diff options
105 files changed, 23200 insertions, 710 deletions
diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt index 47aa205ee0bd..c5ed5d25f642 100644 --- a/Documentation/devicetree/bindings/net/dsa/mt7530.txt +++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt @@ -35,6 +35,42 @@ Required properties for the child nodes within ports container: - phy-mode: String, must be either "trgmii" or "rgmii" for port labeled "cpu". +Port 5 of the switch is muxed between: +1. GMAC5: GMAC5 can interface with another external MAC or PHY. +2. PHY of port 0 or port 4: PHY interfaces with an external MAC like 2nd GMAC + of the SOC. Used in many setups where port 0/4 becomes the WAN port. + Note: On a MT7621 SOC with integrated switch: 2nd GMAC can only connected to + GMAC5 when the gpios for RGMII2 (GPIO 22-33) are not used and not + connected to external component! + +Port 5 modes/configurations: +1. Port 5 is disabled and isolated: An external phy can interface to the 2nd + GMAC of the SOC. + In the case of a build-in MT7530 switch, port 5 shares the RGMII bus with 2nd + GMAC and an optional external phy. Mind the GPIO/pinctl settings of the SOC! +2. Port 5 is muxed to PHY of port 0/4: Port 0/4 interfaces with 2nd GMAC. + It is a simple MAC to PHY interface, port 5 needs to be setup for xMII mode + and RGMII delay. +3. Port 5 is muxed to GMAC5 and can interface to an external phy. + Port 5 becomes an extra switch port. + Only works on platform where external phy TX<->RX lines are swapped. + Like in the Ubiquiti ER-X-SFP. +4. Port 5 is muxed to GMAC5 and interfaces with the 2nd GAMC as 2nd CPU port. + Currently a 2nd CPU port is not supported by DSA code. + +Depending on how the external PHY is wired: +1. normal: The PHY can only connect to 2nd GMAC but not to the switch +2. swapped: RGMII TX, RX are swapped; external phy interface with the switch as + a ethernet port. But can't interface to the 2nd GMAC. + +Based on the DT the port 5 mode is configured. + +Driver tries to lookup the phy-handle of the 2nd GMAC of the master device. +When phy-handle matches PHY of port 0 or 4 then port 5 set-up as mode 2. +phy-mode must be set, see also example 2 below! + * mt7621: phy-mode = "rgmii-txid"; + * mt7623: phy-mode = "rgmii"; + See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional required, optional properties and how the integrated switch subnodes must be specified. @@ -94,3 +130,181 @@ Example: }; }; }; + +Example 2: MT7621: Port 4 is WAN port: 2nd GMAC -> Port 5 -> PHY port 4. + +ð { + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + gmac1: mac@1 { + compatible = "mediatek,eth-mac"; + reg = <1>; + phy-mode = "rgmii-txid"; + phy-handle = <&phy4>; + }; + + mdio: mdio-bus { + #address-cells = <1>; + #size-cells = <0>; + + /* Internal phy */ + phy4: ethernet-phy@4 { + reg = <4>; + }; + + mt7530: switch@1f { + compatible = "mediatek,mt7621"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x1f>; + pinctrl-names = "default"; + mediatek,mcm; + + resets = <&rstctrl 2>; + reset-names = "mcm"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + +/* Commented out. Port 4 is handled by 2nd GMAC. + port@4 { + reg = <4>; + label = "lan4"; + }; +*/ + + cpu_port0: port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; + }; +}; + +Example 3: MT7621: Port 5 is connected to external PHY: Port 5 -> external PHY. + +ð { + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + mdio: mdio-bus { + #address-cells = <1>; + #size-cells = <0>; + + /* External phy */ + ephy5: ethernet-phy@7 { + reg = <7>; + }; + + mt7530: switch@1f { + compatible = "mediatek,mt7621"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x1f>; + pinctrl-names = "default"; + mediatek,mcm; + + resets = <&rstctrl 2>; + reset-names = "mcm"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + port@4 { + reg = <4>; + label = "lan4"; + }; + + port@5 { + reg = <5>; + label = "lan5"; + phy-mode = "rgmii"; + phy-handle = <&ephy5>; + }; + + cpu_port0: port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; + }; +}; diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst index 2b7fefe72351..57fec66c5419 100644 --- a/Documentation/networking/device_drivers/index.rst +++ b/Documentation/networking/device_drivers/index.rst @@ -23,6 +23,7 @@ Contents: intel/ice google/gve mellanox/mlx5 + pensando/ionic .. only:: subproject diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst index b30a63dbf4b7..d071c6b49e1f 100644 --- a/Documentation/networking/device_drivers/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst @@ -11,6 +11,7 @@ Contents - `Enabling the driver and kconfig options`_ - `Devlink info`_ +- `Devlink parameters`_ - `Devlink health reporters`_ - `mlx5 tracepoints`_ @@ -122,6 +123,38 @@ User command example:: stored: fw.version 16.26.0100 +Devlink parameters +================== + +flow_steering_mode: Device flow steering mode +--------------------------------------------- +The flow steering mode parameter controls the flow steering mode of the driver. +Two modes are supported: +1. 'dmfs' - Device managed flow steering. +2. 'smfs - Software/Driver managed flow steering. + +In DMFS mode, the HW steering entities are created and managed through the +Firmware. +In SMFS mode, the HW steering entities are created and managed though by +the driver directly into Hardware without firmware intervention. + +SMFS mode is faster and provides better rule inserstion rate compared to default DMFS mode. + +User command examples: + +- Set SMFS flow steering mode:: + + $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime + +- Read device flow steering mode:: + + $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode + pci/0000:06:00.0: + name flow_steering_mode type driver-specific + values: + cmode runtime value smfs + + Devlink health reporters ======================== diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst new file mode 100644 index 000000000000..67b6839d516b --- /dev/null +++ b/Documentation/networking/device_drivers/pensando/ionic.rst @@ -0,0 +1,43 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +========================================================== +Linux* Driver for the Pensando(R) Ethernet adapter family +========================================================== + +Pensando Linux Ethernet driver. +Copyright(c) 2019 Pensando Systems, Inc + +Contents +======== + +- Identifying the Adapter +- Support + +Identifying the Adapter +======================= + +To find if one or more Pensando PCI Ethernet devices are installed on the +host, check for the PCI devices:: + + $ lspci -d 1dd8: + b5:00.0 Ethernet controller: Device 1dd8:1002 + b6:00.0 Ethernet controller: Device 1dd8:1002 + +If such devices are listed as above, then the ionic.ko driver should find +and configure them for use. There should be log entries in the kernel +messages such as these:: + + $ dmesg | grep ionic + ionic Pensando Ethernet NIC Driver, ver 0.15.0-k + ionic 0000:b5:00.0 enp181s0: renamed from eth0 + ionic 0000:b6:00.0 enp182s0: renamed from eth0 + +Support +======= +For general Linux networking support, please use the netdev mailing +list, which is monitored by Pensando personnel:: + netdev@vger.kernel.org + +For more specific support needs, please use the Pensando driver support +email:: + drivers@pensando.io diff --git a/Documentation/networking/devlink-info-versions.rst b/Documentation/networking/devlink-info-versions.rst index 4316342b7746..4914f581b1fd 100644 --- a/Documentation/networking/devlink-info-versions.rst +++ b/Documentation/networking/devlink-info-versions.rst @@ -14,11 +14,27 @@ board.rev Board design revision. +asic.id +======= + +ASIC design identifier. + +asic.rev +======== + +ASIC design revision. + board.manufacture ================= An identifier of the company or the facility which produced the part. +fw +== + +Overall firmware version, often representing the collection of +fw.mgmt, fw.app, etc. + fw.mgmt ======= diff --git a/MAINTAINERS b/MAINTAINERS index a081c477d1d1..c1fb8fb3b2ee 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12608,6 +12608,14 @@ L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/peaq-wmi.c +PENSANDO ETHERNET DRIVERS +M: Shannon Nelson <snelson@pensando.io> +M: Pensando Drivers <drivers@pensando.io> +L: netdev@vger.kernel.org +S: Supported +F: Documentation/networking/device_drivers/pensando/ionic.rst +F: drivers/net/ethernet/pensando/ + PER-CPU MEMORY ALLOCATOR M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c index 635bb4b447fb..e6df5b95ed47 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -474,7 +474,8 @@ static int chtls_getsockopt(struct sock *sk, int level, int optname, struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) - return ctx->getsockopt(sk, level, optname, optval, optlen); + return ctx->sk_proto->getsockopt(sk, level, + optname, optval, optlen); return do_chtls_getsockopt(sk, optval, optlen); } @@ -541,7 +542,8 @@ static int chtls_setsockopt(struct sock *sk, int level, int optname, struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) - return ctx->setsockopt(sk, level, optname, optval, optlen); + return ctx->sk_proto->setsockopt(sk, level, + optname, optval, optlen); return do_chtls_setsockopt(sk, optname, optval, optlen); } diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 6c8645033102..4937947400cd 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -186,136 +186,6 @@ int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length) return err; } -int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t *addr, u32 *obj_id) -{ - struct mlx5_core_dev *dev = dm->dev; - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; - u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {}; - unsigned long *block_map; - u64 icm_start_addr; - u32 log_icm_size; - u32 num_blocks; - u32 max_blocks; - u64 block_idx; - void *sw_icm; - int ret; - - MLX5_SET(general_obj_in_cmd_hdr, in, opcode, - MLX5_CMD_OP_CREATE_GENERAL_OBJECT); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); - MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); - - switch (type) { - case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: - icm_start_addr = MLX5_CAP64_DEV_MEM(dev, - steering_sw_icm_start_address); - log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size); - block_map = dm->steering_sw_icm_alloc_blocks; - break; - case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - icm_start_addr = MLX5_CAP64_DEV_MEM(dev, - header_modify_sw_icm_start_address); - log_icm_size = MLX5_CAP_DEV_MEM(dev, - log_header_modify_sw_icm_size); - block_map = dm->header_modify_sw_icm_alloc_blocks; - break; - default: - return -EINVAL; - } - - num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); - spin_lock(&dm->lock); - block_idx = bitmap_find_next_zero_area(block_map, - max_blocks, - 0, - num_blocks, 0); - - if (block_idx < max_blocks) - bitmap_set(block_map, - block_idx, num_blocks); - - spin_unlock(&dm->lock); - - if (block_idx >= max_blocks) - return -ENOMEM; - - sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm); - icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr, - icm_start_addr); - MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length)); - - ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); - if (ret) { - spin_lock(&dm->lock); - bitmap_clear(block_map, - block_idx, num_blocks); - spin_unlock(&dm->lock); - - return ret; - } - - *addr = icm_start_addr; - *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); - - return 0; -} - -int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t addr, u32 obj_id) -{ - struct mlx5_core_dev *dev = dm->dev; - u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; - u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; - unsigned long *block_map; - u32 num_blocks; - u64 start_idx; - int err; - - num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - - switch (type) { - case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: - start_idx = - (addr - MLX5_CAP64_DEV_MEM( - dev, steering_sw_icm_start_address)) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - block_map = dm->steering_sw_icm_alloc_blocks; - break; - case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - start_idx = - (addr - - MLX5_CAP64_DEV_MEM( - dev, header_modify_sw_icm_start_address)) >> - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); - block_map = dm->header_modify_sw_icm_alloc_blocks; - break; - default: - return -EINVAL; - } - - MLX5_SET(general_obj_in_cmd_hdr, in, opcode, - MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); - MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); - MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); - - err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); - if (err) - return err; - - spin_lock(&dm->lock); - bitmap_clear(block_map, - start_idx, num_blocks); - spin_unlock(&dm->lock); - - return 0; -} - int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out) { u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index 0572dcba6eae..169cab4915e3 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -65,8 +65,4 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, u16 uid); int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); -int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t *addr, u32 *obj_id); -int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length, - u16 uid, phys_addr_t addr, u32 obj_id); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c index b8841355fcd5..1c8f04abee0c 100644 --- a/drivers/infiniband/hw/mlx5/flow.c +++ b/drivers/infiniband/hw/mlx5/flow.c @@ -322,11 +322,11 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction) switch (maction->flow_action_raw.sub_type) { case MLX5_IB_FLOW_ACTION_MODIFY_HEADER: mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev, - maction->flow_action_raw.action_id); + maction->flow_action_raw.modify_hdr); break; case MLX5_IB_FLOW_ACTION_PACKET_REFORMAT: mlx5_packet_reformat_dealloc(maction->flow_action_raw.dev->mdev, - maction->flow_action_raw.action_id); + maction->flow_action_raw.pkt_reformat); break; case MLX5_IB_FLOW_ACTION_DECAP: break; @@ -352,10 +352,11 @@ mlx5_ib_create_modify_header(struct mlx5_ib_dev *dev, if (!maction) return ERR_PTR(-ENOMEM); - ret = mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in, - &maction->flow_action_raw.action_id); + maction->flow_action_raw.modify_hdr = + mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in); - if (ret) { + if (IS_ERR(maction->flow_action_raw.modify_hdr)) { + ret = PTR_ERR(maction->flow_action_raw.modify_hdr); kfree(maction); return ERR_PTR(ret); } @@ -479,11 +480,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( if (ret) return ret; - ret = mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, - in, namespace, - &maction->flow_action_raw.action_id); - if (ret) + maction->flow_action_raw.pkt_reformat = + mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, + in, namespace); + if (IS_ERR(maction->flow_action_raw.pkt_reformat)) { + ret = PTR_ERR(maction->flow_action_raw.pkt_reformat); return ret; + } maction->flow_action_raw.sub_type = MLX5_IB_FLOW_ACTION_PACKET_REFORMAT; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 0569bcab02d4..4e9f1507ffd9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2280,6 +2280,7 @@ static inline int check_dm_type_support(struct mlx5_ib_dev *dev, return -EOPNOTSUPP; break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: if (!capable(CAP_SYS_RAWIO) || !capable(CAP_NET_RAW)) return -EPERM; @@ -2344,20 +2345,20 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, struct uverbs_attr_bundle *attrs, int type) { - struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm; + struct mlx5_core_dev *dev = to_mdev(ctx->device)->mdev; u64 act_size; int err; /* Allocation size must a multiple of the basic block size * and a power of 2. */ - act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev)); + act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dev)); act_size = roundup_pow_of_two(act_size); dm->size = act_size; - err = mlx5_cmd_alloc_sw_icm(dm_db, type, act_size, - to_mucontext(ctx)->devx_uid, &dm->dev_addr, - &dm->icm_dm.obj_id); + err = mlx5_dm_sw_icm_alloc(dev, type, act_size, + to_mucontext(ctx)->devx_uid, &dm->dev_addr, + &dm->icm_dm.obj_id); if (err) return err; @@ -2365,9 +2366,9 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET, &dm->dev_addr, sizeof(dm->dev_addr)); if (err) - mlx5_cmd_dealloc_sw_icm(dm_db, type, dm->size, - to_mucontext(ctx)->devx_uid, - dm->dev_addr, dm->icm_dm.obj_id); + mlx5_dm_sw_icm_dealloc(dev, type, dm->size, + to_mucontext(ctx)->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); return err; } @@ -2407,8 +2408,14 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev, attrs); break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + err = handle_alloc_dm_sw_icm(context, dm, + attr, attrs, + MLX5_SW_ICM_TYPE_STEERING); + break; case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - err = handle_alloc_dm_sw_icm(context, dm, attr, attrs, type); + err = handle_alloc_dm_sw_icm(context, dm, + attr, attrs, + MLX5_SW_ICM_TYPE_HEADER_MODIFY); break; default: err = -EOPNOTSUPP; @@ -2428,6 +2435,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs) { struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context( &attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext); + struct mlx5_core_dev *dev = to_mdev(ibdm->device)->mdev; struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm; struct mlx5_ib_dm *dm = to_mdm(ibdm); u32 page_idx; @@ -2439,19 +2447,23 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs) if (ret) return ret; - page_idx = (dm->dev_addr - - pci_resource_start(dm_db->dev->pdev, 0) - - MLX5_CAP64_DEV_MEM(dm_db->dev, - memic_bar_start_addr)) >> - PAGE_SHIFT; + page_idx = (dm->dev_addr - pci_resource_start(dev->pdev, 0) - + MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr)) >> + PAGE_SHIFT; bitmap_clear(ctx->dm_pages, page_idx, DIV_ROUND_UP(dm->size, PAGE_SIZE)); break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_STEERING, + dm->size, ctx->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); + if (ret) + return ret; + break; case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: - ret = mlx5_cmd_dealloc_sw_icm(dm_db, dm->type, dm->size, - ctx->devx_uid, dm->dev_addr, - dm->icm_dm.obj_id); + ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + dm->size, ctx->devx_uid, dm->dev_addr, + dm->icm_dm.obj_id); if (ret) return ret; break; @@ -2646,7 +2658,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction, if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return -EINVAL; action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - action->modify_id = maction->flow_action_raw.action_id; + action->modify_hdr = + maction->flow_action_raw.modify_hdr; return 0; } if (maction->flow_action_raw.sub_type == @@ -2663,8 +2676,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction, return -EINVAL; action->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - action->reformat_id = - maction->flow_action_raw.action_id; + action->pkt_reformat = + maction->flow_action_raw.pkt_reformat; return 0; } /* fall through */ @@ -6096,8 +6109,6 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device, static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) { - struct mlx5_core_dev *mdev = dev->mdev; - mlx5_ib_cleanup_multiport_master(dev); if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { srcu_barrier(&dev->mr_srcu); @@ -6105,29 +6116,11 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev) } WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES)); - - WARN_ON(dev->dm.steering_sw_icm_alloc_blocks && - !bitmap_empty( - dev->dm.steering_sw_icm_alloc_blocks, - BIT(MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)))); - - kfree(dev->dm.steering_sw_icm_alloc_blocks); - - WARN_ON(dev->dm.header_modify_sw_icm_alloc_blocks && - !bitmap_empty(dev->dm.header_modify_sw_icm_alloc_blocks, - BIT(MLX5_CAP_DEV_MEM( - mdev, log_header_modify_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)))); - - kfree(dev->dm.header_modify_sw_icm_alloc_blocks); } static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) { struct mlx5_core_dev *mdev = dev->mdev; - u64 header_modify_icm_blocks = 0; - u64 steering_icm_blocks = 0; int err; int i; @@ -6174,51 +6167,17 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) INIT_LIST_HEAD(&dev->qp_list); spin_lock_init(&dev->reset_flow_resource_lock); - if (MLX5_CAP_GEN_64(mdev, general_obj_types) & - MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM) { - if (MLX5_CAP64_DEV_MEM(mdev, steering_sw_icm_start_address)) { - steering_icm_blocks = - BIT(MLX5_CAP_DEV_MEM(mdev, - log_steering_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)); - - dev->dm.steering_sw_icm_alloc_blocks = - kcalloc(BITS_TO_LONGS(steering_icm_blocks), - sizeof(unsigned long), GFP_KERNEL); - if (!dev->dm.steering_sw_icm_alloc_blocks) - goto err_mp; - } - - if (MLX5_CAP64_DEV_MEM(mdev, - header_modify_sw_icm_start_address)) { - header_modify_icm_blocks = BIT( - MLX5_CAP_DEV_MEM( - mdev, log_header_modify_sw_icm_size) - - MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev)); - - dev->dm.header_modify_sw_icm_alloc_blocks = - kcalloc(BITS_TO_LONGS(header_modify_icm_blocks), - sizeof(unsigned long), GFP_KERNEL); - if (!dev->dm.header_modify_sw_icm_alloc_blocks) - goto err_dm; - } - } - spin_lock_init(&dev->dm.lock); dev->dm.dev = mdev; if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) { err = init_srcu_struct(&dev->mr_srcu); if (err) - goto err_dm; + goto err_mp; } return 0; -err_dm: - kfree(dev->dm.steering_sw_icm_alloc_blocks); - kfree(dev->dm.header_modify_sw_icm_alloc_blocks); - err_mp: mlx5_ib_cleanup_multiport_master(dev); diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 9ae587b74b12..125a507c10ed 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -868,7 +868,10 @@ struct mlx5_ib_flow_action { struct { struct mlx5_ib_dev *dev; u32 sub_type; - u32 action_id; + union { + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; + }; } flow_action_raw; }; }; @@ -881,8 +884,6 @@ struct mlx5_dm { */ spinlock_t lock; DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES); - unsigned long *steering_sw_icm_alloc_blocks; - unsigned long *header_modify_sw_icm_alloc_blocks; }; struct mlx5_read_counters_attr { diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index c48e29486b10..1d8d36de4d20 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -13,7 +13,7 @@ #include <linux/of_mdio.h> #include <linux/of_net.h> #include <linux/of_platform.h> -#include <linux/phy.h> +#include <linux/phylink.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> #include <linux/reset.h> @@ -633,61 +633,75 @@ mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset) return ARRAY_SIZE(mt7530_mib); } -static void mt7530_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) +static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) { struct mt7530_priv *priv = ds->priv; + u8 tx_delay = 0; + int val; - if (phy_is_pseudo_fixed_link(phydev)) { - dev_dbg(priv->dev, "phy-mode for master device = %x\n", - phydev->interface); + mutex_lock(&priv->reg_mutex); - /* Setup TX circuit incluing relevant PAD and driving */ - mt7530_pad_clk_setup(ds, phydev->interface); + val = mt7530_read(priv, MT7530_MHWTRAP); - if (priv->id == ID_MT7530) { - /* Setup RX circuit, relevant PAD and driving on the - * host which must be placed after the setup on the - * device side is all finished. - */ - mt7623_pad_clk_setup(ds); - } - } else { - u16 lcl_adv = 0, rmt_adv = 0; - u8 flowctrl; - u32 mcr = PMCR_USERP_LINK | PMCR_FORCE_MODE; + val |= MHWTRAP_MANUAL | MHWTRAP_P5_MAC_SEL | MHWTRAP_P5_DIS; + val &= ~MHWTRAP_P5_RGMII_MODE & ~MHWTRAP_PHY0_SEL; - switch (phydev->speed) { - case SPEED_1000: - mcr |= PMCR_FORCE_SPEED_1000; - break; - case SPEED_100: - mcr |= PMCR_FORCE_SPEED_100; - break; - } + switch (priv->p5_intf_sel) { + case P5_INTF_SEL_PHY_P0: + /* MT7530_P5_MODE_GPHY_P0: 2nd GMAC -> P5 -> P0 */ + val |= MHWTRAP_PHY0_SEL; + /* fall through */ + case P5_INTF_SEL_PHY_P4: + /* MT7530_P5_MODE_GPHY_P4: 2nd GMAC -> P5 -> P4 */ + val &= ~MHWTRAP_P5_MAC_SEL & ~MHWTRAP_P5_DIS; + + /* Setup the MAC by default for the cpu port */ + mt7530_write(priv, MT7530_PMCR_P(5), 0x56300); + break; + case P5_INTF_SEL_GMAC5: + /* MT7530_P5_MODE_GMAC: P5 -> External phy or 2nd GMAC */ + val &= ~MHWTRAP_P5_DIS; + break; + case P5_DISABLED: + interface = PHY_INTERFACE_MODE_NA; + break; + default: + dev_err(ds->dev, "Unsupported p5_intf_sel %d\n", + priv->p5_intf_sel); + goto unlock_exit; + } - if (phydev->link) - mcr |= PMCR_FORCE_LNK; + /* Setup RGMII settings */ + if (phy_interface_mode_is_rgmii(interface)) { + val |= MHWTRAP_P5_RGMII_MODE; - if (phydev->duplex) { - mcr |= PMCR_FORCE_FDX; + /* P5 RGMII RX Clock Control: delay setting for 1000M */ + mt7530_write(priv, MT7530_P5RGMIIRXCR, CSR_RGMII_EDGE_ALIGN); - if (phydev->pause) - rmt_adv = LPA_PAUSE_CAP; - if (phydev->asym_pause) - rmt_adv |= LPA_PAUSE_ASYM; + /* Don't set delay in DSA mode */ + if (!dsa_is_dsa_port(priv->ds, 5) && + (interface == PHY_INTERFACE_MODE_RGMII_TXID || + interface == PHY_INTERFACE_MODE_RGMII_ID)) + tx_delay = 4; /* n * 0.5 ns */ - lcl_adv = linkmode_adv_to_lcl_adv_t( - phydev->advertising); - flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); + /* P5 RGMII TX Clock Control: delay x */ + mt7530_write(priv, MT7530_P5RGMIITXCR, + CSR_RGMII_TXC_CFG(0x10 + tx_delay)); - if (flowctrl & FLOW_CTRL_TX) - mcr |= PMCR_TX_FC_EN; - if (flowctrl & FLOW_CTRL_RX) - mcr |= PMCR_RX_FC_EN; - } - mt7530_write(priv, MT7530_PMCR_P(port), mcr); + /* reduce P5 RGMII Tx driving, 8mA */ + mt7530_write(priv, MT7530_IO_DRV_CR, + P5_IO_CLK_DRV(1) | P5_IO_DATA_DRV(1)); } + + mt7530_write(priv, MT7530_MHWTRAP, val); + + dev_dbg(ds->dev, "Setup P5, HWTRAP=0x%x, intf_sel=%s, phy-mode=%s\n", + val, p5_intf_modes(priv->p5_intf_sel), phy_modes(interface)); + + priv->p5_interface = interface; + +unlock_exit: + mutex_unlock(&priv->reg_mutex); } static int @@ -698,9 +712,6 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv, mt7530_write(priv, MT7530_PVC_P(port), PORT_SPEC_TAG); - /* Setup the MAC by default for the cpu port */ - mt7530_write(priv, MT7530_PMCR_P(port), PMCR_CPUP_LINK); - /* Disable auto learning on the cpu port */ mt7530_set(priv, MT7530_PSC_P(port), SA_DIS); @@ -731,9 +742,6 @@ mt7530_port_enable(struct dsa_switch *ds, int port, mutex_lock(&priv->reg_mutex); - /* Setup the MAC for the user port */ - mt7530_write(priv, MT7530_PMCR_P(port), PMCR_USERP_LINK); - /* Allow the user port gets connected to the cpu port and also * restore the port matrix if the port is the member of a certain * bridge. @@ -742,7 +750,7 @@ mt7530_port_enable(struct dsa_switch *ds, int port, priv->ports[port].enable = true; mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, priv->ports[port].pm); - mt7530_port_set_status(priv, port, 1); + mt7530_port_set_status(priv, port, 0); mutex_unlock(&priv->reg_mutex); @@ -1232,10 +1240,13 @@ static int mt7530_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; - int ret, i; - u32 id, val; - struct device_node *dn; + struct device_node *phy_node; + struct device_node *mac_np; struct mt7530_dummy_poll p; + phy_interface_t interface; + struct device_node *dn; + u32 id, val; + int ret, i; /* The parent node of master netdev which holds the common system * controller also is the container for two GMACs nodes representing @@ -1305,6 +1316,8 @@ mt7530_setup(struct dsa_switch *ds) val |= MHWTRAP_MANUAL; mt7530_write(priv, MT7530_MHWTRAP, val); + priv->p6_interface = PHY_INTERFACE_MODE_NA; + /* Enable and reset MIB counters */ mt7530_mib_reset(ds); @@ -1321,6 +1334,40 @@ mt7530_setup(struct dsa_switch *ds) mt7530_port_disable(ds, i); } + /* Setup port 5 */ + priv->p5_intf_sel = P5_DISABLED; + interface = PHY_INTERFACE_MODE_NA; + + if (!dsa_is_unused_port(ds, 5)) { + priv->p5_intf_sel = P5_INTF_SEL_GMAC5; + interface = of_get_phy_mode(ds->ports[5].dn); + } else { + /* Scan the ethernet nodes. look for GMAC1, lookup used phy */ + for_each_child_of_node(dn, mac_np) { + if (!of_device_is_compatible(mac_np, + "mediatek,eth-mac")) + continue; + + ret = of_property_read_u32(mac_np, "reg", &id); + if (ret < 0 || id != 1) + continue; + + phy_node = of_parse_phandle(mac_np, "phy-handle", 0); + if (phy_node->parent == priv->dev->of_node->parent) { + interface = of_get_phy_mode(mac_np); + id = of_mdio_parse_addr(ds->dev, phy_node); + if (id == 0) + priv->p5_intf_sel = P5_INTF_SEL_PHY_P0; + if (id == 4) + priv->p5_intf_sel = P5_INTF_SEL_PHY_P4; + } + of_node_put(phy_node); + break; + } + } + + mt7530_setup_port5(ds, interface); + /* Flush the FDB table */ ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); if (ret < 0) @@ -1329,6 +1376,216 @@ mt7530_setup(struct dsa_switch *ds) return 0; } +static void mt7530_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct mt7530_priv *priv = ds->priv; + u32 mcr_cur, mcr_new; + + switch (port) { + case 0: /* Internal phy */ + case 1: + case 2: + case 3: + case 4: + if (state->interface != PHY_INTERFACE_MODE_GMII) + return; + break; + case 5: /* 2nd cpu port with phy of port 0 or 4 / external phy */ + if (priv->p5_interface == state->interface) + break; + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_GMII) + return; + + mt7530_setup_port5(ds, state->interface); + break; + case 6: /* 1st cpu port */ + if (priv->p6_interface == state->interface) + break; + + if (state->interface != PHY_INTERFACE_MODE_RGMII && + state->interface != PHY_INTERFACE_MODE_TRGMII) + return; + + /* Setup TX circuit incluing relevant PAD and driving */ + mt7530_pad_clk_setup(ds, state->interface); + + if (priv->id == ID_MT7530) { + /* Setup RX circuit, relevant PAD and driving on the + * host which must be placed after the setup on the + * device side is all finished. + */ + mt7623_pad_clk_setup(ds); + } + + priv->p6_interface = state->interface; + break; + default: + dev_err(ds->dev, "%s: unsupported port: %i\n", __func__, port); + return; + } + + if (phylink_autoneg_inband(mode)) { + dev_err(ds->dev, "%s: in-band negotiation unsupported\n", + __func__); + return; + } + + mcr_cur = mt7530_read(priv, MT7530_PMCR_P(port)); + mcr_new = mcr_cur; + mcr_new &= ~(PMCR_FORCE_SPEED_1000 | PMCR_FORCE_SPEED_100 | + PMCR_FORCE_FDX | PMCR_TX_FC_EN | PMCR_RX_FC_EN); + mcr_new |= PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | PMCR_BACKOFF_EN | + PMCR_BACKPR_EN | PMCR_FORCE_MODE | PMCR_FORCE_LNK; + + /* Are we connected to external phy */ + if (port == 5 && dsa_is_user_port(ds, 5)) + mcr_new |= PMCR_EXT_PHY; + + switch (state->speed) { + case SPEED_1000: + mcr_new |= PMCR_FORCE_SPEED_1000; + break; + case SPEED_100: + mcr_new |= PMCR_FORCE_SPEED_100; + break; + } + if (state->duplex == DUPLEX_FULL) { + mcr_new |= PMCR_FORCE_FDX; + if (state->pause & MLO_PAUSE_TX) + mcr_new |= PMCR_TX_FC_EN; + if (state->pause & MLO_PAUSE_RX) + mcr_new |= PMCR_RX_FC_EN; + } + + if (mcr_new != mcr_cur) + mt7530_write(priv, MT7530_PMCR_P(port), mcr_new); +} + +static void mt7530_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct mt7530_priv *priv = ds->priv; + + mt7530_port_set_status(priv, port, 0); +} + +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 mt7530_priv *priv = ds->priv; + + mt7530_port_set_status(priv, port, 1); +} + +static void mt7530_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + switch (port) { + case 0: /* Internal phy */ + case 1: + case 2: + case 3: + case 4: + if (state->interface != PHY_INTERFACE_MODE_NA && + state->interface != PHY_INTERFACE_MODE_GMII) + goto unsupported; + break; + case 5: /* 2nd cpu port with phy of port 0 or 4 / external phy */ + if (state->interface != PHY_INTERFACE_MODE_NA && + !phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_GMII) + goto unsupported; + break; + case 6: /* 1st cpu port */ + if (state->interface != PHY_INTERFACE_MODE_NA && + state->interface != PHY_INTERFACE_MODE_RGMII && + state->interface != PHY_INTERFACE_MODE_TRGMII) + goto unsupported; + break; + default: + dev_err(ds->dev, "%s: unsupported port: %i\n", __func__, port); +unsupported: + linkmode_zero(supported); + return; + } + + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); + + if (state->interface == PHY_INTERFACE_MODE_TRGMII) { + phylink_set(mask, 1000baseT_Full); + } else { + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + + if (state->interface != PHY_INTERFACE_MODE_MII) { + phylink_set(mask, 1000baseT_Half); + phylink_set(mask, 1000baseT_Full); + if (port == 5) + phylink_set(mask, 1000baseX_Full); + } + } + + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + linkmode_and(supported, supported, mask); + linkmode_and(state->advertising, state->advertising, mask); +} + +static int +mt7530_phylink_mac_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state) +{ + struct mt7530_priv *priv = ds->priv; + u32 pmsr; + + if (port < 0 || port >= MT7530_NUM_PORTS) + return -EINVAL; + + pmsr = mt7530_read(priv, MT7530_PMSR_P(port)); + + state->link = (pmsr & PMSR_LINK); + state->an_complete = state->link; + state->duplex = !!