diff options
481 files changed, 18339 insertions, 4192 deletions
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst index c9856b927055..38c15c6fcb14 100644 --- a/Documentation/bpf/bpf_devel_QA.rst +++ b/Documentation/bpf/bpf_devel_QA.rst @@ -20,11 +20,11 @@ Reporting bugs Q: How do I report bugs for BPF kernel code? -------------------------------------------- A: Since all BPF kernel development as well as bpftool and iproute2 BPF -loader development happens through the netdev kernel mailing list, +loader development happens through the bpf kernel mailing list, please report any found issues around BPF to the following mailing list: - netdev@vger.kernel.org + bpf@vger.kernel.org This may also include issues related to XDP, BPF tracing, etc. @@ -46,17 +46,12 @@ Submitting patches Q: To which mailing list do I need to submit my BPF patches? ------------------------------------------------------------ -A: Please submit your BPF patches to the netdev kernel mailing list: +A: Please submit your BPF patches to the bpf kernel mailing list: - netdev@vger.kernel.org - -Historically, BPF came out of networking and has always been maintained -by the kernel networking community. Although these days BPF touches -many other subsystems as well, the patches are still routed mainly -through the networking community. + bpf@vger.kernel.org In case your patch has changes in various different subsystems (e.g. -tracing, security, etc), make sure to Cc the related kernel mailing +networking, tracing, security, etc), make sure to Cc the related kernel mailing lists and maintainers from there as well, so they are able to review the changes and provide their Acked-by's to the patches. @@ -168,7 +163,7 @@ a BPF point of view. Be aware that this is not a final verdict that the patch will automatically get accepted into net or net-next trees eventually: -On the netdev kernel mailing list reviews can come in at any point +On the bpf kernel mailing list reviews can come in at any point in time. If discussions around a patch conclude that they cannot get included as-is, we will either apply a follow-up fix or drop them from the trees entirely. Therefore, we also reserve to rebase @@ -494,15 +489,15 @@ A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have that set up, proceed with building the latest LLVM and clang version from the git repositories:: - $ git clone http://llvm.org/git/llvm.git - $ cd llvm/tools - $ git clone --depth 1 http://llvm.org/git/clang.git - $ cd ..; mkdir build; cd build - $ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \ + $ git clone https://github.com/llvm/llvm-project.git + $ mkdir -p llvm-project/llvm/build/install + $ cd llvm-project/llvm/build + $ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \ + -DLLVM_ENABLE_PROJECTS="clang" \ -DBUILD_SHARED_LIBS=OFF \ -DCMAKE_BUILD_TYPE=Release \ -DLLVM_BUILD_RUNTIME=OFF - $ make -j $(getconf _NPROCESSORS_ONLN) + $ ninja The built binaries can then be found in the build/bin/ directory, where you can point the PATH variable to. diff --git a/Documentation/devicetree/bindings/net/dsa/ocelot.txt b/Documentation/devicetree/bindings/net/dsa/ocelot.txt new file mode 100644 index 000000000000..66a129fea705 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/ocelot.txt @@ -0,0 +1,116 @@ +Microchip Ocelot switch driver family +===================================== + +Felix +----- + +The VSC9959 core is currently the only switch supported by the driver, and is +found in the NXP LS1028A. It is a PCI device, part of the larger ENETC root +complex. As a result, the ethernet-switch node is a sub-node of the PCIe root +complex node and its "reg" property conforms to the parent node bindings: + +* reg: Specifies PCIe Device Number and Function Number of the endpoint device, + in this case for the Ethernet L2Switch it is PF5 (of device 0, bus 0). + +It does not require a "compatible" string. + +The interrupt line is used to signal availability of PTP TX timestamps and for +TSN frame preemption. + +For the external switch ports, depending on board configuration, "phy-mode" and +"phy-handle" are populated by board specific device tree instances. Ports 4 and +5 are fixed as internal ports in the NXP LS1028A instantiation. + +The CPU port property ("ethernet") configures the feature called "NPI port" in +the Ocelot hardware core. The CPU port in Ocelot is a set of queues, which are +connected, in the Node Processor Interface (NPI) mode, to an Ethernet port. +By default, in fsl-ls1028a.dtsi, the NPI port is assigned to the internal +2.5Gbps port@4, but can be moved to the 1Gbps port@5, depending on the specific +use case. Moving the NPI port to an external switch port is hardware possible, +but there is no platform support for the Linux system on the LS1028A chip to +operate as an entire slave DSA chip. NPI functionality (and therefore DSA +tagging) is supported on a single port at a time. + +Any port can be disabled (and in fsl-ls1028a.dtsi, they are indeed all disabled +by default, and should be enabled on a per-board basis). But if any external +switch port is enabled at all, the ENETC PF2 (enetc_port2) should be enabled as +well, regardless of whether it is configured as the DSA master or not. This is +because the Felix PHYLINK implementation accesses the MAC PCS registers, which +in hardware truly belong to the ENETC port #2 and not to Felix. + +Supported PHY interface types (appropriate SerDes protocol setting changes are +needed in the RCW binary): + +* phy_mode = "internal": on ports 4 and 5 +* phy_mode = "sgmii": on ports 0, 1, 2, 3 +* phy_mode = "qsgmii": on ports 0, 1, 2, 3 +* phy_mode = "usxgmii": on ports 0, 1, 2, 3 +* phy_mode = "2500base-x": on ports 0, 1, 2, 3 + +For the rest of the device tree binding definitions, which are standard DSA and +PCI, refer to the following documents: + +Documentation/devicetree/bindings/net/dsa/dsa.txt +Documentation/devicetree/bindings/pci/pci.txt + +Example: + +&soc { + pcie@1f0000000 { /* Integrated Endpoint Root Complex */ + ethernet-switch@0,5 { + reg = <0x000500 0 0 0 0>; + /* IEP INT_B */ + interrupts = <GIC_SPI 95 IRQ_TYPE_LEVEL_HIGH>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + /* External ports */ + port@0 { + reg = <0>; + label = "swp0"; + }; + + port@1 { + reg = <1>; + label = "swp1"; + }; + + port@2 { + reg = <2>; + label = "swp2"; + }; + + port@3 { + reg = <3>; + label = "swp3"; + }; + + /* Tagging CPU port */ + port@4 { + reg = <4>; + ethernet = <&enetc_port2>; + phy-mode = "internal"; + + fixed-link { + speed = <2500>; + full-duplex; + }; + }; + + /* Non-tagging CPU port */ + port@5 { + reg = <5>; + phy-mode = "internal"; + status = "disabled"; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml b/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml new file mode 100644 index 000000000000..9bc664f414a1 --- /dev/null +++ b/Documentation/devicetree/bindings/ptp/ptp-idt82p33.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ptp/ptp-idt82p33.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: IDT 82P33 PTP Clock Device Tree Bindings + +description: | + IDT 82P33XXX Synchronization Management Unit (SMU) based PTP clock + +maintainers: + - Min Li <min.li.xe@renesas.com> + +properties: + compatible: + enum: + - idt,82p33810 + - idt,82p33813 + - idt,82p33814 + - idt,82p33831 + - idt,82p33910 + - idt,82p33913 + - idt,82p33914 + - idt,82p33931 + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + phc@51 { + compatible = "idt,82p33810"; + reg = <0x51>; + }; + }; diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst new file mode 100644 index 000000000000..465a8b251bfe --- /dev/null +++ b/Documentation/networking/bareudp.rst @@ -0,0 +1,52 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================== +Bare UDP Tunnelling Module Documentation +======================================== + +There are various L3 encapsulation standards using UDP being discussed to +leverage the UDP based load balancing capability of different networks. +MPLSoUDP (__ https://tools.ietf.org/html/rfc7510) is one among them. + +The Bareudp tunnel module provides a generic L3 encapsulation tunnelling +support for tunnelling different L3 protocols like MPLS, IP, NSH etc. inside +a UDP tunnel. + +Special Handling +---------------- +The bareudp device supports special handling for MPLS & IP as they can have +multiple ethertypes. +MPLS procotcol can have ethertypes ETH_P_MPLS_UC (unicast) & ETH_P_MPLS_MC (multicast). +IP protocol can have ethertypes ETH_P_IP (v4) & ETH_P_IPV6 (v6). +This special handling can be enabled only for ethertypes ETH_P_IP & ETH_P_MPLS_UC +with a flag called multiproto mode. + +Usage +------ + +1) Device creation & deletion + + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847. + + This creates a bareudp tunnel device which tunnels L3 traffic with ethertype + 0x8847 (MPLS traffic). The destination port of the UDP header will be set to + 6635.The device will listen on UDP port 6635 to receive traffic. + + b) ip link delete bareudp0 + +2) Device creation with multiple proto mode enabled + +There are two ways to create a bareudp device for MPLS & IP with multiproto mode +enabled. + + a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto + + b) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls + +3) Device Usage + +The bareudp device could be used along with OVS or flower filter in TC. +The OVS or TC flower layer must set the tunnel information in SKB dst field before +sending packet buffer to the bareudp device for transmission. On reception the +bareudp device extracts and stores the tunnel information in SKB dst field before +passing the packet buffer to the network stack. diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst index f575a49790e8..e9b65035cd47 100644 --- a/Documentation/networking/device_drivers/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst @@ -101,7 +101,7 @@ Enabling the driver and kconfig options **External options** ( Choose if the corresponding mlx5 feature is required ) - CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled -- CONFIG_VXLAN: When chosen, mlx5 vxaln support will be enabled. +- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. - CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). Devlink info diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 47a429bb8658..63350e7332ce 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -238,6 +238,12 @@ be added to the following table: - ``drop`` - Traps NVE packets that the device decided to drop because their overlay source MAC is multicast + * - ``ingress_flow_action_drop`` + - ``drop`` + - Traps packets dropped during processing of ingress flow action drop + * - ``egress_flow_action_drop`` + - ``drop`` + - Traps packets dropped during processing of egress flow action drop Driver-specific Packet Traps ============================ @@ -277,6 +283,9 @@ narrow. The description of these groups must be added to the following table: * - ``tunnel_drops`` - Contains packet traps for packets that were dropped by the device during tunnel encapsulation / decapsulation + * - ``acl_drops`` + - Contains packet traps for packets that were dropped by the device during + ACL processing Testing ======= diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d07d9855dcd3..3a83cfb66704 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -8,6 +8,7 @@ Contents: netdev-FAQ af_xdp + bareudp batman-adv can can_ucan_protocol diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst new file mode 100644 index 000000000000..43088ddf95e4 --- /dev/null +++ b/Documentation/networking/page_pool.rst @@ -0,0 +1,159 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============= +Page Pool API +============= + +The page_pool allocator is optimized for the XDP mode that uses one frame +per-page, but it can fallback on the regular page allocator APIs. + +Basic use involves replacing alloc_pages() calls with the +page_pool_alloc_pages() call. Drivers should use page_pool_dev_alloc_pages() +replacing dev_alloc_pages(). + +API keeps track of inflight pages, in order to let API user know +when it is safe to free a page_pool object. Thus, API users +must run page_pool_release_page() when a page is leaving the page_pool or +call page_pool_put_page() where appropriate in order to maintain correct +accounting. + +API user must call page_pool_put_page() once on a page, as it +will either recycle the page, or in case of refcnt > 1, it will +release the DMA mapping and inflight state accounting. + +Architecture overview +===================== + +.. code-block:: none + + +------------------+ + | Driver | + +------------------+ + ^ + | + | + | + v + +--------------------------------------------+ + | request memory | + +--------------------------------------------+ + ^ ^ + | | + | Pool empty | Pool has entries + | | + v v + +-----------------------+ +------------------------+ + | alloc (and map) pages | | get page from cache | + +-----------------------+ +------------------------+ + ^ ^ + | | + | cache available | No entries, refill + | | from ptr-ring + | | + v v + +-----------------+ +------------------+ + | Fast cache | | ptr-ring cache | + +-----------------+ +------------------+ + +API interface +============= +The number of pools created **must** match the number of hardware queues +unless hardware restrictions make that impossible. This would otherwise beat the +purpose of page pool, which is allocate pages fast from cache without locking. +This lockless guarantee naturally comes from running under a NAPI softirq. +The protection doesn't strictly have to be NAPI, any guarantee that allocating +a page will cause no race conditions is enough. + +* page_pool_create(): Create a pool. + * flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV + * order: 2^order pages on allocation + * pool_size: size of the ptr_ring + * nid: preferred NUMA node for allocation + * dev: struct device. Used on DMA operations + * dma_dir: DMA direction + * max_len: max DMA sync memory size + * offset: DMA address offset + +* page_pool_put_page(): The outcome of this depends on the page refcnt. If the + driver bumps the refcnt > 1 this will unmap the page. If the page refcnt is 1 + the allocator owns the page and will try to recycle it in one of the pool + caches. If PP_FLAG_DMA_SYNC_DEV is set, the page will be synced for_device + using dma_sync_single_range_for_device(). + +* page_pool_put_full_page(): Similar to page_pool_put_page(), but will DMA sync + for the entire memory area configured in area pool->max_len. + +* page_pool_recycle_direct(): Similar to page_pool_put_full_page() but caller + must guarantee safe context (e.g NAPI), since it will recycle the page + directly into the pool fast cache. + +* page_pool_release_page(): Unmap the page (if mapped) and account for it on + inflight counters. + +* page_pool_dev_alloc_pages(): Get a page from the page allocator or page_pool + caches. + +* page_pool_get_dma_addr(): Retrieve the stored DMA address. + +* page_pool_get_dma_dir(): Retrieve the stored DMA direction. + +Coding examples +=============== + +Registration +------------ + +.. code-block:: c + + /* Page pool registration */ + struct page_pool_params pp_params = { 0 }; + struct xdp_rxq_info xdp_rxq; + int err; + + pp_params.order = 0; + /* internal DMA mapping in page_pool */ + pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.pool_size = DESC_NUM; + pp_params.nid = NUMA_NO_NODE; + pp_params.dev = priv->dev; + pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + page_pool = page_pool_create(&pp_params); + + err = xdp_rxq_info_reg(&xdp_rxq, ndev, 0); + if (err) + goto err_out; + + err = xdp_rxq_info_reg_mem_model(&xdp_rxq, MEM_TYPE_PAGE_POOL, page_pool); + if (err) + goto err_out; + +NAPI poller +----------- + + +.. code-block:: c + + /* NAPI Rx poller */ + enum dma_data_direction dma_dir; + + dma_dir = page_pool_get_dma_dir(dring->page_pool); + while (done < budget) { + if (some error) + page_pool_recycle_direct(page_pool, page); + if (packet_is_xdp) { + if XDP_DROP: + page_pool_recycle_direct(page_pool, page); + } else (packet_is_skb) { + page_pool_release_page(page_pool, page); + new_page = page_pool_dev_alloc_pages(page_pool); + } + } + +Driver unload +------------- + +.. code-block:: c + + /* Driver unload */ + page_pool_put_full_page(page_pool, page, false); + xdp_rxq_info_unreg(&xdp_rxq); diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst index d753a309f9d1..8d7af28cd835 100644 --- a/Documentation/networking/sfp-phylink.rst +++ b/Documentation/networking/sfp-phylink.rst @@ -74,10 +74,13 @@ phylib to the sfp/phylink support. Please send patches to improve this documentation. 1. Optionally split the network driver's phylib update function into - three parts dealing with link-down, link-up and reconfiguring the - MAC settings. This can be done as a separate preparation commit. + two parts dealing with link-down and link-up. This can be done as + a separate preparation commit. - An example of this preparation can be found in git commit fc548b991fb0. + An older example of this preparation can be found in git commit + fc548b991fb0, although this was splitting into three parts; the + link-up part now includes configuring the MAC for the link settings. + Please see :c:func:`mac_link_up` for more information on this. 2. Replace:: @@ -207,6 +210,14 @@ this documentation. using. This is particularly important for in-band negotiation methods such as 1000base-X and SGMII. + The :c:func:`mac_link_up` method is used to inform the MAC that the + link has come up. The call includes the negotiation mode and interface + for reference only. The finalised link parameters are also supplied + (speed, duplex and flow control/pause enablement settings) which + should be used to configure the MAC when the MAC and PCS are not + tightly integrated, or when the settings are not coming from in-band + negotiation. + The :c:func:`mac_config` method is used to update the MAC with the requested state, and must avoid unnecessarily taking the link down when making changes to the MAC configuration. This means the diff --git a/drivers/base/core.c b/drivers/base/core.c index 42a672456432..fb8b7990f6fd 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3458,6 +3458,126 @@ out: } EXPORT_SYMBOL_GPL(device_move); +static int device_attrs_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + struct kobject *kobj = &dev->kobj; + struct class *class = dev->class; + const struct device_type *type = dev->type; + int error; + + if (class) { + /* + * Change the device groups of the device class for @dev to + * @kuid/@kgid. + */ + error = sysfs_groups_change_owner(kobj, class->dev_groups, kuid, + kgid); + if (error) + return error; + } + + if (type) { + /* + * Change the device groups of the device type for @dev to + * @kuid/@kgid. + */ + error = sysfs_groups_change_owner(kobj, type->groups, kuid, + kgid); + if (error) + return error; + } + + /* Change the device groups of @dev to @kuid/@kgid. */ + error = sysfs_groups_change_owner(kobj, dev->groups, kuid, kgid); + if (error) + return error; + + if (device_supports_offline(dev) && !dev->offline_disabled) { + /* Change online device attributes of @dev to @kuid/@kgid. */ + error = sysfs_file_change_owner(kobj, dev_attr_online.attr.name, + kuid, kgid); + if (error) + return error; + } + + return 0; +} + +/** + * device_change_owner - change the owner of an existing device. + * @dev: device. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This changes the owner of @dev and its corresponding sysfs entries to + * @kuid/@kgid. This function closely mirrors how @dev was added via driver + * core. + * + * Returns 0 on success or error code on failure. + */ +int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) +{ + int error; + struct kobject *kobj = &dev->kobj; + + dev = get_device(dev); + if (!dev) + return -EINVAL; + + /* + * Change the kobject and the default attributes and groups of the + * ktype associated with it to @kuid/@kgid. + */ + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + goto out; + + /* + * Change the uevent file for @dev to the new owner. The uevent file + * was created in a separate step when @dev got added and we mirror + * that step here. + */ + error = sysfs_file_change_owner(kobj, dev_attr_uevent.attr.name, kuid, + kgid); + if (error) + goto out; + + /* + * Change the device groups, the device groups associated with the + * device class, and the groups associated with the device type of @dev + * to @kuid/@kgid. + */ + error = device_attrs_change_owner(dev, kuid, kgid); + if (error) + goto out; + + error = dpm_sysfs_change_owner(dev, kuid, kgid); + if (error) + goto out; + +#ifdef CONFIG_BLOCK + if (sysfs_deprecated && dev->class == &block_class) + goto out; +#endif + + /* + * Change the owner of the symlink located in the class directory of + * the device class associated with @dev which points to the actual + * directory entry for @dev to @kuid/@kgid. This ensures that the + * symlink shows the same permissions as its target. + */ + error = sysfs_link_change_owner(&dev->class->p->subsys.kobj, &dev->kobj, + dev_name(dev), kuid, kgid); + if (error) + goto out; + +out: + put_device(dev); + return error; +} +EXPORT_SYMBOL_GPL(device_change_owner); + /** * device_shutdown - call ->shutdown() on each device to shutdown. */ diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 444f5c169a0b..54292cdd7808 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -74,6 +74,7 @@ extern int pm_qos_sysfs_add_flags(struct device *dev); extern void pm_qos_sysfs_remove_flags(struct device *dev); extern int pm_qos_sysfs_add_latency_tolerance(struct device *dev); extern void pm_qos_sysfs_remove_latency_tolerance(struct device *dev); +extern int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); #else /* CONFIG_PM */ @@ -88,6 +89,8 @@ static inline void pm_runtime_remove(struct device *dev) {} static inline int dpm_sysfs_add(struct device *dev) { return 0; } static inline void dpm_sysfs_remove(struct device *dev) {} +static inline int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) { return 0; } #endif diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c index d7d82db2e4bc..2b99fe1eb207 100644 --- a/drivers/base/power/sysfs.c +++ b/drivers/base/power/sysfs.c @@ -480,6 +480,14 @@ static ssize_t wakeup_last_time_ms_show(struct device *dev, return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + if (dev->power.wakeup && dev->power.wakeup->dev) + return device_change_owner(dev->power.wakeup->dev, kuid, kgid); + return 0; +} + static DEVICE_ATTR_RO(wakeup_last_time_ms); #ifdef CONFIG_PM_AUTOSLEEP @@ -501,7 +509,13 @@ static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ -#endif /* CONFIG_PM_SLEEP */ +#else /* CONFIG_PM_SLEEP */ +static inline int dpm_sysfs_wakeup_change_owner(struct device *dev, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} +#endif #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, @@ -684,6 +698,45 @@ int dpm_sysfs_add(struct device *dev) return rc; } +int dpm_sysfs_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid) +{ + int rc; + + if (device_pm_not_required(dev)) + return 0; + + rc = sysfs_group_change_owner(&dev->kobj, &pm_attr_group, kuid, kgid); + if (rc) + return rc; + + if (pm_runtime_callbacks_present(dev)) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_runtime_attr_group, kuid, kgid); + if (rc) + return rc; + } + + if (device_can_wakeup(dev)) { + rc = sysfs_group_change_owner(&dev->kobj, &pm_wakeup_attr_group, + kuid, kgid); + if (rc) + return rc; + + rc = dpm_sysfs_wakeup_change_owner(dev, kuid, kgid); + if (rc) + return rc; + } + + if (dev->power.set_latency_tolerance) { + rc = sysfs_group_change_owner( + &dev->kobj, &pm_qos_latency_tolerance_attr_group, kuid, + kgid); + if (rc) + return rc; + } + return 0; +} + int wakeup_sysfs_add(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 25a8f9387d5a..66e410e58c8e 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -258,6 +258,19 @@ config GENEVE To compile this driver as a module, choose M here: the module will be called geneve. +config BAREUDP + tristate "Bare UDP Encapsulation" + depends on INET + depends on IPV6 || !IPV6 + select NET_UDP_TUNNEL + select GRO_CELLS + help + This adds a bare UDP tunnel module for tunnelling different + kinds of traffic like MPLS, IP, etc. inside a UDP tunnel. + + To compile this driver as a module, choose M here: the module + will be called bareudp. + config GTP tristate "GPRS Tunneling Protocol datapath (GTP-U)" depends on INET diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 71b88ffc5587..65967246f240 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -29,6 +29,7 @@ obj-$(CONFIG_VETH) += veth.o obj-$(CONFIG_VIRTIO_NET) += virtio_net.o obj-$(CONFIG_VXLAN) += vxlan.o obj-$(CONFIG_GENEVE) += geneve.o +obj-$(CONFIG_BAREUDP) += bareudp.o obj-$(CONFIG_GTP) += gtp.o obj-$(CONFIG_NLMON) += nlmon.o obj-$(CONFIG_NET_VRF) += vrf.o diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c new file mode 100644 index 000000000000..15337e9d4fad --- /dev/null +++ b/drivers/net/bareudp.c @@ -0,0 +1,806 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Bareudp: UDP tunnel encasulation for different Payload types like + * MPLS, NSH, IP, etc. + * Copyright (c) 2019 Nokia, Inc. + * Authors: Martin Varghese, <martin.varghese@nokia.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/etherdevice.h> +#include <linux/hash.h> +#include <net/dst_metadata.h> +#include <net/gro_cells.h> +#include <net/rtnetlink.h> +#include <net/protocol.h> +#include <net/ip6_tunnel.h> +#include <net/ip_tunnels.h> +#include <net/udp_tunnel.h> +#include <net/bareudp.h> + +#define BAREUDP_BASE_HLEN sizeof(struct udphdr) +#define BAREUDP_IPV4_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr)) +#define BAREUDP_IPV6_HLEN (sizeof(struct ipv6hdr) + \ + sizeof(struct udphdr)) + +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + +/* per-network namespace private data for this module */ + +static unsigned int bareudp_net_id; + +struct bareudp_net { + struct list_head bareudp_list; +}; + +/* Pseudo network device */ +struct bareudp_dev { + struct net *net; /* netns for packet i/o */ + struct net_device *dev; /* netdev for bareudp tunnel */ + __be16 ethertype; + __be16 port; + u16 sport_min; + bool multi_proto_mode; + struct socket __rcu *sock; + struct list_head next; /* bareudp node on namespace list */ + struct gro_cells gro_cells; +}; + +static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) +{ + struct metadata_dst *tun_dst = NULL; + struct pcpu_sw_netstats *stats; + struct bareudp_dev *bareudp; + unsigned short family; + unsigned int len; + __be16 proto; + void *oiph; + int err; + + bareudp = rcu_dereference_sk_user_data(sk); + if (!bareudp) + goto drop; + + if (skb->protocol == htons(ETH_P_IP)) + family = AF_INET; + else + family = AF_INET6; + + if (bareudp->ethertype == htons(ETH_P_IP)) { + struct iphdr *iphdr; + + iphdr = (struct iphdr *)(skb->data + BAREUDP_BASE_HLEN); + if (iphdr->version == 4) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && (iphdr->version == 6)) { + proto = htons(ETH_P_IPV6); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) { + struct iphdr *tunnel_hdr; + + tunnel_hdr = (struct iphdr *)skb_network_header(skb); + if (tunnel_hdr->version == 4) { + if (!ipv4_is_multicast(tunnel_hdr->daddr)) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && + ipv4_is_multicast(tunnel_hdr->daddr)) { + proto = htons(ETH_P_MPLS_MC); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } else { + int addr_type; + struct ipv6hdr *tunnel_hdr_v6; + + tunnel_hdr_v6 = (struct ipv6hdr *)skb_network_header(skb); + addr_type = + ipv6_addr_type((struct in6_addr *)&tunnel_hdr_v6->daddr); + if (!(addr_type & IPV6_ADDR_MULTICAST)) { + proto = bareudp->ethertype; + } else if (bareudp->multi_proto_mode && + (addr_type & IPV6_ADDR_MULTICAST)) { + proto = htons(ETH_P_MPLS_MC); + } else { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + } + } else { + proto = bareudp->ethertype; + } + + if (iptunnel_pull_header(skb, BAREUDP_BASE_HLEN, + proto, + !net_eq(bareudp->net, + dev_net(bareudp->dev)))) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + + tun_dst = udp_tun_rx_dst(skb, family, TUNNEL_KEY, 0, 0); + if (!tun_dst) { + bareudp->dev->stats.rx_dropped++; + goto drop; + } + skb_dst_set(skb, &tun_dst->dst); + skb->dev = bareudp->dev; + oiph = skb_network_header(skb); + skb_reset_network_header(skb); + + if (family == AF_INET) + err = IP_ECN_decapsulate(oiph, skb); +#if IS_ENABLED(CONFIG_IPV6) + else + err = IP6_ECN_decapsulate(oiph, skb); +#endif + + if (unlikely(err)) { + if (log_ecn_error) { + if (family == AF_INET) + net_info_ratelimited("non-ECT from %pI4 " + "with TOS=%#x\n", + &((struct iphdr *)oiph)->saddr, + ((struct iphdr *)oiph)->tos); +#if IS_ENABLED(CONFIG_IPV6) + else + net_info_ratelimited("non-ECT from %pI6\n", + &((struct ipv6hdr *)oiph)->saddr); +#endif + } + if (err > 1) { + ++bareudp->dev->stats.rx_frame_errors; + ++bareudp->dev->stats.rx_errors; + goto drop; + } + } + + len = skb->len; + err = gro_cells_receive(&bareudp->gro_cells, skb); + if (likely(err == NET_RX_SUCCESS)) { + stats = this_cpu_ptr(bareudp->dev->tstats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += len; + u64_stats_update_end(&stats->syncp); + } + return 0; +drop: + /* Consume bad packet */ + kfree_skb(skb); + + return 0; +} + +static int bareudp_err_lookup(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} + +static int bareudp_init(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&bareudp->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + return 0; +} + +static void bareudp_uninit(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + gro_cells_destroy(&bareudp->gro_cells); + free_percpu(dev->tstats); +} + +static struct socket *bareudp_create_sock(struct net *net, __be16 port) +{ + struct udp_port_cfg udp_conf; + struct socket *sock; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); +#if IS_ENABLED(CONFIG_IPV6) + udp_conf.family = AF_INET6; +#else + udp_conf.family = AF_INET; +#endif + udp_conf.local_udp_port = port; + /* Open UDP socket */ + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + return sock; +} + +/* Create new listen socket if needed */ +static int bareudp_socket_create(struct bareudp_dev *bareudp, __be16 port) +{ + struct udp_tunnel_sock_cfg tunnel_cfg; + struct socket *sock; + + sock = bareudp_create_sock(bareudp->net, port); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + /* Mark socket as an encapsulation socket */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); + tunnel_cfg.sk_user_data = bareudp; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_rcv = bareudp_udp_encap_recv; + tunnel_cfg.encap_err_lookup = bareudp_err_lookup; + tunnel_cfg.encap_destroy = NULL; + setup_udp_tunnel_sock(bareudp->net, sock, &tunnel_cfg); + + if (sock->sk->sk_family == AF_INET6) + udp_encap_enable(); + + rcu_assign_pointer(bareudp->sock, sock); + return 0; +} + +static int bareudp_open(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + int ret = 0; + + ret = bareudp_socket_create(bareudp, bareudp->port); + return ret; +} + +static void bareudp_sock_release(struct bareudp_dev *bareudp) +{ + struct socket *sock; + + sock = bareudp->sock; + rcu_assign_pointer(bareudp->sock, NULL); + synchronize_net(); + udp_tunnel_sock_release(sock); +} + +static int bareudp_stop(struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + bareudp_sock_release(bareudp); + return 0; +} + +static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct bareudp_dev *bareudp, + const struct ip_tunnel_info *info) +{ + bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct socket *sock = rcu_dereference(bareudp->sock); + bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + const struct ip_tunnel_key *key = &info->key; + struct rtable *rt; + __be16 sport, df; + int min_headroom; + __u8 tos, ttl; + __be32 saddr; + int err; + + if (!sock) + return -ESHUTDOWN; + + rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr, info, + IPPROTO_UDP, use_cache); + + if (IS_ERR(rt)) + return PTR_ERR(rt); + + skb_tunnel_check_pmtu(skb, &rt->dst, + BAREUDP_IPV4_HLEN + info->options_len); + + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); + tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); + ttl = key->ttl; + df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + skb_scrub_packet(skb, xnet); + + err = -ENOSPC; + if (!skb_pull(skb, skb_network_offset(skb))) + goto free_dst; + + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + goto free_dst; + + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) + goto free_dst; + + skb_set_inner_protocol(skb, bareudp->ethertype); + udp_tunnel_xmit_skb(rt, sock->sk, skb, saddr, info->key.u.ipv4.dst, + tos, ttl, df, sport, bareudp->port, + !net_eq(bareudp->net, dev_net(bareudp->dev)), + !(info->key.tun_flags & TUNNEL_CSUM)); + return 0; + +free_dst: + dst_release(&rt->dst); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct bareudp_dev *bareudp, + const struct ip_tunnel_info *info) +{ + bool xnet = !net_eq(bareudp->net, dev_net(bareudp->dev)); + bool use_cache = ip_tunnel_dst_cache_usable(skb, info); + struct socket *sock = rcu_dereference(bareudp->sock); + bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); + const struct ip_tunnel_key *key = &info->key; + struct dst_entry *dst = NULL; + struct in6_addr saddr, daddr; + int min_headroom; + __u8 prio, ttl; + __be16 sport; + int err; + + if (!sock) + return -ESHUTDOWN; + + dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, &saddr, info, + IPPROTO_UDP, use_cache); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len); + + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); + prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); + ttl = key->ttl; + + skb_scrub_packet(skb, xnet); + + err = -ENOSPC; + if (!skb_pull(skb, skb_network_offset(skb))) + goto free_dst; + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); + + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) + goto free_dst; + + err = udp_tunnel_handle_offloads(skb, udp_sum); + if (err) + goto free_dst; + + daddr = info->key.u.ipv6.dst; + udp_tunnel6_xmit_skb(dst, sock->sk, skb, dev, + &saddr, &daddr, prio, ttl, + info->key.label, sport, bareudp->port, + !(info->key.tun_flags & TUNNEL_CSUM)); + return 0; + +free_dst: + dst_release(dst); + return err; +} +#endif + +static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + struct ip_tunnel_info *info = NULL; + int err; + + if (skb->protocol != bareudp->ethertype) { + if (!bareudp->multi_proto_mode || + (skb->protocol != htons(ETH_P_MPLS_MC) && + skb->protocol != htons(ETH_P_IPV6))) { + err = -EINVAL; + goto tx_error; + } + } + + info = skb_tunnel_info(skb); + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { + err = -EINVAL; + goto tx_error; + } + + rcu_read_lock(); +#if IS_ENABLED(CONFIG_IPV6) + if (info->mode & IP_TUNNEL_INFO_IPV6) + err = bareudp6_xmit_skb(skb, dev, bareudp, info); + else +#endif + err = bareudp_xmit_skb(skb, dev, bareudp, info); + + rcu_read_unlock(); + + if (likely(!err)) + return NETDEV_TX_OK; +tx_error: + dev_kfree_skb(skb); + + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static int bareudp_fill_metadata_dst(struct net_device *dev, + struct sk_buff *skb) +{ + struct ip_tunnel_info *info = skb_tunnel_info(skb); + struct bareudp_dev *bareudp = netdev_priv(dev); + bool use_cache; + + use_cache = ip_tunnel_dst_cache_usable(skb, info); + + if (ip_tunnel_info_af(info) == AF_INET) { + struct rtable *rt; + __be32 saddr; + + rt = ip_route_output_tunnel(skb, dev, bareudp->net, &saddr, + info, IPPROTO_UDP, use_cache); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + ip_rt_put(rt); + info->key.u.ipv4.src = saddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (ip_tunnel_info_af(info) == AF_INET6) { + struct dst_entry *dst; + struct in6_addr saddr; + struct socket *sock = rcu_dereference(bareudp->sock); + + dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, + &saddr, info, IPPROTO_UDP, + use_cache); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + dst_release(dst); + info->key.u.ipv6.src = saddr; +#endif + } else { + return -EINVAL; + } + + info->key.tp_src = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, + USHRT_MAX, true); + info->key.tp_dst = bareudp->port; + return 0; +} + +static const struct net_device_ops bareudp_netdev_ops = { + .ndo_init = bareudp_init, + .ndo_uninit = bareudp_uninit, + .ndo_open = bareudp_open, + .ndo_stop = bareudp_stop, + .ndo_start_xmit = bareudp_xmit, + .ndo_get_stats64 = ip_tunnel_get_stats64, + .ndo_fill_metadata_dst = bareudp_fill_metadata_dst, +}; + +static const struct nla_policy bareudp_policy[IFLA_BAREUDP_MAX + 1] = { + [IFLA_BAREUDP_PORT] = { .type = NLA_U16 }, + [IFLA_BAREUDP_ETHERTYPE] = { .type = NLA_U16 }, + [IFLA_BAREUDP_SRCPORT_MIN] = { .type = NLA_U16 }, + [IFLA_BAREUDP_MULTIPROTO_MODE] = { .type = NLA_FLAG }, +}; + +/* Info for udev, that this is a virtual tunnel endpoint */ +static struct device_type bareudp_type = { + .name = "bareudp", +}; + +/* Initialize the device structure. */ +static void bareudp_setup(struct net_device *dev) +{ + dev->netdev_ops = &bareudp_netdev_ops; + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &bareudp_type); + dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM; + dev->features |= NETIF_F_RXCSUM; + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->mtu = ETH_DATA_LEN; + dev->min_mtu = IPV4_MIN_MTU; + dev->max_mtu = IP_MAX_MTU - BAREUDP_BASE_HLEN; + dev->type = ARPHRD_NONE; + netif_keep_dst(dev); + dev->priv_flags |= IFF_NO_QUEUE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; +} + +static int bareudp_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (!data) { + NL_SET_ERR_MSG(extack, + "Not enough attributes provided to perform the operation"); + return -EINVAL; + } + return 0; +} + +static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf) +{ + if (!data[IFLA_BAREUDP_PORT] || !data[IFLA_BAREUDP_ETHERTYPE]) + return -EINVAL; + + if (data[IFLA_BAREUDP_PORT]) + conf->port = nla_get_u16(data[IFLA_BAREUDP_PORT]); + + if (data[IFLA_BAREUDP_ETHERTYPE]) + conf->ethertype = nla_get_u16(data[IFLA_BAREUDP_ETHERTYPE]); + + if (data[IFLA_BAREUDP_SRCPORT_MIN]) + conf->sport_min = nla_get_u16(data[IFLA_BAREUDP_SRCPORT_MIN]); + + return 0; +} + +static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn, + const struct bareudp_conf *conf) +{ + struct bareudp_dev *bareudp, *t = NULL; + + list_for_each_entry(bareudp, &bn->bareudp_list, next) { + if (conf->port == bareudp->port) + t = bareudp; + } + return t; +} + +static int bareudp_configure(struct net *net, struct net_device *dev, + struct bareudp_conf *conf) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + struct bareudp_dev *t, *bareudp = netdev_priv(dev); + int err; + + bareudp->net = net; + bareudp->dev = dev; + t = bareudp_find_dev(bn, conf); + if (t) + return -EBUSY; + + if (conf->multi_proto_mode && + (conf->ethertype != htons(ETH_P_MPLS_UC) && + conf->ethertype != htons(ETH_P_IP))) + return -EINVAL; + + bareudp->port = conf->port; + bareudp->ethertype = conf->ethertype; + bareudp->sport_min = conf->sport_min; + bareudp->multi_proto_mode = conf->multi_proto_mode; + err = register_netdevice(dev); + if (err) + return err; + + list_add(&bareudp->next, &bn->bareudp_list); + return 0; +} + +static int bareudp_link_config(struct net_device *dev, + struct nlattr *tb[]) +{ + int err; + + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err) + return err; + } + return 0; +} + +static int bareudp_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct bareudp_conf conf; + int err; + + err = bareudp2info(data, &conf); + if (err) + return err; + + err = bareudp_configure(net, dev, &conf); + if (err) + return err; + + err = bareudp_link_config(dev, tb); + if (err) + return err; + + return 0; +} + +static void bareudp_dellink(struct net_device *dev, struct list_head *head) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + list_del(&bareudp->next); + unregister_netdevice_queue(dev, head); +} + +static size_t bareudp_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_PORT */ + nla_total_size(sizeof(__be16)) + /* IFLA_BAREUDP_ETHERTYPE */ + nla_total_size(sizeof(__u16)) + /* IFLA_BAREUDP_SRCPORT_MIN */ + nla_total_size(0) + /* IFLA_BAREUDP_MULTIPROTO_MODE */ + 0; +} + +static int bareudp_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct bareudp_dev *bareudp = netdev_priv(dev); + + if (nla_put_be16(skb, IFLA_BAREUDP_PORT, bareudp->port)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_BAREUDP_ETHERTYPE, bareudp->ethertype)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_BAREUDP_SRCPORT_MIN, bareudp->sport_min)) + goto nla_put_failure; + if (bareudp->multi_proto_mode && + nla_put_flag(skb, IFLA_BAREUDP_MULTIPROTO_MODE)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static struct rtnl_link_ops bareudp_link_ops __read_mostly = { + .kind = "bareudp", + .maxtype = IFLA_BAREUDP_MAX, + .policy = bareudp_policy, + .priv_size = sizeof(struct bareudp_dev), + .setup = bareudp_setup, + .validate = bareudp_validate, + .newlink = bareudp_newlink, + .dellink = bareudp_dellink, + .get_size = bareudp_get_size, + .fill_info = bareudp_fill_info, +}; + +struct net_device *bareudp_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct bareudp_conf *conf) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + LIST_HEAD(list_kill); + int err; + + memset(tb, 0, sizeof(tb)); + dev = rtnl_create_link(net, name, name_assign_type, + &bareudp_link_ops, tb, NULL); + if (IS_ERR(dev)) + return dev; + + err = bareudp_configure(net, dev, conf); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + err = dev_set_mtu(dev, IP_MAX_MTU - BAREUDP_BASE_HLEN); + if (err) + goto err; + + err = rtnl_configure_link(dev, NULL); + if (err < 0) + goto err; + + return dev; +err: + bareudp_dellink(dev, &list_kill); + unregister_netdevice_many(&list_kill); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(bareudp_dev_create); + +static __net_init int bareudp_init_net(struct net *net) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + + INIT_LIST_HEAD(&bn->bareudp_list); + return 0; +} + +static void bareudp_destroy_tunnels(struct net *net, struct list_head *head) +{ + struct bareudp_net *bn = net_generic(net, bareudp_net_id); + struct bareudp_dev *bareudp, *next; + + list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next) + unregister_netdevice_queue(bareudp->dev, head); +} + +static void __net_exit bareudp_exit_batch_net(struct list_head *net_list) +{ + struct net *net; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + bareudp_destroy_tunnels(net, &list); + + /* unregister the devices gathered above */ + unregister_netdevice_many(&list); + rtnl_unlock(); +} + +static struct pernet_operations bareudp_net_ops = { + .init = bareudp_init_net, + .exit_batch = bareudp_exit_batch_net, + .id = &bareudp_net_id, + .size = sizeof(struct bareudp_net), +}; + +static int __init bareudp_init_module(void) +{ + int rc; + + rc = register_pernet_subsys(&bareudp_net_ops); + if (rc) + goto out1; + + rc = rtnl_link_register(&bareudp_link_ops); + if (rc) + goto out2; + + return 0; +out2: + unregister_pernet_subsys(&bareudp_net_ops); +out1: + return rc; +} +late_initcall(bareudp_init_module); + +static void __exit bareudp_cleanup_module(void) +{ + rtnl_link_unregister(&bareudp_link_ops); + unregister_pernet_subsys(&bareudp_net_ops); +} +module_exit(bareudp_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Varghese <martin.varghese@nokia.com>"); +MODULE_DESCRIPTION("Interface driver for UDP encapsulated traffic"); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d10805e5e623..2e70e43c5df5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1265,7 +1265,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) skb->dev = bond->dev; if (BOND_MODE(bond) == BOND_MODE_ALB && - bond->dev->priv_flags & IFF_BRIDGE_PORT && + netif_is_bridge_port(bond->dev) && skb->pkt_type == PACKET_HOST) { if (unlikely(skb_cow_head(skb, @@ -4370,7 +4370,6 @@ static void bond_ethtool_get_drvinfo(struct net_device *bond_dev, struct ethtool_drvinfo *drvinfo) { strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d", BOND_ABI_VERSION); } @@ -5008,8 +5007,6 @@ static int __init bonding_init(void) int i; int res; - pr_info("%s", bond_version); - res = bond_check_params(&bonding_defaults); if (res) goto out; @@ -5064,6 +5061,5 @@ static void __exit bonding_exit(void) module_init(bonding_init); module_exit(bonding_exit); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); -MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION); +MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); diff --git a/drivers/net/bonding/bonding_priv.h b/drivers/net/bonding/bonding_priv.h index 5a4d81a9437c..45b77bc8c7b3 100644 --- a/drivers/net/bonding/bonding_priv.h +++ b/drivers/net/bonding/bonding_priv.h @@ -14,12 +14,11 @@ #ifndef _BONDING_PRIV_H #define _BONDING_PRIV_H +#include <linux/vermagic.h> -#define DRV_VERSION "3.7.1" -#define DRV_RELDATE "April 27, 2011" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" -#define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n" +#define bond_version DRV_DESCRIPTION ": v" UTS_RELEASE "\n" #endif diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 1a69286daa8d..ceafce446317 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1289,7 +1289,9 @@ EXPORT_SYMBOL(b53_phylink_mac_link_down); void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct b53_device *dev = ds->priv; diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 3c30f3a7eb29..3d42318bc3f1 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -338,7 +338,9 @@ void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev); + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering); int b53_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index b0f5280a83cb..368ead87e07a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -648,7 +648,9 @@ static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port, static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_eee *p = &priv->dev->ports[port].eee; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 0369c22fe3e1..cf6fa8fede33 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1517,7 +1517,9 @@ static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct gswip_priv *priv = ds->priv; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 022466ca1c19..86818ab3bb07 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1482,7 +1482,9 @@ static void mt7530_phylink_mac_link_down(struct dsa_switch *ds, int port, static void mt7530_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct mt7530_priv *priv = ds->priv; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8c9289549688..483db9d133c3 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -632,33 +632,78 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, dev_err(ds->dev, "p%d: failed to configure MAC\n", port); } -static void mv88e6xxx_mac_link_force(struct dsa_switch *ds, int port, int link) +static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) { struct mv88e6xxx_chip *chip = ds->priv; - int err; + const struct mv88e6xxx_ops *ops; + int err = 0; - mv88e6xxx_reg_lock(chip); - err = chip->info->ops->port_set_link(chip, port, link); - mv88e6xxx_reg_unlock(chip); + ops = chip->info->ops; - if (err) - dev_err(chip->dev, "p%d: failed to force MAC link\n", port); -} + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + * FIXME: we should be using the PPU enable state here. What about + * an automedia port? + */ + if (!mv88e6xxx_phy_is_internal(ds, port) && ops->port_set_link) { + mv88e6xxx_reg_lock(chip); + err = ops->port_set_link(chip, port, LINK_FORCED_DOWN); + mv88e6xxx_reg_unlock(chip); -static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, - unsigned int mode, - phy_interface_t interface) -{ - if (mode == MLO_AN_FIXED) - mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_DOWN); + if (err) + dev_err(chip->dev, + "p%d: failed to force MAC link down\n", port); + } } static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { - if (mode == MLO_AN_FIXED) - mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_UP); + struct mv88e6xxx_chip *chip = ds->priv; + const struct mv88e6xxx_ops *ops; + int err = 0; + + ops = chip->info->ops; + + /* Internal PHYs propagate their configuration directly to the MAC. + * External PHYs depend on whether the PPU is enabled for this port. + * FIXME: we should be using the PPU enable state here. What about + * an automedia port? + */ + if (!mv88e6xxx_phy_is_internal(ds, port)) { + mv88e6xxx_reg_lock(chip); + /* FIXME: for an automedia port, should we force the link + * down here - what if the link comes up due to "other" media + * while we're bringing the port up, how is the exclusivity + * handled in the Marvell hardware? E.g. port 4 on 88E6532 + * shared between internal PHY and Serdes. + */ + if (ops->port_set_speed) { + err = ops->port_set_speed(chip, port, speed); + if (err && err != -EOPNOTSUPP) + goto error; + } + + if (ops->port_set_duplex) { + err = ops->port_set_duplex(chip, port, duplex); + if (err && err != -EOPNOTSUPP) + goto error; + } + + if (ops->port_set_link) + err = ops->port_set_link(chip, port, LINK_FORCED_UP); +error: + mv88e6xxx_reg_unlock(chip); + + if (err && err != -EOPNOTSUPP) + dev_err(ds->dev, + "p%d: failed to configure MAC link up\n", port); + } } static int mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port) @@ -1018,7 +1063,14 @@ static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, static int mv88e6xxx_get_regs_len(struct dsa_switch *ds, int port) { - return 32 * sizeof(u16); + struct mv88e6xxx_chip *chip = ds->priv; + int len; + + len = 32 * sizeof(u16); + if (chip->info->ops->serdes_get_regs_len) + len += chip->info->ops->serdes_get_regs_len(chip, port); + + return len; } static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, @@ -1043,6 +1095,9 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, p[i] = reg; } + if (chip->info->ops->serdes_get_regs) + chip->info->ops->serdes_get_regs(chip, port, &p[i]); + mv88e6xxx_reg_unlock(chip); } @@ -1785,7 +1840,7 @@ static int mv88e6xxx_broadcast_setup(struct mv88e6xxx_chip *chip, u16 vid) } static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, - u16 vid, u8 member) + u16 vid, u8 member, bool warn) { const u8 non_member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER; struct mv88e6xxx_vtu_entry vlan; @@ -1830,7 +1885,7 @@ static int mv88e6xxx_port_vlan_join(struct mv88e6xxx_chip *chip, int port, err = mv88e6xxx_vtu_loadpurge(chip, &vlan); if (err) return err; - } else { + } else if (warn) { dev_info(chip->dev, "p%d: already a member of VLAN %d\n", port, vid); } @@ -1844,6 +1899,7 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + bool warn; u8 member; u16 vid; @@ -1857,10 +1913,15 @@ static void mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, else member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_TAGGED; + /* net/dsa/slave.c will call dsa_port_vlan_add() for the affected port + * and then the CPU port. Do not warn for duplicates for the CPU port. + */ + warn = !dsa_is_cpu_port(ds, port) && !dsa_is_dsa_port(ds, port); + mv88e6xxx_reg_lock(chip); for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) - if (mv88e6xxx_port_vlan_join(chip, port, vid, member)) + if (mv88e6xxx_port_vlan_join(chip, port, vid, member, warn)) dev_err(ds->dev, "p%d: failed to add VLAN %d%c\n", port, vid, untagged ? 'u' : 't'); @@ -3664,6 +3725,8 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_get_lane = mv88e6352_serdes_get_lane, .serdes_power = mv88e6352_serdes_power, + .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, + .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6352_phylink_validate, }; @@ -3758,6 +3821,8 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_irq_enable = mv88e6352_serdes_irq_enable, .serdes_irq_status = mv88e6352_serdes_irq_status, + .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, + .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6352_phylink_validate, }; @@ -3847,6 +3912,8 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_irq_status = mv88e6390_serdes_irq_status, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390_phylink_validate, @@ -3901,6 +3968,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_irq_status = mv88e6390_serdes_irq_status, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390x_phylink_validate, @@ -3954,6 +4023,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_irq_status = mv88e6390_serdes_irq_status, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6390_phylink_validate, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -4008,6 +4079,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .serdes_irq_mapping = mv88e6352_serdes_irq_mapping, .serdes_irq_enable = mv88e6352_serdes_irq_enable, .serdes_irq_status = mv88e6352_serdes_irq_status, + .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, + .serdes_get_regs = mv88e6352_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -4103,6 +4176,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .serdes_irq_status = mv88e6390_serdes_irq_status, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, @@ -4388,6 +4463,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .serdes_get_sset_count = mv88e6352_serdes_get_sset_count, .serdes_get_strings = mv88e6352_serdes_get_strings, .serdes_get_stats = mv88e6352_serdes_get_stats, + .serdes_get_regs_len = mv88e6352_serdes_get_regs_len, + .serdes_get_regs = mv88e6352_serdes_get_regs, .phylink_validate = mv88e6352_phylink_validate, }; @@ -4446,6 +4523,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .phylink_validate = mv88e6390_phylink_validate, }; @@ -4501,6 +4580,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .serdes_get_sset_count = mv88e6390_serdes_get_sset_count, .serdes_get_strings = mv88e6390_serdes_get_strings, .serdes_get_stats = mv88e6390_serdes_get_stats, + .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, + .serdes_get_regs = mv88e6390_serdes_get_regs, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 79cad5e751c6..851686b45414 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -517,6 +517,11 @@ struct mv88e6xxx_ops { int (*serdes_get_stats)(struct mv88e6xxx_chip *chip, int port, uint64_t *data); + /* SERDES registers for ethtool */ + int (*serdes_get_regs_len)(struct mv88e6xxx_chip *chip, int port); + void (*serdes_get_regs)(struct mv88e6xxx_chip *chip, int port, + void *_p); + /* Address Translation Unit operations */ int (*atu_get_hash)(struct mv88e6xxx_chip *chip, u8 *hash); int (*atu_set_hash)(struct mv88e6xxx_chip *chip, u8 hash); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 8d8b3b74aee1..238219787233 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -237,6 +237,29 @@ unsigned int mv88e6352_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port) return irq_find_mapping(chip->g2_irq.domain, MV88E6352_SERDES_IRQ); } +int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port) +{ + if (!mv88e6352_port_has_serdes(chip, port)) + return 0; + + return 32 * sizeof(u16); +} + +void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) +{ + u16 *p = _p; + u16 reg; + int i; + + if (!mv88e6352_port_has_serdes(chip, port)) + return; + + for (i = 0 ; i < 32; i++) { + mv88e6352_serdes_read(chip, i, ®); + p[i] = reg; + } +} + u8 mv88e6341_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) { u8 cmode = chip->ports[port].cmode; @@ -652,3 +675,57 @@ unsigned int mv88e6390_serdes_irq_mapping(struct mv88e6xxx_chip *chip, int port) { return irq_find_mapping(chip->g2_irq.domain, port); } + +static const u16 mv88e6390_serdes_regs[] = { + /* SERDES common registers */ + 0xf00a, 0xf00b, 0xf00c, + 0xf010, 0xf011, 0xf012, 0xf013, + 0xf016, 0xf017, 0xf018, + 0xf01b, 0xf01c, 0xf01d, 0xf01e, 0xf01f, + 0xf020, 0xf021, 0xf022, 0xf023, 0xf024, 0xf025, 0xf026, 0xf027, + 0xf028, 0xf029, + 0xf030, 0xf031, 0xf032, 0xf033, 0xf034, 0xf035, 0xf036, 0xf037, + 0xf038, 0xf039, + /* SGMII */ + 0x2000, 0x2001, 0x2002, 0x2003, 0x2004, 0x2005, 0x2006, 0x2007, + 0x2008, + 0x200f, + 0xa000, 0xa001, 0xa002, 0xa003, + /* 10Gbase-X */ + 0x1000, 0x1001, 0x1002, 0x1003, 0x1004, 0x1005, 0x1006, 0x1007, + 0x1008, + 0x100e, 0x100f, + 0x1018, 0x1019, + 0x9000, 0x9001, 0x9002, 0x9003, 0x9004, + 0x9006, + 0x9010, 0x9011, 0x9012, 0x9013, 0x9014, 0x9015, 0x9016, + /* 10Gbase-R */ + 0x1020, 0x1021, 0x1022, 0x1023, 0x1024, 0x1025, 0x1026, 0x1027, + 0x1028, 0x1029, 0x102a, 0x102b, +}; + +int mv88e6390_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port) +{ + if (mv88e6xxx_serdes_get_lane(chip, port) == 0) + return 0; + + return ARRAY_SIZE(mv88e6390_serdes_regs) * sizeof(u16); +} + +void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p) +{ + u16 *p = _p; + int lane; + u16 reg; + int i; + + lane = mv88e6xxx_serdes_get_lane(chip, port); + if (lane == 0) + return; + + for (i = 0 ; i < ARRAY_SIZE(mv88e6390_serdes_regs); i++) { + mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS, + mv88e6390_serdes_regs[i], ®); + p[i] = reg; + } +} diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index d16ef4da20b0..1906b3ab29c6 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -109,6 +109,11 @@ int mv88e6390_serdes_get_strings(struct mv88e6xxx_chip *chip, int mv88e6390_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, uint64_t *data); +int mv88e6352_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); +void mv88e6352_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); +int mv88e6390_serdes_get_regs_len(struct mv88e6xxx_chip *chip, int port); +void mv88e6390_serdes_get_regs(struct mv88e6xxx_chip *chip, int port, void *_p); + /* Return the (first) SERDES lane address a port is using, 0 otherwise. */ static inline u8 mv88e6xxx_serdes_get_lane(struct mv88e6xxx_chip *chip, int port) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3257962c147e..7e66821b05b4 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -176,8 +176,7 @@ static void felix_phylink_validate(struct dsa_switch *ds, int port, phylink_set(mask, 100baseT_Full); phylink_set(mask, 1000baseT_Full); - /* The internal ports that run at 2.5G are overclocked GMII */ - if (state->interface == PHY_INTERFACE_MODE_GMII || + if (state->interface == PHY_INTERFACE_MODE_INTERNAL || state->interface == PHY_INTERFACE_MODE_2500BASEX || state->interface == PHY_INTERFACE_MODE_USXGMII) { phylink_set(mask, 2500baseT_Full); @@ -264,7 +263,9 @@ static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int link_an_mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct ocelot *ocelot = ds->priv; struct ocelot_port *ocelot_port = ocelot->ports[port]; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 2c812b481778..93800e81cdd4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -955,8 +955,7 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, phy_interface_t phy_mode) { switch (phy_mode) { - case PHY_INTERFACE_MODE_GMII: - /* Only supported on internal to-CPU ports */ + case PHY_INTERFACE_MODE_INTERNAL: if (port != 4 && port != 5) return -ENOTSUPP; return 0; diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index de25f99e995a..7c86056b9401 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -458,7 +458,9 @@ static void ar9331_sw_phylink_mac_link_down(struct dsa_switch *ds, int port, static void ar9331_sw_phylink_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct ar9331_sw_priv *priv = (struct ar9331_sw_priv *)ds->priv; struct regmap *regmap = priv->regmap; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 03ba6d25f7fe..c27cc7b37440 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -786,7 +786,9 @@ static void sja1105_mac_link_down(struct dsa_switch *ds, int port, static void sja1105_mac_link_up(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause) { sja1105_inhibit_tx(ds->priv, BIT(port), false); } diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 3031a5fc5427..bab3a9bb5e6f 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -42,7 +42,6 @@ #include <linux/u64_stats_sync.h> #define DRV_NAME "dummy" -#define DRV_VERSION "1.0" static int numdummies = 1; @@ -104,7 +103,6 @@ static void dummy_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } static const struct ethtool_ops dummy_ethtool_ops = { @@ -212,4 +210,3 @@ module_init(dummy_init_module); module_exit(dummy_cleanup_module); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index 8cafd06ff0c4..b762176a1406 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -60,8 +60,6 @@ */ #define DRV_NAME "3c509" -#define DRV_VERSION "1.20" -#define DRV_RELDATE "04Feb2008" /* A few values that may be tweaked. */ @@ -87,13 +85,12 @@ #include <linux/device.h> #include <linux/eisa.h> #include <linux/bitops.h> +#include <linux/vermagic.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/irq.h> -static char version[] = DRV_NAME ".c:" DRV_VERSION " " DRV_RELDATE " becker@scyld.com\n"; - #ifdef EL3_DEBUG static int el3_debug = EL3_DEBUG; #else @@ -547,8 +544,6 @@ static int el3_common_init(struct net_device *dev) dev->name, dev->base_addr, if_names[(dev->if_port & 0x03)], dev->dev_addr, dev->irq); - if (el3_debug > 0) - pr_info("%s", version); return 0; } @@ -1143,7 +1138,6 @@ el3_netdev_set_ecmd(struct net_device *dev, static void el3_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); } static int el3_get_link_ksettings(struct net_device *dev, diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index 1e233e2f0a5a..90312fcd6319 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -22,12 +22,8 @@ */ +#include <linux/vermagic.h> #define DRV_NAME "3c515" -#define DRV_VERSION "0.99t-ac" -#define DRV_RELDATE "28-Oct-2002" - -static char *version = -DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " becker@scyld.com and others\n"; #define CORKSCREW 1 @@ -84,7 +80,6 @@ static int max_interrupt_work = 20; MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); MODULE_DESCRIPTION("3Com 3c515 Corkscrew driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); /* "Knobs" for adjusting internal parameters. */ /* Put out somewhat more debugging messages. (0 - no msg, 1 minimal msgs). */ @@ -418,8 +413,6 @@ int init_module(void) int found = 0; if (debug >= 0) corkscrew_debug = debug; - if (corkscrew_debug) - pr_debug("%s", version); while (corkscrew_scan(-1)) found++; return found ? 0 : -ENODEV; @@ -429,16 +422,10 @@ int init_module(void) struct net_device *tc515_probe(int unit) { struct net_device *dev = corkscrew_scan(unit); - static int printed; if (!dev) return ERR_PTR(-ENODEV); - if (corkscrew_debug > 0 && !printed) { - printed = 1; - pr_debug("%s", version); - } - return dev; } #endif /* not MODULE */ @@ -1540,7 +1527,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "ISA 0x%lx", dev->base_addr); } diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index d47cde6c5f08..09816e84314d 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -23,7 +23,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "3c589_cs" -#define DRV_VERSION "1.162-ac" #include <linux/module.h> #include <linux/kernel.h> @@ -482,7 +481,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "PCMCIA 0x%lx", dev->base_addr); } diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 14fce6658106..4383ee615793 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -127,7 +127,6 @@ static const int multicast_filter_limit = 32; #include "typhoon.h" MODULE_AUTHOR("David Dillow <dave@thedillows.org>"); -MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_NAME); MODULE_DESCRIPTION("3Com Typhoon Family (3C990, 3CR990, and variants)"); diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 165d18405b0c..2db42211329f 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -27,8 +27,6 @@ */ #define DRV_NAME "starfire" -#define DRV_VERSION "2.1" -#define DRV_RELDATE "July 6, 2008" #include <linux/interrupt.h> #include <linux/module.h> @@ -47,6 +45,7 @@ #include <asm/processor.h> /* Processor type for cache alignment. */ #include <linux/uaccess.h> #include <asm/io.h> +#include <linux/vermagic.h> /* * The current frame processor firmware fails to checksum a fragment @@ -165,15 +164,9 @@ static int rx_copybreak /* = 0 */; #define FIRMWARE_RX "adaptec/starfire_rx.bin" #define FIRMWARE_TX "adaptec/starfire_tx.bin" -/* These identify the driver base version and may not be removed. */ -static const char version[] = -KERN_INFO "starfire.c:v1.03 7/26/2000 Written by Donald Becker <becker@scyld.com>\n" -" (unofficial 2.2/2.4 kernel port, version " DRV_VERSION ", " DRV_RELDATE ")\n"; - MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); MODULE_DESCRIPTION("Adaptec Starfire Ethernet driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); MODULE_FIRMWARE(FIRMWARE_RX); MODULE_FIRMWARE(FIRMWARE_TX); @@ -654,13 +647,6 @@ static int starfire_init_one(struct pci_dev *pdev, int drv_flags, io_size; int boguscnt; -/* when built into the kernel, we only print version if device is found */ -#ifndef MODULE - static int printed_version; - if (!printed_version++) - printk(version); -#endif - if (pci_enable_device (pdev)) return -EIO; @@ -1853,7 +1839,6 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct netdev_private *np = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); } @@ -2073,8 +2058,6 @@ static int __init starfire_init (void) { /* when a module, this is printed whether or not devices are found in probe */ #ifdef MODULE - printk(version); - printk(KERN_INFO DRV_NAME ": polling (NAPI) enabled\n"); #endif diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 2a9f8643629c..bf546118dbc6 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1114,9 +1114,7 @@ static void greth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *in strlcpy(info->driver, dev_driver_string(greth->dev), sizeof(info->driver)); - strlcpy(info->version, "revision: 1.0", sizeof(info->version)); strlcpy(info->bus_info, greth->dev->bus->name, sizeof(info->bus_info)); - strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static void greth_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index cb6a761d5c11..1b19385ad8a9 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2958,7 +2958,6 @@ static void et131x_get_drvinfo(struct net_device *netdev, struct et131x_adapter *adapter = netdev_priv(netdev); strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); - strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(adapter->pdev), sizeof(info->bus_info)); } diff --git a/drivers/net/ethernet/agere/et131x.h b/drivers/net/ethernet/agere/et131x.h index be9a11c02526..d0e922584d8a 100644 --- a/drivers/net/ethernet/agere/et131x.h +++ b/drivers/net/ethernet/agere/et131x.h @@ -46,7 +46,6 @@ */ #define DRIVER_NAME "et131x" -#define DRIVER_VERSION "v2.0" /* EEPROM registers */ diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 9daef4c8feef..6234fcd844ee 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -26,7 +26,6 @@ #include "slic.h" #define DRV_NAME "slicoss" -#define DRV_VERSION "1.0" static const struct pci_device_id slic_id_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_ALACRITECH, @@ -1533,7 +1532,6 @@ static void slic_get_drvinfo(struct net_device *dev, struct slic_device *sdev = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(sdev->pdev), sizeof(info->bus_info)); } @@ -1852,4 +1850,3 @@ module_pci_driver(slic_driver); MODULE_DESCRIPTION("Alacritech non-accelerated SLIC driver"); MODULE_AUTHOR("Lino Sanfilippo <LinoSanfilippo@gmx.de>"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 22cadfbeedfb..18d3b4340bd4 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -33,7 +33,6 @@ #include "sun4i-emac.h" #define DRV_NAME "sun4i-emac" -#define DRV_VERSION "1.02" #define EMAC_MAX_FRAME_LEN 0x0600 @@ -212,7 +211,6 @@ static void emac_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, dev_name(&dev->dev), sizeof(info->bus_info)); } diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index f366faf88eee..5d192d551623 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2699,9 +2699,8 @@ static void ace_get_drvinfo(struct net_device *dev, struct ace_private *ap = netdev_priv(dev); strlcpy(info->driver, "acenic", sizeof(info->driver)); - snprintf(info->version, sizeof(info->version), "%i.%i.%i", - ap->firmware_major, ap->firmware_minor, - ap->firmware_fix); + snprintf(info->fw_version, sizeof(info->version), "%i.%i.%i", + ap->firmware_major, ap->firmware_minor, ap->firmware_fix); if (ap->pdev) strlcpy(info->bus_info, pci_name(ap->pdev), diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c index 23823464f2e7..4299f1301149 100644 --- a/drivers/net/ethernet/altera/altera_tse_ethtool.c +++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c @@ -67,7 +67,6 @@ static void tse_get_drvinfo(struct net_device *dev, u32 rev = ioread32(&priv->mac_dev->megacore_revision); strcpy(info->driver, "altera_tse"); - strcpy(info->version, "v8.0"); snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "v%d.%d", rev & 0xFFFF, (rev & 0xFFFF0000) >> 16); sprintf(info->bus_info, "platform"); diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 1fb58f9ad80b..a250046b8e18 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1067,18 +1067,14 @@ static void ena_com_hash_key_fill_default_key(struct ena_com_dev *ena_dev) static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev) { struct ena_rss *rss = &ena_dev->rss; - struct ena_admin_feature_rss_flow_hash_control *hash_key; struct ena_admin_get_feat_resp get_resp; int rc; - hash_key = (ena_dev->rss).hash_key; - rc = ena_com_get_feature_ex(ena_dev, &get_resp, ENA_ADMIN_RSS_HASH_FUNCTION, ena_dev->rss.hash_key_dma_addr, sizeof(ena_dev->rss.hash_key), 0); if (unlikely(rc)) { - hash_key = NULL; return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index ced1d577b62a..868265a2ec00 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -404,7 +404,6 @@ static void ena_get_drvinfo(struct net_device *dev, struct ena_adapter *adapter = netdev_priv(dev); strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); strlcpy(info->bus_info, pci_name(adapter->pdev), sizeof(info->bus_info)); } @@ -674,7 +673,6 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, * supports getting/setting the hash function. */ rc = ena_com_get_hash_function(adapter->ena_dev, &ena_func, key); - if (rc) { if (rc == -EOPNOTSUPP) { key = NULL; @@ -685,9 +683,6 @@ static int ena_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, return rc; } - if (rc) - return rc; - switch (ena_func) { case ENA_ADMIN_TOEPLITZ: func = ETH_RSS_HASH_TOP; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0b2fd96b93d7..555c7273d712 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -49,12 +49,9 @@ #include <linux/bpf_trace.h> #include "ena_pci_id_tbl.h" -static char version[] = DEVICE_NAME " v" DRV_MODULE_VERSION "\n"; - MODULE_AUTHOR("Amazon.com, Inc. or its affiliates"); MODULE_DESCRIPTION(DEVICE_NAME); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_MODULE_VERSION); /* Time in jiffies before concluding the transmitter is hung. */ #define TX_TIMEOUT (5 * HZ) @@ -3094,9 +3091,9 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, strncpy(host_info->os_dist_str, utsname()->release, sizeof(host_info->os_dist_str) - 1); host_info->driver_version = - (DRV_MODULE_VER_MAJOR) | - (DRV_MODULE_VER_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | - (DRV_MODULE_VER_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | + (DRV_MODULE_GEN_MAJOR) | + (DRV_MODULE_GEN_MINOR << ENA_ADMIN_HOST_INFO_MINOR_SHIFT) | + (DRV_MODULE_GEN_SUBMINOR << ENA_ADMIN_HOST_INFO_SUB_MINOR_SHIFT) | ("K"[0] << ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT); host_info->num_cpus = num_online_cpus(); @@ -3476,9 +3473,7 @@ static int ena_restore_device(struct ena_adapter *adapter) netif_carrier_on(adapter->netdev); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); - dev_err(&pdev->dev, - "Device reset completed successfully, Driver info: %s\n", - version); + dev_err(&pdev->dev, "Device reset completed successfully\n"); return rc; err_disable_msix: @@ -4116,8 +4111,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_dbg(&pdev->dev, "%s\n", __func__); - dev_info_once(&pdev->dev, "%s", version); - rc = pci_enable_device_mem(pdev); if (rc) { dev_err(&pdev->dev, "pci_enable_device_mem() failed!\n"); @@ -4429,8 +4422,6 @@ static struct pci_driver ena_pci_driver = { static int __init ena_init(void) { - pr_info("%s", version); - ena_wq = create_singlethread_workqueue(DRV_MODULE_NAME); if (!ena_wq) { pr_err("Failed to create workqueue\n"); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 8795e0b1dc3c..97dfd0c67e84 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,16 +45,16 @@ #include "ena_com.h" #include "ena_eth_com.h" -#define DRV_MODULE_VER_MAJOR 2 -#define DRV_MODULE_VER_MINOR 1 -#define DRV_MODULE_VER_SUBMINOR 0 +#define DRV_MODULE_GEN_MAJOR 2 +#define DRV_MODULE_GEN_MINOR 1 +#define DRV_MODULE_GEN_SUBMINOR 0 #define DRV_MODULE_NAME "ena" -#ifndef DRV_MODULE_VERSION -#define DRV_MODULE_VERSION \ - __stringify(DRV_MODULE_VER_MAJOR) "." \ - __stringify(DRV_MODULE_VER_MINOR) "." \ - __stringify(DRV_MODULE_VER_SUBMINOR) "K" +#ifndef DRV_MODULE_GENERATION +#define DRV_MODULE_GENERATION \ + __stringify(DRV_MODULE_GEN_MAJOR) "." \ + __stringify(DRV_MODULE_GEN_MINOR) "." \ + __stringify(DRV_MODULE_GEN_SUBMINOR) "K" #endif #define DEVICE_NAME "Elastic Network Adapter (ENA)" diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 0f3b743425e8..7a1286f8e983 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -84,9 +84,8 @@ Revision History: #include "amd8111e.h" #define MODULE_NAME "amd8111e" -#define MODULE_VERS "3.0.7" MODULE_AUTHOR("Advanced Micro Devices, Inc."); -MODULE_DESCRIPTION ("AMD8111 based 10/100 Ethernet Controller. Driver Version "MODULE_VERS); +MODULE_DESCRIPTION("AMD8111 based 10/100 Ethernet Controller."); MODULE_LICENSE("GPL"); module_param_array(speed_duplex, int, NULL, 0); MODULE_PARM_DESC(speed_duplex, "Set device speed and duplex modes, 0: Auto Negotiate, 1: 10Mbps Half Duplex, 2: 10Mbps Full Duplex, 3: 100Mbps Half Duplex, 4: 100Mbps Full Duplex"); @@ -1366,7 +1365,6 @@ static void amd8111e_get_drvinfo(struct net_device *dev, struct amd8111e_priv *lp = netdev_priv(dev); struct pci_dev *pci_dev = lp->pci_dev; strlcpy(info->driver, MODULE_NAME, sizeof(info->driver)); - strlcpy(info->version, MODULE_VERS, sizeof(info->version)); snprintf(info->fw_version, sizeof(info->fw_version), "%u", chip_version); strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info)); @@ -1875,7 +1873,6 @@ static int amd8111e_probe_one(struct pci_dev *pdev, /* display driver and device information */ chip_version = (readl(lp->mmio + CHIPID) & 0xf0000000)>>28; - dev_info(&pdev->dev, "AMD-8111e Driver Version: %s\n", MODULE_VERS); dev_info(&pdev->dev, "[ Rev %x ] PCI 10/100BaseT Ethernet %pM\n", chip_version, dev->dev_addr); if (lp->ext_phy_id) diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 089a4fbc61a0..9f6e3cc2ce80 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -63,14 +63,12 @@ static int au1000_debug = 3; NETIF_MSG_LINK) #define DRV_NAME "au1000_eth" -#define DRV_VERSION "1.7" #define DRV_AUTHOR "Pete Popov <ppopov@embeddedalley.com>" #define DRV_DESC "Au1xxx on-chip Ethernet driver" MODULE_AUTHOR(DRV_AUTHOR); MODULE_DESCRIPTION(DRV_DESC); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); /* AU1000 MAC registers and bits */ #define MAC_CONTROL 0x0 @@ -656,7 +654,6 @@ au1000_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) struct au1000_private *aup = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "%s %d", DRV_NAME, aup->mac_id); } @@ -1290,8 +1287,6 @@ static int au1000_probe(struct platform_device *pdev) netdev_info(dev, "Au1xx0 Ethernet found at 0x%lx, irq %d\n", (unsigned long)base->start, irq); - pr_info_once("%s version %s %s\n", DRV_NAME, DRV_VERSION, DRV_AUTHOR); - return 0; err_out: diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 023aecf6ab30..11c0b13edd30 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -114,8 +114,6 @@ Log: nmclan_cs.c,v #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "nmclan_cs" -#define DRV_VERSION "0.16" - /* ---------------------------------------------------------------------------- Conditional Compilation Options @@ -367,7 +365,7 @@ typedef struct _mace_private { char tx_free_frames; /* Number of free transmit frame buffers */ char tx_irq_disabled; /* MACE TX interrupt disabled */ - + spinlock_t bank_lock; /* Must be held if you step off bank 0 */ } mace_private; @@ -444,7 +442,7 @@ static int nmclan_probe(struct pcmcia_device *link) lp = netdev_priv(dev); lp->p_dev = link; link->priv = dev; - + spin_lock_init(&lp->bank_lock); link->resource[0]->end = 32; link->resource[0]->flags |= IO_DATA_PATH_WIDTH_AUTO; @@ -817,7 +815,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); snprintf(info->bus_info, sizeof(info->bus_info), "PCMCIA 0x%lx", dev->base_addr); } @@ -1110,7 +1107,7 @@ static int mace_rx(struct net_device *dev, unsigned char RxCnt) if (pkt_len & 1) *(skb_tail_pointer(skb) - 1) = inb(ioaddr + AM2150_RCV); skb->protocol = eth_type_trans(skb, dev); - + netif_rx(skb); /* Send the packet to the upper (protocol) layers. */ dev->stats.rx_packets++; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index dc7d88227e76..07e8211eea51 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -24,13 +24,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "pcnet32" -#define DRV_VERSION "1.35" #define DRV_RELDATE "21.Apr.2008" #define PFX DRV_NAME ": " -static const char *const version = - DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " tsbogend@alpha.franken.de\n"; - #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -809,7 +805,6 @@ static void pcnet32_get_drvinfo(struct net_device *dev, struct pcnet32_private *lp = netdev_priv(dev); strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); if (lp->pci_dev) strlcpy(info->bus_info, pci_name(lp->pci_dev), sizeof(info->bus_info)); @@ -3006,8 +3001,6 @@ MODULE_LICENSE("GPL"); static int __init pcnet32_init_module(void) { - pr_info("%s", version); - pcnet32_debug = netif_msg_init(debug, PCNET32_MSG_DEFAULT); if ((tx_start_pt >= 0) && (tx_start_pt <= 3)) diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c index b00e00881253..a21b2e60157e 100644 --- a/drivers/net/ethernet/amd/sunlance.c +++ b/drivers/net/ethernet/amd/sunlance.c @@ -105,14 +105,9 @@ static char lancestr[] = "LANCE"; #include <asm/irq.h> #define DRV_NAME "sunlance" -#define DRV_VERSION "2.02" #define DRV_RELDATE "8/24/03" #define DRV_AUTHOR "Miguel de Icaza (miguel@nuclecu.unam.mx)" -static char version[] = - DRV_NAME ".c:v" DRV_VERSION " " DRV_RELDATE " " DRV_AUTHOR "\n"; - -MODULE_VERSION(DRV_VERSION); MODULE_AUTHOR(DRV_AUTHOR); MODULE_DESCRIPTION("Sun Lance ethernet driver"); MODULE_LICENSE("GPL"); @@ -1282,7 +1277,6 @@ static void lance_free_hwresources(struct lance_private *lp) static void sparc_lance_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strlcpy(info->driver, "sunlance", sizeof(info->driver)); - strlcpy(info->version, "2.02", sizeof(info->version)); } static const struct ethtool_ops sparc_lance_ethtool_ops = { @@ -1305,7 +1299,6 @@ static int sparc_lance_probe_one(struct platform_device *op, struct platform_device *lebuffer) { struct device_node *dp = op->dev.of_node; - static unsigned version_printed; struct lance_private *lp; struct net_device *dev; int i; @@ -1316,9 +1309,6 @@ static int sparc_lance_probe_one(struct platform_device *op, lp = netdev_priv(dev); - if (sparc_lance_debug && version_printed++ == 0) - printk (KERN_INFO "%s", version); - spin_lock_init(&lp->lock); /* Copy the IDPROM ethernet address to the device structure, later we diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 8083173f1a8f..b23c8ee24ee3 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -405,7 +405,6 @@ static void xgbe_get_drvinfo(struct net_device *netdev, struct xgbe_hw_features *hw_feat = &pdata->hw_feat; strlcpy(drvinfo->driver, XGBE_DRV_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, XGBE_DRV_VERSION, sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, dev_name(pdata->dev), sizeof(drvinfo->bus_info)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%d.%d.%d", diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 7ce9c69e9c44..2a70714a791d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -127,7 +127,6 @@ MODULE_AUTHOR("Tom Lendacky <thomas.lendacky@amd.com>"); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_VERSION(XGBE_DRV_VERSION); MODULE_DESCRIPTION(XGBE_DRV_DESC); static int debug = -1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 47bcbcf58048..5897e46faca5 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -135,7 +135,6 @@ #include <linux/list.h> #define XGBE_DRV_NAME "amd-xgbe" -#define XGBE_DRV_VERSION "1.0.3" #define XGBE_DRV_DESC "AMD 10 Gigabit Ethernet Driver" /* Descriptor related defines */ diff --git a/drivers/net/ethernet/apm/xgene-v2/ethtool.c b/drivers/net/ethernet/apm/xgene-v2/ethtool.c index a58250c1b57a..b78d1a99fe81 100644 --- a/drivers/net/ethernet/apm/xgene-v2/ethtool.c +++ b/drivers/net/ethernet/apm/xgene-v2/ethtool.c @@ -89,8 +89,6 @@ static void xge_get_drvinfo(struct net_device *ndev, struct platform_device *pdev = pdata->pdev; strcpy(info->driver, "xgene-enet-v2"); - strcpy(info->version, XGENE_ENET_V2_VERSION); - snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A"); sprintf(info->bus_info, "%s", pdev->name); } diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index c48f60996761..860c18fb7aae 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -741,5 +741,4 @@ module_platform_driver(xge_driver); MODULE_DESCRIPTION("APM X-Gene SoC Ethernet v2 driver"); MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>"); -MODULE_VERSION(XGENE_ENET_V2_VERSION); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/apm/xgene-v2/main.h b/drivers/net/ethernet/apm/xgene-v2/main.h index d41439d2709d..b3985a7be59d 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.h +++ b/drivers/net/ethernet/apm/xgene-v2/main.h @@ -28,7 +28,6 @@ #include "ring.h" #include "ethtool.h" -#define XGENE_ENET_V2_VERSION "v1.0" #define XGENE_ENET_STD_MTU 1536 #define XGENE_ENET_MIN_FRAME 60 #define IRQ_ID_SIZE 16 diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index 246dec27140d..ada70425b48c 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -103,8 +103,6 @@ static void xgene_get_drvinfo(struct net_device *ndev, struct platform_device *pdev = pdata->pdev; strcpy(info->driver, "xgene_enet"); - strcpy(info->version, XGENE_DRV_VERSION); - snprintf(info->fw_version, ETHTOOL_FWVERS_LEN, "N/A"); sprintf(info->bus_info, "%s", pdev->name); } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 6aee2f0fc0db..5f1fc6582d74 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -2179,7 +2179,6 @@ static struct platform_driver xgene_enet_driver = { module_platform_driver(xgene_enet_driver); MODULE_DESCRIPTION("APM X-Gene SoC Ethernet driver"); -MODULE_VERSION(XGENE_DRV_VERSION); MODULE_AUTHOR("Iyappan Subramanian <isubramanian@apm.com>"); MODULE_AUTHOR("Keyur Chudgar <kchudgar@apm.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 18f4923b1723..d35a338120cf 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -28,7 +28,6 @@ #include "xgene_enet_ring2.h" #include "../../../phy/mdio-xgene.h" -#define XGENE_DRV_VERSION "v1.0" #define ETHER_MIN_PACKET 64 #define ETHER_STD_PACKET 1518 #define XGENE_ENET_STD_MTU 1536 diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h index f0c41f7408e5..7560f5506e55 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h @@ -9,8 +9,6 @@ #ifndef AQ_CFG_H #define AQ_CFG_H -#include <generated/utsrelease.h> - #define AQ_CFG_VECS_DEF 8U #define AQ_CFG_TCS_DEF 1U @@ -85,7 +83,5 @@ #define AQ_CFG_DRV_AUTHOR "aQuantia" #define AQ_CFG_DRV_DESC "aQuantia Corporation(R) Network Driver" #define AQ_CFG_DRV_NAME "atlantic" -#define AQ_CFG_DRV_VERSION UTS_RELEASE \ - AQ_CFG_DRV_VERSION_SUFFIX #endif /* AQ_CFG_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h index 42ea8d8daa46..c8c402b013bb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h @@ -12,7 +12,6 @@ #include <linux/etherdevice.h> #include <linux/pci.h> #include <linux/if_vlan.h> -#include "ver.h" #include "aq_cfg.h" #include "aq_utils.h" diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 7b55633d2cb9..0bdaa0d785b7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -132,7 +132,6 @@ static void aq_ethtool_get_drvinfo(struct net_device *ndev, regs_count = aq_nic_get_regs_count(aq_nic); strlcat(drvinfo->driver, AQ_CFG_DRV_NAME, sizeof(drvinfo->driver)); - strlcat(drvinfo->version, AQ_CFG_DRV_VERSION, sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "%u.%u.%u", firmware_version >> 24, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 538f460a3da7..9fcab646cbd5 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -19,7 +19,6 @@ #include <linux/udp.h> MODULE_LICENSE("GPL v2"); -MODULE_VERSION(AQ_CFG_DRV_VERSION); MODULE_AUTHOR(AQ_CFG_DRV_AUTHOR); MODULE_DESCRIPTION(AQ_CFG_DRV_DESC); diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h deleted file mode 100644 index 597654b51e01..000000000000 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * aQuantia Corporation Network Driver - * Copyright (C) 2014-2017 aQuantia Corporation. All rights reserved - */ - -#ifndef VER_H -#define VER_H - -#define AQ_CFG_DRV_VERSION_SUFFIX "-kern" - -#endif /* VER_H */ diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h index d9efbc8d783b..d820ae03a966 100644 --- a/drivers/net/ethernet/arc/emac.h +++ b/drivers/net/ethernet/arc/emac.h @@ -130,7 +130,6 @@ struct arc_emac_mdio_bus_data { */ struct arc_emac_priv { const char *drv_name; - const char *drv_version; void (*set_mac_speed)(void *priv, unsigned int speed); /* Devices */ diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c index 539166112993..1c7736b7eaf7 100644 --- a/drivers/net/ethernet/arc/emac_arc.c +++ b/drivers/net/ethernet/arc/emac_arc.c @@ -15,7 +15,6 @@ #include "emac.h" #define DRV_NAME "emac_arc" -#define DRV_VERSION "1.0" static int emac_arc_probe(struct platform_device *pdev) { @@ -36,7 +35,6 @@ static int emac_arc_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->drv_name = DRV_NAME; - priv->drv_version = DRV_VERSION; err = of_get_phy_mode(dev->of_node, &interface); if (err) { diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 17bda4e8cc45..38cd968b6a3b 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -92,7 +92,6 @@ static void arc_emac_get_drvinfo(struct net_device *ndev, struct arc_emac_priv *priv = netdev_priv(ndev); strlcpy(info->driver, priv->drv_name, sizeof(info->driver)); - strlcpy(info->version, priv->drv_version, sizeof(info->version)); } static const struct ethtool_ops arc_emac_ethtool_ops = { diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index aae231c5224f..48ecdf15eddc 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -16,7 +16,6 @@ #include "emac.h" #define DRV_NAME "rockchip_emac" -#define DRV_VERSION "1.1" struct emac_rockchip_soc_data { unsigned int grf_offset; @@ -112,7 +111,6 @@ static int emac_rockchip_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->emac.drv_name = DRV_NAME; - priv->emac.drv_version = DRV_VERSION; priv->emac.set_mac_speed = emac_rockchip_set_mac_speed; err = of_get_phy_mode(dev->of_node, &interface); diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 1dcbc486eca9..b9b4edb913c1 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1416,10 +1416,7 @@ static int alx_tso(struct sk_buff *skb, struct alx_txd *first) 0, IPPROTO_TCP, 0); first->word1 |= 1 << TPD_IPV4_SHIFT; } else if (skb_is_gso_v6(skb)) { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); /* LSOv2: the first TPD only provides the packet length */ first->adrl.l.pkt_len = skb->len; first->word1 |= 1 << TPD_LSO_V2_SHIFT; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h index 60b2febd7315..a0562a90fb6d 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c.h +++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h @@ -583,7 +583,6 @@ struct atl1c_adapter { readl(((a)->hw_addr + reg) + ((offset) << 2))) extern char atl1c_driver_name[]; -extern char atl1c_driver_version[]; void atl1c_reinit_locked(struct atl1c_adapter *adapter); s32 atl1c_reset_hw(struct atl1c_hw *hw); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c index b5a70a36fa04..e2eb7b8c63a0 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c @@ -221,8 +221,6 @@ static void atl1c_get_drvinfo(struct net_device *netdev, struct atl1c_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl1c_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl1c_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 4c0b1f8551dd..00bd7bd55794 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -8,9 +8,7 @@ #include "atl1c.h" -#define ATL1C_DRV_VERSION "1.0.1.1-NAPI" char atl1c_driver_name[] = "atl1c"; -char atl1c_driver_version[] = ATL1C_DRV_VERSION; /* * atl1c_pci_tbl - PCI Device ID Table @@ -37,7 +35,6 @@ MODULE_AUTHOR("Jie Yang"); MODULE_AUTHOR("Qualcomm Atheros Inc., <nic-devel@qualcomm.com>"); MODULE_DESCRIPTION("Qualcomm Atheros 100/1000M Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATL1C_DRV_VERSION); static int atl1c_stop_mac(struct atl1c_hw *hw); static void atl1c_disable_l0s_l1(struct atl1c_hw *hw); @@ -2025,10 +2022,8 @@ static int atl1c_tso_csum(struct atl1c_adapter *adapter, "IPV6 tso with zero data??\n"); goto check_sum; } else - tcp_hdr(skb)->check = ~csum_ipv6_magic( - &ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); + etpd->word1 |= 1 << TPD_LSO_EN_SHIFT; etpd->word1 |= 1 << TPD_LSO_VER_SHIFT; etpd->pkt_len = cpu_to_le32(skb->len); @@ -2644,8 +2639,6 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_register; } - if (netif_msg_probe(adapter)) - dev_info(&pdev->dev, "version %s\n", ATL1C_DRV_VERSION); cards_found++; return 0; diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e.h b/drivers/net/ethernet/atheros/atl1e/atl1e.h index e9893da50995..9fcad783c939 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e.h +++ b/drivers/net/ethernet/atheros/atl1e/atl1e.h @@ -482,7 +482,6 @@ struct atl1e_adapter { readl(((a)->hw_addr + reg) + ((offset) << 2))) extern char atl1e_driver_name[]; -extern char atl1e_driver_version[]; void atl1e_check_options(struct atl1e_adapter *adapter); int atl1e_up(struct atl1e_adapter *adapter); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c index c6b9e7ea8e38..0cbde352d1ba 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c @@ -307,8 +307,6 @@ static void atl1e_get_drvinfo(struct net_device *netdev, struct atl1e_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl1e_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl1e_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index e0d89942d537..223ef846123e 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -8,10 +8,7 @@ #include "atl1e.h" -#define DRV_VERSION "1.0.0.7-NAPI" - char atl1e_driver_name[] = "ATL1E"; -char atl1e_driver_version[] = DRV_VERSION; #define PCI_DEVICE_ID_ATTANSIC_L1E 0x1026 /* * atl1e_pci_tbl - PCI Device ID Table @@ -33,7 +30,6 @@ MODULE_DEVICE_TABLE(pci, atl1e_pci_tbl); MODULE_AUTHOR("Atheros Corporation, <xiong.huang@atheros.com>, Jie Yang <jie.yang@atheros.com>"); MODULE_DESCRIPTION("Atheros 1000M Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); static void atl1e_setup_mac_ctrl(struct atl1e_adapter *adapter); diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b498fd6a47d0..271e7034fa70 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -65,12 +65,10 @@ #include "atl1.h" -#define ATLX_DRIVER_VERSION "2.1.3" MODULE_AUTHOR("Xiong Huang <xiong.huang@atheros.com>, " "Chris Snook <csnook@redhat.com>, " "Jay Cliburn <jcliburn@gmail.com>"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATLX_DRIVER_VERSION); /* Temporary hack for merging atl1 and atl2 */ #include "atlx.c" @@ -2965,8 +2963,6 @@ static int atl1_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* get device revision number */ adapter->hw.dev_rev = ioread16(adapter->hw.hw_addr + (REG_MASTER_CTRL + 2)); - if (netif_msg_probe(adapter)) - dev_info(&pdev->dev, "version %s\n", ATLX_DRIVER_VERSION); /* set default ring resource counts */ adapter->rfd_ring.count = adapter->rrd_ring.count = ATL1_DEFAULT_RFD; @@ -3344,8 +3340,6 @@ static void atl1_get_drvinfo(struct net_device *netdev, struct atl1_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, ATLX_DRIVER_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, ATLX_DRIVER_VERSION, - sizeof(drvinfo->version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index b81a4e0c5b57..7c52b92b599d 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -36,18 +36,13 @@ #include "atl2.h" -#define ATL2_DRV_VERSION "2.2.3" - static const char atl2_driver_name[] = "atl2"; static const char atl2_driver_string[] = "Atheros(R) L2 Ethernet Driver"; -static const char atl2_copyright[] = "Copyright (c) 2007 Atheros Corporation."; -static const char atl2_driver_version[] = ATL2_DRV_VERSION; static const struct ethtool_ops atl2_ethtool_ops; MODULE_AUTHOR("Atheros Corporation <xiong.huang@atheros.com>, Chris Snook <csnook@redhat.com>"); MODULE_DESCRIPTION("Atheros Fast Ethernet Network Driver"); MODULE_LICENSE("GPL"); -MODULE_VERSION(ATL2_DRV_VERSION); /* * atl2_pci_tbl - PCI Device ID Table @@ -1688,9 +1683,6 @@ static struct pci_driver atl2_driver = { */ static int __init atl2_init_module(void) { - printk(KERN_INFO "%s - version %s\n", atl2_driver_string, - atl2_driver_version); - printk(KERN_INFO "%s\n", atl2_copyright); return pci_register_driver(&atl2_driver); } module_init(atl2_init_module); @@ -2011,8 +2003,6 @@ static void atl2_get_drvinfo(struct net_device *netdev, struct atl2_adapter *adapter = netdev_priv(netdev); strlcpy(drvinfo->driver, atl2_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, atl2_driver_version, - sizeof(drvinfo->version)); strlcpy(drvinfo->fw_version, "L2", sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index e50a15397e11..80feb20a2e53 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "bcmgenet: " fmt +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/sched.h> @@ -2771,6 +2772,21 @@ static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1); } +static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv, + unsigned char *addr) +{ + u32 addr_tmp; + + addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC0); + addr[0] = addr_tmp >> 24; + addr[1] = (addr_tmp >> 16) & 0xff; + addr[2] = (addr_tmp >> 8) & 0xff; + addr[3] = addr_tmp & 0xff; + addr_tmp = bcmgenet_umac_readl(priv, UMAC_MAC1); + addr[4] = (addr_tmp >> 8) & 0xff; + addr[5] = addr_tmp & 0xff; +} + /* Returns a reusable dma control register value */ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) { @@ -3466,10 +3482,8 @@ static int bcmgenet_probe(struct platform_device *pdev) const struct bcmgenet_plat_data *pdata; struct bcmgenet_priv *priv; struct net_device *dev; - const void *macaddr; unsigned int i; int err = -EIO; - const char *phy_mode_str; /* Up to GENET_MAX_MQ_CNT + 1 TX queues and RX queues */ dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, @@ -3498,11 +3512,6 @@ static int bcmgenet_probe(struct platform_device *pdev) } priv->wol_irq = platform_get_irq_optional(pdev, 2); - if (dn) - macaddr = of_get_mac_address(dn); - else - macaddr = pd->mac_address; - priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { err = PTR_ERR(priv->base); @@ -3513,12 +3522,6 @@ static int bcmgenet_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); dev_set_drvdata(&pdev->dev, dev); - if (IS_ERR_OR_NULL(macaddr) || !is_valid_ether_addr(macaddr)) { - dev_warn(&pdev->dev, "using random Ethernet MAC\n"); - eth_hw_addr_random(dev); - } else { - ether_addr_copy(dev->dev_addr, macaddr); - } dev->watchdog_timeo = 2 * HZ; dev->ethtool_ops = &bcmgenet_ethtool_ops; dev->netdev_ops = &bcmgenet_netdev_ops; @@ -3547,8 +3550,9 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->dev = dev; priv->pdev = pdev; - if (of_id) { - pdata = of_id->data; + + pdata = device_get_match_data(&pdev->dev); + if (pdata) { priv->version = pdata->version; priv->dma_max_burst_length = pdata->dma_max_burst_length; } else { @@ -3558,7 +3562,7 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk = devm_clk_get(&priv->pdev->dev, "enet"); if (IS_ERR(priv->clk)) { - dev_warn(&priv->pdev->dev, "failed to get enet clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet clock\n"); priv->clk = NULL; } @@ -3582,23 +3586,34 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol"); if (IS_ERR(priv->clk_wol)) { - dev_warn(&priv->pdev->dev, "failed to get enet-wol clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet-wol clock\n"); priv->clk_wol = NULL; } priv->clk_eee = devm_clk_get(&priv->pdev->dev, "enet-eee"); if (IS_ERR(priv->clk_eee)) { - dev_warn(&priv->pdev->dev, "failed to get enet-eee clock\n"); + dev_dbg(&priv->pdev->dev, "failed to get enet-eee clock\n"); priv->clk_eee = NULL; } /* If this is an internal GPHY, power it on now, before UniMAC is * brought out of reset as absolutely no UniMAC activity is allowed */ - if (dn && !of_property_read_string(dn, "phy-mode", &phy_mode_str) && - !strcasecmp(phy_mode_str, "internal")) + if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + if ((pd) && (!IS_ERR_OR_NULL(pd->mac_address))) + ether_addr_copy(dev->dev_addr, pd->mac_address); + else + if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) + if (has_acpi_companion(&pdev->dev)) + bcmgenet_get_hw_addr(priv, dev->dev_addr); + + if (!is_valid_ether_addr(dev->dev_addr)) { + dev_warn(&pdev->dev, "using random Ethernet MAC\n"); + eth_hw_addr_random(dev); + } + reset_umac(priv); err = bcmgenet_mii_init(dev); @@ -3771,6 +3786,12 @@ static int bcmgenet_suspend(struct device *d) static SIMPLE_DEV_PM_OPS(bcmgenet_pm_ops, bcmgenet_suspend, bcmgenet_resume); +static const struct acpi_device_id genet_acpi_match[] = { + { "BCM6E4E", (kernel_ulong_t)&bcm2711_plat_data }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, genet_acpi_match); + static struct platform_driver bcmgenet_driver = { .probe = bcmgenet_probe, .remove = bcmgenet_remove, @@ -3779,6 +3800,7 @@ static struct platform_driver bcmgenet_driver = { .name = "bcmgenet", .of_match_table = bcmgenet_match, .pm = &bcmgenet_pm_ops, + .acpi_match_table = ACPI_PTR(genet_acpi_match), }, }; module_platform_driver(bcmgenet_driver); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 10244941a7a6..d3003cb1bb09 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -5,7 +5,7 @@ * Copyright (c) 2014-2017 Broadcom */ - +#include <linux/acpi.h> #include <linux/types.h> #include <linux/delay.h> #include <linux/wait.h> @@ -312,7 +312,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) int bcmgenet_mii_probe(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + struct device_node *dn = kdev->of_node; struct phy_device *phydev; u32 phy_flags = 0; int ret; @@ -335,7 +336,27 @@ int bcmgenet_mii_probe(struct net_device *dev) return -ENODEV; } } else { - phydev = dev->phydev; + if (has_acpi_companion(kdev)) { + char mdio_bus_id[MII_BUS_ID_SIZE]; + struct mii_bus *unimacbus; + + snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d", + UNIMAC_MDIO_DRV_NAME, priv->pdev->id); + + unimacbus = mdio_find_bus(mdio_bus_id); + if (!unimacbus) { + pr_err("Unable to find mii\n"); + return -ENODEV; + } + phydev = phy_find_first(unimacbus); + put_device(&unimacbus->dev); + if (!phydev) { + pr_err("Unable to find PHY\n"); + return -ENODEV; + } + } else { + phydev = dev->phydev; + } phydev->dev_flags = phy_flags; ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, @@ -456,9 +477,12 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv) /* Retain this platform_device pointer for later cleanup */ priv->mii_pdev = ppdev; ppdev->dev.parent = &pdev->dev; - ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); - if (pdata) + if (dn) + ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); + else if (pdata) bcmgenet_mii_pdata_init(priv, &ppd); + else + ppd.phy_mask = ~0; ret = platform_device_add_resources(ppdev, &res, 1); if (ret) @@ -478,12 +502,33 @@ out: return ret; } +static int bcmgenet_phy_interface_init(struct bcmgenet_priv *priv) +{ + struct device *kdev = &priv->pdev->dev; + int phy_mode = device_get_phy_mode(kdev); + + if (phy_mode < 0) { + dev_err(kdev, "invalid PHY mode property\n"); + return phy_mode; + } + + priv->phy_interface = phy_mode; + + /* We need to specifically look up whether this PHY interface is + * internal or not *before* we even try to probe the PHY driver + * over MDIO as we may have shut down the internal PHY for power + * saving purposes. + */ + if (priv->phy_interface == PHY_INTERFACE_MODE_INTERNAL) + priv->internal_phy = true; + + return 0; +} + static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) { struct device_node *dn = priv->pdev->dev.of_node; - struct device *kdev = &priv->pdev->dev; struct phy_device *phydev; - phy_interface_t phy_mode; int ret; /* Fetch the PHY phandle */ @@ -501,23 +546,12 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) } /* Get the link mode */ - ret = of_get_phy_mode(dn, &phy_mode); - if (ret) { - dev_err(kdev, "invalid PHY mode property\n"); + ret = bcmgenet_phy_interface_init(priv); + if (ret) return ret; - } - - priv->phy_interface = phy_mode; - - /* We need to specifically look up whether this PHY interface is internal - * or not *before* we even try to probe the PHY driver over MDIO as we - * may have shut down the internal PHY for power saving purposes. - */ - if (priv->phy_interface == PHY_INTERFACE_MODE_INTERNAL) - priv->internal_phy = true; /* Make sure we initialize MoCA PHYs with a link down */ - if (phy_mode == PHY_INTERFACE_MODE_MOCA) { + if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { phydev = of_phy_find_device(dn); if (phydev) { phydev->link = 0; @@ -582,10 +616,13 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) { - struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + struct device_node *dn = kdev->of_node; if (dn) return bcmgenet_mii_of_init(priv); + else if (has_acpi_companion(kdev)) + return bcmgenet_phy_interface_init(priv); else return bcmgenet_mii_pd_init(priv); } diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 01a50a4b2113..d6588502a050 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -2504,12 +2504,7 @@ bnad_tso_prepare(struct bnad *bnad, struct sk_buff *skb) IPPROTO_TCP, 0); BNAD_UPDATE_CTR(bnad, tso4); } else { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); - - ipv6h->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, 0, - IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); BNAD_UPDATE_CTR(bnad, tso6); } diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index a3f0f27fc79a..ab827fb4b6b9 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -1200,7 +1200,6 @@ struct macb { unsigned int dma_burst_length; phy_interface_t phy_interface; - int speed; /* AT91RM9200 transmit */ struct sk_buff *skb; /* holds skb until xmit interrupt completes */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 2c28da1737fe..3a7c26b08607 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -571,37 +571,20 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); - /* Clear all the bits we might set later */ - ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); - if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { if (state->interface == PHY_INTERFACE_MODE_RMII) ctrl |= MACB_BIT(RM9200_RMII); } else { - ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); - - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); + ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); if (state->interface == PHY_INTERFACE_MODE_SGMII) ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); } - if (state->speed == SPEED_1000) - ctrl |= GEM_BIT(GBE); - else if (state->speed == SPEED_100) - ctrl |= MACB_BIT(SPD); - - if (state->duplex) - ctrl |= MACB_BIT(FD); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); - bp->speed = state->speed; - spin_unlock_irqrestore(&bp->lock, flags); } @@ -626,16 +609,42 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, netif_tx_stop_all_queues(ndev); } -static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void macb_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *ndev = to_net_dev(config->dev); struct macb *bp = netdev_priv(ndev); struct macb_queue *queue; + unsigned long flags; unsigned int q; + u32 ctrl; + + spin_lock_irqsave(&bp->lock, flags); + + ctrl = macb_or_gem_readl(bp, NCFGR); + + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD)); + + if (speed == SPEED_100) + ctrl |= MACB_BIT(SPD); + + if (duplex) + ctrl |= MACB_BIT(FD); if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(PAE)); + + if (speed == SPEED_1000) + ctrl |= GEM_BIT(GBE); + + /* We do not support MLO_PAUSE_RX yet */ + if (tx_pause) + ctrl |= MACB_BIT(PAE); + + macb_set_tx_clk(bp->tx_clk, speed, ndev); /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down * cleared the pipeline and control registers. @@ -648,6 +657,10 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } + macb_or_gem_writel(bp, NCFGR, ctrl); + + spin_unlock_irqrestore(&bp->lock, flags); + /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -4429,8 +4442,6 @@ static int macb_probe(struct platform_device *pdev) else bp->phy_interface = interface; - bp->speed = SPEED_UNKNOWN; - /* IP specific init */ err = init(pdev); if (err) diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h index b19e4376ba76..401827b82aa1 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_ioctl.h @@ -79,7 +79,7 @@ struct ch_mem_range { uint32_t addr; uint32_t len; uint32_t version; - uint8_t buf[0]; + uint8_t buf[]; }; struct ch_qset_params { diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h b/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h index 852c399a8b0a..68bb5f39f3f1 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_cpl.h @@ -1448,7 +1448,7 @@ struct cpl_rdma_terminate { #endif __be32 msn; __be32 mo; - __u8 data[0]; + __u8 data[]; }; /* cpl_rdma_terminate.tid_len fields */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h index a0e0ae19649f..290c1058069a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h @@ -29,7 +29,7 @@ struct clip_tbl { atomic_t nfree; struct list_head ce_free_head; void *cl_list; - struct list_head hash_list[0]; + struct list_head hash_list[]; }; enum { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index f5be3ee1bdb4..dcab94cc2dee 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -82,7 +82,7 @@ struct cudbg_ulprx_la { struct cudbg_tp_la { u32 size; u32 mode; - u8 data[0]; + u8 data[]; }; static const char * const cudbg_region[] = { @@ -134,7 +134,7 @@ struct cudbg_meminfo { struct cudbg_cim_pif_la { int size; - u8 data[0]; + u8 data[]; }; struct cudbg_clk_info { @@ -339,13 +339,13 @@ struct cudbg_qdesc_entry { u32 qid; u32 desc_size; u32 num_desc; - u8 data[0]; /* Must be last */ + u8 data[]; /* Must be last */ }; struct cudbg_qdesc_info { u32 qdesc_entry_size; u32 num_queues; - u8 data[0]; /* Must be last */ + u8 data[]; /* Must be last */ }; #define IREG_NUM_ELEM 4 diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index de30d61af065..fe883cb1a7af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -984,7 +984,7 @@ static const char * const devlog_facility_strings[] = { struct devlog_info { unsigned int nentries; /* number of entries in log[] */ unsigned int first; /* first [temporal] entry in log[] */ - struct fw_devlog_e log[0]; /* Firmware Device Log */ + struct fw_devlog_e log[]; /* Firmware Device Log */ }; /* Dump a Firmaware Device Log entry. diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h index ba95e13d52da..1471cf0deb58 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h @@ -49,7 +49,7 @@ struct seq_tab { unsigned int rows; /* # of entries */ unsigned char width; /* size in bytes of each entry */ unsigned char skip_first; /* whether the first line is a header */ - char data[0]; /* the table data */ + char data[]; /* the table data */ }; static inline unsigned int hex2val(char c) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h index a4b99edcc339..125868c6770a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h @@ -289,6 +289,6 @@ struct cxgb4_link { struct cxgb4_tc_u32_table { unsigned int size; /* number of entries in table */ - struct cxgb4_link table[0]; /* Jump table */ + struct cxgb4_link table[]; /* Jump table */ }; #endif /* __CXGB4_TC_U32_PARSE_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 1a16449e9deb..12c3354172cd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -59,7 +59,7 @@ struct l2t_data { rwlock_t lock; atomic_t nfree; /* number of free entries */ struct l2t_entry *rover; /* starting point for next allocation */ - struct l2t_entry l2tab[0]; /* MUST BE LAST */ + struct l2t_entry l2tab[]; /* MUST BE LAST */ }; static inline unsigned int vlan_prio(const struct l2t_entry *e) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.h b/drivers/net/ethernet/chelsio/cxgb4/sched.h index 5cc74a5a1774..5f8b871d79af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.h +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.h @@ -82,7 +82,7 @@ struct sched_class { struct sched_table { /* per port scheduling table */ u8 sched_size; - struct sched_class tab[0]; + struct sched_class tab[]; }; static inline bool can_sched(struct net_device *dev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h index 1268d6e93a47..541249d78914 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.h +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -66,7 +66,7 @@ struct smt_entry { struct smt_data { unsigned int smt_size; rwlock_t lock; - struct smt_entry smtab[0]; + struct smt_entry smtab[]; }; struct smt_data *t4_init_smt(void); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index 575c6abcdae7..7d874f03d6c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -1511,7 +1511,7 @@ struct ulptx_sgl { __be32 cmd_nsge; __be32 len0; __be64 addr0; - struct ulptx_sge_pair sge[0]; + struct ulptx_sge_pair sge[]; }; struct ulptx_idata { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index accad1101ad1..703effc00a05 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -737,7 +737,7 @@ struct fw_flowc_mnemval { struct fw_flowc_wr { __be32 op_to_nparams; __be32 flowid_len16; - struct fw_flowc_mnemval mnemval[0]; + struct fw_flowc_mnemval mnemval[]; }; #define FW_FLOWC_WR_NPARAMS_S 0 diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h index 7b02c200dd1e..1b4156461ba1 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.h @@ -122,7 +122,7 @@ struct cxgbi_ppm_pool { unsigned int base; /* base index */ unsigned int next; /* next possible free index */ spinlock_t lock; /* ppm pool lock */ - unsigned long bmap[0]; + unsigned long bmap[]; } ____cacheline_aligned_in_smp; struct cxgbi_ppm { @@ -145,7 +145,7 @@ struct cxgbi_ppm { unsigned int next; unsigned int max_index_in_edram; unsigned long *ppod_bmap; - struct cxgbi_ppod_data ppod_data[0]; + struct cxgbi_ppod_data ppod_data[]; }; #define DDP_THRESHOLD 512 diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index ddf60dc9ad16..3fc858b2c87b 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -696,8 +696,7 @@ static void enic_preload_tcp_csum(struct sk_buff *skb) tcp_hdr(skb)->check = ~csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); } else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) { - tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); } } diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h index fef5a0a0663d..fcc4a3ccdd94 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h +++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h @@ -541,7 +541,7 @@ struct vnic_devcmd_notify { struct vnic_devcmd_provinfo { u8 oui[3]; u8 type; - u8 data[0]; + u8 data[]; }; /* These are used in flags field of different filters to denote @@ -648,9 +648,9 @@ enum { #define FILTER_MAX_BUF_SIZE 100 struct filter_tlv { - u_int32_t type; - u_int32_t length; - u_int32_t val[0]; + u32 type; + u32 length; + u32 val[]; }; enum { diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.h b/drivers/net/ethernet/cisco/enic/vnic_vic.h index 9ef81f148351..057776908828 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_vic.h +++ b/drivers/net/ethernet/cisco/enic/vnic_vic.h @@ -59,7 +59,7 @@ struct vic_provinfo { u16 type; u16 length; u8 value[0]; - } tlv[0]; + } tlv[]; } __packed; #define VIC_PROVINFO_ADD_TLV(vp, tlvtype, tlvlen, data) \ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 7ff147e89426..b6c46639aa4c 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1704,10 +1704,15 @@ static int dpaa2_eth_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { + struct dpaa2_eth_priv *priv = netdev_priv(dev); + if (cmd == SIOCSHWTSTAMP) return dpaa2_eth_ts_ioctl(dev, rq, cmd); - return -EINVAL; + if (priv->mac) + return phylink_mii_ioctl(priv->mac->phylink, rq, cmd); + + return -EOPNOTSUPP; } static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 96676abcebd5..94347c695233 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -79,6 +79,16 @@ static void dpaa2_eth_get_drvinfo(struct net_device *net_dev, sizeof(drvinfo->bus_info)); } +static int dpaa2_eth_nway_reset(struct net_device *net_dev) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + + if (priv->mac) + return phylink_ethtool_nway_reset(priv->mac->phylink); + + return -EOPNOTSUPP; +} + static int dpaa2_eth_get_link_ksettings(struct net_device *net_dev, struct ethtool_link_ksettings *link_settings) @@ -761,6 +771,7 @@ static int dpaa2_eth_get_ts_info(struct net_device *dev, const struct ethtool_ops dpaa2_ethtool_ops = { .get_drvinfo = dpaa2_eth_get_drvinfo, + .nway_reset = dpaa2_eth_nway_reset, .get_link = ethtool_op_get_link, .get_link_ksettings = dpaa2_eth_get_link_ksettings, .set_link_ksettings = dpaa2_eth_set_link_ksettings, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 84233e467ed1..3ee236c5fc37 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -123,49 +123,60 @@ static void dpaa2_mac_config(struct phylink_config *config, unsigned int mode, struct dpmac_link_state *dpmac_state = &mac->state; int err; - if (state->speed != SPEED_UNKNOWN) - dpmac_state->rate = state->speed; - - if (state->duplex != DUPLEX_UNKNOWN) { - if (!state->duplex) - dpmac_state->options |= DPMAC_LINK_OPT_HALF_DUPLEX; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_HALF_DUPLEX; - } - if (state->an_enabled) dpmac_state->options |= DPMAC_LINK_OPT_AUTONEG; else dpmac_state->options &= ~DPMAC_LINK_OPT_AUTONEG; - if (state->pause & MLO_PAUSE_RX) - dpmac_state->options |= DPMAC_LINK_OPT_PAUSE; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_PAUSE; - - if (!!(state->pause & MLO_PAUSE_RX) ^ !!(state->pause & MLO_PAUSE_TX)) - dpmac_state->options |= DPMAC_LINK_OPT_ASYM_PAUSE; - else - dpmac_state->options &= ~DPMAC_LINK_OPT_ASYM_PAUSE; - err = dpmac_set_link_state(mac->mc_io, 0, mac->mc_dev->mc_handle, dpmac_state); if (err) - netdev_err(mac->net_dev, "dpmac_set_link_state() = %d\n", err); + netdev_err(mac->net_dev, "%s: dpmac_set_link_state() = %d\n", + __func__, err); } -static void dpaa2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void dpaa2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct dpaa2_mac *mac = phylink_to_dpaa2_mac(config); struct dpmac_link_state *dpmac_state = &mac->state; int err; dpmac_state->up = 1; + + if (mac->if_link_type == DPMAC_LINK_TYPE_PHY) { + /* If the DPMAC is configured for PHY mode, we need + * to pass the link parameters to the MC firmware. + */ + dpmac_state->rate = speed; + + if (duplex == DUPLEX_HALF) + dpmac_state->options |= DPMAC_LINK_OPT_HALF_DUPLEX; + else if (duplex == DUPLEX_FULL) + dpmac_state->options &= ~DPMAC_LINK_OPT_HALF_DUPLEX; + + /* This is lossy; the firmware really should take the pause + * enablement status rather than pause/asym pause status. + */ + if (rx_pause) + dpmac_state->options |= DPMAC_LINK_OPT_PAUSE; + else + dpmac_state->options &= ~DPMAC_LINK_OPT_PAUSE; + + if (rx_pause ^ tx_pause) + dpmac_state->options |= DPMAC_LINK_OPT_ASYM_PAUSE; + else + dpmac_state->options &= ~DPMAC_LINK_OPT_ASYM_PAUSE; + } + err = dpmac_set_link_state(mac->mc_io, 0, mac->mc_dev->mc_handle, dpmac_state); if (err) - netdev_err(mac->net_dev, "dpmac_set_link_state() = %d\n", err); + netdev_err(mac->net_dev, "%s: dpmac_set_link_state() = %d\n", + __func__, err); } static void dpaa2_mac_link_down(struct phylink_config *config, @@ -238,6 +249,8 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) goto err_close_dpmac; } + mac->if_link_type = attr.link_type; + dpmac_node = dpaa2_mac_get_node(attr.id); if (!dpmac_node) { netdev_err(net_dev, "No dpmac@%d node found.\n", attr.id); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index 4da8079b9155..2130d9c7d40e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -20,6 +20,7 @@ struct dpaa2_mac { struct phylink_config phylink_config; struct phylink *phylink; phy_interface_t if_mode; + enum dpmac_link_type if_link_type; }; bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev, diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index fe942de19597..f86283411f4d 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config FSL_ENETC tristate "ENETC PF driver" - depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI && PCI_MSI select FSL_ENETC_MDIO select PHYLIB help @@ -13,7 +13,7 @@ config FSL_ENETC config FSL_ENETC_VF tristate "ENETC VF driver" - depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI && PCI_MSI select PHYLIB help This driver supports NXP ENETC gigabit ethernet controller PCIe @@ -23,7 +23,7 @@ config FSL_ENETC_VF config FSL_ENETC_MDIO tristate "ENETC MDIO driver" - depends on PCI && (ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI help This driver supports NXP ENETC Central MDIO controller as a PCIe physical function (PF) device. diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index dd4a227ffc7a..9938f7a5fc0a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -163,7 +163,7 @@ struct enetc_int_vector { char name[ENETC_INT_NAME_MAX]; struct enetc_bdr rx_ring ____cacheline_aligned_in_smp; - struct enetc_bdr tx_ring[0]; + struct enetc_bdr tx_ring[]; }; struct enetc_cls_rule { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 62554f28ce07..da134e211c1a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -588,7 +588,7 @@ struct tgs_gcl_data { __le32 bth; __le32 ct; __le32 cte; - struct gce entry[0]; + struct gce entry[]; }; struct enetc_cbd { diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index f79e57f735b3..bd898f5b4da5 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -584,7 +584,7 @@ struct fec_enet_private { int pps_enable; unsigned int next_counter; - u64 ethtool_stats[0]; + u64 ethtool_stats[]; }; void fec_ptp_init(struct platform_device *pdev, int irq_idx); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4432a59904c7..12edd4e358f8 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3793,6 +3793,7 @@ static struct platform_driver fec_driver = { .name = DRIVER_NAME, .pm = &fec_pm_ops, .of_match_table = fec_dt_ids, + .suppress_bind_attrs = true, }, .id_table = fec_devtype, .probe = fec_probe, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index 2721f1f1ab42..0f0e16f9afc0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -92,7 +92,7 @@ struct ppe_common_cb { u8 comm_index; /*ppe_common index*/ u32 ppe_num; - struct hns_ppe_cb ppe_cb[0]; + struct hns_ppe_cb ppe_cb[]; }; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 3741befb914e..a9f805925699 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -108,7 +108,7 @@ struct rcb_common_cb { u32 ring_num; u32 desc_num; /* desc num per queue*/ - struct ring_pair_cb ring_pair_cb[0]; + struct ring_pair_cb ring_pair_cb[]; }; int hns_rcb_buf_size2type(u32 buf_size); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 1d4ffc5f408a..e1d88095a77e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -260,6 +260,8 @@ static void hns3_dbg_help(struct hnae3_handle *h) dev_info(&h->pdev->dev, "dump m7 info\n"); dev_info(&h->pdev->dev, "dump ncl_config <offset> <length>(in hex)\n"); dev_info(&h->pdev->dev, "dump mac tnl status\n"); + dev_info(&h->pdev->dev, "dump loopback\n"); + dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n"); memset(printf_buf, 0, HNS3_DBG_BUF_LEN); strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c03856e63320..3f59a1924390 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -736,7 +736,7 @@ static int hns3_check_ksettings_param(const struct net_device *netdev, if (ops->get_media_type) ops->get_media_type(handle, &media_type, &module_type); - if (cmd->base.duplex != DUPLEX_FULL && + if (cmd->base.duplex == DUPLEX_HALF && media_type != HNAE3_MEDIA_TYPE_COPPER) { netdev_err(netdev, "only copper port supports half duplex!"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 67fad80035d3..6295cf93c350 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -310,8 +310,9 @@ static void hclge_title_idx_print(struct hclge_dev *hdev, bool flag, int index, char *false_buf) { if (flag) - dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index, - true_buf); + dev_info(&hdev->pdev->dev, "%s(%d): %s weight: %u\n", + title_buf, index, true_buf, + hdev->tm_info.pg_info[0].tc_dwrr[index]); else dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index, false_buf); @@ -339,7 +340,8 @@ static void hclge_dbg_dump_tc(struct hclge_dev *hdev) ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "dump tc\n"); + dev_info(&hdev->pdev->dev, "dump tc: %u tc enabled\n", + hdev->tm_info.num_tc); dev_info(&hdev->pdev->dev, "weight_offset: %u\n", ets_weight->weight_offset); @@ -1169,6 +1171,57 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, } } +static void hclge_dbg_dump_loopback(struct hclge_dev *hdev, + const char *cmd_buf) +{ + struct phy_device *phydev = hdev->hw.mac.phydev; + struct hclge_config_mac_mode_cmd *req_app; + struct hclge_serdes_lb_cmd *req_serdes; + struct hclge_desc desc; + u8 loopback_en; + int ret; + + req_app = (struct hclge_config_mac_mode_cmd *)desc.data; + req_serdes = (struct hclge_serdes_lb_cmd *)desc.data; + + dev_info(&hdev->pdev->dev, "mac id: %u\n", hdev->hw.mac.mac_id); + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump app loopback status, ret = %d\n", ret); + return; + } + + loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en), + HCLGE_MAC_APP_LP_B); + dev_info(&hdev->pdev->dev, "app loopback: %s\n", + loopback_en ? "on" : "off"); + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump serdes loopback status, ret = %d\n", + ret); + return; + } + + loopback_en = req_serdes->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; + dev_info(&hdev->pdev->dev, "serdes serial loopback: %s\n", + loopback_en ? "on" : "off"); + + loopback_en = req_serdes->enable & + HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B; + dev_info(&hdev->pdev->dev, "serdes parallel loopback: %s\n", + loopback_en ? "on" : "off"); + + if (phydev) + dev_info(&hdev->pdev->dev, "phy loopback: %s\n", + phydev->loopback_enabled ? "on" : "off"); +} + /* hclge_dbg_dump_mac_tnl_status: print message about mac tnl interrupt * @hdev: pointer to struct hclge_dev */ @@ -1269,6 +1322,7 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) { #define DUMP_REG "dump reg" #define DUMP_TM_MAP "dump tm map" +#define DUMP_LOOPBACK "dump loopback" struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -1302,6 +1356,9 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) &cmd_buf[sizeof("dump ncl_config")]); } else if (strncmp(cmd_buf, "dump mac tnl status", 19) == 0) { hclge_dbg_dump_mac_tnl_status(hdev); + } else if (strncmp(cmd_buf, DUMP_LOOPBACK, + strlen(DUMP_LOOPBACK)) == 0) { + hclge_dbg_dump_loopback(hdev, &cmd_buf[sizeof(DUMP_LOOPBACK)]); } else if (strncmp(cmd_buf, "dump qs shaper", 14) == 0) { hclge_dbg_dump_qs_shaper(hdev, &cmd_buf[sizeof("dump qs shaper")]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 492bc9446463..89d352385260 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -824,6 +824,8 @@ static void hclge_get_mac_stat(struct hnae3_handle *handle, static int hclge_parse_func_status(struct hclge_dev *hdev, struct hclge_func_status_cmd *status) { +#define HCLGE_MAC_ID_MASK 0xF + if (!