr = &entry->addr; struct nlattr *attr; @@ -1675,7 +1666,7 @@ nla_put_failure: return -EMSGSIZE; } -int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); @@ -1725,8 +1716,13 @@ fail: return ret; } -int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) +{ + return mptcp_pm_get_addr(skb, info); +} + +int mptcp_pm_nl_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; @@ -1768,6 +1764,12 @@ int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, return msg->len; } +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + return mptcp_pm_dump_addr(msg, cb); +} + static int parse_limit(struct genl_info *info, int id, unsigned int *limit) { struct nlattr *attr = info->attrs[id]; @@ -1882,66 +1884,63 @@ next: return ret; } -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup) +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) { - struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); + struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | MPTCP_PM_ADDR_FLAG_FULLMESH; + struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; + struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; + u8 bkup = 0; + int ret; + + pernet = pm_nl_get_pernet(net); + + ret = mptcp_pm_parse_entry(attr, info, false, &addr); + if (ret < 0) + return ret; - if (addr->addr.family == AF_UNSPEC) { + if (addr.addr.family == AF_UNSPEC) { lookup_by_id = 1; - if (!addr->addr.id) + if (!addr.addr.id) { + GENL_SET_ERR_MSG(info, "missing required inputs"); return -EOPNOTSUPP; + } } + if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; + spin_lock_bh(&pernet->lock); - entry = __lookup_addr(pernet, &addr->addr, lookup_by_id); + entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) : + __lookup_addr(pernet, &addr.addr); if (!entry) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "address not found"); return -EINVAL; } - if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; } - changed = (addr->flags ^ entry->flags) & mask; - entry->flags = (entry->flags & ~mask) | (addr->flags & mask); - *addr = *entry; + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); + addr = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_set_flags(net, &addr->addr, bkup, changed); + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { - struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; - struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; - struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct net *net = sock_net(skb->sk); - u8 bkup = 0; - int ret; - - ret = mptcp_pm_parse_entry(attr, info, false, &addr); - if (ret < 0) - return ret; - - if (attr_rem) { - ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote); - if (ret < 0) - return ret; - } - - if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) - bkup = 1; - - return mptcp_pm_set_flags(net, token, &addr, &remote, bkup); + return mptcp_pm_set_flags(skb, info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) @@ -2281,7 +2280,7 @@ nla_put_failure: nlmsg_free(skb); } -static struct genl_family mptcp_genl_family __ro_after_init = { +struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, .netnsok = true, diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index bc97cc30f013..9f5d422d5ef6 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -106,19 +106,26 @@ static int mptcp_userspace_pm_delete_local_addr(struct mptcp_sock *msk, return -EINVAL; } +static struct mptcp_pm_addr_entry * +mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) +{ + struct mptcp_pm_addr_entry *entry; + + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (entry->addr.id == id) + return entry; + } + return NULL; +} + int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex) { - struct mptcp_pm_addr_entry *entry, *match = NULL; + struct mptcp_pm_addr_entry *match; spin_lock_bh(&msk->pm.lock); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (id == entry->addr.id) { - match = entry; - break; - } - } + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id); spin_unlock_bh(&msk->pm.lock); if (match) { *flags = match->flags; @@ -261,7 +268,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; - struct mptcp_pm_addr_entry *match = NULL; + struct mptcp_pm_addr_entry *match; struct mptcp_pm_addr_entry *entry; struct mptcp_sock *msk; LIST_HEAD(free_list); @@ -298,13 +305,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) lock_sock(sk); - list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { - if (entry->addr.id == id_val) { - match = entry; - break; - } - } - + match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val); if (!match) { GENL_SET_ERR_MSG(info, "address with specified id not found"); release_sock(sk); @@ -334,7 +335,6 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct mptcp_pm_addr_entry local = { 0 }; struct mptcp_addr_info addr_r; - struct mptcp_addr_info addr_l; struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; @@ -360,25 +360,31 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) goto create_err; } - err = mptcp_pm_parse_addr(laddr, info, &addr_l); + err = mptcp_pm_parse_entry(laddr, info, true, &local); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); goto create_err; } + if (local.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + GENL_SET_ERR_MSG(info, "invalid addr flags"); + err = -EINVAL; + goto create_err; + } + local.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; + err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr"); goto create_err; } - if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) { + if (!mptcp_pm_addr_families_match(sk, &local.addr, &addr_r)) { GENL_SET_ERR_MSG(info, "families mismatch"); err = -EINVAL; goto create_err; } - local.addr = addr_l; err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); @@ -387,7 +393,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) lock_sock(sk); - err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); + err = __mptcp_subflow_connect(sk, &local.addr, &addr_r); release_sock(sk); @@ -540,35 +546,194 @@ destroy_err: return err; } -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) { + struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; + struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct net *net = sock_net(skb->sk); struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; u32 token_val; + u8 bkup = 0; token_val = nla_get_u32(token); msk = mptcp_token_get_sock(net, token_val); - if (!msk) + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); return ret; + } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "userspace PM not selected"); goto set_flags_err; + } + + ret = mptcp_pm_parse_entry(attr, info, false, &loc); + if (ret < 0) + goto set_flags_err; + + if (attr_rem) { + ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem); + if (ret < 0) + goto set_flags_err; + } - if (loc->addr.family == AF_UNSPEC || - rem->addr.family == AF_UNSPEC) + if (loc.addr.family == AF_UNSPEC || + rem.addr.family == AF_UNSPEC) { + GENL_SET_ERR_MSG(info, "invalid address families"); + ret = -EINVAL; goto set_flags_err; + } + + if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; lock_sock(sk); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup); release_sock(sk); set_flags_err: sock_put(sk); return ret; } + +int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct id_bitmap { + DECLARE_BITMAP(map, MPTCP_PM_MAX_ADDR_ID + 1); + } *bitmap; + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(msg->sk); + struct mptcp_pm_addr_entry *entry; + struct mptcp_sock *msk; + struct nlattr *token; + int ret = -EINVAL; + struct sock *sk; + void *hdr; + + bitmap = (struct id_bitmap *)cb->ctx; + token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + + msk = mptcp_token_get_sock(net, nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return ret; + } + + sk = (struct sock *)msk; + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + goto out; + } + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (test_bit(entry->addr.id, bitmap->map)) + continue; + + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &mptcp_genl_family, + NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); + if (!hdr) + break; + + if (mptcp_nl_fill_addr(msg, entry) < 0) { + genlmsg_cancel(msg, hdr); + break; + } + + __set_bit(entry->addr.id, bitmap->map); + genlmsg_end(msg, hdr); + } + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + ret = msg->len; + +out: + sock_put(sk); + return ret; +} + +int mptcp_userspace_pm_get_addr(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct mptcp_pm_addr_entry addr, *entry; + struct net *net = sock_net(skb->sk); + struct mptcp_sock *msk; + struct sk_buff *msg; + int ret = -EINVAL; + struct sock *sk; + void *reply; + + msk = mptcp_token_get_sock(net, nla_get_u32(token)); + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); + return ret; + } + + sk = (struct sock *)msk; + + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected"); + goto out; + } + + ret = mptcp_pm_parse_entry(attr, info, false, &addr); + if (ret < 0) + goto out; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto out; + } + + reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, + info->genlhdr->cmd); + if (!reply) { + GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); + ret = -EMSGSIZE; + goto fail; + } + + lock_sock(sk); + spin_lock_bh(&msk->pm.lock); + entry = mptcp_userspace_pm_lookup_addr_by_id(msk, addr.addr.id); + if (!entry) { + GENL_SET_ERR_MSG(info, "address not found"); + ret = -EINVAL; + goto unlock_fail; + } + + ret = mptcp_nl_fill_addr(msg, entry); + if (ret) + goto unlock_fail; + + genlmsg_end(msg, reply); + ret = genlmsg_reply(msg, info); + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); + sock_put(sk); + return ret; + +unlock_fail: + spin_unlock_bh(&msk->pm.lock); + release_sock(sk); +fail: + nlmsg_free(msg); +out: + sock_put(sk); + return ret; +} diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 76c8861a852b..3a1967bc7bad 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -15,7 +15,6 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> @@ -1692,15 +1691,6 @@ out: } } -static void mptcp_set_nospace(struct sock *sk) -{ - /* enable autotune */ - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - - /* will be cleared on avail space */ - set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags); -} - static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, @@ -1771,6 +1761,30 @@ static int do_copy_data_nocache(struct sock *sk, int copy, return 0; } +/* open-code sk_stream_memory_free() plus sent limit computation to + * avoid indirect calls in fast-path. + * Called under the msk socket lock, so we can avoid a bunch of ONCE + * annotations. + */ +static u32 mptcp_send_limit(const struct sock *sk) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 limit, not_sent; + + if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf)) + return 0; + + limit = mptcp_notsent_lowat(sk); + if (limit == UINT_MAX) + return UINT_MAX; + + not_sent = msk->write_seq - msk->snd_nxt; + if (not_sent >= limit) + return 0; + + return limit - not_sent; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1815,6 +1829,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; + u32 copy_limit; + + /* ensure fitting the notsent_lowat() constraint */ + copy_limit = mptcp_send_limit(sk); + if (!copy_limit) + goto wait_for_memory; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator @@ -1822,9 +1842,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { - if (!sk_stream_memory_free(sk)) - goto wait_for_memory; - if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; @@ -1839,6 +1856,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); + psize = min_t(size_t, psize, copy_limit); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) @@ -1874,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) continue; wait_for_memory: - mptcp_set_nospace(sk); + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) @@ -3769,6 +3787,7 @@ static struct proto mptcp_prot = { .unhash = mptcp_unhash, .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, + .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, @@ -3942,12 +3961,12 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - if (sk_stream_is_writeable(sk)) + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; - mptcp_set_nospace(sk); - smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */ - if (sk_stream_is_writeable(sk)) + set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */ + if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; return 0; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index d0a7955b96c4..a10ebf3ee10a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -113,10 +113,9 @@ #define MPTCP_RST_TRANSIENT BIT(0) /* MPTCP socket atomic flags */ -#define MPTCP_NOSPACE 1 -#define MPTCP_WORK_RTX 2 -#define MPTCP_FALLBACK_DONE 4 -#define MPTCP_WORK_CLOSE_SUBFLOW 5 +#define MPTCP_WORK_RTX 1 +#define MPTCP_FALLBACK_DONE 2 +#define MPTCP_WORK_CLOSE_SUBFLOW 3 /* MPTCP socket release cb flags */ #define MPTCP_PUSH_PENDING 1 @@ -308,6 +307,7 @@ struct mptcp_sock { in_accept_queue:1, free_first:1, rcvspace_init:1; + u32 notsent_lowat; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; @@ -343,6 +343,8 @@ struct mptcp_sock { #define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp) \ list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node) +extern struct genl_family mptcp_genl_family; + static inline void msk_owned_by_me(const struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); @@ -808,14 +810,36 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } +static inline u32 mptcp_notsent_lowat(const struct sock *sk) +{ + struct net *net = sock_net(sk); + u32 val; + + val = READ_ONCE(mptcp_sk(sk)->notsent_lowat); + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); +} + +static inline bool mptcp_stream_memory_free(const struct sock *sk, int wake) +{ + const struct mptcp_sock *msk = mptcp_sk(sk); + u32 notsent_bytes; + + notsent_bytes = READ_ONCE(msk->write_seq) - READ_ONCE(msk->snd_nxt); + return (notsent_bytes << wake) < mptcp_notsent_lowat(sk); +} + +static inline bool __mptcp_stream_is_writeable(const struct sock *sk, int wake) +{ + return mptcp_stream_memory_free(sk, wake) && + __sk_stream_is_writeable(sk, wake); +} + static inline void mptcp_write_space(struct sock *sk) { - if (sk_stream_is_writeable(sk)) { - /* pairs with memory barrier in mptcp_poll */ - smp_mb(); - if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags)) - sk_stream_write_space(sk); - } + /* pairs with memory barrier in mptcp_poll */ + smp_mb(); + if (mptcp_stream_memory_free(sk, 1)) + sk_stream_write_space(sk); } static inline void __mptcp_sync_sndbuf(struct sock *sk) @@ -826,7 +850,7 @@ static inline void __mptcp_sync_sndbuf(struct sock *sk) if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) return; - new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + new_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]); mptcp_for_each_subflow(mptcp_sk(sk), subflow) { ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); @@ -946,21 +970,15 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup); -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); -void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, - struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -976,6 +994,8 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); +int mptcp_nl_fill_addr(struct sk_buff *skb, + struct mptcp_pm_addr_entry *entry); static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { @@ -1040,6 +1060,15 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); +int mptcp_pm_nl_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb); +int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, + struct netlink_callback *cb); +int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info); +int mptcp_userspace_pm_get_addr(struct sk_buff *skb, + struct genl_info *info); static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) { diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index da37e4541a5d..dcd1c76d2a3b 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -624,20 +624,11 @@ static int mptcp_setsockopt_sol_tcp_congestion(struct mptcp_sock *msk, sockptr_t return ret; } -static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val; - if (optlen < sizeof(int)) - return -EINVAL; - - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; - - lock_sock(sk); sockopt_seq_inc(msk); msk->cork = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -649,25 +640,15 @@ static int mptcp_setsockopt_sol_tcp_cork(struct mptcp_sock *msk, sockptr_t optva } if (!val) mptcp_check_and_set_pending(sk); - release_sock(sk); return 0; } -static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t optval, - unsigned int optlen) +static int __mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, int val) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int val; - - if (optlen < sizeof(int)) - return -EINVAL; - - if (copy_from_sockptr(&val, optval, sizeof(val))) - return -EFAULT; - lock_sock(sk); sockopt_seq_inc(msk); msk->nodelay = !!val; mptcp_for_each_subflow(msk, subflow) { @@ -679,8 +660,6 @@ static int mptcp_setsockopt_sol_tcp_nodelay(struct mptcp_sock *msk, sockptr_t op } if (val) mptcp_check_and_set_pending(sk); - release_sock(sk); - return 0; } @@ -803,25 +782,10 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, int ret, val; switch (optname) { - case TCP_INQ: - ret = mptcp_get_int_option(msk, optval, optlen, &val); - if (ret) - return ret; - if (val < 0 || val > 1) - return -EINVAL; - - lock_sock(sk); - msk->recvmsg_inq = !!val; - release_sock(sk); - return 0; case TCP_ULP: return -EOPNOTSUPP; case TCP_CONGESTION: return mptcp_setsockopt_sol_tcp_congestion(msk, optval, optlen); - case TCP_CORK: - return mptcp_setsockopt_sol_tcp_cork(msk, optval, optlen); - case TCP_NODELAY: - return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen); case TCP_DEFER_ACCEPT: /* See tcp.c: TCP_DEFER_ACCEPT does not fail */ mptcp_setsockopt_first_sf_only(msk, SOL_TCP, optname, optval, optlen); @@ -834,7 +798,34 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, optval, optlen); } - return -EOPNOTSUPP; + ret = mptcp_get_int_option(msk, optval, optlen, &val); + if (ret) + return ret; + + lock_sock(sk); + switch (optname) { + case TCP_INQ: + if (val < 0 || val > 1) + ret = -EINVAL; + else + msk->recvmsg_inq = !!val; + break; + case TCP_NOTSENT_LOWAT: + WRITE_ONCE(msk->notsent_lowat, val); + mptcp_write_space(sk); + break; + case TCP_CORK: + ret = __mptcp_setsockopt_sol_tcp_cork(msk, val); + break; + case TCP_NODELAY: + ret = __mptcp_setsockopt_sol_tcp_nodelay(msk, val); + break; + default: + ret = -ENOPROTOOPT; + } + + release_sock(sk); + return ret; } int mptcp_setsockopt(struct sock *sk, int level, int optname, @@ -1349,6 +1340,8 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return mptcp_put_int_option(msk, optval, optlen, msk->cork); case TCP_NODELAY: return mptcp_put_int_option(msk, optval, optlen, msk->nodelay); + case TCP_NOTSENT_LOWAT: + return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); } return -EOPNOTSUPP; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6403c56f2902..1626dd20c68f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -15,13 +15,11 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> #include <net/transp_v6.h> #endif #include <net/mptcp.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b001..540d97715bd2 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 224e5fb6a916..e93f905e60b6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5008,6 +5008,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -5431,6 +5437,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bfd3e5a14dab..255640013ab8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1256,14 +1256,13 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, switch (priv->l3num) { case NFPROTO_IPV4: case NFPROTO_IPV6: - if (priv->l3num != ctx->family) - return -EINVAL; + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; - fallthrough; - case NFPROTO_INET: - break; + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ default: - return -EOPNOTSUPP; + return -EAFNOSUPPORT; } priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index ad7b645e3ae7..7554803218a2 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1773,6 +1773,9 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, netlink_unlock_table(); return err; } + case NETLINK_LISTEN_ALL_NSID: + flag = NETLINK_F_LISTEN_ALL_NSID; + break; case NETLINK_CAP_ACK: flag = NETLINK_F_CAP_ACK; break; @@ -2267,6 +2270,15 @@ static int netlink_dump(struct sock *sk, bool lock_taken) if (extra_mutex) mutex_unlock(extra_mutex); + /* EMSGSIZE plus something already in the skb means + * that there's more to dump but current skb has filled up. + * If the callback really wants to return EMSGSIZE to user space + * it needs to do so again, on the next cb->dump() call, + * without putting data in the skb. + */ + if (nlk->dump_done_errno == -EMSGSIZE && skb->len) + nlk->dump_done_errno = skb->len; + cb->extack = NULL; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 50ec599a5cff..3b7666944b11 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1232,7 +1232,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) - return -1; + return -EMSGSIZE; if (nla_put_string(skb, CTRL_ATTR_FAMILY_NAME, family->name) || nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, family->id) || @@ -1355,6 +1355,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); int fams_to_skip = cb->args[0]; unsigned int id; + int err = 0; idr_for_each_entry(&genl_fam_idr, rt, id) { if (!rt->netnsok && !net_eq(net, &init_net)) @@ -1363,16 +1364,17 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) if (n++ < fams_to_skip) continue; - if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - skb, CTRL_CMD_NEWFAMILY) < 0) { + err = ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, CTRL_CMD_NEWFAMILY); + if (err) { n--; break; } } cb->args[0] = n; - return skb->len; + return err; } static struct sk_buff *ctrl_build_family_msg(const struct genl_family *family, diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 0eed00184adf..104a80b75477 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 3aaac4a22b38..2c34389c3ce6 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 2f084b6f69d7..97944db6b5ac 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f5b7..5e531394a724 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index baea3cbd76ca..70480869ad1c 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924cff..c3bbd5880850 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/nfc/core.c b/net/nfc/core.c index eb2c0959e5b6..e58dc6405054 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1015,7 +1015,7 @@ static void nfc_check_pres_timeout(struct timer_list *t) schedule_work(&dev->check_pres_work); } -struct class nfc_class = { +const struct class nfc_class = { .name = "nfc", .dev_release = nfc_release, }; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c9bbc2686690..61270826b9ac 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2057,7 +2057,7 @@ retry: skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb->tstamp = sockc.transmit_time; - + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2318,7 +2318,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { - if (po->copy_thresh && + if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); @@ -2586,6 +2586,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb->tstamp = sockc->transmit_time; + skb->mono_delivery_time = !!skb->tstamp; skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3064,6 +3065,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; + skb->mono_delivery_time = !!skb->tstamp; if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -3834,7 +3836,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; - pkt_sk(sk)->copy_thresh = val; + WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: @@ -4088,6 +4090,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; + case PACKET_COPY_THRESH: + val = READ_ONCE(pkt_sk(sk)->copy_thresh); + break; case PACKET_VERSION: val = po->tp_version; break; diff --git a/net/packet/diag.c b/net/packet/diag.c index b3bd2f6c2bf7..47f69f3dbf73 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -17,7 +17,7 @@ static int pdiag_put_info(const struct packet_sock *po, struct sk_buff *nlskb) pinfo.pdi_index = po->ifindex; pinfo.pdi_version = po->tp_version; pinfo.pdi_reserve = po->tp_reserve; - pinfo.pdi_copy_thresh = po->copy_thresh; + pinfo.pdi_copy_thresh = READ_ONCE(po->copy_thresh); pinfo.pdi_tstamp = READ_ONCE(po->tp_tstamp); pinfo.pdi_flags = 0; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index fba82d36593a..a4e3c5de998b 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 5e57a1581dc6..2899def23865 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1313,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 465bfe5eb061..5222bc97d192 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -487,7 +487,7 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); * rxrpc_kernel_set_max_life - Set maximum lifespan on a call * @sock: The socket the call is on * @call: The call to configure - * @hard_timeout: The maximum lifespan of the call in jiffies + * @hard_timeout: The maximum lifespan of the call in ms * * Set the maximum lifespan of a call. The call will end with ETIME or * ETIMEDOUT if it takes longer than this. @@ -495,14 +495,14 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); void rxrpc_kernel_set_max_life(struct socket *sock, struct rxrpc_call *call, unsigned long hard_timeout) { - unsigned long now; + ktime_t delay = ms_to_ktime(hard_timeout), expect_term_by; mutex_lock(&call->user_mutex); - now = jiffies; - hard_timeout += now; - WRITE_ONCE(call->expect_term_by, hard_timeout); - rxrpc_reduce_call_timer(call, hard_timeout, now, rxrpc_timer_set_for_hard); + expect_term_by = ktime_add(ktime_get_real(), delay); + WRITE_ONCE(call->expect_term_by, expect_term_by); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); mutex_unlock(&call->user_mutex); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7818aae1be8e..08c0a32db8c7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,8 +198,8 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ union { + struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ @@ -208,9 +208,12 @@ struct rxrpc_skb_priv { }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ + rxrpc_seq_t prev_ack; /* Highest seq seen */ + rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ + u8 reason; /* Reason for ack */ u8 nr_acks; /* Number of acks+nacks */ u8 nr_nacks; /* Number of nacks */ - }; + } ack; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; @@ -248,10 +251,9 @@ struct rxrpc_security { struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate - * of the amount of data remaining. + * of the amount of data remaining and allocate a data buffer. */ - int (*how_much_data)(struct rxrpc_call *, size_t, - size_t *, size_t *, size_t *); + struct rxrpc_txbuf *(*alloc_txbuf)(struct rxrpc_call *call, size_t remaining, gfp_t gfp); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); @@ -292,6 +294,7 @@ struct rxrpc_local { struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ + struct page_frag_cache tx_alloc; /* Tx control packet allocation (I/O thread only) */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY struct sk_buff_head rx_delay_queue; /* Delay injection queue */ @@ -352,8 +355,8 @@ struct rxrpc_peer { u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ - u32 rto_j; /* Retransmission timeout in jiffies */ - u8 backoff; /* Backoff timeout */ + u32 rto_us; /* Retransmission timeout in usec */ + u8 backoff; /* Backoff timeout (as shift) */ u8 cong_ssthresh; /* Congestion slow-start threshold */ }; @@ -500,6 +503,8 @@ struct rxrpc_connection { struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ + struct page_frag_cache tx_data_alloc; /* Tx DATA packet allocation */ + struct mutex tx_data_alloc_lock; struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ @@ -618,17 +623,17 @@ struct rxrpc_call { const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ - unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ - unsigned long ack_lost_at; /* When ACK is figured as lost */ - unsigned long resend_at; /* When next resend needs to happen */ - unsigned long ping_at; /* When next to send a ping */ - unsigned long keepalive_at; /* When next to send a keepalive ping */ - unsigned long expect_rx_by; /* When we expect to get a packet by */ - unsigned long expect_req_by; /* When we expect to get a request DATA packet by */ - unsigned long expect_term_by; /* When we expect call termination by */ - u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ - u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ - u32 hard_timo; /* Maximum lifetime or 0 (jif) */ + ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ + ktime_t ack_lost_at; /* When ACK is figured as lost */ + ktime_t resend_at; /* When next resend needs to happen */ + ktime_t ping_at; /* When next to send a ping */ + ktime_t keepalive_at; /* When next to send a keepalive ping */ + ktime_t expect_rx_by; /* When we expect to get a packet by */ + ktime_t expect_req_by; /* When we expect to get a request DATA packet by */ + ktime_t expect_term_by; /* When we expect call termination by */ + u32 next_rx_timo; /* Timeout for next Rx packet (ms) */ + u32 next_req_timo; /* Timeout for next Rx request packet (ms) */ + u32 hard_timo; /* Maximum lifetime or 0 (s) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -673,7 +678,7 @@ struct rxrpc_call { rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ - u16 tx_backoff; /* Delay to insert due to Tx failure */ + u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 ktime_t tx_last_sent; /* Last time a transmission occurred */ @@ -788,40 +793,30 @@ struct rxrpc_send_params { * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { - struct rcu_head rcu; struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ + rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; unsigned int len; /* Amount of data in buffer */ unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ - unsigned long flags; -#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ -#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ + unsigned int flags; +#define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ +#define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ + __be16 cksum; /* Checksum to go in header */ + unsigned short ack_rwind; /* ACK receive window */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ - struct { - /* The packet for encrypting and DMA'ing. We align it such - * that data[] aligns correctly for any crypto blocksize. - */ - u8 pad[64 - sizeof(struct rxrpc_wire_header)]; - struct rxrpc_wire_header wire; /* Network-ready header */ - union { - u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ - struct { - struct rxrpc_ackpacket ack; - DECLARE_FLEX_ARRAY(u8, acks); - }; - }; - } __aligned(64); + u8 nr_kvec; /* Amount of kvec[] used */ + struct kvec kvec[3]; }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) { - return txb->wire.flags & RXRPC_CLIENT_INITIATED; + return txb->flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) @@ -869,17 +864,11 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); */ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); -void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why); - bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* @@ -1160,9 +1149,9 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); @@ -1223,7 +1212,7 @@ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans); void rxrpc_peer_init_rtt(struct rxrpc_peer *); /* @@ -1295,8 +1284,9 @@ static inline void rxrpc_sysctl_exit(void) {} * txbuf.c */ extern atomic_t rxrpc_nr_txbuf; -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size); void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0f78544d043b..7bbb68504766 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -23,14 +23,14 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why) { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; - - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + ktime_t delay = ms_to_ktime(READ_ONCE(rxrpc_idle_ack_delay)); + ktime_t now = ktime_get_real(); + ktime_t ping_at = ktime_add(now, delay); + + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + if (ktime_before(ping_at, call->ping_at)) { + call->ping_at = ping_at; + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_ping); } } @@ -40,62 +40,18 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - unsigned long expiry = rxrpc_soft_ack_delay; - unsigned long now = jiffies, ack_at; - - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->delay_ack_at)) { - WRITE_ONCE(call->delay_ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + ktime_t now = ktime_get_real(), delay; trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); -} - -/* - * Queue an ACK for immediate transmission. - */ -void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, - rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) -{ - struct rxrpc_txbuf *txb; - - if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return; - - rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, - rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); - if (!txb) { - kleave(" = -ENOMEM"); - return; - } + if (call->peer->srtt_us) + delay = (call->peer->srtt_us >> 3) * NSEC_PER_USEC; + else + delay = ms_to_ktime(READ_ONCE(rxrpc_soft_ack_delay)); + ktime_add_ms(delay, call->tx_backoff); - txb->ack_why = why; - txb->wire.seq = 0; - txb->wire.type = RXRPC_PACKET_TYPE_ACK; - txb->wire.flags |= RXRPC_SLOW_START_OK; - txb->ack.bufferSpace = 0; - txb->ack.maxSkew = 0; - txb->ack.firstPacket = 0; - txb->ack.previousPacket = 0; - txb->ack.serial = htonl(serial); - txb->ack.reason = ack_reason; - txb->ack.nAcks = 0; - - trace_rxrpc_send_ack(call, why, ack_reason, serial); - rxrpc_send_ack_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + call->delay_ack_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_delayed_ack); } /* @@ -114,25 +70,19 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) struct rxrpc_ackpacket *ack = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_txbuf *txb; - unsigned long resend_at; - rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); - ktime_t now, max_age, oldest, ack_ts; - bool unacked = false; + rxrpc_seq_t transmitted = call->tx_transmitted; + ktime_t next_resend = KTIME_MAX, rto = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); + ktime_t resend_at = KTIME_MAX, now, delay; + bool unacked = false, did_send = false; unsigned int i; - LIST_HEAD(retrans_queue); _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); - max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); - oldest = now; if (list_empty(&call->tx_buffer)) goto no_resend; - if (list_empty(&call->tx_buffer)) - goto no_further_resend; - trace_rxrpc_resend(call, ack_skb); txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); @@ -143,12 +93,12 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) sp = rxrpc_skb(ack_skb); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { rxrpc_seq_t seq; if (ack->acks[i] & 1) continue; - seq = sp->first_ack + i; + seq = sp->ack.first_ack + i; if (after(txb->seq, transmitted)) break; if (after(txb->seq, seq)) @@ -160,19 +110,23 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) goto no_further_resend; found_txb: - if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + resend_at = ktime_add(txb->last_sent, rto); + if (after(txb->serial, call->acks_highest_serial)) { + if (ktime_after(resend_at, now) && + ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; /* Ack point not yet reached */ + } rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - } + trace_rxrpc_retransmit(call, txb->seq, txb->serial, + ktime_sub(resend_at, now)); - trace_rxrpc_retransmit(call, txb->seq, - ktime_to_ns(ktime_sub(txb->last_sent, - max_age))); + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + now = ktime_get_real(); if (list_is_last(&txb->call_link, &call->tx_buffer)) goto no_further_resend; @@ -184,43 +138,46 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) * seen. Anything between the soft-ACK table and that point will get * ACK'd or NACK'd in due course, so don't worry about it here; here we * need to consider retransmitting anything beyond that point. - * - * Note that ACK for a packet can beat the update of tx_transmitted. */ - if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + if (after_eq(call->acks_prev_seq, call->tx_transmitted)) goto no_further_resend; list_for_each_entry_from(txb, &call->tx_buffer, call_link) { - if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + resend_at = ktime_add(txb->last_sent, rto); + + if (before_eq(txb->seq, call->acks_prev_seq)) continue; - if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + if (after(txb->seq, call->tx_transmitted)) break; /* Not transmitted yet */ if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && - before(ntohl(txb->wire.serial), ntohl(ack->serial))) + before(txb->serial, ntohl(ack->serial))) goto do_resend; /* Wasn't accounted for by a more recent ping. */ - if (ktime_after(txb->last_sent, max_age)) { - if (ktime_before(txb->last_sent, oldest)) - oldest = txb->last_sent; + if (ktime_after(resend_at, now)) { + if (ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; } do_resend: unacked = true; - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - } + + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + now = ktime_get_real(); } no_further_resend: no_resend: - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, - !list_empty(&retrans_queue)); - WRITE_ONCE(call->resend_at, resend_at); + if (resend_at < KTIME_MAX) { + delay = rxrpc_get_rto_backoff(call->peer, did_send); + resend_at = ktime_add(resend_at, delay); + trace_rxrpc_timer_set(call, resend_at - now, rxrpc_timer_trace_resend_reset); + } + call->resend_at = resend_at; if (unacked) rxrpc_congestion_timeout(call); @@ -229,25 +186,15 @@ no_resend: * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (list_empty(&retrans_queue)) { - rxrpc_reduce_call_timer(call, resend_at, jiffies, - rxrpc_timer_set_for_resend); - ack_ts = ktime_sub(now, call->acks_latest_ts); - if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) - goto out; - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_lost_ack); - goto out; - } + if (!did_send) { + ktime_t next_ping = ktime_add_us(call->acks_latest_ts, + call->peer->srtt_us >> 3); - /* Retransmit the queue */ - while ((txb = list_first_entry_or_null(&retrans_queue, - struct rxrpc_txbuf, tx_link))) { - list_del_init(&txb->tx_link); - rxrpc_transmit_one(call, txb); + if (ktime_sub(next_ping, now) <= 0) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_0_retrans); } -out: _leave(""); } @@ -257,13 +204,11 @@ out: */ static void rxrpc_begin_service_reply(struct rxrpc_call *call) { - unsigned long now = jiffies; - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY); - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } /* @@ -320,7 +265,7 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) call->tx_top = txb->seq; list_add_tail(&txb->call_link, &call->tx_buffer); - if (txb->wire.flags & RXRPC_LAST_PACKET) + if (txb->flags & RXRPC_LAST_PACKET) rxrpc_close_tx_phase(call); rxrpc_transmit_one(call, txb); @@ -372,8 +317,8 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) */ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { - unsigned long now, next, t; - bool resend = false, expired = false; + ktime_t now, t; + bool resend = false; s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); @@ -397,70 +342,73 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; + if (skb) + rxrpc_input_call_packet(call, skb); + /* If we see our async-event poke, check for timeout trippage. */ - now = jiffies; - t = READ_ONCE(call->expect_rx_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now); - expired = true; + now = ktime_get_real(); + t = ktime_sub(call->expect_rx_by, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_expect_rx); + goto expired; } - t = READ_ONCE(call->expect_req_by); - if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST && - time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); - expired = true; + t = ktime_sub(call->expect_req_by, now); + if (t <= 0) { + call->expect_req_by = KTIME_MAX; + if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_idle); + goto expired; + } } - t = READ_ONCE(call->expect_term_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now); - expired = true; + t = ktime_sub(READ_ONCE(call->expect_term_by), now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_hard); + goto expired; } - t = READ_ONCE(call->delay_ack_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->delay_ack_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_delayed_ack); + call->delay_ack_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0, - rxrpc_propose_ack_ping_for_lost_ack); + rxrpc_propose_ack_delayed_ack); } - t = READ_ONCE(call->ack_lost_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now); - cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ack_lost_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_lost_ack); + call->ack_lost_at = KTIME_MAX; set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events); } - t = READ_ONCE(call->keepalive_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); - cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ping_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_ping); + call->ping_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_keepalive); } - t = READ_ONCE(call->ping_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); - cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_keepalive); - } - - t = READ_ONCE(call->resend_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now); - cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->resend_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_resend); + call->resend_at = KTIME_MAX; resend = true; } - if (skb) - rxrpc_input_call_packet(call, skb); - rxrpc_transmit_some_data(call); + now = ktime_get_real(); + t = ktime_sub(call->keepalive_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_keepalive); + call->keepalive_at = KTIME_MAX; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); + } + if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -472,24 +420,13 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_initial_ping(call); /* Process events */ - if (expired) { - if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && - (int)call->conn->hi_serial - (int)call->rx_serial > 0) { - trace_rxrpc_call_reset(call); - rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, - rxrpc_abort_call_reset); - } else { - rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, - rxrpc_abort_call_timeout); - } - goto out; - } - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY) + if (resend && + __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY && + !test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) rxrpc_resend(call, NULL); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) @@ -511,23 +448,33 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) /* Make sure the timer is restarted */ if (!__rxrpc_call_is_complete(call)) { - next = call->expect_rx_by; + ktime_t next = READ_ONCE(call->expect_term_by), delay; -#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } +#define set(T) { ktime_t _t = (T); if (ktime_before(_t, next)) next = _t; } set(call->expect_req_by); - set(call->expect_term_by); + set(call->expect_rx_by); set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); set(call->ping_at); - now = jiffies; - if (time_after_eq(now, next)) + now = ktime_get_real(); + delay = ktime_sub(next, now); + if (delay <= 0) { rxrpc_poke_call(call, rxrpc_call_poke_timer_now); - - rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + } else { + unsigned long nowj = jiffies, delayj, nextj; + + delayj = max(nsecs_to_jiffies(delay), 1); + nextj = nowj + delayj; + if (time_before(nextj, call->timer.expires) || + !timer_pending(&call->timer)) { + trace_rxrpc_timer_restart(call, delay, delayj); + timer_reduce(&call->timer, nextj); + } + } } out: @@ -542,4 +489,16 @@ out: rxrpc_shrink_call_tx_buffer(call); _leave(""); return true; + +expired: + if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && + (int)call->conn->hi_serial - (int)call->rx_serial > 0) { + trace_rxrpc_call_reset(call); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_reset); + } else { + rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, + rxrpc_abort_call_timeout); + } + goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9fc9a6c3f685..01fa71e8b1f7 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -70,20 +70,11 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (!__rxrpc_call_is_complete(call)) { - trace_rxrpc_timer_expired(call, jiffies); + trace_rxrpc_timer_expired(call); rxrpc_poke_call(call, rxrpc_call_poke_timer); } } -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why) -{ - trace_rxrpc_timer(call, why, now); - timer_reduce(&call->timer, expire_at); -} - static struct lock_class_key rxrpc_call_user_mutex_lock_class_key; static void rxrpc_destroy_call(struct work_struct *); @@ -163,12 +154,20 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); refcount_set(&call->ref, 1); - call->debug_id = debug_id; - call->tx_total_len = -1; - call->next_rx_timo = 20 * HZ; - call->next_req_timo = 1 * HZ; - call->ackr_window = 1; - call->ackr_wtop = 1; + call->debug_id = debug_id; + call->tx_total_len = -1; + call->next_rx_timo = 20 * HZ; + call->next_req_timo = 1 * HZ; + call->ackr_window = 1; + call->ackr_wtop = 1; + call->delay_ack_at = KTIME_MAX; + call->ack_lost_at = KTIME_MAX; + call->resend_at = KTIME_MAX; + call->ping_at = KTIME_MAX; + call->keepalive_at = KTIME_MAX; + call->expect_rx_by = KTIME_MAX; + call->expect_req_by = KTIME_MAX; + call->expect_term_by = KTIME_MAX; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -226,11 +225,11 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); if (p->timeouts.normal) - call->next_rx_timo = min(msecs_to_jiffies(p->timeouts.normal), 1UL); + call->next_rx_timo = min(p->timeouts.normal, 1); if (p->timeouts.idle) - call->next_req_timo = min(msecs_to_jiffies(p->timeouts.idle), 1UL); + call->next_req_timo = min(p->timeouts.idle, 1); if (p->timeouts.hard) - call->hard_timo = p->timeouts.hard * HZ; + call->hard_timo = p->timeouts.hard; ret = rxrpc_init_client_call_security(call); if (ret < 0) { @@ -253,18 +252,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, */ void rxrpc_start_call_timer(struct rxrpc_call *call) { - unsigned long now = jiffies; - unsigned long j = now + MAX_JIFFY_OFFSET; - - call->delay_ack_at = j; - call->ack_lost_at = j; - call->resend_at = j; - call->ping_at = j; - call->keepalive_at = j; - call->expect_rx_by = j; - call->expect_req_by = j; - call->expect_term_by = j + call->hard_timo; - call->timer.expires = now; + if (call->hard_timo) { + ktime_t delay = ms_to_ktime(call->hard_timo * 1000); + + call->expect_term_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + } + call->timer.expires = jiffies; } /* diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3b9b267a4431..d25bf1cf3670 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -636,7 +636,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { unsigned long final_ack_at = jiffies + 2; - WRITE_ONCE(chan->final_ack_at, final_ack_at); + chan->final_ack_at = final_ack_at; smp_wmb(); /* vs rxrpc_process_delayed_final_acks() */ set_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); rxrpc_reduce_conn_timer(conn, final_ack_at); @@ -770,7 +770,7 @@ next: conn_expires_at = conn->idle_timestamp + expiry; - now = READ_ONCE(jiffies); + now = jiffies; if (time_after(conn_expires_at, now)) goto not_yet_expired; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 1f251d758cb9..598b4ee389fc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -88,7 +88,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; - struct rxrpc_ackinfo ack_info; + struct rxrpc_acktrailer trailer; size_t len; int ret, ioc; u32 serial, mtu, call_id, padding; @@ -122,8 +122,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len = sizeof(pkt.whdr); iov[1].iov_base = &padding; iov[1].iov_len = 3; - iov[2].iov_base = &ack_info; - iov[2].iov_len = sizeof(ack_info); + iov[2].iov_base = &trailer; + iov[2].iov_len = sizeof(trailer); serial = rxrpc_get_next_serial(conn); @@ -158,14 +158,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - ack_info.rxMTU = htonl(rxrpc_rx_mtu); - ack_info.maxMTU = htonl(mtu); - ack_info.rwind = htonl(rxrpc_rx_window_size); - ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + trailer.maxMTU = htonl(rxrpc_rx_mtu); + trailer.ifMTU = htonl(mtu); + trailer.rwind = htonl(rxrpc_rx_window_size); + trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; padding = 0; iov[0].iov_len += sizeof(pkt.ack); - len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + len += sizeof(pkt.ack) + 3 + sizeof(trailer); ioc = 3; trace_rxrpc_tx_ack(chan->call_debug_id, serial, diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index df8a271948a1..0af4642aeec4 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -68,6 +68,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); mutex_init(&conn->security_lock); + mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; @@ -341,6 +342,9 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); + if (conn->tx_data_alloc.va) + __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), + conn->tx_data_alloc.pagecnt_bias); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9691de00ade7..3dedb8c0618c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -212,7 +212,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { + if (txb->flags & RXRPC_LAST_PACKET) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } @@ -252,6 +252,9 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, { ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); + call->resend_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_resend); + if (unlikely(call->cong_last_nack)) { rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); call->cong_last_nack = NULL; @@ -288,15 +291,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, static bool rxrpc_receiving_reply(struct rxrpc_call *call) { struct rxrpc_ack_summary summary = { 0 }; - unsigned long now, timo; rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - now = jiffies; - timo = now + MAX_JIFFY_OFFSET; - - WRITE_ONCE(call->delay_ack_at, timo); - trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { @@ -329,7 +328,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) case RXRPC_CALL_SERVER_RECV_REQUEST: rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); - call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; + call->expect_req_by = KTIME_MAX; rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); break; @@ -589,14 +588,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_RECV_REQUEST: { unsigned long timo = READ_ONCE(call->next_req_timo); - unsigned long now, expect_req_by; if (timo) { - now = jiffies; - expect_req_by = now + timo; - WRITE_ONCE(call->expect_req_by, expect_req_by); - rxrpc_reduce_call_timer(call, expect_req_by, now, - rxrpc_timer_set_for_idle); + ktime_t delay = ms_to_ktime(timo); + + call->expect_req_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_idle); } break; } @@ -670,14 +667,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, /* * Process the extra information that may be appended to an ACK packet */ -static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - struct rxrpc_ackinfo *ackinfo) +static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; bool wake = false; - u32 rwind = ntohl(ackinfo->rwind); + u32 rwind = ntohl(trailer->rwind); if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; @@ -691,7 +688,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, if (call->cong_ssthresh > rwind) call->cong_ssthresh = rwind; - mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU)); peer = call->peer; if (mtu < peer->maxdata) { @@ -713,20 +710,19 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, rxrpc_seq_t seq) { struct sk_buff *skb = call->cong_last_nack; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, new_acks = 0, retained_nacks = 0; - rxrpc_seq_t old_seq = sp->first_ack; - u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack); + rxrpc_seq_t old_seq = sp->ack.first_ack; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - if (after_eq(seq, old_seq + sp->nr_acks)) { - summary->nr_new_acks += sp->nr_nacks; - summary->nr_new_acks += seq - (old_seq + sp->nr_acks); + if (after_eq(seq, old_seq + sp->ack.nr_acks)) { + summary->nr_new_acks += sp->ack.nr_nacks; + summary->nr_new_acks += seq - (old_seq + sp->ack.nr_acks); summary->nr_retained_nacks = 0; } else if (seq == old_seq) { - summary->nr_retained_nacks = sp->nr_nacks; + summary->nr_retained_nacks = sp->ack.nr_nacks; } else { - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_NACK) { if (before(old_seq + i, seq)) new_acks++; @@ -739,7 +735,7 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, summary->nr_retained_nacks = retained_nacks; } - return old_seq + sp->nr_acks; + return old_seq + sp->ack.nr_acks; } /* @@ -759,10 +755,10 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, old_nacks = 0; - rxrpc_seq_t lowest_nak = seq + sp->nr_acks; + rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks; u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; if (after_eq(seq, since)) @@ -774,7 +770,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, old_nacks++; } else { summary->nr_new_nacks++; - sp->nr_nacks++; + sp->ack.nr_nacks++; } if (before(seq, lowest_nak)) @@ -835,38 +831,32 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_ackinfo info; + struct rxrpc_acktrailer trailer; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; int nr_acks, offset, ioffset; _enter(""); - offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack); - offset += sizeof(ack); - - ack_serial = sp->hdr.serial; - acked_serial = ntohl(ack.serial); - first_soft_ack = ntohl(ack.firstPacket); - prev_pkt = ntohl(ack.previousPacket); - hard_ack = first_soft_ack - 1; - nr_acks = ack.nAcks; - sp->first_ack = first_soft_ack; - sp->nr_acks = nr_acks; - summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? - ack.reason : RXRPC_ACK__INVALID); + offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + + ack_serial = sp->hdr.serial; + acked_serial = sp->ack.acked_serial; + first_soft_ack = sp->ack.first_ack; + prev_pkt = sp->ack.prev_ack; + nr_acks = sp->ack.nr_acks; + hard_ack = first_soft_ack - 1; + summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? + sp->ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]); if (acked_serial != 0) { - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING_RESPONSE: rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); @@ -886,7 +876,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -899,7 +889,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && call->acks_hard_ack == 0 && @@ -917,11 +907,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto send_response; } - info.rxMTU = 0; + trailer.maxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); + if (skb->len >= ioffset + sizeof(trailer) && + skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0) + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer); if (nr_acks > 0) skb_condense(skb); @@ -940,7 +930,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING: break; default: @@ -950,8 +940,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } /* Parse rwind and mtu sizes if provided. */ - if (info.rxMTU) - rxrpc_input_ackinfo(call, skb, &info); + if (trailer.maxMTU) + rxrpc_input_ack_trailer(call, skb, &trailer); if (first_soft_ack == 0) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); @@ -997,7 +987,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); send_response: - if (ack.reason == RXRPC_ACK_PING) + if (summary.ack_reason == RXRPC_ACK_PING) rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); else if (sp->hdr.flags & RXRPC_REQUEST_ACK) @@ -1048,12 +1038,10 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) timo = READ_ONCE(call->next_rx_timo); if (timo) { - unsigned long now = jiffies, expect_rx_by; + ktime_t delay = ms_to_ktime(timo); - expect_rx_by = now + timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, now, - rxrpc_timer_set_for_normal); + call->expect_rx_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); } switch (sp->hdr.type) { diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 34353b6e584b..f2701068ed9e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -15,14 +15,11 @@ static int none_init_connection_security(struct rxrpc_connection *conn, } /* - * Work out how much data we can put in an unsecured packet. + * Allocate an appropriately sized buffer for the amount of data remaining. */ -static int none_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - *_buf_size = *_data_size = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - *_offset = 0; - return 0; + return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 0, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) @@ -79,7 +76,7 @@ const struct rxrpc_security rxrpc_no_security = { .exit = none_exit, .init_connection_security = none_init_connection_security, .free_call_crypto = none_free_call_crypto, - .how_much_data = none_how_much_data, + .alloc_txbuf = none_alloc_txbuf, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .respond_to_challenge = none_respond_to_challenge, diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 4a3a08a0e2cd..0300baa9afcd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -124,6 +124,7 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) { struct rxrpc_wire_header whdr; + struct rxrpc_ackpacket ack; /* dig out the RxRPC connection details */ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) @@ -141,6 +142,16 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); + + if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(whdr), &ack, sizeof(ack)) < 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_short_ack); + sp->ack.first_ack = ntohl(ack.firstPacket); + sp->ack.prev_ack = ntohl(ack.previousPacket); + sp->ack.acked_serial = ntohl(ack.serial); + sp->ack.reason = ack.reason; + sp->ack.nr_acks = ack.nAcks; + } return true; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 34d307368135..504453c688d7 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,6 +452,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); + if (local->tx_alloc.va) + __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), + local->tx_alloc.pagecnt_bias); } /* diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 825b81183046..657cf35089a6 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -17,22 +17,22 @@ unsigned int rxrpc_max_backlog __read_mostly = 10; /* - * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * How long to wait before scheduling an ACK with subtype DELAY (in ms). * * We use this when we've received new data packets. If those packets aren't * all consumed within this time we will send a DELAY ACK if an ACK was not * requested to let the sender know it doesn't need to resend. */ -unsigned long rxrpc_soft_ack_delay = HZ; +unsigned long rxrpc_soft_ack_delay = 1000; /* - * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * How long to wait before scheduling an ACK with subtype IDLE (in ms). * * We use this when we've consumed some previously soft-ACK'd packets when * further packets aren't immediately received to decide when to send an IDLE * ACK let the other end know that it can free up its Tx buffer space. */ -unsigned long rxrpc_idle_ack_delay = HZ / 2; +unsigned long rxrpc_idle_ack_delay = 500; /* * Receive window size in packets. This indicates the maximum number of diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 4a292f860ae3..5ea9601efd05 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -48,12 +48,10 @@ static const char rxrpc_keepalive_string[] = ""; static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) { if (ret < 0) { - u16 tx_backoff = READ_ONCE(call->tx_backoff); - - if (tx_backoff < HZ) - WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + if (call->tx_backoff < 1000) + call->tx_backoff += 100; } else { - WRITE_ONCE(call->tx_backoff, 0); + call->tx_backoff = 0; } } @@ -65,84 +63,92 @@ static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) * Receiving a response to the ping will prevent the ->expect_rx_by timer from * expiring. */ -static void rxrpc_set_keepalive(struct rxrpc_call *call) +static void rxrpc_set_keepalive(struct rxrpc_call *call, ktime_t now) { - unsigned long now = jiffies, keepalive_at = call->next_rx_timo / 6; + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo) / 6); - keepalive_at += now; - WRITE_ONCE(call->keepalive_at, keepalive_at); - rxrpc_reduce_call_timer(call, keepalive_at, now, - rxrpc_timer_set_for_keepalive); + call->keepalive_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_keepalive); } /* * Fill out an ACK packet. */ -static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, - struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - u16 *_rwind) +static void rxrpc_fill_out_ack(struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + u8 ack_reason, + rxrpc_serial_t serial) { - struct rxrpc_ackinfo ackinfo; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_acktrailer *trailer = txb->kvec[2].iov_base + 3; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); unsigned int qsize, sack, wrap, to; rxrpc_seq_t window, wtop; int rsize; u32 mtu, jmax; - u8 *ackp = txb->acks; + u8 *filler = txb->kvec[2].iov_base; + u8 *sackp = txb->kvec[1].iov_base; - call->ackr_nr_unacked = 0; - atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); - clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); window = call->ackr_window; wtop = call->ackr_wtop; sack = call->ackr_sack_base % RXRPC_SACK_SIZE; - txb->ack.firstPacket = htonl(window); - txb->ack.nAcks = wtop - window; + + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + txb->flags |= RXRPC_SLOW_START_OK; + ack->bufferSpace = 0; + ack->maxSkew = 0; + ack->firstPacket = htonl(window); + ack->previousPacket = htonl(call->rx_highest_seq); + ack->serial = htonl(serial); + ack->reason = ack_reason; + ack->nAcks = wtop - window; + filler[0] = 0; + filler[1] = 0; + filler[2] = 0; + + if (ack_reason == RXRPC_ACK_PING) + txb->flags |= RXRPC_REQUEST_ACK; if (after(wtop, window)) { + txb->len += ack->nAcks; + txb->kvec[1].iov_base = sackp; + txb->kvec[1].iov_len = ack->nAcks; + wrap = RXRPC_SACK_SIZE - sack; - to = min_t(unsigned int, txb->ack.nAcks, RXRPC_SACK_SIZE); + to = min_t(unsigned int, ack->nAcks, RXRPC_SACK_SIZE); - if (sack + txb->ack.nAcks <= RXRPC_SACK_SIZE) { - memcpy(txb->acks, call->ackr_sack_table + sack, txb->ack.nAcks); + if (sack + ack->nAcks <= RXRPC_SACK_SIZE) { + memcpy(sackp, call->ackr_sack_table + sack, ack->nAcks); } else { - memcpy(txb->acks, call->ackr_sack_table + sack, wrap); - memcpy(txb->acks + wrap, call->ackr_sack_table, - to - wrap); + memcpy(sackp, call->ackr_sack_table + sack, wrap); + memcpy(sackp + wrap, call->ackr_sack_table, to - wrap); } - - ackp += to; } else if (before(wtop, window)) { pr_warn("ack window backward %x %x", window, wtop); - } else if (txb->ack.reason == RXRPC_ACK_DELAY) { - txb->ack.reason = RXRPC_ACK_IDLE; + } else if (ack->reason == RXRPC_ACK_DELAY) { + ack->reason = RXRPC_ACK_IDLE; } - mtu = conn->peer->if_mtu; - mtu -= conn->peer->hdrsize; + mtu = call->peer->if_mtu; + mtu -= call->peer->hdrsize; jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); - *_rwind = rsize; - ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(rsize); - ackinfo.jumbo_max = htonl(jmax); - - *ackp++ = 0; - *ackp++ = 0; - *ackp++ = 0; - memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return txb->ack.nAcks + 3 + sizeof(ackinfo); + txb->ack_rwind = rsize; + trailer->maxMTU = htonl(rxrpc_rx_mtu); + trailer->ifMTU = htonl(mtu); + trailer->rwind = htonl(rsize); + trailer->jumbo_max = htonl(jmax); } /* * Record the beginning of an RTT probe. */ -static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, - enum rxrpc_rtt_tx_trace why) +static void rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + ktime_t now, enum rxrpc_rtt_tx_trace why) { unsigned long avail = call->rtt_avail; int rtt_slot = 9; @@ -155,47 +161,31 @@ static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, goto no_slot; call->rtt_serial[rtt_slot] = serial; - call->rtt_sent_at[rtt_slot] = ktime_get_real(); + call->rtt_sent_at[rtt_slot] = now; smp_wmb(); /* Write data before avail bit */ set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); - return rtt_slot; + return; no_slot: trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); - return -1; -} - -/* - * Cancel an RTT probe. - */ -static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, - rxrpc_serial_t serial, int rtt_slot) -{ - if (rtt_slot != -1) { - clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); - smp_wmb(); /* Clear pending bit before setting slot */ - set_bit(rtt_slot, &call->rtt_avail); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); - } } /* * Transmit an ACK packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; struct rxrpc_connection *conn; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len, n; - int ret, rtt_slot = -1; - u16 rwind; + ktime_t now; + int ret; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return -ECONNRESET; + return; conn = call->conn; @@ -203,55 +193,68 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; - msg.msg_flags = 0; - - if (txb->ack.reason == RXRPC_ACK_PING) - txb->wire.flags |= RXRPC_REQUEST_ACK; - - n = rxrpc_fill_out_ack(conn, call, txb, &rwind); - if (n == 0) - return 0; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; - len = iov[0].iov_len; + msg.msg_flags = MSG_SPLICE_PAGES; - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); - trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, - rwind); + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; - if (txb->ack.reason == RXRPC_ACK_PING) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); + txb->serial = rxrpc_get_next_serial(conn); + whdr->serial = htonl(txb->serial); + trace_rxrpc_tx_ack(call->debug_id, txb->serial, + ntohl(ack->firstPacket), + ntohl(ack->serial), ack->reason, ack->nAcks, + txb->ack_rwind); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - /* Grab the highest received seq as late as possible */ - txb->ack.previousPacket = htonl(call->rx_highest_seq); - - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, txb->len); + rxrpc_local_dont_fragment(conn->local, false); + ret = do_udp_sendmsg(conn->local->socket, &msg, txb->len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) { - trace_rxrpc_tx_fail(call->debug_id, serial, ret, + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, rxrpc_tx_point_call_ack); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, + trace_rxrpc_tx_packet(call->debug_id, whdr, rxrpc_tx_point_call_ack); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - call->peer->rtt_last_req = ktime_get_real(); + now = ktime_get_real(); + if (ack->reason == RXRPC_ACK_PING) + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_ping); + if (txb->flags & RXRPC_REQUEST_ACK) + call->peer->rtt_last_req = now; + rxrpc_set_keepalive(call, now); } rxrpc_tx_backoff(call, ret); +} - if (!__rxrpc_call_is_complete(call)) { - if (ret < 0) - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_set_keepalive(call); +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_ack_txbuf(call, call->ackr_wtop - call->ackr_window); + if (!txb) { + kleave(" = -ENOMEM"); + return; } - return ret; + txb->ack_why = why; + + rxrpc_fill_out_ack(call, txb, ack_reason, serial); + call->ackr_nr_unacked = 0; + atomic_set(&call->ackr_nr_consumed, 0); + clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); + + trace_rxrpc_send_ack(call, why, ack_reason, serial); + rxrpc_send_ack_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } /* @@ -319,38 +322,22 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) } /* - * send a packet through the transport endpoint + * Prepare a (sub)packet for transmission. */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_txbuf *txb, + rxrpc_serial_t serial) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len; - int ret, rtt_slot = -1; _enter("%x,{%d}", txb->seq, txb->len); - /* Each transmission of a Tx packet needs a new serial number */ - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); + txb->serial = serial; if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && txb->seq == 1) - txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + txb->len; - len = iov[0].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - - msg.msg_name = &call->peer->srx.transport; - msg.msg_namelen = call->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; + whdr->userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. @@ -359,13 +346,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (txb->wire.flags & RXRPC_REQUEST_ACK) + if (txb->flags & RXRPC_REQUEST_ACK) why = rxrpc_reqack_already_on; - else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) + else if ((txb->flags & RXRPC_LAST_PACKET) && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; - else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) + else if (txb->flags & RXRPC_TXBUF_RESENT) why = rxrpc_reqack_retrans; else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) why = rxrpc_reqack_slow_start; @@ -381,42 +368,116 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, txb->seq, why); if (why != rxrpc_reqack_no_srv_last) - txb->wire.flags |= RXRPC_REQUEST_ACK; + txb->flags |= RXRPC_REQUEST_ACK; dont_set_request_ack: + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; + whdr->serial = htonl(txb->serial); + whdr->cksum = txb->cksum; + + trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, false); +} + +/* + * Prepare a packet for transmission. + */ +static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + rxrpc_serial_t serial; + + /* Each transmission of a Tx packet needs a new serial number */ + serial = rxrpc_get_next_serial(call->conn); + + rxrpc_prepare_data_subpacket(call, txb, serial); + + return txb->len; +} + +/* + * Set timeouts after transmitting a packet. + */ +static void rxrpc_tstamp_data_packets(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + ktime_t now = ktime_get_real(); + bool ack_requested = txb->flags & RXRPC_REQUEST_ACK; + + call->tx_last_sent = now; + txb->last_sent = now; + + if (ack_requested) { + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_data); + + call->peer->rtt_last_req = now; + if (call->peer->rtt_count > 1) { + ktime_t delay = rxrpc_get_rto_backoff(call->peer, false); + + call->ack_lost_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_lost_ack); + } + } + + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo)); + + call->expect_rx_by = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); + } + + rxrpc_set_keepalive(call, now); +} + +/* + * send a packet through the transport endpoint + */ +static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_connection *conn = call->conn; + enum rxrpc_tx_point frag; + struct msghdr msg; + size_t len; + int ret; + + _enter("%x,{%d}", txb->seq, txb->len); + + len = rxrpc_prepare_data_packet(call, txb); + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, txb->seq, serial, - txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), - true); + trace_rxrpc_tx_data(call, txb->seq, txb->serial, + txb->flags, true); goto done; } } - trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, len); + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = MSG_SPLICE_PAGES; /* Track what we've attempted to transmit at least once so that the * retransmission algorithm doesn't try to resend what we haven't sent - * yet. However, this can race as we can receive an ACK before we get - * to this point. But, OTOH, if we won't get an ACK mentioning this - * packet unless the far side received it (though it could have - * discarded it anyway and NAK'd it). + * yet. */ - cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); + if (txb->seq == call->tx_transmitted + 1) + call->tx_transmitted = txb->seq; /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (txb->len >= call->peer->maxdata) - goto send_fragmentable; - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); + if (txb->len >= call->peer->maxdata) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + } else { + rxrpc_local_dont_fragment(conn->local, true); + frag = rxrpc_tx_point_call_data_nofrag; + } +retry: /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -429,46 +490,21 @@ dont_set_request_ack: if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_packet(call->debug_id, whdr, frag); } rxrpc_tx_backoff(call, ret); - if (ret == -EMSGSIZE) - goto send_fragmentable; + if (ret == -EMSGSIZE && frag == rxrpc_tx_point_call_data_frag) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + goto retry; + } done: if (ret >= 0) { - call->tx_last_sent = txb->last_sent; - if (txb->wire.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = txb->last_sent; - if (call->peer->rtt_count > 1) { - unsigned long nowj = jiffies, ack_lost_at; - - ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); - ack_lost_at += nowj; - WRITE_ONCE(call->ack_lost_at, ack_lost_at); - rxrpc_reduce_call_timer(call, ack_lost_at, nowj, - rxrpc_timer_set_for_lost_ack); - } - } - - if (txb->seq == 1 && - !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, - &call->flags)) { - unsigned long nowj = jiffies, expect_rx_by; - - expect_rx_by = nowj + call->next_rx_timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, nowj, - rxrpc_timer_set_for_normal); - } - - rxrpc_set_keepalive(call); + rxrpc_tstamp_data_packets(call, txb); } else { /* Cancel the call if the initial transmission fails, * particularly if that's due to network routing issues that @@ -482,41 +518,6 @@ done: _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; - -send_fragmentable: - /* attempt to send this message with fragmentation enabled */ - _debug("send fragment"); - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); - - switch (conn->local->srx.transport.family) { - case AF_INET6: - case AF_INET: - rxrpc_local_dont_fragment(conn->local, false); - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); - - rxrpc_local_dont_fragment(conn->local, true); - break; - - default: - BUG(); - } - - if (ret < 0) { - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_frag); - } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_frag); - } - rxrpc_tx_backoff(call, ret); - goto done; } /* @@ -723,11 +724,9 @@ void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_instant_resend(call, txb); } } else { - unsigned long now = jiffies; - unsigned long resend_at = now + call->peer->rto_j; + ktime_t delay = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); - WRITE_ONCE(call->resend_at, resend_at); - rxrpc_reduce_call_timer(call, resend_at, now, - rxrpc_timer_set_for_send); + call->resend_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_resend_tx); } } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 26dc2f26d92d..263a2251e3d2 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -52,9 +52,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); enum rxrpc_call_state state; - unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; + long timeout = 0; if (v == &rxnet->calls) { seq_puts(seq, @@ -76,10 +76,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &call->dest_srx.transport); state = rxrpc_call_state(call); - if (state != RXRPC_CALL_SERVER_PREALLOC) { - timeout = READ_ONCE(call->expect_rx_by); - timeout -= jiffies; - } + if (state != RXRPC_CALL_SERVER_PREALLOC) + timeout = ktime_ms_delta(READ_ONCE(call->expect_rx_by), ktime_get_real()); acks_hard_ack = READ_ONCE(call->acks_hard_ack); seq_printf(seq, @@ -309,7 +307,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, - jiffies_to_usecs(peer->rto_j)); + peer->rto_us); return 0; } diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index e8ee4af43ca8..4fe6b4d20ada 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -135,9 +135,9 @@ struct rxrpc_ackpacket { /* * ACK packets can have a further piece of information tagged on the end */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ +struct rxrpc_acktrailer { + __be32 maxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 ifMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ }; diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index be61d6f5be8d..cdab7b7d08a0 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -11,8 +11,8 @@ #include <linux/net.h> #include "ar-internal.h" -#define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) -#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ +#define RXRPC_RTO_MAX (120 * USEC_PER_SEC) +#define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * MSEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) @@ -22,7 +22,7 @@ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) { - return usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); + return (peer->srtt_us >> 3) + peer->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) @@ -124,7 +124,7 @@ static void rxrpc_set_rto(struct rxrpc_peer *peer) /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ - peer->rto_j = rxrpc_bound_rto(rto); + peer->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) @@ -163,33 +163,33 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, spin_unlock(&peer->rtt_input_lock); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, - peer->srtt_us >> 3, peer->rto_j); + peer->srtt_us >> 3, peer->rto_us); } /* - * Get the retransmission timeout to set in jiffies, backing it off each time - * we retransmit. + * Get the retransmission timeout to set in nanoseconds, backing it off each + * time we retransmit. */ -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) { - u64 timo_j; - u8 backoff = READ_ONCE(peer->backoff); + u64 timo_us; + u32 backoff = READ_ONCE(peer->backoff); - timo_j = peer->rto_j; - timo_j <<= backoff; - if (retrans && timo_j * 2 <= RXRPC_RTO_MAX) + timo_us = peer->rto_us; + timo_us <<= backoff; + if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(peer->backoff, backoff + 1); - if (timo_j < 1) - timo_j = 1; + if (timo_us < 1) + timo_us = 1; - return timo_j; + return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) { - peer->rto_j = RXRPC_TIMEOUT_INIT; - peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT); + peer->rto_us = RXRPC_TIMEOUT_INIT; + peer->mdev_us = RXRPC_TIMEOUT_INIT; peer->backoff = 0; //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 6b32d61d4cdc..f1a68270862d 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -145,16 +145,17 @@ error: /* * Work out how much data we can put in a packet. */ -static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - size_t shdr, buf_size, chunk; + struct rxrpc_txbuf *txb; + size_t shdr, space; + + remain = min(remain, 65535 - sizeof(struct rxrpc_wire_header)); switch (call->conn->security_level) { default: - buf_size = chunk = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - shdr = 0; - goto out; + space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); + return rxrpc_alloc_data_txbuf(call, space, 0, gfp); case RXRPC_SECURITY_AUTH: shdr = sizeof(struct rxkad_level1_hdr); break; @@ -163,17 +164,16 @@ static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, break; } - buf_size = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN); + space = min_t(size_t, round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN), remain + shdr); + space = round_up(space, RXKAD_ALIGN); - chunk = buf_size - shdr; - if (remain < chunk) - buf_size = round_up(shdr + remain, RXKAD_ALIGN); + txb = rxrpc_alloc_data_txbuf(call, space, RXKAD_ALIGN, gfp); + if (!txb) + return NULL; -out: - *_buf_size = buf_size; - *_data_size = chunk; - *_offset = shdr; - return 0; + txb->offset += shdr; + txb->space -= shdr; + return txb; } /* @@ -251,7 +251,8 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxkad_level1_hdr *hdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level1_hdr *hdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -259,7 +260,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; hdr->data_size = htonl((u32)check << 16 | txb->len); txb->len += sizeof(struct rxkad_level1_hdr); @@ -267,14 +268,14 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, txb->data, 8); + sg_init_one(&sg, hdr, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -293,7 +294,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level2_hdr *rxkhdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -302,7 +304,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; rxkhdr->data_size = htonl(txb->len | (u32)check << 16); rxkhdr->checksum = 0; @@ -312,7 +314,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } @@ -320,7 +322,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, token = call->conn->key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg, txb->data, txb->len); + sg_init_one(&sg, rxkhdr, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); @@ -362,9 +364,9 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= txb->seq & 0x3fffffff; - crypto.buf[0] = txb->wire.callNumber; + crypto.buf[0] = htonl(call->call_id); crypto.buf[1] = htonl(x); sg_init_one(&sg, crypto.buf, 8); @@ -378,7 +380,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - txb->wire.cksum = htons(y); + txb->cksum = htons(y); switch (call->conn->security_level) { case RXRPC_SECURITY_PLAIN: @@ -726,7 +728,6 @@ static int rxkad_send_response(struct rxrpc_connection *conn, rxrpc_local_dont_fragment(conn->local, false); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); - rxrpc_local_dont_fragment(conn->local, true); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_point_rxkad_response); @@ -1256,7 +1257,7 @@ const struct rxrpc_security rxkad = { .free_preparse_server_key = rxkad_free_preparse_server_key, .destroy_server_key = rxkad_destroy_server_key, .init_connection_security = rxkad_init_connection_security, - .how_much_data = rxkad_how_much_data, + .alloc_txbuf = rxkad_alloc_txbuf, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5677d5690a02..6f765768c49c 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -240,7 +240,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_notify_end_tx_t notify_end_tx) { rxrpc_seq_t seq = txb->seq; - bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; + bool poke, last = txb->flags & RXRPC_LAST_PACKET; rxrpc_inc_stat(call->rxnet, stat_tx_data); @@ -336,7 +336,7 @@ reload: do { if (!txb) { - size_t remain, bufsize, chunk, offset; + size_t remain; _debug("alloc"); @@ -348,23 +348,11 @@ reload: * region (enc blocksize), but the trailer is not. */ remain = more ? INT_MAX : msg_data_left(msg); - ret = call->conn->security->how_much_data(call, remain, - &bufsize, &chunk, &offset); - if (ret < 0) + txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation); + if (IS_ERR(txb)) { + ret = PTR_ERR(txb); goto maybe_error; - - _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); - - /* create a buffer that we can retain until it's ACK'd */ - ret = -ENOMEM; - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, - GFP_KERNEL); - if (!txb) - goto maybe_error; - - txb->offset = offset; - txb->space -= offset; - txb->space = min_t(size_t, chunk, txb->space); + } } _debug("append"); @@ -374,8 +362,8 @@ reload: size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); _debug("add %zu", copy); - if (!copy_from_iter_full(txb->data + txb->offset, copy, - &msg->msg_iter)) + if (!copy_from_iter_full(txb->kvec[0].iov_base + txb->offset, + copy, &msg->msg_iter)) goto efault; _debug("added"); txb->space -= copy; @@ -394,18 +382,18 @@ reload: /* add the packet to the send queue if it's now full */ if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - if (msg_data_left(msg) == 0 && !more) { - txb->wire.flags |= RXRPC_LAST_PACKET; - __set_bit(RXRPC_TXBUF_LAST, &txb->flags); - } + if (msg_data_left(msg) == 0 && !more) + txb->flags |= RXRPC_LAST_PACKET; else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - txb->wire.flags |= RXRPC_MORE_PACKETS; + txb->flags |= RXRPC_MORE_PACKETS; ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; + txb->kvec[0].iov_len += txb->len; + txb->len = txb->kvec[0].iov_len; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } @@ -621,7 +609,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call; - unsigned long now, j; bool dropped_lock = false; int ret; @@ -699,25 +686,21 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) switch (p.call.nr_timeouts) { case 3: - j = msecs_to_jiffies(p.call.timeouts.normal); - if (p.call.timeouts.normal > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_rx_timo, j); + WRITE_ONCE(call->next_rx_timo, p.call.timeouts.normal); fallthrough; case 2: - j = msecs_to_jiffies(p.call.timeouts.idle); - if (p.call.timeouts.idle > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_req_timo, j); + WRITE_ONCE(call->next_req_timo, p.call.timeouts.idle); fallthrough; case 1: if (p.call.timeouts.hard > 0) { - j = p.call.timeouts.hard * HZ; - now = jiffies; - j += now; - WRITE_ONCE(call->expect_term_by, j); - rxrpc_reduce_call_timer(call, j, now, - rxrpc_timer_set_for_hard); + ktime_t delay = ms_to_ktime(p.call.timeouts.hard * MSEC_PER_SEC); + + WRITE_ONCE(call->expect_term_by, + ktime_add(p.call.timeouts.hard, + ktime_get_real())); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); + } break; } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index ecaeb4ecfb58..c9bedd0e2d86 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -15,6 +15,8 @@ static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = 255; +static const unsigned long one_ms = 1; +static const unsigned long max_ms = 1000; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY @@ -28,24 +30,24 @@ static const unsigned long max_500 = 500; * information on the individual parameters. */ static struct ctl_table rxrpc_sysctl_table[] = { - /* Values measured in milliseconds but used in jiffies */ + /* Values measured in milliseconds */ { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_ack_delay", .data = &rxrpc_idle_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_conn_expiry", diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index d43be8512386..b2a82ab756c2 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -14,45 +14,146 @@ static atomic_t rxrpc_txbuf_debug_ids; atomic_t rxrpc_nr_txbuf; /* - * Allocate and partially initialise an I/O request structure. + * Allocate and partially initialise a data transmission buffer. */ -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp) +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp) { + struct rxrpc_wire_header *whdr; struct rxrpc_txbuf *txb; + size_t total, hoff = 0; + void *buf; txb = kmalloc(sizeof(*txb), gfp); - if (txb) { - INIT_LIST_HEAD(&txb->call_link); - INIT_LIST_HEAD(&txb->tx_link); - refcount_set(&txb->ref, 1); - txb->call_debug_id = call->debug_id; - txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); - txb->space = sizeof(txb->data); - txb->len = 0; - txb->offset = 0; - txb->flags = 0; - txb->ack_why = 0; - txb->seq = call->tx_prepared + 1; - txb->wire.epoch = htonl(call->conn->proto.epoch); - txb->wire.cid = htonl(call->cid); - txb->wire.callNumber = htonl(call->call_id); - txb->wire.seq = htonl(txb->seq); - txb->wire.type = packet_type; - txb->wire.flags = call->conn->out_clientflag; - txb->wire.userStatus = 0; - txb->wire.securityIndex = call->security_ix; - txb->wire._rsvd = 0; - txb->wire.serviceId = htons(call->dest_srx.srx_service); - - trace_rxrpc_txbuf(txb->debug_id, - txb->call_debug_id, txb->seq, 1, - packet_type == RXRPC_PACKET_TYPE_DATA ? - rxrpc_txbuf_alloc_data : - rxrpc_txbuf_alloc_ack); - atomic_inc(&rxrpc_nr_txbuf); + if (!txb) + return NULL; + + if (data_align) + hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); + total = hoff + sizeof(*whdr) + data_size; + + mutex_lock(&call->conn->tx_data_alloc_lock); + buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + mutex_unlock(&call->conn->tx_data_alloc_lock); + if (!buf) { + kfree(txb); + return NULL; + } + + whdr = buf + hoff; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->last_sent = KTIME_MIN; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = data_size; + txb->len = 0; + txb->offset = sizeof(*whdr); + txb->flags = call->conn->out_clientflag; + txb->ack_why = 0; + txb->seq = call->tx_prepared + 1; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 1; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = htonl(txb->seq); + whdr->type = RXRPC_PACKET_TYPE_DATA; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_data); + + atomic_inc(&rxrpc_nr_txbuf); + return txb; +} + +/* + * Allocate and partially initialise an ACK packet. + */ +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size) +{ + struct rxrpc_wire_header *whdr; + struct rxrpc_acktrailer *trailer; + struct rxrpc_ackpacket *ack; + struct rxrpc_txbuf *txb; + gfp_t gfp = rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS; + void *buf, *buf2 = NULL; + u8 *filler; + + txb = kmalloc(sizeof(*txb), gfp); + if (!txb) + return NULL; + + buf = page_frag_alloc(&call->local->tx_alloc, + sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); + if (!buf) { + kfree(txb); + return NULL; + } + + if (sack_size) { + buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); + if (!buf2) { + page_frag_free(buf); + kfree(txb); + return NULL; + } } + whdr = buf; + ack = buf + sizeof(*whdr); + filler = buf + sizeof(*whdr) + sizeof(*ack) + 1; + trailer = buf + sizeof(*whdr) + sizeof(*ack) + 1 + 3; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = 0; + txb->len = sizeof(*whdr) + sizeof(*ack) + 3 + sizeof(*trailer); + txb->offset = 0; + txb->flags = call->conn->out_clientflag; + txb->ack_rwind = 0; + txb->seq = 0; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 3; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr) + sizeof(*ack); + txb->kvec[1].iov_base = buf2; + txb->kvec[1].iov_len = sack_size; + txb->kvec[2].iov_base = filler; + txb->kvec[2].iov_len = 3 + sizeof(*trailer); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + get_page(virt_to_head_page(trailer)); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); return txb; } @@ -71,12 +172,15 @@ void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); } -static void rxrpc_free_txbuf(struct rcu_head *rcu) +static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) { - struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + int i; trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, rxrpc_txbuf_free); + for (i = 0; i < txb->nr_kvec; i++) + if (txb->kvec[i].iov_base) + page_frag_free(txb->kvec[i].iov_base); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); } @@ -95,7 +199,7 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) dead = __refcount_dec_and_test(&txb->ref, &r); trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); if (dead) - call_rcu(&txb->rcu, rxrpc_free_txbuf); + rxrpc_free_txbuf(txb); } } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9b3e9262040b..ff5336493777 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -27,6 +27,7 @@ #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/hotdata.