(pmsr & PMSR_DPX); + + switch (pmsr & PMSR_SPEED_MASK) { + case PMSR_SPEED_10: + state->speed = SPEED_10; + break; + case PMSR_SPEED_100: + state->speed = SPEED_100; + break; + case PMSR_SPEED_1000: + state->speed = SPEED_1000; + break; + default: + state->speed = SPEED_UNKNOWN; + break; + } + + state->pause &= ~(MLO_PAUSE_RX | MLO_PAUSE_TX); + if (pmsr & PMSR_RX_FC) + state->pause |= MLO_PAUSE_RX; + if (pmsr & PMSR_TX_FC) + state->pause |= MLO_PAUSE_TX; + + return 1; +} + static const struct dsa_switch_ops mt7530_switch_ops = { .get_tag_protocol = mtk_get_tag_protocol, .setup = mt7530_setup, @@ -1337,7 +1594,6 @@ static const struct dsa_switch_ops mt7530_switch_ops = { .phy_write = mt7530_phy_write, .get_ethtool_stats = mt7530_get_ethtool_stats, .get_sset_count = mt7530_get_sset_count, - .adjust_link = mt7530_adjust_link, .port_enable = mt7530_port_enable, .port_disable = mt7530_port_disable, .port_stp_state_set = mt7530_stp_state_set, @@ -1350,6 +1606,11 @@ static const struct dsa_switch_ops mt7530_switch_ops = { .port_vlan_prepare = mt7530_port_vlan_prepare, .port_vlan_add = mt7530_port_vlan_add, .port_vlan_del = mt7530_port_vlan_del, + .phylink_validate = mt7530_phylink_validate, + .phylink_mac_link_state = mt7530_phylink_mac_link_state, + .phylink_mac_config = mt7530_phylink_mac_config, + .phylink_mac_link_down = mt7530_phylink_mac_link_down, + .phylink_mac_link_up = mt7530_phylink_mac_link_up, }; static const struct of_device_id mt7530_of_match[] = { diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index bfac90f48102..ccb9da8cad0d 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -186,6 +186,7 @@ enum mt7530_vlan_port_attr { /* Register for port MAC control register */ #define MT7530_PMCR_P(x) (0x3000 + ((x) * 0x100)) #define PMCR_IFG_XMIT(x) (((x) & 0x3) << 18) +#define PMCR_EXT_PHY BIT(17) #define PMCR_MAC_MODE BIT(16) #define PMCR_FORCE_MODE BIT(15) #define PMCR_TX_EN BIT(14) @@ -198,26 +199,20 @@ enum mt7530_vlan_port_attr { #define PMCR_FORCE_SPEED_100 BIT(2) #define PMCR_FORCE_FDX BIT(1) #define PMCR_FORCE_LNK BIT(0) -#define PMCR_COMMON_LINK (PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \ - PMCR_BACKOFF_EN | PMCR_BACKPR_EN | \ - PMCR_TX_EN | PMCR_RX_EN | \ - PMCR_TX_FC_EN | PMCR_RX_FC_EN) -#define PMCR_CPUP_LINK (PMCR_COMMON_LINK | PMCR_FORCE_MODE | \ - PMCR_FORCE_SPEED_1000 | \ - PMCR_FORCE_FDX | \ - PMCR_FORCE_LNK) -#define PMCR_USERP_LINK PMCR_COMMON_LINK -#define PMCR_FIXED_LINK (PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | \ - PMCR_FORCE_MODE | PMCR_TX_EN | \ - PMCR_RX_EN | PMCR_BACKPR_EN | \ - PMCR_BACKOFF_EN | \ - PMCR_FORCE_SPEED_1000 | \ - PMCR_FORCE_FDX | \ - PMCR_FORCE_LNK) -#define PMCR_FIXED_LINK_FC (PMCR_FIXED_LINK | \ - PMCR_TX_FC_EN | PMCR_RX_FC_EN) +#define PMCR_SPEED_MASK (PMCR_FORCE_SPEED_100 | \ + PMCR_FORCE_SPEED_1000) #define MT7530_PMSR_P(x) (0x3008 + (x) * 0x100) +#define PMSR_EEE1G BIT(7) +#define PMSR_EEE100M BIT(6) +#define PMSR_RX_FC BIT(5) +#define PMSR_TX_FC BIT(4) +#define PMSR_SPEED_1000 BIT(3) +#define PMSR_SPEED_100 BIT(2) +#define PMSR_SPEED_10 0x00 +#define PMSR_SPEED_MASK (PMSR_SPEED_100 | PMSR_SPEED_1000) +#define PMSR_DPX BIT(1) +#define PMSR_LINK BIT(0) /* Register for MIB */ #define MT7530_PORT_MIB_COUNTER(x) (0x4000 + (x) * 0x100) @@ -251,6 +246,7 @@ enum mt7530_vlan_port_attr { /* Register for hw trap modification */ #define MT7530_MHWTRAP 0x7804 +#define MHWTRAP_PHY0_SEL BIT(20) #define MHWTRAP_MANUAL BIT(16) #define MHWTRAP_P5_MAC_SEL BIT(13) #define MHWTRAP_P6_DIS BIT(8) @@ -408,6 +404,30 @@ struct mt7530_port { u16 pvid; }; +/* Port 5 interface select definitions */ +enum p5_interface_select { + P5_DISABLED = 0, + P5_INTF_SEL_PHY_P0, + P5_INTF_SEL_PHY_P4, + P5_INTF_SEL_GMAC5, +}; + +static const char *p5_intf_modes(unsigned int p5_interface) +{ + switch (p5_interface) { + case P5_DISABLED: + return "DISABLED"; + case P5_INTF_SEL_PHY_P0: + return "PHY P0"; + case P5_INTF_SEL_PHY_P4: + return "PHY P4"; + case P5_INTF_SEL_GMAC5: + return "GMAC5"; + default: + return "unknown"; + } +} + /* struct mt7530_priv - This is the main data structure for holding the state * of the driver * @dev: The device pointer @@ -423,6 +443,8 @@ struct mt7530_port { * @ports: Holding the state among ports * @reg_mutex: The lock for protecting among process accessing * registers + * @p6_interface Holding the current port 6 interface + * @p5_intf_sel: Holding the current port 5 interface select */ struct mt7530_priv { struct device *dev; @@ -435,6 +457,9 @@ struct mt7530_priv { struct gpio_desc *reset; unsigned int id; bool mcm; + phy_interface_t p6_interface; + phy_interface_t p5_interface; + unsigned int p5_intf_sel; struct mt7530_port ports[MT7530_NUM_PORTS]; /* protect among processes for registers access*/ diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 93a2d4deb27c..2830dc283ce6 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -168,6 +168,7 @@ config ETHOC source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" +source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index fb9155cffcff..061edd22f507 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -97,3 +97,4 @@ obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/ obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/ +obj-$(CONFIG_NET_VENDOR_PENSANDO) += pensando/ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 5402867272be..162d7d8fb295 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1348,7 +1348,7 @@ static u32 ingress_fq_count(struct dpaa2_eth_priv *priv) return total; } -static void wait_for_fq_empty(struct dpaa2_eth_priv *priv) +static void wait_for_ingress_fq_empty(struct dpaa2_eth_priv *priv) { int retries = 10; u32 pending; @@ -1360,6 +1360,31 @@ static void wait_for_fq_empty(struct dpaa2_eth_priv *priv) } while (pending && --retries); } +#define DPNI_TX_PENDING_VER_MAJOR 7 +#define DPNI_TX_PENDING_VER_MINOR 13 +static void wait_for_egress_fq_empty(struct dpaa2_eth_priv *priv) +{ + union dpni_statistics stats; + int retries = 10; + int err; + + if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_TX_PENDING_VER_MAJOR, + DPNI_TX_PENDING_VER_MINOR) < 0) + goto out; + + do { + err = dpni_get_statistics(priv->mc_io, 0, priv->mc_token, 6, + &stats); + if (err) + goto out; + if (stats.page_6.tx_pending_frames == 0) + return; + } while (--retries); + +out: + msleep(500); +} + static int dpaa2_eth_stop(struct net_device *net_dev) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); @@ -1379,7 +1404,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) * on WRIOP. After it finishes, wait until all remaining frames on Rx * and Tx conf queues are consumed on NAPI poll. */ - msleep(500); + wait_for_egress_fq_empty(priv); do { dpni_disable(priv->mc_io, 0, priv->mc_token); @@ -1395,7 +1420,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) */ } - wait_for_fq_empty(priv); + wait_for_ingress_fq_empty(priv); disable_ch_napi(priv); /* Empty the buffer pool */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 93076fe01b45..0aa1c34019bb 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -28,6 +28,11 @@ static char dpaa2_ethtool_stats[][ETH_GSTRING_LEN] = { "[hw] rx nobuffer discards", "[hw] tx discarded frames", "[hw] tx confirmed frames", + "[hw] tx dequeued bytes", + "[hw] tx dequeued frames", + "[hw] tx rejected bytes", + "[hw] tx rejected frames", + "[hw] tx pending frames", }; #define DPAA2_ETH_NUM_STATS ARRAY_SIZE(dpaa2_ethtool_stats) @@ -188,27 +193,33 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_drv_stats *extras; struct dpaa2_eth_ch_stats *ch_stats; + int dpni_stats_page_size[DPNI_STATISTICS_CNT] = { + sizeof(dpni_stats.page_0), + sizeof(dpni_stats.page_1), + sizeof(dpni_stats.page_2), + sizeof(dpni_stats.page_3), + sizeof(dpni_stats.page_4), + sizeof(dpni_stats.page_5), + sizeof(dpni_stats.page_6), + }; memset(data, 0, sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS)); /* Print standard counters, from DPNI statistics */ - for (j = 0; j <= 2; j++) { + for (j = 0; j <= 6; j++) { + /* We're not interested in pages 4 & 5 for now */ + if (j == 4 || j == 5) + continue; err = dpni_get_statistics(priv->mc_io, 0, priv->mc_token, j, &dpni_stats); - if (err != 0) + if (err == -EINVAL) + /* Older firmware versions don't support all pages */ + memset(&dpni_stats, 0, sizeof(dpni_stats)); + else netdev_warn(net_dev, "dpni_get_stats(%d) failed\n", j); - switch (j) { - case 0: - num_cnt = sizeof(dpni_stats.page_0) / sizeof(u64); - break; - case 1: - num_cnt = sizeof(dpni_stats.page_1) / sizeof(u64); - break; - case 2: - num_cnt = sizeof(dpni_stats.page_2) / sizeof(u64); - break; - } + + num_cnt = dpni_stats_page_size[j] / sizeof(u64); for (k = 0; k < num_cnt; k++) *(data + i++) = dpni_stats.raw.counter[k]; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c index 05e30893dee6..dd54e6953aeb 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c @@ -1470,7 +1470,7 @@ int dpni_get_queue(struct fsl_mc_io *mc_io, * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' * @token: Token of DPNI object * @page: Selects the statistics page to retrieve, see - * DPNI_GET_STATISTICS output. Pages are numbered 0 to 2. + * DPNI_GET_STATISTICS output. Pages are numbered 0 to 6. * @stat: Structure containing the statistics * * Return: '0' on Success; Error code otherwise. diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index 3e8fc6c7a8da..fd583911b6c0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h @@ -416,6 +416,26 @@ int dpni_get_tx_data_offset(struct fsl_mc_io *mc_io, * lack of buffers * @page_2.egress_discarded_frames: Egress discarded frame count * @page_2.egress_confirmed_frames: Egress confirmed frame count + * @page3: Page_3 statistics structure + * @page_3.egress_dequeue_bytes: Cumulative count of the number of bytes + * dequeued from egress FQs + * @page_3.egress_dequeue_frames: Cumulative count of the number of frames + * dequeued from egress FQs + * @page_3.egress_reject_bytes: Cumulative count of the number of bytes in + * egress frames whose enqueue was rejected + * @page_3.egress_reject_frames: Cumulative count of the number of egress + * frames whose enqueue was rejected + * @page_4: Page_4 statistics structure: congestion points + * @page_4.cgr_reject_frames: number of rejected frames due to congestion point + * @page_4.cgr_reject_bytes: number of rejected bytes due to congestion point + * @page_5: Page_5 statistics structure: policer + * @page_5.policer_cnt_red: NUmber of red colored frames + * @page_5.policer_cnt_yellow: number of yellow colored frames + * @page_5.policer_cnt_green: number of green colored frames + * @page_5.policer_cnt_re_red: number of recolored red frames + * @page_5.policer_cnt_re_yellow: number of recolored yellow frames + * @page_6: Page_6 statistics structure + * @page_6.tx_pending_frames: total number of frames pending in egress FQs * @raw: raw statistics structure, used to index counters */ union dpni_statistics { @@ -443,6 +463,26 @@ union dpni_statistics { u64 egress_confirmed_frames; } page_2; struct { + u64 egress_dequeue_bytes; + u64 egress_dequeue_frames; + u64 egress_reject_bytes; + u64 egress_reject_frames; + } page_3; + struct { + u64 cgr_reject_frames; + u64 cgr_reject_bytes; + } page_4; + struct { + u64 policer_cnt_red; + u64 policer_cnt_yellow; + u64 policer_cnt_green; + u64 policer_cnt_re_red; + u64 policer_cnt_re_yellow; + } page_5; + struct { + u64 tx_pending_frames; + } page_6; + struct { u64 counter[DPNI_STATISTICS_CNT]; } raw; }; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index bf9aa533a7c6..4da0cde9695b 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -35,9 +35,9 @@ struct ice_aqc_get_ver { /* Queue Shutdown (direct 0x0003) */ struct ice_aqc_q_shutdown { - __le32 driver_unloading; + u8 driver_unloading; #define ICE_AQC_DRIVER_UNLOADING BIT(0) - u8 reserved[12]; + u8 reserved[15]; }; /* Request resource ownership (direct 0x0008) @@ -91,6 +91,7 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_SRIOV 0x0012 #define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 +#define ICE_AQC_CAPS_DCB 0x0018 #define ICE_AQC_CAPS_RSS 0x0040 #define ICE_AQC_CAPS_RXQS 0x0041 #define ICE_AQC_CAPS_TXQS 0x0042 diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 302ad981129c..9492cd34b09d 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1275,7 +1275,7 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown); if (unloading) - cmd->driver_unloading = cpu_to_le32(ICE_AQC_DRIVER_UNLOADING); + cmd->driver_unloading = ICE_AQC_DRIVER_UNLOADING; return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } @@ -1594,6 +1594,18 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, prefix, func_p->guar_num_vsi); } break; + case ICE_AQC_CAPS_DCB: + caps->dcb = (number == 1); + caps->active_tc_bitmap = logical_id; + caps->maxtc = phys_id; + ice_debug(hw, ICE_DBG_INIT, + "%s: DCB = %d\n", prefix, caps->dcb); + ice_debug(hw, ICE_DBG_INIT, + "%s: active TC bitmap = %d\n", prefix, + caps->active_tc_bitmap); + ice_debug(hw, ICE_DBG_INIT, + "%s: TC max = %d\n", prefix, caps->maxtc); + break; case ICE_AQC_CAPS_RSS: caps->rss_table_size = number; caps->rss_table_entry_width = logical_id; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index d60c942249e8..c5ee8d930611 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -444,9 +444,15 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv, * |pg0|pg1|pg2|pg3|pg4|pg5|pg6|pg7| * --------------------------------- */ - ice_for_each_traffic_class(i) + ice_for_each_traffic_class(i) { etscfg->tcbwtable[i] = buf[offset++]; + if (etscfg->prio_table[i] == ICE_CEE_PGID_STRICT) + dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT; + else + dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS; + } + /* Number of TCs supported (1 octet) */ etscfg->maxtcs = buf[offset]; } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index d9578919aad8..e922adf1fa15 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -413,7 +413,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked) memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg)); dcbcfg->etscfg.willing = 1; - dcbcfg->etscfg.maxtcs = 8; + dcbcfg->etscfg.maxtcs = hw->func_caps.common_cap.maxtc; dcbcfg->etscfg.tcbwtable[0] = 100; dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS; @@ -422,7 +422,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked) dcbcfg->etsrec.willing = 0; dcbcfg->pfc.willing = 1; - dcbcfg->pfc.pfccap = IEEE_8021QAZ_MAX_TCS; + dcbcfg->pfc.pfccap = hw->func_caps.common_cap.maxtc; dcbcfg->numapps = 1; dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE; @@ -452,11 +452,18 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) port_info = hw->port_info; err = ice_init_dcb(hw); + if (err && !port_info->is_sw_lldp) { + dev_err(&pf->pdev->dev, "Error initializing DCB %d\n", err); + goto dcb_init_err; + } + + dev_info(&pf->pdev->dev, + "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n", + pf->hw.func_caps.common_cap.maxtc); if (err) { /* FW LLDP is disabled, activate SW DCBX/LLDP mode */ dev_info(&pf->pdev->dev, "FW LLDP is disabled, DCBx/LLDP in SW mode.\n"); - port_info->is_sw_lldp = true; clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); err = ice_dcb_sw_dflt_cfg(pf, locked); if (err) { @@ -468,11 +475,9 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - set_bit(ICE_FLAG_DCB_ENA, pf->flags); return 0; } - port_info->is_sw_lldp = false; set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); /* DCBX in FW and LLDP enabled in FW */ @@ -484,7 +489,6 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) if (err) goto dcb_init_err; - dev_info(&pf->pdev->dev, "DCBX offload supported\n"); return err; dcb_init_err: diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index f7dd0bd03d39..edba5bd79097 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3253,25 +3253,25 @@ static int ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, struct ice_ring_container *rc, struct ice_vsi *vsi) { + const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx"; + u32 use_adaptive_coalesce, coalesce_usecs; struct ice_pf *pf = vsi->back; u16 itr_setting; if (!rc->ring) return -EINVAL; - itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; - switch (c_type) { case ICE_RX_CONTAINER: if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL || (ec->rx_coalesce_usecs_high && ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) { netdev_info(vsi->netdev, - "Invalid value, rx-usecs-high valid values are 0 (disabled), %d-%d\n", - pf->hw.intrl_gran, ICE_MAX_INTRL); + "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n", + c_type_str, pf->hw.intrl_gran, + ICE_MAX_INTRL); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) { rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high; wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx), @@ -3279,60 +3279,60 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, pf->hw.intrl_gran)); } - if (ec->rx_coalesce_usecs != itr_setting && - ec->use_adaptive_rx_coalesce) { - netdev_info(vsi->netdev, - "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); - return -EINVAL; - } + use_adaptive_coalesce = ec->use_adaptive_rx_coalesce; + coalesce_usecs = ec->rx_coalesce_usecs; - if (ec->rx_coalesce_usecs > ICE_ITR_MAX) { - netdev_info(vsi->netdev, - "Invalid value, rx-usecs range is 0-%d\n", - ICE_ITR_MAX); - return -EINVAL; - } - - if (ec->use_adaptive_rx_coalesce) { - rc->itr_setting |= ICE_ITR_DYNAMIC; - } else { - rc->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); - rc->target_itr = ITR_TO_REG(rc->itr_setting); - } break; case ICE_TX_CONTAINER: if (ec->tx_coalesce_usecs_high) { netdev_info(vsi->netdev, - "setting tx-usecs-high is not supported\n"); - return -EINVAL; - } - - if (ec->tx_coalesce_usecs != itr_setting && - ec->use_adaptive_tx_coalesce) { - netdev_info(vsi->netdev, - "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); + "setting %s-usecs-high is not supported\n", + c_type_str); return -EINVAL; } - if (ec->tx_coalesce_usecs > ICE_ITR_MAX) { - netdev_info(vsi->netdev, - "Invalid value, tx-usecs range is 0-%d\n", - ICE_ITR_MAX); - return -EINVAL; - } + use_adaptive_coalesce = ec->use_adaptive_tx_coalesce; + coalesce_usecs = ec->tx_coalesce_usecs; - if (ec->use_adaptive_tx_coalesce) { - rc->itr_setting |= ICE_ITR_DYNAMIC; - } else { - rc->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - rc->target_itr = ITR_TO_REG(rc->itr_setting); - } break; default: dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type); return -EINVAL; } + itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; + if (coalesce_usecs != itr_setting && use_adaptive_coalesce) { + netdev_info(vsi->netdev, + "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n", + c_type_str, c_type_str); + return -EINVAL; + } + + if (coalesce_usecs > ICE_ITR_MAX) { + netdev_info(vsi->netdev, + "Invalid value, %s-usecs range is 0-%d\n", + c_type_str, ICE_ITR_MAX); + return -EINVAL; + } + + /* hardware only supports an ITR granularity of 2us */ + if (coalesce_usecs % 2 != 0) { + netdev_info(vsi->netdev, + "Invalid value, %s-usecs must be even\n", + c_type_str); + return -EINVAL; + } + + if (use_adaptive_coalesce) { + rc->itr_setting |= ICE_ITR_DYNAMIC; + } else { + /* store user facing value how it was set */ + rc->itr_setting = coalesce_usecs; + /* set to static and convert to value HW understands */ + rc->target_itr = + ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting)); + } + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f029aee32913..50a17a0337be 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -567,6 +567,8 @@ static void ice_reset_subtask(struct ice_pf *pf) reset_type = ICE_RESET_CORER; if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state)) reset_type = ICE_RESET_GLOBR; + if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state)) + reset_type = ICE_RESET_EMPR; /* return if no valid reset type requested */ if (reset_type == ICE_RESET_INVAL) return; @@ -612,6 +614,22 @@ static void ice_reset_subtask(struct ice_pf *pf) } /** + * ice_print_topo_conflict - print topology conflict message + * @vsi: the VSI whose topology status is being checked + */ +static void ice_print_topo_conflict(struct ice_vsi *vsi) +{ + switch (vsi->port_info->phy.link_info.topo_media_conflict) { + case ICE_AQ_LINK_TOPO_CONFLICT: + case ICE_AQ_LINK_MEDIA_CONFLICT: + netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n"); + break; + default: + break; + } +} + +/** * ice_print_link_msg - print link up or down message * @vsi: the VSI whose link status is being queried * @isup: boolean for if the link is now up or down @@ -624,6 +642,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) const char *speed; const char *fec; const char *fc; + const char *an; if (!vsi) return; @@ -707,6 +726,12 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) break; } + /* check if autoneg completed, might be false due to not supported */ + if (vsi->port_info->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) + an = "True"; + else + an = "False"; + /* Get FEC mode requested based on PHY caps last SW configuration */ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); if (!caps) { @@ -731,8 +756,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) devm_kfree(&vsi->back->pdev->dev, caps); done: - netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Flow Control: %s\n", - speed, fec_req, fec, fc); + netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n", + speed, fec_req, fec, an, fc); + ice_print_topo_conflict(vsi); } /** @@ -2636,6 +2662,11 @@ static void ice_remove(struct pci_dev *pdev) ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); ice_clear_interrupt_scheme(pf); + /* Issue a PFR as part of the prescribed driver unload flow. Do not + * do it via ice_schedule_reset() since there is no need to rebuild + * and the service task is already stopped. + */ + ice_reset(&pf->hw, ICE_RESET_PFR); pci_disable_pcie_error_reporting(pdev); } @@ -3446,12 +3477,16 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) vsi_stats = &vsi->net_stats; - if (test_bit(__ICE_DOWN, vsi->state) || !vsi->num_txq || !vsi->num_rxq) + if (!vsi->num_txq || !vsi->num_rxq) return; + /* netdev packet/byte stats come from ring counter. These are obtained * by summing up ring counters (done by ice_update_vsi_ring_stats). + * But, only call the update routine and read the registers if VSI is + * not down. */ - ice_update_vsi_ring_stats(vsi); + if (!test_bit(__ICE_DOWN, vsi->state)) + ice_update_vsi_ring_stats(vsi); stats->tx_packets = vsi_stats->tx_packets; stats->tx_bytes = vsi_stats->tx_bytes; stats->rx_packets = vsi_stats->rx_packets; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 99cf527d2b1a..1acdd43a2edd 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1623,12 +1623,13 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, ice_aqc_opc_remove_sw_rules, NULL); - if (status) - goto exit; /* Remove a book keeping from the list */ devm_kfree(ice_hw_to_dev(hw), s_rule); + if (status) + goto exit; + list_del(&list_elem->list_entry); devm_kfree(ice_hw_to_dev(hw), list_elem); } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index b538d0b9eb80..4501d50a7dcc 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -4,15 +4,15 @@ #ifndef _ICE_TYPE_H_ #define _ICE_TYPE_H_ +#define ICE_BYTES_PER_WORD 2 +#define ICE_BYTES_PER_DWORD 4 + #include "ice_status.h" #include "ice_hw_autogen.h" #include "ice_osdep.h" #include "ice_controlq.h" #include "ice_lan_tx_rx.h" -#define ICE_BYTES_PER_WORD 2 -#define ICE_BYTES_PER_DWORD 4 - static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { return test_bit(tc, &bitmap); @@ -139,6 +139,9 @@ struct ice_phy_info { /* Common HW capabilities for SW use */ struct ice_hw_common_caps { u32 valid_functions; + /* DCB capabilities */ + u32 active_tc_bitmap; + u32 maxtc; /* Tx/Rx queues */ u16 num_rxq; /* Number/Total Rx queues */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index b93324e9f4bc..c38939b1d496 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -1074,9 +1074,16 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) for (v = 0; v < pf->num_alloc_vfs; v++) ice_trigger_vf_reset(&pf->vf[v], is_vflr); - for (v = 0; v < pf->num_alloc_vfs; v++) - if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[v].vf_states)) - ice_dis_vf_qs(&pf->vf[v]); + for (v = 0; v < pf->num_alloc_vfs; v++) { + struct ice_vsi *vsi; + + vf = &pf->vf[v]; + vsi = pf->vsi[vf->lan_vsi_idx]; + if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) + ice_dis_vf_qs(vf); + ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, + NULL, ICE_VF_RESET, vf->vf_id, NULL); + } /* HW requires some time to make sure it can flush the FIFO for a VF * when it resets it. Poll the VPGEN_VFRSTAT register for each VF in @@ -1171,12 +1178,12 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) ice_dis_vf_qs(vf); - else - /* Call Disable LAN Tx queue AQ call even when queues are not - * enabled. This is needed for successful completion of VFR - */ - ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, - NULL, ICE_VF_RESET, vf->vf_id, NULL); + + /* Call Disable LAN Tx queue AQ whether or not queues are + * enabled. This is needed for successful completion of VFR. + */ + ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, + NULL, ICE_VF_RESET, vf->vf_id, NULL); hw = &pf->hw; /* poll VPGEN_VFRSTAT reg to make sure @@ -2760,8 +2767,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) } vf->num_vlan--; - /* Disable VLAN pruning when removing VLAN */ - ice_cfg_vlan_pruning(vsi, false, false); + /* Disable VLAN pruning when the last VLAN is removed */ + if (!vf->num_vlan) + ice_cfg_vlan_pruning(vsi, false, false); /* Disable Unicast/Multicast VLAN promiscuous mode */ if (vlan_promisc) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 37fef8cd25e3..0d8dd885b7d6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -154,3 +154,10 @@ config MLX5_EN_TLS Build support for TLS cryptography-offload accelaration in the NIC. Note: Support for hardware with this capability needs to be selected for this option to become available. + +config MLX5_SW_STEERING + bool "Mellanox Technologies software-managed steering" + depends on MLX5_CORE_EN && MLX5_ESWITCH + default y + help + Build support for software-managed steering in the NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index f4de9ccb5df1..5708fcc079ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -15,7 +15,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.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 diag/fs_tracepoint.o \ + lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o # @@ -67,3 +67,10 @@ mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o \ en_accel/ktls.o en_accel/ktls_tx.o + +mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ + steering/dr_matcher.o steering/dr_rule.o \ + steering/dr_icm_pool.o steering/dr_crc32.o \ + steering/dr_ste.o steering/dr_send.o \ + steering/dr_cmd.o steering/dr_fw.o \ + steering/dr_action.o steering/fs_dr.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index a400f4430c28..7bf7b6fbc776 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -4,6 +4,7 @@ #include <devlink.h> #include "mlx5_core.h" +#include "fs_core.h" #include "eswitch.h" static int mlx5_devlink_flash_update(struct devlink *devlink, @@ -107,12 +108,121 @@ void mlx5_devlink_free(struct devlink *devlink) devlink_free(devlink); } +static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + char *value = val.vstr; + int err = 0; + + if (!strcmp(value, "dmfs")) { + return 0; + } else if (!strcmp(value, "smfs")) { + u8 eswitch_mode; + bool smfs_cap; + + eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch); + smfs_cap = mlx5_fs_dr_is_supported(dev); + + if (!smfs_cap) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG_MOD(extack, + "Software managed steering is not supported by current device"); + } + + else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_MOD(extack, + "Software managed steering is not supported when eswitch offlaods enabled."); + err = -EOPNOTSUPP; + } + } else { + NL_SET_ERR_MSG_MOD(extack, + "Bad parameter: supported values are [\"dmfs\", \"smfs\"]"); + err = -EINVAL; + } + + return err; +} + +static int mlx5_devlink_fs_mode_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + enum mlx5_flow_steering_mode mode; + + if (!strcmp(ctx->val.vstr, "smfs")) + mode = MLX5_FLOW_STEERING_MODE_SMFS; + else + mode = MLX5_FLOW_STEERING_MODE_DMFS; + dev->priv.steering->mode = mode; + + return 0; +} + +static int mlx5_devlink_fs_mode_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) + strcpy(ctx->val.vstr, "smfs"); + else + strcpy(ctx->val.vstr, "dmfs"); + return 0; +} + +enum mlx5_devlink_param_id { + MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, +}; + +static const struct devlink_param mlx5_devlink_params[] = { + DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set, + mlx5_devlink_fs_mode_validate), +}; + +static void mlx5_devlink_set_params_init_values(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + + if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS) + strcpy(value.vstr, "dmfs"); + else + strcpy(value.vstr, "smfs"); + devlink_param_driverinit_value_set(devlink, + MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + value); +} + int mlx5_devlink_register(struct devlink *devlink, struct device *dev) { - return devlink_register(devlink, dev); + int err; + + err = devlink_register(devlink, dev); + if (err) + return err; + + err = devlink_params_register(devlink, mlx5_devlink_params, + ARRAY_SIZE(mlx5_devlink_params)); + if (err) + goto params_reg_err; + mlx5_devlink_set_params_init_values(devlink); + devlink_params_publish(devlink); + return 0; + +params_reg_err: + devlink_unregister(devlink); + return err; } void mlx5_devlink_unregister(struct devlink *devlink) { + devlink_params_unregister(devlink, mlx5_devlink_params, + ARRAY_SIZE(mlx5_devlink_params)); devlink_unregister(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 4c4620db3d31..f8ee18b4da6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -291,14 +291,14 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, */ goto out; } - - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv4_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); @@ -407,13 +407,14 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto out; } - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv6_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index a0ae5069d8c3..8e512216deb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -161,7 +161,7 @@ struct mlx5e_encap_entry { */ struct hlist_node encap_hlist; struct list_head flows; - u32 encap_id; + struct mlx5_pkt_reformat *pkt_reformat; const struct ip_tunnel_info *tun_info; unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 5581a8045ede..30d26eba75a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -61,7 +61,7 @@ struct mlx5_nic_flow_attr { u32 action; u32 flow_tag; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u32 hairpin_tirn; u8 match_level; struct mlx5_flow_table *hairpin_ft; @@ -201,7 +201,7 @@ struct mlx5e_mod_hdr_entry { struct mod_hdr_key key; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; refcount_t refcnt; struct completion res_ready; @@ -334,7 +334,7 @@ static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, WARN_ON(!list_empty(&mh->flows)); if (mh->compl_result > 0) - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); + mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr); kfree(mh); } @@ -395,11 +395,11 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); mutex_unlock(&tbl->lock); - err = mlx5_modify_header_alloc(priv->mdev, namespace, - mh->key.num_actions, - mh->key.actions, - &mh->mod_hdr_id); - if (err) { + mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace, + mh->key.num_actions, + mh->key.actions); + if (IS_ERR(mh->modify_hdr)) { + err = PTR_ERR(mh->modify_hdr); mh->compl_result = err; goto alloc_header_err; } @@ -412,9 +412,9 @@ attach_flow: list_add(&flow->mod_hdr, &mh->flows); spin_unlock(&mh->flows_lock); if (mlx5e_is_eswitch_flow(flow)) - flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; + flow->esw_attr->modify_hdr = mh->modify_hdr; else - flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; + flow->nic_attr->modify_hdr = mh->modify_hdr; return 0; @@ -906,7 +906,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5_flow_destination dest[2] = {}; struct mlx5_flow_act flow_act = { .action = attr->action, - .reformat_id = 0, .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_fc *counter = NULL; @@ -947,7 +946,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; kfree(parse_attr->mod_hdr_actions); if (err) return err; @@ -1304,14 +1303,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; int err; - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) { - mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n", - err); + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + e->encap_size, e->encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", + PTR_ERR(e->pkt_reformat)); return; } e->flags |= MLX5_ENCAP_ENTRY_VALID; @@ -1326,7 +1324,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, esw_attr = flow->esw_attr; spec = &esw_attr->parse_attr->spec; - esw_attr->dests[flow->tmp_efi_index].encap_id = e->encap_id; + esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat; esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; /* Flow can be associated with multiple encap entries. * Before offloading the flow verify that all of them have @@ -1395,7 +1393,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) @@ -1561,7 +1559,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } kfree(e->encap_header); @@ -1896,7 +1894,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } } else if (*match_level != MLX5_MATCH_NONE) { - MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); + /* cvlan_tag enabled in match criteria and + * disabled in match value means both S & C tags + * don't exist (untagged of both) + */ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); *match_level = MLX5_MATCH_L2; } @@ -3045,7 +3046,7 @@ attach_flow: flow->encaps[out_index].index = out_index; *encap_dev = e->out_dev; if (e->flags & MLX5_ENCAP_ENTRY_VALID) { - attr->dests[out_index].encap_id = e->encap_id; + attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; *encap_valid = true; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index aba9e7a6ad3c..6bd6f5895244 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -69,7 +69,7 @@ struct vport_ingress { struct mlx5_flow_group *allow_spoofchk_only_grp; struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; - int modify_metadata_id; + struct mlx5_modify_hdr *modify_metadata; struct mlx5_flow_handle *modify_metadata_rule; struct mlx5_flow_handle *allow_rule; struct mlx5_flow_handle *drop_rule; @@ -153,6 +153,7 @@ struct mlx5_eswitch_fdb { } legacy; struct offloads_fdb { + struct mlx5_flow_namespace *ns; struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *peer_miss_grp; @@ -385,11 +386,11 @@ struct mlx5_esw_flow_attr { struct { u32 flags; struct mlx5_eswitch_rep *rep; + struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; - u32 encap_id; struct mlx5_termtbl_handle *termtbl; } dests[MLX5_MAX_FLOW_FWD_VPORTS]; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u8 inner_match_level; u8 outer_match_level; struct mlx5_fc *counter; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 7d3582ee66b7..afa623b15a38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -190,10 +190,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - flow_act.reformat_id = attr->dests[j].encap_id; + flow_act.pkt_reformat = attr->dests[j].pkt_reformat; dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = - attr->dests[j].encap_id; + dest[i].vport.pkt_reformat = + attr->dests[j].pkt_reformat; } i++; } @@ -213,7 +213,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split); if (IS_ERR(fdb)) { @@ -276,7 +276,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) { dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = attr->dests[i].encap_id; + dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat; } } dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -1068,6 +1068,13 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) err = -EOPNOTSUPP; goto ns_err; } + esw->fdb_table.offloads.ns = root_ns; + err = mlx5_flow_namespace_set_mode(root_ns, + esw->dev->priv.steering->mode); + if (err) { + esw_warn(dev, "Failed to set FDB namespace steering mode\n"); + goto ns_err; + } max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) | MLX5_CAP_GEN(dev, max_flow_counter_15_0); @@ -1207,6 +1214,8 @@ send_vport_err: esw_destroy_offloads_fast_fdb_tables(esw); mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); slow_fdb_err: + /* Holds true only as long as DMFS is the default */ + mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS); ns_err: kvfree(flow_group_in); return err; @@ -1226,6 +1235,9 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); esw_destroy_offloads_fast_fdb_tables(esw); + /* Holds true only as long as DMFS is the default */ + mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, + MLX5_FLOW_STEERING_MODE_DMFS); } static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) @@ -1623,13 +1635,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) esw_del_fdb_peer_miss_rules(esw); } +static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw, + bool pair) +{ + struct mlx5_flow_root_namespace *peer_ns; + struct mlx5_flow_root_namespace *ns; + int err; + + peer_ns = peer_esw->dev->priv.steering->fdb_root_ns; + ns = esw->dev->priv.steering->fdb_root_ns; + + if (pair) { + err = mlx5_flow_namespace_set_peer(ns, peer_ns); + if (err) + return err; + + mlx5_flow_namespace_set_peer(peer_ns, ns); + if (err) { + mlx5_flow_namespace_set_peer(ns, NULL); + return err; + } + } else { + mlx5_flow_namespace_set_peer(ns, NULL); + mlx5_flow_namespace_set_peer(peer_ns, NULL); + } + + return 0; +} + static int mlx5_esw_offloads_devcom_event(int event, void *my_data, void *event_data) { struct mlx5_eswitch *esw = my_data; - struct mlx5_eswitch *peer_esw = event_data; struct mlx5_devcom *devcom = esw->dev->priv.devcom; + struct mlx5_eswitch *peer_esw = event_data; int err; switch (event) { @@ -1638,9 +1679,12 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; - err = mlx5_esw_offloads_pair(esw, peer_esw); + err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); if (err) goto err_out; + err = mlx5_esw_offloads_pair(esw, peer_esw); + if (err) + goto err_peer; err = mlx5_esw_offloads_pair(peer_esw, esw); if (err) @@ -1656,6 +1700,7 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); mlx5_esw_offloads_unpair(peer_esw); mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); break; } @@ -1663,7 +1708,8 @@ static int mlx5_esw_offloads_devcom_event(int event, err_pair: mlx5_esw_offloads_unpair(esw); - +err_peer: + mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); err_out: mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d", event, err); @@ -1734,7 +1780,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw, if (vport->ingress.modify_metadata_rule) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; } vport->ingress.allow_rule = @@ -1770,9 +1816,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, MLX5_SET(set_action_in, action, data, mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport)); - err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, - 1, action, &vport->ingress.modify_metadata_id); - if (err) { + vport->ingress.modify_metadata = + mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + 1, action); + if (IS_ERR(vport->ingress.modify_metadata)) { + err = PTR_ERR(vport->ingress.modify_metadata); esw_warn(esw->dev, "failed to alloc modify header for vport %d ingress acl (%d)\n", vport->vport, err); @@ -1780,7 +1828,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl, &spec, &flow_act, NULL, 0); if (IS_ERR(vport->ingress.modify_metadata_rule)) { @@ -1794,7 +1842,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, out: if (err) - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); return err; } @@ -1803,7 +1851,7 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, { if (vport->ingress.modify_metadata_rule) { mlx5_del_flow_rules(vport->ingress.modify_metadata_rule); - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); vport->ingress.modify_metadata_rule = NULL; } @@ -2113,9 +2161,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) else esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; + mlx5_rdma_enable_roce(esw->dev); err = esw_offloads_steering_init(esw); if (err) - return err; + goto err_steering_init; err = esw_set_passing_vport_metadata(esw, true); if (err) @@ -2130,8 +2179,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) esw_offloads_devcom_init(esw); mutex_init(&esw->offloads.termtbl_mutex); - mlx5_rdma_enable_roce(esw->dev); - return 0; err_reps: @@ -2139,6 +2186,8 @@ err_reps: esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); +err_steering_init: + mlx5_rdma_disable_roce(esw->dev); return err; } @@ -2163,12 +2212,12 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, void esw_offloads_disable(struct mlx5_eswitch *esw) { - mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw); mlx5_eswitch_disable_pf_vf_vports(esw); esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); + mlx5_rdma_disable_roce(esw->dev); esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1e3381604b3d..579c306caa7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -107,6 +107,50 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns, return 0; } +static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + return 0; +} + +static void mlx5_cmd_stub_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ +} + +static int mlx5_cmd_stub_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + return 0; +} + +static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ +} + +static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + return 0; +} + +static int mlx5_cmd_stub_create_ns(struct mlx5_flow_root_namespace *ns) +{ + return 0; +} + +static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + return 0; +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -412,11 +456,13 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, } else { MLX5_SET(flow_context, in_flow_context, action, fte->action.action); - MLX5_SET(flow_context, in_flow_context, packet_reformat_id, - fte->action.reformat_id); + if (fte->action.pkt_reformat) + MLX5_SET(flow_context, in_flow_context, packet_reformat_id, + fte->action.pkt_reformat->id); } - MLX5_SET(flow_context, in_flow_context, modify_header_id, - fte->action.modify_id); + if (fte->action.modify_hdr) + MLX5_SET(flow_context, in_flow_context, modify_header_id, + fte->action.modify_hdr->id); vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan); @@ -468,7 +514,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_FLOW_DEST_VPORT_REFORMAT_ID)); MLX5_SET(extended_dest_format, in_dests, packet_reformat_id, - dst->dest_attr.vport.reformat_id); + dst->dest_attr.vport.pkt_reformat->id); } break; default: @@ -643,14 +689,15 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id) +static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) { u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; void *packet_reformat_context_in; int max_encap_size; void *reformat; @@ -693,35 +740,36 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out, - out, packet_reformat_id); + pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out, + out, packet_reformat_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_packet_reformat_alloc); -void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id) +static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) { u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, - packet_reformat_id); + pkt_reformat->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id) +static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) { u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)]; int max_actions, actions_size, inlen, err; + struct mlx5_core_dev *dev = ns->dev; void *actions_in; u8 table_type; u32 *in; @@ -772,26 +820,26 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); + modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_modify_header_alloc); -void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id) +static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) { u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_modify_header_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT); MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id, - modify_header_id); + modify_hdr->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_modify_header_dealloc); static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, @@ -803,6 +851,13 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .update_fte = mlx5_cmd_update_fte, .delete_fte = mlx5_cmd_delete_fte, .update_root_ft = mlx5_cmd_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_modify_header_dealloc, + .set_peer = mlx5_cmd_stub_set_peer, + .create_ns = mlx5_cmd_stub_create_ns, + .destroy_ns = mlx5_cmd_stub_destroy_ns, }; static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { @@ -815,9 +870,16 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .update_fte = mlx5_cmd_stub_update_fte, .delete_fte = mlx5_cmd_stub_delete_fte, .update_root_ft = mlx5_cmd_stub_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc, + .set_peer = mlx5_cmd_stub_set_peer, + .create_ns = mlx5_cmd_stub_create_ns, + .destroy_ns = mlx5_cmd_stub_destroy_ns, }; -static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) { return &mlx5_flow_cmds; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index bc4606306009..d62de642eca9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -75,6 +75,30 @@ struct mlx5_flow_cmds { struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect); + + int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat); + + void (*packet_reformat_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat); + + int (*modify_header_alloc)(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr); + + void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr); + + int (*set_peer)(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns); + + int (*create_ns)(struct mlx5_flow_root_namespace *ns); + int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); @@ -90,5 +114,6 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 7bdec442f0ac..3bbb49354829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1415,7 +1415,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ? (d1->vport.vhca_id == d2->vport.vhca_id) : true) && ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ? - (d1->vport.reformat_id == d2->vport.reformat_id) : true)) || + (d1->vport.pkt_reformat->id == + d2->vport.pkt_reformat->id) : true)) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -2888,3 +2889,160 @@ out: return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); + +static struct mlx5_flow_root_namespace +*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_flow_namespace *ns; + + if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS || + ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS) + ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0); + else + ns = mlx5_get_flow_namespace(dev, ns_type); + if (!ns) + return NULL; + + return find_root(&ns->node); +} + +struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 ns_type, u8 num_actions, + void *modify_actions) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_modify_hdr *modify_hdr; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + modify_hdr = kzalloc(sizeof(*modify_hdr), GFP_KERNEL); + if (!modify_hdr) + return ERR_PTR(-ENOMEM); + + modify_hdr->ns_type = ns_type; + err = root->cmds->modify_header_alloc(root, ns_type, num_actions, + modify_actions, modify_hdr); + if (err) { + kfree(modify_hdr); + return ERR_PTR(err); + } + + return modify_hdr; +} +EXPORT_SYMBOL(mlx5_modify_header_alloc); + +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, modify_hdr->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->modify_header_dealloc(root, modify_hdr); + kfree(modify_hdr); +} +EXPORT_SYMBOL(mlx5_modify_header_dealloc); + +struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_pkt_reformat *pkt_reformat; + struct mlx5_flow_root_namespace *root; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + pkt_reformat = kzalloc(sizeof(*pkt_reformat), GFP_KERNEL); + if (!pkt_reformat) + return ERR_PTR(-ENOMEM); + + pkt_reformat->ns_type = ns_type; + pkt_reformat->reformat_type = reformat_type; + err = root->cmds->packet_reformat_alloc(root, reformat_type, size, + reformat_data, ns_type, + pkt_reformat); + if (err) { + kfree(pkt_reformat); + return ERR_PTR(err); + } + + return pkt_reformat; +} +EXPORT_SYMBOL(mlx5_packet_reformat_alloc); + +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, pkt_reformat->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->packet_reformat_dealloc(root, pkt_reformat); + kfree(pkt_reformat); +} +EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); + +int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + if (peer_ns && ns->mode != peer_ns->mode) { + mlx5_core_err(ns->dev, + "Can't peer namespace of different steering mode\n"); + return -EINVAL; + } + + return ns->cmds->set_peer(ns, peer_ns); +} + +/* This function should be called only at init stage of the namespace. + * It is not safe to call this function while steering operations + * are executed in the namespace. + */ +int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, + enum mlx5_flow_steering_mode mode) +{ + struct mlx5_flow_root_namespace *root; + const struct mlx5_flow_cmds *cmds; + int err; + + root = find_root(&ns->node); + if (&root->ns != ns) + /* Can't set cmds to non root namespace */ + return -EINVAL; + + if (root->table_type != FS_FT_FDB) + return -EOPNOTSUPP; + + if (root->mode == mode) + return 0; + + if (mode == MLX5_FLOW_STEERING_MODE_SMFS) + cmds = mlx5_fs_cmd_get_dr_cmds(); + else + cmds = mlx5_fs_cmd_get_fw_cmds(); + if (!cmds) + return -EOPNOTSUPP; + + err = cmds->create_ns(root); + if (err) { + mlx5_core_err(root->dev, "Failed to create flow namespace (%d)\n", + err); + return err; + } + + root->cmds->destroy_ns(root); + root->cmds = cmds; + root->mode = mode; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 0d16b4b5ab83..00717eba2256 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -37,6 +37,24 @@ #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> #include <linux/llist.h> +#include <steering/fs_dr.h> + +struct mlx5_modify_hdr { + enum mlx5_flow_namespace_type ns_type; + union { + struct mlx5_fs_dr_action action; + u32 id; + }; +}; + +struct mlx5_pkt_reformat { + enum mlx5_flow_namespace_type ns_type; + int reformat_type; /* from mlx5_ifc */ + union { + struct mlx5_fs_dr_action action; + u32 id; + }; +}; /* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only, * and those are in parallel to one another when going over them to connect @@ -80,9 +98,15 @@ enum fs_fte_status { FS_FTE_STATUS_EXISTING = 1UL << 0, }; +enum mlx5_flow_steering_mode { + MLX5_FLOW_STEERING_MODE_DMFS, + MLX5_FLOW_STEERING_MODE_SMFS +}; + struct mlx5_flow_steering { struct mlx5_core_dev *dev; - struct kmem_cache *fgs_cache; + enum mlx5_flow_steering_mode mode; + struct kmem_cache *fgs_cache; struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; @@ -128,6 +152,7 @@ struct mlx5_flow_handle { /* Type of children is mlx5_flow_group */ struct mlx5_flow_table { struct fs_node node; + struct mlx5_fs_dr_table fs_dr_table; u32 id; u16 vport; unsigned int max_fte; @@ -168,6 +193,7 @@ struct mlx5_ft_underlay_qp { /* Type of children is mlx5_flow_rule */ struct fs_fte { struct fs_node node; + struct mlx5_fs_dr_rule fs_dr_rule; u32 val[MLX5_ST_SZ_DW_MATCH_PARAM]; u32 dests_size; u32 index; @@ -203,6 +229,7 @@ struct mlx5_flow_group_mask { /* Type of children is fs_fte */ struct mlx5_flow_group { struct fs_node node; + struct mlx5_fs_dr_matcher fs_dr_matcher; struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; @@ -214,6 +241,8 @@ struct mlx5_flow_group { struct mlx5_flow_root_namespace { struct mlx5_flow_namespace ns; + enum mlx5_flow_steering_mode mode; + struct mlx5_fs_dr_domain fs_dr_domain; enum fs_flow_table_type table_type; struct mlx5_core_dev *dev; struct mlx5_flow_table *root_ft; @@ -231,6 +260,14 @@ void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev, void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, unsigned long interval); +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); + +int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns); + +int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, + enum mlx5_flow_steering_mode mode); + int mlx5_init_fs(struct mlx5_core_dev *dev); void mlx5_cleanup_fs(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c new file mode 100644 index 000000000000..e065c2f68f5a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2019 Mellanox Technologies + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/device.h> + +#include "mlx5_core.h" +#include "lib/mlx5.h" + +struct mlx5_dm { + /* protect access to icm bitmask */ + spinlock_t lock; + unsigned long *steering_sw_icm_alloc_blocks; + unsigned long *header_modify_sw_icm_alloc_blocks; +}; + +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) +{ + u64 header_modify_icm_blocks = 0; + u64 steering_icm_blocks = 0; + struct mlx5_dm *dm; + + if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) + return 0; + + dm = kzalloc(sizeof(*dm), GFP_KERNEL); + if (!dm) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&dm->lock); + + if (MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address)) { + steering_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->steering_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(steering_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->steering_sw_icm_alloc_blocks) + goto err_steering; + } + + if (MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address)) { + header_modify_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->header_modify_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(header_modify_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->header_modify_sw_icm_alloc_blocks) + goto err_modify_hdr; + } + + return dm; + +err_modify_hdr: + kfree(dm->steering_sw_icm_alloc_blocks); + +err_steering: + kfree(dm); + + return ERR_PTR(-ENOMEM); +} + +void mlx5_dm_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_dm *dm = dev->dm; + + if (!dev->dm) + return; + + if (dm->steering_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->steering_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->steering_sw_icm_alloc_blocks); + } + + if (dm->header_modify_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->header_modify_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->header_modify_sw_icm_alloc_blocks); + } + + kfree(dm); +} + +int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u32 log_icm_size; + u32 max_blocks; + u64 block_idx; + void *sw_icm; + int ret; + + if (!dev->dm) + return -EOPNOTSUPP; + + if (!length || (length & (length - 1)) || + length & (MLX5_SW_ICM_BLOCK_SIZE(dev) - 1)) + return -EINVAL; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + if (!block_map) + return -EOPNOTSUPP; + + max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + spin_lock(&dm->lock); + block_idx = bitmap_find_next_zero_area(block_map, + max_blocks, + 0, + num_blocks, 0); + + if (block_idx < max_blocks) + bitmap_set(block_map, + block_idx, num_blocks); + + spin_unlock(&dm->lock); + + if (block_idx >= max_blocks) + return -ENOMEM; + + sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm); + icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr, + icm_start_addr); + MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length)); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) { + spin_lock(&dm->lock); + bitmap_clear(block_map, + block_idx, num_blocks); + spin_unlock(&dm->lock); + + return ret; + } + + *addr = icm_start_addr; + *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_alloc); + +int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t addr, u32 obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u64 start_idx; + int err; + + if (!dev->dm) + return -EOPNOTSUPP; + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + start_idx = (addr - icm_start_addr) >> MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + spin_lock(&dm->lock); + bitmap_clear(block_map, + start_idx, num_blocks); + spin_unlock(&dm->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_dealloc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index dee1a8658c87..9648c2297803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -876,6 +876,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eswitch_cleanup; } + dev->dm = mlx5_dm_create(dev); + if (IS_ERR(dev->dm)) + mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + dev->tracer = mlx5_fw_tracer_create(dev); dev->hv_vhca = mlx5_hv_vhca_create(dev); @@ -910,6 +914,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); + mlx5_dm_cleanup(dev); mlx5_fpga_cleanup(dev); mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_sriov_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 87b75b2207c4..b100489dc85c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -198,6 +198,9 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode); +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev); +void mlx5_dm_cleanup(struct mlx5_core_dev *dev); + #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) && \ MLX5_CAP_GEN((mdev), pps_modify) && \ MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) && \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 18af6981e0be..0fc7de4aa572 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -14,9 +14,6 @@ static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev) { struct mlx5_core_roce *roce = &dev->priv.roce; - if (!roce->ft) - return; - mlx5_del_flow_rules(roce->allow_rule); mlx5_destroy_flow_group(roce->fg); mlx5_destroy_flow_table(roce->ft); @@ -145,6 +142,11 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev) void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) { + struct mlx5_core_roce *roce = &dev->priv.roce; + + if (!roce->ft) + return; + mlx5_rdma_disable_roce_steering(dev); mlx5_rdma_del_roce_addr(dev); mlx5_nic_vport_disable_roce(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile new file mode 100644 index 000000000000..c78512eed8d7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +subdir-ccflags-y += -I$(src)/.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c new file mode 100644 index 000000000000..a02f87f85c17 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -0,0 +1,1588 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +enum dr_action_domain { + DR_ACTION_DOMAIN_NIC_INGRESS, + DR_ACTION_DOMAIN_NIC_EGRESS, + DR_ACTION_DOMAIN_FDB_INGRESS, + DR_ACTION_DOMAIN_FDB_EGRESS, + DR_ACTION_DOMAIN_MAX, +}; + +enum dr_action_valid_state { + DR_ACTION_STATE_ERR, + DR_ACTION_STATE_NO_ACTION, + DR_ACTION_STATE_REFORMAT, + DR_ACTION_STATE_MODIFY_HDR, + DR_ACTION_STATE_MODIFY_VLAN, + DR_ACTION_STATE_NON_TERM, + DR_ACTION_STATE_TERM, + DR_ACTION_STATE_MAX, +}; + +static const enum dr_action_valid_state +next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] = { + [DR_ACTION_DOMAIN_NIC_INGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_NIC_EGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_FDB_INGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_FDB_EGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, +}; + +struct dr_action_modify_field_conv { + u16 hw_field; + u8 start; + u8 end; + u8 l3_type; + u8 l4_type; +}; + +static const struct dr_action_modify_field_conv dr_action_conv_arr[] = { + [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 16, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 32, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 16, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 0, .end = 5, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 48, .end = 56, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 0, .end = 15, + }, +}; + +#define MAX_VLANS 2 +struct dr_action_vlan_info { + int count; + u32 headers[MAX_VLANS]; +}; + +struct dr_action_apply_attr { + u32 modify_index; + u16 modify_actions; + u32 decap_index; + u16 decap_actions; + u8 decap_with_vlan:1; + u64 final_icm_addr; + u32 flow_tag; + u32 ctr_id; + u16 gvmi; + u16 hit_gvmi; + u32 reformat_id; + u32 reformat_size; + struct dr_action_vlan_info vlans; +}; + +static int +dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type, + enum mlx5dr_action_type *action_type) +{ + switch (reformat_type) { + case DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2: + *action_type = DR_ACTION_TYP_TNL_L2_TO_L2; + break; + case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2: + *action_type = DR_ACTION_TYP_L2_TO_TNL_L2; + break; + case DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2: + *action_type = DR_ACTION_TYP_TNL_L3_TO_L2; + break; + case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3: + *action_type = DR_ACTION_TYP_L2_TO_TNL_L3; + break; + default: + return -EINVAL; + } + + return 0; +} + +static void dr_actions_init_next_ste(u8 **last_ste, + u32 *added_stes, + enum mlx5dr_ste_entry_type entry_type, + u16 gvmi) +{ + (*added_stes)++; + *last_ste += DR_STE_SIZE; + mlx5dr_ste_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, entry_type, gvmi); +} + +static void dr_actions_apply_tx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *added_stes) +{ + bool encap = action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2] || + action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]; + + /* We want to make sure the modify header comes before L2 + * encapsulation. The reason for that is that we support + * modify headers for outer headers only + */ + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->modify_actions, + attr->modify_index); + } + + if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (i || action_type_set[DR_ACTION_TYP_MODIFY_HDR]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_TX, + attr->gvmi); + + mlx5dr_ste_set_tx_push_vlan(last_ste, + attr->vlans.headers[i], + encap); + } + } + + if (encap) { + /* Modify header and encapsulation require a different STEs. + * Since modify header STE format doesn't support encapsulation + * tunneling_action. + */ + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] || + action_type_set[DR_ACTION_TYP_PUSH_VLAN]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_TX, + attr->gvmi); + + mlx5dr_ste_set_tx_encap(last_ste, + attr->reformat_id, + attr->reformat_size, + action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]); + /* Whenever prio_tag_required enabled, we can be sure that the + * previous table (ACL) already push vlan to our packet, + * And due to HW limitation we need to set this bit, otherwise + * push vlan + reformat will not work. + */ + if (MLX5_CAP_GEN(dmn->mdev, prio_tag_required)) + mlx5dr_ste_set_go_back_bit(last_ste); + } + + if (action_type_set[DR_ACTION_TYP_CTR]) + mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id); +} + +static void dr_actions_apply_rx(u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *added_stes) +{ + if (action_type_set[DR_ACTION_TYP_CTR]) + mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id); + + if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) { + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + mlx5dr_ste_set_rx_decap_l3(last_ste, attr->decap_with_vlan); + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->decap_actions, + attr->decap_index); + } + + if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) + mlx5dr_ste_set_rx_decap(last_ste); + + if (action_type_set[DR_ACTION_TYP_POP_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (i || + action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2] || + action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_RX, + attr->gvmi); + + mlx5dr_ste_set_rx_pop_vlan(last_ste); + } + } + + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_MODIFY_PKT, + attr->gvmi); + else + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->modify_actions, + attr->modify_index); + } + + if (action_type_set[DR_ACTION_TYP_TAG]) { + if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_RX, + attr->gvmi); + + mlx5dr_ste_rx_set_flow_tag(last_ste, attr->flow_tag); + } +} + +/* Apply the actions on the rule STE array starting from the last_ste. + * Actions might require more than one STE, new_num_stes will return + * the new size of the STEs array, rule with actions. + */ +static void dr_actions_apply(struct mlx5dr_domain *dmn, + enum mlx5dr_ste_entry_type ste_type, + u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *new_num_stes) +{ + u32 added_stes = 0; + + if (ste_type == MLX5DR_STE_TYPE_RX) + dr_actions_apply_rx(action_type_set, last_ste, attr, &added_stes); + else + dr_actions_apply_tx(dmn, action_type_set, last_ste, attr, &added_stes); + + last_ste += added_stes * DR_STE_SIZE; + *new_num_stes += added_stes; + + mlx5dr_ste_set_hit_gvmi(last_ste, attr->hit_gvmi); + mlx5dr_ste_set_hit_addr(last_ste, attr->final_icm_addr, 1); +} + +static enum dr_action_domain +dr_action_get_action_domain(enum mlx5dr_domain_type domain, + enum mlx5dr_ste_entry_type ste_type) +{ + switch (domain) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + return DR_ACTION_DOMAIN_NIC_INGRESS; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + return DR_ACTION_DOMAIN_NIC_EGRESS; + case MLX5DR_DOMAIN_TYPE_FDB: + if (ste_type == MLX5DR_STE_TYPE_RX) + return DR_ACTION_DOMAIN_FDB_INGRESS; + return DR_ACTION_DOMAIN_FDB_EGRESS; + default: + WARN_ON(true); + return DR_ACTION_DOMAIN_MAX; + } +} + +static +int dr_action_validate_and_get_next_state(enum dr_action_domain action_domain, + u32 action_type, + u32 *state) +{ + u32 cur_state = *state; + + /* Check action state machine is valid */ + *state = next_action_state[action_domain][cur_state][action_type]; + + if (*state == DR_ACTION_STATE_ERR) + return -EOPNOTSUPP; + + return 0; +} + +static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, + struct mlx5dr_action *dest_action, + u64 *final_icm_addr) +{ + int ret; + + switch (dest_action->action_type) { + case DR_ACTION_TYP_FT: + /* Allow destination flow table only if table is a terminating + * table, since there is an *assumption* that in such case FW + * will recalculate the CS. + */ + if (dest_action->dest_tbl.is_fw_tbl) { + *final_icm_addr = dest_action->dest_tbl.fw_tbl.rx_icm_addr; + } else { + mlx5dr_dbg(dmn, + "Destination FT should be terminating when modify TTL is used\n"); + return -EINVAL; + } + break; + + case DR_ACTION_TYP_VPORT: + /* If destination is vport we will get the FW flow table + * that recalculates the CS and forwards to the vport. + */ + ret = mlx5dr_domain_cache_get_recalc_cs_ft_addr(dest_action->vport.dmn, + dest_action->vport.num, + final_icm_addr); + if (ret) { + mlx5dr_err(dmn, "Failed to get FW cs recalc flow table\n"); + return ret; + } + break; + + default: + break; + } + + return 0; +} + +#define WITH_VLAN_NUM_HW_ACTIONS 6 + +int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_action *actions[], + u32 num_actions, + u8 *ste_arr, + u32 *new_hw_ste_arr_sz) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + bool rx_rule = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + u8 action_type_set[DR_ACTION_TYP_MAX] = {}; + struct mlx5dr_action *dest_action = NULL; + u32 state = DR_ACTION_STATE_NO_ACTION; + struct dr_action_apply_attr attr = {}; + enum dr_action_domain action_domain; + bool recalc_cs_required = false; + u8 *last_ste; + int i, ret; + + attr.gvmi = dmn->info.caps.gvmi; + attr.hit_gvmi = dmn->info.caps.gvmi; + attr.final_icm_addr = nic_dmn->default_icm_addr; + action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->ste_type); + + for (i = 0; i < num_actions; i++) { + struct mlx5dr_action *action; + int max_actions_type = 1; + u32 action_type; + + action = actions[i]; + action_type = action->action_type; + + switch (action_type) { + case DR_ACTION_TYP_DROP: + attr.final_icm_addr = nic_dmn->drop_icm_addr; + break; + case DR_ACTION_TYP_FT: + dest_action = action; + if (!action->dest_tbl.is_fw_tbl) { + if (action->dest_tbl.tbl->dmn != dmn) { + mlx5dr_dbg(dmn, + "Destination table belongs to a different domain\n"); + goto out_invalid_arg; + } + if (action->dest_tbl.tbl->level <= matcher->tbl->level) { + mlx5dr_dbg(dmn, + "Destination table level should be higher than source table\n"); + goto out_invalid_arg; + } + attr.final_icm_addr = rx_rule ? + action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr : + action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr; + } else { + struct mlx5dr_cmd_query_flow_table_details output; + int ret; + + /* get the relevant addresses */ + if (!action->dest_tbl.fw_tbl.rx_icm_addr) { + ret = mlx5dr_cmd_query_flow_table(action->dest_tbl.fw_tbl.mdev, + action->dest_tbl.fw_tbl.ft->type, + action->dest_tbl.fw_tbl.ft->id, + &output); + if (!ret) { + action->dest_tbl.fw_tbl.tx_icm_addr = + output.sw_owner_icm_root_1; + action->dest_tbl.fw_tbl.rx_icm_addr = + output.sw_owner_icm_root_0; + } else { + mlx5dr_dbg(dmn, + "Failed mlx5_cmd_query_flow_table ret: %d\n", + ret); + return ret; + } + } + attr.final_icm_addr = rx_rule ? + action->dest_tbl.fw_tbl.rx_icm_addr : + action->dest_tbl.fw_tbl.tx_icm_addr; + } + break; + case DR_ACTION_TYP_QP: + mlx5dr_info(dmn, "Domain doesn't support QP\n"); + goto out_invalid_arg; + case DR_ACTION_TYP_CTR: + attr.ctr_id = action->ctr.ctr_id + + action->ctr.offeset; + break; + case DR_ACTION_TYP_TAG: + attr.flow_tag = action->flow_tag; + break; + case DR_ACTION_TYP_TNL_L2_TO_L2: + break; + case DR_ACTION_TYP_TNL_L3_TO_L2: + attr.decap_index = action->rewrite.index; + attr.decap_actions = action->rewrite.num_of_actions; + attr.decap_with_vlan = + attr.decap_actions == WITH_VLAN_NUM_HW_ACTIONS; + break; + case DR_ACTION_TYP_MODIFY_HDR: + attr.modify_index = action->rewrite.index; + attr.modify_actions = action->rewrite.num_of_actions; + recalc_cs_required = action->rewrite.modify_ttl; + break; + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + attr.reformat_size = action->reformat.reformat_size; + attr.reformat_id = action->reformat.reformat_id; + break; + case DR_ACTION_TYP_VPORT: + attr.hit_gvmi = action->vport.caps->vhca_gvmi; + dest_action = action; + if (rx_rule) { + /* Loopback on WIRE vport is not supported */ + if (action->vport.num == WIRE_PORT) + goto out_invalid_arg; + + attr.final_icm_addr = action->vport.caps->icm_address_rx; + } else { + attr.final_icm_addr = action->vport.caps->icm_address_tx; + } + break; + case DR_ACTION_TYP_POP_VLAN: + max_actions_type = MAX_VLANS; + attr.vlans.count++; + break; + case DR_ACTION_TYP_PUSH_VLAN: + max_actions_type = MAX_VLANS; + if (attr.vlans.count == MAX_VLANS) + return -EINVAL; + + attr.vlans.headers[attr.vlans.count++] = action->push_vlan.vlan_hdr; + break; + default: + goto out_invalid_arg; + } + + /* Check action duplication */ + if (++action_type_set[action_type] > max_actions_type) { + mlx5dr_dbg(dmn, "Action type %d supports only max %d time(s)\n", + action_type, max_actions_type); + goto out_invalid_arg; + } + + /* Check action state machine is valid */ + if (dr_action_validate_and_get_next_state(action_domain, + action_type, + &state)) { + mlx5dr_dbg(dmn, "Invalid action sequence provided\n"); + return -EOPNOTSUPP; + } + } + + *new_hw_ste_arr_sz = nic_matcher->num_of_builders; + last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); + + /* Due to a HW bug, modifying TTL on RX flows will cause an incorrect + * checksum calculation. In this case we will use a FW table to + * recalculate. + */ + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && + rx_rule && recalc_cs_required && dest_action) { + ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); + if (ret) { + mlx5dr_dbg(dmn, + "Failed to handle checksum recalculation err %d\n", + ret); + return ret; + } + } + + dr_actions_apply(dmn, + nic_dmn->ste_type, + action_type_set, + last_ste, + &attr, + new_hw_ste_arr_sz); + + return 0; + +out_invalid_arg: + return -EINVAL; +} + +#define CVLAN_ETHERTYPE 0x8100 +#define SVLAN_ETHERTYPE 0x88a8 +#define HDR_LEN_L2_ONLY 14 +#define HDR_LEN_L2_VLAN 18 +#define REWRITE_HW_ACTION_NUM 6 + +static int dr_actions_l2_rewrite(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action, + void *data, size_t data_sz) +{ + struct mlx5_ifc_l2_hdr_bits *l2_hdr = data; + u64 ops[REWRITE_HW_ACTION_NUM] = {}; + u32 hdr_fld_4b; + u16 hdr_fld_2b; + u16 vlan_type; + bool vlan; + int i = 0; + int ret; + + vlan = (data_sz != HDR_LEN_L2_ONLY); + + /* dmac_47_16 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 16); + hdr_fld_4b = MLX5_GET(l2_hdr, l2_hdr, dmac_47_16); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_4b); + i++; + + /* smac_47_16 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 16); + hdr_fld_4b = (MLX5_GET(l2_hdr, l2_hdr, smac_31_0) >> 16 | + MLX5_GET(l2_hdr, l2_hdr, smac_47_32) << 16); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_4b); + i++; + + /* dmac_15_0 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, dmac_15_0); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + i++; + + /* ethertype + (optional) vlan */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 32); + if (!vlan) { + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype); + MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_2b); + MLX5_SET(dr_action_hw_set, ops + i, destination_length, 16); + } else { + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype); + vlan_type = hdr_fld_2b == SVLAN_ETHERTYPE ? DR_STE_SVLAN : DR_STE_CVLAN; + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan); + hdr_fld_4b = (vlan_type << 16) | hdr_fld_2b; + MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_4b); + MLX5_SET(dr_action_hw_set, ops + i, destination_length, 18); + } + i++; + + /* smac_15_0 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, smac_31_0); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + i++; + + if (vlan) { + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan_type); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + i++; + } + + action->rewrite.data = (void *)ops; + action->rewrite.num_of_actions = i; + action->rewrite.chunk->byte_size = i * sizeof(*ops); + + ret = mlx5dr_send_postsend_action(dmn, action); + if (ret) { + mlx5dr_dbg(dmn, "Writing encapsulation action to ICM failed\n"); + return ret; + } + + return 0; +} + +static struct mlx5dr_action * +dr_action_create_generic(enum mlx5dr_action_type action_type) +{ + struct mlx5dr_action *action; + + action = kzalloc(sizeof(*action), GFP_KERNEL); + if (!action) + return NULL; + + action->action_type = action_type; + refcount_set(&action->refcount, 1); + + return action; +} + +struct mlx5dr_action *mlx5dr_action_create_drop(void) +{ + return dr_action_create_generic(DR_ACTION_TYP_DROP); +} + +struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *tbl) +{ + struct mlx5dr_action *action; + + refcount_inc(&tbl->refcount); + + action = dr_action_create_generic(DR_ACTION_TYP_FT); + if (!action) + goto dec_ref; + + action->dest_tbl.tbl = tbl; + + return action; + +dec_ref: + refcount_dec(&tbl->refcount); + return NULL; +} + +struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_FT); + if (!action) + return NULL; + + action->dest_tbl.is_fw_tbl = 1; + action->dest_tbl.fw_tbl.ft = ft; + action->dest_tbl.fw_tbl.mdev = mdev; + + return action; +} + +struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_CTR); + if (!action) + return NULL; + + action->ctr.ctr_id = counter_id; + + return action; +} + +struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_TAG); + if (!action) + return NULL; + + action->flow_tag = tag_value & 0xffffff; + + return action; +} + +static int +dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type, + struct mlx5dr_domain *dmn, + size_t data_sz, + void *data) +{ + if ((!data && data_sz) || (data && !data_sz) || reformat_type > + DR_ACTION_TYP_L2_TO_TNL_L3) { + mlx5dr_dbg(dmn, "Invalid reformat parameter!