(status->pf_state & HCLGE_PF_STATE_DONE)) return -EINVAL; @@ -833,6 +835,7 @@ static int hclge_parse_func_status(struct hclge_dev *hdev, else hdev->flag &= ~HCLGE_FLAG_MAIN; + hdev->hw.mac.mac_id = status->mac_id & HCLGE_MAC_ID_MASK; return 0; } @@ -9073,8 +9076,8 @@ init_nic_err: static int hclge_init_roce_client_instance(struct hnae3_ae_dev *ae_dev, struct hclge_vport *vport) { - struct hnae3_client *client = vport->roce.client; struct hclge_dev *hdev = ae_dev->priv; + struct hnae3_client *client; int rst_cnt; int ret; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index f78cbb4cc85e..71df23d5f1b4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -249,6 +249,7 @@ enum HCLGE_MAC_DUPLEX { #define QUERY_ACTIVE_SPEED 1 struct hclge_mac { + u8 mac_id; u8 phy_addr; u8 flag; u8 media_type; /* port media type, e.g. fibre/copper/backplane */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 2bced34c19ba..f7103356ef56 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2715,11 +2715,7 @@ static int e1000_tso(struct e1000_adapter *adapter, cmd_length = E1000_TXD_CMD_IP; ipcse = skb_transport_offset(skb) - 1; } else if (skb_is_gso_v6(skb)) { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); ipcse = 0; } ipcss = skb_network_offset(skb); diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index adce7e319b9e..9e7881db7859 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -897,6 +897,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) case e1000_pch_cnp: /* fall through */ case e1000_pch_tgp: + case e1000_pch_adp: mask |= BIT(18); break; default: @@ -1561,6 +1562,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: fext_nvm11 = er32(FEXTNVM11); fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index f556163481cb..b1447221669e 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -97,6 +97,11 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_TGP_I219_LM14 0x15F9 #define E1000_DEV_ID_PCH_TGP_I219_V14 0x15FA #define E1000_DEV_ID_PCH_TGP_I219_LM15 0x15F4 +#define E1000_DEV_ID_PCH_TGP_I219_V15 0x15F5 +#define E1000_DEV_ID_PCH_ADP_I219_LM16 0x1A1E +#define E1000_DEV_ID_PCH_ADP_I219_V16 0x1A1F +#define E1000_DEV_ID_PCH_ADP_I219_LM17 0x1A1C +#define E1000_DEV_ID_PCH_ADP_I219_V17 0x1A1D #define E1000_REVISION_4 4 @@ -121,6 +126,7 @@ enum e1000_mac_type { e1000_pch_spt, e1000_pch_cnp, e1000_pch_tgp, + e1000_pch_adp, }; enum e1000_media_type { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index b4135c50e905..735bf25952fc 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -317,6 +317,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -460,6 +461,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: /* In case the PHY needs to be in mdio slow mode, * set slow mode and try to get the PHY id again. */ @@ -703,6 +705,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: case e1000_pchlan: /* check management mode */ mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan; @@ -1642,6 +1645,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: rc = e1000_init_phy_params_pchlan(hw); break; default: @@ -2095,6 +2099,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M; break; default: @@ -3133,6 +3138,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: bank1_offset = nvm->flash_bank_size; act_offset = E1000_ICH_NVM_SIG_WORD; @@ -4077,6 +4083,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) case e1000_pch_spt: case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: word = NVM_COMPAT; valid_csum_mask = NVM_COMPAT_VALID_CSUM; break; diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index e531976f8a67..51512a73fdd0 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -1363,7 +1363,7 @@ s32 e1000e_get_hw_semaphore(struct e1000_hw *hw) if (!(swsm & E1000_SWSM_SMBI)) break; - usleep_range(50, 100); + udelay(100); i++; } @@ -1381,7 +1381,7 @@ s32 e1000e_get_hw_semaphore(struct e1000_hw *hw) if (er32(SWSM) & E1000_SWSM_SWESMBI) break; - usleep_range(50, 100); + udelay(100); } if (i == timeout) { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index db4ea58bac82..1e1625122596 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3536,6 +3536,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) break; case e1000_pch_cnp: case e1000_pch_tgp: + case e1000_pch_adp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ incperiod = INCPERIOD_24MHZ; @@ -3807,7 +3808,7 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter) tdt = er32(TDT(0)); BUG_ON(tdt != tx_ring->next_to_use); tx_desc = E1000_TX_DESC(*tx_ring, tx_ring->next_to_use); - tx_desc->buffer_addr = tx_ring->dma; + tx_desc->buffer_addr = cpu_to_le64(tx_ring->dma); tx_desc->lower.data = cpu_to_le32(txd_lower | size); tx_desc->upper.data = 0; @@ -4049,6 +4050,7 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch_cnp: /* fall-through */ case e1000_pch_tgp: + case e1000_pch_adp: fc->refresh_time = 0xFFFF; fc->pause_time = 0xFFFF; @@ -5462,10 +5464,7 @@ static int e1000_tso(struct e1000_ring *tx_ring, struct sk_buff *skb, cmd_length = E1000_TXD_CMD_IP; ipcse = skb_transport_offset(skb) - 1; } else if (skb_is_gso_v6(skb)) { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); ipcse = 0; } ipcss = skb_network_offset(skb); @@ -7760,6 +7759,11 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_cnp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_cnp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_cnp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index eaa5a0fb99f0..439fda2f5368 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -297,6 +297,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_cnp: /* fall-through */ case e1000_pch_tgp: + case e1000_pch_adp: if ((hw->mac.type < e1000_pch_lpt) || (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { adapter->ptp_clock_info.max_adj = 24000000 - 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index f306084ca12c..5b78362b82ac 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -41,7 +41,7 @@ struct fm10k_l2_accel { u16 count; u16 dglort; struct rcu_head rcu; - struct net_device *macvlan[0]; + struct net_device *macvlan[]; }; enum fm10k_ring_state_t { @@ -198,7 +198,7 @@ struct fm10k_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ /* for dynamic allocation of rings associated with this q_vector */ - struct fm10k_ring ring[0] ____cacheline_internodealigned_in_smp; + struct fm10k_ring ring[] ____cacheline_internodealigned_in_smp; }; enum fm10k_ring_f_enum { @@ -218,7 +218,7 @@ struct fm10k_iov_data { unsigned int num_vfs; unsigned int next_vf_mbx; struct rcu_head rcu; - struct fm10k_vf_info vf_info[0]; + struct fm10k_vf_info vf_info[]; }; struct fm10k_udp_port { diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 4833187bd259..e95b8da45e07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -334,13 +334,13 @@ int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash); struct i40e_ddp_profile_list { u32 p_count; - struct i40e_profile_info p_info[0]; + struct i40e_profile_info p_info[]; }; struct i40e_ddp_old_profile_list { struct list_head list; size_t old_ddp_size; - u8 old_ddp_buf[0]; + u8 old_ddp_buf[]; }; /* macros related to FLX_PIT */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 62fe56ddcb6e..76361bd468db 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3061,9 +3061,6 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, struct flow_cls_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { case FLOW_CLS_REPLACE: return iavf_configure_clsflower(adapter, cls_flower); @@ -3087,6 +3084,11 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + struct iavf_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index cb10abb14e11..2d51ceaa2c8c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -212,6 +212,7 @@ enum ice_state { __ICE_SERVICE_SCHED, __ICE_SERVICE_DIS, __ICE_OICR_INTR_DIS, /* Global OICR interrupt disabled */ + __ICE_MDD_VF_PRINT_PENDING, /* set when MDD event handle */ __ICE_STATE_NBITS /* must be last */ }; @@ -340,6 +341,7 @@ enum ice_pf_flags { ICE_FLAG_FW_LLDP_AGENT, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ ICE_FLAG_LEGACY_RX, + ICE_FLAG_MDD_AUTO_RESET_VF, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -363,6 +365,8 @@ struct ice_pf { u16 num_vfs_supported; /* num VFs supported for this PF */ u16 num_vf_qps; /* num queue pairs per VF */ u16 num_vf_msix; /* num vectors per VF */ + /* used to ratelimit the MDD event logging */ + unsigned long last_printed_mdd_jiffies; DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS); unsigned long *avail_txqs; /* bitmap to track PF Tx queue usage */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 6873998cf145..38b6ffb6ad2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1661,6 +1661,13 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[1]; }; +/* Lan Queue Overflow Event (direct, 0x1001) */ +struct ice_aqc_event_lan_overflow { + __le32 prtdcb_ruptq; + __le32 qtx_ctl; + u8 reserved[8]; +}; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -1730,6 +1737,7 @@ struct ice_aq_desc { struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; struct ice_aqc_get_link_status get_link_status; + struct ice_aqc_event_lan_overflow lan_overflow; } params; }; @@ -1860,6 +1868,9 @@ enum ice_adminq_opc { ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, + /* Standalone Commands/Events */ + ice_aqc_opc_event_lan_overflow = 0x1001, + /* debug commands */ ice_aqc_opc_fw_logging = 0xFF09, ice_aqc_opc_fw_logging_info = 0xFF10, diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 81885efadc7a..a19cd6f5436b 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -203,8 +203,7 @@ static void ice_cfg_itr_gran(struct ice_hw *hw) */ static u16 ice_calc_q_handle(struct ice_vsi *vsi, struct ice_ring *ring, u8 tc) { - WARN_ONCE(ice_ring_is_xdp(ring) && tc, - "XDP ring can't belong to TC other than 0"); + WARN_ONCE(ice_ring_is_xdp(ring) && tc, "XDP ring can't belong to TC other than 0\n"); /* Idea here for calculation is that we subtract the number of queue * count from TC that ring belongs to from it's absolute queue index @@ -247,7 +246,6 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) */ switch (vsi->type) { case ICE_VSI_LB: - /* fall through */ case ICE_VSI_PF: tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_PF; break; @@ -387,8 +385,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring) /* Enable Flexible Descriptors in the queue context which * allows this driver to select a specific receive descriptor format */ + regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); if (vsi->type != ICE_VSI_VF) { - regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); regval |= (rxdid << QRXFLXP_CNTXT_RXDID_IDX_S) & QRXFLXP_CNTXT_RXDID_IDX_M; @@ -399,8 +397,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring) regval |= (0x03 << QRXFLXP_CNTXT_RXDID_PRIO_S) & QRXFLXP_CNTXT_RXDID_PRIO_M; - wr32(hw, QRXFLXP_CNTXT(pf_q), regval); + } else { + regval &= ~(QRXFLXP_CNTXT_RXDID_IDX_M | + QRXFLXP_CNTXT_RXDID_PRIO_M | + QRXFLXP_CNTXT_TS_M); } + wr32(hw, QRXFLXP_CNTXT(pf_q), regval); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); @@ -459,17 +461,20 @@ int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg) } /** - * ice_vsi_ctrl_rx_ring - Start or stop a VSI's Rx ring + * ice_vsi_ctrl_one_rx_ring - start/stop VSI's Rx ring with no busy wait * @vsi: the VSI being configured - * @ena: start or stop the Rx rings - * @rxq_idx: Rx queue index + * @ena: start or stop the Rx ring + * @rxq_idx: 0-based Rx queue index for the VSI passed in + * @wait: wait or don't wait for configuration to finish in hardware + * + * Return 0 on success and negative on error. */ -int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) +int +ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait) { int pf_q = vsi->rxq_map[rxq_idx]; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - int ret = 0; u32 rx_reg; rx_reg = rd32(hw, QRX_CTRL(pf_q)); @@ -485,13 +490,30 @@ int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) rx_reg &= ~QRX_CTRL_QENA_REQ_M; wr32(hw, QRX_CTRL(pf_q), rx_reg); - /* wait for the change to finish */ - ret = ice_pf_rxq_wait(pf, pf_q, ena); - if (ret) - dev_err(ice_pf_to_dev(pf), "VSI idx %d Rx ring %d %sable timeout\n", - vsi->idx, pf_q, (ena ? "en" : "dis")); + if (!wait) + return 0; + + ice_flush(hw); + return ice_pf_rxq_wait(pf, pf_q, ena); +} - return ret; +/** + * ice_vsi_wait_one_rx_ring - wait for a VSI's Rx ring to be stopped/started + * @vsi: the VSI being configured + * @ena: true/false to verify Rx ring has been enabled/disabled respectively + * @rxq_idx: 0-based Rx queue index for the VSI passed in + * + * This routine will wait for the given Rx queue of the VSI to reach the + * enabled or disabled state. Returns -ETIMEDOUT in case of failing to reach + * the requested state after multiple retries; else will return 0 in case of + * success. + */ +int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) +{ + int pf_q = vsi->rxq_map[rxq_idx]; + struct ice_pf *pf = vsi->back; + + return ice_pf_rxq_wait(pf, pf_q, ena); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index 407995e8e944..44efdb627043 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -8,7 +8,9 @@ int ice_setup_rx_ctx(struct ice_ring *ring); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); -int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx); +int +ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); +int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx); int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi); void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi); void ice_vsi_free_q_vectors(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 04d5db0a25bf..1fe54f08f162 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -6,7 +6,7 @@ #include "ice_adminq_cmd.h" #include "ice_flow.h" -#define ICE_PF_RESET_WAIT_COUNT 200 +#define ICE_PF_RESET_WAIT_COUNT 300 /** * ice_set_mac_type - Sets MAC type @@ -1181,7 +1181,7 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, case ice_aqc_opc_release_res: if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK) break; - /* fall-through */ + fallthrough; default: mutex_lock(&ice_global_cfg_lock_sw); lock_acquired = true; @@ -2703,7 +2703,7 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; break; } - /* fall-through */ + fallthrough; default: status = ICE_ERR_PARAM; goto ice_aq_get_set_rss_lut_exit; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 7108fb41b604..16656b6c3d09 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -63,6 +63,26 @@ u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg) } /** + * ice_dcb_get_mode - gets the DCB mode + * @port_info: pointer to port info structure + * @host: if set it's HOST if not it's MANAGED + */ +static u8 ice_dcb_get_mode(struct ice_port_info *port_info, bool host) +{ + u8 mode; + + if (host) + mode = DCB_CAP_DCBX_HOST; + else + mode = DCB_CAP_DCBX_LLD_MANAGED; + + if (port_info->local_dcbx_cfg.dcbx_mode & ICE_DCBX_MODE_CEE) + return (mode | DCB_CAP_DCBX_VER_CEE); + else + return (mode | DCB_CAP_DCBX_VER_IEEE); +} + +/** * ice_dcb_get_num_tc - Get the number of TCs from DCBX config * @dcbcfg: config to retrieve number of TCs from */ @@ -149,6 +169,43 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) } /** + * ice_dcb_bwchk - check if ETS bandwidth input parameters are correct + * @pf: pointer to the PF struct + * @dcbcfg: pointer to DCB config structure + */ +int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg) +{ + struct ice_dcb_ets_cfg *etscfg = &dcbcfg->etscfg; + u8 num_tc, total_bw = 0; + int i; + + /* returns number of contigous TCs and 1 TC for non-contigous TCs, + * since at least 1 TC has to be configured + */ + num_tc = ice_dcb_get_num_tc(dcbcfg); + + /* no bandwidth checks required if there's only one TC, so assign + * all bandwidth to TC0 and return + */ + if (num_tc == 1) { + etscfg->tcbwtable[0] = ICE_TC_MAX_BW; + return 0; + } + + for (i = 0; i < num_tc; i++) + total_bw += etscfg->tcbwtable[i]; + + if (!total_bw) { + etscfg->tcbwtable[0] = ICE_TC_MAX_BW; + } else if (total_bw != ICE_TC_MAX_BW) { + dev_err(ice_pf_to_dev(pf), "Invalid config, total bandwidth must equal 100\n"); + return -EINVAL; + } + + return 0; +} + +/** * ice_pf_dcb_cfg - Apply new DCB configuration * @pf: pointer to the PF struct * @new_cfg: DCBX config to apply @@ -182,6 +239,9 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) return ret; } + if (ice_dcb_bwchk(pf, new_cfg)) + return -EINVAL; + /* Store old config in case FW config fails */ old_cfg = kmemdup(curr_cfg, sizeof(*old_cfg), GFP_KERNEL); if (!old_cfg) @@ -605,14 +665,14 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) ice_cfg_sw_lldp(pf_vsi, false, true); - pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; + pf->dcbx_cap = ice_dcb_get_mode(port_info, true); return 0; } set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); - /* DCBX in FW and LLDP enabled in FW */ - pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_IEEE; + /* DCBX/LLDP enabled in FW, set DCBNL mode advertisement */ + pf->dcbx_cap = ice_dcb_get_mode(port_info, false); err = ice_dcb_init_cfg(pf, locked); if (err) @@ -772,6 +832,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, /* No change detected in DCBX configs */ if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) { dev_dbg(dev, "No change detected in DCBX configuration.\n"); + pf->dcbx_cap = ice_dcb_get_mode(pi, false); goto out; } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index f15e5776f287..37680e815b02 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -20,6 +20,7 @@ u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg); u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index); int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked); +int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg); void ice_pf_dcb_recfg(struct ice_pf *pf); void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index b61aba428adb..c4c12414083a 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -95,14 +95,12 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) new_cfg->etsrec.prio_table[i] = ets->reco_prio_tc[i]; } - /* max_tc is a 1-8 value count of number of TC's, not a 0-7 value - * for the TC's index number. Add one to value if not zero, and - * for zero set it to the FW's default value - */ - if (max_tc) - max_tc++; - else - max_tc = IEEE_8021QAZ_MAX_TCS; + if (ice_dcb_bwchk(pf, new_cfg)) { + err = -EINVAL; + goto ets_out; + } + + max_tc = pf->hw.func_caps.common_cap.maxtc; new_cfg->etscfg.maxtcs = max_tc; @@ -119,6 +117,7 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) if (err == ICE_DCB_NO_HW_CHG) err = ICE_DCB_HW_CHG_RST; +ets_out: mutex_unlock(&pf->tc_mutex); return err; } @@ -535,6 +534,30 @@ ice_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int prio, } /** + * ice_dcbnl_set_pg_tc_cfg_rx + * @netdev: relevant netdev struct + * @prio: corresponding user priority + * @prio_type: the traffic priority type + * @pgid: the PG ID + * @bw_pct: BW percentage for corresponding BWG + * @up_map: prio mapped to corresponding TC + * + * lldpad requires this function pointer to be non-NULL to complete CEE config. + */ +static void +ice_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, + int __always_unused prio, + u8 __always_unused prio_type, + u8 __always_unused pgid, + u8 __always_unused bw_pct, + u8 __always_unused up_map) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + + dev_dbg(ice_pf_to_dev(pf), "Rx TC PG Config Not Supported.\n"); +} + +/** * ice_dcbnl_get_pg_bwg_cfg_rx - Get CEE PG BW Rx config * @netdev: pointer to netdev struct * @pgid: the corresponding traffic class @@ -554,6 +577,23 @@ ice_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int __always_unused pgid, } /** + * ice_dcbnl_set_pg_bwg_cfg_rx + * @netdev: the corresponding netdev + * @pgid: corresponding TC + * @bw_pct: BW percentage for given TC + * + * lldpad requires this function pointer to be non-NULL to complete CEE config. + */ +static void +ice_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int __always_unused pgid, + u8 __always_unused bw_pct) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + + dev_dbg(ice_pf_to_dev(pf), "Rx BWG PG Config Not Supported.\n"); +} + +/** * ice_dcbnl_get_cap - Get DCBX capabilities of adapter * @netdev: pointer to netdev struct * @capid: the capability type @@ -799,6 +839,8 @@ static const struct dcbnl_rtnl_ops dcbnl_ops = { .getpermhwaddr = ice_dcbnl_get_perm_hw_addr, .setpgtccfgtx = ice_dcbnl_set_pg_tc_cfg_tx, .setpgbwgcfgtx = ice_dcbnl_set_pg_bwg_cfg_tx, + .setpgtccfgrx = ice_dcbnl_set_pg_tc_cfg_rx, + .setpgbwgcfgrx = ice_dcbnl_set_pg_bwg_cfg_rx, .getpgtccfgtx = ice_dcbnl_get_pg_tc_cfg_tx, .getpgbwgcfgtx = ice_dcbnl_get_pg_bwg_cfg_tx, .getpgtccfgrx = ice_dcbnl_get_pg_tc_cfg_rx, diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index ce63017c56c7..9d8194671f6a 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -5,12 +5,34 @@ #define _ICE_DEVIDS_H_ /* Device IDs */ +/* Intel(R) Ethernet Connection E823-L for backplane */ +#define ICE_DEV_ID_E823L_BACKPLANE 0x124C +/* Intel(R) Ethernet Connection E823-L for SFP */ +#define ICE_DEV_ID_E823L_SFP 0x124D +/* Intel(R) Ethernet Connection E823-L/X557-AT 10GBASE-T */ +#define ICE_DEV_ID_E823L_10G_BASE_T 0x124E +/* Intel(R) Ethernet Connection E823-L 1GbE */ +#define ICE_DEV_ID_E823L_1GBE 0x124F +/* Intel(R) Ethernet Connection E823-L for QSFP */ +#define ICE_DEV_ID_E823L_QSFP 0x151D /* Intel(R) Ethernet Controller E810-C for backplane */ #define ICE_DEV_ID_E810C_BACKPLANE 0x1591 /* Intel(R) Ethernet Controller E810-C for QSFP */ #define ICE_DEV_ID_E810C_QSFP 0x1592 /* Intel(R) Ethernet Controller E810-C for SFP */ #define ICE_DEV_ID_E810C_SFP 0x1593 +/* Intel(R) Ethernet Controller E810-XXV for SFP */ +#define ICE_DEV_ID_E810_XXV_SFP 0x159B +/* Intel(R) Ethernet Connection E823-C for backplane */ +#define ICE_DEV_ID_E823C_BACKPLANE 0x188A +/* Intel(R) Ethernet Connection E823-C for QSFP */ +#define ICE_DEV_ID_E823C_QSFP 0x188B +/* Intel(R) Ethernet Connection E823-C for SFP */ +#define ICE_DEV_ID_E823C_SFP 0x188C +/* Intel(R) Ethernet Connection E823-C/X557-AT 10GBASE-T */ +#define ICE_DEV_ID_E823C_10G_BASE_T 0x188D +/* Intel(R) Ethernet Connection E823-C 1GbE */ +#define ICE_DEV_ID_E823C_SGMII 0x188E /* Intel(R) Ethernet Connection E822-C for backplane */ #define ICE_DEV_ID_E822C_BACKPLANE 0x1890 /* Intel(R) Ethernet Connection E822-C for QSFP */ @@ -21,8 +43,8 @@ #define ICE_DEV_ID_E822C_10G_BASE_T 0x1893 /* Intel(R) Ethernet Connection E822-C 1GbE */ #define ICE_DEV_ID_E822C_SGMII 0x1894 -/* Intel(R) Ethernet Connection E822-X for backplane */ -#define ICE_DEV_ID_E822X_BACKPLANE 0x1897 +/* Intel(R) Ethernet Connection E822-L for backplane */ +#define ICE_DEV_ID_E822L_BACKPLANE 0x1897 /* Intel(R) Ethernet Connection E822-L for SFP */ #define ICE_DEV_ID_E822L_SFP 0x1898 /* Intel(R) Ethernet Connection E822-L/X557-AT 10GBASE-T */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 77c412a7e7a4..ab37dddb225b 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -157,6 +157,7 @@ struct ice_priv_flag { static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA), ICE_PRIV_FLAG("fw-lldp-agent", ICE_FLAG_FW_LLDP_AGENT), + ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF), ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX), }; @@ -462,7 +463,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi) if (status) goto err_setup_rx_ring; - status = ice_vsi_start_rx_rings(vsi); + status = ice_vsi_start_all_rx_rings(vsi); if (status) goto err_start_rx_ring; @@ -494,7 +495,7 @@ static int ice_lbtest_disable_rings(struct ice_vsi *vsi) netdev_err(vsi->netdev, "Failed to stop Tx rings, VSI %d error %d\n", vsi->vsi_num, status); - status = ice_vsi_stop_rx_rings(vsi); + status = ice_vsi_stop_all_rx_rings(vsi); if (status) netdev_err(vsi->netdev, "Failed to stop Rx rings, VSI %d error %d\n", vsi->vsi_num, status); @@ -672,7 +673,7 @@ static u64 ice_loopback_test(struct net_device *netdev) test_vsi = ice_lb_vsi_setup(pf, pf->hw.port_info); if (!test_vsi) { - netdev_err(netdev, "Failed to create a VSI for the loopback test"); + netdev_err(netdev, "Failed to create a VSI for the loopback test\n"); return 1; } @@ -731,7 +732,7 @@ lbtest_free_frame: devm_kfree(dev, tx_frame); remove_mac_filters: if (ice_remove_mac(&pf->hw, &tmp_list)) - netdev_err(netdev, "Could not remove MAC filter for the test VSI"); + netdev_err(netdev, "Could not remove MAC filter for the test VSI\n"); free_mac_list: ice_free_fltr_list(dev, &tmp_list); lbtest_mac_dis: @@ -744,7 +745,7 @@ lbtest_rings_dis: lbtest_vsi_close: test_vsi->netdev = NULL; if (ice_vsi_release(test_vsi)) - netdev_err(netdev, "Failed to remove the test VSI"); + netdev_err(netdev, "Failed to remove the test VSI\n"); return ret; } @@ -834,7 +835,7 @@ ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, int status = ice_open(netdev); if (status) { - dev_err(dev, "Could not open device %s, err %d", + dev_err(dev, "Could not open device %s, err %d\n", pf->int_name, status); } } @@ -1091,7 +1092,6 @@ ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) fecparam->active_fec = ETHTOOL_FEC_BASER; break; case ICE_AQ_LINK_25G_RS_528_FEC_EN: - /* fall through */ case ICE_AQ_LINK_25G_RS_544_FEC_EN: fecparam->active_fec = ETHTOOL_FEC_RS; break; @@ -1781,7 +1781,6 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, Asym_Pause); break; case ICE_FC_PFC: - /* fall through */ default: ethtool_link_ksettings_del_link_mode(ks, lp_advertising, Pause); ethtool_link_ksettings_del_link_mode(ks, lp_advertising, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 99208946224c..42bac3ec5526 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -3471,6 +3471,24 @@ ice_move_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig, } /** + * ice_rem_chg_tcam_ent - remove a specific TCAM entry from change list + * @hw: pointer to the HW struct + * @idx: the index of the TCAM entry to remove + * @chg: the list of change structures to search + */ +static void +ice_rem_chg_tcam_ent(struct ice_hw *hw, u16 idx, struct list_head *chg) +{ + struct ice_chs_chg *pos, *tmp; + + list_for_each_entry_safe(tmp, pos, chg, list_entry) + if (tmp->type == ICE_TCAM_ADD && tmp->tcam_idx == idx) { + list_del(&tmp->list_entry); + devm_kfree(ice_hw_to_dev(hw), tmp); + } +} + +/** * ice_prof_tcam_ena_dis - add enable or disable TCAM change * @hw: pointer to the HW struct * @blk: hardware block @@ -3489,14 +3507,19 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, enum ice_status status; struct ice_chs_chg *p; - /* Default: enable means change the low flag bit to don't care */ - u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 }; + u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; + u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0x00, 0x00, 0x00 }; u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x00, 0x00, 0x00, 0x00, 0x00 }; - u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 }; /* if disabling, free the TCAM */ if (!enable) { - status = ice_free_tcam_ent(hw, blk, tcam->tcam_idx); + status = ice_rel_tcam_idx(hw, blk, tcam->tcam_idx); + + /* if we have already created a change for this TCAM entry, then + * we need to remove that entry, in order to prevent writing to + * a TCAM entry we no longer will have ownership of. + */ + ice_rem_chg_tcam_ent(hw, tcam->tcam_idx, chg); tcam->tcam_idx = 0; tcam->in_use = 0; return status; @@ -3612,11 +3635,12 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, * @blk: hardware block * @vsig: the VSIG to which this profile is to be added * @hdl: the profile handle indicating the profile to add + * @rev: true to add entries to the end of the list * @chg: the change list */ static enum ice_status ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, - struct list_head *chg) + bool rev, struct list_head *chg) { /* Masks that ignore flags */ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; @@ -3625,7 +3649,7 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, struct ice_prof_map *map; struct ice_vsig_prof *t; struct ice_chs_chg *p; - u16 i; + u16 vsig_idx, i; /* Get the details on the profile specified by the handle ID */ map = ice_search_prof_id(hw, blk, hdl); @@ -3687,8 +3711,13 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, } /* add profile to VSIG */ - list_add(&t->list, - &hw->blk[blk].xlt2.vsig_tbl[(vsig & ICE_VSIG_IDX_M)].prop_lst); + vsig_idx = vsig & ICE_VSIG_IDX_M; + if (rev) + list_add_tail(&t->list, + &hw->blk[blk].xlt2.vsig_tbl[vsig_idx].prop_lst); + else + list_add(&t->list, + &hw->blk[blk].xlt2.vsig_tbl[vsig_idx].prop_lst); return 0; @@ -3728,7 +3757,7 @@ ice_create_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl, if (status) goto err_ice_create_prof_id_vsig; - status = ice_add_prof_id_vsig(hw, blk, new_vsig, hdl, chg); + status = ice_add_prof_id_vsig(hw, blk, new_vsig, hdl, false, chg); if (status) goto err_ice_create_prof_id_vsig; @@ -3753,11 +3782,13 @@ err_ice_create_prof_id_vsig: * @blk: hardware block * @vsi: the initial VSI that will be in VSIG * @lst: the list of profile that will be added to the VSIG + * @new_vsig: return of new VSIG * @chg: the change list */ static enum ice_status ice_create_vsig_from_lst(struct ice_hw *hw, enum ice_block blk, u16 vsi, - struct list_head *lst, struct list_head *chg) + struct list_head *lst, u16 *new_vsig, + struct list_head *chg) { struct ice_vsig_prof *t; enum ice_status status; @@ -3772,12 +3803,15 @@ ice_create_vsig_from_lst(struct ice_hw *hw, enum ice_block blk, u16 vsi, return status; list_for_each_entry(t, lst, list) { + /* Reverse the order here since we are copying the list */ status = ice_add_prof_id_vsig(hw, blk, vsig, t->profile_cookie, - chg); + true, chg); if (status) return status; } + *new_vsig = vsig; + return 0; } @@ -3899,7 +3933,8 @@ ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) * not sharing entries and we can simply add the new * profile to the VSIG. */ - status = ice_add_prof_id_vsig(hw, blk, vsig, hdl, &chg); + status = ice_add_prof_id_vsig(hw, blk, vsig, hdl, false, + &chg); if (status) goto err_ice_add_prof_id_flow; @@ -3910,7 +3945,8 @@ ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) } else { /* No match, so we need a new VSIG */ status = ice_create_vsig_from_lst(hw, blk, vsi, - &union_lst, &chg); + &union_lst, &vsig, + &chg); if (status) goto err_ice_add_prof_id_flow; @@ -4076,7 +4112,8 @@ ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) * new VSIG and TCAM entries */ status = ice_create_vsig_from_lst(hw, blk, vsi, - ©, &chg); + ©, &vsig, + &chg); if (status) goto err_ice_rem_prof_id_flow; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 6db3d0494127..1d37a9f02c1c 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -85,6 +85,7 @@ #define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, 0) #define QRXFLXP_CNTXT_RXDID_PRIO_S 8 #define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, 8) +#define QRXFLXP_CNTXT_TS_M BIT(11) #define GLGEN_RSTAT 0x000B8188 #define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0) #define GLGEN_RSTCTL 0x000B8180 @@ -217,6 +218,8 @@ #define VPLAN_TX_QBASE_VFNUMQ_M ICE_M(0xFF, 16) #define VPLAN_TXQ_MAPENA(_VF) (0x00073800 + ((_VF) * 4)) #define VPLAN_TXQ_MAPENA_TX_ENA_M BIT(0) +#define GL_MDCK_TX_TDPU 0x00049348 +#define GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M BIT(1) #define GL_MDET_RX 0x00294C00 #define GL_MDET_RX_QNUM_S 0 #define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) @@ -286,6 +289,8 @@ #define GL_PWR_MODE_CTL 0x000B820C #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) +#define GLDCB_RTCTQ_RXQNUM_S 0 +#define GLDCB_RTCTQ_RXQNUM_M ICE_M(0x7FF, 0) #define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) #define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) #define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d974e2fa3e63..ff72a6d1c978 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -26,16 +26,26 @@ const char *ice_vsi_type_str(enum ice_vsi_type type) } /** - * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings + * ice_vsi_ctrl_all_rx_rings - Start or stop a VSI's Rx rings * @vsi: the VSI being configured * @ena: start or stop the Rx rings + * + * First enable/disable all of the Rx rings, flush any remaining writes, and + * then verify that they have all been enabled/disabled successfully. This will + * let all of the register writes complete when enabling/disabling the Rx rings + * before waiting for the change in hardware to complete. */ -static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) +static int ice_vsi_ctrl_all_rx_rings(struct ice_vsi *vsi, bool ena) { int i, ret = 0; + for (i = 0; i < vsi->num_rxq; i++) + ice_vsi_ctrl_one_rx_ring(vsi, ena, i, false); + + ice_flush(&vsi->back->hw); + for (i = 0; i < vsi->num_rxq; i++) { - ret = ice_vsi_ctrl_rx_ring(vsi, ena, i); + ret = ice_vsi_wait_one_rx_ring(vsi, ena, i); if (ret) break; } @@ -111,7 +121,6 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) { switch (vsi->type) { case ICE_VSI_PF: - /* fall through */ case ICE_VSI_LB: vsi->num_rx_desc = ICE_DFLT_NUM_RX_DESC; vsi->num_tx_desc = ICE_DFLT_NUM_TX_DESC; @@ -433,7 +442,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) .scatter_count = ICE_MAX_SCATTER_TXQS, .vsi_map = vsi->txq_map, .vsi_map_offset = 0, - .mapping_mode = vsi->tx_mapping_mode + .mapping_mode = ICE_VSI_MAP_CONTIG }; struct ice_qs_cfg rx_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, @@ -443,18 +452,21 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) .scatter_count = ICE_MAX_SCATTER_RXQS, .vsi_map = vsi->rxq_map, .vsi_map_offset = 0, - .mapping_mode = vsi->rx_mapping_mode + .mapping_mode = ICE_VSI_MAP_CONTIG }; - int ret = 0; - - vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG; - vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG; + int ret; ret = __ice_vsi_get_qs(&tx_qs_cfg); - if (!ret) - ret = __ice_vsi_get_qs(&rx_qs_cfg); + if (ret) + return ret; + vsi->tx_mapping_mode = tx_qs_cfg.mapping_mode; - return ret; + ret = __ice_vsi_get_qs(&rx_qs_cfg); + if (ret) + return ret; + vsi->rx_mapping_mode = rx_qs_cfg.mapping_mode; + + return 0; } /** @@ -804,7 +816,6 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) ctxt->info = vsi->info; switch (vsi->type) { case ICE_VSI_LB: - /* fall through */ case ICE_VSI_PF: ctxt->flags = ICE_AQ_VSI_TYPE_PF; break; @@ -1348,7 +1359,9 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid) list_add(&tmp->list_entry, &tmp_add_list); status = ice_add_vlan(&pf->hw, &tmp_add_list); - if (status) { + if (!status) { + vsi->num_vlan++; + } else { err = -ENODEV; dev_err(dev, "Failure Adding VLAN %d on VSI %i\n", vid, vsi->vsi_num); @@ -1390,10 +1403,12 @@ int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) list_add(&list->list_entry, &tmp_add_list); status = ice_remove_vlan(&pf->hw, &tmp_add_list); - if (status == ICE_ERR_DOES_NOT_EXIST) { + if (!status) { + vsi->num_vlan--; + } else if (status == ICE_ERR_DOES_NOT_EXIST) { dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %d\n", vid, vsi->vsi_num, status); - } else if (status) { + } else { dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n", vid, vsi->vsi_num, status); err = -EIO; @@ -1678,25 +1693,25 @@ out: } /** - * ice_vsi_start_rx_rings - start VSI's Rx rings - * @vsi: the VSI whose rings are to be started + * ice_vsi_start_all_rx_rings - start/enable all of a VSI's Rx rings + * @vsi: the VSI whose rings are to be enabled * * Returns 0 on success and a negative value on error */ -int ice_vsi_start_rx_rings(struct ice_vsi *vsi) +int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi) { - return ice_vsi_ctrl_rx_rings(vsi, true); + return ice_vsi_ctrl_all_rx_rings(vsi, true); } /** - * ice_vsi_stop_rx_rings - stop VSI's Rx rings - * @vsi: the VSI + * ice_vsi_stop_all_rx_rings - stop/disable all of a VSI's Rx rings + * @vsi: the VSI whose rings are to be disabled * * Returns 0 on success and a negative value on error */ -int ice_vsi_stop_rx_rings(struct ice_vsi *vsi) +int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi) { - return ice_vsi_ctrl_rx_rings(vsi, false); + return ice_vsi_ctrl_all_rx_rings(vsi, false); } /** @@ -1756,6 +1771,26 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) } /** + * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not + * @vsi: VSI to check whether or not VLAN pruning is enabled. + * + * returns true if Rx VLAN pruning and Tx VLAN anti-spoof is enabled and false + * otherwise. + */ +bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi) +{ + u8 rx_pruning = ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + u8 tx_pruning = ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + + if (!vsi) + return false; + + return ((vsi->info.sw_flags2 & rx_pruning) && + (vsi->info.sec_flags & tx_pruning)); +} + +/** * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI * @vsi: VSI to enable or disable VLAN pruning on * @ena: set to true to enable VLAN pruning and false to disable it @@ -2025,6 +2060,17 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; + /* Always add VLAN ID 0 switch rule by default. This is needed + * in order to allow all untagged and 0 tagged priority traffic + * if Rx VLAN pruning is enabled. Also there are cases where we + * don't get the call to add VLAN 0 via ice_vlan_rx_add_vid() + * so this handles those cases (i.e. adding the PF to a bridge + * without the 8021q module loaded). + */ + ret = ice_vsi_add_vlan(vsi, 0); + if (ret) + goto unroll_clear_rings; + ice_vsi_map_rings_to_vectors(vsi); /* Do not exit if configuring RSS had an issue, at least @@ -2104,6 +2150,8 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, return vsi; +unroll_clear_rings: + ice_vsi_clear_rings(vsi); unroll_vector_base: /* reclaim SW interrupts back to the common pool */ ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index e2c0dadce920..585f1350403f 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -30,9 +30,9 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi); int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena); -int ice_vsi_start_rx_rings(struct ice_vsi *vsi); +int ice_vsi_start_all_rx_rings(struct ice_vsi *vsi); -int ice_vsi_stop_rx_rings(struct ice_vsi *vsi); +int ice_vsi_stop_all_rx_rings(struct ice_vsi *vsi); int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, @@ -42,6 +42,8 @@ int ice_vsi_cfg_xdp_txqs(struct ice_vsi *vsi); int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi); +bool ice_vsi_is_vlan_pruning_ena(struct ice_vsi *vsi); + int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5ef28052c0f8..3aa3fc37c70e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -706,7 +706,6 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) /* Get FEC mode based on negotiated link info */ switch (vsi->port_info->phy.link_info.fec_info) { case ICE_AQ_LINK_25G_RS_528_FEC_EN: - /* fall through */ case ICE_AQ_LINK_25G_RS_544_FEC_EN: fec = "RS-FEC"; break; @@ -1029,6 +1028,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) if (ice_handle_link_event(pf, &event)) dev_err(dev, "Could not handle link event\n"); break; + case ice_aqc_opc_event_lan_overflow: + ice_vf_lan_overflow_event(pf, &event); + break; case ice_mbx_opc_send_msg_to_pf: ice_vc_process_vf_msg(pf, &event); break; @@ -1185,20 +1187,28 @@ static void ice_service_timer(struct timer_list *t) * ice_handle_mdd_event - handle malicious driver detect event * @pf: pointer to the PF structure * - * Called from service task. OICR interrupt handler indicates MDD event + * Called from service task. OICR interrupt handler indicates MDD event. + * VF MDD logging is guarded by net_ratelimit. Additional PF and VF log + * messages are wrapped by netif_msg_[rx|tx]_err. Since VF Rx MDD events + * disable the queue, the PF can be configured to reset the VF using ethtool + * private flag mdd-auto-reset-vf. */ static void ice_handle_mdd_event(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - bool mdd_detected = false; u32 reg; int i; - if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state)) + if (!test_and_clear_bit(__ICE_MDD_EVENT_PENDING, pf->state)) { + /* Since the VF MDD event logging is rate limited, check if + * there are pending MDD events. + */ + ice_print_vfs_mdd_events(pf); return; + } - /* find what triggered the MDD event */ + /* find what triggered an MDD event */ reg = rd32(hw, GL_MDET_TX_PQM); if (reg & GL_MDET_TX_PQM_VALID_M) { u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> @@ -1214,7 +1224,6 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); wr32(hw, GL_MDET_TX_PQM, 0xffffffff); - mdd_detected = true; } reg = rd32(hw, GL_MDET_TX_TCLAN); @@ -1232,7 +1241,6 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); - mdd_detected = true; } reg = rd32(hw, GL_MDET_RX); @@ -1250,85 +1258,85 @@ static void ice_handle_mdd_event(struct ice_pf *pf) dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", event, queue, pf_num, vf_num); wr32(hw, GL_MDET_RX, 0xffffffff); - mdd_detected = true; } - if (mdd_detected) { - bool pf_mdd_detected = false; - - reg = rd32(hw, PF_MDET_TX_PQM); - if (reg & PF_MDET_TX_PQM_VALID_M) { - wr32(hw, PF_MDET_TX_PQM, 0xFFFF); - dev_info(dev, "TX driver issue detected, PF reset issued\n"); - pf_mdd_detected = true; - } + /* check to see if this PF caused an MDD event */ + reg = rd32(hw, PF_MDET_TX_PQM); + if (reg & PF_MDET_TX_PQM_VALID_M) { + wr32(hw, PF_MDET_TX_PQM, 0xFFFF); + if (netif_msg_tx_err(pf)) + dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n"); + } - reg = rd32(hw, PF_MDET_TX_TCLAN); - if (reg & PF_MDET_TX_TCLAN_VALID_M) { - wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); - dev_info(dev, "TX driver issue detected, PF reset issued\n"); - pf_mdd_detected = true; - } + reg = rd32(hw, PF_MDET_TX_TCLAN); + if (reg & PF_MDET_TX_TCLAN_VALID_M) { + wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + if (netif_msg_tx_err(pf)) + dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n"); + } - reg = rd32(hw, PF_MDET_RX); - if (reg & PF_MDET_RX_VALID_M) { - wr32(hw, PF_MDET_RX, 0xFFFF); - dev_info(dev, "RX driver issue detected, PF reset issued\n"); - pf_mdd_detected = true; - } - /* Queue belongs to the PF initiate a reset */ - if (pf_mdd_detected) { - set_bit(__ICE_NEEDS_RESTART, pf->state); - ice_service_task_schedule(pf); - } + reg = rd32(hw, PF_MDET_RX); + if (reg & PF_MDET_RX_VALID_M) { + wr32(hw, PF_MDET_RX, 0xFFFF); + if (netif_msg_rx_err(pf)) + dev_info(dev, "Malicious Driver Detection event RX detected on PF\n"); } - /* check to see if one of the VFs caused the MDD */ + /* Check to see if one of the VFs caused an MDD event, and then + * increment counters and set print pending + */ ice_for_each_vf(pf, i) { struct ice_vf *vf = &pf->vf[i]; - bool vf_mdd_detected = false; - reg = rd32(hw, VP_MDET_TX_PQM(i)); if (reg & VP_MDET_TX_PQM_VALID_M) { wr32(hw, VP_MDET_TX_PQM(i), 0xFFFF); - vf_mdd_detected = true; - dev_info(dev, "TX driver issue detected on VF %d\n", - i); + vf->mdd_tx_events.count++; + set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + if (netif_msg_tx_err(pf)) + dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n", + i); } reg = rd32(hw, VP_MDET_TX_TCLAN(i)); if (reg & VP_MDET_TX_TCLAN_VALID_M) { wr32(hw, VP_MDET_TX_TCLAN(i), 0xFFFF); - vf_mdd_detected = true; - dev_info(dev, "TX driver issue detected on VF %d\n", - i); + vf->mdd_tx_events.count++; + set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + if (netif_msg_tx_err(pf)) + dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n", + i); } reg = rd32(hw, VP_MDET_TX_TDPU(i)); if (reg & VP_MDET_TX_TDPU_VALID_M) { wr32(hw, VP_MDET_TX_TDPU(i), 0xFFFF); - vf_mdd_detected = true; - dev_info(dev, "TX driver issue detected on VF %d\n", - i); + vf->mdd_tx_events.count++; + set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + if (netif_msg_tx_err(pf)) + dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n", + i); } reg = rd32(hw, VP_MDET_RX(i)); if (reg & VP_MDET_RX_VALID_M) { wr32(hw, VP_MDET_RX(i), 0xFFFF); - vf_mdd_detected = true; - dev_info(dev, "RX driver issue detected on VF %d\n", - i); - } - - if (vf_mdd_detected) { - vf->num_mdd_events++; - if (vf->num_mdd_events && - vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD) - dev_info(dev, "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n", - i, vf->num_mdd_events); + vf->mdd_rx_events.count++; + set_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state); + if (netif_msg_rx_err(pf)) + dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n", + i); + + /* Since the queue is disabled on VF Rx MDD events, the + * PF can be configured to reset the VF through ethtool + * private flag mdd-auto-reset-vf. + */ + if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + ice_reset_vf(&pf->vf[i], false); } } + + ice_print_vfs_mdd_events(pf); } /** @@ -1916,8 +1924,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (if_running && !test_and_set_bit(__ICE_DOWN, vsi->state)) { ret = ice_down(vsi); if (ret) { - NL_SET_ERR_MSG_MOD(extack, - "Preparing device for XDP attach failed"); + NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed"); return ret; } } @@ -1926,13 +1933,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, vsi->num_xdp_txq = vsi->alloc_txq; xdp_ring_err = ice_prepare_xdp_rings(vsi, prog); if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, - "Setting up XDP Tx resources failed"); + NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, - "Freeing XDP Tx resources failed"); + NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); } else { ice_vsi_assign_bpf_prog(vsi, prog); } @@ -1965,8 +1970,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp) struct ice_vsi *vsi = np->vsi; if (vsi->type != ICE_VSI_PF) { - NL_SET_ERR_MSG_MOD(xdp->extack, - "XDP can be loaded only on PF VSI"); + NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI"); return -EINVAL; } @@ -1993,6 +1997,14 @@ static void ice_ena_misc_vector(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; u32 val; + /* Disable anti-spoof detection interrupt to prevent spurious event + * interrupts during a function reset. Anti-spoof functionally is + * still supported. + */ + val = rd32(hw, GL_MDCK_TX_TDPU); + val |= GL_MDCK_TX_TDPU_RCU_ANTISPOOF_ITR_DIS_M; + wr32(hw, GL_MDCK_TX_TDPU, val); + /* clear things first */ wr32(hw, PFINT_OICR_ENA, 0); /* disable all */ rd32(hw, PFINT_OICR); /* read to clear */ @@ -2461,16 +2473,19 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __always_unused __be16 proto, if (vsi->info.pvid) return -EINVAL; - /* Enable VLAN pruning when VLAN 0 is added */ - if (unlikely(!vid)) { + /* VLAN 0 is added by default during load/reset */ + if (!vid) + return 0; + + /* Enable VLAN pruning when a VLAN other than 0 is added */ + if (!ice_vsi_is_vlan_pruning_ena(vsi)) { ret = ice_cfg_vlan_pruning(vsi, true, false); if (ret) return ret; } - /* Add all VLAN IDs including 0 to the switch filter. VLAN ID 0 is - * needed to continue allowing all untagged packets since VLAN prune - * list is applied to all packets by the switch + /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged + * packets aren't pruned by the device's internal switch on Rx */ ret = ice_vsi_add_vlan(vsi, vid); if (!ret) { @@ -2500,6 +2515,10 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, if (vsi->info.pvid) return -EINVAL; + /* don't allow removal of VLAN 0 */ + if (!vid) + return 0; + /* Make sure ice_vsi_kill_vlan is successful before updating VLAN * information */ @@ -2507,8 +2526,8 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __always_unused __be16 proto, if (ret) return ret; - /* Disable VLAN pruning when VLAN 0 is removed */ - if (unlikely(!vid)) + /* Disable pruning when VLAN 0 is the only VLAN rule */ + if (vsi->num_vlan == 1 && ice_vsi_is_vlan_pruning_ena(vsi)) ret = ice_cfg_vlan_pruning(vsi, false, false); vsi->vlan_ena = false; @@ -2945,7 +2964,6 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) } break; case ICE_ERR_BUF_TOO_SHORT: - /* fall-through */ case ICE_ERR_CFG: dev_err(dev, "The DDP package file is invalid. Entering Safe Mode.\n"); break; @@ -2977,7 +2995,7 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) default: break; } - /* fall-through */ + fallthrough; default: dev_err(dev, "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n", *status); @@ -3534,15 +3552,26 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822X_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 }, /* required last entry */ { 0, } }; @@ -3961,7 +3990,7 @@ static int ice_up_complete(struct ice_vsi *vsi) * Tx queue group list was configured and the context bits were * programmed using ice_vsi_cfg_txqs */ - err = ice_vsi_start_rx_rings(vsi); + err = ice_vsi_start_all_rx_rings(vsi); if (err) return err; @@ -4340,7 +4369,7 @@ int ice_down(struct ice_vsi *vsi) vsi->vsi_num, tx_err); } - rx_err = ice_vsi_stop_rx_rings(vsi); + rx_err = ice_vsi_stop_all_rx_rings(vsi); if (rx_err) netdev_err(vsi->netdev, "Failed stop Rx rings, VSI %d error %d\n", vsi->vsi_num, rx_err); @@ -5027,6 +5056,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, /** * ice_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure + * @txqueue: Tx queue */ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) { diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 7525ac50742e..f6e25db22c23 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -289,17 +289,31 @@ enum ice_status ice_init_nvm(struct ice_hw *hw) nvm->eetrack = (eetrack_hi << 16) | eetrack_lo; + switch (hw->device_id) { /* the following devices do not have boot_cfg_tlv yet */ - if (hw->device_id == ICE_DEV_ID_E822C_BACKPLANE || - hw->device_id == ICE_DEV_ID_E822C_QSFP || - hw->device_id == ICE_DEV_ID_E822C_10G_BASE_T || - hw->device_id == ICE_DEV_ID_E822C_SGMII || - hw->device_id == ICE_DEV_ID_E822C_SFP || - hw->device_id == ICE_DEV_ID_E822X_BACKPLANE || - hw->device_id == ICE_DEV_ID_E822L_SFP || - hw->device_id == ICE_DEV_ID_E822L_10G_BASE_T || - hw->device_id == ICE_DEV_ID_E822L_SGMII) + case ICE_DEV_ID_E823C_BACKPLANE: + case ICE_DEV_ID_E823C_QSFP: + case ICE_DEV_ID_E823C_SFP: + case ICE_DEV_ID_E823C_10G_BASE_T: + case ICE_DEV_ID_E823C_SGMII: + case ICE_DEV_ID_E822C_BACKPLANE: + case ICE_DEV_ID_E822C_QSFP: + case ICE_DEV_ID_E822C_10G_BASE_T: + case ICE_DEV_ID_E822C_SGMII: + case ICE_DEV_ID_E822C_SFP: + case ICE_DEV_ID_E822L_BACKPLANE: + case ICE_DEV_ID_E822L_SFP: + case ICE_DEV_ID_E822L_10G_BASE_T: + case ICE_DEV_ID_E822L_SGMII: + case ICE_DEV_ID_E823L_BACKPLANE: + case ICE_DEV_ID_E823L_SFP: + case ICE_DEV_ID_E823L_10G_BASE_T: + case ICE_DEV_ID_E823L_1GBE: + case ICE_DEV_ID_E823L_QSFP: return status; + default: + break; + } status = ice_get_pfa_module_tlv(hw, &boot_cfg_tlv, &boot_cfg_tlv_len, ICE_SR_BOOT_CFG_PTR); diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index d2db0d04e117..554f567476f3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -121,9 +121,7 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) speed = (u32)VIRTCHNL_LINK_SPEED_25GB; break; case ICE_AQ_LINK_SPEED_40GB: - /* fall through */ case ICE_AQ_LINK_SPEED_50GB: - /* fall through */ case ICE_AQ_LINK_SPEED_100GB: speed = (u32)VIRTCHNL_LINK_SPEED_40GB; break; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 431266081a80..4d96abfd05d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -760,7 +760,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, break; case ICE_SW_LKUP_ETHERTYPE_MAC: daddr = f_info->l_data.ethertype_mac.mac_addr; - /* fall-through */ + fallthrough; case ICE_SW_LKUP_ETHERTYPE: off = (__force __be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); *off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype); @@ -771,7 +771,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, break; case ICE_SW_LKUP_PROMISC_VLAN: vlan_id = f_info->l_data.mac_vlan.vlan_id; - /* fall-through */ + fallthrough; case ICE_SW_LKUP_PROMISC: daddr = f_info->l_data.mac_vlan.mac_addr; break; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 4de61dbedd36..f67e8362958c 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -453,10 +453,10 @@ ice_run_xdp(struct ice_ring *rx_ring, struct xdp_buff *xdp, break; default: bpf_warn_invalid_xdp_action(act); - /* fallthrough -- not supported action */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); - /* fallthrough -- handle aborts by dropping frame */ + fallthrough; case XDP_DROP: result = ICE_XDP_CONSUMED; break; @@ -1188,7 +1188,6 @@ ice_adjust_itr_by_size_and_speed(struct ice_port_info *port_info, avg_pkt_size + 640); break; case ICE_AQ_LINK_SPEED_10GB: - /* fall through */ default: itr += DIV_ROUND_UP(170 * (avg_pkt_size + 24), avg_pkt_size + 640); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 75c70d432c72..6bedfa4676ae 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -91,6 +91,39 @@ ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, } /** + * ice_vf_has_no_qs_ena - check if the VF has any Rx or Tx queues enabled + * @vf: the VF to check + * + * Returns true if the VF has no Rx and no Tx queues enabled and returns false + * otherwise + */ +static bool ice_vf_has_no_qs_ena(struct ice_vf *vf) +{ + return (!bitmap_weight(vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF) && + !bitmap_weight(vf->txq_ena, ICE_MAX_BASE_QS_PER_VF)); +} + +/** + * ice_is_vf_link_up - check if the VF's link is up + * @vf: VF to check if link is up + */ +static bool ice_is_vf_link_up(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + + if (ice_check_vf_init(pf, vf)) + return false; + + if (ice_vf_has_no_qs_ena(vf)) + return false; + else if (vf->link_forced) + return vf->link_up; + else + return pf->hw.port_info->phy.link_info.link_info & + ICE_AQ_LINK_UP; +} + +/** * ice_vc_notify_vf_link_state - Inform a VF of link status * @vf: pointer to the VF structure * @@ -99,28 +132,16 @@ ice_set_pfe_link(struct ice_vf *vf, struct virtchnl_pf_event *pfe, static void ice_vc_notify_vf_link_state(struct ice_vf *vf) { struct virtchnl_pf_event pfe = { 0 }; - struct ice_link_status *ls; - struct ice_pf *pf = vf->pf; - struct ice_hw *hw; - - hw = &pf->hw; - ls = &hw->port_info->phy.link_info; + struct ice_hw *hw = &vf->pf->hw; pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - /* Always report link is down if the VF queues aren't enabled */ - if (!vf->num_qs_ena) { + if (ice_is_vf_link_up(vf)) + ice_set_pfe_link(vf, &pfe, + hw->port_info->phy.link_info.link_speed, true); + else ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false); - } else if (vf->link_forced) { - u16 link_speed = vf->link_up ? - ls->link_speed : ICE_AQ_LINK_SPEED_UNKNOWN; - - ice_set_pfe_link(vf, &pfe, link_speed, vf->link_up); - } else { - ice_set_pfe_link(vf, &pfe, ls->link_speed, - ls->link_info & ICE_AQ_LINK_UP); - } ice_aq_send_msg_to_vf(hw, vf->vf_id, VIRTCHNL_OP_EVENT, VIRTCHNL_STATUS_SUCCESS, (u8 *)&pfe, @@ -150,6 +171,11 @@ static void ice_free_vf_res(struct ice_vf *vf) } last_vector_idx = vf->first_vector_idx + pf->num_vf_msix - 1; + + /* clear VF MDD event information */ + memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); + memset(&vf->mdd_rx_events, 0, sizeof(vf->mdd_rx_events)); + /* Disable interrupts so that VF starts in a known state */ for (i = vf->first_vector_idx; i <= last_vector_idx; i++) { wr32(&pf->hw, GLINT_DYN_CTL(i), GLINT_DYN_CTL_CLEARPBA_M); @@ -247,7 +273,6 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf) /* Clear Rx/Tx enabled queues flag */ bitmap_zero(vf->txq_ena, ICE_MAX_BASE_QS_PER_VF); bitmap_zero(vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF); - vf->num_qs_ena = 0; clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); } @@ -263,7 +288,7 @@ static void ice_dis_vf_qs(struct ice_vf *vf) vsi = pf->vsi[vf->lan_vsi_idx]; ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); - ice_vsi_stop_rx_rings(vsi); + ice_vsi_stop_all_rx_rings(vsi); ice_set_vf_state_qs_dis(vf); } @@ -407,43 +432,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) } /** - * ice_vsi_set_pvid_fill_ctxt - Set VSI ctxt for add PVID - * @ctxt: the VSI ctxt to fill - * @vid: the VLAN ID to set as a PVID - */ -static void ice_vsi_set_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt, u16 vid) -{ - ctxt->info.vlan_flags = (ICE_AQ_VSI_VLAN_MODE_UNTAGGED | - ICE_AQ_VSI_PVLAN_INSERT_PVID | - ICE_AQ_VSI_VLAN_EMOD_STR); - ctxt->info.pvid = cpu_to_le16(vid); - ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | - ICE_AQ_VSI_PROP_SW_VALID); -} - -/** - * ice_vsi_kill_pvid_fill_ctxt - Set VSI ctx for remove PVID - * @ctxt: the VSI ctxt to fill - */ -static void ice_vsi_kill_pvid_fill_ctxt(struct ice_vsi_ctx *ctxt) -{ - ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; - ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; - ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; - ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | - ICE_AQ_VSI_PROP_SW_VALID); -} - -/** * ice_vsi_manage_pvid - Enable or disable port VLAN for VSI * @vsi: the VSI to update - * @vid: the VLAN ID to set as a PVID + * @pvid_info: VLAN ID and QoS used to set the PVID VSI context field * @enable: true for enable PVID false for disable */ -static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable) +static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable) { struct ice_hw *hw = &vsi->back->hw; + struct ice_aqc_vsi_props *info; struct ice_vsi_ctx *ctxt; enum ice_status status; int ret = 0; @@ -453,20 +450,33 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 vid, bool enable) return -ENOMEM; ctxt->info = vsi->info; - if (enable) - ice_vsi_set_pvid_fill_ctxt(ctxt, vid); - else - ice_vsi_kill_pvid_fill_ctxt(ctxt); + info = &ctxt->info; + if (enable) { + info->vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | + ICE_AQ_VSI_PVLAN_INSERT_PVID | + ICE_AQ_VSI_VLAN_EMOD_STR; + info->sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } else { + info->vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING | + ICE_AQ_VSI_VLAN_MODE_ALL; + info->sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + + info->pvid = cpu_to_le16(pvid_info); + info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | + ICE_AQ_VSI_PROP_SW_VALID); status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_info(ice_pf_to_dev(vsi->back), "update VSI for port VLAN failed, err %d aq_err %d\n", + dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %d\n", status, hw->adminq.sq_last_status); ret = -EIO; goto out; } - vsi->info = ctxt->info; + vsi->info.vlan_flags = info->vlan_flags; + vsi->info.sw_flags2 = info->sw_flags2; + vsi->info.pvid = info->pvid; out: kfree(ctxt); return ret; @@ -533,9 +543,20 @@ static int ice_alloc_vsi_res(struct ice_vf *vf) vf->lan_vsi_num = vsi->vsi_num; /* Check if port VLAN exist before, and restore it accordingly */ - if (vf->port_vlan_id) { - ice_vsi_manage_pvid(vsi, vf->port_vlan_id, true); - ice_vsi_add_vlan(vsi, vf->port_vlan_id & ICE_VLAN_M); + if (vf->port_vlan_info) { + ice_vsi_manage_pvid(vsi, vf->port_vlan_info, true); + if (ice_vsi_add_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK)) + dev_warn(ice_pf_to_dev(pf), "Failed to add Port VLAN %d filter for VF %d\n", + vf->port_vlan_info & VLAN_VID_MASK, vf->vf_id); + } else { + /* set VLAN 0 filter by default when no port VLAN is + * enabled. If a port VLAN is enabled we don't want + * untagged broadcast/multicast traffic seen on the VF + * interface. + */ + if (ice_vsi_add_vlan(vsi, 0)) + dev_warn(ice_pf_to_dev(pf), "Failed to add VLAN 0 filter for VF %d, MDD events will trigger. Reset the VF, disable spoofchk, or enable 8021q module on the guest\n", + vf->vf_id); } eth_broadcast_addr(broadcast); @@ -943,17 +964,9 @@ static void ice_cleanup_and_realloc_vf(struct ice_vf *vf) /* reallocate VF resources to finish resetting the VSI state */ if (!ice_alloc_vf_res(vf)) { - struct ice_vsi *vsi; - ice_ena_vf_mappings(vf); set_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); clear_bit(ICE_VF_STATE_DIS, vf->vf_states); - - vsi = pf->vsi[vf->lan_vsi_idx]; - if (ice_vsi_add_vlan(vsi, 0)) - dev_warn(ice_pf_to_dev(pf), - "Failed to add VLAN 0 filter for VF %d, MDD events will trigger. Reset the VF, disable spoofchk, or enable 8021q module on the guest", - vf->vf_id); } /* Tell the VF driver the reset is done. This needs to be done only @@ -985,13 +998,13 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m, if (vsi->num_vlan) { status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m, rm_promisc); - } else if (vf->port_vlan_id) { + } else if (vf->port_vlan_info) { if (rm_promisc) status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_id); + vf->port_vlan_info); else status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_id); + vf->port_vlan_info); } else { if (rm_promisc) status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m, @@ -1167,7 +1180,7 @@ static bool ice_is_vf_disabled(struct ice_vf *vf) * * Returns true if the VF is reset, false otherwise. */ -static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) +bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) { struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; @@ -1231,7 +1244,7 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) */ if (test_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states) || test_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) { - if (vf->port_vlan_id || vsi->num_vlan) + if (vf->port_vlan_info || vsi->num_vlan) promisc_m = ICE_UCAST_VLAN_PROMISC_BITS; else promisc_m = ICE_UCAST_PROMISC_BITS; @@ -1518,6 +1531,72 @@ static void ice_vc_reset_vf(struct ice_vf *vf) } /** + * ice_get_vf_from_pfq - get the VF who owns the PF space queue passed in + * @pf: PF used to index all VFs + * @pfq: queue index relative to the PF's function space + * + * If no VF is found who owns the pfq then return NULL, otherwise return a + * pointer to the VF who owns the pfq + */ +static struct ice_vf *ice_get_vf_from_pfq(struct ice_pf *pf, u16 pfq) +{ + int vf_id; + + ice_for_each_vf(pf, vf_id) { + struct ice_vf *vf = &pf->vf[vf_id]; + struct ice_vsi *vsi; + u16 rxq_idx; + + vsi = pf->vsi[vf->lan_vsi_idx]; + + ice_for_each_rxq(vsi, rxq_idx) + if (vsi->rxq_map[rxq_idx] == pfq) + return vf; + } + + return NULL; +} + +/** + * ice_globalq_to_pfq - convert from global queue index to PF space queue index + * @pf: PF used for conversion + * @globalq: global queue index used to convert to PF space queue index + */ +static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq) +{ + return globalq - pf->hw.func_caps.common_cap.rxq_first_id; +} + +/** + * ice_vf_lan_overflow_event - handle LAN overflow event for a VF + * @pf: PF that the LAN overflow event happened on + * @event: structure holding the event information for the LAN overflow event + * + * Determine if the LAN overflow event was caused by a VF queue. If it was not + * caused by a VF, do nothing. If a VF caused this LAN overflow event trigger a + * reset on the offending VF. + */ +void +ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + u32 gldcb_rtctq, queue; + struct ice_vf *vf; + + gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq); + dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq); + + /* event returns device global Rx queue number */ + queue = (gldcb_rtctq & GLDCB_RTCTQ_RXQNUM_M) >> + GLDCB_RTCTQ_RXQNUM_S; + + vf = ice_get_vf_from_pfq(pf, ice_globalq_to_pfq(pf, queue)); + if (!vf) + return; + + ice_vc_reset_vf(vf); +} + +/** * ice_vc_send_msg_to_vf - Send message to VF * @vf: pointer to the VF info * @v_opcode: virtual channel opcode @@ -1981,7 +2060,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); if (status) { - dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d", + dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d\n", ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, status); ret = -EIO; goto out; @@ -2039,6 +2118,22 @@ error_param: } /** + * ice_vc_validate_vqs_bitmaps - validate Rx/Tx queue bitmaps from VIRTCHNL + * @vqs: virtchnl_queue_select structure containing bitmaps to validate + * + * Return true on successful validation, else false + */ +static bool ice_vc_validate_vqs_bitmaps(struct virtchnl_queue_select *vqs) +{ + if ((!vqs->rx_queues && !vqs->tx_queues) || + vqs->rx_queues >= BIT(ICE_MAX_BASE_QS_PER_VF) || + vqs->tx_queues >= BIT(ICE_MAX_BASE_QS_PER_VF)) + return false; + + return true; +} + +/** * ice_vc_ena_qs_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2065,13 +2160,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - if (!vqs->rx_queues && !vqs->tx_queues) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - - if (vqs->rx_queues > ICE_MAX_BASE_QS_PER_VF || - vqs->tx_queues > ICE_MAX_BASE_QS_PER_VF) { + if (!ice_vc_validate_vqs_bitmaps(vqs)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -2097,7 +2186,7 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) if (test_bit(vf_q_id, vf->rxq_ena)) continue; - if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) { + if (ice_vsi_ctrl_one_rx_ring(vsi, true, vf_q_id, true)) { dev_err(ice_pf_to_dev(vsi->back), "Failed to enable Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2105,7 +2194,6 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) } set_bit(vf_q_id, vf->rxq_ena); - vf->num_qs_ena++; } vsi = pf->vsi[vf->lan_vsi_idx]; @@ -2121,7 +2209,6 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) continue; set_bit(vf_q_id, vf->txq_ena); - vf->num_qs_ena++; } /* Set flag to indicate that queues are enabled */ @@ -2163,7 +2250,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - if (!vqs->rx_queues && !vqs->tx_queues) { + if (!ice_vc_validate_vqs_bitmaps(vqs)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -2208,13 +2295,22 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) /* Clear enabled queues flag */ clear_bit(vf_q_id, vf->txq_ena); - vf->num_qs_ena--; } } - if (vqs->rx_queues) { - q_map = vqs->rx_queues; + q_map = vqs->rx_queues; + /* speed up Rx queue disable by batching them if possible */ + if (q_map && + bitmap_equal(&q_map, vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF)) { + if (ice_vsi_stop_all_rx_rings(vsi)) { + dev_err(ice_pf_to_dev(vsi->back), "Failed to stop all Rx rings on VSI %d\n", + vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + bitmap_zero(vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF); + } else if (q_map) { for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) { if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2225,7 +2321,8 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) if (!test_bit(vf_q_id, vf->rxq_ena)) continue; - if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) { + if (ice_vsi_ctrl_one_rx_ring(vsi, false, vf_q_id, + true)) { dev_err(ice_pf_to_dev(vsi->back), "Failed to stop Rx ring %d on VSI %d\n", vf_q_id, vsi->vsi_num); v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2234,12 +2331,11 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) /* Clear enabled queues flag */ clear_bit(vf_q_id, vf->rxq_ena); - vf->num_qs_ena--; } } /* Clear enabled queues flag */ - if (v_ret == VIRTCHNL_STATUS_SUCCESS && !vf->num_qs_ena) + if (v_ret == VIRTCHNL_STATUS_SUCCESS && ice_vf_has_no_qs_ena(vf)) clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); error_param: @@ -2733,19 +2829,20 @@ int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, __be16 vlan_proto) { - u16 vlanprio = vlan_id | (qos << ICE_VLAN_PRIORITY_S); struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vsi *vsi; struct device *dev; struct ice_vf *vf; + u16 vlanprio; int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; - if (vlan_id > ICE_MAX_VLANID || qos > 7) { - dev_err(dev, "Invalid VF Parameters\n"); + if (vlan_id >= VLAN_N_VID || qos > 7) { + dev_err(dev, "Invalid Port VLAN parameters for VF %d, ID %d, QoS %d\n", + vf_id, vlan_id, qos); return -EINVAL; } @@ -2761,40 +2858,52 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (ret) return ret; - if (le16_to_cpu(vsi->info.pvid) == vlanprio) { + vlanprio = vlan_id | (qos << VLAN_PRIO_SHIFT); + + if (vf->port_vlan_info == vlanprio) { /* duplicate request, so just return success */ dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); return 0; } - /* If PVID, then remove all filters on the old VLAN */ - if (vsi->info.pvid) - ice_vsi_kill_vlan(vsi, (le16_to_cpu(vsi->info.pvid) & - VLAN_VID_MASK)); - if (vlan_id || qos) { + /* remove VLAN 0 filter set by default when transitioning from + * no port VLAN to a port VLAN. No change to old port VLAN on + * failure. + */ + ret = ice_vsi_kill_vlan(vsi, 0); + if (ret) + return ret; ret = ice_vsi_manage_pvid(vsi, vlanprio, true); if (ret) return ret; } else { - ice_vsi_manage_pvid(vsi, 0, false); - vsi->info.pvid = 0; + /* add VLAN 0 filter back when transitioning from port VLAN to + * no port VLAN. No change to old port VLAN on failure. + */ + ret = ice_vsi_add_vlan(vsi, 0); + if (ret) + return ret; + ret = ice_vsi_manage_pvid(vsi, 0, false); + if (ret) + return ret; } if (vlan_id) { dev_info(dev, "Setting VLAN %d, QoS 0x%x on VF %d\n", vlan_id, qos, vf_id); - /* add new VLAN filter for each MAC */ + /* add VLAN filter for the port VLAN */ ret = ice_vsi_add_vlan(vsi, vlan_id); if (ret) return ret; } + /* remove old port VLAN filter with valid VLAN ID or QoS fields */ + if (vf->port_vlan_info) + ice_vsi_kill_vlan(vsi, vf->port_vlan_info & VLAN_VID_MASK); - /* The Port VLAN needs to be saved across resets the same as the - * default LAN MAC address. - */ - vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + /* keep port VLAN information persistent on resets */ + vf->port_vlan_info = le16_to_cpu(vsi->info.pvid); return 0; } @@ -2849,7 +2958,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) } for (i = 0; i < vfl->num_elements; i++) { - if (vfl->vlan_id[i] > ICE_MAX_VLANID) { + if (vfl->vlan_id[i] >= VLAN_N_VID) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; dev_err(dev, "invalid VF VLAN id %d\n", vfl->vlan_id[i]); @@ -2911,9 +3020,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) goto error_param; } - vsi->num_vlan++; - /* Enable VLAN pruning when VLAN is added */ - if (!vlan_promisc) { + /* Enable VLAN pruning when non-zero VLAN is added */ + if (!vlan_promisc && vid && + !ice_vsi_is_vlan_pruning_ena(vsi)) { status = ice_cfg_vlan_pruning(vsi, true, false); if (status) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2921,7 +3030,7 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) vid, status); goto error_param; } - } else { + } else if (vlan_promisc) { /* Enable Ucast/Mcast VLAN promiscuous mode */ promisc_m = ICE_PROMISC_VLAN_TX | ICE_PROMISC_VLAN_RX; @@ -2965,9 +3074,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) goto error_param; } - vsi->num_vlan--; - /* Disable VLAN pruning when the last VLAN is removed */ - if (!vsi->num_vlan) + /* Disable VLAN pruning when only VLAN 0 is left */ + if (vsi->num_vlan == 1 && + ice_vsi_is_vlan_pruning_ena(vsi)) ice_cfg_vlan_pruning(vsi, false, false); /* Disable Unicast/Multicast VLAN promiscuous mode */ @@ -3246,14 +3355,12 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) { struct ice_pf *pf = ice_netdev_to_pf(netdev); - struct ice_vsi *vsi; struct ice_vf *vf; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - vsi = pf->vsi[vf->lan_vsi_idx]; if (ice_check_vf_init(pf, vf)) return -EBUSY; @@ -3262,9 +3369,8 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr); /* VF configuration for VLAN and applicable QoS */ - ivi->vlan = le16_to_cpu(vsi->info.pvid) & ICE_VLAN_M; - ivi->qos = (le16_to_cpu(vsi->info.pvid) & ICE_PRIORITY_M) >> - ICE_VLAN_PRIORITY_S; + ivi->vlan = vf->port_vlan_info & VLAN_VID_MASK; + ivi->qos = (vf->port_vlan_info & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; ivi->trusted = vf->trusted; ivi->spoofchk = vf->spoofchk; @@ -3442,3 +3548,52 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id, return 0; } + +/** + * ice_print_vfs_mdd_event - print VFs malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from ice_handle_mdd_event to rate limit and print VFs MDD events. + */ +void ice_print_vfs_mdd_events(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int i; + + /* check that there are pending MDD events to print */ + if (!test_and_clear_bit(__ICE_MDD_VF_PRINT_PENDING, pf->state)) + return; + + /* VF MDD event logs are rate limited to one second intervals */ + if (time_is_after_jiffies(pf->last_printed_mdd_jiffies + HZ * 1)) + return; + + pf->last_printed_mdd_jiffies = jiffies; + + ice_for_each_vf(pf, i) { + struct ice_vf *vf = &pf->vf[i]; + + /* only print Rx MDD event message if there are new events */ + if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { + vf->mdd_rx_events.last_printed = + vf->mdd_rx_events.count; + + dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", + vf->mdd_rx_events.count, hw->pf_id, i, + vf->dflt_lan_addr.addr, + test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) + ? "on" : "off"); + } + + /* only print Tx MDD event message if there are new events */ + if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { + vf->mdd_tx_events.last_printed = + vf->mdd_tx_events.count; + + dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", + vf->mdd_tx_events.count, hw->pf_id, i, + vf->dflt_lan_addr.addr); + } + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index ac67982751df..36dad0eba3db 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -5,11 +5,6 @@ #define _ICE_VIRTCHNL_PF_H_ #include "ice.h" -#define ICE_MAX_VLANID 4095 -#define ICE_VLAN_PRIORITY_S 12 -#define ICE_VLAN_M 0xFFF -#define ICE_PRIORITY_M 0x7000 - /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */ #define ICE_MAX_VLAN_PER_VF 8 #define ICE_MAX_MACADDR_PER_VF 12 @@ -61,6 +56,13 @@ enum ice_virtchnl_cap { ICE_VIRTCHNL_VF_CAP_PRIVILEGE, }; +/* VF MDD events print structure */ +struct ice_mdd_vf_events { + u16 count; /* total count of Rx|Tx events */ + /* count number of the last printed event */ + u16 last_printed; +}; + /* VF information structure */ struct ice_vf { struct ice_pf *pf; @@ -75,7 +77,7 @@ struct ice_vf { struct virtchnl_ether_addr dflt_lan_addr; DECLARE_BITMAP(txq_ena, ICE_MAX_BASE_QS_PER_VF); DECLARE_BITMAP(rxq_ena, ICE_MAX_BASE_QS_PER_VF); - u16 port_vlan_id; + u16 port_vlan_info; /* Port VLAN ID and QoS */ u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ u8 trusted:1; u8 spoofchk:1; @@ -89,14 +91,14 @@ struct ice_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ - u64 num_mdd_events; /* number of MDD events detected */ u64 num_inval_msgs; /* number of continuous invalid msgs */ u64 num_valid_msgs; /* number of valid msgs detected */ unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; u16 num_vf_qs; /* num of queue configured per VF */ - u16 num_qs_ena; /* total num of Tx/Rx queue enabled */ + struct ice_mdd_vf_events mdd_rx_events; + struct ice_mdd_vf_events mdd_tx_events; }; #ifdef CONFIG_PCI_IOV @@ -111,6 +113,7 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_vc_notify_link_state(struct ice_pf *pf); void ice_vc_notify_reset(struct ice_pf *pf); bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr); +bool ice_reset_vf(struct ice_vf *vf, bool is_vflr); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -128,6 +131,9 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf); int ice_get_vf_stats(struct net_device *netdev, int vf_id, struct ifla_vf_stats *vf_stats); +void +ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_print_vfs_mdd_events(struct ice_pf *pf); #else /* CONFIG_PCI_IOV */ #define ice_process_vflr_event(pf) do {} while (0) #define ice_free_vfs(pf) do {} while (0) @@ -135,6 +141,8 @@ ice_get_vf_stats(struct net_device *netdev, int vf_id, #define ice_vc_notify_link_state(pf) do {} while (0) #define ice_vc_notify_reset(pf) do {} while (0) #define ice_set_vf_state_qs_dis(vf) do {} while (0) +#define ice_vf_lan_overflow_event(pf, event) do {} while (0) +#define ice_print_vfs_mdd_events(pf) do {} while (0) static inline bool ice_reset_all_vfs(struct ice_pf __always_unused *pf, @@ -143,6 +151,12 @@ ice_reset_all_vfs(struct ice_pf __always_unused *pf, return true; } +static inline bool +ice_reset_vf(struct ice_vf __always_unused *vf, bool __always_unused is_vflr) +{ + return true; +} + static inline int ice_sriov_configure(struct pci_dev __always_unused *pdev, int __always_unused num_vfs) diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 4d3407bbd4c4..8279db15e870 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -183,7 +183,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - err = ice_vsi_ctrl_rx_ring(vsi, false, q_idx); + err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; @@ -243,7 +243,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) ice_qvec_cfg_msix(vsi, q_vector); - err = ice_vsi_ctrl_rx_ring(vsi, true, q_idx); + err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true); if (err) goto free_buf; @@ -457,7 +457,7 @@ int ice_xsk_umem_setup(struct ice_vsi *vsi, struct xdp_umem *umem, u16 qid) if (if_running) { ret = ice_qp_dis(vsi, qid); if (ret) { - netdev_err(vsi->netdev, "ice_qp_dis error = %d", ret); + netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); goto xsk_umem_if_up; } } @@ -471,11 +471,11 @@ xsk_umem_if_up: if (!ret && umem_present) napi_schedule(&vsi->xdp_rings[qid]->q_vector->napi); else if (ret) - netdev_err(vsi->netdev, "ice_qp_ena error = %d", ret); + netdev_err(vsi->netdev, "ice_qp_ena error = %d\n", ret); } if (umem_failure) { - netdev_err(vsi->netdev, "Could not %sable UMEM, error = %d", + netdev_err(vsi->netdev, "Could not %sable UMEM, error = %d\n", umem_present ? "en" : "dis", umem_failure); return umem_failure; } @@ -609,7 +609,7 @@ ice_alloc_buf_slow_zc(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) */ static bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, int count, - bool alloc(struct ice_ring *, struct ice_rx_buf *)) + bool (*alloc)(struct ice_ring *, struct ice_rx_buf *)) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -816,10 +816,10 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) break; default: bpf_warn_invalid_xdp_action(act); - /* fallthrough -- not supported action */ + fallthrough; case XDP_ABORTED: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); - /* fallthrough -- handle aborts by dropping frame */ + fallthrough; case XDP_DROP: result = ICE_XDP_CONSUMED; break; @@ -841,8 +841,8 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); unsigned int xdp_xmit = 0; + bool failure = false; struct xdp_buff xdp; - bool failure = 0; xdp.rxq = &rx_ring->xdp_rxq; @@ -937,6 +937,15 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) ice_finalize_xdp_rx(rx_ring, xdp_xmit); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + else + xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + + return (int)total_rx_packets; + } + return failure ? budget : (int)total_rx_packets; } @@ -988,6 +997,8 @@ static bool ice_xmit_zc(struct ice_ring *xdp_ring, int budget) if (tx_desc) { ice_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) + xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return budget > 0 && work_done; @@ -1063,6 +1074,13 @@ bool ice_clean_tx_irq_zc(struct ice_ring *xdp_ring, int budget) if (xsk_frames) xsk_umem_complete_tx(xdp_ring->xsk_umem, xsk_frames); + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) { + if (xdp_ring->next_to_clean == xdp_ring->next_to_use) + xsk_set_tx_need_wakeup(xdp_ring->xsk_umem); + else + xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); + } + ice_update_tx_ring_stats(xdp_ring, total_packets, total_bytes); xmit_done = ice_xmit_zc(xdp_ring, ICE_DFLT_IRQ_WORK); diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 49b5fa9d4783..0c9282e2aaec 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -306,7 +306,7 @@ struct igb_q_vector { char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ - struct igb_ring ring[0] ____cacheline_internodealigned_in_smp; + struct igb_ring ring[] ____cacheline_internodealigned_in_smp; }; enum e1000_ring_flags_t { diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index 49fb1e1965cd..e3c164c12e10 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_IGC) += igc.o igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_ethtool.o igc_ptp.o +igc_ethtool.o igc_ptp.o igc_dump.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 52066bdbbad0..a1f845a2aa80 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -42,6 +42,10 @@ int igc_del_mac_steering_filter(struct igc_adapter *adapter, const u8 *addr, u8 queue, u8 flags); void igc_update_stats(struct igc_adapter *adapter); +/* igc_dump declarations */ +void igc_rings_dump(struct igc_adapter *adapter); +void igc_regs_dump(struct igc_adapter *adapter); + extern char igc_driver_name[]; extern char igc_driver_version[]; @@ -53,10 +57,13 @@ extern char igc_driver_version[]; /* Interrupt defines */ #define IGC_START_ITR 648 /* ~6000 ints/sec */ + +/* Flags definitions */ #define IGC_FLAG_HAS_MSI BIT(0) #define IGC_FLAG_QUEUE_PAIRS BIT(3) #define IGC_FLAG_DMAC BIT(4) #define IGC_FLAG_PTP BIT(8) +#define IGC_FLAG_WOL_SUPPORTED BIT(8) #define IGC_FLAG_NEED_LINK_UPDATE BIT(9) #define IGC_FLAG_MEDIA_RESET BIT(10) #define IGC_FLAG_MAS_ENABLE BIT(12) @@ -108,7 +115,7 @@ extern char igc_driver_version[]; #define IGC_RX_HDR_LEN IGC_RXBUFFER_256 /* Transmit and receive latency (for PTP timestamps) */ -/* FIXME: These values were estimated using the ones that i210 has as +/* FIXME: These values were estimated using the ones that i225 has as * basis, they seem to provide good numbers with ptp4l/phc2sys, but we * need to confirm them. */ @@ -319,7 +326,7 @@ struct igc_q_vector { struct net_device poll_dev; /* for dynamic allocation of rings associated with this q_vector */ - struct igc_ring ring[0] ____cacheline_internodealigned_in_smp; + struct igc_ring ring[] ____cacheline_internodealigned_in_smp; }; #define MAX_ETYPE_FILTER (4 - 1) @@ -552,6 +559,7 @@ int igc_erase_filter(struct igc_adapter *adapter, void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); +void igc_ptp_suspend(struct igc_adapter *adapter); void igc_ptp_stop(struct igc_adapter *adapter); void igc_ptp_rx_rgtstamp(struct igc_q_vector *q_vector, struct sk_buff *skb); void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 58efa7a02c68..4ddccccf42cc 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -16,7 +16,10 @@ /* Wake Up Filter Control */ #define IGC_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */ +#define IGC_WUFC_MAG 0x00000002 /* Magic Packet Wakeup Enable */ +#define IGC_WUFC_EX 0x00000004 /* Directed Exact Wakeup Enable */ #define IGC_WUFC_MC 0x00000008 /* Directed Multicast Wakeup Enable */ +#define IGC_WUFC_BC 0x00000010 /* Broadcast Wakeup Enable */ #define IGC_CTRL_ADVD3WUC 0x00100000 /* D3 WUC */ @@ -259,6 +262,9 @@ #define IGC_GPIE_EIAME 0x40000000 #define IGC_GPIE_PBA 0x80000000 +/* Receive Descriptor bit definitions */ +#define IGC_RXD_STAT_DD 0x01 /* Descriptor Done */ + /* Transmit Descriptor bit definitions */ #define IGC_TXD_DTYP_D 0x00100000 /* Data Descriptor */ #define IGC_TXD_DTYP_C 0x00000000 /* Context Descriptor */ diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c new file mode 100644 index 000000000000..657ab50ae296 --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_dump.c @@ -0,0 +1,323 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Intel Corporation */ + +#include "igc.h" + +struct igc_reg_info { + u32 ofs; + char *name; +}; + +static const struct igc_reg_info igc_reg_info_tbl[] = { + /* General Registers */ + {IGC_CTRL, "CTRL"}, + {IGC_STATUS, "STATUS"}, + {IGC_CTRL_EXT, "CTRL_EXT"}, + {IGC_MDIC, "MDIC"}, + + /* Interrupt Registers */ + {IGC_ICR, "ICR"}, + + /* RX Registers */ + {IGC_RCTL, "RCTL"}, + {IGC_RDLEN(0), "RDLEN"}, + {IGC_RDH(0), "RDH"}, + {IGC_RDT(0), "RDT"}, + {IGC_RXDCTL(0), "RXDCTL"}, + {IGC_RDBAL(0), "RDBAL"}, + {IGC_RDBAH(0), "RDBAH"}, + + /* TX Registers */ + {IGC_TCTL, "TCTL"}, + {IGC_TDBAL(0), "TDBAL"}, + {IGC_TDBAH(0), "TDBAH"}, + {IGC_TDLEN(0), "TDLEN"}, + {IGC_TDH(0), "TDH"}, + {IGC_TDT(0), "TDT"}, + {IGC_TXDCTL(0), "TXDCTL"}, + {IGC_TDFH, "TDFH"}, + {IGC_TDFT, "TDFT"}, + {IGC_TDFHS, "TDFHS"}, + {IGC_TDFPC, "TDFPC"}, + + /* List Terminator */ + {} +}; + +/* igc_regdump - register printout routine */ +static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo) +{ + int n = 0; + char rname[16]; + u32 regs[8]; + + switch (reginfo->ofs) { + case IGC_RDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDLEN(n)); + break; + case IGC_RDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDH(n)); + break; + case IGC_RDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDT(n)); + break; + case IGC_RXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RXDCTL(n)); + break; + case IGC_RDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDBAL(n)); + break; + case IGC_RDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDBAH(n)); + break; + case IGC_TDBAL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_RDBAL(n)); + break; + case IGC_TDBAH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_TDBAH(n)); + break; + case IGC_TDLEN(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_TDLEN(n)); + break; + case IGC_TDH(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_TDH(n)); + break; + case IGC_TDT(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_TDT(n)); + break; + case IGC_TXDCTL(0): + for (n = 0; n < 4; n++) + regs[n] = rd32(IGC_TXDCTL(n)); + break; + default: + pr_info("%-15s %08x\n", reginfo->name, rd32(reginfo->ofs)); + return; + } + + snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]"); + pr_info("%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1], + regs[2], regs[3]); +} + +/* igc_rings_dump - Tx-rings and Rx-rings */ +void igc_rings_dump(struct igc_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct my_u0 { u64 a; u64 b; } *u0; + union igc_adv_tx_desc *tx_desc; + union igc_adv_rx_desc *rx_desc; + struct igc_ring *tx_ring; + struct igc_ring *rx_ring; + u32 staterr; + u16 i, n; + + if (!netif_msg_hw(adapter)) + return; + + /* Print netdevice Info */ + if (netdev) { + dev_info(&adapter->pdev->dev, "Net device Info\n"); + pr_info("Device Name state trans_start\n"); + pr_info("%-15s %016lX %016lX\n", netdev->name, + netdev->state, dev_trans_start(netdev)); + } + + /* Print TX Ring Summary */ + if (!netdev || !netif_running(netdev)) + goto exit; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n"); + for (n = 0; n < adapter->num_tx_queues; n++) { + struct igc_tx_buffer *buffer_info; + + tx_ring = adapter->tx_ring[n]; + buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; + + pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n", + n, tx_ring->next_to_use, tx_ring->next_to_clean, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp); + } + + /* Print TX Rings */ + if (!netif_msg_tx_done(adapter)) + goto rx_ring_summary; + + dev_info(&adapter->pdev->dev, "TX Rings Dump\n"); + + /* Transmit Descriptor Formats + * + * Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 | PAYLEN | PORTS |CC|IDX | STA | DCMD |DTYP|MAC|RSV| DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 38 36 35 32 31 24 15 0 + */ + + for (n = 0; n < adapter->num_tx_queues; n++) { + tx_ring = adapter->tx_ring[n]; + pr_info("------------------------------------\n"); + pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index); + pr_info("------------------------------------\n"); + pr_info("T [desc] [address 63:0 ] [PlPOCIStDDM Ln] [bi->dma ] leng ntw timestamp bi->skb\n"); + + for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { + const char *next_desc; + struct igc_tx_buffer *buffer_info; + + tx_desc = IGC_TX_DESC(tx_ring, i); + buffer_info = &tx_ring->tx_buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + if (i == tx_ring->next_to_use && + i == tx_ring->next_to_clean) + next_desc = " NTC/U"; + else if (i == tx_ring->next_to_use) + next_desc = " NTU"; + else if (i == tx_ring->next_to_clean) + next_desc = " NTC"; + else + next_desc = ""; + + pr_info("T [0x%03X] %016llX %016llX %016llX %04X %p %016llX %p%s\n", + i, le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp, + buffer_info->skb, next_desc); + + if (netif_msg_pktdata(adapter) && buffer_info->skb) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, buffer_info->skb->data, + dma_unmap_len(buffer_info, len), + true); + } + } + + /* Print RX Rings Summary */ +rx_ring_summary: + dev_info(&adapter->pdev->dev, "RX Rings Summary\n"); + pr_info("Queue [NTU] [NTC]\n"); + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + pr_info(" %5d %5X %5X\n", + n, rx_ring->next_to_use, rx_ring->next_to_clean); + } + + /* Print RX Rings */ + if (!netif_msg_rx_status(adapter)) + goto exit; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + + /* Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 17 16 4 3 0 + * +------------------------------------------------------+ + * 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS | + * | Checksum Ident | | | | Type | Type | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + */ + + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + pr_info("------------------------------------\n"); + pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); + pr_info("------------------------------------\n"); + pr_info("R [desc] [ PktBuf A0] [ HeadBuf DD] [bi->dma ] [bi->skb] <-- Adv Rx Read format\n"); + pr_info("RWB[desc] [PcsmIpSHl PtRs] [vl er S cks ln] ---------------- [bi->skb] <-- Adv Rx Write-Back format\n"); + + for (i = 0; i < rx_ring->count; i++) { + const char *next_desc; + struct igc_rx_buffer *buffer_info; + + buffer_info = &rx_ring->rx_buffer_info[i]; + rx_desc = IGC_RX_DESC(rx_ring, i); + u0 = (struct my_u0 *)rx_desc; + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + + if (i == rx_ring->next_to_use) + next_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + next_desc = " NTC"; + else + next_desc = ""; + + if (staterr & IGC_RXD_STAT_DD) { + /* Descriptor Done */ + pr_info("%s[0x%03X] %016llX %016llX ---------------- %s\n", + "RWB", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + next_desc); + } else { + pr_info("%s[0x%03X] %016llX %016llX %016llX %s\n", + "R ", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)buffer_info->dma, + next_desc); + + if (netif_msg_pktdata(adapter) && + buffer_info->dma && buffer_info->page) { + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, + page_address + (buffer_info->page) + + buffer_info->page_offset, + igc_rx_bufsz(rx_ring), + true); + } + } + } + } + +exit: + return; +} + +/* igc_regs_dump - registers dump */ +void igc_regs_dump(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + struct igc_reg_info *reginfo; + + /* Print Registers */ + dev_info(&adapter->pdev->dev, "Register Dump\n"); + pr_info(" Register Name Value\n"); + for (reginfo = (struct igc_reg_info *)igc_reg_info_tbl; + reginfo->name; reginfo++) { + igc_regdump(hw, reginfo); + } +} diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index ee07011e13e9..69f50b8e2af3 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -308,6 +308,65 @@ static void igc_get_regs(struct net_device *netdev, regs_buff[168 + i] = rd32(IGC_TXDCTL(i)); } +static void igc_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + wol->wolopts = 0; + + if (!(adapter->flags & IGC_FLAG_WOL_SUPPORTED)) + return; + + wol->supported = WAKE_UCAST | WAKE_MCAST | + WAKE_BCAST | WAKE_MAGIC | + WAKE_PHY; + + /* apply any specific unsupported masks here */ + switch (adapter->hw.device_id) { + default: + break; + } + + if (adapter->wol & IGC_WUFC_EX) + wol->wolopts |= WAKE_UCAST; + if (adapter->wol & IGC_WUFC_MC) + wol->wolopts |= WAKE_MCAST; + if (adapter->wol & IGC_WUFC_BC) + wol->wolopts |= WAKE_BCAST; + if (adapter->wol & IGC_WUFC_MAG) + wol->wolopts |= WAKE_MAGIC; + if (adapter->wol & IGC_WUFC_LNKC) + wol->wolopts |= WAKE_PHY; +} + +static int igc_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER)) + return -EOPNOTSUPP; + + if (!(adapter->flags & IGC_FLAG_WOL_SUPPORTED)) + return wol->wolopts ? -EOPNOTSUPP : 0; + + /* these settings will always override what we currently have */ + adapter->wol = 0; + + if (wol->wolopts & WAKE_UCAST) + adapter->wol |= IGC_WUFC_EX; + if (wol->wolopts & WAKE_MCAST) + adapter->wol |= IGC_WUFC_MC; + if (wol->wolopts & WAKE_BCAST) + adapter->wol |= IGC_WUFC_BC; + if (wol->wolopts & WAKE_MAGIC) + adapter->wol |= IGC_WUFC_MAG; + if (wol->wolopts & WAKE_PHY) + adapter->wol |= IGC_WUFC_LNKC; + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + static u32 igc_get_msglevel(struct net_device *netdev) { struct igc_adapter *adapter = netdev_priv(netdev); @@ -1859,6 +1918,8 @@ static const struct ethtool_ops igc_ethtool_ops = { .get_drvinfo = igc_get_drvinfo, .get_regs_len = igc_get_regs_len, .get_regs = igc_get_regs, + .get_wol = igc_get_wol, + .set_wol = igc_set_wol, .get_msglevel = igc_get_msglevel, .set_msglevel = igc_set_msglevel, .nway_reset = igc_nway_reset, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index d9d5425fe8d9..69fa1ce1f927 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3546,6 +3546,8 @@ static void igc_reset_task(struct work_struct *work) adapter = container_of(work, struct igc_adapter, reset_task); + igc_rings_dump(adapter); + igc_regs_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igc_reinit_locked(adapter); } @@ -4029,6 +4031,9 @@ static void igc_watchdog_task(struct work_struct *work) } } if (link) { + /* Cancel scheduled suspend requests. */ + pm_runtime_resume(netdev->dev.parent); + if (!netif_carrier_ok(netdev)) { u32 ctrl; @@ -4114,6 +4119,8 @@ no_wait: return; } } + pm_schedule_suspend(netdev->dev.parent, + MSEC_PER_SEC * 5); /* also check for alternate media here */ } else if (!netif_carrier_ok(netdev) && @@ -4337,6 +4344,7 @@ request_done: static int __igc_open(struct net_device *netdev, bool resuming) { struct igc_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; int err = 0; int i = 0; @@ -4348,6 +4356,9 @@ static int __igc_open(struct net_device *netdev, bool resuming) return -EBUSY; } + if (!resuming) + pm_runtime_get_sync(&pdev->dev); + netif_carrier_off(netdev); /* allocate transmit descriptors */ @@ -4386,6 +4397,9 @@ static int __igc_open(struct net_device *netdev, bool resuming) rd32(IGC_ICR); igc_irq_enable(adapter); + if (!resuming) + pm_runtime_put(&pdev->dev); + netif_tx_start_all_queues(netdev); /* start the watchdog. */ @@ -4404,6 +4418,8 @@ err_setup_rx: igc_free_all_tx_resources(adapter); err_setup_tx: igc_reset(adapter); + if (!resuming) + pm_runtime_put(&pdev->dev); return err; } @@ -4428,9 +4444,13 @@ static int igc_open(struct net_device *netdev) static int __igc_close(struct net_device *netdev, bool suspending) { struct igc_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; WARN_ON(test_bit(__IGC_RESETTING, &adapter->state)); + if (!suspending) + pm_runtime_get_sync(&pdev->dev); + igc_down(adapter); igc_release_hw_control(adapter); @@ -4440,6 +4460,9 @@ static int __igc_close(struct net_device *netdev, bool suspending) igc_free_all_tx_resources(adapter); igc_free_all_rx_resources(adapter); + if (!suspending) + pm_runtime_put_sync(&pdev->dev); + return 0; } @@ -4766,6 +4789,16 @@ static int igc_probe(struct pci_dev *pdev, hw->fc.requested_mode = igc_fc_default; hw->fc.current_mode = igc_fc_default; + /* By default, support wake on port A */ + adapter->flags |= IGC_FLAG_WOL_SUPPORTED; + + /* initialize the wol settings based on the eeprom settings */ + if (adapter->flags & IGC_FLAG_WOL_SUPPORTED) + adapter->wol |= IGC_WUFC_MAG; + + device_set_wakeup_enable(&adapter->pdev->dev, + adapter->flags & IGC_FLAG_WOL_SUPPORTED); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -4792,6 +4825,10 @@ static int igc_probe(struct pci_dev *pdev, pcie_print_link_status(pdev); netdev_info(netdev, "MAC: %pM\n", netdev->dev_addr); + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP); + + pm_runtime_put_noidle(&pdev->dev); + return 0; err_register: @@ -4826,6 +4863,8 @@ static void igc_remove(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + pm_runtime_get_noresume(&pdev->dev); + igc_ptp_stop(adapter); set_bit(__IGC_DOWN, &adapter->state); @@ -4870,6 +4909,8 @@ static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake, if (netif_running(netdev)) __igc_close(netdev, true); + igc_ptp_suspend(adapter); + igc_clear_interrupt_scheme(adapter); rtnl_unlock(); @@ -5045,6 +5086,108 @@ static void igc_shutdown(struct pci_dev *pdev) } } +/** + * igc_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current PCI connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + **/ +static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igc_adapter *adapter = netdev_priv(netdev); + + netif_device_detach(netdev); + + if (state == pci_channel_io_perm_failure) + return PCI_ERS_RESULT_DISCONNECT; + + if (netif_running(netdev)) + igc_down(adapter); + pci_disable_device(pdev); + + /* Request a slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * igc_io_slot_reset - called after the PCI bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the igc_resume routine. + **/ +static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + pci_ers_result_t result; + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Could not re-enable PCI device after reset.\n"); + result = PCI_ERS_RESULT_DISCONNECT; + } else { + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + + pci_enable_wake(pdev, PCI_D3hot, 0); + pci_enable_wake(pdev, PCI_D3cold, 0); + + /* In case of PCI error, adapter loses its HW address + * so we should re-assign it here. + */ + hw->hw_addr = adapter->io_addr; + + igc_reset(adapter); + wr32(IGC_WUS, ~0); + result = PCI_ERS_RESULT_RECOVERED; + } + + return result; +} + +/** + * igc_io_resume - called when traffic can start to flow again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the igc_resume routine. + */ +static void igc_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igc_adapter *adapter = netdev_priv(netdev); + + rtnl_lock(); + if (netif_running(netdev)) { + if (igc_open(netdev)) { + dev_err(&pdev->dev, "igc_open failed after reset\n"); + return; + } + } + + netif_device_attach(netdev); + + /* let the f/w know that the h/w is now under the control of the + * driver. + */ + igc_get_hw_control(adapter); + rtnl_unlock(); +} + +static const struct pci_error_handlers igc_err_handler = { + .error_detected = igc_io_error_detected, + .slot_reset = igc_io_slot_reset, + .resume = igc_io_resume, +}; + #ifdef CONFIG_PM static const struct dev_pm_ops igc_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume) @@ -5062,6 +5205,7 @@ static struct pci_driver igc_driver = { .driver.pm = &igc_pm_ops, #endif .shutdown = igc_shutdown, + .err_handler = &igc_err_handler, }; /** diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 693506587198..f99c514ad0f4 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -509,7 +509,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) * This work function polls the TSYNCTXCTL valid bit to determine when a * timestamp has been taken for the current stored skb. */ -void igc_ptp_tx_work(struct work_struct *work) +static void igc_ptp_tx_work(struct work_struct *work) { struct igc_adapter *adapter = container_of(work, struct igc_adapter, ptp_tx_work); diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index c9029b549b90..d4af53a80f11 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -17,6 +17,11 @@ /* Internal Packet Buffer Size Registers */ #define IGC_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */ #define IGC_TXPBS 0x03404 /* Tx Packet Buffer Size - RW */ +#define IGC_TDFH 0x03410 /* Tx Data FIFO Head - RW */ +#define IGC_TDFT 0x03418 /* Tx Data FIFO Tail - RW */ +#define IGC_TDFHS 0x03420 /* Tx Data FIFO Head Saved - RW */ +#define IGC_TDFTS 0x03428 /* Tx Data FIFO Tail Saved - RW */ +#define IGC_TDFPC 0x03430 /* Tx Data FIFO Packet Count - RW */ /* NVM Register Descriptions */ #define IGC_EERD 0x12014 /* EEprom mode read - RW */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 39e73ad60352..2833e4f041ce 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -462,7 +462,7 @@ struct ixgbe_q_vector { char name[IFNAMSIZ + 9]; /* for dynamic allocation of rings associated with this q_vector */ - struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp; + struct ixgbe_ring ring[] ____cacheline_internodealigned_in_smp; }; #ifdef CONFIG_IXGBE_HWMON diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 2e4975572e9f..de3c7ce9353c 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2077,12 +2077,7 @@ jme_tx_tso(struct sk_buff *skb, __le16 *mss, u8 *flags) IPPROTO_TCP, 0); } else { - struct ipv6hdr *ip6h = ipv6_hdr(skb); - - tcp_hdr(skb)->check = ~csum_ipv6_magic(&ip6h->saddr, - &ip6h->daddr, 0, - IPPROTO_TCP, - 0); + tcp_v6_gso_csum_prep(skb); } return 0; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 98017e7d5dd0..b22eeb5f8700 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -341,6 +341,11 @@ enum { ETHTOOL_STAT_EEE_WAKEUP, ETHTOOL_STAT_SKB_ALLOC_ERR, ETHTOOL_STAT_REFILL_ERR, + ETHTOOL_XDP_REDIRECT, + ETHTOOL_XDP_PASS, + ETHTOOL_XDP_DROP, + ETHTOOL_XDP_XMIT, + ETHTOOL_XDP_TX, ETHTOOL_MAX_STATS, }; @@ -354,10 +359,10 @@ struct mvneta_statistic { #define T_REG_64 64 #define T_SW 1 -#define MVNETA_XDP_PASS BIT(0) -#define MVNETA_XDP_DROPPED BIT(1) -#define MVNETA_XDP_TX BIT(2) -#define MVNETA_XDP_REDIR BIT(3) +#define MVNETA_XDP_PASS 0 +#define MVNETA_XDP_DROPPED BIT(0) +#define MVNETA_XDP_TX BIT(1) +#define MVNETA_XDP_REDIR BIT(2) static const struct mvneta_statistic mvneta_statistics[] = { { 0x3000, T_REG_64, "good_octets_received", }, @@ -395,16 +400,38 @@ static const struct mvneta_statistic mvneta_statistics[] = { { ETHTOOL_STAT_EEE_WAKEUP, T_SW, "eee_wakeup_errors", }, { ETHTOOL_STAT_SKB_ALLOC_ERR, T_SW, "skb_alloc_errors", }, { ETHTOOL_STAT_REFILL_ERR, T_SW, "refill_errors", }, + { ETHTOOL_XDP_REDIRECT, T_SW, "rx_xdp_redirect", }, + { ETHTOOL_XDP_PASS, T_SW, "rx_xdp_pass", }, + { ETHTOOL_XDP_DROP, T_SW, "rx_xdp_drop", }, + { ETHTOOL_XDP_TX, T_SW, "rx_xdp_tx", }, + { ETHTOOL_XDP_XMIT, T_SW, "tx_xdp_xmit", }, }; -struct mvneta_pcpu_stats { - struct u64_stats_sync syncp; +struct mvneta_stats { u64 rx_packets; u64 rx_bytes; - u64 rx_dropped; - u64 rx_errors; u64 tx_packets; u64 tx_bytes; + /* xdp */ + u64 xdp_redirect; + u64 xdp_pass; + u64 xdp_drop; + u64 xdp_xmit; + u64 xdp_tx; +}; + +struct mvneta_ethtool_stats { + struct mvneta_stats ps; + u64 skb_alloc_error; + u64 refill_error; +}; + +struct mvneta_pcpu_stats { + struct u64_stats_sync syncp; + + struct mvneta_ethtool_stats es; + u64 rx_dropped; + u64 rx_errors; }; struct mvneta_pcpu_port { @@ -660,10 +687,6 @@ struct mvneta_rx_queue { /* pointer to uncomplete skb buffer */ struct sk_buff *skb; int left_size; - - /* error counters */ - u32 skb_alloc_err; - u32 refill_err; }; static enum cpuhp_state online_hpstate; @@ -748,12 +771,12 @@ mvneta_get_stats64(struct net_device *dev, cpu_stats = per_cpu_ptr(pp->stats, cpu); do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - rx_packets = cpu_stats->rx_packets; - rx_bytes = cpu_stats->rx_bytes; + rx_packets = cpu_stats->es.ps.rx_packets; + rx_bytes = cpu_stats->es.ps.rx_bytes; rx_dropped = cpu_stats->rx_dropped; rx_errors = cpu_stats->rx_errors; - tx_packets = cpu_stats->tx_packets; - tx_bytes = cpu_stats->tx_bytes; + tx_packets = cpu_stats->es.ps.tx_packets; + tx_bytes = cpu_stats->es.ps.tx_bytes; } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); stats->rx_packets += rx_packets; @@ -1933,7 +1956,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, if (!data || !(rx_desc->buf_phys_addr)) continue; - page_pool_put_page(rxq->page_pool, data, false); + page_pool_put_full_page(rxq->page_pool, data, false); } if (xdp_rxq_info_is_reg(&rxq->xdp_rxq)) xdp_rxq_info_unreg(&rxq->xdp_rxq); @@ -1942,19 +1965,18 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, } static void -mvneta_update_stats(struct mvneta_port *pp, u32 pkts, - u32 len, bool tx) +mvneta_update_stats(struct mvneta_port *pp, + struct mvneta_stats *ps) { struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); u64_stats_update_begin(&stats->syncp); - if (tx) { - stats->tx_packets += pkts; - stats->tx_bytes += len; - } else { - stats->rx_packets += pkts; - stats->rx_bytes += len; - } + stats->es.ps.rx_packets += ps->rx_packets; + stats->es.ps.rx_bytes += ps->rx_bytes; + /* xdp */ + stats->es.ps.xdp_redirect += ps->xdp_redirect; + stats->es.ps.xdp_pass += ps->xdp_pass; + stats->es.ps.xdp_drop += ps->xdp_drop; u64_stats_update_end(&stats->syncp); } @@ -1969,9 +1991,15 @@ int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) rx_desc = rxq->descs + curr_desc; if (!(rx_desc->buf_phys_addr)) { if (mvneta_rx_refill(pp, rx_desc, rxq, GFP_ATOMIC)) { + struct mvneta_pcpu_stats *stats; + pr_err("Can't refill queue %d. Done %d from %d\n", rxq->id, i, rxq->refill_num); - rxq->refill_err++; + + stats = this_cpu_ptr(pp->stats); + u64_stats_update_begin(&stats->syncp); + stats->es.refill_error++; + u64_stats_update_end(&stats->syncp); break; } } @@ -2021,7 +2049,6 @@ mvneta_xdp_submit_frame(struct mvneta_port *pp, struct mvneta_tx_queue *txq, tx_desc->buf_phys_addr = dma_addr; tx_desc->data_size = xdpf->len; - mvneta_update_stats(pp, 1, xdpf->len, true); mvneta_txq_inc_put(txq); txq->pending++; txq->count++; @@ -2048,8 +2075,17 @@ mvneta_xdp_xmit_back(struct mvneta_port *pp, struct xdp_buff *xdp) __netif_tx_lock(nq, cpu); ret = mvneta_xdp_submit_frame(pp, txq, xdpf, false); - if (ret == MVNETA_XDP_TX) + if (ret == MVNETA_XDP_TX) { + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + + u64_stats_update_begin(&stats->syncp); + stats->es.ps.tx_bytes += xdpf->len; + stats->es.ps.tx_packets++; + stats->es.ps.xdp_tx++; + u64_stats_update_end(&stats->syncp); + mvneta_txq_pend_desc_add(pp, txq, 0); + } __netif_tx_unlock(nq); return ret; @@ -2060,10 +2096,11 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, struct xdp_frame **frames, u32 flags) { struct mvneta_port *pp = netdev_priv(dev); + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + int i, nxmit_byte = 0, nxmit = num_frame; int cpu = smp_processor_id(); struct mvneta_tx_queue *txq; struct netdev_queue *nq; - int i, drops = 0; u32 ret; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -2075,9 +2112,11 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, __netif_tx_lock(nq, cpu); for (i = 0; i < num_frame; i++) { ret = mvneta_xdp_submit_frame(pp, txq, frames[i], true); - if (ret != MVNETA_XDP_TX) { + if (ret == MVNETA_XDP_TX) { + nxmit_byte += frames[i]->len; + } else { xdp_return_frame_rx_napi(frames[i]); - drops++; + nxmit--; } } @@ -2085,12 +2124,19 @@ mvneta_xdp_xmit(struct net_device *dev, int num_frame, mvneta_txq_pend_desc_add(pp, txq, 0); __netif_tx_unlock(nq); - return num_frame - drops; + u64_stats_update_begin(&stats->syncp); + stats->es.ps.tx_bytes += nxmit_byte; + stats->es.ps.tx_packets += nxmit; + stats->es.ps.xdp_xmit += nxmit; + u64_stats_update_end(&stats->syncp); + + return nxmit; } static int mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, - struct bpf_prog *prog, struct xdp_buff *xdp) + struct bpf_prog *prog, struct xdp_buff *xdp, + struct mvneta_stats *stats) { unsigned int len; u32 ret, act; @@ -2100,28 +2146,29 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, switch (act) { case XDP_PASS: - ret = MVNETA_XDP_PASS; - break; + stats->xdp_pass++; + return MVNETA_XDP_PASS; case XDP_REDIRECT: { int err; err = xdp_do_redirect(pp->dev, xdp, prog); if (err) { ret = MVNETA_XDP_DROPPED; - __page_pool_put_page(rxq->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(rxq->page_pool, + virt_to_head_page(xdp->data), len, + true); } else { ret = MVNETA_XDP_REDIR; + stats->xdp_redirect++; } break; } case XDP_TX: ret = mvneta_xdp_xmit_back(pp, xdp); if (ret != MVNETA_XDP_TX) - __page_pool_put_page(rxq->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(rxq->page_pool, + virt_to_head_page(xdp->data), len, + true); break; default: bpf_warn_invalid_xdp_action(act); @@ -2130,13 +2177,16 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, trace_xdp_exception(pp->dev, prog, act); /* fall through */ case XDP_DROP: - __page_pool_put_page(rxq->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(rxq->page_pool, + virt_to_head_page(xdp->data), len, true); ret = MVNETA_XDP_DROPPED; + stats->xdp_drop++; break; } + stats->rx_bytes += xdp->data_end - xdp->data; + stats->rx_packets++; + return ret; } @@ -2146,12 +2196,14 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, - struct page *page, u32 *xdp_ret) + struct page *page, + struct mvneta_stats *stats) { unsigned char *data = page_address(page); int data_len = -MVNETA_MH_SIZE, len; struct net_device *dev = pp->dev; enum dma_data_direction dma_dir; + int ret = 0; if (MVNETA_SKB_SIZE(rx_desc->data_size) > PAGE_SIZE) { len = MVNETA_MAX_RX_BUF_SIZE; @@ -2175,17 +2227,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, xdp_set_data_meta_invalid(xdp); if (xdp_prog) { - u32 ret; - - ret = mvneta_run_xdp(pp, rxq, xdp_prog, xdp); - if (ret != MVNETA_XDP_PASS) { - mvneta_update_stats(pp, 1, - xdp->data_end - xdp->data, - false); - rx_desc->buf_phys_addr = 0; - *xdp_ret |= ret; - return ret; - } + ret = mvneta_run_xdp(pp, rxq, xdp_prog, xdp, stats); + if (ret) + goto out; } rxq->skb = build_skb(xdp->data_hard_start, PAGE_SIZE); @@ -2193,9 +2237,9 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); netdev_err(dev, "Can't allocate skb on queue %d\n", rxq->id); - rxq->skb_alloc_err++; u64_stats_update_begin(&stats->syncp); + stats->es.skb_alloc_error++; stats->rx_dropped++; u64_stats_update_end(&stats->syncp); @@ -2209,9 +2253,11 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp, mvneta_rx_csum(pp, rx_desc->status, rxq->skb); rxq->left_size = rx_desc->data_size - len; + +out: rx_desc->buf_phys_addr = 0; - return 0; + return ret; } static void @@ -2252,12 +2298,11 @@ static int mvneta_rx_swbm(struct napi_struct *napi, struct mvneta_port *pp, int budget, struct mvneta_rx_queue *rxq) { - int rcvd_pkts = 0, rcvd_bytes = 0, rx_proc = 0; + int rx_proc = 0, rx_todo, refill; struct net_device *dev = pp->dev; + struct mvneta_stats ps = {}; struct bpf_prog *xdp_prog; struct xdp_buff xdp_buf; - int rx_todo, refill; - u32 xdp_ret = 0; /* Get number of received packets */ rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); @@ -2290,7 +2335,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, } err = mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf, - xdp_prog, page, &xdp_ret); + xdp_prog, page, &ps); if (err) continue; } else { @@ -2314,8 +2359,9 @@ static int mvneta_rx_swbm(struct napi_struct *napi, rxq->skb = NULL; continue; } - rcvd_pkts++; - rcvd_bytes += rxq->skb->len; + + ps.rx_bytes += rxq->skb->len; + ps.rx_packets++; /* Linux processing */ rxq->skb->protocol = eth_type_trans(rxq->skb, dev); @@ -2327,11 +2373,11 @@ static int mvneta_rx_swbm(struct napi_struct *napi, } rcu_read_unlock(); - if (xdp_ret & MVNETA_XDP_REDIR) + if (ps.xdp_redirect) xdp_do_flush_map(); - if (rcvd_pkts) - mvneta_update_stats(pp, rcvd_pkts, rcvd_bytes, false); + if (ps.rx_packets) + mvneta_update_stats(pp, &ps); /* return some buffers to hardware queue, one at a time is too slow */ refill = mvneta_rx_refill_queue(pp, rxq); @@ -2339,7 +2385,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, /* Update rxq management counters */ mvneta_rxq_desc_num_update(pp, rxq, rx_proc, refill); - return rcvd_pkts; + return ps.rx_packets; } /* Main rx processing when using hardware buffer management */ @@ -2423,8 +2469,15 @@ err_drop_frame: /* Refill processing */ err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC); if (err) { + struct mvneta_pcpu_stats *stats; + netdev_err(dev, "Linux processing - Can't refill\n"); - rxq->refill_err++; + + stats = this_cpu_ptr(pp->stats); + u64_stats_update_begin(&stats->syncp); + stats->es.refill_error++; + u64_stats_update_end(&stats->syncp); + goto err_drop_frame_ret_pool; } @@ -2454,8 +2507,14 @@ err_drop_frame: napi_gro_receive(napi, skb); } - if (rcvd_pkts) - mvneta_update_stats(pp, rcvd_pkts, rcvd_bytes, false); + if (rcvd_pkts) { + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); + + u64_stats_update_begin(&stats->syncp); + stats->es.ps.rx_packets += rcvd_pkts; + stats->es.ps.rx_bytes += rcvd_bytes; + u64_stats_update_end(&stats->syncp); + } /* Update rxq management counters */ mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done); @@ -2711,6 +2770,7 @@ static netdev_tx_t mvneta_tx(struct sk_buff *skb, struct net_device *dev) out: if (frags > 0) { struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id); + struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); netdev_tx_sent_queue(nq, len); @@ -2724,7 +2784,10 @@ out: else txq->pending += frags; - mvneta_update_stats(pp, 1, len, true); + u64_stats_update_begin(&stats->syncp); + stats->es.ps.tx_bytes += len; + stats->es.ps.tx_packets++; + u64_stats_update_end(&stats->syncp); } else { dev->stats.tx_dropped++; dev_kfree_skb_any(skb); @@ -3767,13 +3830,9 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, new_clk = gmac_clk & ~MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = gmac_an & ~(MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_INBAND_RESTART_AN | - MVNETA_GMAC_CONFIG_MII_SPEED | - MVNETA_GMAC_CONFIG_GMII_SPEED | MVNETA_GMAC_AN_SPEED_EN | MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL | - MVNETA_GMAC_CONFIG_FLOW_CTRL | MVNETA_GMAC_AN_FLOW_CTRL_EN | - MVNETA_GMAC_CONFIG_FULL_DUPLEX | MVNETA_GMAC_AN_DUPLEX_EN); /* Even though it might look weird, when we're configured in @@ -3788,24 +3847,20 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, if (phylink_test(state->advertising, Pause)) new_an |= MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL; - if (state->pause & MLO_PAUSE_TXRX_MASK) - new_an |= MVNETA_GMAC_CONFIG_FLOW_CTRL; if (!phylink_autoneg_inband(mode)) { - /* Phy or fixed speed */ - if (state->duplex) - new_an |= MVNETA_GMAC_CONFIG_FULL_DUPLEX; - - if (state->speed == SPEED_1000 || state->speed == SPEED_2500) - new_an |= MVNETA_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - new_an |= MVNETA_GMAC_CONFIG_MII_SPEED; + /* Phy or fixed speed - nothing to do, leave the + * configured speed, duplex and flow control as-is. + */ } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII mode receives the state from the PHY */ new_ctrl2 |= MVNETA_GMAC2_INBAND_AN_ENABLE; new_clk |= MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS)) | + MVNETA_GMAC_FORCE_LINK_PASS | + MVNETA_GMAC_CONFIG_MII_SPEED | + MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FULL_DUPLEX)) | MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_AN_SPEED_EN | MVNETA_GMAC_AN_DUPLEX_EN; @@ -3814,7 +3869,8 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, new_ctrl0 |= MVNETA_GMAC0_PORT_1000BASE_X; new_clk |= MVNETA_GMAC_1MS_CLOCK_ENABLE; new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS)) | + MVNETA_GMAC_FORCE_LINK_PASS | + MVNETA_GMAC_CONFIG_MII_SPEED)) | MVNETA_GMAC_INBAND_AN_ENABLE | MVNETA_GMAC_CONFIG_GMII_SPEED | /* The MAC only supports FD mode */ @@ -3902,9 +3958,11 @@ static void mvneta_mac_link_down(struct phylink_config *config, mvneta_set_eee(pp, false); } -static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) +static void mvneta_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *ndev = to_net_dev(config->dev); struct mvneta_port *pp = netdev_priv(ndev); @@ -3912,8 +3970,36 @@ static void mvneta_mac_link_up(struct phylink_config *config, unsigned int mode, if (!phylink_autoneg_inband(mode)) { val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); - val &= ~MVNETA_GMAC_FORCE_LINK_DOWN; + val &= ~(MVNETA_GMAC_FORCE_LINK_DOWN | + MVNETA_GMAC_CONFIG_MII_SPEED | + MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FLOW_CTRL | + MVNETA_GMAC_CONFIG_FULL_DUPLEX); val |= MVNETA_GMAC_FORCE_LINK_PASS; + + if (speed == SPEED_1000 || speed == SPEED_2500) + val |= MVNETA_GMAC_CONFIG_GMII_SPEED; + else if (speed == SPEED_100) + val |= MVNETA_GMAC_CONFIG_MII_SPEED; + + if (duplex == DUPLEX_FULL) + val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX; + + if (tx_pause || rx_pause) + val |= MVNETA_GMAC_CONFIG_FLOW_CTRL; + + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); + } else { + /* When inband doesn't cover flow control or flow control is + * disabled, we need to manually configure it. This bit will + * only have effect if MVNETA_GMAC_AN_FLOW_CTRL_EN is unset. + */ + val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); + val &= ~MVNETA_GMAC_CONFIG_FLOW_CTRL; + + if (tx_pause || rx_pause) + val |= MVNETA_GMAC_CONFIG_FLOW_CTRL; + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); } @@ -4420,45 +4506,100 @@ static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset, } } +static void +mvneta_ethtool_update_pcpu_stats(struct mvneta_port *pp, + struct mvneta_ethtool_stats *es) +{ + unsigned int start; + int cpu; + + for_each_possible_cpu(cpu) { + struct mvneta_pcpu_stats *stats; + u64 skb_alloc_error; + u64 refill_error; + u64 xdp_redirect; + u64 xdp_pass; + u64 xdp_drop; + u64 xdp_xmit; + u64 xdp_tx; + + stats = per_cpu_ptr(pp->stats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + skb_alloc_error = stats->es.skb_alloc_error; + refill_error = stats->es.refill_error; + xdp_redirect = stats->es.ps.xdp_redirect; + xdp_pass = stats->es.ps.xdp_pass; + xdp_drop = stats->es.ps.xdp_drop; + xdp_xmit = stats->es.ps.xdp_xmit; + xdp_tx = stats->es.ps.xdp_tx; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + es->skb_alloc_error += skb_alloc_error; + es->refill_error += refill_error; + es->ps.xdp_redirect += xdp_redirect; + es->ps.xdp_pass += xdp_pass; + es->ps.xdp_drop += xdp_drop; + es->ps.xdp_xmit += xdp_xmit; + es->ps.xdp_tx += xdp_tx; + } +} + static void mvneta_ethtool_update_stats(struct mvneta_port *pp) { + struct mvneta_ethtool_stats stats = {}; const struct mvneta_statistic *s; void __iomem *base = pp->base; u32 high, low; u64 val; int i; + mvneta_ethtool_update_pcpu_stats(pp, &stats); for (i = 0, s = mvneta_statistics; s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics); s++, i++) { - val = 0; - switch (s->type) { case T_REG_32: val = readl_relaxed(base + s->offset); + pp->ethtool_stats[i] += val; break; case T_REG_64: /* Docs say to read low 32-bit then high */ low = readl_relaxed(base + s->offset); high = readl_relaxed(base + s->offset + 4); val = (u64)high << 32 | low; + pp->ethtool_stats[i] += val; break; case T_SW: switch (s->offset) { case ETHTOOL_STAT_EEE_WAKEUP: val = phylink_get_eee_err(pp->phylink); + pp->ethtool_stats[i] += val; break; case ETHTOOL_STAT_SKB_ALLOC_ERR: - val = pp->rxqs[0].skb_alloc_err; + pp->ethtool_stats[i] = stats.skb_alloc_error; break; case ETHTOOL_STAT_REFILL_ERR: - val = pp->rxqs[0].refill_err; + pp->ethtool_stats[i] = stats.refill_error; + break; + case ETHTOOL_XDP_REDIRECT: + pp->ethtool_stats[i] = stats.ps.xdp_redirect; + break; + case ETHTOOL_XDP_PASS: + pp->ethtool_stats[i] = stats.ps.xdp_pass; + break; + case ETHTOOL_XDP_DROP: + pp->ethtool_stats[i] = stats.ps.xdp_drop; + break; + case ETHTOOL_XDP_TX: + pp->ethtool_stats[i] = stats.ps.xdp_tx; + break; + case ETHTOOL_XDP_XMIT: + pp->ethtool_stats[i] = stats.ps.xdp_xmit; break; } break; } - - pp->ethtool_stats[i] += val; } } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 72133cbe55d4..6b9c7ed2547e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,8 +58,11 @@ static struct { */ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); -static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy); +static void mvpp2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -3473,8 +3476,9 @@ static void mvpp2_start_dev(struct mvpp2_port *port) .interface = port->phy_interface, }; mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state); - mvpp2_mac_link_up(&port->phylink_config, MLO_AN_INBAND, - port->phy_interface, NULL); + mvpp2_mac_link_up(&port->phylink_config, NULL, + MLO_AN_INBAND, port->phy_interface, + SPEED_UNKNOWN, DUPLEX_UNKNOWN, false, false); } netif_tx_start_all_queues(port->dev); @@ -4972,15 +4976,13 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | + an &= ~(MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | - MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN | - MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); + MVPP2_GMAC_AN_DUPLEX_EN | MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK; ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK); - ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); /* Configure port type */ if (phy_interface_mode_is_8023z(state->interface)) { @@ -5010,31 +5012,20 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, /* Configure negotiation style */ if (!phylink_autoneg_inband(mode)) { - /* Phy or fixed speed - no in-band AN */ - if (state->duplex) - an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; - - if (state->speed == SPEED_1000 || state->speed == SPEED_2500) - an |= MVPP2_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - an |= MVPP2_GMAC_CONFIG_MII_SPEED; - - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + /* Phy or fixed speed - no in-band AN, nothing to do, leave the + * configured speed, duplex and flow control as-is. + */ } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII in-band mode receives the speed and duplex from * the PHY. Flow control information is not received. */ - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); an |= MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_AN_DUPLEX_EN; - - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; } else if (phy_interface_mode_is_8023z(state->interface)) { /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can * they negotiate duplex: they are always operating with a fixed @@ -5042,19 +5033,17 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, * speed and full duplex here. */ ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; - an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); an |= MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_CONFIG_GMII_SPEED | MVPP2_GMAC_CONFIG_FULL_DUPLEX; - if (state->pause & MLO_PAUSE_AN && state->an_enabled) { + if (state->pause & MLO_PAUSE_AN && state->an_enabled) an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; - } else { - if (state->pause & MLO_PAUSE_TX) - ctrl4 |= MVPP22_CTRL4_TX_FC_EN; - if (state->pause & MLO_PAUSE_RX) - ctrl4 |= MVPP22_CTRL4_RX_FC_EN; - } } /* Some fields of the auto-negotiation register require the port to be down when @@ -5141,25 +5130,54 @@ static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, mvpp2_port_enable(port); } -static void mvpp2_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, struct phy_device *phy) +static void mvpp2_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct net_device *dev = to_net_dev(config->dev); struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode)) { - if (mvpp2_is_xlg(interface)) { + if (mvpp2_is_xlg(interface)) { + if (!phylink_autoneg_inband(mode)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_DOWN; val |= MVPP22_XLG_CTRL0_FORCE_LINK_PASS; writel(val, port->base + MVPP22_XLG_CTRL0_REG); - } else { + } + } else { + if (!phylink_autoneg_inband(mode)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - val &= ~MVPP2_GMAC_FORCE_LINK_DOWN; + val &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | + MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX); val |= MVPP2_GMAC_FORCE_LINK_PASS; + + if (speed == SPEED_1000 || speed == SPEED_2500) + val |= MVPP2_GMAC_CONFIG_GMII_SPEED; + else if (speed == SPEED_100) + val |= MVPP2_GMAC_CONFIG_MII_SPEED; + + if (duplex == DUPLEX_FULL) + val |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); } + + /* We can always update the flow control enable bits; + * these will only be effective if flow control AN + * (MVPP2_GMAC_FLOW_CTRL_AUTONEG) is disabled. + */ + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + val &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); + if (tx_pause) + val |= MVPP22_CTRL4_TX_FC_EN; + if (rx_pause) + val |= MVPP22_CTRL4_RX_FC_EN; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); } mvpp2_port_enable(port); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 5ca788691911..9f5b7229574e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -113,7 +113,6 @@ int cgx_get_cgxcnt_max(void) return idmax + 1; } -EXPORT_SYMBOL(cgx_get_cgxcnt_max); int cgx_get_lmac_cnt(void *cgxd) { @@ -124,7 +123,6 @@ int cgx_get_lmac_cnt(void *cgxd) return cgx->lmac_count; } -EXPORT_SYMBOL(cgx_get_lmac_cnt); void *cgx_get_pdata(int cgx_id) { @@ -136,7 +134,6 @@ void *cgx_get_pdata(int cgx_id) } return NULL; } -EXPORT_SYMBOL(cgx_get_pdata); int cgx_get_cgxid(void *cgxd) { @@ -164,7 +161,6 @@ int cgx_get_link_info(void *cgxd, int lmac_id, *linfo = lmac->link_info; return 0; } -EXPORT_SYMBOL(cgx_get_link_info); static u64 mac2u64 (u8 *mac_addr) { @@ -195,7 +191,6 @@ int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr) return 0; } -EXPORT_SYMBOL(cgx_lmac_addr_set); u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id) { @@ -205,7 +200,6 @@ u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id) cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8); return cfg & CGX_RX_DMAC_ADR_MASK; } -EXPORT_SYMBOL(cgx_lmac_addr_get); int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind) { @@ -217,7 +211,6 @@ int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind) cgx_write(cgx, lmac_id, CGXX_CMRX_RX_ID_MAP, (pkind & 0x3F)); return 0; } -EXPORT_SYMBOL(cgx_set_pkind); static inline u8 cgx_get_lmac_type(struct cgx *cgx, int lmac_id) { @@ -255,7 +248,6 @@ int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable) } return 0; } -EXPORT_SYMBOL(cgx_lmac_internal_loopback); void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable) { @@ -289,7 +281,6 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable) (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg); } } -EXPORT_SYMBOL(cgx_lmac_promisc_config); /* Enable or disable forwarding received pause frames to Tx block */ void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable) @@ -318,7 +309,6 @@ void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable) cgx_write(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL, cfg); } } -EXPORT_SYMBOL(cgx_lmac_enadis_rx_pause_fwding); int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat) { @@ -329,7 +319,6 @@ int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat) *rx_stat = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_STAT0 + (idx * 8)); return 0; } -EXPORT_SYMBOL(cgx_get_rx_stats); int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat) { @@ -340,7 +329,6 @@ int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat) *tx_stat = cgx_read(cgx, lmac_id, CGXX_CMRX_TX_STAT0 + (idx * 8)); return 0; } -EXPORT_SYMBOL(cgx_get_tx_stats); int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable) { @@ -358,7 +346,6 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable) cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg); return 0; } -EXPORT_SYMBOL(cgx_lmac_rx_tx_enable); int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable) { @@ -379,7 +366,6 @@ int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable) cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg); return !!