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> @@ -409,7 +410,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = READ_ONCE(dev_tx_weight); + int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b9fcdb0952a..c67679a41044 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -67,6 +67,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <net/rps.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 9f2c58c5a86b..2adb92b8c469 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -806,6 +806,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7cf36b8d3ae7..5a5dd3ce497f 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -611,19 +611,12 @@ static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry, return 0; } -enum cfg80211_rnr_iter_ret { - RNR_ITER_CONTINUE, - RNR_ITER_BREAK, - RNR_ITER_ERROR, -}; - -static bool -cfg80211_iter_rnr(const u8 *elems, size_t elems_len, - enum cfg80211_rnr_iter_ret - (*iter)(void *data, u8 type, - const struct ieee80211_neighbor_ap_info *info, - const u8 *tbtt_info, u8 tbtt_info_len), - void *iter_data) +bool cfg80211_iter_rnr(const u8 *elems, size_t elems_len, + enum cfg80211_rnr_iter_ret + (*iter)(void *data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len), + void *iter_data) { const struct element *rnr; const u8 *pos, *end; @@ -675,6 +668,7 @@ cfg80211_iter_rnr(const u8 *elems, size_t elems_len, return true; } +EXPORT_SYMBOL_GPL(cfg80211_iter_rnr); struct colocated_ap_data { const struct element *ssid_elem; @@ -2510,16 +2504,22 @@ ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies, if (elem->id == WLAN_EID_EXTENSION) { copied = elem->datalen - 1; - if (copied > data_len) - return -ENOSPC; - memmove(data, elem->data + 1, copied); + if (data) { + if (copied > data_len) + return -ENOSPC; + + memmove(data, elem->data + 1, copied); + } } else { copied = elem->datalen; - if (copied > data_len) - return -ENOSPC; - memmove(data, elem->data, copied); + if (data) { + if (copied > data_len) + return -ENOSPC; + + memmove(data, elem->data, copied); + } } /* Fragmented elements must have 255 bytes */ @@ -2538,10 +2538,13 @@ ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies, elem_datalen = elem->datalen; - if (copied + elem_datalen > data_len) - return -ENOSPC; + if (data) { + if (copied + elem_datalen > data_len) + return -ENOSPC; + + memmove(data + copied, elem->data, elem_datalen); + } - memmove(data + copied, elem->data, elem_datalen); copied += elem_datalen; /* Only the last fragment may be short */ diff --git a/net/wireless/tests/fragmentation.c b/net/wireless/tests/fragmentation.c index 49a339ca8880..411fae18cd88 100644 --- a/net/wireless/tests/fragmentation.c +++ b/net/wireless/tests/fragmentation.c @@ -2,7 +2,7 @@ /* * KUnit tests for element fragmentation * - * Copyright (C) 2023 Intel Corporation + * Copyright (C) 2023-2024 Intel Corporation */ #include <linux/ieee80211.h> #include <net/cfg80211.h> @@ -27,7 +27,12 @@ static void defragment_0(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 253); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); KUNIT_EXPECT_EQ(test, ret, 253); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 253); @@ -63,7 +68,12 @@ static void defragment_1(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 7); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); /* this means the last fragment was not used */ KUNIT_EXPECT_EQ(test, ret, 254 + 7); @@ -106,10 +116,15 @@ static void defragment_2(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, WLAN_EID_FRAGMENT); /* this means the last fragment was not used */ KUNIT_EXPECT_EQ(test, ret, 254 + 255 + 1); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 255 + 1); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 254); KUNIT_EXPECT_MEMEQ(test, data + 254, input + 257 + 2, 255); KUNIT_EXPECT_MEMEQ(test, data + 254 + 255, input + 2 * 257 + 2, 1); @@ -134,7 +149,12 @@ static void defragment_at_end(struct kunit *test) ret = cfg80211_defragment_element((void *)input, input, sizeof(input), - data, sizeof(input), + NULL, 0, + WLAN_EID_FRAGMENT); + KUNIT_EXPECT_EQ(test, ret, 254 + 7); + ret = cfg80211_defragment_element((void *)input, + input, sizeof(input), + data, ret, WLAN_EID_FRAGMENT); KUNIT_EXPECT_EQ(test, ret, 254 + 7); KUNIT_EXPECT_MEMEQ(test, data, input + 3, 254); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 361331c29116..e039e66ab377 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -818,8 +818,8 @@ DECLARE_EVENT_CLASS(station_add_change, params->link_sta_params.opmode_notif_used; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" - ", station flags mask: %u, station flags set: %u, " - "station modify mask: %u, listen interval: %d, aid: %u, " + ", station flags mask: 0x%x, station flags set: 0x%x, " + "station modify mask: 0x%x, listen interval: %d, aid: %u, " "plink action: %u, plink state: %u, uapsd queues: %u, vlan:%s", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->sta_mac, __entry->sta_flags_mask, __entry->sta_flags_set, @@ -1075,7 +1075,7 @@ TRACE_EVENT(rdev_return_int_mpath_info, ), TP_printk(WIPHY_PR_FMT ", returned %d. mpath info - generation: %d, " "filled: %u, frame qlen: %u, sn: %u, metric: %u, exptime: %u," - " discovery timeout: %u, discovery retries: %u, flags: %u", + " discovery timeout: %u, discovery retries: %u, flags: 0x%x", WIPHY_PR_ARG, __entry->ret, __entry->generation, __entry->filled, __entry->frame_qlen, __entry->sn, __entry->metric, __entry->exptime, __entry->discovery_timeout, @@ -1317,7 +1317,7 @@ TRACE_EVENT(rdev_assoc, req->fils_nonces, 2 * FILS_NONCE_LEN); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM" - ", previous bssid: %pM, use mfp: %s, flags: %u", + ", previous bssid: %pM, use mfp: %s, flags: 0x%x", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->bssid, __entry->prev_bssid, BOOL_TO_STR(__entry->use_mfp), __entry->flags) @@ -1439,7 +1439,7 @@ TRACE_EVENT(rdev_connect, ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM" ", ssid: %s, auth type: %d, privacy: %s, wpa versions: %u, " - "flags: %u, previous bssid: %pM", + "flags: 0x%x, previous bssid: %pM", WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->bssid, __entry->ssid, __entry->auth_type, BOOL_TO_STR(__entry->privacy), __entry->wpa_versions, __entry->flags, __entry->prev_bssid) diff --git a/net/wireless/util.c b/net/wireless/util.c index 379f742fd741..2bde8a354631 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -791,15 +791,19 @@ ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { - int offset = 0, remaining, subframe_len, padding; + int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { + int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; + if (sizeof(hdr) > remaining) + return false; + if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; @@ -807,7 +811,6 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; - remaining = skb->len - offset; if (subframe_len > remaining) return false; @@ -825,7 +828,7 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; - int offset = 0, remaining; + int offset = 0; struct { struct ethhdr eth; uint8_t flags; @@ -839,10 +842,14 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, copy_len = sizeof(hdr); while (!last) { + int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; + if (copy_len > remaining) + goto purge; + skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); @@ -852,7 +859,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ - remaining = skb->len - offset; if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks */ diff --git a/net/x25/Kconfig b/net/x25/Kconfig index 68729aa3a5d5..dc72302cbd07 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -17,8 +17,6 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <https://www.sangoma.com/tutorials/x25/> and - <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.rst> and <file:Documentation/networking/x25-iface.rst>. diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index f7a7c7798c3b..d18d51412cc0 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -460,12 +460,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index d3b3f9e720b3..fe82e2d07300 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -10,6 +10,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif +#include <net/hotdata.h> static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, struct sock *sk) @@ -169,7 +170,8 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&ctx->out_queue) >= + READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3784534c9185..653e51ae3964 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload || x->encap) + if (!x->type_offload) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd4ce21d76d7..161f535c8b94 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -21,6 +21,7 @@ #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/dst_metadata.h> +#include <net/hotdata.h> #include "xfrm_inout.h" @@ -764,7 +765,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 717855b9acf1..4df5c06e3ece 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -240,7 +240,6 @@ static void xfrmi_dev_free(struct net_device *dev) struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); - free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) @@ -749,6 +748,7 @@ static void xfrmi_dev_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); @@ -765,15 +765,9 @@ static int xfrmi_dev_init(struct net_device *dev) struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&xi->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 662c83beb345..e5722c95b8bb 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -704,9 +704,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct xfrm_state *x = skb_dst(skb)->xfrm; + int family; int err; - switch (x->outer_mode.family) { + family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family + : skb_dst(skb)->ops->family; + + switch (family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1b7e75159727..6affe5cd85d8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -29,6 +29,7 @@ #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> +#include <linux/icmp.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> @@ -2694,7 +2695,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); - family = xfrm[i]->props.family; + if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET) + family = xfrm[i]->props.family; + oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); @@ -3416,7 +3419,7 @@ decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reve } fl4->flowi4_proto = flkeys->basic.ip_proto; - fl4->flowi4_tos = flkeys->ip.tos; + fl4->flowi4_tos = flkeys->ip.tos & ~INET_ECN_MASK; } #if IS_ENABLED(CONFIG_IPV6) @@ -3503,6 +3506,128 @@ static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int return 0; } +static bool icmp_err_packet(const struct flowi *fl, unsigned short family) +{ + const struct flowi4 *fl4 = &fl->u.ip4; + + if (family == AF_INET && + fl4->flowi4_proto == IPPROTO_ICMP && + (fl4->fl4_icmp_type == ICMP_DEST_UNREACH || + fl4->fl4_icmp_type == ICMP_TIME_EXCEEDED)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) { + const struct flowi6 *fl6 = &fl->u.ip6; + + if (fl6->flowi6_proto == IPPROTO_ICMPV6 && + (fl6->fl6_icmp_type == ICMPV6_DEST_UNREACH || + fl6->fl6_icmp_type == ICMPV6_PKT_TOOBIG || + fl6->fl6_icmp_type == ICMPV6_TIME_EXCEED)) + return true; + } +#endif + return false; +} + +static bool xfrm_icmp_flow_decode(struct sk_buff *skb, unsigned short family, + const struct flowi *fl, struct flowi *fl1) +{ + bool ret = true; + struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); + int hl = family == AF_INET ? (sizeof(struct iphdr) + sizeof(struct icmphdr)) : + (sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr)); + + if (!newskb) + return true; + + if (!pskb_pull(newskb, hl)) + goto out; + + skb_reset_network_header(newskb); + + if (xfrm_decode_session_reverse(dev_net(skb->dev), newskb, fl1, family) < 0) + goto out; + + fl1->flowi_oif = fl->flowi_oif; + fl1->flowi_mark = fl->flowi_mark; + fl1->flowi_tos = fl->flowi_tos; + nf_nat_decode_session(newskb, fl1, family); + ret = false; + +out: + consume_skb(newskb); + return ret; +} + +static bool xfrm_selector_inner_icmp_match(struct sk_buff *skb, unsigned short family, + const struct xfrm_selector *sel, + const struct flowi *fl) +{ + bool ret = false; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return ret; + + ret = xfrm_selector_match(sel, &fl1, family); + } + + return ret; +} + +static inline struct +xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, + const struct flowi *fl, unsigned short family, + u32 if_id) +{ + struct xfrm_policy *pol = NULL; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + struct net *net = dev_net(skb->dev); + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return pol; + + pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); + } + + return pol; +} + +static inline struct +dst_entry *xfrm_out_fwd_icmp(struct sk_buff *skb, struct flowi *fl, + unsigned short family, struct dst_entry *dst) +{ + if (icmp_err_packet(fl, family)) { + struct net *net = dev_net(skb->dev); + struct dst_entry *dst2; + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return dst; + + dst_hold(dst); + + dst2 = xfrm_lookup(net, dst, &fl1, NULL, (XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_ICMP)); + + if (IS_ERR(dst2)) + return dst; + + if (dst2->xfrm) { + dst_release(dst); + dst = dst2; + } else { + dst_release(dst2); + } + } + + return dst; +} + int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { @@ -3549,9 +3674,17 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; + int ret = 0; + if (!xfrm_selector_match(&x->sel, &fl, family)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); - return 0; + ret = 1; + if (x->props.flags & XFRM_STATE_ICMP && + xfrm_selector_inner_icmp_match(skb, family, &x->sel, &fl)) + ret = 0; + if (ret) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); + return 0; + } } } } @@ -3574,6 +3707,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } + if (!pol && dir == XFRM_POLICY_FWD) + pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); + if (!pol) { if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); @@ -3707,6 +3843,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) res = 0; dst = NULL; } + + if (dst && !dst->xfrm) + dst = xfrm_out_fwd_icmp(skb, &fl, family, dst); + skb_dst_set(skb, dst); return res; } @@ -4025,10 +4165,7 @@ static int __net_init xfrm_policy_init(struct net *net) int dir, err; if (net_eq(net, &init_net)) { - xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", - sizeof(struct xfrm_dst), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL); + xfrm_dst_cache = KMEM_CACHE(xfrm_dst, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a5232dcfea46..810b520493f3 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 5a84b6443875..3ee8ecfb8c04 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -33,7 +33,7 @@ ld-option = $(success,$(LD) -v $(1)) # $(as-instr,<instr>) # Return y if the assembler supports <instr>, n otherwise -as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler-with-cpp -o /dev/null -) +as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -) # check if $(CC) and $(LD) exist $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found) diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 8fcb427405a6..92be0c9a13ee 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -38,7 +38,7 @@ as-option = $(call try-run,\ # Usage: aflags-y += $(call as-instr,instr,option1,option2) as-instr = $(call try-run,\ - printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3)) + printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3)) # __cc-option # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586) diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index df387de29bfa..45c3e5dda355 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -179,7 +179,8 @@ static int __init integrity_add_key(const unsigned int id, const void *data, KEY_ALLOC_NOT_IN_QUOTA); if (IS_ERR(key)) { rc = PTR_ERR(key); - pr_err("Problem loading X.509 certificate %d\n", rc); + if (id != INTEGRITY_KEYRING_MACHINE) + pr_err("Problem loading X.509 certificate %d\n", rc); } else { pr_notice("Loaded X.509 cert '%s'\n", key_ref_to_ptr(key)->description); diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 57ee70ae50f2..ea3140d510ec 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2649,13 +2649,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, { int error = buffer_len; size_t avail_len = buffer_len; - char *cp0 = head->write_buf; + char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ diff --git a/sound/core/Makefile b/sound/core/Makefile index a6b444ee2832..f6526b337137 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -32,7 +32,6 @@ snd-ump-objs := ump.o snd-ump-$(CONFIG_SND_UMP_LEGACY_RAWMIDI) += ump_convert.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o -snd-rtctimer-objs := rtctimer.o snd-hwdep-objs := hwdep.o snd-seq-device-objs := seq_device.o diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index f5ff00f99788..21baf6bf7e25 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -486,6 +486,11 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream, i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS); if (snd_interval_single(i)) params->msbits = snd_interval_value(i); + m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); + if (snd_mask_single(m)) { + snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m); + params->msbits = snd_pcm_format_width(format); + } } if (params->msbits) { diff --git a/sound/core/ump.c b/sound/core/ump.c index 3bef1944e955..fe7911498cc4 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -985,7 +985,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) struct snd_ump_endpoint *ump = substream->rmidi->private_data; int dir = substream->stream; int group = ump->legacy_mapping[substream->number]; - int err; + int err = 0; mutex_lock(&ump->open_mutex); if (ump->legacy_substreams[dir][group]) { @@ -1009,7 +1009,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) spin_unlock_irq(&ump->legacy_locks[dir]); unlock: mutex_unlock(&ump->open_mutex); - return 0; + return err; } static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream) diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index a13c0b408aad..7be17bca257f 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -951,7 +951,7 @@ static int generate_tx_packet_descs(struct amdtp_stream *s, struct pkt_desc *des // to the reason. unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle, IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES); - lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0); + lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0); } if (lost) { dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n", diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0ec1312bffd5..62701197a019 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3684,6 +3684,7 @@ static void alc285_hp_init(struct hda_codec *codec) int i, val; int coef38, coef0d, coef36; + alc_write_coefex_idx(codec, 0x58, 0x00, 0x1888); /* write default value */ alc_update_coef_idx(codec, 0x4a, 1<<15, 1<<15); /* Reset HP JD */ coef38 = alc_read_coef_idx(codec, 0x38); /* Amp control */ coef0d = alc_read_coef_idx(codec, 0x0d); /* Digital Misc control */ @@ -7444,6 +7445,7 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC298_FIXUP_LENOVO_C940_DUET7, + ALC287_FIXUP_LENOVO_14IRP8_DUETITL, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, @@ -7495,6 +7497,26 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* A special fixup for Lenovo Slim/Yoga Pro 9 14IRP8 and Yoga DuetITL 2021; + * 14IRP8 PCI SSID will mistakenly be matched with the DuetITL codec SSID, + * so we need to apply a different fixup in this case. The only DuetITL codec + * SSID reported so far is the 17aa:3802 while the 14IRP8 has the 17aa:38be + * and 17aa:38bf. If it weren't for the PCI SSID, the 14IRP8 models would + * have matched correctly by their codecs. + */ +static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa3802) + id = ALC287_FIXUP_YOGA7_14ITL_SPEAKERS; /* DuetITL */ + else + id = ALC287_FIXUP_TAS2781_I2C; /* 14IRP8 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -9379,6 +9401,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_lenovo_c940_duet7, }, + [ALC287_FIXUP_LENOVO_14IRP8_DUETITL] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_14irp8_duetitl, + }, [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9585,7 +9611,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = tas2781_fixup_i2c, .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, }, [ALC287_FIXUP_YOGA7_14ARB7_I2C] = { .type = HDA_FIXUP_FUNC, @@ -9746,6 +9772,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), @@ -9902,6 +9929,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), @@ -9927,11 +9955,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -10247,7 +10277,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), - SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8 / DuetITL 2021", ALC287_FIXUP_LENOVO_14IRP8_DUETITL), SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index cc231185d72c..abb9589b8477 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -203,6 +203,20 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21J2"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21J0"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "21J5"), } }, diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c index 7af6a349b1d4..694b8e313902 100644 --- a/sound/soc/amd/yc/pci-acp6x.c +++ b/sound/soc/amd/yc/pci-acp6x.c @@ -162,6 +162,7 @@ static int snd_acp6x_probe(struct pci_dev *pci, /* Yellow Carp device check */ switch (pci->revision) { case 0x60: + case 0x63: case 0x6f: break; default: diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index 44c221745c3b..2392c6effed8 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -184,7 +184,7 @@ static int cs35l45_activate_ctl(struct snd_soc_component *component, else snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", ctl_name); - kcontrol = snd_soc_card_get_kcontrol(component->card, name); + kcontrol = snd_soc_card_get_kcontrol_locked(component->card, name); if (!kcontrol) { dev_err(component->dev, "Can't find kcontrol %s\n", name); return -EINVAL; diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index 995d979b6d87..cb4e83126b08 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -335,6 +335,7 @@ void cs35l56_wait_min_reset_pulse(void) EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, SND_SOC_CS35L56_SHARED); static const struct reg_sequence cs35l56_system_reset_seq[] = { + REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0), REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET), }; diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 2c1313e34cce..6dd0319bc843 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -114,7 +114,7 @@ static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private name = full_name; } - kcontrol = snd_soc_card_get_kcontrol(dapm->card, name); + kcontrol = snd_soc_card_get_kcontrol_locked(dapm->card, name); if (!kcontrol) { dev_warn(cs35l56->base.dev, "Could not find control %s\n", name); continue; diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index f0fb33d719c2..c46f64557a7f 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -174,7 +174,9 @@ static int fsl_xcvr_activate_ctl(struct snd_soc_dai *dai, const char *name, struct snd_kcontrol *kctl; bool enabled; - kctl = snd_soc_card_get_kcontrol(card, name); + lockdep_assert_held(&card->snd_card->controls_rwsem); + + kctl = snd_soc_card_get_kcontrol_locked(card, name); if (kctl == NULL) return -ENOENT; @@ -576,10 +578,14 @@ static int fsl_xcvr_startup(struct snd_pcm_substream *substream, xcvr->streams |= BIT(substream->stream); if (!xcvr->soc_data->spdif_only) { + struct snd_soc_card *card = dai->component->card; + /* Disable XCVR controls if there is stream started */ + down_read(&card->snd_card->controls_rwsem); fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, false); fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, false); fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, false); + up_read(&card->snd_card->controls_rwsem); } return 0; @@ -598,11 +604,15 @@ static void fsl_xcvr_shutdown(struct snd_pcm_substream *substream, /* Enable XCVR controls if there is no stream started */ if (!xcvr->streams) { if (!xcvr->soc_data->spdif_only) { + struct snd_soc_card *card = dai->component->card; + + down_read(&card->snd_card->controls_rwsem); fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, true); fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, (xcvr->mode == FSL_XCVR_MODE_ARC)); fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, (xcvr->mode == FSL_XCVR_MODE_EARC)); + up_read(&card->snd_card->controls_rwsem); } ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_IER0, FSL_XCVR_IRQ_EARC_ALL, 0); diff --git a/sound/soc/qcom/lpass-cdc-dma.c b/sound/soc/qcom/lpass-cdc-dma.c index 48b03e60e3a3..8106c586f68a 100644 --- a/sound/soc/qcom/lpass-cdc-dma.c +++ b/sound/soc/qcom/lpass-cdc-dma.c @@ -259,7 +259,7 @@ static int lpass_cdc_dma_daiops_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct snd_soc_pcm_runtime *soc_runtime = snd_soc_substream_to_rtd(substream); - struct lpaif_dmactl *dmactl; + struct lpaif_dmactl *dmactl = NULL; int ret = 0, id; switch (cmd) { diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c index 285ab4c9c716..8a2f163da6bc 100644 --- a/sound/soc/soc-card.c +++ b/sound/soc/soc-card.c @@ -5,6 +5,9 @@ // Copyright (C) 2019 Renesas Electronics Corp. // Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> // + +#include <linux/lockdep.h> +#include <linux/rwsem.h> #include <sound/soc.h> #include <sound/jack.h> @@ -26,12 +29,15 @@ static inline int _soc_card_ret(struct snd_soc_card *card, return ret; } -struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, - const char *name) +struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card, + const char *name) { struct snd_card *card = soc_card->snd_card; struct snd_kcontrol *kctl; + /* must be held read or write */ + lockdep_assert_held(&card->controls_rwsem); + if (unlikely(!name)) return NULL; @@ -40,6 +46,20 @@ struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, return kctl; return NULL; } +EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol_locked); + +struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, + const char *name) +{ + struct snd_card *card = soc_card->snd_card; + struct snd_kcontrol *kctl; + + down_read(&card->controls_rwsem); + kctl = snd_soc_card_get_kcontrol_locked(soc_card, name); + up_read(&card->controls_rwsem); + + return kctl; +} EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol); static int jack_new(struct snd_soc_card *card, const char *id, int type, diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 93cb411adf72..bb65ee840cda 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -133,6 +137,21 @@ enum { }; enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -144,6 +163,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index da1aa10bbcc3..8e9e09d84e26 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -11,11 +11,11 @@ $(SUBDIRS): $(MAKE) -C $@ ; \ fi -clean hardclean: +clean distclean: @for dir in $(SUBDIRS) ; do \ if [ -f "$$dir/Makefile" ] ; then \ $(MAKE) -C $$dir $@; \ fi \ done -.PHONY: clean all $(SUBDIRS) +.PHONY: all clean distclean $(SUBDIRS) diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index 0f8239979670..f131e33ac3ee 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -6,7 +6,7 @@ import json import pprint import time -from lib import YnlFamily, Netlink +from lib import YnlFamily, Netlink, NlError class YnlEncoder(json.JSONEncoder): @@ -38,6 +38,8 @@ def main(): const=Netlink.NLM_F_APPEND) parser.add_argument('--process-unknown', action=argparse.BooleanOptionalAction) parser.add_argument('--output-json', action='store_true') + parser.add_argument('--dbg-small-recv', default=0, const=4000, + action='store', nargs='?', type=int) args = parser.parse_args() def output(msg): @@ -53,7 +55,10 @@ def main(): if args.json_text: attrs = json.loads(args.json_text) - ynl = YnlFamily(args.spec, args.schema, args.process_unknown) + ynl = YnlFamily(args.spec, args.schema, args.process_unknown, + recv_size=args.dbg_small_recv) + if args.dbg_small_recv: + ynl.set_recv_dbg(True) if args.ntf: ynl.ntf_subscribe(args.ntf) @@ -61,12 +66,16 @@ def main(): if args.sleep: time.sleep(args.sleep) - if args.do: - reply = ynl.do(args.do, attrs, args.flags) - output(reply) - if args.dump: - reply = ynl.dump(args.dump, attrs) - output(reply) + try: + if args.do: + reply = ynl.do(args.do, attrs, args.flags) + output(reply) + if args.dump: + reply = ynl.dump(args.dump, attrs) + output(reply) + except NlError as e: + print(e) + exit(1) if args.ntf: ynl.check_ntf() diff --git a/tools/net/ynl/generated/Makefile b/tools/net/ynl/generated/Makefile index 7135028cb449..713f5fb9cc2d 100644 --- a/tools/net/ynl/generated/Makefile +++ b/tools/net/ynl/generated/Makefile @@ -43,11 +43,11 @@ protos.a: $(OBJS) clean: rm -f *.o -hardclean: clean +distclean: clean rm -f *.c *.h *.a regen: @../ynl-regen.sh -.PHONY: all clean hardclean regen +.PHONY: all clean distclean regen .DEFAULT_GOAL: all diff --git a/tools/net/ynl/lib/Makefile b/tools/net/ynl/lib/Makefile index d2e50fd0a52d..dfff3ecd1cba 100644 --- a/tools/net/ynl/lib/Makefile +++ b/tools/net/ynl/lib/Makefile @@ -17,12 +17,13 @@ ynl.a: $(OBJS) ar rcs $@ $(OBJS) clean: rm -f *.o *.d *~ + rm -rf __pycache__ -hardclean: clean +distclean: clean rm -f *.a %.o: %.c $(COMPILE.c) -MMD -c -o $@ $< -.PHONY: all clean +.PHONY: all clean distclean .DEFAULT_GOAL=all diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py index f7eaa07783e7..9137b83e580a 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/lib/__init__.py @@ -2,7 +2,7 @@ from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \ SpecFamily, SpecOperation -from .ynl import YnlFamily, Netlink +from .ynl import YnlFamily, Netlink, NlError __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet", - "SpecFamily", "SpecOperation", "YnlFamily", "Netlink"] + "SpecFamily", "SpecOperation", "YnlFamily", "Netlink", "NlError"] diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index fbce52395b3b..6d08ab9e213f 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -418,6 +418,7 @@ class SpecFamily(SpecElement): consts dict of all constants/enums fixed_header string, optional name of family default fixed header struct mcast_groups dict of all multicast groups (index by name) + kernel_family dict of kernel family attributes """ def __init__(self, spec_path, schema_path=None, exclude_ops=None): with open(spec_path, "r") as stream: @@ -461,6 +462,7 @@ class SpecFamily(SpecElement): self.ntfs = collections.OrderedDict() self.consts = collections.OrderedDict() self.mcast_groups = collections.OrderedDict() + self.kernel_family = collections.OrderedDict(self.yaml.get('kernel-family', {})) last_exception = None while len(self._resolution_list) > 0: diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h index a8099fab035d..6cf890080dc0 100644 --- a/tools/net/ynl/lib/ynl-priv.h +++ b/tools/net/ynl/lib/ynl-priv.h @@ -135,6 +135,8 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); /* Netlink message handling helpers */ +#define YNL_MSG_OVERFLOW 1 + static inline struct nlmsghdr *ynl_nlmsg_put_header(void *buf) { struct nlmsghdr *nlh = buf; @@ -239,11 +241,29 @@ ynl_attr_first(const void *start, size_t len, size_t skip) return ynl_attr_if_good(start + len, attr); } +static inline bool +__ynl_attr_put_overflow(struct nlmsghdr *nlh, size_t size) +{ + bool o; + + /* ynl_msg_start() stashed buffer length in nlmsg_pid. */ + o = nlh->nlmsg_len + NLA_HDRLEN + NLMSG_ALIGN(size) > nlh->nlmsg_pid; + if (o) + /* YNL_MSG_OVERFLOW is < NLMSG_HDRLEN, all subsequent checks + * are guaranteed to fail. + */ + nlh->nlmsg_pid = YNL_MSG_OVERFLOW; + return o; +} + static inline struct nlattr * ynl_attr_nest_start(struct nlmsghdr *nlh, unsigned int attr_type) { struct nlattr *attr; + if (__ynl_attr_put_overflow(nlh, 0)) + return ynl_nlmsg_end_addr(nlh) - NLA_HDRLEN; + attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type | NLA_F_NESTED; nlh->nlmsg_len += NLA_HDRLEN; @@ -263,6 +283,9 @@ ynl_attr_put(struct nlmsghdr *nlh, unsigned int attr_type, { struct nlattr *attr; + if (__ynl_attr_put_overflow(nlh, size)) + return; + attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; attr->nla_len = NLA_HDRLEN + size; @@ -276,14 +299,17 @@ static inline void ynl_attr_put_str(struct nlmsghdr *nlh, unsigned int attr_type, const char *str) { struct nlattr *attr; - const char *end; + size_t len; + + len = strlen(str); + if (__ynl_attr_put_overflow(nlh, len)) + return; attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; - end = stpcpy(ynl_attr_data(attr), str); - attr->nla_len = - NLA_HDRLEN + NLA_ALIGN(end - (char *)ynl_attr_data(attr)); + strcpy(ynl_attr_data(attr), str); + attr->nla_len = NLA_HDRLEN + NLA_ALIGN(len); nlh->nlmsg_len += NLMSG_ALIGN(attr->nla_len); } diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index 484070492b17..4b9c091fc86b 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -404,9 +404,33 @@ struct nlmsghdr *ynl_msg_start(struct ynl_sock *ys, __u32 id, __u16 flags) nlh->nlmsg_flags = flags; nlh->nlmsg_seq = ++ys->seq; + /* This is a local YNL hack for length checking, we put the buffer + * length in nlmsg_pid, since messages sent to the kernel always use + * PID 0. Message needs to be terminated with ynl_msg_end(). + */ + nlh->nlmsg_pid = YNL_SOCKET_BUFFER_SIZE; + return nlh; } +static int ynl_msg_end(struct ynl_sock *ys, struct nlmsghdr *nlh) +{ + /* We stash buffer length in nlmsg_pid. */ + if (nlh->nlmsg_pid == 0) { + yerr(ys, YNL_ERROR_INPUT_INVALID, + "Unknown input buffer length"); + return -EINVAL; + } + if (nlh->nlmsg_pid == YNL_MSG_OVERFLOW) { + yerr(ys, YNL_ERROR_INPUT_TOO_BIG, + "Constructed message longer than internal buffer"); + return -EMSGSIZE; + } + + nlh->nlmsg_pid = 0; + return 0; +} + struct nlmsghdr * ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags, __u8 cmd, __u8 version) @@ -607,6 +631,10 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) nlh = ynl_gemsg_start_req(ys, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 1); ynl_attr_put_str(nlh, CTRL_ATTR_FAMILY_NAME, family_name); + err = ynl_msg_end(ys, nlh); + if (err < 0) + return err; + err = send(ys->socket, nlh, nlh->nlmsg_len, 0); if (err < 0) { perr(ys, "failed to request socket family info"); @@ -868,6 +896,10 @@ int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, { int err; + err = ynl_msg_end(ys, req_nlh); + if (err < 0) + return err; + err = send(ys->socket, req_nlh, req_nlh->nlmsg_len, 0); if (err < 0) return err; @@ -921,6 +953,10 @@ int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, { int err; + err = ynl_msg_end(ys, req_nlh); + if (err < 0) + return err; + err = send(ys->socket, req_nlh, req_nlh->nlmsg_len, 0); if (err < 0) return err; diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h index dbeeef8ce91a..9842e85a8c57 100644 --- a/tools/net/ynl/lib/ynl.h +++ b/tools/net/ynl/lib/ynl.h @@ -20,6 +20,8 @@ enum ynl_error_code { YNL_ERROR_ATTR_INVALID, YNL_ERROR_UNKNOWN_NTF, YNL_ERROR_INV_RESP, + YNL_ERROR_INPUT_INVALID, + YNL_ERROR_INPUT_TOO_BIG, }; /** diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index ac55aa5a3083..5fa7957f6e0f 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -7,6 +7,7 @@ import random import socket import struct from struct import Struct +import sys import yaml import ipaddress import uuid @@ -84,6 +85,10 @@ class NlError(Exception): return f"Netlink error: {os.strerror(-self.nl_msg.error)}\n{self.nl_msg}" +class ConfigError(Exception): + pass + + class NlAttr: ScalarFormat = namedtuple('ScalarFormat', ['native', 'big', 'little']) type_formats = { @@ -213,11 +218,11 @@ class NlMsg: return self.nl_type def __repr__(self): - msg = f"nl_len = {self.nl_len} ({len(self.raw)}) nl_flags = 0x{self.nl_flags:x} nl_type = {self.nl_type}\n" + msg = f"nl_len = {self.nl_len} ({len(self.raw)}) nl_flags = 0x{self.nl_flags:x} nl_type = {self.nl_type}" if self.error: - msg += '\terror: ' + str(self.error) + msg += '\n\terror: ' + str(self.error) if self.extack: - msg += '\textack: ' + repr(self.extack) + msg += '\n\textack: ' + repr(self.extack) return msg @@ -348,6 +353,9 @@ class NetlinkProtocol: raise Exception(f'Multicast group "{mcast_name}" not present in the spec') return mcast_groups[mcast_name].value + def msghdr_size(self): + return 16 + class GenlProtocol(NetlinkProtocol): def __init__(self, family_name): @@ -373,6 +381,8 @@ class GenlProtocol(NetlinkProtocol): raise Exception(f'Multicast group "{mcast_name}" not present in the family') return self.genl_family['mcast'][mcast_name] + def msghdr_size(self): + return super().msghdr_size() + 4 class SpaceAttrs: @@ -400,7 +410,8 @@ class SpaceAttrs: class YnlFamily(SpecFamily): - def __init__(self, def_path, schema=None, process_unknown=False): + def __init__(self, def_path, schema=None, process_unknown=False, + recv_size=0): super().__init__(def_path, schema) self.include_raw = False @@ -415,6 +426,17 @@ class YnlFamily(SpecFamily): except KeyError: raise Exception(f"Family '{self.yaml['name']}' not supported by the kernel") + self._recv_dbg = False + # Note that netlink will use conservative (min) message size for + # the first dump recv() on the socket, our setting will only matter + # from the second recv() on. + self._recv_size = recv_size if recv_size else 131072 + # Netlink will always allocate at least PAGE_SIZE - sizeof(skb_shinfo) + # for a message, so smaller receive sizes will lead to truncation. + # Note that the min size for other families may be larger than 4k! + if self._recv_size < 4000: + raise ConfigError() + self.sock = socket.socket(socket.AF_NETLINK, socket.SOCK_RAW, self.nlproto.proto_num) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_CAP_ACK, 1) self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_EXT_ACK, 1) @@ -438,6 +460,17 @@ class YnlFamily(SpecFamily): self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, mcast_id) + def set_recv_dbg(self, enabled): + self._recv_dbg = enabled + + def _recv_dbg_print(self, reply, nl_msgs): + if not self._recv_dbg: + return + print("Recv: read", len(reply), "bytes,", + len(nl_msgs.msgs), "messages", file=sys.stderr) + for nl_msg in nl_msgs: + print(" ", nl_msg, file=sys.stderr) + def _encode_enum(self, attr_spec, value): enum = self.consts[attr_spec['enum']] if enum.type == 'flags' or attr_spec.get('enum-as-flags', False): @@ -456,7 +489,7 @@ class YnlFamily(SpecFamily): except (ValueError, TypeError) as e: if 'enum' not in attr_spec: raise e - return self._encode_enum(attr_spec, value); + return self._encode_enum(attr_spec, value) def _add_attr(self, space, name, value, search_attrs): try: @@ -562,6 +595,16 @@ class YnlFamily(SpecFamily): decoded.append({ item.type: subattrs }) return decoded + def _decode_nest_type_value(self, attr, attr_spec): + decoded = {} + value = attr + for name in attr_spec['type-value']: + value = NlAttr(value.raw, 0) + decoded[name] = value.type + subattrs = self._decode(NlAttrs(value.raw), attr_spec['nested-attributes']) + decoded.update(subattrs) + return decoded + def _decode_unknown(self, attr): if attr.is_nest: return self._decode(NlAttrs(attr.raw), None) @@ -653,6 +696,8 @@ class YnlFamily(SpecFamily): decoded = {"value": value, "selector": selector} elif attr_spec["type"] == 'sub-message': decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) + elif attr_spec["type"] == 'nest-type-value': + decoded = self._decode_nest_type_value(attr, attr_spec) else: if not self.process_unknown: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') @@ -693,7 +738,7 @@ class YnlFamily(SpecFamily): return msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set)) - offset = 20 + self._struct_size(op.fixed_header) + offset = self.nlproto.msghdr_size() + self._struct_size(op.fixed_header) path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset, extack['bad-attr-offs']) if path: @@ -799,11 +844,12 @@ class YnlFamily(SpecFamily): def check_ntf(self): while True: try: - reply = self.sock.recv(128 * 1024, socket.MSG_DONTWAIT) + reply = self.sock.recv(self._recv_size, socket.MSG_DONTWAIT) except BlockingIOError: return nms = NlMsgs(reply) + self._recv_dbg_print(reply, nms) for nl_msg in nms: if nl_msg.error: print("Netlink error in ntf!?", os.strerror(-nl_msg.error)) @@ -854,8 +900,9 @@ class YnlFamily(SpecFamily): done = False rsp = [] while not done: - reply = self.sock.recv(128 * 1024) + reply = self.sock.recv(self._recv_size) nms = NlMsgs(reply, attr_space=op.attr_set) + self._recv_dbg_print(reply, nms) for nl_msg in nms: if nl_msg.extack: self._decode_extack(msg, op, nl_msg.extack) diff --git a/tools/net/ynl/samples/Makefile b/tools/net/ynl/samples/Makefile index 1d33e98e3ffe..e194a7565861 100644 --- a/tools/net/ynl/samples/Makefile +++ b/tools/net/ynl/samples/Makefile @@ -28,8 +28,8 @@ $(BINS): ../lib/ynl.a ../generated/protos.a $(SRCS) clean: rm -f *.o *.d *~ -hardclean: clean +distclean: clean rm -f $(BINS) -.PHONY: all clean +.PHONY: all clean distclean .DEFAULT_GOAL=all diff --git a/tools/net/ynl/samples/page-pool.c b/tools/net/ynl/samples/page-pool.c index 098b5190d0e5..332f281ee5cb 100644 --- a/tools/net/ynl/samples/page-pool.c +++ b/tools/net/ynl/samples/page-pool.c @@ -95,6 +95,8 @@ int main(int argc, char **argv) if (pp->_present.alloc_fast) s->alloc_fast += pp->alloc_fast; + if (pp->_present.alloc_refill) + s->alloc_fast += pp->alloc_refill; if (pp->_present.alloc_slow) s->alloc_slow += pp->alloc_slow; if (pp->_present.recycle_ring) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 2f5febfe66a1..6b7eb2d2aaf1 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -80,6 +80,8 @@ class Type(SpecAttr): value = self.checks.get(limit, default) if value is None: return value + elif value in self.family.consts: + return c_upper(f"{self.family['name']}-{value}") if not isinstance(value, int): value = limit_to_number(value) return value @@ -1667,7 +1669,7 @@ def _multi_parse(ri, struct, init_lines, local_vars): aspec = struct[anest] ri.cw.block_start(line=f"if (n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc({aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") @@ -2340,6 +2342,10 @@ def print_kernel_family_struct_hdr(family, cw): cw.p(f"extern struct genl_family {family.c_name}_nl_family;") cw.nl() + if 'sock-priv' in family.kernel_family: + cw.p(f'void {family.c_name}_nl_sock_priv_init({family.kernel_family["sock-priv"]} *priv);') + cw.p(f'void {family.c_name}_nl_sock_priv_destroy({family.kernel_family["sock-priv"]} *priv);') + cw.nl() def print_kernel_family_struct_src(family, cw): @@ -2361,6 +2367,11 @@ def print_kernel_family_struct_src(family, cw): if family.mcgrps['list']: cw.p(f'.mcgrps\t\t= {family.c_name}_nl_mcgrps,') cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),') + if 'sock-priv' in family.kernel_family: + cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),') + # Force cast here, actual helpers take pointer to the real type. + cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,') + cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,') cw.block_end(';') @@ -2657,6 +2668,7 @@ def main(): cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') cw.nl() headers = ['uapi/' + parsed.uapi_header] + headers += parsed.kernel_family.get('headers', []) else: cw.p('#include <stdlib.h>') cw.p('#include <string.h>') diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c index a52ecd43dbe3..ca81afa4ee90 100644 --- a/tools/testing/selftests/alsa/test-pcmtest-driver.c +++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c @@ -127,11 +127,11 @@ FIXTURE_SETUP(pcmtest) { int err; if (geteuid()) - SKIP(exit(-1), "This test needs root to run!"); + SKIP(return, "This test needs root to run!"); err = read_patterns(); if (err) - SKIP(exit(-1), "Can't read patterns. Probably, module isn't loaded"); + SKIP(return, "Can't read patterns. Probably, module isn't loaded"); card_name = malloc(127); ASSERT_NE(card_name, NULL); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index c3b45745cbcc..6d8b54124cb3 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + if (!ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags")) goto out; @@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags"); out: bpf_link__destroy(link); diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 04cdbce4652f..99e561f18f9b 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -237,6 +237,76 @@ int bpf_loop_iter_limit_nested(void *unused) return 1000 * a + b + c; } +struct iter_limit_bug_ctx { + __u64 a; + __u64 b; + __u64 c; +}; + +static __naked void iter_limit_bug_cb(void) +{ + /* This is the same as C code below, but written + * in assembly to control which branches are fall-through. + * + * switch (bpf_get_prandom_u32()) { + * case 1: ctx->a = 42; break; + * case 2: ctx->b = 42; break; + * default: ctx->c = 42; break; + * } + */ + asm volatile ( + "r9 = r2;" + "call %[bpf_get_prandom_u32];" + "r1 = r0;" + "r2 = 42;" + "r0 = 0;" + "if r1 == 0x1 goto 1f;" + "if r1 == 0x2 goto 2f;" + "*(u64 *)(r9 + 16) = r2;" + "exit;" + "1: *(u64 *)(r9 + 0) = r2;" + "exit;" + "2: *(u64 *)(r9 + 8) = r2;" + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +SEC("tc") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +int iter_limit_bug(struct __sk_buff *skb) +{ + struct iter_limit_bug_ctx ctx = { 7, 7, 7 }; + + bpf_loop(2, iter_limit_bug_cb, &ctx, 0); + + /* This is the same as C code below, + * written in assembly to guarantee checks order. + * + * if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7) + * asm volatile("r1 /= 0;":::"r1"); + */ + asm volatile ( + "r1 = *(u64 *)%[ctx_a];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_b];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_c];" + "if r1 != 7 goto 1f;" + "r1 /= 0;" + "1:" + : + : [ctx_a]"m"(ctx.a), + [ctx_b]"m"(ctx.b), + [ctx_c]"m"(ctx.c) + : "r1" + ); + return 0; +} + #define ARR_SZ 1000000 int zero; char arr[ARR_SZ]; diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index 616d3581419c..31252bc8775e 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -869,7 +869,7 @@ bloom_simple_test() bloom_complex_test() { # Bloom filter index computation is affected from region ID, eRP - # ID and from the region key size. In order to excercise those parts + # ID and from the region key size. In order to exercise those parts # of the Bloom filter code, use a series of regions, each with a # different key size and send packet that should hit all of them. local index diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh index 7d7829f57550..6c52ce1b0450 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh @@ -49,7 +49,7 @@ for o in llrs rs; do Active FEC encoding: ${o^^}" done -# Test mutliple bits +# Test multiple bits $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 634be793ad58..4fd735e48ee7 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -382,29 +382,33 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ pid_t child = 1; \ + int status = 0; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ if (setjmp(_metadata->env) == 0) { \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (_metadata->exit_code) \ - return; \ - _metadata->setup_completed = true; \ /* Use the same _metadata. */ \ child = vfork(); \ if (child == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (_metadata->exit_code) \ + _exit(0); \ + _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ - _exit(0); \ - } \ - if (child < 0) { \ + } else if (child < 0 || child != waitpid(child, &status, 0)) { \ ksft_print_msg("ERROR SPAWNING TEST GRANDCHILD\n"); \ _metadata->exit_code = KSFT_FAIL; \ } \ } \ - if (child == 0) \ - /* Child failed and updated the shared _metadata. */ \ + if (child == 0) { \ + if (_metadata->setup_completed && !_metadata->teardown_parent) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ _exit(0); \ - if (_metadata->setup_completed) \ + } \ + if (_metadata->setup_completed && _metadata->teardown_parent) \ fixture_name##_teardown(_metadata, &self, variant->data); \ + if (!WIFEXITED(status) && WIFSIGNALED(status)) \ + /* Forward signal to __wait_for_test(). */ \ + kill(getpid(), WTERMSIG(status)); \ __test_check_assert(_metadata); \ } \ static struct __test_metadata \ @@ -414,6 +418,7 @@ .fixture = &_##fixture_name##_fixture_object, \ .termsig = signal, \ .timeout = tmout, \ + .teardown_parent = false, \ }; \ static void __attribute__((constructor)) \ _register_##fixture_name##_##test_name(void) \ @@ -873,6 +878,7 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ bool aborted; /* stopped test due to failed ASSERT */ bool setup_completed; /* did setup finish? */ + bool teardown_parent; /* run teardown in a parent process */ jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 98817a14c91b..9a6036fbf289 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -285,6 +285,8 @@ static void prepare_layout_opt(struct __test_metadata *const _metadata, static void prepare_layout(struct __test_metadata *const _metadata) { + _metadata->teardown_parent = true; + prepare_layout_opt(_metadata, &mnt_tmp); } @@ -3861,9 +3863,7 @@ FIXTURE_SETUP(layout1_bind) FIXTURE_TEARDOWN(layout1_bind) { - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(dir_s2d2)); - clear_cap(_metadata, CAP_SYS_ADMIN); + /* umount(dir_s2d2)) is handled by namespace lifetime. */ remove_layout1(_metadata); @@ -4276,9 +4276,8 @@ FIXTURE_TEARDOWN(layout2_overlay) EXPECT_EQ(0, remove_path(lower_fl1)); EXPECT_EQ(0, remove_path(lower_do1_fo2)); EXPECT_EQ(0, remove_path(lower_fo1)); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(LOWER_BASE)); - clear_cap(_metadata, CAP_SYS_ADMIN); + + /* umount(LOWER_BASE)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(LOWER_BASE)); EXPECT_EQ(0, remove_path(upper_do1_fu3)); @@ -4287,14 +4286,11 @@ FIXTURE_TEARDOWN(layout2_overlay) EXPECT_EQ(0, remove_path(upper_do1_fo2)); EXPECT_EQ(0, remove_path(upper_fo1)); EXPECT_EQ(0, remove_path(UPPER_WORK "/work")); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(UPPER_BASE)); - clear_cap(_metadata, CAP_SYS_ADMIN); + + /* umount(UPPER_BASE)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(UPPER_BASE)); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(MERGE_DATA)); - clear_cap(_metadata, CAP_SYS_ADMIN); + /* umount(MERGE_DATA)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(MERGE_DATA)); cleanup_layout(_metadata); @@ -4691,6 +4687,8 @@ FIXTURE_SETUP(layout3_fs) SKIP(return, "this filesystem is not supported (setup)"); } + _metadata->teardown_parent = true; + slash = strrchr(variant->file_path, '/'); ASSERT_NE(slash, NULL); dir_len = (size_t)slash - (size_t)variant->file_path; diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 20294553a5dd..d2cfc9b494a0 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -138,7 +138,7 @@ FIXTURE_SETUP(hmm) self->fd = hmm_open(variant->device_number); if (self->fd < 0 && hmm_is_coherent_type(variant->device_number)) - SKIP(exit(0), "DEVICE_COHERENT not available"); + SKIP(return, "DEVICE_COHERENT not available"); ASSERT_GE(self->fd, 0); } @@ -149,7 +149,7 @@ FIXTURE_SETUP(hmm2) self->fd0 = hmm_open(variant->device_number0); if (self->fd0 < 0 && hmm_is_coherent_type(variant->device_number0)) - SKIP(exit(0), "DEVICE_COHERENT not available"); + SKIP(return, "DEVICE_COHERENT not available"); ASSERT_GE(self->fd0, 0); self->fd1 = hmm_open(variant->device_number1); ASSERT_GE(self->fd1, 0); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 3ec1050e47a2..73895711cdf4 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -789,6 +789,7 @@ fib6_gc_test() set -e EXPIRE=5 + GC_WAIT_TIME=$((EXPIRE * 2 + 2)) # Check expiration of routes every $EXPIRE seconds (GC) $NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE @@ -805,7 +806,7 @@ fib6_gc_test() $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2 + 1)) + sleep $GC_WAIT_TIME $NS_EXEC sysctl -wq net.ipv6.route.flush=1 check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection" @@ -823,7 +824,8 @@ fib6_gc_test() $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2 + 1)) + # Wait for GC + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (with permanent routes)" @@ -840,10 +842,8 @@ fib6_gc_test() $IP -6 route replace 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - check_rt_num_clean 5 $($IP -6 route list |grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with expires)" @@ -863,8 +863,7 @@ fib6_gc_test() check_rt_num_clean 0 $($IP -6 route list |grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - + sleep $GC_WAIT_TIME check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with permanent)" @@ -901,9 +900,7 @@ fib6_gc_test() check_rt_num_clean 1 $($IP -6 route list|grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - - $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (RA message)" diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index cdefc9a5ec34..535865b3d1d6 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -123,6 +123,7 @@ TEST_FILES := devlink_lib.sh \ mirror_gre_topo_lib.sh \ mirror_lib.sh \ mirror_topo_lib.sh \ + router_mpath_nh_lib.sh \ sch_ets_core.sh \ sch_ets_tests.sh \ sch_tbf_core.sh \ diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index 56eb83d1a3bd..1783c10215e5 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -183,42 +183,42 @@ send_src_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_flowlabel() @@ -234,14 +234,14 @@ send_src_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:4::2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:4::2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } custom_hash_test() diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index 4a546509de90..1fc4f0242fc5 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -28,6 +28,8 @@ PING=ping PING6=ping6 # Packet generator. Some distributions use 'mz'. MZ=mausezahn +# mausezahn delay between transmissions in microseconds. +MZ_DELAY=0 # Time to wait after interfaces participating in the test are all UP WAIT_TIME=5 # Whether to pause on failure or not. diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index 0446db9c6f74..9788bd0f6e8b 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -278,42 +278,42 @@ send_src_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_flowlabel() @@ -329,14 +329,14 @@ send_src_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } custom_hash_test() diff --git a/tools/testing/selftests/net/forwarding/gre_inner_v4_multipath.sh b/tools/testing/selftests/net/forwarding/gre_inner_v4_multipath.sh index e4009f658003..efca6114a3ce 100755 --- a/tools/testing/selftests/net/forwarding/gre_inner_v4_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_inner_v4_multipath.sh @@ -267,7 +267,7 @@ multipath4_test() ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A "192.0.3.2-192.0.3.62" -B "192.0.4.2-192.0.4.62" \ - -d 1msec -c 50 -t udp "sp=1024,dp=1024" + -d $MZ_DELAY -c 50 -t udp "sp=1024,dp=1024" sleep 1 local t1_111=$(tc_rule_stats_get $ul32 111 ingress) diff --git a/tools/testing/selftests/net/forwarding/gre_inner_v6_multipath.sh b/tools/testing/selftests/net/forwarding/gre_inner_v6_multipath.sh index e449475c4d3e..a71ad39fc0c3 100755 --- a/tools/testing/selftests/net/forwarding/gre_inner_v6_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_inner_v6_multipath.sh @@ -266,9 +266,9 @@ multipath6_test() local t0_222=$(tc_rule_stats_get $ul32 222 ingress) ip vrf exec v$h1 \ - $MZ $h1 -6 -q -p 64 -A "2001:db8:1::2-2001:db8:1::1e" \ - -B "2001:db8:2::2-2001:db8:2::1e" \ - -d 1msec -c 50 -t udp "sp=1024,dp=1024" + $MZ $h1 -6 -q -p 64 -A "2001:db8:1::2-2001:db8:1::3e" \ + -B "2001:db8:2::2-2001:db8:2::3e" \ + -d $MZ_DELAY -c 50 -t udp "sp=1024,dp=1024" sleep 1 local t1_111=$(tc_rule_stats_get $ul32 111 ingress) diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh index a8d8e8b3dc81..57531c1d884d 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh @@ -220,7 +220,7 @@ multipath4_test() ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" local t1_111=$(tc_rule_stats_get $ul2 111 ingress) local t1_222=$(tc_rule_stats_get $ul2 222 ingress) diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh index d03aa2cab9fd..7d5b2b9cc133 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh @@ -64,7 +64,6 @@ ALL_TESTS=" ping_ipv6 multipath_ipv4 multipath_ipv6 - multipath_ipv6_l4 " NUM_NETIFS=6 @@ -245,7 +244,7 @@ multipath4_test() ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" local t1_111=$(tc_rule_stats_get $ul2 111 ingress) local t1_222=$(tc_rule_stats_get $ul2 222 ingress) @@ -264,34 +263,6 @@ multipath6_test() local weight1=$1; shift local weight2=$1; shift - sysctl_set net.ipv6.fib_multipath_hash_policy 0 - ip nexthop replace id 103 group 101,$weight1/102,$weight2 - - local t0_111=$(tc_rule_stats_get $ul2 111 ingress) - local t0_222=$(tc_rule_stats_get $ul2 222 ingress) - - # Generate 16384 echo requests, each with a random flow label. - for ((i=0; i < 16384; ++i)); do - ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null - done - - local t1_111=$(tc_rule_stats_get $ul2 111 ingress) - local t1_222=$(tc_rule_stats_get $ul2 222 ingress) - - local d111=$((t1_111 - t0_111)) - local d222=$((t1_222 - t0_222)) - multipath_eval "$what" $weight1 $weight2 $d111 $d222 - - ip nexthop replace id 103 group 101/102 - sysctl_restore net.ipv6.fib_multipath_hash_policy -} - -multipath6_l4_test() -{ - local what=$1; shift - local weight1=$1; shift - local weight2=$1; shift - sysctl_set net.ipv6.fib_multipath_hash_policy 1 ip nexthop replace id 103 group 101,$weight1/102,$weight2 @@ -300,7 +271,7 @@ multipath6_l4_test() ip vrf exec v$h1 \ $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" local t1_111=$(tc_rule_stats_get $ul2 111 ingress) local t1_222=$(tc_rule_stats_get $ul2 222 ingress) @@ -339,14 +310,6 @@ multipath_ipv6() multipath6_test "Weighted MP 11:45" 11 45 } -multipath_ipv6_l4() -{ - log_info "Running IPv6 L4 hash multipath tests" - multipath6_l4_test "ECMP" 1 1 - multipath6_l4_test "Weighted MP 2:1" 2 1 - multipath6_l4_test "Weighted MP 11:45" 11 45 -} - trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh index 088b65e64d66..370f9925302d 100755 --- a/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh_res.sh @@ -64,7 +64,6 @@ ALL_TESTS=" ping_ipv6 multipath_ipv4 multipath_ipv6 - multipath_ipv6_l4 " NUM_NETIFS=6 @@ -248,7 +247,7 @@ multipath4_test() ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" local t1_111=$(tc_rule_stats_get $ul2 111 ingress) local t1_222=$(tc_rule_stats_get $ul2 222 ingress) @@ -267,35 +266,6 @@ multipath6_test() local weight1=$1; shift local weight2=$1; shift - sysctl_set net.ipv6.fib_multipath_hash_policy 0 - ip nexthop replace id 103 group 101,$weight1/102,$weight2 \ - type resilient - - local t0_111=$(tc_rule_stats_get $ul2 111 ingress) - local t0_222=$(tc_rule_stats_get $ul2 222 ingress) - - # Generate 16384 echo requests, each with a random flow label. - for ((i=0; i < 16384; ++i)); do - ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null - done - - local t1_111=$(tc_rule_stats_get $ul2 111 ingress) - local t1_222=$(tc_rule_stats_get $ul2 222 ingress) - - local d111=$((t1_111 - t0_111)) - local d222=$((t1_222 - t0_222)) - multipath_eval "$what" $weight1 $weight2 $d111 $d222 - - ip nexthop replace id 103 group 101/102 type resilient - sysctl_restore net.ipv6.fib_multipath_hash_policy -} - -multipath6_l4_test() -{ - local what=$1; shift - local weight1=$1; shift - local weight2=$1; shift - sysctl_set net.ipv6.fib_multipath_hash_policy 1 ip nexthop replace id 103 group 101,$weight1/102,$weight2 \ type resilient @@ -305,7 +275,7 @@ multipath6_l4_test() ip vrf exec v$h1 \ $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" local t1_111=$(tc_rule_stats_get $ul2 111 ingress) local t1_222=$(tc_rule_stats_get $ul2 222 ingress) @@ -344,14 +314,6 @@ multipath_ipv6() multipath6_test "Weighted MP 11:45" 11 45 } -multipath_ipv6_l4() -{ - log_info "Running IPv6 L4 hash multipath tests" - multipath6_l4_test "ECMP" 1 1 - multipath6_l4_test "Weighted MP 2:1" 2 1 - multipath6_l4_test "Weighted MP 11:45" 11 45 -} - trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index d40183b4eccc..2ab9eaaa5532 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -280,42 +280,42 @@ send_src_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_src_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp4() { ip vrf exec v$h1 $MZ $h1 -q -p 64 \ -A 198.51.100.2 -B 203.0.113.2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } send_src_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_dst_ipv6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ - -d 1msec -c 50 -t udp "sp=20000,dp=30000" + -d $MZ_DELAY -c 50 -t udp "sp=20000,dp=30000" } send_flowlabel() @@ -331,14 +331,14 @@ send_src_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=0-32768,dp=30000" + -d $MZ_DELAY -t udp "sp=0-32768,dp=30000" } send_dst_udp6() { ip vrf exec v$h1 $MZ -6 $h1 -q -p 64 \ -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=20000,dp=0-32768" + -d $MZ_DELAY -t udp "sp=20000,dp=0-32768" } custom_hash_test() diff --git a/tools/testing/selftests/net/forwarding/ip6gre_inner_v4_multipath.sh b/tools/testing/selftests/net/forwarding/ip6gre_inner_v4_multipath.sh index a257979d3fc5..32d1461f37b7 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_inner_v4_multipath.