\n"); + goto out_err; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB) + return 0; + + if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + if (reformat_type != DR_ACTION_TYP_TNL_L2_TO_L2 && + reformat_type != DR_ACTION_TYP_TNL_L3_TO_L2) { + mlx5dr_dbg(dmn, "Action reformat type not support on RX domain\n"); + goto out_err; + } + } else if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + if (reformat_type != DR_ACTION_TYP_L2_TO_TNL_L2 && + reformat_type != DR_ACTION_TYP_L2_TO_TNL_L3) { + mlx5dr_dbg(dmn, "Action reformat type not support on TX domain\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -EINVAL; +} + +#define ACTION_CACHE_LINE_SIZE 64 + +static int +dr_action_create_reformat_action(struct mlx5dr_domain *dmn, + size_t data_sz, void *data, + struct mlx5dr_action *action) +{ + u32 reformat_id; + int ret; + + switch (action->action_type) { + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + { + enum mlx5dr_action_type rt; + + if (action->action_type == DR_ACTION_TYP_L2_TO_TNL_L2) + rt = MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL; + else + rt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL; + + ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, data_sz, data, + &reformat_id); + if (ret) + return ret; + + action->reformat.reformat_id = reformat_id; + action->reformat.reformat_size = data_sz; + return 0; + } + case DR_ACTION_TYP_TNL_L2_TO_L2: + { + return 0; + } + case DR_ACTION_TYP_TNL_L3_TO_L2: + { + /* Only Ethernet frame is supported, with VLAN (18) or without (14) */ + if (data_sz != HDR_LEN_L2_ONLY && data_sz != HDR_LEN_L2_VLAN) + return -EINVAL; + + action->rewrite.chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool, + DR_CHUNK_SIZE_8); + if (!action->rewrite.chunk) + return -ENOMEM; + + action->rewrite.index = (action->rewrite.chunk->icm_addr - + dmn->info.caps.hdr_modify_icm_addr) / + ACTION_CACHE_LINE_SIZE; + + ret = dr_actions_l2_rewrite(dmn, action, data, data_sz); + if (ret) { + mlx5dr_icm_free_chunk(action->rewrite.chunk); + return ret; + } + return 0; + } + default: + mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type); + return -EINVAL; + } +} + +struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void) +{ + return dr_action_create_generic(DR_ACTION_TYP_POP_VLAN); +} + +struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn, + __be32 vlan_hdr) +{ + u32 vlan_hdr_h = ntohl(vlan_hdr); + u16 ethertype = vlan_hdr_h >> 16; + struct mlx5dr_action *action; + + if (ethertype != SVLAN_ETHERTYPE && ethertype != CVLAN_ETHERTYPE) { + mlx5dr_dbg(dmn, "Invalid vlan ethertype\n"); + return NULL; + } + + action = dr_action_create_generic(DR_ACTION_TYP_PUSH_VLAN); + if (!action) + return NULL; + + action->push_vlan.vlan_hdr = vlan_hdr_h; + return action; +} + +struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data) +{ + enum mlx5dr_action_type action_type; + struct mlx5dr_action *action; + int ret; + + refcount_inc(&dmn->refcount); + + /* General checks */ + ret = dr_action_reformat_to_action_type(reformat_type, &action_type); + if (ret) { + mlx5dr_dbg(dmn, "Invalid reformat_type provided\n"); + goto dec_ref; + } + + ret = dr_action_verify_reformat_params(action_type, dmn, data_sz, data); + if (ret) + goto dec_ref; + + action = dr_action_create_generic(action_type); + if (!action) + goto dec_ref; + + action->reformat.dmn = dmn; + + ret = dr_action_create_reformat_action(dmn, + data_sz, + data, + action); + if (ret) { + mlx5dr_dbg(dmn, "Failed creating reformat action %d\n", ret); + goto free_action; + } + + return action; + +free_action: + kfree(action); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +static const struct dr_action_modify_field_conv * +dr_action_modify_get_hw_info(u16 sw_field) +{ + const struct dr_action_modify_field_conv *hw_action_info; + + if (sw_field >= ARRAY_SIZE(dr_action_conv_arr)) + goto not_found; + + hw_action_info = &dr_action_conv_arr[sw_field]; + if (!hw_action_info->end && !hw_action_info->start) + goto not_found; + + return hw_action_info; + +not_found: + return NULL; +} + +static int +dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn, + __be64 *sw_action, + __be64 *hw_action, + const struct dr_action_modify_field_conv **ret_hw_info) +{ + const struct dr_action_modify_field_conv *hw_action_info; + u8 offset, length, max_length, action; + u16 sw_field; + u8 hw_opcode; + u32 data; + + /* Get SW modify action data */ + action = MLX5_GET(set_action_in, sw_action, action_type); + length = MLX5_GET(set_action_in, sw_action, length); + offset = MLX5_GET(set_action_in, sw_action, offset); + sw_field = MLX5_GET(set_action_in, sw_action, field); + data = MLX5_GET(set_action_in, sw_action, data); + + /* Convert SW data to HW modify action format */ + hw_action_info = dr_action_modify_get_hw_info(sw_field); + if (!hw_action_info) { + mlx5dr_dbg(dmn, "Modify action invalid field given\n"); + return -EINVAL; + } + + max_length = hw_action_info->end - hw_action_info->start + 1; + + switch (action) { + case MLX5_ACTION_TYPE_SET: + hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_SET; + /* PRM defines that length zero specific length of 32bits */ + if (!length) + length = 32; + + if (length + offset > max_length) { + mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n"); + return -EINVAL; + } + break; + + case MLX5_ACTION_TYPE_ADD: + hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_ADD; + offset = 0; + length = max_length; + break; + + default: + mlx5dr_info(dmn, "Unsupported action_type for modify action\n"); + return -EOPNOTSUPP; + } + + MLX5_SET(dr_action_hw_set, hw_action, opcode, hw_opcode); + + MLX5_SET(dr_action_hw_set, hw_action, destination_field_code, + hw_action_info->hw_field); + + MLX5_SET(dr_action_hw_set, hw_action, destination_left_shifter, + hw_action_info->start + offset); + + MLX5_SET(dr_action_hw_set, hw_action, destination_length, + length == 32 ? 0 : length); + + MLX5_SET(dr_action_hw_set, hw_action, inline_data, data); + + *ret_hw_info = hw_action_info; + + return 0; +} + +static int +dr_action_modify_check_field_limitation(struct mlx5dr_domain *dmn, + const __be64 *sw_action) +{ + u16 sw_field; + u8 action; + + sw_field = MLX5_GET(set_action_in, sw_action, field); + action = MLX5_GET(set_action_in, sw_action, action_type); + + /* Check if SW field is supported in current domain (RX/TX) */ + if (action == MLX5_ACTION_TYPE_SET) { + if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_A) { + if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) { + mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n", + sw_field); + return -EINVAL; + } + } + + if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_B) { + if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) { + mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n", + sw_field); + return -EINVAL; + } + } + } else if (action == MLX5_ACTION_TYPE_ADD) { + if (sw_field != MLX5_ACTION_IN_FIELD_OUT_IP_TTL && + sw_field != MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT && + sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM && + sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM) { + mlx5dr_dbg(dmn, "Unsupported field %d for add action\n", sw_field); + return -EINVAL; + } + } else { + mlx5dr_info(dmn, "Unsupported action %d modify action\n", action); + return -EOPNOTSUPP; + } + + return 0; +} + +static bool +dr_action_modify_check_is_ttl_modify(const u64 *sw_action) +{ + u16 sw_field = MLX5_GET(set_action_in, sw_action, field); + + return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; +} + +static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn, + u32 max_hw_actions, + u32 num_sw_actions, + __be64 sw_actions[], + __be64 hw_actions[], + u32 *num_hw_actions, + bool *modify_ttl) +{ + const struct dr_action_modify_field_conv *hw_action_info; + u16 hw_field = MLX5DR_ACTION_MDFY_HW_FLD_RESERVED; + u32 l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE; + u32 l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE; + int ret, i, hw_idx = 0; + __be64 *sw_action; + __be64 hw_action; + + *modify_ttl = false; + + for (i = 0; i < num_sw_actions; i++) { + sw_action = &sw_actions[i]; + + ret = dr_action_modify_check_field_limitation(dmn, sw_action); + if (ret) + return ret; + + if (!(*modify_ttl)) + *modify_ttl = dr_action_modify_check_is_ttl_modify(sw_action); + + /* Convert SW action to HW action */ + ret = dr_action_modify_sw_to_hw(dmn, + sw_action, + &hw_action, + &hw_action_info); + if (ret) + return ret; + + /* Due to a HW limitation we cannot modify 2 different L3 types */ + if (l3_type && hw_action_info->l3_type && + hw_action_info->l3_type != l3_type) { + mlx5dr_dbg(dmn, "Action list can't support two different L3 types\n"); + return -EINVAL; + } + if (hw_action_info->l3_type) + l3_type = hw_action_info->l3_type; + + /* Due to a HW limitation we cannot modify two different L4 types */ + if (l4_type && hw_action_info->l4_type && + hw_action_info->l4_type != l4_type) { + mlx5dr_dbg(dmn, "Action list can't support two different L4 types\n"); + return -EINVAL; + } + if (hw_action_info->l4_type) + l4_type = hw_action_info->l4_type; + + /* HW reads and executes two actions at once this means we + * need to create a gap if two actions access the same field + */ + if ((hw_idx % 2) && hw_field == hw_action_info->hw_field) { + /* Check if after gap insertion the total number of HW + * modify actions doesn't exceeds the limit + */ + hw_idx++; + if ((num_sw_actions + hw_idx - i) >= max_hw_actions) { + mlx5dr_dbg(dmn, "Modify header action number exceeds HW limit\n"); + return -EINVAL; + } + } + hw_field = hw_action_info->hw_field; + + hw_actions[hw_idx] = hw_action; + hw_idx++; + } + + *num_hw_actions = hw_idx; + + return 0; +} + +static int dr_action_create_modify_action(struct mlx5dr_domain *dmn, + size_t actions_sz, + __be64 actions[], + struct mlx5dr_action *action) +{ + struct mlx5dr_icm_chunk *chunk; + u32 max_hw_actions; + u32 num_hw_actions; + u32 num_sw_actions; + __be64 *hw_actions; + bool modify_ttl; + int ret; + + num_sw_actions = actions_sz / DR_MODIFY_ACTION_SIZE; + max_hw_actions = mlx5dr_icm_pool_chunk_size_to_entries(DR_CHUNK_SIZE_16); + + if (num_sw_actions > max_hw_actions) { + mlx5dr_dbg(dmn, "Max number of actions %d exceeds limit %d\n", + num_sw_actions, max_hw_actions); + return -EINVAL; + } + + chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool, DR_CHUNK_SIZE_16); + if (!chunk) + return -ENOMEM; + + hw_actions = kcalloc(1, max_hw_actions * DR_MODIFY_ACTION_SIZE, GFP_KERNEL); + if (!hw_actions) { + ret = -ENOMEM; + goto free_chunk; + } + + ret = dr_actions_convert_modify_header(dmn, + max_hw_actions, + num_sw_actions, + actions, + hw_actions, + &num_hw_actions, + &modify_ttl); + if (ret) + goto free_hw_actions; + + action->rewrite.chunk = chunk; + action->rewrite.modify_ttl = modify_ttl; + action->rewrite.data = (u8 *)hw_actions; + action->rewrite.num_of_actions = num_hw_actions; + action->rewrite.index = (chunk->icm_addr - + dmn->info.caps.hdr_modify_icm_addr) / + ACTION_CACHE_LINE_SIZE; + + ret = mlx5dr_send_postsend_action(dmn, action); + if (ret) + goto free_hw_actions; + + return 0; + +free_hw_actions: + kfree(hw_actions); +free_chunk: + mlx5dr_icm_free_chunk(chunk); + return ret; +} + +struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *dmn, + u32 flags, + size_t actions_sz, + __be64 actions[]) +{ + struct mlx5dr_action *action; + int ret = 0; + + refcount_inc(&dmn->refcount); + + if (actions_sz % DR_MODIFY_ACTION_SIZE) { + mlx5dr_dbg(dmn, "Invalid modify actions size provided\n"); + goto dec_ref; + } + + action = dr_action_create_generic(DR_ACTION_TYP_MODIFY_HDR); + if (!action) + goto dec_ref; + + action->rewrite.dmn = dmn; + + ret = dr_action_create_modify_action(dmn, + actions_sz, + actions, + action); + if (ret) { + mlx5dr_dbg(dmn, "Failed creating modify header action %d\n", ret); + goto free_action; + } + + return action; + +free_action: + kfree(action); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, + u32 vport, u8 vhca_id_valid, + u16 vhca_id) +{ + struct mlx5dr_cmd_vport_cap *vport_cap; + struct mlx5dr_domain *vport_dmn; + struct mlx5dr_action *action; + u8 peer_vport; + + peer_vport = vhca_id_valid && (vhca_id != dmn->info.caps.gvmi); + vport_dmn = peer_vport ? dmn->peer_dmn : dmn; + if (!vport_dmn) { + mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n"); + return NULL; + } + + if (vport_dmn->type != MLX5DR_DOMAIN_TYPE_FDB) { + mlx5dr_dbg(dmn, "Domain doesn't support vport actions\n"); + return NULL; + } + + vport_cap = mlx5dr_get_vport_cap(&vport_dmn->info.caps, vport); + if (!vport_cap) { + mlx5dr_dbg(dmn, "Failed to get vport %d caps\n", vport); + return NULL; + } + + action = dr_action_create_generic(DR_ACTION_TYP_VPORT); + if (!action) + return NULL; + + action->vport.dmn = vport_dmn; + action->vport.caps = vport_cap; + + return action; +} + +int mlx5dr_action_destroy(struct mlx5dr_action *action) +{ + if (refcount_read(&action->refcount) > 1) + return -EBUSY; + + switch (action->action_type) { + case DR_ACTION_TYP_FT: + if (!action->dest_tbl.is_fw_tbl) + refcount_dec(&action->dest_tbl.tbl->refcount); + break; + case DR_ACTION_TYP_TNL_L2_TO_L2: + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_TNL_L3_TO_L2: + mlx5dr_icm_free_chunk(action->rewrite.chunk); + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + mlx5dr_cmd_destroy_reformat_ctx((action->reformat.dmn)->mdev, + action->reformat.reformat_id); + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_MODIFY_HDR: + mlx5dr_icm_free_chunk(action->rewrite.chunk); + refcount_dec(&action->rewrite.dmn->refcount); + break; + default: + break; + } + + kfree(action); + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c new file mode 100644 index 000000000000..41662c4e2664 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev, + bool other_vport, + u16 vport_number, + u64 *icm_address_rx, + u64 *icm_address_tx) +{ + u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {}; + int err; + + MLX5_SET(query_esw_vport_context_in, in, opcode, + MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT); + MLX5_SET(query_esw_vport_context_in, in, other_vport, other_vport); + MLX5_SET(query_esw_vport_context_in, in, vport_number, vport_number); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *icm_address_rx = + MLX5_GET64(query_esw_vport_context_out, out, + esw_vport_context.sw_steering_vport_icm_address_rx); + *icm_address_tx = + MLX5_GET64(query_esw_vport_context_out, out, + esw_vport_context.sw_steering_vport_icm_address_tx); + return 0; +} + +int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, + u16 vport_number, u16 *gvmi) +{ + u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {}; + int out_size; + void *out; + int err; + + out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out); + out = kzalloc(out_size, GFP_KERNEL); + if (!out) + return -ENOMEM; + + MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); + MLX5_SET(query_hca_cap_in, in, other_function, other_vport); + MLX5_SET(query_hca_cap_in, in, function_id, vport_number); + MLX5_SET(query_hca_cap_in, in, op_mod, + MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 | + HCA_CAP_OPMOD_GET_CUR); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size); + if (err) { + kfree(out); + return err; + } + + *gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id); + + kfree(out); + return 0; +} + +int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_esw_caps *caps) +{ + caps->drop_icm_address_rx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_fdb_action_drop_icm_address_rx); + caps->drop_icm_address_tx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_fdb_action_drop_icm_address_tx); + caps->uplink_icm_address_rx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_uplink_icm_address_rx); + caps->uplink_icm_address_tx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_uplink_icm_address_tx); + caps->sw_owner = + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, + sw_owner); + + return 0; +} + +int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, + struct mlx5dr_cmd_caps *caps) +{ + caps->prio_tag_required = MLX5_CAP_GEN(mdev, prio_tag_required); + caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager); + caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); + caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); + + if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { + caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); + caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1); + } + + if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) { + caps->flex_parser_id_icmpv6_dw0 = + MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0); + caps->flex_parser_id_icmpv6_dw1 = + MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw1); + } + + caps->nic_rx_drop_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_rx_action_drop_icm_address); + caps->nic_tx_drop_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_drop_icm_address); + caps->nic_tx_allow_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_allow_icm_address); + + caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner); + caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level); + + caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner); + + caps->log_icm_size = MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size); + caps->hdr_modify_icm_addr = + MLX5_CAP64_DEV_MEM(mdev, header_modify_sw_icm_start_address); + + caps->roce_min_src_udp = MLX5_CAP_ROCE(mdev, r_roce_min_src_udp_port); + + return 0; +} + +int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, + u32 table_id, + struct mlx5dr_cmd_query_flow_table_details *output) +{ + u32 out[MLX5_ST_SZ_DW(query_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_flow_table_in)] = {}; + int err; + + MLX5_SET(query_flow_table_in, in, opcode, + MLX5_CMD_OP_QUERY_FLOW_TABLE); + + MLX5_SET(query_flow_table_in, in, table_type, type); + MLX5_SET(query_flow_table_in, in, table_id, table_id); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + output->status = MLX5_GET(query_flow_table_out, out, status); + output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level); + + output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out, + flow_table_context.sw_owner_icm_root_1); + output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out, + flow_table_context.sw_owner_icm_root_0); + + return 0; +} + +int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev) +{ + u32 out[MLX5_ST_SZ_DW(sync_steering_out)] = {}; + u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {}; + + MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id, + u32 modify_header_id, + u32 vport_id) +{ + u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {}; + void *in_flow_context; + unsigned int inlen; + void *in_dests; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(set_fte_in) + + 1 * MLX5_ST_SZ_BYTES(dest_format_struct); /* One destination only */ + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY); + MLX5_SET(set_fte_in, in, table_type, table_type); + MLX5_SET(set_fte_in, in, table_id, table_id); + + in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); + MLX5_SET(flow_context, in_flow_context, group_id, group_id); + MLX5_SET(flow_context, in_flow_context, modify_header_id, modify_header_id); + MLX5_SET(flow_context, in_flow_context, destination_list_size, 1); + MLX5_SET(flow_context, in_flow_context, action, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR); + + in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); + MLX5_SET(dest_format_struct, in_dests, destination_type, + MLX5_FLOW_DESTINATION_TYPE_VPORT); + MLX5_SET(dest_format_struct, in_dests, destination_id, vport_id); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + kvfree(in); + + return err; +} + +int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id) +{ + u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {}; + u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {}; + + MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY); + MLX5_SET(delete_fte_in, in, table_type, table_type); + MLX5_SET(delete_fte_in, in, table_id, table_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev, + u32 table_type, + u8 num_of_actions, + u64 *actions, + u32 *modify_header_id) +{ + u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)] = {}; + void *p_actions; + u32 inlen; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + + num_of_actions * sizeof(u64); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(alloc_modify_header_context_in, in, opcode, + MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT); + MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type); + MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_of_actions); + p_actions = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions); + memcpy(p_actions, actions, num_of_actions * sizeof(u64)); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + goto out; + + *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, + modify_header_id); +out: + kvfree(in); + return err; +} + +int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev, + u32 modify_header_id) +{ + u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {}; + + MLX5_SET(dealloc_modify_header_context_in, in, opcode, + MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT); + MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id, + modify_header_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 *group_id) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {}; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + u32 *in; + int err; + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP); + MLX5_SET(create_flow_group_in, in, table_type, table_type); + MLX5_SET(create_flow_group_in, in, table_id, table_id); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + goto out; + + *group_id = MLX5_GET(create_flow_group_out, out, group_id); + +out: + kfree(in); + return err; +} + +int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id) +{ + u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {}; + + MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP); + MLX5_SET(destroy_flow_group_in, in, table_type, table_type); + MLX5_SET(destroy_flow_group_in, in, table_id, table_id); + MLX5_SET(destroy_flow_group_in, in, group_id, group_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev, + u32 table_type, + u64 icm_addr_rx, + u64 icm_addr_tx, + u8 level, + bool sw_owner, + bool term_tbl, + u64 *fdb_rx_icm_addr, + u32 *table_id) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {}; + void *ft_mdev; + int err; + + MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); + MLX5_SET(create_flow_table_in, in, table_type, table_type); + + ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context); + MLX5_SET(flow_table_context, ft_mdev, termination_table, term_tbl); + MLX5_SET(flow_table_context, ft_mdev, sw_owner, sw_owner); + MLX5_SET(flow_table_context, ft_mdev, level, level); + + if (sw_owner) { + /* icm_addr_0 used for FDB RX / NIC TX / NIC_RX + * icm_addr_1 used for FDB TX + */ + if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_rx); + } else if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_tx); + } else if (table_type == MLX5_FLOW_TABLE_TYPE_FDB) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_rx); + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_1, icm_addr_tx); + } + } + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *table_id = MLX5_GET(create_flow_table_out, out, table_id); + if (!sw_owner && table_type == MLX5_FLOW_TABLE_TYPE_FDB) + *fdb_rx_icm_addr = + (u64)MLX5_GET(create_flow_table_out, out, icm_address_31_0) | + (u64)MLX5_GET(create_flow_table_out, out, icm_address_39_32) << 32 | + (u64)MLX5_GET(create_flow_table_out, out, icm_address_63_40) << 40; + + return 0; +} + +int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev, + u32 table_id, + u32 table_type) +{ + u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {}; + + MLX5_SET(destroy_flow_table_in, in, opcode, + MLX5_CMD_OP_DESTROY_FLOW_TABLE); + MLX5_SET(destroy_flow_table_in, in, table_type, table_type); + MLX5_SET(destroy_flow_table_in, in, table_id, table_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, + enum mlx5_reformat_ctx_type rt, + size_t reformat_size, + void *reformat_data, + u32 *reformat_id) +{ + u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {}; + size_t inlen, cmd_data_sz, cmd_total_sz; + void *prctx; + void *pdata; + void *in; + int err; + + cmd_total_sz = MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in); + cmd_data_sz = MLX5_FLD_SZ_BYTES(alloc_packet_reformat_context_in, + packet_reformat_context.reformat_data); + inlen = ALIGN(cmd_total_sz + reformat_size - cmd_data_sz, 4); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(alloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT); + + prctx = MLX5_ADDR_OF(alloc_packet_reformat_context_in, in, packet_reformat_context); + pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data); + + MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt); + MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size); + memcpy(pdata, reformat_data, reformat_size); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + return err; + + *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); + kvfree(in); + + return err; +} + +void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, + u32 reformat_id) +{ + u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {}; + + MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); + MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, + reformat_id); + + mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num, + u16 index, struct mlx5dr_cmd_gid_attr *attr) +{ + u32 out[MLX5_ST_SZ_DW(query_roce_address_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_roce_address_in)] = {}; + int err; + + MLX5_SET(query_roce_address_in, in, opcode, + MLX5_CMD_OP_QUERY_ROCE_ADDRESS); + + MLX5_SET(query_roce_address_in, in, roce_address_index, index); + MLX5_SET(query_roce_address_in, in, vhca_port_num, vhca_port_num); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + memcpy(&attr->gid, + MLX5_ADDR_OF(query_roce_address_out, + out, roce_address.source_l3_address), + sizeof(attr->gid)); + memcpy(attr->mac, + MLX5_ADDR_OF(query_roce_address_out, out, + roce_address.source_mac_47_32), + sizeof(attr->mac)); + + if (MLX5_GET(query_roce_address_out, out, + roce_address.roce_version) == MLX5_ROCE_VERSION_2) + attr->roce_ver = MLX5_ROCE_VERSION_2; + else + attr->roce_ver = MLX5_ROCE_VERSION_1; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c new file mode 100644 index 000000000000..9e2eccbb1eb8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved. + * Slicing-by-16 contributed by Bulat Ziganshin + * + * This software is provided 'as-is', without any express or implied warranty. + * In no event will the author be held liable for any damages arising from the + * of this software. + * + * Permission is granted to anyone to use this software for any purpose, + * including commercial applications, and to alter it and redistribute it + * freely, subject to the following restrictions: + * + * 1. The origin of this software must not be misrepresented; you must not + * claim that you wrote the original software. + * 2. If you use this software in a product, an acknowledgment in the product + * documentation would be appreciated but is not required. + * 3. Altered source versions must be plainly marked as such, and must not be + * misrepresented as being the original software. + * + * Taken from http://create.stephan-brumme.com/crc32/ and adapted. + */ + +#include "dr_types.h" + +#define DR_STE_CRC_POLY 0xEDB88320L + +static u32 dr_ste_crc_tab32[8][256]; + +static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j) +{ + tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff]; +} + +void mlx5dr_crc32_init_table(void) +{ + u32 crc, i, j; + + for (i = 0; i < 256; i++) { + crc = i; + for (j = 0; j < 8; j++) { + if (crc & 0x00000001L) + crc = (crc >> 1) ^ DR_STE_CRC_POLY; + else + crc = crc >> 1; + } + dr_ste_crc_tab32[0][i] = crc; + } + + /* Init CRC lookup tables according to crc_slice_8 algorithm */ + for (i = 0; i < 256; i++) { + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i); + } +} + +/* Compute CRC32 (Slicing-by-8 algorithm) */ +u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length) +{ + const u32 *curr = (const u32 *)input_data; + const u8 *curr_char; + u32 crc = 0, one, two; + + if (!input_data) + return 0; + + /* Process eight bytes at once (Slicing-by-8) */ + while (length >= 8) { + one = *curr++ ^ crc; + two = *curr++; + + crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff] + ^ dr_ste_crc_tab32[1][(two >> 16) & 0xff] + ^ dr_ste_crc_tab32[2][(two >> 8) & 0xff] + ^ dr_ste_crc_tab32[3][two & 0xff] + ^ dr_ste_crc_tab32[4][(one >> 24) & 0xff] + ^ dr_ste_crc_tab32[5][(one >> 16) & 0xff] + ^ dr_ste_crc_tab32[6][(one >> 8) & 0xff] + ^ dr_ste_crc_tab32[7][one & 0xff]; + + length -= 8; + } + + curr_char = (const u8 *)curr; + /* Remaining 1 to 7 bytes (standard algorithm) */ + while (length-- != 0) + crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff) + ^ *curr_char++]; + + return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | + ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c new file mode 100644 index 000000000000..3b9cf0bccf4d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/mlx5/eswitch.h> +#include "dr_types.h" + +static int dr_domain_init_cache(struct mlx5dr_domain *dmn) +{ + /* Per vport cached FW FT for checksum recalculation, this + * recalculation is needed due to a HW bug. + */ + dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports, + sizeof(dmn->cache.recalc_cs_ft[0]), + GFP_KERNEL); + if (!dmn->cache.recalc_cs_ft) + return -ENOMEM; + + return 0; +} + +static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn) +{ + int i; + + for (i = 0; i < dmn->info.caps.num_vports; i++) { + if (!dmn->cache.recalc_cs_ft[i]) + continue; + + mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]); + } + + kfree(dmn->cache.recalc_cs_ft); +} + +int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u32 vport_num, + u64 *rx_icm_addr) +{ + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + + recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num]; + if (!recalc_cs_ft) { + /* Table not in cache, need to allocate a new one */ + recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num); + if (!recalc_cs_ft) + return -EINVAL; + + dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft; + } + + *rx_icm_addr = recalc_cs_ft->rx_icm_addr; + + return 0; +} + +static int dr_domain_init_resources(struct mlx5dr_domain *dmn) +{ + int ret; + + ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn); + if (ret) { + mlx5dr_dbg(dmn, "Couldn't allocate PD\n"); + return ret; + } + + dmn->uar = mlx5_get_uars_page(dmn->mdev); + if (!dmn->uar) { + mlx5dr_err(dmn, "Couldn't allocate UAR\n"); + goto clean_pd; + } + + dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE); + if (!dmn->ste_icm_pool) { + mlx5dr_err(dmn, "Couldn't get icm memory for %s\n", + dev_name(dmn->mdev->device)); + goto clean_uar; + } + + dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION); + if (!dmn->action_icm_pool) { + mlx5dr_err(dmn, "Couldn't get action icm memory for %s\n", + dev_name(dmn->mdev->device)); + goto free_ste_icm_pool; + } + + ret = mlx5dr_send_ring_alloc(dmn); + if (ret) { + mlx5dr_err(dmn, "Couldn't create send-ring for %s\n", + dev_name(dmn->mdev->device)); + goto free_action_icm_pool; + } + + return 0; + +free_action_icm_pool: + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); +free_ste_icm_pool: + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); +clean_uar: + mlx5_put_uars_page(dmn->mdev, dmn->uar); +clean_pd: + mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); + + return ret; +} + +static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn) +{ + mlx5dr_send_ring_free(dmn, dmn->send_ring); + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); + mlx5_put_uars_page(dmn->mdev, dmn->uar); + mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); +} + +static int dr_domain_query_vport(struct mlx5dr_domain *dmn, + bool other_vport, + u16 vport_number) +{ + struct mlx5dr_cmd_vport_cap *vport_caps; + int ret; + + vport_caps = &dmn->info.caps.vports_caps[vport_number]; + + ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, + other_vport, + vport_number, + &vport_caps->icm_address_rx, + &vport_caps->icm_address_tx); + if (ret) + return ret; + + ret = mlx5dr_cmd_query_gvmi(dmn->mdev, + other_vport, + vport_number, + &vport_caps->vport_gvmi); + if (ret) + return ret; + + vport_caps->num = vport_number; + vport_caps->vhca_gvmi = dmn->info.caps.gvmi; + + return 0; +} + +static int dr_domain_query_vports(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps; + struct mlx5dr_cmd_vport_cap *wire_vport; + int vport; + int ret; + + /* Query vports (except wire vport) */ + for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) { + ret = dr_domain_query_vport(dmn, !!vport, vport); + if (ret) + return ret; + } + + /* Last vport is the wire port */ + wire_vport = &dmn->info.caps.vports_caps[vport]; + wire_vport->num = WIRE_PORT; + wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx; + wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx; + wire_vport->vport_gvmi = 0; + wire_vport->vhca_gvmi = dmn->info.caps.gvmi; + + return 0; +} + +static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_domain *dmn) +{ + int ret; + + if (!dmn->info.caps.eswitch_manager) + return -EOPNOTSUPP; + + ret = mlx5dr_cmd_query_esw_caps(mdev, &dmn->info.caps.esw_caps); + if (ret) + return ret; + + dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner; + dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx; + dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx; + + dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports, + sizeof(dmn->info.caps.vports_caps[0]), + GFP_KERNEL); + if (!dmn->info.caps.vports_caps) + return -ENOMEM; + + ret = dr_domain_query_vports(dmn); + if (ret) { + mlx5dr_dbg(dmn, "Failed to query vports caps\n"); + goto free_vports_caps; + } + + dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1; + + return 0; + +free_vports_caps: + kfree(dmn->info.caps.vports_caps); + dmn->info.caps.vports_caps = NULL; + return ret; +} + +static int dr_domain_caps_init(struct mlx5_core_dev *mdev, + struct mlx5dr_domain *dmn) +{ + struct mlx5dr_cmd_vport_cap *vport_cap; + int ret; + + if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) { + mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n"); + return -EOPNOTSUPP; + } + + dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev); + + ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps); + if (ret) + return ret; + + ret = dr_domain_query_fdb_caps(mdev, dmn); + if (ret) + return ret; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + if (!dmn->info.caps.rx_sw_owner) + return -ENOTSUPP; + + dmn->info.supp_sw_steering = true; + dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; + dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address; + dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address; + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + if (!dmn->info.caps.tx_sw_owner) + return -ENOTSUPP; + + dmn->info.supp_sw_steering = true; + dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address; + dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address; + break; + case MLX5DR_DOMAIN_TYPE_FDB: + if (!dmn->info.caps.eswitch_manager) + return -ENOTSUPP; + + if (!dmn->info.caps.fdb_sw_owner) + return -ENOTSUPP; + + dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; + dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0); + if (!vport_cap) { + mlx5dr_dbg(dmn, "Failed to get esw manager vport\n"); + return -ENOENT; + } + + dmn->info.supp_sw_steering = true; + dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx; + dmn->info.rx.default_icm_addr = vport_cap->icm_address_rx; + dmn->info.rx.drop_icm_addr = dmn->info.caps.esw_rx_drop_address; + dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address; + break; + default: + mlx5dr_dbg(dmn, "Invalid domain\n"); + ret = -EINVAL; + break; + } + + return ret; +} + +static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn) +{ + kfree(dmn->info.caps.vports_caps); +} + +struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) +{ + struct mlx5dr_domain *dmn; + int ret; + + if (type > MLX5DR_DOMAIN_TYPE_FDB) + return NULL; + + dmn = kzalloc(sizeof(*dmn), GFP_KERNEL); + if (!dmn) + return NULL; + + dmn->mdev = mdev; + dmn->type = type; + refcount_set(&dmn->refcount, 1); + mutex_init(&dmn->mutex); + + if (dr_domain_caps_init(mdev, dmn)) { + mlx5dr_dbg(dmn, "Failed init domain, no caps\n"); + goto free_domain; + } + + dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K; + dmn->info.max_log_sw_icm_sz = min_t(u32, DR_CHUNK_SIZE_1024K, + dmn->info.caps.log_icm_size); + + if (!dmn->info.supp_sw_steering) { + mlx5dr_err(dmn, "SW steering not supported for %s\n", + dev_name(mdev->device)); + goto uninit_caps; + } + + /* Allocate resources */ + ret = dr_domain_init_resources(dmn); + if (ret) { + mlx5dr_err(dmn, "Failed init domain resources for %s\n", + dev_name(mdev->device)); + goto uninit_caps; + } + + ret = dr_domain_init_cache(dmn); + if (ret) { + mlx5dr_err(dmn, "Failed initialize domain cache\n"); + goto uninit_resourses; + } + + /* Init CRC table for htbl CRC calculation */ + mlx5dr_crc32_init_table(); + + return dmn; + +uninit_resourses: + dr_domain_uninit_resources(dmn); +uninit_caps: + dr_domain_caps_uninit(dmn); +free_domain: + kfree(dmn); + return NULL; +} + +/* Assure synchronization of the device steering tables with updates made by SW + * insertion. + */ +int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags) +{ + int ret = 0; + + if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) { + mutex_lock(&dmn->mutex); + ret = mlx5dr_send_ring_force_drain(dmn); + mutex_unlock(&dmn->mutex); + if (ret) + return ret; + } + + if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW) + ret = mlx5dr_cmd_sync_steering(dmn->mdev); + + return ret; +} + +int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) +{ + if (refcount_read(&dmn->refcount) > 1) + return -EBUSY; + + /* make sure resources are not used by the hardware */ + mlx5dr_cmd_sync_steering(dmn->mdev); + dr_domain_uninit_cache(dmn); + dr_domain_uninit_resources(dmn); + dr_domain_caps_uninit(dmn); + mutex_destroy(&dmn->mutex); + kfree(dmn); + return 0; +} + +void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn) +{ + mutex_lock(&dmn->mutex); + + if (dmn->peer_dmn) + refcount_dec(&dmn->peer_dmn->refcount); + + dmn->peer_dmn = peer_dmn; + + if (dmn->peer_dmn) + refcount_inc(&dmn->peer_dmn->refcount); + + mutex_unlock(&dmn->mutex); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c new file mode 100644 index 000000000000..60ef6e6171e3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/types.h> +#include "dr_types.h" + +struct mlx5dr_fw_recalc_cs_ft * +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num) +{ + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + u32 table_id, group_id, modify_hdr_id; + u64 rx_icm_addr, modify_ttl_action; + int ret; + + recalc_cs_ft = kzalloc(sizeof(*recalc_cs_ft), GFP_KERNEL); + if (!recalc_cs_ft) + return NULL; + + ret = mlx5dr_cmd_create_flow_table(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, + 0, 0, dmn->info.caps.max_ft_level - 1, + false, true, &rx_icm_addr, &table_id); + if (ret) { + mlx5dr_err(dmn, "Failed creating TTL W/A FW flow table %d\n", ret); + goto free_ttl_tbl; + } + + ret = mlx5dr_cmd_create_empty_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, &group_id); + if (ret) { + mlx5dr_err(dmn, "Failed creating TTL W/A FW flow group %d\n", ret); + goto destroy_flow_table; + } + + /* Modify TTL action by adding zero to trigger CS recalculation */ + modify_ttl_action = 0; + MLX5_SET(set_action_in, &modify_ttl_action, action_type, MLX5_ACTION_TYPE_ADD); + MLX5_SET(set_action_in, &modify_ttl_action, field, MLX5_ACTION_IN_FIELD_OUT_IP_TTL); + + ret = mlx5dr_cmd_alloc_modify_header(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, 1, + &modify_ttl_action, + &modify_hdr_id); + if (ret) { + mlx5dr_err(dmn, "Failed modify header TTL %d\n", ret); + goto destroy_flow_group; + } + + ret = mlx5dr_cmd_set_fte_modify_and_vport(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, group_id, modify_hdr_id, + vport_num); + if (ret) { + mlx5dr_err(dmn, "Failed setting TTL W/A flow table entry %d\n", ret); + goto dealloc_modify_header; + } + + recalc_cs_ft->modify_hdr_id = modify_hdr_id; + recalc_cs_ft->rx_icm_addr = rx_icm_addr; + recalc_cs_ft->table_id = table_id; + recalc_cs_ft->group_id = group_id; + + return recalc_cs_ft; + +dealloc_modify_header: + mlx5dr_cmd_dealloc_modify_header(dmn->mdev, modify_hdr_id); +destroy_flow_group: + mlx5dr_cmd_destroy_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, group_id); +destroy_flow_table: + mlx5dr_cmd_destroy_flow_table(dmn->mdev, table_id, MLX5_FLOW_TABLE_TYPE_FDB); +free_ttl_tbl: + kfree(recalc_cs_ft); + return NULL; +} + +void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn, + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft) +{ + mlx5dr_cmd_del_flow_table_entry(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + recalc_cs_ft->table_id); + mlx5dr_cmd_dealloc_modify_header(dmn->mdev, recalc_cs_ft->modify_hdr_id); + mlx5dr_cmd_destroy_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + recalc_cs_ft->table_id, + recalc_cs_ft->group_id); + mlx5dr_cmd_destroy_flow_table(dmn->mdev, + recalc_cs_ft->table_id, + MLX5_FLOW_TABLE_TYPE_FDB); + + kfree(recalc_cs_ft); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c new file mode 100644 index 000000000000..e76f61e7555e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -0,0 +1,570 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 +#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024) + +struct mlx5dr_icm_pool; + +struct mlx5dr_icm_bucket { + struct mlx5dr_icm_pool *pool; + + /* Chunks that aren't visible to HW not directly and not in cache */ + struct list_head free_list; + unsigned int free_list_count; + + /* Used chunks, HW may be accessing this memory */ + struct list_head used_list; + unsigned int used_list_count; + + /* HW may be accessing this memory but at some future, + * undetermined time, it might cease to do so. Before deciding to call + * sync_ste, this list is moved to sync_list + */ + struct list_head hot_list; + unsigned int hot_list_count; + + /* Pending sync list, entries from the hot list are moved to this list. + * sync_ste is executed and then sync_list is concatenated to the free list + */ + struct list_head sync_list; + unsigned int sync_list_count; + + u32 total_chunks; + u32 num_of_entries; + u32 entry_size; + /* protect the ICM bucket */ + struct mutex mutex; +}; + +struct mlx5dr_icm_pool { + struct mlx5dr_icm_bucket *buckets; + enum mlx5dr_icm_type icm_type; + enum mlx5dr_icm_chunk_size max_log_chunk_sz; + enum mlx5dr_icm_chunk_size num_of_buckets; + struct list_head icm_mr_list; + /* protect the ICM MR list */ + struct mutex mr_mutex; + struct mlx5dr_domain *dmn; +}; + +struct mlx5dr_icm_dm { + u32 obj_id; + enum mlx5_sw_icm_type type; + u64 addr; + size_t length; +}; + +struct mlx5dr_icm_mr { + struct mlx5dr_icm_pool *pool; + struct mlx5_core_mkey mkey; + struct mlx5dr_icm_dm dm; + size_t used_length; + size_t length; + u64 icm_start_addr; + struct list_head mr_list; +}; + +static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, + u32 pd, u64 length, u64 start_addr, int mode, + struct mlx5_core_mkey *mkey) +{ + u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; + void *mkc; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + + MLX5_SET(mkc, mkc, access_mode_1_0, mode); + MLX5_SET(mkc, mkc, access_mode_4_2, (mode >> 2) & 0x7); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + if (mode == MLX5_MKC_ACCESS_MODE_SW_ICM) { + MLX5_SET(mkc, mkc, rw, 1); + MLX5_SET(mkc, mkc, rr, 1); + } + + MLX5_SET64(mkc, mkc, len, length); + MLX5_SET(mkc, mkc, pd, pd); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET64(mkc, mkc, start_addr, start_addr); + + return mlx5_core_create_mkey(mdev, mkey, in, inlen); +} + +static struct mlx5dr_icm_mr * +dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool, + enum mlx5_sw_icm_type type, + size_t align_base) +{ + struct mlx5_core_dev *mdev = pool->dmn->mdev; + struct mlx5dr_icm_mr *icm_mr; + size_t align_diff; + int err; + + icm_mr = kvzalloc(sizeof(*icm_mr), GFP_KERNEL); + if (!icm_mr) + return NULL; + + icm_mr->pool = pool; + INIT_LIST_HEAD(&icm_mr->mr_list); + + icm_mr->dm.type = type; + + /* 2^log_biggest_table * entry-size * double-for-alignment */ + icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type) * 2; + + err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, + &icm_mr->dm.addr, &icm_mr->dm.obj_id); + if (err) { + mlx5dr_err(pool->dmn, "Failed to allocate SW ICM memory, err (%d)\n", err); + goto free_icm_mr; + } + + /* Register device memory */ + err = dr_icm_create_dm_mkey(mdev, pool->dmn->pdn, + icm_mr->dm.length, + icm_mr->dm.addr, + MLX5_MKC_ACCESS_MODE_SW_ICM, + &icm_mr->mkey); + if (err) { + mlx5dr_err(pool->dmn, "Failed to create SW ICM MKEY, err (%d)\n", err); + goto free_dm; + } + + icm_mr->icm_start_addr = icm_mr->dm.addr; + + align_diff = icm_mr->icm_start_addr % align_base; + if (align_diff) + icm_mr->used_length = align_base - align_diff; + + list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list); + + return icm_mr; + +free_dm: + mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, + icm_mr->dm.addr, icm_mr->dm.obj_id); +free_icm_mr: + kvfree(icm_mr); + return NULL; +} + +static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) +{ + struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev; + struct mlx5dr_icm_dm *dm = &icm_mr->dm; + + list_del(&icm_mr->mr_list); + mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, + dm->addr, dm->obj_id); + kvfree(icm_mr); +} + +static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + chunk->ste_arr = kvzalloc(bucket->num_of_entries * + sizeof(chunk->ste_arr[0]), GFP_KERNEL); + if (!chunk->ste_arr) + return -ENOMEM; + + chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries * + DR_STE_SIZE_REDUCED, GFP_KERNEL); + if (!chunk->hw_ste_arr) + goto out_free_ste_arr; + + chunk->miss_list = kvmalloc(bucket->num_of_entries * + sizeof(chunk->miss_list[0]), GFP_KERNEL); + if (!chunk->miss_list) + goto out_free_hw_ste_arr; + + return 0; + +out_free_hw_ste_arr: + kvfree(chunk->hw_ste_arr); +out_free_ste_arr: + kvfree(chunk->ste_arr); + return -ENOMEM; +} + +static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket) +{ + size_t mr_free_size, mr_req_size, mr_row_size; + struct mlx5dr_icm_pool *pool = bucket->pool; + struct mlx5dr_icm_mr *icm_mr = NULL; + struct mlx5dr_icm_chunk *chunk; + enum mlx5_sw_icm_type dm_type; + size_t align_base; + int i, err = 0; + + mr_req_size = bucket->num_of_entries * bucket->entry_size; + mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type); + + if (pool->icm_type == DR_ICM_TYPE_STE) { + dm_type = MLX5_SW_ICM_TYPE_STEERING; + /* Align base is the biggest chunk size / row size */ + align_base = mr_row_size; + } else { + dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY; + /* Align base is 64B */ + align_base = DR_ICM_MODIFY_HDR_ALIGN_BASE; + } + + mutex_lock(&pool->mr_mutex); + if (!list_empty(&pool->icm_mr_list)) { + icm_mr = list_last_entry(&pool->icm_mr_list, + struct mlx5dr_icm_mr, mr_list); + + if (icm_mr) + mr_free_size = icm_mr->dm.length - icm_mr->used_length; + } + + if (!icm_mr || mr_free_size < mr_row_size) { + icm_mr = dr_icm_pool_mr_create(pool, dm_type, align_base); + if (!icm_mr) { + err = -ENOMEM; + goto out_err; + } + } + + /* Create memory aligned chunks */ + for (i = 0; i < mr_row_size / mr_req_size; i++) { + chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); + if (!chunk) { + err = -ENOMEM; + goto out_err; + } + + chunk->bucket = bucket; + chunk->rkey = icm_mr->mkey.key; + /* mr start addr is zero based */ + chunk->mr_addr = icm_mr->used_length; + chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length; + icm_mr->used_length += mr_req_size; + chunk->num_of_entries = bucket->num_of_entries; + chunk->byte_size = chunk->num_of_entries * bucket->entry_size; + + if (pool->icm_type == DR_ICM_TYPE_STE) { + err = dr_icm_chunk_ste_init(chunk); + if (err) + goto out_free_chunk; + } + + INIT_LIST_HEAD(&chunk->chunk_list); + list_add(&chunk->chunk_list, &bucket->free_list); + bucket->free_list_count++; + bucket->total_chunks++; + } + mutex_unlock(&pool->mr_mutex); + return 0; + +out_free_chunk: + kvfree(chunk); +out_err: + mutex_unlock(&pool->mr_mutex); + return err; +} + +static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) +{ + kvfree(chunk->miss_list); + kvfree(chunk->hw_ste_arr); + kvfree(chunk->ste_arr); +} + +static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + list_del(&chunk->chunk_list); + bucket->total_chunks--; + + if (bucket->pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_chunk_ste_cleanup(chunk); + + kvfree(chunk); +} + +static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *bucket, + enum mlx5dr_icm_chunk_size chunk_size) +{ + if (pool->icm_type == DR_ICM_TYPE_STE) + bucket->entry_size = DR_STE_SIZE; + else + bucket->entry_size = DR_MODIFY_ACTION_SIZE; + + bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + bucket->pool = pool; + mutex_init(&bucket->mutex); + INIT_LIST_HEAD(&bucket->free_list); + INIT_LIST_HEAD(&bucket->used_list); + INIT_LIST_HEAD(&bucket->hot_list); + INIT_LIST_HEAD(&bucket->sync_list); +} + +static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket) +{ + struct mlx5dr_icm_chunk *chunk, *next; + + mutex_destroy(&bucket->mutex); + list_splice_tail_init(&bucket->sync_list, &bucket->free_list); + list_splice_tail_init(&bucket->hot_list, &bucket->free_list); + + list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list) + dr_icm_chunk_destroy(chunk); + + WARN_ON(bucket->total_chunks != 0); + + /* Cleanup of unreturned chunks */ + list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list) + dr_icm_chunk_destroy(chunk); +} + +static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool) +{ + u64 hot_size = 0; + int chunk_order; + + for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++) + hot_size += pool->buckets[chunk_order].hot_list_count * + mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type); + + return hot_size; +} + +static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *bucket) +{ + u64 bytes_for_sync; + + bytes_for_sync = dr_icm_hot_mem_size(pool); + if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count) + return false; + + return true; +} + +static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->hot_list, &bucket->sync_list); + bucket->sync_list_count += bucket->hot_list_count; + bucket->hot_list_count = 0; +} + +static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->sync_list, &bucket->free_list); + bucket->free_list_count += bucket->sync_list_count; + bucket->sync_list_count = 0; +} + +static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->sync_list, &bucket->hot_list); + bucket->hot_list_count += bucket->sync_list_count; + bucket->sync_list_count = 0; +} + +static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_start(bucket); + continue; + } + + /* Freeing the mutex is done at the end of that process, after + * sync_ste was executed at dr_icm_chill_buckets_end func. + */ + if (mutex_trylock(&bucket->mutex)) { + dr_icm_chill_bucket_start(bucket); + buckets[i] = true; + } + } +} + +static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_end(bucket); + continue; + } + + if (!buckets[i]) + continue; + + dr_icm_chill_bucket_end(bucket); + mutex_unlock(&bucket->mutex); + } +} + +static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_abort(bucket); + continue; + } + + if (!buckets[i]) + continue; + + dr_icm_chill_bucket_abort(bucket); + mutex_unlock(&bucket->mutex); + } +} + +/* Allocate an ICM chunk, each chunk holds a piece of ICM memory and + * also memory used for HW STE management for optimizations. + */ +struct mlx5dr_icm_chunk * +mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size) +{ + struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */ + bool buckets[DR_CHUNK_SIZE_MAX] = {}; + struct mlx5dr_icm_bucket *bucket; + int err; + + if (chunk_size > pool->max_log_chunk_sz) + return NULL; + + bucket = &pool->buckets[chunk_size]; + + mutex_lock(&bucket->mutex); + + /* Take chunk from pool if available, otherwise allocate new chunks */ + if (list_empty(&bucket->free_list)) { + if (dr_icm_reuse_hot_entries(pool, bucket)) { + dr_icm_chill_buckets_start(pool, bucket, buckets); + err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); + if (err) { + dr_icm_chill_buckets_abort(pool, bucket, buckets); + mlx5dr_dbg(pool->dmn, "Sync_steering failed\n"); + chunk = NULL; + goto out; + } + dr_icm_chill_buckets_end(pool, bucket, buckets); + } else { + dr_icm_chunks_create(bucket); + } + } + + if (!list_empty(&bucket->free_list)) { + chunk = list_last_entry(&bucket->free_list, + struct mlx5dr_icm_chunk, + chunk_list); + if (chunk) { + list_del_init(&chunk->chunk_list); + list_add_tail(&chunk->chunk_list, &bucket->used_list); + bucket->free_list_count--; + bucket->used_list_count++; + } + } +out: + mutex_unlock(&bucket->mutex); + return chunk; +} + +void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + if (bucket->pool->icm_type == DR_ICM_TYPE_STE) { + memset(chunk->ste_arr, 0, + bucket->num_of_entries * sizeof(chunk->ste_arr[0])); + memset(chunk->hw_ste_arr, 0, + bucket->num_of_entries * DR_STE_SIZE_REDUCED); + } + + mutex_lock(&bucket->mutex); + list_del_init(&chunk->chunk_list); + list_add_tail(&chunk->chunk_list, &bucket->hot_list); + bucket->hot_list_count++; + bucket->used_list_count--; + mutex_unlock(&bucket->mutex); +} + +struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, + enum mlx5dr_icm_type icm_type) +{ + enum mlx5dr_icm_chunk_size max_log_chunk_sz; + struct mlx5dr_icm_pool *pool; + int i; + + if (icm_type == DR_ICM_TYPE_STE) + max_log_chunk_sz = dmn->info.max_log_sw_icm_sz; + else + max_log_chunk_sz = dmn->info.max_log_action_icm_sz; + + pool = kvzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + pool->buckets = kcalloc(max_log_chunk_sz + 1, + sizeof(pool->buckets[0]), + GFP_KERNEL); + if (!pool->buckets) + goto free_pool; + + pool->dmn = dmn; + pool->icm_type = icm_type; + pool->max_log_chunk_sz = max_log_chunk_sz; + pool->num_of_buckets = max_log_chunk_sz + 1; + INIT_LIST_HEAD(&pool->icm_mr_list); + + for (i = 0; i < pool->num_of_buckets; i++) + dr_icm_bucket_init(pool, &pool->buckets[i], i); + + mutex_init(&pool->mr_mutex); + + return pool; + +free_pool: + kvfree(pool); + return NULL; +} + +void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool) +{ + struct mlx5dr_icm_mr *icm_mr, *next; + int i; + + mutex_destroy(&pool->mr_mutex); + + list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list) + dr_icm_pool_mr_destroy(icm_mr); + + for (i = 0; i < pool->num_of_buckets; i++) + dr_icm_bucket_cleanup(&pool->buckets[i]); + + kfree(pool->buckets); + kvfree(pool); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c new file mode 100644 index 000000000000..01008cd66f75 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -0,0 +1,770 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +static bool dr_mask_is_smac_set(struct mlx5dr_match_spec *spec) +{ + return (spec->smac_47_16 || spec->smac_15_0); +} + +static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dmac_47_16 || spec->dmac_15_0); +} + +static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec) +{ + return (spec->src_ip_127_96 || spec->src_ip_95_64 || + spec->src_ip_63_32 || spec->src_ip_31_0); +} + +static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dst_ip_127_96 || spec->dst_ip_95_64 || + spec->dst_ip_63_32 || spec->dst_ip_31_0); +} + +static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec) +{ + return (spec->ip_protocol || spec->frag || spec->tcp_flags || + spec->ip_ecn || spec->ip_dscp); +} + +static bool dr_mask_is_tcp_udp_base_set(struct mlx5dr_match_spec *spec) +{ + return (spec->tcp_sport || spec->tcp_dport || + spec->udp_sport || spec->udp_dport); +} + +static bool dr_mask_is_ipv4_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dst_ip_31_0 || spec->src_ip_31_0); +} + +static bool dr_mask_is_ipv4_5_tuple_set(struct mlx5dr_match_spec *spec) +{ + return (dr_mask_is_l3_base_set(spec) || + dr_mask_is_tcp_udp_base_set(spec) || + dr_mask_is_ipv4_set(spec)); +} + +static bool dr_mask_is_eth_l2_tnl_set(struct mlx5dr_match_misc *misc) +{ + return misc->vxlan_vni; +} + +static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec) +{ + return spec->ttl_hoplimit; +} + +#define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \ + (_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \ + (_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \ + (_spec).ethertype || (_spec).ip_version || \ + (_misc)._inner_outer##_second_vid || \ + (_misc)._inner_outer##_second_cfi || \ + (_misc)._inner_outer##_second_prio || \ + (_misc)._inner_outer##_second_cvlan_tag || \ + (_misc)._inner_outer##_second_svlan_tag) + +#define DR_MASK_IS_ETH_L4_SET(_spec, _misc, _inner_outer) ( \ + dr_mask_is_l3_base_set(&(_spec)) || \ + dr_mask_is_tcp_udp_base_set(&(_spec)) || \ + dr_mask_is_ttl_set(&(_spec)) || \ + (_misc)._inner_outer##_ipv6_flow_label) + +#define DR_MASK_IS_ETH_L4_MISC_SET(_misc3, _inner_outer) ( \ + (_misc3)._inner_outer##_tcp_seq_num || \ + (_misc3)._inner_outer##_tcp_ack_num) + +#define DR_MASK_IS_FIRST_MPLS_SET(_misc2, _inner_outer) ( \ + (_misc2)._inner_outer##_first_mpls_label || \ + (_misc2)._inner_outer##_first_mpls_exp || \ + (_misc2)._inner_outer##_first_mpls_s_bos || \ + (_misc2)._inner_outer##_first_mpls_ttl) + +static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) +{ + return (misc->gre_key_h || misc->gre_key_l || + misc->gre_protocol || misc->gre_c_present || + misc->gre_k_present || misc->gre_s_present); +} + +#define DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET(_misc2, gre_udp) ( \ + (_misc2).outer_first_mpls_over_##gre_udp##_label || \ + (_misc2).outer_first_mpls_over_##gre_udp##_exp || \ + (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \ + (_misc2).outer_first_mpls_over_##gre_udp##_ttl) + +#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \ + DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \ + DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp)) + +static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3) +{ + return (misc3->outer_vxlan_gpe_vni || + misc3->outer_vxlan_gpe_next_protocol || + misc3->outer_vxlan_gpe_flags); +} + +static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) +{ + return (misc3->icmpv6_type || misc3->icmpv6_code || + misc3->icmpv6_header_data); +} + +static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2) +{ + return misc2->metadata_reg_a; +} + +static bool dr_mask_is_reg_c_0_3_set(struct mlx5dr_match_misc2 *misc2) +{ + return (misc2->metadata_reg_c_0 || misc2->metadata_reg_c_1 || + misc2->metadata_reg_c_2 || misc2->metadata_reg_c_3); +} + +static bool dr_mask_is_reg_c_4_7_set(struct mlx5dr_match_misc2 *misc2) +{ + return (misc2->metadata_reg_c_4 || misc2->metadata_reg_c_5 || + misc2->metadata_reg_c_6 || misc2->metadata_reg_c_7); +} + +static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc) +{ + return (misc->source_sqn || misc->source_port); +} + +static bool +dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn) +{ + return dmn->info.caps.flex_protocols & + MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; +} + +int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6) +{ + if (ipv6) { + nic_matcher->ste_builder = nic_matcher->ste_builder6; + nic_matcher->num_of_builders = nic_matcher->num_of_builders6; + } else { + nic_matcher->ste_builder = nic_matcher->ste_builder4; + nic_matcher->num_of_builders = nic_matcher->num_of_builders4; + } + + if (!nic_matcher->num_of_builders) { + mlx5dr_dbg(matcher->tbl->dmn, + "Rule not supported on this matcher due to IP related fields\n"); + return -EINVAL; + } + + return 0; +} + +static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_match_param mask = {}; + struct mlx5dr_match_misc3 *misc3; + struct mlx5dr_ste_build *sb; + u8 *num_of_builders; + bool inner, rx; + int idx = 0; + int ret, i; + + if (ipv6) { + sb = nic_matcher->ste_builder6; + num_of_builders = &nic_matcher->num_of_builders6; + } else { + sb = nic_matcher->ste_builder4; + num_of_builders = &nic_matcher->num_of_builders4; + } + + rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + + /* Create a temporary mask to track and clear used mask fields */ + if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER) + mask.outer = matcher->mask.outer; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC) + mask.misc = matcher->mask.misc; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_INNER) + mask.inner = matcher->mask.inner; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC2) + mask.misc2 = matcher->mask.misc2; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC3) + mask.misc3 = matcher->mask.misc3; + + ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria, + &matcher->mask, NULL); + if (ret) + return ret; + + /* Outer */ + if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER | + DR_MATCHER_CRITERIA_MISC | + DR_MATCHER_CRITERIA_MISC2 | + DR_MATCHER_CRITERIA_MISC3)) { + inner = false; + + if (dr_mask_is_wqe_metadata_set(&mask.misc2)) + mlx5dr_ste_build_general_purpose(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_reg_c_0_3_set(&mask.misc2)) + mlx5dr_ste_build_register_0(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_reg_c_4_7_set(&mask.misc2)) + mlx5dr_ste_build_register_1(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) && + (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) { + ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask, + &dmn->info.caps, + inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.outer) && + dr_mask_is_dmac_set(&mask.outer)) { + ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask, + inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.outer)) + mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer)) + mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); + + if (ipv6) { + if (dr_mask_is_dst_addr_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_src_addr_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer)) + mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); + } else { + if (dr_mask_is_ipv4_5_tuple_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_ttl_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask, + inner, rx); + } + + if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) && + dr_matcher_supp_flex_parser_vxlan_gpe(dmn)) + mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) + mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer)) + mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) + mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, + inner, rx); + + misc3 = &mask.misc3; + if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) && + mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) || + (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) && + mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) { + ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++], + &mask, &dmn->info.caps, + inner, rx); + if (ret) + return ret; + } + if (dr_mask_is_gre_set(&mask.misc)) + mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx); + } + + /* Inner */ + if (matcher->match_criteria & (DR_MATCHER_CRITERIA_INNER | + DR_MATCHER_CRITERIA_MISC | + DR_MATCHER_CRITERIA_MISC2 | + DR_MATCHER_CRITERIA_MISC3)) { + inner = true; + + if (dr_mask_is_eth_l2_tnl_set(&mask.misc)) + mlx5dr_ste_build_eth_l2_tnl(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_smac_set(&mask.inner) && + dr_mask_is_dmac_set(&mask.inner)) { + ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], + &mask, inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.inner)) + mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner)) + mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); + + if (ipv6) { + if (dr_mask_is_dst_addr_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_src_addr_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner)) + mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); + } else { + if (dr_mask_is_ipv4_5_tuple_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_ttl_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask, + inner, rx); + } + + if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, inner)) + mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner)) + mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) + mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx); + } + /* Empty matcher, takes all */ + if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) + mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx); + + if (idx == 0) { + mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n"); + return -EINVAL; + } + + /* Check that all mask fields were consumed */ + for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) { + if (((u8 *)&mask)[i] != 0) { + mlx5dr_info(dmn, "Mask contains unsupported parameters\n"); + return -EOPNOTSUPP; + } + } + + *num_of_builders = idx; + + return 0; +} + +static int dr_matcher_connect(struct mlx5dr_domain *dmn, + struct mlx5dr_matcher_rx_tx *curr_nic_matcher, + struct mlx5dr_matcher_rx_tx *next_nic_matcher, + struct mlx5dr_matcher_rx_tx *prev_nic_matcher) +{ + struct mlx5dr_table_rx_tx *nic_tbl = curr_nic_matcher->nic_tbl; + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *prev_htbl; + int ret; + + /* Connect end anchor hash table to next_htbl or to the default address */ + if (next_nic_matcher) { + info.type = CONNECT_HIT; + info.hit_next_htbl = next_nic_matcher->s_htbl; + } else { + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_tbl->default_icm_addr; + } + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + curr_nic_matcher->e_anchor, + &info, info.type == CONNECT_HIT); + if (ret) + return ret; + + /* Connect start hash table to end anchor */ + info.type = CONNECT_MISS; + info.miss_icm_addr = curr_nic_matcher->e_anchor->chunk->icm_addr; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + curr_nic_matcher->s_htbl, + &info, false); + if (ret) + return ret; + + /* Connect previous hash table to matcher start hash table */ + if (prev_nic_matcher) + prev_htbl = prev_nic_matcher->e_anchor; + else + prev_htbl = nic_tbl->s_anchor; + + info.type = CONNECT_HIT; + info.hit_next_htbl = curr_nic_matcher->s_htbl; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_htbl, + &info, true); + if (ret) + return ret; + + /* Update the pointing ste and next hash table */ + curr_nic_matcher->s_htbl->pointing_ste = prev_htbl->ste_arr; + prev_htbl->ste_arr[0].next_htbl = curr_nic_matcher->s_htbl; + + if (next_nic_matcher) { + next_nic_matcher->s_htbl->pointing_ste = curr_nic_matcher->e_anchor->ste_arr; + curr_nic_matcher->e_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl; + } + + return 0; +} + +static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_matcher *next_matcher, *prev_matcher, *tmp_matcher; + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + bool first = true; + int ret; + + next_matcher = NULL; + if (!list_empty(&tbl->matcher_list)) + list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) { + if (tmp_matcher->prio >= matcher->prio) { + next_matcher = tmp_matcher; + break; + } + first = false; + } + + prev_matcher = NULL; + if (next_matcher && !first) + prev_matcher = list_entry(next_matcher->matcher_list.prev, + struct mlx5dr_matcher, + matcher_list); + else if (!first) + prev_matcher = list_entry(tbl->matcher_list.prev, + struct mlx5dr_matcher, + matcher_list); + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + ret = dr_matcher_connect(dmn, &matcher->rx, + next_matcher ? &next_matcher->rx : NULL, + prev_matcher ? &prev_matcher->rx : NULL); + if (ret) + return ret; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + ret = dr_matcher_connect(dmn, &matcher->tx, + next_matcher ? &next_matcher->tx : NULL, + prev_matcher ? &prev_matcher->tx : NULL); + if (ret) + return ret; + } + + if (prev_matcher) + list_add(&matcher->matcher_list, &prev_matcher->matcher_list); + else if (next_matcher) + list_add_tail(&matcher->matcher_list, + &next_matcher->matcher_list); + else + list_add(&matcher->matcher_list, &tbl->matcher_list); + + return 0; +} + +static void dr_matcher_uninit_nic(struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + mlx5dr_htbl_put(nic_matcher->s_htbl); + mlx5dr_htbl_put(nic_matcher->e_anchor); +} + +static void dr_matcher_uninit_fdb(struct mlx5dr_matcher *matcher) +{ + dr_matcher_uninit_nic(&matcher->rx); + dr_matcher_uninit_nic(&matcher->tx); +} + +static void dr_matcher_uninit(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_matcher_uninit_nic(&matcher->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_matcher_uninit_nic(&matcher->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_matcher_uninit_fdb(matcher); + break; + default: + WARN_ON(true); + break; + } +} + +static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + int ret, ret_v4, ret_v6; + + ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false); + ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true); + + if (ret_v4 && ret_v6) { + mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n"); + return -EINVAL; + } + + if (!ret_v4) + nic_matcher->ste_builder = nic_matcher->ste_builder4; + else + nic_matcher->ste_builder = nic_matcher->ste_builder6; + + nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!nic_matcher->e_anchor) + return -ENOMEM; + + nic_matcher->s_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + nic_matcher->ste_builder[0].lu_type, + nic_matcher->ste_builder[0].byte_mask); + if (!nic_matcher->s_htbl) { + ret = -ENOMEM; + goto free_e_htbl; + } + + /* make sure the tables exist while empty */ + mlx5dr_htbl_get(nic_matcher->s_htbl); + mlx5dr_htbl_get(nic_matcher->e_anchor); + + return 0; + +free_e_htbl: + mlx5dr_ste_htbl_free(nic_matcher->e_anchor); + return ret; +} + +static int dr_matcher_init_fdb(struct mlx5dr_matcher *matcher) +{ + int ret; + + ret = dr_matcher_init_nic(matcher, &matcher->rx); + if (ret) + return ret; + + ret = dr_matcher_init_nic(matcher, &matcher->tx); + if (ret) + goto uninit_nic_rx; + + return 0; + +uninit_nic_rx: + dr_matcher_uninit_nic(&matcher->rx); + return ret; +} + +static int dr_matcher_init(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *mask) +{ + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + int ret; + + if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) { + mlx5dr_info(dmn, "Invalid match criteria attribute\n"); + return -EINVAL; + } + + if (mask) { + if (mask->match_sz > sizeof(struct mlx5dr_match_param)) { + mlx5dr_info(dmn, "Invalid match size attribute\n"); + return -EINVAL; + } + mlx5dr_ste_copy_param(matcher->match_criteria, + &matcher->mask, mask); + } + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + matcher->rx.nic_tbl = &tbl->rx; + ret = dr_matcher_init_nic(matcher, &matcher->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + matcher->tx.nic_tbl = &tbl->tx; + ret = dr_matcher_init_nic(matcher, &matcher->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + matcher->rx.nic_tbl = &tbl->rx; + matcher->tx.nic_tbl = &tbl->tx; + ret = dr_matcher_init_fdb(matcher); + break; + default: + WARN_ON(true); + return -EINVAL; + } + + return ret; +} + +struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *tbl, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask) +{ + struct mlx5dr_matcher *matcher; + int ret; + + refcount_inc(&tbl->refcount); + + matcher = kzalloc(sizeof(*matcher), GFP_KERNEL); + if (!matcher) + goto dec_ref; + + matcher->tbl = tbl; + matcher->prio = priority; + matcher->match_criteria = match_criteria_enable; + refcount_set(&matcher->refcount, 1); + INIT_LIST_HEAD(&matcher->matcher_list); + + mutex_lock(&tbl->dmn->mutex); + + ret = dr_matcher_init(matcher, mask); + if (ret) + goto free_matcher; + + ret = dr_matcher_add_to_tbl(matcher); + if (ret) + goto matcher_uninit; + + mutex_unlock(&tbl->dmn->mutex); + + return matcher; + +matcher_uninit: + dr_matcher_uninit(matcher); +free_matcher: + mutex_unlock(&tbl->dmn->mutex); + kfree(matcher); +dec_ref: + refcount_dec(&tbl->refcount); + return NULL; +} + +static int dr_matcher_disconnect(struct mlx5dr_domain *dmn, + struct mlx5dr_table_rx_tx *nic_tbl, + struct mlx5dr_matcher_rx_tx *next_nic_matcher, + struct mlx5dr_matcher_rx_tx *prev_nic_matcher) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *prev_anchor; + + if (prev_nic_matcher) + prev_anchor = prev_nic_matcher->e_anchor; + else + prev_anchor = nic_tbl->s_anchor; + + /* Connect previous anchor hash table to next matcher or to the default address */ + if (next_nic_matcher) { + info.type = CONNECT_HIT; + info.hit_next_htbl = next_nic_matcher->s_htbl; + next_nic_matcher->s_htbl->pointing_ste = prev_anchor->ste_arr; + prev_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl; + } else { + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_tbl->default_icm_addr; + prev_anchor->ste_arr[0].next_htbl = NULL; + } + + return mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_anchor, + &info, true); +} + +static int dr_matcher_remove_from_tbl(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_matcher *prev_matcher, *next_matcher; + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + int ret = 0; + + if (list_is_last(&matcher->matcher_list, &tbl->matcher_list)) + next_matcher = NULL; + else + next_matcher = list_next_entry(matcher, matcher_list); + + if (matcher->matcher_list.prev == &tbl->matcher_list) + prev_matcher = NULL; + else + prev_matcher = list_prev_entry(matcher, matcher_list); + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + ret = dr_matcher_disconnect(dmn, &tbl->rx, + next_matcher ? &next_matcher->rx : NULL, + prev_matcher ? &prev_matcher->rx : NULL); + if (ret) + return ret; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + ret = dr_matcher_disconnect(dmn, &tbl->tx, + next_matcher ? &next_matcher->tx : NULL, + prev_matcher ? &prev_matcher->tx : NULL); + if (ret) + return ret; + } + + list_del(&matcher->matcher_list); + + return 0; +} + +int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_table *tbl = matcher->tbl; + + if (refcount_read(&matcher->refcount) > 1) + return -EBUSY; + + mutex_lock(&tbl->dmn->mutex); + + dr_matcher_remove_from_tbl(matcher); + dr_matcher_uninit(matcher); + refcount_dec(&matcher->tbl->refcount); + + mutex_unlock(&tbl->dmn->mutex); + kfree(matcher); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c new file mode 100644 index 000000000000..3bc3f66b8fa8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -0,0 +1,1243 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define DR_RULE_MAX_STE_CHAIN (DR_RULE_MAX_STES + DR_ACTION_MAX_STES) + +struct mlx5dr_rule_action_member { + struct mlx5dr_action *action; + struct list_head list; +}; + +static int dr_rule_append_to_miss_list(struct mlx5dr_ste *new_last_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info_last; + struct mlx5dr_ste *last_ste; + + /* The new entry will be inserted after the last */ + last_ste = list_entry(miss_list->prev, struct mlx5dr_ste, miss_list_node); + WARN_ON(!last_ste); + + ste_info_last = kzalloc(sizeof(*ste_info_last), GFP_KERNEL); + if (!ste_info_last) + return -ENOMEM; + + mlx5dr_ste_set_miss_addr(last_ste->hw_ste, + mlx5dr_ste_get_icm_addr(new_last_ste)); + list_add_tail(&new_last_ste->miss_list_node, miss_list); + + mlx5dr_send_fill_and_append_ste_send_info(last_ste, DR_STE_SIZE_REDUCED, + 0, last_ste->hw_ste, + ste_info_last, send_list, true); + + return 0; +} + +static struct mlx5dr_ste * +dr_rule_create_collision_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 *hw_ste) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_htbl *new_htbl; + struct mlx5dr_ste *ste; + + /* Create new table for miss entry */ + new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!new_htbl) { + mlx5dr_dbg(dmn, "Failed allocating collision table\n"); + return NULL; + } + + /* One and only entry, never grows */ + ste = new_htbl->ste_arr; + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + mlx5dr_htbl_get(new_htbl); + + return ste; +} + +static struct mlx5dr_ste * +dr_rule_create_collision_entry(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 *hw_ste, + struct mlx5dr_ste *orig_ste) +{ + struct mlx5dr_ste *ste; + + ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste); + if (!ste) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed creating collision entry\n"); + return NULL; + } + + ste->ste_chain_location = orig_ste->ste_chain_location; + + /* In collision entry, all members share the same miss_list_head */ + ste->htbl->miss_list = mlx5dr_ste_get_miss_list(orig_ste); + + /* Next table */ + if (mlx5dr_ste_create_next_htbl(matcher, nic_matcher, ste, hw_ste, + DR_CHUNK_SIZE_1)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n"); + goto free_tbl; + } + + return ste; + +free_tbl: + mlx5dr_ste_free(ste, matcher, nic_matcher); + return NULL; +} + +static int +dr_rule_handle_one_ste_in_update_list(struct mlx5dr_ste_send_info *ste_info, + struct mlx5dr_domain *dmn) +{ + int ret; + + list_del(&ste_info->send_list); + ret = mlx5dr_send_postsend_ste(dmn, ste_info->ste, ste_info->data, + ste_info->size, ste_info->offset); + if (ret) + goto out; + /* Copy data to ste, only reduced size, the last 16B (mask) + * is already written to the hw. + */ + memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_REDUCED); + +out: + kfree(ste_info); + return ret; +} + +static int dr_rule_send_update_list(struct list_head *send_ste_list, + struct mlx5dr_domain *dmn, + bool is_reverse) +{ + struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info; + int ret; + + if (is_reverse) { + list_for_each_entry_safe_reverse(ste_info, tmp_ste_info, + send_ste_list, send_list) { + ret = dr_rule_handle_one_ste_in_update_list(ste_info, + dmn); + if (ret) + return ret; + } + } else { + list_for_each_entry_safe(ste_info, tmp_ste_info, + send_ste_list, send_list) { + ret = dr_rule_handle_one_ste_in_update_list(ste_info, + dmn); + if (ret) + return ret; + } + } + + return 0; +} + +static struct mlx5dr_ste * +dr_rule_find_ste_in_miss_list(struct list_head *miss_list, u8 *hw_ste) +{ + struct mlx5dr_ste *ste; + + if (list_empty(miss_list)) + return NULL; + + /* Check if hw_ste is present in the list */ + list_for_each_entry(ste, miss_list, miss_list_node) { + if (mlx5dr_ste_equal_tag(ste->hw_ste, hw_ste)) + return ste; + } + + return NULL; +} + +static struct mlx5dr_ste * +dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct list_head *update_list, + struct mlx5dr_ste *col_ste, + u8 *hw_ste) +{ + struct mlx5dr_ste *new_ste; + int ret; + + new_ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste); + if (!new_ste) + return NULL; + + /* In collision entry, all members share the same miss_list_head */ + new_ste->htbl->miss_list = mlx5dr_ste_get_miss_list(col_ste); + + /* Update the previous from the list */ + ret = dr_rule_append_to_miss_list(new_ste, + mlx5dr_ste_get_miss_list(col_ste), + update_list); + if (ret) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed update dup entry\n"); + goto err_exit; + } + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); + return NULL; +} + +static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *cur_ste, + struct mlx5dr_ste *new_ste) +{ + new_ste->next_htbl = cur_ste->next_htbl; + new_ste->ste_chain_location = cur_ste->ste_chain_location; + + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, new_ste->ste_chain_location)) + new_ste->next_htbl->pointing_ste = new_ste; + + /* We need to copy the refcount since this ste + * may have been traversed several times + */ + refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount)); + + /* Link old STEs rule_mem list to the new ste */ + mlx5dr_rule_update_rule_member(cur_ste, new_ste); + INIT_LIST_HEAD(&new_ste->rule_list); + list_splice_tail_init(&cur_ste->rule_list, &new_ste->rule_list); +} + +static struct mlx5dr_ste * +dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *cur_ste, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste_send_info *ste_info; + bool use_update_list = false; + u8 hw_ste[DR_STE_SIZE] = {}; + struct mlx5dr_ste *new_ste; + int new_idx; + u8 sb_idx; + + /* Copy STE mask from the matcher */ + sb_idx = cur_ste->ste_chain_location - 1; + mlx5dr_ste_set_bit_mask(hw_ste, nic_matcher->ste_builder[sb_idx].bit_mask); + + /* Copy STE control and tag */ + memcpy(hw_ste, cur_ste->hw_ste, DR_STE_SIZE_REDUCED); + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + + new_idx = mlx5dr_ste_calc_hash_index(hw_ste, new_htbl); + new_ste = &new_htbl->ste_arr[new_idx]; + + if (mlx5dr_ste_not_used_ste(new_ste)) { + mlx5dr_htbl_get(new_htbl); + list_add_tail(&new_ste->miss_list_node, + mlx5dr_ste_get_miss_list(new_ste)); + } else { + new_ste = dr_rule_rehash_handle_collision(matcher, + nic_matcher, + update_list, + new_ste, + hw_ste); + if (!new_ste) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed adding collision entry, index: %d\n", + new_idx); + return NULL; + } + new_htbl->ctrl.num_of_collisions++; + use_update_list = true; + } + + memcpy(new_ste->hw_ste, hw_ste, DR_STE_SIZE_REDUCED); + + new_htbl->ctrl.num_of_valid_entries++; + + if (use_update_list) { + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + goto err_exit; + + mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0, + hw_ste, ste_info, + update_list, true); + } + + dr_rule_rehash_copy_ste_ctrl(matcher, nic_matcher, cur_ste, new_ste); + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); + return NULL; +} + +static int dr_rule_rehash_copy_miss_list(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct list_head *cur_miss_list, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste *tmp_ste, *cur_ste, *new_ste; + + if (list_empty(cur_miss_list)) + return 0; + + list_for_each_entry_safe(cur_ste, tmp_ste, cur_miss_list, miss_list_node) { + new_ste = dr_rule_rehash_copy_ste(matcher, + nic_matcher, + cur_ste, + new_htbl, + update_list); + if (!new_ste) + goto err_insert; + + list_del(&cur_ste->miss_list_node); + mlx5dr_htbl_put(cur_ste->htbl); + } + return 0; + +err_insert: + mlx5dr_err(matcher->tbl->dmn, "Fatal error during resize\n"); + WARN_ON(true); + return -EINVAL; +} + +static int dr_rule_rehash_copy_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_htbl *cur_htbl, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste *cur_ste; + int cur_entries; + int err = 0; + int i; + + cur_entries = mlx5dr_icm_pool_chunk_size_to_entries(cur_htbl->chunk_size); + + if (cur_entries < 1) { + mlx5dr_dbg(matcher->tbl->dmn, "Invalid number of entries\n"); + return -EINVAL; + } + + for (i = 0; i < cur_entries; i++) { + cur_ste = &cur_htbl->ste_arr[i]; + if (mlx5dr_ste_not_used_ste(cur_ste)) /* Empty, nothing to copy */ + continue; + + err = dr_rule_rehash_copy_miss_list(matcher, + nic_matcher, + mlx5dr_ste_get_miss_list(cur_ste), + new_htbl, + update_list); + if (err) + goto clean_copy; + } + +clean_copy: + return err; +} + +static struct mlx5dr_ste_htbl * +dr_rule_rehash_htbl(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste_htbl *cur_htbl, + u8 ste_location, + struct list_head *update_list, + enum mlx5dr_icm_chunk_size new_size) +{ + struct mlx5dr_ste_send_info *del_ste_info, *tmp_ste_info; + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_ste_send_info *ste_info; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_domain_rx_tx *nic_dmn; + u8 formatted_ste[DR_STE_SIZE] = {}; + LIST_HEAD(rehash_table_send_list); + struct mlx5dr_ste *ste_to_update; + struct mlx5dr_ste_htbl *new_htbl; + int err; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + return NULL; + + new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + new_size, + cur_htbl->lu_type, + cur_htbl->byte_mask); + if (!new_htbl) { + mlx5dr_err(dmn, "Failed to allocate new hash table\n"); + goto free_ste_info; + } + + /* Write new table to HW */ + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr; + mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi, + nic_dmn, + new_htbl, + formatted_ste, + &info); + + new_htbl->pointing_ste = cur_htbl->pointing_ste; + new_htbl->pointing_ste->next_htbl = new_htbl; + err = dr_rule_rehash_copy_htbl(matcher, + nic_matcher, + cur_htbl, + new_htbl, + &rehash_table_send_list); + if (err) + goto free_new_htbl; + + if (mlx5dr_send_postsend_htbl(dmn, new_htbl, formatted_ste, + nic_matcher->ste_builder[ste_location - 1].bit_mask)) { + mlx5dr_err(dmn, "Failed writing table to HW\n"); + goto free_new_htbl; + } + + /* Writing to the hw is done in regular order of rehash_table_send_list, + * in order to have the origin data written before the miss address of + * collision entries, if exists. + */ + if (dr_rule_send_update_list(&rehash_table_send_list, dmn, false)) { + mlx5dr_err(dmn, "Failed updating table to HW\n"); + goto free_ste_list; + } + + /* Connect previous hash table to current */ + if (ste_location == 1) { + /* The previous table is an anchor, anchors size is always one STE */ + struct mlx5dr_ste_htbl *prev_htbl = cur_htbl->pointing_ste->htbl; + + /* On matcher s_anchor we keep an extra refcount */ + mlx5dr_htbl_get(new_htbl); + mlx5dr_htbl_put(cur_htbl); + + nic_matcher->s_htbl = new_htbl; + + /* It is safe to operate dr_ste_set_hit_addr on the hw_ste here + * (48B len) which works only on first 32B + */ + mlx5dr_ste_set_hit_addr(prev_htbl->ste_arr[0].hw_ste, + new_htbl->chunk->icm_addr, + new_htbl->chunk->num_of_entries); + + ste_to_update = &prev_htbl->ste_arr[0]; + } else { + mlx5dr_ste_set_hit_addr_by_next_htbl(cur_htbl->pointing_ste->hw_ste, + new_htbl); + ste_to_update = cur_htbl->pointing_ste; + } + + mlx5dr_send_fill_and_append_ste_send_info(ste_to_update, DR_STE_SIZE_REDUCED, + 0, ste_to_update->hw_ste, ste_info, + update_list, false); + + return new_htbl; + +free_ste_list: + /* Clean all ste_info's from the new table */ + list_for_each_entry_safe(del_ste_info, tmp_ste_info, + &rehash_table_send_list, send_list) { + list_del(&del_ste_info->send_list); + kfree(del_ste_info); + } + +free_new_htbl: + mlx5dr_ste_htbl_free(new_htbl); +free_ste_info: + kfree(ste_info); + mlx5dr_info(dmn, "Failed creating rehash table\n"); + return NULL; +} + +static struct mlx5dr_ste_htbl *dr_rule_rehash(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste_htbl *cur_htbl, + u8 ste_location, + struct list_head *update_list) +{ + struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn; + enum mlx5dr_icm_chunk_size new_size; + + new_size = mlx5dr_icm_next_higher_chunk(cur_htbl->chunk_size); + new_size = min_t(u32, new_size, dmn->info.max_log_sw_icm_sz); + + if (new_size == cur_htbl->chunk_size) + return NULL; /* Skip rehash, we already at the max size */ + + return dr_rule_rehash_htbl(rule, nic_rule, cur_htbl, ste_location, + update_list, new_size); +} + +static struct mlx5dr_ste * +dr_rule_handle_collision(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *hw_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info; + struct mlx5dr_ste *new_ste; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + return NULL; + + new_ste = dr_rule_create_collision_entry(matcher, nic_matcher, hw_ste, ste); + if (!new_ste) + goto free_send_info; + + if (dr_rule_append_to_miss_list(new_ste, miss_list, send_list)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed to update prev miss_list\n"); + goto err_exit; + } + + mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0, hw_ste, + ste_info, send_list, false); + + ste->htbl->ctrl.num_of_collisions++; + ste->htbl->ctrl.num_of_valid_entries++; + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); +free_send_info: + kfree(ste_info); + return NULL; +} + +static void dr_rule_remove_action_members(struct mlx5dr_rule *rule) +{ + struct mlx5dr_rule_action_member *action_mem; + struct mlx5dr_rule_action_member *tmp; + + list_for_each_entry_safe(action_mem, tmp, &rule->rule_actions_list, list) { + list_del(&action_mem->list); + refcount_dec(&action_mem->action->refcount); + kvfree(action_mem); + } +} + +static int dr_rule_add_action_members(struct mlx5dr_rule *rule, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_rule_action_member *action_mem; + int i; + + for (i = 0; i < num_actions; i++) { + action_mem = kvzalloc(sizeof(*action_mem), GFP_KERNEL); + if (!action_mem) + goto free_action_members; + + action_mem->action = actions[i]; + INIT_LIST_HEAD(&action_mem->list); + list_add_tail(&action_mem->list, &rule->rule_actions_list); + refcount_inc(&action_mem->action->refcount); + } + + return 0; + +free_action_members: + dr_rule_remove_action_members(rule); + return -ENOMEM; +} + +/* While the pointer of ste is no longer valid, like while moving ste to be + * the first in the miss_list, and to be in the origin table, + * all rule-members that are attached to this ste should update their ste member + * to the new pointer + */ +void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste, + struct mlx5dr_ste *new_ste) +{ + struct mlx5dr_rule_member *rule_mem; + + if (!list_empty(&ste->rule_list)) + list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list) + rule_mem->ste = new_ste; +} + +static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule) +{ + struct mlx5dr_rule_member *rule_mem; + struct mlx5dr_rule_member *tmp_mem; + + if (list_empty(&nic_rule->rule_members_list)) + return; + list_for_each_entry_safe(rule_mem, tmp_mem, &nic_rule->rule_members_list, list) { + list_del(&rule_mem->list); + list_del(&rule_mem->use_ste_list); + mlx5dr_ste_put(rule_mem->ste, rule->matcher, nic_rule->nic_matcher); + kvfree(rule_mem); + } +} + +static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn) +{ + struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; + + if (dmn->info.max_log_sw_icm_sz <= htbl->chunk_size) + return false; + + if (!ctrl->may_grow) + return false; + + if (ctrl->num_of_collisions >= ctrl->increase_threshold && + (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) + return true; + + return false; +} + +static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste *ste) +{ + struct mlx5dr_rule_member *rule_mem; + + rule_mem = kvzalloc(sizeof(*rule_mem), GFP_KERNEL); + if (!rule_mem) + return -ENOMEM; + + rule_mem->ste = ste; + list_add_tail(&rule_mem->list, &nic_rule->rule_members_list); + + list_add_tail(&rule_mem->use_ste_list, &ste->rule_list); + + return 0; +} + +static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct list_head *send_ste_list, + struct mlx5dr_ste *last_ste, + u8 *hw_ste_arr, + u32 new_hw_ste_arr_sz) +{ + struct mlx5dr_matcher_rx_tx *nic_matcher = nic_rule->nic_matcher; + struct mlx5dr_ste_send_info *ste_info_arr[DR_ACTION_MAX_STES]; + u8 num_of_builders = nic_matcher->num_of_builders; + struct mlx5dr_matcher *matcher = rule->matcher; + u8 *curr_hw_ste, *prev_hw_ste; + struct mlx5dr_ste *action_ste; + int i, k, ret; + + /* Two cases: + * 1. num_of_builders is equal to new_hw_ste_arr_sz, the action in the ste + * 2. num_of_builders is less then new_hw_ste_arr_sz, new ste was added + * to support the action. + */ + if (num_of_builders == new_hw_ste_arr_sz) + return 0; + + for (i = num_of_builders, k = 0; i < new_hw_ste_arr_sz; i++, k++) { + curr_hw_ste = hw_ste_arr + i * DR_STE_SIZE; + prev_hw_ste = (i == 0) ? curr_hw_ste : hw_ste_arr + ((i - 1) * DR_STE_SIZE); + action_ste = dr_rule_create_collision_htbl(matcher, + nic_matcher, + curr_hw_ste); + if (!action_ste) + return -ENOMEM; + + mlx5dr_ste_get(action_ste); + + /* While free ste we go over the miss list, so add this ste to the list */ + list_add_tail(&action_ste->miss_list_node, + mlx5dr_ste_get_miss_list(action_ste)); + + ste_info_arr[k] = kzalloc(sizeof(*ste_info_arr[k]), + GFP_KERNEL); + if (!ste_info_arr[k]) + goto err_exit; + + /* Point current ste to the new action */ + mlx5dr_ste_set_hit_addr_by_next_htbl(prev_hw_ste, action_ste->htbl); + ret = dr_rule_add_member(nic_rule, action_ste); + if (ret) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed adding rule member\n"); + goto free_ste_info; + } + mlx5dr_send_fill_and_append_ste_send_info(action_ste, DR_STE_SIZE, 0, + curr_hw_ste, + ste_info_arr[k], + send_ste_list, false); + } + + return 0; + +free_ste_info: + kfree(ste_info_arr[k]); +err_exit: + mlx5dr_ste_put(action_ste, matcher, nic_matcher); + return -ENOMEM; +} + +static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_htbl *cur_htbl, + struct mlx5dr_ste *ste, + u8 ste_location, + u8 *hw_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info; + + /* Take ref on table, only on first time this ste is used */ + mlx5dr_htbl_get(cur_htbl); + + /* new entry -> new branch */ + list_add_tail(&ste->miss_list_node, miss_list); + + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + + ste->ste_chain_location = ste_location; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + goto clean_ste_setting; + + if (mlx5dr_ste_create_next_htbl(matcher, + nic_matcher, + ste, + hw_ste, + DR_CHUNK_SIZE_1)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n"); + goto clean_ste_info; + } + + cur_htbl->ctrl.num_of_valid_entries++; + + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, 0, hw_ste, + ste_info, send_list, false); + + return 0; + +clean_ste_info: + kfree(ste_info); +clean_ste_setting: + list_del_init(&ste->miss_list_node); + mlx5dr_htbl_put(cur_htbl); + + return -ENOMEM; +} + +static struct mlx5dr_ste * +dr_rule_handle_ste_branch(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *cur_htbl, + u8 *hw_ste, + u8 ste_location, + struct mlx5dr_ste_htbl **put_htbl) +{ + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_domain_rx_tx *nic_dmn; + struct mlx5dr_ste_htbl *new_htbl; + struct mlx5dr_ste *matched_ste; + struct list_head *miss_list; + bool skip_rehash = false; + struct mlx5dr_ste *ste; + int index; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + +again: + index = mlx5dr_ste_calc_hash_index(hw_ste, cur_htbl); + miss_list = &cur_htbl->chunk->miss_list[index]; + ste = &cur_htbl->ste_arr[index]; + + if (mlx5dr_ste_not_used_ste(ste)) { + if (dr_rule_handle_empty_entry(matcher, nic_matcher, cur_htbl, + ste, ste_location, + hw_ste, miss_list, + send_ste_list)) + return NULL; + } else { + /* Hash table index in use, check if this ste is in the miss list */ + matched_ste = dr_rule_find_ste_in_miss_list(miss_list, hw_ste); + if (matched_ste) { + /* If it is last STE in the chain, and has the same tag + * it means that all the previous stes are the same, + * if so, this rule is duplicated. + */ + if (mlx5dr_ste_is_last_in_rule(nic_matcher, + matched_ste->ste_chain_location)) { + mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n"); + return NULL; + } + return matched_ste; + } + + if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) { + /* Hash table index in use, try to resize of the hash */ + skip_rehash = true; + + /* Hold the table till we update. + * Release in dr_rule_create_rule() + */ + *put_htbl = cur_htbl; + mlx5dr_htbl_get(cur_htbl); + + new_htbl = dr_rule_rehash(rule, nic_rule, cur_htbl, + ste_location, send_ste_list); + if (!new_htbl) { + mlx5dr_htbl_put(cur_htbl); + mlx5dr_info(dmn, "failed creating rehash table, htbl-log_size: %d\n", + cur_htbl->chunk_size); + } else { + cur_htbl = new_htbl; + } + goto again; + } else { + /* Hash table index in use, add another collision (miss) */ + ste = dr_rule_handle_collision(matcher, + nic_matcher, + ste, + hw_ste, + miss_list, + send_ste_list); + if (!ste) { + mlx5dr_dbg(dmn, "failed adding collision entry, index: %d\n", + index); + return NULL; + } + } + } + return ste; +} + +static bool dr_rule_cmp_value_to_mask(u8 *mask, u8 *value, + u32 s_idx, u32 e_idx) +{ + u32 i; + + for (i = s_idx; i < e_idx; i++) { + if (value[i] & ~mask[i]) { + pr_info("Rule parameters contains a value not specified by mask\n"); + return false; + } + } + return true; +} + +static bool dr_rule_verify(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + struct mlx5dr_match_param *param) +{ + u8 match_criteria = matcher->match_criteria; + size_t value_size = value->match_sz; + u8 *mask_p = (u8 *)&matcher->mask; + u8 *param_p = (u8 *)param; + u32 s_idx, e_idx; + + if (!value_size || + (value_size > sizeof(struct mlx5dr_match_param) || + (value_size % sizeof(u32)))) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule parameters length is incorrect\n"); + return false; + } + + mlx5dr_ste_copy_param(matcher->match_criteria, param, value); + + if (match_criteria & DR_MATCHER_CRITERIA_OUTER) { + s_idx = offsetof(struct mlx5dr_match_param, outer); + e_idx = min(s_idx + sizeof(param->outer), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule outer parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC) { + s_idx = offsetof(struct mlx5dr_match_param, misc); + e_idx = min(s_idx + sizeof(param->misc), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_INNER) { + s_idx = offsetof(struct mlx5dr_match_param, inner); + e_idx = min(s_idx + sizeof(param->inner), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule inner parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC2) { + s_idx = offsetof(struct mlx5dr_match_param, misc2); + e_idx = min(s_idx + sizeof(param->misc2), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc2 parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC3) { + s_idx = offsetof(struct mlx5dr_match_param, misc3); + e_idx = min(s_idx + sizeof(param->misc3), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc3 parameters contains a value not specified by mask\n"); + return false; + } + } + return true; +} + +static int dr_rule_destroy_rule_nic(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule) +{ + dr_rule_clean_rule_members(rule, nic_rule); + return 0; +} + +static int dr_rule_destroy_rule_fdb(struct mlx5dr_rule *rule) +{ + dr_rule_destroy_rule_nic(rule, &rule->rx); + dr_rule_destroy_rule_nic(rule, &rule->tx); + return 0; +} + +static int dr_rule_destroy_rule(struct mlx5dr_rule *rule) +{ + struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_rule_destroy_rule_nic(rule, &rule->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_rule_destroy_rule_nic(rule, &rule->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_rule_destroy_rule_fdb(rule); + break; + default: + return -EINVAL; + } + + dr_rule_remove_action_members(rule); + kfree(rule); + return 0; +} + +static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param) +{ + return (param->outer.ip_version == 6 || + param->inner.ip_version == 6 || + param->outer.ethertype == ETH_P_IPV6 || + param->inner.ethertype == ETH_P_IPV6); +} + +static bool dr_rule_skip(enum mlx5dr_domain_type domain, + enum mlx5dr_ste_entry_type ste_type, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value) +{ + if (domain != MLX5DR_DOMAIN_TYPE_FDB) + return false; + + if (mask->misc.source_port) { + if (ste_type == MLX5DR_STE_TYPE_RX) + if (value->misc.source_port != WIRE_PORT) + return true; + + if (ste_type == MLX5DR_STE_TYPE_TX) + if (value->misc.source_port == WIRE_PORT) + return true; + } + + /* Metadata C can be used to describe the source vport */ + if (mask->misc2.metadata_reg_c_0) { + if (ste_type == MLX5DR_STE_TYPE_RX) + if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) != WIRE_PORT) + return true; + + if (ste_type == MLX5DR_STE_TYPE_TX) + if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) == WIRE_PORT) + return true; + } + return false; +} + +static int +dr_rule_create_rule_nic(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_match_param *param, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info; + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_domain_rx_tx *nic_dmn; + struct mlx5dr_ste_htbl *htbl = NULL; + struct mlx5dr_ste_htbl *cur_htbl; + struct mlx5dr_ste *ste = NULL; + LIST_HEAD(send_ste_list); + u8 *hw_ste_arr = NULL; + u32 new_hw_ste_arr_sz; + int ret, i; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + + INIT_LIST_HEAD(&nic_rule->rule_members_list); + + if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param)) + return 0; + + ret = mlx5dr_matcher_select_builders(matcher, + nic_matcher, + dr_rule_is_ipv6(param)); + if (ret) + goto out_err; + + hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL); + if (!hw_ste_arr) { + ret = -ENOMEM; + goto out_err; + } + + /* Set the tag values inside the ste array */ + ret = mlx5dr_ste_build_ste_arr(matcher, nic_matcher, param, hw_ste_arr); + if (ret) + goto free_hw_ste; + + /* Set the actions values/addresses inside the ste array */ + ret = mlx5dr_actions_build_ste_arr(matcher, nic_matcher, actions, + num_actions, hw_ste_arr, + &new_hw_ste_arr_sz); + if (ret) + goto free_hw_ste; + + cur_htbl = nic_matcher->s_htbl; + + /* Go over the array of STEs, and build dr_ste accordingly. + * The loop is over only the builders which are equal or less to the + * number of stes, in case we have actions that lives in other stes. + */ + for (i = 0; i < nic_matcher->num_of_builders; i++) { + /* Calculate CRC and keep new ste entry */ + u8 *cur_hw_ste_ent = hw_ste_arr + (i * DR_STE_SIZE); + + ste = dr_rule_handle_ste_branch(rule, + nic_rule, + &send_ste_list, + cur_htbl, + cur_hw_ste_ent, + i + 1, + &htbl); + if (!ste) { + mlx5dr_err(dmn, "Failed creating next branch\n"); + ret = -ENOENT; + goto free_rule; + } + + cur_htbl = ste->next_htbl; + + /* Keep all STEs in the rule struct */ + ret = dr_rule_add_member(nic_rule, ste); + if (ret) { + mlx5dr_dbg(dmn, "Failed adding rule member index %d\n", i); + goto free_ste; + } + + mlx5dr_ste_get(ste); + } + + /* Connect actions */ + ret = dr_rule_handle_action_stes(rule, nic_rule, &send_ste_list, + ste, hw_ste_arr, new_hw_ste_arr_sz); + if (ret) { + mlx5dr_dbg(dmn, "Failed apply actions\n"); + goto free_rule; + } + ret = dr_rule_send_update_list(&send_ste_list, dmn, true); + if (ret) { + mlx5dr_err(dmn, "Failed sending ste!\n"); + goto free_rule; + } + + if (htbl) + mlx5dr_htbl_put(htbl); + + return 0; + +free_ste: + mlx5dr_ste_put(ste, matcher, nic_matcher); +free_rule: + dr_rule_clean_rule_members(rule, nic_rule); + /* Clean all ste_info's */ + list_for_each_entry_safe(ste_info, tmp_ste_info, &send_ste_list, send_list) { + list_del(&ste_info->send_list); + kfree(ste_info); + } +free_hw_ste: + kfree(hw_ste_arr); +out_err: + return ret; +} + +static int +dr_rule_create_rule_fdb(struct mlx5dr_rule *rule, + struct mlx5dr_match_param *param, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_match_param copy_param = {}; + int ret; + + /* Copy match_param since they will be consumed during the first + * nic_rule insertion. + */ + memcpy(©_param, param, sizeof(struct mlx5dr_match_param)); + + ret = dr_rule_create_rule_nic(rule, &rule->rx, param, + num_actions, actions); + if (ret) + return ret; + + ret = dr_rule_create_rule_nic(rule, &rule->tx, ©_param, + num_actions, actions); + if (ret) + goto destroy_rule_nic_rx; + + return 0; + +destroy_rule_nic_rx: + dr_rule_destroy_rule_nic(rule, &rule->rx); + return ret; +} + +static struct mlx5dr_rule * +dr_rule_create_rule(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_match_param param = {}; + struct mlx5dr_rule *rule; + int ret; + + if (!dr_rule_verify(matcher, value, ¶m)) + return NULL; + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return NULL; + + rule->matcher = matcher; + INIT_LIST_HEAD(&rule->rule_actions_list); + + ret = dr_rule_add_action_members(rule, num_actions, actions); + if (ret) + goto free_rule; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + rule->rx.nic_matcher = &matcher->rx; + ret = dr_rule_create_rule_nic(rule, &rule->rx, ¶m, + num_actions, actions); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + rule->tx.nic_matcher = &matcher->tx; + ret = dr_rule_create_rule_nic(rule, &rule->tx, ¶m, + num_actions, actions); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + rule->rx.nic_matcher = &matcher->rx; + rule->tx.nic_matcher = &matcher->tx; + ret = dr_rule_create_rule_fdb(rule, ¶m, + num_actions, actions); + break; + default: + ret = -EINVAL; + break; + } + + if (ret) + goto remove_action_members; + + return rule; + +remove_action_members: + dr_rule_remove_action_members(rule); +free_rule: + kfree(rule); + mlx5dr_info(dmn, "Failed creating rule\n"); + return NULL; +} + +struct mlx5dr_rule *mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_rule *rule; + + mutex_lock(&matcher->tbl->dmn->mutex); + refcount_inc(&matcher->refcount); + + rule = dr_rule_create_rule(matcher, value, num_actions, actions); + if (!rule) + refcount_dec(&matcher->refcount); + + mutex_unlock(&matcher->tbl->dmn->mutex); + + return rule; +} + +int mlx5dr_rule_destroy(struct mlx5dr_rule *rule) +{ + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_table *tbl = rule->matcher->tbl; + int ret; + + mutex_lock(&tbl->dmn->mutex); + + ret = dr_rule_destroy_rule(rule); + + mutex_unlock(&tbl->dmn->mutex); + + if (!ret) + refcount_dec(&matcher->refcount); + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c new file mode 100644 index 000000000000..ef0dea44f3b3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -0,0 +1,976 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define QUEUE_SIZE 128 +#define SIGNAL_PER_DIV_QUEUE 16 +#define TH_NUMS_TO_DRAIN 2 + +enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 }; + +struct dr_data_seg { + u64 addr; + u32 length; + u32 lkey; + unsigned int send_flags; +}; + +struct postsend_info { + struct dr_data_seg write; + struct dr_data_seg read; + u64 remote_addr; + u32 rkey; +}; + +struct dr_qp_rtr_attr { + struct mlx5dr_cmd_gid_attr dgid_attr; + enum ib_mtu mtu; + u32 qp_num; + u16 port_num; + u8 min_rnr_timer; + u8 sgid_index; + u16 udp_src_port; +}; + +struct dr_qp_rts_attr { + u8 timeout; + u8 retry_cnt; + u8 rnr_retry; +}; + +struct dr_qp_init_attr { + u32 cqn; + u32 pdn; + u32 max_send_wr; + struct mlx5_uars_page *uar; +}; + +static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64) +{ + unsigned int idx; + u8 opcode; + + opcode = get_cqe_opcode(cqe64); + if (opcode == MLX5_CQE_REQ_ERR) { + idx = be16_to_cpu(cqe64->wqe_counter) & + (dr_cq->qp->sq.wqe_cnt - 1); + dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1; + } else if (opcode == MLX5_CQE_RESP_ERR) { + ++dr_cq->qp->sq.cc; + } else { + idx = be16_to_cpu(cqe64->wqe_counter) & + (dr_cq->qp->sq.wqe_cnt - 1); + dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1; + + return CQ_OK; + } + + return CQ_POLL_ERR; +} + +static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq) +{ + struct mlx5_cqe64 *cqe64; + int err; + + cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq); + if (!cqe64) + return CQ_EMPTY; + + mlx5_cqwq_pop(&dr_cq->wq); + err = dr_parse_cqe(dr_cq, cqe64); + mlx5_cqwq_update_db_record(&dr_cq->wq); + + return err; +} + +static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne) +{ + int npolled; + int err = 0; + + for (npolled = 0; npolled < ne; ++npolled) { + err = dr_cq_poll_one(dr_cq); + if (err != CQ_OK) + break; + } + + return err == CQ_POLL_ERR ? err : npolled; +} + +static void dr_qp_event(struct mlx5_core_qp *mqp, int event) +{ + pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn); +} + +static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, + struct dr_qp_init_attr *attr) +{ + u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {}; + struct mlx5_wq_param wqp; + struct mlx5dr_qp *dr_qp; + int inlen; + void *qpc; + void *in; + int err; + + dr_qp = kzalloc(sizeof(*dr_qp), GFP_KERNEL); + if (!dr_qp) + return