(last & DATA_PKT_TX_EN); } -EXPORT_SYMBOL(cgx_lmac_tx_enable); /* CGX Firmware interface low level support */ static int cgx_fwi_cmd_send(u64 req, u64 *resp, struct lmac *lmac) @@ -610,7 +596,6 @@ int cgx_get_mkex_prfl_info(u64 *addr, u64 *size) return 0; } -EXPORT_SYMBOL(cgx_get_mkex_prfl_info); static irqreturn_t cgx_fwi_event_handler(int irq, void *data) { @@ -676,7 +661,6 @@ int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id) return 0; } -EXPORT_SYMBOL(cgx_lmac_evh_register); int cgx_lmac_evh_unregister(void *cgxd, int lmac_id) { @@ -695,7 +679,6 @@ int cgx_lmac_evh_unregister(void *cgxd, int lmac_id) return 0; } -EXPORT_SYMBOL(cgx_lmac_evh_unregister); static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable) { @@ -769,7 +752,6 @@ int cgx_lmac_linkup_start(void *cgxd) return 0; } -EXPORT_SYMBOL(cgx_lmac_linkup_start); static int cgx_lmac_init(struct cgx *cgx) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 51c206f4fe6f..7afb7caad873 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -432,7 +432,7 @@ int rvu_nix_reserve_mark_format(struct rvu *rvu, struct nix_hw *nix_hw, void rvu_nix_freemem(struct rvu *rvu); int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); -int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf); +int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 11e5921c55b9..b8e8f337316f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -350,6 +350,18 @@ int rvu_cgx_exit(struct rvu *rvu) return 0; } +/* Most of the CGX configuration is restricted to the mapped PF only, + * VF's of mapped PF and other PFs are not allowed. This fn() checks + * whether a PFFUNC is permitted to do the config or not. + */ +static bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc) +{ + if ((pcifunc & RVU_PFVF_FUNC_MASK) || + !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) + return false; + return true; +} + void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable) { u8 cgx_id, lmac_id; @@ -373,11 +385,8 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) int pf = rvu_get_pf(pcifunc); u8 cgx_id, lmac_id; - /* This msg is expected only from PFs that are mapped to CGX LMACs, - * if received from other PF/VF simply ACK, nothing to do. - */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) || !is_pf_cgxmapped(rvu, pf)) - return -ENODEV; + if (!is_cgx_config_permitted(rvu, pcifunc)) + return -EPERM; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); @@ -409,8 +418,7 @@ int rvu_mbox_handler_cgx_stats(struct rvu *rvu, struct msg_req *req, u8 cgx_idx, lmac; void *cgxd; - if ((req->hdr.pcifunc & RVU_PFVF_FUNC_MASK) || - !is_pf_cgxmapped(rvu, pf)) + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) return -ENODEV; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_idx, &lmac); @@ -477,12 +485,8 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req, int pf = rvu_get_pf(pcifunc); u8 cgx_id, lmac_id; - /* This msg is expected only from PFs that are mapped to CGX LMACs, - * if received from other PF/VF simply ACK, nothing to do. - */ - if ((req->hdr.pcifunc & RVU_PFVF_FUNC_MASK) || - !is_pf_cgxmapped(rvu, pf)) - return -ENODEV; + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); @@ -493,16 +497,11 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req, int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - u16 pcifunc = req->hdr.pcifunc; - int pf = rvu_get_pf(pcifunc); + int pf = rvu_get_pf(req->hdr.pcifunc); u8 cgx_id, lmac_id; - /* This msg is expected only from PFs that are mapped to CGX LMACs, - * if received from other PF/VF simply ACK, nothing to do. - */ - if ((req->hdr.pcifunc & RVU_PFVF_FUNC_MASK) || - !is_pf_cgxmapped(rvu, pf)) - return -ENODEV; + if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) + return -EPERM; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); @@ -515,11 +514,8 @@ static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en) int pf = rvu_get_pf(pcifunc); u8 cgx_id, lmac_id; - /* This msg is expected only from PFs that are mapped to CGX LMACs, - * if received from other PF/VF simply ACK, nothing to do. - */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) || !is_pf_cgxmapped(rvu, pf)) - return -ENODEV; + if (!is_cgx_config_permitted(rvu, pcifunc)) + return -EPERM; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); @@ -571,11 +567,8 @@ static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en) int pf = rvu_get_pf(pcifunc); u8 cgx_id, lmac_id; - /* This msg is expected only from PFs that are mapped to CGX LMACs, - * if received from other PF/VF simply ACK, nothing to do. - */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) || !is_pf_cgxmapped(rvu, pf)) - return -ENODEV; + if (!is_cgx_config_permitted(rvu, pcifunc)) + return -EPERM; rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index eb5e542424e7..a29e5c7c8cfc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -90,6 +90,26 @@ int rvu_get_nixlf_count(struct rvu *rvu) return block->lf.max; } +int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + struct rvu_hwinfo *hw = rvu->hw; + int blkaddr; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (!pfvf->nixlf || blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + *nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); + if (*nixlf < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + if (nix_blkaddr) + *nix_blkaddr = blkaddr; + + return 0; +} + static void nix_mce_list_init(struct nix_mce_list *list, int max) { INIT_HLIST_HEAD(&list->head); @@ -1667,13 +1687,9 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu, req->num_regs > MAX_REGS_PER_MBOX_MSG) return NIX_AF_INVAL_TXSCHQ_CFG; - err = nix_get_nixlf(rvu, pcifunc, &nixlf); + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); if (err) - return NIX_AF_ERR_AF_LF_INVALID; - - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; + return err; nix_hw = get_nix_hw(rvu->hw, blkaddr); if (!nix_hw) @@ -1767,17 +1783,12 @@ int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu, struct nix_vtag_config *req, struct msg_rsp *rsp) { - struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int blkaddr, nixlf, err; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return err; if (req->cfg_type) { err = nix_rx_vtag_cfg(rvu, nixlf, blkaddr, req); @@ -2119,18 +2130,13 @@ static int nix_af_mark_format_setup(struct rvu *rvu, struct nix_hw *nix_hw, int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { - struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; - int i, nixlf, blkaddr; + int i, nixlf, blkaddr, err; u64 stats; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return err; /* Get stats count supported by HW */ stats = rvu_read64(rvu, blkaddr, NIX_AF_CONST1); @@ -2418,18 +2424,14 @@ int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu, struct nix_rss_flowkey_cfg *req, struct nix_rss_flowkey_cfg_rsp *rsp) { - struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int alg_idx, nixlf, blkaddr; struct nix_hw *nix_hw; + int err; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return err; nix_hw = get_nix_hw(rvu->hw, blkaddr); if (!nix_hw) @@ -2522,19 +2524,15 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu, struct nix_set_mac_addr *req, struct msg_rsp *rsp) { - struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; + int blkaddr, nixlf, err; struct rvu_pfvf *pfvf; - int blkaddr, nixlf; - pfvf = rvu_get_pfvf(rvu, pcifunc); - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (!pfvf->nixlf || blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return err; - nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + pfvf = rvu_get_pfvf(rvu, pcifunc); ether_addr_copy(pfvf->mac_addr, req->mac_addr); @@ -2567,19 +2565,15 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, struct msg_rsp *rsp) { bool allmulti = false, disable_promisc = false; - struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; + int blkaddr, nixlf, err; struct rvu_pfvf *pfvf; - int blkaddr, nixlf; - pfvf = rvu_get_pfvf(rvu, pcifunc); - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (!pfvf->nixlf || blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (err) + return err; - nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + pfvf = rvu_get_pfvf(rvu, pcifunc); if (req->mode & NIX_RX_MODE_PROMISC) allmulti = false; @@ -2794,22 +2788,12 @@ free_entry: int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, struct msg_rsp *rsp) { - struct rvu_hwinfo *hw = rvu->hw; - u16 pcifunc = req->hdr.pcifunc; - struct rvu_block *block; - struct rvu_pfvf *pfvf; - int nixlf, blkaddr; + int nixlf, blkaddr, err; u64 cfg; - pfvf = rvu_get_pfvf(rvu, pcifunc); - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (!pfvf->nixlf || blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - block = &hw->block[blkaddr]; - nixlf = rvu_get_lf(rvu, block, pcifunc, 0); - if (nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; + err = nix_get_nixlf(rvu, req->hdr.pcifunc, &nixlf, &blkaddr); + if (err) + return err; cfg = rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf)); /* Set the interface configuration */ @@ -3114,30 +3098,13 @@ void rvu_nix_freemem(struct rvu *rvu) } } -int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf) -{ - struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); - struct rvu_hwinfo *hw = rvu->hw; - int blkaddr; - - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (!pfvf->nixlf || blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - *nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); - if (*nixlf < 0) - return NIX_AF_ERR_AF_LF_INVALID; - - return 0; -} - int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; int nixlf, err; - err = nix_get_nixlf(rvu, pcifunc, &nixlf); + err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) return err; @@ -3152,7 +3119,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, u16 pcifunc = req->hdr.pcifunc; int nixlf, err; - err = nix_get_nixlf(rvu, pcifunc, &nixlf); + err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) return err; diff --git a/drivers/net/ethernet/marvell/skge.h b/drivers/net/ethernet/marvell/skge.h index 6fa7b6a34c08..a1313d57e283 100644 --- a/drivers/net/ethernet/marvell/skge.h +++ b/drivers/net/ethernet/marvell/skge.h @@ -2426,7 +2426,7 @@ struct skge_hw { spinlock_t phy_lock; struct tasklet_struct phy_task; - char irq_name[0]; /* skge@pci:000:04:00.0 */ + char irq_name[]; /* skge@pci:000:04:00.0 */ }; enum pause_control { diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h index b02b6523083c..ada1ca60f088 100644 --- a/drivers/net/ethernet/marvell/sky2.h +++ b/drivers/net/ethernet/marvell/sky2.h @@ -2309,7 +2309,7 @@ struct sky2_hw { struct work_struct restart_work; wait_queue_head_t msi_wait; - char irq_name[0]; + char irq_name[]; }; static inline int sky2_is_copper(const struct sky2_hw *hw) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 8c6cfd15481c..8d28f90acfe7 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -412,9 +412,10 @@ static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } -static void mtk_mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) +static void mtk_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause) { struct mtk_mac *mac = container_of(config, struct mtk_mac, phylink_config); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index d3e06cec8317..e0bb8e12356e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -16,7 +16,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ - diag/fw_tracer.o diag/crdump.o devlink.o + diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o # # Netdev basic diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 94d7b69a95c7..c9c9b479bda5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -188,7 +188,7 @@ static int mlx5_fw_tracer_create_mkey(struct mlx5_fw_tracer *tracer) MLX5_SET(create_mkey_in, in, translations_octword_actual_size, DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2)); - mtt = (u64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); for (i = 0 ; i < TRACER_BUFFER_PAGE_NUM ; i++) mtt[i] = cpu_to_be64(tracer->buff.dma + i * PAGE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c new file mode 100644 index 000000000000..17ab7efe693d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "rsc_dump.h" +#include "lib/mlx5.h" + +#define MLX5_SGMT_TYPE(SGMT) MLX5_SGMT_TYPE_##SGMT +#define MLX5_SGMT_STR_ASSING(SGMT)[MLX5_SGMT_TYPE(SGMT)] = #SGMT +static const char *const mlx5_rsc_sgmt_name[] = { + MLX5_SGMT_STR_ASSING(HW_CQPC), + MLX5_SGMT_STR_ASSING(HW_SQPC), + MLX5_SGMT_STR_ASSING(HW_RQPC), + MLX5_SGMT_STR_ASSING(FULL_SRQC), + MLX5_SGMT_STR_ASSING(FULL_CQC), + MLX5_SGMT_STR_ASSING(FULL_EQC), + MLX5_SGMT_STR_ASSING(FULL_QPC), + MLX5_SGMT_STR_ASSING(SND_BUFF), + MLX5_SGMT_STR_ASSING(RCV_BUFF), + MLX5_SGMT_STR_ASSING(SRQ_BUFF), + MLX5_SGMT_STR_ASSING(CQ_BUFF), + MLX5_SGMT_STR_ASSING(EQ_BUFF), + MLX5_SGMT_STR_ASSING(SX_SLICE), + MLX5_SGMT_STR_ASSING(SX_SLICE_ALL), + MLX5_SGMT_STR_ASSING(RDB), + MLX5_SGMT_STR_ASSING(RX_SLICE_ALL), +}; + +struct mlx5_rsc_dump { + u32 pdn; + struct mlx5_core_mkey mkey; + u16 fw_segment_type[MLX5_SGMT_TYPE_NUM]; +}; + +struct mlx5_rsc_dump_cmd { + u64 mem_size; + u8 cmd[MLX5_ST_SZ_BYTES(resource_dump)]; +}; + +static int mlx5_rsc_dump_sgmt_get_by_name(char *name) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlx5_rsc_sgmt_name); i++) + if (!strcmp(name, mlx5_rsc_sgmt_name[i])) + return i; + + return -EINVAL; +} + +static void mlx5_rsc_dump_read_menu_sgmt(struct mlx5_rsc_dump *rsc_dump, struct page *page) +{ + void *data = page_address(page); + enum mlx5_sgmt_type sgmt_idx; + int num_of_items; + char *sgmt_name; + void *member; + void *menu; + int i; + + menu = MLX5_ADDR_OF(menu_resource_dump_response, data, menu); + num_of_items = MLX5_GET(resource_dump_menu_segment, menu, num_of_records); + + for (i = 0; i < num_of_items; i++) { + member = MLX5_ADDR_OF(resource_dump_menu_segment, menu, record[i]); + sgmt_name = MLX5_ADDR_OF(resource_dump_menu_record, member, segment_name); + sgmt_idx = mlx5_rsc_dump_sgmt_get_by_name(sgmt_name); + if (sgmt_idx == -EINVAL) + continue; + rsc_dump->fw_segment_type[sgmt_idx] = MLX5_GET(resource_dump_menu_record, + member, segment_type); + } +} + +static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, + struct page *page) +{ + struct mlx5_rsc_dump *rsc_dump = dev->rsc_dump; + struct device *ddev = &dev->pdev->dev; + u32 out_seq_num; + u32 in_seq_num; + dma_addr_t dma; + int err; + + dma = dma_map_page(ddev, page, 0, cmd->mem_size, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ddev, dma))) + return -ENOMEM; + + in_seq_num = MLX5_GET(resource_dump, cmd->cmd, seq_num); + MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey.key); + MLX5_SET64(resource_dump, cmd->cmd, address, dma); + + err = mlx5_core_access_reg(dev, cmd->cmd, sizeof(cmd->cmd), cmd->cmd, + sizeof(cmd->cmd), MLX5_REG_RESOURCE_DUMP, 0, 1); + if (err) { + mlx5_core_err(dev, "Resource dump: Failed to access err %d\n", err); + goto out; + } + out_seq_num = MLX5_GET(resource_dump, cmd->cmd, seq_num); + if (out_seq_num && (in_seq_num + 1 != out_seq_num)) + err = -EIO; +out: + dma_unmap_page(ddev, dma, cmd->mem_size, DMA_FROM_DEVICE); + return err; +} + +struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev, + struct mlx5_rsc_key *key) +{ + struct mlx5_rsc_dump_cmd *cmd; + int sgmt_type; + + if (IS_ERR_OR_NULL(dev->rsc_dump)) + return ERR_PTR(-EOPNOTSUPP); + + sgmt_type = dev->rsc_dump->fw_segment_type[key->rsc]; + if (!sgmt_type && key->rsc != MLX5_SGMT_TYPE_MENU) + return ERR_PTR(-EOPNOTSUPP); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + mlx5_core_err(dev, "Resource dump: Failed to allocate command\n"); + return ERR_PTR(-ENOMEM); + } + MLX5_SET(resource_dump, cmd->cmd, segment_type, sgmt_type); + MLX5_SET(resource_dump, cmd->cmd, index1, key->index1); + MLX5_SET(resource_dump, cmd->cmd, index2, key->index2); + MLX5_SET(resource_dump, cmd->cmd, num_of_obj1, key->num_of_obj1); + MLX5_SET(resource_dump, cmd->cmd, num_of_obj2, key->num_of_obj2); + MLX5_SET(resource_dump, cmd->cmd, size, key->size); + cmd->mem_size = key->size; + return cmd; +} + +void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd) +{ + kfree(cmd); +} + +int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, + struct page *page, int *size) +{ + bool more_dump; + int err; + + if (IS_ERR_OR_NULL(dev->rsc_dump)) + return -EOPNOTSUPP; + + err = mlx5_rsc_dump_trigger(dev, cmd, page); + if (err) { + mlx5_core_err(dev, "Resource dump: Failed to trigger dump, %d\n", err); + return err; + } + *size = MLX5_GET(resource_dump, cmd->cmd, size); + more_dump = MLX5_GET(resource_dump, cmd->cmd, more_dump); + + return more_dump; +} + +#define MLX5_RSC_DUMP_MENU_SEGMENT 0xffff +static int mlx5_rsc_dump_menu(struct mlx5_core_dev *dev) +{ + struct mlx5_rsc_dump_cmd *cmd = NULL; + struct mlx5_rsc_key key = {}; + struct page *page; + int size; + int err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + key.rsc = MLX5_SGMT_TYPE_MENU; + key.size = PAGE_SIZE; + cmd = mlx5_rsc_dump_cmd_create(dev, &key); + if (IS_ERR(cmd)) { + err = PTR_ERR(cmd); + goto free_page; + } + MLX5_SET(resource_dump, cmd->cmd, segment_type, MLX5_RSC_DUMP_MENU_SEGMENT); + + do { + err = mlx5_rsc_dump_next(dev, cmd, page, &size); + if (err < 0) + goto destroy_cmd; + + mlx5_rsc_dump_read_menu_sgmt(dev->rsc_dump, page); + + } while (err > 0); + +destroy_cmd: + mlx5_rsc_dump_cmd_destroy(cmd); +free_page: + __free_page(page); + + return err; +} + +static int mlx5_rsc_dump_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, + struct mlx5_core_mkey *mkey) +{ + int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + void *mkc; + u32 *in; + int err; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + + MLX5_SET(mkc, mkc, pd, pdn); + MLX5_SET(mkc, mkc, length64, 1); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + + err = mlx5_core_create_mkey(mdev, mkey, in, inlen); + + kvfree(in); + return err; +} + +struct mlx5_rsc_dump *mlx5_rsc_dump_create(struct mlx5_core_dev *dev) +{ + struct mlx5_rsc_dump *rsc_dump; + + if (!MLX5_CAP_DEBUG(dev, resource_dump)) { + mlx5_core_dbg(dev, "Resource dump: capability not present\n"); + return NULL; + } + rsc_dump = kzalloc(sizeof(*rsc_dump), GFP_KERNEL); + if (!rsc_dump) + return ERR_PTR(-ENOMEM); + + return rsc_dump; +} + +void mlx5_rsc_dump_destroy(struct mlx5_core_dev *dev) +{ + if (IS_ERR_OR_NULL(dev->rsc_dump)) + return; + kfree(dev->rsc_dump); +} + +int mlx5_rsc_dump_init(struct mlx5_core_dev *dev) +{ + struct mlx5_rsc_dump *rsc_dump = dev->rsc_dump; + int err; + + if (IS_ERR_OR_NULL(dev->rsc_dump)) + return 0; + + err = mlx5_core_alloc_pd(dev, &rsc_dump->pdn); + if (err) { + mlx5_core_warn(dev, "Resource dump: Failed to allocate PD %d\n", err); + return err; + } + err = mlx5_rsc_dump_create_mkey(dev, rsc_dump->pdn, &rsc_dump->mkey); + if (err) { + mlx5_core_err(dev, "Resource dump: Failed to create mkey, %d\n", err); + goto free_pd; + } + err = mlx5_rsc_dump_menu(dev); + if (err) { + mlx5_core_err(dev, "Resource dump: Failed to read menu, %d\n", err); + goto destroy_mkey; + } + return err; + +destroy_mkey: + mlx5_core_destroy_mkey(dev, &rsc_dump->mkey); +free_pd: + mlx5_core_dealloc_pd(dev, rsc_dump->pdn); + return err; +} + +void mlx5_rsc_dump_cleanup(struct mlx5_core_dev *dev) +{ + if (IS_ERR_OR_NULL(dev->rsc_dump)) + return; + + mlx5_core_destroy_mkey(dev, &dev->rsc_dump->mkey); + mlx5_core_dealloc_pd(dev, dev->rsc_dump->pdn); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h new file mode 100644 index 000000000000..148270073e71 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_RSC_DUMP_H +#define __MLX5_RSC_DUMP_H + +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" + +enum mlx5_sgmt_type { + MLX5_SGMT_TYPE_HW_CQPC, + MLX5_SGMT_TYPE_HW_SQPC, + MLX5_SGMT_TYPE_HW_RQPC, + MLX5_SGMT_TYPE_FULL_SRQC, + MLX5_SGMT_TYPE_FULL_CQC, + MLX5_SGMT_TYPE_FULL_EQC, + MLX5_SGMT_TYPE_FULL_QPC, + MLX5_SGMT_TYPE_SND_BUFF, + MLX5_SGMT_TYPE_RCV_BUFF, + MLX5_SGMT_TYPE_SRQ_BUFF, + MLX5_SGMT_TYPE_CQ_BUFF, + MLX5_SGMT_TYPE_EQ_BUFF, + MLX5_SGMT_TYPE_SX_SLICE, + MLX5_SGMT_TYPE_SX_SLICE_ALL, + MLX5_SGMT_TYPE_RDB, + MLX5_SGMT_TYPE_RX_SLICE_ALL, + MLX5_SGMT_TYPE_MENU, + MLX5_SGMT_TYPE_TERMINATE, + + MLX5_SGMT_TYPE_NUM, /* Keep last */ +}; + +struct mlx5_rsc_key { + enum mlx5_sgmt_type rsc; + int index1; + int index2; + int num_of_obj1; + int num_of_obj2; + int size; +}; + +#define MLX5_RSC_DUMP_ALL 0xFFFF +struct mlx5_rsc_dump_cmd; +struct mlx5_rsc_dump; + +struct mlx5_rsc_dump *mlx5_rsc_dump_create(struct mlx5_core_dev *dev); +void mlx5_rsc_dump_destroy(struct mlx5_core_dev *dev); + +int mlx5_rsc_dump_init(struct mlx5_core_dev *dev); +void mlx5_rsc_dump_cleanup(struct mlx5_core_dev *dev); + +struct mlx5_rsc_dump_cmd *mlx5_rsc_dump_cmd_create(struct mlx5_core_dev *dev, + struct mlx5_rsc_key *key); +void mlx5_rsc_dump_cmd_destroy(struct mlx5_rsc_dump_cmd *cmd); + +int mlx5_rsc_dump_next(struct mlx5_core_dev *dev, struct mlx5_rsc_dump_cmd *cmd, + struct page *page, int *size); +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 220ef9f06f84..3cc439ab3253 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -737,7 +737,6 @@ struct mlx5e_channel { DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int cpu; - cpumask_var_t xps_cpumask; }; struct mlx5e_channels { @@ -813,6 +812,15 @@ struct mlx5e_xsk { bool ever_used; }; +/* Temporary storage for variables that are allocated when struct mlx5e_priv is + * initialized, and used where we can't allocate them because that functions + * must not fail. Use with care and make sure the same variable is not used + * simultaneously by multiple users. + */ +struct mlx5e_scratchpad { + cpumask_var_t cpumask; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -876,6 +884,7 @@ struct mlx5e_priv { #if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) struct mlx5e_hv_vhca_stats_agent stats_agent; #endif + struct mlx5e_scratchpad scratchpad; }; struct mlx5e_profile { @@ -1035,14 +1044,22 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs); void mlx5e_close_channels(struct mlx5e_channels *chs); -/* Function pointer to be used to modify WH settings while +/* Function pointer to be used to modify HW or kernel settings while * switching channels */ -typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv); +typedef int (*mlx5e_fp_preactivate)(struct mlx5e_priv *priv, void *context); +#define MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(fn) \ +int fn##_ctx(struct mlx5e_priv *priv, void *context) \ +{ \ + return fn(priv); \ +} int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv); int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify); + mlx5e_fp_preactivate preactivate, + void *context); +int mlx5e_num_channels_changed(struct mlx5e_priv *priv); +int mlx5e_num_channels_changed_ctx(struct mlx5e_priv *priv, void *context); void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); @@ -1122,10 +1139,10 @@ void mlx5e_update_ndo_stats(struct mlx5e_priv *priv); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); int mlx5e_bits_invert(unsigned long a, int size); -typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv); int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv); +int mlx5e_set_dev_port_mtu_ctx(struct mlx5e_priv *priv, void *context); int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, - change_hw_mtu_cb set_mtu_cb); + mlx5e_fp_preactivate preactivate); /* ethtool helpers */ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 20b907dc1e29..3a199a03d929 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -3,6 +3,7 @@ #include "health.h" #include "lib/eq.h" +#include "lib/mlx5.h" int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name) { @@ -197,10 +198,114 @@ int mlx5e_health_report(struct mlx5e_priv *priv, struct devlink_health_reporter *reporter, char *err_str, struct mlx5e_err_ctx *err_ctx) { - netdev_err(priv->netdev, err_str); + netdev_err(priv->netdev, "%s\n", err_str); if (!reporter) return err_ctx->recover(err_ctx->ctx); return devlink_health_report(reporter, err_str, err_ctx); } + +#define MLX5_HEALTH_DEVLINK_MAX_SIZE 1024 +static int mlx5e_health_rsc_fmsg_binary(struct devlink_fmsg *fmsg, + const void *value, u32 value_len) + +{ + u32 data_size; + u32 offset; + int err; + + for (offset = 0; offset < value_len; offset += data_size) { + data_size = value_len - offset; + if (data_size > MLX5_HEALTH_DEVLINK_MAX_SIZE) + data_size = MLX5_HEALTH_DEVLINK_MAX_SIZE; + err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); + if (err) + break; + } + return err; +} + +int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key, + struct devlink_fmsg *fmsg) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_rsc_dump_cmd *cmd; + struct page *page; + int cmd_err, err; + int end_err; + int size; + + if (IS_ERR_OR_NULL(mdev->rsc_dump)) + return -EOPNOTSUPP; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + err = devlink_fmsg_binary_pair_nest_start(fmsg, "data"); + if (err) + return err; + + cmd = mlx5_rsc_dump_cmd_create(mdev, key); + if (IS_ERR(cmd)) { + err = PTR_ERR(cmd); + goto free_page; + } + + do { + cmd_err = mlx5_rsc_dump_next(mdev, cmd, page, &size); + if (cmd_err < 0) { + err = cmd_err; + goto destroy_cmd; + } + + err = mlx5e_health_rsc_fmsg_binary(fmsg, page_address(page), size); + if (err) + goto destroy_cmd; + + } while (cmd_err > 0); + +destroy_cmd: + mlx5_rsc_dump_cmd_destroy(cmd); + end_err = devlink_fmsg_binary_pair_nest_end(fmsg); + if (end_err) + err = end_err; +free_page: + __free_page(page); + return err; +} + +int mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + int queue_idx, char *lbl) +{ + struct mlx5_rsc_key key = {}; + int err; + + key.rsc = MLX5_SGMT_TYPE_FULL_QPC; + key.index1 = queue_idx; + key.size = PAGE_SIZE; + key.num_of_obj1 = 1; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, lbl); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "index", queue_idx); + if (err) + return err; + + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return devlink_fmsg_obj_nest_end(fmsg); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index d3693fa547ac..e90e3aec422f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -5,6 +5,7 @@ #define __MLX5E_EN_HEALTH_H #include "en.h" +#include "diag/rsc_dump.h" #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) @@ -36,6 +37,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); struct mlx5e_err_ctx { int (*recover)(void *ctx); + int (*dump)(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, void *ctx); void *ctx; }; @@ -48,6 +50,8 @@ int mlx5e_health_report(struct mlx5e_priv *priv, int mlx5e_health_create_reporters(struct mlx5e_priv *priv); void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv); void mlx5e_health_channels_update(struct mlx5e_priv *priv); - - +int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key, + struct devlink_fmsg *fmsg); +int mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + int queue_idx, char *lbl); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index fce6eccdcf8b..2c4a670c8ffd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -343,64 +343,76 @@ out: return err; } -static u32 fec_supported_speeds[] = { - 10000, - 40000, - 25000, - 50000, - 56000, - 100000 +enum mlx5e_fec_supported_link_mode { + MLX5E_FEC_SUPPORTED_LINK_MODES_10G_40G, + MLX5E_FEC_SUPPORTED_LINK_MODES_25G, + MLX5E_FEC_SUPPORTED_LINK_MODES_50G, + MLX5E_FEC_SUPPORTED_LINK_MODES_56G, + MLX5E_FEC_SUPPORTED_LINK_MODES_100G, + MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X, + MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X, + MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X, + MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X, + MLX5E_MAX_FEC_SUPPORTED_LINK_MODE, }; -#define MLX5E_FEC_SUPPORTED_SPEEDS ARRAY_SIZE(fec_supported_speeds) +#define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X + +#define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link) \ + do { \ + u16 *_policy = &(policy); \ + u32 *_buf = buf; \ + \ + if (write) \ + MLX5_SET(pplm_reg, _buf, fec_override_admin_##link, *_policy); \ + else \ + *_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link); \ + } while (0) + +#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link) \ + do { \ + u16 *__policy = &(policy); \ + bool _write = (write); \ + \ + if (_write && *__policy) \ + *__policy = find_first_bit((u_long *)__policy, \ + sizeof(u16) * BITS_PER_BYTE);\ + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link); \ + if (!_write && *__policy) \ + *__policy = 1 << *__policy; \ + } while (0) /* get/set FEC admin field for a given speed */ -static int mlx5e_fec_admin_field(u32 *pplm, - u8 *fec_policy, - bool write, - u32 speed) +static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write, + enum mlx5e_fec_supported_link_mode link_mode) { - switch (speed) { - case 10000: - case 40000: - if (!write) - *fec_policy = MLX5_GET(pplm_reg, pplm, - fec_override_admin_10g_40g); - else - MLX5_SET(pplm_reg, pplm, - fec_override_admin_10g_40g, *fec_policy); + switch (link_mode) { + case MLX5E_FEC_SUPPORTED_LINK_MODES_10G_40G: + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 10g_40g); break; - case 25000: - if (!write) - *fec_policy = MLX5_GET(pplm_reg, pplm, - fec_override_admin_25g); - else - MLX5_SET(pplm_reg, pplm, - fec_override_admin_25g, *fec_policy); + case MLX5E_FEC_SUPPORTED_LINK_MODES_25G: + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 25g); break; - case 50000: - if (!write) - *fec_policy = MLX5_GET(pplm_reg, pplm, - fec_override_admin_50g); - else - MLX5_SET(pplm_reg, pplm, - fec_override_admin_50g, *fec_policy); + case MLX5E_FEC_SUPPORTED_LINK_MODES_50G: + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 50g); break; - case 56000: - if (!write) - *fec_policy = MLX5_GET(pplm_reg, pplm, - fec_override_admin_56g); - else - MLX5_SET(pplm_reg, pplm, - fec_override_admin_56g, *fec_policy); + case MLX5E_FEC_SUPPORTED_LINK_MODES_56G: + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 56g); break; - case 100000: - if (!write) - *fec_policy = MLX5_GET(pplm_reg, pplm, - fec_override_admin_100g); - else - MLX5_SET(pplm_reg, pplm, - fec_override_admin_100g, *fec_policy); + case MLX5E_FEC_SUPPORTED_LINK_MODES_100G: + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X: + MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 50g_1x); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X: + MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 100g_2x); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X: + MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 200g_4x); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X: + MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 400g_8x); break; default: return -EINVAL; @@ -408,32 +420,40 @@ static int mlx5e_fec_admin_field(u32 *pplm, return 0; } +#define MLX5E_GET_FEC_OVERRIDE_CAP(buf, link) \ + MLX5_GET(pplm_reg, buf, fec_override_cap_##link) + /* returns FEC capabilities for a given speed */ -static int mlx5e_get_fec_cap_field(u32 *pplm, - u8 *fec_cap, - u32 speed) +static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap, + enum mlx5e_fec_supported_link_mode link_mode) { - switch (speed) { - case 10000: - case 40000: - *fec_cap = MLX5_GET(pplm_reg, pplm, - fec_override_cap_10g_40g); + switch (link_mode) { + case MLX5E_FEC_SUPPORTED_LINK_MODES_10G_40G: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 10g_40g); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODES_25G: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 25g); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODES_50G: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 50g); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODES_56G: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 56g); + break; + case MLX5E_FEC_SUPPORTED_LINK_MODES_100G: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 100g); break; - case 25000: - *fec_cap = MLX5_GET(pplm_reg, pplm, - fec_override_cap_25g); + case MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 50g_1x); break; - case 50000: - *fec_cap = MLX5_GET(pplm_reg, pplm, - fec_override_cap_50g); + case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 100g_2x); break; - case 56000: - *fec_cap = MLX5_GET(pplm_reg, pplm, - fec_override_cap_56g); + case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_4x); break; - case 100000: - *fec_cap = MLX5_GET(pplm_reg, pplm, - fec_override_cap_100g); + case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X: + *fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_8x); break; default: return -EINVAL; @@ -441,13 +461,14 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, return 0; } -int mlx5e_get_fec_caps(struct mlx5_core_dev *dev, u8 *fec_caps) +bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy) { + bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm); u32 out[MLX5_ST_SZ_DW(pplm_reg)] = {}; u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(pplm_reg); - u32 current_fec_speed; int err; + int i; if (!MLX5_CAP_GEN(dev, pcam_reg)) return -EOPNOTSUPP; @@ -458,23 +479,30 @@ int mlx5e_get_fec_caps(struct mlx5_core_dev *dev, u8 *fec_caps) MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) - return err; + return false; - err = mlx5e_port_linkspeed(dev, ¤t_fec_speed); - if (err) - return err; + for (i = 0; i < MLX5E_MAX_FEC_SUPPORTED_LINK_MODE; i++) { + u16 fec_caps; - return mlx5e_get_fec_cap_field(out, fec_caps, current_fec_speed); + if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane) + break; + + mlx5e_get_fec_cap_field(out, &fec_caps, i); + if (fec_caps & fec_policy) + return true; + } + return false; } int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active, - u8 *fec_configured_mode) + u16 *fec_configured_mode) { + bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm); u32 out[MLX5_ST_SZ_DW(pplm_reg)] = {}; u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(pplm_reg); - u32 link_speed; int err; + int i; if (!MLX5_CAP_GEN(dev, pcam_reg)) return -EOPNOTSUPP; @@ -490,24 +518,28 @@ int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active, *fec_mode_active = MLX5_GET(pplm_reg, out, fec_mode_active); if (!fec_configured_mode) - return 0; + goto out; - err = mlx5e_port_linkspeed(dev, &link_speed); - if (err) - return err; + *fec_configured_mode = 0; + for (i = 0; i < MLX5E_MAX_FEC_SUPPORTED_LINK_MODE; i++) { + if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane) + break; - return mlx5e_fec_admin_field(out, fec_configured_mode, 0, link_speed); + mlx5e_fec_admin_field(out, fec_configured_mode, 0, i); + if (*fec_configured_mode != 0) + goto out; + } +out: + return 0; } -int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u8 fec_policy) +int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) { - u8 fec_policy_nofec = BIT(MLX5E_FEC_NOFEC); - bool fec_mode_not_supp_in_speed = false; + bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm); u32 out[MLX5_ST_SZ_DW(pplm_reg)] = {}; u32 in[MLX5_ST_SZ_DW(pplm_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(pplm_reg); - u8 fec_policy_auto = 0; - u8 fec_caps = 0; + u16 fec_policy_auto = 0; int err; int i; @@ -517,6 +549,9 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u8 fec_policy) if (!MLX5_CAP_PCAM_REG(dev, pplm)) return -EOPNOTSUPP; + if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) + return -EOPNOTSUPP; + MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) @@ -524,25 +559,31 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u8 fec_policy) MLX5_SET(pplm_reg, out, local_port, 1); - for (i = 0; i < MLX5E_FEC_SUPPORTED_SPEEDS; i++) { - mlx5e_get_fec_cap_field(out, &fec_caps, fec_supported_speeds[i]); - /* policy supported for link speed, or policy is auto */ - if (fec_caps & fec_policy || fec_policy == fec_policy_auto) { - mlx5e_fec_admin_field(out, &fec_policy, 1, - fec_supported_speeds[i]); - } else { - /* turn off FEC if supported. Else, leave it the same */ - if (fec_caps & fec_policy_nofec) - mlx5e_fec_admin_field(out, &fec_policy_nofec, 1, - fec_supported_speeds[i]); - fec_mode_not_supp_in_speed = true; - } - } + for (i = 0; i < MLX5E_MAX_FEC_SUPPORTED_LINK_MODE; i++) { + u16 conf_fec = fec_policy; + u16 fec_caps = 0; + + if (i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE && !fec_50g_per_lane) + break; - if (fec_mode_not_supp_in_speed) - mlx5_core_dbg(dev, - "FEC policy 0x%x is not supported for some speeds", - fec_policy); + /* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514 + * to link modes up to 25G per lane and to + * MLX5E_FEC_RS_544_514 in the new link modes based on + * 50 G per lane + */ + if (conf_fec == (1 << MLX5E_FEC_RS_528_514) && + i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE) + conf_fec = (1 << MLX5E_FEC_RS_544_514); + + mlx5e_get_fec_cap_field(out, &fec_caps, i); + + /* policy supported for link speed */ + if (fec_caps & conf_fec) + mlx5e_fec_admin_field(out, &conf_fec, 1, i); + else + /* set FEC to auto*/ + mlx5e_fec_admin_field(out, &fec_policy_auto, 1, i); + } return mlx5_core_access_reg(dev, out, sz, out, sz, MLX5_REG_PPLM, 0, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index 4a7f4497692b..a2ddd446dd59 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -60,15 +60,17 @@ int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); int mlx5e_port_set_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); -int mlx5e_get_fec_caps(struct mlx5_core_dev *dev, u8 *fec_caps); +bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy); int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active, - u8 *fec_configured_mode); -int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u8 fec_policy); + u16 *fec_configured_mode); +int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy); enum { MLX5E_FEC_NOFEC, MLX5E_FEC_FIRECODE, MLX5E_FEC_RS_528_514, + MLX5E_FEC_RS_544_514 = 7, + MLX5E_FEC_LLRS_272_257_1 = 9, }; #endif 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 6c72b592315b..ce2b41c61090 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -102,19 +102,6 @@ out: return err; } -void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq) -{ - struct mlx5e_priv *priv = icosq->channel->priv; - char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; - struct mlx5e_err_ctx err_ctx = {}; - - err_ctx.ctx = icosq; - err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover; - sprintf(err_str, "ERR CQE on ICOSQ: 0x%x", icosq->sqn); - - mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); -} - static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) { struct net_device *dev = rq->netdev; @@ -171,19 +158,6 @@ out: return err; } -void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq) -{ - struct mlx5e_priv *priv = rq->channel->priv; - char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; - struct mlx5e_err_ctx err_ctx = {}; - - err_ctx.ctx = rq; - err_ctx.recover = mlx5e_rx_reporter_err_rq_cqe_recover; - sprintf(err_str, "ERR CQE on RQ: 0x%x", rq->rqn); - - mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); -} - static int mlx5e_rx_reporter_timeout_recover(void *ctx) { struct mlx5e_icosq *icosq; @@ -201,21 +175,6 @@ static int mlx5e_rx_reporter_timeout_recover(void *ctx) return err; } -void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) -{ - struct mlx5e_icosq *icosq = &rq->channel->icosq; - struct mlx5e_priv *priv = rq->channel->priv; - char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; - struct mlx5e_err_ctx err_ctx = {}; - - err_ctx.ctx = rq; - err_ctx.recover = mlx5e_rx_reporter_timeout_recover; - sprintf(err_str, "RX timeout on channel: %d, ICOSQ: 0x%x RQ: 0x%x, CQ: 0x%x\n", - icosq->channel->ix, icosq->sqn, rq->rqn, rq->cq.mcq.cqn); - - mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); -} - static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) { return err_ctx->recover(err_ctx->ctx); @@ -371,10 +330,235 @@ unlock: return err; } +static int mlx5e_rx_reporter_dump_icosq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + void *ctx) +{ + struct mlx5e_txqsq *icosq = ctx; + struct mlx5_rsc_key key = {}; + int err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "SX Slice"); + if (err) + return err; + + key.size = PAGE_SIZE; + key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "ICOSQ"); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "QPC"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_FULL_QPC; + key.index1 = icosq->sqn; + key.num_of_obj1 = 1; + + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "send_buff"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_SND_BUFF; + key.num_of_obj2 = MLX5_RSC_DUMP_ALL; + + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return mlx5e_reporter_named_obj_nest_end(fmsg); +} + +static int mlx5e_rx_reporter_dump_rq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + void *ctx) +{ + struct mlx5_rsc_key key = {}; + struct mlx5e_rq *rq = ctx; + int err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "RX Slice"); + if (err) + return err; + + key.size = PAGE_SIZE; + key.rsc = MLX5_SGMT_TYPE_RX_SLICE_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "RQ"); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "QPC"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_FULL_QPC; + key.index1 = rq->rqn; + key.num_of_obj1 = 1; + + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "receive_buff"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_RCV_BUFF; + key.num_of_obj2 = MLX5_RSC_DUMP_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return mlx5e_reporter_named_obj_nest_end(fmsg); +} + +static int mlx5e_rx_reporter_dump_all_rqs(struct mlx5e_priv *priv, + struct devlink_fmsg *fmsg) +{ + struct mlx5_rsc_key key = {}; + int i, err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "RX Slice"); + if (err) + return err; + + key.size = PAGE_SIZE; + key.rsc = MLX5_SGMT_TYPE_RX_SLICE_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); + if (err) + return err; + + for (i = 0; i < priv->channels.num; i++) { + struct mlx5e_rq *rq = &priv->channels.c[i]->rq; + + err = mlx5e_health_queue_dump(priv, fmsg, rq->rqn, "RQ"); + if (err) + return err; + } + + return devlink_fmsg_arr_pair_nest_end(fmsg); +} + +static int mlx5e_rx_reporter_dump_from_ctx(struct mlx5e_priv *priv, + struct mlx5e_err_ctx *err_ctx, + struct devlink_fmsg *fmsg) +{ + return err_ctx->dump(priv, fmsg, err_ctx->ctx); +} + +static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *context, + struct netlink_ext_ack *extack) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_rx_reporter_dump_from_ctx(priv, err_ctx, fmsg) : + mlx5e_rx_reporter_dump_all_rqs(priv, fmsg); +} + +void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) +{ + struct mlx5e_icosq *icosq = &rq->channel->icosq; + struct mlx5e_priv *priv = rq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = rq; + err_ctx.recover = mlx5e_rx_reporter_timeout_recover; + err_ctx.dump = mlx5e_rx_reporter_dump_rq; + snprintf(err_str, sizeof(err_str), + "RX timeout on channel: %d, ICOSQ: 0x%x RQ: 0x%x, CQ: 0x%x", + icosq->channel->ix, icosq->sqn, rq->rqn, rq->cq.mcq.cqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + +void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq) +{ + struct mlx5e_priv *priv = rq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = rq; + err_ctx.recover = mlx5e_rx_reporter_err_rq_cqe_recover; + err_ctx.dump = mlx5e_rx_reporter_dump_rq; + snprintf(err_str, sizeof(err_str), "ERR CQE on RQ: 0x%x", rq->rqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + +void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq) +{ + struct mlx5e_priv *priv = icosq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = icosq; + err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover; + err_ctx.dump = mlx5e_rx_reporter_dump_icosq; + snprintf(err_str, sizeof(err_str), "ERR CQE on ICOSQ: 0x%x", icosq->sqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = { .name = "rx", .recover = mlx5e_rx_reporter_recover, .diagnose = mlx5e_rx_reporter_diagnose, + .dump = mlx5e_rx_reporter_dump, }; #define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500 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 b468549e96ff..2028ce9b151f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -82,19 +82,6 @@ out: return err; } -void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq) -{ - struct mlx5e_priv *priv = sq->channel->priv; - char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; - struct mlx5e_err_ctx err_ctx = {0}; - - err_ctx.ctx = sq; - err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; - sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); - - mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); -} - static int mlx5e_tx_reporter_timeout_recover(void *ctx) { struct mlx5_eq_comp *eq; @@ -110,22 +97,6 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) return err; } -int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) -{ - struct mlx5e_priv *priv = sq->channel->priv; - char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; - struct mlx5e_err_ctx err_ctx; - - err_ctx.ctx = sq; - err_ctx.recover = mlx5e_tx_reporter_timeout_recover; - sprintf(err_str, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - sq->txq->trans_start)); - - return mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); -} - /* state lock cannot be grabbed within this function. * It can cause a dead lock or a read-after-free. */ @@ -275,10 +246,162 @@ unlock: return err; } +static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + void *ctx) +{ + struct mlx5_rsc_key key = {}; + struct mlx5e_txqsq *sq = ctx; + int err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "SX Slice"); + if (err) + return err; + + key.size = PAGE_SIZE; + key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "SQ"); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "QPC"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_FULL_QPC; + key.index1 = sq->sqn; + key.num_of_obj1 = 1; + + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "send_buff"); + if (err) + return err; + + key.rsc = MLX5_SGMT_TYPE_SND_BUFF; + key.num_of_obj2 = MLX5_RSC_DUMP_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return mlx5e_reporter_named_obj_nest_end(fmsg); +} + +static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, + struct devlink_fmsg *fmsg) +{ + struct mlx5_rsc_key key = {}; + int i, tc, err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + return 0; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "SX Slice"); + if (err) + return err; + + key.size = PAGE_SIZE; + key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; + err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); + if (err) + return err; + + for (i = 0; i < priv->channels.num; i++) { + struct mlx5e_channel *c = priv->channels.c[i]; + + for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + struct mlx5e_txqsq *sq = &c->sq[tc]; + + err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "SQ"); + if (err) + return err; + } + } + return devlink_fmsg_arr_pair_nest_end(fmsg); +} + +static int mlx5e_tx_reporter_dump_from_ctx(struct mlx5e_priv *priv, + struct mlx5e_err_ctx *err_ctx, + struct devlink_fmsg *fmsg) +{ + return err_ctx->dump(priv, fmsg, err_ctx->ctx); +} + +static int mlx5e_tx_reporter_dump(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *context, + struct netlink_ext_ack *extack) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_tx_reporter_dump_from_ctx(priv, err_ctx, fmsg) : + mlx5e_tx_reporter_dump_all_sqs(priv, fmsg); +} + +void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq) +{ + struct mlx5e_priv *priv = sq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = sq; + err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; + err_ctx.dump = mlx5e_tx_reporter_dump_sq; + snprintf(err_str, sizeof(err_str), "ERR CQE on SQ: 0x%x", sq->sqn); + + mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); +} + +int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) +{ + struct mlx5e_priv *priv = sq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = sq; + err_ctx.recover = mlx5e_tx_reporter_timeout_recover; + err_ctx.dump = mlx5e_tx_reporter_dump_sq; + snprintf(err_str, sizeof(err_str), + "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u", + sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + jiffies_to_usecs(jiffies - sq->txq->trans_start)); + + return mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); +} + static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { .name = "tx", .recover = mlx5e_tx_reporter_recover, .diagnose = mlx5e_tx_reporter_diagnose, + .dump = mlx5e_tx_reporter_dump, }; #define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index cf58c9637904..29626c6c9c25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -433,7 +433,6 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) if (!ipsec) return; - drain_workqueue(ipsec->wq); destroy_workqueue(ipsec->wq); ida_destroy(&ipsec->halloc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 01f2918063af..47874d34156b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1098,49 +1098,59 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) mlx5e_dcbnl_dscp_app(priv, DELETE); } -static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, - struct mlx5e_params *params) +static void mlx5e_params_calc_trust_tx_min_inline_mode(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u8 trust_state) { - mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); - if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); + if (trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; } -static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv) +static int mlx5e_update_trust_state_hw(struct mlx5e_priv *priv, void *context) +{ + u8 *trust_state = context; + int err; + + err = mlx5_set_trust_state(priv->mdev, *trust_state); + if (err) + return err; + priv->dcbx_dp.trust_state = *trust_state; + + return 0; +} + +static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) { struct mlx5e_channels new_channels = {}; + bool reset_channels = true; + int err = 0; mutex_lock(&priv->state_lock); new_channels.params = priv->channels.params; - mlx5e_trust_update_tx_min_inline_mode(priv, &new_channels.params); + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &new_channels.params, + trust_state); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; - goto out; + reset_channels = false; } /* Skip if tx_min_inline is the same */ if (new_channels.params.tx_min_inline_mode == priv->channels.params.tx_min_inline_mode) - goto out; + reset_channels = false; - mlx5e_safe_switch_channels(priv, &new_channels, NULL); + if (reset_channels) + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_update_trust_state_hw, + &trust_state); + else + err = mlx5e_update_trust_state_hw(priv, &trust_state); -out: mutex_unlock(&priv->state_lock); -} - -static int mlx5e_set_trust_state(struct mlx5e_priv *priv, u8 trust_state) -{ - int err; - - err = mlx5_set_trust_state(priv->mdev, trust_state); - if (err) - return err; - priv->dcbx_dp.trust_state = trust_state; - mlx5e_trust_update_sq_inline_mode(priv); return err; } @@ -1171,7 +1181,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) if (err) return err; - mlx5e_trust_update_tx_min_inline_mode(priv, &priv->channels.params); + mlx5e_params_calc_trust_tx_min_inline_mode(priv->mdev, &priv->channels.params, + priv->dcbx_dp.trust_state); err = mlx5_query_dscp2prio(priv->mdev, priv->dcbx_dp.dscp2prio); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d674cb679895..06f6f08ff5eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -357,7 +357,7 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, goto unlock; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); unlock: mutex_unlock(&priv->state_lock); @@ -432,9 +432,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { *cur_params = new_channels.params; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); + mlx5e_num_channels_changed(priv); goto out; } @@ -442,12 +440,9 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (arfs_enabled) mlx5e_arfs_disable(priv); - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); - /* Switch to new channels, set new parameters and close old ones */ - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_num_channels_changed_ctx, NULL); if (arfs_enabled) { int err2 = mlx5e_arfs_enable(priv); @@ -580,7 +575,7 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); out: mutex_unlock(&priv->state_lock); @@ -633,6 +628,8 @@ static const u32 pplm_fec_2_ethtool[] = { [MLX5E_FEC_NOFEC] = ETHTOOL_FEC_OFF, [MLX5E_FEC_FIRECODE] = ETHTOOL_FEC_BASER, [MLX5E_FEC_RS_528_514] = ETHTOOL_FEC_RS, + [MLX5E_FEC_RS_544_514] = ETHTOOL_FEC_RS, + [MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_FEC_LLRS, }; static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size) @@ -650,45 +647,48 @@ static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size) return 0; } -/* we use ETHTOOL_FEC_* offset and apply it to ETHTOOL_LINK_MODE_FEC_*_BIT */ -static u32 ethtool_fec2ethtool_caps(u_long ethtool_fec_code) -{ - u32 offset; - - offset = find_first_bit(ðtool_fec_code, sizeof(u32)); - offset -= ETHTOOL_FEC_OFF_BIT; - offset += ETHTOOL_LINK_MODE_FEC_NONE_BIT; +#define MLX5E_ADVERTISE_SUPPORTED_FEC(mlx5_fec, ethtool_fec) \ + do { \ + if (mlx5e_fec_in_caps(dev, 1 << (mlx5_fec))) \ + __set_bit(ethtool_fec, \ + link_ksettings->link_modes.supported);\ + } while (0) - return offset; -} +static const u32 pplm_fec_2_ethtool_linkmodes[] = { + [MLX5E_FEC_NOFEC] = ETHTOOL_LINK_MODE_FEC_NONE_BIT, + [MLX5E_FEC_FIRECODE] = ETHTOOL_LINK_MODE_FEC_BASER_BIT, + [MLX5E_FEC_RS_528_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, + [MLX5E_FEC_RS_544_514] = ETHTOOL_LINK_MODE_FEC_RS_BIT, + [MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_LINK_MODE_FEC_LLRS_BIT, +}; static int get_fec_supported_advertised(struct mlx5_core_dev *dev, struct ethtool_link_ksettings *link_ksettings) { - u_long fec_caps = 0; - u32 active_fec = 0; - u32 offset; + u_long active_fec = 0; u32 bitn; int err; - err = mlx5e_get_fec_caps(dev, (u8 *)&fec_caps); + err = mlx5e_get_fec_mode(dev, (u32 *)&active_fec, NULL); if (err) return (err == -EOPNOTSUPP) ? 0 : err; - err = mlx5e_get_fec_mode(dev, &active_fec, NULL); - if (err) - return err; - - for_each_set_bit(bitn, &fec_caps, ARRAY_SIZE(pplm_fec_2_ethtool)) { - u_long ethtool_bitmask = pplm_fec_2_ethtool[bitn]; - - offset = ethtool_fec2ethtool_caps(ethtool_bitmask); - __set_bit(offset, link_ksettings->link_modes.supported); - } - - active_fec = pplm2ethtool_fec(active_fec, sizeof(u32) * BITS_PER_BYTE); - offset = ethtool_fec2ethtool_caps(active_fec); - __set_bit(offset, link_ksettings->link_modes.advertising); + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_NOFEC, + ETHTOOL_LINK_MODE_FEC_NONE_BIT); + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_FIRECODE, + ETHTOOL_LINK_MODE_FEC_BASER_BIT); + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_RS_528_514, + ETHTOOL_LINK_MODE_FEC_RS_BIT); + MLX5E_ADVERTISE_SUPPORTED_FEC(MLX5E_FEC_LLRS_272_257_1, + ETHTOOL_LINK_MODE_FEC_LLRS_BIT); + + /* active fec is a bit set, find out which bit is set and + * advertise the corresponding ethtool bit + */ + bitn = find_first_bit(&active_fec, sizeof(u32) * BITS_PER_BYTE); + if (bitn < ARRAY_SIZE(pplm_fec_2_ethtool_linkmodes)) + __set_bit(pplm_fec_2_ethtool_linkmodes[bitn], + link_ksettings->link_modes.advertising); return 0; } @@ -1511,7 +1511,7 @@ static int mlx5e_get_fecparam(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - u8 fec_configured = 0; + u16 fec_configured = 0; u32 fec_active = 0; int err; @@ -1527,7 +1527,7 @@ static int mlx5e_get_fecparam(struct net_device *netdev, return -EOPNOTSUPP; fecparam->fec = pplm2ethtool_fec((u_long)fec_configured, - sizeof(u8) * BITS_PER_BYTE); + sizeof(u16) * BITS_PER_BYTE); return 0; } @@ -1537,10 +1537,14 @@ static int mlx5e_set_fecparam(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - u8 fec_policy = 0; + u16 fec_policy = 0; int mode; int err; + if (bitmap_weight((unsigned long *)&fecparam->fec, + ETHTOOL_FEC_LLRS_BIT + 1) > 1) + return -EOPNOTSUPP; + for (mode = 0; mode < ARRAY_SIZE(pplm_fec_2_ethtool); mode++) { if (!(pplm_fec_2_ethtool[mode] & fecparam->fec)) continue; @@ -1739,7 +1743,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable, return 0; } - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable) @@ -1772,7 +1776,7 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return 0; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) return err; @@ -1829,7 +1833,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return 0; } - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable) @@ -1873,7 +1877,7 @@ static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable) return 0; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 21de4764d4c0..a230df2a45aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1794,29 +1794,6 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } -static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c, - struct mlx5e_params *params) -{ - int num_comp_vectors = mlx5_comp_vectors_count(c->mdev); - int irq; - - if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL)) - return -ENOMEM; - - for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq)); - - cpumask_set_cpu(cpu, c->xps_cpumask); - } - - return 0; -} - -static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c) -{ - free_cpumask_var(c->xps_cpumask); -} - static int mlx5e_open_queues(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1967,10 +1944,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->irq_desc = irq_to_desc(irq); c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); - err = mlx5e_alloc_xps_cpumask(c, params); - if (err) - goto err_free_channel; - netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); err = mlx5e_open_queues(c, params, cparam); @@ -1993,9 +1966,7 @@ err_close_queues: err_napi_del: netif_napi_del(&c->napi); - mlx5e_free_xps_cpumask(c); -err_free_channel: kvfree(c); return err; @@ -2009,7 +1980,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_icosq(&c->icosq); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix); if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) mlx5e_activate_xsk(c); @@ -2034,7 +2004,6 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) mlx5e_close_xsk(c); mlx5e_close_queues(c); netif_napi_del(&c->napi); - mlx5e_free_xps_cpumask(c); kvfree(c); } @@ -2784,6 +2753,8 @@ free_in: return err; } +static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro); + static int mlx5e_set_mtu(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 mtu) { @@ -2833,6 +2804,8 @@ int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv) return 0; } +MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_set_dev_port_mtu); + void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv) { struct mlx5e_params *params = &priv->channels.params; @@ -2869,6 +2842,54 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_tc_queue(netdev, tc, nch, 0); } +static void mlx5e_update_netdev_queues(struct mlx5e_priv *priv, u16 count) +{ + int num_txqs = count * priv->channels.params.num_tc; + int num_rxqs = count * priv->profile->rq_groups; + struct net_device *netdev = priv->netdev; + + mlx5e_netdev_set_tcs(netdev); + netif_set_real_num_tx_queues(netdev, num_txqs); + netif_set_real_num_rx_queues(netdev, num_rxqs); +} + +static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, + struct mlx5e_params *params) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int num_comp_vectors, ix, irq; + + num_comp_vectors = mlx5_comp_vectors_count(mdev); + + for (ix = 0; ix < params->num_channels; ix++) { + cpumask_clear(priv->scratchpad.cpumask); + + for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(mdev, irq)); + + cpumask_set_cpu(cpu, priv->scratchpad.cpumask); + } + + netif_set_xps_queue(priv->netdev, priv->scratchpad.cpumask, ix); + } +} + +int mlx5e_num_channels_changed(struct mlx5e_priv *priv) +{ + u16 count = priv->channels.params.num_channels; + + mlx5e_update_netdev_queues(priv, count); + mlx5e_set_default_xps_cpumasks(priv, &priv->channels.params); + + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + + return 0; +} + +MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_num_channels_changed); + static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) { int i, ch; @@ -2890,14 +2911,6 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv) void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { - int num_txqs = priv->channels.num * priv->channels.params.num_tc; - int num_rxqs = priv->channels.num * priv->profile->rq_groups; - struct net_device *netdev = priv->netdev; - - mlx5e_netdev_set_tcs(netdev); - netif_set_real_num_tx_queues(netdev, num_txqs); - netif_set_real_num_rx_queues(netdev, num_rxqs); - mlx5e_build_txq_maps(priv); mlx5e_activate_channels(&priv->channels); mlx5e_xdp_tx_enable(priv); @@ -2930,42 +2943,52 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) mlx5e_deactivate_channels(&priv->channels); } -static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, - struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) +static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *new_chs, + mlx5e_fp_preactivate preactivate, + void *context) { struct net_device *netdev = priv->netdev; - int new_num_txqs; + struct mlx5e_channels old_chs; int carrier_ok; - - new_num_txqs = new_chs->num * new_chs->params.num_tc; + int err = 0; carrier_ok = netif_carrier_ok(netdev); netif_carrier_off(netdev); - if (new_num_txqs < netdev->real_num_tx_queues) - netif_set_real_num_tx_queues(netdev, new_num_txqs); - mlx5e_deactivate_priv_channels(priv); - mlx5e_close_channels(&priv->channels); + old_chs = priv->channels; priv->channels = *new_chs; - /* New channels are ready to roll, modify HW settings if needed */ - if (hw_modify) - hw_modify(priv); + /* New channels are ready to roll, call the preactivate hook if needed + * to modify HW settings or update kernel parameters. + */ + if (preactivate) { + err = preactivate(priv, context); + if (err) { + priv->channels = old_chs; + goto out; + } + } + mlx5e_close_channels(&old_chs); priv->profile->update_rx(priv); + +out: mlx5e_activate_priv_channels(priv); /* return carrier back if needed */ if (carrier_ok) netif_carrier_on(netdev); + + return err; } int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, struct mlx5e_channels *new_chs, - mlx5e_fp_hw_modify hw_modify) + mlx5e_fp_preactivate preactivate, + void *context) { int err; @@ -2973,8 +2996,16 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv, if (err) return err; - mlx5e_switch_priv_channels(priv, new_chs, hw_modify); + err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context); + if (err) + goto err_close; + return 0; + +err_close: + mlx5e_close_channels(new_chs); + + return err; } int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) @@ -2982,7 +3013,7 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) struct mlx5e_channels new_channels = {}; new_channels.params = priv->channels.params; - return mlx5e_safe_switch_channels(priv, &new_channels, NULL); + return mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); } void mlx5e_timestamp_init(struct mlx5e_priv *priv) @@ -3431,7 +3462,8 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv, goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_num_channels_changed_ctx, NULL); if (err) goto out; @@ -3644,7 +3676,8 @@ static int set_feature_lro(struct net_device *netdev, bool enable) goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro); + err = mlx5e_safe_switch_channels(priv, &new_channels, + mlx5e_modify_tirs_lro_ctx, NULL); out: mutex_unlock(&priv->state_lock); return err; @@ -3863,7 +3896,7 @@ static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, } int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, - change_hw_mtu_cb set_mtu_cb) + mlx5e_fp_preactivate preactivate) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels new_channels = {}; @@ -3912,13 +3945,13 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (!reset) { params->sw_mtu = new_mtu; - if (set_mtu_cb) - set_mtu_cb(priv); + if (preactivate) + preactivate(priv, NULL); netdev->mtu = params->sw_mtu; goto out; } - err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb); + err = mlx5e_safe_switch_channels(priv, &new_channels, preactivate, NULL); if (err) goto out; @@ -3931,7 +3964,7 @@ out: static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu) { - return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu); + return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx); } int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) @@ -4392,7 +4425,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) mlx5e_set_rq_type(priv->mdev, &new_channels.params); old_prog = priv->channels.params.xdp_prog; - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) goto unlock; } else { @@ -4770,9 +4803,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, mlx5e_build_rq_params(mdev, params); /* HW LRO */ - - /* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */ - if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + if (MLX5_CAP_ETH(mdev, lro_cap) && + params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { /* No XSK params: checking the availability of striding RQ in general. */ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) params->lro_en = !slow_pci_heuristic(mdev); @@ -5213,6 +5245,9 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); priv->max_opened_tc = 1; + if (!alloc_cpumask_var(&priv->scratchpad.cpumask, GFP_KERNEL)) + return -ENOMEM; + mutex_init(&priv->state_lock); INIT_WORK(&priv->update_carrier_work, mlx5e_update_carrier_work); INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); @@ -5221,7 +5256,7 @@ int mlx5e_netdev_init(struct net_device *netdev, priv->wq = create_singlethread_workqueue("mlx5e"); if (!priv->wq) - return -ENOMEM; + goto err_free_cpumask; /* netdev init */ netif_carrier_off(netdev); @@ -5231,11 +5266,17 @@ int mlx5e_netdev_init(struct net_device *netdev, #endif return 0; + +err_free_cpumask: + free_cpumask_var(priv->scratchpad.cpumask); + + return -ENOMEM; } void mlx5e_netdev_cleanup(struct net_device *netdev, struct mlx5e_priv *priv) { destroy_workqueue(priv->wq); + free_cpumask_var(priv->scratchpad.cpumask); } struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, @@ -5270,6 +5311,7 @@ err_free_netdev: int mlx5e_attach_netdev(struct mlx5e_priv *priv) { + const bool take_rtnl = priv->netdev->reg_state == NETREG_REGISTERED; const struct mlx5e_profile *profile; int max_nch; int err; @@ -5281,10 +5323,25 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) max_nch = mlx5e_get_max_num_channels(priv->mdev); if (priv->channels.params.num_channels > max_nch) { mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch); + /* Reducing the number of channels - RXFH has to be reset, and + * mlx5e_num_channels_changed below will build the RQT. + */ + priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED; priv->channels.params.num_channels = max_nch; - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, max_nch); } + /* 1. Set the real number of queues in the kernel the first time. + * 2. Set our default XPS cpumask. + * 3. Build the RQT. + * + * rtnl_lock is required by netif_set_real_num_*_queues in case the + * netdev has been registered by this point (if this function was called + * in the reload or resume flow). + */ + if (take_rtnl) + rtnl_lock(); + mlx5e_num_channels_changed(priv); + if (take_rtnl) + rtnl_unlock(); err = profile->init_tx(priv); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 6ed307d7f191..5df8f50b76e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1396,7 +1396,7 @@ static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu) { - return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu); + return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu_ctx); } static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1c3ab69cbd96..065c74a2d0c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -158,7 +158,8 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, mlx5e_read_mini_arr_slot(wq, cqd, cqcc); mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); - rq->handle_rx_cqe(rq, &cqd->title); + INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, rq, &cqd->title); } mlx5e_cqes_update_owner(wq, cqcc - wq->cc); wq->cc = cqcc; @@ -178,7 +179,8 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, mlx5e_read_title_slot(rq, wq, cc); mlx5e_read_mini_arr_slot(wq, cqd, cc + 1); mlx5e_decompress_cqe(rq, wq, cc); - rq->handle_rx_cqe(rq, &cqd->title); + INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, rq, &cqd->title); cqd->mini_arr_idx++; return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index ee60383adc5b..fd6b2a1898c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -72,8 +72,8 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, { int txq_ix = netdev_pick_tx(dev, skb, NULL); struct mlx5e_priv *priv = netdev_priv(dev); - u16 num_channels; int up = 0; + int ch_ix; if (!netdev_get_num_tc(dev)) return txq_ix; @@ -86,14 +86,13 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, if (skb_vlan_tag_present(skb)) up = skb_vlan_tag_get_prio(skb); - /* txq_ix can be larger than num_channels since - * dev->num_real_tx_queues = num_channels * num_tc + /* Normalize any picked txq_ix to [0, num_channels), + * So we can return a txq_ix that matches the channel and + * packet UP. */ - num_channels = priv->channels.params.num_channels; - if (txq_ix >= num_channels) - txq_ix = priv->txq2sq[txq_ix]->ch_ix; + ch_ix = priv->txq2sq[txq_ix]->ch_ix; - return priv->channel_tc2realtxq[txq_ix][up]; + return priv->channel_tc2realtxq[ch_ix][up]; } static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 257a7c9f7a14..267f4535c36b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -31,6 +31,7 @@ */ #include <linux/irq.h> +#include <linux/indirect_call_wrapper.h> #include "en.h" #include "en/xdp.h" #include "en/xsk/rx.h" @@ -99,7 +100,10 @@ static bool mlx5e_napi_xsk_post(struct mlx5e_xdpsq *xsksq, struct mlx5e_rq *xskr busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); mlx5e_xsk_update_tx_wakeup(xsksq); - xsk_rx_alloc_err = xskrq->post_wqes(xskrq); + xsk_rx_alloc_err = INDIRECT_CALL_2(xskrq->post_wqes, + mlx5e_post_rx_mpwqes, + mlx5e_post_rx_wqes, + xskrq); busy_xsk |= mlx5e_xsk_update_rx_wakeup(xskrq, xsk_rx_alloc_err); return busy_xsk; @@ -142,7 +146,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_poll_ico_cq(&c->icosq.cq); - busy |= rq->post_wqes(rq); + busy |= INDIRECT_CALL_2(rq->post_wqes, + mlx5e_post_rx_mpwqes, + mlx5e_post_rx_wqes, + rq); if (xsk_open) { mlx5e_poll_ico_cq(&c->xskicosq.cq); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 909a7f284614..90e3d0233101 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -613,6 +613,44 @@ static void mlx5_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle) fwhandle, 0); } +#define MLX5_FSM_REACTIVATE_TOUT 5000 /* msecs */ +static int mlx5_fsm_reactivate(struct mlxfw_dev *mlxfw_dev, u8 *status) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(MLX5_FSM_REACTIVATE_TOUT); + struct mlx5_mlxfw_dev *mlx5_mlxfw_dev = + container_of(mlxfw_dev, struct mlx5_mlxfw_dev, mlxfw_dev); + struct mlx5_core_dev *dev = mlx5_mlxfw_dev->mlx5_core_dev; + u32 out[MLX5_ST_SZ_DW(mirc_reg)]; + u32 in[MLX5_ST_SZ_DW(mirc_reg)]; + int err; + + if (!MLX5_CAP_MCAM_REG2(dev, mirc)) + return -EOPNOTSUPP; + + memset(in, 0, sizeof(in)); + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_MIRC, 0, 1); + if (err) + return err; + + do { + memset(out, 0, sizeof(out)); + err = mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_MIRC, 0, 0); + if (err) + return err; + + *status = MLX5_GET(mirc_reg, out, status_code); + if (*status != MLXFW_FSM_REACTIVATE_STATUS_BUSY) + return 0; + + msleep(20); + } while (time_before(jiffies, exp_time)); + + return 0; +} + static const struct mlxfw_dev_ops mlx5_mlxfw_dev_ops = { .component_query = mlx5_component_query, .fsm_lock = mlx5_fsm_lock, @@ -620,6 +658,7 @@ static const struct mlxfw_dev_ops mlx5_mlxfw_dev_ops = { .fsm_block_download = mlx5_fsm_block_download, .fsm_component_verify = mlx5_fsm_component_verify, .fsm_activate = mlx5_fsm_activate, + .fsm_reactivate = mlx5_fsm_reactivate, .fsm_query_state = mlx5_fsm_query_state, .fsm_cancel = mlx5_fsm_cancel, .fsm_release = mlx5_fsm_release @@ -634,6 +673,7 @@ int mlx5_firmware_flash(struct mlx5_core_dev *dev, .ops = &mlx5_mlxfw_dev_ops, .psid = dev->board_id, .psid_size = strlen(dev->board_id), + .devlink = priv_to_devlink(dev), }, .mlx5_core_dev = dev }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 56078b23f1a0..673aaa815f57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -483,7 +483,7 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu) new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; - err = mlx5e_safe_switch_channels(priv, &new_channels, NULL); + err = mlx5e_safe_switch_channels(priv, &new_channels, NULL, NULL); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c index e065c2f68f5a..6cbccba56f70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -21,7 +21,7 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) struct mlx5_dm *dm; if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) - return 0; + return NULL; dm = kzalloc(sizeof(*dm), GFP_KERNEL); if (!dm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f554cfddcf4e..204a26bf0a5f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -70,6 +70,7 @@ #include "diag/fw_tracer.h" #include "ecpf.h" #include "lib/hv_vhca.h" +#include "diag/rsc_dump.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -880,6 +881,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->tracer = mlx5_fw_tracer_create(dev); dev->hv_vhca = mlx5_hv_vhca_create(dev); + dev->rsc_dump = mlx5_rsc_dump_create(dev); return 0; @@ -909,6 +911,7 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { + mlx5_rsc_dump_destroy(dev); mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); mlx5_dm_cleanup(dev); @@ -1079,6 +1082,12 @@ static int mlx5_load(struct mlx5_core_dev *dev) mlx5_hv_vhca_init(dev->hv_vhca); + err = mlx5_rsc_dump_init(dev); + if (err) { + mlx5_core_err(dev, "Failed to init Resource dump\n"); + goto err_rsc_dump; + } + err = mlx5_fpga_device_start(dev); if (err) { mlx5_core_err(dev, "fpga device start failed %d\n", err); @@ -1134,6 +1143,8 @@ err_tls_start: err_ipsec_start: mlx5_fpga_device_stop(dev); err_fpga_start: + mlx5_rsc_dump_cleanup(dev); +err_rsc_dump: mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); err_fw_tracer: @@ -1155,6 +1166,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); + mlx5_rsc_dump_cleanup(dev); mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); mlx5_eq_table_destroy(dev); diff --git a/drivers/net/ethernet/mellanox/mlxfw/Kconfig b/drivers/net/ethernet/mellanox/mlxfw/Kconfig index 0367f835a846..5b604501f33e 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxfw/Kconfig @@ -12,3 +12,4 @@ config MLXFW To compile this driver as a module, choose M here: the module will be called mlxfw. select XZ_DEC + select NET_DEVLINK diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h index c50e74ab02c4..7654841a05c2 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h @@ -6,6 +6,30 @@ #include <linux/firmware.h> #include <linux/netlink.h> +#include <linux/device.h> +#include <net/devlink.h> + +struct mlxfw_dev { + const struct mlxfw_dev_ops *ops; + const char *psid; + u16 psid_size; + struct devlink *devlink; +}; + +static inline +struct device *mlxfw_dev_dev(struct mlxfw_dev *mlxfw_dev) +{ + return mlxfw_dev->devlink->dev; +} + +#define MLXFW_PRFX "mlxfw: " + +#define mlxfw_info(mlxfw_dev, fmt, ...) \ + dev_info(mlxfw_dev_dev(mlxfw_dev), MLXFW_PRFX fmt, ## __VA_ARGS__) +#define mlxfw_err(mlxfw_dev, fmt, ...) \ + dev_err(mlxfw_dev_dev(mlxfw_dev), MLXFW_PRFX fmt, ## __VA_ARGS__) +#define mlxfw_dbg(mlxfw_dev, fmt, ...) \ + dev_dbg(mlxfw_dev_dev(mlxfw_dev), MLXFW_PRFX fmt, ## __VA_ARGS__) enum mlxfw_fsm_state { MLXFW_FSM_STATE_IDLE, @@ -31,7 +55,19 @@ enum mlxfw_fsm_state_err { MLXFW_FSM_STATE_ERR_MAX, }; -struct mlxfw_dev; +enum mlxfw_fsm_reactivate_status { + MLXFW_FSM_REACTIVATE_STATUS_OK, + MLXFW_FSM_REACTIVATE_STATUS_BUSY, + MLXFW_FSM_REACTIVATE_STATUS_PROHIBITED_FW_VER_ERR, + MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_COPY_FAILED, + MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_ERASE_FAILED, + MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_RESTORE_FAILED, + MLXFW_FSM_REACTIVATE_STATUS_CANDIDATE_FW_DEACTIVATION_FAILED, + MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED, + MLXFW_FSM_REACTIVATE_STATUS_ERR_DEVICE_RESET_REQUIRED, + MLXFW_FSM_REACTIVATE_STATUS_ERR_FW_PROGRAMMING_NEEDED, + MLXFW_FSM_REACTIVATE_STATUS_MAX, +}; struct mlxfw_dev_ops { int (*component_query)(struct mlxfw_dev *mlxfw_dev, u16 component_index, @@ -51,6 +87,8 @@ struct mlxfw_dev_ops { int (*fsm_activate)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle); + int (*fsm_reactivate)(struct mlxfw_dev *mlxfw_dev, u8 *status); + int (*fsm_query_state)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, enum mlxfw_fsm_state *fsm_state, enum mlxfw_fsm_state_err *fsm_state_err); @@ -58,16 +96,6 @@ struct mlxfw_dev_ops { void (*fsm_cancel)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle); void (*fsm_release)(struct mlxfw_dev *mlxfw_dev, u32 fwhandle); - - void (*status_notify)(struct mlxfw_dev *mlxfw_dev, - const char *msg, const char *comp_name, - u32 done_bytes, u32 total_bytes); -}; - -struct mlxfw_dev { - const struct mlxfw_dev_ops *ops; - const char *psid; - u16 psid_size; }; #if IS_REACHABLE(CONFIG_MLXFW) diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c index 29e95d0a6ad1..046a0cb82ed8 100644 --- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c +++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c @@ -16,38 +16,70 @@ (MLXFW_FSM_STATE_WAIT_TIMEOUT_MS / MLXFW_FSM_STATE_WAIT_CYCLE_MS) #define MLXFW_FSM_MAX_COMPONENT_SIZE (10 * (1 << 20)) -static const char * const mlxfw_fsm_state_err_str[] = { - [MLXFW_FSM_STATE_ERR_ERROR] = - "general error", - [MLXFW_FSM_STATE_ERR_REJECTED_DIGEST_ERR] = - "component hash mismatch", - [MLXFW_FSM_STATE_ERR_REJECTED_NOT_APPLICABLE] = - "component not applicable", - [MLXFW_FSM_STATE_ERR_REJECTED_UNKNOWN_KEY] = - "unknown key", - [MLXFW_FSM_STATE_ERR_REJECTED_AUTH_FAILED] = - "authentication failed", - [MLXFW_FSM_STATE_ERR_REJECTED_UNSIGNED] = - "component was not signed", - [MLXFW_FSM_STATE_ERR_REJECTED_KEY_NOT_APPLICABLE] = - "key not applicable", - [MLXFW_FSM_STATE_ERR_REJECTED_BAD_FORMAT] = - "bad format", - [MLXFW_FSM_STATE_ERR_BLOCKED_PENDING_RESET] = - "pending reset", - [MLXFW_FSM_STATE_ERR_MAX] = - "unknown error" +static const int mlxfw_fsm_state_errno[] = { + [MLXFW_FSM_STATE_ERR_ERROR] = -EIO, + [MLXFW_FSM_STATE_ERR_REJECTED_DIGEST_ERR] = -EBADMSG, + [MLXFW_FSM_STATE_ERR_REJECTED_NOT_APPLICABLE] = -ENOENT, + [MLXFW_FSM_STATE_ERR_REJECTED_UNKNOWN_KEY] = -ENOKEY, + [MLXFW_FSM_STATE_ERR_REJECTED_AUTH_FAILED] = -EACCES, + [MLXFW_FSM_STATE_ERR_REJECTED_UNSIGNED] = -EKEYREVOKED, + [MLXFW_FSM_STATE_ERR_REJECTED_KEY_NOT_APPLICABLE] = -EKEYREJECTED, + [MLXFW_FSM_STATE_ERR_REJECTED_BAD_FORMAT] = -ENOEXEC, + [MLXFW_FSM_STATE_ERR_BLOCKED_PENDING_RESET] = -EBUSY, + [MLXFW_FSM_STATE_ERR_MAX] = -EINVAL }; -static void mlxfw_status_notify(struct mlxfw_dev *mlxfw_dev, - const char *msg, const char *comp_name, - u32 done_bytes, u32 total_bytes) +#define MLXFW_ERR_PRFX "Firmware flash failed: " +#define MLXFW_ERR_MSG(fwdev, extack, msg, err) do { \ + mlxfw_err(fwdev, "%s, err (%d)\n", MLXFW_ERR_PRFX msg, err); \ + NL_SET_ERR_MSG_MOD(extack, MLXFW_ERR_PRFX msg); \ +} while (0) + +static int mlxfw_fsm_state_err(struct mlxfw_dev *mlxfw_dev, + struct netlink_ext_ack *extack, + enum mlxfw_fsm_state_err err) { - if (!mlxfw_dev->ops->status_notify) - return; - mlxfw_dev->ops->status_notify(mlxfw_dev, msg, comp_name, - done_bytes, total_bytes); -} + enum mlxfw_fsm_state_err fsm_state_err; + + fsm_state_err = min_t(enum mlxfw_fsm_state_err, err, + MLXFW_FSM_STATE_ERR_MAX); + + switch (fsm_state_err) { + case MLXFW_FSM_STATE_ERR_ERROR: + MLXFW_ERR_MSG(mlxfw_dev, extack, "general error", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_DIGEST_ERR: + MLXFW_ERR_MSG(mlxfw_dev, extack, "component hash mismatch", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_NOT_APPLICABLE: + MLXFW_ERR_MSG(mlxfw_dev, extack, "component not applicable", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_UNKNOWN_KEY: + MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown key", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_AUTH_FAILED: + MLXFW_ERR_MSG(mlxfw_dev, extack, "authentication failed", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_UNSIGNED: + MLXFW_ERR_MSG(mlxfw_dev, extack, "component was not signed", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_KEY_NOT_APPLICABLE: + MLXFW_ERR_MSG(mlxfw_dev, extack, "key not applicable", err); + break; + case MLXFW_FSM_STATE_ERR_REJECTED_BAD_FORMAT: + MLXFW_ERR_MSG(mlxfw_dev, extack, "bad format", err); + break; + case MLXFW_FSM_STATE_ERR_BLOCKED_PENDING_RESET: + MLXFW_ERR_MSG(mlxfw_dev, extack, "pending reset", err); + break; + case MLXFW_FSM_STATE_ERR_OK: /* fall through */ + case MLXFW_FSM_STATE_ERR_MAX: + MLXFW_ERR_MSG(mlxfw_dev, extack, "unknown error", err); + break; + }; + + return mlxfw_fsm_state_errno[fsm_state_err]; +}; static int mlxfw_fsm_state_wait(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, enum mlxfw_fsm_state fsm_state, @@ -62,21 +94,18 @@ static int mlxfw_fsm_state_wait(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, retry: err = mlxfw_dev->ops->fsm_query_state(mlxfw_dev, fwhandle, &curr_fsm_state, &fsm_state_err); - if (err) + if (err) { + MLXFW_ERR_MSG(mlxfw_dev, extack, "FSM state query failed", err); return err; - - if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) { - fsm_state_err = min_t(enum mlxfw_fsm_state_err, - fsm_state_err, MLXFW_FSM_STATE_ERR_MAX); - pr_err("Firmware flash failed: %s\n", - mlxfw_fsm_state_err_str[fsm_state_err]); - NL_SET_ERR_MSG_MOD(extack, "Firmware flash failed"); - return -EINVAL; } + + if (fsm_state_err != MLXFW_FSM_STATE_ERR_OK) + return mlxfw_fsm_state_err(mlxfw_dev, extack, fsm_state_err); + if (curr_fsm_state != fsm_state) { if (--times == 0) { - pr_err("Timeout reached on FSM state change"); - NL_SET_ERR_MSG_MOD(extack, "Timeout reached on FSM state change"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Timeout reached on FSM state change", -ETIMEDOUT); return -ETIMEDOUT; } msleep(MLXFW_FSM_STATE_WAIT_CYCLE_MS); @@ -85,6 +114,92 @@ retry: return 0; } +static int +mlxfw_fsm_reactivate_err(struct mlxfw_dev *mlxfw_dev, + struct netlink_ext_ack *extack, u8 err) +{ + enum mlxfw_fsm_reactivate_status status; + +#define MXFW_REACT_PRFX "Reactivate FSM: " +#define MLXFW_REACT_ERR(msg, err) \ + MLXFW_ERR_MSG(mlxfw_dev, extack, MXFW_REACT_PRFX msg, err) + + status = min_t(enum mlxfw_fsm_reactivate_status, err, + MLXFW_FSM_REACTIVATE_STATUS_MAX); + + switch (status) { + case MLXFW_FSM_REACTIVATE_STATUS_BUSY: + MLXFW_REACT_ERR("busy", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_PROHIBITED_FW_VER_ERR: + MLXFW_REACT_ERR("prohibited fw ver", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_COPY_FAILED: + MLXFW_REACT_ERR("first page copy failed", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_ERASE_FAILED: + MLXFW_REACT_ERR("first page erase failed", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_FIRST_PAGE_RESTORE_FAILED: + MLXFW_REACT_ERR("first page restore failed", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_CANDIDATE_FW_DEACTIVATION_FAILED: + MLXFW_REACT_ERR("candidate fw deactivation failed", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_ERR_DEVICE_RESET_REQUIRED: + MLXFW_REACT_ERR("device reset required", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_ERR_FW_PROGRAMMING_NEEDED: + MLXFW_REACT_ERR("fw programming needed", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED: + MLXFW_REACT_ERR("fw already activated", err); + break; + case MLXFW_FSM_REACTIVATE_STATUS_OK: /* fall through */ + case MLXFW_FSM_REACTIVATE_STATUS_MAX: + MLXFW_REACT_ERR("unexpected error", err); + break; + }; + return -EREMOTEIO; +}; + +static int mlxfw_fsm_reactivate(struct mlxfw_dev *mlxfw_dev, + struct netlink_ext_ack *extack, + bool *supported) +{ + u8 status; + int err; + + if (!mlxfw_dev->ops->fsm_reactivate) + return 0; + + err = mlxfw_dev->ops->fsm_reactivate(mlxfw_dev, &status); + if (err == -EOPNOTSUPP) { + *supported = false; + return 0; + } + + if (err) { + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Could not reactivate firmware flash", err); + return err; + } + + if (status == MLXFW_FSM_REACTIVATE_STATUS_OK || + status == MLXFW_FSM_REACTIVATE_STATUS_FW_ALREADY_ACTIVATED) + return 0; + + return mlxfw_fsm_reactivate_err(mlxfw_dev, extack, status); +} + +static void mlxfw_status_notify(struct mlxfw_dev *mlxfw_dev, + const char *msg, const char *comp_name, + u32 done_bytes, u32 total_bytes) +{ + devlink_flash_update_status_notify(mlxfw_dev->devlink, msg, comp_name, + done_bytes, total_bytes); +} + #define MLXFW_ALIGN_DOWN(x, align_bits) ((x) & ~((1 << (align_bits)) - 1)) #define MLXFW_ALIGN_UP(x, align_bits) \ MLXFW_ALIGN_DOWN((x) + ((1 << (align_bits)) - 1), (align_bits)) @@ -92,6 +207,7 @@ retry: static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, struct mlxfw_mfa2_component *comp, + bool reactivate_supp, struct netlink_ext_ack *extack) { u16 comp_max_write_size; @@ -108,34 +224,43 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev, err = mlxfw_dev->ops->component_query(mlxfw_dev, comp->index, &comp_max_size, &comp_align_bits, &comp_max_write_size); - if (err) + if (err) { + MLXFW_ERR_MSG(mlxfw_dev, extack, "FSM component query failed", err); return err; + } comp_max_size = min_t(u32, comp_max_size, MLXFW_FSM_MAX_COMPONENT_SIZE); if (comp->data_size > comp_max_size) { - pr_err("Component %d is of size %d which is bigger than limit %d\n", - comp->index, comp->data_size, comp_max_size); - NL_SET_ERR_MSG_MOD(extack, "Component is bigger than limit"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Component size is bigger than limit", -EINVAL); return -EINVAL; } comp_max_write_size = MLXFW_ALIGN_DOWN(comp_max_write_size, comp_align_bits); - pr_debug("Component update\n"); + mlxfw_dbg(mlxfw_dev, "Component update\n"); mlxfw_status_notify(mlxfw_dev, "Updating component", comp_name, 0, 0); err = mlxfw_dev->ops->fsm_component_update(mlxfw_dev, fwhandle, comp->index, comp->data_size); - if (err) + if (err) { + if (!reactivate_supp) + MLXFW_ERR_MSG(mlxfw_dev, extack, + "FSM component update failed, FW reactivate is not supported", + err); + else + MLXFW_ERR_MSG(mlxfw_dev, extack, + "FSM component update failed", err); return err; + } err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle, MLXFW_FSM_STATE_DOWNLOAD, extack); if (err) goto err_out; - pr_debug("Component download\n"); + mlxfw_dbg(mlxfw_dev, "Component download\n"); mlxfw_status_notify(mlxfw_dev, "Downloading component", comp_name, 0, comp->data_size); for (offset = 0; @@ -147,19 +272,25 @@ static int mlxfw_flash_component(struct mlxfw_dev *mlxfw_dev, err = mlxfw_dev->ops->fsm_block_download(mlxfw_dev, fwhandle, block_ptr, block_size, offset); - if (err) + if (err) { + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Component download failed", err); goto err_out; + } mlxfw_status_notify(mlxfw_dev, "Downloading component", comp_name, offset + block_size, comp->data_size); } - pr_debug("Component verify\n"); + mlxfw_dbg(mlxfw_dev, "Component verify\n"); mlxfw_status_notify(mlxfw_dev, "Verifying component", comp_name, 0, 0); err = mlxfw_dev->ops->fsm_component_verify(mlxfw_dev, fwhandle, comp->index); - if (err) + if (err) { + MLXFW_ERR_MSG(mlxfw_dev, extack, + "FSM component verify failed", err); goto err_out; + } err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle, MLXFW_FSM_STATE_LOCKED, extack); @@ -174,6 +305,7 @@ err_out: static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, struct mlxfw_mfa2_file *mfa2_file, + bool reactivate_supp, struct netlink_ext_ack *extack) { u32 component_count; @@ -184,8 +316,8 @@ static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, mlxfw_dev->psid_size, &component_count); if (err) { - pr_err("Could not find device PSID in MFA2 file\n"); - NL_SET_ERR_MSG_MOD(extack, "Could not find device PSID in MFA2 file"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Could not find device PSID in MFA2 file", err); return err; } @@ -194,11 +326,17 @@ static int mlxfw_flash_components(struct mlxfw_dev *mlxfw_dev, u32 fwhandle, comp = mlxfw_mfa2_file_component_get(mfa2_file, mlxfw_dev->psid, mlxfw_dev->psid_size, i); - if (IS_ERR(comp)) - return PTR_ERR(comp); + if (IS_ERR(comp)) { + err = PTR_ERR(comp); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Failed to get MFA2 component", err); + return err; + } - pr_info("Flashing component type %d\n", comp->index); - err = mlxfw_flash_component(mlxfw_dev, fwhandle, comp, extack); + mlxfw_info(mlxfw_dev, "Flashing component type %d\n", + comp->index); + err = mlxfw_flash_component(mlxfw_dev, fwhandle, comp, + reactivate_supp, extack); mlxfw_mfa2_file_component_put(comp); if (err) return err; @@ -211,26 +349,32 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev, struct netlink_ext_ack *extack) { struct mlxfw_mfa2_file *mfa2_file; + bool reactivate_supp = true; u32 fwhandle; int err; if (!mlxfw_mfa2_check(firmware)) { - pr_err("Firmware file is not MFA2\n"); - NL_SET_ERR_MSG_MOD(extack, "Firmware file is not MFA2"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Firmware file is not MFA2", -EINVAL); return -EINVAL; } mfa2_file = mlxfw_mfa2_file_init(firmware); - if (IS_ERR(mfa2_file)) - return PTR_ERR(mfa2_file); + if (IS_ERR(mfa2_file)) { + err = PTR_ERR(mfa2_file); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Failed to initialize MFA2 firmware file", err); + return err; + } - pr_info("Initialize firmware flash process\n"); + mlxfw_info(mlxfw_dev, "Initialize firmware flash process\n"); + devlink_flash_update_begin_notify(mlxfw_dev->devlink); mlxfw_status_notify(mlxfw_dev, "Initializing firmware flash process", NULL, 0, 0); err = mlxfw_dev->ops->fsm_lock(mlxfw_dev, &fwhandle); if (err) { - pr_err("Could not lock the firmware FSM\n"); - NL_SET_ERR_MSG_MOD(extack, "Could not lock the firmware FSM"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Could not lock the firmware FSM", err); goto err_fsm_lock; } @@ -239,16 +383,26 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev, if (err) goto err_state_wait_idle_to_locked; - err = mlxfw_flash_components(mlxfw_dev, fwhandle, mfa2_file, extack); + err = mlxfw_fsm_reactivate(mlxfw_dev, extack, &reactivate_supp); + if (err) + goto err_fsm_reactivate; + + err = mlxfw_fsm_state_wait(mlxfw_dev, fwhandle, + MLXFW_FSM_STATE_LOCKED, extack); + if (err) + goto err_state_wait_reactivate_to_locked; + + err = mlxfw_flash_components(mlxfw_dev, fwhandle, mfa2_file, + reactivate_supp, extack); if (err) goto err_flash_components; - pr_debug("Activate image\n"); + mlxfw_dbg(mlxfw_dev, "Activate image\n"); mlxfw_status_notify(mlxfw_dev, "Activating image", NULL, 0, 0); err = mlxfw_dev->ops->fsm_activate(mlxfw_dev, fwhandle); if (err) { - pr_err("Could not activate the downloaded image\n"); - NL_SET_ERR_MSG_MOD(extack, "Could not activate the downloaded image"); + MLXFW_ERR_MSG(mlxfw_dev, extack, + "Could not activate the downloaded image", err); goto err_fsm_activate; } @@ -257,21 +411,25 @@ int mlxfw_firmware_flash(struct mlxfw_dev *mlxfw_dev, if (err) goto err_state_wait_activate_to_locked; - pr_debug("Handle release\n"); + mlxfw_dbg(mlxfw_dev, "Handle release\n"); mlxfw_dev->ops->fsm_release(mlxfw_dev, fwhandle); - pr_info("Firmware flash done.\n"); + mlxfw_info(mlxfw_dev, "Firmware flash done\n"); mlxfw_status_notify(mlxfw_dev, "Firmware flash done", NULL, 0, 0); mlxfw_mfa2_file_fini(mfa2_file); + devlink_flash_update_end_notify(mlxfw_dev->devlink); return 0; err_state_wait_activate_to_locked: err_fsm_activate: err_flash_components: +err_state_wait_reactivate_to_locked: +err_fsm_reactivate: err_state_wait_idle_to_locked: mlxfw_dev->ops->fsm_release(mlxfw_dev, fwhandle); err_fsm_lock: mlxfw_mfa2_file_fini(mfa2_file); + devlink_flash_update_end_notify(mlxfw_dev->devlink); return err; } EXPORT_SYMBOL(mlxfw_firmware_flash); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e9f791c43f20..1078f88cff18 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -82,7 +82,7 @@ struct mlxsw_core { struct mlxsw_core_port *ports; unsigned int max_ports; bool fw_flash_in_progress; - unsigned long driver_priv[0]; + unsigned long driver_priv[]; /* driver_priv has to be always the last item */ }; @@ -142,6 +142,7 @@ struct mlxsw_rx_listener_item { struct list_head list; struct mlxsw_rx_listener rxl; void *priv; + bool enabled; }; struct mlxsw_event_listener_item { @@ -1457,14 +1458,12 @@ static bool __is_rx_listener_equal(const struct mlxsw_rx_listener *rxl_a, static struct mlxsw_rx_listener_item * __find_rx_listener_item(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv) + const struct mlxsw_rx_listener *rxl) { struct mlxsw_rx_listener_item *rxl_item; list_for_each_entry(rxl_item, &mlxsw_core->rx_listener_list, list) { - if (__is_rx_listener_equal(&rxl_item->rxl, rxl) && - rxl_item->priv == priv) + if (__is_rx_listener_equal(&rxl_item->rxl, rxl)) return rxl_item; } return NULL; @@ -1472,11 +1471,11 @@ __find_rx_listener_item(struct mlxsw_core *mlxsw_core, int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, - void *priv) + void *priv, bool enabled) { struct mlxsw_rx_listener_item *rxl_item; - rxl_item = __find_rx_listener_item(mlxsw_core, rxl, priv); + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); if (rxl_item) return -EEXIST; rxl_item = kmalloc(sizeof(*rxl_item), GFP_KERNEL); @@ -1484,6 +1483,7 @@ int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, return -ENOMEM; rxl_item->rxl = *rxl; rxl_item->priv = priv; + rxl_item->enabled = enabled; list_add_rcu(&rxl_item->list, &mlxsw_core->rx_listener_list); return 0; @@ -1491,12 +1491,11 @@ int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, EXPORT_SYMBOL(mlxsw_core_rx_listener_register); void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv) + const struct mlxsw_rx_listener *rxl) { struct mlxsw_rx_listener_item *rxl_item; - rxl_item = __find_rx_listener_item(mlxsw_core, rxl, priv); + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); if (!rxl_item) return; list_del_rcu(&rxl_item->list); @@ -1505,6 +1504,19 @@ void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_rx_listener_unregister); +static void +mlxsw_core_rx_listener_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_rx_listener *rxl, + bool enabled) +{ + struct mlxsw_rx_listener_item *rxl_item; + + rxl_item = __find_rx_listener_item(mlxsw_core, rxl); + if (WARN_ON(!rxl_item)) + return; + rxl_item->enabled = enabled; +} + static void mlxsw_core_event_listener_func(struct sk_buff *skb, u8 local_port, void *priv) { @@ -1534,14 +1546,12 @@ static bool __is_event_listener_equal(const struct mlxsw_event_listener *el_a, static struct mlxsw_event_listener_item * __find_event_listener_item(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv) + const struct mlxsw_event_listener *el) { struct mlxsw_event_listener_item *el_item; list_for_each_entry(el_item, &mlxsw_core->event_listener_list, list) { - if (__is_event_listener_equal(&el_item->el, el) && - el_item->priv == priv) + if (__is_event_listener_equal(&el_item->el, el)) return el_item; } return NULL; @@ -1559,7 +1569,7 @@ int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, .trap_id = el->trap_id, }; - el_item = __find_event_listener_item(mlxsw_core, el, priv); + el_item = __find_event_listener_item(mlxsw_core, el); if (el_item) return -EEXIST; el_item = kmalloc(sizeof(*el_item), GFP_KERNEL); @@ -1568,7 +1578,7 @@ int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, el_item->el = *el; el_item->priv = priv; - err = mlxsw_core_rx_listener_register(mlxsw_core, &rxl, el_item); + err = mlxsw_core_rx_listener_register(mlxsw_core, &rxl, el_item, true); if (err) goto err_rx_listener_register; @@ -1586,8 +1596,7 @@ err_rx_listener_register: EXPORT_SYMBOL(mlxsw_core_event_listener_register); void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv) + const struct mlxsw_event_listener *el) { struct mlxsw_event_listener_item *el_item; const struct mlxsw_rx_listener rxl = { @@ -1596,10 +1605,10 @@ void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, .trap_id = el->trap_id, }; - el_item = __find_event_listener_item(mlxsw_core, el, priv); + el_item = __find_event_listener_item(mlxsw_core, el); if (!el_item) return; - mlxsw_core_rx_listener_unregister(mlxsw_core, &rxl, el_item); + mlxsw_core_rx_listener_unregister(mlxsw_core, &rxl); list_del(&el_item->list); kfree(el_item); } @@ -1607,16 +1616,18 @@ EXPORT_SYMBOL(mlxsw_core_event_listener_unregister); static int mlxsw_core_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, - void *priv) + void *priv, bool enabled) { - if (listener->is_event) + if (listener->is_event) { + WARN_ON(!enabled); return mlxsw_core_event_listener_register(mlxsw_core, - &listener->u.event_listener, + &listener->event_listener, priv); - else + } else { return mlxsw_core_rx_listener_register(mlxsw_core, - &listener->u.rx_listener, - priv); + &listener->rx_listener, + priv, enabled); + } } static void mlxsw_core_listener_unregister(struct mlxsw_core *mlxsw_core, @@ -1625,26 +1636,31 @@ static void mlxsw_core_listener_unregister(struct mlxsw_core *mlxsw_core, { if (listener->is_event) mlxsw_core_event_listener_unregister(mlxsw_core, - &listener->u.event_listener, - priv); + &listener->event_listener); else mlxsw_core_rx_listener_unregister(mlxsw_core, - &listener->u.rx_listener, - priv); + &listener->rx_listener); } int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv) { + enum mlxsw_reg_htgt_trap_group trap_group; + enum mlxsw_reg_hpkt_action action; char hpkt_pl[MLXSW_REG_HPKT_LEN]; int err; - err = mlxsw_core_listener_register(mlxsw_core, listener, priv); + err = mlxsw_core_listener_register(mlxsw_core, listener, priv, + listener->enabled_on_register); if (err) return err; - mlxsw_reg_hpkt_pack(hpkt_pl, listener->action, listener->trap_id, - listener->trap_group, listener->is_ctrl); + action = listener->enabled_on_register ? listener->en_action : + listener->dis_action; + trap_group = listener->enabled_on_register ? listener->en_trap_group : + listener->dis_trap_group; + mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id, + trap_group, listener->is_ctrl); err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); if (err) goto err_trap_set; @@ -1664,8 +1680,8 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, char hpkt_pl[MLXSW_REG_HPKT_LEN]; if (!listener->is_event) { - mlxsw_reg_hpkt_pack(hpkt_pl, listener->unreg_action, - listener->trap_id, listener->trap_group, + mlxsw_reg_hpkt_pack(hpkt_pl, listener->dis_action, + listener->trap_id, listener->dis_trap_group, listener->is_ctrl); mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); } @@ -1674,17 +1690,33 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_trap_unregister); -int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, - const struct mlxsw_listener *listener, - enum mlxsw_reg_hpkt_action action) +int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + bool enabled) { + enum mlxsw_reg_htgt_trap_group trap_group; + enum mlxsw_reg_hpkt_action action; char hpkt_pl[MLXSW_REG_HPKT_LEN]; + int err; + + /* Not supported for event listener */ + if (WARN_ON(listener->is_event)) + return -EINVAL; + action = enabled ? listener->en_action : listener->dis_action; + trap_group = enabled ? listener->en_trap_group : + listener->dis_trap_group; mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id, - listener->trap_group, listener->is_ctrl); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); + trap_group, listener->is_ctrl); + err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); + if (err) + return err; + + mlxsw_core_rx_listener_state_set(mlxsw_core, &listener->rx_listener, + enabled); + return 0; } -EXPORT_SYMBOL(mlxsw_core_trap_action_set); +EXPORT_SYMBOL(mlxsw_core_trap_state_set); static u64 mlxsw_core_tid_get(struct mlxsw_core *mlxsw_core) { @@ -1942,7 +1974,8 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, if ((rxl->local_port == MLXSW_PORT_DONT_CARE || rxl->local_port == local_port) && rxl->trap_id == rx_info->trap_id) { - found = true; + if (rxl_item->enabled) + found = true; break; } } @@ -2168,13 +2201,22 @@ int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) /* Here we need to get the module width according to the module type. */ switch (module_type) { + case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_OSFP: + return 8; + case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: /* fall through */ case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP: + case MLXSW_REG_PMTM_MODULE_TYPE_QSFP: return 4; - case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: + case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_DSFP: return 2; - case MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP: /* fall through */ - case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: + case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: /* fall through */ + case MLXSW_REG_PMTM_MODULE_TYPE_SFP: return 1; default: return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 543476a2e503..46226823c7a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -62,7 +62,6 @@ struct mlxsw_rx_listener { void (*func)(struct sk_buff *skb, u8 local_port, void *priv); u8 local_port; u16 trap_id; - enum mlxsw_reg_hpkt_action action; }; struct mlxsw_event_listener { @@ -76,58 +75,71 @@ struct mlxsw_listener { union { struct mlxsw_rx_listener rx_listener; struct mlxsw_event_listener event_listener; - } u; - enum mlxsw_reg_hpkt_action action; - enum mlxsw_reg_hpkt_action unreg_action; - u8 trap_group; - bool is_ctrl; /* should go via control buffer or not */ - bool is_event; + }; + enum mlxsw_reg_hpkt_action en_action; /* Action when enabled */ + enum mlxsw_reg_hpkt_action dis_action; /* Action when disabled */ + u8 en_trap_group; /* Trap group when enabled */ + u8 dis_trap_group; /* Trap group when disabled */ + u8 is_ctrl:1, /* should go via control buffer or not */ + is_event:1, + enabled_on_register:1; /* Trap should be enabled when listener + * is registered. + */ }; -#define MLXSW_RXL(_func, _trap_id, _action, _is_ctrl, _trap_group, \ - _unreg_action) \ - { \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - .u.rx_listener = \ - { \ - .func = _func, \ - .local_port = MLXSW_PORT_DONT_CARE, \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - }, \ - .action = MLXSW_REG_HPKT_ACTION_##_action, \ - .unreg_action = MLXSW_REG_HPKT_ACTION_##_unreg_action, \ - .trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ - .is_ctrl = _is_ctrl, \ - .is_event = false, \ +#define __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, _enabled_on_register, _dis_trap_group) \ + { \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + .rx_listener = \ + { \ + .func = _func, \ + .local_port = MLXSW_PORT_DONT_CARE, \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + }, \ + .en_action = MLXSW_REG_HPKT_ACTION_##_en_action, \ + .dis_action = MLXSW_REG_HPKT_ACTION_##_dis_action, \ + .en_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_en_trap_group, \ + .dis_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_dis_trap_group, \ + .is_ctrl = _is_ctrl, \ + .enabled_on_register = _enabled_on_register, \ } -#define MLXSW_EVENTL(_func, _trap_id, _trap_group) \ - { \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - .u.event_listener = \ - { \ - .func = _func, \ - .trap_id = MLXSW_TRAP_ID_##_trap_id, \ - }, \ - .action = MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, \ - .trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ - .is_ctrl = false, \ - .is_event = true, \ +#define MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ + _dis_action) \ + __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _trap_group, \ + _dis_action, true, _trap_group) + +#define MLXSW_RXL_DIS(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, _dis_trap_group) \ + __MLXSW_RXL(_func, _trap_id, _en_action, _is_ctrl, _en_trap_group, \ + _dis_action, false, _dis_trap_group) + +#define MLXSW_EVENTL(_func, _trap_id, _trap_group) \ + { \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + .event_listener = \ + { \ + .func = _func, \ + .trap_id = MLXSW_TRAP_ID_##_trap_id, \ + }, \ + .en_action = MLXSW_REG_HPKT_ACTION_TRAP_TO_CPU, \ + .en_trap_group = MLXSW_REG_HTGT_TRAP_GROUP_##_trap_group, \ + .is_event = true, \ + .enabled_on_register = true, \ } int mlxsw_core_rx_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_rx_listener *rxl, - void *priv); + void *priv, bool enabled); void mlxsw_core_rx_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_rx_listener *rxl, - void *priv); + const struct mlxsw_rx_listener *rxl); int mlxsw_core_event_listener_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_event_listener *el, void *priv); void mlxsw_core_event_listener_unregister(struct mlxsw_core *mlxsw_core, - const struct mlxsw_event_listener *el, - void *priv); + const struct mlxsw_event_listener *el); int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, @@ -135,9 +147,9 @@ int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv); -int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, - const struct mlxsw_listener *listener, - enum mlxsw_reg_hpkt_action action); +int mlxsw_core_trap_state_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + bool enabled); typedef void mlxsw_reg_trans_cb_t(struct mlxsw_core *mlxsw_core, char *payload, size_t payload_len, unsigned long cb_priv); @@ -461,7 +473,10 @@ enum mlxsw_devlink_param_id { }; struct mlxsw_skb_cb { - struct mlxsw_tx_info tx_info; + union { + struct mlxsw_tx_info tx_info; + u32 cookie_index; /* Only used during receive */ + }; }; static inline struct mlxsw_skb_cb *mlxsw_skb_cb(struct sk_buff *skb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index c51b2adfc1e1..1f2e6db743e1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -7,6 +7,9 @@ #include <linux/errno.h> #include <linux/rhashtable.h> #include <linux/list.h> +#include <linux/idr.h> +#include <linux/refcount.h> +#include <net/flow_offload.h> #include "item.h" #include "trap.h" @@ -63,6 +66,8 @@ struct mlxsw_afa { void *ops_priv; struct rhashtable set_ht; struct rhashtable fwd_entry_ht; + struct rhashtable cookie_ht; + struct idr cookie_idr; }; #define MLXSW_AFA_SET_LEN 0xA8 @@ -121,6 +126,55 @@ static const struct rhashtable_params mlxsw_afa_fwd_entry_ht_params = { .automatic_shrinking = true, }; +struct mlxsw_afa_cookie { + struct rhash_head ht_node; + refcount_t ref_count; + struct rcu_head rcu; + u32 cookie_index; + struct flow_action_cookie fa_cookie; +}; + +static u32 mlxsw_afa_cookie_hash(const struct flow_action_cookie *fa_cookie, + u32 seed) +{ + return jhash2((u32 *) fa_cookie->cookie, + fa_cookie->cookie_len / sizeof(u32), seed); +} + +static u32 mlxsw_afa_cookie_key_hashfn(const void *data, u32 len, u32 seed) +{ + const struct flow_action_cookie *fa_cookie = data; + + return mlxsw_afa_cookie_hash(fa_cookie, seed); +} + +static u32 mlxsw_afa_cookie_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct mlxsw_afa_cookie *cookie = data; + + return mlxsw_afa_cookie_hash(&cookie->fa_cookie, seed); +} + +static int mlxsw_afa_cookie_obj_cmpfn(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct flow_action_cookie *fa_cookie = arg->key; + const struct mlxsw_afa_cookie *cookie = obj; + + if (cookie->fa_cookie.cookie_len == fa_cookie->cookie_len) + return memcmp(cookie->fa_cookie.cookie, fa_cookie->cookie, + fa_cookie->cookie_len); + return 1; +} + +static const struct rhashtable_params mlxsw_afa_cookie_ht_params = { + .head_offset = offsetof(struct mlxsw_afa_cookie, ht_node), + .hashfn = mlxsw_afa_cookie_key_hashfn, + .obj_hashfn = mlxsw_afa_cookie_obj_hashfn, + .obj_cmpfn = mlxsw_afa_cookie_obj_cmpfn, + .automatic_shrinking = true, +}; + struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set, const struct mlxsw_afa_ops *ops, void *ops_priv) @@ -138,11 +192,18 @@ struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set, &mlxsw_afa_fwd_entry_ht_params); if (err) goto err_fwd_entry_rhashtable_init; + err = rhashtable_init(&mlxsw_afa->cookie_ht, + &mlxsw_afa_cookie_ht_params); + if (err) + goto err_cookie_rhashtable_init; + idr_init(&mlxsw_afa->cookie_idr); mlxsw_afa->max_acts_per_set = max_acts_per_set; mlxsw_afa->ops = ops; mlxsw_afa->ops_priv = ops_priv; return mlxsw_afa; +err_cookie_rhashtable_init: + rhashtable_destroy(&mlxsw_afa->fwd_entry_ht); err_fwd_entry_rhashtable_init: rhashtable_destroy(&mlxsw_afa->set_ht); err_set_rhashtable_init: @@ -153,6 +214,9 @@ EXPORT_SYMBOL(mlxsw_afa_create); void mlxsw_afa_destroy(struct mlxsw_afa *mlxsw_afa) { + WARN_ON(!idr_is_empty(&mlxsw_afa->cookie_idr)); + idr_destroy(&mlxsw_afa->cookie_idr); + rhashtable_destroy(&mlxsw_afa->cookie_ht); rhashtable_destroy(&mlxsw_afa->fwd_entry_ht); rhashtable_destroy(&mlxsw_afa->set_ht); kfree(mlxsw_afa); @@ -627,6 +691,151 @@ err_counter_index_get: return ERR_PTR(err); } +/* 20 bits is a maximum that hardware can handle in trap with userdef action + * and carry along with the trapped packet. + */ +#define MLXSW_AFA_COOKIE_INDEX_BITS 20 +#define MLXSW_AFA_COOKIE_INDEX_MAX ((1 << MLXSW_AFA_COOKIE_INDEX_BITS) - 1) + +static struct mlxsw_afa_cookie * +mlxsw_afa_cookie_create(struct mlxsw_afa *mlxsw_afa, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie *cookie; + u32 cookie_index; + int err; + + cookie = kzalloc(sizeof(*cookie) + fa_cookie->cookie_len, GFP_KERNEL); + if (!cookie) + return ERR_PTR(-ENOMEM); + refcount_set(&cookie->ref_count, 1); + memcpy(&cookie->fa_cookie, fa_cookie, + sizeof(*fa_cookie) + fa_cookie->cookie_len); + + err = rhashtable_insert_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); + if (err) + goto err_rhashtable_insert; + + /* Start cookie indexes with 1. Leave the 0 index unused. Packets + * that come from the HW which are not dropped by drop-with-cookie + * action are going to pass cookie_index 0 to lookup. + */ + cookie_index = 1; + err = idr_alloc_u32(&mlxsw_afa->cookie_idr, cookie, &cookie_index, + MLXSW_AFA_COOKIE_INDEX_MAX, GFP_KERNEL); + if (err) + goto err_idr_alloc; + cookie->cookie_index = cookie_index; + return cookie; + +err_idr_alloc: + rhashtable_remove_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); +err_rhashtable_insert: + kfree(cookie); + return ERR_PTR(err); +} + +static void mlxsw_afa_cookie_destroy(struct mlxsw_afa *mlxsw_afa, + struct mlxsw_afa_cookie *cookie) +{ + idr_remove(&mlxsw_afa->cookie_idr, cookie->cookie_index); + rhashtable_remove_fast(&mlxsw_afa->cookie_ht, &cookie->ht_node, + mlxsw_afa_cookie_ht_params); + kfree_rcu(cookie, rcu); +} + +static struct mlxsw_afa_cookie * +mlxsw_afa_cookie_get(struct mlxsw_afa *mlxsw_afa, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie *cookie; + + cookie = rhashtable_lookup_fast(&mlxsw_afa->cookie_ht, fa_cookie, + mlxsw_afa_cookie_ht_params); + if (cookie) { + refcount_inc(&cookie->ref_count); + return cookie; + } + return mlxsw_afa_cookie_create(mlxsw_afa, fa_cookie); +} + +static void mlxsw_afa_cookie_put(struct mlxsw_afa *mlxsw_afa, + struct mlxsw_afa_cookie *cookie) +{ + if (!refcount_dec_and_test(&cookie->ref_count)) + return; + mlxsw_afa_cookie_destroy(mlxsw_afa, cookie); +} + +/* RCU read lock must be held */ +const struct flow_action_cookie * +mlxsw_afa_cookie_lookup(struct mlxsw_afa *mlxsw_afa, u32 cookie_index) +{ + struct mlxsw_afa_cookie *cookie; + + /* 0 index means no cookie */ + if (!cookie_index) + return NULL; + cookie = idr_find(&mlxsw_afa->cookie_idr, cookie_index); + if (!cookie) + return NULL; + return &cookie->fa_cookie; +} +EXPORT_SYMBOL(mlxsw_afa_cookie_lookup); + +struct mlxsw_afa_cookie_ref { + struct mlxsw_afa_resource resource; + struct mlxsw_afa_cookie *cookie; +}; + +static void +mlxsw_afa_cookie_ref_destroy(struct mlxsw_afa_block *block, + struct mlxsw_afa_cookie_ref *cookie_ref) +{ + mlxsw_afa_resource_del(&cookie_ref->resource); + mlxsw_afa_cookie_put(block->afa, cookie_ref->cookie); + kfree(cookie_ref); +} + +static void +mlxsw_afa_cookie_ref_destructor(struct mlxsw_afa_block *block, + struct mlxsw_afa_resource *resource) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + + cookie_ref = container_of(resource, struct mlxsw_afa_cookie_ref, + resource); + mlxsw_afa_cookie_ref_destroy(block, cookie_ref); +} + +static struct mlxsw_afa_cookie_ref * +mlxsw_afa_cookie_ref_create(struct mlxsw_afa_block *block, + const struct flow_action_cookie *fa_cookie) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + struct mlxsw_afa_cookie *cookie; + int err; + + cookie_ref = kzalloc(sizeof(*cookie_ref), GFP_KERNEL); + if (!cookie_ref) + return ERR_PTR(-ENOMEM); + cookie = mlxsw_afa_cookie_get(block->afa, fa_cookie); + if (IS_ERR(cookie)) { + err = PTR_ERR(cookie); + goto err_cookie_get; + } + cookie_ref->cookie = cookie; + cookie_ref->resource.destructor = mlxsw_afa_cookie_ref_destructor; + mlxsw_afa_resource_add(block, &cookie_ref->resource); + return cookie_ref; + +err_cookie_get: + kfree(cookie_ref); + return ERR_PTR(err); +} + #define MLXSW_AFA_ONE_ACTION_LEN 32 #define MLXSW_AFA_PAYLOAD_OFFSET 4 @@ -747,97 +956,170 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, } EXPORT_SYMBOL(mlxsw_afa_block_append_vlan_modify); -/* Trap / Discard Action - * --------------------- - * The Trap / Discard action enables trapping / mirroring packets to the CPU +/* Trap Action / Trap With Userdef Action + * -------------------------------------- + * The Trap action enables trapping / mirroring packets to the CPU * as well as discarding packets. * The ACL Trap / Discard separates the forward/discard control from CPU * trap control. In addition, the Trap / Discard action enables activating * SPAN (port mirroring). + * + * The Trap with userdef action action has the same functionality as + * the Trap action with addition of user defined value that can be set + * and used by higher layer applications. */ -#define MLXSW_AFA_TRAPDISC_CODE 0x03 -#define MLXSW_AFA_TRAPDISC_SIZE 1 +#define MLXSW_AFA_TRAP_CODE 0x03 +#define MLXSW_AFA_TRAP_SIZE 1 + +#define MLXSW_AFA_TRAPWU_CODE 0x04 +#define MLXSW_AFA_TRAPWU_SIZE 2 -enum mlxsw_afa_trapdisc_trap_action { - MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP = 0, - MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP = 2, +enum mlxsw_afa_trap_trap_action { + MLXSW_AFA_TRAP_TRAP_ACTION_NOP = 0, + MLXSW_AFA_TRAP_TRAP_ACTION_TRAP = 2, }; -/* afa_trapdisc_trap_action +/* afa_trap_trap_action * Trap Action. */ -MLXSW_ITEM32(afa, trapdisc, trap_action, 0x00, 24, 4); +MLXSW_ITEM32(afa, trap, trap_action, 0x00, 24, 4); -enum mlxsw_afa_trapdisc_forward_action { - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD = 1, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD = 3, +enum mlxsw_afa_trap_forward_action { + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD = 1, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD = 3, }; -/* afa_trapdisc_forward_action +/* afa_trap_forward_action * Forward Action. */ -MLXSW_ITEM32(afa, trapdisc, forward_action, 0x00, 0, 4); +MLXSW_ITEM32(afa, trap, forward_action, 0x00, 0, 4); -/* afa_trapdisc_trap_id +/* afa_trap_trap_id * Trap ID to configure. */ -MLXSW_ITEM32(afa, trapdisc, trap_id, 0x04, 0, 9); +MLXSW_ITEM32(afa, trap, trap_id, 0x04, 0, 9); -/* afa_trapdisc_mirror_agent +/* afa_trap_mirror_agent * Mirror agent. */ -MLXSW_ITEM32(afa, trapdisc, mirror_agent, 0x08, 29, 3); +MLXSW_ITEM32(afa, trap, mirror_agent, 0x08, 29, 3); -/* afa_trapdisc_mirror_enable +/* afa_trap_mirror_enable * Mirror enable. */ -MLXSW_ITEM32(afa, trapdisc, mirror_enable, 0x08, 24, 1); +MLXSW_ITEM32(afa, trap, mirror_enable, 0x08, 24, 1); + +/* user_def_val + * Value for the SW usage. Can be used to pass information of which + * rule has caused a trap. This may be overwritten by later traps. + * This field does a set on the packet's user_def_val only if this + * is the first trap_id or if the trap_id has replaced the previous + * packet's trap_id. + */ +MLXSW_ITEM32(afa, trap, user_def_val, 0x0C, 0, 20); static inline void -mlxsw_afa_trapdisc_pack(char *payload, - enum mlxsw_afa_trapdisc_trap_action trap_action, - enum mlxsw_afa_trapdisc_forward_action forward_action, - u16 trap_id) +mlxsw_afa_trap_pack(char *payload, + enum mlxsw_afa_trap_trap_action trap_action, + enum mlxsw_afa_trap_forward_action forward_action, + u16 trap_id) { - mlxsw_afa_trapdisc_trap_action_set(payload, trap_action); - mlxsw_afa_trapdisc_forward_action_set(payload, forward_action); - mlxsw_afa_trapdisc_trap_id_set(payload, trap_id); + mlxsw_afa_trap_trap_action_set(payload, trap_action); + mlxsw_afa_trap_forward_action_set(payload, forward_action); + mlxsw_afa_trap_trap_id_set(payload, trap_id); } static inline void -mlxsw_afa_trapdisc_mirror_pack(char *payload, bool mirror_enable, - u8 mirror_agent) +mlxsw_afa_trapwu_pack(char *payload, + enum mlxsw_afa_trap_trap_action trap_action, + enum mlxsw_afa_trap_forward_action forward_action, + u16 trap_id, u32 user_def_val) { - mlxsw_afa_trapdisc_mirror_enable_set(payload, mirror_enable); - mlxsw_afa_trapdisc_mirror_agent_set(payload, mirror_agent); + mlxsw_afa_trap_pack(payload, trap_action, forward_action, trap_id); + mlxsw_afa_trap_user_def_val_set(payload, user_def_val); } -int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block) +static inline void +mlxsw_afa_trap_mirror_pack(char *payload, bool mirror_enable, + u8 mirror_agent) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + mlxsw_afa_trap_mirror_enable_set(payload, mirror_enable); + mlxsw_afa_trap_mirror_agent_set(payload, mirror_agent); +} + +static int mlxsw_afa_block_append_drop_plain(struct mlxsw_afa_block *block, + bool ingress) +{ + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, + ingress ? MLXSW_TRAP_ID_DISCARD_INGRESS_ACL : + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL); return 0; } + +static int +mlxsw_afa_block_append_drop_with_cookie(struct mlxsw_afa_block *block, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) +{ + struct mlxsw_afa_cookie_ref *cookie_ref; + u32 cookie_index; + char *act; + int err; + + cookie_ref = mlxsw_afa_cookie_ref_create(block, fa_cookie); + if (IS_ERR(cookie_ref)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot create cookie for drop action"); + return PTR_ERR(cookie_ref); + } + cookie_index = cookie_ref->cookie->cookie_index; + + act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAPWU_CODE, + MLXSW_AFA_TRAPWU_SIZE); + if (IS_ERR(act)) { + NL_SET_ERR_MSG_MOD(extack, "Cannot append drop with cookie action"); + err = PTR_ERR(act); + goto err_append_action; + } + mlxsw_afa_trapwu_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, + ingress ? MLXSW_TRAP_ID_DISCARD_INGRESS_ACL : + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL, + cookie_index); + return 0; + +err_append_action: + mlxsw_afa_cookie_ref_destroy(block, cookie_ref); + return err; +} + +int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block, bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) +{ + return fa_cookie ? + mlxsw_afa_block_append_drop_with_cookie(block, ingress, + fa_cookie, extack) : + mlxsw_afa_block_append_drop_plain(block, ingress); +} EXPORT_SYMBOL(mlxsw_afa_block_append_drop); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, - trap_id); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_DISCARD, trap_id); return 0; } EXPORT_SYMBOL(mlxsw_afa_block_append_trap); @@ -845,15 +1127,13 @@ EXPORT_SYMBOL(mlxsw_afa_block_append_trap); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id) { - char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, - trap_id); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_TRAP, + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD, trap_id); return 0; } EXPORT_SYMBOL(mlxsw_afa_block_append_trap_and_forward); @@ -920,13 +1200,13 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, u8 mirror_agent) { char *act = mlxsw_afa_block_append_action(block, - MLXSW_AFA_TRAPDISC_CODE, - MLXSW_AFA_TRAPDISC_SIZE); + MLXSW_AFA_TRAP_CODE, + MLXSW_AFA_TRAP_SIZE); if (IS_ERR(act)) return PTR_ERR(act); - mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, - MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0); - mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent); + mlxsw_afa_trap_pack(act, MLXSW_AFA_TRAP_TRAP_ACTION_NOP, + MLXSW_AFA_TRAP_FORWARD_ACTION_FORWARD, 0); + mlxsw_afa_trap_mirror_pack(act, true, mirror_agent); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h index 0e3a59dda12e..5f4c1e505136 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h @@ -6,6 +6,7 @@ #include <linux/types.h> #include <linux/netdevice.h> +#include <net/flow_offload.h> struct mlxsw_afa; struct mlxsw_afa_block; @@ -42,7 +43,11 @@ int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity); int mlxsw_afa_block_continue(struct mlxsw_afa_block *block); int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id); int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block); -int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block); +const struct flow_action_cookie * +mlxsw_afa_cookie_lookup(struct mlxsw_afa *mlxsw_afa, u32 cookie_index); +int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block, bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack); int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id); int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, u16 trap_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c index feb4672a5ac0..bd2207f60722 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c @@ -72,7 +72,7 @@ struct mlxsw_afk_key_info { * is index inside "blocks" */ struct mlxsw_afk_element_usage elusage; - const struct mlxsw_afk_block *blocks[0]; + const struct mlxsw_afk_block *blocks[]; }; static bool diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 914c33e46fb4..67ee0da75af2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -575,6 +575,15 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe); + if (rx_info.trap_id == MLXSW_TRAP_ID_DISCARD_INGRESS_ACL || + rx_info.trap_id == MLXSW_TRAP_ID_DISCARD_EGRESS_ACL) { + u32 cookie_index = 0; + + if (mlxsw_pci->max_cqe_ver >= MLXSW_PCI_CQE_V2) + cookie_index = mlxsw_pci_cqe2_user_def_val_orig_pkt_len_get(cqe); + mlxsw_skb_cb(skb)->cookie_index = cookie_index; + } + byte_count = mlxsw_pci_cqe_byte_count_get(cqe); if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) byte_count -= ETH_FCS_LEN; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index 43fa8c85b5d9..32c7cabfb261 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -25,8 +25,6 @@ #define MLXSW_PCI_CIR_CTRL_STATUS_SHIFT 24 #define MLXSW_PCI_CIR_TIMEOUT_MSECS 1000 -#define MLXSW_PCI_SW_RESET 0xF0010 -#define MLXSW_PCI_SW_RESET_RST_BIT BIT(0) #define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS 900000 #define MLXSW_PCI_SW_RESET_WAIT_MSECS 200 #define MLXSW_PCI_FW_READY 0xA1844 @@ -210,6 +208,11 @@ MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5); MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6); mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12); +/* pci_cqe_user_def_val_orig_pkt_len + * When trap_id is an ACL: User defined value from policy engine action. + */ +MLXSW_ITEM32(pci, cqe2, user_def_val_orig_pkt_len, 0x14, 0, 20); + /* pci_cqe_owner * Ownership bit. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index dd6685156396..1bc65e597de0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -621,7 +621,7 @@ static inline void mlxsw_reg_sfn_pack(char *payload) { MLXSW_REG_ZERO(sfn, payload); mlxsw_reg_sfn_swid_set(payload, 0); - mlxsw_reg_sfn_end_set(payload, 1); + mlxsw_reg_sfn_end_set(payload, 0); mlxsw_reg_sfn_num_rec_set(payload, MLXSW_REG_SFN_REC_MAX_COUNT); } @@ -5440,15 +5440,29 @@ enum mlxsw_reg_pmtm_module_type { /* Backplane with 4 lanes */ MLXSW_REG_PMTM_MODULE_TYPE_BP_4X, /* QSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_QSFP, + MLXSW_REG_PMTM_MODULE_TYPE_QSFP, /* SFP */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_SFP, + MLXSW_REG_PMTM_MODULE_TYPE_SFP, /* Backplane with single lane */ MLXSW_REG_PMTM_MODULE_TYPE_BP_1X = 4, /* Backplane with two lane */ MLXSW_REG_PMTM_MODULE_TYPE_BP_2X = 8, - /* Chip2Chip */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C = 10, + /* Chip2Chip4x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C4X = 10, + /* Chip2Chip2x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C2X, + /* Chip2Chip1x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C1X, + /* QSFP-DD */ + MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, + /* OSFP */ + MLXSW_REG_PMTM_MODULE_TYPE_OSFP, + /* SFP-DD */ + MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD, + /* DSFP */ + MLXSW_REG_PMTM_MODULE_TYPE_DSFP, + /* Chip2Chip8x */ + MLXSW_REG_PMTM_MODULE_TYPE_C2C8X, }; /* reg_pmtm_module_type @@ -5526,9 +5540,11 @@ enum mlxsw_reg_htgt_trap_group { enum mlxsw_reg_htgt_discard_trap_group { MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX, + MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY, MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_L3_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS, }; /* reg_htgt_trap_group diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 7358b5bc7eb6..673fa2fd995c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -347,19 +347,6 @@ static void mlxsw_sp_fsm_release(struct mlxfw_dev *mlxfw_dev, u32 fwhandle) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mcc), mcc_pl); } -static void mlxsw_sp_status_notify(struct mlxfw_dev *mlxfw_dev, - const char *msg, const char *comp_name, - u32 done_bytes, u32 total_bytes) -{ - struct mlxsw_sp_mlxfw_dev *mlxsw_sp_mlxfw_dev = - container_of(mlxfw_dev, struct mlxsw_sp_mlxfw_dev, mlxfw_dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_mlxfw_dev->mlxsw_sp; - - devlink_flash_update_status_notify(priv_to_devlink(mlxsw_sp->core), - msg, comp_name, - done_bytes, total_bytes); -} - static const struct mlxfw_dev_ops mlxsw_sp_mlxfw_dev_ops = { .component_query = mlxsw_sp_component_query, .fsm_lock = mlxsw_sp_fsm_lock, @@ -370,7 +357,6 @@ static const struct mlxfw_dev_ops mlxsw_sp_mlxfw_dev_ops = { .fsm_query_state = mlxsw_sp_fsm_query_state, .fsm_cancel = mlxsw_sp_fsm_cancel, .fsm_release = mlxsw_sp_fsm_release, - .status_notify = mlxsw_sp_status_notify, }; static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp, @@ -382,16 +368,15 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp, .ops = &mlxsw_sp_mlxfw_dev_ops, .psid = mlxsw_sp->bus_info->psid, .psid_size = strlen(mlxsw_sp->bus_info->psid), + .devlink = priv_to_devlink(mlxsw_sp->core), }, .mlxsw_sp = mlxsw_sp }; int err; mlxsw_core_fw_flash_start(mlxsw_sp->core); - devlink_flash_update_begin_notify(priv_to_devlink(mlxsw_sp->core)); err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware, extack); - devlink_flash_update_end_notify(priv_to_devlink(mlxsw_sp->core)); mlxsw_core_fw_flash_end(mlxsw_sp->core); return err; @@ -2243,6 +2228,15 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_3635_stats[] = { #define MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN \ ARRAY_SIZE(mlxsw_sp_port_hw_rfc_3635_stats) +static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_ext_stats[] = { + { + .str = "ecn_marked", + .getter = mlxsw_reg_ppcnt_ecn_marked_get, + }, +}; + +#define MLXSW_SP_PORT_HW_EXT_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_ext_stats) + static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_discard_stats[] = { { .str = "discard_ingress_general", @@ -2352,6 +2346,7 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = { MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN + \ MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \ MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN + \ + MLXSW_SP_PORT_HW_EXT_STATS_LEN + \ MLXSW_SP_PORT_HW_DISCARD_STATS_LEN + \ (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \ IEEE_8021QAZ_MAX_TCS) + \ @@ -2413,6 +2408,12 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev, p += ETH_GSTRING_LEN; } + for (i = 0; i < MLXSW_SP_PORT_HW_EXT_STATS_LEN; i++) { + memcpy(p, mlxsw_sp_port_hw_ext_stats[i].str, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; i++) { memcpy(p, mlxsw_sp_port_hw_discard_stats[i].str, ETH_GSTRING_LEN); @@ -2474,6 +2475,10 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats, *p_hw_stats = mlxsw_sp_port_hw_rfc_3635_stats; *p_len = MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; break; + case MLXSW_REG_PPCNT_EXT_CNT: + *p_hw_stats = mlxsw_sp_port_hw_ext_stats; + *p_len = MLXSW_SP_PORT_HW_EXT_STATS_LEN; + break; case MLXSW_REG_PPCNT_DISCARD_CNT: *p_hw_stats = mlxsw_sp_port_hw_discard_stats; *p_len = MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; @@ -2543,6 +2548,11 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev, data, data_index); data_index += MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; + /* Extended Counters */ + __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_EXT_CNT, 0, + data, data_index); + data_index += MLXSW_SP_PORT_HW_EXT_STATS_LEN; + /* Discard Counters */ __mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_DISCARD_CNT, 0, data, data_index); @@ -2788,27 +2798,6 @@ static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u8 width, return ptys_proto; } -static u32 -mlxsw_sp1_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sp1_port_link_mode[i].speed <= upper_speed) - ptys_proto |= mlxsw_sp1_port_link_mode[i].mask; - } - return ptys_proto; -} - -static int -mlxsw_sp1_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed) -{ - *base_speed = MLXSW_SP_PORT_BASE_SPEED_25G; - return 0; -} - static void mlxsw_sp1_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, bool autoneg) @@ -2833,8 +2822,6 @@ mlxsw_sp1_port_type_speed_ops = { .from_ptys_speed_duplex = mlxsw_sp1_from_ptys_speed_duplex, .to_ptys_advert_link = mlxsw_sp1_to_ptys_advert_link, .to_ptys_speed = mlxsw_sp1_to_ptys_speed, - .to_ptys_upper_speed = mlxsw_sp1_to_ptys_upper_speed, - .port_speed_base = mlxsw_sp1_port_speed_base, .reg_ptys_eth_pack = mlxsw_sp1_reg_ptys_eth_pack, .reg_ptys_eth_unpack = mlxsw_sp1_reg_ptys_eth_unpack, }; @@ -3235,51 +3222,6 @@ static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, return ptys_proto; } -static u32 -mlxsw_sp2_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sp2_port_link_mode[i].speed <= upper_speed) - ptys_proto |= mlxsw_sp2_port_link_mode[i].mask; - } - return ptys_proto; -} - -static int -mlxsw_sp2_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed) -{ - char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_cap; - int err; - - /* In Spectrum-2, the speed of 1x can change from port to port, so query - * it from firmware. - */ - mlxsw_reg_ptys_ext_eth_pack(ptys_pl, local_port, 0, false); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); - if (err) - return err; - mlxsw_reg_ptys_ext_eth_unpack(ptys_pl, ð_proto_cap, NULL, NULL); - - if (eth_proto_cap & - MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR) { - *base_speed = MLXSW_SP_PORT_BASE_SPEED_50G; - return 0; - } - - if (eth_proto_cap & - MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR) { - *base_speed = MLXSW_SP_PORT_BASE_SPEED_25G; - return 0; - } - - return -EIO; -} - static void mlxsw_sp2_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, @@ -3305,8 +3247,6 @@ mlxsw_sp2_port_type_speed_ops = { .from_ptys_speed_duplex = mlxsw_sp2_from_ptys_speed_duplex, .to_ptys_advert_link = mlxsw_sp2_to_ptys_advert_link, .to_ptys_speed = mlxsw_sp2_to_ptys_speed, - .to_ptys_upper_speed = mlxsw_sp2_to_ptys_upper_speed, - .port_speed_base = mlxsw_sp2_port_speed_base, .reg_ptys_eth_pack = mlxsw_sp2_reg_ptys_eth_pack, .reg_ptys_eth_unpack = mlxsw_sp2_reg_ptys_eth_unpack, }; @@ -3520,24 +3460,24 @@ static int mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u32 eth_proto_cap, eth_proto_admin, eth_proto_oper; const struct mlxsw_sp_port_type_speed_ops *ops; char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_admin; - u32 upper_speed; - u32 base_speed; int err; ops = mlxsw_sp->port_type_speed_ops; - err = ops->port_speed_base(mlxsw_sp, mlxsw_sp_port->local_port, - &base_speed); + /* Set advertised speeds to supported speeds. */ + ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port, + 0, false); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); if (err) return err; - upper_speed = base_speed * mlxsw_sp_port->mapping.width; - eth_proto_admin = ops->to_ptys_upper_speed(mlxsw_sp, upper_speed); + ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap, + ð_proto_admin, ð_proto_oper); ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port, - eth_proto_admin, mlxsw_sp_port->link.autoneg); + eth_proto_cap, mlxsw_sp_port->link.autoneg); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl); } @@ -4935,16 +4875,35 @@ static const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = { }; #define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38 +#define MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR 50 + +static u32 __mlxsw_sp_span_buffsize_get(int mtu, u32 speed, u32 buffer_factor) +{ + return 3 * mtu + buffer_factor * speed / 1000; +} static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed) { - return 3 * mtu + MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR * speed / 1000; + int factor = MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); } static const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = { .buffsize_get = mlxsw_sp2_span_buffsize_get, }; +static u32 mlxsw_sp3_span_buffsize_get(int mtu, u32 speed) +{ + int factor = MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR; + + return __mlxsw_sp_span_buffsize_get(mtu, speed, factor); +} + +static const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops = { + .buffsize_get = mlxsw_sp3_span_buffsize_get, +}; + u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed) { u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu); @@ -5223,7 +5182,7 @@ static int mlxsw_sp3_init(struct mlxsw_core *mlxsw_core, mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals; mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops; mlxsw_sp->ptp_ops = &mlxsw_sp2_ptp_ops; - mlxsw_sp->span_ops = &mlxsw_sp2_span_ops; + mlxsw_sp->span_ops = &mlxsw_sp3_span_ops; mlxsw_sp->lowest_shaper_bs = MLXSW_REG_QEEC_LOWEST_SHAPER_BS_SP3; return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info, extack); @@ -6316,7 +6275,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, return -EINVAL; } if (netif_is_macvlan(upper_dev) && - !mlxsw_sp_rif_find_by_dev(mlxsw_sp, lower_dev)) { + !mlxsw_sp_rif_exists(mlxsw_sp, lower_dev)) { NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces"); return -EOPNOTSUPP; } @@ -6472,7 +6431,7 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, return -EINVAL; } if (netif_is_macvlan(upper_dev) && - !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) { + !mlxsw_sp_rif_exists(mlxsw_sp, vlan_dev)) { NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces"); return -EOPNOTSUPP; } @@ -6549,7 +6508,7 @@ static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev, if (!info->linking) break; if (netif_is_macvlan(upper_dev) && - !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) { + !mlxsw_sp_rif_exists(mlxsw_sp, vlan_dev)) { NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces"); return -EOPNOTSUPP; } @@ -6609,7 +6568,7 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev, if (!info->linking) break; if (netif_is_macvlan(upper_dev) && - !mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev)) { + !mlxsw_sp_rif_exists(mlxsw_sp, br_dev)) { NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a0f1f9dceec5..9708156e7871 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -19,6 +19,7 @@ #include <net/pkt_cls.h> #include <net/red.h> #include <net/vxlan.h> +#include <net/flow_offload.h> #include "port.h" #include "core.h" @@ -32,9 +33,6 @@ #define MLXSW_SP_MID_MAX 7000 -#define MLXSW_SP_PORT_BASE_SPEED_25G 25000 /* Mb/s */ -#define MLXSW_SP_PORT_BASE_SPEED_50G 50000 /* Mb/s */ - #define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */ #define MLXSW_SP_KVD_GRANULARITY 128 @@ -168,12 +166,8 @@ struct mlxsw_sp { struct notifier_block netdevice_nb; struct mlxsw_sp_ptp_clock *clock; struct mlxsw_sp_ptp_state *ptp_state; - struct mlxsw_sp_counter_pool *counter_pool; - struct { - struct mlxsw_sp_span_entry *entries; - int entries_count; - } span; + struct mlxsw_sp_span *span; const struct mlxsw_fw_rev *req_rev; const char *fw_filename; const struct mlxsw_sp_kvdl_ops *kvdl_ops; @@ -313,9 +307,6 @@ struct mlxsw_sp_port_type_speed_ops { u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp, u8 width, const struct ethtool_link_ksettings *cmd); u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u8 width, u32 speed); - u32 (*to_ptys_upper_speed)(struct mlxsw_sp *mlxsw_sp, u32 upper_speed); - int (*port_speed_base)(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u32 *base_speed); void (*reg_ptys_eth_pack)(struct mlxsw_sp *mlxsw_sp, char *payload, u8 local_port, u32 proto_admin, bool autoneg); void (*reg_ptys_eth_unpack)(struct mlxsw_sp *mlxsw_sp, char *payload, @@ -468,10 +459,6 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack); void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp, const struct net_device *vxlan_dev); -struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, - const struct net_device *br_dev, - u16 vid, - struct netlink_ext_ack *extack); extern struct notifier_block mlxsw_sp_switchdev_notifier; /* spectrum.c */ @@ -556,7 +543,7 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, struct netdev_notifier_changeupper_info *info); bool mlxsw_sp_netdev_is_ipip_ol(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); -bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp, +bool mlxsw_sp_netdev_is_ipip_ul(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp, struct net_device *l3_dev, @@ -571,10 +558,10 @@ void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, struct net_device *dev); -struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, - const struct net_device *dev); +bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); +u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp); -struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif); int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, enum mlxsw_sp_l3proto ul_proto, const union mlxsw_sp_l3addr *ul_sip, @@ -653,6 +640,7 @@ struct mlxsw_sp_acl_rule_info { struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; u8 action_created:1, + ingress_bind_blocker:1, egress_bind_blocker:1; unsigned int counter_index; }; @@ -672,16 +660,20 @@ struct mlxsw_sp_acl_block { struct mlxsw_sp *mlxsw_sp; unsigned int rule_count; unsigned int disable_count; + unsigned int ingress_blocker_rule_count; unsigned int egress_blocker_rule_count; + unsigned int ingress_binding_count; + unsigned int egress_binding_count; struct net *net; }; struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl); struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block); -unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block); +unsigned int +mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block); void mlxsw_sp_acl_block_disable_inc(struct mlxsw_sp_acl_block *block); void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block); -bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block); struct mlxsw_sp_acl_block *mlxsw_sp_acl_block_create(struct mlxsw_sp *mlxsw_sp, struct net *net); void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block); @@ -694,7 +686,9 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, bool ingress); -bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block); +bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block); struct mlxsw_sp_acl_ruleset * mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, u32 chain_index, @@ -726,7 +720,10 @@ int mlxsw_sp_acl_rulei_act_continue(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_jump(struct mlxsw_sp_acl_rule_info *rulei, u16 group_id); int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei); -int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei); +int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack); int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei); int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, @@ -777,6 +774,12 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp); +static inline const struct flow_action_cookie * +mlxsw_sp_acl_act_cookie_lookup(struct mlxsw_sp *mlxsw_sp, u32 cookie_index) +{ + return mlxsw_afa_cookie_lookup(mlxsw_sp->afa, cookie_index); +} + int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); @@ -974,9 +977,6 @@ void mlxsw_sp_nve_flood_ip_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, enum mlxsw_sp_l3proto proto, union mlxsw_sp_l3addr *addr); -u32 mlxsw_sp_nve_decap_tunnel_index_get(const struct mlxsw_sp *mlxsw_sp); -bool mlxsw_sp_nve_ipv4_route_is_decap(const struct mlxsw_sp *mlxsw_sp, - u32 tb_id, __be32 addr); int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c index 09ee0a807747..a9fff8adc75e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c @@ -60,7 +60,7 @@ static const struct mlxsw_sp1_kvdl_part_info mlxsw_sp1_kvdl_parts_info[] = { struct mlxsw_sp1_kvdl_part { struct mlxsw_sp1_kvdl_part_info info; - unsigned long usage[0]; /* Entries */ + unsigned long usage[]; /* Entries */ }; struct mlxsw_sp1_kvdl { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c index 8d14770766b4..3a73d654017f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c @@ -45,7 +45,7 @@ struct mlxsw_sp2_kvdl_part { unsigned int usage_bit_count; unsigned int indexes_per_usage_bit; unsigned int last_allocated_bit; - unsigned long usage[0]; /* Usage bits */ + unsigned long usage[]; /* Usage bits */ }; struct mlxsw_sp2_kvdl { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 3d3cca596116..36b264798f04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -58,7 +58,7 @@ struct mlxsw_sp_acl_ruleset { struct mlxsw_sp_acl_ruleset_ht_key ht_key; struct rhashtable rule_ht; unsigned int ref_count; - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; @@ -71,7 +71,7 @@ struct mlxsw_sp_acl_rule { u64 last_used; u64 last_packets; u64 last_bytes; - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; @@ -99,7 +99,8 @@ struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block) return block->mlxsw_sp; } -unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block) +unsigned int +mlxsw_sp_acl_block_rule_count(const struct mlxsw_sp_acl_block *block) { return block ? block->rule_count : 0; } @@ -116,20 +117,24 @@ void mlxsw_sp_acl_block_disable_dec(struct mlxsw_sp_acl_block *block) block->disable_count--; } -bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block) +bool mlxsw_sp_acl_block_disabled(const struct mlxsw_sp_acl_block *block) { return block->disable_count; } -bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block) +bool mlxsw_sp_acl_block_is_egress_bound(const struct mlxsw_sp_acl_block *block) { - struct mlxsw_sp_acl_block_binding *binding; + return block->egress_binding_count; +} - list_for_each_entry(binding, &block->binding_list, list) { - if (!binding->ingress) - return true; - } - return false; +bool mlxsw_sp_acl_block_is_ingress_bound(const struct mlxsw_sp_acl_block *block) +{ + return block->ingress_binding_count; +} + +bool mlxsw_sp_acl_block_is_mixed_bound(const struct mlxsw_sp_acl_block *block) +{ + return block->ingress_binding_count && block->egress_binding_count; } static bool @@ -163,7 +168,8 @@ mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp, binding->mlxsw_sp_port, binding->ingress); } -static bool mlxsw_sp_acl_ruleset_block_bound(struct mlxsw_sp_acl_block *block) +static bool +mlxsw_sp_acl_ruleset_block_bound(const struct mlxsw_sp_acl_block *block) { return block->ruleset_zero; } @@ -250,6 +256,11 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress))) return -EEXIST; + if (ingress && block->ingress_blocker_rule_count) { + NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to ingress because it contains unsupported rules"); + return -EOPNOTSUPP; + } + if (!ingress && block->egress_blocker_rule_count) { NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules"); return -EOPNOTSUPP; @@ -267,6 +278,10 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, goto err_ruleset_bind; } + if (ingress) + block->ingress_binding_count++; + else + block->egress_binding_count++; list_add(&binding->list, &block->binding_list); return 0; @@ -288,6 +303,11 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, list_del(&binding->list); + if (ingress) + block->ingress_binding_count--; + else + block->egress_binding_count--; + if (mlxsw_sp_acl_ruleset_block_bound(block)) mlxsw_sp_acl_ruleset_unbind(mlxsw_sp, block, binding); @@ -515,9 +535,13 @@ int mlxsw_sp_acl_rulei_act_terminate(struct mlxsw_sp_acl_rule_info *rulei) return mlxsw_afa_block_terminate(rulei->act_block); } -int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei) +int mlxsw_sp_acl_rulei_act_drop(struct mlxsw_sp_acl_rule_info *rulei, + bool ingress, + const struct flow_action_cookie *fa_cookie, + struct netlink_ext_ack *extack) { - return mlxsw_afa_block_append_drop(rulei->act_block); + return mlxsw_afa_block_append_drop(rulei->act_block, ingress, + fa_cookie, extack); } int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei) @@ -707,6 +731,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, list_add_tail(&rule->list, &mlxsw_sp->acl->rules); mutex_unlock(&mlxsw_sp->acl->rules_lock); block->rule_count++; + block->ingress_blocker_rule_count += rule->rulei->ingress_bind_blocker; block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; @@ -726,6 +751,7 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; + block->ingress_blocker_rule_count -= rule->rulei->ingress_bind_blocker; ruleset->ht_key.block->rule_count--; mutex_lock(&mlxsw_sp->acl->rules_lock); list_del(&rule->list); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c index 3a2de13fcb68..dbd3bebf11ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c @@ -13,7 +13,7 @@ struct mlxsw_sp_acl_bf { struct mutex lock; /* Protects Bloom Filter updates. */ unsigned int bank_size; - refcount_t refcnt[0]; + refcount_t refcnt[]; }; /* Bloom filter uses a crc-16 hash over chunks of data which contain 4 key diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index e993159e8e4c..430da69003d8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -224,7 +224,7 @@ struct mlxsw_sp_acl_tcam_vchunk; struct mlxsw_sp_acl_tcam_chunk { struct mlxsw_sp_acl_tcam_vchunk *vchunk; struct mlxsw_sp_acl_tcam_region *region; - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; @@ -243,7 +243,7 @@ struct mlxsw_sp_acl_tcam_vchunk { struct mlxsw_sp_acl_tcam_entry { struct mlxsw_sp_acl_tcam_ventry *ventry; struct mlxsw_sp_acl_tcam_chunk *chunk; - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 5965913565a5..96437992b102 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -20,7 +20,7 @@ struct mlxsw_sp_acl_tcam { struct mutex lock; /* guards vregion list */ struct list_head vregion_list; u32 vregion_rehash_intrvl; /* ms */ - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; @@ -86,7 +86,7 @@ struct mlxsw_sp_acl_tcam_region { char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN]; struct mlxsw_afk_key_info *key_info; struct mlxsw_sp *mlxsw_sp; - unsigned long priv[0]; + unsigned long priv[]; /* priv has to be always the last item */ }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c index 83c2e1e5f216..6a02ef9ec00e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <linux/bitops.h> +#include <linux/spinlock.h> #include "spectrum_cnt.h" @@ -18,6 +19,7 @@ struct mlxsw_sp_counter_sub_pool { struct mlxsw_sp_counter_pool { unsigned int pool_size; unsigned long *usage; /* Usage bitmap */ + spinlock_t counter_pool_lock; /* Protects counter pool allocations */ struct mlxsw_sp_counter_sub_pool *sub_pools; }; @@ -87,6 +89,7 @@ int mlxsw_sp_counter_pool_init(struct mlxsw_sp *mlxsw_sp) pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return -ENOMEM; + spin_lock_init(&pool->counter_pool_lock); pool->pool_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, COUNTER_POOL_SIZE); map_size = BITS_TO_LONGS(pool->pool_size) * sizeof(unsigned long); @@ -139,25 +142,35 @@ int mlxsw_sp_counter_alloc(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_counter_sub_pool *sub_pool; unsigned int entry_index; unsigned int stop_index; - int i; + int i, err; sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; stop_index = sub_pool->base_index + sub_pool->size; entry_index = sub_pool->base_index; + spin_lock(&pool->counter_pool_lock); entry_index = find_next_zero_bit(pool->usage, stop_index, entry_index); - if (entry_index == stop_index) - return -ENOBUFS; + if (entry_index == stop_index) { + err = -ENOBUFS; + goto err_alloc; + } /* The sub-pools can contain non-integer number of entries * so we must check for overflow */ - if (entry_index + sub_pool->entry_size > stop_index) - return -ENOBUFS; + if (entry_index + sub_pool->entry_size > stop_index) { + err = -ENOBUFS; + goto err_alloc; + } for (i = 0; i < sub_pool->entry_size; i++) __set_bit(entry_index + i, pool->usage); + spin_unlock(&pool->counter_pool_lock); *p_counter_index = entry_index; return 0; + +err_alloc: + spin_unlock(&pool->counter_pool_lock); + return err; } void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, @@ -171,6 +184,8 @@ void mlxsw_sp_counter_free(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(counter_index >= pool->pool_size)) return; sub_pool = &mlxsw_sp_counter_sub_pools[sub_pool_id]; + spin_lock(&pool->counter_pool_lock); for (i = 0; i < sub_pool->entry_size; i++) __clear_bit(counter_index + i, pool->usage); + spin_unlock(&pool->counter_pool_lock); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index 2dc0978428e6..daf029931b5f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */ #include <linux/kernel.h> +#include <linux/mutex.h> #include <net/devlink.h> #include "spectrum.h" @@ -210,7 +211,7 @@ mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled, return err; rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); i = 0; start_again: err = devlink_dpipe_entry_ctx_prepare(dump_ctx); @@ -241,14 +242,14 @@ start_again: devlink_dpipe_entry_ctx_close(dump_ctx); if (i != rif_count) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); devlink_dpipe_entry_clear(&entry); return 0; err_entry_append: err_entry_get: err_ctx_prepare: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); devlink_dpipe_entry_clear(&entry); return err; } @@ -258,7 +259,7 @@ static int mlxsw_sp_dpipe_table_erif_counters_update(void *priv, bool enable) struct mlxsw_sp *mlxsw_sp = priv; int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); @@ -271,7 +272,7 @@ static int mlxsw_sp_dpipe_table_erif_counters_update(void *priv, bool enable) mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS); } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; } @@ -546,7 +547,7 @@ mlxsw_sp_dpipe_table_host_entries_get(struct mlxsw_sp *mlxsw_sp, int i, j; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); i = 0; rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); start_again: @@ -602,12 +603,12 @@ out: if (i != rif_count) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; err_ctx_prepare: err_entry_append: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -662,7 +663,7 @@ mlxsw_sp_dpipe_table_host_counters_update(struct mlxsw_sp *mlxsw_sp, { int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); struct mlxsw_sp_neigh_entry *neigh_entry; @@ -684,7 +685,7 @@ mlxsw_sp_dpipe_table_host_counters_update(struct mlxsw_sp *mlxsw_sp, enable); } } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); } static int mlxsw_sp_dpipe_table_host4_counters_update(void *priv, bool enable) @@ -701,7 +702,7 @@ mlxsw_sp_dpipe_table_host_size_get(struct mlxsw_sp *mlxsw_sp, int type) u64 size = 0; int i; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); struct mlxsw_sp_neigh_entry *neigh_entry; @@ -721,7 +722,7 @@ mlxsw_sp_dpipe_table_host_size_get(struct mlxsw_sp *mlxsw_sp, int type) size++; } } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return size; } @@ -1093,7 +1094,7 @@ mlxsw_sp_dpipe_table_adj_entries_get(struct mlxsw_sp *mlxsw_sp, int j; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); nh_count_max = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); start_again: err = devlink_dpipe_entry_ctx_prepare(dump_ctx); @@ -1130,13 +1131,13 @@ skip: devlink_dpipe_entry_ctx_close(dump_ctx); if (nh_count != nh_count_max) goto start_again; - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return 0; err_ctx_prepare: err_entry_append: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -1206,9 +1207,9 @@ mlxsw_sp_dpipe_table_adj_size_get(void *priv) struct mlxsw_sp *mlxsw_sp = priv; u64 size; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); size = mlxsw_sp_dpipe_table_adj_size(mlxsw_sp); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return size; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index 8df3cb21baa6..65486a90b526 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -8,6 +8,7 @@ #include <linux/netdevice.h> #include <linux/rhashtable.h> #include <linux/rtnetlink.h> +#include <linux/refcount.h> #include "spectrum.h" #include "reg.h" @@ -24,7 +25,7 @@ struct mlxsw_sp_fid_core { struct mlxsw_sp_fid { struct list_head list; struct mlxsw_sp_rif *rif; - unsigned int ref_count; + refcount_t ref_count; u16 fid_index; struct mlxsw_sp_fid_family *fid_family; struct rhash_head ht_node; @@ -149,7 +150,7 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp, fid = rhashtable_lookup_fast(&mlxsw_sp->fid_core->fid_ht, &fid_index, mlxsw_sp_fid_ht_params); if (fid) - fid->ref_count++; + refcount_inc(&fid->ref_count); return fid; } @@ -183,7 +184,7 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp, fid = rhashtable_lookup_fast(&mlxsw_sp->fid_core->vni_ht, &vni, mlxsw_sp_fid_vni_ht_params); if (fid) - fid->ref_count++; + refcount_inc(&fid->ref_count); return fid; } @@ -1030,7 +1031,7 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_lookup(struct mlxsw_sp *mlxsw_sp, list_for_each_entry(fid, &fid_family->fids_list, list) { if (!fid->fid_family->ops->compare(fid, arg)) continue; - fid->ref_count++; + refcount_inc(&fid->ref_count); return fid; } @@ -1075,7 +1076,7 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_get(struct mlxsw_sp *mlxsw_sp, goto err_rhashtable_insert; list_add(&fid->list, &fid_family->fids_list); - fid->ref_count++; + refcount_set(&fid->ref_count, 1); return fid; err_rhashtable_insert: @@ -1093,7 +1094,7 @@ void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid) struct mlxsw_sp_fid_family *fid_family = fid->fid_family; struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp; - if (--fid->ref_count != 0) + if (!refcount_dec_and_test(&fid->ref_count)) return; list_del(&fid->list); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index b607919c8ad0..0011a71114e3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -41,12 +41,30 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, return err; } break; - case FLOW_ACTION_DROP: - err = mlxsw_sp_acl_rulei_act_drop(rulei); + case FLOW_ACTION_DROP: { + bool ingress; + + if (mlxsw_sp_acl_block_is_mixed_bound(block)) { + NL_SET_ERR_MSG_MOD(extack, "Drop action is not supported when block is bound to ingress and egress"); + return -EOPNOTSUPP; + } + ingress = mlxsw_sp_acl_block_is_ingress_bound(block); + err = mlxsw_sp_acl_rulei_act_drop(rulei, ingress, + act->cookie, extack); if (err) { NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action"); return err; } + + /* Forbid block with this rulei to be bound + * to ingress/egress in future. Ingress rule is + * a blocker for egress and vice versa. + */ + if (ingress) + rulei->egress_bind_blocker = 1; + else + rulei->ingress_bind_blocker = 1; + } break; case FLOW_ACTION_TRAP: err = mlxsw_sp_acl_rulei_act_trap(rulei); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c index 1e4cdee7bcd7..20d72f1c0cee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c @@ -2,13 +2,15 @@ /* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */ #include <linux/kernel.h> +#include <linux/mutex.h> #include <linux/slab.h> #include "spectrum.h" struct mlxsw_sp_kvdl { const struct mlxsw_sp_kvdl_ops *kvdl_ops; - unsigned long priv[0]; + struct mutex kvdl_lock; /* Protects kvdl allocations */ + unsigned long priv[]; /* priv has to be always the last item */ }; @@ -22,6 +24,7 @@ int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp) GFP_KERNEL); if (!kvdl) return -ENOMEM; + mutex_init(&kvdl->kvdl_lock); kvdl->kvdl_ops = kvdl_ops; mlxsw_sp->kvdl = kvdl; @@ -31,6 +34,7 @@ int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp) return 0; err_init: + mutex_destroy(&kvdl->kvdl_lock); kfree(kvdl); return err; } @@ -40,6 +44,7 @@ void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl; kvdl->kvdl_ops->fini(mlxsw_sp, kvdl->priv); + mutex_destroy(&kvdl->kvdl_lock); kfree(kvdl); } @@ -48,9 +53,14 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count, u32 *p_entry_index) { struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl; + int err; + + mutex_lock(&kvdl->kvdl_lock); + err = kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv, type, + entry_count, p_entry_index); + mutex_unlock(&kvdl->kvdl_lock); - return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv, type, - entry_count, p_entry_index); + return err; } void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, @@ -59,8 +69,10 @@ void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl; + mutex_lock(&kvdl->kvdl_lock); kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type, entry_count, entry_index); + mutex_unlock(&kvdl->kvdl_lock); } int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 54275624718b..085d9676e34b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */ +#include <linux/mutex.h> #include <linux/rhashtable.h> #include <net/ipv6.h> @@ -12,6 +13,7 @@ struct mlxsw_sp_mr { void *catchall_route_priv; struct delayed_work stats_update_dw; struct list_head table_list; + struct mutex table_list_lock; /* Protects table_list */ #define MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL 5000 /* ms */ unsigned long priv[0]; /* priv has to be always the last item */ @@ -66,9 +68,10 @@ struct mlxsw_sp_mr_table { u32 vr_id; struct mlxsw_sp_mr_vif vifs[MAXVIFS]; struct list_head route_list; + struct mutex route_list_lock; /* Protects route_list */ struct rhashtable route_ht; const struct mlxsw_sp_mr_table_ops *ops; - char catchall_route_priv[0]; + char catchall_route_priv[]; /* catchall_route_priv has to be always the last item */ }; @@ -370,11 +373,13 @@ static void mlxsw_sp_mr_mfc_offload_update(struct mlxsw_sp_mr_route *mr_route) static void __mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table, struct mlxsw_sp_mr_route *mr_route) { + WARN_ON_ONCE(!mutex_is_locked(&mr_table->route_list_lock)); + mlxsw_sp_mr_mfc_offload_set(mr_route, false); - mlxsw_sp_mr_route_erase(mr_table, mr_route); rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, mlxsw_sp_mr_route_ht_params); list_del(&mr_route->node); + mlxsw_sp_mr_route_erase(mr_table, mr_route); mlxsw_sp_mr_route_destroy(mr_table, mr_route); } @@ -415,19 +420,21 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, goto err_duplicate_route; } + /* Write the route to the hardware */ + err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace); + if (err) + goto err_mr_route_write; + /* Put it in the table data-structures */ + mutex_lock(&mr_table->route_list_lock); list_add_tail(&mr_route->node, &mr_table->route_list); + mutex_unlock(&mr_table->route_list_lock); err = rhashtable_insert_fast(&mr_table->route_ht, &mr_route->ht_node, mlxsw_sp_mr_route_ht_params); if (err) goto err_rhashtable_insert; - /* Write the route to the hardware */ - err = mlxsw_sp_mr_route_write(mr_table, mr_route, replace); - if (err) - goto err_mr_route_write; - /* Destroy the original route */ if (replace) { rhashtable_remove_fast(&mr_table->route_ht, @@ -440,11 +447,12 @@ int mlxsw_sp_mr_route_add(struct mlxsw_sp_mr_table *mr_table, mlxsw_sp_mr_mfc_offload_update(mr_route); return 0; -err_mr_route_write: - rhashtable_remove_fast(&mr_table->route_ht, &mr_route->ht_node, - mlxsw_sp_mr_route_ht_params); err_rhashtable_insert: + mutex_lock(&mr_table->route_list_lock); list_del(&mr_route->node); + mutex_unlock(&mr_table->route_list_lock); + mlxsw_sp_mr_route_erase(mr_table, mr_route); +err_mr_route_write: err_no_orig_route: err_duplicate_route: mlxsw_sp_mr_route_destroy(mr_table, mr_route); @@ -460,8 +468,11 @@ void mlxsw_sp_mr_route_del(struct mlxsw_sp_mr_table *mr_table, mr_table->ops->key_create(mr_table, &key, mfc); mr_route = rhashtable_lookup_fast(&mr_table->route_ht, &key, mlxsw_sp_mr_route_ht_params); - if (mr_route) + if (mr_route) { + mutex_lock(&mr_table->route_list_lock); __mlxsw_sp_mr_route_del(mr_table, mr_route); + mutex_unlock(&mr_table->route_list_lock); + } } /* Should be called after the VIF struct is updated */ @@ -910,6 +921,7 @@ struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, mr_table->proto = proto; mr_table->ops = &mlxsw_sp_mr_table_ops_arr[proto]; INIT_LIST_HEAD(&mr_table->route_list); + mutex_init(&mr_table->route_list_lock); err = rhashtable_init(&mr_table->route_ht, &mlxsw_sp_mr_route_ht_params); @@ -927,12 +939,15 @@ struct mlxsw_sp_mr_table *mlxsw_sp_mr_table_create(struct mlxsw_sp *mlxsw_sp, &catchall_route_params); if (err) goto err_ops_route_create; + mutex_lock(&mr->table_list_lock); list_add_tail(&mr_table->node, &mr->table_list); + mutex_unlock(&mr->table_list_lock); return mr_table; err_ops_route_create: rhashtable_destroy(&mr_table->route_ht); err_route_rhashtable_init: + mutex_destroy(&mr_table->route_list_lock); kfree(mr_table); return ERR_PTR(err); } @@ -943,10 +958,13 @@ void mlxsw_sp_mr_table_destroy(struct mlxsw_sp_mr_table *mr_table) struct mlxsw_sp_mr *mr = mlxsw_sp->mr; WARN_ON(!mlxsw_sp_mr_table_empty(mr_table)); + mutex_lock(&mr->table_list_lock); list_del(&mr_table->node); + mutex_unlock(&mr->table_list_lock); mr->mr_ops->route_destroy(mlxsw_sp, mr->priv, &mr_table->catchall_route_priv); rhashtable_destroy(&mr_table->route_ht); + mutex_destroy(&mr_table->route_list_lock); kfree(mr_table); } @@ -955,8 +973,10 @@ void mlxsw_sp_mr_table_flush(struct mlxsw_sp_mr_table *mr_table) struct mlxsw_sp_mr_route *mr_route, *tmp; int i; + mutex_lock(&mr_table->route_list_lock); list_for_each_entry_safe(mr_route, tmp, &mr_table->route_list, node) __mlxsw_sp_mr_route_del(mr_table, mr_route); + mutex_unlock(&mr_table->route_list_lock); for (i = 0; i < MAXVIFS; i++) { mr_table->vifs[i].dev = NULL; @@ -1000,12 +1020,15 @@ static void mlxsw_sp_mr_stats_update(struct work_struct *work) struct mlxsw_sp_mr_route *mr_route; unsigned long interval; - rtnl_lock(); - list_for_each_entry(mr_table, &mr->table_list, node) + mutex_lock(&mr->table_list_lock); + list_for_each_entry(mr_table, &mr->table_list, node) { + mutex_lock(&mr_table->route_list_lock); list_for_each_entry(mr_route, &mr_table->route_list, node) mlxsw_sp_mr_route_stats_update(mr_table->mlxsw_sp, mr_route); - rtnl_unlock(); + mutex_unlock(&mr_table->route_list_lock); + } + mutex_unlock(&mr->table_list_lock); interval = msecs_to_jiffies(MLXSW_SP_MR_ROUTES_COUNTER_UPDATE_INTERVAL); mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); @@ -1024,6 +1047,7 @@ int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, mr->mr_ops = mr_ops; mlxsw_sp->mr = mr; INIT_LIST_HEAD(&mr->table_list); + mutex_init(&mr->table_list_lock); err = mr_ops->init(mlxsw_sp, mr->priv); if (err) @@ -1035,6 +1059,7 @@ int mlxsw_sp_mr_init(struct mlxsw_sp *mlxsw_sp, mlxsw_core_schedule_dw(&mr->stats_update_dw, interval); return 0; err: + mutex_destroy(&mr->table_list_lock); kfree(mr); return err; } @@ -1045,5 +1070,6 @@ void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp) cancel_delayed_work_sync(&mr->stats_update_dw); mr->mr_ops->fini(mlxsw_sp, mr->priv); + mutex_destroy(&mr->table_list_lock); kfree(mr); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 2153bcc4b585..54d3e7dcd303 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -67,7 +67,7 @@ struct mlxsw_sp_nve_mc_record { struct mlxsw_sp_nve_mc_list *mc_list; const struct mlxsw_sp_nve_mc_record_ops *ops; u32 kvdl_index; - struct mlxsw_sp_nve_mc_entry entries[0]; + struct mlxsw_sp_nve_mc_entry entries[]; }; struct mlxsw_sp_nve_mc_list { @@ -713,27 +713,6 @@ static void mlxsw_sp_nve_flood_ip_flush(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nve_mc_list_put(mlxsw_sp, mc_list); } -u32 mlxsw_sp_nve_decap_tunnel_index_get(const struct mlxsw_sp *mlxsw_sp) -{ - WARN_ON(mlxsw_sp->nve->num_nve_tunnels == 0); - - return mlxsw_sp->nve->tunnel_index; -} - -bool mlxsw_sp_nve_ipv4_route_is_decap(const struct mlxsw_sp *mlxsw_sp, - u32 tb_id, __be32 addr) -{ - struct mlxsw_sp_nve *nve = mlxsw_sp->nve; - struct mlxsw_sp_nve_config *config = &nve->config; - - if (nve->num_nve_tunnels && - config->ul_proto == MLXSW_SP_L3_PROTO_IPV4 && - config->ul_sip.addr4 == addr && config->ul_tb_id == tb_id) - return true; - - return false; -} - static int mlxsw_sp_nve_tunnel_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nve_config *config) { @@ -744,6 +723,8 @@ static int mlxsw_sp_nve_tunnel_init(struct mlxsw_sp *mlxsw_sp, if (nve->num_nve_tunnels++ != 0) return 0; + nve->config = *config; + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, &nve->tunnel_index); if (err) @@ -760,6 +741,7 @@ err_ops_init: mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, nve->tunnel_index); err_kvdl_alloc: + memset(&nve->config, 0, sizeof(nve->config)); nve->num_nve_tunnels--; return err; } @@ -840,8 +822,6 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, goto err_fid_vni_set; } - nve->config = config; - err = ops->fdb_replay(params->dev, params->vni, extack); if (err) goto err_fdb_replay; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c index 02526c53d4f5..13a054c0ce0f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c @@ -347,7 +347,6 @@ mlxsw_sp_setup_tc_qdisc_red_clean_stats(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_qdisc->prio_bitmap, &stats_base->tx_packets, &stats_base->tx_bytes); - red_base->prob_mark = xstats->ecn; red_base->prob_drop = xstats->wred_drop[tclass_num]; red_base->pdrop = mlxsw_sp_xstats_tail_drop(xstats, tclass_num); @@ -453,22 +452,19 @@ mlxsw_sp_qdisc_get_red_xstats(struct mlxsw_sp_port *mlxsw_sp_port, u8 tclass_num = mlxsw_sp_qdisc->tclass_num; struct mlxsw_sp_port_xstats *xstats; struct red_stats *res = xstats_ptr; - int early_drops, marks, pdrops; + int early_drops, pdrops; xstats = &mlxsw_sp_port->periodic_hw_stats.xstats; early_drops = xstats->wred_drop[tclass_num] - xstats_base->prob_drop; - marks = xstats->ecn - xstats_base->prob_mark; pdrops = mlxsw_sp_xstats_tail_drop(xstats, tclass_num) - xstats_base->pdrop; res->pdrop += pdrops; res->prob_drop += early_drops; - res->prob_mark += marks; xstats_base->pdrop += pdrops; xstats_base->prob_drop += early_drops; - xstats_base->prob_mark += marks; return 0; } @@ -486,8 +482,7 @@ mlxsw_sp_qdisc_get_red_stats(struct mlxsw_sp_port *mlxsw_sp_port, stats_base = &mlxsw_sp_qdisc->stats_base; mlxsw_sp_qdisc_get_tc_stats(mlxsw_sp_port, mlxsw_sp_qdisc, stats_ptr); - overlimits = xstats->wred_drop[tclass_num] + xstats->ecn - - stats_base->overlimits; + overlimits = xstats->wred_drop[tclass_num] - stats_base->overlimits; stats_ptr->qstats->overlimits += overlimits; stats_base->overlimits += overlimits; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4a77b511ead2..b527387ccf80 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -17,6 +17,7 @@ #include <linux/refcount.h> #include <linux/jhash.h> #include <linux/net_namespace.h> +#include <linux/mutex.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> @@ -48,39 +49,6 @@ struct mlxsw_sp_vr; struct mlxsw_sp_lpm_tree; struct mlxsw_sp_rif_ops; -struct mlxsw_sp_router { - struct mlxsw_sp *mlxsw_sp; - struct mlxsw_sp_rif **rifs; - struct mlxsw_sp_vr *vrs; - struct rhashtable neigh_ht; - struct rhashtable nexthop_group_ht; - struct rhashtable nexthop_ht; - struct list_head nexthop_list; - struct { - /* One tree for each protocol: IPv4 and IPv6 */ - struct mlxsw_sp_lpm_tree *proto_trees[2]; - struct mlxsw_sp_lpm_tree *trees; - unsigned int tree_count; - } lpm; - struct { - struct delayed_work dw; - unsigned long interval; /* ms */ - } neighs_update; - struct delayed_work nexthop_probe_dw; -#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ - struct list_head nexthop_neighs_list; - struct list_head ipip_list; - bool aborted; - struct notifier_block fib_nb; - struct notifier_block netevent_nb; - struct notifier_block inetaddr_nb; - struct notifier_block inet6addr_nb; - const struct mlxsw_sp_rif_ops **rif_ops_arr; - const struct mlxsw_sp_ipip_ops **ipip_ops_arr; - u32 adj_discard_index; - bool adj_discard_index_valid; -}; - struct mlxsw_sp_rif { struct list_head nexthop_list; struct list_head neigh_list; @@ -145,6 +113,9 @@ struct mlxsw_sp_rif_ops { void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac); }; +static struct mlxsw_sp_rif * +mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev); static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif); static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree); static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, @@ -760,13 +731,18 @@ int mlxsw_sp_router_tb_id_vr_id(struct mlxsw_sp *mlxsw_sp, u32 tb_id, u16 *vr_id) { struct mlxsw_sp_vr *vr; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); vr = mlxsw_sp_vr_find(mlxsw_sp, tb_id); - if (!vr) - return -ESRCH; + if (!vr) { + err = -ESRCH; + goto out; + } *vr_id = vr->id; - - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, @@ -988,17 +964,23 @@ __mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) struct ip_tunnel *tun = netdev_priv(ol_dev); struct net *net = dev_net(ol_dev); - return __dev_get_by_index(net, tun->parms.link); + return dev_get_by_index_rcu(net, tun->parms.link); } u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) { - struct net_device *d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + struct net_device *d; + u32 tb_id; + rcu_read_lock(); + d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); if (d) - return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; + tb_id = l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else - return RT_TABLE_MAIN; + tb_id = RT_TABLE_MAIN; + rcu_read_unlock(); + + return tb_id; } static struct mlxsw_sp_rif * @@ -1355,8 +1337,12 @@ mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp, ipip_list_node); list_for_each_entry_continue(ipip_entry, &mlxsw_sp->router->ipip_list, ipip_list_node) { - struct net_device *ipip_ul_dev = - __mlxsw_sp_ipip_netdev_ul_dev_get(ipip_entry->ol_dev); + struct net_device *ol_dev = ipip_entry->ol_dev; + struct net_device *ipip_ul_dev; + + rcu_read_lock(); + ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + rcu_read_unlock(); if (ipip_ul_dev == ul_dev) return ipip_entry; @@ -1365,10 +1351,16 @@ mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp, return NULL; } -bool mlxsw_sp_netdev_is_ipip_ul(const struct mlxsw_sp *mlxsw_sp, +bool mlxsw_sp_netdev_is_ipip_ul(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { - return mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, dev, NULL); + bool is_ipip_ul; + + mutex_lock(&mlxsw_sp->router->lock); + is_ipip_ul = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, dev, NULL); + mutex_unlock(&mlxsw_sp->router->lock); + + return is_ipip_ul; } static bool mlxsw_sp_netdevice_ipip_can_offload(struct mlxsw_sp *mlxsw_sp, @@ -1722,9 +1714,12 @@ static void mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(struct mlxsw_sp *mlxsw_sp, list_for_each_entry_safe(ipip_entry, tmp, &mlxsw_sp->router->ipip_list, ipip_list_node) { - struct net_device *ipip_ul_dev = - __mlxsw_sp_ipip_netdev_ul_dev_get(ipip_entry->ol_dev); + struct net_device *ol_dev = ipip_entry->ol_dev; + struct net_device *ipip_ul_dev; + rcu_read_lock(); + ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + rcu_read_unlock(); if (ipip_ul_dev == ul_dev) mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); } @@ -1737,35 +1732,41 @@ int mlxsw_sp_netdevice_ipip_ol_event(struct mlxsw_sp *mlxsw_sp, { struct netdev_notifier_changeupper_info *chup; struct netlink_ext_ack *extack; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); switch (event) { case NETDEV_REGISTER: - return mlxsw_sp_netdevice_ipip_ol_reg_event(mlxsw_sp, ol_dev); + err = mlxsw_sp_netdevice_ipip_ol_reg_event(mlxsw_sp, ol_dev); + break; case NETDEV_UNREGISTER: mlxsw_sp_netdevice_ipip_ol_unreg_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_UP: mlxsw_sp_netdevice_ipip_ol_up_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_DOWN: mlxsw_sp_netdevice_ipip_ol_down_event(mlxsw_sp, ol_dev); - return 0; + break; case NETDEV_CHANGEUPPER: chup = container_of(info, typeof(*chup), info); extack = info->extack; if (netif_is_l3_master(chup->upper_dev)) - return mlxsw_sp_netdevice_ipip_ol_vrf_event(mlxsw_sp, - ol_dev, - extack); - return 0; + err = mlxsw_sp_netdevice_ipip_ol_vrf_event(mlxsw_sp, + ol_dev, + extack); + break; case NETDEV_CHANGE: extack = info->extack; - return mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp, - ol_dev, extack); + err = mlxsw_sp_netdevice_ipip_ol_change_event(mlxsw_sp, + ol_dev, extack); + break; case NETDEV_CHANGEMTU: - return mlxsw_sp_netdevice_ipip_ol_update_mtu(mlxsw_sp, ol_dev); + err = mlxsw_sp_netdevice_ipip_ol_update_mtu(mlxsw_sp, ol_dev); + break; } - return 0; + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static int @@ -1809,8 +1810,9 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, struct netdev_notifier_info *info) { struct mlxsw_sp_ipip_entry *ipip_entry = NULL; - int err; + int err = 0; + mutex_lock(&mlxsw_sp->router->lock); while ((ipip_entry = mlxsw_sp_ipip_entry_find_by_ul_dev(mlxsw_sp, ul_dev, ipip_entry))) { @@ -1823,7 +1825,7 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, if (err) { mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(mlxsw_sp, ul_dev); - return err; + break; } if (demote_this) { @@ -1840,8 +1842,9 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, ipip_entry = prev; } } + mutex_unlock(&mlxsw_sp->router->lock); - return 0; + return err; } int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, @@ -1850,8 +1853,22 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, u32 tunnel_index) { enum mlxsw_sp_fib_entry_type type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + struct mlxsw_sp_router *router = mlxsw_sp->router; struct mlxsw_sp_fib_entry *fib_entry; - int err; + int err = 0; + + mutex_lock(&mlxsw_sp->router->lock); + + if (WARN_ON_ONCE(router->nve_decap_config.valid)) { + err = -EINVAL; + goto out; + } + + router->nve_decap_config.ul_tb_id = ul_tb_id; + router->nve_decap_config.tunnel_index = tunnel_index; + router->nve_decap_config.ul_proto = ul_proto; + router->nve_decap_config.ul_sip = *ul_sip; + router->nve_decap_config.valid = true; /* It is valid to create a tunnel with a local IP and only later * assign this IP address to a local interface @@ -1860,7 +1877,7 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, ul_proto, ul_sip, type); if (!fib_entry) - return 0; + goto out; fib_entry->decap.tunnel_index = tunnel_index; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; @@ -1869,11 +1886,13 @@ int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, if (err) goto err_fib_entry_update; - return 0; + goto out; err_fib_entry_update: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); +out: + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -1882,16 +1901,40 @@ void mlxsw_sp_router_nve_demote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, const union mlxsw_sp_l3addr *ul_sip) { enum mlxsw_sp_fib_entry_type type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; + struct mlxsw_sp_router *router = mlxsw_sp->router; struct mlxsw_sp_fib_entry *fib_entry; + mutex_lock(&mlxsw_sp->router->lock); + + if (WARN_ON_ONCE(!router->nve_decap_config.valid)) + goto out; + + router->nve_decap_config.valid = false; + fib_entry = mlxsw_sp_router_ip2me_fib_entry_find(mlxsw_sp, ul_tb_id, ul_proto, ul_sip, type); if (!fib_entry) - return; + goto out; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); +out: + mutex_unlock(&mlxsw_sp->router->lock); +} + +static bool mlxsw_sp_router_nve_is_decap(struct mlxsw_sp *mlxsw_sp, + u32 ul_tb_id, + enum mlxsw_sp_l3proto ul_proto, + const union mlxsw_sp_l3addr *ul_sip) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + + return router->nve_decap_config.valid && + router->nve_decap_config.ul_tb_id == ul_tb_id && + router->nve_decap_config.ul_proto == ul_proto && + !memcmp(&router->nve_decap_config.ul_sip, ul_sip, + sizeof(*ul_sip)); } struct mlxsw_sp_neigh_key { @@ -2264,10 +2307,8 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, int i, num_rec; int err; - /* Make sure the neighbour's netdev isn't removed in the - * process. - */ - rtnl_lock(); + /* Ensure the RIF we read from the device does not change mid-dump. */ + mutex_lock(&mlxsw_sp->router->lock); do { mlxsw_reg_rauhtd_pack(rauhtd_pl, type); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd), @@ -2281,7 +2322,7 @@ __mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, i); } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -2312,15 +2353,14 @@ static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_neigh_entry *neigh_entry; - /* Take RTNL mutex here to prevent lists from changes */ - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); list_for_each_entry(neigh_entry, &mlxsw_sp->router->nexthop_neighs_list, nexthop_neighs_list_node) /* If this neigh have nexthops, make the kernel think this neigh * is active regardless of the traffic. */ neigh_event_send(neigh_entry->key.n, NULL); - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); } static void @@ -2360,15 +2400,13 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) * the nexthop wouldn't get offloaded until the neighbor is resolved * but it wouldn't get resolved ever in case traffic is flowing in HW * using different nexthop. - * - * Take RTNL mutex here to prevent lists from changes. */ - rtnl_lock(); + mutex_lock(&router->lock); list_for_each_entry(neigh_entry, &router->nexthop_neighs_list, nexthop_neighs_list_node) if (!neigh_entry->connected) neigh_event_send(neigh_entry->key.n, NULL); - rtnl_unlock(); + mutex_unlock(&router->lock); mlxsw_core_schedule_dw(&router->nexthop_probe_dw, MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL); @@ -2506,7 +2544,7 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) dead = n->dead; read_unlock_bh(&n->lock); - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); entry_connected = nud_state & NUD_VALID && !dead; @@ -2528,7 +2566,7 @@ static void mlxsw_sp_router_neigh_event_work(struct work_struct *work) mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); out: - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); neigh_release(n); kfree(net_work); } @@ -3711,9 +3749,15 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) { - struct net_device *ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + struct net_device *ul_dev; + bool is_up; + + rcu_read_lock(); + ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + is_up = ul_dev ? (ul_dev->flags & IFF_UP) : true; + rcu_read_unlock(); - return ul_dev ? (ul_dev->flags & IFF_UP) : true; + return is_up; } static void mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, @@ -3840,10 +3884,14 @@ static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, if (!dev) return 0; - in_dev = __in_dev_get_rtnl(dev); + rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && - fib_nh->fib_nh_flags & RTNH_F_LINKDOWN) + fib_nh->fib_nh_flags & RTNH_F_LINKDOWN) { + rcu_read_unlock(); return 0; + } + rcu_read_unlock(); err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); if (err) @@ -4473,6 +4521,7 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, { struct net_device *dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev; union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) }; + struct mlxsw_sp_router *router = mlxsw_sp->router; u32 tb_id = mlxsw_sp_fix_tb_id(fen_info->tb_id); struct mlxsw_sp_ipip_entry *ipip_entry; struct fib_info *fi = fen_info->fi; @@ -4487,12 +4536,13 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry, ipip_entry); } - if (mlxsw_sp_nve_ipv4_route_is_decap(mlxsw_sp, tb_id, - dip.addr4)) { - u32 t_index; + if (mlxsw_sp_router_nve_is_decap(mlxsw_sp, tb_id, + MLXSW_SP_L3_PROTO_IPV4, + &dip)) { + u32 tunnel_index; - t_index = mlxsw_sp_nve_decap_tunnel_index_get(mlxsw_sp); - fib_entry->decap.tunnel_index = t_index; + tunnel_index = router->nve_decap_config.tunnel_index; + fib_entry->decap.tunnel_index = tunnel_index; fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; return 0; } @@ -5923,8 +5973,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - /* Protect internal structures from changes */ - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); switch (fib_work->event) { @@ -5946,7 +5995,7 @@ static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) fib_info_put(fib_work->fnh_info.fib_nh->nh_parent); break; } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); kfree(fib_work); } @@ -5957,7 +6006,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; - rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); switch (fib_work->event) { @@ -5984,7 +6033,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) mlxsw_sp_router_fib6_work_fini(&fib_work->fib6_work); break; } - rtnl_unlock(); + mutex_unlock(&mlxsw_sp->router->lock); kfree(fib_work); } @@ -5997,6 +6046,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) int err; rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ case FIB_EVENT_ENTRY_ADD: @@ -6025,6 +6075,7 @@ static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) dev_put(fib_work->ven_info.dev); break; } + mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); kfree(fib_work); } @@ -6233,7 +6284,7 @@ err_fib_event: return NOTIFY_BAD; } -struct mlxsw_sp_rif * +static struct mlxsw_sp_rif * mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) { @@ -6247,6 +6298,41 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, return NULL; } +bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev) +{ + struct mlxsw_sp_rif *rif; + + mutex_lock(&mlxsw_sp->router->lock); + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + mutex_unlock(&mlxsw_sp->router->lock); + + return rif; +} + +u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev) +{ + struct mlxsw_sp_rif *rif; + u16 vid = 0; + + mutex_lock(&mlxsw_sp->router->lock); + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) + goto out; + + /* We only return the VID for VLAN RIFs. Otherwise we return an + * invalid value (0). + */ + if (rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN) + goto out; + + vid = mlxsw_sp_fid_8021q_vid(rif->fid); + +out: + mutex_unlock(&mlxsw_sp->router->lock); + return vid; +} + static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) { char ritr_pl[MLXSW_REG_RITR_LEN]; @@ -6281,7 +6367,8 @@ mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev, case NETDEV_UP: return rif == NULL; case NETDEV_DOWN: - idev = __in_dev_get_rtnl(dev); + rcu_read_lock(); + idev = __in_dev_get_rcu(dev); if (idev && idev->ifa_list) addr_list_empty = false; @@ -6289,6 +6376,7 @@ mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev, if (addr_list_empty && inet6_dev && !list_empty(&inet6_dev->addr_list)) addr_list_empty = false; + rcu_read_unlock(); /* macvlans do not have a RIF, but rather piggy back on the * RIF of their lower device. @@ -6411,11 +6499,6 @@ const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif) return rif->dev; } -struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif) -{ - return rif->fid; -} - static struct mlxsw_sp_rif * mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_rif_params *params, @@ -6528,10 +6611,13 @@ void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_rif *rif; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!rif) - return; + goto out; mlxsw_sp_rif_destroy(rif); +out: + mutex_unlock(&mlxsw_sp->router->lock); } static void @@ -6631,8 +6717,8 @@ err_fid_port_vid_map: return err; } -void -mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) +static void +__mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port; struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid; @@ -6650,6 +6736,16 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) mlxsw_sp_rif_subport_put(rif); } +void +mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port_vlan->mlxsw_sp_port->mlxsw_sp; + + mutex_lock(&mlxsw_sp->router->lock); + __mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); + mutex_unlock(&mlxsw_sp->router->lock); +} + static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, struct net_device *port_dev, unsigned long event, u16 vid, @@ -6667,7 +6763,7 @@ static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev, return mlxsw_sp_port_vlan_router_join(mlxsw_sp_port_vlan, l3_dev, extack); case NETDEV_DOWN: - mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); + __mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan); break; } @@ -6848,8 +6944,8 @@ err_rif_vrrp_add: return err; } -void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, - const struct net_device *macvlan_dev) +static void __mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, + const struct net_device *macvlan_dev) { struct macvlan_dev *vlan = netdev_priv(macvlan_dev); struct mlxsw_sp_rif *rif; @@ -6866,6 +6962,14 @@ void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_fid_index(rif->fid), false); } +void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp, + const struct net_device *macvlan_dev) +{ + mutex_lock(&mlxsw_sp->router->lock); + __mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev); + mutex_unlock(&mlxsw_sp->router->lock); +} + static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp, struct net_device *macvlan_dev, unsigned long event, @@ -6875,7 +6979,7 @@ static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp, case NETDEV_UP: return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack); case NETDEV_DOWN: - mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev); + __mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev); break; } @@ -6945,15 +7049,17 @@ static int mlxsw_sp_inetaddr_event(struct notifier_block *nb, /* NETDEV_UP event is handled by mlxsw_sp_inetaddr_valid_event */ if (event == NETDEV_UP) - goto out; + return NOTIFY_DONE; router = container_of(nb, struct mlxsw_sp_router, inetaddr_nb); + mutex_lock(&router->lock); rif = mlxsw_sp_rif_find_by_dev(router->mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL); out: + mutex_unlock(&router->lock); return notifier_from_errno(err); } @@ -6968,8 +7074,9 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) - goto out; + return NOTIFY_DONE; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; @@ -6981,6 +7088,7 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused, err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack); out: + mutex_unlock(&mlxsw_sp->router->lock); return notifier_from_errno(err); } @@ -7001,6 +7109,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) struct mlxsw_sp_rif *rif; rtnl_lock(); + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) @@ -7008,6 +7117,7 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL); out: + mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); dev_put(dev); kfree(inet6addr_work); @@ -7052,8 +7162,9 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) - goto out; + return NOTIFY_DONE; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; @@ -7065,6 +7176,7 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused, err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack); out: + mutex_unlock(&mlxsw_sp->router->lock); return notifier_from_errno(err); } @@ -7151,24 +7263,30 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev, { struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif *rif; + int err = 0; mlxsw_sp = mlxsw_sp_lower_get(dev); if (!mlxsw_sp) return 0; + mutex_lock(&mlxsw_sp->router->lock); rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); if (!rif) - return 0; + goto out; switch (event) { case NETDEV_CHANGEMTU: /* fall through */ case NETDEV_CHANGEADDR: - return mlxsw_sp_router_port_change_event(mlxsw_sp, rif); + err = mlxsw_sp_router_port_change_event(mlxsw_sp, rif); + break; case NETDEV_PRE_CHANGEADDR: - return mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr); + err = mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr); + break; } - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp, @@ -7211,9 +7329,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, if (!mlxsw_sp || netif_is_macvlan(l3_dev)) return 0; + mutex_lock(&mlxsw_sp->router->lock); switch (event) { case NETDEV_PRECHANGEUPPER: - return 0; + break; case NETDEV_CHANGEUPPER: if (info->linking) { struct netlink_ext_ack *extack; @@ -7225,6 +7344,7 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, } break; } + mutex_unlock(&mlxsw_sp->router->lock); return err; } @@ -7428,7 +7548,7 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif, } } - return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, br_dev, vid, extack); + return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid); } static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) @@ -7519,7 +7639,7 @@ static struct mlxsw_sp_fid * mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif, struct netlink_ext_ack *extack) { - return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, rif->dev, 0, extack); + return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex); } static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac) @@ -7733,28 +7853,32 @@ int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id, u16 *ul_rif_index) { struct mlxsw_sp_rif *ul_rif; + int err = 0; - ASSERT_RTNL(); - + mutex_lock(&mlxsw_sp->router->lock); ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL); - if (IS_ERR(ul_rif)) - return PTR_ERR(ul_rif); + if (IS_ERR(ul_rif)) { + err = PTR_ERR(ul_rif); + goto out; + } *ul_rif_index = ul_rif->rif_index; - - return 0; +out: + mutex_unlock(&mlxsw_sp->router->lock); + return err; } void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index) { struct mlxsw_sp_rif *ul_rif; - ASSERT_RTNL(); - + mutex_lock(&mlxsw_sp->router->lock); ul_rif = mlxsw_sp->router->rifs[ul_rif_index]; if (WARN_ON(!ul_rif)) - return; + goto out; mlxsw_sp_ul_rif_put(ul_rif); +out: + mutex_unlock(&mlxsw_sp->router->lock); } static int @@ -8004,6 +8128,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, router = kzalloc(sizeof(*mlxsw_sp->router), GFP_KERNEL); if (!router) return -ENOMEM; + mutex_init(&router->lock); mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; @@ -8107,6 +8232,7 @@ err_router_init: err_register_inet6addr_notifier: unregister_inetaddr_notifier(&router->inetaddr_nb); err_register_inetaddr_notifier: + mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); return err; } @@ -8127,5 +8253,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) __mlxsw_sp_router_fini(mlxsw_sp); unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); + mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index c9b94f435cdd..8418dc3ae967 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -7,6 +7,49 @@ #include "spectrum.h" #include "reg.h" +struct mlxsw_sp_router_nve_decap { + u32 ul_tb_id; + u32 tunnel_index; + enum mlxsw_sp_l3proto ul_proto; + union mlxsw_sp_l3addr ul_sip; + u8 valid:1; +}; + +struct mlxsw_sp_router { + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif **rifs; + struct mlxsw_sp_vr *vrs; + struct rhashtable neigh_ht; + struct rhashtable nexthop_group_ht; + struct rhashtable nexthop_ht; + struct list_head nexthop_list; + struct { + /* One tree for each protocol: IPv4 and IPv6 */ + struct mlxsw_sp_lpm_tree *proto_trees[2]; + struct mlxsw_sp_lpm_tree *trees; + unsigned int tree_count; + } lpm; + struct { + struct delayed_work dw; + unsigned long interval; /* ms */ + } neighs_update; + struct delayed_work nexthop_probe_dw; +#define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ + struct list_head nexthop_neighs_list; + struct list_head ipip_list; + bool aborted; + struct notifier_block fib_nb; + struct notifier_block netevent_nb; + struct notifier_block inetaddr_nb; + struct notifier_block inet6addr_nb; + const struct mlxsw_sp_rif_ops **rif_ops_arr; + const struct mlxsw_sp_ipip_ops **ipip_ops_arr; + u32 adj_discard_index; + bool adj_discard_index_valid; + struct mlxsw_sp_router_nve_decap nve_decap_config; + struct mutex lock; /* Protects shared router resources */ +}; + struct mlxsw_sp_rif_ipip_lb; struct mlxsw_sp_rif_ipip_lb_config { enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 0cdd7954a085..9fb2e9d93929 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -3,6 +3,8 @@ #include <linux/if_bridge.h> #include <linux/list.h> +#include <linux/rtnetlink.h> +#include <linux/workqueue.h> #include <net/arp.h> #include <net/gre.h> #include <net/lag.h> @@ -14,38 +16,43 @@ #include "spectrum_span.h" #include "spectrum_switchdev.h" +struct mlxsw_sp_span { + struct work_struct work; + struct mlxsw_sp *mlxsw_sp; + atomic_t active_entries_count; + int entries_count; + struct mlxsw_sp_span_entry entries[0]; +}; + +static void mlxsw_sp_span_respin_work(struct work_struct *work); + static u64 mlxsw_sp_span_occ_get(void *priv) { const struct mlxsw_sp *mlxsw_sp = priv; - u64 occ = 0; - int i; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - if (mlxsw_sp->span.entries[i].ref_count) - occ++; - } - - return occ; + return atomic_read(&mlxsw_sp->span->active_entries_count); } int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); - int i; + struct mlxsw_sp_span *span; + int i, entries_count; if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_SPAN)) return -EIO; - mlxsw_sp->span.entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, - MAX_SPAN); - mlxsw_sp->span.entries = kcalloc(mlxsw_sp->span.entries_count, - sizeof(struct mlxsw_sp_span_entry), - GFP_KERNEL); - if (!mlxsw_sp->span.entries) + entries_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_SPAN); + span = kzalloc(struct_size(span, entries, entries_count), GFP_KERNEL); + if (!span) return -ENOMEM; + span->entries_count = entries_count; + atomic_set(&span->active_entries_count, 0); + span->mlxsw_sp = mlxsw_sp; + mlxsw_sp->span = span; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; INIT_LIST_HEAD(&curr->bound_ports_list); curr->id = i; @@ -53,6 +60,7 @@ int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) devlink_resource_occ_get_register(devlink, MLXSW_SP_RESOURCE_SPAN, mlxsw_sp_span_occ_get, mlxsw_sp); + INIT_WORK(&span->work, mlxsw_sp_span_respin_work); return 0; } @@ -62,14 +70,15 @@ void mlxsw_sp_span_fini(struct mlxsw_sp *mlxsw_sp) struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); int i; + cancel_work_sync(&mlxsw_sp->span->work); devlink_resource_occ_get_unregister(devlink, MLXSW_SP_RESOURCE_SPAN); - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; WARN_ON_ONCE(!list_empty(&curr->bound_ports_list)); } - kfree(mlxsw_sp->span.entries); + kfree(mlxsw_sp->span); } static int @@ -645,15 +654,16 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, int i; /* find a free entry to use */ - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - if (!mlxsw_sp->span.entries[i].ref_count) { - span_entry = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + if (!mlxsw_sp->span->entries[i].ref_count) { + span_entry = &mlxsw_sp->span->entries[i]; break; } } if (!span_entry) return NULL; + atomic_inc(&mlxsw_sp->span->active_entries_count); span_entry->ops = ops; span_entry->ref_count = 1; span_entry->to_dev = to_dev; @@ -662,9 +672,11 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp *mlxsw_sp, return span_entry; } -static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp_span_entry *span_entry) +static void mlxsw_sp_span_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_span_entry *span_entry) { mlxsw_sp_span_entry_deconfigure(span_entry); + atomic_dec(&mlxsw_sp->span->active_entries_count); } struct mlxsw_sp_span_entry * @@ -673,8 +685,8 @@ mlxsw_sp_span_entry_find_by_port(struct mlxsw_sp *mlxsw_sp, { int i; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; if (curr->ref_count && curr->to_dev == to_dev) return curr; @@ -694,8 +706,8 @@ mlxsw_sp_span_entry_find_by_id(struct mlxsw_sp *mlxsw_sp, int span_id) { int i; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; if (curr->ref_count && curr->id == span_id) return curr; @@ -726,7 +738,7 @@ static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, { WARN_ON(!span_entry->ref_count); if (--span_entry->ref_count == 0) - mlxsw_sp_span_entry_destroy(span_entry); + mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); return 0; } @@ -736,8 +748,8 @@ static bool mlxsw_sp_span_is_egress_mirror(struct mlxsw_sp_port *port) struct mlxsw_sp_span_inspected_port *p; int i; - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; list_for_each_entry(p, &curr->bound_ports_list, list) if (p->local_port == port->local_port && @@ -842,9 +854,9 @@ mlxsw_sp_span_inspected_port_add(struct mlxsw_sp_port *port, * so if a binding is requested, check for conflicts. */ if (bind) - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { struct mlxsw_sp_span_entry *curr = - &mlxsw_sp->span.entries[i]; + &mlxsw_sp->span->entries[i]; if (mlxsw_sp_span_entry_bound_port_find(curr, type, port, bind)) @@ -988,14 +1000,18 @@ void mlxsw_sp_span_mirror_del(struct mlxsw_sp_port *from, int span_id, mlxsw_sp_span_inspected_port_del(from, span_entry, type, bind); } -void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_span_respin_work(struct work_struct *work) { - int i; - int err; + struct mlxsw_sp_span *span; + struct mlxsw_sp *mlxsw_sp; + int i, err; - ASSERT_RTNL(); - for (i = 0; i < mlxsw_sp->span.entries_count; i++) { - struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span.entries[i]; + span = container_of(work, struct mlxsw_sp_span, work); + mlxsw_sp = span->mlxsw_sp; + + rtnl_lock(); + for (i = 0; i < mlxsw_sp->span->entries_count; i++) { + struct mlxsw_sp_span_entry *curr = &mlxsw_sp->span->entries[i]; struct mlxsw_sp_span_parms sparms = {NULL}; if (!curr->ref_count) @@ -1010,4 +1026,12 @@ void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_span_entry_configure(mlxsw_sp, curr, sparms); } } + rtnl_unlock(); +} + +void mlxsw_sp_span_respin(struct mlxsw_sp *mlxsw_sp) +{ + if (atomic_read(&mlxsw_sp->span->active_entries_count) == 0) + return; + mlxsw_core_schedule_work(&mlxsw_sp->span->work); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index a3af171c6358..a26162b08b7d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -153,16 +153,64 @@ static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp); } +static int mlxsw_sp_bridge_device_vxlan_init(struct mlxsw_sp_bridge *bridge, + struct net_device *br_dev, + struct netlink_ext_ack *extack) +{ + struct net_device *dev, *stop_dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(br_dev, dev, iter) { + if (netif_is_vxlan(dev) && netif_running(dev)) { + err = mlxsw_sp_bridge_vxlan_join(bridge->mlxsw_sp, + br_dev, dev, 0, + extack); + if (err) { + stop_dev = dev; + goto err_vxlan_join; + } + } + } + + return 0; + +err_vxlan_join: + netdev_for_each_lower_dev(br_dev, dev, iter) { + if (netif_is_vxlan(dev) && netif_running(dev)) { + if (stop_dev == dev) + break; + mlxsw_sp_bridge_vxlan_leave(bridge->mlxsw_sp, dev); + } + } + return err; +} + +static void mlxsw_sp_bridge_device_vxlan_fini(struct mlxsw_sp_bridge *bridge, + struct net_device *br_dev) +{ + struct net_device *dev; + struct list_head *iter; + + netdev_for_each_lower_dev(br_dev, dev, iter) { + if (netif_is_vxlan(dev) && netif_running(dev)) + mlxsw_sp_bridge_vxlan_leave(bridge->mlxsw_sp, dev); + } +} + static struct mlxsw_sp_bridge_device * mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, - struct net_device *br_dev) + struct net_device *br_dev, + struct netlink_ext_ack *extack) { struct device *dev = bridge->mlxsw_sp->bus_info->dev; struct mlxsw_sp_bridge_device *bridge_device; bool vlan_enabled = br_vlan_enabled(br_dev); + int err; if (vlan_enabled && bridge->vlan_enabled_exists) { dev_err(dev, "Only one VLAN-aware bridge is supported\n"); + NL_SET_ERR_MSG_MOD(extack, "Only one VLAN-aware bridge is supported"); return ERR_PTR(-EINVAL); } @@ -184,13 +232,29 @@ mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, INIT_LIST_HEAD(&bridge_device->mids_list); list_add(&bridge_device->list, &bridge->bridges_list); + /* It is possible we already have VXLAN devices enslaved to the bridge. + * In which case, we need to replay their configuration as if they were + * just now enslaved to the bridge. + */ + err = mlxsw_sp_bridge_device_vxlan_init(bridge, br_dev, extack); + if (err) + goto err_vxlan_init; + return bridge_device; + +err_vxlan_init: + list_del(&bridge_device->list); + if (bridge_device->vlan_enabled) + bridge->vlan_enabled_exists = false; + kfree(bridge_device); + return ERR_PTR(err); } static void mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge, struct mlxsw_sp_bridge_device *bridge_device) { + mlxsw_sp_bridge_device_vxlan_fini(bridge, bridge_device->dev); mlxsw_sp_bridge_device_rifs_destroy(bridge->mlxsw_sp, bridge_device->dev); list_del(&bridge_device->list); @@ -203,7 +267,8 @@ mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge, static struct mlxsw_sp_bridge_device * mlxsw_sp_bridge_device_get(struct mlxsw_sp_bridge *bridge, - struct net_device *br_dev) + struct net_device *br_dev, + struct netlink_ext_ack *extack) { struct mlxsw_sp_bridge_device *bridge_device; @@ -211,7 +276,7 @@ mlxsw_sp_bridge_device_get(struct mlxsw_sp_bridge *bridge, if (bridge_device) return bridge_device; - return mlxsw_sp_bridge_device_create(bridge, br_dev); + return mlxsw_sp_bridge_device_create(bridge, br_dev, extack); } static void @@ -292,7 +357,8 @@ mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port) static struct mlxsw_sp_bridge_port * mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge, - struct net_device *brport_dev) + struct net_device *brport_dev, + struct netlink_ext_ack *extack) { struct net_device *br_dev = netdev_master_upper_dev_get(brport_dev); struct mlxsw_sp_bridge_device *bridge_device; @@ -305,7 +371,7 @@ mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge, return bridge_port; } - bridge_device = mlxsw_sp_bridge_device_get(bridge, br_dev); + bridge_device = mlxsw_sp_bridge_device_get(bridge, br_dev, extack); if (IS_ERR(bridge_device)) return ERR_CAST(bridge_device); @@ -1000,7 +1066,7 @@ mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, &bridge_vlan->port_vlan_list); mlxsw_sp_bridge_port_get(mlxsw_sp_port->mlxsw_sp->bridge, - bridge_port->dev); + bridge_port->dev, extack); mlxsw_sp_port_vlan->bridge_port = bridge_port; return 0; @@ -1107,16 +1173,12 @@ mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp, const struct net_device *br_dev, const struct switchdev_obj_port_vlan *vlan) { - struct mlxsw_sp_rif *rif; - struct mlxsw_sp_fid *fid; u16 pvid; u16 vid; - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev); - if (!rif) + pvid = mlxsw_sp_rif_vid(mlxsw_sp, br_dev); + if (!pvid) return 0; - fid = mlxsw_sp_rif_fid(rif); - pvid = mlxsw_sp_fid_8021q_vid(fid); for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { if (vlan->flags & BRIDGE_VLAN_INFO_PVID) { @@ -1712,36 +1774,6 @@ mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port, } } -struct mlxsw_sp_span_respin_work { - struct work_struct work; - struct mlxsw_sp *mlxsw_sp; -}; - -static void mlxsw_sp_span_respin_work(struct work_struct *work) -{ - struct mlxsw_sp_span_respin_work *respin_work = - container_of(work, struct mlxsw_sp_span_respin_work, work); - - rtnl_lock(); - mlxsw_sp_span_respin(respin_work->mlxsw_sp); - rtnl_unlock(); - kfree(respin_work); -} - -static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_span_respin_work *respin_work; - - respin_work = kzalloc(sizeof(*respin_work), GFP_ATOMIC); - if (!respin_work) - return; - - INIT_WORK(&respin_work->work, mlxsw_sp_span_respin_work); - respin_work->mlxsw_sp = mlxsw_sp; - - mlxsw_core_schedule_work(&respin_work->work); -} - static int mlxsw_sp_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans, @@ -1763,7 +1795,7 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, * call for later, so that the respin logic sees the * updated bridge state. */ - mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp); + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); } break; case SWITCHDEV_OBJ_ID_PORT_MDB: @@ -1916,7 +1948,7 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev, break; } - mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp); + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); return err; } @@ -1990,12 +2022,11 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, return err; } - /* If no other port is member in the VLAN, then the FID does not exist. - * NVE will be enabled on the FID once a port joins the VLAN - */ - fid = mlxsw_sp_fid_8021q_lookup(mlxsw_sp, vid); - if (!fid) - return 0; + fid = mlxsw_sp_fid_8021q_get(mlxsw_sp, vid); + if (IS_ERR(fid)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to create 802.1Q FID"); + return PTR_ERR(fid); + } if (mlxsw_sp_fid_vni_is_set(fid)) { NL_SET_ERR_MSG_MOD(extack, "VNI is already set on FID"); @@ -2007,11 +2038,6 @@ mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, if (err) goto err_nve_fid_enable; - /* The tunnel port does not hold a reference on the FID. Only - * local ports and the router port - */ - mlxsw_sp_fid_put(fid); - return 0; err_nve_fid_enable: @@ -2048,38 +2074,8 @@ mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device, u16 vid, struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev); - struct net_device *vxlan_dev; - struct mlxsw_sp_fid *fid; - int err; - - fid = mlxsw_sp_fid_8021q_get(mlxsw_sp, vid); - if (IS_ERR(fid)) - return fid; - - if (mlxsw_sp_fid_vni_is_set(fid)) - return fid; - - /* Find the VxLAN device that has the specified VLAN configured as - * PVID and egress untagged. There can be at most one such device - */ - vxlan_dev = mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev, - vid); - if (!vxlan_dev) - return fid; - - if (!netif_running(vxlan_dev)) - return fid; - - err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid, - extack); - if (err) - goto err_vxlan_join; - - return fid; -err_vxlan_join: - mlxsw_sp_fid_put(fid); - return ERR_PTR(err); + return mlxsw_sp_fid_8021q_get(mlxsw_sp, vid); } static struct mlxsw_sp_fid * @@ -2184,9 +2180,9 @@ mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, struct mlxsw_sp_fid *fid; int err; - fid = mlxsw_sp_fid_8021d_lookup(mlxsw_sp, bridge_device->dev->ifindex); - if (!fid) { - NL_SET_ERR_MSG_MOD(extack, "Did not find a corresponding FID"); + fid = mlxsw_sp_fid_8021d_get(mlxsw_sp, bridge_device->dev->ifindex); + if (IS_ERR(fid)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to create 802.1D FID"); return -EINVAL; } @@ -2200,11 +2196,6 @@ mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device, if (err) goto err_nve_fid_enable; - /* The tunnel port does not hold a reference on the FID. Only - * local ports and the router port - */ - mlxsw_sp_fid_put(fid); - return 0; err_nve_fid_enable: @@ -2218,34 +2209,8 @@ mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device, u16 vid, struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev); - struct net_device *vxlan_dev; - struct mlxsw_sp_fid *fid; - int err; - fid = mlxsw_sp_fid_8021d_get(mlxsw_sp, bridge_device->dev->ifindex); - if (IS_ERR(fid)) - return fid; - - if (mlxsw_sp_fid_vni_is_set(fid)) - return fid; - - vxlan_dev = mlxsw_sp_bridge_vxlan_dev_find(bridge_device->dev); - if (!vxlan_dev) - return fid; - - if (!netif_running(vxlan_dev)) - return fid; - - err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, 0, - extack); - if (err) - goto err_vxlan_join; - - return fid; - -err_vxlan_join: - mlxsw_sp_fid_put(fid); - return ERR_PTR(err); + return mlxsw_sp_fid_8021d_get(mlxsw_sp, bridge_device->dev->ifindex); } static struct mlxsw_sp_fid * @@ -2287,7 +2252,8 @@ int mlxsw_sp_port_bridge_join(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_bridge_port *bridge_port; int err; - bridge_port = mlxsw_sp_bridge_port_get(mlxsw_sp->bridge, brport_dev); + bridge_port = mlxsw_sp_bridge_port_get(mlxsw_sp->bridge, brport_dev, + extack); if (IS_ERR(bridge_port)) return PTR_ERR(bridge_port); bridge_device = bridge_port->bridge_device; @@ -2351,21 +2317,11 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp, return; mlxsw_sp_nve_fid_disable(mlxsw_sp, fid); + /* Drop both the reference we just took during lookup and the reference + * the VXLAN device took. + */ + mlxsw_sp_fid_put(fid); mlxsw_sp_fid_put(fid); -} - -struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp, - const struct net_device *br_dev, - u16 vid, - struct netlink_ext_ack *extack) -{ - struct mlxsw_sp_bridge_device *bridge_device; - - bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev); - if (WARN_ON(!bridge_device)) - return ERR_PTR(-EINVAL); - - return bridge_device->ops->fid_get(bridge_device, vid, extack); } static void @@ -2718,19 +2674,24 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp, } } -static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_fdb_notify_work_schedule(struct mlxsw_sp *mlxsw_sp, + bool no_delay) { struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge; + unsigned int interval = no_delay ? 0 : bridge->fdb_notify.interval; mlxsw_core_schedule_dw(&bridge->fdb_notify.dw, - msecs_to_jiffies(bridge->fdb_notify.interval)); + msecs_to_jiffies(interval)); } +#define MLXSW_SP_FDB_SFN_QUERIES_PER_SESSION 10 + static void mlxsw_sp_fdb_notify_work(struct work_struct *work) { struct mlxsw_sp_bridge *bridge; struct mlxsw_sp *mlxsw_sp; char *sfn_pl; + int queries; u8 num_rec; int i; int err; @@ -2743,20 +2704,26 @@ static void mlxsw_sp_fdb_notify_work(struct work_struct *work) mlxsw_sp = bridge->mlxsw_sp; rtnl_lock(); - mlxsw_reg_sfn_pack(sfn_pl); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); - if (err) { - dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get FDB notifications\n"); - goto out; + queries = MLXSW_SP_FDB_SFN_QUERIES_PER_SESSION; + while (queries > 0) { + mlxsw_reg_sfn_pack(sfn_pl); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfn), sfn_pl); + if (err) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get FDB notifications\n"); + goto out; + } + num_rec = mlxsw_reg_sfn_num_rec_get(sfn_pl); + for (i = 0; i < num_rec; i++) + mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); + if (num_rec != MLXSW_REG_SFN_REC_MAX_COUNT) + goto out; + queries--; } - num_rec = mlxsw_reg_sfn_num_rec_get(sfn_pl); - for (i = 0; i < num_rec; i++) - mlxsw_sp_fdb_notify_rec_process(mlxsw_sp, sfn_pl, i); out: rtnl_unlock(); kfree(sfn_pl); - mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp, !queries); } struct mlxsw_sp_switchdev_event_work { @@ -3502,7 +3469,7 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) INIT_DELAYED_WORK(&bridge->fdb_notify.dw, mlxsw_sp_fdb_notify_work); bridge->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL; - mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp); + mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp, false); return 0; err_register_switchdev_blocking_notifier: diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 60205aa3f6a5..9c300d625e04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -25,16 +25,121 @@ enum { #define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT +static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, + u8 local_port, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + if (unlikely(!mlxsw_sp_port)) { + dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", + local_port); + kfree_skb(skb); + return -EINVAL; + } + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + + return 0; +} + static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, - void *priv); + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, NULL); + consume_skb(skb); +} + +static void mlxsw_sp_rx_acl_drop_listener(struct sk_buff *skb, u8 local_port, + void *trap_ctx) +{ + u32 cookie_index = mlxsw_skb_cb(skb)->cookie_index; + const struct flow_action_cookie *fa_cookie; + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + rcu_read_lock(); + fa_cookie = mlxsw_sp_acl_act_cookie_lookup(mlxsw_sp, cookie_index); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, fa_cookie); + rcu_read_unlock(); + consume_skb(skb); +} + static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx); + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + int err; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + err = mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port); + if (err) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + skb_push(skb, ETH_HLEN); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port, NULL); + skb_pull(skb, ETH_HLEN); + skb->offload_fwd_mark = 1; + netif_receive_skb(skb); +} #define MLXSW_SP_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ MLXSW_SP_TRAP_METADATA) +#define MLXSW_SP_TRAP_DROP_EXT(_id, _group_id, _metadata) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + MLXSW_SP_TRAP_METADATA | (_metadata)) + #define MLXSW_SP_TRAP_DRIVER_DROP(_id, _group_id) \ DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_MLXSW_TRAP_ID_##_id, \ DEVLINK_MLXSW_TRAP_NAME_##_id, \ @@ -47,14 +152,20 @@ static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, MLXSW_SP_TRAP_METADATA) #define MLXSW_SP_RXL_DISCARD(_id, _group_id) \ - MLXSW_RXL(mlxsw_sp_rx_drop_listener, DISCARD_##_id, SET_FW_DEFAULT, \ - false, SP_##_group_id, DISCARD) + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, DISCARD_##_id, \ + TRAP_EXCEPTION_TO_CPU, false, SP_##_group_id, \ + SET_FW_DEFAULT, SP_##_group_id) + +#define MLXSW_SP_RXL_ACL_DISCARD(_id, _en_group_id, _dis_group_id) \ + MLXSW_RXL_DIS(mlxsw_sp_rx_acl_drop_listener, DISCARD_##_id, \ + TRAP_EXCEPTION_TO_CPU, false, SP_##_en_group_id, \ + SET_FW_DEFAULT, SP_##_dis_group_id) #define MLXSW_SP_RXL_EXCEPTION(_id, _group_id, _action) \ MLXSW_RXL(mlxsw_sp_rx_exception_listener, _id, \ - _action, false, SP_##_group_id, DISCARD) + _action, false, SP_##_group_id, SET_FW_DEFAULT) -static struct devlink_trap mlxsw_sp_traps_arr[] = { +static const struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS), MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS), @@ -83,9 +194,13 @@ static struct devlink_trap mlxsw_sp_traps_arr[] = { MLXSW_SP_TRAP_DROP(NON_ROUTABLE, L3_DROPS), MLXSW_SP_TRAP_EXCEPTION(DECAP_ERROR, TUNNEL_DROPS), MLXSW_SP_TRAP_DROP(OVERLAY_SMAC_MC, TUNNEL_DROPS), + MLXSW_SP_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + MLXSW_SP_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), }; -static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { +static const struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW, L2_DISCARDS), MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS), @@ -124,13 +239,15 @@ static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { MLXSW_SP_RXL_EXCEPTION(DISCARD_DEC_PKT, TUNNEL_DISCARDS, TRAP_EXCEPTION_TO_CPU), MLXSW_SP_RXL_DISCARD(OVERLAY_SMAC_MC, TUNNEL_DISCARDS), + MLXSW_SP_RXL_ACL_DISCARD(INGRESS_ACL, ACL_DISCARDS, DUMMY), + MLXSW_SP_RXL_ACL_DISCARD(EGRESS_ACL, ACL_DISCARDS, DUMMY), }; /* Mapping between hardware trap and devlink trap. Multiple hardware traps can * be mapped to the same devlink trap. Order is according to * 'mlxsw_sp_listeners_arr'. */ -static u16 mlxsw_sp_listener_devlink_map[] = { +static const u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_SMAC_MC, DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER, @@ -164,83 +281,53 @@ static u16 mlxsw_sp_listener_devlink_map[] = { DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP, + DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP, }; -static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, - u8 local_port, - struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct mlxsw_sp_port_pcpu_stats *pcpu_stats; - - if (unlikely(!mlxsw_sp_port)) { - dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", - local_port); - kfree_skb(skb); - return -EINVAL; - } - - skb->dev = mlxsw_sp_port->dev; - - pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); - u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += skb->len; - u64_stats_update_end(&pcpu_stats->syncp); - - skb->protocol = eth_type_trans(skb, skb->dev); - - return 0; -} +#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1) +#define MLXSW_SP_THIN_POLICER_ID (MLXSW_SP_DISCARD_POLICER_ID + 1) -static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx) +static int mlxsw_sp_trap_cpu_policers_set(struct mlxsw_sp *mlxsw_sp) { - struct devlink_port *in_devlink_port; - struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp *mlxsw_sp; - struct devlink *devlink; - - mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; + char qpcr_pl[MLXSW_REG_QPCR_LEN]; + int err; - if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) - return; + mlxsw_reg_qpcr_pack(qpcr_pl, MLXSW_SP_DISCARD_POLICER_ID, + MLXSW_REG_QPCR_IR_UNITS_M, false, 10 * 1024, 7); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); + if (err) + return err; - devlink = priv_to_devlink(mlxsw_sp->core); - in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - local_port); - skb_push(skb, ETH_HLEN); - devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); - consume_skb(skb); + /* The purpose of "thin" policer is to drop as many packets + * as possible. The dummy group is using it. + */ + mlxsw_reg_qpcr_pack(qpcr_pl, MLXSW_SP_THIN_POLICER_ID, + MLXSW_REG_QPCR_IR_UNITS_M, false, 1, 4); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); } -static void mlxsw_sp_rx_exception_listener(struct sk_buff *skb, u8 local_port, - void *trap_ctx) +static int mlxsw_sp_trap_dummy_group_init(struct mlxsw_sp *mlxsw_sp) { - struct devlink_port *in_devlink_port; - struct mlxsw_sp_port *mlxsw_sp_port; - struct mlxsw_sp *mlxsw_sp; - struct devlink *devlink; - - mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); - mlxsw_sp_port = mlxsw_sp->ports[local_port]; - - if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) - return; + char htgt_pl[MLXSW_REG_HTGT_LEN]; - devlink = priv_to_devlink(mlxsw_sp->core); - in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - local_port); - skb_push(skb, ETH_HLEN); - devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); - skb_pull(skb, ETH_HLEN); - skb->offload_fwd_mark = 1; - netif_receive_skb(skb); + mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SP_DUMMY, + MLXSW_SP_THIN_POLICER_ID, 0, 1); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); } int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + int err; + + err = mlxsw_sp_trap_cpu_policers_set(mlxsw_sp); + if (err) + return err; + + err = mlxsw_sp_trap_dummy_group_init(mlxsw_sp); + if (err) + return err; if (WARN_ON(ARRAY_SIZE(mlxsw_sp_listener_devlink_map) != ARRAY_SIZE(mlxsw_sp_listeners_arr))) @@ -265,7 +352,7 @@ int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; int err; if (mlxsw_sp_listener_devlink_map[i] != trap->id) @@ -286,7 +373,7 @@ void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; if (mlxsw_sp_listener_devlink_map[i] != trap->id) continue; @@ -303,27 +390,24 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, int i; for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { - enum mlxsw_reg_hpkt_action hw_action; - struct mlxsw_listener *listener; + const struct mlxsw_listener *listener; + bool enabled; int err; if (mlxsw_sp_listener_devlink_map[i] != trap->id) continue; listener = &mlxsw_sp_listeners_arr[i]; - switch (action) { case DEVLINK_TRAP_ACTION_DROP: - hw_action = MLXSW_REG_HPKT_ACTION_SET_FW_DEFAULT; + enabled = false; break; case DEVLINK_TRAP_ACTION_TRAP: - hw_action = MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU; + enabled = true; break; default: return -EINVAL; } - - err = mlxsw_core_trap_action_set(mlxsw_core, listener, - hw_action); + err = mlxsw_core_trap_state_set(mlxsw_core, listener, enabled); if (err) return err; } @@ -331,41 +415,8 @@ int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, return 0; } -#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1) - -static int -mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp, - const struct devlink_trap_group *group) -{ - enum mlxsw_reg_qpcr_ir_units ir_units; - char qpcr_pl[MLXSW_REG_QPCR_LEN]; - u16 policer_id; - u8 burst_size; - bool is_bytes; - u32 rate; - - switch (group->id) { - case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: /* fall through */ - case DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS: /* fall through */ - case DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS: - policer_id = MLXSW_SP_DISCARD_POLICER_ID; - ir_units = MLXSW_REG_QPCR_IR_UNITS_M; - is_bytes = false; - rate = 10 * 1024; /* 10Kpps */ - burst_size = 7; - break; - default: - return -EINVAL; - } - - mlxsw_reg_qpcr_pack(qpcr_pl, policer_id, ir_units, is_bytes, rate, - burst_size); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); -} - -static int -__mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, - const struct devlink_trap_group *group) +int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap_group *group) { char htgt_pl[MLXSW_REG_HTGT_LEN]; u8 priority, tc, group_id; @@ -390,27 +441,16 @@ __mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, priority = 0; tc = 1; break; + case DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS: + group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS; + policer_id = MLXSW_SP_DISCARD_POLICER_ID; + priority = 0; + tc = 1; + break; default: return -EINVAL; } mlxsw_reg_htgt_pack(htgt_pl, group_id, policer_id, priority, tc); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); -} - -int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, - const struct devlink_trap_group *group) -{ - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - int err; - - err = mlxsw_sp_trap_group_policer_init(mlxsw_sp, group); - if (err) - return err; - - err = __mlxsw_sp_trap_group_init(mlxsw_sp, group); - if (err) - return err; - - return 0; + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 12e1fa998d42..eaa521b7561b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -102,6 +102,8 @@ enum { MLXSW_TRAP_ID_ACL1 = 0x1C1, /* Multicast trap used for routes with trap-and-forward action */ MLXSW_TRAP_ID_ACL2 = 0x1C2, + MLXSW_TRAP_ID_DISCARD_INGRESS_ACL = 0x1C3, + MLXSW_TRAP_ID_DISCARD_EGRESS_ACL = 0x1C4, MLXSW_TRAP_ID_MAX = 0x1FF }; diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index d1444ba36e10..4fe6aedca22f 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -5694,7 +5694,7 @@ static void dev_set_promiscuous(struct net_device *dev, struct dev_priv *priv, * from the bridge. */ if ((hw->features & STP_SUPPORT) && !promiscuous && - (dev->priv_flags & IFF_BRIDGE_PORT)) { + netif_is_bridge_port(dev)) { struct ksz_switch *sw = hw->ksz_switch; int port = priv->port.first_port; diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index 51fa82b429a3..bfa0c0d39600 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -147,39 +147,12 @@ static int sonic_probe1(struct net_device *dev) dev->dev_addr[i*2+1] = val >> 8; } - err = -ENOMEM; - - /* Initialize the device structure. */ - lp->dma_bitmode = SONIC_BITMODE32; - /* Allocate the entire chunk of memory for the descriptors. - Note that this cannot cross a 64K boundary. */ - lp->descriptors = dma_alloc_coherent(lp->device, - SIZEOF_SONIC_DESC * - SONIC_BUS_SCALE(lp->dma_bitmode), - &lp->descriptors_laddr, - GFP_KERNEL); - if (lp->descriptors == NULL) + err = sonic_alloc_descriptors(dev); + if (err) goto out; - /* Now set up the pointers to point to the appropriate places */ - lp->cda = lp->descriptors; - lp->tda = lp->cda + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda = lp->tda + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra = lp->rda + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - - lp->cda_laddr = lp->descriptors_laddr; - lp->tda_laddr = lp->cda_laddr + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda_laddr = lp->tda_laddr + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra_laddr = lp->rda_laddr + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - dev->netdev_ops = &sonic_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c index 0937fc2a928e..1b5559aacb38 100644 --- a/drivers/net/ethernet/natsemi/macsonic.c +++ b/drivers/net/ethernet/natsemi/macsonic.c @@ -114,17 +114,6 @@ static inline void bit_reverse_addr(unsigned char addr[6]) addr[i] = bitrev8(addr[i]); } -static irqreturn_t macsonic_interrupt(int irq, void *dev_id) -{ - irqreturn_t result; - unsigned long flags; - - local_irq_save(flags); - result = sonic_interrupt(irq, dev_id); - local_irq_restore(flags); - return result; -} - static int macsonic_open(struct net_device* dev) { int retval; @@ -135,12 +124,12 @@ static int macsonic_open(struct net_device* dev) dev->name, dev->irq); goto err; } - /* Under the A/UX interrupt scheme, the onboard SONIC interrupt comes - * in at priority level 3. However, we sometimes get the level 2 inter- - * rupt as well, which must prevent re-entrance of the sonic handler. + /* Under the A/UX interrupt scheme, the onboard SONIC interrupt gets + * moved from level 2 to level 3. Unfortunately we still get some + * level 2 interrupts so register the handler for both. */ if (dev->irq == IRQ_AUTO_3) { - retval = request_irq(IRQ_NUBUS_9, macsonic_interrupt, 0, + retval = request_irq(IRQ_NUBUS_9, sonic_interrupt, 0, "sonic", dev); if (retval) { printk(KERN_ERR "%s: unable to get IRQ %d.\n", @@ -186,33 +175,10 @@ static const struct net_device_ops macsonic_netdev_ops = { static int macsonic_init(struct net_device *dev) { struct sonic_local* lp = netdev_priv(dev); + int err = sonic_alloc_descriptors(dev); - /* Allocate the entire chunk of memory for the descriptors. - Note that this cannot cross a 64K boundary. */ - lp->descriptors = dma_alloc_coherent(lp->device, - SIZEOF_SONIC_DESC * - SONIC_BUS_SCALE(lp->dma_bitmode), - &lp->descriptors_laddr, - GFP_KERNEL); - if (lp->descriptors == NULL) - return -ENOMEM; - - /* Now set up the pointers to point to the appropriate places */ - lp->cda = lp->descriptors; - lp->tda = lp->cda + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda = lp->tda + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra = lp->rda + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - - lp->cda_laddr = lp->descriptors_laddr; - lp->tda_laddr = lp->cda_laddr + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda_laddr = lp->tda_laddr + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra_laddr = lp->rda_laddr + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); + if (err) + return err; dev->netdev_ops = &macsonic_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index 31be3ba66877..dd3605aa5f23 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -50,6 +50,42 @@ static void sonic_msg_init(struct net_device *dev) netif_dbg(lp, drv, dev, "%s", version); } +static int sonic_alloc_descriptors(struct net_device *dev) +{ + struct sonic_local *lp = netdev_priv(dev); + + /* Allocate a chunk of memory for the descriptors. Note that this + * must not cross a 64K boundary. It is smaller than one page which + * means that page alignment is a sufficient condition. + */ + lp->descriptors = + dma_alloc_coherent(lp->device, + SIZEOF_SONIC_DESC * + SONIC_BUS_SCALE(lp->dma_bitmode), + &lp->descriptors_laddr, GFP_KERNEL); + + if (!lp->descriptors) + return -ENOMEM; + + lp->cda = lp->descriptors; + lp->tda = lp->cda + SIZEOF_SONIC_CDA * + SONIC_BUS_SCALE(lp->dma_bitmode); + lp->rda = lp->tda + SIZEOF_SONIC_TD * SONIC_NUM_TDS * + SONIC_BUS_SCALE(lp->dma_bitmode); + lp->rra = lp->rda + SIZEOF_SONIC_RD * SONIC_NUM_RDS * + SONIC_BUS_SCALE(lp->dma_bitmode); + + lp->cda_laddr = lp->descriptors_laddr; + lp->tda_laddr = lp->cda_laddr + SIZEOF_SONIC_CDA * + SONIC_BUS_SCALE(lp->dma_bitmode); + lp->rda_laddr = lp->tda_laddr + SIZEOF_SONIC_TD * SONIC_NUM_TDS * + SONIC_BUS_SCALE(lp->dma_bitmode); + lp->rra_laddr = lp->rda_laddr + SIZEOF_SONIC_RD * SONIC_NUM_RDS * + SONIC_BUS_SCALE(lp->dma_bitmode); + + return 0; +} + /* * Open/initialize the SONIC controller. * @@ -264,7 +300,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&lp->lock, flags); - entry = lp->next_tx; + entry = (lp->eol_tx + 1) & SONIC_TDS_MASK; sonic_tda_put(dev, entry, SONIC_TD_STATUS, 0); /* clear status */ sonic_tda_put(dev, entry, SONIC_TD_FRAG_COUNT, 1); /* single fragment */ @@ -275,27 +311,26 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) sonic_tda_put(dev, entry, SONIC_TD_LINK, sonic_tda_get(dev, entry, SONIC_TD_LINK) | SONIC_EOL); - wmb(); + sonic_tda_put(dev, lp->eol_tx, SONIC_TD_LINK, ~SONIC_EOL & + sonic_tda_get(dev, lp->eol_tx, SONIC_TD_LINK)); + + netif_dbg(lp, tx_queued, dev, "%s: issuing Tx command\n", __func__); + + SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + lp->tx_len[entry] = length; lp->tx_laddr[entry] = laddr; lp->tx_skb[entry] = skb; - wmb(); - sonic_tda_put(dev, lp->eol_tx, SONIC_TD_LINK, - sonic_tda_get(dev, lp->eol_tx, SONIC_TD_LINK) & ~SONIC_EOL); lp->eol_tx = entry; - lp->next_tx = (entry + 1) & SONIC_TDS_MASK; - if (lp->tx_skb[lp->next_tx] != NULL) { + entry = (entry + 1) & SONIC_TDS_MASK; + if (lp->tx_skb[entry]) { /* The ring is full, the ISR has yet to process the next TD. */ netif_dbg(lp, tx_queued, dev, "%s: stopping queue\n", __func__); netif_stop_queue(dev); /* after this packet, wait for ISR to free up some TDAs */ - } else netif_start_queue(dev); - - netif_dbg(lp, tx_queued, dev, "%s: issuing Tx command\n", __func__); - - SONIC_WRITE(SONIC_CMD, SONIC_CR_TXP); + } spin_unlock_irqrestore(&lp->lock, flags); @@ -594,11 +629,6 @@ static void sonic_rx(struct net_device *dev) if (rbe) SONIC_WRITE(SONIC_ISR, SONIC_INT_RBE); - /* - * If any worth-while packets have been received, netif_rx() - * has done a mark_bh(NET_BH) for us and will work on them - * when we get to the bottom-half routine. - */ } @@ -780,7 +810,7 @@ static int sonic_init(struct net_device *dev) SONIC_WRITE(SONIC_UTDA, lp->tda_laddr >> 16); SONIC_WRITE(SONIC_CTDA, lp->tda_laddr & 0xffff); - lp->cur_tx = lp->next_tx = 0; + lp->cur_tx = 0; lp->eol_tx = SONIC_NUM_TDS - 1; /* diff --git a/drivers/net/ethernet/natsemi/sonic.h b/drivers/net/ethernet/natsemi/sonic.h index e0e4cba6f6f6..3cbb62c860c8 100644 --- a/drivers/net/ethernet/natsemi/sonic.h +++ b/drivers/net/ethernet/natsemi/sonic.h @@ -321,7 +321,6 @@ struct sonic_local { unsigned int cur_tx; /* first unacked transmit packet */ unsigned int eol_rx; unsigned int eol_tx; /* last unacked transmit packet */ - unsigned int next_tx; /* next free TD */ int msg_enable; struct device *device; /* generic device */ struct net_device_stats stats; @@ -342,6 +341,7 @@ static void sonic_multicast_list(struct net_device *dev); static int sonic_init(struct net_device *dev); static void sonic_tx_timeout(struct net_device *dev, unsigned int txqueue); static void sonic_msg_init(struct net_device *dev); +static int sonic_alloc_descriptors(struct net_device *dev); /* Internal inlines for reading/writing DMA buffers. Note that bus size and endianness matter here, whereas they don't for registers, diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c index e1b886e87a76..dda9ec7d9cee 100644 --- a/drivers/net/ethernet/natsemi/xtsonic.c +++ b/drivers/net/ethernet/natsemi/xtsonic.c @@ -167,47 +167,11 @@ static int __init sonic_probe1(struct net_device *dev) dev->dev_addr[i*2+1] = val >> 8; } - /* Initialize the device structure. */ - lp->dma_bitmode = SONIC_BITMODE32; - /* - * Allocate local private descriptor areas in uncached space. - * The entire structure must be located within the same 64kb segment. - * A simple way to ensure this is to allocate twice the - * size of the structure -- given that the structure is - * much less than 64 kB, at least one of the halves of - * the allocated area will be contained entirely in 64 kB. - * We also allocate extra space for a pointer to allow freeing - * this structure later on (in xtsonic_cleanup_module()). - */ - lp->descriptors = dma_alloc_coherent(lp->device, - SIZEOF_SONIC_DESC * - SONIC_BUS_SCALE(lp->dma_bitmode), - &lp->descriptors_laddr, - GFP_KERNEL); - if (lp->descriptors == NULL) { - err = -ENOMEM; + err = sonic_alloc_descriptors(dev); + if (err) goto out; - } - - lp->cda = lp->descriptors; - lp->tda = lp->cda + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda = lp->tda + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra = lp->rda + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - - /* get the virtual dma address */ - - lp->cda_laddr = lp->descriptors_laddr; - lp->tda_laddr = lp->cda_laddr + (SIZEOF_SONIC_CDA - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rda_laddr = lp->tda_laddr + (SIZEOF_SONIC_TD * SONIC_NUM_TDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); - lp->rra_laddr = lp->rda_laddr + (SIZEOF_SONIC_RD * SONIC_NUM_RDS - * SONIC_BUS_SCALE(lp->dma_bitmode)); dev->netdev_ops = &xtsonic_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h index a83a0ad5e27d..4268a7e0f344 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h @@ -104,14 +104,14 @@ struct cmsg_req_map_op { __be32 tid; __be32 count; __be32 flags; - u8 data[0]; + u8 data[]; }; struct cmsg_reply_map_op { struct cmsg_reply_map_simple reply_hdr; __be32 count; __be32 resv; - u8 data[0]; + u8 data[]; }; struct cmsg_bpf_event { @@ -120,6 +120,6 @@ struct cmsg_bpf_event { __be64 map_ptr; __be32 data_size; __be32 pkt_size; - u8 data[0]; + u8 data[]; }; #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 9b50d76bbc09..bf516285510f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -587,7 +587,7 @@ struct nfp_flower_cmsg_mac_repr { u8 info; u8 nbi_port; u8 phys_port; - } ports[0]; + } ports[]; }; #define NFP_FLOWER_CMSG_MAC_REPR_NBI GENMASK(1, 0) @@ -619,7 +619,7 @@ struct nfp_flower_cmsg_merge_hint { struct { __be32 host_ctx; __be64 host_cookie; - } __packed flow[0]; + } __packed flow[]; }; enum nfp_flower_cmsg_port_type { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index 5d5812fd9317..fa6b13a05941 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -42,7 +42,7 @@ struct nfp_shared_buf; */ struct nfp_dumpspec { u32 size; - u8 data[0]; + u8 data[]; }; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index 769ceef09756..a614df095b08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -36,7 +36,7 @@ enum nfp_dumpspec_type { struct nfp_dump_tl { __be32 type; __be32 length; /* chunk length to follow, aligned to 8 bytes */ - char data[0]; + char data[]; }; /* NFP CPP parameters */ @@ -62,7 +62,7 @@ struct nfp_dumpspec_csr { struct nfp_dumpspec_rtsym { struct nfp_dump_tl tl; - char rtsym[0]; + char rtsym[]; }; /* header for register dumpable */ @@ -79,7 +79,7 @@ struct nfp_dump_rtsym { struct nfp_dump_common_cpp cpp; __be32 error; /* error code encountered while reading */ u8 padded_name_length; /* pad so data starts at 8 byte boundary */ - char rtsym[0]; + char rtsym[]; /* after padded_name_length, there is dump_length data */ }; @@ -92,7 +92,7 @@ struct nfp_dump_error { struct nfp_dump_tl tl; __be32 error; char padding[4]; - char spec[0]; + char spec[]; }; /* to track state through debug size calculation TLV traversal */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h index e0f13dfe1f39..48a74accbbd3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h @@ -18,7 +18,7 @@ struct nfp_port; */ struct nfp_reprs { unsigned int num_reprs; - struct net_device __rcu *reprs[0]; + struct net_device __rcu *reprs[]; }; /** diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index 1531c1870020..f5360bae6f75 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -183,7 +183,7 @@ struct nfp_eth_table { bool is_split; unsigned int fec_modes_supported; - } ports[0]; + } ports[]; }; struct nfp_eth_table *nfp_eth_read_ports(struct nfp_cpp *cpp); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index e452f4242ba0..020acc300d7e 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -632,10 +632,7 @@ static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); } else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) { - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); } return 0; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h index 3dce769d83a1..86153660d245 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h @@ -1316,7 +1316,7 @@ struct netxen_minidump_template_hdr { u32 driver_info_word4; u32 saved_state_array[NX_DUMP_STATE_ARRAY_LEN]; u32 capture_size_array[NX_DUMP_CAP_SIZE_ARRAY_LEN]; - u32 rsvd[0]; + u32 rsvd[]; }; /* Common Entry Header: Common to All Entry Types */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 374a4d4371f9..134611aa2c9a 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -418,7 +418,7 @@ struct qlcnic_83xx_dump_template_hdr { u32 saved_state[16]; u32 cap_sizes[8]; u32 ocm_wnd_reg[16]; - u32 rsvd[0]; + u32 rsvd[]; }; struct qlcnic_82xx_dump_template_hdr { @@ -436,7 +436,7 @@ struct qlcnic_82xx_dump_template_hdr { u32 cap_sizes[8]; u32 rsvd[7]; u32 capabilities; - u32 rsvd1[0]; + u32 rsvd1[]; }; #define QLC_PEX_DMA_READ_SIZE (PAGE_SIZE * 16) @@ -740,7 +740,7 @@ struct qlcnic_hostrq_rx_ctx { The following is packed: - N hostrq_rds_rings - N hostrq_sds_rings */ - char data[0]; + char data[]; } __packed; struct qlcnic_cardrsp_rds_ring{ @@ -769,7 +769,7 @@ struct qlcnic_cardrsp_rx_ctx { The following is packed: - N cardrsp_rds_rings - N cardrs_sds_rings */ - char data[0]; + char data[]; } __packed; #define SIZEOF_HOSTRQ_RX(HOSTRQ_RX, rds_rings, sds_rings) \ diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index bebe38d74d66..251d4ac4af02 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1288,11 +1288,8 @@ static int emac_tso_csum(struct emac_adapter *adpt, memset(tpd, 0, sizeof(*tpd)); memset(&extra_tpd, 0, sizeof(extra_tpd)); - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); + TPD_PKT_LEN_SET(&extra_tpd, skb->len); TPD_LSO_SET(&extra_tpd, 1); TPD_LSOV_SET(&extra_tpd, 1); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a2168a14794c..f081007a245b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -212,7 +212,6 @@ enum rtl_registers { /* Unlimited maximum PCI burst. */ #define RX_DMA_BURST (7 << RXCFG_DMA_SHIFT) - RxMissed = 0x4c, Cfg9346 = 0x50, Config0 = 0x51, Config1 = 0x52, @@ -576,6 +575,7 @@ struct rtl8169_tc_offsets { __le64 tx_errors; __le32 tx_multi_collision; __le16 tx_aborted; + __le16 rx_missed; }; enum rtl_flag { @@ -689,6 +689,12 @@ static void rtl_unlock_config_regs(struct rtl8169_private *tp) RTL_W8(tp, Cfg9346, Cfg9346_Unlock); } +static void rtl_pci_commit(struct rtl8169_private *tp) +{ + /* Read an arbitrary register to commit a preceding PCI write */ + RTL_R8(tp, ChipCmd); +} + static bool rtl_is_8125(struct rtl8169_private *tp) { return tp->mac_version >= RTL_GIGA_MAC_VER_60; @@ -1302,10 +1308,6 @@ static void rtl_irq_disable(struct rtl8169_private *tp) tp->irq_enabled = 0; } -#define RTL_EVENT_NAPI_RX (RxOK | RxErr) -#define RTL_EVENT_NAPI_TX (TxOK | TxErr) -#define RTL_EVENT_NAPI (RTL_EVENT_NAPI_RX | RTL_EVENT_NAPI_TX) - static void rtl_irq_enable(struct rtl8169_private *tp) { tp->irq_enabled = 1; @@ -1319,18 +1321,13 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp) { rtl_irq_disable(tp); rtl_ack_events(tp, 0xffffffff); - /* PCI commit */ - RTL_R8(tp, ChipCmd); + rtl_pci_commit(tp); } static void rtl_link_chg_patch(struct rtl8169_private *tp) { - struct net_device *dev = tp->dev; struct phy_device *phydev = tp->phydev; - if (!netif_running(dev)) - return; - if (tp->mac_version == RTL_GIGA_MAC_VER_34 || tp->mac_version == RTL_GIGA_MAC_VER_38) { if (phydev->speed == SPEED_1000) { @@ -1536,7 +1533,7 @@ static int rtl8169_set_features(struct net_device *dev, } RTL_W16(tp, CPlusCmd, tp->cp_cmd); - RTL_R16(tp, CPlusCmd); + rtl_pci_commit(tp); rtl_unlock_work(tp); @@ -1622,7 +1619,7 @@ static bool rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd) u32 cmd; RTL_W32(tp, CounterAddrHigh, (u64)paddr >> 32); - RTL_R32(tp, CounterAddrHigh); + rtl_pci_commit(tp); cmd = (u64)paddr & DMA_BIT_MASK(32); RTL_W32(tp, CounterAddrLow, cmd); RTL_W32(tp, CounterAddrLow, cmd | counter_cmd); @@ -1689,6 +1686,7 @@ static bool rtl8169_init_counter_offsets(struct rtl8169_private *tp) tp->tc_offset.tx_errors = counters->tx_errors; tp->tc_offset.tx_multi_collision = counters->tx_multi_collision; tp->tc_offset.tx_aborted = counters->tx_aborted; + tp->tc_offset.rx_missed = counters->rx_missed; tp->tc_offset.inited = true; return ret; @@ -1946,7 +1944,7 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) tp->cp_cmd = (tp->cp_cmd & ~INTT_MASK) | cp01; RTL_W16(tp, CPlusCmd, tp->cp_cmd); - RTL_R16(tp, CPlusCmd); + rtl_pci_commit(tp); rtl_unlock_work(tp); @@ -2044,7 +2042,7 @@ static void rtl_enable_eee(struct rtl8169_private *tp) phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv); } -static void rtl8169_get_mac_version(struct rtl8169_private *tp) +static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { /* * The driver currently handles the 8168Bf and the 8168Be identically @@ -2060,7 +2058,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp) static const struct rtl_mac_info { u16 mask; u16 val; - u16 mac_version; + enum mac_version ver; } mac_info[] = { /* 8125 family. */ { 0x7cf, 0x608, RTL_GIGA_MAC_VER_60 }, @@ -2147,22 +2145,22 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp) { 0x000, 0x000, RTL_GIGA_MAC_NONE } }; const struct rtl_mac_info *p = mac_info; - u16 reg = RTL_R32(tp, TxConfig) >> 20; + enum mac_version ver; - while ((reg & p->mask) != p->val) + while ((xid & p->mask) != p->val) p++; - tp->mac_version = p->mac_version; - - if (tp->mac_version == RTL_GIGA_MAC_NONE) { - dev_err(tp_to_dev(tp), "unknown chip XID %03x\n", reg & 0xfcf); - } else if (!tp->supports_gmii) { - if (tp->mac_version == RTL_GIGA_MAC_VER_42) - tp->mac_version = RTL_GIGA_MAC_VER_43; - else if (tp->mac_version == RTL_GIGA_MAC_VER_45) - tp->mac_version = RTL_GIGA_MAC_VER_47; - else if (tp->mac_version == RTL_GIGA_MAC_VER_46) - tp->mac_version = RTL_GIGA_MAC_VER_48; + ver = p->ver; + + if (ver != RTL_GIGA_MAC_NONE && !gmii) { + if (ver == RTL_GIGA_MAC_VER_42) + ver = RTL_GIGA_MAC_VER_43; + else if (ver == RTL_GIGA_MAC_VER_45) + ver = RTL_GIGA_MAC_VER_47; + else if (ver == RTL_GIGA_MAC_VER_46) + ver = RTL_GIGA_MAC_VER_48; } + + return ver; } static void rtl_release_firmware(struct rtl8169_private *tp) @@ -2264,10 +2262,10 @@ static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr) rtl_unlock_config_regs(tp); RTL_W32(tp, MAC4, addr[4] | addr[5] << 8); - RTL_R32(tp, MAC4); + rtl_pci_commit(tp); RTL_W32(tp, MAC0, addr[0] | addr[1] << 8 | addr[2] << 16 | addr[3] << 24); - RTL_R32(tp, MAC0); + rtl_pci_commit(tp); if (tp->mac_version == RTL_GIGA_MAC_VER_34) rtl_rar_exgmac_set(tp, addr); @@ -2471,66 +2469,52 @@ static void r8168b_1_hw_jumbo_disable(struct rtl8169_private *tp) RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~(1 << 0)); } -static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) +static void rtl_jumbo_config(struct rtl8169_private *tp) { - rtl_unlock_config_regs(tp); - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - pcie_set_readrq(tp->pci_dev, 512); - r8168b_1_hw_jumbo_enable(tp); - break; - case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26: - pcie_set_readrq(tp->pci_dev, 512); - r8168c_hw_jumbo_enable(tp); - break; - case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: - r8168dp_hw_jumbo_enable(tp); - break; - case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: - pcie_set_readrq(tp->pci_dev, 512); - r8168e_hw_jumbo_enable(tp); - break; - default: - break; - } - rtl_lock_config_regs(tp); -} + bool jumbo = tp->dev->mtu > ETH_DATA_LEN; -static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) -{ rtl_unlock_config_regs(tp); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_12: case RTL_GIGA_MAC_VER_17: - r8168b_1_hw_jumbo_disable(tp); + if (jumbo) { + pcie_set_readrq(tp->pci_dev, 512); + r8168b_1_hw_jumbo_enable(tp); + } else { + r8168b_1_hw_jumbo_disable(tp); + } break; case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_26: - r8168c_hw_jumbo_disable(tp); + if (jumbo) { + pcie_set_readrq(tp->pci_dev, 512); + r8168c_hw_jumbo_enable(tp); + } else { + r8168c_hw_jumbo_disable(tp); + } break; case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: - r8168dp_hw_jumbo_disable(tp); + if (jumbo) + r8168dp_hw_jumbo_enable(tp); + else + r8168dp_hw_jumbo_disable(tp); break; case RTL_GIGA_MAC_VER_31 ... RTL_GIGA_MAC_VER_33: - r8168e_hw_jumbo_disable(tp); + if (jumbo) { + pcie_set_readrq(tp->pci_dev, 512); + r8168e_hw_jumbo_enable(tp); + } else { + r8168e_hw_jumbo_disable(tp); + } break; default: break; } rtl_lock_config_regs(tp); - if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii) + if (!jumbo && pci_is_pcie(tp->pci_dev) && tp->supports_gmii) pcie_set_readrq(tp->pci_dev, 4096); } -static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu) -{ - if (mtu > ETH_DATA_LEN) - rtl_hw_jumbo_enable(tp); - else - rtl_hw_jumbo_disable(tp); -} - DECLARE_RTL_COND(rtl_chipcmd_cond) { return RTL_R8(tp, ChipCmd) & CmdReset; @@ -3838,9 +3822,6 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp) static void rtl_hw_start_8169(struct rtl8169_private *tp) { - if (tp->mac_version == RTL_GIGA_MAC_VER_05) - pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08); - RTL_W8(tp, EarlyTxThres, NoEarlyTx); tp->cp_cmd |= PCIMulRW; @@ -3853,8 +3834,6 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp) rtl8169_set_magic_reg(tp, tp->mac_version); - RTL_W32(tp, RxMissed, 0); - /* disable interrupt coalescing */ RTL_W16(tp, IntrMitigate, 0x0000); } @@ -3877,10 +3856,11 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_tx_desc_registers(tp); rtl_lock_config_regs(tp); - rtl_jumbo_config(tp, tp->dev->mtu); + rtl_jumbo_config(tp); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ - RTL_R16(tp, CPlusCmd); + rtl_pci_commit(tp); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); rtl_set_tx_config_registers(tp); @@ -3892,10 +3872,9 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) { struct rtl8169_private *tp = netdev_priv(dev); - rtl_jumbo_config(tp, new_mtu); - dev->mtu = new_mtu; netdev_update_features(dev); + rtl_jumbo_config(tp); return 0; } @@ -4108,12 +4087,10 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb, tp->tx_skb[entry].len = len; } - if (cur_frag) { - tp->tx_skb[entry].skb = skb; - txd->opts1 |= cpu_to_le32(LastFrag); - } + tp->tx_skb[entry].skb = skb; + txd->opts1 |= cpu_to_le32(LastFrag); - return cur_frag; + return 0; err_out: rtl8169_tx_clear_range(tp, tp->cur_tx + 1, cur_frag); @@ -4125,29 +4102,6 @@ static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb) return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34; } -/* msdn_giant_send_check() - * According to the document of microsoft, the TCP Pseudo Header excludes the - * packet length for IPv6 TCP large packets. - */ -static int msdn_giant_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct tcphdr *th; - int ret; - - ret = skb_cow_head(skb, 0); - if (ret) - return ret; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0); - - return ret; -} - static void rtl8169_tso_csum_v1(struct sk_buff *skb, u32 *opts) { u32 mss = skb_shinfo(skb)->gso_size; @@ -4180,9 +4134,10 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, break; case htons(ETH_P_IPV6): - if (msdn_giant_send_check(skb)) + if (skb_cow_head(skb, 0)) return false; + tcp_v6_gso_csum_prep(skb); opts[0] |= TD1_GTSENV6; break; @@ -4260,6 +4215,7 @@ static void rtl8169_doorbell(struct rtl8169_private *tp) static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev) { + unsigned int frags = skb_shinfo(skb)->nr_frags; struct rtl8169_private *tp = netdev_priv(dev); unsigned int entry = tp->cur_tx % NUM_TX_DESC; struct TxDesc *txd = tp->TxDescArray + entry; @@ -4268,9 +4224,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, u32 opts[2], len; bool stop_queue; bool door_bell; - int frags; - if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { + if (unlikely(!rtl_tx_slots_avail(tp, frags))) { netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n"); goto err_stop_0; } @@ -4299,14 +4254,13 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->tx_skb[entry].len = len; txd->addr = cpu_to_le64(mapping); - frags = rtl8169_xmit_frags(tp, skb, opts); - if (frags < 0) - goto err_dma_1; - else if (frags) - opts[0] |= FirstFrag; - else { + if (!frags) { opts[0] |= FirstFrag | LastFrag; tp->tx_skb[entry].skb = skb; + } else { + if (rtl8169_xmit_frags(tp, skb, opts)) + goto err_dma_1; + opts[0] |= FirstFrag; } txd->opts2 = cpu_to_le32(opts[1]); @@ -4697,17 +4651,6 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) return work_done; } -static void rtl8169_rx_missed(struct net_device *dev) -{ - struct rtl8169_private *tp = netdev_priv(dev); - - if (tp->mac_version > RTL_GIGA_MAC_VER_06) - return; - - dev->stats.rx_missed_errors += RTL_R32(tp, RxMissed) & 0xffffff; - RTL_W32(tp, RxMissed, 0); -} - static void r8169_phylink_handler(struct net_device *ndev) { struct rtl8169_private *tp = netdev_priv(ndev); @@ -4757,12 +4700,6 @@ static void rtl8169_down(struct net_device *dev) netif_stop_queue(dev); rtl8169_hw_reset(tp); - /* - * At this point device interrupts can not be enabled in any function, - * as netif_running is not true (rtl8169_interrupt, rtl8169_reset_task) - * and napi is disabled (rtl8169_poll). - */ - rtl8169_rx_missed(dev); /* Give a racing hard_start_xmit a few cycles to complete. */ synchronize_rcu(); @@ -4907,9 +4844,6 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) pm_runtime_get_noresume(&pdev->dev); - if (netif_running(dev) && pm_runtime_active(&pdev->dev)) - rtl8169_rx_missed(dev); - do { start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp); stats->rx_packets = tp->rx_stats.packets; @@ -4928,7 +4862,6 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_errors = dev->stats.rx_errors; stats->rx_crc_errors = dev->stats.rx_crc_errors; stats->rx_fifo_errors = dev->stats.rx_fifo_errors; - stats->rx_missed_errors = dev->stats.rx_missed_errors; stats->multicast = dev->stats.multicast; /* @@ -4948,6 +4881,8 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) le32_to_cpu(tp->tc_offset.tx_multi_collision); stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted) - le16_to_cpu(tp->tc_offset.tx_aborted); + stats->rx_missed_errors = le16_to_cpu(counters->rx_missed) - + le16_to_cpu(tp->tc_offset.rx_missed); pm_runtime_put_noidle(&pdev->dev); } @@ -5033,7 +4968,6 @@ static int rtl8169_runtime_suspend(struct device *device) rtl8169_net_suspend(dev); /* Update counters before going runtime suspend */ - rtl8169_rx_missed(dev); rtl8169_update_counters(tp); return 0; @@ -5098,8 +5032,7 @@ static void rtl_wol_shutdown_quirk(struct rtl8169_private *tp) pci_clear_master(tp->pci_dev); RTL_W8(tp, ChipCmd, CmdRxEnb); - /* PCI commit */ - RTL_R8(tp, ChipCmd); + rtl_pci_commit(tp); break; default: break; @@ -5173,7 +5106,7 @@ static const struct net_device_ops rtl_netdev_ops = { static void rtl_set_irq_mask(struct rtl8169_private *tp) { - tp->irq_mask = RTL_EVENT_NAPI | LinkChg; + tp->irq_mask = RxOK | RxErr | TxOK | TxErr | LinkChg; if (tp->mac_version <= RTL_GIGA_MAC_VER_06) tp->irq_mask |= SYSErr | RxOverflow | RxFIFOOver; @@ -5442,9 +5375,10 @@ done: static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; + int jumbo_max, region, rc; + enum mac_version chipset; struct net_device *dev; - int chipset, region; - int jumbo_max, rc; + u16 xid; /* Some tools for creating an initramfs don't consider softdeps, then * r8169.ko may be in initramfs, but realtek.ko not. Then the generic @@ -5511,10 +5445,16 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->mmio_addr = pcim_iomap_table(pdev)[region]; + xid = (RTL_R32(tp, TxConfig) >> 20) & 0xfcf; + /* Identify chip attached to board */ - rtl8169_get_mac_version(tp); - if (tp->mac_version == RTL_GIGA_MAC_NONE) + chipset = rtl8169_get_mac_version(xid, tp->supports_gmii); + if (chipset == RTL_GIGA_MAC_NONE) { + dev_err(&pdev->dev, "unknown chip XID %03x\n", xid); return -ENODEV; + } + + tp->mac_version = chipset; tp->cp_cmd = RTL_R16(tp, CPlusCmd); @@ -5532,8 +5472,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - chipset = tp->mac_version; - rc = rtl_alloc_irq(tp); if (rc < 0) { dev_err(&pdev->dev, "Can't allocate interrupt\n"); @@ -5551,9 +5489,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT); - dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | - NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; @@ -5575,7 +5510,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rtl_chip_supports_csum_v2(tp)) { dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; - dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; dev->gso_max_size = RTL_GSO_MAX_SIZE_V2; dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2; } else { @@ -5590,9 +5524,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->mac_version == RTL_GIGA_MAC_VER_22) { dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); - dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); } + dev->features |= dev->hw_features; + dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; @@ -5624,8 +5559,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_mdio_unregister; netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n", - rtl_chip_infos[chipset].name, dev->dev_addr, - (RTL_R32(tp, TxConfig) >> 20) & 0xfcf, + rtl_chip_infos[chipset].name, dev->dev_addr, xid, pci_irq_vector(pdev, 0)); if (jumbo_max) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 58ca126518a2..8ed73f44405d 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -142,69 +142,6 @@ static const u16 sh_eth_offset_gigabit[SH_ETH_MAX_REGISTER_OFFSET] = { [FWALCR1] = 0x00b4, }; -static const u16 sh_eth_offset_fast_rz[SH_ETH_MAX_REGISTER_OFFSET] = { - SH_ETH_OFFSET_DEFAULTS, - - [EDSR] = 0x0000, - [EDMR] = 0x0400, - [EDTRR] = 0x0408, - [EDRRR] = 0x0410, - [EESR] = 0x0428, - [EESIPR] = 0x0430, - [TDLAR] = 0x0010, - [TDFAR] = 0x0014, - [TDFXR] = 0x0018, - [TDFFR] = 0x001c, - [RDLAR] = 0x0030, - [RDFAR] = 0x0034, - [RDFXR] = 0x0038, - [RDFFR] = 0x003c, - [TRSCER] = 0x0438, - [RMFCR] = 0x0440, - [TFTR] = 0x0448, - [FDR] = 0x0450, - [RMCR] = 0x0458, - [RPADIR] = 0x0460, - [FCFTR] = 0x0468, - [CSMR] = 0x04E4, - - [ECMR] = 0x0500, - [RFLR] = 0x0508, - [ECSR] = 0x0510, - [ECSIPR] = 0x0518, - [PIR] = 0x0520, - [APR] = 0x0554, - [MPR] = 0x0558, - [PFTCR] = 0x055c, - [PFRCR] = 0x0560, - [TPAUSER] = 0x0564, - [MAHR] = 0x05c0, - [MALR] = 0x05c8, - [CEFCR] = 0x0740, - [FRECR] = 0x0748, - [TSFRCR] = 0x0750, - [TLFRCR] = 0x0758, - [RFCR] = 0x0760, - [MAFCR] = 0x0778, - - [ARSTR] = 0x0000, - [TSU_CTRST] = 0x0004, - [TSU_FWSLC] = 0x0038, - [TSU_VTAG0] = 0x0058, - [TSU_ADSBSY] = 0x0060, - [TSU_TEN] = 0x0064, - [TSU_POST1] = 0x0070, - [TSU_POST2] = 0x0074, - [TSU_POST3] = 0x0078, - [TSU_POST4] = 0x007c, - [TSU_ADRH0] = 0x0100, - - [TXNLCR0] = 0x0080, - [TXALCR0] = 0x0084, - [RXNLCR0] = 0x0088, - [RXALCR0] = 0x008C, -}; - static const u16 sh_eth_offset_fast_rcar[SH_ETH_MAX_REGISTER_OFFSET] = { SH_ETH_OFFSET_DEFAULTS, @@ -569,6 +506,9 @@ static void sh_eth_set_rate_gether(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); + if (WARN_ON(!mdp->cd->gecmr)) + return; + switch (mdp->speed) { case 10: /* 10BASE */ sh_eth_write(ndev, GECMR_10, GECMR); @@ -590,7 +530,7 @@ static struct sh_eth_cpu_data r7s72100_data = { .chip_reset = sh_eth_chip_reset, .set_duplex = sh_eth_set_duplex, - .register_type = SH_ETH_REG_FAST_RZ, + .register_type = SH_ETH_REG_GIGABIT, .edtrr_trns = EDTRR_TRNS_GETHER, .ecsr_value = ECSR_ICD, @@ -663,6 +603,7 @@ static struct sh_eth_cpu_data r8a7740_data = { .apr = 1, .mpr = 1, .tpauser = 1, + .gecmr = 1, .bculr = 1, .hw_swap = 1, .rpadir = 1, @@ -788,6 +729,7 @@ static struct sh_eth_cpu_data r8a77980_data = { .apr = 1, .mpr = 1, .tpauser = 1, + .gecmr = 1, .bculr = 1, .hw_swap = 1, .nbst = 1, @@ -957,6 +899,9 @@ static void sh_eth_set_rate_giga(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); + if (WARN_ON(!mdp->cd->gecmr)) + return; + switch (mdp->speed) { case 10: /* 10BASE */ sh_eth_write(ndev, 0x00000000, GECMR); @@ -1002,6 +947,7 @@ static struct sh_eth_cpu_data sh7757_data_giga = { .apr = 1, .mpr = 1, .tpauser = 1, + .gecmr = 1, .bculr = 1, .hw_swap = 1, .rpadir = 1, @@ -1042,6 +988,7 @@ static struct sh_eth_cpu_data sh7734_data = { .apr = 1, .mpr = 1, .tpauser = 1, + .gecmr = 1, .bculr = 1, .hw_swap = 1, .no_trimd = 1, @@ -1083,6 +1030,7 @@ static struct sh_eth_cpu_data sh7763_data = { .apr = 1, .mpr = 1, .tpauser = 1, + .gecmr = 1, .bculr = 1, .hw_swap = 1, .no_trimd = 1, @@ -2140,11 +2088,13 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_reg(EESR); add_reg(EESIPR); add_reg(TDLAR); - add_reg(TDFAR); + if (!cd->no_xdfar) + add_reg(TDFAR); add_reg(TDFXR); add_reg(TDFFR); add_reg(RDLAR); - add_reg(RDFAR); + if (!cd->no_xdfar) + add_reg(RDFAR); add_reg(RDFXR); add_reg(RDFFR); add_reg(TRSCER); @@ -2179,21 +2129,26 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) if (cd->tpauser) add_reg(TPAUSER); add_reg(TPAUSECR); - add_reg(GECMR); + if (cd->gecmr) + add_reg(GECMR); if (cd->bculr) add_reg(BCULR); add_reg(MAHR); add_reg(MALR); - add_reg(TROCR); - add_reg(CDCR); - add_reg(LCCR); - add_reg(CNDCR); + if (!cd->no_tx_cntrs) { + add_reg(TROCR); + add_reg(CDCR); + add_reg(LCCR); + add_reg(CNDCR); + } add_reg(CEFCR); add_reg(FRECR); add_reg(TSFRCR); add_reg(TLFRCR); - add_reg(CERCR); - add_reg(CEECR); + if (cd->cexcr) { + add_reg(CERCR); + add_reg(CEECR); + } add_reg(MAFCR); if (cd->rtrate) add_reg(RTRATE); @@ -3121,9 +3076,6 @@ static const u16 *sh_eth_get_register_offset(int register_type) case SH_ETH_REG_GIGABIT: reg_offset = sh_eth_offset_gigabit; break; - case SH_ETH_REG_FAST_RZ: - reg_offset = sh_eth_offset_fast_rz; - break; case SH_ETH_REG_FAST_RCAR: reg_offset = sh_eth_offset_fast_rcar; break; diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 850726301e1c..c1b3751b12c4 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -145,7 +145,6 @@ enum { enum { SH_ETH_REG_GIGABIT, - SH_ETH_REG_FAST_RZ, SH_ETH_REG_FAST_RCAR, SH_ETH_REG_FAST_SH4, SH_ETH_REG_FAST_SH3_SH2 @@ -490,6 +489,7 @@ struct sh_eth_cpu_data { unsigned apr:1; /* EtherC has APR */ unsigned mpr:1; /* EtherC has MPR */ unsigned tpauser:1; /* EtherC has TPAUSER */ + unsigned gecmr:1; /* EtherC has GECMR */ unsigned bculr:1; /* EtherC has BCULR */ unsigned tsu:1; /* EtherC has TSU */ unsigned hw_swap:1; /* E-DMAC has DE bit in EDMR */ diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 4481f21a1f43..256807c28ff7 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -113,7 +113,6 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value"); * *************************************************************************/ -static const struct efx_channel_type efx_default_channel_type; static void efx_remove_port(struct efx_nic *efx); static int efx_xdp_setup_prog(struct efx_nic *efx, struct bpf_prog *prog); static int efx_xdp(struct net_device *dev, struct netdev_bpf *xdp); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index f1bdb04efbe4..da54afaa3c44 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -150,24 +150,6 @@ static inline s32 efx_filter_get_rx_ids(struct efx_nic *efx, int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); bool __efx_filter_rfs_expire(struct efx_channel *channel, unsigned int quota); -static inline void efx_filter_rfs_expire(struct work_struct *data) -{ - struct delayed_work *dwork = to_delayed_work(data); - struct efx_channel *channel; - unsigned int time, quota; - - channel = container_of(dwork, struct efx_channel, filter_work); - time = jiffies - channel->rfs_last_expiry; - quota = channel->rfs_filter_count * time / (30 * HZ); - if (quota > 20 && __efx_filter_rfs_expire(channel, min(channel->rfs_filter_count, quota))) - channel->rfs_last_expiry += time; - /* Ensure we do more work eventually even if NAPI poll is not happening */ - schedule_delayed_work(dwork, 30 * HZ); -} -#define efx_filter_rfs_enabled() 1 -#else -static inline void efx_filter_rfs_expire(struct work_struct *data) {} -#define efx_filter_rfs_enabled() 0 #endif /* RSS contexts */ diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index aeb5e8aa2f2a..d2d738314c50 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -485,6 +485,23 @@ void efx_remove_eventq(struct efx_channel *channel) * *************************************************************************/ +#ifdef CONFIG_RFS_ACCEL +static void efx_filter_rfs_expire(struct work_struct *data) +{ + struct delayed_work *dwork = to_delayed_work(data); + struct efx_channel *channel; + unsigned int time, quota; + + channel = container_of(dwork, struct efx_channel, filter_work); + time = jiffies - channel->rfs_last_expiry; + quota = channel->rfs_filter_count * time / (30 * HZ); + if (quota >= 20 && __efx_filter_rfs_expire(channel, min(channel->rfs_filter_count, quota))) + channel->rfs_last_expiry += time; + /* Ensure we do more work eventually even if NAPI poll is not happening */ + schedule_delayed_work(dwork, 30 * HZ); +} +#endif + /* Allocate and initialise a channel structure. */ struct efx_channel * efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel) @@ -1166,6 +1183,9 @@ static int efx_poll(struct napi_struct *napi, int budget) struct efx_channel *channel = container_of(napi, struct efx_channel, napi_str); struct efx_nic *efx = channel->efx; +#ifdef CONFIG_RFS_ACCEL + unsigned int time; +#endif int spent; netif_vdbg(efx, intr, efx->net_dev, @@ -1185,7 +1205,10 @@ static int efx_poll(struct napi_struct *napi, int budget) #ifdef CONFIG_RFS_ACCEL /* Perhaps expire some ARFS filters */ - mod_delayed_work(system_wq, &channel->filter_work, 0); + time = jiffies - channel->rfs_last_expiry; + /* Would our quota be >= 20? */ + if (channel->rfs_filter_count * time >= 600 * HZ) + mod_delayed_work(system_wq, &channel->filter_work, 0); #endif /* There is no race here; although napi_disable() will diff --git a/drivers/net/ethernet/sfc/falcon/net_driver.h b/drivers/net/ethernet/sfc/falcon/net_driver.h index a49ea2e719b6..a529ff395ead 100644 --- a/drivers/net/ethernet/sfc/falcon/net_driver.h +++ b/drivers/net/ethernet/sfc/falcon/net_driver.h @@ -288,7 +288,7 @@ struct ef4_rx_buffer { struct ef4_rx_page_state { dma_addr_t dma_addr; - unsigned int __pad[0] ____cacheline_aligned; + unsigned int __pad[] ____cacheline_aligned; }; /** diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 9f9886f222c8..392bd5b7017e 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -336,7 +336,7 @@ struct efx_rx_buffer { struct efx_rx_page_state { dma_addr_t dma_addr; - unsigned int __pad[0] ____cacheline_aligned; + unsigned int __pad[] ____cacheline_aligned; }; /** diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 04d7f41d7ed9..696a77c20cb7 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -287,9 +287,8 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue, return PTR_ERR(segments); dev_consume_skb_any(skb); - skb = segments; - skb_list_walk_safe(skb, skb, next) { + skb_list_walk_safe(segments, skb, next) { skb_mark_not_on_list(skb); efx_enqueue_skb(tx_queue, skb); } diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index e8224b543dfc..58b9b7ce7195 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -896,9 +896,9 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog, case XDP_TX: ret = netsec_xdp_xmit_back(priv, xdp); if (ret != NETSEC_XDP_TX) - __page_pool_put_page(dring->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(dring->page_pool, + virt_to_head_page(xdp->data), len, + true); break; case XDP_REDIRECT: err = xdp_do_redirect(priv->ndev, xdp, prog); @@ -906,9 +906,9 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog, ret = NETSEC_XDP_REDIR; } else { ret = NETSEC_XDP_CONSUMED; - __page_pool_put_page(dring->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(dring->page_pool, + virt_to_head_page(xdp->data), len, + true); } break; default: @@ -919,9 +919,8 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog, /* fall through -- handle aborts by dropping packet */ case XDP_DROP: ret = NETSEC_XDP_CONSUMED; - __page_pool_put_page(dring->page_pool, - virt_to_head_page(xdp->data), - len, true); + page_pool_put_page(dring->page_pool, + virt_to_head_page(xdp->data), len, true); break; } @@ -1020,8 +1019,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) * cache state. Since we paid the allocation cost if * building an skb fails try to put the page into cache */ - __page_pool_put_page(dring->page_pool, page, - pkt_len, true); + page_pool_put_page(dring->page_pool, page, pkt_len, + true); netif_err(priv, drv, priv->ndev, "rx failed to build skb\n"); break; @@ -1148,11 +1147,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb, ~tcp_v4_check(0, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, 0); } else { - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); } tx_ctrl.tcp_seg_offload_flag = true; @@ -1199,7 +1194,7 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id) if (id == NETSEC_RING_RX) { struct page *page = virt_to_page(desc->addr); - page_pool_put_page(dring->page_pool, page, false); + page_pool_put_full_page(dring->page_pool, page, false); } else if (id == NETSEC_RING_TX) { dma_unmap_single(priv->dev, desc->dma_addr, desc->len, DMA_TO_DEVICE); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 9b7be996d07b..b2dc99289687 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -304,7 +304,7 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, /* Get ETH_CLK clocks */ dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck"); if (IS_ERR(dwmac->clk_eth_ck)) { - dev_warn(dev, "No phy clock provided...