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_inner_v4_multipath.sh @@ -266,7 +266,7 @@ multipath4_test() ip vrf exec v$h1 \ $MZ $h1 -q -p 64 -A "192.0.3.2-192.0.3.62" -B "192.0.4.2-192.0.4.62" \ - -d 1msec -c 50 -t udp "sp=1024,dp=1024" + -d $MZ_DELAY -c 50 -t udp "sp=1024,dp=1024" sleep 1 local t1_111=$(tc_rule_stats_get $ul32 111 ingress) diff --git a/tools/testing/selftests/net/forwarding/ip6gre_inner_v6_multipath.sh b/tools/testing/selftests/net/forwarding/ip6gre_inner_v6_multipath.sh index d208f5243ade..e1a4b50505f5 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_inner_v6_multipath.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_inner_v6_multipath.sh @@ -265,9 +265,9 @@ multipath6_test() local t0_222=$(tc_rule_stats_get $ul32 222 ingress) ip vrf exec v$h1 \ - $MZ $h1 -6 -q -p 64 -A "2001:db8:1::2-2001:db8:1::1e" \ - -B "2001:db8:2::2-2001:db8:2::1e" \ - -d 1msec -c 50 -t udp "sp=1024,dp=1024" + $MZ $h1 -6 -q -p 64 -A "2001:db8:1::2-2001:db8:1::3e" \ + -B "2001:db8:2::2-2001:db8:2::3e" \ + -d $MZ_DELAY -c 50 -t udp "sp=1024,dp=1024" sleep 1 local t1_111=$(tc_rule_stats_get $ul32 111 ingress) diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh index 58a3597037b1..24f4ab328bd2 100644 --- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -356,7 +356,7 @@ test_traffic_ip4ip6() flower $TC_FLAG dst_ip 203.0.113.1 action pass $MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \ - -B 203.0.113.1 -t ip -q -d 1msec + -B 203.0.113.1 -t ip -q -d $MZ_DELAY # Check ports after encap and after decap. tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 @@ -389,7 +389,7 @@ test_traffic_ip6ip6() flower $TC_FLAG dst_ip 2001:db8:2::1 action pass $MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \ - -B 2001:db8:2::1 -t ip -q -d 1msec + -B 2001:db8:2::1 -t ip -q -d $MZ_DELAY # Check ports after encap and after decap. tc_check_at_least_x_packets "dev $ul1 egress" 101 1000 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index db3688f52888..e579c2e0c462 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -8,6 +8,7 @@ PING=${PING:=ping} PING6=${PING6:=ping6} MZ=${MZ:=mausezahn} +MZ_DELAY=${MZ_DELAY:=0} ARPING=${ARPING:=arping} TEAMD=${TEAMD:=teamd} WAIT_TIME=${WAIT_TIME:=5} @@ -899,6 +900,33 @@ hw_stats_get() jq ".[0].stats64.$dir.$stat" } +__nh_stats_get() +{ + local key=$1; shift + local group_id=$1; shift + local member_id=$1; shift + + ip -j -s -s nexthop show id $group_id | + jq --argjson member_id "$member_id" --arg key "$key" \ + '.[].group_stats[] | select(.id == $member_id) | .[$key]' +} + +nh_stats_get() +{ + local group_id=$1; shift + local member_id=$1; shift + + __nh_stats_get packets "$group_id" "$member_id" +} + +nh_stats_get_hw() +{ + local group_id=$1; shift + local member_id=$1; shift + + __nh_stats_get packets_hw "$group_id" "$member_id" +} + humanize() { local speed=$1; shift @@ -2009,3 +2037,10 @@ bail_on_lldpad() fi fi } + +absval() +{ + local v=$1; shift + + echo $((v > 0 ? v : -v)) +} diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index a0d612e04990..3f0f5dc95542 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -7,9 +7,12 @@ ALL_TESTS=" multipath_test ping_ipv4_blackhole ping_ipv6_blackhole + nh_stats_test_v4 + nh_stats_test_v6 " NUM_NETIFS=8 source lib.sh +source router_mpath_nh_lib.sh h1_create() { @@ -204,7 +207,7 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -218,7 +221,7 @@ multipath4_test() sysctl_restore net.ipv4.fib_multipath_hash_policy } -multipath6_l4_test() +multipath6_test() { local desc="$1" local weight_rp12=$2 @@ -237,7 +240,7 @@ multipath6_l4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -251,34 +254,6 @@ multipath6_l4_test() sysctl_restore net.ipv6.fib_multipath_hash_policy } -multipath6_test() -{ - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 - local t0_rp12 t0_rp13 t1_rp12 t1_rp13 - local packets_rp12 packets_rp13 - - ip nexthop replace id 106 group 104,$weight_rp12/105,$weight_rp13 - - t0_rp12=$(link_stats_tx_packets_get $rp12) - t0_rp13=$(link_stats_tx_packets_get $rp13) - - # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec vrf-h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done - - t1_rp12=$(link_stats_tx_packets_get $rp12) - t1_rp13=$(link_stats_tx_packets_get $rp13) - - let "packets_rp12 = $t1_rp12 - $t0_rp12" - let "packets_rp13 = $t1_rp13 - $t0_rp13" - multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13 - - ip nexthop replace id 106 group 104/105 -} - multipath_test() { log_info "Running IPv4 multipath tests" @@ -301,11 +276,6 @@ multipath_test() multipath6_test "ECMP" 1 1 multipath6_test "Weighted MP 2:1" 2 1 multipath6_test "Weighted MP 11:45" 11 45 - - log_info "Running IPv6 L4 hash multipath tests" - multipath6_l4_test "ECMP" 1 1 - multipath6_l4_test "Weighted MP 2:1" 2 1 - multipath6_l4_test "Weighted MP 11:45" 11 45 } ping_ipv4_blackhole() @@ -358,6 +328,16 @@ ping_ipv6_blackhole() ip -6 nexthop del id 1001 } +nh_stats_test_v4() +{ + __nh_stats_test_v4 mpath +} + +nh_stats_test_v6() +{ + __nh_stats_test_v6 mpath +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh new file mode 100644 index 000000000000..7e7d62161c34 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: GPL-2.0 + +nh_stats_do_test() +{ + local what=$1; shift + local nh1_id=$1; shift + local nh2_id=$1; shift + local group_id=$1; shift + local stats_get=$1; shift + local mz="$@" + + local dp + + RET=0 + + sleep 2 + for ((dp=0; dp < 60000; dp += 10000)); do + local dd + local t0_rp12=$(link_stats_tx_packets_get $rp12) + local t0_rp13=$(link_stats_tx_packets_get $rp13) + local t0_nh1=$($stats_get $group_id $nh1_id) + local t0_nh2=$($stats_get $group_id $nh2_id) + + ip vrf exec vrf-h1 \ + $mz -q -p 64 -d 0 -t udp \ + "sp=1024,dp=$((dp))-$((dp + 10000))" + sleep 2 + + local t1_rp12=$(link_stats_tx_packets_get $rp12) + local t1_rp13=$(link_stats_tx_packets_get $rp13) + local t1_nh1=$($stats_get $group_id $nh1_id) + local t1_nh2=$($stats_get $group_id $nh2_id) + + local d_rp12=$((t1_rp12 - t0_rp12)) + local d_rp13=$((t1_rp13 - t0_rp13)) + local d_nh1=$((t1_nh1 - t0_nh1)) + local d_nh2=$((t1_nh2 - t0_nh2)) + + dd=$(absval $((d_rp12 - d_nh1))) + ((dd < 10)) + check_err $? "Discrepancy between link and $stats_get: d_rp12=$d_rp12 d_nh1=$d_nh1" + + dd=$(absval $((d_rp13 - d_nh2))) + ((dd < 10)) + check_err $? "Discrepancy between link and $stats_get: d_rp13=$d_rp13 d_nh2=$d_nh2" + done + + log_test "NH stats test $what" +} + +nh_stats_test_dispatch_swhw() +{ + local what=$1; shift + local nh1_id=$1; shift + local nh2_id=$1; shift + local group_id=$1; shift + local mz="$@" + + local used + + nh_stats_do_test "$what" "$nh1_id" "$nh2_id" "$group_id" \ + nh_stats_get "${mz[@]}" + + used=$(ip -s -j -d nexthop show id $group_id | + jq '.[].hw_stats.used') + kind=$(ip -j -d link show dev $rp11 | + jq -r '.[].linkinfo.info_kind') + if [[ $used == true ]]; then + nh_stats_do_test "HW $what" "$nh1_id" "$nh2_id" "$group_id" \ + nh_stats_get_hw "${mz[@]}" + elif [[ $kind == veth ]]; then + log_test_skip "HW stats not offloaded on veth topology" + fi +} + +nh_stats_test_dispatch() +{ + local nhgtype=$1; shift + local what=$1; shift + local nh1_id=$1; shift + local nh2_id=$1; shift + local group_id=$1; shift + local mz="$@" + + local enabled + local kind + + if ! ip nexthop help 2>&1 | grep -q hw_stats; then + log_test_skip "NH stats test: ip doesn't support HW stats" + return + fi + + ip nexthop replace id $group_id group $nh1_id/$nh2_id \ + hw_stats on type $nhgtype + enabled=$(ip -s -j -d nexthop show id $group_id | + jq '.[].hw_stats.enabled') + if [[ $enabled == true ]]; then + nh_stats_test_dispatch_swhw "$what" "$nh1_id" "$nh2_id" \ + "$group_id" "${mz[@]}" + elif [[ $enabled == false ]]; then + check_err 1 "HW stats still disabled after enabling" + log_test "NH stats test" + else + log_test_skip "NH stats test: ip doesn't report hw_stats info" + fi + + ip nexthop replace id $group_id group $nh1_id/$nh2_id \ + hw_stats off type $nhgtype +} + +__nh_stats_test_v4() +{ + local nhgtype=$1; shift + + sysctl_set net.ipv4.fib_multipath_hash_policy 1 + nh_stats_test_dispatch $nhgtype "IPv4" 101 102 103 \ + $MZ $h1 -A 192.0.2.2 -B 198.51.100.2 + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +__nh_stats_test_v6() +{ + local nhgtype=$1; shift + + sysctl_set net.ipv6.fib_multipath_hash_policy 1 + nh_stats_test_dispatch $nhgtype "IPv6" 104 105 106 \ + $MZ -6 $h1 -A 2001:db8:1::2 -B 2001:db8:2::2 + sysctl_restore net.ipv6.fib_multipath_hash_policy +} diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index cb08ffe2356a..4b483d24ad00 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -5,9 +5,12 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 multipath_test + nh_stats_test_v4 + nh_stats_test_v6 " NUM_NETIFS=8 source lib.sh +source router_mpath_nh_lib.sh h1_create() { @@ -205,7 +208,7 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -235,7 +238,7 @@ multipath6_l4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -333,6 +336,16 @@ multipath_test() ip nexthop replace id 106 group 104,1/105,1 type resilient } +nh_stats_test_v4() +{ + __nh_stats_test_v4 resilient +} + +nh_stats_test_v6() +{ + __nh_stats_test_v6 resilient +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 464821c587a5..e2be354167a1 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -179,7 +179,7 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -195,7 +195,7 @@ multipath4_test() sysctl_restore net.ipv4.fib_multipath_hash_policy } -multipath6_l4_test() +multipath6_test() { local desc="$1" local weight_rp12=$2 @@ -216,7 +216,7 @@ multipath6_l4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d 1msec -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -232,38 +232,6 @@ multipath6_l4_test() sysctl_restore net.ipv6.fib_multipath_hash_policy } -multipath6_test() -{ - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 - local t0_rp12 t0_rp13 t1_rp12 t1_rp13 - local packets_rp12 packets_rp13 - - ip route replace 2001:db8:2::/64 vrf vrf-r1 \ - nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ - nexthop via fe80:3::23 dev $rp13 weight $weight_rp13 - - t0_rp12=$(link_stats_tx_packets_get $rp12) - t0_rp13=$(link_stats_tx_packets_get $rp13) - - # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec vrf-h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null - done - - t1_rp12=$(link_stats_tx_packets_get $rp12) - t1_rp13=$(link_stats_tx_packets_get $rp13) - - let "packets_rp12 = $t1_rp12 - $t0_rp12" - let "packets_rp13 = $t1_rp13 - $t0_rp13" - multipath_eval "$desc" $weight_rp12 $weight_rp13 $packets_rp12 $packets_rp13 - - ip route replace 2001:db8:2::/64 vrf vrf-r1 \ - nexthop via fe80:2::22 dev $rp12 \ - nexthop via fe80:3::23 dev $rp13 -} - multipath_test() { log_info "Running IPv4 multipath tests" @@ -275,11 +243,6 @@ multipath_test() multipath6_test "ECMP" 1 1 multipath6_test "Weighted MP 2:1" 2 1 multipath6_test "Weighted MP 11:45" 11 45 - - log_info "Running IPv6 L4 hash multipath tests" - multipath6_l4_test "ECMP" 1 1 - multipath6_l4_test "Weighted MP 2:1" 2 1 - multipath6_l4_test "Weighted MP 11:45" 11 45 } setup_prepare() diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 0a51eef21b9e..5103f64a71d6 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -140,7 +140,7 @@ police_common_test() sleep 10 local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) - local er=$((80 * 1000 * 1000)) + local er=$((10 * 1000 * 1000)) local nr=$(rate $t0 $t1 10) local nr_pct=$((100 * (nr - er) / er)) ((-10 <= nr_pct && nr_pct <= 10)) @@ -157,7 +157,7 @@ police_rx_test() # Rule to police traffic destined to $h2 on ingress of $rp1 tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ - action police rate 80mbit burst 16k conform-exceed drop/ok + action police rate 10mbit burst 16k conform-exceed drop/ok police_common_test "police on rx" @@ -169,7 +169,7 @@ police_tx_test() # Rule to police traffic destined to $h2 on egress of $rp2 tc filter add dev $rp2 egress protocol ip pref 1 handle 101 flower \ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ - action police rate 80mbit burst 16k conform-exceed drop/ok + action police rate 10mbit burst 16k conform-exceed drop/ok police_common_test "police on tx" @@ -190,7 +190,7 @@ police_shared_common_test() sleep 10 local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) - local er=$((80 * 1000 * 1000)) + local er=$((10 * 1000 * 1000)) local nr=$(rate $t0 $t1 10) local nr_pct=$((100 * (nr - er) / er)) ((-10 <= nr_pct && nr_pct <= 10)) @@ -211,7 +211,7 @@ police_shared_test() # Rule to police traffic destined to $h2 on ingress of $rp1 tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ - action police rate 80mbit burst 16k conform-exceed drop/ok \ + action police rate 10mbit burst 16k conform-exceed drop/ok \ index 10 # Rule to police a different flow destined to $h2 on egress of $rp2 @@ -250,7 +250,7 @@ police_mirror_common_test() # Rule to police traffic destined to $h2 and mirror to $h3 tc filter add dev $pol_if $dir protocol ip pref 1 handle 101 flower \ dst_ip 198.51.100.1 ip_proto udp dst_port 54321 \ - action police rate 80mbit burst 16k conform-exceed drop/pipe \ + action police rate 10mbit burst 16k conform-exceed drop/pipe \ action mirred egress mirror dev $rp3 mausezahn $h1 -a own -b $(mac_get $rp1) -A 192.0.2.1 -B 198.51.100.1 \ @@ -260,7 +260,7 @@ police_mirror_common_test() sleep 10 local t1=$(tc_rule_stats_get $h2 1 ingress .bytes) - local er=$((80 * 1000 * 1000)) + local er=$((10 * 1000 * 1000)) local nr=$(rate $t0 $t1 10) local nr_pct=$((100 * (nr - er) / er)) ((-10 <= nr_pct && nr_pct <= 10)) @@ -270,7 +270,7 @@ police_mirror_common_test() sleep 10 local t1=$(tc_rule_stats_get $h3 1 ingress .bytes) - local er=$((80 * 1000 * 1000)) + local er=$((10 * 1000 * 1000)) local nr=$(rate $t0 $t1 10) local nr_pct=$((100 * (nr - er) / er)) ((-10 <= nr_pct && nr_pct <= 10)) diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index eb307ca37bfa..6f0a2e452ba1 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -495,7 +495,7 @@ vxlan_ping_test() local delta=$((t1 - t0)) # Tolerate a couple stray extra packets. - ((expect <= delta && delta <= expect + 2)) + ((expect <= delta && delta <= expect + 5)) check_err $? "$capture_dev: Expected to capture $expect packets, got $delta." } @@ -532,7 +532,7 @@ __test_ecn_encap() RET=0 tc filter add dev v1 egress pref 77 prot ip \ - flower ip_tos $tos action pass + flower ip_tos $tos ip_proto udp dst_port $VXPORT action pass sleep 1 vxlan_ping_test $h1 192.0.2.3 "-Q $q" v1 egress 77 10 tc filter del dev v1 egress pref 77 prot ip diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh index ac97f07e5ce8..a0bb4524e1e9 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d_ipv6.sh @@ -616,7 +616,7 @@ vxlan_ping_test() local delta=$((t1 - t0)) # Tolerate a couple stray extra packets. - ((expect <= delta && delta <= expect + 2)) + ((expect <= delta && delta <= expect + 5)) check_err $? "$capture_dev: Expected to capture $expect packets, got $delta." } @@ -653,7 +653,7 @@ __test_ecn_encap() RET=0 tc filter add dev v1 egress pref 77 protocol ipv6 \ - flower ip_tos $tos action pass + flower ip_tos $tos ip_proto udp dst_port $VXPORT action pass sleep 1 vxlan_ping_test $h1 2001:db8:1::3 "-Q $q" v1 egress 77 10 tc filter del dev v1 egress pref 77 protocol ipv6 diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh index a596bbf3ed6a..fb9a34cb50c6 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh @@ -750,7 +750,7 @@ __test_learning() expects[0]=0; expects[$idx1]=10; expects[$idx2]=0 vxlan_flood_test $mac $dst $vid "${expects[@]}" - sleep 20 + sleep 60 bridge fdb show brport $vx | grep $mac | grep -q self check_fail $? @@ -796,11 +796,11 @@ test_learning() local dst=192.0.2.100 local vid=10 - # Enable learning on the VxLAN devices and set ageing time to 10 seconds - ip link set dev br1 type bridge ageing_time 1000 - ip link set dev vx10 type vxlan ageing 10 + # Enable learning on the VxLAN devices and set ageing time to 30 seconds + ip link set dev br1 type bridge ageing_time 3000 + ip link set dev vx10 type vxlan ageing 30 ip link set dev vx10 type vxlan learning - ip link set dev vx20 type vxlan ageing 10 + ip link set dev vx20 type vxlan ageing 30 ip link set dev vx20 type vxlan learning reapply_config diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index e87cf76b3e4a..bc97ab33a00e 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,13 +1,14 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns="ns1-$rndh" -ksft_skip=4 -test_cnt=1 +ns="" timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) ret=0 @@ -26,25 +27,17 @@ flush_pids() done } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null - ip netns del $ns + mptcp_lib_ns_exit "${ns}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi -ss -h | grep -q MPTCP -if [ $? -ne 0 ];then - echo "SKIP: ss tool does not support MPTCP" - exit $ksft_skip -fi +mptcp_lib_check_tools ip ss get_msk_inuse() { @@ -61,21 +54,20 @@ __chk_nr() nr=$(eval $command) - printf "%-50s" "$msg" + mptcp_lib_print_title "$msg" if [ "$nr" != "$expected" ]; then if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then - echo "[ skip ] Feature probably not supported" + mptcp_lib_pr_skip "Feature probably not supported" mptcp_lib_result_skip "${msg}" else - echo "[ fail ] expected $expected found $nr" + mptcp_lib_pr_fail "expected $expected found $nr" mptcp_lib_result_fail "${msg}" - ret=$test_cnt + ret=${KSFT_FAIL} fi else - echo "[ ok ]" + mptcp_lib_pr_ok mptcp_lib_result_pass "${msg}" fi - test_cnt=$((test_cnt+1)) } __chk_msk_nr() @@ -96,8 +88,8 @@ chk_listener_nr() local expected=$1 local msg="$2" - __chk_nr "ss -inmlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 - __chk_nr "ss -inmlHtON $ns | wc -l" "$expected" "$msg - subflows" + __chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 + __chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows" } wait_msk_nr() @@ -120,20 +112,19 @@ wait_msk_nr() sleep 1 done - printf "%-50s" "$msg" + mptcp_lib_print_title "$msg" if [ $i -ge $timeout ]; then - echo "[ fail ] timeout while expecting $expected max $max last $nr" + mptcp_lib_pr_fail "timeout while expecting $expected max $max last $nr" mptcp_lib_result_fail "${msg} # timeout" - ret=$test_cnt + ret=${KSFT_FAIL} elif [ $nr != $expected ]; then - echo "[ fail ] expected $expected found $nr" + mptcp_lib_pr_fail "expected $expected found $nr" mptcp_lib_result_fail "${msg} # unexpected result" - ret=$test_cnt + ret=${KSFT_FAIL} else - echo "[ ok ]" + mptcp_lib_pr_ok mptcp_lib_result_pass "${msg}" fi - test_cnt=$((test_cnt+1)) } chk_msk_fallback_nr() @@ -186,7 +177,7 @@ chk_msk_inuse() expected=$((expected + listen_nr)) for _ in $(seq 10); do - if [ $(get_msk_inuse) -eq $expected ];then + if [ "$(get_msk_inuse)" -eq $expected ]; then break fi sleep 0.1 @@ -224,8 +215,7 @@ wait_connected() } trap cleanup EXIT -ip netns add $ns -ip -n $ns link set dev lo up +mptcp_lib_ns_init ns echo "a" | \ timeout ${timeout_test} \ @@ -273,7 +263,7 @@ chk_msk_inuse 0 "1->0" chk_msk_cestab 0 "1->0" NR_CLIENTS=100 -for I in `seq 1 $NR_CLIENTS`; do +for I in $(seq 1 $NR_CLIENTS); do echo "a" | \ timeout ${timeout_test} \ ip netns exec $ns \ @@ -282,7 +272,7 @@ for I in `seq 1 $NR_CLIENTS`; do done mptcp_lib_wait_local_port_listen $ns $((NR_CLIENTS + 10001)) -for I in `seq 1 $NR_CLIENTS`; do +for I in $(seq 1 $NR_CLIENTS); do echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ @@ -304,10 +294,7 @@ for I in $(seq 1 $NR_SERVERS); do ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \ -t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 & done - -for I in $(seq 1 $NR_SERVERS); do - mptcp_lib_wait_local_port_listen $ns $((I + 20001)) -done +mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001)) chk_listener_nr $NR_SERVERS "many listener sockets" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 7898d62fce0b..4c4248554826 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" time_start=$(date +%s) @@ -13,7 +18,6 @@ sout="" cin_disconnect="" cin="" cout="" -ksft_skip=4 capture=false timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) @@ -29,6 +33,7 @@ do_tcp=0 checksum=false filesize=0 connect_per_transfer=1 +port=$((10000 - 1)) if [ $tc_loss -eq 100 ];then tc_loss=1% @@ -60,14 +65,14 @@ while getopts "$optstring" option;do case "$option" in "h") usage $0 - exit 0 + exit ${KSFT_PASS} ;; "d") if [ $OPTARG -ge 0 ];then tc_delay="$OPTARG" else echo "-d requires numeric argument, got \"$OPTARG\"" 1>&2 - exit 1 + exit ${KSFT_FAIL} fi ;; "e") @@ -91,7 +96,7 @@ while getopts "$optstring" option;do sndbuf="$OPTARG" else echo "-S requires numeric argument, got \"$OPTARG\"" 1>&2 - exit 1 + exit ${KSFT_FAIL} fi ;; "R") @@ -99,7 +104,7 @@ while getopts "$optstring" option;do rcvbuf="$OPTARG" else echo "-R requires numeric argument, got \"$OPTARG\"" 1>&2 - exit 1 + exit ${KSFT_FAIL} fi ;; "m") @@ -116,21 +121,20 @@ while getopts "$optstring" option;do ;; "?") usage $0 - exit 1 + exit ${KSFT_FAIL} ;; esac done -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns3="ns3-$rndh" -ns4="ns4-$rndh" +ns1="" +ns2="" +ns3="" +ns4="" -TEST_COUNT=0 TEST_GROUP="" +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f "$cin_disconnect" "$cout_disconnect" @@ -138,21 +142,12 @@ cleanup() rm -f "$sin" "$sout" rm -f "$capout" - local netns - for netns in "$ns1" "$ns2" "$ns3" "$ns4";do - ip netns del $netns - rm -f /tmp/$netns.{nstat,out} - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}" "${ns4}" } mptcp_lib_check_mptcp mptcp_lib_check_kallsyms - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip sin=$(mktemp) sout=$(mktemp) @@ -163,10 +158,7 @@ cin_disconnect="$cin".disconnect cout_disconnect="$cout".disconnect trap cleanup EXIT -for i in "$ns1" "$ns2" "$ns3" "$ns4";do - ip netns add $i || exit $ksft_skip - ip -net $i link set lo up -done +mptcp_lib_ns_init ns1 ns2 ns3 ns4 # "$ns1" ns2 ns3 ns4 # ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3 @@ -225,8 +217,9 @@ set_ethtool_flags() { local dev="$2" local flags="$3" - ip netns exec $ns ethtool -K $dev $flags 2>/dev/null - [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" + if ip netns exec $ns ethtool -K $dev $flags 2>/dev/null; then + mptcp_lib_pr_info "set $ns dev $dev: ethtool -K $flags" + fi } set_random_ethtool_flags() { @@ -254,16 +247,23 @@ else set_ethtool_flags "$ns4" ns4eth3 "$ethtool_args" fi +print_larger_title() { + # here we don't have the time, a bit longer for the alignment + MPTCP_LIB_TEST_FORMAT="%02u %-69s" \ + mptcp_lib_print_title "${@}" +} + check_mptcp_disabled() { - local disabled_ns="ns_disabled-$rndh" - ip netns add ${disabled_ns} || exit $ksft_skip + local disabled_ns + mptcp_lib_ns_init disabled_ns + print_larger_title "New MPTCP socket can be blocked via sysctl" # net.mptcp.enabled should be enabled by default if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then - echo -e "net.mptcp.enabled sysctl is not 1 by default\t\t[ FAIL ]" + mptcp_lib_pr_fail "net.mptcp.enabled sysctl is not 1 by default" mptcp_lib_result_fail "net.mptcp.enabled sysctl is not 1 by default" - ret=1 + ret=${KSFT_FAIL} return 1 fi ip netns exec ${disabled_ns} sysctl -q net.mptcp.enabled=0 @@ -271,16 +271,16 @@ check_mptcp_disabled() local err=0 LC_ALL=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \ grep -q "^socket: Protocol not available$" && err=1 - ip netns delete ${disabled_ns} + mptcp_lib_ns_exit "${disabled_ns}" if [ ${err} -eq 0 ]; then - echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" + mptcp_lib_pr_fail "New MPTCP socket cannot be blocked via sysctl" mptcp_lib_result_fail "New MPTCP socket cannot be blocked via sysctl" - ret=1 + ret=${KSFT_FAIL} return 1 fi - echo -e "New MPTCP socket can be blocked via sysctl\t\t[ OK ]" + mptcp_lib_pr_ok mptcp_lib_result_pass "New MPTCP socket can be blocked via sysctl" return 0 } @@ -301,8 +301,8 @@ do_ping() ip netns exec ${connector_ns} ping ${ping_args} $connect_addr >/dev/null || rc=1 if [ $rc -ne 0 ] ; then - echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 - ret=1 + mptcp_lib_pr_fail "$listener_ns -> $connect_addr connectivity" + ret=${KSFT_FAIL} return 1 fi @@ -320,24 +320,22 @@ do_transfer() local local_addr="$6" local extra_args="$7" - local port - port=$((10000+$TEST_COUNT)) - TEST_COUNT=$((TEST_COUNT+1)) + port=$((port + 1)) if [ "$rcvbuf" -gt 0 ]; then - extra_args="$extra_args -R $rcvbuf" + extra_args+=" -R $rcvbuf" fi if [ "$sndbuf" -gt 0 ]; then - extra_args="$extra_args -S $sndbuf" + extra_args+=" -S $sndbuf" fi if [ -n "$testmode" ]; then - extra_args="$extra_args -m $testmode" + extra_args+=" -m $testmode" fi if [ -n "$extra_args" ] && $options_log; then - echo "INFO: extra options: $extra_args" + mptcp_lib_pr_info "extra options: $extra_args" fi options_log=false @@ -349,10 +347,11 @@ do_transfer() addr_port=$(printf "%s:%d" ${connect_addr} ${port}) local result_msg result_msg="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})" - printf "%s\t" "${result_msg}" + mptcp_lib_print_title "${result_msg}" if $capture; then local capuser + local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else @@ -378,12 +377,18 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l + local stat_ackrx_last_l + local stat_cookietx_last + local stat_cookierx_last + local stat_csum_err_s + local stat_csum_err_c + stat_synrx_last_l=$(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") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -427,7 +432,7 @@ do_transfer() result_msg+=" # time=${duration}ms" printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then - echo "[ FAIL ] client exit code $retc, server $rets" 1>&2 + mptcp_lib_pr_fail "client exit code $retc, server $rets" echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" cat /tmp/${listener_ns}.out @@ -446,11 +451,17 @@ do_transfer() mptcp_lib_check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local extra="" + local stat_synrx_now_l + local stat_ackrx_now_l + local stat_cookietx_now + local stat_cookierx_now + local stat_ooo_now + 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") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -459,75 +470,79 @@ do_transfer() 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+$connect_per_transfer)) + expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) + expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) fi if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then - printf "[ FAIL ] lower MPC SYN rx (%d) than expected (%d)\n" \ - "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 + mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx_now_l})" \ + "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ] && [ ${stat_ooo_now} -eq 0 ]; then if [ ${stat_ooo_now} -eq 0 ]; then - printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ - "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 + mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ + "than expected (${expect_ackrx})" rets=1 else - printf "[ Note ] fallback due to TCP OoO" + extra+=" [ Note ] fallback due to TCP OoO" fi fi if $checksum; then - local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s + local csum_err_c + csum_err_s=$(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 - printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + mptcp_lib_pr_fail "server got ${csum_err_s_nr} data checksum error[s]" rets=1 fi local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) if [ $csum_err_c_nr -gt 0 ]; then - printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + mptcp_lib_pr_fail "client got ${csum_err_c_nr} data checksum error[s]" retc=1 fi fi - if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then - printf "[ OK ]" - mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}" - else - mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" - fi - if [ $cookies -eq 2 ];then if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then - printf " WARN: CookieSent: did not advance" + extra+=" WARN: CookieSent: did not advance" fi if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then - printf " WARN: CookieRecv: did not advance" + extra+=" WARN: CookieRecv: did not advance" fi else if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then - printf " WARN: CookieSent: changed" + extra+=" WARN: CookieSent: changed" fi if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then - printf " WARN: CookieRecv: changed" + extra+=" WARN: CookieRecv: changed" fi fi if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then - printf " WARN: SYNRX: expect %d, got %d (probably retransmissions)" \ - "${expect_synrx}" "${stat_synrx_now_l}" + extra+=" WARN: SYNRX: expect ${expect_synrx}," + extra+=" got ${stat_synrx_now_l} (probably retransmissions)" fi if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then - printf " WARN: ACKRX: expect %d, got %d (probably retransmissions)" \ - "${expect_ackrx}" "${stat_ackrx_now_l}" + extra+=" WARN: ACKRX: expect ${expect_ackrx}," + extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + fi + + if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then + mptcp_lib_pr_ok "${extra:1}" + mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}" + else + if [ -n "${extra}" ]; then + mptcp_lib_print_warn "${extra:1}" + fi + mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}" fi - echo cat "$capout" [ $retc -eq 0 ] && [ $rets -eq 0 ] } @@ -653,12 +668,12 @@ run_test_transparent() # following function has been exported (T). Not great but better than # checking for a specific kernel version. if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then - echo "INFO: ${msg} not supported by the kernel: SKIP" + mptcp_lib_pr_skip "${msg} not supported by the kernel" mptcp_lib_result_skip "${TEST_GROUP}" return fi -ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" + if ! ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { chain divert { @@ -669,8 +684,8 @@ table inet mangle { } } EOF - if [ $? -ne 0 ]; then - echo "SKIP: $msg, could not load nft ruleset" + then + mptcp_lib_pr_skip "$msg, could not load nft ruleset" mptcp_lib_fail_if_expected_feature "nft rules" mptcp_lib_result_skip "${TEST_GROUP}" return @@ -684,28 +699,26 @@ EOF local_addr="0.0.0.0" fi - ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100; then ip netns exec "$listener_ns" nft flush ruleset - echo "SKIP: $msg, ip $r6flag rule failed" + mptcp_lib_pr_skip "$msg, ip $r6flag rule failed" mptcp_lib_fail_if_expected_feature "ip rule" mptcp_lib_result_skip "${TEST_GROUP}" return fi - ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100; then ip netns exec "$listener_ns" nft flush ruleset ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 - echo "SKIP: $msg, ip route add local $local_addr failed" + mptcp_lib_pr_skip "$msg, ip route add local $local_addr failed" mptcp_lib_fail_if_expected_feature "ip route" mptcp_lib_result_skip "${TEST_GROUP}" return fi - echo "INFO: test $msg" + mptcp_lib_pr_info "test $msg" - TEST_COUNT=10000 + port=$((20000 - 1)) local extra_args="-o TRANSPARENT" do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP \ ${connect_addr} ${local_addr} "${extra_args}" @@ -716,12 +729,12 @@ EOF ip -net "$listener_ns" route del local $local_addr/0 dev lo table 100 if [ $lret -ne 0 ]; then - echo "FAIL: $msg, mptcp connection error" 1>&2 + mptcp_lib_pr_fail "$msg, mptcp connection error" ret=$lret return 1 fi - echo "PASS: $msg" + mptcp_lib_pr_info "$msg pass" return 0 } @@ -730,7 +743,7 @@ run_tests_peekmode() local peekmode="$1" TEST_GROUP="peek mode: ${peekmode}" - echo "INFO: with peek mode: ${peekmode}" + mptcp_lib_pr_info "with peek mode: ${peekmode}" run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-P ${peekmode}" run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}" } @@ -740,12 +753,12 @@ run_tests_mptfo() TEST_GROUP="MPTFO" if ! mptcp_lib_kallsyms_has "mptcp_fastopen_"; then - echo "INFO: TFO not supported by the kernel: SKIP" + mptcp_lib_pr_skip "TFO not supported by the kernel" mptcp_lib_result_skip "${TEST_GROUP}" return fi - echo "INFO: with MPTFO start" + mptcp_lib_pr_info "with MPTFO start" ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=2 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=1 @@ -757,7 +770,7 @@ run_tests_mptfo() ip netns exec "$ns1" sysctl -q net.ipv4.tcp_fastopen=0 ip netns exec "$ns2" sysctl -q net.ipv4.tcp_fastopen=0 - echo "INFO: with MPTFO end" + mptcp_lib_pr_info "with MPTFO end" } run_tests_disconnect() @@ -768,7 +781,7 @@ run_tests_disconnect() TEST_GROUP="full disconnect" if ! mptcp_lib_kallsyms_has "mptcp_pm_data_reset$"; then - echo "INFO: Full disconnect not supported: SKIP" + mptcp_lib_pr_skip "Full disconnect not supported" mptcp_lib_result_skip "${TEST_GROUP}" return fi @@ -781,7 +794,7 @@ run_tests_disconnect() cin_disconnect="$old_cin" connect_per_transfer=3 - echo "INFO: disconnect" + mptcp_lib_pr_info "disconnect" run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 "-I 3 -i $old_cin" run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin" @@ -805,10 +818,10 @@ log_if_error() local msg="$1" if [ ${ret} -ne 0 ]; then - echo "FAIL: ${msg}" 1>&2 + mptcp_lib_pr_fail "${msg}" final_ret=${ret} - ret=0 + ret=${KSFT_PASS} return ${final_ret} fi @@ -830,7 +843,7 @@ check_mptcp_disabled stop_if_error "The kernel configuration is not valid for MPTCP" -echo "INFO: validating network environment with pings" +print_larger_title "Validating network environment with pings" for sender in "$ns1" "$ns2" "$ns3" "$ns4";do do_ping "$ns1" $sender 10.0.1.1 do_ping "$ns1" $sender dead:beef:1::1 @@ -852,12 +865,13 @@ done mptcp_lib_result_code "${ret}" "ping tests" stop_if_error "Could not even run ping tests" +mptcp_lib_pr_ok [ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms -echo -n "INFO: Using loss of $tc_loss " -test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " +tc_info="loss of $tc_loss " +test "$tc_delay" -gt 0 && tc_info+="delay $tc_delay ms " -reorder_delay=$(($tc_delay / 4)) +reorder_delay=$((tc_delay / 4)) if [ -z "${tc_reorder}" ]; then reorder1=$((RANDOM%10)) @@ -866,17 +880,17 @@ if [ -z "${tc_reorder}" ]; then if [ $reorder_delay -gt 0 ] && [ $reorder1 -lt 100 ] && [ $reorder2 -gt 0 ]; then tc_reorder="reorder ${reorder1}% ${reorder2}%" - echo -n "$tc_reorder with delay ${reorder_delay}ms " + tc_info+="$tc_reorder with delay ${reorder_delay}ms " fi elif [ "$tc_reorder" = "0" ];then tc_reorder="" elif [ "$reorder_delay" -gt 0 ];then # reordering requires some delay tc_reorder="reorder $tc_reorder" - echo -n "$tc_reorder with delay ${reorder_delay}ms " + tc_info+="$tc_reorder with delay ${reorder_delay}ms " fi -echo "on ns3eth4" +mptcp_lib_pr_info "Using ${tc_info}on ns3eth4" tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 1267d5708e13..5e9211e89825 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -21,10 +21,10 @@ cinfail="" cinsent="" tmpfile="" cout="" +err="" capout="" ns1="" ns2="" -ksft_skip=4 iptables="iptables" ip6tables="ip6tables" timeout_poll=30 @@ -47,7 +47,7 @@ declare -A all_tests declare -a only_tests_ids declare -a only_tests_names declare -A failed_tests -TEST_COUNT=0 +MPTCP_LIB_TEST_FORMAT="%03u %s\n" TEST_NAME="" nr_blank=6 @@ -85,21 +85,11 @@ init_partial() { capout=$(mktemp) - local sec rndh - sec=$(date +%s) - rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) - - ns1="ns1-$rndh" - ns2="ns2-$rndh" + mptcp_lib_ns_init ns1 ns2 local netns for netns in "$ns1" "$ns2"; do - ip netns add $netns || exit $ksft_skip - ip -net $netns link set lo up - ip netns exec $netns sysctl -q net.mptcp.enabled=1 ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true - ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if $checksum; then ip netns exec $netns sysctl -q net.mptcp.checksum_enabled=1 fi @@ -144,51 +134,22 @@ cleanup_partial() { rm -f "$capout" - local netns - for netns in "$ns1" "$ns2"; do - ip netns del $netns - rm -f /tmp/$netns.{nstat,out} - done -} - -check_tools() -{ - mptcp_lib_check_mptcp - mptcp_lib_check_kallsyms - - if ! ip -Version &> /dev/null; then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip - fi - - if ! ss -h | grep -q MPTCP; then - echo "SKIP: ss tool does not support MPTCP" - exit $ksft_skip - fi - - # Use the legacy version if available to support old kernel versions - if iptables-legacy -V &> /dev/null; then - iptables="iptables-legacy" - ip6tables="ip6tables-legacy" - elif ! iptables -V &> /dev/null; then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip - elif ! ip6tables -V &> /dev/null; then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip - fi + mptcp_lib_ns_exit "${ns1}" "${ns2}" } init() { init=1 - check_tools + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + mptcp_lib_check_tools ip ss "${iptables}" "${ip6tables}" sin=$(mktemp) sout=$(mktemp) cin=$(mktemp) cinsent=$(mktemp) cout=$(mktemp) + err=$(mktemp) evts_ns1=$(mktemp) evts_ns2=$(mktemp) @@ -204,14 +165,10 @@ cleanup() rm -f "$sin" "$sout" "$cinsent" "$cinfail" rm -f "$tmpfile" rm -rf $evts_ns1 $evts_ns2 + rm -f "$err" cleanup_partial } -print_title() -{ - printf "%03u %s\n" "${TEST_COUNT}" "${TEST_NAME}" -} - print_check() { printf "%-${nr_blank}s%-36s" " " "${*}" @@ -227,17 +184,17 @@ print_info() print_ok() { - mptcp_lib_print_ok "[ ok ]${1:+ ${*}}" + mptcp_lib_pr_ok "${@}" } print_fail() { - mptcp_lib_print_err "[fail]${1:+ ${*}}" + mptcp_lib_pr_fail "${@}" } print_skip() { - mptcp_lib_print_warn "[skip]${1:+ ${*}}" + mptcp_lib_pr_skip "${@}" } # [ $1: fail msg ] @@ -270,7 +227,7 @@ skip_test() local i for i in "${only_tests_ids[@]}"; do - if [ "${TEST_COUNT}" -eq "${i}" ]; then + if [ "$((MPTCP_LIB_TEST_COUNTER+1))" -eq "${i}" ]; then return 1 fi done @@ -305,14 +262,13 @@ reset() TEST_NAME="${1}" - TEST_COUNT=$((TEST_COUNT+1)) - if skip_test; then + MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1)) last_test_ignored=1 return 1 fi - print_title + mptcp_lib_print_title "${TEST_NAME}" if [ "${init}" != "1" ]; then init @@ -435,15 +391,15 @@ setup_fail_rules() -p tcp \ -m length --length 150:9999 \ -m statistic --mode nth --packet 1 --every 99999 \ - -j MARK --set-mark 42 || return ${ksft_skip} + -j MARK --set-mark 42 || return ${KSFT_SKIP} - tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${ksft_skip} + tc -n $ns2 qdisc add dev ns2eth$i clsact || return ${KSFT_SKIP} tc -n $ns2 filter add dev ns2eth$i egress \ protocol ip prio 1000 \ handle 42 fw \ action pedit munge offset 148 u8 invert \ pipe csum tcp \ - index 100 || return ${ksft_skip} + index 100 || return ${KSFT_SKIP} } reset_with_fail() @@ -457,7 +413,7 @@ reset_with_fail() local rc=0 setup_fail_rules "${@}" || rc=$? - if [ ${rc} -eq ${ksft_skip} ]; then + if [ ${rc} -eq ${KSFT_SKIP} ]; then mark_as_skipped "unable to set the 'fail' rules" return 1 fi @@ -467,12 +423,8 @@ reset_with_events() { reset "${1}" || return 1 - :> "$evts_ns1" - :> "$evts_ns2" - ip netns exec $ns1 ./pm_nl_ctl events >> "$evts_ns1" 2>&1 & - evts_ns1_pid=$! - ip netns exec $ns2 ./pm_nl_ctl events >> "$evts_ns2" 2>&1 & - evts_ns2_pid=$! + mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid + mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid } reset_with_tcp_filter() @@ -497,13 +449,15 @@ reset_with_tcp_filter() # $1: err msg fail_test() { - ret=1 + ret=${KSFT_FAIL} - print_fail "${@}" + if [ ${#} -gt 0 ]; then + print_fail "${@}" + fi # just in case a test is marked twice as failed if [ ${last_test_failed} -eq 0 ]; then - failed_tests[${TEST_COUNT}]="${TEST_NAME}" + failed_tests[${MPTCP_LIB_TEST_COUNTER}]="${TEST_NAME}" dump_stats last_test_failed=1 fi @@ -645,7 +599,9 @@ wait_mpj() kill_events_pids() { mptcp_lib_kill_wait $evts_ns1_pid + evts_ns1_pid=0 mptcp_lib_kill_wait $evts_ns2_pid + evts_ns2_pid=0 } pm_nl_set_limits() @@ -799,18 +755,18 @@ pm_nl_check_endpoint() line="${line% }" # the dump order is: address id flags port dev [ -n "$addr" ] && expected_line="$addr" - expected_line="$expected_line $id" - [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" - [ -n "$dev" ] && expected_line="$expected_line $dev" - [ -n "$port" ] && expected_line="$expected_line $port" + expected_line+=" $id" + [ -n "$_flags" ] && expected_line+=" ${_flags//","/" "}" + [ -n "$dev" ] && expected_line+=" $dev" + [ -n "$port" ] && expected_line+=" $port" else line=$(ip netns exec $ns ./pm_nl_ctl get $_id) # the dump order is: id flags dev address port expected_line="$id" - [ -n "$flags" ] && expected_line="$expected_line $flags" - [ -n "$dev" ] && expected_line="$expected_line $dev" - [ -n "$addr" ] && expected_line="$expected_line $addr" - [ -n "$_port" ] && expected_line="$expected_line $_port" + [ -n "$flags" ] && expected_line+=" $flags" + [ -n "$dev" ] && expected_line+=" $dev" + [ -n "$addr" ] && expected_line+=" $addr" + [ -n "$_port" ] && expected_line+=" $_port" fi if [ "$line" = "$expected_line" ]; then print_ok @@ -1012,7 +968,7 @@ do_transfer() local srv_proto="$4" local connect_addr="$5" - local port=$((10000 + TEST_COUNT - 1)) + local port=$((10000 + MPTCP_LIB_TEST_COUNTER - 1)) local cappid local FAILING_LINKS=${FAILING_LINKS:-""} local fastclose=${fastclose:-""} @@ -1030,9 +986,9 @@ do_transfer() capuser="-Z $SUDO_USER" fi - capfile=$(printf "mp_join-%02u-%s.pcap" "$TEST_COUNT" "${listener_ns}") + capfile=$(printf "mp_join-%02u-%s.pcap" "$MPTCP_LIB_TEST_COUNTER" "${listener_ns}") - echo "Capturing traffic for test $TEST_COUNT into $capfile" + echo "Capturing traffic for test $MPTCP_LIB_TEST_COUNTER into $capfile" ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 & cappid=$! @@ -1261,7 +1217,7 @@ chk_csum_nr() print_check "sum" count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns1" ]; then - extra_msg="$extra_msg ns1=$count" + extra_msg+=" ns1=$count" fi if [ -z "$count" ]; then print_skip @@ -1274,7 +1230,7 @@ chk_csum_nr() print_check "csum" count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr") if [ "$count" != "$csum_ns2" ]; then - extra_msg="$extra_msg ns2=$count" + extra_msg+=" ns2=$count" fi if [ -z "$count" ]; then print_skip @@ -1318,7 +1274,7 @@ chk_fail_nr() print_check "ftx" count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx") if [ "$count" != "$fail_tx" ]; then - extra_msg="$extra_msg,tx=$count" + extra_msg+=",tx=$count" fi if [ -z "$count" ]; then print_skip @@ -1332,7 +1288,7 @@ chk_fail_nr() print_check "failrx" count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx") if [ "$count" != "$fail_rx" ]; then - extra_msg="$extra_msg,rx=$count" + extra_msg+=",rx=$count" fi if [ -z "$count" ]; then print_skip @@ -1367,7 +1323,7 @@ chk_fclose_nr() if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_tx" ]; then - extra_msg="$extra_msg,tx=$count" + extra_msg+=",tx=$count" fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx" else print_ok @@ -1378,7 +1334,7 @@ chk_fclose_nr() if [ -z "$count" ]; then print_skip elif [ "$count" != "$fclose_rx" ]; then - extra_msg="$extra_msg,rx=$count" + extra_msg+=",rx=$count" fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx" else print_ok @@ -1747,7 +1703,7 @@ chk_rm_nr() count=$((count + cnt)) if [ "$count" != "$rm_subflow_nr" ]; then suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]" - extra_msg="$extra_msg simult" + extra_msg+=" simult" fi if [ $count -ge "$rm_subflow_nr" ] && \ [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then @@ -2828,29 +2784,16 @@ backup_tests() fi } -SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED -LISTENER_CREATED=15 #MPTCP_EVENT_LISTENER_CREATED -LISTENER_CLOSED=16 #MPTCP_EVENT_LISTENER_CLOSED - -AF_INET=2 -AF_INET6=10 - verify_listener_events() { - local evt=$1 local e_type=$2 - local e_family=$3 local e_saddr=$4 local e_sport=$5 - local type - local family - local saddr - local sport local name - if [ $e_type = $LISTENER_CREATED ]; then + if [ $e_type = $MPTCP_LIB_EVENT_LISTENER_CREATED ]; then name="LISTENER_CREATED" - elif [ $e_type = $LISTENER_CLOSED ]; then + elif [ $e_type = $MPTCP_LIB_EVENT_LISTENER_CLOSED ]; then name="LISTENER_CLOSED " else name="$e_type" @@ -2863,23 +2806,11 @@ verify_listener_events() return fi - type=$(mptcp_lib_evts_get_info type "$evt" "$e_type") - family=$(mptcp_lib_evts_get_info family "$evt" "$e_type") - sport=$(mptcp_lib_evts_get_info sport "$evt" "$e_type") - if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(mptcp_lib_evts_get_info saddr6 "$evt" "$e_type") - else - saddr=$(mptcp_lib_evts_get_info saddr4 "$evt" "$e_type") - fi - - if [ $type ] && [ $type = $e_type ] && - [ $family ] && [ $family = $e_family ] && - [ $saddr ] && [ $saddr = $e_saddr ] && - [ $sport ] && [ $sport = $e_sport ]; then + if mptcp_lib_verify_listener_events "${@}"; then print_ok return 0 fi - fail_test "$e_type:$type $e_family:$family $e_saddr:$saddr $e_sport:$sport" + fail_test } add_addr_ports_tests() @@ -2917,8 +2848,10 @@ add_addr_ports_tests() chk_add_nr 1 1 1 chk_rm_nr 1 1 invert - verify_listener_events $evts_ns1 $LISTENER_CREATED $AF_INET 10.0.2.1 10100 - verify_listener_events $evts_ns1 $LISTENER_CLOSED $AF_INET 10.0.2.1 10100 + verify_listener_events $evts_ns1 $MPTCP_LIB_EVENT_LISTENER_CREATED \ + $MPTCP_LIB_AF_INET 10.0.2.1 10100 + verify_listener_events $evts_ns1 $MPTCP_LIB_EVENT_LISTENER_CLOSED \ + $MPTCP_LIB_AF_INET 10.0.2.1 10100 kill_events_pids fi @@ -3356,6 +3289,77 @@ userspace_pm_rm_sf() wait_rm_sf $1 "${cnt}" } +check_output() +{ + local cmd="$1" + local expected="$2" + local msg="$3" + local rc=0 + + mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?} + if [ ${rc} -eq 2 ]; then + fail_test "fail to check output # error ${rc}" + elif [ ${rc} -eq 0 ]; then + print_ok + elif [ ${rc} -eq 1 ]; then + fail_test "fail to check output # different output" + fi +} + +# $1: ns +userspace_pm_dump() +{ + local evts=$evts_ns1 + local tk + + [ "$1" == "$ns2" ] && evts=$evts_ns2 + tk=$(mptcp_lib_evts_get_info token "$evts") + + ip netns exec $1 ./pm_nl_ctl dump token $tk +} + +# $1: ns ; $2: id +userspace_pm_get_addr() +{ + local evts=$evts_ns1 + local tk + + [ "$1" == "$ns2" ] && evts=$evts_ns2 + tk=$(mptcp_lib_evts_get_info token "$evts") + + ip netns exec $1 ./pm_nl_ctl get $2 token $tk +} + +userspace_pm_chk_dump_addr() +{ + local ns="${1}" + local exp="${2}" + local check="${3}" + + print_check "dump addrs ${check}" + + if mptcp_lib_kallsyms_has "mptcp_userspace_pm_dump_addr$"; then + check_output "userspace_pm_dump ${ns}" "${exp}" + else + print_skip + fi +} + +userspace_pm_chk_get_addr() +{ + local ns="${1}" + local id="${2}" + local exp="${3}" + + print_check "get id ${id} addr" + + if mptcp_lib_kallsyms_has "mptcp_userspace_pm_get_addr$"; then + check_output "userspace_pm_get_addr ${ns} ${id}" "${exp}" + else + print_skip + fi +} + userspace_tests() { # userspace pm type prevents add_addr @@ -3447,10 +3451,18 @@ userspace_tests() chk_mptcp_info subflows 2 subflows 2 chk_subflows_total 3 3 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + userspace_pm_chk_dump_addr "${ns1}" \ + $'id 10 flags signal 10.0.2.1\nid 20 flags signal 10.0.3.1' \ + "signal" + userspace_pm_chk_get_addr "${ns1}" "10" "id 10 flags signal 10.0.2.1" + userspace_pm_chk_get_addr "${ns1}" "20" "id 20 flags signal 10.0.3.1" userspace_pm_rm_addr $ns1 10 - userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $SUB_ESTABLISHED + userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $MPTCP_LIB_EVENT_SUB_ESTABLISHED + userspace_pm_chk_dump_addr "${ns1}" \ + "id 20 flags signal 10.0.3.1" "after rm_addr 10" userspace_pm_rm_addr $ns1 20 - userspace_pm_rm_sf $ns1 10.0.3.1 $SUB_ESTABLISHED + userspace_pm_rm_sf $ns1 10.0.3.1 $MPTCP_LIB_EVENT_SUB_ESTABLISHED + userspace_pm_chk_dump_addr "${ns1}" "" "after rm_addr 20" chk_rm_nr 2 2 invert chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 @@ -3471,8 +3483,15 @@ userspace_tests() chk_join_nr 1 1 1 chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 + userspace_pm_chk_dump_addr "${ns2}" \ + "id 20 flags subflow 10.0.3.2" \ + "subflow" + userspace_pm_chk_get_addr "${ns2}" "20" "id 20 flags subflow 10.0.3.2" userspace_pm_rm_addr $ns2 20 - userspace_pm_rm_sf $ns2 10.0.3.2 $SUB_ESTABLISHED + userspace_pm_rm_sf $ns2 10.0.3.2 $MPTCP_LIB_EVENT_SUB_ESTABLISHED + userspace_pm_chk_dump_addr "${ns2}" \ + "" \ + "after rm_addr 20" chk_rm_nr 1 1 chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 @@ -3492,6 +3511,8 @@ userspace_tests() chk_mptcp_info subflows 0 subflows 0 chk_subflows_total 1 1 userspace_pm_add_sf $ns2 10.0.3.2 0 + userspace_pm_chk_dump_addr "${ns2}" \ + "id 0 flags subflow 10.0.3.2" "id 0 subflow" chk_join_nr 1 1 1 chk_mptcp_info subflows 1 subflows 1 chk_subflows_total 2 2 @@ -3610,7 +3631,7 @@ usage() { if [ -n "${1}" ]; then echo "${1}" - ret=1 + ret=${KSFT_FAIL} fi echo "mptcp_join usage:" diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 108a1e12436c..d529b4b37af8 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -8,8 +8,21 @@ readonly KSFT_SKIP=4 # shellcheck disable=SC2155 # declare and assign separately readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}" +# These variables are used in some selftests, read-only +declare -rx MPTCP_LIB_EVENT_ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED +declare -rx MPTCP_LIB_EVENT_REMOVED=7 # MPTCP_EVENT_REMOVED +declare -rx MPTCP_LIB_EVENT_SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED +declare -rx MPTCP_LIB_EVENT_SUB_CLOSED=11 # MPTCP_EVENT_SUB_CLOSED +declare -rx MPTCP_LIB_EVENT_LISTENER_CREATED=15 # MPTCP_EVENT_LISTENER_CREATED +declare -rx MPTCP_LIB_EVENT_LISTENER_CLOSED=16 # MPTCP_EVENT_LISTENER_CLOSED + +declare -rx MPTCP_LIB_AF_INET=2 +declare -rx MPTCP_LIB_AF_INET6=10 + MPTCP_LIB_SUBTESTS=() MPTCP_LIB_SUBTESTS_DUPLICATED=0 +MPTCP_LIB_TEST_COUNTER=0 +MPTCP_LIB_TEST_FORMAT="%02u %-50s" # only if supported (or forced) and not disabled, see no-color.org if { [ -t 1 ] || [ "${SELFTESTS_MPTCP_LIB_COLOR_FORCE:-}" = "1" ]; } && @@ -48,6 +61,23 @@ mptcp_lib_print_err() { mptcp_lib_print_color "${MPTCP_LIB_COLOR_RED}${*}" } +# shellcheck disable=SC2120 # parameters are optional +mptcp_lib_pr_ok() { + mptcp_lib_print_ok "[ OK ]${1:+ ${*}}" +} + +mptcp_lib_pr_skip() { + mptcp_lib_print_warn "[SKIP]${1:+ ${*}}" +} + +mptcp_lib_pr_fail() { + mptcp_lib_print_err "[FAIL]${1:+ ${*}}" +} + +mptcp_lib_pr_info() { + mptcp_lib_print_info "INFO: ${*}" +} + # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all # features using the last version of the kernel and the selftests to make sure # a test is not being skipped by mistake. @@ -78,14 +108,14 @@ mptcp_lib_has_file() { mptcp_lib_check_mptcp() { if ! mptcp_lib_has_file "/proc/sys/net/mptcp/enabled"; then - echo "SKIP: MPTCP support is not available" + mptcp_lib_pr_skip "MPTCP support is not available" exit ${KSFT_SKIP} fi } mptcp_lib_check_kallsyms() { if ! mptcp_lib_has_file "/proc/kallsyms"; then - echo "SKIP: CONFIG_KALLSYMS is missing" + mptcp_lib_pr_skip "CONFIG_KALLSYMS is missing" exit ${KSFT_SKIP} fi } @@ -292,7 +322,7 @@ mptcp_lib_check_transfer() { local what="${3}" if ! cmp "$in" "$out" > /dev/null 2>&1; then - echo "[ FAIL ] $what does not match (in, out):" + mptcp_lib_pr_fail "$what does not match (in, out):" mptcp_lib_print_file_err "$in" mptcp_lib_print_file_err "$out" @@ -319,3 +349,159 @@ mptcp_lib_wait_local_port_listen() { sleep 0.1 done } + +mptcp_lib_check_output() { + local err="${1}" + local cmd="${2}" + local expected="${3}" + local cmd_ret=0 + local out + + if ! out=$(${cmd} 2>"${err}"); then + cmd_ret=${?} + fi + + if [ ${cmd_ret} -ne 0 ]; then + mptcp_lib_pr_fail "command execution '${cmd}' stderr" + cat "${err}" + return 2 + elif [ "${out}" = "${expected}" ]; then + return 0 + else + mptcp_lib_pr_fail "expected '${expected}' got '${out}'" + return 1 + fi +} + +mptcp_lib_check_tools() { + local tool + + for tool in "${@}"; do + case "${tool}" in + "ip") + if ! ip -Version &> /dev/null; then + mptcp_lib_pr_skip "Could not run test without ip tool" + exit ${KSFT_SKIP} + fi + ;; + "ss") + if ! ss -h | grep -q MPTCP; then + mptcp_lib_pr_skip "ss tool does not support MPTCP" + exit ${KSFT_SKIP} + fi + ;; + "iptables"* | "ip6tables"*) + if ! "${tool}" -V &> /dev/null; then + mptcp_lib_pr_skip "Could not run all tests without ${tool}" + exit ${KSFT_SKIP} + fi + ;; + *) + mptcp_lib_pr_fail "Internal error: unsupported tool: ${tool}" + exit ${KSFT_FAIL} + ;; + esac + done +} + +mptcp_lib_ns_init() { + local sec rndh + + sec=$(date +%s) + rndh=$(printf %x "${sec}")-$(mktemp -u XXXXXX) + + local netns + for netns in "${@}"; do + eval "${netns}=${netns}-${rndh}" + + ip netns add "${!netns}" || exit ${KSFT_SKIP} + ip -net "${!netns}" link set lo up + ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1 + ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0 + done +} + +mptcp_lib_ns_exit() { + local netns + for netns in "${@}"; do + ip netns del "${netns}" + rm -f /tmp/"${netns}".{nstat,out} + done +} + +mptcp_lib_events() { + local ns="${1}" + local evts="${2}" + declare -n pid="${3}" + + :>"${evts}" + + mptcp_lib_kill_wait "${pid:-0}" + ip netns exec "${ns}" ./pm_nl_ctl events >> "${evts}" 2>&1 & + pid=$! +} + +mptcp_lib_print_title() { + : "${MPTCP_LIB_TEST_COUNTER:?}" + : "${MPTCP_LIB_TEST_FORMAT:?}" + + # shellcheck disable=SC2059 # the format is in a variable + printf "${MPTCP_LIB_TEST_FORMAT}" "$((++MPTCP_LIB_TEST_COUNTER))" "${*}" +} + +# $1: var name ; $2: prev ret +mptcp_lib_check_expected_one() { + local var="${1}" + local exp="e_${var}" + local prev_ret="${2}" + + if [ "${!var}" = "${!exp}" ]; then + return 0 + fi + + if [ "${prev_ret}" = "0" ]; then + mptcp_lib_pr_fail + fi + + mptcp_lib_print_err "Expected value for '${var}': '${!exp}', got '${!var}'." + return 1 +} + +# $@: all var names to check +mptcp_lib_check_expected() { + local rc=0 + local var + + for var in "${@}"; do + mptcp_lib_check_expected_one "${var}" "${rc}" || rc=1 + done + + return "${rc}" +} + +# shellcheck disable=SC2034 # Some variables are used below but indirectly +mptcp_lib_verify_listener_events() { + local evt=${1} + local e_type=${2} + local e_family=${3} + local e_saddr=${4} + local e_sport=${5} + local type + local family + local saddr + local sport + local rc=0 + + type=$(mptcp_lib_evts_get_info type "${evt}" "${e_type}") + family=$(mptcp_lib_evts_get_info family "${evt}" "${e_type}") + if [ "${family}" ] && [ "${family}" = "${AF_INET6}" ]; then + saddr=$(mptcp_lib_evts_get_info saddr6 "${evt}" "${e_type}") + else + saddr=$(mptcp_lib_evts_get_info saddr4 "${evt}" "${e_type}") + fi + sport=$(mptcp_lib_evts_get_info sport "${evt}" "${e_type}") + + mptcp_lib_check_expected "type" "family" "saddr" "sport" || rc="${?}" + return "${rc}" +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index c643872ddf47..e2d70c18786e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" ret=0 @@ -8,17 +13,14 @@ sin="" sout="" cin="" cout="" -ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) iptables="iptables" ip6tables="ip6tables" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns_sbox="ns_sbox-$rndh" +ns1="" +ns2="" +ns_sbox="" add_mark_rules() { @@ -40,17 +42,10 @@ add_mark_rules() init() { - local netns - for netns in "$ns1" "$ns2" "$ns_sbox";do - ip netns add $netns || exit $ksft_skip - ip -net $netns link set lo up - ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 - done + mptcp_lib_ns_init ns1 ns2 ns_sbox local i - for i in `seq 1 4`; do + for i in $(seq 1 4); do ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad @@ -77,36 +72,18 @@ init() add_mark_rules $ns2 2 } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { - local netns - for netns in "$ns1" "$ns2" "$ns_sbox"; do - ip netns del $netns - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}" rm -f "$cin" "$cout" rm -f "$sin" "$sout" } mptcp_lib_check_mptcp mptcp_lib_check_kallsyms - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -# Use the legacy version if available to support old kernel versions -if iptables-legacy -V &> /dev/null; then - iptables="iptables-legacy" - ip6tables="ip6tables-legacy" -elif ! iptables -V &> /dev/null; then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip -elif ! ip6tables -V &> /dev/null; then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip "${iptables}" "${ip6tables}" check_mark() { @@ -126,8 +103,9 @@ check_mark() local v for v in $values; do if [ $v -ne 0 ]; then - echo "FAIL: got $tables $values in ns $ns , not 0 - not all expected packets marked" 1>&2 - ret=1 + mptcp_lib_pr_fail "got $tables $values in ns $ns," \ + "not 0 - not all expected packets marked" + ret=${KSFT_FAIL} return 1 fi done @@ -135,6 +113,11 @@ check_mark() return 0 } +print_title() +{ + mptcp_lib_print_title "${@}" +} + do_transfer() { local listener_ns="$1" @@ -184,8 +167,9 @@ do_transfer() wait $spid local rets=$? + print_title "Transfer ${ip:2}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then - echo " client exit code $retc, server $rets" 1>&2 + mptcp_lib_pr_fail "client exit code $retc, server $rets" echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" @@ -194,10 +178,17 @@ do_transfer() mptcp_lib_result_fail "transfer ${ip}" - ret=1 + ret=${KSFT_FAIL} return 1 fi + if ! mptcp_lib_check_transfer $cin $sout "file received by server"; then + rets=1 + else + mptcp_lib_pr_ok + fi + mptcp_lib_result_code "${rets}" "transfer ${ip}" + print_title "Mark ${ip:2}" if [ $local_addr = "::" ];then check_mark $listener_ns 6 || retc=1 check_mark $connector_ns 6 || retc=1 @@ -206,15 +197,13 @@ do_transfer() check_mark $connector_ns 4 || retc=1 fi - mptcp_lib_check_transfer $cin $sout "file received by server" - rets=$? - mptcp_lib_result_code "${retc}" "mark ${ip}" - mptcp_lib_result_code "${rets}" "transfer ${ip}" if [ $retc -eq 0 ] && [ $rets -eq 0 ];then + mptcp_lib_pr_ok return 0 fi + mptcp_lib_pr_fail return 1 } @@ -235,7 +224,7 @@ do_mptcp_sockopt_tests() local lret=0 if ! mptcp_lib_kallsyms_has "mptcp_diag_fill_info$"; then - echo "INFO: MPTCP sockopt not supported: SKIP" + mptcp_lib_pr_skip "MPTCP sockopt not supported" mptcp_lib_result_skip "sockopt" return fi @@ -243,23 +232,27 @@ do_mptcp_sockopt_tests() ip netns exec "$ns_sbox" ./mptcp_sockopt lret=$? + print_title "SOL_MPTCP sockopt v4" if [ $lret -ne 0 ]; then - echo "FAIL: SOL_MPTCP getsockopt" 1>&2 + mptcp_lib_pr_fail mptcp_lib_result_fail "sockopt v4" ret=$lret return fi + mptcp_lib_pr_ok mptcp_lib_result_pass "sockopt v4" ip netns exec "$ns_sbox" ./mptcp_sockopt -6 lret=$? + print_title "SOL_MPTCP sockopt v6" if [ $lret -ne 0 ]; then - echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2 + mptcp_lib_pr_fail mptcp_lib_result_fail "sockopt v6" ret=$lret return fi + mptcp_lib_pr_ok mptcp_lib_result_pass "sockopt v6" } @@ -282,16 +275,17 @@ run_tests() do_tcpinq_test() { + print_title "TCP_INQ cmsg/ioctl $*" ip netns exec "$ns_sbox" ./mptcp_inq "$@" local lret=$? if [ $lret -ne 0 ];then ret=$lret - echo "FAIL: mptcp_inq $@" 1>&2 + mptcp_lib_pr_fail mptcp_lib_result_fail "TCP_INQ: $*" return $lret fi - echo "PASS: TCP_INQ cmsg/ioctl $@" + mptcp_lib_pr_ok mptcp_lib_result_pass "TCP_INQ: $*" return $lret } @@ -301,7 +295,7 @@ do_tcpinq_tests() local lret=0 if ! mptcp_lib_kallsyms_has "mptcp_ioctl$"; then - echo "INFO: TCP_INQ not supported: SKIP" + mptcp_lib_pr_skip "TCP_INQ not supported" mptcp_lib_result_skip "TCP_INQ" return fi @@ -337,15 +331,7 @@ trap cleanup EXIT run_tests $ns1 $ns2 10.0.1.1 run_tests $ns1 $ns2 dead:beef:1::1 -if [ $ret -eq 0 ];then - echo "PASS: all packets had packet mark set" -fi - do_mptcp_sockopt_tests -if [ $ret -eq 0 ];then - echo "PASS: SOL_MPTCP getsockopt has expected information" -fi - do_tcpinq_tests mptcp_lib_result_print_all_tap diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index ebfefae71e13..6ab8c5d36340 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,76 +1,69 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -ksft_skip=4 ret=0 usage() { echo "Usage: $0 [ -h ]" } - +optstring=h while getopts "$optstring" option;do case "$option" in "h") usage $0 - exit 0 + exit ${KSFT_PASS} ;; "?") usage $0 - exit 1 + exit ${KSFT_FAIL} ;; esac done -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" +ns1="" err=$(mktemp) +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f $err - ip netns del $ns1 + mptcp_lib_ns_exit "${ns1}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip trap cleanup EXIT -ip netns add $ns1 || exit $ksft_skip -ip -net $ns1 link set lo up -ip netns exec $ns1 sysctl -q net.mptcp.enabled=1 +mptcp_lib_ns_init ns1 check() { local cmd="$1" local expected="$2" local msg="$3" - local out=`$cmd 2>$err` - local cmd_ret=$? - - printf "%-50s" "$msg" - if [ $cmd_ret -ne 0 ]; then - echo "[FAIL] command execution '$cmd' stderr " - cat $err - mptcp_lib_result_fail "${msg} # error ${cmd_ret}" - ret=1 - elif [ "$out" = "$expected" ]; then - echo "[ OK ]" + local rc=0 + + mptcp_lib_print_title "$msg" + mptcp_lib_check_output "${err}" "${cmd}" "${expected}" || rc=${?