\n"); + dev_info(dev, "No phy clock provided...\n"); dwmac->clk_eth_ck = NULL; } @@ -324,7 +324,7 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac, /* Get IRQ information early to have an ability to ask for deferred * probe if needed before we went too far with resource allocation. */ - dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev, + dwmac->irq_pwr_wakeup = platform_get_irq_byname_optional(pdev, "stm32_pwr_wakeup"); if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER) return -EPROBE_DEFER; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7da18c9afa01..cb7a5bad4cfe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -950,8 +950,10 @@ static void stmmac_mac_link_down(struct phylink_config *config, } static void stmmac_mac_link_up(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, phy_interface_t interface, - struct phy_device *phy) + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); @@ -1251,11 +1253,11 @@ static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i) struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; if (buf->page) - page_pool_put_page(rx_q->page_pool, buf->page, false); + page_pool_put_full_page(rx_q->page_pool, buf->page, false); buf->page = NULL; if (buf->sec_page) - page_pool_put_page(rx_q->page_pool, buf->sec_page, false); + page_pool_put_full_page(rx_q->page_pool, buf->sec_page, false); buf->sec_page = NULL; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index fe2c9fa6a71c..7acbac73c29c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -579,28 +579,23 @@ static int __maybe_unused stmmac_pci_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); /* synthetic ID, no official vendor */ -#define PCI_VENDOR_ID_STMMAC 0x700 - -#define STMMAC_QUARK_ID 0x0937 -#define STMMAC_DEVICE_ID 0x1108 -#define STMMAC_EHL_RGMII1G_ID 0x4b30 -#define STMMAC_EHL_SGMII1G_ID 0x4b31 -#define STMMAC_TGL_SGMII1G_ID 0xa0ac -#define STMMAC_GMAC5_ID 0x7102 - -#define STMMAC_DEVICE(vendor_id, dev_id, info) { \ - PCI_VDEVICE(vendor_id, dev_id), \ - .driver_data = (kernel_ulong_t)&info \ - } +#define PCI_VENDOR_ID_STMMAC 0x0700 + +#define PCI_DEVICE_ID_STMMAC_STMMAC 0x1108 +#define PCI_DEVICE_ID_INTEL_QUARK_ID 0x0937 +#define PCI_DEVICE_ID_INTEL_EHL_RGMII1G_ID 0x4b30 +#define PCI_DEVICE_ID_INTEL_EHL_SGMII1G_ID 0x4b31 +#define PCI_DEVICE_ID_INTEL_TGL_SGMII1G_ID 0xa0ac +#define PCI_DEVICE_ID_SYNOPSYS_GMAC5_ID 0x7102 static const struct pci_device_id stmmac_id_table[] = { - STMMAC_DEVICE(STMMAC, STMMAC_DEVICE_ID, stmmac_pci_info), - STMMAC_DEVICE(STMICRO, PCI_DEVICE_ID_STMICRO_MAC, stmmac_pci_info), - STMMAC_DEVICE(INTEL, STMMAC_QUARK_ID, quark_pci_info), - STMMAC_DEVICE(INTEL, STMMAC_EHL_RGMII1G_ID, ehl_rgmii1g_pci_info), - STMMAC_DEVICE(INTEL, STMMAC_EHL_SGMII1G_ID, ehl_sgmii1g_pci_info), - STMMAC_DEVICE(INTEL, STMMAC_TGL_SGMII1G_ID, tgl_sgmii1g_pci_info), - STMMAC_DEVICE(SYNOPSYS, STMMAC_GMAC5_ID, snps_gmac5_pci_info), + { PCI_DEVICE_DATA(STMMAC, STMMAC, &stmmac_pci_info) }, + { PCI_DEVICE_DATA(STMICRO, MAC, &stmmac_pci_info) }, + { PCI_DEVICE_DATA(INTEL, QUARK_ID, &quark_pci_info) }, + { PCI_DEVICE_DATA(INTEL, EHL_RGMII1G_ID, &ehl_rgmii1g_pci_info) }, + { PCI_DEVICE_DATA(INTEL, EHL_SGMII1G_ID, &ehl_sgmii1g_pci_info) }, + { PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_pci_info) }, + { PCI_DEVICE_DATA(SYNOPSYS, GMAC5_ID, &snps_gmac5_pci_info) }, {} }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index d10ac54bf385..165958c9f069 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -588,7 +588,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) if (IS_ERR(plat->clk_ptp_ref)) { plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk); plat->clk_ptp_ref = NULL; - dev_warn(&pdev->dev, "PTP uses main clock\n"); + dev_info(&pdev->dev, "PTP uses main clock\n"); } else { plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref); dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index 805903dbddcc..68f324ed4eaf 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -308,7 +308,7 @@ struct gelic_port { struct gelic_card *card; struct net_device *netdev; enum gelic_port_type type; - long priv[0]; /* long for alignment */ + long priv[]; /* long for alignment */ }; static inline struct gelic_card *port_to_card(struct gelic_port *p) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h index 4041d946b649..1f203d1ae8db 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.h @@ -158,7 +158,7 @@ struct gelic_eurus_scan_info { __be32 reserved2; __be32 reserved3; __be32 reserved4; - u8 elements[0]; /* ie */ + u8 elements[]; /* ie */ } __packed; /* the hypervisor returns bbs up to 16 */ diff --git a/drivers/net/ethernet/toshiba/spider_net.h b/drivers/net/ethernet/toshiba/spider_net.h index c0c68cbc898c..05b1a0736835 100644 --- a/drivers/net/ethernet/toshiba/spider_net.h +++ b/drivers/net/ethernet/toshiba/spider_net.h @@ -470,7 +470,7 @@ struct spider_net_card { struct spider_net_extra_stats spider_stats; /* Must be last item in struct */ - struct spider_net_descr darray[0]; + struct spider_net_descr darray[]; }; #endif diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 3fd43d30b20d..b50c3ec3495b 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -367,7 +367,7 @@ struct TxFD { struct RxFD { struct FDesc fd; - struct BDesc bd[0]; /* variable length */ + struct BDesc bd[]; /* variable length */ }; struct FrFD { diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 20746b801959..c2f4c5ca2e80 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1441,6 +1441,22 @@ static void axienet_mac_an_restart(struct phylink_config *config) static void axienet_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { + /* nothing meaningful to do */ +} + +static void axienet_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + /* nothing meaningful to do */ +} + +static void axienet_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); u32 emmc_reg, fcc_reg; @@ -1448,7 +1464,7 @@ static void axienet_mac_config(struct phylink_config *config, unsigned int mode, emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET); emmc_reg &= ~XAE_EMMC_LINKSPEED_MASK; - switch (state->speed) { + switch (speed) { case SPEED_1000: emmc_reg |= XAE_EMMC_LINKSPD_1000; break; @@ -1467,32 +1483,17 @@ static void axienet_mac_config(struct phylink_config *config, unsigned int mode, axienet_iow(lp, XAE_EMMC_OFFSET, emmc_reg); fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET); - if (state->pause & MLO_PAUSE_TX) + if (tx_pause) fcc_reg |= XAE_FCC_FCTX_MASK; else fcc_reg &= ~XAE_FCC_FCTX_MASK; - if (state->pause & MLO_PAUSE_RX) + if (rx_pause) fcc_reg |= XAE_FCC_FCRX_MASK; else fcc_reg &= ~XAE_FCC_FCRX_MASK; axienet_iow(lp, XAE_FCC_OFFSET, fcc_reg); } -static void axienet_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - /* nothing meaningful to do */ -} - -static void axienet_mac_link_up(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface, - struct phy_device *phy) -{ - /* nothing meaningful to do */ -} - static const struct phylink_mac_ops axienet_phylink_ops = { .validate = axienet_validate, .mac_pcs_get_state = axienet_mac_pcs_get_state, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 2c0a24c606fc..245ce2374035 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -638,10 +638,7 @@ static int netvsc_xmit(struct sk_buff *skb, struct net_device *net, bool xdp_tx) } else { lso_info->lso_v2_transmit.ip_version = NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6; - ipv6_hdr(skb)->payload_len = 0; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); } lso_info->lso_v2_transmit.tcp_header_offset = skb_transport_offset(skb); lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d7706a0346f2..f81c47377f32 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -28,6 +28,7 @@ #include <linux/workqueue.h> #include <net/devlink.h> #include <net/ip.h> +#include <net/flow_offload.h> #include <uapi/linux/devlink.h> #include <uapi/linux/ip.h> #include <uapi/linux/udp.h> @@ -71,6 +72,98 @@ static const struct file_operations nsim_dev_take_snapshot_fops = { .llseek = generic_file_llseek, }; +static ssize_t nsim_dev_trap_fa_cookie_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + unsigned int buf_len; + ssize_t ret; + char *buf; + + spin_lock(&nsim_dev->fa_cookie_lock); + fa_cookie = nsim_dev->fa_cookie; + if (!fa_cookie) { + ret = -EINVAL; + goto errout; + } + buf_len = fa_cookie->cookie_len * 2; + buf = kmalloc(buf_len, GFP_ATOMIC); + if (!buf) { + ret = -ENOMEM; + goto errout; + } + bin2hex(buf, fa_cookie->cookie, fa_cookie->cookie_len); + spin_unlock(&nsim_dev->fa_cookie_lock); + + ret = simple_read_from_buffer(data, count, ppos, buf, buf_len); + + kfree(buf); + return ret; + +errout: + spin_unlock(&nsim_dev->fa_cookie_lock); + return ret; +} + +static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_dev *nsim_dev = file->private_data; + struct flow_action_cookie *fa_cookie; + size_t cookie_len; + ssize_t ret; + char *buf; + + if (*ppos != 0) + return -EINVAL; + cookie_len = (count - 1) / 2; + if ((count - 1) % 2) + return -EINVAL; + buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); + if (!buf) + return -ENOMEM; + + ret = simple_write_to_buffer(buf, count, ppos, data, count); + if (ret < 0) + goto free_buf; + + fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, + GFP_KERNEL | __GFP_NOWARN); + if (!fa_cookie) { + ret = -ENOMEM; + goto free_buf; + } + + fa_cookie->cookie_len = cookie_len; + ret = hex2bin(fa_cookie->cookie, buf, cookie_len); + if (ret) + goto free_fa_cookie; + kfree(buf); + + spin_lock(&nsim_dev->fa_cookie_lock); + kfree(nsim_dev->fa_cookie); + nsim_dev->fa_cookie = fa_cookie; + spin_unlock(&nsim_dev->fa_cookie_lock); + + return count; + +free_fa_cookie: + kfree(fa_cookie); +free_buf: + kfree(buf); + return ret; +} + +static const struct file_operations nsim_dev_trap_fa_cookie_fops = { + .open = simple_open, + .read = nsim_dev_trap_fa_cookie_read, + .write = nsim_dev_trap_fa_cookie_write, + .llseek = generic_file_llseek, +}; + static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) { char dev_ddir_name[sizeof(DRV_NAME) + 10]; @@ -97,6 +190,8 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) &nsim_dev->dont_allow_reload); debugfs_create_bool("fail_reload", 0600, nsim_dev->ddir, &nsim_dev->fail_reload); + debugfs_create_file("trap_flow_action_cookie", 0600, nsim_dev->ddir, + nsim_dev, &nsim_dev_trap_fa_cookie_fops); return 0; } @@ -288,6 +383,10 @@ enum { DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ NSIM_TRAP_METADATA) +#define NSIM_TRAP_DROP_EXT(_id, _group_id, _metadata) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + NSIM_TRAP_METADATA | (_metadata)) #define NSIM_TRAP_EXCEPTION(_id, _group_id) \ DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ @@ -309,6 +408,10 @@ static const struct devlink_trap nsim_traps_arr[] = { NSIM_TRAP_DROP(BLACKHOLE_ROUTE, L3_DROPS), NSIM_TRAP_EXCEPTION(TTL_ERROR, L3_DROPS), NSIM_TRAP_DROP(TAIL_DROP, BUFFER_DROPS), + NSIM_TRAP_DROP_EXT(INGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), + NSIM_TRAP_DROP_EXT(EGRESS_FLOW_ACTION_DROP, ACL_DROPS, + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE), }; #define NSIM_TRAP_L4_DATA_LEN 100 @@ -366,8 +469,13 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) spin_lock(&nsim_trap_data->trap_lock); for (i = 0; i < ARRAY_SIZE(nsim_traps_arr); i++) { + struct flow_action_cookie *fa_cookie = NULL; struct nsim_trap_item *nsim_trap_item; struct sk_buff *skb; + bool has_fa_cookie; + + has_fa_cookie = nsim_traps_arr[i].metadata_cap & + DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE; nsim_trap_item = &nsim_trap_data->trap_items_arr[i]; if (nsim_trap_item->action == DEVLINK_TRAP_ACTION_DROP) @@ -383,10 +491,12 @@ static void nsim_dev_trap_report(struct nsim_dev_port *nsim_dev_port) * softIRQs to prevent lockdep from complaining about * "incosistent lock state". */ - local_bh_disable(); + + spin_lock_bh(&nsim_dev->fa_cookie_lock); + fa_cookie = has_fa_cookie ? nsim_dev->fa_cookie : NULL; devlink_trap_report(devlink, skb, nsim_trap_item->trap_ctx, - &nsim_dev_port->devlink_port); - local_bh_enable(); + &nsim_dev_port->devlink_port, fa_cookie); + spin_unlock_bh(&nsim_dev->fa_cookie_lock); consume_skb(skb); } spin_unlock(&nsim_trap_data->trap_lock); @@ -780,6 +890,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) nsim_dev->fw_update_status = true; nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; + spin_lock_init(&nsim_dev->fa_cookie_lock); dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev); diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 2eb7b0dc1594..e46fc565b981 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -178,6 +178,8 @@ struct nsim_dev { bool fail_reload; struct devlink_region *dummy_region; struct nsim_dev_health health; + struct flow_action_cookie *fa_cookie; + spinlock_t fa_cookie_lock; /* protects fa_cookie */ }; static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 9dabe03a668c..edb1cb8a228e 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -326,8 +326,8 @@ config BROADCOM_PHY BCM5481, BCM54810 and BCM5482 PHYs. config BCM84881_PHY - bool "Broadcom BCM84881 PHY" - depends on PHYLIB=y + tristate "Broadcom BCM84881 PHY" + depends on PHYLIB ---help--- Support the Broadcom BCM84881 PHY. diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index fe5badf13b65..d523fd5670e4 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux PHY drivers and MDIO bus drivers -libphy-y := phy.o phy-c45.o phy-core.o phy_device.o +libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ + linkmode.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index a62229a8b1a4..ae4873f2f86e 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -194,7 +194,8 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) /* Abort if we are using an untested phy. */ if (BRCM_PHY_MODEL(phydev) != PHY_ID_BCM57780 && BRCM_PHY_MODEL(phydev) != PHY_ID_BCM50610 && - BRCM_PHY_MODEL(phydev) != PHY_ID_BCM50610M) + BRCM_PHY_MODEL(phydev) != PHY_ID_BCM50610M && + BRCM_PHY_MODEL(phydev) != PHY_ID_BCM54810) return; val = bcm_phy_read_shadow(phydev, BCM54XX_SHD_SCR3); @@ -272,10 +273,7 @@ static int bcm54xx_config_init(struct phy_device *phydev) (phydev->dev_flags & PHY_BRCM_CLEAR_RGMII_MODE)) bcm_phy_write_shadow(phydev, BCM54XX_SHD_RGMII_MODE, 0); - if ((phydev->dev_flags & PHY_BRCM_RX_REFCLK_UNUSED) || - (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) || - (phydev->dev_flags & PHY_BRCM_AUTO_PWRDWN_ENABLE)) - bcm54xx_adjust_rxrefclk(phydev); + bcm54xx_adjust_rxrefclk(phydev); if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E) { err = bcm54210e_config_init(phydev); @@ -315,6 +313,20 @@ static int bcm54xx_config_init(struct phy_device *phydev) return 0; } +static int bcm54xx_resume(struct phy_device *phydev) +{ + int ret; + + /* Writes to register other than BMCR would be ignored + * unless we clear the PDOWN bit first + */ + ret = genphy_resume(phydev); + if (ret < 0) + return ret; + + return bcm54xx_config_init(phydev); +} + static int bcm5482_config_init(struct phy_device *phydev) { int err, reg; @@ -708,6 +720,8 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm5481_config_aneg, .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .suspend = genphy_suspend, + .resume = bcm54xx_resume, }, { .phy_id = PHY_ID_BCM5482, .phy_id_mask = 0xfffffff0, diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 967f57ed0b65..13f7f2d5a2ea 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -14,6 +14,7 @@ #include <linux/delay.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/bitfield.h> #include <dt-bindings/net/ti-dp83867.h> @@ -21,6 +22,7 @@ #define DP83867_DEVADDR 0x1f #define MII_DP83867_PHYCTRL 0x10 +#define MII_DP83867_PHYSTS 0x11 #define MII_DP83867_MICR 0x12 #define MII_DP83867_ISR 0x13 #define DP83867_CFG2 0x14 @@ -118,6 +120,24 @@ #define DP83867_IO_MUX_CFG_CLK_O_SEL_MASK (0x1f << 8) #define DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT 8 +/* PHY STS bits */ +#define DP83867_PHYSTS_1000 BIT(15) +#define DP83867_PHYSTS_100 BIT(14) +#define DP83867_PHYSTS_DUPLEX BIT(13) +#define DP83867_PHYSTS_LINK BIT(10) + +/* CFG2 bits */ +#define DP83867_DOWNSHIFT_EN (BIT(8) | BIT(9)) +#define DP83867_DOWNSHIFT_ATTEMPT_MASK (BIT(10) | BIT(11)) +#define DP83867_DOWNSHIFT_1_COUNT_VAL 0 +#define DP83867_DOWNSHIFT_2_COUNT_VAL 1 +#define DP83867_DOWNSHIFT_4_COUNT_VAL 2 +#define DP83867_DOWNSHIFT_8_COUNT_VAL 3 +#define DP83867_DOWNSHIFT_1_COUNT 1 +#define DP83867_DOWNSHIFT_2_COUNT 2 +#define DP83867_DOWNSHIFT_4_COUNT 4 +#define DP83867_DOWNSHIFT_8_COUNT 8 + /* CFG3 bits */ #define DP83867_CFG3_INT_OE BIT(7) #define DP83867_CFG3_ROBUST_AUTO_MDIX BIT(9) @@ -287,6 +307,126 @@ static int dp83867_config_intr(struct phy_device *phydev) return phy_write(phydev, MII_DP83867_MICR, micr_status); } +static int dp83867_read_status(struct phy_device *phydev) +{ + int status = phy_read(phydev, MII_DP83867_PHYSTS); + int ret; + + ret = genphy_read_status(phydev); + if (ret) + return ret; + + if (status < 0) + return status; + + if (status & DP83867_PHYSTS_DUPLEX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + + if (status & DP83867_PHYSTS_1000) + phydev->speed = SPEED_1000; + else if (status & DP83867_PHYSTS_100) + phydev->speed = SPEED_100; + else + phydev->speed = SPEED_10; + + return 0; +} + +static int dp83867_get_downshift(struct phy_device *phydev, u8 *data) +{ + int val, cnt, enable, count; + + val = phy_read(phydev, DP83867_CFG2); + if (val < 0) + return val; + + enable = FIELD_GET(DP83867_DOWNSHIFT_EN, val); + cnt = FIELD_GET(DP83867_DOWNSHIFT_ATTEMPT_MASK, val); + + switch (cnt) { + case DP83867_DOWNSHIFT_1_COUNT_VAL: + count = DP83867_DOWNSHIFT_1_COUNT; + break; + case DP83867_DOWNSHIFT_2_COUNT_VAL: + count = DP83867_DOWNSHIFT_2_COUNT; + break; + case DP83867_DOWNSHIFT_4_COUNT_VAL: + count = DP83867_DOWNSHIFT_4_COUNT; + break; + case DP83867_DOWNSHIFT_8_COUNT_VAL: + count = DP83867_DOWNSHIFT_8_COUNT; + break; + default: + return -EINVAL; + }; + + *data = enable ? count : DOWNSHIFT_DEV_DISABLE; + + return 0; +} + +static int dp83867_set_downshift(struct phy_device *phydev, u8 cnt) +{ + int val, count; + + if (cnt > DP83867_DOWNSHIFT_8_COUNT) + return -E2BIG; + + if (!cnt) + return phy_clear_bits(phydev, DP83867_CFG2, + DP83867_DOWNSHIFT_EN); + + switch (cnt) { + case DP83867_DOWNSHIFT_1_COUNT: + count = DP83867_DOWNSHIFT_1_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_2_COUNT: + count = DP83867_DOWNSHIFT_2_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_4_COUNT: + count = DP83867_DOWNSHIFT_4_COUNT_VAL; + break; + case DP83867_DOWNSHIFT_8_COUNT: + count = DP83867_DOWNSHIFT_8_COUNT_VAL; + break; + default: + phydev_err(phydev, + "Downshift count must be 1, 2, 4 or 8\n"); + return -EINVAL; + }; + + val = DP83867_DOWNSHIFT_EN; + val |= FIELD_PREP(DP83867_DOWNSHIFT_ATTEMPT_MASK, count); + + return phy_modify(phydev, DP83867_CFG2, + DP83867_DOWNSHIFT_EN | DP83867_DOWNSHIFT_ATTEMPT_MASK, + val); +} + +static int dp83867_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return dp83867_get_downshift(phydev, data); + default: + return -EOPNOTSUPP; + } +} + +static int dp83867_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return dp83867_set_downshift(phydev, *(const u8 *)data); + default: + return -EOPNOTSUPP; + } +} + static int dp83867_config_port_mirroring(struct phy_device *phydev) { struct dp83867_private *dp83867 = @@ -467,6 +607,12 @@ static int dp83867_config_init(struct phy_device *phydev) int ret, val, bs; u16 delay; + /* Force speed optimization for the PHY even if it strapped */ + ret = phy_modify(phydev, DP83867_CFG2, DP83867_DOWNSHIFT_EN, + DP83867_DOWNSHIFT_EN); + if (ret) + return ret; + ret = dp83867_verify_rgmii_cfg(phydev); if (ret) return ret; @@ -655,6 +801,10 @@ static struct phy_driver dp83867_driver[] = { .config_init = dp83867_config_init, .soft_reset = dp83867_phy_reset, + .read_status = dp83867_read_status, + .get_tunable = dp83867_get_tunable, + .set_tunable = dp83867_set_tunable, + .get_wol = dp83867_get_wol, .set_wol = dp83867_set_wol, diff --git a/drivers/net/phy/linkmode.c b/drivers/net/phy/linkmode.c new file mode 100644 index 000000000000..f60560fe3499 --- /dev/null +++ b/drivers/net/phy/linkmode.c @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0+ +#include <linux/linkmode.h> + +/** + * linkmode_resolve_pause - resolve the allowable pause modes + * @local_adv: local advertisement in ethtool format + * @partner_adv: partner advertisement in ethtool format + * @tx_pause: pointer to bool to indicate whether transmit pause should be + * enabled. + * @rx_pause: pointer to bool to indicate whether receive pause should be + * enabled. + * + * Flow control is resolved according to our and the link partners + * advertisements using the following drawn from the 802.3 specs: + * Local device Link partner + * Pause AsymDir Pause AsymDir Result + * 0 X 0 X Disabled + * 0 1 1 0 Disabled + * 0 1 1 1 TX + * 1 0 0 X Disabled + * 1 X 1 X TX+RX + * 1 1 0 1 RX + */ +void linkmode_resolve_pause(const unsigned long *local_adv, + const unsigned long *partner_adv, + bool *tx_pause, bool *rx_pause) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(m); + + linkmode_and(m, local_adv, partner_adv); + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, m)) { + *tx_pause = true; + *rx_pause = true; + } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, m)) { + *tx_pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + partner_adv); + *rx_pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + local_adv); + } else { + *tx_pause = false; + *rx_pause = false; + } +} +EXPORT_SYMBOL_GPL(linkmode_resolve_pause); + +/** + * linkmode_set_pause - set the pause mode advertisement + * @advertisement: advertisement in ethtool format + * @tx: boolean from ethtool struct ethtool_pauseparam tx_pause member + * @rx: boolean from ethtool struct ethtool_pauseparam rx_pause member + * + * Configure the advertised Pause and Asym_Pause bits according to the + * capabilities of provided in @tx and @rx. + * + * We convert as follows: + * tx rx Pause AsymDir + * 0 0 0 0 + * 0 1 1 1 + * 1 0 0 1 + * 1 1 1 0 + * + * Note: this translation from ethtool tx/rx notation to the advertisement + * is actually very problematical. Here are some examples: + * + * For tx=0 rx=1, meaning transmit is unsupported, receive is supported: + * + * Local device Link partner + * Pause AsymDir Pause AsymDir Result + * 1 1 1 0 TX + RX - but we have no TX support. + * 1 1 0 1 Only this gives RX only + * + * For tx=1 rx=1, meaning we have the capability to transmit and receive + * pause frames: + * + * Local device Link partner + * Pause AsymDir Pause AsymDir Result + * 1 0 0 1 Disabled - but since we do support tx and rx, + * this should resolve to RX only. + * + * Hence, asking for: + * rx=1 tx=0 gives Pause+AsymDir advertisement, but we may end up + * resolving to tx+rx pause or only rx pause depending on + * the partners advertisement. + * rx=0 tx=1 gives AsymDir only, which will only give tx pause if + * the partners advertisement allows it. + * rx=1 tx=1 gives Pause only, which will only allow tx+rx pause + * if the other end also advertises Pause. + */ +void linkmode_set_pause(unsigned long *advertisement, bool tx, bool rx) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertisement, rx); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertisement, + rx ^ tx); +} +EXPORT_SYMBOL_GPL(linkmode_set_pause); diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 64c9f3bba2cd..9a4e12a2af07 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -39,10 +39,19 @@ enum { MV_PCS_BASE_R = 0x1000, MV_PCS_1000BASEX = 0x2000, - MV_PCS_PAIRSWAP = 0x8182, - MV_PCS_PAIRSWAP_MASK = 0x0003, - MV_PCS_PAIRSWAP_AB = 0x0002, - MV_PCS_PAIRSWAP_NONE = 0x0003, + MV_PCS_CSSR1 = 0x8008, + MV_PCS_CSSR1_SPD1_MASK = 0xc000, + MV_PCS_CSSR1_SPD1_SPD2 = 0xc000, + MV_PCS_CSSR1_SPD1_1000 = 0x8000, + MV_PCS_CSSR1_SPD1_100 = 0x4000, + MV_PCS_CSSR1_SPD1_10 = 0x0000, + MV_PCS_CSSR1_DUPLEX_FULL= BIT(13), + MV_PCS_CSSR1_RESOLVED = BIT(11), + MV_PCS_CSSR1_MDIX = BIT(6), + MV_PCS_CSSR1_SPD2_MASK = 0x000c, + MV_PCS_CSSR1_SPD2_5000 = 0x0008, + MV_PCS_CSSR1_SPD2_2500 = 0x0004, + MV_PCS_CSSR1_SPD2_10000 = 0x0000, /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is @@ -413,35 +422,18 @@ static void mv3310_update_interface(struct phy_device *phydev) } /* 10GBASE-ER,LR,LRM,SR do not support autonegotiation. */ -static int mv3310_read_10gbr_status(struct phy_device *phydev) +static int mv3310_read_status_10gbaser(struct phy_device *phydev) { phydev->link = 1; phydev->speed = SPEED_10000; phydev->duplex = DUPLEX_FULL; - mv3310_update_interface(phydev); - return 0; } -static int mv3310_read_status(struct phy_device *phydev) +static int mv3310_read_status_copper(struct phy_device *phydev) { - int val; - - phydev->speed = SPEED_UNKNOWN; - phydev->duplex = DUPLEX_UNKNOWN; - linkmode_zero(phydev->lp_advertising); - phydev->link = 0; - phydev->pause = 0; - phydev->asym_pause = 0; - phydev->mdix = 0; - - val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_BASE_R + MDIO_STAT1); - if (val < 0) - return val; - - if (val & MDIO_STAT1_LSTATUS) - return mv3310_read_10gbr_status(phydev); + int cssr1, speed, val; val = genphy_c45_read_link(phydev); if (val < 0) @@ -451,6 +443,52 @@ static int mv3310_read_status(struct phy_device *phydev) if (val < 0) return val; + cssr1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_CSSR1); + if (cssr1 < 0) + return val; + + /* If the link settings are not resolved, mark the link down */ + if (!(cssr1 & MV_PCS_CSSR1_RESOLVED)) { + phydev->link = 0; + return 0; + } + + /* Read the copper link settings */ + speed = cssr1 & MV_PCS_CSSR1_SPD1_MASK; + if (speed == MV_PCS_CSSR1_SPD1_SPD2) + speed |= cssr1 & MV_PCS_CSSR1_SPD2_MASK; + + switch (speed) { + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_10000: + phydev->speed = SPEED_10000; + break; + + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_5000: + phydev->speed = SPEED_5000; + break; + + case MV_PCS_CSSR1_SPD1_SPD2 | MV_PCS_CSSR1_SPD2_2500: + phydev->speed = SPEED_2500; + break; + + case MV_PCS_CSSR1_SPD1_1000: + phydev->speed = SPEED_1000; + break; + + case MV_PCS_CSSR1_SPD1_100: + phydev->speed = SPEED_100; + break; + + case MV_PCS_CSSR1_SPD1_10: + phydev->speed = SPEED_10; + break; + } + + phydev->duplex = cssr1 & MV_PCS_CSSR1_DUPLEX_FULL ? + DUPLEX_FULL : DUPLEX_HALF; + phydev->mdix = cssr1 & MV_PCS_CSSR1_MDIX ? + ETH_TP_MDI_X : ETH_TP_MDI; + if (val & MDIO_AN_STAT1_COMPLETE) { val = genphy_c45_read_lpa(phydev); if (val < 0) @@ -463,39 +501,38 @@ static int mv3310_read_status(struct phy_device *phydev) mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, val); - if (phydev->autoneg == AUTONEG_ENABLE) - phy_resolve_aneg_linkmode(phydev); + /* Update the pause status */ + phy_resolve_aneg_pause(phydev); } - if (phydev->autoneg != AUTONEG_ENABLE) { - val = genphy_c45_read_pma(phydev); - if (val < 0) - return val; - } + return 0; +} - if (phydev->speed == SPEED_10000) { - val = genphy_c45_read_mdix(phydev); - if (val < 0) - return val; - } else { - val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PAIRSWAP); - if (val < 0) - return val; +static int mv3310_read_status(struct phy_device *phydev) +{ + int err, val; - switch (val & MV_PCS_PAIRSWAP_MASK) { - case MV_PCS_PAIRSWAP_AB: - phydev->mdix = ETH_TP_MDI_X; - break; - case MV_PCS_PAIRSWAP_NONE: - phydev->mdix = ETH_TP_MDI; - break; - default: - phydev->mdix = ETH_TP_MDI_INVALID; - break; - } - } + phydev->speed = SPEED_UNKNOWN; + phydev->duplex = DUPLEX_UNKNOWN; + linkmode_zero(phydev->lp_advertising); + phydev->link = 0; + phydev->pause = 0; + phydev->asym_pause = 0; + phydev->mdix = ETH_TP_MDI_INVALID; - mv3310_update_interface(phydev); + val = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_BASE_R + MDIO_STAT1); + if (val < 0) + return val; + + if (val & MDIO_STAT1_LSTATUS) + err = mv3310_read_status_10gbaser(phydev); + else + err = mv3310_read_status_copper(phydev); + if (err < 0) + return err; + + if (phydev->link) + mv3310_update_interface(phydev); return 0; } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 9bb9f37f21dc..3ab9ca7614d1 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -462,6 +462,23 @@ static struct class mdio_bus_class = { .dev_groups = mdio_bus_groups, }; +/** + * mdio_find_bus - Given the name of a mdiobus, find the mii_bus. + * @mdio_bus_np: Pointer to the mii_bus. + * + * Returns a reference to the mii_bus, or NULL if none found. The + * embedded struct device will have its reference count incremented, + * and this must be put_deviced'ed once the bus is finished with. + */ +struct mii_bus *mdio_find_bus(const char *mdio_name) +{ + struct device *d; + + d = class_find_device_by_name(&mdio_bus_class, mdio_name); + return d ? to_mii_bus(d) : NULL; +} +EXPORT_SYMBOL(mdio_find_bus); + #if IS_ENABLED(CONFIG_OF_MDIO) /** * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index f686f40f6bdc..d24577de0775 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -2813,8 +2813,8 @@ static int vsc8584_config_init(struct phy_device *phydev) val = phy_read(phydev, MSCC_PHY_EXT_PHY_CNTL_1); val &= ~(MEDIA_OP_MODE_MASK | VSC8584_MAC_IF_SELECTION_MASK); - val |= MEDIA_OP_MODE_COPPER | (VSC8584_MAC_IF_SELECTION_SGMII << - VSC8584_MAC_IF_SELECTION_POS); + val |= (MEDIA_OP_MODE_COPPER << MEDIA_OP_MODE_POS) | + (VSC8584_MAC_IF_SELECTION_SGMII << VSC8584_MAC_IF_SELECTION_POS); ret = phy_write(phydev, MSCC_PHY_EXT_PHY_CNTL_1, val); ret = genphy_soft_reset(phydev); @@ -3276,7 +3276,7 @@ static int vsc8514_config_init(struct phy_device *phydev) return ret; ret = phy_modify(phydev, MSCC_PHY_EXT_PHY_CNTL_1, MEDIA_OP_MODE_MASK, - MEDIA_OP_MODE_COPPER); + MEDIA_OP_MODE_COPPER << MEDIA_OP_MODE_POS); if (ret) return ret; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index dd2e23fb67c0..67ba47ae5284 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -239,9 +239,10 @@ int genphy_c45_read_link(struct phy_device *phydev) /* The link state is latched low so that momentary link * drops can be detected. Do not double-read the status - * in polling mode to detect such short link drops. + * in polling mode to detect such short link drops except + * the link was already down. */ - if (!phy_polling_mode(phydev)) { + if (!phy_polling_mode(phydev) || !phydev->link) { val = phy_read_mmd(phydev, devad, MDIO_STAT1); if (val < 0) return val; diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index a4d2d59fceca..e083e7a76ada 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -8,7 +8,7 @@ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 74, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 75, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index c8b0c34030d3..7c00b029ebfb 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1931,9 +1931,10 @@ int genphy_update_link(struct phy_device *phydev) /* The link state is latched low so that momentary link * drops can be detected. Do not double-read the status - * in polling mode to detect such short link drops. + * in polling mode to detect such short link drops except + * the link was already down. */ - if (!phy_polling_mode(phydev)) { + if (!phy_polling_mode(phydev) || !phydev->link) { status = phy_read(phydev, MII_BMSR); if (status < 0) return status; @@ -2362,22 +2363,7 @@ void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx) __ETHTOOL_DECLARE_LINK_MODE_MASK(oldadv); linkmode_copy(oldadv, phydev->advertising); - - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - - if (rx) { - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - } - - if (tx) - linkmode_change_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); + linkmode_set_pause(phydev->advertising, tx, rx); if (!linkmode_equal(oldadv, phydev->advertising) && phydev->autoneg) @@ -2410,6 +2396,32 @@ bool phy_validate_pause(struct phy_device *phydev, } EXPORT_SYMBOL(phy_validate_pause); +/** + * phy_get_pause - resolve negotiated pause modes + * @phydev: phy_device struct + * @tx_pause: pointer to bool to indicate whether transmit pause should be + * enabled. + * @rx_pause: pointer to bool to indicate whether receive pause should be + * enabled. + * + * Resolve and return the flow control modes according to the negotiation + * result. This includes checking that we are operating in full duplex mode. + * See linkmode_resolve_pause() for further details. + */ +void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause) +{ + if (phydev->duplex != DUPLEX_FULL) { + *tx_pause = false; + *rx_pause = false; + return; + } + + return linkmode_resolve_pause(phydev->advertising, + phydev->lp_advertising, + tx_pause, rx_pause); +} +EXPORT_SYMBOL(phy_get_pause); + static bool phy_drv_supports_irq(struct phy_driver *phydrv) { return phydrv->config_intr && phydrv->ack_interrupt; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 70b9a143db84..b4367fab7899 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -181,9 +181,11 @@ static int phylink_parse_fixedlink(struct phylink *pl, /* We treat the "pause" and "asym-pause" terminology as * defining the link partner's ability. */ if (fwnode_property_read_bool(fixed_node, "pause")) - pl->link_config.pause |= MLO_PAUSE_SYM; + __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + pl->link_config.lp_advertising); if (fwnode_property_read_bool(fixed_node, "asym-pause")) - pl->link_config.pause |= MLO_PAUSE_ASYM; + __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + pl->link_config.lp_advertising); if (ret == 0) { desc = fwnode_gpiod_get_index(fixed_node, "link", 0, @@ -215,9 +217,11 @@ static int phylink_parse_fixedlink(struct phylink *pl, DUPLEX_FULL : DUPLEX_HALF; pl->link_config.speed = prop[2]; if (prop[3]) - pl->link_config.pause |= MLO_PAUSE_SYM; + __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + pl->link_config.lp_advertising); if (prop[4]) - pl->link_config.pause |= MLO_PAUSE_ASYM; + __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + pl->link_config.lp_advertising); } } @@ -339,6 +343,34 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode) return 0; } +static void phylink_apply_manual_flow(struct phylink *pl, + struct phylink_link_state *state) +{ + /* If autoneg is disabled, pause AN is also disabled */ + if (!state->an_enabled) + state->pause &= ~MLO_PAUSE_AN; + + /* Manual configuration of pause modes */ + if (!(pl->link_config.pause & MLO_PAUSE_AN)) + state->pause = pl->link_config.pause; +} + +static void phylink_resolve_flow(struct phylink_link_state *state) +{ + bool tx_pause, rx_pause; + + state->pause = MLO_PAUSE_NONE; + if (state->duplex == DUPLEX_FULL) { + linkmode_resolve_pause(state->advertising, + state->lp_advertising, + &tx_pause, &rx_pause); + if (tx_pause) + state->pause |= MLO_PAUSE_TX; + if (rx_pause) + state->pause |= MLO_PAUSE_RX; + } +} + static void phylink_mac_config(struct phylink *pl, const struct phylink_link_state *state) { @@ -387,49 +419,45 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, /* The fixed state is... fixed except for the link state, * which may be determined by a GPIO or a callback. */ -static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_state *state) +static void phylink_get_fixed_state(struct phylink *pl, + struct phylink_link_state *state) { *state = pl->link_config; if (pl->get_fixed_state) pl->get_fixed_state(pl->netdev, state); else if (pl->link_gpio) state->link = !!gpiod_get_value_cansleep(pl->link_gpio); + + phylink_resolve_flow(state); } -/* Flow control is resolved according to our and the link partners - * advertisements using the following drawn from the 802.3 specs: - * Local device Link partner - * Pause AsymDir Pause AsymDir Result - * 1 X 1 X TX+RX - * 0 1 1 1 TX - * 1 1 0 1 RX - */ -static void phylink_resolve_flow(struct phylink *pl, - struct phylink_link_state *state) +static void phylink_mac_initial_config(struct phylink *pl) { - int new_pause = 0; + struct phylink_link_state link_state; - if (pl->link_config.pause & MLO_PAUSE_AN) { - int pause = 0; + switch (pl->cur_link_an_mode) { + case MLO_AN_PHY: + link_state = pl->phy_state; + break; - if (phylink_test(pl->link_config.advertising, Pause)) - pause |= MLO_PAUSE_SYM; - if (phylink_test(pl->link_config.advertising, Asym_Pause)) - pause |= MLO_PAUSE_ASYM; + case MLO_AN_FIXED: + phylink_get_fixed_state(pl, &link_state); + break; - pause &= state->pause; + case MLO_AN_INBAND: + link_state = pl->link_config; + if (link_state.interface == PHY_INTERFACE_MODE_SGMII) + link_state.pause = MLO_PAUSE_NONE; + break; - if (pause & MLO_PAUSE_SYM) - new_pause = MLO_PAUSE_TX | MLO_PAUSE_RX; - else if (pause & MLO_PAUSE_ASYM) - new_pause = state->pause & MLO_PAUSE_SYM ? - MLO_PAUSE_TX : MLO_PAUSE_RX; - } else { - new_pause = pl->link_config.pause & MLO_PAUSE_TXRX_MASK; + default: /* can't happen */ + return; } - state->pause &= ~MLO_PAUSE_TXRX_MASK; - state->pause |= new_pause; + link_state.link = false; + + phylink_apply_manual_flow(pl, &link_state); + phylink_mac_config(pl, &link_state); } static const char *phylink_pause_to_str(int pause) @@ -452,8 +480,11 @@ static void phylink_mac_link_up(struct phylink *pl, struct net_device *ndev = pl->netdev; pl->cur_interface = link_state.interface; - pl->ops->mac_link_up(pl->config, pl->cur_link_an_mode, - pl->cur_interface, pl->phydev); + pl->ops->mac_link_up(pl->config, pl->phydev, + pl->cur_link_an_mode, pl->cur_interface, + link_state.speed, link_state.duplex, + !!(link_state.pause & MLO_PAUSE_TX), + !!(link_state.pause & MLO_PAUSE_RX)); if (ndev) netif_carrier_on(ndev); @@ -493,7 +524,7 @@ static void phylink_resolve(struct work_struct *w) switch (pl->cur_link_an_mode) { case MLO_AN_PHY: link_state = pl->phy_state; - phylink_resolve_flow(pl, &link_state); + phylink_apply_manual_flow(pl, &link_state); phylink_mac_config_up(pl, &link_state); break; @@ -515,10 +546,12 @@ static void phylink_resolve(struct work_struct *w) link_state.interface = pl->phy_state.interface; /* If we have a PHY, we need to update with - * the pause mode bits. */ - link_state.pause |= pl->phy_state.pause; - phylink_resolve_flow(pl, &link_state); + * the PHY flow control bits. */ + link_state.pause = pl->phy_state.pause; + phylink_apply_manual_flow(pl, &link_state); phylink_mac_config(pl, &link_state); + } else { + phylink_apply_manual_flow(pl, &link_state); } break; } @@ -705,15 +738,18 @@ static void phylink_phy_change(struct phy_device *phydev, bool up, bool do_carrier) { struct phylink *pl = phydev->phylink; + bool tx_pause, rx_pause; + + phy_get_pause(phydev, &tx_pause, &rx_pause); mutex_lock(&pl->state_mutex); pl->phy_state.speed = phydev->speed; pl->phy_state.duplex = phydev->duplex; pl->phy_state.pause = MLO_PAUSE_NONE; - if (phydev->pause) - pl->phy_state.pause |= MLO_PAUSE_SYM; - if (phydev->asym_pause) - pl->phy_state.pause |= MLO_PAUSE_ASYM; + if (tx_pause) + pl->phy_state.pause |= MLO_PAUSE_TX; + if (rx_pause) + pl->phy_state.pause |= MLO_PAUSE_RX; pl->phy_state.interface = phydev->interface; pl->phy_state.link = up; mutex_unlock(&pl->state_mutex); @@ -777,6 +813,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, mutex_lock(&pl->state_mutex); pl->phydev = phy; pl->phy_state.interface = interface; + pl->phy_state.pause = MLO_PAUSE_NONE; + pl->phy_state.speed = SPEED_UNKNOWN; + pl->phy_state.duplex = DUPLEX_UNKNOWN; linkmode_copy(pl->supported, supported); linkmode_copy(pl->link_config.advertising, config.advertising); @@ -1006,8 +1045,7 @@ void phylink_start(struct phylink *pl) * a fixed-link to start with the correct parameters, and also * ensures that we set the appropriate advertisement for Serdes links. */ - phylink_resolve_flow(pl, &pl->link_config); - phylink_mac_config(pl, &pl->link_config); + phylink_mac_initial_config(pl); /* Restart autonegotiation if using 802.3z to ensure that the link * parameters are properly negotiated. This is necessary for DSA @@ -1373,6 +1411,9 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, ASSERT_RTNL(); + if (pl->cur_link_an_mode == MLO_AN_FIXED) + return -EOPNOTSUPP; + if (!phylink_test(pl->supported, Pause) && !phylink_test(pl->supported, Asym_Pause)) return -EOPNOTSUPP; @@ -1381,8 +1422,8 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, !pause->autoneg && pause->rx_pause != pause->tx_pause) return -EINVAL; - config->pause &= ~(MLO_PAUSE_AN | MLO_PAUSE_TXRX_MASK); - + mutex_lock(&pl->state_mutex); + config->pause = 0; if (pause->autoneg) config->pause |= MLO_PAUSE_AN; if (pause->rx_pause) @@ -1390,6 +1431,22 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, if (pause->tx_pause) config->pause |= MLO_PAUSE_TX; + /* + * See the comments for linkmode_set_pause(), wrt the deficiencies + * with the current implementation. A solution to this issue would + * be: + * ethtool Local device + * rx tx Pause AsymDir + * 0 0 0 0 + * 1 0 1 1 + * 0 1 0 1 + * 1 1 1 1 + * and then use the ethtool rx/tx enablement status to mask the + * rx/tx pause resolution. + */ + linkmode_set_pause(config->advertising, pause->tx_pause, + pause->rx_pause); + /* If we have a PHY, phylib will call our link state function if the * mode has changed, which will trigger a resolve and update the MAC * configuration. @@ -1399,19 +1456,10 @@ int phylink_ethtool_set_pauseparam(struct phylink *pl, pause->tx_pause); } else if (!test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) { - switch (pl->cur_link_an_mode) { - case MLO_AN_FIXED: - /* Should we allow fixed links to change against the config? */ - phylink_resolve_flow(pl, config); - phylink_mac_config(pl, config); - break; - - case MLO_AN_INBAND: - phylink_mac_config(pl, config); - phylink_mac_an_restart(pl); - break; - } + phylink_mac_config(pl, &pl->link_config); + phylink_mac_an_restart(pl); } + mutex_unlock(&pl->state_mutex); return 0; } @@ -1503,13 +1551,14 @@ static int phylink_mii_emul_read(unsigned int reg, struct phylink_link_state *state) { struct fixed_phy_status fs; + unsigned long *lpa = state->lp_advertising; int val; fs.link = state->link; fs.speed = state->speed; fs.duplex = state->duplex; - fs.pause = state->pause & MLO_PAUSE_SYM; - fs.asym_pause = state->pause & MLO_PAUSE_ASYM; + fs.pause = test_bit(ETHTOOL_LINK_MODE_Pause_BIT, lpa); + fs.asym_pause = test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, lpa); val = swphy_read_reg(reg, &fs); if (reg == MII_BMSR) { @@ -1814,7 +1863,7 @@ static int phylink_sfp_config(struct phylink *pl, u8 mode, if (changed && !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) - phylink_mac_config(pl, &pl->link_config); + phylink_mac_initial_config(pl); return ret; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 650c937ed56b..79f248cb282d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1078,8 +1078,6 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len); - BUG_ON(!tfile); - /* Drop if the filter does not like it. * This is a noop if the filter is disabled. * Filter can be enabled only for the TAP devices. */ diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index bcabd39d136a..9bdbd7b472a0 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -36,7 +36,7 @@ struct usbpn_dev { spinlock_t rx_lock; struct sk_buff *rx_skb; - struct urb *urbs[0]; + struct urb *urbs[]; }; static void tx_complete(struct urb *req); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 78ddbaf6401b..709578f4d060 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1948,29 +1948,6 @@ drop: } } -/* msdn_giant_send_check() - * According to the document of microsoft, the TCP Pseudo Header excludes the - * packet length for IPv6 TCP large packets. - */ -static int msdn_giant_send_check(struct sk_buff *skb) -{ - const struct ipv6hdr *ipv6h; - struct tcphdr *th; - int ret; - - ret = skb_cow_head(skb, 0); - if (ret) - return ret; - - ipv6h = ipv6_hdr(skb); - th = tcp_hdr(skb); - - th->check = 0; - th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0); - - return ret; -} - static inline void rtl_tx_vlan_tag(struct tx_desc *desc, struct sk_buff *skb) { if (skb_vlan_tag_present(skb)) { @@ -2016,10 +1993,11 @@ static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, break; case htons(ETH_P_IPV6): - if (msdn_giant_send_check(skb)) { + if (skb_cow_head(skb, 0)) { ret = TX_CSUM_TSO; goto unavailable; } + tcp_v6_gso_csum_prep(skb); opts1 |= GTSENDV6; break; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 18f152fa0068..722cb054a5cd 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -942,10 +942,7 @@ vmxnet3_prepare_tso(struct sk_buff *skb, tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, 0, IPPROTO_TCP, 0); } else if (ctx->ipv6) { - struct ipv6hdr *iph = ipv6_hdr(skb); - - tcph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, 0, - IPPROTO_TCP, 0); + tcp_v6_gso_csum_prep(skb); } } diff --git a/drivers/net/wan/farsync.h b/drivers/net/wan/farsync.h index 47b8e36f97ab..5f43568a9715 100644 --- a/drivers/net/wan/farsync.h +++ b/drivers/net/wan/farsync.h @@ -65,7 +65,7 @@ struct fstioc_write { unsigned int size; unsigned int offset; - unsigned char data[0]; + unsigned char data[]; }; diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index 23f93f1c815d..499f7cd19a4a 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -78,7 +78,7 @@ struct card { struct sk_buff *rx_skbs[RX_QUEUE_LENGTH]; struct card_status *status; /* shared between host and card */ dma_addr_t status_address; - struct port ports[0]; /* 1 - 4 port structures follow */ + struct port ports[]; /* 1 - 4 port structures follow */ }; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 7fee35ff966b..2f820d4eb308 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -5103,7 +5103,8 @@ static int ath10k_mac_txpower_recalc(struct ath10k *ar) lockdep_assert_held(&ar->conf_mutex); list_for_each_entry(arvif, &ar->arvifs, list) { - if (arvif->txpower <= 0) + /* txpower not initialized yet? */ + if (arvif->txpower == INT_MIN) continue; if (txpower == -1) diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 0548aa3702e3..983b6d6c89f0 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1196,6 +1196,9 @@ static void ath9k_tpc_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif) { int *power = data; + if (vif->bss_conf.txpower == INT_MIN) + return; + if (*power < vif->bss_conf.txpower) *power = vif->bss_conf.txpower; } diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 31e7b108279c..e60d4737fc6e 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -2095,10 +2095,13 @@ static void setup_frame_info(struct ieee80211_hw *hw, if (tx_info->control.vif) { struct ieee80211_vif *vif = tx_info->control.vif; - + if (vif->bss_conf.txpower == INT_MIN) + goto nonvifpower; txpower = 2 * vif->bss_conf.txpower; } else { - struct ath_softc *sc = hw->priv; + struct ath_softc *sc; + nonvifpower: + sc = hw->priv; txpower = sc->cur_chan->cur_txpower; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 02df603b6400..7b6d14445f1b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2019,7 +2019,7 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, struct iwl_he_sta_context_cmd sta_ctxt_cmd = { .sta_id = sta_id, .tid_limit = IWL_MAX_TID_COUNT, - .bss_color = vif->bss_conf.bss_color, + .bss_color = vif->bss_conf.he_bss_color.color, .htc_trig_based_pkt_ext = vif->bss_conf.htc_trig_based_pkt_ext, .frame_time_rts_th = cpu_to_le16(vif->bss_conf.frame_time_rts_th), diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 03738107fd10..da0a6b6c4771 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -300,14 +300,12 @@ static struct net_device *hwsim_mon; /* global monitor netdev */ .band = NL80211_BAND_2GHZ, \ .center_freq = (_freq), \ .hw_value = (_freq), \ - .max_power = 20, \ } #define CHAN5G(_freq) { \ .band = NL80211_BAND_5GHZ, \ .center_freq = (_freq), \ .hw_value = (_freq), \ - .max_power = 20, \ } static const struct ieee80211_channel hwsim_channels_2ghz[] = { @@ -1595,6 +1593,11 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, mac80211_hwsim_tx_frame(hw, skb, rcu_dereference(vif->chanctx_conf)->def.chan); + while ((skb = ieee80211_get_buffered_bc(hw, vif)) != NULL) { + mac80211_hwsim_tx_frame(hw, skb, + rcu_dereference(vif->chanctx_conf)->def.chan); + } + if (vif->csa_active && ieee80211_csa_is_complete(vif)) ieee80211_csa_finish(vif); } @@ -2925,11 +2928,15 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ieee80211_hw_set(hw, MFP_CAPABLE); ieee80211_hw_set(hw, SIGNAL_DBM); ieee80211_hw_set(hw, SUPPORTS_PS); + ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS); + ieee80211_hw_set(hw, HOST_BROADCAST_PS_BUFFERING); + ieee80211_hw_set(hw, PS_NULLFUNC_STACK); ieee80211_hw_set(hw, TDLS_WIDER_BW); if (rctbl) ieee80211_hw_set(hw, SUPPORTS_RC_TABLE); ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); + hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT; hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS | WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL | WIPHY_FLAG_AP_UAPSD | @@ -2940,6 +2947,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, NL80211_FEATURE_DYNAMIC_SMPS | NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_VHT_IBSS); + wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION); hw->wiphy->interface_modes = param->iftypes; diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 0cc9ac856fe2..7c0b1e6b80ff 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -76,7 +76,7 @@ static u8 nci_core_get_config_otp_ram_version[5] = { struct nci_core_get_config_rsp { u8 status; u8 count; - u8 data[0]; + u8 data[]; }; static int fdp_nci_create_conn(struct nci_dev *ndev) diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 60acdfd1cb8c..a1d69f9b2d4a 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -66,7 +66,7 @@ struct st21nfca_atr_req { u8 bsi; u8 bri; u8 ppi; - u8 gbi[0]; + u8 gbi[]; } __packed; struct st21nfca_atr_res { @@ -79,7 +79,7 @@ struct st21nfca_atr_res { u8 bri; u8 to; u8 ppi; - u8 gbi[0]; + u8 gbi[]; } __packed; struct st21nfca_psl_req { diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index 475c60dccaa4..3b424ffceb83 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -115,6 +115,18 @@ config PTP_1588_CLOCK_KVM To compile this driver as a module, choose M here: the module will be called ptp_kvm. +config PTP_1588_CLOCK_IDT82P33 + tristate "IDT 82P33xxx PTP clock" + depends on PTP_1588_CLOCK && I2C + default n + help + This driver adds support for using the IDT 82P33xxx as a PTP + clock. This clock is only useful if your time stamping MAC + is connected to the IDT chip. + + To compile this driver as a module, choose M here: the module + will be called ptp_idt82p33. + config PTP_1588_CLOCK_IDTCM tristate "IDT CLOCKMATRIX as PTP clock" depends on PTP_1588_CLOCK && I2C diff --git a/drivers/ptp/Makefile b/drivers/ptp/Makefile index 8c830336f178..01ff7fc3e820 100644 --- a/drivers/ptp/Makefile +++ b/drivers/ptp/Makefile @@ -13,3 +13,4 @@ obj-$(CONFIG_PTP_1588_CLOCK_QORIQ) += ptp-qoriq.o ptp-qoriq-y += ptp_qoriq.o ptp-qoriq-$(CONFIG_DEBUG_FS) += ptp_qoriq_debugfs.o obj-$(CONFIG_PTP_1588_CLOCK_IDTCM) += ptp_clockmatrix.o +obj-$(CONFIG_PTP_1588_CLOCK_IDT82P33) += ptp_idt82p33.o diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c new file mode 100644 index 000000000000..b63ac240308b --- /dev/null +++ b/drivers/ptp/ptp_idt82p33.c @@ -0,0 +1,1008 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright (C) 2018 Integrated Device Technology, Inc +// + +#define pr_fmt(fmt) "IDT_82p33xxx: " fmt + +#include <linux/firmware.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/timekeeping.h> +#include <linux/bitops.h> + +#include "ptp_private.h" +#include "ptp_idt82p33.h" + +MODULE_DESCRIPTION("Driver for IDT 82p33xxx clock devices"); +MODULE_AUTHOR("IDT support-1588 <IDT-support-1588@lm.renesas.com>"); +MODULE_VERSION("1.0"); +MODULE_LICENSE("GPL"); + +/* Module Parameters */ +u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC; +module_param(sync_tod_timeout, uint, 0); +MODULE_PARM_DESC(sync_tod_timeout, +"duration in second to keep SYNC_TOD on (set to 0 to keep it always on)"); + +u32 phase_snap_threshold = SNAP_THRESHOLD_NS; +module_param(phase_snap_threshold, uint, 0); +MODULE_PARM_DESC(phase_snap_threshold, +"threshold (150000ns by default) below which adjtime would ignore"); + +static void idt82p33_byte_array_to_timespec(struct timespec64 *ts, + u8 buf[TOD_BYTE_COUNT]) +{ + time64_t sec; + s32 nsec; + u8 i; + + nsec = buf[3]; + for (i = 0; i < 3; i++) { + nsec <<= 8; + nsec |= buf[2 - i]; + } + + sec = buf[9]; + for (i = 0; i < 5; i++) { + sec <<= 8; + sec |= buf[8 - i]; + } + + ts->tv_sec = sec; + ts->tv_nsec = nsec; +} + +static void idt82p33_timespec_to_byte_array(struct timespec64 const *ts, + u8 buf[TOD_BYTE_COUNT]) +{ + time64_t sec; + s32 nsec; + u8 i; + + nsec = ts->tv_nsec; + sec = ts->tv_sec; + + for (i = 0; i < 4; i++) { + buf[i] = nsec & 0xff; + nsec >>= 8; + } + + for (i = 4; i < TOD_BYTE_COUNT; i++) { + buf[i] = sec & 0xff; + sec >>= 8; + } +} + +static int idt82p33_xfer(struct idt82p33 *idt82p33, + unsigned char regaddr, + unsigned char *buf, + unsigned int count, + int write) +{ + struct i2c_client *client = idt82p33->client; + struct i2c_msg msg[2]; + int cnt; + + msg[0].addr = client->addr; + msg[0].flags = 0; + msg[0].len = 1; + msg[0].buf = ®addr; + + msg[1].addr = client->addr; + msg[1].flags = write ? 0 : I2C_M_RD; + msg[1].len = count; + msg[1].buf = buf; + + cnt = i2c_transfer(client->adapter, msg, 2); + if (cnt < 0) { + dev_err(&client->dev, "i2c_transfer returned %d\n", cnt); + return cnt; + } else if (cnt != 2) { + dev_err(&client->dev, + "i2c_transfer sent only %d of %d messages\n", cnt, 2); + return -EIO; + } + return 0; +} + +static int idt82p33_page_offset(struct idt82p33 *idt82p33, unsigned char val) +{ + int err; + + if (idt82p33->page_offset == val) + return 0; + + err = idt82p33_xfer(idt82p33, PAGE_ADDR, &val, sizeof(val), 1); + if (err) + dev_err(&idt82p33->client->dev, + "failed to set page offset %d\n", val); + else + idt82p33->page_offset = val; + + return err; +} + +static int idt82p33_rdwr(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count, bool write) +{ + u8 offset, page; + int err; + + page = _PAGE(regaddr); + offset = _OFFSET(regaddr); + + err = idt82p33_page_offset(idt82p33, page); + if (err) + goto out; + + err = idt82p33_xfer(idt82p33, offset, buf, count, write); +out: + return err; +} + +static int idt82p33_read(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count) +{ + return idt82p33_rdwr(idt82p33, regaddr, buf, count, false); +} + +static int idt82p33_write(struct idt82p33 *idt82p33, unsigned int regaddr, + unsigned char *buf, unsigned int count) +{ + return idt82p33_rdwr(idt82p33, regaddr, buf, count, true); +} + +static int idt82p33_dpll_set_mode(struct idt82p33_channel *channel, + enum pll_mode mode) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 dpll_mode; + int err; + + if (channel->pll_mode == mode) + return 0; + + err = idt82p33_read(idt82p33, channel->dpll_mode_cnfg, + &dpll_mode, sizeof(dpll_mode)); + if (err) + return err; + + dpll_mode &= ~(PLL_MODE_MASK << PLL_MODE_SHIFT); + + dpll_mode |= (mode << PLL_MODE_SHIFT); + + err = idt82p33_write(idt82p33, channel->dpll_mode_cnfg, + &dpll_mode, sizeof(dpll_mode)); + if (err) + return err; + + channel->pll_mode = dpll_mode; + + return 0; +} + +static int _idt82p33_gettime(struct idt82p33_channel *channel, + struct timespec64 *ts) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 buf[TOD_BYTE_COUNT]; + u8 trigger; + int err; + + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + if (err) + return err; + + if (idt82p33->calculate_overhead_flag) + idt82p33->start_time = ktime_get_raw(); + + err = idt82p33_read(idt82p33, channel->dpll_tod_sts, buf, sizeof(buf)); + + if (err) + return err; + + idt82p33_byte_array_to_timespec(ts, buf); + + return 0; +} + +/* + * TOD Trigger: + * Bits[7:4] Write 0x9, MSB write + * Bits[3:0] Read 0x9, LSB read + */ + +static int _idt82p33_settime(struct idt82p33_channel *channel, + struct timespec64 const *ts) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 local_ts = *ts; + char buf[TOD_BYTE_COUNT]; + s64 dynamic_overhead_ns; + unsigned char trigger; + int err; + u8 i; + + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + if (err) + return err; + + if (idt82p33->calculate_overhead_flag) { + dynamic_overhead_ns = ktime_to_ns(ktime_get_raw()) + - ktime_to_ns(idt82p33->start_time); + + timespec64_add_ns(&local_ts, dynamic_overhead_ns); + + idt82p33->calculate_overhead_flag = 0; + } + + idt82p33_timespec_to_byte_array(&local_ts, buf); + + /* + * Store the new time value. + */ + for (i = 0; i < TOD_BYTE_COUNT; i++) { + err = idt82p33_write(idt82p33, channel->dpll_tod_cnfg + i, + &buf[i], sizeof(buf[i])); + if (err) + return err; + } + + return err; +} + +static int _idt82p33_adjtime(struct idt82p33_channel *channel, s64 delta_ns) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 ts; + s64 now_ns; + int err; + + idt82p33->calculate_overhead_flag = 1; + + err = _idt82p33_gettime(channel, &ts); + + if (err) + return err; + + now_ns = timespec64_to_ns(&ts); + now_ns += delta_ns + idt82p33->tod_write_overhead_ns; + + ts = ns_to_timespec64(now_ns); + + err = _idt82p33_settime(channel, &ts); + + return err; +} + +static int _idt82p33_adjfine(struct idt82p33_channel *channel, long scaled_ppm) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + unsigned char buf[5] = {0}; + int neg_adj = 0; + int err, i; + s64 fcw; + + if (scaled_ppm == channel->current_freq_ppb) + return 0; + + /* + * Frequency Control Word unit is: 1.68 * 10^-10 ppm + * + * adjfreq: + * ppb * 10^9 + * FCW = ---------- + * 168 + * + * adjfine: + * scaled_ppm * 5^12 + * FCW = ------------- + * 168 * 2^4 + */ + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + + fcw = scaled_ppm * 244140625ULL; + fcw = div_u64(fcw, 2688); + + if (neg_adj) + fcw = -fcw; + + for (i = 0; i < 5; i++) { + buf[i] = fcw & 0xff; + fcw >>= 8; + } + + err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO); + + if (err) + return err; + + err = idt82p33_write(idt82p33, channel->dpll_freq_cnfg, + buf, sizeof(buf)); + + if (err == 0) + channel->current_freq_ppb = scaled_ppm; + + return err; +} + +static int idt82p33_measure_one_byte_write_overhead( + struct idt82p33_channel *channel, s64 *overhead_ns) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + ktime_t start, stop; + s64 total_ns; + u8 trigger; + int err; + u8 i; + + total_ns = 0; + *overhead_ns = 0; + trigger = TOD_TRIGGER(HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS); + + for (i = 0; i < MAX_MEASURMENT_COUNT; i++) { + + start = ktime_get_raw(); + + err = idt82p33_write(idt82p33, channel->dpll_tod_trigger, + &trigger, sizeof(trigger)); + + stop = ktime_get_raw(); + + if (err) + return err; + + total_ns += ktime_to_ns(stop) - ktime_to_ns(start); + } + + *overhead_ns = div_s64(total_ns, MAX_MEASURMENT_COUNT); + + return err; +} + +static int idt82p33_measure_tod_write_9_byte_overhead( + struct idt82p33_channel *channel) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 buf[TOD_BYTE_COUNT]; + ktime_t start, stop; + s64 total_ns; + int err = 0; + u8 i, j; + + total_ns = 0; + idt82p33->tod_write_overhead_ns = 0; + + for (i = 0; i < MAX_MEASURMENT_COUNT; i++) { + + start = ktime_get_raw(); + + /* Need one less byte for applicable overhead */ + for (j = 0; j < (TOD_BYTE_COUNT - 1); j++) { + err = idt82p33_write(idt82p33, + channel->dpll_tod_cnfg + i, + &buf[i], sizeof(buf[i])); + if (err) + return err; + } + + stop = ktime_get_raw(); + + total_ns += ktime_to_ns(stop) - ktime_to_ns(start); + } + + idt82p33->tod_write_overhead_ns = div_s64(total_ns, + MAX_MEASURMENT_COUNT); + + return err; +} + +static int idt82p33_measure_settime_gettime_gap_overhead( + struct idt82p33_channel *channel, s64 *overhead_ns) +{ + struct timespec64 ts1 = {0, 0}; + struct timespec64 ts2; + int err; + + *overhead_ns = 0; + + err = _idt82p33_settime(channel, &ts1); + + if (err) + return err; + + err = _idt82p33_gettime(channel, &ts2); + + if (!err) + *overhead_ns = timespec64_to_ns(&ts2) - timespec64_to_ns(&ts1); + + return err; +} + +static int idt82p33_measure_tod_write_overhead(struct idt82p33_channel *channel) +{ + s64 trailing_overhead_ns, one_byte_write_ns, gap_ns; + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + idt82p33->tod_write_overhead_ns = 0; + + err = idt82p33_measure_settime_gettime_gap_overhead(channel, &gap_ns); + + if (err) + return err; + + err = idt82p33_measure_one_byte_write_overhead(channel, + &one_byte_write_ns); + + if (err) + return err; + + err = idt82p33_measure_tod_write_9_byte_overhead(channel); + + if (err) + return err; + + trailing_overhead_ns = gap_ns - (2 * one_byte_write_ns); + + idt82p33->tod_write_overhead_ns -= trailing_overhead_ns; + + return err; +} + +static int idt82p33_check_and_set_masks(struct idt82p33 *idt82p33, + u8 page, + u8 offset, + u8 val) +{ + int err = 0; + + if (page == PLLMASK_ADDR_HI && offset == PLLMASK_ADDR_LO) { + if ((val & 0xfc) || !(val & 0x3)) { + dev_err(&idt82p33->client->dev, + "Invalid PLL mask 0x%hhx\n", val); + err = -EINVAL; + } else { + idt82p33->pll_mask = val; + } + } else if (page == PLL0_OUTMASK_ADDR_HI && + offset == PLL0_OUTMASK_ADDR_LO) { + idt82p33->channel[0].output_mask = val; + } else if (page == PLL1_OUTMASK_ADDR_HI && + offset == PLL1_OUTMASK_ADDR_LO) { + idt82p33->channel[1].output_mask = val; + } + + return err; +} + +static void idt82p33_display_masks(struct idt82p33 *idt82p33) +{ + u8 mask, i; + + dev_info(&idt82p33->client->dev, + "pllmask = 0x%02x\n", idt82p33->pll_mask); + + for (i = 0; i < MAX_PHC_PLL; i++) { + mask = 1 << i; + + if (mask & idt82p33->pll_mask) + dev_info(&idt82p33->client->dev, + "PLL%d output_mask = 0x%04x\n", + i, idt82p33->channel[i].output_mask); + } +} + +static int idt82p33_sync_tod(struct idt82p33_channel *channel, bool enable) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 sync_cnfg; + int err; + + if (enable == channel->sync_tod_on) { + if (enable && sync_tod_timeout) { + mod_delayed_work(system_wq, &channel->sync_tod_work, + sync_tod_timeout * HZ); + } + return 0; + } + + err = idt82p33_read(idt82p33, channel->dpll_sync_cnfg, + &sync_cnfg, sizeof(sync_cnfg)); + if (err) + return err; + + sync_cnfg &= ~SYNC_TOD; + + if (enable) + sync_cnfg |= SYNC_TOD; + + err = idt82p33_write(idt82p33, channel->dpll_sync_cnfg, + &sync_cnfg, sizeof(sync_cnfg)); + if (err) + return err; + + channel->sync_tod_on = enable; + + if (enable && sync_tod_timeout) { + mod_delayed_work(system_wq, &channel->sync_tod_work, + sync_tod_timeout * HZ); + } + + return 0; +} + +static void idt82p33_sync_tod_work_handler(struct work_struct *work) +{ + struct idt82p33_channel *channel = + container_of(work, struct idt82p33_channel, sync_tod_work.work); + struct idt82p33 *idt82p33 = channel->idt82p33; + + mutex_lock(&idt82p33->reg_lock); + + (void)idt82p33_sync_tod(channel, false); + + mutex_unlock(&idt82p33->reg_lock); +} + +static int idt82p33_pps_enable(struct idt82p33_channel *channel, bool enable) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + u8 mask, outn, val; + int err; + + mask = channel->output_mask; + outn = 0; + + while (mask) { + if (mask & 0x1) { + err = idt82p33_read(idt82p33, OUT_MUX_CNFG(outn), + &val, sizeof(val)); + if (err) + return err; + + if (enable) + val &= ~SQUELCH_ENABLE; + else + val |= SQUELCH_ENABLE; + + err = idt82p33_write(idt82p33, OUT_MUX_CNFG(outn), + &val, sizeof(val)); + + if (err) + return err; + } + mask >>= 0x1; + outn++; + } + + return 0; +} + +static int idt82p33_enable_tod(struct idt82p33_channel *channel) +{ + struct idt82p33 *idt82p33 = channel->idt82p33; + struct timespec64 ts = {0, 0}; + int err; + u8 val; + + val = 0; + err = idt82p33_write(idt82p33, channel->dpll_input_mode_cnfg, + &val, sizeof(val)); + if (err) + return err; + + err = idt82p33_pps_enable(channel, false); + + if (err) + return err; + + err = idt82p33_measure_tod_write_overhead(channel); + + if (err) + return err; + + err = _idt82p33_settime(channel, &ts); + + if (err) + return err; + + return idt82p33_sync_tod(channel, true); +} + +static void idt82p33_ptp_clock_unregister_all(struct idt82p33 *idt82p33) +{ + struct idt82p33_channel *channel; + u8 i; + + for (i = 0; i < MAX_PHC_PLL; i++) { + + channel = &idt82p33->channel[i]; + + if (channel->ptp_clock) { + ptp_clock_unregister(channel->ptp_clock); + cancel_delayed_work_sync(&channel->sync_tod_work); + } + } +} + +static int idt82p33_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + err = -EOPNOTSUPP; + + mutex_lock(&idt82p33->reg_lock); + + if (rq->type == PTP_CLK_REQ_PEROUT) { + if (!on) + err = idt82p33_pps_enable(channel, false); + + /* Only accept a 1-PPS aligned to the second. */ + else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || + rq->perout.period.nsec) { + err = -ERANGE; + } else + err = idt82p33_pps_enable(channel, true); + } + + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_adjfine(channel, scaled_ppm); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_adjtime(struct ptp_clock_info *ptp, s64 delta_ns) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + + if (abs(delta_ns) < phase_snap_threshold) { + mutex_unlock(&idt82p33->reg_lock); + return 0; + } + + err = _idt82p33_adjtime(channel, delta_ns); + + if (err) { + mutex_unlock(&idt82p33->reg_lock); + return err; + } + + err = idt82p33_sync_tod(channel, true); + + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_gettime(channel, ts); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct idt82p33_channel *channel = + container_of(ptp, struct idt82p33_channel, caps); + struct idt82p33 *idt82p33 = channel->idt82p33; + int err; + + mutex_lock(&idt82p33->reg_lock); + err = _idt82p33_settime(channel, ts); + mutex_unlock(&idt82p33->reg_lock); + + return err; +} + +static int idt82p33_channel_init(struct idt82p33_channel *channel, int index) +{ + switch (index) { + case 0: + channel->dpll_tod_cnfg = DPLL1_TOD_CNFG; + channel->dpll_tod_trigger = DPLL1_TOD_TRIGGER; + channel->dpll_tod_sts = DPLL1_TOD_STS; + channel->dpll_mode_cnfg = DPLL1_OPERATING_MODE_CNFG; + channel->dpll_freq_cnfg = DPLL1_HOLDOVER_FREQ_CNFG; + channel->dpll_phase_cnfg = DPLL1_PHASE_OFFSET_CNFG; + channel->dpll_sync_cnfg = DPLL1_SYNC_EDGE_CNFG; + channel->dpll_input_mode_cnfg = DPLL1_INPUT_MODE_CNFG; + break; + case 1: + channel->dpll_tod_cnfg = DPLL2_TOD_CNFG; + channel->dpll_tod_trigger = DPLL2_TOD_TRIGGER; + channel->dpll_tod_sts = DPLL2_TOD_STS; + channel->dpll_mode_cnfg = DPLL2_OPERATING_MODE_CNFG; + channel->dpll_freq_cnfg = DPLL2_HOLDOVER_FREQ_CNFG; + channel->dpll_phase_cnfg = DPLL2_PHASE_OFFSET_CNFG; + channel->dpll_sync_cnfg = DPLL2_SYNC_EDGE_CNFG; + channel->dpll_input_mode_cnfg = DPLL2_INPUT_MODE_CNFG; + break; + default: + return -EINVAL; + } + + INIT_DELAYED_WORK(&channel->sync_tod_work, + idt82p33_sync_tod_work_handler); + channel->sync_tod_on = false; + channel->current_freq_ppb = 0; + + return 0; +} + +static void idt82p33_caps_init(struct ptp_clock_info *caps) +{ + caps->owner = THIS_MODULE; + caps->max_adj = 92000; + caps->adjfine = idt82p33_adjfine; + caps->adjtime = idt82p33_adjtime; + caps->gettime64 = idt82p33_gettime; + caps->settime64 = idt82p33_settime; + caps->enable = idt82p33_enable; +} + +static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) +{ + struct idt82p33_channel *channel; + int err; + + if (!(index < MAX_PHC_PLL)) + return -EINVAL; + + channel = &idt82p33->channel[index]; + + err = idt82p33_channel_init(channel, index); + if (err) + return err; + + channel->idt82p33 = idt82p33; + + idt82p33_caps_init(&channel->caps); + snprintf(channel->caps.name, sizeof(channel->caps.name), + "IDT 82P33 PLL%u", index); + channel->caps.n_per_out = hweight8(channel->output_mask); + + err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO); + if (err) + return err; + + err = idt82p33_enable_tod(channel); + if (err) + return err; + + channel->ptp_clock = ptp_clock_register(&channel->caps, NULL); + + if (IS_ERR(channel->ptp_clock)) { + err = PTR_ERR(channel->ptp_clock); + channel->ptp_clock = NULL; + return err; + } + + if (!channel->ptp_clock) + return -ENOTSUPP; + + dev_info(&idt82p33->client->dev, "PLL%d registered as ptp%d\n", + index, channel->ptp_clock->index); + + return 0; +} + +static int idt82p33_load_firmware(struct idt82p33 *idt82p33) +{ + const struct firmware *fw; + struct idt82p33_fwrc *rec; + u8 loaddr, page, val; + int err; + s32 len; + + dev_dbg(&idt82p33->client->dev, + "requesting firmware '%s'\n", FW_FILENAME); + + err = request_firmware(&fw, FW_FILENAME, &idt82p33->client->dev); + + if (err) + return err; + + dev_dbg(&idt82p33->client->dev, "firmware size %zu bytes\n", fw->size); + + rec = (struct idt82p33_fwrc *) fw->data; + + for (len = fw->size; len > 0; len -= sizeof(*rec)) { + + if (rec->reserved) { + dev_err(&idt82p33->client->dev, + "bad firmware, reserved field non-zero\n"); + err = -EINVAL; + } else { + val = rec->value; + loaddr = rec->loaddr; + page = rec->hiaddr; + + rec++; + + err = idt82p33_check_and_set_masks(idt82p33, page, + loaddr, val); + } + + if (err == 0) { + /* maximum 8 pages */ + if (page >= PAGE_NUM) + continue; + + /* Page size 128, last 4 bytes of page skipped */ + if (((loaddr > 0x7b) && (loaddr <= 0x7f)) + || ((loaddr > 0xfb) && (loaddr <= 0xff))) + continue; + + err = idt82p33_write(idt82p33, _ADDR(page, loaddr), + &val, sizeof(val)); + } + + if (err) + goto out; + } + + idt82p33_display_masks(idt82p33); +out: + release_firmware(fw); + return err; +} + + +static int idt82p33_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct idt82p33 *idt82p33; + int err; + u8 i; + + (void)id; + + idt82p33 = devm_kzalloc(&client->dev, + sizeof(struct idt82p33), GFP_KERNEL); + if (!idt82p33) + return -ENOMEM; + + mutex_init(&idt82p33->reg_lock); + + idt82p33->client = client; + idt82p33->page_offset = 0xff; + idt82p33->tod_write_overhead_ns = 0; + idt82p33->calculate_overhead_flag = 0; + idt82p33->pll_mask = DEFAULT_PLL_MASK; + idt82p33->channel[0].output_mask = DEFAULT_OUTPUT_MASK_PLL0; + idt82p33->channel[1].output_mask = DEFAULT_OUTPUT_MASK_PLL1; + + mutex_lock(&idt82p33->reg_lock); + + err = idt82p33_load_firmware(idt82p33); + + if (err) + dev_warn(&idt82p33->client->dev, + "loading firmware failed with %d\n", err); + + if (idt82p33->pll_mask) { + for (i = 0; i < MAX_PHC_PLL; i++) { + if (idt82p33->pll_mask & (1 << i)) { + err = idt82p33_enable_channel(idt82p33, i); + if (err) + break; + } + } + } else { + dev_err(&idt82p33->client->dev, + "no PLLs flagged as PHCs, nothing to do\n"); + err = -ENODEV; + } + + mutex_unlock(&idt82p33->reg_lock); + + if (err) { + idt82p33_ptp_clock_unregister_all(idt82p33); + return err; + } + + i2c_set_clientdata(client, idt82p33); + + return 0; +} + +static int idt82p33_remove(struct i2c_client *client) +{ + struct idt82p33 *idt82p33 = i2c_get_clientdata(client); + + idt82p33_ptp_clock_unregister_all(idt82p33); + mutex_destroy(&idt82p33->reg_lock); + + return 0; +} + +#ifdef CONFIG_OF +static const struct of_device_id idt82p33_dt_id[] = { + { .compatible = "idt,82p33810" }, + { .compatible = "idt,82p33813" }, + { .compatible = "idt,82p33814" }, + { .compatible = "idt,82p33831" }, + { .compatible = "idt,82p33910" }, + { .compatible = "idt,82p33913" }, + { .compatible = "idt,82p33914" }, + { .compatible = "idt,82p33931" }, + {}, +}; +MODULE_DEVICE_TABLE(of, idt82p33_dt_id); +#endif + +static const struct i2c_device_id idt82p33_i2c_id[] = { + { "idt82p33810", }, + { "idt82p33813", }, + { "idt82p33814", }, + { "idt82p33831", }, + { "idt82p33910", }, + { "idt82p33913", }, + { "idt82p33914", }, + { "idt82p33931", }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, idt82p33_i2c_id); + +static struct i2c_driver idt82p33_driver = { + .driver = { + .of_match_table = of_match_ptr(idt82p33_dt_id), + .name = "idt82p33", + }, + .probe = idt82p33_probe, + .remove = idt82p33_remove, + .id_table = idt82p33_i2c_id, +}; + +module_i2c_driver(idt82p33_driver); diff --git a/drivers/ptp/ptp_idt82p33.h b/drivers/ptp/ptp_idt82p33.h new file mode 100644 index 000000000000..9d46966d25f1 --- /dev/null +++ b/drivers/ptp/ptp_idt82p33.h @@ -0,0 +1,171 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * PTP hardware clock driver for the IDT 82P33XXX family of clocks. + * + * Copyright (C) 2019 Integrated Device Technology, Inc., a Renesas Company. + */ +#ifndef PTP_IDT82P33_H +#define PTP_IDT82P33_H + +#include <linux/ktime.h> +#include <linux/workqueue.h> + + +/* Register Map - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf */ +#define PAGE_NUM (8) +#define _ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) +#define _PAGE(addr) (((addr) >> 0x7) & 0x7) +#define _OFFSET(addr) ((addr) & 0x7f) + +#define DPLL1_TOD_CNFG 0x134 +#define DPLL2_TOD_CNFG 0x1B4 + +#define DPLL1_TOD_STS 0x10B +#define DPLL2_TOD_STS 0x18B + +#define DPLL1_TOD_TRIGGER 0x115 +#define DPLL2_TOD_TRIGGER 0x195 + +#define DPLL1_OPERATING_MODE_CNFG 0x120 +#define DPLL2_OPERATING_MODE_CNFG 0x1A0 + +#define DPLL1_HOLDOVER_FREQ_CNFG 0x12C +#define DPLL2_HOLDOVER_FREQ_CNFG 0x1AC + +#define DPLL1_PHASE_OFFSET_CNFG 0x143 +#define DPLL2_PHASE_OFFSET_CNFG 0x1C3 + +#define DPLL1_SYNC_EDGE_CNFG 0X140 +#define DPLL2_SYNC_EDGE_CNFG 0X1C0 + +#define DPLL1_INPUT_MODE_CNFG 0X116 +#define DPLL2_INPUT_MODE_CNFG 0X196 + +#define OUT_MUX_CNFG(outn) _ADDR(0x6, (0xC * (outn))) + +#define PAGE_ADDR 0x7F +/* Register Map end */ + +/* Register definitions - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf*/ +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) +#define SYNC_TOD BIT(1) +#define PH_OFFSET_EN BIT(7) +#define SQUELCH_ENABLE BIT(5) + +/* Bit definitions for the DPLL_MODE register */ +#define PLL_MODE_SHIFT (0) +#define PLL_MODE_MASK (0x1F) + +enum pll_mode { + PLL_MODE_MIN = 0, + PLL_MODE_AUTOMATIC = PLL_MODE_MIN, + PLL_MODE_FORCE_FREERUN = 1, + PLL_MODE_FORCE_HOLDOVER = 2, + PLL_MODE_FORCE_LOCKED = 4, + PLL_MODE_FORCE_PRE_LOCKED2 = 5, + PLL_MODE_FORCE_PRE_LOCKED = 6, + PLL_MODE_FORCE_LOST_PHASE = 7, + PLL_MODE_DCO = 10, + PLL_MODE_WPH = 18, + PLL_MODE_MAX = PLL_MODE_WPH, +}; + +enum hw_tod_trig_sel { + HW_TOD_TRIG_SEL_MIN = 0, + HW_TOD_TRIG_SEL_NO_WRITE = HW_TOD_TRIG_SEL_MIN, + HW_TOD_TRIG_SEL_SYNC_SEL = 1, + HW_TOD_TRIG_SEL_IN12 = 2, + HW_TOD_TRIG_SEL_IN13 = 3, + HW_TOD_TRIG_SEL_IN14 = 4, + HW_TOD_TRIG_SEL_TOD_PPS = 5, + HW_TOD_TRIG_SEL_TIMER_INTERVAL = 6, + HW_TOD_TRIG_SEL_MSB_PHASE_OFFSET_CNFG = 7, + HW_TOD_TRIG_SEL_MSB_HOLDOVER_FREQ_CNFG = 8, + HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG = 9, + HW_TOD_RD_TRIG_SEL_LSB_TOD_STS = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, + WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, +}; + +/* Register bit definitions end */ +#define FW_FILENAME "idt82p33xxx.bin" +#define MAX_PHC_PLL (2) +#define TOD_BYTE_COUNT (10) +#define MAX_MEASURMENT_COUNT (5) +#define SNAP_THRESHOLD_NS (150000) +#define SYNC_TOD_TIMEOUT_SEC (5) + +#define PLLMASK_ADDR_HI 0xFF +#define PLLMASK_ADDR_LO 0xA5 + +#define PLL0_OUTMASK_ADDR_HI 0xFF +#define PLL0_OUTMASK_ADDR_LO 0xB0 + +#define PLL1_OUTMASK_ADDR_HI 0xFF +#define PLL1_OUTMASK_ADDR_LO 0xB2 + +#define PLL2_OUTMASK_ADDR_HI 0xFF +#define PLL2_OUTMASK_ADDR_LO 0xB4 + +#define PLL3_OUTMASK_ADDR_HI 0xFF +#define PLL3_OUTMASK_ADDR_LO 0xB6 + +#define DEFAULT_PLL_MASK (0x01) +#define DEFAULT_OUTPUT_MASK_PLL0 (0xc0) +#define DEFAULT_OUTPUT_MASK_PLL1 DEFAULT_OUTPUT_MASK_PLL0 + +/* PTP Hardware Clock interface */ +struct idt82p33_channel { + struct ptp_clock_info caps; + struct ptp_clock *ptp_clock; + struct idt82p33 *idt82p33; + enum pll_mode pll_mode; + /* task to turn off SYNC_TOD bit after pps sync */ + struct delayed_work sync_tod_work; + bool sync_tod_on; + s32 current_freq_ppb; + u8 output_mask; + u16 dpll_tod_cnfg; + u16 dpll_tod_trigger; + u16 dpll_tod_sts; + u16 dpll_mode_cnfg; + u16 dpll_freq_cnfg; + u16 dpll_phase_cnfg; + u16 dpll_sync_cnfg; + u16 dpll_input_mode_cnfg; +}; + +struct idt82p33 { + struct idt82p33_channel channel[MAX_PHC_PLL]; + struct i2c_client *client; + u8 page_offset; + u8 pll_mask; + ktime_t start_time; + int calculate_overhead_flag; + s64 tod_write_overhead_ns; + /* Protects I2C read/modify/write registers from concurrent access */ + struct mutex reg_lock; +}; + +/* firmware interface */ +struct idt82p33_fwrc { + u8 hiaddr; + u8 loaddr; + u8 value; + u8 reserved; +} __packed; + +/** + * @brief Maximum absolute value for write phase offset in femtoseconds + */ +#define WRITE_PHASE_OFFSET_LIMIT (20000052084ll) + +/** @brief Phase offset resolution + * + * DPLL phase offset = 10^15 fs / ( System Clock * 2^13) + * = 10^15 fs / ( 1638400000 * 2^23) + * = 74.5058059692382 fs + */ +#define IDT_T0DPLL_PHASE_RESOL 74506 + + +#endif /* PTP_IDT82P33_H */ diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index b27c46ebfc8f..c09c16be0edf 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -131,8 +131,7 @@ irqreturn_t ptp_qoriq_isr(int irq, void *priv) struct ptp_qoriq *ptp_qoriq = priv; struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; struct ptp_clock_event event; - u64 ns; - u32 ack = 0, lo, hi, mask, val, irqs; + u32 ack = 0, mask, val, irqs; spin_lock(&ptp_qoriq->lock); @@ -153,32 +152,6 @@ irqreturn_t ptp_qoriq_isr(int irq, void *priv) extts_clean_up(ptp_qoriq, 1, true); } - if (irqs & ALM2) { - ack |= ALM2; - if (ptp_qoriq->alarm_value) { - event.type = PTP_CLOCK_ALARM; - event.index = 0; - event.timestamp = ptp_qoriq->alarm_value; - ptp_clock_event(ptp_qoriq->clock, &event); - } - if (ptp_qoriq->alarm_interval) { - ns = ptp_qoriq->alarm_value + ptp_qoriq->alarm_interval; - hi = ns >> 32; - lo = ns & 0xffffffff; - ptp_qoriq->write(®s->alarm_regs->tmr_alarm2_l, lo); - ptp_qoriq->write(®s->alarm_regs->tmr_alarm2_h, hi); - ptp_qoriq->alarm_value = ns; - } else { - spin_lock(&ptp_qoriq->lock); - mask = ptp_qoriq->read(®s->ctrl_regs->tmr_temask); - mask &= ~ALM2EN; - ptp_qoriq->write(®s->ctrl_regs->tmr_temask, mask); - spin_unlock(&ptp_qoriq->lock); - ptp_qoriq->alarm_value = 0; - ptp_qoriq->alarm_interval = 0; - } - } - if (irqs & PP1) { ack |= PP1; event.type = PTP_CLOCK_PPS; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 9575a627a1e1..b7d64690ea38 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -189,6 +189,8 @@ struct qeth_vnicc_info { #define QETH_IQD_MIN_TXQ 2 /* One for ucast, one for mcast. */ #define QETH_IQD_MCAST_TXQ 0 #define QETH_IQD_MIN_UCAST_TXQ 1 + +#define QETH_RX_COPYBREAK (PAGE_SIZE >> 1) #define QETH_IN_BUF_SIZE_DEFAULT 65536 #define QETH_IN_BUF_COUNT_DEFAULT 64 #define QETH_IN_BUF_COUNT_HSDEFAULT 128 @@ -219,9 +221,6 @@ struct qeth_vnicc_info { #define QETH_HIGH_WATERMARK_PACK 5 #define QETH_WATERMARK_PACK_FUZZ 1 -/* large receive scatter gather copy break */ -#define QETH_RX_SG_CB (PAGE_SIZE >> 1) - struct qeth_hdr_layer3 { __u8 id; __u8 flags; @@ -711,7 +710,6 @@ struct qeth_card_options { struct qeth_vnicc_info vnicc; /* VNICC options */ int fake_broadcast; enum qeth_discipline_id layer; - int rx_sg_cb; enum qeth_ipa_isolation_modes isolation; enum qeth_ipa_isolation_modes prev_isolation; int sniffer; @@ -770,6 +768,10 @@ struct qeth_switch_info { __u32 settings; }; +struct qeth_priv { + unsigned int rx_copybreak; +}; + #define QETH_NAPI_WEIGHT NAPI_POLL_WEIGHT struct qeth_card { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8ca85c8a01a1..fdc50543ce9a 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -742,7 +742,7 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, /* fall through */ default: qeth_clear_ipacmd_list(card); - goto out; + goto err_idx; } cmd = __ipa_reply(iob); @@ -795,8 +795,9 @@ out: memcpy(&card->seqno.pdu_hdr_ack, QETH_PDU_HEADER_SEQ_NO(iob->data), QETH_SEQ_NO_LENGTH); - qeth_put_cmd(iob); __qeth_issue_next_read(card); +err_idx: + qeth_put_cmd(iob); } static int qeth_set_thread_start_bit(struct qeth_card *card, @@ -1257,7 +1258,6 @@ static void qeth_set_initial_options(struct qeth_card *card) { card->options.route4.type = NO_ROUTER; card->options.route6.type = NO_ROUTER; - card->options.rx_sg_cb = QETH_RX_SG_CB; card->options.isolation = ISOLATION_MODE_NONE; card->options.cq = QETH_CQ_DISABLED; card->options.layer = QETH_DISCIPLINE_UNDETERMINED; @@ -1625,17 +1625,16 @@ static void qeth_set_blkt_defaults(struct qeth_card *card) } } -static void qeth_init_tokens(struct qeth_card *card) +static void qeth_idx_init(struct qeth_card *card) { + memset(&card->seqno, 0, sizeof(card->seqno)); + card->token.issuer_rm_w = 0x00010103UL; card->token.cm_filter_w = 0x00010108UL; card->token.cm_connection_w = 0x0001010aUL; card->token.ulp_filter_w = 0x0001010bUL; card->token.ulp_connection_w = 0x0001010dUL; -} -static void qeth_init_func_level(struct qeth_card *card) -{ switch (card->info.type) { case QETH_CARD_TYPE_IQD: card->info.func_level = QETH_IDX_FUNC_LEVEL_IQD; @@ -3407,8 +3406,7 @@ static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue, { struct qeth_card *card = (struct qeth_card *)card_ptr; - if (card->dev->flags & IFF_UP) - napi_schedule_irqoff(&card->napi); + napi_schedule_irqoff(&card->napi); } int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) @@ -4952,9 +4950,9 @@ retriable: else goto retry; } + qeth_determine_capabilities(card); - qeth_init_tokens(card); - qeth_init_func_level(card); + qeth_idx_init(card); rc = qeth_idx_activate_read_channel(card); if (rc == -EINTR) { @@ -5269,6 +5267,7 @@ static int qeth_extract_skb(struct qeth_card *card, int *__offset) { struct qdio_buffer_element *element = *__element; + struct qeth_priv *priv = netdev_priv(card->dev); struct qdio_buffer *buffer = qethbuffer->buffer; struct napi_struct *napi = &card->napi; unsigned int linear_len = 0; @@ -5344,7 +5343,7 @@ next_packet: } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - (skb_len > card->options.rx_sg_cb && + (skb_len > READ_ONCE(priv->rx_copybreak) && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); @@ -5893,25 +5892,30 @@ static void qeth_clear_dbf_list(void) static struct net_device *qeth_alloc_netdev(struct qeth_card *card) { struct net_device *dev; + struct qeth_priv *priv; switch (card->info.type) { case QETH_CARD_TYPE_IQD: - dev = alloc_netdev_mqs(0, "hsi%d", NET_NAME_UNKNOWN, + dev = alloc_netdev_mqs(sizeof(*priv), "hsi%d", NET_NAME_UNKNOWN, ether_setup, QETH_MAX_QUEUES, 1); break; case QETH_CARD_TYPE_OSM: - dev = alloc_etherdev(0); + dev = alloc_etherdev(sizeof(*priv)); break; case QETH_CARD_TYPE_OSN: - dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup); + dev = alloc_netdev(sizeof(*priv), "osn%d", NET_NAME_UNKNOWN, + ether_setup); break; default: - dev = alloc_etherdev_mqs(0, QETH_MAX_QUEUES, 1); + dev = alloc_etherdev_mqs(sizeof(*priv), QETH_MAX_QUEUES, 1); } if (!dev) return NULL; + priv = netdev_priv(dev); + priv->rx_copybreak = QETH_RX_COPYBREAK; + dev->ml_priv = card; dev->watchdog_timeo = QETH_TX_TIMEOUT; dev->min_mtu = IS_OSN(card) ? 64 : 576; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 3865f7258449..6f304fdbb073 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -93,10 +93,6 @@ enum qeth_link_types { QETH_LINK_TYPE_LANE = 0x88, }; -/* - * Routing stuff - */ -#define RESET_ROUTING_FLAG 0x10 /* indicate that routing type shall be set */ enum qeth_routing_types { /* TODO: set to bit flag used in IPA Command */ NO_ROUTER = 0, @@ -427,7 +423,6 @@ struct qeth_ipacmd_setassparms { struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; - __u8 ip[16]; } data; } __attribute__ ((packed)); @@ -550,8 +545,9 @@ struct qeth_ipacmd_setadpparms { /* CREATE_ADDR IPA Command: ***********************************************/ struct qeth_create_destroy_address { - __u8 unique_id[8]; -} __attribute__ ((packed)); + u8 mac_addr[ETH_ALEN]; + u16 uid; +}; /* SET DIAGNOSTIC ASSIST IPA Command: *************************************/ diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index ab59bc975719..9052c72d5b8f 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -175,6 +175,35 @@ static void qeth_get_channels(struct net_device *dev, channels->combined_count = 0; } +static int qeth_get_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, void *data) +{ + struct qeth_priv *priv = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = priv->rx_copybreak; + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int qeth_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct qeth_priv *priv = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + WRITE_ONCE(priv->rx_copybreak, *(u32 *)data); + return 0; + default: + return -EOPNOTSUPP; + } +} + /* Helper function to fill 'advertising' and 'supported' which are the same. */ /* Autoneg and full-duplex are supported and advertised unconditionally. */ /* Always advertise and support all speeds up to specified, and only one */ @@ -381,6 +410,8 @@ const struct ethtool_ops qeth_ethtool_ops = { .get_sset_count = qeth_get_sset_count, .get_drvinfo = qeth_get_drvinfo, .get_channels = qeth_get_channels, + .get_tunable = qeth_get_tunable, + .set_tunable = qeth_set_tunable, .get_link_ksettings = qeth_get_link_ksettings, }; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 317d56647a4a..1000e18c1090 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -920,9 +920,11 @@ static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card, if (cmd->hdr.return_code) return -EIO; + if (!is_valid_ether_addr(cmd->data.create_destroy_addr.mac_addr)) + return -EADDRNOTAVAIL; ether_addr_copy(card->dev->dev_addr, - cmd->data.create_destroy_addr.unique_id); + cmd->data.create_destroy_addr.mac_addr); return 0; } @@ -930,7 +932,6 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) { int rc = 0; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; QETH_CARD_TEXT(card, 2, "hsrmac"); @@ -938,9 +939,6 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; - cmd = __ipa_cmd(iob); - *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = - card->info.unique_id; rc = qeth_send_ipa_cmd(card, iob, qeth_l3_iqd_read_initial_mac_cb, NULL); @@ -953,8 +951,7 @@ static int qeth_l3_get_unique_id_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; if (cmd->hdr.return_code == 0) { - card->info.unique_id = *((__u16 *) - &cmd->data.create_destroy_addr.unique_id[6]); + card->info.unique_id = cmd->data.create_destroy_addr.uid; return 0; } @@ -968,7 +965,6 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) { int rc = 0; struct qeth_cmd_buffer *iob; - struct qeth_ipa_cmd *cmd; QETH_CARD_TEXT(card, 2, "guniqeid"); @@ -982,10 +978,8 @@ static int qeth_l3_get_unique_id(struct qeth_card *card) IPA_DATA_SIZEOF(create_destroy_addr)); if (!iob) return -ENOMEM; - cmd = __ipa_cmd(iob); - *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]) = - card->info.unique_id; + __ipa_cmd(iob)->data.create_destroy_addr.uid = card->info.unique_id; rc = qeth_send_ipa_cmd(card, iob, qeth_l3_get_unique_id_cb, NULL); return rc; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 130fc6fbcc03..26bbf960e2a2 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -558,3 +558,151 @@ void sysfs_remove_bin_file(struct kobject *kobj, kernfs_remove_by_name(kobj->sd, attr->attr.name); } EXPORT_SYMBOL_GPL(sysfs_remove_bin_file); + +static int internal_change_owner(struct kernfs_node *kn, kuid_t kuid, + kgid_t kgid) +{ + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + return kernfs_setattr(kn, &newattrs); +} + +/** + * sysfs_link_change_owner - change owner of a sysfs file. + * @kobj: object of the kernfs_node the symlink is located in. + * @targ: object of the kernfs_node the symlink points to. + * @name: name of the link. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This function looks up the sysfs symlink entry @name under @kobj and changes + * the ownership to @kuid/@kgid. The symlink is looked up in the namespace of + * @targ. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid) +{ + struct kernfs_node *kn = NULL; + int error; + + if (!name || !kobj->state_in_sysfs || !targ->state_in_sysfs) + return -EINVAL; + + error = -ENOENT; + kn = kernfs_find_and_get_ns(kobj->sd, name, targ->sd->ns); + if (!kn) + goto out; + + error = -EINVAL; + if (kernfs_type(kn) != KERNFS_LINK) + goto out; + if (kn->symlink.target_kn->priv != targ) + goto out; + + error = internal_change_owner(kn, kuid, kgid); + +out: + kernfs_put(kn); + return error; +} + +/** + * sysfs_file_change_owner - change owner of a sysfs file. + * @kobj: object. + * @name: name of the file to change. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * This function looks up the sysfs entry @name under @kobj and changes the + * ownership to @kuid/@kgid. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *kn; + int error; + + if (!name) + return -EINVAL; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + kn = kernfs_find_and_get(kobj->sd, name); + if (!kn) + return -ENOENT; + + error = internal_change_owner(kn, kuid, kgid); + + kernfs_put(kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_file_change_owner); + +/** + * sysfs_change_owner - change owner of the given object. + * @kobj: object. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Change the owner of the default directory, files, groups, and attributes of + * @kobj to @kuid/@kgid. Note that sysfs_change_owner mirrors how the sysfs + * entries for a kobject are added by driver core. In summary, + * sysfs_change_owner() takes care of the default directory entry for @kobj, + * the default attributes associated with the ktype of @kobj and the default + * attributes associated with the ktype of @kobj. + * Additional properties not added by driver core have to be changed by the + * driver or subsystem which created them. This is similar to how + * driver/subsystem specific entries are removed. + * + * Returns 0 on success or error code on failure. + */ +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + int error; + const struct kobj_type *ktype; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + /* Change the owner of the kobject itself. */ + error = internal_change_owner(kobj->sd, kuid, kgid); + if (error) + return error; + + ktype = get_ktype(kobj); + if (ktype) { + struct attribute **kattr; + + /* + * Change owner of the default attributes associated with the + * ktype of @kobj. + */ + for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { + error = sysfs_file_change_owner(kobj, (*kattr)->name, + kuid, kgid); + if (error) + return error; + } + + /* + * Change owner of the default groups associated with the + * ktype of @kobj. + */ + error = sysfs_groups_change_owner(kobj, ktype->default_groups, + kuid, kgid); + if (error) + return error; + } + + return 0; +} +EXPORT_SYMBOL_GPL(sysfs_change_owner); diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index c4ab045926b7..5afe0e7ff7cd 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -13,6 +13,7 @@ #include <linux/dcache.h> #include <linux/namei.h> #include <linux/err.h> +#include <linux/fs.h> #include "sysfs.h" @@ -457,3 +458,117 @@ int __compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, return PTR_ERR_OR_ZERO(link); } EXPORT_SYMBOL_GPL(__compat_only_sysfs_link_entry_to_kobj); + +static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, + const struct attribute_group *grp, + struct iattr *newattrs) +{ + struct kernfs_node *kn; + int error; + + if (grp->attrs) { + struct attribute *const *attr; + + for (attr = grp->attrs; *attr; attr++) { + kn = kernfs_find_and_get(grp_kn, (*attr)->name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + if (grp->bin_attrs) { + struct bin_attribute *const *bin_attr; + + for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); + if (!kn) + return -ENOENT; + + error = kernfs_setattr(kn, newattrs); + kernfs_put(kn); + if (error) + return error; + } + } + + return 0; +} + +/** + * sysfs_group_change_owner - change owner of an attribute group. + * @kobj: The kobject containing the group. + * @grp: The attribute group. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *grp, kuid_t kuid, + kgid_t kgid) +{ + struct kernfs_node *grp_kn; + int error; + struct iattr newattrs = { + .ia_valid = ATTR_UID | ATTR_GID, + .ia_uid = kuid, + .ia_gid = kgid, + }; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (grp->name) { + grp_kn = kernfs_find_and_get(kobj->sd, grp->name); + } else { + kernfs_get(kobj->sd); + grp_kn = kobj->sd; + } + if (!grp_kn) + return -ENOENT; + + error = kernfs_setattr(grp_kn, &newattrs); + if (!error) + error = sysfs_group_attrs_change_owner(grp_kn, grp, &newattrs); + + kernfs_put(grp_kn); + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_group_change_owner); + +/** + * sysfs_groups_change_owner - change owner of a set of attribute groups. + * @kobj: The kobject containing the groups. + * @groups: The attribute groups. + * @kuid: new owner's kuid + * @kgid: new owner's kgid + * + * Returns 0 on success or error code on failure. + */ +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + int error = 0, i; + + if (!kobj->state_in_sysfs) + return -EINVAL; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = sysfs_group_change_owner(kobj, groups[i], kuid, kgid); + if (error) + break; + } + + return error; +} +EXPORT_SYMBOL_GPL(sysfs_groups_change_owner); diff --git a/include/linux/device.h b/include/linux/device.h index 0cd7c647c16c..3e40533d2037 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -817,6 +817,7 @@ extern struct device *device_find_child_by_name(struct device *parent, extern int device_rename(struct device *dev, const char *new_name); extern int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); +extern int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); extern const char *device_get_devnode(struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index b0b743563f43..75884563059f 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -149,8 +149,6 @@ struct ptp_qoriq { bool extts_fifo_support; int irq; int phc_index; - u64 alarm_interval; /* for periodic alarm */ - u64 alarm_value; u32 tclk_period; /* nanoseconds */ u32 tmr_prsc; u32 tmr_add; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7d3f2ced92d1..33d907eec0b6 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -620,6 +620,15 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee80211_is_any_nullfunc(__le16 fc) +{ + return (ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)); +} + +/** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @fc: frame control field in little-endian byteorder */ @@ -2047,13 +2056,13 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 #define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 #define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 +#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size - * @he_oper_ie: byte data of the He Operations IE, stating from the the byte + * @he_oper_ie: byte data of the He Operations IE, stating from the byte * after the ext ID byte. It is assumed that he_oper_ie has at least * sizeof(struct ieee80211_he_operation) bytes, the caller must have * validated this. @@ -2091,7 +2100,7 @@ ieee80211_he_oper_size(const u8 *he_oper_ie) /* * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size - * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the the byte + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte * after the ext ID byte. It is assumed that he_spr_ie has at least * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated * this @@ -2523,6 +2532,7 @@ enum ieee80211_eid { WLAN_EID_FILS_INDICATION = 240, WLAN_EID_DILS = 241, WLAN_EID_FRAGMENT = 242, + WLAN_EID_RSNX = 244, WLAN_EID_EXTENSION = 255 }; @@ -2734,7 +2744,7 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) -/* TDLS capabilities in the the 4th byte of @WLAN_EID_EXT_CAPABILITY */ +/* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) #define WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH BIT(6) @@ -3034,6 +3044,7 @@ struct ieee80211_multiple_bssid_configuration { #define WLAN_AKM_SUITE_FILS_SHA384 SUITE(0x000FAC, 15) #define WLAN_AKM_SUITE_FT_FILS_SHA256 SUITE(0x000FAC, 16) #define WLAN_AKM_SUITE_FT_FILS_SHA384 SUITE(0x000FAC, 17) +#define WLAN_AKM_SUITE_OWE SUITE(0x000FAC, 18) #define WLAN_MAX_KEY_LEN 32 @@ -3412,4 +3423,11 @@ static inline bool for_each_element_completed(const struct element *element, return (const u8 *)element == (const u8 *)data + datalen; } +/** + * RSNX Capabilities: + * bits 0-3: Field length (n-1) + */ +#define WLAN_RSNX_CAPA_PROTECTED_TWT BIT(4) +#define WLAN_RSNX_CAPA_SAE_H2E BIT(5) + #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index fe740031339d..c664c27a29a0 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -71,7 +71,7 @@ static inline void linkmode_change_bit(int nr, volatile unsigned long *addr) __change_bit(nr, addr); } -static inline int linkmode_test_bit(int nr, volatile unsigned long *addr) +static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) { return test_bit(nr, addr); } @@ -88,4 +88,10 @@ static inline int linkmode_subset(const unsigned long *src1, return bitmap_subset(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +void linkmode_resolve_pause(const unsigned long *local_adv, + const unsigned long *partner_adv, + bool *tx_pause, bool *rx_pause); + +void linkmode_set_pause(unsigned long *advertisement, bool tx, bool rx); + #endif /* __LINKMODE_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 277a51d3ec40..f99cbe249425 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -722,6 +722,7 @@ struct mlx5_core_dev { struct mlx5_clock clock; struct mlx5_ib_clock_info *clock_info; struct mlx5_fw_tracer *tracer; + struct mlx5_rsc_dump *rsc_dump; u32 vsc_addr; struct mlx5_hv_vhca *hv_vhca; }; diff --git a/include/linux/phy.h b/include/linux/phy.h index c570e162e05e..e72dbd0d2d6a 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -289,6 +289,7 @@ static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) return devm_mdiobus_alloc_size(dev, 0); } +struct mii_bus *mdio_find_bus(const char *mdio_name); void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); @@ -1257,6 +1258,9 @@ void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); +void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); +void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, + bool *tx_pause, bool *rx_pause); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 523209e70947..2180eb1aa254 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -12,12 +12,10 @@ struct net_device; enum { MLO_PAUSE_NONE, - MLO_PAUSE_ASYM = BIT(0), - MLO_PAUSE_SYM = BIT(1), - MLO_PAUSE_RX = BIT(2), - MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_RX = BIT(0), + MLO_PAUSE_TX = BIT(1), MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, - MLO_PAUSE_AN = BIT(4), + MLO_PAUSE_AN = BIT(2), MLO_AN_PHY = 0, /* Conventional PHY */ MLO_AN_FIXED, /* Fixed-link mode */ @@ -93,9 +91,10 @@ struct phylink_mac_ops { void (*mac_an_restart)(struct phylink_config *config); void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); + void (*mac_link_up)(struct phylink_config *config, + struct phy_device *phy, unsigned int mode, + phy_interface_t interface, int speed, int duplex, + bool tx_pause, bool rx_pause); }; #if 0 /* For kernel-doc purposes only. */ @@ -154,15 +153,33 @@ void mac_pcs_get_state(struct phylink_config *config, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * (this requires a rewrite - please refer to mac_link_up() for situations + * where the PCS and MAC are not tightly integrated.) + * + * In all negotiation modes, as defined by @mode, @state->pause indicates the + * pause settings which should be applied as follows. If %MLO_PAUSE_AN is not + * set, %MLO_PAUSE_TX and %MLO_PAUSE_RX indicate whether the MAC should send + * pause frames and/or act on received pause frames respectively. Otherwise, + * the results of in-band negotiation/status from the MAC PCS should be used + * to control the MAC pause mode settings. + * * The action performed depends on the currently selected mode: * * %MLO_AN_FIXED, %MLO_AN_PHY: - * Configure the specified @state->speed, @state->duplex and - * @state->pause (%MLO_PAUSE_TX / %MLO_PAUSE_RX) modes over a link - * specified by @state->interface. @state->advertising may be used, - * but is not required. Other members of @state must be ignored. + * Configure for non-inband negotiation mode, where the link settings + * are completely communicated via mac_link_up(). The physical link + * protocol from the MAC is specified by @state->interface. + * + * @state->advertising may be used, but is not required. * - * Valid state members: interface, speed, duplex, pause, advertising. + * Older drivers (prior to the mac_link_up() change) may use @state->speed, + * @state->duplex and @state->pause to configure the MAC, but this is + * deprecated; such drivers should be converted to use mac_link_up(). + * + * Other members of @state must be ignored. + * + * Valid state members: interface, advertising. + * Deprecated state members: speed, duplex, pause. * * %MLO_AN_INBAND: * place the link in an inband negotiation mode (such as 802.3z @@ -172,11 +189,14 @@ void mac_pcs_get_state(struct phylink_config *config, * mac_pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * + * Interface mode specific details are mentioned below. + * * If in 802.3z mode, the link speed is fixed, dependent on the - * @state->interface. Duplex is negotiated, and pause is advertised - * according to @state->an_enabled, @state->pause and - * @state->advertising flags. Beware of MACs which only support full - * duplex at gigabit and higher speeds. + * @state->interface. Duplex and pause modes are negotiated via + * the in-band configuration word. Advertised pause modes are set + * according to the @state->an_enabled and @state->advertising + * flags. Beware of MACs which only support full duplex at gigabit + * and higher speeds. * * If in Cisco SGMII mode, the link speed and duplex mode are passed * in the serial bitstream 16-bit configuration word, and the MAC @@ -220,19 +240,34 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, /** * mac_link_up() - allow the link to come up * @config: a pointer to a &struct phylink_config. + * @phy: any attached phy * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode - * @phy: any attached phy + * @speed: link speed + * @duplex: link duplex + * @tx_pause: link transmit pause enablement status + * @rx_pause: link receive pause enablement status * - * If @mode is not an in-band negotiation mode (as defined by - * phylink_autoneg_inband()), allow the link to come up. If @phy - * is non-%NULL, configure Energy Efficient Ethernet by calling + * Configure the MAC for an established link. + * + * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link + * settings, and should be used to configure the MAC block appropriately + * where these settings are not automatically conveyed from the PCS block, + * or if in-band negotiation (as defined by phylink_autoneg_inband(@mode)) + * is disabled. + * + * Note that when 802.3z in-band negotiation is in use, it is possible + * that the user wishes to override the pause settings, and this should + * be allowed when considering the implementation of this method. + * + * If in-band negotiation mode is disabled, allow the link to come up. If + * @phy is non-%NULL, configure Energy Efficient Ethernet by calling * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ -void mac_link_up(struct phylink_config *config, unsigned int mode, - phy_interface_t interface, - struct phy_device *phy); +void mac_link_up(struct phylink_config *config, struct phy_device *phy, + unsigned int mode, phy_interface_t interface, + int speed, int duplex, bool tx_pause, bool rx_pause); #endif struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14d61bba0b79..112765bd146d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -352,29 +352,15 @@ static inline void sk_psock_update_proto(struct sock *sk, psock->saved_write_space = sk->sk_write_space; psock->sk_proto = sk->sk_prot; - sk->sk_prot = ops; + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, ops); } static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - - if (psock->sk_proto) { - struct inet_connection_sock *icsk = inet_csk(sk); - bool has_ulp = !!icsk->icsk_ulp_data; - - if (has_ulp) { - tcp_update_ulp(sk, psock->sk_proto, - psock->saved_write_space); - } else { - sk->sk_prot = psock->sk_proto; - sk->sk_write_space = psock->saved_write_space; - } - psock->sk_proto = NULL; - } else { - sk->sk_write_space = psock->saved_write_space; - } + tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } static inline void sk_psock_set_state(struct sk_psock *psock, diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index fa7ee503fb76..9e531ec76274 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -310,6 +310,18 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) return kernfs_enable_ns(kn); } +int sysfs_file_change_owner(struct kobject *kobj, const char *name, kuid_t kuid, + kgid_t kgid); +int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid); +int sysfs_link_change_owner(struct kobject *kobj, struct kobject *targ, + const char *name, kuid_t kuid, kgid_t kgid); +int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid); +int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group *groups, kuid_t kuid, + kgid_t kgid); + #else /* CONFIG_SYSFS */ static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) @@ -522,6 +534,40 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn) { } +static inline int sysfs_file_change_owner(struct kobject *kobj, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_link_change_owner(struct kobject *kobj, + struct kobject *targ, + const char *name, kuid_t kuid, + kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_groups_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + +static inline int sysfs_group_change_owner(struct kobject *kobj, + const struct attribute_group **groups, + kuid_t kuid, kgid_t kgid) +{ + return 0; +} + #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/net/bareudp.h b/include/net/bareudp.h new file mode 100644 index 000000000000..cb03f6f15956 --- /dev/null +++ b/include/net/bareudp.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NET_BAREUDP_H +#define __NET_BAREUDP_H + +#include <linux/types.h> +#include <linux/skbuff.h> + +struct bareudp_conf { + __be16 ethertype; + __be16 port; + u16 sport_min; + bool multi_proto_mode; +}; + +struct net_device *bareudp_dev_create(struct net *net, const char *name, + u8 name_assign_type, + struct bareudp_conf *info); + +#endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f22bd6c838a3..f7c84c32ba39 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -72,12 +72,12 @@ struct wiphy; * * @IEEE80211_CHAN_DISABLED: This channel is disabled. * @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes - * sending probe requests or beaconing. + * sending probe requests or beaconing. * @IEEE80211_CHAN_RADAR: Radar detection is required on this channel. * @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel - * is not permitted. + * is not permitted. * @IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel - * is not permitted. + * is not permitted. * @IEEE80211_CHAN_NO_OFDM: OFDM is not allowed on this channel. * @IEEE80211_CHAN_NO_80MHZ: If the driver supports 80 MHz on the band, * this flag indicates that an 80 MHz channel cannot use this @@ -95,6 +95,7 @@ struct wiphy; * on this channel. * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted * on this channel. + * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel. * */ enum ieee80211_channel_flags { @@ -111,6 +112,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_IR_CONCURRENT = 1<<10, IEEE80211_CHAN_NO_20MHZ = 1<<11, IEEE80211_CHAN_NO_10MHZ = 1<<12, + IEEE80211_CHAN_NO_HE = 1<<13, }; #define IEEE80211_CHAN_NO_HT40 \ @@ -260,6 +262,32 @@ struct ieee80211_he_obss_pd { }; /** + * struct cfg80211_he_bss_color - AP settings for BSS coloring + * + * @color: the current color. + * @disabled: is the feature disabled. + * @partial: define the AID equation. + */ +struct cfg80211_he_bss_color { + u8 color; + bool disabled; + bool partial; +}; + +/** + * struct ieee80211_he_bss_color - AP settings for BSS coloring + * + * @color: the current color. + * @disabled: is the feature disabled. + * @partial: define the AID equation. + */ +struct ieee80211_he_bss_color { + u8 color; + bool disabled; + bool partial; +}; + +/** * struct ieee80211_sta_ht_cap - STA's HT capabilities * * This structure describes most essential parameters needed @@ -599,6 +627,41 @@ struct cfg80211_chan_def { }; /** + * struct cfg80211_tid_cfg - TID specific configuration + * @config_override: Flag to notify driver to reset TID configuration + * of the peer. + * @tids: bitmap of TIDs to modify + * @mask: bitmap of attributes indicating which parameter changed, + * similar to &nl80211_tid_config_supp. + * @noack: noack configuration value for the TID + * @retry_long: retry count value + * @retry_short: retry count value + * @ampdu: Enable/Disable aggregation + * @rtscts: Enable/Disable RTS/CTS + */ +struct cfg80211_tid_cfg { + bool config_override; + u8 tids; + u32 mask; + enum nl80211_tid_config noack; + u8 retry_long, retry_short; + enum nl80211_tid_config ampdu; + enum nl80211_tid_config rtscts; +}; + +/** + * struct cfg80211_tid_config - TID configuration + * @peer: Station's MAC address + * @n_tid_conf: Number of TID specific configurations to be applied + * @tid_conf: Configuration change info + */ +struct cfg80211_tid_config { + const u8 *peer; + u32 n_tid_conf; + struct cfg80211_tid_cfg tid_conf[]; +}; + +/** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition * @@ -990,6 +1053,7 @@ enum cfg80211_ap_settings_flags { * @twt_responder: Enable Target Wait Time * @flags: flags, as defined in enum cfg80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings + * @he_bss_color: BSS Color settings */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1018,6 +1082,7 @@ struct cfg80211_ap_settings { bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; + struct cfg80211_he_bss_color he_bss_color; }; /** @@ -1656,7 +1721,7 @@ struct mpath_info { * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations * @ht_opmode: HT Operation mode - * (u16 = opmode, -1 = do not change) + * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) * @p2p_opp_ps: P2P opportunistic PS (-1 = no change) */ @@ -2032,8 +2097,8 @@ struct cfg80211_bss_select_adjust { * @ie_len: length of ie in octets * @flags: bit field of flags controlling operation * @match_sets: sets of parameters to be matched for a scan result - * entry to be considered valid and to be passed to the host - * (others are filtered out). + * entry to be considered valid and to be passed to the host + * (others are filtered out). * If ommited, all results are passed. * @n_match_sets: number of match sets * @report_results: indicates that results were reported for this request @@ -2426,7 +2491,7 @@ struct cfg80211_disassoc_request { * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. * @wep_keys: static WEP keys, if not NULL points to an array of - * CFG80211_MAX_WEP_KEYS WEP keys + * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key */ struct cfg80211_ibss_params { @@ -3339,6 +3404,8 @@ struct cfg80211_update_owe_info { * @set_default_key: set the default key on an interface * * @set_default_mgmt_key: set the default management frame key on an interface + + * @set_default_beacon_key: set the default Beacon frame key on an interface * * @set_rekey_data: give the data necessary for GTK rekeying to the driver * @@ -3639,6 +3706,10 @@ struct cfg80211_update_owe_info { * * @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame * and overrule HWMP path selection algorithm. + * @set_tid_config: TID specific configuration, this can be peer or BSS specific + * This callback may sleep. + * @reset_tid_config: Reset TID specific configuration for the peer, for the + * given TIDs. This callback may sleep. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3672,6 +3743,9 @@ struct cfg80211_ops { int (*set_default_mgmt_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index); + int (*set_default_beacon_key)(struct wiphy *wiphy, + struct net_device *netdev, + u8 key_index); int (*start_ap)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *settings); @@ -3959,6 +4033,10 @@ struct cfg80211_ops { struct cfg80211_update_owe_info *owe_info); int (*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); + int (*set_tid_config)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_tid_config *tid_conf); + int (*reset_tid_config)(struct wiphy *wiphy, struct net_device *dev, + const u8 *peer, u8 tids); }; /* @@ -4376,19 +4454,42 @@ struct cfg80211_pmsr_capabilities { }; /** + * struct wiphy_iftype_akm_suites - This structure encapsulates supported akm + * suites for interface types defined in @iftypes_mask. Each type in the + * @iftypes_mask must be unique across all instances of iftype_akm_suites. + * + * @iftypes_mask: bitmask of interfaces types + * @akm_suites: points to an array of supported akm suites + * @n_akm_suites: number of supported AKM suites + */ +struct wiphy_iftype_akm_suites { + u16 iftypes_mask; + const u32 *akm_suites; + int n_akm_suites; +}; + +/** * struct wiphy - wireless hardware description * @reg_notifier: the driver's regulatory notification callback, * note that if your driver uses wiphy_apply_custom_regulatory() * the reg_notifier's request can be passed as NULL * @regd: the driver's regulatory domain, if one was requested via - * the regulatory_hint() API. This can be used by the driver + * the regulatory_hint() API. This can be used by the driver * on the reg_notifier() if it chooses to ignore future * regulatory domain changes caused by other drivers. * @signal_type: signal type reported in &struct cfg80211_bss. * @cipher_suites: supported cipher suites * @n_cipher_suites: number of supported cipher suites - * @akm_suites: supported AKM suites + * @akm_suites: supported AKM suites. These are the default AKMs supported if + * the supported AKMs not advertized for a specific interface type in + * iftype_akm_suites. * @n_akm_suites: number of supported AKM suites + * @iftype_akm_suites: array of supported akm suites info per interface type. + * Note that the bits in @iftypes_mask inside this structure cannot + * overlap (i.e. only one occurrence of each type is allowed across all + * instances of iftype_akm_suites). + * @num_iftype_akm_suites: number of interface types for which supported akm + * suites are specified separately. * @retry_short: Retry limit for short frames (dot11ShortRetryLimit) * @retry_long: Retry limit for long frames (dot11LongRetryLimit) * @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold); @@ -4409,10 +4510,11 @@ struct cfg80211_pmsr_capabilities { * the same number of arbitrary MAC addresses. * @registered: protects ->resume and ->suspend sysfs callbacks against * unregister hardware - * @debugfsdir: debugfs directory used for this wiphy, will be renamed - * automatically on wiphy renames - * @dev: (virtual) struct device for this wiphy - * @registered: helps synchronize suspend/resume with wiphy unregister + * @debugfsdir: debugfs directory used for this wiphy (ieee80211/<wiphyname>). + * It will be renamed automatically on wiphy renames + * @dev: (virtual) struct device for this wiphy. The item in + * /sys/class/ieee80211/ points to this. You need use set_wiphy_dev() + * (see below). * @wext: wireless extension handlers * @priv: driver private data (sized according to wiphy_new() parameter) * @interface_modes: bitmask of interfaces types valid for this wiphy, @@ -4523,12 +4625,6 @@ struct cfg80211_pmsr_capabilities { * and probe responses. This value should be set if the driver * wishes to limit the number of csa counters. Default (0) means * infinite. - * @max_adj_channel_rssi_comp: max offset of between the channel on which the - * frame was sent and the channel on which the frame was heard for which - * the reported rssi is still valid. If a driver is able to compensate the - * low rssi when a frame is heard on different channel, then it should set - * this variable to the maximal offset for which it can compensate. - * This value should be set in MHz. * @bss_select_support: bitmask indicating the BSS selection criteria supported * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. @@ -4548,11 +4644,19 @@ struct cfg80211_pmsr_capabilities { * @support_mbssid must be set for this to have any effect. * * @pmsr_capa: peer measurement capabilities + * + * @tid_config_support: describes the per-TID config support that the + * device has + * @tid_config_support.vif: bitmap of attributes (configurations) + * supported by the driver for each vif + * @tid_config_support.peer: bitmap of attributes (configurations) + * supported by the driver for each peer + * @tid_config_support.max_retry: maximum supported retry count for + * long/short retry configuration */ struct wiphy { /* assign these fields before you register the wiphy */ - /* permanent MAC address(es) */ u8 perm_addr[ETH_ALEN]; u8 addr_mask[ETH_ALEN]; @@ -4595,6 +4699,9 @@ struct wiphy { int n_akm_suites; const u32 *akm_suites; + const struct wiphy_iftype_akm_suites *iftype_akm_suites; + unsigned int num_iftype_akm_suites; + u8 retry_short; u8 retry_long; u32 frag_threshold; @@ -4616,11 +4723,6 @@ struct wiphy { u32 available_antennas_tx; u32 available_antennas_rx; - /* - * Bitmap of supported protocols for probe response offloading - * see &enum nl80211_probe_resp_offload_support_attr. Only valid - * when the wiphy flag @WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD is set. - */ u32 probe_resp_offload; const u8 *extended_capabilities, *extended_capabilities_mask; @@ -4629,16 +4731,10 @@ struct wiphy { const struct wiphy_iftype_ext_capab *iftype_ext_capab; unsigned int num_iftype_ext_capab; - /* If multiple wiphys are registered and you're handed e.g. - * a regular netdev with assigned ieee80211_ptr, you won't - * know whether it points to a wiphy your driver has registered - * or not. Assign this to something global to your driver to - * help determine whether you own this wiphy or not. */ const void *privid; struct ieee80211_supported_band *bands[NUM_NL80211_BANDS]; - /* Lets us get back the wiphy on the callback */ void (*reg_notifier)(struct wiphy *wiphy, struct regulatory_request *request); @@ -4646,14 +4742,10 @@ struct wiphy { const struct ieee80211_regdomain __rcu *regd; - /* the item in /sys/class/ieee80211/ points to this, - * you need use set_wiphy_dev() (see below) */ struct device dev; - /* protects ->resume, ->suspend sysfs callbacks against unregister hw */ bool registered; - /* dir in debugfs: ieee80211/<wiphyname> */ struct dentry *debugfsdir; const struct ieee80211_ht_cap *ht_capa_mod_mask; @@ -4661,7 +4753,6 @@ struct wiphy { struct list_head wdev_list; - /* the network namespace this phy lives in currently */ possible_net_t _net; #ifdef CONFIG_CFG80211_WEXT @@ -4677,7 +4768,6 @@ struct wiphy { u16 max_ap_assoc_sta; u8 max_num_csa_counters; - u8 max_adj_channel_rssi_comp; u32 bss_select_support; @@ -4687,11 +4777,20 @@ struct wiphy { u32 txq_memory_limit; u32 txq_quantum; + unsigned long tx_queue_len; + u8 support_mbssid:1, support_only_he_mbssid:1; const struct cfg80211_pmsr_capabilities *pmsr_capa; + struct { + u64 peer, vif; + u8 max_retry; + } tid_config_support; + + u8 max_data_retry_count; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -5467,9 +5566,9 @@ void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr); * @wiphy: the wireless device giving the hint (used only for reporting * conflicts) * @alpha2: the ISO/IEC 3166 alpha2 the driver claims its regulatory domain - * should be in. If @rd is set this should be NULL. Note that if you - * set this to NULL you should still set rd->alpha2 to some accepted - * alpha2. + * should be in. If @rd is set this should be NULL. Note that if you + * set this to NULL you should still set rd->alpha2 to some accepted + * alpha2. * * Wireless drivers can use this function to hint to the wireless core * what it believes should be the current regulatory domain by diff --git a/include/net/devlink.h b/include/net/devlink.h index ce5cea428fdc..c9ca86b054bc 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -16,6 +16,7 @@ #include <linux/workqueue.h> #include <linux/refcount.h> #include <net/net_namespace.h> +#include <net/flow_offload.h> #include <uapi/linux/devlink.h> struct devlink_ops; @@ -541,6 +542,7 @@ struct devlink_trap_group { }; #define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0) +#define DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE BIT(1) /** * struct devlink_trap - Immutable packet trap attributes. @@ -596,6 +598,8 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_NON_ROUTABLE, DEVLINK_TRAP_GENERIC_ID_DECAP_ERROR, DEVLINK_TRAP_GENERIC_ID_OVERLAY_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_INGRESS_FLOW_ACTION_DROP, + DEVLINK_TRAP_GENERIC_ID_EGRESS_FLOW_ACTION_DROP, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -610,6 +614,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_TUNNEL_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_DROPS, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -671,6 +676,10 @@ enum devlink_trap_group_generic_id { "decap_error" #define DEVLINK_TRAP_GENERIC_NAME_OVERLAY_SMAC_MC \ "overlay_smac_is_mc" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_FLOW_ACTION_DROP \ + "ingress_flow_action_drop" +#define DEVLINK_TRAP_GENERIC_NAME_EGRESS_FLOW_ACTION_DROP \ + "egress_flow_action_drop" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -680,6 +689,8 @@ enum devlink_trap_group_generic_id { "buffer_drops" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_TUNNEL_DROPS \ "tunnel_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_ACL_DROPS \ + "acl_drops" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \ { \ @@ -981,12 +992,17 @@ int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg); int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg); +int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name); +int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg); int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value); int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value); @@ -1035,9 +1051,9 @@ int devlink_traps_register(struct devlink *devlink, void devlink_traps_unregister(struct devlink *devlink, const struct devlink_trap *traps, size_t traps_count); -void devlink_trap_report(struct devlink *devlink, - struct sk_buff *skb, void *trap_ctx, - struct devlink_port *in_devlink_port); +void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie); void *devlink_trap_ctx_priv(void *trap_ctx); #if IS_ENABLED(CONFIG_NET_DEVLINK) diff --git a/include/net/drop_monitor.h b/include/net/drop_monitor.h index 2ab668461463..ddd441a60e03 100644 --- a/include/net/drop_monitor.h +++ b/include/net/drop_monitor.h @@ -6,17 +6,20 @@ #include <linux/ktime.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/flow_offload.h> /** * struct net_dm_hw_metadata - Hardware-supplied packet metadata. * @trap_group_name: Hardware trap group name. * @trap_name: Hardware trap name. * @input_dev: Input netdevice. + * @fa_cookie: Flow action user cookie. */ struct net_dm_hw_metadata { const char *trap_group_name; const char *trap_name; struct net_device *input_dev; + const struct flow_action_cookie *fa_cookie; }; #if IS_ENABLED(CONFIG_NET_DROP_MONITOR) diff --git a/include/net/dsa.h b/include/net/dsa.h index 63495e3443ac..7d3d84f0ef42 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -420,7 +420,9 @@ struct dsa_switch_ops { void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev); + struct phy_device *phydev, + int speed, int duplex, + bool tx_pause, bool rx_pause); void (*phylink_fixed_state)(struct dsa_switch *ds, int port, struct phylink_link_state *state); /* diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index c6f7bd22db60..4e864c34a1b0 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -156,6 +156,16 @@ enum flow_action_mangle_base { typedef void (*action_destr)(void *priv); +struct flow_action_cookie { + u32 cookie_len; + u8 cookie[]; +}; + +struct flow_action_cookie *flow_action_cookie_create(void *data, + unsigned int len, + gfp_t gfp); +void flow_action_cookie_destroy(struct flow_action_cookie *cookie); + struct flow_action_entry { enum flow_action_id id; action_destr destructor; @@ -214,6 +224,7 @@ struct flow_action_entry { u8 ttl; } mpls_mangle; }; + struct flow_action_cookie *cookie; /* user defined action cookie */ }; struct flow_action { diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 7bec95df4f80..27ec612cd4a4 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -76,6 +76,15 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb, } } +static inline void tcp_v6_gso_csum_prep(struct sk_buff *skb) +{ + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + ipv6h->payload_len = 0; + th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0); +} + #if IS_ENABLED(CONFIG_IPV6) static inline void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index cec1a54401f2..1bf8065fe871 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1027,6 +1027,12 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); +struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, struct socket *sock, + struct in6_addr *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 77e6b5a83b06..5ef34a2ba3c7 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -316,6 +316,7 @@ struct ieee80211_vif_chanctx_switch { * functionality changed for this BSS (AP mode). * @BSS_CHANGED_TWT: TWT status changed * @BSS_CHANGED_HE_OBSS_PD: OBSS Packet Detection status changed. + * @BSS_CHANGED_HE_BSS_COLOR: BSS Color has changed * */ enum ieee80211_bss_change { @@ -348,6 +349,7 @@ enum ieee80211_bss_change { BSS_CHANGED_FTM_RESPONDER = 1<<26, BSS_CHANGED_TWT = 1<<27, BSS_CHANGED_HE_OBSS_PD = 1<<28, + BSS_CHANGED_HE_BSS_COLOR = 1<<29, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -494,7 +496,6 @@ struct ieee80211_ftm_responder_params { * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * - * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK * @uora_exists: is the UORA element advertised by AP @@ -573,7 +574,7 @@ struct ieee80211_ftm_responder_params { * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. - * @txpower: TX power in dBm + * @txpower: TX power in dBm. INT_MIN means not configured. * @txpower_type: TX power adjustment used to control per packet Transmit * Power Control (TPC) in lower driver for the current vif. In particular * TPC is enabled if value passed in %txpower_type is @@ -604,10 +605,10 @@ struct ieee80211_ftm_responder_params { * in order to discover all the nontransmitted BSSIDs in the set. * @he_operation: HE operation information of the AP we are connected to * @he_obss_pd: OBSS Packet Detection parameters. + * @he_bss_color: BSS coloring settings, if BSS supports HE */ struct ieee80211_bss_conf { const u8 *bssid; - u8 bss_color; u8 htc_trig_based_pkt_ext; bool multi_sta_back_32bit; bool uora_exists; @@ -667,6 +668,7 @@ struct ieee80211_bss_conf { u8 profile_periodicity; struct ieee80211_he_operation he_operation; struct ieee80211_he_obss_pd he_obss_pd; + struct cfg80211_he_bss_color he_bss_color; }; /** @@ -826,6 +828,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_AMSDU = BIT(3), IEEE80211_TX_CTRL_FAST_XMIT = BIT(4), IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), + IEEE80211_TX_CTRL_HW_80211_ENCAP = BIT(6), }; /* @@ -3773,6 +3776,9 @@ enum ieee80211_reconfig_type { * * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep) * @abort_pmsr: abort peer measurement (this call can sleep) + * @set_tid_config: Apply TID specific configurations. This callback may sleep. + * @reset_tid_config: Reset TID specific configuration for the peer. + * This callback may sleep. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4077,6 +4083,13 @@ struct ieee80211_ops { struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_pmsr_request *request); + int (*set_tid_config)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct cfg80211_tid_config *tid_conf); + int (*reset_tid_config)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, u8 tids); }; /** @@ -4660,6 +4673,26 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw, struct sk_buff *skb); /** + * ieee80211_tx_status_8023 - transmit status callback for 802.3 frame format + * + * Call this function for all transmitted data frames after their transmit + * completion. This callback should only be called for data frames which + * are are using driver's (or hardware's) offload capability of encap/decap + * 802.11 frames. + * + * This function may not be called in IRQ context. Calls to this function + * for a single hardware must be synchronized against each other and all + * calls in the same tx status family. + * + * @hw: the hardware the frame was transmitted by + * @vif: the interface for which the frame was transmitted + * @skb: the frame that was transmitted, owned by mac80211 after this call + */ +void ieee80211_tx_status_8023(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct sk_buff *skb); + +/** * ieee80211_report_low_ack - report non-responding station * * When operating in AP-mode, call this function to report a non-responding @@ -6479,5 +6512,16 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_info *info, int len); +/** + * ieee80211_set_hw_80211_encap - enable hardware encapsulation offloading. + * + * This function is used to notify mac80211 that a vif can be passed raw 802.3 + * frames. The driver needs to then handle the 802.11 encapsulation inside the + * hardware or firmware. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @enable: indicate if the feature should be turned on or off + */ +bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable); #endif /* MAC80211_H */ diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index 6ab5a83f597c..0550e0380b8d 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -244,13 +244,13 @@ struct dest_spec_params { struct core_conn_create_dest_spec_params { __u8 type; __u8 length; - __u8 value[0]; + __u8 value[]; } __packed; struct nci_core_conn_create_cmd { __u8 destination_type; __u8 number_destination_params; - struct core_conn_create_dest_spec_params params[0]; + struct core_conn_create_dest_spec_params params[]; } __packed; #define NCI_OP_CORE_CONN_CLOSE_CMD nci_opcode_pack(NCI_GID_CORE, 0x05) @@ -321,7 +321,7 @@ struct nci_core_init_rsp_1 { __u8 status; __le32 nfcc_features; __u8 num_supported_rf_interfaces; - __u8 supported_rf_interfaces[0]; /* variable size array */ + __u8 supported_rf_interfaces[]; /* variable size array */ /* continuted in nci_core_init_rsp_2 */ } __packed; @@ -338,7 +338,7 @@ struct nci_core_init_rsp_2 { struct nci_core_set_config_rsp { __u8 status; __u8 num_params; - __u8 params_id[0]; /* variable size array */ + __u8 params_id[]; /* variable size array */ } __packed; #define NCI_OP_CORE_CONN_CREATE_RSP nci_opcode_pack(NCI_GID_CORE, 0x04) @@ -501,18 +501,18 @@ struct nci_rf_nfcee_action_ntf { __u8 nfcee_id; __u8 trigger; __u8 supported_data_length; - __u8 supported_data[0]; + __u8 supported_data[]; } __packed; #define NCI_OP_NFCEE_DISCOVER_NTF nci_opcode_pack(NCI_GID_NFCEE_MGMT, 0x00) struct nci_nfcee_supported_protocol { __u8 num_protocol; - __u8 supported_protocol[0]; + __u8 supported_protocol[]; } __packed; struct nci_nfcee_information_tlv { __u8 num_tlv; - __u8 information_tlv[0]; + __u8 information_tlv[]; } __packed; struct nci_nfcee_discover_ntf { diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 5d277d68fd8d..2cd3a261bcbc 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -146,7 +146,7 @@ struct nfc_evt_transaction { u32 aid_len; u8 aid[NFC_MAX_AID_LENGTH]; u8 params_len; - u8 params[0]; + u8 params[]; } __packed; struct nfc_genl_data { diff --git a/include/net/page_pool.h b/include/net/page_pool.h index cfbed00ba7ee..81d7773f96cd 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -151,6 +151,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params); #ifdef CONFIG_PAGE_POOL void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); +void page_pool_release_page(struct page_pool *pool, struct page *page); #else static inline void page_pool_destroy(struct page_pool *pool) { @@ -160,41 +161,32 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)) { } +static inline void page_pool_release_page(struct page_pool *pool, + struct page *page) +{ +} #endif -/* Never call this directly, use helpers below */ -void __page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct); +void page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct); -static inline void page_pool_put_page(struct page_pool *pool, - struct page *page, bool allow_direct) +/* Same as above but will try to sync the entire area pool->max_len */ +static inline void page_pool_put_full_page(struct page_pool *pool, + struct page *page, bool allow_direct) { /* When page_pool isn't compiled-in, net/core/xdp.c doesn't * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - __page_pool_put_page(pool, page, -1, allow_direct); + page_pool_put_page(pool, page, -1, allow_direct); #endif } -/* Very limited use-cases allow recycle direct */ + +/* Same as above but the caller must guarantee safe context. e.g NAPI */ static inline void page_pool_recycle_direct(struct page_pool *pool, struct page *page) { - __page_pool_put_page(pool, page, -1, true); -} - -/* Disconnects a page (from a page_pool). API users can have a need - * to disconnect a page (from a page_pool), to allow it to be used as - * a regular page (that will eventually be returned to the normal - * page-allocator via put_page). - */ -void page_pool_unmap_page(struct page_pool *pool, struct page *page); -static inline void page_pool_release_page(struct page_pool *pool, - struct page *page) -{ -#ifdef CONFIG_PAGE_POOL - page_pool_unmap_page(pool, page); -#endif + page_pool_put_full_page(pool, page, true); } static inline dma_addr_t page_pool_get_dma_addr(struct page *page) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a972244ab193..53946b509b51 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -509,7 +509,7 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts, bool rtnl_held); + const struct tcf_exts *exts); void tc_cleanup_flow_action(struct flow_action *flow_action); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, diff --git a/include/net/route.h b/include/net/route.h index a9c60fc68e36..81750ae50833 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -128,6 +128,12 @@ static inline struct rtable *__ip_route_output_key(struct net *net, struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, const struct sock *sk); +struct rtable *ip_route_output_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, __be32 *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache); + struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); diff --git a/include/net/sock.h b/include/net/sock.h index 328564525526..b5cca7bae69b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -527,10 +527,43 @@ enum sk_pacing { SK_PACING_FQ = 2, }; +/* Pointer stored in sk_user_data might not be suitable for copying + * when cloning the socket. For instance, it can point to a reference + * counted object. sk_user_data bottom bit is set if pointer must not + * be copied. + */ +#define SK_USER_DATA_NOCOPY 1UL +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY) + +/** + * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied + * @sk: socket + */ +static inline bool sk_user_data_is_nocopy(const struct sock *sk) +{ + return ((uintptr_t)sk->sk_user_data & SK_USER_DATA_NOCOPY); +} + #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) -#define rcu_dereference_sk_user_data(sk) rcu_dereference(__sk_user_data((sk))) -#define rcu_assign_sk_user_data(sk, ptr) rcu_assign_pointer(__sk_user_data((sk)), ptr) +#define rcu_dereference_sk_user_data(sk) \ +({ \ + void *__tmp = rcu_dereference(__sk_user_data((sk))); \ + (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \ +}) +#define rcu_assign_sk_user_data(sk, ptr) \ +({ \ + uintptr_t __tmp = (uintptr_t)(ptr); \ + WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ + rcu_assign_pointer(__sk_user_data((sk)), __tmp); \ +}) +#define rcu_assign_sk_user_data_nocopy(sk, ptr) \ +({ \ + uintptr_t __tmp = (uintptr_t)(ptr); \ + WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ + rcu_assign_pointer(__sk_user_data((sk)), \ + __tmp | SK_USER_DATA_NOCOPY); \ +}) /* * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 43f4a818d88f..3ecaa15d1850 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -55,6 +55,4 @@ static inline bool reuseport_has_conns(struct sock *sk, bool set) return ret; } -int reuseport_get_id(struct sock_reuseport *reuse); - #endif /* _SOCK_REUSEPORT_H */ diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index bdc20ab3b88d..a8b156402873 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -33,8 +33,10 @@ struct tcf_ct { }; #define to_ct(a) ((struct tcf_ct *)a) -#define to_ct_params(a) ((struct tcf_ct_params *) \ - rtnl_dereference((to_ct(a)->params))) +#define to_ct_params(a) \ + ((struct tcf_ct_params *) \ + rcu_dereference_protected(to_ct(a)->params, \ + lockdep_is_held(&a->tcfa_lock))) static inline uint16_t tcf_ct_zone(const struct tc_action *a) { diff --git a/include/net/tc_act/tc_police.h b/include/net/tc_act/tc_police.h index cfdc7cb82cad..f098ad4424be 100644 --- a/include/net/tc_act/tc_police.h +++ b/include/net/tc_act/tc_police.h @@ -54,7 +54,8 @@ static inline u64 tcf_police_rate_bytes_ps(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh_rtnl(police->params); + params = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); return params->rate.rate_bytes_ps; } @@ -63,7 +64,8 @@ static inline s64 tcf_police_tcfp_burst(const struct tc_action *act) struct tcf_police *police = to_police(act); struct tcf_police_params *params; - params = rcu_dereference_bh_rtnl(police->params); + params = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); return params->tcfp_burst; } diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index 0689d9bcdf84..2b3df076e5b6 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -69,7 +69,7 @@ tcf_tunnel_info_copy(const struct tc_action *a) if (tun) { size_t tun_size = sizeof(*tun) + tun->options_len; struct ip_tunnel_info *tun_copy = kmemdup(tun, tun_size, - GFP_KERNEL); + GFP_ATOMIC); return tun_copy; } diff --git a/include/net/tcp.h b/include/net/tcp.h index a5ea27df3c2b..07f947cc80e6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2203,6 +2203,13 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); +#ifdef CONFIG_NET_SOCK_MSG +void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); +#else +static inline void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ +} +#endif /* Call BPF_SOCK_OPS program that returns an int. If the return value * is < 0, then the BPF op failed (for example if the loaded BPF diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22f235260a3a..906e9f2752db 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2890,6 +2890,25 @@ union bpf_attr { * Obtain the 64bit jiffies * Return * The 64 bit jiffies + * + * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * Description + * For an eBPF program attached to a perf event, retrieve the + * branch records (struct perf_branch_entry) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size + * *size* bytes. + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to + * instead return the number of bytes required to store all the + * branch entries. If this flag is set, *buf* may be NULL. + * + * **-EINVAL** if arguments invalid or **size** not a multiple + * of sizeof(struct perf_branch_entry). + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3010,7 +3029,8 @@ union bpf_attr { FN(probe_read_kernel_str), \ FN(tcp_send_ack), \ FN(send_signal_thread), \ - FN(jiffies64), + FN(jiffies64), \ + FN(read_branch_records), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3089,6 +3109,9 @@ enum bpf_func_id { /* BPF_FUNC_sk_storage_get flags */ #define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) +/* BPF_FUNC_read_branch_records flags. */ +#define BPF_F_GET_BRANCH_RECORDS_SIZE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ae37fd4d194a..be2a2948f452 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -252,6 +252,8 @@ enum devlink_trap_type { enum { /* Trap can report input port as metadata */ DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT, + /* Trap can report flow action cookie as metadata */ + DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE, }; enum devlink_attr { diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4295ebfa2f91..d586ee5e10a1 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1330,6 +1330,7 @@ enum ethtool_fec_config_bits { ETHTOOL_FEC_OFF_BIT, ETHTOOL_FEC_RS_BIT, ETHTOOL_FEC_BASER_BIT, + ETHTOOL_FEC_LLRS_BIT, }; #define ETHTOOL_FEC_NONE (1 << ETHTOOL_FEC_NONE_BIT) @@ -1337,6 +1338,7 @@ enum ethtool_fec_config_bits { #define ETHTOOL_FEC_OFF (1 << ETHTOOL_FEC_OFF_BIT) #define ETHTOOL_FEC_RS (1 << ETHTOOL_FEC_RS_BIT) #define ETHTOOL_FEC_BASER (1 << ETHTOOL_FEC_BASER_BIT) +#define ETHTOOL_FEC_LLRS (1 << ETHTOOL_FEC_LLRS_BIT) /* CMDs currently supported */ #define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. @@ -1521,7 +1523,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT = 71, ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT = 72, ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT = 73, - + ETHTOOL_LINK_MODE_FEC_LLRS_BIT = 74, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 024af2d1d0af..61e0801c82df 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -590,6 +590,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 8bf79a9eb234..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -92,6 +92,7 @@ enum net_dm_attr { NET_DM_ATTR_HW_TRAP_COUNT, /* u32 */ NET_DM_ATTR_SW_DROPS, /* flag */ NET_DM_ATTR_HW_DROPS, /* flag */ + NET_DM_ATTR_FLOW_ACTION_COOKIE, /* binary */ __NET_DM_ATTR_MAX, NET_DM_ATTR_MAX = __NET_DM_ATTR_MAX - 1 diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5eab191607f8..b002ef2060fa 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -265,6 +265,29 @@ */ /** + * DOC: TID configuration + * + * TID config support can be checked in the %NL80211_ATTR_TID_CONFIG + * attribute given in wiphy capabilities. + * + * The necessary configuration parameters are mentioned in + * &enum nl80211_tid_config_attr and it will be passed to the + * %NL80211_CMD_SET_TID_CONFIG command in %NL80211_ATTR_TID_CONFIG. + * + * If the configuration needs to be applied for specific peer then the MAC + * address of the peer needs to be passed in %NL80211_ATTR_MAC, otherwise the + * configuration will be applied for all the connected peers in the vif except + * any peers that have peer specific configuration for the TID by default; if + * the %NL80211_TID_CONFIG_ATTR_OVERRIDE flag is set, peer specific values + * will be overwritten. + * + * All this configuration is valid only for STA's current connection + * i.e. the configuration will be reset to default when the STA connects back + * after disconnection/roaming, and this configuration will be cleared when + * the interface goes down. + */ + +/** * enum nl80211_commands - supported nl80211 commands * * @NL80211_CMD_UNSPEC: unspecified command to catch errors @@ -1125,6 +1148,9 @@ * peer MAC address and %NL80211_ATTR_FRAME is used to specify the frame * content. The frame is ethernet data. * + * @NL80211_CMD_SET_TID_CONFIG: Data frame TID specific configuration + * is passed using %NL80211_ATTR_TID_CONFIG attribute. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1349,6 +1375,8 @@ enum nl80211_commands { NL80211_CMD_PROBE_MESH_LINK, + NL80211_CMD_SET_TID_CONFIG, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2400,6 +2428,20 @@ enum nl80211_commands { * @NL80211_ATTR_VLAN_ID: VLAN ID (1..4094) for the station and VLAN group key * (u16). * + * @NL80211_ATTR_HE_BSS_COLOR: nested attribute for BSS Color Settings. + * + * @NL80211_ATTR_IFTYPE_AKM_SUITES: nested array attribute, with each entry + * using attributes from &enum nl80211_iftype_akm_attributes. This + * attribute is sent in a response to %NL80211_CMD_GET_WIPHY indicating + * supported AKM suites capability per interface. AKMs advertised in + * %NL80211_ATTR_AKM_SUITES are default capabilities if AKM suites not + * advertised for a specific interface type. + * + * @NL80211_ATTR_TID_CONFIG: TID specific configuration in a + * nested attribute with &enum nl80211_tid_config_attr sub-attributes; + * on output (in wiphy attributes) it contains only the feature sub- + * attributes. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2864,6 +2906,12 @@ enum nl80211_attrs { NL80211_ATTR_VLAN_ID, + NL80211_ATTR_HE_BSS_COLOR, + + NL80211_ATTR_IFTYPE_AKM_SUITES, + + NL80211_ATTR_TID_CONFIG, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3583,6 +3631,8 @@ enum nl80211_wmm_rule { * @NL80211_FREQUENCY_ATTR_WMM: this channel has wmm limitations. * This is a nested attribute that contains the wmm limitation per AC. * (see &enum nl80211_wmm_rule) + * @NL80211_FREQUENCY_ATTR_NO_HE: HE operation is not allowed on this channel + * in current regulatory domain. * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number * currently defined * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use @@ -3612,6 +3662,7 @@ enum nl80211_frequency_attr { NL80211_FREQUENCY_ATTR_NO_20MHZ, NL80211_FREQUENCY_ATTR_NO_10MHZ, NL80211_FREQUENCY_ATTR_WMM, + NL80211_FREQUENCY_ATTR_NO_HE, /* keep last */ __NL80211_FREQUENCY_ATTR_AFTER_LAST, @@ -3809,6 +3860,7 @@ enum nl80211_sched_scan_match_attr { * @NL80211_RRF_NO_HT40PLUS: channels can't be used in HT40+ operation * @NL80211_RRF_NO_80MHZ: 80MHz operation not allowed * @NL80211_RRF_NO_160MHZ: 160MHz operation not allowed + * @NL80211_RRF_NO_HE: HE operation not allowed */ enum nl80211_reg_rule_flags { NL80211_RRF_NO_OFDM = 1<<0, @@ -3826,6 +3878,7 @@ enum nl80211_reg_rule_flags { NL80211_RRF_NO_HT40PLUS = 1<<14, NL80211_RRF_NO_80MHZ = 1<<15, NL80211_RRF_NO_160MHZ = 1<<16, + NL80211_RRF_NO_HE = 1<<17, }; #define NL80211_RRF_PASSIVE_SCAN NL80211_RRF_NO_IR @@ -4532,6 +4585,7 @@ enum nl80211_key_default_types { * See &enum nl80211_key_default_types. * @NL80211_KEY_MODE: the mode from enum nl80211_key_mode. * Defaults to @NL80211_KEY_RX_TX. + * @NL80211_KEY_DEFAULT_BEACON: flag indicating default Beacon frame key * * @__NL80211_KEY_AFTER_LAST: internal * @NL80211_KEY_MAX: highest key attribute @@ -4547,6 +4601,7 @@ enum nl80211_key_attributes { NL80211_KEY_TYPE, NL80211_KEY_DEFAULT_TYPES, NL80211_KEY_MODE, + NL80211_KEY_DEFAULT_BEACON, /* keep last */ __NL80211_KEY_AFTER_LAST, @@ -4703,6 +4758,69 @@ enum nl80211_tx_power_setting { }; /** + * enum nl80211_tid_config - TID config state + * @NL80211_TID_CONFIG_ENABLE: Enable config for the TID + * @NL80211_TID_CONFIG_DISABLE: Disable config for the TID + */ +enum nl80211_tid_config { + NL80211_TID_CONFIG_ENABLE, + NL80211_TID_CONFIG_DISABLE, +}; + +/* enum nl80211_tid_config_attr - TID specific configuration. + * @NL80211_TID_CONFIG_ATTR_PAD: pad attribute for 64-bit values + * @NL80211_TID_CONFIG_ATTR_VIF_SUPP: a bitmap (u64) of attributes supported + * for per-vif configuration; doesn't list the ones that are generic + * (%NL80211_TID_CONFIG_ATTR_TIDS, %NL80211_TID_CONFIG_ATTR_OVERRIDE). + * @NL80211_TID_CONFIG_ATTR_PEER_SUPP: same as the previous per-vif one, but + * per peer instead. + * @NL80211_TID_CONFIG_ATTR_OVERRIDE: flag attribue, if no peer + * is selected, if set indicates that the new configuration overrides + * all previous peer configurations, otherwise previous peer specific + * configurations should be left untouched. If peer is selected then + * it will reset particular TID configuration of that peer and it will + * not accept other TID config attributes along with peer. + * @NL80211_TID_CONFIG_ATTR_TIDS: a bitmask value of TIDs (bit 0 to 7) + * Its type is u16. + * @NL80211_TID_CONFIG_ATTR_NOACK: Configure ack policy for the TID. + * specified in %NL80211_TID_CONFIG_ATTR_TID. see %enum nl80211_tid_config. + * Its type is u8. + * @NL80211_TID_CONFIG_ATTR_RETRY_SHORT: Number of retries used with data frame + * transmission, user-space sets this configuration in + * &NL80211_CMD_SET_TID_CONFIG. It is u8 type, min value is 1 and + * the max value is advertised by the driver in this attribute on + * output in wiphy capabilities. + * @NL80211_TID_CONFIG_ATTR_RETRY_LONG: Number of retries used with data frame + * transmission, user-space sets this configuration in + * &NL80211_CMD_SET_TID_CONFIG. Its type is u8, min value is 1 and + * the max value is advertised by the driver in this attribute on + * output in wiphy capabilities. + * @NL80211_TID_CONFIG_ATTR_AMPDU_CTRL: Enable/Disable aggregation for the TIDs + * specified in %NL80211_TID_CONFIG_ATTR_TIDS. Its type is u8, using + * the values from &nl80211_tid_config. + * @NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL: Enable/Disable RTS_CTS for the TIDs + * specified in %NL80211_TID_CONFIG_ATTR_TIDS. It is u8 type, using + * the values from &nl80211_tid_config. + */ +enum nl80211_tid_config_attr { + __NL80211_TID_CONFIG_ATTR_INVALID, + NL80211_TID_CONFIG_ATTR_PAD, + NL80211_TID_CONFIG_ATTR_VIF_SUPP, + NL80211_TID_CONFIG_ATTR_PEER_SUPP, + NL80211_TID_CONFIG_ATTR_OVERRIDE, + NL80211_TID_CONFIG_ATTR_TIDS, + NL80211_TID_CONFIG_ATTR_NOACK, + NL80211_TID_CONFIG_ATTR_RETRY_SHORT, + NL80211_TID_CONFIG_ATTR_RETRY_LONG, + NL80211_TID_CONFIG_ATTR_AMPDU_CTRL, + NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL, + + /* keep last */ + __NL80211_TID_CONFIG_ATTR_AFTER_LAST, + NL80211_TID_CONFIG_ATTR_MAX = __NL80211_TID_CONFIG_ATTR_AFTER_LAST - 1 +}; + +/** * enum nl80211_packet_pattern_attr - packet pattern attribute * @__NL80211_PKTPAT_INVALID: invalid number for nested attribute * @NL80211_PKTPAT_PATTERN: the pattern, values where the mask has @@ -5521,6 +5639,9 @@ enum nl80211_feature_flags { * feature, which prevents bufferbloat by using the expected transmission * time to limit the amount of data buffered in the hardware. * + * @NL80211_EXT_FEATURE_BEACON_PROTECTION: The driver supports Beacon protection + * and can receive key configuration for BIGTK using key indexes 6 and 7. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5568,6 +5689,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SAE_OFFLOAD, NL80211_EXT_FEATURE_VLAN_OFFLOAD, NL80211_EXT_FEATURE_AQL, + NL80211_EXT_FEATURE_BEACON_PROTECTION, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -6587,5 +6709,51 @@ enum nl80211_obss_pd_attributes { NL80211_HE_OBSS_PD_ATTR_MAX = __NL80211_HE_OBSS_PD_ATTR_LAST - 1, }; +/** + * enum nl80211_bss_color_attributes - BSS Color attributes + * @__NL80211_HE_BSS_COLOR_ATTR_INVALID: Invalid + * + * @NL80211_HE_BSS_COLOR_ATTR_COLOR: the current BSS Color. + * @NL80211_HE_BSS_COLOR_ATTR_DISABLED: is BSS coloring disabled. + * @NL80211_HE_BSS_COLOR_ATTR_PARTIAL: the AID equation to be used.. + * + * @__NL80211_HE_BSS_COLOR_ATTR_LAST: Internal + * @NL80211_HE_BSS_COLOR_ATTR_MAX: highest BSS Color attribute. + */ +enum nl80211_bss_color_attributes { + __NL80211_HE_BSS_COLOR_ATTR_INVALID, + + NL80211_HE_BSS_COLOR_ATTR_COLOR, + NL80211_HE_BSS_COLOR_ATTR_DISABLED, + NL80211_HE_BSS_COLOR_ATTR_PARTIAL, + + /* keep last */ + __NL80211_HE_BSS_COLOR_ATTR_LAST, + NL80211_HE_BSS_COLOR_ATTR_MAX = __NL80211_HE_BSS_COLOR_ATTR_LAST - 1, +}; + +/** + * enum nl80211_iftype_akm_attributes - interface type AKM attributes + * @__NL80211_IFTYPE_AKM_ATTR_INVALID: Invalid + * + * @NL80211_IFTYPE_AKM_ATTR_IFTYPES: nested attribute containing a flag + * attribute for each interface type that supports AKM suites specified in + * %NL80211_IFTYPE_AKM_ATTR_SUITES + * @NL80211_IFTYPE_AKM_ATTR_SUITES: an array of u32. Used to indicate supported + * AKM suites for the specified interface types. + * + * @__NL80211_IFTYPE_AKM_ATTR_LAST: Internal + * @NL80211_IFTYPE_AKM_ATTR_MAX: highest interface type AKM attribute. + */ +enum nl80211_iftype_akm_attributes { + __NL80211_IFTYPE_AKM_ATTR_INVALID, + + NL80211_IFTYPE_AKM_ATTR_IFTYPES, + NL80211_IFTYPE_AKM_ATTR_SUITES, + + /* keep last */ + __NL80211_IFTYPE_AKM_ATTR_LAST, + NL80211_IFTYPE_AKM_ATTR_MAX = __NL80211_IFTYPE_AKM_ATTR_LAST - 1, +}; #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index ae2bff14e7e1..9b14519e74d9 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -958,6 +958,7 @@ enum ovs_action_attr { OVS_ACTION_ATTR_CLONE, /* Nested OVS_CLONE_ATTR_*. */ OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */ OVS_ACTION_ATTR_ADD_MPLS, /* struct ovs_action_add_mpls. */ + OVS_ACTION_ATTR_DEC_TTL, /* Nested OVS_DEC_TTL_ATTR_*. */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ @@ -1050,4 +1051,10 @@ struct ovs_zone_limit { __u32 count; }; +enum ovs_dec_ttl_attr { + OVS_DEC_TTL_ATTR_UNSPEC, + OVS_DEC_TTL_ATTR_ACTION, /* Nested struct nlattr */ + __OVS_DEC_TTL_ATTR_MAX +}; + #endif /* _LINUX_OPENVSWITCH_H */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index fd9eb8f6bcae..1a7fc856e237 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -345,5 +345,7 @@ struct tcp_zerocopy_receive { __u64 address; /* in: address of mapping */ __u32 length; /* in/out: number of bytes to map/mapped */ __u32 recv_skip_hint; /* out: amount of bytes to skip */ + __u32 inq; /* out: amount of bytes in read queue */ + __s32 err; /* out: socket error */ }; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/include/uapi/linux/wireless.h b/include/uapi/linux/wireless.h index 86eca3208b6b..a2c006a364e0 100644 --- a/include/uapi/linux/wireless.h +++ b/include/uapi/linux/wireless.h @@ -74,6 +74,8 @@ #include <linux/socket.h> /* for "struct sockaddr" et al */ #include <linux/if.h> /* for IFNAMSIZ and co... */ +#include <stddef.h> /* for offsetof */ + /***************************** VERSION *****************************/ /* * This constant is used to know the availability of the wireless @@ -1090,8 +1092,7 @@ struct iw_event { /* iw_point events are special. First, the payload (extra data) come at * the end of the event, so they are bigger than IW_EV_POINT_LEN. Second, * we omit the pointer, so start at an offset. */ -#define IW_EV_POINT_OFF (((char *) &(((struct iw_point *) NULL)->length)) - \ - (char *) NULL) +#define IW_EV_POINT_OFF offsetof(struct iw_point, length) #define IW_EV_POINT_LEN (IW_EV_LCP_LEN + sizeof(struct iw_point) - \ IW_EV_POINT_OFF) diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 50c083ba978c..01badd3eda7a 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -305,11 +305,6 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, if (err) goto put_file_unlock; - /* Ensure reuse->reuseport_id is set */ - err = reuseport_get_id(reuse); - if (err < 0) - goto put_file_unlock; - WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1cc945daa9c8..6d15dfbd4b88 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3693,14 +3693,16 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_map_delete_elem && - func_id != BPF_FUNC_msg_redirect_map) + func_id != BPF_FUNC_msg_redirect_map && + func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_map_delete_elem && - func_id != BPF_FUNC_msg_redirect_hash) + func_id != BPF_FUNC_msg_redirect_hash && + func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: @@ -3774,7 +3776,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_sk_select_reuseport: - if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + map->map_type != BPF_MAP_TYPE_SOCKMAP && + map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_peek_elem: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 19e793aa441a..b8661bd0d028 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -843,6 +843,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_send_signal_proto; case BPF_FUNC_send_signal_thread: return &bpf_send_signal_thread_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; default: return NULL; } @@ -858,8 +860,6 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: return &bpf_get_stack_proto; - case BPF_FUNC_perf_event_read_value: - return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; @@ -1028,6 +1028,45 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { .arg3_type = ARG_CONST_SIZE, }; +BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, + void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + struct perf_branch_stack *br_stack = ctx->data->br_stack; + u32 to_copy; + + if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE)) + return -EINVAL; + + if (unlikely(!br_stack)) + return -EINVAL; + + if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) + return br_stack->nr * br_entry_size; + + if (!buf || (size % br_entry_size != 0)) + return -EINVAL; + + to_copy = min_t(u32, br_stack->nr * br_entry_size, size); + memcpy(buf, br_stack->entries, to_copy); + + return to_copy; +#endif +} + +static const struct bpf_func_proto bpf_read_branch_records_proto = { + .func = bpf_read_branch_records, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1040,6 +1079,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; + case BPF_FUNC_read_branch_records: + return &bpf_read_branch_records_proto; default: return tracing_func_proto(func_id, prog); } diff --git a/lib/objagg.c b/lib/objagg.c index 55621fb82e0a..5e1676ccdadd 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -28,7 +28,7 @@ struct objagg_hints_node { struct objagg_hints_node *parent; unsigned int root_id; struct objagg_obj_stats_info stats_info; - unsigned long obj[0]; + unsigned long obj[]; }; static struct objagg_hints_node * @@ -66,7 +66,7 @@ struct objagg_obj { * including nested objects */ struct objagg_obj_stats stats; - unsigned long obj[0]; + unsigned long obj[]; }; static unsigned int objagg_obj_ref_inc(struct objagg_obj *objagg_obj) diff --git a/net/802/psnap.c b/net/802/psnap.c index 40ab2aea7b31..4492e8d7ad20 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -30,7 +30,7 @@ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; - list_for_each_entry_rcu(p, &snap_list, node) { + list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index a313165e7a67..78ec2e1b14d1 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -359,9 +359,8 @@ static void __vlan_vid_del(struct vlan_info *vlan_info, int err; err = vlan_kill_rx_filter_info(dev, proto, vid); - if (err) - pr_warn("failed to kill vid %04x/%d for device %s\n", - proto, vid, dev->name); + if (err && dev->reg_state != NETREG_UNREGISTERING) + netdev_warn(dev, "failed to kill vid %04x/%d\n", proto, vid); list_del(&vid_info->list); kfree(vid_info); diff --git a/net/core/dev.c b/net/core/dev.c index c6c985fe7b1b..25dab1598803 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4638,7 +4638,6 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) kfree_skb(skb); } } -EXPORT_SYMBOL_GPL(generic_xdp_tx); static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); @@ -10006,6 +10005,7 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { + struct net *net_old = dev_net(dev); int err, new_nsid, new_ifindex; ASSERT_RTNL(); @@ -10021,7 +10021,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Get out if there is nothing todo */ err = 0; - if (net_eq(dev_net(dev), net)) + if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure @@ -10097,6 +10097,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char err = device_rename(&dev->dev, dev->name); WARN_ON(err); + /* Adapt owner in case owning user namespace of target network + * namespace is different from the original one. + */ + err = netdev_change_owner(dev, net_old, net); + WARN_ON(err); + /* Add the device back in the hashes */ list_netdevice(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 5e220809844c..f8af5e2d748b 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4237,6 +4237,12 @@ struct devlink_fmsg_item { struct devlink_fmsg { struct list_head item_list; + bool putting_binary; /* This flag forces enclosing of binary data + * in an array brackets. It forces using + * of designated API: + * devlink_fmsg_binary_pair_nest_start() + * devlink_fmsg_binary_pair_nest_end() + */ }; static struct devlink_fmsg *devlink_fmsg_alloc(void) @@ -4280,17 +4286,26 @@ static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); } int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); @@ -4301,6 +4316,9 @@ static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) { struct devlink_fmsg_item *item; + if (fmsg->putting_binary) + return -EINVAL; + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) return -EMSGSIZE; @@ -4321,6 +4339,9 @@ int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); if (err) return err; @@ -4335,6 +4356,9 @@ EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); @@ -4344,6 +4368,9 @@ int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_pair_nest_start(fmsg, name); if (err) return err; @@ -4360,6 +4387,9 @@ int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) { int err; + if (fmsg->putting_binary) + return -EINVAL; + err = devlink_fmsg_nest_end(fmsg); if (err) return err; @@ -4372,6 +4402,30 @@ int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); +int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); + if (err) + return err; + + fmsg->putting_binary = true; + return err; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); + +int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) +{ + if (!fmsg->putting_binary) + return -EINVAL; + + fmsg->putting_binary = false; + return devlink_fmsg_arr_pair_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); + static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, const void *value, u16 value_len, u8 value_nla_type) @@ -4396,40 +4450,59 @@ static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { + if (fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { + if (!fmsg->putting_binary) + return -EINVAL; + return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) @@ -4540,10 +4613,11 @@ int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, const void *value, u32 value_len) { u32 data_size; + int end_err; u32 offset; int err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, name); + err = devlink_fmsg_binary_pair_nest_start(fmsg, name); if (err) return err; @@ -4553,14 +4627,18 @@ int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, data_size = DEVLINK_FMSG_MAX_SIZE; err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); if (err) - return err; + break; + /* Exit from loop with a break (instead of + * return) to make sure putting_binary is turned off in + * devlink_fmsg_binary_pair_nest_end + */ } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; + end_err = devlink_fmsg_binary_pair_nest_end(fmsg); + if (end_err) + err = end_err; - return 0; + return err; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); @@ -5462,6 +5540,9 @@ static int devlink_trap_metadata_put(struct sk_buff *msg, if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) goto nla_put_failure; + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_FA_COOKIE) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_FA_COOKIE)) + goto nla_put_failure; nla_nest_end(msg, attr); @@ -7725,6 +7806,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(NON_ROUTABLE, DROP), DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), + DEVLINK_TRAP(INGRESS_FLOW_ACTION_DROP, DROP), + DEVLINK_TRAP(EGRESS_FLOW_ACTION_DROP, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7738,6 +7821,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), DEVLINK_TRAP_GROUP(TUNNEL_DROPS), + DEVLINK_TRAP_GROUP(ACL_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -8129,12 +8213,14 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, static void devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port) + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) { struct devlink_trap_group_item *group_item = trap_item->group_item; hw_metadata->trap_group_name = group_item->group->name; hw_metadata->trap_name = trap_item->trap->name; + hw_metadata->fa_cookie = fa_cookie; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) @@ -8148,9 +8234,12 @@ devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, * @skb: Trapped packet. * @trap_ctx: Trap context. * @in_devlink_port: Input devlink port. + * @fa_cookie: Flow action cookie. Could be NULL. */ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, - void *trap_ctx, struct devlink_port *in_devlink_port) + void *trap_ctx, struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) + { struct devlink_trap_item *trap_item = trap_ctx; struct net_dm_hw_metadata hw_metadata = {}; @@ -8159,7 +8248,7 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, devlink_trap_stats_update(trap_item->group_item->stats, skb->len); devlink_trap_report_metadata_fill(&hw_metadata, trap_item, - in_devlink_port); + in_devlink_port, fa_cookie); net_dm_hw_report(skb, &hw_metadata); } EXPORT_SYMBOL_GPL(devlink_trap_report); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 31700e0c3928..d58c1c45a895 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -29,6 +29,7 @@ #include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> +#include <net/flow_offload.h> #include <trace/events/skb.h> #include <trace/events/napi.h> @@ -701,6 +702,13 @@ static void net_dm_packet_work(struct work_struct *work) } static size_t +net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) +{ + return hw_metadata->fa_cookie ? + nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; +} + +static size_t net_dm_hw_packet_report_size(size_t payload_len, const struct net_dm_hw_metadata *hw_metadata) { @@ -717,6 +725,8 @@ net_dm_hw_packet_report_size(size_t payload_len, nla_total_size(strlen(hw_metadata->trap_name) + 1) + /* NET_DM_ATTR_IN_PORT */ net_dm_in_port_size() + + /* NET_DM_ATTR_FLOW_ACTION_COOKIE */ + net_dm_flow_action_cookie_size(hw_metadata) + /* NET_DM_ATTR_TIMESTAMP */ nla_total_size(sizeof(u64)) + /* NET_DM_ATTR_ORIG_LEN */ @@ -762,6 +772,12 @@ static int net_dm_hw_packet_report_fill(struct sk_buff *msg, goto nla_put_failure; } + if (hw_metadata->fa_cookie && + nla_put(msg, NET_DM_ATTR_FLOW_ACTION_COOKIE, + hw_metadata->fa_cookie->cookie_len, + hw_metadata->fa_cookie->cookie)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, NET_DM_ATTR_TIMESTAMP, ktime_to_ns(skb->tstamp), NET_DM_ATTR_PAD)) goto nla_put_failure; @@ -794,11 +810,12 @@ nla_put_failure: static struct net_dm_hw_metadata * net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) { + const struct flow_action_cookie *fa_cookie; struct net_dm_hw_metadata *n_hw_metadata; const char *trap_group_name; const char *trap_name; - n_hw_metadata = kmalloc(sizeof(*hw_metadata), GFP_ATOMIC); + n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); if (!n_hw_metadata) return NULL; @@ -812,12 +829,25 @@ net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) goto free_trap_group; n_hw_metadata->trap_name = trap_name; + if (hw_metadata->fa_cookie) { + size_t cookie_size = sizeof(*fa_cookie) + + hw_metadata->fa_cookie->cookie_len; + + fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size, + GFP_ATOMIC); + if (!fa_cookie) + goto free_trap_name; + n_hw_metadata->fa_cookie = fa_cookie; + } + n_hw_metadata->input_dev = hw_metadata->input_dev; if (n_hw_metadata->input_dev) dev_hold(n_hw_metadata->input_dev); return n_hw_metadata; +free_trap_name: + kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: @@ -830,6 +860,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) { if (hw_metadata->input_dev) dev_put(hw_metadata->input_dev); + kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); kfree(hw_metadata); diff --git a/net/core/filter.c b/net/core/filter.c index c180871e606d..4a08c9fb2be7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3626,7 +3626,6 @@ err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); return err; } -EXPORT_SYMBOL_GPL(xdp_do_generic_redirect); BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { @@ -8620,6 +8619,7 @@ struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { + bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; @@ -8628,26 +8628,20 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); - if (!reuse) - /* selected_sk is unhashed (e.g. by close()) after the - * above map_lookup_elem(). Treat selected_sk has already - * been removed from the map. + if (!reuse) { + /* reuseport_array has only sk with non NULL sk_reuseport_cb. + * The only (!reuse) case here is - the sk has already been + * unhashed (e.g. by close()), so treat it as -ENOENT. + * + * Other maps (e.g. sock_map) do not provide this guarantee and + * the sk may never be in the reuseport group to begin with. */ - return -ENOENT; + return is_sockarray ? -ENOENT : -EINVAL; + } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { - struct sock *sk; - - if (unlikely(!reuse_kern->reuseport_id)) - /* There is a small race between adding the - * sk to the map and setting the - * reuse_kern->reuseport_id. - * Treat it as the sk has not been added to - * the bpf map yet. - */ - return -ENOENT; + struct sock *sk = reuse_kern->sk; - sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) return -EPROTOTYPE; else if (sk->sk_family != selected_sk->sk_family) diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 45b6a59ac124..d21348202ba6 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -167,6 +167,27 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); +struct flow_action_cookie *flow_action_cookie_create(void *data, + unsigned int len, + gfp_t gfp) +{ + struct flow_action_cookie *cookie; + + cookie = kmalloc(sizeof(*cookie) + len, gfp); + if (!cookie) + return NULL; + cookie->cookie_len = len; + memcpy(cookie->cookie, data, len); + return cookie; +} +EXPORT_SYMBOL(flow_action_cookie_create); + +void flow_action_cookie_destroy(struct flow_action_cookie *cookie) +{ + kfree(cookie); +} +EXPORT_SYMBOL(flow_action_cookie_destroy); + struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 789a73aa7bd8..5bf8d22a47ec 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3553,9 +3553,6 @@ static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, #define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies) -#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \ - NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies) - #define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4c826b8bf9b1..cf0215734ceb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -944,6 +944,24 @@ err: kobject_put(kobj); return error; } + +static int rx_queue_change_owner(struct net_device *dev, int index, kuid_t kuid, + kgid_t kgid) +{ + struct netdev_rx_queue *queue = dev->_rx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + + if (dev->sysfs_rx_queue_group) + error = sysfs_group_change_owner( + kobj, dev->sysfs_rx_queue_group, kuid, kgid); + + return error; +} #endif /* CONFIG_SYSFS */ int @@ -981,6 +999,29 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif } +static int net_rx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + +#ifndef CONFIG_RPS + if (!dev->sysfs_rx_queue_group) + return 0; +#endif + for (i = 0; i < num; i++) { + error = rx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif +} + #ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. @@ -1486,6 +1527,23 @@ err: kobject_put(kobj); return error; } + +static int tx_queue_change_owner(struct net_device *ndev, int index, + kuid_t kuid, kgid_t kgid) +{ + struct netdev_queue *queue = ndev->_tx + index; + struct kobject *kobj = &queue->kobj; + int error; + + error = sysfs_change_owner(kobj, kuid, kgid); + if (error) + return error; + +#ifdef CONFIG_BQL + error = sysfs_group_change_owner(kobj, &dql_group, kuid, kgid); +#endif + return error; +} #endif /* CONFIG_SYSFS */ int @@ -1520,6 +1578,25 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) #endif /* CONFIG_SYSFS */ } +static int net_tx_queue_change_owner(struct net_device *dev, int num, + kuid_t kuid, kgid_t kgid) +{ +#ifdef CONFIG_SYSFS + int error = 0; + int i; + + for (i = 0; i < num; i++) { + error = tx_queue_change_owner(dev, i, kuid, kgid); + if (error) + break; + } + + return error; +#else + return 0; +#endif /* CONFIG_SYSFS */ +} + static int register_queue_kobjects(struct net_device *dev) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; @@ -1554,6 +1631,31 @@ error: return error; } +static int queue_change_owner(struct net_device *ndev, kuid_t kuid, kgid_t kgid) +{ + int error = 0, real_rx = 0, real_tx = 0; + +#ifdef CONFIG_SYSFS + if (ndev->queues_kset) { + error = sysfs_change_owner(&ndev->queues_kset->kobj, kuid, kgid); + if (error) + return error; + } + real_rx = ndev->real_num_rx_queues; +#endif + real_tx = ndev->real_num_tx_queues; + + error = net_rx_queue_change_owner(ndev, real_rx, kuid, kgid); + if (error) + return error; + + error = net_tx_queue_change_owner(ndev, real_tx, kuid, kgid); + if (error) + return error; + + return 0; +} + static void remove_queue_kobjects(struct net_device *dev) { int real_rx = 0, real_tx = 0; @@ -1767,6 +1869,37 @@ int netdev_register_kobject(struct net_device *ndev) return error; } +/* Change owner for sysfs entries when moving network devices across network + * namespaces owned by different user namespaces. + */ +int netdev_change_owner(struct net_device *ndev, const struct net *net_old, + const struct net *net_new) +{ + struct device *dev = &ndev->dev; + kuid_t old_uid, new_uid; + kgid_t old_gid, new_gid; + int error; + + net_ns_get_ownership(net_old, &old_uid, &old_gid); + net_ns_get_ownership(net_new, &new_uid, &new_gid); + + /* The network namespace was changed but the owning user namespace is + * identical so there's no need to change the owner of sysfs entries. + */ + if (uid_eq(old_uid, new_uid) && gid_eq(old_gid, new_gid)) + return 0; + + error = device_change_owner(dev, new_uid, new_gid); + if (error) + return error; + + error = queue_change_owner(ndev, new_uid, new_gid); + if (error) + return error; + + return 0; +} + int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns) { diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 006876c7b78d..8a5b04c2699a 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -8,5 +8,7 @@ void netdev_unregister_kobject(struct net_device *); int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num); +int netdev_change_owner(struct net_device *, const struct net *net_old, + const struct net *net_new); #endif diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 10d2b255df5e..626db912fce4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -96,7 +96,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) } EXPORT_SYMBOL(page_pool_create); -static void __page_pool_return_page(struct page_pool *pool, struct page *page); +static void page_pool_return_page(struct page_pool *pool, struct page *page); noinline static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) @@ -136,7 +136,7 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) * (2) break out to fallthrough to alloc_pages_node. * This limit stress on page buddy alloactor. */ - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); page = NULL; break; } @@ -274,18 +274,25 @@ static s32 page_pool_inflight(struct page_pool *pool) return inflight; } -/* Cleanup page_pool state from page */ -static void __page_pool_clean_page(struct page_pool *pool, - struct page *page) +/* Disconnects a page (from a page_pool). API users can have a need + * to disconnect a page (from a page_pool), to allow it to be used as + * a regular page (that will eventually be returned to the normal + * page-allocator via put_page). + */ +void page_pool_release_page(struct page_pool *pool, struct page *page) { dma_addr_t dma; int count; if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + /* Always account for inflight pages, even if we didn't + * map them + */ goto skip_dma_unmap; dma = page->dma_addr; - /* DMA unmap */ + + /* When page is unmapped, it cannot be returned our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); @@ -297,21 +304,12 @@ skip_dma_unmap: count = atomic_inc_return(&pool->pages_state_release_cnt); trace_page_pool_state_release(pool, page, count); } - -/* unmap the page and clean our state */ -void page_pool_unmap_page(struct page_pool *pool, struct page *page) -{ - /* When page is unmapped, this implies page will not be - * returned to page_pool. - */ - __page_pool_clean_page(pool, page); -} -EXPORT_SYMBOL(page_pool_unmap_page); +EXPORT_SYMBOL(page_pool_release_page); /* Return a page to the page allocator, cleaning up our state */ -static void __page_pool_return_page(struct page_pool *pool, struct page *page) +static void page_pool_return_page(struct page_pool *pool, struct page *page) { - __page_pool_clean_page(pool, page); + page_pool_release_page(pool, page); put_page(page); /* An optimization would be to call __free_pages(page, pool->p.order) @@ -320,8 +318,7 @@ static void __page_pool_return_page(struct page_pool *pool, struct page *page) */ } -static bool __page_pool_recycle_into_ring(struct page_pool *pool, - struct page *page) +static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; /* BH protection not needed if current is serving softirq */ @@ -338,7 +335,7 @@ static bool __page_pool_recycle_into_ring(struct page_pool *pool, * * Caller must provide appropriate safe context. */ -static bool __page_pool_recycle_direct(struct page *page, +static bool page_pool_recycle_in_cache(struct page *page, struct page_pool *pool) { if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) @@ -357,8 +354,14 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page) return !page_is_pfmemalloc(page); } -void __page_pool_put_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +/* 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). + * If the page refcnt != 1, then the page will be returned to memory + * subsystem. + */ +void page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the @@ -375,12 +378,12 @@ void __page_pool_put_page(struct page_pool *pool, struct page *page, dma_sync_size); if (allow_direct && in_serving_softirq()) - if (__page_pool_recycle_direct(page, pool)) + if (page_pool_recycle_in_cache(page, pool)) return; - if (!__page_pool_recycle_into_ring(pool, page)) { + if (!page_pool_recycle_in_ring(pool, page)) { /* Cache full, fallback to free pages */ - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } return; } @@ -397,12 +400,13 @@ void __page_pool_put_page(struct page_pool *pool, struct page *page, * doing refcnt based recycle tricks, meaning another process * will be invoking put_page. */ - __page_pool_clean_page(pool, page); + /* Do not replace this with page_pool_return_page() */ + page_pool_release_page(pool, page); put_page(page); } -EXPORT_SYMBOL(__page_pool_put_page); +EXPORT_SYMBOL(page_pool_put_page); -static void __page_pool_empty_ring(struct page_pool *pool) +static void page_pool_empty_ring(struct page_pool *pool) { struct page *page; @@ -413,7 +417,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) pr_crit("%s() page_pool refcnt %d violation\n", __func__, page_ref_count(page)); - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } @@ -443,7 +447,7 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool) */ while (pool->alloc.count) { page = pool->alloc.cache[--pool->alloc.count]; - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } @@ -455,7 +459,7 @@ static void page_pool_scrub(struct page_pool *pool) /* No more consumers should exist, but producers could still * be in-flight. */ - __page_pool_empty_ring(pool); + page_pool_empty_ring(pool); } static int page_pool_release(struct page_pool *pool) @@ -529,7 +533,7 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) /* Flush pool alloc cache, as refill will check NUMA node */ while (pool->alloc.count) { page = pool->alloc.cache[--pool->alloc.count]; - __page_pool_return_page(pool, page); + page_pool_return_page(pool, page); } } EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e1152f4ffe33..14e6ea21c378 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3909,7 +3909,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && - (dev->priv_flags & IFF_BRIDGE_PORT)) { + netif_is_bridge_port(dev)) { struct net_device *br_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops = br_dev->netdev_ops; @@ -4020,7 +4020,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && - (dev->priv_flags & IFF_BRIDGE_PORT)) { + netif_is_bridge_port(dev)) { struct net_device *br_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops = br_dev->netdev_ops; @@ -4246,13 +4246,13 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (!br_idx) { /* user did not specify a specific bridge */ - if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (netif_is_bridge_port(dev)) { br_dev = netdev_master_upper_dev_get(dev); cops = br_dev->netdev_ops; } } else { if (dev != br_dev && - !(dev->priv_flags & IFF_BRIDGE_PORT)) + !netif_is_bridge_port(dev)) continue; if (br_dev != netdev_master_upper_dev_get(dev) && @@ -4264,7 +4264,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; - if (dev->priv_flags & IFF_BRIDGE_PORT) { + if (netif_is_bridge_port(dev)) { if (cops && cops->ndo_fdb_dump) { err = cops->ndo_fdb_dump(skb, cb, br_dev, dev, @@ -4414,7 +4414,7 @@ static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (dev) { if (!ndm_flags || (ndm_flags & NTF_MASTER)) { - if (!(dev->priv_flags & IFF_BRIDGE_PORT)) { + if (!netif_is_bridge_port(dev)) { NL_SET_ERR_MSG(extack, "Device is not a bridge port"); return -EINVAL; } @@ -4553,7 +4553,11 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, brport_nla_put_flag(skb, flags, mask, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) || brport_nla_put_flag(skb, flags, mask, - IFLA_BRPORT_PROXYARP, BR_PROXYARP)) { + IFLA_BRPORT_PROXYARP, BR_PROXYARP) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD)) { nla_nest_cancel(skb, protinfo); goto nla_put_failure; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ded2d5227678..eeb28cb85664 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -512,7 +512,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED); refcount_set(&psock->refcnt, 1); - rcu_assign_sk_user_data(sk, psock); + rcu_assign_sk_user_data_nocopy(sk, psock); sock_hold(sk); return psock; diff --git a/net/core/sock.c b/net/core/sock.c index a4c8fac781ff..e4af4dbc1c9e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1572,13 +1572,14 @@ static inline void sock_lock_init(struct sock *sk) */ static void sock_copy(struct sock *nsk, const struct sock *osk) { + const struct proto *prot = READ_ONCE(osk->sk_prot); #ifdef CONFIG_SECURITY_NETWORK void *sptr = nsk->sk_security; #endif memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, - osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; @@ -1792,16 +1793,17 @@ static void sk_init_common(struct sock *sk) */ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { + struct proto *prot = READ_ONCE(sk->sk_prot); struct sock *newsk; bool is_charged = true; - newsk = sk_prot_alloc(sk->sk_prot, priority, sk->sk_family); + newsk = sk_prot_alloc(prot, priority, sk->sk_family); if (newsk != NULL) { struct sk_filter *filter; sock_copy(newsk, sk); - newsk->sk_prot_creator = sk->sk_prot; + newsk->sk_prot_creator = prot; /* SANITY */ if (likely(newsk->sk_net_refcnt)) @@ -1863,6 +1865,12 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) goto out; } + /* Clear sk_user_data if parent had the pointer tagged + * as not suitable for copying when cloning. + */ + if (sk_user_data_is_nocopy(newsk)) + RCU_INIT_POINTER(newsk->sk_user_data, NULL); + newsk->sk_err = 0; newsk->sk_err_soft = 0; newsk->sk_priority = 0; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 085cef5857bb..2e0f465295c3 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -10,6 +10,7 @@ #include <linux/skmsg.h> #include <linux/list.h> #include <linux/jhash.h> +#include <linux/sock_diag.h> struct bpf_stab { struct bpf_map map; @@ -31,7 +32,8 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || + (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -228,6 +230,30 @@ out: return ret; } +static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) +{ + struct sk_psock *psock; + int ret; + + psock = sk_psock_get_checked(sk); + if (IS_ERR(psock)) + return PTR_ERR(psock); + + if (psock) { + tcp_bpf_reinit(sk); + return 0; + } + + psock = sk_psock_init(sk, map->numa_node); + if (!psock) + return -ENOMEM; + + ret = tcp_bpf_init(sk); + if (ret < 0) + sk_psock_put(sk, psock); + return ret; +} + static void sock_map_free(struct bpf_map *map) { struct bpf_stab *stab = container_of(map, struct bpf_stab, map); @@ -275,7 +301,22 @@ static struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) static void *sock_map_lookup(struct bpf_map *map, void *key) { - return ERR_PTR(-EOPNOTSUPP); + return __sock_map_lookup_elem(map, *(u32 *)key); +} + +static void *sock_map_lookup_sys(struct bpf_map *map, void *key) +{ + struct sock *sk; + + if (map->value_size != sizeof(u64)) + return ERR_PTR(-ENOSPC); + + sk = __sock_map_lookup_elem(map, *(u32 *)key); + if (!sk) + return ERR_PTR(-ENOENT); + + sock_gen_cookie(sk); + return &sk->sk_cookie; } static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, @@ -334,6 +375,11 @@ static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next) return 0; } +static bool sock_map_redirect_allowed(const struct sock *sk) +{ + return sk->sk_state != TCP_LISTEN; +} + static int sock_map_update_common(struct bpf_map *map, u32 idx, struct sock *sk, u64 flags) { @@ -356,7 +402,14 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, if (!link) return -ENOMEM; - ret = sock_map_link(map, &stab->progs, sk); + /* Only sockets we can redirect into/from in BPF need to hold + * refs to parser/verdict progs and have their sk_data_ready + * and sk_write_space callbacks overridden. + */ + if (sock_map_redirect_allowed(sk)) + ret = sock_map_link(map, &stab->progs, sk); + else + ret = sock_map_link_no_progs(map, sk); if (ret < 0) goto out_free; @@ -391,7 +444,8 @@ out_free: static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) { return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || - ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; + ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB || + ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } static bool sock_map_sk_is_suitable(const struct sock *sk) @@ -400,14 +454,26 @@ static bool sock_map_sk_is_suitable(const struct sock *sk) sk->sk_protocol == IPPROTO_TCP; } +static bool sock_map_sk_state_allowed(const struct sock *sk) +{ + return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); +} + static int sock_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { - u32 ufd = *(u32 *)value; u32 idx = *(u32 *)key; struct socket *sock; struct sock *sk; int ret; + u64 ufd; + + if (map->value_size == sizeof(u64)) + ufd = *(u64 *)value; + else + ufd = *(u32 *)value; + if (ufd > S32_MAX) + return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) @@ -423,7 +489,7 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, } sock_map_sk_acquire(sk); - if (sk->sk_state != TCP_ESTABLISHED) + if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else ret = sock_map_update_common(map, idx, sk, flags); @@ -460,13 +526,17 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, struct bpf_map *, map, u32, key, u64, flags) { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) + + sk = __sock_map_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = sk; return SK_PASS; } @@ -483,12 +553,17 @@ const struct bpf_func_proto bpf_sk_redirect_map_proto = { BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, struct bpf_map *, map, u32, key, u64, flags) { + struct sock *sk; + if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - msg->flags = flags; - msg->sk_redir = __sock_map_lookup_elem(map, key); - if (!msg->sk_redir) + + sk = __sock_map_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + msg->flags = flags; + msg->sk_redir = sk; return SK_PASS; } @@ -506,6 +581,7 @@ const struct bpf_map_ops sock_map_ops = { .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, + .map_lookup_elem_sys_only = sock_map_lookup_sys, .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_map_delete_elem, .map_lookup_elem = sock_map_lookup, @@ -518,7 +594,7 @@ struct bpf_htab_elem { u32 hash; struct sock *sk; struct hlist_node node; - u8 key[0]; + u8 key[]; }; struct bpf_htab_bucket { @@ -680,7 +756,14 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, if (!link) return -ENOMEM; - ret = sock_map_link(map, &htab->progs, sk); + /* Only sockets we can redirect into/from in BPF need to hold + * refs to parser/verdict progs and have their sk_data_ready + * and sk_write_space callbacks overridden. + */ + if (sock_map_redirect_allowed(sk)) + ret = sock_map_link(map, &htab->progs, sk); + else + ret = sock_map_link_no_progs(map, sk); if (ret < 0) goto out_free; @@ -729,10 +812,17 @@ out_free: static int sock_hash_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { - u32 ufd = *(u32 *)value; struct socket *sock; struct sock *sk; int ret; + u64 ufd; + + if (map->value_size == sizeof(u64)) + ufd = *(u64 *)value; + else + ufd = *(u32 *)value; + if (ufd > S32_MAX) + return -EINVAL; sock = sockfd_lookup(ufd, &ret); if (!sock) @@ -748,7 +838,7 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key, } sock_map_sk_acquire(sk); - if (sk->sk_state != TCP_ESTABLISHED) + if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; else ret = sock_hash_update_common(map, key, sk, flags); @@ -808,7 +898,8 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size == 0 || - attr->value_size != 4 || + (attr->value_size != sizeof(u32) && + attr->value_size != sizeof(u64)) || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->key_size > MAX_BPF_STACK) @@ -885,6 +976,26 @@ static void sock_hash_free(struct bpf_map *map) kfree(htab); } +static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) +{ + struct sock *sk; + + if (map->value_size != sizeof(u64)) + return ERR_PTR(-ENOSPC); + + sk = __sock_hash_lookup_elem(map, key); + if (!sk) + return ERR_PTR(-ENOENT); + + sock_gen_cookie(sk); + return &sk->sk_cookie; +} + +static void *sock_hash_lookup(struct bpf_map *map, void *key) +{ + return __sock_hash_lookup_elem(map, key); +} + static void sock_hash_release_progs(struct bpf_map *map) { psock_progs_drop(&container_of(map, struct bpf_htab, map)->progs); @@ -916,13 +1027,17 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, struct bpf_map *, map, void *, key, u64, flags) { struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); + struct sock *sk; if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - tcb->bpf.flags = flags; - tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key); - if (!tcb->bpf.sk_redir) + + sk = __sock_hash_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + tcb->bpf.flags = flags; + tcb->bpf.sk_redir = sk; return SK_PASS; } @@ -939,12 +1054,17 @@ const struct bpf_func_proto bpf_sk_redirect_hash_proto = { BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, struct bpf_map *, map, void *, key, u64, flags) { + struct sock *sk; + if (unlikely(flags & ~(BPF_F_INGRESS))) return SK_DROP; - msg->flags = flags; - msg->sk_redir = __sock_hash_lookup_elem(map, key); - if (!msg->sk_redir) + + sk = __sock_hash_lookup_elem(map, key); + if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + + msg->flags = flags; + msg->sk_redir = sk; return SK_PASS; } @@ -964,7 +1084,8 @@ const struct bpf_map_ops sock_hash_ops = { .map_get_next_key = sock_hash_get_next_key, .map_update_elem = sock_hash_update_elem, .map_delete_elem = sock_hash_delete_elem, - .map_lookup_elem = sock_map_lookup, + .map_lookup_elem = sock_hash_lookup, + .map_lookup_elem_sys_only = sock_hash_lookup_sys, .map_release_uref = sock_hash_release_progs, .map_check_btf = map_check_no_btf, }; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 91e9f2223c39..adcb3aea576d 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -16,27 +16,8 @@ DEFINE_SPINLOCK(reuseport_lock); -#define REUSEPORT_MIN_ID 1 static DEFINE_IDA(reuseport_ida); -int reuseport_get_id(struct sock_reuseport *reuse) -{ - int id; - - if (reuse->reuseport_id) - return reuse->reuseport_id; - - id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0, - /* Called under reuseport_lock */ - GFP_ATOMIC); - if (id < 0) - return id; - - reuse->reuseport_id = id; - - return reuse->reuseport_id; -} - static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + @@ -55,6 +36,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; + int id, ret = 0; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context @@ -78,10 +60,18 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { - spin_unlock_bh(&reuseport_lock); - return -ENOMEM; + ret = -ENOMEM; + goto out; } + id = ida_alloc(&reuseport_ida, GFP_ATOMIC); + if (id < 0) { + kfree(reuse); + ret = id; + goto out; + } + + reuse->reuseport_id = id; reuse->socks[0] = sk; reuse->num_socks = 1; reuse->bind_inany = bind_inany; @@ -90,7 +80,7 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) out: spin_unlock_bh(&reuseport_lock); - return 0; + return ret; } EXPORT_SYMBOL(reuseport_alloc); @@ -134,8 +124,7 @@ static void reuseport_free_rcu(struct rcu_head *head) reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); - if (reuse->reuseport_id) - ida_simple_remove(&reuseport_ida, reuse->reuseport_id); + ida_free(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } @@ -199,12 +188,15 @@ void reuseport_detach_sock(struct sock *sk) reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); - /* At least one of the sk in this reuseport group is added to - * a bpf map. Notify the bpf side. The bpf map logic will - * remove the sk if it is indeed added to a bpf map. + /* Notify the bpf side. The sk may be added to a sockarray + * map. If so, sockarray logic will remove it from the map. + * + * Other bpf map types that work with reuseport, like sockmap, + * don't need an explicit callback from here. They override sk + * unhash/close ops to remove the sk from the map before we + * get to this point. */ - if (reuse->reuseport_id) - bpf_sk_reuseport_detach(sk); + bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); diff --git a/net/core/xdp.c b/net/core/xdp.c index 8310714c47fd..4c7ea85486af 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -372,7 +372,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); napi_direct &= !xdp_return_frame_no_direct(); - page_pool_put_page(xa->page_pool, page, napi_direct); + page_pool_put_full_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 25187528c308..c5c74a34d139 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -216,6 +216,7 @@ EXPORT_SYMBOL_GPL(dccp_check_req); */ int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb) + __releases(child) { int ret = 0; const int state = child->sk_state; diff --git a/net/dsa/port.c b/net/dsa/port.c index 774facb8d547..d4450a454249 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -489,9 +489,11 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, } static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int mode, phy_interface_t interface, - struct phy_device *phydev) + int speed, int duplex, + bool tx_pause, bool rx_pause) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -502,7 +504,8 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, return; } - ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev, + speed, duplex, tx_pause, rx_pause); } const struct phylink_mac_ops dsa_port_phylink_mac_ops = { diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 636ec6d5110e..7b6969af5ae7 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -168,6 +168,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(400000, LR8_ER8_FR8, Full), __DEFINE_LINK_MODE_NAME(400000, DR8, Full), __DEFINE_LINK_MODE_NAME(400000, CR8, Full), + __DEFINE_SPECIAL_MODE_NAME(FEC_LLRS, "LLRS"), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index 96f20be64553..f049b97072fe 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -237,6 +237,7 @@ static const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), + __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), }; static const struct nla_policy diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index ff0c24371e33..f4c2ac445b3f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -35,9 +35,6 @@ * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ - -#define VERSION "0.409" - #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> @@ -304,8 +301,6 @@ static inline void alias_free_mem_rcu(struct fib_alias *fa) call_rcu(&fa->rcu, __alias_free_mem); } -#define TNODE_KMALLOC_MAX \ - ilog2((PAGE_SIZE - TNODE_SIZE(0)) / sizeof(struct key_vector *)) #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3b9c7a2725a9..47f0502b2101 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -107,8 +107,6 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) -#define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ebe7060d0fc9..042599cc691d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2774,6 +2774,54 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); +struct rtable *ip_route_output_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, __be32 *saddr, + const struct ip_tunnel_info *info, + u8 protocol, bool use_cache) +{ +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct rtable *rt = NULL; + struct flowi4 fl4; + __u8 tos; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + rt = dst_cache_get_ip4(dst_cache, saddr); + if (rt) + return rt; + } +#endif + memset(&fl4, 0, sizeof(fl4)); + fl4.flowi4_mark = skb->mark; + fl4.flowi4_proto = protocol; + fl4.daddr = info->key.u.ipv4.dst; + fl4.saddr = info->key.u.ipv4.src; + tos = info->key.tos; + fl4.flowi4_tos = RT_TOS(tos); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (rt->dst.dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI4\n", &fl4.daddr); + ip_rt_put(rt); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr); +#endif + *saddr = fl4.saddr; + return rt; +} +EXPORT_SYMBOL_GPL(ip_route_output_tunnel); + /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9684af02e0a5..d9531b4b33f2 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -555,18 +555,6 @@ static struct ctl_table ipv4_table[] = { }, #endif /* CONFIG_NETLABEL */ { - .procname = "tcp_available_congestion_control", - .maxlen = TCP_CA_BUF_MAX, - .mode = 0444, - .proc_handler = proc_tcp_available_congestion_control, - }, - { - .procname = "tcp_allowed_congestion_control", - .maxlen = TCP_CA_BUF_MAX, - .mode = 0644, - .proc_handler = proc_allowed_congestion_control, - }, - { .procname = "tcp_available_ulp", .maxlen = TCP_ULP_BUF_MAX, .mode = 0444, @@ -886,6 +874,18 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_tcp_congestion_control, }, { + .procname = "tcp_available_congestion_control", + .maxlen = TCP_CA_BUF_MAX, + .mode = 0444, + .proc_handler = proc_tcp_available_congestion_control, + }, + { + .procname = "tcp_allowed_congestion_control", + .maxlen = TCP_CA_BUF_MAX, + .mode = 0644, + .proc_handler = proc_allowed_congestion_control, + }, + { .procname = "tcp_keepalive_time", .data = &init_net.ipv4.sysctl_tcp_keepalive_time, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index eb2d80519f8e..48aa457a9516 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3667,13 +3667,35 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - if (len != sizeof(zc)) + if (len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; + if (len > sizeof(zc)) { + len = sizeof(zc); + if (put_user(len, optlen)) + return -EFAULT; + } if (copy_from_user(&zc, optval, len)) return -EFAULT; lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc); release_sock(sk); + if (len == sizeof(zc)) + goto zerocopy_rcv_sk_err; + switch (len) { + case offsetofend(struct tcp_zerocopy_receive, err): + goto zerocopy_rcv_sk_err; + case offsetofend(struct tcp_zerocopy_receive, inq): + goto zerocopy_rcv_inq; + case offsetofend(struct tcp_zerocopy_receive, length): + default: + goto zerocopy_rcv_out; + } +zerocopy_rcv_sk_err: + if (!err) + zc.err = sock_error(sk); +zerocopy_rcv_inq: + zc.inq = tcp_inq_hint(sk); +zerocopy_rcv_out: if (!err && copy_to_user(optval, &zc, len)) err = -EFAULT; return err; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a01428f80c1..7d6e1b75d4d4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -645,8 +645,10 @@ static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock) /* Reinit occurs when program types change e.g. TCP_BPF_TX is removed * or added requiring sk_prot hook updates. We keep original saved * hooks in this case. + * + * Pairs with lockless read in sk_clone_lock(). */ - sk->sk_prot = &tcp_bpf_prots[family][config]; + WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); } static int tcp_bpf_assert_proto_ops(struct proto *ops) @@ -691,3 +693,17 @@ int tcp_bpf_init(struct sock *sk) rcu_read_unlock(); return 0; } + +/* If a child got cloned from a listening socket that had tcp_bpf + * protocol callbacks installed, we need to restore the callbacks to + * the default ones because the child does not inherit the psock state + * that tcp_bpf callbacks expect. + */ +void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) +{ + int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; + struct proto *prot = newsk->sk_prot; + + if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + newsk->sk_prot = sk->sk_prot_creator; +} diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index df1166b76126..52acf0bc2ee5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1019,7 +1019,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, if (!md5sig) return NULL; - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) @@ -1064,7 +1065,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, if (family == AF_INET6) size = sizeof(struct in6_addr); #endif - hlist_for_each_entry_rcu(key, &md5sig->head, node) { + hlist_for_each_entry_rcu(key, &md5sig->head, node, + lockdep_sock_is_held(sk)) { if (key->family != family) continue; if (key->l3index && key->l3index != l3index) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ad3b56d9fa71..c8274371c3d0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -548,6 +548,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->fastopen_req = NULL; RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); + tcp_bpf_clone(sk, newsk); + __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); return newsk; diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 38d3ad141161..2703f24c5d1a 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -22,7 +22,8 @@ static struct tcp_ulp_ops *tcp_ulp_find(const char *name) { struct tcp_ulp_ops *e; - list_for_each_entry_rcu(e, &tcp_ulp_list, list) { + list_for_each_entry_rcu(e, &tcp_ulp_list, list, + lockdep_is_held(&tcp_ulp_list_lock)) { if (strcmp(e->name, name) == 0) return e; } @@ -106,7 +107,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto, if (!icsk->icsk_ulp_ops) { sk->sk_write_space = write_space; - sk->sk_prot = proto; + /* Pairs with lockless read in sk_clone_lock() */ + WRITE_ONCE(sk->sk_prot, proto); return; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 087304427bbb..8a8c2d0cfcc8 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -54,6 +54,7 @@ #include <linux/mroute6.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> +#include <net/ip_tunnels.h> static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -1196,6 +1197,75 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); +/** + * ip6_dst_lookup_tunnel - perform route lookup on tunnel + * @skb: Packet for which lookup is done + * @dev: Tunnel device + * @net: Network namespace of tunnel device + * @sk: Socket which provides route info + * @saddr: Memory to store the src ip address + * @info: Tunnel information + * @protocol: IP protocol + * @use_cahce: Flag to enable cache usage + * This function performs a route lookup on a tunnel + * + * It returns a valid dst pointer and stores src address to be used in + * tunnel in param saddr on success, else a pointer encoded error code. + */ + +struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, + struct in6_addr *saddr, + const struct ip_tunnel_info *info, + u8 protocol, + bool use_cache) +{ + struct dst_entry *dst = NULL; +#ifdef CONFIG_DST_CACHE + struct dst_cache *dst_cache; +#endif + struct flowi6 fl6; + __u8 prio; + +#ifdef CONFIG_DST_CACHE + dst_cache = (struct dst_cache *)&info->dst_cache; + if (use_cache) { + dst = dst_cache_get_ip6(dst_cache, saddr); + if (dst) + return dst; + } +#endif + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = protocol; + fl6.daddr = info->key.u.ipv6.dst; + fl6.saddr = info->key.u.ipv6.src; + prio = info->key.tos; + fl6.flowlabel = ip6_make_flowinfo(RT_TOS(prio), + info->key.label); + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, + NULL); + if (IS_ERR(dst)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (use_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); +#endif + *saddr = fl6.saddr; + return dst; +} +EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); + static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index bfa49ff70531..d6483926f449 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -97,7 +97,8 @@ static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES #define ip6mr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \ + lockdep_rtnl_is_held()) static struct mr_table *ip6mr_mr_table_iter(struct net *net, struct mr_table *mrt) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2922d4150d88..54fb8d452a7b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -47,7 +47,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout); #if 0 #define dprintk(args...) printk(KERN_DEBUG args) #else -#define dprintk(args...) +#define dprintk(args...) do {} while (0) #endif /* Maybe we'll add some more in the future. */ diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index f3a36c16a5e7..a4eccb98220a 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -56,7 +56,7 @@ found: return sk; } -static void *llc_seq_start(struct seq_file *seq, loff_t *pos) +static void *llc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { loff_t l = *pos; diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index 57748cab0e28..b31f1021ad9c 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -26,12 +26,20 @@ void ieee80211_aes_cmac(struct crypto_shash *tfm, const u8 *aad, { SHASH_DESC_ON_STACK(desc, tfm); u8 out[AES_BLOCK_SIZE]; + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, data_len - 8 - CMAC_TLEN); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN); + } crypto_shash_finup(desc, zero, CMAC_TLEN, out); memcpy(mic, out, CMAC_TLEN); @@ -41,12 +49,21 @@ void ieee80211_aes_cmac_256(struct crypto_shash *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic) { SHASH_DESC_ON_STACK(desc, tfm); + const __le16 *fc; desc->tfm = tfm; crypto_shash_init(desc); crypto_shash_update(desc, aad, AAD_LEN); - crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + crypto_shash_update(desc, zero, 8); + crypto_shash_update(desc, data + 8, + data_len - 8 - CMAC_TLEN_256); + } else { + crypto_shash_update(desc, data, data_len - CMAC_TLEN_256); + } crypto_shash_finup(desc, zero, CMAC_TLEN_256, mic); } diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index 363ad1c1dc0c..16ba09cb5def 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -17,10 +17,11 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, const u8 *data, size_t data_len, u8 *mic) { - struct scatterlist sg[4]; + struct scatterlist sg[5]; u8 *zero, *__aad, iv[AES_BLOCK_SIZE]; struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); + const __le16 *fc; if (data_len < GMAC_MIC_LEN) return -EINVAL; @@ -33,11 +34,22 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, __aad = zero + GMAC_MIC_LEN; memcpy(__aad, aad, GMAC_AAD_LEN); - sg_init_table(sg, 4); - sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); - sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); - sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); - sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + fc = (const __le16 *)aad; + if (ieee80211_is_beacon(*fc)) { + /* mask Timestamp field to zero */ + sg_init_table(sg, 5); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], zero, 8); + sg_set_buf(&sg[2], data + 8, data_len - 8 - GMAC_MIC_LEN); + sg_set_buf(&sg[3], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[4], mic, GMAC_MIC_LEN); + } else { + sg_init_table(sg, 4); + sg_set_buf(&sg[0], __aad, GMAC_AAD_LEN); + sg_set_buf(&sg[1], data, data_len - GMAC_MIC_LEN); + sg_set_buf(&sg[2], zero, GMAC_MIC_LEN); + sg_set_buf(&sg[3], mic, GMAC_MIC_LEN); + } memcpy(iv, nonce, GMAC_NONCE_LEN); memset(iv + GMAC_NONCE_LEN, 0, sizeof(iv) - GMAC_NONCE_LEN); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 6aee699deb28..7b654d2b8bb2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -568,7 +568,8 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, if (pairwise && key_idx < NUM_DEFAULT_KEYS) key = rcu_dereference(sta->ptk[key_idx]); else if (!pairwise && - key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) key = rcu_dereference(sta->gtk[key_idx]); } else key = rcu_dereference(sdata->keys[key_idx]); @@ -680,6 +681,17 @@ static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, return 0; } +static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, + struct net_device *dev, + u8 key_idx) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + ieee80211_set_default_beacon_key(sdata, key_idx); + + return 0; +} + void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) @@ -981,7 +993,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | BSS_CHANGED_TWT | - BSS_CHANGED_HE_OBSS_PD; + BSS_CHANGED_HE_OBSS_PD | + BSS_CHANGED_HE_BSS_COLOR; int err; int prev_beacon_int; @@ -989,20 +1002,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (old) return -EALREADY; - switch (params->smps_mode) { - case NL80211_SMPS_OFF: - sdata->smps_mode = IEEE80211_SMPS_OFF; - break; - case NL80211_SMPS_STATIC: - sdata->smps_mode = IEEE80211_SMPS_STATIC; - break; - case NL80211_SMPS_DYNAMIC: - sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; - break; - default: - return -EINVAL; - } - sdata->u.ap.req_smps = sdata->smps_mode; + if (params->smps_mode != NL80211_SMPS_OFF) + return -ENOTSUPP; + + sdata->smps_mode = IEEE80211_SMPS_OFF; sdata->needed_rx_chains = sdata->local->rx_chains; @@ -1054,6 +1057,8 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.twt_responder = params->twt_responder; memcpy(&sdata->vif.bss_conf.he_obss_pd, ¶ms->he_obss_pd, sizeof(struct ieee80211_he_obss_pd)); + memcpy(&sdata->vif.bss_conf.he_bss_color, ¶ms->he_bss_color, + sizeof(struct ieee80211_he_bss_color)); sdata->vif.bss_conf.ssid_len = params->ssid_len; if (params->ssid_len) @@ -1166,7 +1171,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); - sdata->u.ap.driver_smps_mode = IEEE80211_SMPS_OFF; kfree(sdata->vif.bss_conf.ftmr_params); sdata->vif.bss_conf.ftmr_params = NULL; @@ -1691,20 +1695,6 @@ static int ieee80211_change_station(struct wiphy *wiphy, mutex_unlock(&local->sta_mtx); - if ((sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && - sta->known_smps_mode != sta->sdata->bss->req_smps && - test_sta_flag(sta, WLAN_STA_AUTHORIZED) && - sta_info_tx_streams(sta) != 1) { - ht_dbg(sta->sdata, - "%pM just authorized and MIMO capable - update SMPS\n", - sta->sta.addr); - ieee80211_send_smps_action(sta->sdata, - sta->sdata->bss->req_smps, - sta->sta.addr, - sta->sdata->vif.bss_conf.bssid); - } - if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { ieee80211_recalc_ps(local); @@ -2636,74 +2626,6 @@ static int ieee80211_testmode_dump(struct wiphy *wiphy, } #endif -int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode) -{ - struct sta_info *sta; - enum ieee80211_smps_mode old_req; - - if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP)) - return -EINVAL; - - if (sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT) - return 0; - - old_req = sdata->u.ap.req_smps; - sdata->u.ap.req_smps = smps_mode; - - /* AUTOMATIC doesn't mean much for AP - don't allow it */ - if (old_req == smps_mode || - smps_mode == IEEE80211_SMPS_AUTOMATIC) - return 0; - - ht_dbg(sdata, - "SMPS %d requested in AP mode, sending Action frame to %d stations\n", - smps_mode, atomic_read(&sdata->u.ap.num_mcast_sta)); - - mutex_lock(&sdata->local->sta_mtx); - list_for_each_entry(sta, &sdata->local->sta_list, list) { - /* - * Only stations associated to our AP and - * associated VLANs - */ - if (sta->sdata->bss != &sdata->u.ap) - continue; - - /* This station doesn't support MIMO - skip it */ - if (sta_info_tx_streams(sta) == 1) - continue; - - /* - * Don't wake up a STA just to send the action frame - * unless we are getting more restrictive. - */ - if (test_sta_flag(sta, WLAN_STA_PS_STA) && - !ieee80211_smps_is_restrictive(sta->known_smps_mode, - smps_mode)) { - ht_dbg(sdata, "Won't send SMPS to sleeping STA %pM\n", - sta->sta.addr); - continue; - } - - /* - * If the STA is not authorized, wait until it gets - * authorized and the action frame will be sent then. - */ - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) - continue; - - ht_dbg(sdata, "Sending SMPS to %pM\n", sta->sta.addr); - ieee80211_send_smps_action(sdata, smps_mode, sta->sta.addr, - sdata->vif.bss_conf.bssid); - } - mutex_unlock(&sdata->local->sta_mtx); - - sdata->smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, &sdata->recalc_smps); - - return 0; -} - int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode) { @@ -3964,6 +3886,60 @@ ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, return drv_abort_pmsr(local, sdata, request); } +static int ieee80211_set_tid_config(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->set_tid_config) + return -EOPNOTSUPP; + + if (!tid_conf->peer) + return drv_set_tid_config(sdata->local, sdata, NULL, tid_conf); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, tid_conf->peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_set_tid_config(sdata->local, sdata, &sta->sta, tid_conf); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + +static int ieee80211_reset_tid_config(struct wiphy *wiphy, + struct net_device *dev, + const u8 *peer, u8 tid) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + int ret; + + if (!sdata->local->ops->reset_tid_config) + return -EOPNOTSUPP; + + if (!peer) + return drv_reset_tid_config(sdata->local, sdata, NULL, tid); + + mutex_lock(&sdata->local->sta_mtx); + sta = sta_info_get_bss(sdata, peer); + if (!sta) { + mutex_unlock(&sdata->local->sta_mtx); + return -ENOENT; + } + + ret = drv_reset_tid_config(sdata->local, sdata, &sta->sta, tid); + mutex_unlock(&sdata->local->sta_mtx); + + return ret; +} + const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -3975,6 +3951,7 @@ const struct cfg80211_ops mac80211_config_ops = { .get_key = ieee80211_get_key, .set_default_key = ieee80211_config_default_key, .set_default_mgmt_key = ieee80211_config_default_mgmt_key, + .set_default_beacon_key = ieee80211_config_default_beacon_key, .start_ap = ieee80211_start_ap, .change_beacon = ieee80211_change_beacon, .stop_ap = ieee80211_stop_ap, @@ -4063,4 +4040,6 @@ const struct cfg80211_ops mac80211_config_ops = { .start_pmsr = ieee80211_start_pmsr, .abort_pmsr = ieee80211_abort_pmsr, .probe_mesh_link = ieee80211_probe_mesh_link, + .set_tid_config = ieee80211_set_tid_config, + .reset_tid_config = ieee80211_reset_tid_config, }; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index ad41d74530c6..54080290d6e2 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -150,6 +150,59 @@ static const struct file_operations aqm_ops = { .llseek = default_llseek, }; +static ssize_t airtime_flags_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[128] = {}, *pos, *end; + + pos = buf; + end = pos + sizeof(buf) - 1; + + if (local->airtime_flags & AIRTIME_USE_TX) + pos += scnprintf(pos, end - pos, "AIRTIME_TX\t(%lx)\n", + AIRTIME_USE_TX); + if (local->airtime_flags & AIRTIME_USE_RX) + pos += scnprintf(pos, end - pos, "AIRTIME_RX\t(%lx)\n", + AIRTIME_USE_RX); + + return simple_read_from_buffer(user_buf, count, ppos, buf, + strlen(buf)); +} + +static ssize_t airtime_flags_write(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[16]; + size_t len; + + if (count > sizeof(buf)) + return -EINVAL; + + if (copy_from_user(buf, user_buf, count)) + return -EFAULT; + + buf[sizeof(buf) - 1] = 0; + len = strlen(buf); + if (len > 0 && buf[len - 1] == '\n') + buf[len - 1] = 0; + + if (kstrtou16(buf, 0, &local->airtime_flags)) + return -EINVAL; + + return count; +} + +static const struct file_operations airtime_flags_ops = { + .write = airtime_flags_write, + .read = airtime_flags_read, + .open = simple_open, + .llseek = default_llseek, +}; + static ssize_t aql_txq_limit_read(struct file *file, char __user *user_buf, size_t count, @@ -522,8 +575,7 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); - debugfs_create_u16("airtime_flags", 0600, - phyd, &local->airtime_flags); + DEBUGFS_ADD_MODE(airtime_flags, 0600); DEBUGFS_ADD(aql_txq_limit); debugfs_create_u32("aql_threshold", 0600, diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 7b8735ced2a1..98a713475e0f 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -433,6 +433,37 @@ void ieee80211_debugfs_key_remove_mgmt_default(struct ieee80211_sub_if_data *sda sdata->debugfs.default_mgmt_key = NULL; } +void +ieee80211_debugfs_key_add_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + char buf[50]; + struct ieee80211_key *key; + + if (!sdata->vif.debugfs_dir) + return; + + key = key_mtx_dereference(sdata->local, + sdata->default_beacon_key); + if (key) { + sprintf(buf, "../keys/%d", key->debugfs.cnt); + sdata->debugfs.default_beacon_key = + debugfs_create_symlink("default_beacon_key", + sdata->vif.debugfs_dir, buf); + } else { + ieee80211_debugfs_key_remove_beacon_default(sdata); + } +} + +void +ieee80211_debugfs_key_remove_beacon_default(struct ieee80211_sub_if_data *sdata) +{ + if (!sdata) + return; + + debugfs_remove(sdata->debugfs.default_beacon_key); + sdata->debugfs.default_beacon_key = NULL; +} + void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) { diff --git a/net/mac80211/debugfs_key.h b/net/mac80211/debugfs_key.h index 1cd7b8bff56c..af7cf495f8d1 100644 --- a/net/mac80211/debugfs_key.h +++ b/net/mac80211/debugfs_key.h @@ -10,6 +10,10 @@ void ieee80211_debugfs_key_add_mgmt_default( struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata); +void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata); void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta); #else @@ -26,6 +30,12 @@ static inline void ieee80211_debugfs_key_add_mgmt_default( static inline void ieee80211_debugfs_key_remove_mgmt_default( struct ieee80211_sub_if_data *sdata) {} +static inline void ieee80211_debugfs_key_add_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} +static inline void ieee80211_debugfs_key_remove_beacon_default( + struct ieee80211_sub_if_data *sdata) +{} static inline void ieee80211_debugfs_key_sta_del(struct ieee80211_key *key, struct sta_info *sta) {} diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 64b544ae9966..3dbe7c5cefd1 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> + * Copyright (C) 2020 Intel Corporation */ #include <linux/kernel.h> @@ -254,15 +255,11 @@ static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata, smps_mode == IEEE80211_SMPS_AUTOMATIC)) return -EINVAL; - if (sdata->vif.type != NL80211_IFTYPE_STATION && - sdata->vif.type != NL80211_IFTYPE_AP) + if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; sdata_lock(sdata); - if (sdata->vif.type == NL80211_IFTYPE_STATION) - err = __ieee80211_request_smps_mgd(sdata, smps_mode); - else - err = __ieee80211_request_smps_ap(sdata, smps_mode); + err = __ieee80211_request_smps_mgd(sdata, smps_mode); sdata_unlock(sdata); return err; @@ -282,10 +279,6 @@ static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_sub_if_data *sdata, return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[sdata->u.mgd.req_smps], smps_modes[sdata->smps_mode]); - if (sdata->vif.type == NL80211_IFTYPE_AP) - return snprintf(buf, buflen, "request: %s\nused: %s\n", - smps_modes[sdata->u.ap.req_smps], - smps_modes[sdata->smps_mode]); return -EINVAL; } diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index c80b1e163ea4..266d63819415 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -1025,12 +1025,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); DEBUGFS_ADD_COUNTER(tx_filtered, status_stats.filtered); - if (local->ops->wake_tx_queue) + if (local->ops->wake_tx_queue) { DEBUGFS_ADD(aqm); - - if (wiphy_ext_feature_isset(local->hw.wiphy, - NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) DEBUGFS_ADD(airtime); + } if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 2c9b3eb8b652..3877710e3b48 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1358,4 +1358,31 @@ static inline void drv_del_nan_func(struct ieee80211_local *local, trace_drv_return_void(local); } +static inline int drv_set_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + might_sleep(); + ret = local->ops->set_tid_config(&local->hw, &sdata->vif, sta, + tid_conf); + trace_drv_return_int(local, ret); + + return ret; +} + +static inline int drv_reset_tid_config(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_sta *sta, u8 tid) +{ + int ret; + + might_sleep(); + ret = local->ops->reset_tid_config(&local->hw, &sdata->vif, sta, tid); + trace_drv_return_int(local, ret); + + return ret; +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 736da0035135..1087f715338b 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -3,6 +3,7 @@ * HE handling * * Copyright(c) 2017 Intel Deutschland GmbH + * Copyright(c) 2019 - 2020 Intel Corporation */ #include "ieee80211_i.h" @@ -49,6 +50,9 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, he_ppe_size); he_cap->has_he = true; + + sta->cur_max_bandwidth = ieee80211_sta_cap_rx_bw(sta); + sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); } void diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index a2e4d6b8fd98..e32906202575 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -9,6 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright 2017 Intel Deutschland GmbH + * Copyright(c) 2020 Intel Corporation */ #include <linux/ieee80211.h> @@ -144,7 +145,6 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, int i, max_tx_streams; bool changed; enum ieee80211_sta_rx_bandwidth bw; - enum ieee80211_smps_mode smps_mode; memset(&ht_cap, 0, sizeof(ht_cap)); @@ -270,24 +270,30 @@ bool ieee80211_ht_cap_ie_to_sta_ht_cap(struct ieee80211_sub_if_data *sdata, ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : IEEE80211_STA_RX_BW_20; - switch ((ht_cap.cap & IEEE80211_HT_CAP_SM_PS) - >> IEEE80211_HT_CAP_SM_PS_SHIFT) { - case WLAN_HT_CAP_SM_PS_INVALID: - case WLAN_HT_CAP_SM_PS_STATIC: - smps_mode = IEEE80211_SMPS_STATIC; - break; - case WLAN_HT_CAP_SM_PS_DYNAMIC: - smps_mode = IEEE80211_SMPS_DYNAMIC; - break; - case WLAN_HT_CAP_SM_PS_DISABLED: - smps_mode = IEEE80211_SMPS_OFF; - break; - } - - if (smps_mode != sta->sta.smps_mode) - changed = true; - sta->sta.smps_mode = smps_mode; + if (sta->sdata->vif.type == NL80211_IFTYPE_AP || + sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { + enum ieee80211_smps_mode smps_mode; + + switch ((ht_cap.cap & IEEE80211_HT_CAP_SM_PS) + >> IEEE80211_HT_CAP_SM_PS_SHIFT) { + case WLAN_HT_CAP_SM_PS_INVALID: + case WLAN_HT_CAP_SM_PS_STATIC: + smps_mode = IEEE80211_SMPS_STATIC; + break; + case WLAN_HT_CAP_SM_PS_DYNAMIC: + smps_mode = IEEE80211_SMPS_DYNAMIC; + break; + case WLAN_HT_CAP_SM_PS_DISABLED: + smps_mode = IEEE80211_SMPS_OFF; + break; + } + if (smps_mode != sta->sta.smps_mode) + changed = true; + sta->sta.smps_mode = smps_mode; + } else { + sta->sta.smps_mode = IEEE80211_SMPS_OFF; + } return changed; } @@ -544,19 +550,6 @@ void ieee80211_request_smps_mgd_work(struct work_struct *work) sdata_unlock(sdata); } -void ieee80211_request_smps_ap_work(struct work_struct *work) -{ - struct ieee80211_sub_if_data *sdata = - container_of(work, struct ieee80211_sub_if_data, - u.ap.request_smps_work); - - sdata_lock(sdata); - if (sdata_dereference(sdata->u.ap.beacon, sdata)) - __ieee80211_request_smps_ap(sdata, - sdata->u.ap.driver_smps_mode); - sdata_unlock(sdata); -} - void ieee80211_request_smps(struct ieee80211_vif *vif, enum ieee80211_smps_mode smps_mode) { @@ -572,15 +565,6 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, sdata->u.mgd.driver_smps_mode = smps_mode; ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.request_smps_work); - } else { - /* AUTOMATIC is meaningless in AP mode */ - if (WARN_ON_ONCE(smps_mode == IEEE80211_SMPS_AUTOMATIC)) - return; - if (sdata->u.ap.driver_smps_mode == smps_mode) - return; - sdata->u.ap.driver_smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, - &sdata->u.ap.request_smps_work); } } /* this might change ... don't want non-open drivers using it */ diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ad15b3be8bb3..de39f9ca9935 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #ifndef IEEE80211_I_H @@ -292,10 +292,7 @@ struct ieee80211_if_ap { struct ps_data ps; atomic_t num_mcast_sta; /* number of stations receiving multicast */ - enum ieee80211_smps_mode req_smps, /* requested smps mode */ - driver_smps_mode; /* smps mode request */ - struct work_struct request_smps_work; bool multicast_to_unicast; }; @@ -904,10 +901,13 @@ struct ieee80211_sub_if_data { /* bit field of ACM bits (BIT(802.1D tag)) */ u8 wmm_acm; - struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *keys[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *default_unicast_key; struct ieee80211_key __rcu *default_multicast_key; struct ieee80211_key __rcu *default_mgmt_key; + struct ieee80211_key __rcu *default_beacon_key; u16 sequence_number; __be16 control_port_protocol; @@ -981,9 +981,12 @@ struct ieee80211_sub_if_data { struct dentry *default_unicast_key; struct dentry *default_multicast_key; struct dentry *default_mgmt_key; + struct dentry *default_beacon_key; } debugfs; #endif + bool hw_80211_encap; + /* must be last, dynamically sized area in this! */ struct ieee80211_vif vif; }; @@ -1473,6 +1476,7 @@ struct ieee802_11_elems { const struct ieee80211_tim_ie *tim; const u8 *challenge; const u8 *rsn; + const u8 *rsnx; const u8 *erp_info; const u8 *ext_supp_rates; const u8 *wmm_info; @@ -1520,6 +1524,7 @@ struct ieee802_11_elems { u8 tim_len; u8 challenge_len; u8 rsn_len; + u8 rsnx_len; u8 ext_supp_rates_len; u8 wmm_info_len; u8 wmm_param_len; @@ -1727,6 +1732,13 @@ int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); /* interface handling */ +#define MAC80211_SUPPORTED_FEATURES_TX (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ + NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_HIGHDMA | NETIF_F_GSO_SOFTWARE) +#define MAC80211_SUPPORTED_FEATURES_RX (NETIF_F_RXCSUM) +#define MAC80211_SUPPORTED_FEATURES (MAC80211_SUPPORTED_FEATURES_TX | \ + MAC80211_SUPPORTED_FEATURES_RX) + int ieee80211_iface_init(void); void ieee80211_iface_exit(void); int ieee80211_if_add(struct ieee80211_local *local, const char *name, @@ -1762,6 +1774,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, + struct net_device *dev); void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, @@ -1948,6 +1962,11 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, enum nl80211_band band, u32 txdata_flags); +/* sta_out needs to be checked for ERR_PTR() before using */ +int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct sta_info **sta_out); + static inline void ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int tid, @@ -2132,8 +2151,6 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, enum nl80211_band band, u32 *basic_rates); int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode); -int __ieee80211_request_smps_ap(struct ieee80211_sub_if_data *sdata, - enum ieee80211_smps_mode smps_mode); void ieee80211_recalc_smps(struct ieee80211_sub_if_data *sdata); void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index af8b09214786..128b3468d13e 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 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -824,9 +824,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_ADHOC: ieee80211_ibss_stop(sdata); break; - case NL80211_IFTYPE_AP: - cancel_work_sync(&sdata->u.ap.request_smps_work); - break; case NL80211_IFTYPE_MONITOR: if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) break; @@ -1205,6 +1202,72 @@ static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_get_stats64 = ieee80211_get_stats64, }; +static const struct net_device_ops ieee80211_dataif_8023_ops = { + .ndo_open = ieee80211_open, + .ndo_stop = ieee80211_stop, + .ndo_uninit = ieee80211_uninit, + .ndo_start_xmit = ieee80211_subif_start_xmit_8023, + .ndo_set_rx_mode = ieee80211_set_multicast_list, + .ndo_set_mac_address = ieee80211_change_mac, + .ndo_select_queue = ieee80211_netdev_select_queue, + .ndo_get_stats64 = ieee80211_get_stats64, +}; + +static void __ieee80211_set_hw_80211_encap(struct ieee80211_sub_if_data *sdata, + bool enable) +{ + sdata->dev->netdev_ops = enable ? &ieee80211_dataif_8023_ops : + &ieee80211_dataif_ops; + sdata->hw_80211_encap = enable; +} + +bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *iter; + struct ieee80211_key *key; + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(iter, &local->interfaces, list) { + struct ieee80211_sub_if_data *disable = NULL; + + if (vif->type == NL80211_IFTYPE_MONITOR) { + disable = iter; + __ieee80211_set_hw_80211_encap(iter, false); + } else if (iter->vif.type == NL80211_IFTYPE_MONITOR) { + disable = sdata; + enable = false; + } + if (disable) + sdata_dbg(disable, + "disable hw 80211 encap due to mon co-exist\n"); + } + mutex_unlock(&local->iflist_mtx); + + if (enable == sdata->hw_80211_encap) + return enable; + + if (!sdata->dev) + return false; + + if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) && + (local->hw.wiphy->frag_threshold != (u32)-1)) + enable = false; + + mutex_lock(&sdata->local->key_mtx); + list_for_each_entry(key, &sdata->key_list, list) { + if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) + enable = false; + } + mutex_unlock(&sdata->local->key_mtx); + + __ieee80211_set_hw_80211_encap(sdata, enable); + + return enable; +} +EXPORT_SYMBOL(ieee80211_set_hw_80211_encap); + static void ieee80211_if_free(struct net_device *dev) { free_percpu(dev->tstats); @@ -1402,8 +1465,10 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->control_port_no_encrypt = false; sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; sdata->vif.bss_conf.idle = true; + sdata->vif.bss_conf.txpower = INT_MIN; /* unset */ sdata->noack_map = 0; + sdata->hw_80211_encap = false; /* only monitor/p2p-device differ */ if (sdata->dev) { @@ -1427,10 +1492,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, case NL80211_IFTYPE_AP: skb_queue_head_init(&sdata->u.ap.ps.bc_buf); INIT_LIST_HEAD(&sdata->u.ap.vlans); - INIT_WORK(&sdata->u.ap.request_smps_work, - ieee80211_request_smps_ap_work); sdata->vif.bss_conf.bssid = sdata->vif.addr; - sdata->u.ap.req_smps = IEEE80211_SMPS_OFF; break; case NL80211_IFTYPE_P2P_CLIENT: type = NL80211_IFTYPE_STATION; @@ -1772,6 +1834,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, if_setup, txqs, 1); if (!ndev) return -ENOMEM; + + if (!local->ops->wake_tx_queue && local->hw.wiphy->tx_queue_len) + ndev->tx_queue_len = local->hw.wiphy->tx_queue_len; + dev_net_set(ndev, wiphy_net(local->hw.wiphy)); ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); @@ -1871,6 +1937,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->u.mgd.use_4addr = params->use_4addr; ndev->features |= local->hw.netdev_features; + ndev->hw_features |= ndev->features & + MAC80211_SUPPORTED_FEATURES_TX; netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 0f889b919b06..6354491c5a09 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -177,6 +177,13 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) } } + /* TKIP countermeasures don't work in encap offload mode */ + if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP && + sdata->hw_80211_encap) { + sdata_dbg(sdata, "TKIP is not allowed in hw 80211 encap mode\n"); + return -EINVAL; + } + ret = drv_set_key(key->local, SET_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); @@ -210,12 +217,20 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + /* We cannot do software crypto of data frames with + * encapsulation offload enabled. However for 802.11w to + * function properly we need cmac/gmac keys. + */ + if (sdata->hw_80211_encap) + return -EINVAL; + /* Fall through */ + case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: - case WLAN_CIPHER_SUITE_GCMP: - case WLAN_CIPHER_SUITE_GCMP_256: /* all of these we can do in software - if driver can */ if (ret == 1) return 0; @@ -392,6 +407,31 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, mutex_unlock(&sdata->local->key_mtx); } +static void +__ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, int idx) +{ + struct ieee80211_key *key = NULL; + + assert_key_lock(sdata->local); + + if (idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS && + idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + key = key_mtx_dereference(sdata->local, sdata->keys[idx]); + + rcu_assign_pointer(sdata->default_beacon_key, key); + + ieee80211_debugfs_key_update_default(sdata); +} + +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx) +{ + mutex_lock(&sdata->local->key_mtx); + __ieee80211_set_default_beacon_key(sdata, idx); + mutex_unlock(&sdata->local->key_mtx); +} + static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, bool pairwise, @@ -400,7 +440,7 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, { int idx; int ret = 0; - bool defunikey, defmultikey, defmgmtkey; + bool defunikey, defmultikey, defmgmtkey, defbeaconkey; /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) @@ -465,6 +505,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, defmgmtkey = old && old == key_mtx_dereference(sdata->local, sdata->default_mgmt_key); + defbeaconkey = old && + old == key_mtx_dereference(sdata->local, + sdata->default_beacon_key); if (defunikey && !new) __ieee80211_set_default_key(sdata, -1, true, false); @@ -472,6 +515,8 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, __ieee80211_set_default_key(sdata, -1, false, true); if (defmgmtkey && !new) __ieee80211_set_default_mgmt_key(sdata, -1); + if (defbeaconkey && !new) + __ieee80211_set_default_beacon_key(sdata, -1); rcu_assign_pointer(sdata->keys[idx], new); if (defunikey && new) @@ -483,6 +528,9 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (defmgmtkey && new) __ieee80211_set_default_mgmt_key(sdata, new->conf.keyidx); + if (defbeaconkey && new) + __ieee80211_set_default_beacon_key(sdata, + new->conf.keyidx); } if (old) @@ -500,7 +548,9 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, struct ieee80211_key *key; int i, j, err; - if (WARN_ON(idx < 0 || idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)) + if (WARN_ON(idx < 0 || + idx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS)) return ERR_PTR(-EINVAL); key = kzalloc(sizeof(struct ieee80211_key) + key_len, GFP_KERNEL); @@ -963,6 +1013,7 @@ static void ieee80211_free_keys_iface(struct ieee80211_sub_if_data *sdata, sdata->crypto_tx_tailroom_pending_dec = 0; ieee80211_debugfs_key_remove_mgmt_default(sdata); + ieee80211_debugfs_key_remove_beacon_default(sdata); list_for_each_entry_safe(key, tmp, &sdata->key_list, list) { ieee80211_key_replace(key->sdata, key->sta, diff --git a/net/mac80211/key.h b/net/mac80211/key.h index d6d6e89cf7dd..7ad72e9b4991 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -17,6 +17,7 @@ #define NUM_DEFAULT_KEYS 4 #define NUM_DEFAULT_MGMT_KEYS 2 +#define NUM_DEFAULT_BEACON_KEYS 2 #define INVALID_PTK_KEYIDX 2 /* Keyidx always pointing to a NULL key for PTK */ struct ieee80211_local; @@ -153,6 +154,8 @@ void ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, int idx, bool uni, bool multi); void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, int idx); +void ieee80211_set_default_beacon_key(struct ieee80211_sub_if_data *sdata, + int idx); void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata, bool force_synchronize); void ieee80211_free_sta_keys(struct ieee80211_local *local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4c2b5ba3ac09..944e86da5c65 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -146,6 +146,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local) continue; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) continue; + if (sdata->vif.bss_conf.txpower == INT_MIN) + continue; power = min(power, sdata->vif.bss_conf.txpower); } rcu_read_unlock(); @@ -416,7 +418,20 @@ ieee80211_default_mgmt_stypes[NUM_NL80211_IFTYPES] = { }, [NL80211_IFTYPE_STATION] = { .tx = 0xffff, + /* + * To support Pre Association Security Negotiation (PASN) while + * already associated to one AP, allow user space to register to + * Rx authentication frames, so that the user space logic would + * be able to receive/handle authentication frames from a + * different AP as part of PASN. + * It is expected that user space would intelligently register + * for Rx authentication frames, i.e., only when PASN is used + * and configure a match filter only for PASN authentication + * algorithm, as otherwise the MLME functionality of mac80211 + * would be broken. + */ .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4) | BIT(IEEE80211_STYPE_PROBE_REQ >> 4), }, [NL80211_IFTYPE_AP] = { @@ -872,7 +887,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) enum nl80211_band band; int channels, max_bitrates; bool supp_ht, supp_vht, supp_he; - netdev_features_t feature_whitelist; struct cfg80211_chan_def dflt_chandef = {}; if (ieee80211_hw_check(hw, QUEUE_CONTROL) && @@ -931,10 +945,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) } /* Only HW csum features are currently compatible with mac80211 */ - feature_whitelist = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_GSO_SOFTWARE | NETIF_F_RXCSUM; - if (WARN_ON(hw->netdev_features & ~feature_whitelist)) + if (WARN_ON(hw->netdev_features & ~MAC80211_SUPPORTED_FEATURES)) return -EINVAL; if (hw->max_report_rates == 0) @@ -981,6 +992,11 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!supp_he) supp_he = !!ieee80211_get_he_sta_cap(sband); + /* HT, VHT, HE require QoS, thus >= 4 queues */ + if (WARN_ON(local->hw.queues < IEEE80211_NUM_ACS && + (supp_ht || supp_vht || supp_he))) + return -EINVAL; + if (!sband->ht_cap.ht_supported) continue; @@ -1184,10 +1200,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->hw.weight_multiplier) local->hw.weight_multiplier = 1; - result = ieee80211_wep_init(local); - if (result < 0) - wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", - result); + ieee80211_wep_init(local); local->hw.conf.flags = IEEE80211_CONF_IDLE; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 88d7a692a965..8a2f2fa21916 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -164,7 +164,9 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, chandef->center_freq1 = channel->center_freq; if (!ht_oper || !sta_ht_cap.ht_supported) { - ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + ret = IEEE80211_STA_DISABLE_HT | + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; goto out; } @@ -185,7 +187,9 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, "Wrong control channel: center-freq: %d ht-cfreq: %d ht->primary_chan: %d band: %d - Disabling HT\n", channel->center_freq, ht_cfreq, ht_oper->primary_chan, channel->band); - ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT; + ret = IEEE80211_STA_DISABLE_HT | + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; goto out; } @@ -301,13 +305,18 @@ out: IEEE80211_CHAN_DISABLED)) { if (WARN_ON(chandef->width == NL80211_CHAN_WIDTH_20_NOHT)) { ret = IEEE80211_STA_DISABLE_HT | - IEEE80211_STA_DISABLE_VHT; + IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE; break; } ret |= ieee80211_chandef_downgrade(chandef); } + if (!he_oper || !cfg80211_chandef_usable(sdata->wdev.wiphy, chandef, + IEEE80211_CHAN_NO_HE)) + ret |= IEEE80211_STA_DISABLE_HE; + if (chandef->width != vht_chandef.width && !tracking) sdata_info(sdata, "capabilities/regulatory prevented using AP HT/VHT configuration, downgraded\n"); @@ -393,6 +402,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, if (flags != (ifmgd->flags & (IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_VHT | + IEEE80211_STA_DISABLE_HE | IEEE80211_STA_DISABLE_40MHZ | IEEE80211_STA_DISABLE_80P80MHZ | IEEE80211_STA_DISABLE_160MHZ)) || @@ -616,10 +626,21 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, { u8 *pos; const struct ieee80211_sta_he_cap *he_cap = NULL; + struct ieee80211_chanctx_conf *chanctx_conf; u8 he_cap_size; + bool reg_cap = false; + + rcu_read_lock(); + chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); + if (!WARN_ON_ONCE(!chanctx_conf)) + reg_cap = cfg80211_chandef_usable(sdata->wdev.wiphy, + &chanctx_conf->def, + IEEE80211_CHAN_NO_HE); + + rcu_read_unlock(); he_cap = ieee80211_get_he_sta_cap(sband); - if (!he_cap) + if (!he_cap || !reg_cap) return; /* @@ -650,6 +671,13 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_channel *chan; u32 rates = 0; + struct element *ext_capa = NULL; + + /* we know it's writable, cast away the const */ + if (assoc_data->ie_len) + ext_capa = (void *)cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, + assoc_data->ie, + assoc_data->ie_len); sdata_assert_lock(sdata); @@ -800,7 +828,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) *pos++ = ieee80211_chandef_max_power(&chanctx_conf->def); } - if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT) { + /* + * Per spec, we shouldn't include the list of channels if we advertise + * support for extended channel switching, but we've always done that; + * (for now?) apply this restriction only on the (new) 6 GHz band. + */ + if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT && + (sband->band != NL80211_BAND_6GHZ || + !ext_capa || ext_capa->datalen < 1 || + !(ext_capa->data[0] & WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING))) { /* TODO: get this in reg domain format */ pos = skb_put(skb, 2 * sband->n_channels + 2); *pos++ = WLAN_EID_SUPPORTED_CHANNELS; @@ -814,18 +850,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) /* Set MBSSID support for HE AP if needed */ if (ieee80211_hw_check(&local->hw, SUPPORTS_ONLY_HE_MULTI_BSSID) && - !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && assoc_data->ie_len) { - struct element *elem; - - /* we know it's writable, cast away the const */ - elem = (void *)cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, - assoc_data->ie, - assoc_data->ie_len); - - /* We can probably assume both always true */ - if (elem && elem->datalen >= 3) - elem->data[2] |= WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; - } + !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && assoc_data->ie_len && + ext_capa && ext_capa->datalen >= 3) + ext_capa->data[2] |= WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT; /* if present, add any custom IEs that go before HT */ if (assoc_data->ie_len) { @@ -2460,7 +2487,7 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, if (!ieee80211_is_data(hdr->frame_control)) return; - if (ieee80211_is_nullfunc(hdr->frame_control) && + if (ieee80211_is_any_nullfunc(hdr->frame_control) && sdata->u.mgd.probe_send_count > 0) { if (ack) ieee80211_sta_reset_conn_monitor(sdata); @@ -3364,9 +3391,16 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } if (bss_conf->he_support) { - bss_conf->bss_color = + bss_conf->he_bss_color.color = le32_get_bits(elems->he_operation->he_oper_params, IEEE80211_HE_OPERATION_BSS_COLOR_MASK); + bss_conf->he_bss_color.partial = + le32_get_bits(elems->he_operation->he_oper_params, + IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR); + bss_conf->he_bss_color.disabled = + le32_get_bits(elems->he_operation->he_oper_params, + IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED); + changed |= BSS_CHANGED_HE_BSS_COLOR; bss_conf->htc_trig_based_pkt_ext = le32_get_bits(elems->he_operation->he_oper_params, @@ -3645,13 +3679,28 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_if_managed *ifmgd; struct ieee80211_rx_status *rx_status = (void *) skb->cb; + struct ieee80211_channel *channel; size_t baselen, len = skb->len; ifmgd = &sdata->u.mgd; sdata_assert_lock(sdata); - if (!ether_addr_equal(mgmt->da, sdata->vif.addr)) + /* + * According to Draft P802.11ax D6.0 clause 26.17.2.3.2: + * "If a 6 GHz AP receives a Probe Request frame and responds with + * a Probe Response frame [..], the Address 1 field of the Probe + * Response frame shall be set to the broadcast address [..]" + * So, on 6GHz band we should also accept broadcast responses. + */ + channel = ieee80211_get_channel(sdata->local->hw.wiphy, + rx_status->freq); + if (!channel) + return; + + if (!ether_addr_equal(mgmt->da, sdata->vif.addr) && + (channel->band != NL80211_BAND_6GHZ || + !is_broadcast_ether_addr(mgmt->da))) return; /* ignore ProbeResp to foreign address */ baselen = (u8 *) mgmt->u.probe_resp.variable - (u8 *) mgmt; @@ -4749,10 +4798,22 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, IEEE80211_STA_DISABLE_80P80MHZ | IEEE80211_STA_DISABLE_160MHZ); + /* disable HT/VHT/HE if we don't support them */ + if (!sband->ht_cap.ht_supported) { + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + } + + if (!sband->vht_cap.vht_supported) + ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + + if (!ieee80211_get_he_sta_cap(sband)) + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + rcu_read_lock(); - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT) && - sband->ht_cap.ht_supported) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HT)) { const u8 *ht_oper_ie, *ht_cap_ie; ht_oper_ie = ieee80211_bss_get_ie(cbss, WLAN_EID_HT_OPERATION); @@ -4769,8 +4830,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT) && - sband->vht_cap.vht_supported) { + if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) { const u8 *vht_oper_ie, *vht_cap; vht_oper_ie = ieee80211_bss_get_ie(cbss, @@ -4780,9 +4840,10 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, if (vht_oper && !ht_oper) { vht_oper = NULL; sdata_info(sdata, - "AP advertised VHT without HT, disabling both\n"); + "AP advertised VHT without HT, disabling HT/VHT/HE\n"); ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } vht_cap = ieee80211_bss_get_ie(cbss, WLAN_EID_VHT_CAPABILITY); @@ -4792,9 +4853,6 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } } - if (!ieee80211_get_he_sta_cap(sband)) - ifmgd->flags |= IEEE80211_STA_DISABLE_HE; - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) { const struct cfg80211_bss_ies *ies; const u8 *he_oper_ie; @@ -5293,27 +5351,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, } } - /* Also disable HT if we don't support it or the AP doesn't use WMM */ sband = local->hw.wiphy->bands[req->bss->channel->band]; - if (!sband->ht_cap.ht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || - ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { - ifmgd->flags |= IEEE80211_STA_DISABLE_HT; - if (!bss->wmm_used && - !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) - netdev_info(sdata->dev, - "disabling HT as WMM/QoS is not supported by the AP\n"); - } - /* disable VHT if we don't support it or the AP doesn't use WMM */ - if (!sband->vht_cap.vht_supported || - local->hw.queues < IEEE80211_NUM_ACS || !bss->wmm_used || - ifmgd->flags & IEEE80211_STA_DISABLE_WMM) { + /* also disable HT/VHT/HE if the AP doesn't use WMM */ + if (!bss->wmm_used) { + ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; - if (!bss->wmm_used && - !(ifmgd->flags & IEEE80211_STA_DISABLE_WMM)) - netdev_info(sdata->dev, - "disabling VHT as WMM/QoS is not supported by the AP\n"); + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; + netdev_info(sdata->dev, + "disabling HT/VHT/HE as WMM/QoS is not supported by the AP\n"); } memcpy(&ifmgd->ht_capa, &req->ht_capa, sizeof(ifmgd->ht_capa)); @@ -5445,6 +5491,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (req->flags & ASSOC_REQ_DISABLE_HT) { ifmgd->flags |= IEEE80211_STA_DISABLE_HT; ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; + ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } if (req->flags & ASSOC_REQ_DISABLE_VHT) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0ba98ad9bc85..2ffb4ee467e1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/jiffies.h> @@ -983,7 +983,8 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da)) return -1; - if (!ieee80211_is_robust_mgmt_frame(skb)) + if (!ieee80211_is_robust_mgmt_frame(skb) && + !ieee80211_is_beacon(hdr->frame_control)) return -1; /* not a robust management frame */ mmie = (struct ieee80211_mmie *) @@ -1450,8 +1451,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || - ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control) || + ieee80211_is_any_nullfunc(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) return RX_CONTINUE; @@ -1838,8 +1838,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) * Drop (qos-)data::nullfunc frames silently, since they * are used only to control station power saving mode. */ - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { + if (ieee80211_is_any_nullfunc(hdr->frame_control)) { I802_DEBUG_INC(rx->local->rx_handlers_drop_nullfunc); /* @@ -1870,6 +1869,41 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) return RX_CONTINUE; } /* ieee80211_rx_h_sta_process */ +static struct ieee80211_key * +ieee80211_rx_get_bigtk(struct ieee80211_rx_data *rx, int idx) +{ + struct ieee80211_key *key = NULL; + struct ieee80211_sub_if_data *sdata = rx->sdata; + int idx2; + + /* Make sure key gets set if either BIGTK key index is set so that + * ieee80211_drop_unencrypted_mgmt() can properly drop both unprotected + * Beacon frames and Beacon frames that claim to use another BIGTK key + * index (i.e., a key that we do not have). + */ + + if (idx < 0) { + idx = NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS; + idx2 = idx + 1; + } else { + if (idx == NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS) + idx2 = idx + 1; + else + idx2 = idx - 1; + } + + if (rx->sta) + key = rcu_dereference(rx->sta->gtk[idx]); + if (!key) + key = rcu_dereference(sdata->keys[idx]); + if (!key && rx->sta) + key = rcu_dereference(rx->sta->gtk[idx2]); + if (!key) + key = rcu_dereference(sdata->keys[idx2]); + + return key; +} + static ieee80211_rx_result debug_noinline ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) { @@ -1887,17 +1921,18 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* * Key selection 101 * - * There are four types of keys: + * There are five types of keys: * - GTK (group keys) * - IGTK (group keys for management frames) + * - BIGTK (group keys for Beacon frames) * - PTK (pairwise keys) * - STK (station-to-station pairwise keys) * * When selecting a key, we have to distinguish between multicast * (including broadcast) and unicast frames, the latter can only - * use PTKs and STKs while the former always use GTKs and IGTKs. - * Unless, of course, actual WEP keys ("pre-RSNA") are used, then - * unicast frames can also use key indices like GTKs. Hence, if we + * use PTKs and STKs while the former always use GTKs, IGTKs, and + * BIGTKs. Unless, of course, actual WEP keys ("pre-RSNA") are used, + * then unicast frames can also use key indices like GTKs. Hence, if we * don't have a PTK/STK we check the key index for a WEP key. * * Note that in a regular BSS, multicast frames are sent by the @@ -1941,6 +1976,20 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) /* Skip decryption if the frame is not protected. */ if (!ieee80211_has_protected(fc)) return RX_CONTINUE; + } else if (mmie_keyidx >= 0 && ieee80211_is_beacon(fc)) { + /* Broadcast/multicast robust management frame / BIP */ + if ((status->flag & RX_FLAG_DECRYPTED) && + (status->flag & RX_FLAG_IV_STRIPPED)) + return RX_CONTINUE; + + if (mmie_keyidx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS || + mmie_keyidx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + return RX_DROP_MONITOR; /* unexpected BIP keyidx */ + + rx->key = ieee80211_rx_get_bigtk(rx, mmie_keyidx); + if (!rx->key) + return RX_CONTINUE; /* Beacon protection not in use */ } else if (mmie_keyidx >= 0) { /* Broadcast/multicast robust management frame / BIP */ if ((status->flag & RX_FLAG_DECRYPTED) && @@ -1970,11 +2019,12 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; int i; - if (ieee80211_is_mgmt(fc) && - is_multicast_ether_addr(hdr->addr1) && - (key = rcu_dereference(rx->sdata->default_mgmt_key))) - rx->key = key; - else { + if (ieee80211_is_beacon(fc)) { + key = ieee80211_rx_get_bigtk(rx, -1); + } else if (ieee80211_is_mgmt(fc) && + is_multicast_ether_addr(hdr->addr1)) { + key = rcu_dereference(rx->sdata->default_mgmt_key); + } else { if (rx->sta) { for (i = 0; i < NUM_DEFAULT_KEYS; i++) { key = rcu_dereference(rx->sta->gtk[i]); @@ -1989,9 +2039,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) break; } } - if (key) - rx->key = key; } + if (key) + rx->key = key; return RX_CONTINUE; } else { /* @@ -2319,7 +2369,7 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && - !ieee80211_is_nullfunc(fc) && + !ieee80211_is_any_nullfunc(fc) && ieee80211_is_data(fc) && rx->key)) return -EACCES; @@ -2360,6 +2410,9 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) rx->skb->len); return -EACCES; } + if (unlikely(ieee80211_is_beacon(fc) && rx->key && + ieee80211_get_mmie_keyidx(rx->skb) < 0)) + return -EACCES; /* * When using MFP, Action frames are not allowed prior to * having configured keys. @@ -3084,6 +3137,10 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) enum ieee80211_smps_mode smps_mode; struct sta_opmode_info sta_opmode = {}; + if (sdata->vif.type != NL80211_IFTYPE_AP && + sdata->vif.type != NL80211_IFTYPE_AP_VLAN) + goto handled; + /* convert to HT capability */ switch (mgmt->u.action.u.ht_smps.smps_control) { case WLAN_HT_SMPS_CONTROL_DISABLED: diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 4d31d9688dc2..fdac8192a519 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -201,8 +201,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local, mgmt->bssid, cbss->bssid); /* In case the signal is invalid update the status */ - signal_valid = abs(channel->center_freq - cbss->channel->center_freq) - <= local->hw.wiphy->max_adj_channel_rssi_comp; + signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 0f5f40678885..f357156b86ee 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/module.h> @@ -1351,20 +1351,6 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) atomic_dec(&ps->num_sta_ps); - /* This station just woke up and isn't aware of our SMPS state */ - if (!ieee80211_vif_is_mesh(&sdata->vif) && - !ieee80211_smps_is_restrictive(sta->known_smps_mode, - sdata->smps_mode) && - sta->known_smps_mode != sdata->bss->req_smps && - sta_info_tx_streams(sta) != 1) { - ht_dbg(sdata, - "%pM just woke up and MIMO capable - update SMPS\n", - sta->sta.addr); - ieee80211_send_smps_action(sdata, sdata->bss->req_smps, - sta->sta.addr, - sdata->vif.bss_conf.bssid); - } - local->total_ps_buffered -= buffered; sta_info_recalc_tim(sta); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c00e28585f9d..364a35414d05 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -533,7 +533,9 @@ struct sta_info { u8 addr[ETH_ALEN]; struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; - struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS]; + struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS]; struct ieee80211_key __rcu *ptk[NUM_DEFAULT_KEYS]; u8 ptk_idx; struct rate_control_ref *rate_ctrl; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index b720feaf9a74..22512805eafb 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -643,8 +643,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) + if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, @@ -888,6 +887,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, int rates_idx; bool send_to_cooked; bool acked; + bool noack_success; struct ieee80211_bar *bar; int shift = 0; int tid = IEEE80211_NUM_TIDS; @@ -906,6 +906,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, clear_sta_flag(sta, WLAN_STA_SP); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); + noack_success = !!(info->flags & + IEEE80211_TX_STAT_NOACK_TRANSMITTED); /* mesh Peer Service Period support */ if (ieee80211_vif_is_mesh(&sta->sdata->vif) && @@ -970,12 +972,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_handle_filtered_frame(local, sta, skb); return; } else { - if (!acked) + if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; if (ieee80211_is_data_present(fc)) { - if (!acked) + if (!acked && !noack_success) sta->status_stats.msdu_failed[tid]++; sta->status_stats.msdu_retries[tid] += @@ -1013,7 +1015,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, } if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { - if (info->flags & IEEE80211_TX_STAT_ACK) { + if (acked) { if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; @@ -1021,6 +1023,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) sta->status_stats.last_tdls_pkt_time = jiffies; + } else if (noack_success) { + /* nothing to do here, do not account as lost */ } else { ieee80211_lost_packet(sta, info); } @@ -1056,7 +1060,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, I802_DEBUG_INC(local->dot11FailedCount); } - if ((ieee80211_is_nullfunc(fc) || ieee80211_is_qos_nullfunc(fc)) && + if (ieee80211_is_any_nullfunc(fc) && ieee80211_has_pm(fc) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && @@ -1141,7 +1145,7 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, sta = container_of(pubsta, struct sta_info, sta); - if (!acked) + if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1156,6 +1160,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, sta->status_stats.last_tdls_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; + } else if (noack_success) { + /* nothing to do here, do not account as lost */ } else { ieee80211_lost_packet(sta, info); } @@ -1198,6 +1204,77 @@ void ieee80211_tx_rate_update(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_tx_rate_update); +void ieee80211_tx_status_8023(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct sk_buff *skb) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct sta_info *sta; + int retry_count; + int rates_idx; + bool acked; + + sdata = vif_to_sdata(vif); + + acked = info->flags & IEEE80211_TX_STAT_ACK; + rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count); + + rcu_read_lock(); + + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + goto counters_update; + + if (IS_ERR(sta)) + goto counters_update; + + if (!acked) + sta->status_stats.retry_failed++; + + if (rates_idx != -1) + sta->tx_stats.last_rate = info->status.rates[rates_idx]; + + sta->status_stats.retry_count += retry_count; + + if (ieee80211_hw_check(hw, REPORTS_TX_ACK_STATUS)) { + if (acked && vif->type == NL80211_IFTYPE_STATION) + ieee80211_sta_reset_conn_monitor(sdata); + + sta->status_stats.last_ack = jiffies; + if (info->flags & IEEE80211_TX_STAT_ACK) { + if (sta->status_stats.lost_packets) + sta->status_stats.lost_packets = 0; + + if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) + sta->status_stats.last_tdls_pkt_time = jiffies; + } else { + ieee80211_lost_packet(sta, info); + } + } + +counters_update: + rcu_read_unlock(); + ieee80211_led_tx(local); + + if (!(info->flags & IEEE80211_TX_STAT_ACK) && + !(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED)) + goto skip_stats_update; + + I802_DEBUG_INC(local->dot11TransmittedFrameCount); + if (is_multicast_ether_addr(skb->data)) + I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount); + if (retry_count > 0) + I802_DEBUG_INC(local->dot11RetryCount); + if (retry_count > 1) + I802_DEBUG_INC(local->dot11MultipleRetryCount); + +skip_stats_update: + ieee80211_report_used_skb(local, skb, false); + dev_kfree_skb(skb); +} +EXPORT_SYMBOL(ieee80211_tx_status_8023); + void ieee80211_report_low_ack(struct ieee80211_sta *pubsta, u32 num_packets) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 87def9cb91ff..83147385c200 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation * * Transmit and frame generation functions. */ @@ -297,7 +297,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) && !ieee80211_is_probe_req(hdr->frame_control) && - !ieee80211_is_nullfunc(hdr->frame_control)) + !ieee80211_is_any_nullfunc(hdr->frame_control)) /* * When software scanning only nullfunc frames (to notify * the sleep state to the AP) and probe requests (for the @@ -1250,7 +1250,8 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) return NULL; - if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) { + if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) && + unlikely(!ieee80211_is_data_present(hdr->frame_control))) { if ((!ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_bufferable_mmpdu(hdr->frame_control) || vif->type == NL80211_IFTYPE_STATION) && @@ -2360,9 +2361,9 @@ static inline bool ieee80211_is_tdls_setup(struct sk_buff *skb) skb->data[14] == WLAN_TDLS_SNAP_RFTYPE; } -static int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, - struct sta_info **sta_out) +int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, + struct sta_info **sta_out) { struct sta_info *sta; @@ -3616,6 +3617,9 @@ begin: else info->flags &= ~IEEE80211_TX_CTL_AMPDU; + if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) + goto encap_out; + if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, sta); @@ -3675,9 +3679,11 @@ begin: break; } +encap_out: IEEE80211_SKB_CB(skb)->control.vif = vif; - if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { + if (vif && + wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { u32 airtime; airtime = ieee80211_calc_expected_tx_airtime(hw, vif, txq->sta, @@ -4103,6 +4109,153 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } +static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, int led_len, + struct sta_info *sta, + bool txpending) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_tx_control control = {}; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_sta *pubsta = NULL; + unsigned long flags; + int q = info->hw_queue; + + if (ieee80211_queue_skb(local, sdata, sta, skb)) + return true; + + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + + if (local->queue_stop_reasons[q] || + (!txpending && !skb_queue_empty(&local->pending[q]))) { + if (txpending) + skb_queue_head(&local->pending[q], skb); + else + skb_queue_tail(&local->pending[q], skb); + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + return false; + } + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + if (sta && sta->uploaded) + pubsta = &sta->sta; + + control.sta = pubsta; + + drv_tx(local, &control, skb); + + return true; +} + +static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, + struct net_device *dev, struct sta_info *sta, + struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ethhdr *ehdr = (struct ethhdr *)skb->data; + struct ieee80211_local *local = sdata->local; + bool authorized = false; + bool multicast; + unsigned char *ra = ehdr->h_dest; + + if (IS_ERR(sta) || (sta && !sta->uploaded)) + sta = NULL; + + if (sdata->vif.type == NL80211_IFTYPE_STATION && + (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER))) + ra = sdata->u.mgd.bssid; + + if (!is_valid_ether_addr(ra)) + goto out_free; + + multicast = is_multicast_ether_addr(ra); + + if (sta) + authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED); + + if (!multicast && !authorized && + (ehdr->h_proto != sdata->control_port_protocol || + !ether_addr_equal(sdata->vif.addr, ehdr->h_source))) + goto out_free; + + if (multicast && sdata->vif.type == NL80211_IFTYPE_AP && + !atomic_read(&sdata->u.ap.num_mcast_sta)) + goto out_free; + + if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) && + test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) + goto out_free; + + if (unlikely(!multicast && skb->sk && + skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) + ieee80211_store_ack_skb(local, skb, &info->flags); + + memset(info, 0, sizeof(*info)); + + if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) { + if (sdata->control_port_no_encrypt) + info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + } + + if (multicast) + info->flags |= IEEE80211_TX_CTL_NO_ACK; + + info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; + + ieee80211_tx_stats(dev, skb->len); + + if (sta) { + sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len; + sta->tx_stats.packets[skb_get_queue_mapping(skb)]++; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + sdata = container_of(sdata->bss, + struct ieee80211_sub_if_data, u.ap); + + info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP; + info->control.vif = &sdata->vif; + + ieee80211_tx_8023(sdata, skb, skb->len, sta, false); + + return; + +out_free: + kfree_skb(skb); +} + +netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, + struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct sta_info *sta; + + if (WARN_ON(!sdata->hw_80211_encap)) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (unlikely(skb->len < ETH_HLEN)) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + rcu_read_lock(); + + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) + kfree_skb(skb); + else + ieee80211_8023_xmit(sdata, dev, sta, skb); + + rcu_read_unlock(); + + return NETDEV_TX_OK; +} + struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags) @@ -4181,6 +4334,16 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, } info->band = chanctx_conf->def.chan->band; result = ieee80211_tx(sdata, NULL, skb, true, 0); + } else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) { + if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) { + dev_kfree_skb(skb); + return true; + } + + if (IS_ERR(sta) || (sta && !sta->uploaded)) + sta = NULL; + + result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true); } else { struct sk_buff_head skbs; @@ -4501,6 +4664,28 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif) } EXPORT_SYMBOL(ieee80211_csa_is_complete); +static int ieee80211_beacon_protect(struct sk_buff *skb, + struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + ieee80211_tx_result res; + struct ieee80211_tx_data tx; + + memset(&tx, 0, sizeof(tx)); + tx.key = rcu_dereference(sdata->default_beacon_key); + if (!tx.key) + return 0; + tx.local = local; + tx.sdata = sdata; + __skb_queue_head_init(&tx.skbs); + __skb_queue_tail(&tx.skbs, skb); + res = ieee80211_tx_h_encrypt(&tx); + if (WARN_ON_ONCE(res != TX_CONTINUE)) + return -1; + + return 0; +} + static struct sk_buff * __ieee80211_beacon_get(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -4568,6 +4753,9 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw, if (beacon->tail) skb_put_data(skb, beacon->tail, beacon->tail_len); + + if (ieee80211_beacon_protect(skb, local, sdata) < 0) + goto out; } else goto out; } else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index decd46b38393..ea7d277a8c45 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2019 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation * * utilities for mac80211 */ @@ -39,7 +39,6 @@ const void *const mac80211_wiphy_privid = &mac80211_wiphy_privid; struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy) { struct ieee80211_local *local; - BUG_ON(!wiphy); local = wiphy_priv(wiphy); return &local->hw; @@ -891,6 +890,51 @@ void ieee80211_queue_delayed_work(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_queue_delayed_work); +static void ieee80211_parse_extension_element(u32 *crc, + const struct element *elem, + struct ieee802_11_elems *elems) +{ + const void *data = elem->data + 1; + u8 len = elem->datalen - 1; + + switch (elem->data[0]) { + case WLAN_EID_EXT_HE_MU_EDCA: + if (len == sizeof(*elems->mu_edca_param_set)) { + elems->mu_edca_param_set = data; + if (crc) + *crc = crc32_be(*crc, (void *)elem, + elem->datalen + 2); + } + break; + case WLAN_EID_EXT_HE_CAPABILITY: + elems->he_cap = data; + elems->he_cap_len = len; + break; + case WLAN_EID_EXT_HE_OPERATION: + if (len >= sizeof(*elems->he_operation) && + len == ieee80211_he_oper_size(data) - 1) + elems->he_operation = data; + break; + case WLAN_EID_EXT_UORA: + if (len == 1) + elems->uora_element = data; + break; + case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: + if (len == 3) + elems->max_channel_switch_time = data; + break; + case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: + if (len == sizeof(*elems->mbssid_config_ie)) + elems->mbssid_config_ie = data; + break; + case WLAN_EID_EXT_HE_SPR: + if (len >= sizeof(*elems->he_spr) && + len >= ieee80211_he_spr_size(data)) + elems->he_spr = data; + break; + } +} + static u32 _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, struct ieee802_11_elems *elems, @@ -950,6 +994,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, case WLAN_EID_CHAN_SWITCH_TIMING: case WLAN_EID_LINK_ID: case WLAN_EID_BSS_MAX_IDLE_PERIOD: + case WLAN_EID_RSNX: /* * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible * that if the content gets bigger it might be needed more than once @@ -1226,34 +1271,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, if (elen >= sizeof(*elems->max_idle_period_ie)) elems->max_idle_period_ie = (void *)pos; break; + case WLAN_EID_RSNX: + elems->rsnx = pos; + elems->rsnx_len = elen; + break; case WLAN_EID_EXTENSION: - if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && - elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { - elems->mu_edca_param_set = (void *)&pos[1]; - if (calc_crc) - crc = crc32_be(crc, pos - 2, elen + 2); - } else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) { - elems->he_cap = (void *)&pos[1]; - elems->he_cap_len = elen - 1; - } else if (pos[0] == WLAN_EID_EXT_HE_OPERATION && - elen >= sizeof(*elems->he_operation) && - elen >= ieee80211_he_oper_size(&pos[1])) { - elems->he_operation = (void *)&pos[1]; - } else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) { - elems->uora_element = (void *)&pos[1]; - } else if (pos[0] == - WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME && - elen == 4) { - elems->max_channel_switch_time = pos + 1; - } else if (pos[0] == - WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION && - elen == 3) { - elems->mbssid_config_ie = (void *)&pos[1]; - } else if (pos[0] == WLAN_EID_EXT_HE_SPR && - elen >= sizeof(*elems->he_spr) && - elen >= ieee80211_he_spr_size(&pos[1])) { - elems->he_spr = (void *)&pos[1]; - } + ieee80211_parse_extension_element(calc_crc ? + &crc : NULL, + elem, elems); break; default: break; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index ccdcb9ad9ac7..632f07401850 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -333,11 +333,33 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, } } +/* FIXME: move this to some better location - parses HE now */ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cap_rx_bw(struct sta_info *sta) { struct ieee80211_sta_vht_cap *vht_cap = &sta->sta.vht_cap; + struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; u32 cap_width; + if (he_cap->has_he) { + u8 info = he_cap->he_cap_elem.phy_cap_info[0]; + + if (sta->sdata->vif.bss_conf.chandef.chan->band == + NL80211_BAND_2GHZ) { + if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return IEEE80211_STA_RX_BW_40; + else + return IEEE80211_STA_RX_BW_20; + } + + if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G || + info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + return IEEE80211_STA_RX_BW_160; + else if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + return IEEE80211_STA_RX_BW_80; + + return IEEE80211_STA_RX_BW_20; + } + if (!vht_cap->vht_supported) return sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 ? IEEE80211_STA_RX_BW_40 : @@ -433,6 +455,7 @@ ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) } } +/* FIXME: rename/move - this deals with everything not just VHT */ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; @@ -458,12 +481,40 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta) void ieee80211_sta_set_rx_nss(struct sta_info *sta) { - u8 ht_rx_nss = 0, vht_rx_nss = 0; + u8 ht_rx_nss = 0, vht_rx_nss = 0, he_rx_nss = 0, rx_nss; /* if we received a notification already don't overwrite it */ if (sta->sta.rx_nss) return; + if (sta->sta.he_cap.has_he) { + int i; + u8 rx_mcs_80 = 0, rx_mcs_160 = 0; + const struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; + u16 mcs_160_map = + le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + u16 mcs_80_map = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + + for (i = 7; i >= 0; i--) { + u8 mcs_160 = (mcs_160_map >> (2 * i)) & 3; + + if (mcs_160 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + rx_mcs_160 = i + 1; + break; + } + } + for (i = 7; i >= 0; i--) { + u8 mcs_80 = (mcs_80_map >> (2 * i)) & 3; + + if (mcs_80 != IEEE80211_VHT_MCS_NOT_SUPPORTED) { + rx_mcs_80 = i + 1; + break; + } + } + + he_rx_nss = min(rx_mcs_80, rx_mcs_160); + } + if (sta->sta.ht_cap.ht_supported) { if (sta->sta.ht_cap.mcs.rx_mask[0]) ht_rx_nss++; @@ -493,8 +544,9 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta) /* FIXME: consider rx_highest? */ } - ht_rx_nss = max(ht_rx_nss, vht_rx_nss); - sta->sta.rx_nss = max_t(u8, 1, ht_rx_nss); + rx_nss = max(vht_rx_nss, ht_rx_nss); + rx_nss = max(he_rx_nss, rx_nss); + sta->sta.rx_nss = max_t(u8, 1, rx_nss); } u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index b75c2c54e665..9a6e11d7b4db 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -22,12 +22,10 @@ #include "wep.h" -int ieee80211_wep_init(struct ieee80211_local *local) +void ieee80211_wep_init(struct ieee80211_local *local) { /* start WEP IV from a random value */ get_random_bytes(&local->wep_iv, IEEE80211_WEP_IV_LEN); - - return 0; } static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen) diff --git a/net/mac80211/wep.h b/net/mac80211/wep.h index 997a034233c2..4ffe83554c67 100644 --- a/net/mac80211/wep.h +++ b/net/mac80211/wep.h @@ -13,7 +13,7 @@ #include "ieee80211_i.h" #include "key.h" -int ieee80211_wep_init(struct ieee80211_local *local); +void ieee80211_wep_init(struct ieee80211_local *local); int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len); int ieee80211_wep_encrypt(struct ieee80211_local *local, diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3c19a8efdcea..a8445407d25a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -31,6 +31,12 @@ struct mptcp6_sock { }; #endif +struct mptcp_skb_cb { + u32 offset; +}; + +#define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) + /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not * completed yet or has failed, return the subflow socket. * Otherwise return NULL. @@ -111,6 +117,141 @@ static struct sock *mptcp_subflow_get(const struct mptcp_sock *msk) return NULL; } +static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, + struct sk_buff *skb, + unsigned int offset, size_t copy_len) +{ + struct sock *sk = (struct sock *)msk; + + __skb_unlink(skb, &ssk->sk_receive_queue); + skb_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); + + msk->ack_seq += copy_len; + MPTCP_SKB_CB(skb)->offset = offset; +} + +static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, + struct sock *ssk, + unsigned int *bytes) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + bool more_data_avail; + struct tcp_sock *tp; + bool done = false; + int rcvbuf; + + rcvbuf = max(ssk->sk_rcvbuf, sk->sk_rcvbuf); + if (rcvbuf > sk->sk_rcvbuf) + sk->sk_rcvbuf = rcvbuf; + + tp = tcp_sk(ssk); + do { + u32 map_remaining, offset; + u32 seq = tp->copied_seq; + struct sk_buff *skb; + bool fin; + + /* try to move as much data as available */ + map_remaining = subflow->map_data_len - + mptcp_subflow_get_map_offset(subflow); + + skb = skb_peek(&ssk->sk_receive_queue); + if (!skb) + break; + + offset = seq - TCP_SKB_CB(skb)->seq; + fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; + if (fin) { + done = true; + seq++; + } + + if (offset < skb->len) { + size_t len = skb->len - offset; + + if (tp->urg_data) + done = true; + + __mptcp_move_skb(msk, ssk, skb, offset, len); + seq += len; + moved += len; + + if (WARN_ON_ONCE(map_remaining < len)) + break; + } else { + WARN_ON_ONCE(!fin); + sk_eat_skb(ssk, skb); + done = true; + } + + WRITE_ONCE(tp->copied_seq, seq); + more_data_avail = mptcp_subflow_data_available(ssk); + + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) { + done = true; + break; + } + } while (more_data_avail); + + *bytes = moved; + + return done; +} + +/* In most cases we will be able to lock the mptcp socket. If its already + * owned, we need to defer to the work queue to avoid ABBA deadlock. + */ +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +{ + struct sock *sk = (struct sock *)msk; + unsigned int moved = 0; + + if (READ_ONCE(sk->sk_lock.owned)) + return false; + + if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock))) + return false; + + /* must re-check after taking the lock */ + if (!READ_ONCE(sk->sk_lock.owned)) + __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + + spin_unlock_bh(&sk->sk_lock.slock); + + return moved > 0; +} + +void mptcp_data_ready(struct sock *sk, struct sock *ssk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + set_bit(MPTCP_DATA_READY, &msk->flags); + + if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && + move_skbs_to_msk(msk, ssk)) + goto wake; + + /* don't schedule if mptcp sk is (still) over limit */ + if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) + goto wake; + + /* mptcp socket is owned, release_cb should retry */ + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, + &sk->sk_tsq_flags)) { + sock_hold(sk); + + /* need to try again, its possible release_cb() has already + * been called after the test_and_set_bit() above. + */ + move_skbs_to_msk(msk, ssk); + } +wake: + sk->sk_data_ready(sk); +} + static bool mptcp_ext_cache_refill(struct mptcp_sock *msk) { if (!msk->cached_ext) @@ -323,61 +464,83 @@ fallback: return ret; } -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len) +static void mptcp_wait_data(struct sock *sk, long *timeo) { - struct mptcp_read_arg *arg = desc->arg.data; - size_t copy_len; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + struct mptcp_sock *msk = mptcp_sk(sk); + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - copy_len = min(desc->count, len); + sk_wait_event(sk, timeo, + test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); - if (likely(arg->msg)) { + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); +} + +static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, + struct msghdr *msg, + size_t len) +{ + struct sock *sk = (struct sock *)msk; + struct sk_buff *skb; + int copied = 0; + + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { + u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 data_len = skb->len - offset; + u32 count = min_t(size_t, len - copied, data_len); int err; - err = skb_copy_datagram_msg(skb, offset, arg->msg, copy_len); - if (err) { - pr_debug("error path"); - desc->error = err; - return err; + err = skb_copy_datagram_msg(skb, offset, msg, count); + if (unlikely(err < 0)) { + if (!copied) + return err; + break; + } + + copied += count; + + if (count < data_len) { + MPTCP_SKB_CB(skb)->offset += count; + break; } - } else { - pr_debug("Flushing skb payload"); - } - desc->count -= copy_len; + __skb_unlink(skb, &sk->sk_receive_queue); + __kfree_skb(skb); - pr_debug("consumed %zu bytes, %zu left", copy_len, desc->count); - return copy_len; + if (copied >= len) + break; + } + + return copied; } -static void mptcp_wait_data(struct sock *sk, long *timeo) +static bool __mptcp_move_skbs(struct mptcp_sock *msk) { - DEFINE_WAIT_FUNC(wait, woken_wake_function); - struct mptcp_sock *msk = mptcp_sk(sk); + unsigned int moved = 0; + bool done; - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + do { + struct sock *ssk = mptcp_subflow_recv_lookup(msk); - sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + if (!ssk) + break; - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); + lock_sock(ssk); + done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + release_sock(ssk); + } while (!done); + + return moved > 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - struct mptcp_subflow_context *subflow; - bool more_data_avail = false; - struct mptcp_read_arg arg; - read_descriptor_t desc; - bool wait_data = false; struct socket *ssock; - struct tcp_sock *tp; - bool done = false; - struct sock *ssk; int copied = 0; int target; long timeo; @@ -395,65 +558,26 @@ fallback: return copied; } - arg.msg = msg; - desc.arg.data = &arg; - desc.error = 0; - timeo = sock_rcvtimeo(sk, nonblock); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - while (!done) { - u32 map_remaining; + while (len > (size_t)copied) { int bytes_read; - ssk = mptcp_subflow_recv_lookup(msk); - pr_debug("msk=%p ssk=%p", msk, ssk); - if (!ssk) - goto wait_for_data; - - subflow = mptcp_subflow_ctx(ssk); - tp = tcp_sk(ssk); - - lock_sock(ssk); - do { - /* try to read as much data as available */ - map_remaining = subflow->map_data_len - - mptcp_subflow_get_map_offset(subflow); - desc.count = min_t(size_t, len - copied, map_remaining); - pr_debug("reading %zu bytes, copied %d", desc.count, - copied); - bytes_read = tcp_read_sock(ssk, &desc, - mptcp_read_actor); - if (bytes_read < 0) { - if (!copied) - copied = bytes_read; - done = true; - goto next; - } + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied); + if (unlikely(bytes_read < 0)) { + if (!copied) + copied = bytes_read; + goto out_err; + } - pr_debug("msk ack_seq=%llx -> %llx", msk->ack_seq, - msk->ack_seq + bytes_read); - msk->ack_seq += bytes_read; - copied += bytes_read; - if (copied >= len) { - done = true; - goto next; - } - if (tp->urg_data && tp->urg_seq == tp->copied_seq) { - pr_err("Urgent data present, cannot proceed"); - done = true; - goto next; - } -next: - more_data_avail = mptcp_subflow_data_available(ssk); - } while (more_data_avail && !done); - release_sock(ssk); - continue; + copied += bytes_read; -wait_for_data: - more_data_avail = false; + if (skb_queue_empty(&sk->sk_receive_queue) && + __mptcp_move_skbs(msk)) + continue; /* only the master socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() @@ -494,26 +618,25 @@ wait_for_data: } pr_debug("block timeout %ld", timeo); - wait_data = true; mptcp_wait_data(sk, &timeo); if (unlikely(__mptcp_tcp_fallback(msk))) goto fallback; } - if (more_data_avail) { - if (!test_bit(MPTCP_DATA_READY, &msk->flags)) - set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (!wait_data) { + if (skb_queue_empty(&sk->sk_receive_queue)) { + /* entire backlog drained, clear DATA_READY. */ clear_bit(MPTCP_DATA_READY, &msk->flags); - /* .. race-breaker: ssk might get new data after last - * data_available() returns false. + /* .. race-breaker: ssk might have gotten new data + * after last __mptcp_move_skbs() returned false. */ - ssk = mptcp_subflow_recv_lookup(msk); - if (unlikely(ssk)) + if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); + } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { + /* data to read but mptcp_wait_data() cleared DATA_READY */ + set_bit(MPTCP_DATA_READY, &msk->flags); } - +out_err: release_sock(sk); return copied; } @@ -548,12 +671,24 @@ static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) return 0; } +static void mptcp_worker(struct work_struct *work) +{ + struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); + struct sock *sk = &msk->sk.icsk_inet.sk; + + lock_sock(sk); + __mptcp_move_skbs(msk); + release_sock(sk); + sock_put(sk); +} + static int __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); __set_bit(MPTCP_SEND_SPACE, &msk->flags); + INIT_WORK(&msk->work, mptcp_worker); msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -569,6 +704,14 @@ static int mptcp_init_sock(struct sock *sk) return __mptcp_init_sock(sk); } +static void mptcp_cancel_work(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + if (cancel_work_sync(&msk->work)) + sock_put(sk); +} + static void mptcp_subflow_shutdown(struct sock *ssk, int how) { lock_sock(ssk); @@ -614,6 +757,10 @@ static void mptcp_close(struct sock *sk, long timeout) __mptcp_close_ssk(sk, ssk, subflow, timeout); } + mptcp_cancel_work(sk); + + __skb_queue_purge(&sk->sk_receive_queue); + sk_common_release(sk); } @@ -807,6 +954,32 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; } +#define MPTCP_DEFERRED_ALL TCPF_DELACK_TIMER_DEFERRED + +/* this is very alike tcp_release_cb() but we must handle differently a + * different set of events + */ +static void mptcp_release_cb(struct sock *sk) +{ + unsigned long flags, nflags; + + do { + flags = sk->sk_tsq_flags; + if (!(flags & MPTCP_DEFERRED_ALL)) + return; + nflags = flags & ~MPTCP_DEFERRED_ALL; + } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); + + if (flags & TCPF_DELACK_TIMER_DEFERRED) { + struct mptcp_sock *msk = mptcp_sk(sk); + struct sock *ssk; + + ssk = mptcp_subflow_recv_lookup(msk); + if (!ssk || !schedule_work(&msk->work)) + __sock_put(sk); + } +} + static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -882,6 +1055,7 @@ static struct proto mptcp_prot = { .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .recvmsg = mptcp_recvmsg, + .release_cb = mptcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = mptcp_get_port, @@ -1180,6 +1354,8 @@ void mptcp_proto_init(void) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); + + BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 9f8663b30456..6c0b2c8ab674 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -70,6 +70,7 @@ struct mptcp_sock { u32 token; unsigned long flags; bool can_ack; + struct work_struct work; struct list_head conn_list; struct skb_ext *cached_ext; /* for the next sendmsg */ struct socket *subflow; /* outgoing connect/listener/!mp_capable */ @@ -190,17 +191,11 @@ void mptcp_proto_init(void); int mptcp_proto_v6_init(void); #endif -struct mptcp_read_arg { - struct msghdr *msg; -}; - -int mptcp_read_actor(read_descriptor_t *desc, struct sk_buff *skb, - unsigned int offset, size_t len); - void mptcp_get_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx); void mptcp_finish_connect(struct sock *sk); +void mptcp_data_ready(struct sock *sk, struct sock *ssk); int mptcp_token_new_request(struct request_sock *req); void mptcp_token_destroy_request(u32 token); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 65122edf60aa..0de2a44bdaa0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,6 +408,18 @@ validate_seq: return MAPPING_OK; } +static int subflow_read_actor(read_descriptor_t *desc, + struct sk_buff *skb, + unsigned int offset, size_t len) +{ + size_t copy_len = min(desc->count, len); + + desc->count -= copy_len; + + pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count); + return copy_len; +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -482,16 +494,12 @@ static bool subflow_check_data_avail(struct sock *ssk) pr_debug("discarding %zu bytes, current map len=%d", delta, map_remaining); if (delta) { - struct mptcp_read_arg arg = { - .msg = NULL, - }; read_descriptor_t desc = { .count = delta, - .arg.data = &arg, }; int ret; - ret = tcp_read_sock(ssk, &desc, mptcp_read_actor); + ret = tcp_read_sock(ssk, &desc, subflow_read_actor); if (ret < 0) { ssk->sk_err = -ret; goto fatal; @@ -554,11 +562,8 @@ static void subflow_data_ready(struct sock *sk) return; } - if (mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); } static void subflow_write_space(struct sock *sk) @@ -690,11 +695,8 @@ static void subflow_state_change(struct sock *sk) * a fin packet carrying a DSS can be unnoticed if we don't trigger * the data available machinery here. */ - if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) { - set_bit(MPTCP_DATA_READY, &mptcp_sk(parent)->flags); - - parent->sk_data_ready(parent); - } + if (parent && subflow->mp_capable && mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); if (parent && !(parent->sk_shutdown & RCV_SHUTDOWN) && !subflow->rx_eof && subflow_is_done(sk)) { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index edf3e285e242..813bfab13296 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -71,7 +71,7 @@ struct listeners { struct rcu_head rcu; - unsigned long masks[0]; + unsigned long masks[]; }; /* state bits */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 58d5373c513c..7b1a74f74aad 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1230,6 +1230,7 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #ifdef CONFIG_PROC_FS static void *nr_info_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_list_lock) { spin_lock_bh(&nr_list_lock); return seq_hlist_start_head(&nr_list, *pos); @@ -1241,6 +1242,7 @@ static void *nr_info_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_info_stop(struct seq_file *seq, void *v) + __releases(&nr_list_lock) { spin_unlock_bh(&nr_list_lock); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d41335bad1f8..79f12d8c7b86 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -838,6 +838,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) #ifdef CONFIG_PROC_FS static void *nr_node_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_node_list_lock) { spin_lock_bh(&nr_node_list_lock); return seq_hlist_start_head(&nr_node_list, *pos); @@ -849,6 +850,7 @@ static void *nr_node_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_node_stop(struct seq_file *seq, void *v) + __releases(&nr_node_list_lock) { spin_unlock_bh(&nr_node_list_lock); } @@ -893,6 +895,7 @@ const struct seq_operations nr_node_seqops = { }; static void *nr_neigh_start(struct seq_file *seq, loff_t *pos) + __acquires(&nr_neigh_list_lock) { spin_lock_bh(&nr_neigh_list_lock); return seq_hlist_start_head(&nr_neigh_list, *pos); @@ -904,6 +907,7 @@ static void *nr_neigh_next(struct seq_file *seq, void *v, loff_t *pos) } static void nr_neigh_stop(struct seq_file *seq, void *v) + __releases(&nr_neigh_list_lock) { spin_unlock_bh(&nr_neigh_list_lock); } diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c index 65aaa9d7c813..304b1a9bb18a 100644 --- a/net/nfc/digital_dep.c +++ b/net/nfc/digital_dep.c @@ -71,7 +71,7 @@ struct digital_atr_req { u8 bs; u8 br; u8 pp; - u8 gb[0]; + u8 gb[]; } __packed; struct digital_atr_res { @@ -83,7 +83,7 @@ struct digital_atr_res { u8 br; u8 to; u8 pp; - u8 gb[0]; + u8 gb[]; } __packed; struct digital_psl_req { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7fbfe2adfffa..fc0efd8833c8 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -964,6 +964,25 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, return ovs_dp_upcall(dp, skb, key, &upcall, cutlen); } +static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, + const struct nlattr *attr, bool last) +{ + /* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */ + struct nlattr *dec_ttl_arg = nla_data(attr); + int rem = nla_len(attr); + + if (nla_len(dec_ttl_arg)) { + struct nlattr *actions = nla_next(dec_ttl_arg, &rem); + + if (actions) + return clone_execute(dp, skb, key, 0, actions, rem, + last, false); + } + consume_skb(skb); + return 0; +} + /* When 'last' is true, sample() should always consume the 'skb'. * Otherwise, sample() should keep 'skb' intact regardless what * actions are executed within sample(). @@ -1180,6 +1199,45 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, nla_len(actions), last, clone_flow_key); } +static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) +{ + int err; + + if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *nh; + + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(*nh)); + if (unlikely(err)) + return err; + + nh = ipv6_hdr(skb); + + if (nh->hop_limit <= 1) + return -EHOSTUNREACH; + + key->ip.ttl = --nh->hop_limit; + } else { + struct iphdr *nh; + u8 old_ttl; + + err = skb_ensure_writable(skb, skb_network_offset(skb) + + sizeof(*nh)); + if (unlikely(err)) + return err; + + nh = ip_hdr(skb); + if (nh->ttl <= 1) + return -EHOSTUNREACH; + + old_ttl = nh->ttl--; + csum_replace2(&nh->check, htons(old_ttl << 8), + htons(nh->ttl << 8)); + key->ip.ttl = nh->ttl; + } + return 0; +} + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1365,6 +1423,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, break; } + + case OVS_ACTION_ATTR_DEC_TTL: + err = execute_dec_ttl(skb, key); + if (err == -EHOSTUNREACH) { + err = dec_ttl_exception_handler(dp, skb, key, + a, true); + return err; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 288122eec7c8..79252d4887ff 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -80,6 +80,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_METER: case OVS_ACTION_ATTR_CHECK_PKT_LEN: case OVS_ACTION_ATTR_ADD_MPLS: + case OVS_ACTION_ATTR_DEC_TTL: default: return true; } @@ -2495,6 +2496,39 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return 0; } +static int validate_and_copy_dec_ttl(struct net *net, + const struct nlattr *attr, + const struct sw_flow_key *key, + struct sw_flow_actions **sfa, + __be16 eth_type, __be16 vlan_tci, + u32 mpls_label_count, bool log) +{ + int start, err; + u32 nested = true; + + if (!nla_len(attr)) + return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL, + NULL, 0, log); + + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); + if (start < 0) + return start; + + err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested, + sizeof(nested), log); + + if (err) + return err; + + err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, + vlan_tci, mpls_label_count, log); + if (err) + return err; + + add_nested_action_end(*sfa, start); + return 0; +} + static int validate_and_copy_clone(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, @@ -3009,6 +3043,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_CLONE] = (u32)-1, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), + [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3269,6 +3304,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, break; } + case OVS_ACTION_ATTR_DEC_TTL: + err = validate_and_copy_dec_ttl(net, a, key, sfa, + eth_type, vlan_tci, + mpls_label_count, log); + if (err) + return err; + skip_copy = true; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; @@ -3440,6 +3484,26 @@ out: return err; } +static int dec_ttl_action_to_attr(const struct nlattr *attr, + struct sk_buff *skb) +{ + int err = 0, rem = nla_len(attr); + struct nlattr *start; + + start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); + + if (!start) + return -EMSGSIZE; + + err = ovs_nla_put_actions(nla_data(attr), rem, skb); + if (err) + nla_nest_cancel(skb, start); + else + nla_nest_end(skb, start); + + return err; +} + static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) { const struct nlattr *ovs_key = nla_data(a); @@ -3540,6 +3604,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb) return err; break; + case OVS_ACTION_ATTR_DEC_TTL: + err = dec_ttl_action_to_attr(a, skb); + if (err) + return err; + break; + default: if (nla_put(skb, type, nla_len(a), nla_data(a))) return -EMSGSIZE; diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index 1c6d6c120fb7..32d4e923925d 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_QRTR) := qrtr.o +obj-$(CONFIG_QRTR) := qrtr.o ns.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c new file mode 100644 index 000000000000..413228c4520e --- /dev/null +++ b/net/qrtr/ns.c @@ -0,0 +1,751 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (c) 2015, Sony Mobile Communications Inc. + * Copyright (c) 2013, The Linux Foundation. All rights reserved. + * Copyright (c) 2020, Linaro Ltd. + */ + +#include <linux/module.h> +#include <linux/qrtr.h> +#include <linux/workqueue.h> +#include <net/sock.h> + +#include "qrtr.h" + +static RADIX_TREE(nodes, GFP_KERNEL); + +static struct { + struct socket *sock; + struct sockaddr_qrtr bcast_sq; + struct list_head lookups; + struct workqueue_struct *workqueue; + struct work_struct work; + int local_node; +} qrtr_ns; + +static const char * const qrtr_ctrl_pkt_strings[] = { + [QRTR_TYPE_HELLO] = "hello", + [QRTR_TYPE_BYE] = "bye", + [QRTR_TYPE_NEW_SERVER] = "new-server", + [QRTR_TYPE_DEL_SERVER] = "del-server", + [QRTR_TYPE_DEL_CLIENT] = "del-client", + [QRTR_TYPE_RESUME_TX] = "resume-tx", + [QRTR_TYPE_EXIT] = "exit", + [QRTR_TYPE_PING] = "ping", + [QRTR_TYPE_NEW_LOOKUP] = "new-lookup", + [QRTR_TYPE_DEL_LOOKUP] = "del-lookup", +}; + +struct qrtr_server_filter { + unsigned int service; + unsigned int instance; + unsigned int ifilter; +}; + +struct qrtr_lookup { + unsigned int service; + unsigned int instance; + + struct sockaddr_qrtr sq; + struct list_head li; +}; + +struct qrtr_server { + unsigned int service; + unsigned int instance; + + unsigned int node; + unsigned int port; + + struct list_head qli; +}; + +struct qrtr_node { + unsigned int id; + struct radix_tree_root servers; +}; + +static struct qrtr_node *node_get(unsigned int node_id) +{ + struct qrtr_node *node; + + node = radix_tree_lookup(&nodes, node_id); + if (node) + return node; + + /* If node didn't exist, allocate and insert it to the tree */ + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) + return NULL; + + node->id = node_id; + + radix_tree_insert(&nodes, node_id, node); + + return node; +} + +static int server_match(const struct qrtr_server *srv, + const struct qrtr_server_filter *f) +{ + unsigned int ifilter = f->ifilter; + + if (f->service != 0 && srv->service != f->service) + return 0; + if (!ifilter && f->instance) + ifilter = ~0; + + return (srv->instance & ifilter) == f->instance; +} + +static int service_announce_new(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + + trace_printk("advertising new server [%d:%x]@[%d:%d]\n", + srv->service, srv->instance, srv->node, srv->port); + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_NEW_SERVER); + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + + msg.msg_name = (struct sockaddr *)dest; + msg.msg_namelen = sizeof(*dest); + + return kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); +} + +static int service_announce_del(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + trace_printk("advertising removal of server [%d:%x]@[%d:%d]\n", + srv->service, srv->instance, srv->node, srv->port); + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_DEL_SERVER); + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + + msg.msg_name = (struct sockaddr *)dest; + msg.msg_namelen = sizeof(*dest); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to announce del service\n"); + + return ret; +} + +static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, + bool new) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = new ? cpu_to_le32(QRTR_TYPE_NEW_SERVER) : + cpu_to_le32(QRTR_TYPE_DEL_SERVER); + if (srv) { + pkt.server.service = cpu_to_le32(srv->service); + pkt.server.instance = cpu_to_le32(srv->instance); + pkt.server.node = cpu_to_le32(srv->node); + pkt.server.port = cpu_to_le32(srv->port); + } + + msg.msg_name = (struct sockaddr *)to; + msg.msg_namelen = sizeof(*to); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to send lookup notification\n"); +} + +static int announce_servers(struct sockaddr_qrtr *sq) +{ + struct radix_tree_iter iter; + struct qrtr_server *srv; + struct qrtr_node *node; + void __rcu **slot; + int ret; + + node = node_get(qrtr_ns.local_node); + if (!node) + return 0; + + /* Announce the list of servers registered in this node */ + radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + ret = service_announce_new(sq, srv); + if (ret < 0) { + pr_err("failed to announce new service\n"); + return ret; + } + } + + return 0; +} + +static struct qrtr_server *server_add(unsigned int service, + unsigned int instance, + unsigned int node_id, + unsigned int port) +{ + struct qrtr_server *srv; + struct qrtr_server *old; + struct qrtr_node *node; + + if (!service || !port) + return NULL; + + srv = kzalloc(sizeof(*srv), GFP_KERNEL); + if (!srv) + return NULL; + + srv->service = service; + srv->instance = instance; + srv->node = node_id; + srv->port = port; + + node = node_get(node_id); + if (!node) + goto err; + + /* Delete the old server on the same port */ + old = radix_tree_lookup(&node->servers, port); + if (old) { + radix_tree_delete(&node->servers, port); + kfree(old); + } + + radix_tree_insert(&node->servers, port, srv); + + trace_printk("add server [%d:%x]@[%d:%d]\n", srv->service, + srv->instance, srv->node, srv->port); + + return srv; + +err: + kfree(srv); + return NULL; +} + +static int server_del(struct qrtr_node *node, unsigned int port) +{ + struct qrtr_lookup *lookup; + struct qrtr_server *srv; + struct list_head *li; + + srv = radix_tree_lookup(&node->servers, port); + if (!srv) + return -ENOENT; + + radix_tree_delete(&node->servers, port); + + /* Broadcast the removal of local servers */ + if (srv->node == qrtr_ns.local_node) + service_announce_del(&qrtr_ns.bcast_sq, srv); + + /* Announce the service's disappearance to observers */ + list_for_each(li, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->service && lookup->service != srv->service) + continue; + if (lookup->instance && lookup->instance != srv->instance) + continue; + + lookup_notify(&lookup->sq, srv, false); + } + + kfree(srv); + + return 0; +} + +/* Announce the list of servers registered on the local node */ +static int ctrl_cmd_hello(struct sockaddr_qrtr *sq) +{ + return announce_servers(sq); +} + +static int ctrl_cmd_bye(struct sockaddr_qrtr *from) +{ + struct qrtr_node *local_node; + struct radix_tree_iter iter; + struct qrtr_ctrl_pkt pkt; + struct qrtr_server *srv; + struct sockaddr_qrtr sq; + struct msghdr msg = { }; + struct qrtr_node *node; + void __rcu **slot; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + node = node_get(from->sq_node); + if (!node) + return 0; + + /* Advertise removal of this client to all servers of remote node */ + radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + server_del(node, srv->port); + } + + /* Advertise the removal of this client to all local servers */ + local_node = node_get(qrtr_ns.local_node); + if (!local_node) + return 0; + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE); + pkt.client.node = cpu_to_le32(from->sq_node); + + radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + sq.sq_family = AF_QIPCRTR; + sq.sq_node = srv->node; + sq.sq_port = srv->port; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) { + pr_err("failed to send bye cmd\n"); + return ret; + } + } + + return 0; +} + +static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, + unsigned int node_id, unsigned int port) +{ + struct qrtr_node *local_node; + struct radix_tree_iter iter; + struct qrtr_lookup *lookup; + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct qrtr_server *srv; + struct sockaddr_qrtr sq; + struct qrtr_node *node; + struct list_head *tmp; + struct list_head *li; + void __rcu **slot; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + /* Local DEL_CLIENT messages comes from the port being closed */ + if (from->sq_node == qrtr_ns.local_node && from->sq_port != port) + return -EINVAL; + + /* Remove any lookups by this client */ + list_for_each_safe(li, tmp, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->sq.sq_node != node_id) + continue; + if (lookup->sq.sq_port != port) + continue; + + list_del(&lookup->li); + kfree(lookup); + } + + /* Remove the server belonging to this port */ + node = node_get(node_id); + if (node) + server_del(node, port); + + /* Advertise the removal of this client to all local servers */ + local_node = node_get(qrtr_ns.local_node); + if (!local_node) + return 0; + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT); + pkt.client.node = cpu_to_le32(node_id); + pkt.client.port = cpu_to_le32(port); + + radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { + srv = radix_tree_deref_slot(slot); + + sq.sq_family = AF_QIPCRTR; + sq.sq_node = srv->node; + sq.sq_port = srv->port; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) { + pr_err("failed to send del client cmd\n"); + return ret; + } + } + + return 0; +} + +static int ctrl_cmd_new_server(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance, + unsigned int node_id, unsigned int port) +{ + struct qrtr_lookup *lookup; + struct qrtr_server *srv; + struct list_head *li; + int ret = 0; + + /* Ignore specified node and port for local servers */ + if (from->sq_node == qrtr_ns.local_node) { + node_id = from->sq_node; + port = from->sq_port; + } + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + srv = server_add(service, instance, node_id, port); + if (!srv) + return -EINVAL; + + if (srv->node == qrtr_ns.local_node) { + ret = service_announce_new(&qrtr_ns.bcast_sq, srv); + if (ret < 0) { + pr_err("failed to announce new service\n"); + return ret; + } + } + + /* Notify any potential lookups about the new server */ + list_for_each(li, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->service && lookup->service != service) + continue; + if (lookup->instance && lookup->instance != instance) + continue; + + lookup_notify(&lookup->sq, srv, true); + } + + return ret; +} + +static int ctrl_cmd_del_server(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance, + unsigned int node_id, unsigned int port) +{ + struct qrtr_node *node; + + /* Ignore specified node and port for local servers*/ + if (from->sq_node == qrtr_ns.local_node) { + node_id = from->sq_node; + port = from->sq_port; + } + + /* Don't accept spoofed messages */ + if (from->sq_node != node_id) + return -EINVAL; + + /* Local servers may only unregister themselves */ + if (from->sq_node == qrtr_ns.local_node && from->sq_port != port) + return -EINVAL; + + node = node_get(node_id); + if (!node) + return -ENOENT; + + return server_del(node, port); +} + +static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance) +{ + struct radix_tree_iter node_iter; + struct qrtr_server_filter filter; + struct radix_tree_iter srv_iter; + struct qrtr_lookup *lookup; + struct qrtr_node *node; + void __rcu **node_slot; + void __rcu **srv_slot; + + /* Accept only local observers */ + if (from->sq_node != qrtr_ns.local_node) + return -EINVAL; + + lookup = kzalloc(sizeof(*lookup), GFP_KERNEL); + if (!lookup) + return -ENOMEM; + + lookup->sq = *from; + lookup->service = service; + lookup->instance = instance; + list_add_tail(&lookup->li, &qrtr_ns.lookups); + + memset(&filter, 0, sizeof(filter)); + filter.service = service; + filter.instance = instance; + + radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) { + node = radix_tree_deref_slot(node_slot); + + radix_tree_for_each_slot(srv_slot, &node->servers, + &srv_iter, 0) { + struct qrtr_server *srv; + + srv = radix_tree_deref_slot(srv_slot); + if (!server_match(srv, &filter)) + continue; + + lookup_notify(from, srv, true); + } + } + + /* Empty notification, to indicate end of listing */ + lookup_notify(from, NULL, true); + + return 0; +} + +static void ctrl_cmd_del_lookup(struct sockaddr_qrtr *from, + unsigned int service, unsigned int instance) +{ + struct qrtr_lookup *lookup; + struct list_head *tmp; + struct list_head *li; + + list_for_each_safe(li, tmp, &qrtr_ns.lookups) { + lookup = container_of(li, struct qrtr_lookup, li); + if (lookup->sq.sq_node != from->sq_node) + continue; + if (lookup->sq.sq_port != from->sq_port) + continue; + if (lookup->service != service) + continue; + if (lookup->instance && lookup->instance != instance) + continue; + + list_del(&lookup->li); + kfree(lookup); + } +} + +static int say_hello(void) +{ + struct qrtr_ctrl_pkt pkt; + struct msghdr msg = { }; + struct kvec iv; + int ret; + + iv.iov_base = &pkt; + iv.iov_len = sizeof(pkt); + + memset(&pkt, 0, sizeof(pkt)); + pkt.cmd = cpu_to_le32(QRTR_TYPE_HELLO); + + msg.msg_name = (struct sockaddr *)&qrtr_ns.bcast_sq; + msg.msg_namelen = sizeof(qrtr_ns.bcast_sq); + + ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); + if (ret < 0) + pr_err("failed to send hello msg\n"); + + return ret; +} + +static void qrtr_ns_worker(struct work_struct *work) +{ + const struct qrtr_ctrl_pkt *pkt; + size_t recv_buf_size = 4096; + struct sockaddr_qrtr sq; + struct msghdr msg = { }; + unsigned int cmd; + ssize_t msglen; + void *recv_buf; + struct kvec iv; + int ret; + + msg.msg_name = (struct sockaddr *)&sq; + msg.msg_namelen = sizeof(sq); + + recv_buf = kzalloc(recv_buf_size, GFP_KERNEL); + if (!recv_buf) + return; + + for (;;) { + iv.iov_base = recv_buf; + iv.iov_len = recv_buf_size; + + msglen = kernel_recvmsg(qrtr_ns.sock, &msg, &iv, 1, + iv.iov_len, MSG_DONTWAIT); + + if (msglen == -EAGAIN) + break; + + if (msglen < 0) { + pr_err("error receiving packet: %zd\n", msglen); + break; + } + + pkt = recv_buf; + cmd = le32_to_cpu(pkt->cmd); + if (cmd < ARRAY_SIZE(qrtr_ctrl_pkt_strings) && + qrtr_ctrl_pkt_strings[cmd]) + trace_printk("%s from %d:%d\n", + qrtr_ctrl_pkt_strings[cmd], sq.sq_node, + sq.sq_port); + + ret = 0; + switch (cmd) { + case QRTR_TYPE_HELLO: + ret = ctrl_cmd_hello(&sq); + break; + case QRTR_TYPE_BYE: + ret = ctrl_cmd_bye(&sq); + break; + case QRTR_TYPE_DEL_CLIENT: + ret = ctrl_cmd_del_client(&sq, + le32_to_cpu(pkt->client.node), + le32_to_cpu(pkt->client.port)); + break; + case QRTR_TYPE_NEW_SERVER: + ret = ctrl_cmd_new_server(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance), + le32_to_cpu(pkt->server.node), + le32_to_cpu(pkt->server.port)); + break; + case QRTR_TYPE_DEL_SERVER: + ret = ctrl_cmd_del_server(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance), + le32_to_cpu(pkt->server.node), + le32_to_cpu(pkt->server.port)); + break; + case QRTR_TYPE_EXIT: + case QRTR_TYPE_PING: + case QRTR_TYPE_RESUME_TX: + break; + case QRTR_TYPE_NEW_LOOKUP: + ret = ctrl_cmd_new_lookup(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance)); + break; + case QRTR_TYPE_DEL_LOOKUP: + ctrl_cmd_del_lookup(&sq, + le32_to_cpu(pkt->server.service), + le32_to_cpu(pkt->server.instance)); + break; + } + + if (ret < 0) + pr_err("failed while handling packet from %d:%d", + sq.sq_node, sq.sq_port); + } + + kfree(recv_buf); +} + +static void qrtr_ns_data_ready(struct sock *sk) +{ + queue_work(qrtr_ns.workqueue, &qrtr_ns.work); +} + +void qrtr_ns_init(struct work_struct *work) +{ + struct sockaddr_qrtr sq; + int ret; + + INIT_LIST_HEAD(&qrtr_ns.lookups); + INIT_WORK(&qrtr_ns.work, qrtr_ns_worker); + + ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM, + PF_QIPCRTR, &qrtr_ns.sock); + if (ret < 0) + return; + + ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq); + if (ret < 0) { + pr_err("failed to get socket name\n"); + goto err_sock; + } + + qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready; + + sq.sq_port = QRTR_PORT_CTRL; + qrtr_ns.local_node = sq.sq_node; + + ret = kernel_bind(qrtr_ns.sock, (struct sockaddr *)&sq, sizeof(sq)); + if (ret < 0) { + pr_err("failed to bind to socket\n"); + goto err_sock; + } + + qrtr_ns.bcast_sq.sq_family = AF_QIPCRTR; + qrtr_ns.bcast_sq.sq_node = QRTR_NODE_BCAST; + qrtr_ns.bcast_sq.sq_port = QRTR_PORT_CTRL; + + qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); + if (!qrtr_ns.workqueue) + goto err_sock; + + ret = say_hello(); + if (ret < 0) + goto err_wq; + + return; + +err_wq: + destroy_workqueue(qrtr_ns.workqueue); +err_sock: + sock_release(qrtr_ns.sock); +} +EXPORT_SYMBOL_GPL(qrtr_ns_init); + +void qrtr_ns_remove(void) +{ + cancel_work_sync(&qrtr_ns.work); + destroy_workqueue(qrtr_ns.workqueue); + sock_release(qrtr_ns.sock); +} +EXPORT_SYMBOL_GPL(qrtr_ns_remove); + +MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>"); +MODULE_DESCRIPTION("Qualcomm IPC Router Nameservice"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 5a8e42ad1504..423310896285 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -7,9 +7,9 @@ #include <linux/netlink.h> #include <linux/qrtr.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ -#include <linux/numa.h> #include <linux/spinlock.h> #include <linux/wait.h> +#include <linux/workqueue.h> #include <net/sock.h> @@ -96,7 +96,7 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) return container_of(sk, struct qrtr_sock, sk); } -static unsigned int qrtr_local_nid = NUMA_NO_NODE; +static unsigned int qrtr_local_nid = 1; /* for node ids */ static RADIX_TREE(qrtr_nodes, GFP_ATOMIC); @@ -110,6 +110,8 @@ static DEFINE_MUTEX(qrtr_node_lock); static DEFINE_IDR(qrtr_ports); static DEFINE_MUTEX(qrtr_port_lock); +static struct delayed_work qrtr_ns_work; + /** * struct qrtr_node - endpoint node * @ep_lock: lock for endpoint management and callbacks @@ -1241,38 +1243,6 @@ static int qrtr_create(struct net *net, struct socket *sock, return 0; } -static const struct nla_policy qrtr_policy[IFA_MAX + 1] = { - [IFA_LOCAL] = { .type = NLA_U32 }, -}; - -static int qrtr_addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[IFA_MAX + 1]; - struct ifaddrmsg *ifm; - int rc; - - if (!netlink_capable(skb, CAP_NET_ADMIN)) - return -EPERM; - - if (!netlink_capable(skb, CAP_SYS_ADMIN)) - return -EPERM; - - ASSERT_RTNL(); - - rc = nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - qrtr_policy, extack); - if (rc < 0) - return rc; - - ifm = nlmsg_data(nlh); - if (!tb[IFA_LOCAL]) - return -EINVAL; - - qrtr_local_nid = nla_get_u32(tb[IFA_LOCAL]); - return 0; -} - static const struct net_proto_family qrtr_family = { .owner = THIS_MODULE, .family = AF_QIPCRTR, @@ -1293,11 +1263,11 @@ static int __init qrtr_proto_init(void) return rc; } - rc = rtnl_register_module(THIS_MODULE, PF_QIPCRTR, RTM_NEWADDR, qrtr_addr_doit, NULL, 0); - if (rc) { - sock_unregister(qrtr_family.family); - proto_unregister(&qrtr_proto); - } + /* FIXME: Currently, this 2s delay is required to catch the NEW_SERVER + * messages from routers. But the fix could be somewhere else. + */ + INIT_DELAYED_WORK(&qrtr_ns_work, qrtr_ns_init); + schedule_delayed_work(&qrtr_ns_work, msecs_to_jiffies(2000)); return rc; } @@ -1305,7 +1275,8 @@ postcore_initcall(qrtr_proto_init); static void __exit qrtr_proto_fini(void) { - rtnl_unregister(PF_QIPCRTR, RTM_NEWADDR); + cancel_delayed_work_sync(&qrtr_ns_work); + qrtr_ns_remove(); sock_unregister(qrtr_family.family); proto_unregister(&qrtr_proto); } diff --git a/net/qrtr/qrtr.h b/net/qrtr/qrtr.h index b81e6953c04b..53a237a28971 100644 --- a/net/qrtr/qrtr.h +++ b/net/qrtr/qrtr.h @@ -29,4 +29,8 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep); int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len); +void qrtr_ns_init(struct work_struct *work); + +void qrtr_ns_remove(void); + #endif diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index ce948c1e24dc..5e2df590bb58 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -267,14 +267,12 @@ tcf_sample_get_group(const struct tc_action *a, struct tcf_sample *s = to_sample(a); struct psample_group *group; - spin_lock_bh(&s->tcf_lock); group = rcu_dereference_protected(s->psample_group, lockdep_is_held(&s->tcf_lock)); if (group) { psample_group_take(group); *destructor = tcf_psample_group_put; } - spin_unlock_bh(&s->tcf_lock); return group; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c2cdd0fc2e70..4e766c5ab77a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3382,14 +3382,40 @@ int tc_setup_cb_reoffload(struct tcf_block *block, struct tcf_proto *tp, } EXPORT_SYMBOL(tc_setup_cb_reoffload); +static int tcf_act_get_cookie(struct flow_action_entry *entry, + const struct tc_action *act) +{ + struct tc_cookie *cookie; + int err = 0; + + rcu_read_lock(); + cookie = rcu_dereference(act->act_cookie); + if (cookie) { + entry->cookie = flow_action_cookie_create(cookie->data, + cookie->len, + GFP_ATOMIC); + if (!entry->cookie) + err = -ENOMEM; + } + rcu_read_unlock(); + return err; +} + +static void tcf_act_put_cookie(struct flow_action_entry *entry) +{ + flow_action_cookie_destroy(entry->cookie); +} + void tc_cleanup_flow_action(struct flow_action *flow_action) { struct flow_action_entry *entry; int i; - flow_action_for_each(i, entry, flow_action) + flow_action_for_each(i, entry, flow_action) { + tcf_act_put_cookie(entry); if (entry->destructor) entry->destructor(entry->destructor_priv); + } } EXPORT_SYMBOL(tc_cleanup_flow_action); @@ -3433,22 +3459,23 @@ static void tcf_sample_get_group(struct flow_action_entry *entry, } int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts, bool rtnl_held) + const struct tcf_exts *exts) { - const struct tc_action *act; + struct tc_action *act; int i, j, k, err = 0; if (!exts) return 0; - if (!rtnl_held) - rtnl_lock(); - j = 0; tcf_exts_for_each_action(i, act, exts) { struct flow_action_entry *entry; entry = &flow_action->entries[j]; + spin_lock_bh(&act->tcfa_lock); + err = tcf_act_get_cookie(entry, act); + if (err) + goto err_out_locked; if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; } else if (is_tcf_gact_shot(act)) { @@ -3489,13 +3516,13 @@ int tc_setup_flow_action(struct flow_action *flow_action, break; default: err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } } else if (is_tcf_tunnel_set(act)) { entry->id = FLOW_ACTION_TUNNEL_ENCAP; err = tcf_tunnel_encap_get_tunnel(entry, act); if (err) - goto err_out; + goto err_out_locked; } else if (is_tcf_tunnel_release(act)) { entry->id = FLOW_ACTION_TUNNEL_DECAP; } else if (is_tcf_pedit(act)) { @@ -3509,7 +3536,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, break; default: err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } entry->mangle.htype = tcf_pedit_htype(act, k); entry->mangle.mask = tcf_pedit_mask(act, k); @@ -3560,28 +3587,29 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; default: - goto err_out; + goto err_out_locked; } } else if (is_tcf_skbedit_ptype(act)) { entry->id = FLOW_ACTION_PTYPE; entry->ptype = tcf_skbedit_ptype(act); } else { err = -EOPNOTSUPP; - goto err_out; + goto err_out_locked; } + spin_unlock_bh(&act->tcfa_lock); if (!is_tcf_pedit(act)) j++; } err_out: - if (!rtnl_held) - rtnl_unlock(); - if (err) tc_cleanup_flow_action(flow_action); return err; +err_out_locked: + spin_unlock_bh(&act->tcfa_lock); + goto err_out; } EXPORT_SYMBOL(tc_setup_flow_action); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d32d4233d337..258dc45ab7e3 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -450,8 +450,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - rtnl_held); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (skip_sw) { @@ -2001,8 +2000,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, cls_flower.rule->match.mask = &f->mask->key; cls_flower.rule->match.key = &f->mkey; - err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts, - true); + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); if (err) { kfree(cls_flower.rule); if (tc_skip_sw(f->flags)) { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 610a0b728161..a34b36adb9b7 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -97,7 +97,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, cls_mall.command = TC_CLSMATCHALL_REPLACE; cls_mall.cookie = cookie; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); mall_destroy_hw_filter(tp, head, cookie, NULL); @@ -302,7 +302,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY; cls_mall.cookie = (unsigned long)head; - err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts, true); + err = tc_setup_flow_action(&cls_mall.rule->action, &head->exts); if (err) { kfree(cls_mall.rule); if (add && tc_skip_sw(head->flags)) { diff --git a/net/sctp/input.c b/net/sctp/input.c index efaaefc3bb1c..55d4fc6f371d 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -548,6 +548,7 @@ out: /* Common cleanup code for icmp/icmpv6 error handler. */ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) + __releases(&((__sk)->sk_lock.slock)) { bh_unlock_sock(sk); sctp_transport_put(t); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1b56fc440606..fed26a1e9518 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5333,14 +5333,14 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, EXPORT_SYMBOL_GPL(sctp_get_sctp_info); /* use callback to avoid exporting the core structure */ -void sctp_transport_walk_start(struct rhashtable_iter *iter) +void sctp_transport_walk_start(struct rhashtable_iter *iter) __acquires(RCU) { rhltable_walk_enter(&sctp_transport_hashtable, iter); rhashtable_walk_start(iter); } -void sctp_transport_walk_stop(struct rhashtable_iter *iter) +void sctp_transport_walk_stop(struct rhashtable_iter *iter) __releases(RCU) { rhashtable_walk_stop(iter); rhashtable_walk_exit(iter); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 86cccc24e52e..ea0068f0173c 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -349,7 +349,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, smc->peer_diagnosis = ntohl(dclc->peer_diagnosis); if (((struct smc_clc_msg_decline *)buf)->hdr.flag) { smc->conn.lgr->sync_err = 1; - smc_lgr_terminate(smc->conn.lgr, true); + smc_lgr_terminate_sched(smc->conn.lgr); } } @@ -372,7 +372,8 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) && + smc_ib_is_valid_local_systemid()) memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 5b085efa3bce..824c5211b027 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -46,6 +46,7 @@ static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted); static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb, struct smc_buf_desc *buf_desc); +static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft); /* return head of link group list and its lock for a given link group */ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr, @@ -241,7 +242,7 @@ static void smc_lgr_terminate_work(struct work_struct *work) struct smc_link_group *lgr = container_of(work, struct smc_link_group, terminate_work); - smc_lgr_terminate(lgr, true); + __smc_lgr_terminate(lgr, true); } /* create a new SMC link group */ @@ -588,15 +589,15 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) } else { struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK]; - wake_up(&lnk->wr_reg_wait); - if (lnk->state != SMC_LNK_INACTIVE) { - smc_link_send_delete(lnk, false); + if (lnk->state != SMC_LNK_INACTIVE) smc_llc_link_inactive(lnk); - } } } -/* terminate link group */ +/* terminate link group + * @soft: true if link group shutdown can take its time + * false if immediate link group shutdown is required + */ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) { struct smc_connection *conn; @@ -634,25 +635,20 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr, bool soft) smc_lgr_free(lgr); } -/* unlink and terminate link group - * @soft: true if link group shutdown can take its time - * false if immediate link group shutdown is required - */ -void smc_lgr_terminate(struct smc_link_group *lgr, bool soft) +/* unlink link group and schedule termination */ +void smc_lgr_terminate_sched(struct smc_link_group *lgr) { spinlock_t *lgr_lock; smc_lgr_list_head(lgr, &lgr_lock); spin_lock_bh(lgr_lock); - if (lgr->terminating) { + if (list_empty(&lgr->list) || lgr->terminating || lgr->freeing) { spin_unlock_bh(lgr_lock); return; /* lgr already terminating */ } - if (!soft) - lgr->freeing = 1; list_del_init(&lgr->list); spin_unlock_bh(lgr_lock); - __smc_lgr_terminate(lgr, soft); + schedule_work(&lgr->terminate_work); } /* Called when IB port is terminated */ diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 234ae25f0025..8041db20c753 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -285,19 +285,13 @@ static inline struct smc_connection *smc_lgr_find_conn( return res; } -static inline void smc_lgr_terminate_sched(struct smc_link_group *lgr) -{ - if (!lgr->terminating && !lgr->freeing) - schedule_work(&lgr->terminate_work); -} - struct smc_sock; struct smc_clc_msg_accept_confirm; struct smc_clc_msg_local; void smc_lgr_forget(struct smc_link_group *lgr); void smc_lgr_cleanup_early(struct smc_connection *conn); -void smc_lgr_terminate(struct smc_link_group *lgr, bool soft); +void smc_lgr_terminate_sched(struct smc_link_group *lgr); void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport); void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan); diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index d6ba186f67e2..9239cf881f21 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -37,11 +37,7 @@ struct smc_ib_devices smc_ib_devices = { /* smc-registered ib devices */ .list = LIST_HEAD_INIT(smc_ib_devices.list), }; -#define SMC_LOCAL_SYSTEMID_RESET "%%%%%%%" - -u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET; /* unique system - * identifier - */ +u8 local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */ static int smc_ib_modify_qp_init(struct smc_link *lnk) { @@ -168,6 +164,15 @@ static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev, { memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1], sizeof(smcibdev->mac[ibport - 1])); +} + +bool smc_ib_is_valid_local_systemid(void) +{ + return !is_zero_ether_addr(&local_systemid[2]); +} + +static void smc_ib_init_local_systemid(void) +{ get_random_bytes(&local_systemid[0], 2); } @@ -224,8 +229,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport) rc = smc_ib_fill_mac(smcibdev, ibport); if (rc) goto out; - if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET, - sizeof(local_systemid)) && + if (!smc_ib_is_valid_local_systemid() && smc_ib_port_active(smcibdev, ibport)) /* create unique system identifier */ smc_ib_define_local_systemid(smcibdev, ibport); @@ -257,6 +261,7 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, struct ib_event *ibevent) { struct smc_ib_device *smcibdev; + bool schedule = false; u8 port_idx; smcibdev = container_of(handler, struct smc_ib_device, event_handler); @@ -266,22 +271,35 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, /* terminate all ports on device */ for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) { set_bit(port_idx, &smcibdev->port_event_mask); - set_bit(port_idx, smcibdev->ports_going_away); + if (!test_and_set_bit(port_idx, + smcibdev->ports_going_away)) + schedule = true; } - schedule_work(&smcibdev->port_event_work); + if (schedule) + schedule_work(&smcibdev->port_event_work); break; - case IB_EVENT_PORT_ERR: case IB_EVENT_PORT_ACTIVE: - case IB_EVENT_GID_CHANGE: port_idx = ibevent->element.port_num - 1; - if (port_idx < SMC_MAX_PORTS) { - set_bit(port_idx, &smcibdev->port_event_mask); - if (ibevent->event == IB_EVENT_PORT_ERR) - set_bit(port_idx, smcibdev->ports_going_away); - else if (ibevent->event == IB_EVENT_PORT_ACTIVE) - clear_bit(port_idx, smcibdev->ports_going_away); + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (test_and_clear_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); - } + break; + case IB_EVENT_PORT_ERR: + port_idx = ibevent->element.port_num - 1; + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) + schedule_work(&smcibdev->port_event_work); + break; + case IB_EVENT_GID_CHANGE: + port_idx = ibevent->element.port_num - 1; + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); break; default: break; @@ -316,11 +334,11 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_QP_FATAL: case IB_EVENT_QP_ACCESS_ERR: port_idx = ibevent->element.qp->port - 1; - if (port_idx < SMC_MAX_PORTS) { - set_bit(port_idx, &smcibdev->port_event_mask); - set_bit(port_idx, smcibdev->ports_going_away); + if (port_idx >= SMC_MAX_PORTS) + break; + set_bit(port_idx, &smcibdev->port_event_mask); + if (!test_and_set_bit(port_idx, smcibdev->ports_going_away)) schedule_work(&smcibdev->port_event_work); - } break; default: break; @@ -593,6 +611,7 @@ static struct ib_client smc_ib_client = { int __init smc_ib_register_client(void) { + smc_ib_init_local_systemid(); return ib_register_client(&smc_ib_client); } diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 255db87547d3..5c2b115d36da 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -84,4 +84,5 @@ void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev, enum dma_data_direction data_direction); int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index); +bool smc_ib_is_valid_local_systemid(void); #endif diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a9f6431dd69a..0e52aab53d97 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -614,7 +614,7 @@ static void smc_llc_testlink_work(struct work_struct *work) rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, SMC_LLC_WAIT_TIME); if (rc <= 0) { - smc_lgr_terminate(smc_get_lgr(link), true); + smc_lgr_terminate_sched(smc_get_lgr(link)); return; } next_interval = link->llc_testlink_time; diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 0d42e7716b91..9f1ade86d70e 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -284,7 +284,7 @@ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) - smc_lgr_terminate(lgr, true); + smc_lgr_terminate_sched(lgr); return rc; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 3a1d428c1336..f25604d68337 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -29,7 +29,7 @@ struct switchdev_deferred_item { struct list_head list; struct net_device *dev; switchdev_deferred_func_t *func; - unsigned long data[0]; + unsigned long data[]; }; static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) @@ -475,6 +475,9 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info, check_cb, add_cb); if (err && err != -EOPNOTSUPP) @@ -526,6 +529,9 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info, check_cb, del_cb); if (err && err != -EOPNOTSUPP) @@ -576,6 +582,9 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, * necessary to go through this helper. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { + if (netif_is_bridge_master(lower_dev)) + continue; + err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info, check_cb, set_cb); if (err && err != -EOPNOTSUPP) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 94774c0e5ff3..82225bcc1117 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -742,7 +742,8 @@ static void tls_update(struct sock *sk, struct proto *p, ctx->sk_write_space = write_space; ctx->sk_proto = p; } else { - sk->sk_prot = p; + /* Pairs with lockless read in sk_clone_lock(). */ + WRITE_ONCE(sk->sk_prot, p); sk->sk_write_space = write_space; } } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 68debcb28fa4..9d0518d9bdd4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1211,6 +1211,7 @@ out: } static long unix_wait_for_peer(struct sock *other, long timeo) + __releases(&unix_sk(other)->lock) { struct unix_sock *u = unix_sk(other); int sched; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index f3c4bab2f737..709038a4783e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1151,6 +1151,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, virtio_transport_free_pkt(pkt); break; default: + (void)virtio_transport_reset_no_sock(t, pkt); virtio_transport_free_pkt(pkt); break; } diff --git a/net/wireless/core.h b/net/wireless/core.h index ed487e324571..bb897a803ffe 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -385,7 +385,7 @@ void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, struct net_device *dev); int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, u16 frame_type, const u8 *match_data, - int match_len); + int match_len, struct netlink_ext_ack *extack); void cfg80211_mlme_unreg_wk(struct work_struct *wk); void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid); void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f9462010575f..e4805a3bd310 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -4,6 +4,7 @@ * * Copyright (c) 2009, Jouni Malinen <j@w1.fi> * Copyright (c) 2015 Intel Deutschland GmbH + * Copyright (C) 2019 Intel Corporation */ #include <linux/kernel.h> @@ -470,7 +471,7 @@ void cfg80211_mlme_unreg_wk(struct work_struct *wk) int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, u16 frame_type, const u8 *match_data, - int match_len) + int match_len, struct netlink_ext_ack *extack) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -481,15 +482,38 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, if (!wdev->wiphy->mgmt_stypes) return -EOPNOTSUPP; - if ((frame_type & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_MGMT) + if ((frame_type & IEEE80211_FCTL_FTYPE) != IEEE80211_FTYPE_MGMT) { + NL_SET_ERR_MSG(extack, "frame type not management"); return -EINVAL; + } - if (frame_type & ~(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) + if (frame_type & ~(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) { + NL_SET_ERR_MSG(extack, "Invalid frame type"); return -EINVAL; + } mgmt_type = (frame_type & IEEE80211_FCTL_STYPE) >> 4; - if (!(wdev->wiphy->mgmt_stypes[wdev->iftype].rx & BIT(mgmt_type))) + if (!(wdev->wiphy->mgmt_stypes[wdev->iftype].rx & BIT(mgmt_type))) { + NL_SET_ERR_MSG(extack, + "Registration to specific type not supported"); + return -EINVAL; + } + + /* + * To support Pre Association Security Negotiation (PASN), registration + * for authentication frames should be supported. However, as some + * versions of the user space daemons wrongly register to all types of + * authentication frames (which might result in unexpected behavior) + * allow such registration if the request is for a specific + * authentication algorithm number. + */ + if (wdev->iftype == NL80211_IFTYPE_STATION && + (frame_type & IEEE80211_FCTL_STYPE) == IEEE80211_STYPE_AUTH && + !(match_data && match_len >= 2)) { + NL_SET_ERR_MSG(extack, + "Authentication algorithm number required"); return -EINVAL; + } nreg = kzalloc(sizeof(*reg) + match_len, GFP_KERNEL); if (!nreg) @@ -504,6 +528,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, continue; if (memcmp(reg->match, match_data, mlen) == 0) { + NL_SET_ERR_MSG(extack, "Match already configured"); err = -EALREADY; break; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5b19e9fac4aa..15000275b32d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -322,6 +322,29 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = { NLA_POLICY_RANGE(NLA_U8, 1, 20), }; +static const struct nla_policy +he_bss_color_policy[NL80211_HE_BSS_COLOR_ATTR_MAX + 1] = { + [NL80211_HE_BSS_COLOR_ATTR_COLOR] = NLA_POLICY_RANGE(NLA_U8, 1, 63), + [NL80211_HE_BSS_COLOR_ATTR_DISABLED] = { .type = NLA_FLAG }, + [NL80211_HE_BSS_COLOR_ATTR_PARTIAL] = { .type = NLA_FLAG }, +}; + +static const struct nla_policy +nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = { + [NL80211_TID_CONFIG_ATTR_VIF_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_PEER_SUPP] = { .type = NLA_U64 }, + [NL80211_TID_CONFIG_ATTR_OVERRIDE] = { .type = NLA_FLAG }, + [NL80211_TID_CONFIG_ATTR_TIDS] = NLA_POLICY_RANGE(NLA_U16, 1, 0xff), + [NL80211_TID_CONFIG_ATTR_NOACK] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RETRY_SHORT] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_RETRY_LONG] = NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_TID_CONFIG_ATTR_AMPDU_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), + [NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL] = + NLA_POLICY_MAX(NLA_U8, NL80211_TID_CONFIG_DISABLE), +}; + const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -362,7 +385,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_KEY] = { .type = NLA_NESTED, }, [NL80211_ATTR_KEY_DATA] = { .type = NLA_BINARY, .len = WLAN_MAX_KEY_LEN }, - [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 5), + [NL80211_ATTR_KEY_IDX] = NLA_POLICY_MAX(NLA_U8, 7), [NL80211_ATTR_KEY_CIPHER] = { .type = NLA_U32 }, [NL80211_ATTR_KEY_DEFAULT] = { .type = NLA_FLAG }, [NL80211_ATTR_KEY_SEQ] = { .type = NLA_BINARY, .len = 16 }, @@ -627,6 +650,9 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TWT_RESPONDER] = { .type = NLA_FLAG }, [NL80211_ATTR_HE_OBSS_PD] = NLA_POLICY_NESTED(he_obss_pd_policy), [NL80211_ATTR_VLAN_ID] = NLA_POLICY_RANGE(NLA_U16, 1, VLAN_N_VID - 2), + [NL80211_ATTR_HE_BSS_COLOR] = NLA_POLICY_NESTED(he_bss_color_policy), + [NL80211_ATTR_TID_CONFIG] = + NLA_POLICY_NESTED_ARRAY(nl80211_tid_config_attr_policy), }; /* policy for the key attributes */ @@ -966,6 +992,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_10MHZ) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_10MHZ)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_NO_HE) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HE)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -1027,7 +1056,7 @@ struct key_parse { struct key_params p; int idx; int type; - bool def, defmgmt; + bool def, defmgmt, defbeacon; bool def_uni, def_multi; }; @@ -1043,12 +1072,13 @@ static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key, k->def = !!tb[NL80211_KEY_DEFAULT]; k->defmgmt = !!tb[NL80211_KEY_DEFAULT_MGMT]; + k->defbeacon = !!tb[NL80211_KEY_DEFAULT_BEACON]; if (k->def) { k->def_uni = true; k->def_multi = true; } - if (k->defmgmt) + if (k->defmgmt || k->defbeacon) k->def_multi = true; if (tb[NL80211_KEY_IDX]) @@ -1155,14 +1185,17 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) if (err) return err; - if (k->def && k->defmgmt) { - GENL_SET_ERR_MSG(info, "key with def && defmgmt is invalid"); + if ((k->def ? 1 : 0) + (k->defmgmt ? 1 : 0) + + (k->defbeacon ? 1 : 0) > 1) { + GENL_SET_ERR_MSG(info, + "key with multiple default flags is invalid"); return -EINVAL; } - if (k->defmgmt) { + if (k->defmgmt || k->defbeacon) { if (k->def_uni || !k->def_multi) { - GENL_SET_ERR_MSG(info, "defmgmt key must be mcast"); + GENL_SET_ERR_MSG(info, + "defmgmt/defbeacon key must be mcast"); return -EINVAL; } } @@ -1174,14 +1207,20 @@ static int nl80211_parse_key(struct genl_info *info, struct key_parse *k) "defmgmt key idx not 4 or 5"); return -EINVAL; } + } else if (k->defbeacon) { + if (k->idx < 6 || k->idx > 7) { + GENL_SET_ERR_MSG(info, + "defbeacon key idx not 6 or 7"); + return -EINVAL; + } } else if (k->def) { if (k->idx < 0 || k->idx > 3) { GENL_SET_ERR_MSG(info, "def key idx not 0-3"); return -EINVAL; } } else { - if (k->idx < 0 || k->idx > 5) { - GENL_SET_ERR_MSG(info, "key idx not 0-5"); + if (k->idx < 0 || k->idx > 7) { + GENL_SET_ERR_MSG(info, "key idx not 0-7"); return -EINVAL; } } @@ -1887,6 +1926,88 @@ static int nl80211_send_pmsr_capa(struct cfg80211_registered_device *rdev, return 0; } +static int +nl80211_put_iftype_akm_suites(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + int i; + struct nlattr *nested, *nested_akms; + const struct wiphy_iftype_akm_suites *iftype_akms; + + if (!rdev->wiphy.num_iftype_akm_suites || + !rdev->wiphy.iftype_akm_suites) + return 0; + + nested = nla_nest_start(msg, NL80211_ATTR_IFTYPE_AKM_SUITES); + if (!nested) + return -ENOBUFS; + + for (i = 0; i < rdev->wiphy.num_iftype_akm_suites; i++) { + nested_akms = nla_nest_start(msg, i + 1); + if (!nested_akms) + return -ENOBUFS; + + iftype_akms = &rdev->wiphy.iftype_akm_suites[i]; + + if (nl80211_put_iftypes(msg, NL80211_IFTYPE_AKM_ATTR_IFTYPES, + iftype_akms->iftypes_mask)) + return -ENOBUFS; + + if (nla_put(msg, NL80211_IFTYPE_AKM_ATTR_SUITES, + sizeof(u32) * iftype_akms->n_akm_suites, + iftype_akms->akm_suites)) { + return -ENOBUFS; + } + nla_nest_end(msg, nested_akms); + } + + nla_nest_end(msg, nested); + + return 0; +} + +static int +nl80211_put_tid_config_support(struct cfg80211_registered_device *rdev, + struct sk_buff *msg) +{ + struct nlattr *supp; + + if (!rdev->wiphy.tid_config_support.vif && + !rdev->wiphy.tid_config_support.peer) + return 0; + + supp = nla_nest_start(msg, NL80211_ATTR_TID_CONFIG); + if (!supp) + return -ENOSPC; + + if (rdev->wiphy.tid_config_support.vif && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_VIF_SUPP, + rdev->wiphy.tid_config_support.vif, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + if (rdev->wiphy.tid_config_support.peer && + nla_put_u64_64bit(msg, NL80211_TID_CONFIG_ATTR_PEER_SUPP, + rdev->wiphy.tid_config_support.peer, + NL80211_TID_CONFIG_ATTR_PAD)) + goto fail; + + /* for now we just use the same value ... makes more sense */ + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_SHORT, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + if (nla_put_u8(msg, NL80211_TID_CONFIG_ATTR_RETRY_LONG, + rdev->wiphy.tid_config_support.max_retry)) + goto fail; + + nla_nest_end(msg, supp); + + return 0; +fail: + nla_nest_cancel(msg, supp); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2445,6 +2566,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.akm_suites)) goto nla_put_failure; + if (nl80211_put_iftype_akm_suites(rdev, msg)) + goto nla_put_failure; + + if (nl80211_put_tid_config_support(rdev, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -3476,7 +3603,7 @@ static int nl80211_valid_4addr(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { if (!use_4addr) { - if (netdev && (netdev->priv_flags & IFF_BRIDGE_PORT)) + if (netdev && netif_is_bridge_port(netdev)) return -EBUSY; return 0; } @@ -3764,8 +3891,14 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) void *hdr; struct sk_buff *msg; - if (info->attrs[NL80211_ATTR_KEY_IDX]) + if (info->attrs[NL80211_ATTR_KEY_IDX]) { key_idx = nla_get_u8(info->attrs[NL80211_ATTR_KEY_IDX]); + if (key_idx > 5 && + !wiphy_ext_feature_isset( + &rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3841,7 +3974,7 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) /* Only support setting default key and * Extended Key ID action NL80211_KEY_SET_TX. */ - if (!key.def && !key.defmgmt && + if (!key.def && !key.defmgmt && !key.defbeacon && !(key.p.mode == NL80211_KEY_SET_TX)) return -EINVAL; @@ -3888,6 +4021,24 @@ static int nl80211_set_key(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_CFG80211_WEXT dev->ieee80211_ptr->wext.default_mgmt_key = key.idx; #endif + } else if (key.defbeacon) { + if (key.def_uni || !key.def_multi) { + err = -EINVAL; + goto out; + } + + if (!rdev->ops->set_default_beacon_key) { + err = -EOPNOTSUPP; + goto out; + } + + err = nl80211_key_allowed(dev->ieee80211_ptr); + if (err) + goto out; + + err = rdev_set_default_beacon_key(rdev, dev, key.idx); + if (err) + goto out; } else if (key.p.mode == NL80211_KEY_SET_TX && wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { @@ -3925,8 +4076,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; - if (!key.p.key) + if (!key.p.key) { + GENL_SET_ERR_MSG(info, "no key"); return -EINVAL; + } if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); @@ -3940,8 +4093,10 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) /* for now */ if (key.type != NL80211_KEYTYPE_PAIRWISE && - key.type != NL80211_KEYTYPE_GROUP) + key.type != NL80211_KEYTYPE_GROUP) { + GENL_SET_ERR_MSG(info, "key type not pairwise or group"); return -EINVAL; + } if (key.type == NL80211_KEYTYPE_GROUP && info->attrs[NL80211_ATTR_VLAN_ID]) @@ -3952,15 +4107,22 @@ static int nl80211_new_key(struct sk_buff *skb, struct genl_info *info) if (cfg80211_validate_key_settings(rdev, &key.p, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, - mac_addr)) + mac_addr)) { + GENL_SET_ERR_MSG(info, "key setting validation failed"); return -EINVAL; + } wdev_lock(dev->ieee80211_ptr); err = nl80211_key_allowed(dev->ieee80211_ptr); - if (!err) + if (err) + GENL_SET_ERR_MSG(info, "key not allowed"); + if (!err) { err = rdev_add_key(rdev, dev, key.idx, key.type == NL80211_KEYTYPE_PAIRWISE, mac_addr, &key.p); + if (err) + GENL_SET_ERR_MSG(info, "key addition failed"); + } wdev_unlock(dev->ieee80211_ptr); return err; @@ -4513,6 +4675,30 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs, return 0; } +static int nl80211_parse_he_bss_color(struct nlattr *attrs, + struct cfg80211_he_bss_color *he_bss_color) +{ + struct nlattr *tb[NL80211_HE_BSS_COLOR_ATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, NL80211_HE_BSS_COLOR_ATTR_MAX, attrs, + he_bss_color_policy, NULL); + if (err) + return err; + + if (!tb[NL80211_HE_BSS_COLOR_ATTR_COLOR]) + return -EINVAL; + + he_bss_color->color = + nla_get_u8(tb[NL80211_HE_BSS_COLOR_ATTR_COLOR]); + he_bss_color->disabled = + nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_DISABLED]); + he_bss_color->partial = + nla_get_flag(tb[NL80211_HE_BSS_COLOR_ATTR_PARTIAL]); + + return 0; +} + static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params, const u8 *rates) { @@ -4804,6 +4990,14 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_HE_BSS_COLOR]) { + err = nl80211_parse_he_bss_color( + info->attrs[NL80211_ATTR_HE_BSS_COLOR], + ¶ms.he_bss_color); + if (err) + return err; + } + nl80211_calculate_ap_params(¶ms); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -10540,8 +10734,9 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; return cfg80211_mlme_register_mgmt(wdev, info->snd_portid, frame_type, - nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), - nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH])); + nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), + nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH]), + info->extack); } static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) @@ -13803,6 +13998,141 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info) return rdev_probe_mesh_link(rdev, dev, dest, buf, len); } +static int parse_tid_conf(struct cfg80211_registered_device *rdev, + struct nlattr *attrs[], struct net_device *dev, + struct cfg80211_tid_cfg *tid_conf, + struct genl_info *info, const u8 *peer) +{ + struct netlink_ext_ack *extack = info->extack; + u64 mask; + int err; + + if (!attrs[NL80211_TID_CONFIG_ATTR_TIDS]) + return -EINVAL; + + tid_conf->config_override = + nla_get_flag(attrs[NL80211_TID_CONFIG_ATTR_OVERRIDE]); + tid_conf->tids = nla_get_u16(attrs[NL80211_TID_CONFIG_ATTR_TIDS]); + + if (tid_conf->config_override) { + if (rdev->ops->reset_tid_config) { + err = rdev_reset_tid_config(rdev, dev, peer, + tid_conf->tids); + /* If peer is there no other configuration will be + * allowed + */ + if (err || peer) + return err; + } else { + return -EINVAL; + } + } + + if (attrs[NL80211_TID_CONFIG_ATTR_NOACK]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_NOACK); + tid_conf->noack = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_NOACK]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_SHORT); + tid_conf->retry_short = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_SHORT]); + + if (tid_conf->retry_short > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RETRY_LONG); + tid_conf->retry_long = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RETRY_LONG]); + + if (tid_conf->retry_long > rdev->wiphy.max_data_retry_count) + return -EINVAL; + } + + if (attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_AMPDU_CTRL); + tid_conf->ampdu = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_AMPDU_CTRL]); + } + + if (attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]) { + tid_conf->mask |= BIT(NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL); + tid_conf->rtscts = + nla_get_u8(attrs[NL80211_TID_CONFIG_ATTR_RTSCTS_CTRL]); + } + + if (peer) + mask = rdev->wiphy.tid_config_support.peer; + else + mask = rdev->wiphy.tid_config_support.vif; + + if (tid_conf->mask & ~mask) { + NL_SET_ERR_MSG(extack, "unsupported TID configuration"); + return -ENOTSUPP; + } + + return 0; +} + +static int nl80211_set_tid_config(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct nlattr *attrs[NL80211_TID_CONFIG_ATTR_MAX + 1]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_tid_config *tid_config; + struct nlattr *tid; + int conf_idx = 0, rem_conf; + int ret = -EINVAL; + u32 num_conf = 0; + + if (!info->attrs[NL80211_ATTR_TID_CONFIG]) + return -EINVAL; + + if (!rdev->ops->set_tid_config) + return -EOPNOTSUPP; + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) + num_conf++; + + tid_config = kzalloc(struct_size(tid_config, tid_conf, num_conf), + GFP_KERNEL); + if (!tid_config) + return -ENOMEM; + + tid_config->n_tid_conf = num_conf; + + if (info->attrs[NL80211_ATTR_MAC]) + tid_config->peer = nla_data(info->attrs[NL80211_ATTR_MAC]); + + nla_for_each_nested(tid, info->attrs[NL80211_ATTR_TID_CONFIG], + rem_conf) { + ret = nla_parse_nested(attrs, NL80211_TID_CONFIG_ATTR_MAX, + tid, NULL, NULL); + + if (ret) + goto bad_tid_conf; + + ret = parse_tid_conf(rdev, attrs, dev, + &tid_config->tid_conf[conf_idx], + info, tid_config->peer); + if (ret) + goto bad_tid_conf; + + conf_idx++; + } + + ret = rdev_set_tid_config(rdev, dev, tid_config); + +bad_tid_conf: + kfree(tid_config); + return ret; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -14757,6 +15087,13 @@ static const struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_TID_CONFIG, + .doit = nl80211_set_tid_config, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index e0d34f796d0b..99462f0c4e08 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -136,6 +136,19 @@ rdev_set_default_mgmt_key(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_default_beacon_key(struct cfg80211_registered_device *rdev, + struct net_device *netdev, u8 key_index) +{ + int ret; + + trace_rdev_set_default_beacon_key(&rdev->wiphy, netdev, key_index); + ret = rdev->ops->set_default_beacon_key(&rdev->wiphy, netdev, + key_index); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + static inline int rdev_start_ap(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_ap_settings *settings) @@ -1313,4 +1326,28 @@ rdev_probe_mesh_link(struct cfg80211_registered_device *rdev, return ret; } +static inline int rdev_set_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, + struct cfg80211_tid_config *tid_conf) +{ + int ret; + + trace_rdev_set_tid_config(&rdev->wiphy, dev, tid_conf); + ret = rdev->ops->set_tid_config(&rdev->wiphy, dev, tid_conf); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + +static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev, + struct net_device *dev, const u8 *peer, + u8 tids) +{ + int ret; + + trace_rdev_reset_tid_config(&rdev->wiphy, dev, peer, tids); + ret = rdev->ops->reset_tid_config(&rdev->wiphy, dev, peer, tids); + trace_rdev_return_int(&rdev->wiphy, ret); + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 1a8218f1bbe0..d476d4da0d09 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1569,6 +1569,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_80MHZ; if (rd_flags & NL80211_RRF_NO_160MHZ) channel_flags |= IEEE80211_CHAN_NO_160MHZ; + if (rd_flags & NL80211_RRF_NO_HE) + channel_flags |= IEEE80211_CHAN_NO_HE; return channel_flags; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index aef240fdf8df..dd41e41f9d26 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -556,9 +556,8 @@ cfg80211_find_sched_scan_req(struct cfg80211_registered_device *rdev, u64 reqid) { struct cfg80211_sched_scan_request *pos; - WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - - list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list) { + list_for_each_entry_rcu(pos, &rdev->sched_scan_req_list, list, + lockdep_rtnl_is_held()) { if (pos->reqid == reqid) return pos; } @@ -1434,8 +1433,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, ts); if (!res) return NULL; @@ -1852,8 +1850,7 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, memcpy(tmp.pub.chain_signal, data->chain_signal, IEEE80211_MAX_CHAINS); ether_addr_copy(tmp.parent_bssid, data->parent_bssid); - signal_valid = abs(data->chan->center_freq - channel->center_freq) <= - wiphy->max_adj_channel_rssi_comp; + signal_valid = data->chan == channel; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid, jiffies); if (!res) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d32a2ec4d96a..ac3e60aa1fc8 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1111,9 +1111,16 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ - if (rdev->ops->del_key) - for (i = 0; i < 6; i++) + if (rdev->ops->del_key) { + int max_key_idx = 5; + + if (wiphy_ext_feature_isset( + wdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, i, false, NULL); + } rdev_set_qos_map(rdev, dev, NULL); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 3ef1679b0e66..839df54cee21 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -510,6 +510,23 @@ TRACE_EVENT(rdev_set_default_mgmt_key, WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) ); +TRACE_EVENT(rdev_set_default_beacon_key, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 key_index), + TP_ARGS(wiphy, netdev, key_index), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(u8, key_index) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->key_index = key_index; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", key index: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->key_index) +); + TRACE_EVENT(rdev_start_ap, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_ap_settings *settings), @@ -3463,6 +3480,43 @@ TRACE_EVENT(rdev_probe_mesh_link, WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(dest)) ); +TRACE_EVENT(rdev_set_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_tid_config *tid_conf), + TP_ARGS(wiphy, netdev, tid_conf), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, tid_conf->peer); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer)) +); + +TRACE_EVENT(rdev_reset_tid_config, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + const u8 *peer, u8 tids), + TP_ARGS(wiphy, netdev, peer, tids), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(peer) + __field(u8, tids) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(peer, peer); + __entry->tids = tids; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", tids: 0x%x", + WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tids) +); #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 8481e9ac33da..6590efbbcbb9 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -231,7 +231,12 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { - if (key_idx < 0 || key_idx > 5) + int max_key_idx = 5; + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_BEACON_PROTECTION)) + max_key_idx = 7; + if (key_idx < 0 || key_idx > max_key_idx) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) @@ -934,7 +939,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, return -EOPNOTSUPP; /* if it's part of a bridge, reject changing type to station/ibss */ - if ((dev->priv_flags & IFF_BRIDGE_PORT) && + if (netif_is_bridge_port(dev) && (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION || ntype == NL80211_IFTYPE_P2P_CLIENT)) diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index c82999941d3f..d48ad6d29197 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -131,13 +131,11 @@ out: void x25_clear_forward_by_lci(unsigned int lci) { - struct x25_forward *fwd; - struct list_head *entry, *tmp; + struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); - list_for_each_safe(entry, tmp, &x25_forward_list) { - fwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if (fwd->lci == lci) { list_del(&fwd->node); kfree(fwd); @@ -149,13 +147,11 @@ void x25_clear_forward_by_lci(unsigned int lci) void x25_clear_forward_by_dev(struct net_device *dev) { - struct x25_forward *fwd; - struct list_head *entry, *tmp; + struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); - list_for_each_safe(entry, tmp, &x25_forward_list) { - fwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if ((fwd->dev1 == dev) || (fwd->dev2 == dev)){ list_del(&fwd->node); kfree(fwd); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 22f235260a3a..906e9f2752db 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2890,6 +2890,25 @@ union bpf_attr { * Obtain the 64bit jiffies * Return * The 64 bit jiffies + * + * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * Description + * For an eBPF program attached to a perf event, retrieve the + * branch records (struct perf_branch_entry) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size + * *size* bytes. + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to + * instead return the number of bytes required to store all the + * branch entries. If this flag is set, *buf* may be NULL. + * + * **-EINVAL** if arguments invalid or **size** not a multiple + * of sizeof(struct perf_branch_entry). + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3010,7 +3029,8 @@ union bpf_attr { FN(probe_read_kernel_str), \ FN(tcp_send_ack), \ FN(send_signal_thread), \ - FN(jiffies64), + FN(jiffies64), \ + FN(read_branch_records), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -3089,6 +3109,9 @@ enum bpf_func_id { /* BPF_FUNC_sk_storage_get flags */ #define BPF_SK_STORAGE_GET_F_CREATE (1ULL << 0) +/* BPF_FUNC_read_branch_records flags. */ +#define BPF_F_GET_BRANCH_RECORDS_SIZE (1ULL << 0) + /* Mode for BPF_FUNC_skb_adjust_room helper. */ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 7469c7dcc15e..996162801f7a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2286,9 +2286,7 @@ static void bpf_object__sanitize_btf_ext(struct bpf_object *obj) static bool bpf_object__is_btf_mandatory(const struct bpf_object *obj) { - return obj->efile.btf_maps_shndx >= 0 || - obj->efile.st_ops_shndx >= 0 || - obj->nr_extern > 0; + return obj->efile.st_ops_shndx >= 0 || obj->nr_extern > 0; } static int bpf_object__init_btf(struct bpf_object *obj, @@ -4945,8 +4943,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { int err = 0, fd, i, btf_id; - if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { + if ((prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { btf_id = libbpf_find_attach_btf_id(prog); if (btf_id <= 0) return btf_id; @@ -6589,6 +6587,9 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, else err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + return err; } @@ -6661,8 +6662,6 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog) err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, name + section_defs[i].len, attach_type); - if (err <= 0) - pr_warn("%s is not found in vmlinux BTF\n", name); return err; } pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name); @@ -8138,6 +8137,31 @@ void bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear) } } +int bpf_program__set_attach_target(struct bpf_program *prog, + int attach_prog_fd, + const char *attach_func_name) +{ + int btf_id; + + if (!prog || attach_prog_fd < 0 || !attach_func_name) + return -EINVAL; + + if (attach_prog_fd) + btf_id = libbpf_find_prog_btf_id(attach_func_name, + attach_prog_fd); + else + btf_id = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, + attach_func_name, + prog->expected_attach_type); + + if (btf_id < 0) + return btf_id; + + prog->attach_btf_id = btf_id; + prog->attach_prog_fd = attach_prog_fd; + return 0; +} + int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz) { int err = 0, n, len, start, end = -1; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 3fe12c9d1f92..02fc58a21a7f 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -334,6 +334,10 @@ LIBBPF_API void bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); +LIBBPF_API int +bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, + const char *attach_func_name); + LIBBPF_API bool bpf_program__is_socket_filter(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_tracepoint(const struct bpf_program *prog); LIBBPF_API bool bpf_program__is_raw_tracepoint(const struct bpf_program *prog); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index b035122142bb..7b014c8cdece 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -235,3 +235,8 @@ LIBBPF_0.0.7 { btf__align_of; libbpf_find_kernel_btf; } LIBBPF_0.0.6; + +LIBBPF_0.0.8 { + global: + bpf_program__set_attach_target; +} LIBBPF_0.0.7; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 257a1aaaa37d..2a583196fa51 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -209,7 +209,7 @@ define CLANG_BPF_BUILD_RULE $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -target bpf -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ - $(LLC) -mattr=dwarfris -march=bpf -mcpu=probe $4 -filetype=obj -o $2 + $(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2 endef # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32 define CLANG_NOALU32_BPF_BUILD_RULE @@ -223,7 +223,7 @@ define CLANG_NATIVE_BPF_BUILD_RULE $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2) ($(CLANG) $3 -O2 -emit-llvm \ -c $1 -o - || echo "BPF obj compilation failed") | \ - $(LLC) -march=bpf -mcpu=probe $4 -filetype=obj -o $2 + $(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2 endef # Build BPF object using GCC define GCC_BPF_BUILD_RULE diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c new file mode 100644 index 000000000000..e35c444902a7 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <pthread.h> +#include <sched.h> +#include <sys/socket.h> +#include <test_progs.h> +#include "bpf/libbpf_internal.h" +#include "test_perf_branches.skel.h" + +static void check_good_sample(struct test_perf_branches *skel) +{ + int written_global = skel->bss->written_global_out; + int required_size = skel->bss->required_size_out; + int written_stack = skel->bss->written_stack_out; + int pbe_size = sizeof(struct perf_branch_entry); + int duration = 0; + + if (CHECK(!skel->bss->valid, "output not valid", + "no valid sample from prog")) + return; + + /* + * It's hard to validate the contents of the branch entries b/c it + * would require some kind of disassembler and also encoding the + * valid jump instructions for supported architectures. So just check + * the easy stuff for now. + */ + CHECK(required_size <= 0, "read_branches_size", "err %d\n", required_size); + CHECK(written_stack < 0, "read_branches_stack", "err %d\n", written_stack); + CHECK(written_stack % pbe_size != 0, "read_branches_stack", + "stack bytes written=%d not multiple of struct size=%d\n", + written_stack, pbe_size); + CHECK(written_global < 0, "read_branches_global", "err %d\n", written_global); + CHECK(written_global % pbe_size != 0, "read_branches_global", + "global bytes written=%d not multiple of struct size=%d\n", + written_global, pbe_size); + CHECK(written_global < written_stack, "read_branches_size", + "written_global=%d < written_stack=%d\n", written_global, written_stack); +} + +static void check_bad_sample(struct test_perf_branches *skel) +{ + int written_global = skel->bss->written_global_out; + int required_size = skel->bss->required_size_out; + int written_stack = skel->bss->written_stack_out; + int duration = 0; + + if (CHECK(!skel->bss->valid, "output not valid", + "no valid sample from prog")) + return; + + CHECK((required_size != -EINVAL && required_size != -ENOENT), + "read_branches_size", "err %d\n", required_size); + CHECK((written_stack != -EINVAL && written_stack != -ENOENT), + "read_branches_stack", "written %d\n", written_stack); + CHECK((written_global != -EINVAL && written_global != -ENOENT), + "read_branches_global", "written %d\n", written_global); +} + +static void test_perf_branches_common(int perf_fd, + void (*cb)(struct test_perf_branches *)) +{ + struct test_perf_branches *skel; + int err, i, duration = 0; + bool detached = false; + struct bpf_link *link; + volatile int j = 0; + cpu_set_t cpu_set; + + skel = test_perf_branches__open_and_load(); + if (CHECK(!skel, "test_perf_branches_load", + "perf_branches skeleton failed\n")) + return; + + /* attach perf_event */ + link = bpf_program__attach_perf_event(skel->progs.perf_branches, perf_fd); + if (CHECK(IS_ERR(link), "attach_perf_event", "err %ld\n", PTR_ERR(link))) + goto out_destroy_skel; + + /* generate some branches on cpu 0 */ + CPU_ZERO(&cpu_set); + CPU_SET(0, &cpu_set); + err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set); + if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err)) + goto out_destroy; + /* spin the loop for a while (random high number) */ + for (i = 0; i < 1000000; ++i) + ++j; + + test_perf_branches__detach(skel); + detached = true; + + cb(skel); +out_destroy: + bpf_link__destroy(link); +out_destroy_skel: + if (!detached) + test_perf_branches__detach(skel); + test_perf_branches__destroy(skel); +} + +static void test_perf_branches_hw(void) +{ + struct perf_event_attr attr = {0}; + int duration = 0; + int pfd; + + /* create perf event */ + attr.size = sizeof(attr); + attr.type = PERF_TYPE_HARDWARE; + attr.config = PERF_COUNT_HW_CPU_CYCLES; + attr.freq = 1; + attr.sample_freq = 4000; + attr.sample_type = PERF_SAMPLE_BRANCH_STACK; + attr.branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; + pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); + + /* + * Some setups don't support branch records (virtual machines, !x86), + * so skip test in this case. + */ + if (pfd == -1) { + if (errno == ENOENT || errno == EOPNOTSUPP) { + printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", + __func__); + test__skip(); + return; + } + if (CHECK(pfd < 0, "perf_event_open", "err %d errno %d\n", + pfd, errno)) + return; + } + + test_perf_branches_common(pfd, check_good_sample); + + close(pfd); +} + +/* + * Tests negative case -- run bpf_read_branch_records() on improperly configured + * perf event. + */ +static void test_perf_branches_no_hw(void) +{ + struct perf_event_attr attr = {0}; + int duration = 0; + int pfd; + + /* create perf event */ + attr.size = sizeof(attr); + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_CPU_CLOCK; + attr.freq = 1; + attr.sample_freq = 4000; + pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); + if (CHECK(pfd < 0, "perf_event_open", "err %d\n", pfd)) + return; + + test_perf_branches_common(pfd, check_bad_sample); + + close(pfd); +} + +void test_perf_branches(void) +{ + if (test__start_subtest("perf_branches_hw")) + test_perf_branches_hw(); + if (test__start_subtest("perf_branches_no_hw")) + test_perf_branches_no_hw(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 0800036ed654..68d452bb9fd9 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -36,6 +36,7 @@ static int result_map, tmp_index_ovr_map, linum_map, data_check_map; static __u32 expected_results[NR_RESULTS]; static int sk_fds[REUSEPORT_ARRAY_SIZE]; static int reuseport_array = -1, outer_map = -1; +static enum bpf_map_type inner_map_type; static int select_by_skb_data_prog; static int saved_tcp_syncookie = -1; static struct bpf_object *obj; @@ -63,13 +64,15 @@ static union sa46 { } \ }) -static int create_maps(void) +static int create_maps(enum bpf_map_type inner_type) { struct bpf_create_map_attr attr = {}; + inner_map_type = inner_type; + /* Creating reuseport_array */ attr.name = "reuseport_array"; - attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; + attr.map_type = inner_type; attr.key_size = sizeof(__u32); attr.value_size = sizeof(__u32); attr.max_entries = REUSEPORT_ARRAY_SIZE; @@ -728,12 +731,36 @@ static void cleanup_per_test(bool no_inner_map) static void cleanup(void) { - if (outer_map != -1) + if (outer_map != -1) { close(outer_map); - if (reuseport_array != -1) + outer_map = -1; + } + + if (reuseport_array != -1) { close(reuseport_array); - if (obj) + reuseport_array = -1; + } + + if (obj) { bpf_object__close(obj); + obj = NULL; + } + + memset(expected_results, 0, sizeof(expected_results)); +} + +static const char *maptype_str(enum bpf_map_type type) +{ + switch (type) { + case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: + return "reuseport_sockarray"; + case BPF_MAP_TYPE_SOCKMAP: + return "sockmap"; + case BPF_MAP_TYPE_SOCKHASH: + return "sockhash"; + default: + return "unknown"; + } } static const char *family_str(sa_family_t family) @@ -781,13 +808,21 @@ static void test_config(int sotype, sa_family_t family, bool inany) const struct test *t; for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { - snprintf(s, sizeof(s), "%s/%s %s %s", + snprintf(s, sizeof(s), "%s %s/%s %s %s", + maptype_str(inner_map_type), family_str(family), sotype_str(sotype), inany ? "INANY" : "LOOPBACK", t->name); if (!test__start_subtest(s)) continue; + if (sotype == SOCK_DGRAM && + inner_map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* SOCKMAP/SOCKHASH don't support UDP yet */ + test__skip(); + continue; + } + setup_per_test(sotype, family, inany, t->no_inner_map); t->fn(sotype, family); cleanup_per_test(t->no_inner_map); @@ -816,13 +851,20 @@ static void test_all(void) test_config(c->sotype, c->family, c->inany); } -void test_select_reuseport(void) +void test_map_type(enum bpf_map_type mt) { - if (create_maps()) + if (create_maps(mt)) goto out; if (prepare_bpf_obj()) goto out; + test_all(); +out: + cleanup(); +} + +void test_select_reuseport(void) +{ saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); if (saved_tcp_fo < 0) goto out; @@ -835,8 +877,9 @@ void test_select_reuseport(void) if (disable_syncookie()) goto out; - test_all(); + test_map_type(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + test_map_type(BPF_MAP_TYPE_SOCKMAP); + test_map_type(BPF_MAP_TYPE_SOCKHASH); out: - cleanup(); restore_sysctls(); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c new file mode 100644 index 000000000000..06b86addc181 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +/* + * Tests for sockmap/sockhash holding kTLS sockets. + */ + +#include "test_progs.h" + +#define MAX_TEST_NAME 80 +#define TCP_ULP 31 + +static int tcp_server(int family) +{ + int err, s; + + s = socket(family, SOCK_STREAM, 0); + if (CHECK_FAIL(s == -1)) { + perror("socket"); + return -1; + } + + err = listen(s, SOMAXCONN); + if (CHECK_FAIL(err)) { + perror("listen"); + return -1; + } + + return s; +} + +static int disconnect(int fd) +{ + struct sockaddr unspec = { AF_UNSPEC }; + + return connect(fd, &unspec, sizeof(unspec)); +} + +/* Disconnect (unhash) a kTLS socket after removing it from sockmap. */ +static void test_sockmap_ktls_disconnect_after_delete(int family, int map) +{ + struct sockaddr_storage addr = {0}; + socklen_t len = sizeof(addr); + int err, cli, srv, zero = 0; + + srv = tcp_server(family); + if (srv == -1) + return; + + err = getsockname(srv, (struct sockaddr *)&addr, &len); + if (CHECK_FAIL(err)) { + perror("getsockopt"); + goto close_srv; + } + + cli = socket(family, SOCK_STREAM, 0); + if (CHECK_FAIL(cli == -1)) { + perror("socket"); + goto close_srv; + } + + err = connect(cli, (struct sockaddr *)&addr, len); + if (CHECK_FAIL(err)) { + perror("connect"); + goto close_cli; + } + + err = bpf_map_update_elem(map, &zero, &cli, 0); + if (CHECK_FAIL(err)) { + perror("bpf_map_update_elem"); + goto close_cli; + } + + err = setsockopt(cli, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (CHECK_FAIL(err)) { + perror("setsockopt(TCP_ULP)"); + goto close_cli; + } + + err = bpf_map_delete_elem(map, &zero); + if (CHECK_FAIL(err)) { + perror("bpf_map_delete_elem"); + goto close_cli; + } + + err = disconnect(cli); + if (CHECK_FAIL(err)) + perror("disconnect"); + +close_cli: + close(cli); +close_srv: + close(srv); +} + +static void run_tests(int family, enum bpf_map_type map_type) +{ + char test_name[MAX_TEST_NAME]; + int map; + + map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + if (CHECK_FAIL(map == -1)) { + perror("bpf_map_create"); + return; + } + + snprintf(test_name, MAX_TEST_NAME, + "sockmap_ktls disconnect_after_delete %s %s", + family == AF_INET ? "IPv4" : "IPv6", + map_type == BPF_MAP_TYPE_SOCKMAP ? "SOCKMAP" : "SOCKHASH"); + if (!test__start_subtest(test_name)) + return; + + test_sockmap_ktls_disconnect_after_delete(family, map); + + close(map); +} + +void test_sockmap_ktls(void) +{ + run_tests(AF_INET, BPF_MAP_TYPE_SOCKMAP); + run_tests(AF_INET, BPF_MAP_TYPE_SOCKHASH); + run_tests(AF_INET6, BPF_MAP_TYPE_SOCKMAP); + run_tests(AF_INET6, BPF_MAP_TYPE_SOCKHASH); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c new file mode 100644 index 000000000000..b1b2acea0638 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -0,0 +1,1496 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare +/* + * Test suite for SOCKMAP/SOCKHASH holding listening sockets. + * Covers: + * 1. BPF map operations - bpf_map_{update,lookup delete}_elem + * 2. BPF redirect helpers - bpf_{sk,msg}_redirect_map + * 3. BPF reuseport helper - bpf_sk_select_reuseport + */ + +#include <linux/compiler.h> +#include <errno.h> +#include <error.h> +#include <limits.h> +#include <netinet/in.h> +#include <pthread.