} + if [ ${rc} -eq 2 ]; then + mptcp_lib_result_fail "${msg} # error ${rc}" + ret=${KSFT_FAIL} + elif [ ${rc} -eq 0 ]; then + mptcp_lib_print_ok "[ OK ]" mptcp_lib_result_pass "${msg}" - else - echo -n "[FAIL] " - echo "expected '$expected' got '$out'" + elif [ ${rc} -eq 1 ]; then mptcp_lib_result_fail "${msg} # different output" - ret=1 + ret=${KSFT_FAIL} fi } @@ -104,14 +97,14 @@ check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 flags signal check "ip netns exec $ns1 ./pm_nl_ctl get 4" "id 4 flags signal 10.0.1.4" "id addr increment" -for i in `seq 5 9`; do +for i in $(seq 5 9); do ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.$i flags signal >/dev/null 2>&1 done check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit" check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit" ip netns exec $ns1 ./pm_nl_ctl del 9 -for i in `seq 10 255`; do +for i in $(seq 10 255); do ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $i ip netns exec $ns1 ./pm_nl_ctl del $i done @@ -196,7 +189,8 @@ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" else for st in fullmesh nofullmesh backup,fullmesh; do st=" (${st})" - printf "%-50s%s\n" "${st}" "[SKIP]" + mptcp_lib_print_title "${st}" + mptcp_lib_pr_skip mptcp_lib_result_skip "${st}" done fi diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 49369c4a5f26..7426a2cbd4a0 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -453,6 +453,7 @@ int csf(int fd, int pm_family, int argc, char *argv[]) char data[NLMSG_ALIGN(sizeof(struct nlmsghdr)) + NLMSG_ALIGN(sizeof(struct genlmsghdr)) + 1024]; + u_int32_t flags = MPTCP_PM_ADDR_FLAG_SUBFLOW; const char *params[5]; struct nlmsghdr *nh; struct rtattr *addr; @@ -558,6 +559,13 @@ int csf(int fd, int pm_family, int argc, char *argv[]) off += NLMSG_ALIGN(rta->rta_len); } + /* addr flags */ + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ADDR_ATTR_FLAGS; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &flags, 4); + off += NLMSG_ALIGN(rta->rta_len); + addr->rta_len = off - addr_start; } @@ -1079,6 +1087,7 @@ int get_addr(int fd, int pm_family, int argc, char *argv[]) 1024]; struct rtattr *rta, *nest; struct nlmsghdr *nh; + u_int32_t token = 0; int nest_start; u_int8_t id; int off = 0; @@ -1089,10 +1098,12 @@ int get_addr(int fd, int pm_family, int argc, char *argv[]) MPTCP_PM_VER); /* the only argument is the address id */ - if (argc != 3) + if (argc != 3 && argc != 5) syntax(argv); id = atoi(argv[2]); + if (argc == 5 && !strcmp(argv[3], "token")) + token = strtoul(argv[4], NULL, 10); nest_start = off; nest = (void *)(data + off); @@ -1108,6 +1119,15 @@ int get_addr(int fd, int pm_family, int argc, char *argv[]) off += NLMSG_ALIGN(rta->rta_len); nest->rta_len = off - nest_start; + /* token */ + if (token) { + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + } + print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data))); return 0; } @@ -1119,8 +1139,16 @@ int dump_addrs(int fd, int pm_family, int argc, char *argv[]) 1024]; pid_t pid = getpid(); struct nlmsghdr *nh; + u_int32_t token = 0; + struct rtattr *rta; int off = 0; + if (argc != 2 && argc != 4) + syntax(argv); + + if (argc == 4 && !strcmp(argv[2], "token")) + token = strtoul(argv[3], NULL, 10); + memset(data, 0, sizeof(data)); nh = (void *)data; off = init_genl_req(data, pm_family, MPTCP_PM_CMD_GET_ADDR, @@ -1130,6 +1158,15 @@ int dump_addrs(int fd, int pm_family, int argc, char *argv[]) nh->nlmsg_pid = pid; nh->nlmsg_len = off; + /* token */ + if (token) { + rta = (void *)(data + off); + rta->rta_type = MPTCP_PM_ATTR_TOKEN; + rta->rta_len = RTA_LENGTH(4); + memcpy(RTA_DATA(rta), &token, 4); + off += NLMSG_ALIGN(rta->rta_len); + } + print_addrs(nh, pm_family, do_nl_req(fd, nh, off, sizeof(data))); return 0; } diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ed0165c15a24..1b2366220388 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,18 +1,21 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns3="ns3-$rndh" +ns1="" +ns2="" +ns3="" capture=false -ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) -test_cnt=1 +# a bit more space: because we have more to display +MPTCP_LIB_TEST_FORMAT="%02u %-60s" ret=0 bail=0 slack=50 @@ -30,25 +33,19 @@ usage() { echo -e "\t-d: debug this script" } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f "$cout" "$sout" rm -f "$large" "$small" rm -f "$capout" - local netns - for netns in "$ns1" "$ns2" "$ns3";do - ip netns del $netns - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip # "$ns1" ns2 ns3 # ns1eth1 ns2eth1 ns2eth3 ns3eth1 @@ -70,12 +67,7 @@ setup() trap cleanup EXIT - for i in "$ns1" "$ns2" "$ns3";do - ip netns add $i || exit $ksft_skip - ip -net $i link set lo up - ip netns exec $i sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $i sysctl -q net.ipv4.conf.default.rp_filter=0 - done + mptcp_lib_ns_init ns1 ns2 ns3 ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2" @@ -135,8 +127,7 @@ do_transfer() local sin=$2 local max_time=$3 local port - port=$((10000+$test_cnt)) - test_cnt=$((test_cnt+1)) + port=$((10000+MPTCP_LIB_TEST_COUNTER)) :> "$cout" :> "$sout" @@ -144,6 +135,7 @@ do_transfer() if $capture; then local capuser + local rndh="${ns1:4}" if [ -z $SUDO_USER ] ; then capuser="" else @@ -195,12 +187,12 @@ do_transfer() printf "%-16s" " max $max_time " if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then - echo "[ OK ]" + mptcp_lib_pr_ok cat "$capout" return 0 fi - echo " [ fail ]" + mptcp_lib_pr_fail echo "client exit code $retc, server $rets" 1>&2 echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2 ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port" @@ -247,7 +239,7 @@ run_test() # completion (see mptcp_connect): 200ms on each side, add some slack time=$((time + 400 + slack)) - printf "%-60s" "$msg" + mptcp_lib_print_title "$msg" do_transfer $small $large $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" @@ -257,7 +249,7 @@ run_test() fi msg+=" - reverse direction" - printf "%-60s" "${msg}" + mptcp_lib_print_title "${msg}" do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" @@ -271,7 +263,7 @@ while getopts "bcdh" option;do case "$option" in "h") usage $0 - exit 0 + exit ${KSFT_PASS} ;; "b") bail=1 @@ -284,7 +276,7 @@ while getopts "bcdh" option;do ;; "?") usage $0 - exit 1 + exit ${KSFT_FAIL} ;; esac done diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 1b94a75604fe..9e2981f2d7f5 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -5,7 +5,7 @@ # code but we accept it. #shellcheck disable=SC2086 -# Some variables are used below but indirectly, see check_expected_one() +# Some variables are used below but indirectly, see verify_*_event() #shellcheck disable=SC2034 . "$(dirname "${0}")/mptcp_lib.sh" @@ -17,21 +17,17 @@ if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then echo "userspace pm tests are not supported by the kernel: SKIP" exit ${KSFT_SKIP} fi +mptcp_lib_check_tools ip -if ! ip -Version &> /dev/null; then - echo "SKIP: Cannot not run test without ip tool" - exit ${KSFT_SKIP} -fi +ANNOUNCED=${MPTCP_LIB_EVENT_ANNOUNCED} +REMOVED=${MPTCP_LIB_EVENT_REMOVED} +SUB_ESTABLISHED=${MPTCP_LIB_EVENT_SUB_ESTABLISHED} +SUB_CLOSED=${MPTCP_LIB_EVENT_SUB_CLOSED} +LISTENER_CREATED=${MPTCP_LIB_EVENT_LISTENER_CREATED} +LISTENER_CLOSED=${MPTCP_LIB_EVENT_LISTENER_CLOSED} -ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED -REMOVED=7 # MPTCP_EVENT_REMOVED -SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED -SUB_CLOSED=11 # MPTCP_EVENT_SUB_CLOSED -LISTENER_CREATED=15 #MPTCP_EVENT_LISTENER_CREATED -LISTENER_CLOSED=16 #MPTCP_EVENT_LISTENER_CLOSED - -AF_INET=2 -AF_INET6=10 +AF_INET=${MPTCP_LIB_AF_INET} +AF_INET6=${MPTCP_LIB_AF_INET6} file="" server_evts="" @@ -54,20 +50,16 @@ app6_port=50004 client_addr_id=${RANDOM:0:2} server_addr_id=${RANDOM:0:2} -sec=$(date +%s) -rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" +ns1="" +ns2="" ret=0 test_name="" - -_printf() { - stdbuf -o0 -e0 printf "${@}" -} +# a bit more space: because we have more to display +MPTCP_LIB_TEST_FORMAT="%02u %-68s" print_title() { - _printf "INFO: %s\n" "${1}" + mptcp_lib_pr_info "${1}" } # $1: test name @@ -75,36 +67,29 @@ print_test() { test_name="${1}" - _printf "%-68s" "${test_name}" -} - -print_results() -{ - _printf "[%s]\n" "${1}" + mptcp_lib_print_title "${test_name}" } test_pass() { - print_results " OK " + mptcp_lib_pr_ok mptcp_lib_result_pass "${test_name}" } test_skip() { - print_results "SKIP" + mptcp_lib_pr_skip mptcp_lib_result_skip "${test_name}" } # $1: msg test_fail() { - print_results "FAIL" - ret=1 - - if [ -n "${1}" ]; then - _printf "\t%s\n" "${1}" + if [ ${#} -gt 0 ] + then + mptcp_lib_pr_fail "${@}" fi - + ret=${KSFT_FAIL} mptcp_lib_result_fail "${test_name}" } @@ -122,23 +107,18 @@ cleanup() mptcp_lib_kill_wait $pid done - local netns - for netns in "$ns1" "$ns2" ;do - ip netns del "$netns" - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" rm -rf $file $client_evts $server_evts - _printf "Done\n" + mptcp_lib_pr_info "Done" } trap cleanup EXIT # Create and configure network namespaces for testing +mptcp_lib_ns_init ns1 ns2 for i in "$ns1" "$ns2" ;do - ip netns add "$i" || exit 1 - ip -net "$i" link set lo up - ip netns exec "$i" sysctl -q net.mptcp.enabled=1 ip netns exec "$i" sysctl -q net.mptcp.pm_type=1 done @@ -160,17 +140,23 @@ ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad ip -net "$ns2" link set ns2eth1 up +file=$(mktemp) +mptcp_lib_make_file "$file" 2 1 + +# Capture netlink events over the two network namespaces running +# the MPTCP client and server +client_evts=$(mktemp) +mptcp_lib_events "${ns2}" "${client_evts}" client_evts_pid +server_evts=$(mktemp) +mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid +sleep 0.5 + print_title "Init" print_test "Created network namespaces ns1, ns2" test_pass make_connection() { - if [ -z "$file" ]; then - file=$(mktemp) - fi - mptcp_lib_make_file "$file" 2 1 - local is_v6=$1 local app_port=$app4_port local connect_addr="10.0.1.1" @@ -184,27 +170,8 @@ make_connection() is_v6="v4" fi - # Capture netlink events over the two network namespaces running - # the MPTCP client and server - if [ -z "$client_evts" ]; then - client_evts=$(mktemp) - fi :>"$client_evts" - if [ $client_evts_pid -ne 0 ]; then - mptcp_lib_kill_wait $client_evts_pid - fi - ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & - client_evts_pid=$! - if [ -z "$server_evts" ]; then - server_evts=$(mktemp) - fi :>"$server_evts" - if [ $server_evts_pid -ne 0 ]; then - mptcp_lib_kill_wait $server_evts_pid - fi - ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 & - server_evts_pid=$! - sleep 0.5 # Run the server ip netns exec "$ns1" \ @@ -242,7 +209,7 @@ make_connection() else test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" mptcp_lib_result_print_all_tap - exit 1 + exit ${KSFT_FAIL} fi if [ "$is_v6" = "v6" ] @@ -261,45 +228,16 @@ make_connection() fi } -# $1: var name ; $2: prev ret -check_expected_one() -{ - local var="${1}" - local exp="e_${var}" - local prev_ret="${2}" - - if [ "${!var}" = "${!exp}" ] - then - return 0 - fi - - if [ "${prev_ret}" = "0" ] - then - test_fail - fi - - _printf "\tExpected value for '%s': '%s', got '%s'.\n" \ - "${var}" "${!exp}" "${!var}" - return 1 -} - # $@: all var names to check check_expected() { - local rc=0 - local var - - for var in "${@}" - do - check_expected_one "${var}" "${rc}" || rc=1 - done - - if [ ${rc} -eq 0 ] + if mptcp_lib_check_expected "${@}" then test_pass return 0 fi + test_fail return 1 } @@ -449,7 +387,7 @@ test_remove() then test_pass else - test_fail + test_fail "unexpected type: ${type}" fi # RM_ADDR using an invalid addr id should result in no action @@ -462,7 +400,7 @@ test_remove() then test_pass else - test_fail + test_fail "unexpected type: ${type}" fi # RM_ADDR from the client to server machine @@ -897,32 +835,11 @@ test_prio() verify_listener_events() { - local evt=$1 - local e_type=$2 - local e_family=$3 - local e_saddr=$4 - local e_sport=$5 - local type - local family - local saddr - local sport - - if [ $e_type = $LISTENER_CREATED ]; then - print_test "CREATE_LISTENER $e_saddr:$e_sport" - elif [ $e_type = $LISTENER_CLOSED ]; then - print_test "CLOSE_LISTENER $e_saddr:$e_sport" - fi - - type=$(mptcp_lib_evts_get_info type $evt $e_type) - family=$(mptcp_lib_evts_get_info family $evt $e_type) - sport=$(mptcp_lib_evts_get_info sport $evt $e_type) - if [ $family ] && [ $family = $AF_INET6 ]; then - saddr=$(mptcp_lib_evts_get_info saddr6 $evt $e_type) + if mptcp_lib_verify_listener_events "${@}"; then + test_pass else - saddr=$(mptcp_lib_evts_get_info saddr4 $evt $e_type) + test_fail fi - - check_expected "type" "family" "saddr" "sport" } test_listener() @@ -944,6 +861,7 @@ test_listener() local listener_pid=$! sleep 0.5 + print_test "CREATE_LISTENER 10.0.2.2:$client4_port" verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -960,6 +878,7 @@ test_listener() mptcp_lib_kill_wait $listener_pid sleep 0.5 + print_test "CLOSE_LISTENER 10.0.2.2:$client4_port" verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c index 7b1addd50420..8a64f63e37ce 100644 --- a/tools/testing/selftests/powerpc/math/fpu_signal.c +++ b/tools/testing/selftests/powerpc/math/fpu_signal.c @@ -18,6 +18,7 @@ #include <pthread.h> #include "utils.h" +#include "fpu.h" /* Number of times each thread should receive the signal */ #define ITERATIONS 10 @@ -27,9 +28,7 @@ */ #define THREAD_FACTOR 8 -__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, - 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0, - 2.1}; +__thread double darray[32]; bool bad_context; int threads_starting; @@ -43,9 +42,9 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) ucontext_t *uc = context; mcontext_t *mc = &uc->uc_mcontext; - /* Only the non volatiles were loaded up */ - for (i = 14; i < 32; i++) { - if (mc->fp_regs[i] != darray[i - 14]) { + // Don't check f30/f31, they're used as scratches in check_all_fprs() + for (i = 0; i < 30; i++) { + if (mc->fp_regs[i] != darray[i]) { bad_context = true; break; } @@ -54,7 +53,6 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) void *signal_fpu_c(void *p) { - int i; long rc; struct sigaction act; act.sa_sigaction = signal_fpu_sig; @@ -64,9 +62,7 @@ void *signal_fpu_c(void *p) return p; srand(pthread_self()); - for (i = 0; i < 21; i++) - darray[i] = rand(); - + randomise_darray(darray, ARRAY_SIZE(darray)); rc = preempt_fpu(darray, &threads_starting, &running); return (void *) rc; diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json index 795cf1ce8af0..b73bd255ea36 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json @@ -657,6 +657,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -711,6 +712,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -765,6 +767,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -819,6 +822,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -873,6 +877,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -937,6 +942,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, @@ -995,6 +1001,7 @@ "actions", "mirred" ], + "dependsOn": "$TC actions add action mirred help 2>&1 | grep -q blockid", "plugins": { "requires": "nsPlugin" }, diff --git a/tools/virtio/.gitignore b/tools/virtio/.gitignore index 9934d48d9a55..7e47b281c442 100644 --- a/tools/virtio/.gitignore +++ b/tools/virtio/.gitignore @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only *.d virtio_test +vhost_net_test vringh_test virtio-trace/trace-agent diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index d128925980e0..e25e99c1c3b7 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -1,8 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 all: test mod -test: virtio_test vringh_test +test: virtio_test vringh_test vhost_net_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o +vhost_net_test: virtio_ring.o vhost_net_test.o try-run = $(shell set -e; \ if ($(1)) >/dev/null 2>&1; \ @@ -49,6 +50,7 @@ oot-clean: OOT_BUILD+=clean .PHONY: all test mod clean vhost oot oot-clean oot-build clean: - ${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \ - vhost_test/Module.symvers vhost_test/modules.order *.d + ${RM} *.o vringh_test virtio_test vhost_net_test vhost_test/*.o \ + vhost_test/.*.cmd vhost_test/Module.symvers \ + vhost_test/modules.order *.d -include *.d diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 2a8a70e2a950..42a564f22f2d 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_VIRTIO_CONFIG_H +#define LINUX_VIRTIO_CONFIG_H #include <linux/virtio_byteorder.h> #include <linux/virtio.h> #include <uapi/linux/virtio_config.h> @@ -95,3 +97,5 @@ static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val) { return __cpu_to_virtio64(virtio_is_little_endian(vdev), val); } + +#endif diff --git a/tools/virtio/vhost_net_test.c b/tools/virtio/vhost_net_test.c new file mode 100644 index 000000000000..389d99a6d7c7 --- /dev/null +++ b/tools/virtio/vhost_net_test.c @@ -0,0 +1,532 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <getopt.h> +#include <limits.h> +#include <string.h> +#include <poll.h> +#include <sys/eventfd.h> +#include <stdlib.h> +#include <assert.h> +#include <unistd.h> +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <fcntl.h> +#include <stdbool.h> +#include <linux/vhost.h> +#include <linux/if.h> +#include <linux/if_tun.h> +#include <linux/in.h> +#include <linux/if_packet.h> +#include <linux/virtio_net.h> +#include <netinet/ether.h> + +#define HDR_LEN sizeof(struct virtio_net_hdr_mrg_rxbuf) +#define TEST_BUF_LEN 256 +#define TEST_PTYPE ETH_P_LOOPBACK +#define DESC_NUM 256 + +/* Used by implementation of kmalloc() in tools/virtio/linux/kernel.h */ +void *__kmalloc_fake, *__kfree_ignore_start, *__kfree_ignore_end; + +struct vq_info { + int kick; + int call; + int idx; + long started; + long completed; + struct pollfd fds; + void *ring; + /* copy used for control */ + struct vring vring; + struct virtqueue *vq; +}; + +struct vdev_info { + struct virtio_device vdev; + int control; + struct vq_info vqs[2]; + int nvqs; + void *buf; + size_t buf_size; + char *test_buf; + char *res_buf; + struct vhost_memory *mem; + int sock; + int ifindex; + unsigned char mac[ETHER_ADDR_LEN]; +}; + +static int tun_alloc(struct vdev_info *dev, char *tun_name) +{ + struct ifreq ifr; + int len = HDR_LEN; + int fd, e; + + fd = open("/dev/net/tun", O_RDWR); + if (fd < 0) { + perror("Cannot open /dev/net/tun"); + return fd; + } + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; + strncpy(ifr.ifr_name, tun_name, IFNAMSIZ); + + e = ioctl(fd, TUNSETIFF, &ifr); + if (e < 0) { + perror("ioctl[TUNSETIFF]"); + close(fd); + return e; + } + + e = ioctl(fd, TUNSETVNETHDRSZ, &len); + if (e < 0) { + perror("ioctl[TUNSETVNETHDRSZ]"); + close(fd); + return e; + } + + e = ioctl(fd, SIOCGIFHWADDR, &ifr); + if (e < 0) { + perror("ioctl[SIOCGIFHWADDR]"); + close(fd); + return e; + } + + memcpy(dev->mac, &ifr.ifr_hwaddr.sa_data, ETHER_ADDR_LEN); + return fd; +} + +static void vdev_create_socket(struct vdev_info *dev, char *tun_name) +{ + struct ifreq ifr; + + dev->sock = socket(AF_PACKET, SOCK_RAW, htons(TEST_PTYPE)); + assert(dev->sock != -1); + + strncpy(ifr.ifr_name, tun_name, IFNAMSIZ); + assert(ioctl(dev->sock, SIOCGIFINDEX, &ifr) >= 0); + + dev->ifindex = ifr.ifr_ifindex; + + /* Set the flags that bring the device up */ + assert(ioctl(dev->sock, SIOCGIFFLAGS, &ifr) >= 0); + ifr.ifr_flags |= (IFF_UP | IFF_RUNNING); + assert(ioctl(dev->sock, SIOCSIFFLAGS, &ifr) >= 0); +} + +static void vdev_send_packet(struct vdev_info *dev) +{ + char *sendbuf = dev->test_buf + HDR_LEN; + struct sockaddr_ll saddrll = {0}; + int sockfd = dev->sock; + int ret; + + saddrll.sll_family = PF_PACKET; + saddrll.sll_ifindex = dev->ifindex; + saddrll.sll_halen = ETH_ALEN; + saddrll.sll_protocol = htons(TEST_PTYPE); + + ret = sendto(sockfd, sendbuf, TEST_BUF_LEN, 0, + (struct sockaddr *)&saddrll, + sizeof(struct sockaddr_ll)); + assert(ret >= 0); +} + +static bool vq_notify(struct virtqueue *vq) +{ + struct vq_info *info = vq->priv; + unsigned long long v = 1; + int r; + + r = write(info->kick, &v, sizeof(v)); + assert(r == sizeof(v)); + + return true; +} + +static void vhost_vq_setup(struct vdev_info *dev, struct vq_info *info) +{ + struct vhost_vring_addr addr = { + .index = info->idx, + .desc_user_addr = (uint64_t)(unsigned long)info->vring.desc, + .avail_user_addr = (uint64_t)(unsigned long)info->vring.avail, + .used_user_addr = (uint64_t)(unsigned long)info->vring.used, + }; + struct vhost_vring_state state = { .index = info->idx }; + struct vhost_vring_file file = { .index = info->idx }; + int r; + + state.num = info->vring.num; + r = ioctl(dev->control, VHOST_SET_VRING_NUM, &state); + assert(r >= 0); + + state.num = 0; + r = ioctl(dev->control, VHOST_SET_VRING_BASE, &state); + assert(r >= 0); + + r = ioctl(dev->control, VHOST_SET_VRING_ADDR, &addr); + assert(r >= 0); + + file.fd = info->kick; + r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file); + assert(r >= 0); +} + +static void vq_reset(struct vq_info *info, int num, struct virtio_device *vdev) +{ + if (info->vq) + vring_del_virtqueue(info->vq); + + memset(info->ring, 0, vring_size(num, 4096)); + vring_init(&info->vring, num, info->ring, 4096); + info->vq = vring_new_virtqueue(info->idx, num, 4096, vdev, true, false, + info->ring, vq_notify, NULL, "test"); + assert(info->vq); + info->vq->priv = info; +} + +static void vq_info_add(struct vdev_info *dev, int idx, int num, int fd) +{ + struct vhost_vring_file backend = { .index = idx, .fd = fd }; + struct vq_info *info = &dev->vqs[idx]; + int r; + + info->idx = idx; + info->kick = eventfd(0, EFD_NONBLOCK); + r = posix_memalign(&info->ring, 4096, vring_size(num, 4096)); + assert(r >= 0); + vq_reset(info, num, &dev->vdev); + vhost_vq_setup(dev, info); + + r = ioctl(dev->control, VHOST_NET_SET_BACKEND, &backend); + assert(!r); +} + +static void vdev_info_init(struct vdev_info *dev, unsigned long long features) +{ + struct ether_header *eh; + int i, r; + + dev->vdev.features = features; + INIT_LIST_HEAD(&dev->vdev.vqs); + spin_lock_init(&dev->vdev.vqs_list_lock); + + dev->buf_size = (HDR_LEN + TEST_BUF_LEN) * 2; + dev->buf = malloc(dev->buf_size); + assert(dev->buf); + dev->test_buf = dev->buf; + dev->res_buf = dev->test_buf + HDR_LEN + TEST_BUF_LEN; + + memset(dev->test_buf, 0, HDR_LEN + TEST_BUF_LEN); + eh = (struct ether_header *)(dev->test_buf + HDR_LEN); + eh->ether_type = htons(TEST_PTYPE); + memcpy(eh->ether_dhost, dev->mac, ETHER_ADDR_LEN); + memcpy(eh->ether_shost, dev->mac, ETHER_ADDR_LEN); + + for (i = sizeof(*eh); i < TEST_BUF_LEN; i++) + dev->test_buf[i + HDR_LEN] = (char)i; + + dev->control = open("/dev/vhost-net", O_RDWR); + assert(dev->control >= 0); + + r = ioctl(dev->control, VHOST_SET_OWNER, NULL); + assert(r >= 0); + + dev->mem = malloc(offsetof(struct vhost_memory, regions) + + sizeof(dev->mem->regions[0])); + assert(dev->mem); + memset(dev->mem, 0, offsetof(struct vhost_memory, regions) + + sizeof(dev->mem->regions[0])); + dev->mem->nregions = 1; + dev->mem->regions[0].guest_phys_addr = (long)dev->buf; + dev->mem->regions[0].userspace_addr = (long)dev->buf; + dev->mem->regions[0].memory_size = dev->buf_size; + + r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem); + assert(r >= 0); + + r = ioctl(dev->control, VHOST_SET_FEATURES, &features); + assert(r >= 0); + + dev->nvqs = 2; +} + +static void wait_for_interrupt(struct vq_info *vq) +{ + unsigned long long val; + + poll(&vq->fds, 1, 100); + + if (vq->fds.revents & POLLIN) + read(vq->fds.fd, &val, sizeof(val)); +} + +static void verify_res_buf(char *res_buf) +{ + int i; + + for (i = ETHER_HDR_LEN; i < TEST_BUF_LEN; i++) + assert(res_buf[i] == (char)i); +} + +static void run_tx_test(struct vdev_info *dev, struct vq_info *vq, + bool delayed, int bufs) +{ + long long spurious = 0; + struct scatterlist sl; + unsigned int len; + int r; + + for (;;) { + long started_before = vq->started; + long completed_before = vq->completed; + + virtqueue_disable_cb(vq->vq); + do { + while (vq->started < bufs && + (vq->started - vq->completed) < 1) { + sg_init_one(&sl, dev->test_buf, HDR_LEN + TEST_BUF_LEN); + r = virtqueue_add_outbuf(vq->vq, &sl, 1, + dev->test_buf + vq->started, + GFP_ATOMIC); + if (unlikely(r != 0)) + break; + + ++vq->started; + + if (unlikely(!virtqueue_kick(vq->vq))) { + r = -1; + break; + } + } + + if (vq->started >= bufs) + r = -1; + + /* Flush out completed bufs if any */ + while (virtqueue_get_buf(vq->vq, &len)) { + int n; + + n = recvfrom(dev->sock, dev->res_buf, TEST_BUF_LEN, 0, NULL, NULL); + assert(n == TEST_BUF_LEN); + verify_res_buf(dev->res_buf); + + ++vq->completed; + r = 0; + } + } while (r == 0); + + if (vq->completed == completed_before && vq->started == started_before) + ++spurious; + + assert(vq->completed <= bufs); + assert(vq->started <= bufs); + if (vq->completed == bufs) + break; + + if (delayed) { + if (virtqueue_enable_cb_delayed(vq->vq)) + wait_for_interrupt(vq); + } else { + if (virtqueue_enable_cb(vq->vq)) + wait_for_interrupt(vq); + } + } + printf("TX spurious wakeups: 0x%llx started=0x%lx completed=0x%lx\n", + spurious, vq->started, vq->completed); +} + +static void run_rx_test(struct vdev_info *dev, struct vq_info *vq, + bool delayed, int bufs) +{ + long long spurious = 0; + struct scatterlist sl; + unsigned int len; + int r; + + for (;;) { + long started_before = vq->started; + long completed_before = vq->completed; + + do { + while (vq->started < bufs && + (vq->started - vq->completed) < 1) { + sg_init_one(&sl, dev->res_buf, HDR_LEN + TEST_BUF_LEN); + + r = virtqueue_add_inbuf(vq->vq, &sl, 1, + dev->res_buf + vq->started, + GFP_ATOMIC); + if (unlikely(r != 0)) + break; + + ++vq->started; + + vdev_send_packet(dev); + + if (unlikely(!virtqueue_kick(vq->vq))) { + r = -1; + break; + } + } + + if (vq->started >= bufs) + r = -1; + + /* Flush out completed bufs if any */ + while (virtqueue_get_buf(vq->vq, &len)) { + struct ether_header *eh; + + eh = (struct ether_header *)(dev->res_buf + HDR_LEN); + + /* tun netdev is up and running, only handle the + * TEST_PTYPE packet. + */ + if (eh->ether_type == htons(TEST_PTYPE)) { + assert(len == TEST_BUF_LEN + HDR_LEN); + verify_res_buf(dev->res_buf + HDR_LEN); + } + + ++vq->completed; + r = 0; + } + } while (r == 0); + + if (vq->completed == completed_before && vq->started == started_before) + ++spurious; + + assert(vq->completed <= bufs); + assert(vq->started <= bufs); + if (vq->completed == bufs) + break; + } + + printf("RX spurious wakeups: 0x%llx started=0x%lx completed=0x%lx\n", + spurious, vq->started, vq->completed); +} + +static const char optstring[] = "h"; +static const struct option longopts[] = { + { + .name = "help", + .val = 'h', + }, + { + .name = "event-idx", + .val = 'E', + }, + { + .name = "no-event-idx", + .val = 'e', + }, + { + .name = "indirect", + .val = 'I', + }, + { + .name = "no-indirect", + .val = 'i', + }, + { + .name = "virtio-1", + .val = '1', + }, + { + .name = "no-virtio-1", + .val = '0', + }, + { + .name = "delayed-interrupt", + .val = 'D', + }, + { + .name = "no-delayed-interrupt", + .val = 'd', + }, + { + .name = "buf-num", + .val = 'n', + .has_arg = required_argument, + }, + { + .name = "batch", + .val = 'b', + .has_arg = required_argument, + }, + { + } +}; + +static void help(int status) +{ + fprintf(stderr, "Usage: vhost_net_test [--help]" + " [--no-indirect]" + " [--no-event-idx]" + " [--no-virtio-1]" + " [--delayed-interrupt]" + " [--buf-num]" + "\n"); + + exit(status); +} + +int main(int argc, char **argv) +{ + unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) | + (1ULL << VIRTIO_RING_F_EVENT_IDX) | (1ULL << VIRTIO_F_VERSION_1); + char tun_name[IFNAMSIZ]; + long nbufs = 0x100000; + struct vdev_info dev; + bool delayed = false; + int o, fd; + + for (;;) { + o = getopt_long(argc, argv, optstring, longopts, NULL); + switch (o) { + case -1: + goto done; + case '?': + help(2); + case 'e': + features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX); + break; + case 'h': + help(0); + case 'i': + features &= ~(1ULL << VIRTIO_RING_F_INDIRECT_DESC); + break; + case '0': + features &= ~(1ULL << VIRTIO_F_VERSION_1); + break; + case 'D': + delayed = true; + break; + case 'n': + nbufs = strtol(optarg, NULL, 10); + assert(nbufs > 0); + break; + default: + assert(0); + break; + } + } + +done: + memset(&dev, 0, sizeof(dev)); + snprintf(tun_name, IFNAMSIZ, "tun_%d", getpid()); + + fd = tun_alloc(&dev, tun_name); + assert(fd >= 0); + + vdev_info_init(&dev, features); + vq_info_add(&dev, 0, DESC_NUM, fd); + vq_info_add(&dev, 1, DESC_NUM, fd); + vdev_create_socket(&dev, tun_name); + + run_rx_test(&dev, &dev.vqs[0], delayed, nbufs); + run_tx_test(&dev, &dev.vqs[1], delayed, nbufs); + + return 0; +} |