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" +#include "test_progs.h" +#include "test_sockmap_listen.skel.h" + +#define MAX_STRERR_LEN 256 +#define MAX_TEST_NAME 80 + +#define _FAIL(errnum, fmt...) \ + ({ \ + error_at_line(0, (errnum), __func__, __LINE__, fmt); \ + CHECK_FAIL(true); \ + }) +#define FAIL(fmt...) _FAIL(0, fmt) +#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt) +#define FAIL_LIBBPF(err, msg) \ + ({ \ + char __buf[MAX_STRERR_LEN]; \ + libbpf_strerror((err), __buf, sizeof(__buf)); \ + FAIL("%s: %s", (msg), __buf); \ + }) + +/* Wrappers that fail the test on error and report it. */ + +#define xaccept(fd, addr, len) \ + ({ \ + int __ret = accept((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("accept"); \ + __ret; \ + }) + +#define xbind(fd, addr, len) \ + ({ \ + int __ret = bind((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("bind"); \ + __ret; \ + }) + +#define xclose(fd) \ + ({ \ + int __ret = close((fd)); \ + if (__ret == -1) \ + FAIL_ERRNO("close"); \ + __ret; \ + }) + +#define xconnect(fd, addr, len) \ + ({ \ + int __ret = connect((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("connect"); \ + __ret; \ + }) + +#define xgetsockname(fd, addr, len) \ + ({ \ + int __ret = getsockname((fd), (addr), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockname"); \ + __ret; \ + }) + +#define xgetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = getsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("getsockopt(" #name ")"); \ + __ret; \ + }) + +#define xlisten(fd, backlog) \ + ({ \ + int __ret = listen((fd), (backlog)); \ + if (__ret == -1) \ + FAIL_ERRNO("listen"); \ + __ret; \ + }) + +#define xsetsockopt(fd, level, name, val, len) \ + ({ \ + int __ret = setsockopt((fd), (level), (name), (val), (len)); \ + if (__ret == -1) \ + FAIL_ERRNO("setsockopt(" #name ")"); \ + __ret; \ + }) + +#define xsocket(family, sotype, flags) \ + ({ \ + int __ret = socket(family, sotype, flags); \ + if (__ret == -1) \ + FAIL_ERRNO("socket"); \ + __ret; \ + }) + +#define xbpf_map_delete_elem(fd, key) \ + ({ \ + int __ret = bpf_map_delete_elem((fd), (key)); \ + if (__ret == -1) \ + FAIL_ERRNO("map_delete"); \ + __ret; \ + }) + +#define xbpf_map_lookup_elem(fd, key, val) \ + ({ \ + int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ + if (__ret == -1) \ + FAIL_ERRNO("map_lookup"); \ + __ret; \ + }) + +#define xbpf_map_update_elem(fd, key, val, flags) \ + ({ \ + int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("map_update"); \ + __ret; \ + }) + +#define xbpf_prog_attach(prog, target, type, flags) \ + ({ \ + int __ret = \ + bpf_prog_attach((prog), (target), (type), (flags)); \ + if (__ret == -1) \ + FAIL_ERRNO("prog_attach(" #type ")"); \ + __ret; \ + }) + +#define xbpf_prog_detach2(prog, target, type) \ + ({ \ + int __ret = bpf_prog_detach2((prog), (target), (type)); \ + if (__ret == -1) \ + FAIL_ERRNO("prog_detach2(" #type ")"); \ + __ret; \ + }) + +#define xpthread_create(thread, attr, func, arg) \ + ({ \ + int __ret = pthread_create((thread), (attr), (func), (arg)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_create"); \ + __ret; \ + }) + +#define xpthread_join(thread, retval) \ + ({ \ + int __ret = pthread_join((thread), (retval)); \ + errno = __ret; \ + if (__ret) \ + FAIL_ERRNO("pthread_join"); \ + __ret; \ + }) + +static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len) +{ + struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss)); + + addr4->sin_family = AF_INET; + addr4->sin_port = 0; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + *len = sizeof(*addr4); +} + +static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len) +{ + struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss)); + + addr6->sin6_family = AF_INET6; + addr6->sin6_port = 0; + addr6->sin6_addr = in6addr_loopback; + *len = sizeof(*addr6); +} + +static void init_addr_loopback(int family, struct sockaddr_storage *ss, + socklen_t *len) +{ + switch (family) { + case AF_INET: + init_addr_loopback4(ss, len); + return; + case AF_INET6: + init_addr_loopback6(ss, len); + return; + default: + FAIL("unsupported address family %d", family); + } +} + +static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss) +{ + return (struct sockaddr *)ss; +} + +static int enable_reuseport(int s, int progfd) +{ + int err, one = 1; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + if (err) + return -1; + err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd, + sizeof(progfd)); + if (err) + return -1; + + return 0; +} + +static int listen_loopback_reuseport(int family, int sotype, int progfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return -1; + + if (progfd >= 0) + enable_reuseport(s, progfd); + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + err = xlisten(s, SOMAXCONN); + if (err) + goto close; + + return s; +close: + xclose(s); + return -1; +} + +static int listen_loopback(int family, int sotype) +{ + return listen_loopback_reuseport(family, sotype, -1); +} + +static void test_insert_invalid(int family, int sotype, int mapfd) +{ + u32 key = 0; + u64 value; + int err; + + value = -1; + err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + if (!err || errno != EINVAL) + FAIL_ERRNO("map_update: expected EINVAL"); + + value = INT_MAX; + err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + if (!err || errno != EBADF) + FAIL_ERRNO("map_update: expected EBADF"); +} + +static void test_insert_opened(int family, int sotype, int mapfd) +{ + u32 key = 0; + u64 value; + int err, s; + + s = xsocket(family, sotype, 0); + if (s == -1) + return; + + errno = 0; + value = s; + err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + if (!err || errno != EOPNOTSUPP) + FAIL_ERRNO("map_update: expected EOPNOTSUPP"); + + xclose(s); +} + +static void test_insert_bound(int family, int sotype, int mapfd) +{ + struct sockaddr_storage addr; + socklen_t len; + u32 key = 0; + u64 value; + int err, s; + + init_addr_loopback(family, &addr, &len); + + s = xsocket(family, sotype, 0); + if (s == -1) + return; + + err = xbind(s, sockaddr(&addr), len); + if (err) + goto close; + + errno = 0; + value = s; + err = bpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + if (!err || errno != EOPNOTSUPP) + FAIL_ERRNO("map_update: expected EOPNOTSUPP"); +close: + xclose(s); +} + +static void test_insert_listening(int family, int sotype, int mapfd) +{ + u64 value; + u32 key; + int s; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + xclose(s); +} + +static void test_delete_after_insert(int family, int sotype, int mapfd) +{ + u64 value; + u32 key; + int s; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + xbpf_map_delete_elem(mapfd, &key); + xclose(s); +} + +static void test_delete_after_close(int family, int sotype, int mapfd) +{ + int err, s; + u64 value; + u32 key; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + + xclose(s); + + errno = 0; + err = bpf_map_delete_elem(mapfd, &key); + if (!err || (errno != EINVAL && errno != ENOENT)) + /* SOCKMAP and SOCKHASH return different error codes */ + FAIL_ERRNO("map_delete: expected EINVAL/EINVAL"); +} + +static void test_lookup_after_insert(int family, int sotype, int mapfd) +{ + u64 cookie, value; + socklen_t len; + u32 key; + int s; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + + len = sizeof(cookie); + xgetsockopt(s, SOL_SOCKET, SO_COOKIE, &cookie, &len); + + xbpf_map_lookup_elem(mapfd, &key, &value); + + if (value != cookie) { + FAIL("map_lookup: have %#llx, want %#llx", + (unsigned long long)value, (unsigned long long)cookie); + } + + xclose(s); +} + +static void test_lookup_after_delete(int family, int sotype, int mapfd) +{ + int err, s; + u64 value; + u32 key; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + xbpf_map_delete_elem(mapfd, &key); + + errno = 0; + err = bpf_map_lookup_elem(mapfd, &key, &value); + if (!err || errno != ENOENT) + FAIL_ERRNO("map_lookup: expected ENOENT"); + + xclose(s); +} + +static void test_lookup_32_bit_value(int family, int sotype, int mapfd) +{ + u32 key, value32; + int err, s; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + mapfd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(key), + sizeof(value32), 1, 0); + if (mapfd < 0) { + FAIL_ERRNO("map_create"); + goto close; + } + + key = 0; + value32 = s; + xbpf_map_update_elem(mapfd, &key, &value32, BPF_NOEXIST); + + errno = 0; + err = bpf_map_lookup_elem(mapfd, &key, &value32); + if (!err || errno != ENOSPC) + FAIL_ERRNO("map_lookup: expected ENOSPC"); + + xclose(mapfd); +close: + xclose(s); +} + +static void test_update_listening(int family, int sotype, int mapfd) +{ + int s1, s2; + u64 value; + u32 key; + + s1 = listen_loopback(family, sotype); + if (s1 < 0) + return; + + s2 = listen_loopback(family, sotype); + if (s2 < 0) + goto close_s1; + + key = 0; + value = s1; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + + value = s2; + xbpf_map_update_elem(mapfd, &key, &value, BPF_EXIST); + xclose(s2); +close_s1: + xclose(s1); +} + +/* Exercise the code path where we destroy child sockets that never + * got accept()'ed, aka orphans, when parent socket gets closed. + */ +static void test_destroy_orphan_child(int family, int sotype, int mapfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s, c; + u64 value; + u32 key; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + + c = xsocket(family, sotype, 0); + if (c == -1) + goto close_srv; + + xconnect(c, sockaddr(&addr), len); + xclose(c); +close_srv: + xclose(s); +} + +/* Perform a passive open after removing listening socket from SOCKMAP + * to ensure that callbacks get restored properly. + */ +static void test_clone_after_delete(int family, int sotype, int mapfd) +{ + struct sockaddr_storage addr; + socklen_t len; + int err, s, c; + u64 value; + u32 key; + + s = listen_loopback(family, sotype); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + key = 0; + value = s; + xbpf_map_update_elem(mapfd, &key, &value, BPF_NOEXIST); + xbpf_map_delete_elem(mapfd, &key); + + c = xsocket(family, sotype, 0); + if (c < 0) + goto close_srv; + + xconnect(c, sockaddr(&addr), len); + xclose(c); +close_srv: + xclose(s); +} + +/* Check that child socket that got created while parent was in a + * SOCKMAP, but got accept()'ed only after the parent has been removed + * from SOCKMAP, gets cloned without parent psock state or callbacks. + */ +static void test_accept_after_delete(int family, int sotype, int mapfd) +{ + struct sockaddr_storage addr; + const u32 zero = 0; + int err, s, c, p; + socklen_t len; + u64 value; + + s = listen_loopback(family, sotype); + if (s == -1) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + value = s; + err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST); + if (err) + goto close_srv; + + c = xsocket(family, sotype, 0); + if (c == -1) + goto close_srv; + + /* Create child while parent is in sockmap */ + err = xconnect(c, sockaddr(&addr), len); + if (err) + goto close_cli; + + /* Remove parent from sockmap */ + err = xbpf_map_delete_elem(mapfd, &zero); + if (err) + goto close_cli; + + p = xaccept(s, NULL, NULL); + if (p == -1) + goto close_cli; + + /* Check that child sk_user_data is not set */ + value = p; + xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST); + + xclose(p); +close_cli: + xclose(c); +close_srv: + xclose(s); +} + +/* Check that child socket that got created and accepted while parent + * was in a SOCKMAP is cloned without parent psock state or callbacks. + */ +static void test_accept_before_delete(int family, int sotype, int mapfd) +{ + struct sockaddr_storage addr; + const u32 zero = 0, one = 1; + int err, s, c, p; + socklen_t len; + u64 value; + + s = listen_loopback(family, sotype); + if (s == -1) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + value = s; + err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST); + if (err) + goto close_srv; + + c = xsocket(family, sotype, 0); + if (c == -1) + goto close_srv; + + /* Create & accept child while parent is in sockmap */ + err = xconnect(c, sockaddr(&addr), len); + if (err) + goto close_cli; + + p = xaccept(s, NULL, NULL); + if (p == -1) + goto close_cli; + + /* Check that child sk_user_data is not set */ + value = p; + xbpf_map_update_elem(mapfd, &one, &value, BPF_NOEXIST); + + xclose(p); +close_cli: + xclose(c); +close_srv: + xclose(s); +} + +struct connect_accept_ctx { + int sockfd; + unsigned int done; + unsigned int nr_iter; +}; + +static bool is_thread_done(struct connect_accept_ctx *ctx) +{ + return READ_ONCE(ctx->done); +} + +static void *connect_accept_thread(void *arg) +{ + struct connect_accept_ctx *ctx = arg; + struct sockaddr_storage addr; + int family, socktype; + socklen_t len; + int err, i, s; + + s = ctx->sockfd; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto done; + + len = sizeof(family); + err = xgetsockopt(s, SOL_SOCKET, SO_DOMAIN, &family, &len); + if (err) + goto done; + + len = sizeof(socktype); + err = xgetsockopt(s, SOL_SOCKET, SO_TYPE, &socktype, &len); + if (err) + goto done; + + for (i = 0; i < ctx->nr_iter; i++) { + int c, p; + + c = xsocket(family, socktype, 0); + if (c < 0) + break; + + err = xconnect(c, (struct sockaddr *)&addr, sizeof(addr)); + if (err) { + xclose(c); + break; + } + + p = xaccept(s, NULL, NULL); + if (p < 0) { + xclose(c); + break; + } + + xclose(p); + xclose(c); + } +done: + WRITE_ONCE(ctx->done, 1); + return NULL; +} + +static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) +{ + struct connect_accept_ctx ctx = { 0 }; + struct sockaddr_storage addr; + socklen_t len; + u32 zero = 0; + pthread_t t; + int err, s; + u64 value; + + s = listen_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close; + + ctx.sockfd = s; + ctx.nr_iter = 1000; + + err = xpthread_create(&t, NULL, connect_accept_thread, &ctx); + if (err) + goto close; + + value = s; + while (!is_thread_done(&ctx)) { + err = xbpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST); + if (err) + break; + + err = xbpf_map_delete_elem(mapfd, &zero); + if (err) + break; + } + + xpthread_join(t, NULL); +close: + xclose(s); +} + +static void *listen_thread(void *arg) +{ + struct sockaddr unspec = { AF_UNSPEC }; + struct connect_accept_ctx *ctx = arg; + int err, i, s; + + s = ctx->sockfd; + + for (i = 0; i < ctx->nr_iter; i++) { + err = xlisten(s, 1); + if (err) + break; + err = xconnect(s, &unspec, sizeof(unspec)); + if (err) + break; + } + + WRITE_ONCE(ctx->done, 1); + return NULL; +} + +static void test_race_insert_listen(int family, int socktype, int mapfd) +{ + struct connect_accept_ctx ctx = { 0 }; + const u32 zero = 0; + const int one = 1; + pthread_t t; + int err, s; + u64 value; + + s = xsocket(family, socktype, 0); + if (s < 0) + return; + + err = xsetsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)); + if (err) + goto close; + + ctx.sockfd = s; + ctx.nr_iter = 10000; + + err = pthread_create(&t, NULL, listen_thread, &ctx); + if (err) + goto close; + + value = s; + while (!is_thread_done(&ctx)) { + err = bpf_map_update_elem(mapfd, &zero, &value, BPF_NOEXIST); + /* Expecting EOPNOTSUPP before listen() */ + if (err && errno != EOPNOTSUPP) { + FAIL_ERRNO("map_update"); + break; + } + + err = bpf_map_delete_elem(mapfd, &zero); + /* Expecting no entry after unhash on connect(AF_UNSPEC) */ + if (err && errno != EINVAL && errno != ENOENT) { + FAIL_ERRNO("map_delete"); + break; + } + } + + xpthread_join(t, NULL); +close: + xclose(s); +} + +static void zero_verdict_count(int mapfd) +{ + unsigned int zero = 0; + int key; + + key = SK_DROP; + xbpf_map_update_elem(mapfd, &key, &zero, BPF_ANY); + key = SK_PASS; + xbpf_map_update_elem(mapfd, &key, &zero, BPF_ANY); +} + +enum redir_mode { + REDIR_INGRESS, + REDIR_EGRESS, +}; + +static const char *redir_mode_str(enum redir_mode mode) +{ + switch (mode) { + case REDIR_INGRESS: + return "ingress"; + case REDIR_EGRESS: + return "egress"; + default: + return "unknown"; + } +} + +static void redir_to_connected(int family, int sotype, int sock_mapfd, + int verd_mapfd, enum redir_mode mode) +{ + const char *log_prefix = redir_mode_str(mode); + struct sockaddr_storage addr; + int s, c0, c1, p0, p1; + unsigned int pass; + socklen_t len; + int err, n; + u64 value; + u32 key; + char b; + + zero_verdict_count(verd_mapfd); + + s = listen_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + c0 = xsocket(family, sotype, 0); + if (c0 < 0) + goto close_srv; + err = xconnect(c0, sockaddr(&addr), len); + if (err) + goto close_cli0; + + p0 = xaccept(s, NULL, NULL); + if (p0 < 0) + goto close_cli0; + + c1 = xsocket(family, sotype, 0); + if (c1 < 0) + goto close_peer0; + err = xconnect(c1, sockaddr(&addr), len); + if (err) + goto close_cli1; + + p1 = xaccept(s, NULL, NULL); + if (p1 < 0) + goto close_cli1; + + key = 0; + value = p0; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + goto close_peer1; + + key = 1; + value = p1; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + goto close_peer1; + + n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1); + if (n < 0) + FAIL_ERRNO("%s: write", log_prefix); + if (n == 0) + FAIL("%s: incomplete write", log_prefix); + if (n < 1) + goto close_peer1; + + key = SK_PASS; + err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass); + if (err) + goto close_peer1; + if (pass != 1) + FAIL("%s: want pass count 1, have %d", log_prefix, pass); + + n = read(c0, &b, 1); + if (n < 0) + FAIL_ERRNO("%s: read", log_prefix); + if (n == 0) + FAIL("%s: incomplete read", log_prefix); + +close_peer1: + xclose(p1); +close_cli1: + xclose(c1); +close_peer0: + xclose(p0); +close_cli0: + xclose(c0); +close_srv: + xclose(s); +} + +static void test_skb_redir_to_connected(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + int parser = bpf_program__fd(skel->progs.prog_skb_parser); + int verdict_map = bpf_map__fd(skel->maps.verdict_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return; + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + goto detach; + + redir_to_connected(family, sotype, sock_map, verdict_map, + REDIR_INGRESS); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT); +detach: + xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER); +} + +static void test_msg_redir_to_connected(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + int verdict_map = bpf_map__fd(skel->maps.verdict_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_MSG_VERDICT, 0); + if (err) + return; + + redir_to_connected(family, sotype, sock_map, verdict_map, REDIR_EGRESS); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT); +} + +static void redir_to_listening(int family, int sotype, int sock_mapfd, + int verd_mapfd, enum redir_mode mode) +{ + const char *log_prefix = redir_mode_str(mode); + struct sockaddr_storage addr; + int s, c, p, err, n; + unsigned int drop; + socklen_t len; + u64 value; + u32 key; + + zero_verdict_count(verd_mapfd); + + s = listen_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + c = xsocket(family, sotype, 0); + if (c < 0) + goto close_srv; + err = xconnect(c, sockaddr(&addr), len); + if (err) + goto close_cli; + + p = xaccept(s, NULL, NULL); + if (p < 0) + goto close_cli; + + key = 0; + value = s; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + goto close_peer; + + key = 1; + value = p; + err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); + if (err) + goto close_peer; + + n = write(mode == REDIR_INGRESS ? c : p, "a", 1); + if (n < 0 && errno != EACCES) + FAIL_ERRNO("%s: write", log_prefix); + if (n == 0) + FAIL("%s: incomplete write", log_prefix); + if (n < 1) + goto close_peer; + + key = SK_DROP; + err = xbpf_map_lookup_elem(verd_mapfd, &key, &drop); + if (err) + goto close_peer; + if (drop != 1) + FAIL("%s: want drop count 1, have %d", log_prefix, drop); + +close_peer: + xclose(p); +close_cli: + xclose(c); +close_srv: + xclose(s); +} + +static void test_skb_redir_to_listening(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + int parser = bpf_program__fd(skel->progs.prog_skb_parser); + int verdict_map = bpf_map__fd(skel->maps.verdict_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return; + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + goto detach; + + redir_to_listening(family, sotype, sock_map, verdict_map, + REDIR_INGRESS); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT); +detach: + xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER); +} + +static void test_msg_redir_to_listening(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + int verdict_map = bpf_map__fd(skel->maps.verdict_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_MSG_VERDICT, 0); + if (err) + return; + + redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT); +} + +static void test_reuseport_select_listening(int family, int sotype, + int sock_map, int verd_map, + int reuseport_prog) +{ + struct sockaddr_storage addr; + unsigned int pass; + int s, c, p, err; + socklen_t len; + u64 value; + u32 key; + + zero_verdict_count(verd_map); + + s = listen_loopback_reuseport(family, sotype, reuseport_prog); + if (s < 0) + return; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + key = 0; + value = s; + err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST); + if (err) + goto close_srv; + + c = xsocket(family, sotype, 0); + if (c < 0) + goto close_srv; + err = xconnect(c, sockaddr(&addr), len); + if (err) + goto close_cli; + + p = xaccept(s, NULL, NULL); + if (p < 0) + goto close_cli; + + key = SK_PASS; + err = xbpf_map_lookup_elem(verd_map, &key, &pass); + if (err) + goto close_peer; + if (pass != 1) + FAIL("want pass count 1, have %d", pass); + +close_peer: + xclose(p); +close_cli: + xclose(c); +close_srv: + xclose(s); +} + +static void test_reuseport_select_connected(int family, int sotype, + int sock_map, int verd_map, + int reuseport_prog) +{ + struct sockaddr_storage addr; + int s, c0, c1, p0, err; + unsigned int drop; + socklen_t len; + u64 value; + u32 key; + + zero_verdict_count(verd_map); + + s = listen_loopback_reuseport(family, sotype, reuseport_prog); + if (s < 0) + return; + + /* Populate sock_map[0] to avoid ENOENT on first connection */ + key = 0; + value = s; + err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST); + if (err) + goto close_srv; + + len = sizeof(addr); + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + goto close_srv; + + c0 = xsocket(family, sotype, 0); + if (c0 < 0) + goto close_srv; + + err = xconnect(c0, sockaddr(&addr), len); + if (err) + goto close_cli0; + + p0 = xaccept(s, NULL, NULL); + if (err) + goto close_cli0; + + /* Update sock_map[0] to redirect to a connected socket */ + key = 0; + value = p0; + err = xbpf_map_update_elem(sock_map, &key, &value, BPF_EXIST); + if (err) + goto close_peer0; + + c1 = xsocket(family, sotype, 0); + if (c1 < 0) + goto close_peer0; + + errno = 0; + err = connect(c1, sockaddr(&addr), len); + if (!err || errno != ECONNREFUSED) + FAIL_ERRNO("connect: expected ECONNREFUSED"); + + key = SK_DROP; + err = xbpf_map_lookup_elem(verd_map, &key, &drop); + if (err) + goto close_cli1; + if (drop != 1) + FAIL("want drop count 1, have %d", drop); + +close_cli1: + xclose(c1); +close_peer0: + xclose(p0); +close_cli0: + xclose(c0); +close_srv: + xclose(s); +} + +/* Check that redirecting across reuseport groups is not allowed. */ +static void test_reuseport_mixed_groups(int family, int sotype, int sock_map, + int verd_map, int reuseport_prog) +{ + struct sockaddr_storage addr; + int s1, s2, c, err; + unsigned int drop; + socklen_t len; + u64 value; + u32 key; + + zero_verdict_count(verd_map); + + /* Create two listeners, each in its own reuseport group */ + s1 = listen_loopback_reuseport(family, sotype, reuseport_prog); + if (s1 < 0) + return; + + s2 = listen_loopback_reuseport(family, sotype, reuseport_prog); + if (s2 < 0) + goto close_srv1; + + key = 0; + value = s1; + err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST); + if (err) + goto close_srv2; + + key = 1; + value = s2; + err = xbpf_map_update_elem(sock_map, &key, &value, BPF_NOEXIST); + + /* Connect to s2, reuseport BPF selects s1 via sock_map[0] */ + len = sizeof(addr); + err = xgetsockname(s2, sockaddr(&addr), &len); + if (err) + goto close_srv2; + + c = xsocket(family, sotype, 0); + if (c < 0) + goto close_srv2; + + err = connect(c, sockaddr(&addr), len); + if (err && errno != ECONNREFUSED) { + FAIL_ERRNO("connect: expected ECONNREFUSED"); + goto close_cli; + } + + /* Expect drop, can't redirect outside of reuseport group */ + key = SK_DROP; + err = xbpf_map_lookup_elem(verd_map, &key, &drop); + if (err) + goto close_cli; + if (drop != 1) + FAIL("want drop count 1, have %d", drop); + +close_cli: + xclose(c); +close_srv2: + xclose(s2); +close_srv1: + xclose(s1); +} + +#define TEST(fn) \ + { \ + fn, #fn \ + } + +static void test_ops_cleanup(const struct bpf_map *map) +{ + const struct bpf_map_def *def; + int err, mapfd; + u32 key; + + def = bpf_map__def(map); + mapfd = bpf_map__fd(map); + + for (key = 0; key < def->max_entries; key++) { + err = bpf_map_delete_elem(mapfd, &key); + if (err && errno != EINVAL && errno != ENOENT) + FAIL_ERRNO("map_delete: expected EINVAL/ENOENT"); + } +} + +static const char *family_str(sa_family_t family) +{ + switch (family) { + case AF_INET: + return "IPv4"; + case AF_INET6: + return "IPv6"; + default: + return "unknown"; + } +} + +static const char *map_type_str(const struct bpf_map *map) +{ + const struct bpf_map_def *def; + + def = bpf_map__def(map); + if (IS_ERR(def)) + return "invalid"; + + switch (def->type) { + case BPF_MAP_TYPE_SOCKMAP: + return "sockmap"; + case BPF_MAP_TYPE_SOCKHASH: + return "sockhash"; + default: + return "unknown"; + } +} + +static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, + int family, int sotype) +{ + const struct op_test { + void (*fn)(int family, int sotype, int mapfd); + const char *name; + } tests[] = { + /* insert */ + TEST(test_insert_invalid), + TEST(test_insert_opened), + TEST(test_insert_bound), + TEST(test_insert_listening), + /* delete */ + TEST(test_delete_after_insert), + TEST(test_delete_after_close), + /* lookup */ + TEST(test_lookup_after_insert), + TEST(test_lookup_after_delete), + TEST(test_lookup_32_bit_value), + /* update */ + TEST(test_update_listening), + /* races with insert/delete */ + TEST(test_destroy_orphan_child), + TEST(test_syn_recv_insert_delete), + TEST(test_race_insert_listen), + /* child clone */ + TEST(test_clone_after_delete), + TEST(test_accept_after_delete), + TEST(test_accept_before_delete), + }; + const char *family_name, *map_name; + const struct op_test *t; + char s[MAX_TEST_NAME]; + int map_fd; + + family_name = family_str(family); + map_name = map_type_str(map); + map_fd = bpf_map__fd(map); + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, + t->name); + + if (!test__start_subtest(s)) + continue; + + t->fn(family, sotype, map_fd); + test_ops_cleanup(map); + } +} + +static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, + int family, int sotype) +{ + const struct redir_test { + void (*fn)(struct test_sockmap_listen *skel, + struct bpf_map *map, int family, int sotype); + const char *name; + } tests[] = { + TEST(test_skb_redir_to_connected), + TEST(test_skb_redir_to_listening), + TEST(test_msg_redir_to_connected), + TEST(test_msg_redir_to_listening), + }; + const char *family_name, *map_name; + const struct redir_test *t; + char s[MAX_TEST_NAME]; + + family_name = family_str(family); + map_name = map_type_str(map); + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, + t->name); + if (!test__start_subtest(s)) + continue; + + t->fn(skel, map, family, sotype); + } +} + +static void test_reuseport(struct test_sockmap_listen *skel, + struct bpf_map *map, int family, int sotype) +{ + const struct reuseport_test { + void (*fn)(int family, int sotype, int socket_map, + int verdict_map, int reuseport_prog); + const char *name; + } tests[] = { + TEST(test_reuseport_select_listening), + TEST(test_reuseport_select_connected), + TEST(test_reuseport_mixed_groups), + }; + int socket_map, verdict_map, reuseport_prog; + const char *family_name, *map_name; + const struct reuseport_test *t; + char s[MAX_TEST_NAME]; + + family_name = family_str(family); + map_name = map_type_str(map); + + socket_map = bpf_map__fd(map); + verdict_map = bpf_map__fd(skel->maps.verdict_map); + reuseport_prog = bpf_program__fd(skel->progs.prog_reuseport); + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, + t->name); + + if (!test__start_subtest(s)) + continue; + + t->fn(family, sotype, socket_map, verdict_map, reuseport_prog); + } +} + +static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map, + int family) +{ + test_ops(skel, map, family, SOCK_STREAM); + test_redir(skel, map, family, SOCK_STREAM); + test_reuseport(skel, map, family, SOCK_STREAM); +} + +void test_sockmap_listen(void) +{ + struct test_sockmap_listen *skel; + + skel = test_sockmap_listen__open_and_load(); + if (!skel) { + FAIL("skeleton open/load failed"); + return; + } + + skel->bss->test_sockmap = true; + run_tests(skel, skel->maps.sock_map, AF_INET); + run_tests(skel, skel->maps.sock_map, AF_INET6); + + skel->bss->test_sockmap = false; + run_tests(skel, skel->maps.sock_hash, AF_INET); + run_tests(skel, skel->maps.sock_hash, AF_INET6); + + test_sockmap_listen__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 1f6ccdaed1ac..781c8d11604b 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -55,31 +55,40 @@ void test_trampoline_count(void) /* attach 'allowed' 40 trampoline programs */ for (i = 0; i < MAX_TRAMP_PROGS; i++) { obj = bpf_object__open_file(object, NULL); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) { + obj = NULL; goto cleanup; + } err = bpf_object__load(obj); if (CHECK(err, "obj_load", "err %d\n", err)) goto cleanup; inst[i].obj = obj; + obj = NULL; if (rand() % 2) { - link = load(obj, fentry_name); - if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + link = load(inst[i].obj, fentry_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) { + link = NULL; goto cleanup; + } inst[i].link_fentry = link; } else { - link = load(obj, fexit_name); - if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) + link = load(inst[i].obj, fexit_name); + if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) { + link = NULL; goto cleanup; + } inst[i].link_fexit = link; } } /* and try 1 extra.. */ obj = bpf_object__open_file(object, NULL); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) { + obj = NULL; goto cleanup; + } err = bpf_object__load(obj); if (CHECK(err, "obj_load", "err %d\n", err)) @@ -104,7 +113,9 @@ void test_trampoline_count(void) cleanup_extra: bpf_object__close(obj); cleanup: - while (--i) { + if (i >= MAX_TRAMP_PROGS) + i = MAX_TRAMP_PROGS - 1; + for (; i >= 0; i--) { bpf_link__destroy(inst[i].link_fentry); bpf_link__destroy(inst[i].link_fexit); bpf_object__close(inst[i].obj); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index 6b56bdc73ebc..4ba011031d4c 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -14,7 +14,7 @@ void test_xdp_bpf2bpf(void) struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; struct vip key4 = {.protocol = 6, .family = AF_INET}; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts); + struct bpf_program *prog; /* Load XDP program to introspect */ pkt_skel = test_xdp__open_and_load(); @@ -27,11 +27,21 @@ void test_xdp_bpf2bpf(void) bpf_map_update_elem(map_fd, &key4, &value4, 0); /* Load trace program */ - opts.attach_prog_fd = pkt_fd, - ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts); + ftrace_skel = test_xdp_bpf2bpf__open(); if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n")) goto out; + /* Demonstrate the bpf_program__set_attach_target() API rather than + * the load with options, i.e. opts.attach_prog_fd. + */ + prog = ftrace_skel->progs.trace_on_entry; + bpf_program__set_expected_attach_type(prog, BPF_TRACE_FENTRY); + bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); + + prog = ftrace_skel->progs.trace_on_exit; + bpf_program__set_expected_attach_type(prog, BPF_TRACE_FEXIT); + bpf_program__set_attach_target(prog, pkt_fd, "_xdp_tx_iptunnel"); + err = test_xdp_bpf2bpf__load(ftrace_skel); if (CHECK(err, "__load", "ftrace skeleton failed\n")) goto out; diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c new file mode 100644 index 000000000000..0f7e27d97567 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook + +#include <stddef.h> +#include <linux/ptrace.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_trace_helpers.h" + +int valid = 0; +int required_size_out = 0; +int written_stack_out = 0; +int written_global_out = 0; + +struct { + __u64 _a; + __u64 _b; + __u64 _c; +} fpbe[30] = {0}; + +SEC("perf_event") +int perf_branches(void *ctx) +{ + __u64 entries[4 * 3] = {0}; + int required_size, written_stack, written_global; + + /* write to stack */ + written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0); + /* ignore spurious events */ + if (!written_stack) + return 1; + + /* get required size */ + required_size = bpf_read_branch_records(ctx, NULL, 0, + BPF_F_GET_BRANCH_RECORDS_SIZE); + + written_global = bpf_read_branch_records(ctx, fpbe, sizeof(fpbe), 0); + /* ignore spurious events */ + if (!written_global) + return 1; + + required_size_out = required_size; + written_stack_out = written_stack; + written_global_out = written_global; + valid = 1; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c new file mode 100644 index 000000000000..a3a366c57ce1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2020 Cloudflare + +#include <errno.h> +#include <stdbool.h> +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, __u64); +} sock_hash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, int); + __type(value, unsigned int); +} verdict_map SEC(".maps"); + +static volatile bool test_sockmap; /* toggled by user-space */ + +SEC("sk_skb/stream_parser") +int prog_skb_parser(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict(struct __sk_buff *skb) +{ + unsigned int *count; + __u32 zero = 0; + int verdict; + + if (test_sockmap) + verdict = bpf_sk_redirect_map(skb, &sock_map, zero, 0); + else + verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero, 0); + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +SEC("sk_msg") +int prog_msg_verdict(struct sk_msg_md *msg) +{ + unsigned int *count; + __u32 zero = 0; + int verdict; + + if (test_sockmap) + verdict = bpf_msg_redirect_map(msg, &sock_map, zero, 0); + else + verdict = bpf_msg_redirect_hash(msg, &sock_hash, &zero, 0); + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +SEC("sk_reuseport") +int prog_reuseport(struct sk_reuseport_md *reuse) +{ + unsigned int *count; + int err, verdict; + __u32 zero = 0; + + if (test_sockmap) + err = bpf_sk_select_reuseport(reuse, &sock_map, &zero, 0); + else + err = bpf_sk_select_reuseport(reuse, &sock_hash, &zero, 0); + verdict = err ? SK_DROP : SK_PASS; + + count = bpf_map_lookup_elem(&verdict_map, &verdict); + if (count) + (*count)++; + + return verdict; +} + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c index cb8a04ab7a78..b840fc9e3ed5 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c @@ -28,7 +28,7 @@ struct xdp_buff { } __attribute__((preserve_access_index)); __u64 test_result_fentry = 0; -SEC("fentry/_xdp_tx_iptunnel") +SEC("fentry/FUNC") int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) { test_result_fentry = xdp->rxq->dev->ifindex; @@ -36,7 +36,7 @@ int BPF_PROG(trace_on_entry, struct xdp_buff *xdp) } __u64 test_result_fexit = 0; -SEC("fexit/_xdp_tx_iptunnel") +SEC("fexit/FUNC") int BPF_PROG(trace_on_exit, struct xdp_buff *xdp, int ret) { test_result_fexit = ret; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 02eae1e864c2..c6766b2cff85 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -756,11 +756,7 @@ static void test_sockmap(unsigned int tasks, void *data) /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (i < 2 && !err) { - printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n", - i, sfd[i]); - goto out_sockmap; - } else if (i >= 2 && err) { + if (err) { printf("Failed noprog update sockmap '%i:%i'\n", i, sfd[i]); goto out_sockmap; diff --git a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh index 5ba5bef44d5b..bdffe698e1d1 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh @@ -45,6 +45,7 @@ ALL_TESTS=" blackhole_ipv6 " NUM_NETIFS=4 +: ${TIMEOUT:=20000} # ms source $lib_dir/tc_common.sh source $lib_dir/lib.sh @@ -123,7 +124,7 @@ blackhole_ipv4() skip_hw dst_ip 198.51.100.1 src_ip 192.0.2.1 ip_proto icmp \ action pass - ip -4 route show 198.51.100.0/30 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip -4 route show 198.51.100.0/30 check_err $? "route not marked as offloaded when should" ping_do $h1 198.51.100.1 @@ -147,7 +148,7 @@ blackhole_ipv6() skip_hw dst_ip 2001:db8:2::1 src_ip 2001:db8:1::1 \ ip_proto icmpv6 action pass - ip -6 route show 2001:db8:2::/120 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip -6 route show 2001:db8:2::/120 check_err $? "route not marked as offloaded when should" ping6_do $h1 2001:db8:2::1 diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh new file mode 100755 index 000000000000..26044e397157 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_acl_drops.sh @@ -0,0 +1,151 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test devlink-trap ACL drops functionality over mlxsw. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ingress_flow_action_drop_test + egress_flow_action_drop_test +" +NUM_NETIFS=4 +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +h1_create() +{ + simple_if_init $h1 +} + +h1_destroy() +{ + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 +} + +h2_destroy() +{ + simple_if_fini $h2 +} + +switch_create() +{ + ip link add dev br0 type bridge vlan_filtering 1 mcast_snooping 0 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + tc qdisc add dev $swp2 clsact +} + +switch_destroy() +{ + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +ingress_flow_action_drop_test() +{ + local mz_pid + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower src_mac $h1mac action pass + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 \ + flower dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -d 1msec -q & + mz_pid=$! + + RET=0 + + devlink_trap_drop_test ingress_flow_action_drop acl_drops $swp2 101 + + log_test "ingress_flow_action_drop" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 +} + +egress_flow_action_drop_test() +{ + local mz_pid + + tc filter add dev $swp2 egress protocol ip pref 2 handle 102 \ + flower src_mac $h1mac action pass + + tc filter add dev $swp2 egress protocol ip pref 1 handle 101 \ + flower dst_ip 192.0.2.2 action drop + + $MZ $h1 -c 0 -p 100 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -d 1msec -q & + mz_pid=$! + + RET=0 + + devlink_trap_drop_test egress_flow_action_drop acl_drops $swp2 102 + + log_test "egress_flow_action_drop" + + tc filter del dev $swp2 egress protocol ip pref 1 handle 101 flower + + devlink_trap_drop_cleanup $mz_pid $swp2 ip 2 102 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh index 58cdbfb608e9..e7aecb065409 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh @@ -107,11 +107,11 @@ source_mac_is_multicast_test() RET=0 - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 log_test "Source MAC is multicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } __vlan_tag_mismatch_test() @@ -132,7 +132,7 @@ __vlan_tag_mismatch_test() $MZ $h1 "$opt" -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Add PVID and make sure packets are no longer dropped. bridge vlan add vid 1 dev $swp1 pvid untagged master @@ -148,7 +148,7 @@ __vlan_tag_mismatch_test() devlink_trap_action_set $trap_name "drop" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } vlan_tag_mismatch_untagged_test() @@ -193,7 +193,7 @@ ingress_vlan_filter_test() $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Add the VLAN on the bridge port and make sure packets are no longer # dropped. @@ -212,7 +212,7 @@ ingress_vlan_filter_test() log_test "Ingress VLAN filter" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 bridge vlan del vid $vid dev $swp1 master bridge vlan del vid $vid dev $swp2 master @@ -237,7 +237,7 @@ __ingress_stp_filter_test() $MZ $h1 -Q $vid -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Change STP state to forwarding and make sure packets are no longer # dropped. @@ -254,7 +254,7 @@ __ingress_stp_filter_test() devlink_trap_action_set $trap_name "drop" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 bridge vlan del vid $vid dev $swp1 master bridge vlan del vid $vid dev $swp2 master @@ -308,7 +308,7 @@ port_list_is_empty_uc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded to one port. ip link set dev $swp2 type bridge_slave flood on @@ -326,7 +326,7 @@ port_list_is_empty_uc_test() log_test "Port list is empty - unicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 ip link set dev $swp1 type bridge_slave flood on } @@ -354,7 +354,7 @@ port_list_is_empty_mc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded to one port. ip link set dev $swp2 type bridge_slave mcast_flood on @@ -372,7 +372,7 @@ port_list_is_empty_mc_test() log_test "Port list is empty - multicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 ip link set dev $swp1 type bridge_slave mcast_flood on } @@ -401,7 +401,7 @@ port_loopback_filter_uc_test() $MZ $h1 -c 0 -p 100 -a own -b $dmac -t ip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp2 + devlink_trap_drop_test $trap_name $group_name $swp2 101 # Allow packets to be flooded. ip link set dev $swp2 type bridge_slave flood on @@ -419,7 +419,7 @@ port_loopback_filter_uc_test() log_test "Port loopback filter - unicast" - devlink_trap_drop_cleanup $mz_pid $swp2 ip + devlink_trap_drop_cleanup $mz_pid $swp2 ip 1 101 } port_loopback_filter_test() diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index d88d8e47d11b..616f47d86a61 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -176,11 +176,11 @@ non_ip_test() 00:00 de:ad:be:ef" & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Non IP" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } __uc_dip_over_mc_dmac_test() @@ -206,11 +206,11 @@ __uc_dip_over_mc_dmac_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Unicast destination IP over multicast destination MAC: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } uc_dip_over_mc_dmac_test() @@ -242,11 +242,11 @@ __sip_is_loopback_test() -b $rp1mac -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Source IP is loopback address: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } sip_is_loopback_test() @@ -277,11 +277,11 @@ __dip_is_loopback_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Destination IP is loopback address: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } dip_is_loopback_test() @@ -313,11 +313,11 @@ __sip_is_mc_test() -b $rp1mac -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Source IP is multicast: $desc" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 } sip_is_mc_test() @@ -345,11 +345,11 @@ ipv4_sip_is_limited_bc_test() -B $h2_ipv4 -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv4 source IP is limited broadcast" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ipv4_payload_get() @@ -399,11 +399,11 @@ __ipv4_header_corrupted_test() $MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IP header corrupted: $desc: IPv4" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ipv6_payload_get() @@ -446,11 +446,11 @@ __ipv6_header_corrupted_test() $MZ $h1 -c 0 -d 1msec -a $h1mac -b $rp1mac -q p=$payload & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IP header corrupted: $desc: IPv6" - devlink_trap_drop_cleanup $mz_pid $rp2 "ip" + devlink_trap_drop_cleanup $mz_pid $rp2 "ip" 1 101 } ip_header_corrupted_test() @@ -485,11 +485,11 @@ ipv6_mc_dip_reserved_scope_test() "33:33:00:00:00:00" -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv6 multicast destination IP reserved scope" - devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" + devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101 } ipv6_mc_dip_interface_local_scope_test() @@ -511,11 +511,11 @@ ipv6_mc_dip_interface_local_scope_test() "33:33:00:00:00:00" -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "IPv6 multicast destination IP interface-local scope" - devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" + devlink_trap_drop_cleanup $mz_pid $rp2 "ipv6" 1 101 } __blackhole_route_test() @@ -542,10 +542,10 @@ __blackhole_route_test() -B $dip -d 1msec -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $rp2 + devlink_trap_drop_test $trap_name $group_name $rp2 101 log_test "Blackhole route: IPv$flags" - devlink_trap_drop_cleanup $mz_pid $rp2 $proto + devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101 ip -$flags route del blackhole $subnet } @@ -641,13 +641,9 @@ erif_disabled_test() mz_pid=$! sleep 5 - # In order to see this trap we need a route that points to disabled RIF. - # When ipv6 address is flushed, there is a delay and the routes are - # deleted before the RIF and we cannot get state that we have route - # to disabled RIF. - # Delete IPv6 address first and then check this trap with flushing IPv4. - ip -6 add flush dev br0 - ip -4 add flush dev br0 + # Unlinking the port from the bridge will disable the RIF associated + # with br0 as it is no longer an upper of any mlxsw port. + ip link set dev $rp1 nomaster t1_packets=$(devlink_trap_rx_packets_get $trap_name) t1_bytes=$(devlink_trap_rx_bytes_get $trap_name) @@ -659,7 +655,6 @@ erif_disabled_test() log_test "Egress RIF disabled" kill $mz_pid && wait $mz_pid &> /dev/null - ip link set dev $rp1 nomaster __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge devlink_trap_action_set $trap_name "drop" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index fd19161dd4ec..e11a416323cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -314,11 +314,11 @@ overlay_smac_is_mc_test() -B 192.0.2.17 -t udp sp=12345,dp=$VXPORT,p=$payload -q & mz_pid=$! - devlink_trap_drop_test $trap_name $group_name $swp1 + devlink_trap_drop_test $trap_name $group_name $swp1 101 log_test "Overlay source MAC is multicast" - devlink_trap_drop_cleanup $mz_pid $swp1 "ip" + devlink_trap_drop_cleanup $mz_pid $swp1 "ip" 1 101 } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh index d72d8488a3b2..7a0a99c1d22f 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh @@ -8,7 +8,8 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS=" netdev_pre_up_test vxlan_vlan_add_test - port_vlan_add_test + vxlan_bridge_create_test + bridge_create_test " NUM_NETIFS=2 source $lib_dir/lib.sh @@ -106,32 +107,56 @@ vxlan_vlan_add_test() ip link del dev br1 } -port_vlan_add_test() +vxlan_bridge_create_test() { RET=0 - ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 - # Unsupported configuration: mlxsw demands VXLAN with "noudpcsum". ip link add name vx1 up type vxlan id 1000 \ local 192.0.2.17 remote 192.0.2.18 \ dstport 4789 tos inherit ttl 100 - ip link set dev $swp1 master br1 - check_err $? - - bridge vlan del dev $swp1 vid 1 + # Test with VLAN-aware bridge. + ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0 ip link set dev vx1 master br1 + + ip link set dev $swp1 master br1 2>&1 > /dev/null \ + | grep -q mlxsw_spectrum check_err $? - bridge vlan add dev $swp1 vid 1 pvid untagged 2>&1 >/dev/null \ + # Test with VLAN-unaware bridge. + ip link set dev br1 type bridge vlan_filtering 0 + + ip link set dev $swp1 master br1 2>&1 > /dev/null \ | grep -q mlxsw_spectrum check_err $? - log_test "extack - map VLAN at port" + log_test "extack - bridge creation with VXLAN" + ip link del dev br1 ip link del dev vx1 +} + +bridge_create_test() +{ + RET=0 + + ip link add name br1 up type bridge vlan_filtering 1 + ip link add name br2 up type bridge vlan_filtering 1 + + ip link set dev $swp1 master br1 + check_err $? + + # Only one VLAN-aware bridge is supported, so this should fail with + # an extack. + ip link set dev $swp2 master br2 2>&1 > /dev/null \ + | grep -q mlxsw_spectrum + check_err $? + + log_test "extack - multiple VLAN-aware bridges creation" + + ip link del dev br2 ip link del dev br1 } diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh new file mode 100644 index 000000000000..cbe50f260a40 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh @@ -0,0 +1,13 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +############################################################################## +# Defines + +if [[ ! -v MLXSW_CHIP ]]; then + MLXSW_CHIP=$(devlink -j dev info $DEVLINK_DEV | jq -r '.[][]["driver"]') + if [ -z "$MLXSW_CHIP" ]; then + echo "SKIP: Device $DEVLINK_DEV doesn't support devlink info command" + exit 1 + fi +fi diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh index d231649b4f01..e93878d42596 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh @@ -2,16 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 ROUTER_NUM_NETIFS=4 +: ${TIMEOUT:=20000} # ms router_h1_create() { simple_if_init $h1 192.0.1.1/24 - ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1 } router_h1_destroy() { - ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1 simple_if_fini $h1 192.0.1.1/24 } @@ -64,13 +63,15 @@ router_setup_prepare() router_create } -router_offload_validate() +wait_for_routes() { - local route_count=$1 - local offloaded_count + local t0=$1; shift + local route_count=$1; shift - offloaded_count=$(ip route | grep -o 'offload' | wc -l) - [[ $offloaded_count -ge $route_count ]] + local t1=$(ip route | grep -o 'offload' | wc -l) + local delta=$((t1 - t0)) + echo $delta + [[ $delta -ge $route_count ]] } router_routes_create() @@ -90,8 +91,8 @@ router_routes_create() break 3 fi - echo route add 193.${i}.${j}.${k}/32 via \ - 192.0.2.1 dev $rp2 >> $ROUTE_FILE + echo route add 193.${i}.${j}.${k}/32 dev $rp2 \ + >> $ROUTE_FILE ((count++)) done done @@ -111,45 +112,19 @@ router_test() { local route_count=$1 local should_fail=$2 - local count=0 + local delta RET=0 + local t0=$(ip route | grep -o 'offload' | wc -l) router_routes_create $route_count + delta=$(busywait "$TIMEOUT" wait_for_routes $t0 $route_count) - router_offload_validate $route_count - check_err_fail $should_fail $? "Offload of $route_count routes" + check_err_fail $should_fail $? "Offload routes: Expected $route_count, got $delta." if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then return fi - tc filter add dev $h2 ingress protocol ip pref 1 flower \ - skip_sw dst_ip 193.0.0.0/8 action drop - - for i in {0..255} - do - for j in {0..255} - do - for k in {0..255} - do - if [[ $count -eq $route_count ]]; then - break 3 - fi - - $MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \ - -A 192.0.1.1 -B 193.${i}.${j}.${k} \ - -t ip -q - ((count++)) - done - done - done - - tc_check_packets "dev $h2 ingress" 1 $route_count - check_err $? "Offload mismatch" - - tc filter del dev $h2 ingress protocol ip pref 1 flower \ - skip_sw dst_ip 193.0.0.0/8 action drop - router_routes_destroy } diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index 5c39e5f6a480..f4031002d5e9 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -32,6 +32,7 @@ ALL_TESTS=" devlink_reload_test " NUM_NETIFS=2 +: ${TIMEOUT:=20000} # ms source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh @@ -360,20 +361,24 @@ vlan_rif_refcount_test() ip link add link br0 name br0.10 up type vlan id 10 ip -6 address add 2001:db8:1::1/64 dev br0.10 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was not created before adding port to vlan" bridge vlan add vid 10 dev $swp1 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was destroyed after adding port to vlan" bridge vlan del vid 10 dev $swp1 - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 check_err $? "vlan rif was destroyed after removing port from vlan" ip link set dev $swp1 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload - check_fail $? "vlan rif was not destroyed after unlinking port from bridge" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 + check_err $? "vlan rif was not destroyed after unlinking port from bridge" log_test "vlan rif refcount" @@ -401,22 +406,28 @@ subport_rif_refcount_test() ip -6 address add 2001:db8:1::1/64 dev bond1 ip -6 address add 2001:db8:2::1/64 dev bond1.10 - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 check_err $? "subport rif was not created on lag device" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 check_err $? "subport rif was not created on vlan device" ip link set dev $swp1 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 check_err $? "subport rif of lag device was destroyed when should not" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 check_err $? "subport rif of vlan device was destroyed when should not" ip link set dev $swp2 nomaster - ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload - check_fail $? "subport rif of lag device was not destroyed when should" - ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload - check_fail $? "subport rif of vlan device was not destroyed when should" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:1::2 dev bond1 + check_err $? "subport rif of lag device was not destroyed when should" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 + check_err $? "subport rif of vlan device was not destroyed when should" log_test "subport rif refcount" @@ -575,7 +586,8 @@ bridge_extern_learn_test() bridge fdb add de:ad:be:ef:13:37 dev $swp1 master extern_learn - bridge fdb show brport $swp1 | grep de:ad:be:ef:13:37 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + bridge fdb show brport $swp1 de:ad:be:ef:13:37 check_err $? "fdb entry not marked as offloaded when should" log_test "externally learned fdb entry" @@ -595,9 +607,11 @@ neigh_offload_test() ip -6 neigh add 2001:db8:1::2 lladdr de:ad:be:ef:13:37 nud perm \ dev $swp1 - ip -4 neigh show dev $swp1 | grep 192.0.2.2 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 neigh show dev $swp1 192.0.2.2 check_err $? "ipv4 neigh entry not marked as offloaded when should" - ip -6 neigh show dev $swp1 | grep 2001:db8:1::2 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 neigh show dev $swp1 2001:db8:1::2 check_err $? "ipv6 neigh entry not marked as offloaded when should" log_test "neighbour offload indication" @@ -623,25 +637,31 @@ nexthop_offload_test() ip -6 route add 2001:db8:2::/64 vrf v$swp1 \ nexthop via 2001:db8:1::2 dev $swp1 - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 check_err $? "ipv4 nexthop not marked as offloaded when should" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 check_err $? "ipv6 nexthop not marked as offloaded when should" ip link set dev $swp2 down sleep 1 - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload - check_fail $? "ipv4 nexthop marked as offloaded when should not" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload - check_fail $? "ipv6 nexthop marked as offloaded when should not" + busywait "$TIMEOUT" not wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 + check_err $? "ipv4 nexthop marked as offloaded when should not" + busywait "$TIMEOUT" not wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 + check_err $? "ipv6 nexthop marked as offloaded when should not" ip link set dev $swp2 up setup_wait - ip -4 route show 198.51.100.0/24 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -4 route show 198.51.100.0/24 vrf v$swp1 check_err $? "ipv4 nexthop not marked as offloaded after neigh add" - ip -6 route show 2001:db8:2::/64 vrf v$swp1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip -6 route show 2001:db8:2::/64 vrf v$swp1 check_err $? "ipv6 nexthop not marked as offloaded after neigh add" log_test "nexthop offload indication" diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh new file mode 100644 index 000000000000..ebf7752f6d93 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh @@ -0,0 +1,499 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This test sends a >1Gbps stream of traffic from H1, to the switch, which +# forwards it to a 1Gbps port. This 1Gbps stream is then looped back to the +# switch and forwarded to the port under test $swp3, which is also 1Gbps. +# +# This way, $swp3 should be 100% filled with traffic without any of it spilling +# to the backlog. Any extra packets sent should almost 1:1 go to backlog. That +# is what H2 is used for--it sends the extra traffic to create backlog. +# +# A RED Qdisc is installed on $swp3. The configuration is such that the minimum +# and maximum size are 1 byte apart, so there is a very clear border under which +# no marking or dropping takes place, and above which everything is marked or +# dropped. +# +# The test uses the buffer build-up behavior to test the installed RED. +# +# In order to test WRED, $swp3 actually contains RED under PRIO, with two +# different configurations. Traffic is prioritized using 802.1p and relies on +# the implicit mlxsw configuration, where packet priority is taken 1:1 from the +# 802.1p marking. +# +# +--------------------------+ +--------------------------+ +# | H1 | | H2 | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | | | | | +# | | $h1.11 + | | | $h2.11 + | +# | | 192.0.2.17/28 | | | | 192.0.2.18/28 | | +# | | | | | | | | +# | \______ ______/ | | \______ ______/ | +# | \ / | | \ / | +# | + $h1 | | + $h2 | +# +-------------|------------+ +-------------|------------+ +# | >1Gbps | +# +-------------|------------------------------------------------|------------+ +# | SW + $swp1 + $swp2 | +# | _______/ \___________ ___________/ \_______ | +# | / \ / \ | +# | +-|-----------------+ | +-|-----------------+ | | +# | | + $swp1.10 | | | + $swp2.10 | | | +# | | | | .-------------+ $swp5.10 | | | +# | | BR1_10 | | | | | | | +# | | | | | | BR2_10 | | | +# | | + $swp2.10 | | | | | | | +# | +-|-----------------+ | | | + $swp3.10 | | | +# | | | | +-|-----------------+ | | +# | | +-----------------|-+ | | +-----------------|-+ | +# | | | $swp1.11 + | | | | $swp2.11 + | | +# | | | | | .-----------------+ $swp5.11 | | +# | | | BR1_11 | | | | | | | +# | | | | | | | | BR2_11 | | +# | | | $swp2.11 + | | | | | | | +# | | +-----------------|-+ | | | | $swp3.11 + | | +# | | | | | | +-----------------|-+ | +# | \_______ ___________/ | | \___________ _______/ | +# | \ / \ / \ / | +# | + $swp4 + $swp5 + $swp3 | +# +-------------|----------------------|-------------------------|------------+ +# | | | 1Gbps +# \________1Gbps_________/ | +# +----------------------------|------------+ +# | H3 + $h3 | +# | _____________________/ \_______ | +# | / \ | +# | | | | +# | + $h3.10 $h3.11 + | +# | 192.0.2.3/28 192.0.2.19/28 | +# +-----------------------------------------+ + +NUM_NETIFS=8 +CHECK_TC="yes" +lib_dir=$(dirname $0)/../../../net/forwarding +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh +source qos_lib.sh + +ipaddr() +{ + local host=$1; shift + local vlan=$1; shift + + echo 192.0.2.$((16 * (vlan - 10) + host)) +} + +host_create() +{ + local dev=$1; shift + local host=$1; shift + + simple_if_init $dev + mtu_set $dev 10000 + + vlan_create $dev 10 v$dev $(ipaddr $host 10)/28 + ip link set dev $dev.10 type vlan egress 0:0 + + vlan_create $dev 11 v$dev $(ipaddr $host 11)/28 + ip link set dev $dev.11 type vlan egress 0:1 +} + +host_destroy() +{ + local dev=$1; shift + + vlan_destroy $dev 11 + vlan_destroy $dev 10 + mtu_restore $dev + simple_if_fini $dev +} + +h1_create() +{ + host_create $h1 1 +} + +h1_destroy() +{ + host_destroy $h1 +} + +h2_create() +{ + host_create $h2 2 + + # Some of the tests in this suite use multicast traffic. As this traffic + # enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus + # e.g. traffic ingressing through $swp2 is flooded to $swp3 (the + # intended destination) and $swp5 (which is intended as ingress for + # another stream of traffic). + # + # This is generally not a problem, but if the $swp5 throughput is lower + # than $swp2 throughput, there will be a build-up at $swp5. That may + # cause packets to fail to queue up at $swp3 due to shared buffer + # quotas, and the test to spuriously fail. + # + # Prevent this by setting the speed of $h2 to 1Gbps. + + ethtool -s $h2 speed 1000 autoneg off +} + +h2_destroy() +{ + ethtool -s $h2 autoneg on + host_destroy $h2 +} + +h3_create() +{ + host_create $h3 3 + ethtool -s $h3 speed 1000 autoneg off +} + +h3_destroy() +{ + ethtool -s $h3 autoneg on + host_destroy $h3 +} + +switch_create() +{ + local intf + local vlan + + ip link add dev br1_10 type bridge + ip link add dev br1_11 type bridge + + ip link add dev br2_10 type bridge + ip link add dev br2_11 type bridge + + for intf in $swp1 $swp2 $swp3 $swp4 $swp5; do + ip link set dev $intf up + mtu_set $intf 10000 + done + + for intf in $swp1 $swp4; do + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br1_$vlan + ip link set dev $intf.$vlan up + done + done + + for intf in $swp2 $swp3 $swp5; do + for vlan in 10 11; do + vlan_create $intf $vlan + ip link set dev $intf.$vlan master br2_$vlan + ip link set dev $intf.$vlan up + done + done + + ip link set dev $swp4.10 type vlan egress 0:0 + ip link set dev $swp4.11 type vlan egress 0:1 + for intf in $swp1 $swp2 $swp5; do + for vlan in 10 11; do + ip link set dev $intf.$vlan type vlan ingress 0:0 1:1 + done + done + + for intf in $swp2 $swp3 $swp4 $swp5; do + ethtool -s $intf speed 1000 autoneg off + done + + ip link set dev br1_10 up + ip link set dev br1_11 up + ip link set dev br2_10 up + ip link set dev br2_11 up + + local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1) + devlink_port_pool_th_set $swp3 8 $size +} + +switch_destroy() +{ + local intf + local vlan + + devlink_port_pool_th_restore $swp3 8 + + tc qdisc del dev $swp3 root 2>/dev/null + + ip link set dev br2_11 down + ip link set dev br2_10 down + ip link set dev br1_11 down + ip link set dev br1_10 down + + for intf in $swp5 $swp4 $swp3 $swp2; do + ethtool -s $intf autoneg on + done + + for intf in $swp5 $swp3 $swp2 $swp4 $swp1; do + for vlan in 11 10; do + ip link set dev $intf.$vlan down + ip link set dev $intf.$vlan nomaster + vlan_destroy $intf $vlan + done + + mtu_restore $intf + ip link set dev $intf down + done + + ip link del dev br2_11 + ip link del dev br2_10 + ip link del dev br1_11 + ip link del dev br1_10 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + swp4=${NETIFS[p7]} + swp5=${NETIFS[p8]} + + h3_mac=$(mac_get $h3) + + vrf_prepare + + h1_create + h2_create + h3_create + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1.10 $(ipaddr 3 10) " from host 1, vlan 10" + ping_test $h1.11 $(ipaddr 3 11) " from host 1, vlan 11" + ping_test $h2.10 $(ipaddr 3 10) " from host 2, vlan 10" + ping_test $h2.11 $(ipaddr 3 11) " from host 2, vlan 11" +} + +get_tc() +{ + local vlan=$1; shift + + echo $((vlan - 10)) +} + +get_qdisc_handle() +{ + local vlan=$1; shift + + local tc=$(get_tc $vlan) + local band=$((8 - tc)) + + # Handle is 107: for TC1, 108: for TC0. + echo "10$band:" +} + +get_qdisc_backlog() +{ + local vlan=$1; shift + + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .backlog +} + +get_mc_transmit_queue() +{ + local vlan=$1; shift + + local tc=$(($(get_tc $vlan) + 8)) + ethtool_stats_get $swp3 tc_transmit_queue_tc_$tc +} + +get_nmarked() +{ + local vlan=$1; shift + + ethtool_stats_get $swp3 ecn_marked +} + +get_qdisc_npackets() +{ + local vlan=$1; shift + + busywait_for_counter 1100 +1 \ + qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets +} + +# This sends traffic in an attempt to build a backlog of $size. Returns 0 on +# success. After 10 failed attempts it bails out and returns 1. It dumps the +# backlog size to stdout. +build_backlog() +{ + local vlan=$1; shift + local size=$1; shift + local proto=$1; shift + + local tc=$((vlan - 10)) + local band=$((8 - tc)) + local cur=-1 + local i=0 + + while :; do + local cur=$(busywait 1100 until_counter_is $((cur + 1)) \ + get_qdisc_backlog $vlan) + local diff=$((size - cur)) + local pkts=$(((diff + 7999) / 8000)) + + if ((cur >= size)); then + echo $cur + return 0 + elif ((i++ > 10)); then + echo $cur + return 1 + fi + + $MZ $h2.$vlan -p 8000 -a own -b $h3_mac \ + -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \ + -t $proto -q -c $pkts "$@" + done +} + +check_marking() +{ + local vlan=$1; shift + local cond=$1; shift + + local npackets_0=$(get_qdisc_npackets $vlan) + local nmarked_0=$(get_nmarked $vlan) + sleep 5 + local npackets_1=$(get_qdisc_npackets $vlan) + local nmarked_1=$(get_nmarked $vlan) + + local nmarked_d=$((nmarked_1 - nmarked_0)) + local npackets_d=$((npackets_1 - npackets_0)) + local pct=$((100 * nmarked_d / npackets_d)) + + echo $pct + ((pct $cond)) +} + +do_ecn_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + # Main stream. + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Build the below-the-limit backlog using UDP. We could use TCP just + # fine, but this way we get a proof that UDP is accepted when queue + # length is below the limit. The main stream is using TCP, and if the + # limit is misconfigured, we would see this traffic being ECN marked. + RET=0 + backlog=$(build_backlog $vlan $((2 * limit / 3)) udp) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "TC $((vlan - 10)): ECN backlog < limit" + + # Now push TCP, because non-TCP traffic would be early-dropped after the + # backlog crosses the limit, and we want to make sure that the backlog + # is above the limit. + RET=0 + backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan ">= 95") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95." + log_test "TC $((vlan - 10)): ECN backlog > limit" + + # Up there we saw that UDP gets accepted when backlog is below the + # limit. Now that it is above, it should all get dropped, and backlog + # building should fail. + RET=0 + build_backlog $vlan $((2 * limit)) udp >/dev/null + check_fail $? "UDP traffic went into backlog instead of being early-dropped" + log_test "TC $((vlan - 10)): ECN backlog > limit: UDP early-dropped" + + stop_traffic + sleep 1 +} + +do_red_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + # Use ECN-capable TCP to verify there's no marking even though the queue + # is above limit. + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \ + $h3_mac tos=0x01 + + # Pushing below the queue limit should work. + RET=0 + backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01) + check_err $? "Could not build the requested backlog" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + log_test "TC $((vlan - 10)): RED backlog < limit" + + # Pushing above should not. + RET=0 + backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01) + check_fail $? "Traffic went into backlog instead of being early-dropped" + pct=$(check_marking $vlan "== 0") + check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0." + local diff=$((limit - backlog)) + pct=$((100 * diff / limit)) + ((0 <= pct && pct <= 5)) + check_err $? "backlog $backlog / $limit expected <= 5% distance" + log_test "TC $((vlan - 10)): RED backlog > limit" + + stop_traffic + sleep 1 +} + +do_mc_backlog_test() +{ + local vlan=$1; shift + local limit=$1; shift + local backlog + local pct + + RET=0 + + start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) bc + start_tcp_traffic $h2.$vlan $(ipaddr 2 $vlan) $(ipaddr 3 $vlan) bc + + qbl=$(busywait 5000 until_counter_is 500000 \ + get_qdisc_backlog $vlan) + check_err $? "Could not build MC backlog" + + # Verify that we actually see the backlog on BUM TC. Do a busywait as + # well, performance blips might cause false fail. + local ebl + ebl=$(busywait 5000 until_counter_is 500000 \ + get_mc_transmit_queue $vlan) + check_err $? "MC backlog reported by qdisc not visible in ethtool" + + stop_traffic + stop_traffic + + log_test "TC $((vlan - 10)): Qdisc reports MC backlog" +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh new file mode 100755 index 000000000000..af83efe9ccf1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ecn_test + red_test + mc_backlog_test +" +: ${QDISC:=ets} +source sch_red_core.sh + +# do_ecn_test first build 2/3 of the requested backlog and expects no marking, +# and then builds 3/2 of it and does expect marking. The values of $BACKLOG1 and +# $BACKLOG2 are far enough not to overlap, so that we can assume that if we do +# see (do not see) marking, it is actually due to the configuration of that one +# TC, and not due to configuration of the other TC leaking over. +BACKLOG1=200000 +BACKLOG2=500000 + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc add dev $swp3 root handle 10: $QDISC \ + bands 8 priomap 7 6 5 4 3 2 1 0 + tc qdisc add dev $swp3 parent 10:8 handle 108: red \ + limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \ + probability 1.0 avpkt 8000 burst 38 "${args[@]}" + tc qdisc add dev $swp3 parent 10:7 handle 107: red \ + limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \ + probability 1.0 avpkt 8000 burst 63 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 parent 10:7 + tc qdisc del dev $swp3 parent 10:8 + tc qdisc del dev $swp3 root +} + +ecn_test() +{ + install_qdisc ecn + + do_ecn_test 10 $BACKLOG1 + do_ecn_test 11 $BACKLOG2 + + uninstall_qdisc +} + +red_test() +{ + install_qdisc + + do_red_test 10 $BACKLOG1 + do_red_test 11 $BACKLOG2 + + uninstall_qdisc +} + +mc_backlog_test() +{ + install_qdisc + + # Note that the backlog numbers here do not correspond to RED + # configuration, but are arbitrary. + do_mc_backlog_test 10 $BACKLOG1 + do_mc_backlog_test 11 $BACKLOG2 + + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +bail_on_lldpad +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh new file mode 100755 index 000000000000..76820a0e9a1b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_prio.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +QDISC=prio +source sch_red_ets.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh new file mode 100755 index 000000000000..b2217493a88e --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh @@ -0,0 +1,60 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + ping_ipv4 + ecn_test + red_test + mc_backlog_test +" +source sch_red_core.sh + +BACKLOG=300000 + +install_qdisc() +{ + local -a args=("$@") + + tc qdisc add dev $swp3 root handle 108: red \ + limit 1000000 min $BACKLOG max $((BACKLOG + 1)) \ + probability 1.0 avpkt 8000 burst 38 "${args[@]}" + sleep 1 +} + +uninstall_qdisc() +{ + tc qdisc del dev $swp3 root +} + +ecn_test() +{ + install_qdisc ecn + do_ecn_test 10 $BACKLOG + uninstall_qdisc +} + +red_test() +{ + install_qdisc + do_red_test 10 $BACKLOG + uninstall_qdisc +} + +mc_backlog_test() +{ + install_qdisc + # Note that the backlog value here does not correspond to RED + # configuration, but is arbitrary. + do_mc_backlog_test 10 $BACKLOG + uninstall_qdisc +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +bail_on_lldpad +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh new file mode 100755 index 000000000000..58f3a05f08af --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -0,0 +1,222 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS=" + port_pool_test + port_tc_ip_test + port_tc_arp_test +" + +NUM_NETIFS=2 +source ../../../net/forwarding/lib.sh +source ../../../net/forwarding/devlink_lib.sh +source mlxsw_lib.sh + +SB_POOL_ING=0 +SB_POOL_EGR_CPU=10 + +SB_ITC_CPU_IP=3 +SB_ITC_CPU_ARP=2 +SB_ITC=0 + +h1_create() +{ + simple_if_init $h1 192.0.1.1/24 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.1.1/24 +} + +h2_create() +{ + simple_if_init $h2 192.0.1.2/24 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.1.2/24 +} + +sb_occ_pool_check() +{ + local dl_port=$1; shift + local pool=$1; shift + local exp_max_occ=$1 + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"pool\"][\"$pool\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +sb_occ_itc_check() +{ + local dl_port=$1; shift + local itc=$1; shift + local exp_max_occ=$1 + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"itc\"][\"$itc\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +sb_occ_etc_check() +{ + local dl_port=$1; shift + local etc=$1; shift + local exp_max_occ=$1; shift + local max_occ + local err=0 + + max_occ=$(devlink sb -j occupancy show $dl_port \ + | jq -e ".[][][\"etc\"][\"$etc\"][\"max\"]") + + if [[ "$max_occ" -ne "$exp_max_occ" ]]; then + err=1 + fi + + echo $max_occ + return $err +} + +port_pool_test() +{ + local exp_max_occ=288 + local max_occ + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + -t ip -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ) + check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress pool" + + RET=0 + max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ) + check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress pool" + + RET=0 + max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ) + check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress pool" +} + +port_tc_ip_test() +{ + local exp_max_occ=288 + local max_occ + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ + -t ip -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress TC - IP packet" + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress TC - IP packet" + + RET=0 + max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ) + check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress TC - IP packet" +} + +port_tc_arp_test() +{ + local exp_max_occ=96 + local max_occ + + if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then + exp_max_occ=144 + fi + + devlink sb occupancy clearmax $DEVLINK_DEV + + $MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q + + devlink sb occupancy snapshot $DEVLINK_DEV + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h1) ingress TC - ARP packet" + + RET=0 + max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) + check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "physical port's($h2) ingress TC - ARP packet" + + RET=0 + max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ) + check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ" + log_test "CPU port's egress TC - ARP packet" +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + h2=${NETIFS[p2]} + + h1mac=$(mac_get $h1) + h2mac=$(mac_get $h2) + + dl_port1=$(devlink_port_by_netdev $h1) + dl_port2=$(devlink_port_by_netdev $h2) + + cpu_dl_port=$(devlink_cpu_port_get) + + vrf_prepare + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + h2_destroy + h1_destroy + + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py new file mode 100755 index 000000000000..0d4b9327c9b3 --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer_configuration.py @@ -0,0 +1,416 @@ +#!/usr/bin/python +# SPDX-License-Identifier: GPL-2.0 + +import subprocess +import json as j +import random + + +class SkipTest(Exception): + pass + + +class RandomValuePicker: + """ + Class for storing shared buffer configuration. Can handle 3 different + objects, pool, tcbind and portpool. Provide an interface to get random + values for a specific object type as the follow: + 1. Pool: + - random size + + 2. TcBind: + - random pool number + - random threshold + + 3. PortPool: + - random threshold + """ + def __init__(self, pools): + self._pools = [] + for pool in pools: + self._pools.append(pool) + + def _cell_size(self): + return self._pools[0]["cell_size"] + + def _get_static_size(self, th): + # For threshold of 16, this works out to be about 12MB on Spectrum-1, + # and about 17MB on Spectrum-2. + return th * 8000 * self._cell_size() + + def _get_size(self): + return self._get_static_size(16) + + def _get_thtype(self): + return "static" + + def _get_th(self, pool): + # Threshold value could be any integer between 3 to 16 + th = random.randint(3, 16) + if pool["thtype"] == "dynamic": + return th + else: + return self._get_static_size(th) + + def _get_pool(self, direction): + ing_pools = [] + egr_pools = [] + for pool in self._pools: + if pool["type"] == "ingress": + ing_pools.append(pool) + else: + egr_pools.append(pool) + if direction == "ingress": + arr = ing_pools + else: + arr = egr_pools + return arr[random.randint(0, len(arr) - 1)] + + def get_value(self, objid): + if isinstance(objid, Pool): + if objid["pool"] in [4, 8, 9, 10]: + # The threshold type of pools 4, 8, 9 and 10 cannot be changed + raise SkipTest() + else: + return (self._get_size(), self._get_thtype()) + if isinstance(objid, TcBind): + if objid["tc"] >= 8: + # Multicast TCs cannot be changed + raise SkipTest() + else: + pool = self._get_pool(objid["type"]) + th = self._get_th(pool) + pool_n = pool["pool"] + return (pool_n, th) + if isinstance(objid, PortPool): + pool_n = objid["pool"] + pool = self._pools[pool_n] + assert pool["pool"] == pool_n + th = self._get_th(pool) + return (th,) + + +class RecordValuePickerException(Exception): + pass + + +class RecordValuePicker: + """ + Class for storing shared buffer configuration. Can handle 2 different + objects, pool and tcbind. Provide an interface to get the stored values per + object type. + """ + def __init__(self, objlist): + self._recs = [] + for item in objlist: + self._recs.append({"objid": item, "value": item.var_tuple()}) + + def get_value(self, objid): + if isinstance(objid, Pool) and objid["pool"] in [4, 8, 9, 10]: + # The threshold type of pools 4, 8, 9 and 10 cannot be changed + raise SkipTest() + if isinstance(objid, TcBind) and objid["tc"] >= 8: + # Multicast TCs cannot be changed + raise SkipTest() + for rec in self._recs: + if rec["objid"].weak_eq(objid): + return rec["value"] + raise RecordValuePickerException() + + +def run_cmd(cmd, json=False): + out = subprocess.check_output(cmd, shell=True) + if json: + return j.loads(out) + return out + + +def run_json_cmd(cmd): + return run_cmd(cmd, json=True) + + +def log_test(test_name, err_msg=None): + if err_msg: + print("\t%s" % err_msg) + print("TEST: %-80s [FAIL]" % test_name) + else: + print("TEST: %-80s [ OK ]" % test_name) + + +class CommonItem(dict): + varitems = [] + + def var_tuple(self): + ret = [] + self.varitems.sort() + for key in self.varitems: + ret.append(self[key]) + return tuple(ret) + + def weak_eq(self, other): + for key in self: + if key in self.varitems: + continue + if self[key] != other[key]: + return False + return True + + +class CommonList(list): + def get_by(self, by_obj): + for item in self: + if item.weak_eq(by_obj): + return item + return None + + def del_by(self, by_obj): + for item in self: + if item.weak_eq(by_obj): + self.remove(item) + + +class Pool(CommonItem): + varitems = ["size", "thtype"] + + def dl_set(self, dlname, size, thtype): + run_cmd("devlink sb pool set {} sb {} pool {} size {} thtype {}".format(dlname, self["sb"], + self["pool"], + size, thtype)) + + +class PoolList(CommonList): + pass + + +def get_pools(dlname, direction=None): + d = run_json_cmd("devlink sb pool show -j") + pools = PoolList() + for pooldict in d["pool"][dlname]: + if not direction or direction == pooldict["type"]: + pools.append(Pool(pooldict)) + return pools + + +def do_check_pools(dlname, pools, vp): + for pool in pools: + pre_pools = get_pools(dlname) + try: + (size, thtype) = vp.get_value(pool) + except SkipTest: + continue + pool.dl_set(dlname, size, thtype) + post_pools = get_pools(dlname) + pool = post_pools.get_by(pool) + + err_msg = None + if pool["size"] != size: + err_msg = "Incorrect pool size (got {}, expected {})".format(pool["size"], size) + if pool["thtype"] != thtype: + err_msg = "Incorrect pool threshold type (got {}, expected {})".format(pool["thtype"], thtype) + + pre_pools.del_by(pool) + post_pools.del_by(pool) + if pre_pools != post_pools: + err_msg = "Other pool setup changed as well" + log_test("pool {} of sb {} set verification".format(pool["pool"], + pool["sb"]), err_msg) + + +def check_pools(dlname, pools): + # Save defaults + record_vp = RecordValuePicker(pools) + + # For each pool, set random size and static threshold type + do_check_pools(dlname, pools, RandomValuePicker(pools)) + + # Restore defaults + do_check_pools(dlname, pools, record_vp) + + +class TcBind(CommonItem): + varitems = ["pool", "threshold"] + + def __init__(self, port, d): + super(TcBind, self).__init__(d) + self["dlportname"] = port.name + + def dl_set(self, pool, th): + run_cmd("devlink sb tc bind set {} sb {} tc {} type {} pool {} th {}".format(self["dlportname"], + self["sb"], + self["tc"], + self["type"], + pool, th)) + + +class TcBindList(CommonList): + pass + + +def get_tcbinds(ports, verify_existence=False): + d = run_json_cmd("devlink sb tc bind show -j -n") + tcbinds = TcBindList() + for port in ports: + err_msg = None + if port.name not in d["tc_bind"] or len(d["tc_bind"][port.name]) == 0: + err_msg = "No tc bind for port" + else: + for tcbinddict in d["tc_bind"][port.name]: + tcbinds.append(TcBind(port, tcbinddict)) + if verify_existence: + log_test("tc bind existence for port {} verification".format(port.name), err_msg) + return tcbinds + + +def do_check_tcbind(ports, tcbinds, vp): + for tcbind in tcbinds: + pre_tcbinds = get_tcbinds(ports) + try: + (pool, th) = vp.get_value(tcbind) + except SkipTest: + continue + tcbind.dl_set(pool, th) + post_tcbinds = get_tcbinds(ports) + tcbind = post_tcbinds.get_by(tcbind) + + err_msg = None + if tcbind["pool"] != pool: + err_msg = "Incorrect pool (got {}, expected {})".format(tcbind["pool"], pool) + if tcbind["threshold"] != th: + err_msg = "Incorrect threshold (got {}, expected {})".format(tcbind["threshold"], th) + + pre_tcbinds.del_by(tcbind) + post_tcbinds.del_by(tcbind) + if pre_tcbinds != post_tcbinds: + err_msg = "Other tc bind setup changed as well" + log_test("tc bind {}-{} of sb {} set verification".format(tcbind["dlportname"], + tcbind["tc"], + tcbind["sb"]), err_msg) + + +def check_tcbind(dlname, ports, pools): + tcbinds = get_tcbinds(ports, verify_existence=True) + + # Save defaults + record_vp = RecordValuePicker(tcbinds) + + # Bind each port and unicast TC (TCs < 8) to a random pool and a random + # threshold + do_check_tcbind(ports, tcbinds, RandomValuePicker(pools)) + + # Restore defaults + do_check_tcbind(ports, tcbinds, record_vp) + + +class PortPool(CommonItem): + varitems = ["threshold"] + + def __init__(self, port, d): + super(PortPool, self).__init__(d) + self["dlportname"] = port.name + + def dl_set(self, th): + run_cmd("devlink sb port pool set {} sb {} pool {} th {}".format(self["dlportname"], + self["sb"], + self["pool"], th)) + + +class PortPoolList(CommonList): + pass + + +def get_portpools(ports, verify_existence=False): + d = run_json_cmd("devlink sb port pool -j -n") + portpools = PortPoolList() + for port in ports: + err_msg = None + if port.name not in d["port_pool"] or len(d["port_pool"][port.name]) == 0: + err_msg = "No port pool for port" + else: + for portpooldict in d["port_pool"][port.name]: + portpools.append(PortPool(port, portpooldict)) + if verify_existence: + log_test("port pool existence for port {} verification".format(port.name), err_msg) + return portpools + + +def do_check_portpool(ports, portpools, vp): + for portpool in portpools: + pre_portpools = get_portpools(ports) + (th,) = vp.get_value(portpool) + portpool.dl_set(th) + post_portpools = get_portpools(ports) + portpool = post_portpools.get_by(portpool) + + err_msg = None + if portpool["threshold"] != th: + err_msg = "Incorrect threshold (got {}, expected {})".format(portpool["threshold"], th) + + pre_portpools.del_by(portpool) + post_portpools.del_by(portpool) + if pre_portpools != post_portpools: + err_msg = "Other port pool setup changed as well" + log_test("port pool {}-{} of sb {} set verification".format(portpool["dlportname"], + portpool["pool"], + portpool["sb"]), err_msg) + + +def check_portpool(dlname, ports, pools): + portpools = get_portpools(ports, verify_existence=True) + + # Save defaults + record_vp = RecordValuePicker(portpools) + + # For each port pool, set a random threshold + do_check_portpool(ports, portpools, RandomValuePicker(pools)) + + # Restore defaults + do_check_portpool(ports, portpools, record_vp) + + +class Port: + def __init__(self, name): + self.name = name + + +class PortList(list): + pass + + +def get_ports(dlname): + d = run_json_cmd("devlink port show -j") + ports = PortList() + for name in d["port"]: + if name.find(dlname) == 0 and d["port"][name]["flavour"] == "physical": + ports.append(Port(name)) + return ports + + +def get_device(): + devices_info = run_json_cmd("devlink -j dev info")["info"] + for d in devices_info: + if "mlxsw_spectrum" in devices_info[d]["driver"]: + return d + return None + + +class UnavailableDevlinkNameException(Exception): + pass + + +def test_sb_configuration(): + # Use static seed + random.seed(0) + + dlname = get_device() + if not dlname: + raise UnavailableDevlinkNameException() + + ports = get_ports(dlname) + pools = get_pools(dlname) + + check_pools(dlname, pools) + check_tcbind(dlname, ports, pools) + check_portpool(dlname, ports, pools) + + +test_sb_configuration() diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh index 7b2acba82a49..fd583a171db7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh @@ -8,8 +8,9 @@ source $lib_dir/lib.sh source $lib_dir/tc_common.sh source $lib_dir/devlink_lib.sh -if [ "$DEVLINK_VIDDID" != "15b3:cf6c" ]; then - echo "SKIP: test is tailored for Mellanox Spectrum-2" +if [[ "$DEVLINK_VIDDID" != "15b3:cf6c" && \ + "$DEVLINK_VIDDID" != "15b3:cf70" ]]; then + echo "SKIP: test is tailored for Mellanox Spectrum-2 and Spectrum-3" exit 1 fi diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh new file mode 100755 index 000000000000..68c80d0ec1ec --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_restrictions.sh @@ -0,0 +1,186 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + shared_block_drop_test + egress_redirect_test + multi_mirror_test +" +NUM_NETIFS=2 + +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh + +switch_create() +{ + simple_if_init $swp1 192.0.2.1/24 + simple_if_init $swp2 192.0.2.2/24 +} + +switch_destroy() +{ + simple_if_fini $swp2 192.0.2.2/24 + simple_if_fini $swp1 192.0.2.1/24 +} + +shared_block_drop_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have mixed-bound + # shared block with a drop rule. + + tc qdisc add dev $swp1 ingress_block 22 clsact + check_err $? "Failed to create clsact with ingress block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add drop rule to ingress bound block" + + tc qdisc add dev $swp2 ingress_block 22 clsact + check_err $? "Failed to create another clsact with ingress shared block" + + tc qdisc del dev $swp2 clsact + + tc qdisc add dev $swp2 egress_block 22 clsact + check_fail $? "Incorrect success to create another clsact with egress shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc add dev $swp2 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block after blocker drop rule removed" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_fail $? "Incorrect success to add drop rule to mixed bound block" + + tc qdisc del dev $swp1 clsact + + tc qdisc add dev $swp1 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 action drop + check_err $? "Failed to add drop rule to egress bound shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc del dev $swp2 clsact + tc qdisc del dev $swp1 clsact + + log_test "shared block drop" +} + +egress_redirect_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have mirred redirect on + # egress-bound block. + + tc qdisc add dev $swp1 ingress_block 22 clsact + check_err $? "Failed to create clsact with ingress block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_err $? "Failed to add redirect rule to ingress bound block" + + tc qdisc add dev $swp2 ingress_block 22 clsact + check_err $? "Failed to create another clsact with ingress shared block" + + tc qdisc del dev $swp2 clsact + + tc qdisc add dev $swp2 egress_block 22 clsact + check_fail $? "Incorrect success to create another clsact with egress shared block" + + tc filter del block 22 protocol ip pref 1 handle 101 flower + + tc qdisc add dev $swp2 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block after blocker redirect rule removed" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to mixed bound block" + + tc qdisc del dev $swp1 clsact + + tc qdisc add dev $swp1 egress_block 22 clsact + check_err $? "Failed to create another clsact with egress shared block" + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to egress bound shared block" + + tc qdisc del dev $swp2 clsact + + tc filter add block 22 protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress redirect dev $swp2 + check_fail $? "Incorrect success to add redirect rule to egress bound block" + + tc qdisc del dev $swp1 clsact + + log_test "shared block drop" +} + +multi_mirror_test() +{ + RET=0 + + # It is forbidden in mlxsw driver to have multiple mirror + # actions in a single rule. + + tc qdisc add dev $swp1 clsact + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress mirror dev $swp2 + check_err $? "Failed to add rule with single mirror action" + + tc filter del dev $swp1 ingress protocol ip pref 1 handle 101 flower + + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ + skip_sw dst_ip 192.0.2.2 \ + action mirred egress mirror dev $swp2 \ + action mirred egress mirror dev $swp1 + check_fail $? "Incorrect success to add rule with two mirror actions" + + tc qdisc del dev $swp1 clsact + + log_test "multi mirror" +} + +setup_prepare() +{ + swp1=${NETIFS[p1]} + swp2=${NETIFS[p2]} + + vrf_prepare + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + vrf_cleanup +} + +check_tc_shblock_support + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh index a6d733d2a4b4..cc0f07e72cf2 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh @@ -2,9 +2,9 @@ # SPDX-License-Identifier: GPL-2.0 # Test for resource limit of offloaded flower rules. The test adds a given -# number of flower matches for different IPv6 addresses, then generates traffic, -# and ensures each was hit exactly once. This file contains functions to set up -# a testing topology and run the test, and is meant to be sourced from a test +# number of flower matches for different IPv6 addresses, then check the offload +# indication for all of the tc flower rules. This file contains functions to set +# up a testing topology and run the test, and is meant to be sourced from a test # script that calls the testing routine with a given number of rules. TC_FLOWER_NUM_NETIFS=2 @@ -94,22 +94,15 @@ __tc_flower_test() tc_flower_rules_create $count $should_fail - for ((i = 0; i < count; ++i)); do - $MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \ - -A 2001:db8:2::1 \ - -B $(tc_flower_addr $i) - done - - MISMATCHES=$( - tc -j -s filter show dev $h2 ingress | - jq -r '[ .[] | select(.kind == "flower") | .options | - values as $rule | .actions[].stats.packets | - select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] | - join(", ")' - ) - - test -z "$MISMATCHES" - check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES" + offload_count=$(tc -j -s filter show dev $h2 ingress | + jq -r '[ .[] | select(.kind == "flower") | + .options | .in_hw ]' | jq .[] | wc -l) + [[ $((offload_count - 1)) -eq $count ]] + if [[ $should_fail -eq 0 ]]; then + check_err $? "Offload mismatch" + else + check_err_fail $should_fail $? "Offload more than expacted" + fi } tc_flower_test() diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 4632f51af7ab..729a86cc4ede 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -9,6 +9,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS="sanitization_test offload_indication_test \ sanitization_vlan_aware_test offload_indication_vlan_aware_test" NUM_NETIFS=2 +: ${TIMEOUT:=20000} # ms source $lib_dir/lib.sh setup_prepare() @@ -470,8 +471,8 @@ offload_indication_fdb_flood_test() bridge fdb append 00:00:00:00:00:00 dev vxlan0 self dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep 00:00:00:00:00:00 \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb 00:00:00:00:00:00 \ + bridge fdb show brport vxlan0 check_err $? bridge fdb del 00:00:00:00:00:00 dev vxlan0 self @@ -486,11 +487,11 @@ offload_indication_fdb_bridge_test() bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self master static \ dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - initial state" @@ -500,9 +501,9 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan0 master - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 + check_err $? log_test "vxlan entry offload indication - after removal from bridge" @@ -511,11 +512,11 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan0 master static - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - after re-add to bridge" @@ -525,9 +526,9 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan0 self - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 + check_err $? log_test "vxlan entry offload indication - after removal from vxlan" @@ -536,11 +537,11 @@ offload_indication_fdb_bridge_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan0 self dst 198.51.100.2 - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan0 check_err $? - bridge fdb show brport vxlan0 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan0 check_err $? log_test "vxlan entry offload indication - after re-add to vxlan" @@ -558,27 +559,32 @@ offload_indication_decap_route_test() { RET=0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan0 down - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan1 down - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - vxlan device down" RET=0 ip link set dev vxlan1 up - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev vxlan0 up - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - vxlan device up" @@ -586,11 +592,13 @@ offload_indication_decap_route_test() RET=0 ip address delete 198.51.100.1/32 dev lo - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? ip address add 198.51.100.1/32 dev lo - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - add local route" @@ -598,16 +606,19 @@ offload_indication_decap_route_test() RET=0 ip link set dev $swp1 nomaster - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link set dev $swp2 nomaster - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? ip link set dev $swp1 master br0 ip link set dev $swp2 master br1 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - local ports enslavement" @@ -615,12 +626,14 @@ offload_indication_decap_route_test() RET=0 ip link del dev br0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev br1 - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - bridge device deletion" @@ -632,16 +645,19 @@ offload_indication_decap_route_test() ip link set dev $swp2 master br1 ip link set dev vxlan0 master br0 ip link set dev vxlan1 master br1 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev vxlan0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? ip link del dev vxlan1 - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? log_test "vxlan decap route - vxlan device deletion" @@ -656,12 +672,15 @@ check_fdb_offloaded() local mac=00:11:22:33:44:55 local zmac=00:00:00:00:00:00 - bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac self \ + bridge fdb show dev vxlan0 check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $mac master \ + bridge fdb show dev vxlan0 check_err $? - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 check_err $? } @@ -672,13 +691,15 @@ check_vxlan_fdb_not_offloaded() bridge fdb show dev vxlan0 | grep $mac | grep -q self check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac self \ + bridge fdb show dev vxlan0 + check_err $? bridge fdb show dev vxlan0 | grep $zmac | grep -q self check_err $? - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 + check_err $? } check_bridge_fdb_not_offloaded() @@ -688,8 +709,9 @@ check_bridge_fdb_not_offloaded() bridge fdb show dev vxlan0 | grep $mac | grep -q master check_err $? - bridge fdb show dev vxlan0 | grep $mac | grep master | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $mac master \ + bridge fdb show dev vxlan0 + check_err $? } __offload_indication_join_vxlan_first() @@ -771,12 +793,14 @@ __offload_indication_join_vxlan_last() ip link set dev $swp1 master br0 - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 + check_err $? ip link set dev vxlan0 master br0 - bridge fdb show dev vxlan0 | grep $zmac | grep self | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show dev vxlan0 check_err $? log_test "offload indication - attach vxlan last" @@ -854,20 +878,26 @@ sanitization_vlan_aware_test() bridge vlan del vid 10 dev vxlan20 bridge vlan add vid 20 dev vxlan20 pvid untagged - # Test that offloading of an unsupported tunnel fails when it is - # triggered by addition of VLAN to a local port - RET=0 + # Test that when two VXLAN tunnels with conflicting configurations + # (i.e., different TTL) are enslaved to the same VLAN-aware bridge, + # then the enslavement of a port to the bridge is denied. - # TOS must be set to inherit - ip link set dev vxlan10 type vxlan tos 42 + # Use the offload indication of the local route to ensure the VXLAN + # configuration was correctly rollbacked. + ip address add 198.51.100.1/32 dev lo - ip link set dev $swp1 master br0 - bridge vlan add vid 10 dev $swp1 &> /dev/null + ip link set dev vxlan10 type vxlan ttl 10 + ip link set dev $swp1 master br0 &> /dev/null check_fail $? - log_test "vlan-aware - failed vlan addition to a local port" + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? + + log_test "vlan-aware - failed enslavement to bridge due to conflict" - ip link set dev vxlan10 type vxlan tos inherit + ip link set dev vxlan10 type vxlan ttl 20 + ip address del 198.51.100.1/32 dev lo ip link del dev vxlan20 ip link del dev vxlan10 @@ -924,11 +954,11 @@ offload_indication_vlan_aware_fdb_test() bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self master static \ dst 198.51.100.2 vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - initial state" @@ -938,9 +968,9 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan10 master vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 + check_err $? log_test "vxlan entry offload indication - after removal from bridge" @@ -949,11 +979,11 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan10 master static vlan 10 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - after re-add to bridge" @@ -963,9 +993,9 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb del de:ad:be:ef:13:37 dev vxlan10 self - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 + check_err $? log_test "vxlan entry offload indication - after removal from vxlan" @@ -974,11 +1004,11 @@ offload_indication_vlan_aware_fdb_test() RET=0 bridge fdb add de:ad:be:ef:13:37 dev vxlan10 self dst 198.51.100.2 - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self bridge fdb show brport vxlan10 check_err $? - bridge fdb show brport vxlan10 | grep de:ad:be:ef:13:37 | grep -v self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb \ + de:ad:be:ef:13:37 self -v bridge fdb show brport vxlan10 check_err $? log_test "vxlan entry offload indication - after re-add to vxlan" @@ -990,28 +1020,31 @@ offload_indication_vlan_aware_decap_route_test() { RET=0 - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? # Toggle PVID flag on one VxLAN device and make sure route is still # marked as offloaded bridge vlan add vid 10 dev vxlan10 untagged - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload \ + ip route show table local 198.51.100.1 check_err $? # Toggle PVID flag on second VxLAN device and make sure route is no # longer marked as offloaded bridge vlan add vid 20 dev vxlan20 untagged - ip route show table local | grep 198.51.100.1 | grep -q offload - check_fail $? + busywait "$TIMEOUT" not wait_for_offload \ + ip route show table local 198.51.100.1 + check_err $? # Toggle PVID flag back and make sure route is marked as offloaded bridge vlan add vid 10 dev vxlan10 pvid untagged bridge vlan add vid 20 dev vxlan20 pvid untagged - ip route show table local | grep 198.51.100.1 | grep -q offload + busywait "$TIMEOUT" wait_for_offload ip route show table local 198.51.100.1 check_err $? log_test "vxlan decap route - vni map/unmap" @@ -1064,35 +1097,33 @@ offload_indication_vlan_aware_l3vni_test() ip link set dev vxlan0 master br0 bridge vlan add dev vxlan0 vid 10 pvid untagged - # No local port or router port is member in the VLAN, so tunnel should - # not be offloaded - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload - check_fail $? "vxlan tunnel offloaded when should not" + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 + check_err $? "vxlan tunnel not offloaded when should" # Configure a VLAN interface and make sure tunnel is offloaded ip link add link br0 name br10 up type vlan id 10 sysctl_set net.ipv6.conf.br10.disable_ipv6 0 ip -6 address add 2001:db8:1::1/64 dev br10 - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 check_err $? "vxlan tunnel not offloaded when should" # Unlink the VXLAN device, make sure tunnel is no longer offloaded, # then add it back to the bridge and make sure it is offloaded ip link set dev vxlan0 nomaster - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload - check_fail $? "vxlan tunnel offloaded after unlinked from bridge" + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 + check_err $? "vxlan tunnel offloaded after unlinked from bridge" ip link set dev vxlan0 master br0 - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload - check_fail $? "vxlan tunnel offloaded despite no matching vid" + busywait "$TIMEOUT" not wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 + check_err $? "vxlan tunnel offloaded despite no matching vid" bridge vlan add dev vxlan0 vid 10 pvid untagged - bridge fdb show brport vxlan0 | grep $zmac | grep self \ - | grep -q offload + busywait "$TIMEOUT" wait_for_offload grep_bridge_fdb $zmac self \ + bridge fdb show brport vxlan0 check_err $? "vxlan tunnel not offloaded after adding vid" log_test "vxlan - l3 vni" diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh index f101ab9441e2..437d32bd4cfd 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh @@ -103,6 +103,11 @@ trap_metadata_test() for trap_name in $(devlink_traps_get); do devlink_trap_metadata_test $trap_name "input_port" check_err $? "Input port not reported as metadata of trap $trap_name" + if [ $trap_name == "ingress_flow_action_drop" ] || + [ $trap_name == "egress_flow_action_drop" ]; then + devlink_trap_metadata_test $trap_name "flow_action_cookie" + check_err $? "Flow action cookie not reported as metadata of trap $trap_name" + fi done log_test "Trap metadata" diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 40b076983239..0df6d8942721 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -35,6 +35,12 @@ if [ $? -ne 0 ]; then exit 1 fi +devlink dev help 2>&1 | grep info &> /dev/null +if [ $? -ne 0 ]; then + echo "SKIP: iproute2 too old, missing devlink dev info support" + exit 1 +fi + ############################################################################## # Devlink helpers @@ -373,6 +379,7 @@ devlink_trap_drop_test() local trap_name=$1; shift local group_name=$1; shift local dev=$1; shift + local handle=$1; shift # This is the common part of all the tests. It checks that stats are # initially idle, then non-idle after changing the trap action and @@ -397,7 +404,7 @@ devlink_trap_drop_test() devlink_trap_group_stats_idle_test $group_name check_err $? "Trap group stats not idle after setting action to drop" - tc_check_packets "dev $dev egress" 101 0 + tc_check_packets "dev $dev egress" $handle 0 check_err $? "Packets were not dropped" } @@ -406,7 +413,25 @@ devlink_trap_drop_cleanup() local mz_pid=$1; shift local dev=$1; shift local proto=$1; shift + local pref=$1; shift + local handle=$1; shift kill $mz_pid && wait $mz_pid &> /dev/null - tc filter del dev $dev egress protocol $proto pref 1 handle 101 flower + tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower +} + +devlink_port_by_netdev() +{ + local if_name=$1 + + devlink -j port show $if_name | jq -e '.[] | keys' | jq -r '.[]' +} + +devlink_cpu_port_get() +{ + local cpu_dl_port_num=$(devlink port list | grep "$DEVLINK_DEV" | + grep cpu | cut -d/ -f3 | cut -d: -f1 | + sed -n '1p') + + echo "$DEVLINK_DEV/$cpu_dl_port_num" } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 2f5da414aaa7..83fd15e3e545 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -248,6 +248,33 @@ busywait() done } +not() +{ + "$@" + [[ $? != 0 ]] +} + +grep_bridge_fdb() +{ + local addr=$1; shift + local word + local flag + + if [ "$1" == "self" ] || [ "$1" == "master" ]; then + word=$1; shift + if [ "$1" == "-v" ]; then + flag=$1; shift + fi + fi + + $@ | grep $addr | grep $flag "$word" +} + +wait_for_offload() +{ + "$@" | grep -q offload +} + until_counter_is() { local value=$1; shift @@ -607,6 +634,16 @@ ethtool_stats_get() ethtool -S $dev | grep "^ *$stat:" | head -n 1 | cut -d: -f2 } +qdisc_stats_get() +{ + local dev=$1; shift + local handle=$1; shift + local selector=$1; shift + + tc -j -s qdisc show dev "$dev" \ + | jq '.[] | select(.handle == "'"$handle"'") | '"$selector" +} + humanize() { local speed=$1; shift @@ -1132,18 +1169,29 @@ flood_test() flood_multicast_test $br_port $host1_if $host2_if } -start_traffic() +__start_traffic() { + local proto=$1; shift local h_in=$1; shift # Where the traffic egresses the host local sip=$1; shift local dip=$1; shift local dmac=$1; shift $MZ $h_in -p 8000 -A $sip -B $dip -c 0 \ - -a own -b $dmac -t udp -q & + -a own -b $dmac -t "$proto" -q "$@" & sleep 1 } +start_traffic() +{ + __start_traffic udp "$@" +} + +start_tcp_traffic() +{ + __start_traffic tcp "$@" +} + stop_traffic() { # Suppress noise from killing mausezahn. diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json index 98a20faf3198..afb9187b46a7 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/basic.json @@ -372,5 +372,687 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "bae4", + "name": "Add basic filter with u32 ematch u8/zero offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x11 0x0f at 0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(01000000/0f000000 at 0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "e6cb", + "name": "Add basic filter with u32 ematch u8/zero offset and invalid value >0xFF", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x1122 0x0f at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/0f000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "7727", + "name": "Add basic filter with u32 ematch u8/positive offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0x1f at 12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(17000000/1f000000 at 12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "a429", + "name": "Add basic filter with u32 ematch u8/invalid mask >0xFF", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff00 at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000/ff000000 at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "8373", + "name": "Add basic filter with u32 ematch u8/missing offset", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff at)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000 at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "ab8e", + "name": "Add basic filter with u32 ematch u8/missing AT keyword", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x77 0xff 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77000000 at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "712d", + "name": "Add basic filter with u32 ematch u8/missing value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "350f", + "name": "Add basic filter with u32 ematch u8/non-numeric value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 zero 0xff at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ff000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "e28f", + "name": "Add basic filter with u32 ematch u8/non-numeric mask", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x11 mask at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11000000/00000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "6d5f", + "name": "Add basic filter with u32 ematch u8/negative offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0xaa 0xf0 at -14)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(0000a000/0000f000 at -16\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "12dc", + "name": "Add basic filter with u32 ematch u8/nexthdr+ offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0xaa 0xf0 at nexthdr+0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(a0000000/f0000000 at nexthdr\\+0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1d85", + "name": "Add basic filter with u32 ematch u16/zero offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x1122 0xffff at 0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/ffff0000 at 0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "3672", + "name": "Add basic filter with u32 ematch u16/zero offset and invalid value >0xFFFF", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x112233 0xffff at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11223300/ffff0000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "7fb0", + "name": "Add basic filter with u32 ematch u16/positive offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0x1fff at 12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(17880000/1fff0000 at 12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "19af", + "name": "Add basic filter with u32 ematch u16/invalid mask >0xFFFF", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffffffff at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000/ffffffff at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "446d", + "name": "Add basic filter with u32 ematch u16/missing offset", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffff at)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000 at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "151b", + "name": "Add basic filter with u32 ematch u16/missing AT keyword", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0x7788 0xffff 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77880000/ffff0000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "bb23", + "name": "Add basic filter with u32 ematch u16/missing value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "decc", + "name": "Add basic filter with u32 ematch u16/non-numeric value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 zero 0xffff at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ffff0000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "e988", + "name": "Add basic filter with u32 ematch u16/non-numeric mask", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u8 0x1122 mask at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11220000/00000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "07d8", + "name": "Add basic filter with u32 ematch u16/negative offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0xaabb 0xffff at -12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabb0000/ffff0000 at -12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "f474", + "name": "Add basic filter with u32 ematch u16/nexthdr+ offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u16 0xaabb 0xf0f0 at nexthdr+0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(a0b00000/f0f00000 at nexthdr\\+0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "47a0", + "name": "Add basic filter with u32 ematch u32/zero offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at 0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at 0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "849f", + "name": "Add basic filter with u32 ematch u32/positive offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0x1ffff0f0 at 12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227080/1ffff0f0 at 12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "d288", + "name": "Add basic filter with u32 ematch u32/missing offset", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11227788 0xffffffff at)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11227788/ffffffff at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "4998", + "name": "Add basic filter with u32 ematch u32/missing AT keyword", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x77889900 0xfffff0f0 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(77889900/fffff0f0 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "1f0a", + "name": "Add basic filter with u32 ematch u32/missing value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 at 12)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(at 12\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "848e", + "name": "Add basic filter with u32 ematch u32/non-numeric value", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 zero 0xffff at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(00000000/ffff0000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "f748", + "name": "Add basic filter with u32 ematch u32/non-numeric mask", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0x11223344 mask at 0)' classid 1:1", + "expExitCode": "1", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(11223344/00000000 at 0\\)", + "matchCount": "0", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "55a6", + "name": "Add basic filter with u32 ematch u32/negative offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xff00ff00 at -12)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aa00cc00/ff00ff00 at -12\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "7282", + "name": "Add basic filter with u32 ematch u32/nexthdr+ offset and default action", + "category": [ + "filter", + "basic" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 protocol ip prio 1 basic match 'u32(u32 0xaabbccdd 0xffffffff at nexthdr+0)' classid 1:1", + "expExitCode": "0", + "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol ip basic", + "matchPattern": "^filter parent ffff: protocol ip pref 1 basic.*handle 0x1 flowid 1:1.*u32\\(aabbccdd/ffffffff at nexthdr\\+0\\)", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] } ] diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 1d8b93f1af31..5a4fb80fa832 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -55,6 +55,78 @@ static void test_stream_connection_reset(const struct test_opts *opts) close(fd); } +static void test_stream_bind_only_client(const struct test_opts *opts) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = opts->peer_cid, + }, + }; + int ret; + int fd; + + /* Wait for the server to be ready */ + control_expectln("BIND"); + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + timeout_begin(TIMEOUT); + do { + ret = connect(fd, &addr.sa, sizeof(addr.svm)); + timeout_check("connect"); + } while (ret < 0 && errno == EINTR); + timeout_end(); + + if (ret != -1) { + fprintf(stderr, "expected connect(2) failure, got %d\n", ret); + exit(EXIT_FAILURE); + } + if (errno != ECONNRESET) { + fprintf(stderr, "unexpected connect(2) errno %d\n", errno); + exit(EXIT_FAILURE); + } + + /* Notify the server that the client has finished */ + control_writeln("DONE"); + + close(fd); +} + +static void test_stream_bind_only_server(const struct test_opts *opts) +{ + union { + struct sockaddr sa; + struct sockaddr_vm svm; + } addr = { + .svm = { + .svm_family = AF_VSOCK, + .svm_port = 1234, + .svm_cid = VMADDR_CID_ANY, + }, + }; + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + + if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { + perror("bind"); + exit(EXIT_FAILURE); + } + + /* Notify the client that the server is ready */ + control_writeln("BIND"); + + /* Wait for the client to finish */ + control_expectln("DONE"); + + close(fd); +} + static void test_stream_client_close_client(const struct test_opts *opts) { int fd; @@ -213,6 +285,11 @@ static struct test_case test_cases[] = { .run_client = test_stream_connection_reset, }, { + .name = "SOCK_STREAM bind only", + .run_client = test_stream_bind_only_client, + .run_server = test_stream_bind_only_server, + }, + { .name = "SOCK_STREAM client close", .run_client = test_stream_client_close_client, .run_server = test_stream_client_close_server, |