NULL; + + wqp.buf_numa_node = mdev->priv.numa_node; + wqp.db_numa_node = mdev->priv.numa_node; + + dr_qp->rq.pc = 0; + dr_qp->rq.cc = 0; + dr_qp->rq.wqe_cnt = 4; + dr_qp->sq.pc = 0; + dr_qp->sq.cc = 0; + dr_qp->sq.wqe_cnt = roundup_pow_of_two(attr->max_send_wr); + + MLX5_SET(qpc, temp_qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4); + MLX5_SET(qpc, temp_qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); + MLX5_SET(qpc, temp_qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq, + &dr_qp->wq_ctrl); + if (err) { + mlx5_core_info(mdev, "Can't create QP WQ\n"); + goto err_wq; + } + + dr_qp->sq.wqe_head = kcalloc(dr_qp->sq.wqe_cnt, + sizeof(dr_qp->sq.wqe_head[0]), + GFP_KERNEL); + + if (!dr_qp->sq.wqe_head) { + mlx5_core_warn(mdev, "Can't allocate wqe head\n"); + goto err_wqe_head; + } + + inlen = MLX5_ST_SZ_BYTES(create_qp_in) + + MLX5_FLD_SZ_BYTES(create_qp_in, pas[0]) * + dr_qp->wq_ctrl.buf.npages; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_in; + } + + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC); + MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); + MLX5_SET(qpc, qpc, pd, attr->pdn); + MLX5_SET(qpc, qpc, uar_page, attr->uar->index); + MLX5_SET(qpc, qpc, log_page_size, + dr_qp->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET(qpc, qpc, fre, 1); + MLX5_SET(qpc, qpc, rlky, 1); + MLX5_SET(qpc, qpc, cqn_snd, attr->cqn); + MLX5_SET(qpc, qpc, cqn_rcv, attr->cqn); + MLX5_SET(qpc, qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4); + MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); + MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ); + MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma); + if (MLX5_CAP_GEN(mdev, cqe_version) == 1) + MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); + mlx5_fill_page_frag_array(&dr_qp->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(create_qp_in, + in, pas)); + + err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen); + kfree(in); + + if (err) { + mlx5_core_warn(mdev, " Can't create QP\n"); + goto err_in; + } + dr_qp->mqp.event = dr_qp_event; + dr_qp->uar = attr->uar; + + return dr_qp; + +err_in: + kfree(dr_qp->sq.wqe_head); +err_wqe_head: + mlx5_wq_destroy(&dr_qp->wq_ctrl); +err_wq: + kfree(dr_qp); + return NULL; +} + +static void dr_destroy_qp(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp) +{ + mlx5_core_destroy_qp(mdev, &dr_qp->mqp); + kfree(dr_qp->sq.wqe_head); + mlx5_wq_destroy(&dr_qp->wq_ctrl); + kfree(dr_qp); +} + +static void dr_cmd_notify_hw(struct mlx5dr_qp *dr_qp, void *ctrl) +{ + dma_wmb(); + *dr_qp->wq.sq.db = cpu_to_be32(dr_qp->sq.pc & 0xfffff); + + /* After wmb() the hw aware of new work */ + wmb(); + + mlx5_write64(ctrl, dr_qp->uar->map + MLX5_BF_OFFSET); +} + +static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr, + u32 rkey, struct dr_data_seg *data_seg, + u32 opcode, int nreq) +{ + struct mlx5_wqe_raddr_seg *wq_raddr; + struct mlx5_wqe_ctrl_seg *wq_ctrl; + struct mlx5_wqe_data_seg *wq_dseg; + unsigned int size; + unsigned int idx; + + size = sizeof(*wq_ctrl) / 16 + sizeof(*wq_dseg) / 16 + + sizeof(*wq_raddr) / 16; + + idx = dr_qp->sq.pc & (dr_qp->sq.wqe_cnt - 1); + + wq_ctrl = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx); + wq_ctrl->imm = 0; + wq_ctrl->fm_ce_se = (data_seg->send_flags) ? + MLX5_WQE_CTRL_CQ_UPDATE : 0; + wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) | + opcode); + wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8); + wq_raddr = (void *)(wq_ctrl + 1); + wq_raddr->raddr = cpu_to_be64(remote_addr); + wq_raddr->rkey = cpu_to_be32(rkey); + wq_raddr->reserved = 0; + + wq_dseg = (void *)(wq_raddr + 1); + wq_dseg->byte_count = cpu_to_be32(data_seg->length); + wq_dseg->lkey = cpu_to_be32(data_seg->lkey); + wq_dseg->addr = cpu_to_be64(data_seg->addr); + + dr_qp->sq.wqe_head[idx] = dr_qp->sq.pc++; + + if (nreq) + dr_cmd_notify_hw(dr_qp, wq_ctrl); +} + +static void dr_post_send(struct mlx5dr_qp *dr_qp, struct postsend_info *send_info) +{ + dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey, + &send_info->write, MLX5_OPCODE_RDMA_WRITE, 0); + dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey, + &send_info->read, MLX5_OPCODE_RDMA_READ, 1); +} + +/** + * mlx5dr_send_fill_and_append_ste_send_info: Add data to be sent + * with send_list parameters: + * + * @ste: The data that attached to this specific ste + * @size: of data to write + * @offset: of the data from start of the hw_ste entry + * @data: data + * @ste_info: ste to be sent with send_list + * @send_list: to append into it + * @copy_data: if true indicates that the data should be kept because + * it's not backuped any where (like in re-hash). + * if false, it lets the data to be updated after + * it was added to the list. + */ +void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size, + u16 offset, u8 *data, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_list, + bool copy_data) +{ + ste_info->size = size; + ste_info->ste = ste; + ste_info->offset = offset; + + if (copy_data) { + memcpy(ste_info->data_cont, data, size); + ste_info->data = ste_info->data_cont; + } else { + ste_info->data = data; + } + + list_add_tail(&ste_info->send_list, send_list); +} + +/* The function tries to consume one wc each time, unless the queue is full, in + * that case, which means that the hw is behind the sw in a full queue len + * the function will drain the cq till it empty. + */ +static int dr_handle_pending_wc(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring) +{ + bool is_drain = false; + int ne; + + if (send_ring->pending_wqe < send_ring->signal_th) + return 0; + + /* Queue is full start drain it */ + if (send_ring->pending_wqe >= + dmn->send_ring->signal_th * TH_NUMS_TO_DRAIN) + is_drain = true; + + do { + ne = dr_poll_cq(send_ring->cq, 1); + if (ne < 0) + return ne; + else if (ne == 1) + send_ring->pending_wqe -= send_ring->signal_th; + } while (is_drain && send_ring->pending_wqe); + + return 0; +} + +static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring, + struct postsend_info *send_info) +{ + send_ring->pending_wqe++; + + if (send_ring->pending_wqe % send_ring->signal_th == 0) + send_info->write.send_flags |= IB_SEND_SIGNALED; + + send_ring->pending_wqe++; + send_info->read.length = send_info->write.length; + /* Read into the same write area */ + send_info->read.addr = (uintptr_t)send_info->write.addr; + send_info->read.lkey = send_ring->mr->mkey.key; + + if (send_ring->pending_wqe % send_ring->signal_th == 0) + send_info->read.send_flags = IB_SEND_SIGNALED; + else + send_info->read.send_flags = 0; +} + +static int dr_postsend_icm_data(struct mlx5dr_domain *dmn, + struct postsend_info *send_info) +{ + struct mlx5dr_send_ring *send_ring = dmn->send_ring; + u32 buff_offset; + int ret; + + ret = dr_handle_pending_wc(dmn, send_ring); + if (ret) + return ret; + + if (send_info->write.length > dmn->info.max_inline_size) { + buff_offset = (send_ring->tx_head & + (dmn->send_ring->signal_th - 1)) * + send_ring->max_post_send_size; + /* Copy to ring mr */ + memcpy(send_ring->buf + buff_offset, + (void *)(uintptr_t)send_info->write.addr, + send_info->write.length); + send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset; + send_info->write.lkey = send_ring->mr->mkey.key; + } + + send_ring->tx_head++; + dr_fill_data_segs(send_ring, send_info); + dr_post_send(send_ring->qp, send_info); + + return 0; +} + +static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 **data, + u32 *byte_size, + int *iterations, + int *num_stes) +{ + int alloc_size; + + if (htbl->chunk->byte_size > dmn->send_ring->max_post_send_size) { + *iterations = htbl->chunk->byte_size / + dmn->send_ring->max_post_send_size; + *byte_size = dmn->send_ring->max_post_send_size; + alloc_size = *byte_size; + *num_stes = *byte_size / DR_STE_SIZE; + } else { + *iterations = 1; + *num_stes = htbl->chunk->num_of_entries; + alloc_size = *num_stes * DR_STE_SIZE; + } + + *data = kzalloc(alloc_size, GFP_KERNEL); + if (!*data) + return -ENOMEM; + + return 0; +} + +/** + * mlx5dr_send_postsend_ste: write size bytes into offset from the hw cm. + * + * @dmn: Domain + * @ste: The ste struct that contains the data (at + * least part of it) + * @data: The real data to send size data + * @size: for writing. + * @offset: The offset from the icm mapped data to + * start write to this for write only part of the + * buffer. + * + * Return: 0 on success. + */ +int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste, + u8 *data, u16 size, u16 offset) +{ + struct postsend_info send_info = {}; + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = size; + send_info.write.lkey = 0; + send_info.remote_addr = mlx5dr_ste_get_mr_addr(ste) + offset; + send_info.rkey = ste->htbl->chunk->rkey; + + return dr_postsend_icm_data(dmn, &send_info); +} + +int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, u8 *mask) +{ + u32 byte_size = htbl->chunk->byte_size; + int num_stes_per_iter; + int iterations; + u8 *data; + int ret; + int i; + int j; + + ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size, + &iterations, &num_stes_per_iter); + if (ret) + return ret; + + /* Send the data iteration times */ + for (i = 0; i < iterations; i++) { + u32 ste_index = i * (byte_size / DR_STE_SIZE); + struct postsend_info send_info = {}; + + /* Copy all ste's on the data buffer + * need to add the bit_mask + */ + for (j = 0; j < num_stes_per_iter; j++) { + u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste; + u32 ste_off = j * DR_STE_SIZE; + + if (mlx5dr_ste_is_not_valid_entry(hw_ste)) { + memcpy(data + ste_off, + formatted_ste, DR_STE_SIZE); + } else { + /* Copy data */ + memcpy(data + ste_off, + htbl->ste_arr[ste_index + j].hw_ste, + DR_STE_SIZE_REDUCED); + /* Copy bit_mask */ + memcpy(data + ste_off + DR_STE_SIZE_REDUCED, + mask, DR_STE_SIZE_MASK); + } + } + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = + mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index); + send_info.rkey = htbl->chunk->rkey; + + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + goto out_free; + } + +out_free: + kfree(data); + return ret; +} + +/* Initialize htble with default STEs */ +int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *ste_init_data, + bool update_hw_ste) +{ + u32 byte_size = htbl->chunk->byte_size; + int iterations; + int num_stes; + u8 *data; + int ret; + int i; + + ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size, + &iterations, &num_stes); + if (ret) + return ret; + + for (i = 0; i < num_stes; i++) { + u8 *copy_dst; + + /* Copy the same ste on the data buffer */ + copy_dst = data + i * DR_STE_SIZE; + memcpy(copy_dst, ste_init_data, DR_STE_SIZE); + + if (update_hw_ste) { + /* Copy the reduced ste to hash table ste_arr */ + copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; + memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED); + } + } + + /* Send the data iteration times */ + for (i = 0; i < iterations; i++) { + u8 ste_index = i * (byte_size / DR_STE_SIZE); + struct postsend_info send_info = {}; + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = + mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index); + send_info.rkey = htbl->chunk->rkey; + + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + goto out_free; + } + +out_free: + kfree(data); + return ret; +} + +int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action) +{ + struct postsend_info send_info = {}; + int ret; + + send_info.write.addr = (uintptr_t)action->rewrite.data; + send_info.write.length = action->rewrite.chunk->byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = action->rewrite.chunk->mr_addr; + send_info.rkey = action->rewrite.chunk->rkey; + + mutex_lock(&dmn->mutex); + ret = dr_postsend_icm_data(dmn, &send_info); + mutex_unlock(&dmn->mutex); + + return ret; +} + +static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + int port) +{ + u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc); + + MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, port); + MLX5_SET(qpc, qpc, pm_state, MLX5_QPC_PM_STATE_MIGRATED); + MLX5_SET(qpc, qpc, rre, 1); + MLX5_SET(qpc, qpc, rwe, 1); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + struct dr_qp_rts_attr *attr) +{ + u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc); + + MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn); + + MLX5_SET(qpc, qpc, log_ack_req_freq, 0); + MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt); + MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + struct dr_qp_rtr_attr *attr) +{ + u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc); + + MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn); + + MLX5_SET(qpc, qpc, mtu, attr->mtu); + MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1); + MLX5_SET(qpc, qpc, remote_qpn, attr->qp_num); + memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rmac_47_32), + attr->dgid_attr.mac, sizeof(attr->dgid_attr.mac)); + memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rgid_rip), + attr->dgid_attr.gid, sizeof(attr->dgid_attr.gid)); + MLX5_SET(qpc, qpc, primary_address_path.src_addr_index, + attr->sgid_index); + + if (attr->dgid_attr.roce_ver == MLX5_ROCE_VERSION_2) + MLX5_SET(qpc, qpc, primary_address_path.udp_sport, + attr->udp_src_port); + + MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num); + MLX5_SET(qpc, qpc, min_rnr_nak, 1); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_qp *dr_qp = dmn->send_ring->qp; + struct dr_qp_rts_attr rts_attr = {}; + struct dr_qp_rtr_attr rtr_attr = {}; + enum ib_mtu mtu = IB_MTU_1024; + u16 gid_index = 0; + int port = 1; + int ret; + + /* Init */ + ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port); + if (ret) + return ret; + + /* RTR */ + ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr); + if (ret) + return ret; + + rtr_attr.mtu = mtu; + rtr_attr.qp_num = dr_qp->mqp.qpn; + rtr_attr.min_rnr_timer = 12; + rtr_attr.port_num = port; + rtr_attr.sgid_index = gid_index; + rtr_attr.udp_src_port = dmn->info.caps.roce_min_src_udp; + + ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr); + if (ret) + return ret; + + /* RTS */ + rts_attr.timeout = 14; + rts_attr.retry_cnt = 7; + rts_attr.rnr_retry = 7; + + ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr); + if (ret) + return ret; + + return 0; +} + +static void dr_cq_event(struct mlx5_core_cq *mcq, + enum mlx5_event event) +{ + pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); +} + +static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, + struct mlx5_uars_page *uar, + size_t ncqe) +{ + u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {}; + u32 out[MLX5_ST_SZ_DW(create_cq_out)]; + struct mlx5_wq_param wqp; + struct mlx5_cqe64 *cqe; + struct mlx5dr_cq *cq; + int inlen, err, eqn; + unsigned int irqn; + void *cqc, *in; + __be64 *pas; + u32 i; + + cq = kzalloc(sizeof(*cq), GFP_KERNEL); + if (!cq) + return NULL; + + ncqe = roundup_pow_of_two(ncqe); + MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(ncqe)); + + wqp.buf_numa_node = mdev->priv.numa_node; + wqp.db_numa_node = mdev->priv.numa_node; + + err = mlx5_cqwq_create(mdev, &wqp, temp_cqc, &cq->wq, + &cq->wq_ctrl); + if (err) + goto out; + + for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { + cqe = mlx5_cqwq_get_wqe(&cq->wq, i); + cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK; + } + + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + + sizeof(u64) * cq->wq_ctrl.buf.npages; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + goto err_cqwq; + + err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + if (err) { + kvfree(in); + goto err_cqwq; + } + + cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); + MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe)); + MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, uar_page, uar->index); + MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - + MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); + + pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); + mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); + + cq->mcq.event = dr_cq_event; + + err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); + kvfree(in); + + if (err) + goto err_cqwq; + + cq->mcq.cqe_sz = 64; + cq->mcq.set_ci_db = cq->wq_ctrl.db.db; + cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; + *cq->mcq.set_ci_db = 0; + *cq->mcq.arm_db = 0; + cq->mcq.vector = 0; + cq->mcq.irqn = irqn; + cq->mcq.uar = uar; + + return cq; + +err_cqwq: + mlx5_wq_destroy(&cq->wq_ctrl); +out: + kfree(cq); + return NULL; +} + +static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq) +{ + mlx5_core_destroy_cq(mdev, &cq->mcq); + mlx5_wq_destroy(&cq->wq_ctrl); + kfree(cq); +} + +static int +dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey) +{ + u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; + void *mkc; + + 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, a, 1); + MLX5_SET(mkc, mkc, rw, 1); + MLX5_SET(mkc, mkc, rr, 1); + 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); + + return mlx5_core_create_mkey(mdev, mkey, in, sizeof(in)); +} + +static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev, + u32 pdn, void *buf, size_t size) +{ + struct mlx5dr_mr *mr = kzalloc(sizeof(*mr), GFP_KERNEL); + struct device *dma_device; + dma_addr_t dma_addr; + int err; + + if (!mr) + return NULL; + + dma_device = &mdev->pdev->dev; + dma_addr = dma_map_single(dma_device, buf, size, + DMA_BIDIRECTIONAL); + err = dma_mapping_error(dma_device, dma_addr); + if (err) { + mlx5_core_warn(mdev, "Can't dma buf\n"); + kfree(mr); + return NULL; + } + + err = dr_create_mkey(mdev, pdn, &mr->mkey); + if (err) { + mlx5_core_warn(mdev, "Can't create mkey\n"); + dma_unmap_single(dma_device, dma_addr, size, + DMA_BIDIRECTIONAL); + kfree(mr); + return NULL; + } + + mr->dma_addr = dma_addr; + mr->size = size; + mr->addr = buf; + + return mr; +} + +static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr) +{ + mlx5_core_destroy_mkey(mdev, &mr->mkey); + dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size, + DMA_BIDIRECTIONAL); + kfree(mr); +} + +int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) +{ + struct dr_qp_init_attr init_attr = {}; + int cq_size; + int size; + int ret; + + dmn->send_ring = kzalloc(sizeof(*dmn->send_ring), GFP_KERNEL); + if (!dmn->send_ring) + return -ENOMEM; + + cq_size = QUEUE_SIZE + 1; + dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size); + if (!dmn->send_ring->cq) { + ret = -ENOMEM; + goto free_send_ring; + } + + init_attr.cqn = dmn->send_ring->cq->mcq.cqn; + init_attr.pdn = dmn->pdn; + init_attr.uar = dmn->uar; + init_attr.max_send_wr = QUEUE_SIZE; + + dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr); + if (!dmn->send_ring->qp) { + ret = -ENOMEM; + goto clean_cq; + } + + dmn->send_ring->cq->qp = dmn->send_ring->qp; + + dmn->info.max_send_wr = QUEUE_SIZE; + dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data, + DR_STE_SIZE); + + dmn->send_ring->signal_th = dmn->info.max_send_wr / + SIGNAL_PER_DIV_QUEUE; + + /* Prepare qp to be used */ + ret = dr_prepare_qp_to_rts(dmn); + if (ret) + goto clean_qp; + + dmn->send_ring->max_post_send_size = + mlx5dr_icm_pool_chunk_size_to_byte(DR_CHUNK_SIZE_1K, + DR_ICM_TYPE_STE); + + /* Allocating the max size as a buffer for writing */ + size = dmn->send_ring->signal_th * dmn->send_ring->max_post_send_size; + dmn->send_ring->buf = kzalloc(size, GFP_KERNEL); + if (!dmn->send_ring->buf) { + ret = -ENOMEM; + goto clean_qp; + } + + memset(dmn->send_ring->buf, 0, size); + dmn->send_ring->buf_size = size; + + dmn->send_ring->mr = dr_reg_mr(dmn->mdev, + dmn->pdn, dmn->send_ring->buf, size); + if (!dmn->send_ring->mr) { + ret = -ENOMEM; + goto free_mem; + } + + dmn->send_ring->sync_mr = dr_reg_mr(dmn->mdev, + dmn->pdn, dmn->send_ring->sync_buff, + MIN_READ_SYNC); + if (!dmn->send_ring->sync_mr) { + ret = -ENOMEM; + goto clean_mr; + } + + return 0; + +clean_mr: + dr_dereg_mr(dmn->mdev, dmn->send_ring->mr); +free_mem: + kfree(dmn->send_ring->buf); +clean_qp: + dr_destroy_qp(dmn->mdev, dmn->send_ring->qp); +clean_cq: + dr_destroy_cq(dmn->mdev, dmn->send_ring->cq); +free_send_ring: + kfree(dmn->send_ring); + + return ret; +} + +void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring) +{ + dr_destroy_qp(dmn->mdev, send_ring->qp); + dr_destroy_cq(dmn->mdev, send_ring->cq); + dr_dereg_mr(dmn->mdev, send_ring->sync_mr); + dr_dereg_mr(dmn->mdev, send_ring->mr); + kfree(send_ring->buf); + kfree(send_ring); +} + +int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_send_ring *send_ring = dmn->send_ring; + struct postsend_info send_info = {}; + u8 data[DR_STE_SIZE]; + int num_of_sends_req; + int ret; + int i; + + /* Sending this amount of requests makes sure we will get drain */ + num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2; + + /* Send fake requests forcing the last to be signaled */ + send_info.write.addr = (uintptr_t)data; + send_info.write.length = DR_STE_SIZE; + send_info.write.lkey = 0; + /* Using the sync_mr in order to write/read */ + send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr; + send_info.rkey = send_ring->sync_mr->mkey.key; + + for (i = 0; i < num_of_sends_req; i++) { + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + return ret; + } + + ret = dr_handle_pending_wc(dmn, send_ring); + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c new file mode 100644 index 000000000000..6b0af64536d8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -0,0 +1,2308 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/types.h> +#include "dr_types.h" + +#define DR_STE_CRC_POLY 0xEDB88320L +#define STE_IPV4 0x1 +#define STE_IPV6 0x2 +#define STE_TCP 0x1 +#define STE_UDP 0x2 +#define STE_SPI 0x3 +#define IP_VERSION_IPV4 0x4 +#define IP_VERSION_IPV6 0x6 +#define STE_SVLAN 0x1 +#define STE_CVLAN 0x2 + +#define DR_STE_ENABLE_FLOW_TAG BIT(31) + +/* Set to STE a specific value using DR_STE_SET */ +#define DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, value) do { \ + if ((spec)->s_fname) { \ + MLX5_SET(ste_##lookup_type, tag, t_fname, value); \ + (spec)->s_fname = 0; \ + } \ +} while (0) + +/* Set to STE spec->s_fname to tag->t_fname */ +#define DR_STE_SET_TAG(lookup_type, tag, t_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, spec->s_fname) + +/* Set to STE -1 to bit_mask->bm_fname and set spec->s_fname as used */ +#define DR_STE_SET_MASK(lookup_type, bit_mask, bm_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, -1) + +/* Set to STE spec->s_fname to bit_mask->bm_fname and set spec->s_fname as used */ +#define DR_STE_SET_MASK_V(lookup_type, bit_mask, bm_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, (spec)->s_fname) + +#define DR_STE_SET_TCP_FLAGS(lookup_type, tag, spec) do { \ + MLX5_SET(ste_##lookup_type, tag, tcp_ns, !!((spec)->tcp_flags & (1 << 8))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_cwr, !!((spec)->tcp_flags & (1 << 7))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_ece, !!((spec)->tcp_flags & (1 << 6))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_urg, !!((spec)->tcp_flags & (1 << 5))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_ack, !!((spec)->tcp_flags & (1 << 4))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_psh, !!((spec)->tcp_flags & (1 << 3))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_rst, !!((spec)->tcp_flags & (1 << 2))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_syn, !!((spec)->tcp_flags & (1 << 1))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_fin, !!((spec)->tcp_flags & (1 << 0))); \ +} while (0) + +#define DR_STE_SET_MPLS_MASK(lookup_type, mask, in_out, bit_mask) do { \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_label, mask, \ + in_out##_first_mpls_label);\ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_s_bos, mask, \ + in_out##_first_mpls_s_bos); \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_exp, mask, \ + in_out##_first_mpls_exp); \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_ttl, mask, \ + in_out##_first_mpls_ttl); \ +} while (0) + +#define DR_STE_SET_MPLS_TAG(lookup_type, mask, in_out, tag) do { \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_label, mask, \ + in_out##_first_mpls_label);\ + DR_STE_SET_TAG(lookup_type, tag, mpls0_s_bos, mask, \ + in_out##_first_mpls_s_bos); \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_exp, mask, \ + in_out##_first_mpls_exp); \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_ttl, mask, \ + in_out##_first_mpls_ttl); \ +} while (0) + +#define DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(_misc) (\ + (_misc)->outer_first_mpls_over_gre_label || \ + (_misc)->outer_first_mpls_over_gre_exp || \ + (_misc)->outer_first_mpls_over_gre_s_bos || \ + (_misc)->outer_first_mpls_over_gre_ttl) +#define DR_STE_IS_OUTER_MPLS_OVER_UDP_SET(_misc) (\ + (_misc)->outer_first_mpls_over_udp_label || \ + (_misc)->outer_first_mpls_over_udp_exp || \ + (_misc)->outer_first_mpls_over_udp_s_bos || \ + (_misc)->outer_first_mpls_over_udp_ttl) + +#define DR_STE_CALC_LU_TYPE(lookup_type, rx, inner) \ + ((inner) ? MLX5DR_STE_LU_TYPE_##lookup_type##_I : \ + (rx) ? MLX5DR_STE_LU_TYPE_##lookup_type##_D : \ + MLX5DR_STE_LU_TYPE_##lookup_type##_O) + +enum dr_ste_tunl_action { + DR_STE_TUNL_ACTION_NONE = 0, + DR_STE_TUNL_ACTION_ENABLE = 1, + DR_STE_TUNL_ACTION_DECAP = 2, + DR_STE_TUNL_ACTION_L3_DECAP = 3, + DR_STE_TUNL_ACTION_POP_VLAN = 4, +}; + +enum dr_ste_action_type { + DR_STE_ACTION_TYPE_PUSH_VLAN = 1, + DR_STE_ACTION_TYPE_ENCAP_L3 = 3, + DR_STE_ACTION_TYPE_ENCAP = 4, +}; + +struct dr_hw_ste_format { + u8 ctrl[DR_STE_SIZE_CTRL]; + u8 tag[DR_STE_SIZE_TAG]; + u8 mask[DR_STE_SIZE_MASK]; +}; + +u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 masked[DR_STE_SIZE_TAG] = {}; + u32 crc32, index; + u16 bit; + int i; + + /* Don't calculate CRC if the result is predicted */ + if (htbl->chunk->num_of_entries == 1 || htbl->byte_mask == 0) + return 0; + + /* Mask tag using byte mask, bit per byte */ + bit = 1 << (DR_STE_SIZE_TAG - 1); + for (i = 0; i < DR_STE_SIZE_TAG; i++) { + if (htbl->byte_mask & bit) + masked[i] = hw_ste->tag[i]; + + bit = bit >> 1; + } + + crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG); + index = crc32 & (htbl->chunk->num_of_entries - 1); + + return index; +} + +static u16 dr_ste_conv_bit_to_byte_mask(u8 *bit_mask) +{ + u16 byte_mask = 0; + int i; + + for (i = 0; i < DR_STE_SIZE_MASK; i++) { + byte_mask = byte_mask << 1; + if (bit_mask[i] == 0xff) + byte_mask |= 1; + } + return byte_mask; +} + +void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + + memcpy(hw_ste->mask, bit_mask, DR_STE_SIZE_MASK); +} + +void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer, + DR_STE_ENABLE_FLOW_TAG | flow_tag); +} + +void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id) +{ + /* This can be used for both rx_steering_mult and for sx_transmit */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_15_0, ctr_id); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_23_16, ctr_id >> 16); +} + +void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, go_back, 1); +} + +void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_hdr, + bool go_back) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_type, + DR_STE_ACTION_TYPE_PUSH_VLAN); + MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, vlan_hdr); + /* Due to HW limitation we need to set this bit, otherwise reforamt + + * push vlan will not work. + */ + if (go_back) + mlx5dr_ste_set_go_back_bit(hw_ste_p); +} + +void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, int size, bool encap_l3) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_type, + encap_l3 ? DR_STE_ACTION_TYPE_ENCAP_L3 : DR_STE_ACTION_TYPE_ENCAP); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_description, size / 2); + MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, reformat_id); +} + +void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_DECAP); +} + +void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_POP_VLAN); +} + +void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_L3_DECAP); + MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0); +} + +void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type) +{ + MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type); +} + +u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p) +{ + return MLX5_GET(ste_general, hw_ste_p, entry_type); +} + +void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, + u32 re_write_index) +{ + MLX5_SET(ste_modify_packet, hw_ste_p, number_of_re_write_actions, + num_of_actions); + MLX5_SET(ste_modify_packet, hw_ste_p, header_re_write_actions_pointer, + re_write_index); +} + +void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi) +{ + MLX5_SET(ste_general, hw_ste_p, next_table_base_63_48, gvmi); +} + +void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type, + u16 gvmi) +{ + MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type); + MLX5_SET(ste_general, hw_ste_p, entry_sub_type, lu_type); + MLX5_SET(ste_general, hw_ste_p, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE); + + /* Set GVMI once, this is the same for RX/TX + * bits 63_48 of next table base / miss address encode the next GVMI + */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, gvmi, gvmi); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, next_table_base_63_48, gvmi); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi); +} + +static void dr_ste_set_always_hit(struct dr_hw_ste_format *hw_ste) +{ + memset(&hw_ste->tag, 0, sizeof(hw_ste->tag)); + memset(&hw_ste->mask, 0, sizeof(hw_ste->mask)); +} + +static void dr_ste_set_always_miss(struct dr_hw_ste_format *hw_ste) +{ + hw_ste->tag[0] = 0xdc; + hw_ste->mask[0] = 0; +} + +u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste) +{ + u64 index = + (MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_31_6) | + MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_39_32) << 26); + + return index << 6; +} + +void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size) +{ + u64 index = (icm_addr >> 5) | ht_size; + + MLX5_SET(ste_general, hw_ste, next_table_base_39_32_size, index >> 27); + MLX5_SET(ste_general, hw_ste, next_table_base_31_5_size, index); +} + +u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return ste->htbl->chunk->icm_addr + DR_STE_SIZE * index; +} + +u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return ste->htbl->chunk->mr_addr + DR_STE_SIZE * index; +} + +struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return &ste->htbl->miss_list[index]; +} + +static void dr_ste_always_hit_htbl(struct mlx5dr_ste *ste, + struct mlx5dr_ste_htbl *next_htbl) +{ + struct mlx5dr_icm_chunk *chunk = next_htbl->chunk; + u8 *hw_ste = ste->hw_ste; + + MLX5_SET(ste_general, hw_ste, byte_mask, next_htbl->byte_mask); + MLX5_SET(ste_general, hw_ste, next_lu_type, next_htbl->lu_type); + mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries); + + dr_ste_set_always_hit((struct dr_hw_ste_format *)ste->hw_ste); +} + +bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 ste_location) +{ + return ste_location == nic_matcher->num_of_builders; +} + +/* Replace relevant fields, except of: + * htbl - keep the origin htbl + * miss_list + list - already took the src from the list. + * icm_addr/mr_addr - depends on the hosting table. + * + * Before: + * | a | -> | b | -> | c | -> + * + * After: + * | a | -> | c | -> + * While the data that was in b copied to a. + */ +static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src) +{ + memcpy(dst->hw_ste, src->hw_ste, DR_STE_SIZE_REDUCED); + dst->next_htbl = src->next_htbl; + if (dst->next_htbl) + dst->next_htbl->pointing_ste = dst; + + refcount_set(&dst->refcount, refcount_read(&src->refcount)); + + INIT_LIST_HEAD(&dst->rule_list); + list_splice_tail_init(&src->rule_list, &dst->rule_list); +} + +/* Free ste which is the head and the only one in miss_list */ +static void +dr_ste_remove_head_ste(struct mlx5dr_ste *ste, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_send_info *ste_info_head, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) +{ + u8 tmp_data_ste[DR_STE_SIZE] = {}; + struct mlx5dr_ste tmp_ste = {}; + u64 miss_addr; + + tmp_ste.hw_ste = tmp_data_ste; + + /* Use temp ste because dr_ste_always_miss_addr + * touches bit_mask area which doesn't exist at ste->hw_ste. + */ + memcpy(tmp_ste.hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED); + miss_addr = nic_matcher->e_anchor->chunk->icm_addr; + mlx5dr_ste_always_miss_addr(&tmp_ste, miss_addr); + memcpy(ste->hw_ste, tmp_ste.hw_ste, DR_STE_SIZE_REDUCED); + + list_del_init(&ste->miss_list_node); + + /* Write full STE size in order to have "always_miss" */ + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, + 0, tmp_data_ste, + ste_info_head, + send_ste_list, + true /* Copy data */); + + stats_tbl->ctrl.num_of_valid_entries--; +} + +/* Free ste which is the head but NOT the only one in miss_list: + * |_ste_| --> |_next_ste_| -->|__| -->|__| -->/0 + */ +static void +dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste, + struct mlx5dr_ste_send_info *ste_info_head, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) + +{ + struct mlx5dr_ste_htbl *next_miss_htbl; + + next_miss_htbl = next_ste->htbl; + + /* Remove from the miss_list the next_ste before copy */ + list_del_init(&next_ste->miss_list_node); + + /* All rule-members that use next_ste should know about that */ + mlx5dr_rule_update_rule_member(next_ste, ste); + + /* Move data from next into ste */ + dr_ste_replace(ste, next_ste); + + /* Del the htbl that contains the next_ste. + * The origin htbl stay with the same number of entries. + */ + mlx5dr_htbl_put(next_miss_htbl); + + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE_REDUCED, + 0, ste->hw_ste, + ste_info_head, + send_ste_list, + true /* Copy data */); + + stats_tbl->ctrl.num_of_collisions--; + stats_tbl->ctrl.num_of_valid_entries--; +} + +/* Free ste that is located in the middle of the miss list: + * |__| -->|_prev_ste_|->|_ste_|-->|_next_ste_| + */ +static void dr_ste_remove_middle_ste(struct mlx5dr_ste *ste, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) +{ + struct mlx5dr_ste *prev_ste; + u64 miss_addr; + + prev_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->prev, struct mlx5dr_ste, + miss_list_node); + if (!prev_ste) { + WARN_ON(true); + return; + } + + miss_addr = mlx5dr_ste_get_miss_addr(ste->hw_ste); + mlx5dr_ste_set_miss_addr(prev_ste->hw_ste, miss_addr); + + mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_REDUCED, 0, + prev_ste->hw_ste, ste_info, + send_ste_list, true /* Copy data*/); + + list_del_init(&ste->miss_list_node); + + stats_tbl->ctrl.num_of_valid_entries--; + stats_tbl->ctrl.num_of_collisions--; +} + +void mlx5dr_ste_free(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + struct mlx5dr_ste_send_info *cur_ste_info, *tmp_ste_info; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_send_info ste_info_head; + struct mlx5dr_ste *next_ste, *first_ste; + bool put_on_origin_table = true; + struct mlx5dr_ste_htbl *stats_tbl; + LIST_HEAD(send_ste_list); + + first_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->next, + struct mlx5dr_ste, miss_list_node); + stats_tbl = first_ste->htbl; + + /* Two options: + * 1. ste is head: + * a. head ste is the only ste in the miss list + * b. head ste is not the only ste in the miss-list + * 2. ste is not head + */ + if (first_ste == ste) { /* Ste is the head */ + struct mlx5dr_ste *last_ste; + + last_ste = list_last_entry(mlx5dr_ste_get_miss_list(ste), + struct mlx5dr_ste, miss_list_node); + if (last_ste == first_ste) + next_ste = NULL; + else + next_ste = list_entry(ste->miss_list_node.next, + struct mlx5dr_ste, miss_list_node); + + if (!next_ste) { + /* One and only entry in the list */ + dr_ste_remove_head_ste(ste, nic_matcher, + &ste_info_head, + &send_ste_list, + stats_tbl); + } else { + /* First but not only entry in the list */ + dr_ste_replace_head_ste(ste, next_ste, &ste_info_head, + &send_ste_list, stats_tbl); + put_on_origin_table = false; + } + } else { /* Ste in the middle of the list */ + dr_ste_remove_middle_ste(ste, &ste_info_head, &send_ste_list, stats_tbl); + } + + /* Update HW */ + list_for_each_entry_safe(cur_ste_info, tmp_ste_info, + &send_ste_list, send_list) { + list_del(&cur_ste_info->send_list); + mlx5dr_send_postsend_ste(dmn, cur_ste_info->ste, + cur_ste_info->data, cur_ste_info->size, + cur_ste_info->offset); + } + + if (put_on_origin_table) + mlx5dr_htbl_put(ste->htbl); +} + +bool mlx5dr_ste_equal_tag(void *src, void *dst) +{ + struct dr_hw_ste_format *s_hw_ste = (struct dr_hw_ste_format *)src; + struct dr_hw_ste_format *d_hw_ste = (struct dr_hw_ste_format *)dst; + + return !memcmp(s_hw_ste->tag, d_hw_ste->tag, DR_STE_SIZE_TAG); +} + +void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, + struct mlx5dr_ste_htbl *next_htbl) +{ + struct mlx5dr_icm_chunk *chunk = next_htbl->chunk; + + mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries); +} + +void mlx5dr_ste_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) +{ + u64 index = miss_addr >> 6; + + /* Miss address for TX and RX STEs located in the same offsets */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32, index >> 26); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6, index); +} + +void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr) +{ + u8 *hw_ste = ste->hw_ste; + + MLX5_SET(ste_rx_steering_mult, hw_ste, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE); + mlx5dr_ste_set_miss_addr(hw_ste, miss_addr); + dr_ste_set_always_miss((struct dr_hw_ste_format *)ste->hw_ste); +} + +/* The assumption here is that we don't update the ste->hw_ste if it is not + * used ste, so it will be all zero, checking the next_lu_type. + */ +bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)p_hw_ste; + + if (MLX5_GET(ste_general, hw_ste, next_lu_type) == + MLX5DR_STE_LU_TYPE_NOP) + return true; + + return false; +} + +bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) +{ + return !refcount_read(&ste->refcount); +} + +static u16 get_bits_per_mask(u16 byte_mask) +{ + u16 bits = 0; + + while (byte_mask) { + byte_mask = byte_mask & (byte_mask - 1); + bits++; + } + + return bits; +} + +/* Init one ste as a pattern for ste data array */ +void mlx5dr_ste_set_formatted_ste(u16 gvmi, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, + struct mlx5dr_htbl_connect_info *connect_info) +{ + struct mlx5dr_ste ste = {}; + + mlx5dr_ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi); + ste.hw_ste = formatted_ste; + + if (connect_info->type == CONNECT_HIT) + dr_ste_always_hit_htbl(&ste, connect_info->hit_next_htbl); + else + mlx5dr_ste_always_miss_addr(&ste, connect_info->miss_icm_addr); +} + +int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_htbl_connect_info *connect_info, + bool update_hw_ste) +{ + u8 formatted_ste[DR_STE_SIZE] = {}; + + mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi, + nic_dmn, + htbl, + formatted_ste, + connect_info); + + return mlx5dr_send_postsend_formatted_htbl(dmn, htbl, formatted_ste, update_hw_ste); +} + +int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *cur_hw_ste, + enum mlx5dr_icm_chunk_size log_table_size) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)cur_hw_ste; + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *next_htbl; + + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) { + u32 bits_in_mask; + u8 next_lu_type; + u16 byte_mask; + + next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type); + byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask); + + /* Don't allocate table more than required, + * the size of the table defined via the byte_mask, so no need + * to allocate more than that. + */ + bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE; + log_table_size = min(log_table_size, bits_in_mask); + + next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + log_table_size, + next_lu_type, + byte_mask); + if (!next_htbl) { + mlx5dr_dbg(dmn, "Failed allocating table\n"); + return -ENOMEM; + } + + /* Write new table to HW */ + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr; + if (mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, next_htbl, + &info, false)) { + mlx5dr_info(dmn, "Failed writing table to HW\n"); + goto free_table; + } + + mlx5dr_ste_set_hit_addr_by_next_htbl(cur_hw_ste, next_htbl); + ste->next_htbl = next_htbl; + next_htbl->pointing_ste = ste; + } + + return 0; + +free_table: + mlx5dr_ste_htbl_free(next_htbl); + return -ENOENT; +} + +static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) +{ + struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; + int num_of_entries; + + htbl->ctrl.may_grow = true; + + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1) + htbl->ctrl.may_grow = false; + + /* Threshold is 50%, one is added to table of size 1 */ + num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size); + ctrl->increase_threshold = (num_of_entries + 1) / 2; +} + +struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + u8 lu_type, u16 byte_mask) +{ + struct mlx5dr_icm_chunk *chunk; + struct mlx5dr_ste_htbl *htbl; + int i; + + htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); + if (!htbl) + return NULL; + + chunk = mlx5dr_icm_alloc_chunk(pool, chunk_size); + if (!chunk) + goto out_free_htbl; + + htbl->chunk = chunk; + htbl->lu_type = lu_type; + htbl->byte_mask = byte_mask; + htbl->ste_arr = chunk->ste_arr; + htbl->hw_ste_arr = chunk->hw_ste_arr; + htbl->miss_list = chunk->miss_list; + refcount_set(&htbl->refcount, 0); + + for (i = 0; i < chunk->num_of_entries; i++) { + struct mlx5dr_ste *ste = &htbl->ste_arr[i]; + + ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; + ste->htbl = htbl; + refcount_set(&ste->refcount, 0); + INIT_LIST_HEAD(&ste->miss_list_node); + INIT_LIST_HEAD(&htbl->miss_list[i]); + INIT_LIST_HEAD(&ste->rule_list); + } + + htbl->chunk_size = chunk_size; + dr_ste_set_ctrl(htbl); + return htbl; + +out_free_htbl: + kfree(htbl); + return NULL; +} + +int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl) +{ + if (refcount_read(&htbl->refcount)) + return -EBUSY; + + mlx5dr_icm_free_chunk(htbl->chunk); + kfree(htbl); + return 0; +} + +int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, + u8 match_criteria, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value) +{ + if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) { + if (mask->misc.source_port && mask->misc.source_port != 0xffff) { + mlx5dr_dbg(dmn, "Partial mask source_port is not supported\n"); + return -EINVAL; + } + } + + return 0; +} + +int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_match_param *value, + u8 *ste_arr) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_build *sb; + int ret, i; + + ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria, + &matcher->mask, value); + if (ret) + return ret; + + sb = nic_matcher->ste_builder; + for (i = 0; i < nic_matcher->num_of_builders; i++) { + mlx5dr_ste_init(ste_arr, + sb->lu_type, + nic_dmn->ste_type, + dmn->info.caps.gvmi); + + mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask); + + ret = sb->ste_build_tag_func(value, sb, ste_arr); + if (ret) + return ret; + + /* Connect the STEs */ + if (i < (nic_matcher->num_of_builders - 1)) { + /* Need the next builder for these fields, + * not relevant for the last ste in the chain. + */ + sb++; + MLX5_SET(ste_general, ste_arr, next_lu_type, sb->lu_type); + MLX5_SET(ste_general, ste_arr, byte_mask, sb->byte_mask); + } + ste_arr += DR_STE_SIZE; + } + return 0; +} + +static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_15_0, mask, dmac_15_0); + + if (mask->smac_47_16 || mask->smac_15_0) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_47_32, + mask->smac_47_16 >> 16); + MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_31_0, + mask->smac_47_16 << 16 | mask->smac_15_0); + mask->smac_47_16 = 0; + mask->smac_15_0 = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK(eth_l2_src_dst, bit_mask, l3_type, mask, ip_version); + + if (mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + } else if (mask->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1); + mask->svlan_tag = 0; + } + + if (mask->cvlan_tag || mask->svlan_tag) { + pr_info("Invalid c/svlan mask configuration\n"); + return -EINVAL; + } + + return 0; +} + +static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec) +{ + spec->gre_c_present = MLX5_GET(fte_match_set_misc, mask, gre_c_present); + spec->gre_k_present = MLX5_GET(fte_match_set_misc, mask, gre_k_present); + spec->gre_s_present = MLX5_GET(fte_match_set_misc, mask, gre_s_present); + spec->source_vhca_port = MLX5_GET(fte_match_set_misc, mask, source_vhca_port); + spec->source_sqn = MLX5_GET(fte_match_set_misc, mask, source_sqn); + + spec->source_port = MLX5_GET(fte_match_set_misc, mask, source_port); + + spec->outer_second_prio = MLX5_GET(fte_match_set_misc, mask, outer_second_prio); + spec->outer_second_cfi = MLX5_GET(fte_match_set_misc, mask, outer_second_cfi); + spec->outer_second_vid = MLX5_GET(fte_match_set_misc, mask, outer_second_vid); + spec->inner_second_prio = MLX5_GET(fte_match_set_misc, mask, inner_second_prio); + spec->inner_second_cfi = MLX5_GET(fte_match_set_misc, mask, inner_second_cfi); + spec->inner_second_vid = MLX5_GET(fte_match_set_misc, mask, inner_second_vid); + + spec->outer_second_cvlan_tag = + MLX5_GET(fte_match_set_misc, mask, outer_second_cvlan_tag); + spec->inner_second_cvlan_tag = + MLX5_GET(fte_match_set_misc, mask, inner_second_cvlan_tag); + spec->outer_second_svlan_tag = + MLX5_GET(fte_match_set_misc, mask, outer_second_svlan_tag); + spec->inner_second_svlan_tag = + MLX5_GET(fte_match_set_misc, mask, inner_second_svlan_tag); + + spec->gre_protocol = MLX5_GET(fte_match_set_misc, mask, gre_protocol); + + spec->gre_key_h = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi); + spec->gre_key_l = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo); + + spec->vxlan_vni = MLX5_GET(fte_match_set_misc, mask, vxlan_vni); + + spec->geneve_vni = MLX5_GET(fte_match_set_misc, mask, geneve_vni); + spec->geneve_oam = MLX5_GET(fte_match_set_misc, mask, geneve_oam); + + spec->outer_ipv6_flow_label = + MLX5_GET(fte_match_set_misc, mask, outer_ipv6_flow_label); + + spec->inner_ipv6_flow_label = + MLX5_GET(fte_match_set_misc, mask, inner_ipv6_flow_label); + + spec->geneve_opt_len = MLX5_GET(fte_match_set_misc, mask, geneve_opt_len); + spec->geneve_protocol_type = + MLX5_GET(fte_match_set_misc, mask, geneve_protocol_type); + + spec->bth_dst_qp = MLX5_GET(fte_match_set_misc, mask, bth_dst_qp); +} + +static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec) +{ + u32 raw_ip[4]; + + spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16); + + spec->smac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0); + spec->ethertype = MLX5_GET(fte_match_set_lyr_2_4, mask, ethertype); + + spec->dmac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16); + + spec->dmac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0); + spec->first_prio = MLX5_GET(fte_match_set_lyr_2_4, mask, first_prio); + spec->first_cfi = MLX5_GET(fte_match_set_lyr_2_4, mask, first_cfi); + spec->first_vid = MLX5_GET(fte_match_set_lyr_2_4, mask, first_vid); + + spec->ip_protocol = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_protocol); + spec->ip_dscp = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_dscp); + spec->ip_ecn = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_ecn); + spec->cvlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, cvlan_tag); + spec->svlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, svlan_tag); + spec->frag = MLX5_GET(fte_match_set_lyr_2_4, mask, frag); + spec->ip_version = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_version); + spec->tcp_flags = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_flags); + spec->tcp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_sport); + spec->tcp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_dport); + + spec->ttl_hoplimit = MLX5_GET(fte_match_set_lyr_2_4, mask, ttl_hoplimit); + + spec->udp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_sport); + spec->udp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_dport); + + memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip)); + + spec->src_ip_127_96 = be32_to_cpu(raw_ip[0]); + spec->src_ip_95_64 = be32_to_cpu(raw_ip[1]); + spec->src_ip_63_32 = be32_to_cpu(raw_ip[2]); + spec->src_ip_31_0 = be32_to_cpu(raw_ip[3]); + + memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip)); + + spec->dst_ip_127_96 = be32_to_cpu(raw_ip[0]); + spec->dst_ip_95_64 = be32_to_cpu(raw_ip[1]); + spec->dst_ip_63_32 = be32_to_cpu(raw_ip[2]); + spec->dst_ip_31_0 = be32_to_cpu(raw_ip[3]); +} + +static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec) +{ + spec->outer_first_mpls_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_label); + spec->outer_first_mpls_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp); + spec->outer_first_mpls_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos); + spec->outer_first_mpls_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl); + spec->inner_first_mpls_label = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_label); + spec->inner_first_mpls_exp = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp); + spec->inner_first_mpls_s_bos = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos); + spec->inner_first_mpls_ttl = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl); + spec->outer_first_mpls_over_gre_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label); + spec->outer_first_mpls_over_gre_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp); + spec->outer_first_mpls_over_gre_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos); + spec->outer_first_mpls_over_gre_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl); + spec->outer_first_mpls_over_udp_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label); + spec->outer_first_mpls_over_udp_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp); + spec->outer_first_mpls_over_udp_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos); + spec->outer_first_mpls_over_udp_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl); + spec->metadata_reg_c_7 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_7); + spec->metadata_reg_c_6 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_6); + spec->metadata_reg_c_5 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_5); + spec->metadata_reg_c_4 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_4); + spec->metadata_reg_c_3 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_3); + spec->metadata_reg_c_2 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_2); + spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1); + spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0); + spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a); + spec->metadata_reg_b = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_b); +} + +static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec) +{ + spec->inner_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_seq_num); + spec->outer_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_seq_num); + spec->inner_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_ack_num); + spec->outer_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_ack_num); + spec->outer_vxlan_gpe_vni = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_vni); + spec->outer_vxlan_gpe_next_protocol = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol); + spec->outer_vxlan_gpe_flags = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_flags); + spec->icmpv4_header_data = MLX5_GET(fte_match_set_misc3, mask, icmp_header_data); + spec->icmpv6_header_data = + MLX5_GET(fte_match_set_misc3, mask, icmpv6_header_data); + spec->icmpv4_type = MLX5_GET(fte_match_set_misc3, mask, icmp_type); + spec->icmpv4_code = MLX5_GET(fte_match_set_misc3, mask, icmp_code); + spec->icmpv6_type = MLX5_GET(fte_match_set_misc3, mask, icmpv6_type); + spec->icmpv6_code = MLX5_GET(fte_match_set_misc3, mask, icmpv6_code); +} + +void mlx5dr_ste_copy_param(u8 match_criteria, + struct mlx5dr_match_param *set_param, + struct mlx5dr_match_parameters *mask) +{ + u8 tail_param[MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4)] = {}; + u8 *data = (u8 *)mask->match_buf; + size_t param_location; + void *buff; + + if (match_criteria & DR_MATCHER_CRITERIA_OUTER) { + if (mask->match_sz < sizeof(struct mlx5dr_match_spec)) { + memcpy(tail_param, data, mask->match_sz); + buff = tail_param; + } else { + buff = mask->match_buf; + } + dr_ste_copy_mask_spec(buff, &set_param->outer); + } + param_location = sizeof(struct mlx5dr_match_spec); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc(buff, &set_param->misc); + } + param_location += sizeof(struct mlx5dr_match_misc); + + if (match_criteria & DR_MATCHER_CRITERIA_INNER) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_spec)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_spec(buff, &set_param->inner); + } + param_location += sizeof(struct mlx5dr_match_spec); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC2) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc2)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc2(buff, &set_param->misc2); + } + + param_location += sizeof(struct mlx5dr_match_misc2); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC3) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc3)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc3(buff, &set_param->misc3); + } +} + +static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_15_0, spec, dmac_15_0); + + if (spec->smac_47_16 || spec->smac_15_0) { + MLX5_SET(ste_eth_l2_src_dst, tag, smac_47_32, + spec->smac_47_16 >> 16); + MLX5_SET(ste_eth_l2_src_dst, tag, smac_31_0, + spec->smac_47_16 << 16 | spec->smac_15_0); + spec->smac_47_16 = 0; + spec->smac_15_0 = 0; + } + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + pr_info("Unsupported ip_version value\n"); + return -EINVAL; + } + } + + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_priority, spec, first_prio); + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + return 0; +} + +int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_des_tag; + + return 0; +} + +static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_127_96, mask, dst_ip_127_96); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_95_64, mask, dst_ip_95_64); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_63_32, mask, dst_ip_63_32); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_31_0, mask, dst_ip_31_0); +} + +static int dr_ste_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_63_32, spec, dst_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_31_0, spec, dst_ip_31_0); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv6_dst_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_dst_tag; +} + +static void dr_ste_build_eth_l3_ipv6_src_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_127_96, mask, src_ip_127_96); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_95_64, mask, src_ip_95_64); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_63_32, mask, src_ip_63_32); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_31_0, mask, src_ip_31_0); +} + +static int dr_ste_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_63_32, spec, src_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_31_0, spec, src_ip_31_0); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv6_src_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_SRC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_src_tag; +} + +static void dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(struct mlx5dr_match_param *value, + bool inner, + u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_address, mask, dst_ip_31_0); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_address, mask, src_ip_31_0); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_port, mask, tcp_dport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_port, mask, udp_dport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_port, mask, tcp_sport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_port, mask, udp_sport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + protocol, mask, ip_protocol); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + dscp, mask, ip_dscp); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + ecn, mask, ip_ecn); + + if (mask->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, bit_mask, mask); + mask->tcp_flags = 0; + } +} + +static int dr_ste_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_address, spec, dst_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_address, spec, src_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, ecn, spec, ip_ecn); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_5_TUPLE, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_5_tuple_tag; +} + +static void +dr_ste_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, l3_ethertype, mask, ethertype); + DR_STE_SET_MASK(eth_l2_src, bit_mask, l3_type, mask, ip_version); + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } + + if (inner) { + if (misc_mask->inner_second_cvlan_tag || + misc_mask->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1); + misc_mask->inner_second_cvlan_tag = 0; + misc_mask->inner_second_svlan_tag = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_vlan_id, misc_mask, inner_second_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_cfi, misc_mask, inner_second_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_priority, misc_mask, inner_second_prio); + } else { + if (misc_mask->outer_second_cvlan_tag || + misc_mask->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1); + misc_mask->outer_second_cvlan_tag = 0; + misc_mask->outer_second_svlan_tag = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_vlan_id, misc_mask, outer_second_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_cfi, misc_mask, outer_second_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_priority, misc_mask, outer_second_prio); + } +} + +static int dr_ste_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value, + bool inner, u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_spec = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_src, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_src, tag, l3_ethertype, spec, ethertype); + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + pr_info("Unsupported ip_version value\n"); + return -EINVAL; + } + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (inner) { + if (misc_spec->inner_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->inner_second_cvlan_tag = 0; + } else if (misc_spec->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->inner_second_svlan_tag = 0; + } + + DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, inner_second_vid); + DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, inner_second_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, inner_second_prio); + } else { + if (misc_spec->outer_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->outer_second_cvlan_tag = 0; + } else if (misc_spec->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->outer_second_svlan_tag = 0; + } + DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, outer_second_vid); + DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, outer_second_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, outer_second_prio); + } + + return 0; +} + +static void dr_ste_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_47_16, mask, smac_47_16); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_15_0, mask, smac_15_0); + + dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_build_eth_l2_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src, tag, smac_47_16, spec, smac_47_16); + DR_STE_SET_TAG(eth_l2_src, tag, smac_15_0, spec, smac_15_0); + + return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p); +} + +void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l2_src_bit_mask(mask, inner, sb->bit_mask); + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_tag; +} + +static void dr_ste_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_15_0, mask, dmac_15_0); + + dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_build_eth_l2_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_dst, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_dst, tag, dmac_15_0, spec, dmac_15_0); + + return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p); +} + +void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l2_dst_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_dst_tag; +} + +static void dr_ste_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_15_0, mask, dmac_15_0); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, l3_ethertype, mask, ethertype); + DR_STE_SET_MASK(eth_l2_tnl, bit_mask, l3_type, mask, ip_version); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl, bit_mask, + l2_tunneling_network_id, (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } +} + +static int dr_ste_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_15_0, spec, dmac_15_0); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_tnl, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_tnl, tag, l3_ethertype, spec, ethertype); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl, tag, l2_tunneling_network_id, + (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + return -EINVAL; + } + } + + return 0; +} + +void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) +{ + dr_ste_build_eth_l2_tnl_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_tnl_tag; +} + +static void dr_ste_build_eth_l3_ipv4_misc_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv4_misc, bit_mask, time_to_live, mask, ttl_hoplimit); +} + +static int dr_ste_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv4_misc_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_MISC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_misc_tag; +} + +static void dr_ste_build_ipv6_l3_l4_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, tcp_dport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, tcp_sport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, udp_dport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, udp_sport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, protocol, mask, ip_protocol); + DR_STE_SET_MASK_V(eth_l4, bit_mask, fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l4, bit_mask, dscp, mask, ip_dscp); + DR_STE_SET_MASK_V(eth_l4, bit_mask, ecn, mask, ip_ecn); + DR_STE_SET_MASK_V(eth_l4, bit_mask, ipv6_hop_limit, mask, ttl_hoplimit); + + if (mask->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l4, bit_mask, mask); + mask->tcp_flags = 0; + } +} + +static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l4, tag, src_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l4, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l4, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l4, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn); + DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_ipv6_l3_l4_tag; +} + +static int dr_ste_build_empty_always_hit_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + return 0; +} + +void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx) +{ + sb->rx = rx; + sb->lu_type = MLX5DR_STE_LU_TYPE_DONT_CARE; + sb->byte_mask = 0; + sb->ste_build_tag_func = &dr_ste_build_empty_always_hit_tag; +} + +static void dr_ste_build_mpls_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc2_mask = &value->misc2; + + if (inner) + DR_STE_SET_MPLS_MASK(mpls, misc2_mask, inner, bit_mask); + else + DR_STE_SET_MPLS_MASK(mpls, misc2_mask, outer, bit_mask); +} + +static int dr_ste_build_mpls_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + if (sb->inner) + DR_STE_SET_MPLS_TAG(mpls, misc2_mask, inner, tag); + else + DR_STE_SET_MPLS_TAG(mpls, misc2_mask, outer, tag); + + return 0; +} + +void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_mpls_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(MPLS_FIRST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_mpls_tag; +} + +static void dr_ste_build_gre_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_MASK_V(gre, bit_mask, gre_protocol, misc_mask, gre_protocol); + DR_STE_SET_MASK_V(gre, bit_mask, gre_k_present, misc_mask, gre_k_present); + DR_STE_SET_MASK_V(gre, bit_mask, gre_key_h, misc_mask, gre_key_h); + DR_STE_SET_MASK_V(gre, bit_mask, gre_key_l, misc_mask, gre_key_l); + + DR_STE_SET_MASK_V(gre, bit_mask, gre_c_present, misc_mask, gre_c_present); + DR_STE_SET_MASK_V(gre, bit_mask, gre_s_present, misc_mask, gre_s_present); +} + +static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(gre, tag, gre_protocol, misc, gre_protocol); + + DR_STE_SET_TAG(gre, tag, gre_k_present, misc, gre_k_present); + DR_STE_SET_TAG(gre, tag, gre_key_h, misc, gre_key_h); + DR_STE_SET_TAG(gre, tag, gre_key_l, misc, gre_key_l); + + DR_STE_SET_TAG(gre, tag, gre_c_present, misc, gre_c_present); + + DR_STE_SET_TAG(gre, tag, gre_s_present, misc, gre_s_present); + + return 0; +} + +void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) +{ + dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_GRE; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_gre_tag; +} + +static void dr_ste_build_flex_parser_0_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) { + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label, + misc_2_mask, outer_first_mpls_over_gre_label); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp, + misc_2_mask, outer_first_mpls_over_gre_exp); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_gre_s_bos); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_gre_ttl); + } else { + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label, + misc_2_mask, outer_first_mpls_over_udp_label); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp, + misc_2_mask, outer_first_mpls_over_udp_exp); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_udp_s_bos); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_udp_ttl); + } +} + +static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) { + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label, + misc_2_mask, outer_first_mpls_over_gre_label); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp, + misc_2_mask, outer_first_mpls_over_gre_exp); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_gre_s_bos); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_gre_ttl); + } else { + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label, + misc_2_mask, outer_first_mpls_over_udp_label); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp, + misc_2_mask, outer_first_mpls_over_udp_exp); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_udp_s_bos); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_udp_ttl); + } + return 0; +} + +void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_0; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_0_tag; +} + +#define ICMP_TYPE_OFFSET_FIRST_DW 24 +#define ICMP_CODE_OFFSET_FIRST_DW 16 +#define ICMP_HEADER_DATA_OFFSET_SECOND_DW 0 + +static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3; + bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask); + u32 icmp_header_data_mask; + u32 icmp_type_mask; + u32 icmp_code_mask; + int dw0_location; + int dw1_location; + + if (is_ipv4_mask) { + icmp_header_data_mask = misc_3_mask->icmpv4_header_data; + icmp_type_mask = misc_3_mask->icmpv4_type; + icmp_code_mask = misc_3_mask->icmpv4_code; + dw0_location = caps->flex_parser_id_icmp_dw0; + dw1_location = caps->flex_parser_id_icmp_dw1; + } else { + icmp_header_data_mask = misc_3_mask->icmpv6_header_data; + icmp_type_mask = misc_3_mask->icmpv6_type; + icmp_code_mask = misc_3_mask->icmpv6_code; + dw0_location = caps->flex_parser_id_icmpv6_dw0; + dw1_location = caps->flex_parser_id_icmpv6_dw1; + } + + switch (dw0_location) { + case 4: + if (icmp_type_mask) { + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4, + (icmp_type_mask << ICMP_TYPE_OFFSET_FIRST_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_type = 0; + else + misc_3_mask->icmpv6_type = 0; + } + if (icmp_code_mask) { + u32 cur_val = MLX5_GET(ste_flex_parser_1, bit_mask, + flex_parser_4); + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4, + cur_val | (icmp_code_mask << ICMP_CODE_OFFSET_FIRST_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_code = 0; + else + misc_3_mask->icmpv6_code = 0; + } + break; + default: + return -EINVAL; + } + + switch (dw1_location) { + case 5: + if (icmp_header_data_mask) { + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_5, + (icmp_header_data_mask << ICMP_HEADER_DATA_OFFSET_SECOND_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_header_data = 0; + else + misc_3_mask->icmpv6_header_data = 0; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc_3 = &value->misc3; + u8 *tag = hw_ste->tag; + u32 icmp_header_data; + int dw0_location; + int dw1_location; + u32 icmp_type; + u32 icmp_code; + bool is_ipv4; + + is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3); + if (is_ipv4) { + icmp_header_data = misc_3->icmpv4_header_data; + icmp_type = misc_3->icmpv4_type; + icmp_code = misc_3->icmpv4_code; + dw0_location = sb->caps->flex_parser_id_icmp_dw0; + dw1_location = sb->caps->flex_parser_id_icmp_dw1; + } else { + icmp_header_data = misc_3->icmpv6_header_data; + icmp_type = misc_3->icmpv6_type; + icmp_code = misc_3->icmpv6_code; + dw0_location = sb->caps->flex_parser_id_icmpv6_dw0; + dw1_location = sb->caps->flex_parser_id_icmpv6_dw1; + } + + switch (dw0_location) { + case 4: + if (icmp_type) { + MLX5_SET(ste_flex_parser_1, tag, flex_parser_4, + (icmp_type << ICMP_TYPE_OFFSET_FIRST_DW)); + if (is_ipv4) + misc_3->icmpv4_type = 0; + else + misc_3->icmpv6_type = 0; + } + + if (icmp_code) { + u32 cur_val = MLX5_GET(ste_flex_parser_1, tag, + flex_parser_4); + MLX5_SET(ste_flex_parser_1, tag, flex_parser_4, + cur_val | (icmp_code << ICMP_CODE_OFFSET_FIRST_DW)); + if (is_ipv4) + misc_3->icmpv4_code = 0; + else + misc_3->icmpv6_code = 0; + } + break; + default: + return -EINVAL; + } + + switch (dw1_location) { + case 5: + if (icmp_header_data) { + MLX5_SET(ste_flex_parser_1, tag, flex_parser_5, + (icmp_header_data << ICMP_HEADER_DATA_OFFSET_SECOND_DW)); + if (is_ipv4) + misc_3->icmpv4_header_data = 0; + else + misc_3->icmpv6_header_data = 0; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_flex_parser_1_bit_mask(mask, caps, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->inner = inner; + sb->caps = caps; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_1; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_1_tag; + + return 0; +} + +static void dr_ste_build_general_purpose_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(general_purpose, bit_mask, + general_purpose_lookup_field, misc_2_mask, + metadata_reg_a); +} + +static int dr_ste_build_general_purpose_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field, + misc_2_mask, metadata_reg_a); + + return 0; +} + +void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_general_purpose_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_general_purpose_tag; +} + +static void dr_ste_build_eth_l4_misc_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3; + + if (inner) { + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask, + inner_tcp_seq_num); + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask, + inner_tcp_ack_num); + } else { + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask, + outer_tcp_seq_num); + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask, + outer_tcp_ack_num); + } +} + +static int dr_ste_build_eth_l4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + u8 *tag = hw_ste->tag; + + if (sb->inner) { + DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, inner_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, inner_tcp_ack_num); + } else { + DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, outer_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, outer_tcp_ack_num); + } + + return 0; +} + +void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l4_misc_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4_MISC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag; +} + +static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3; + + if (misc_3_mask->outer_vxlan_gpe_flags || + misc_3_mask->outer_vxlan_gpe_next_protocol) { + MLX5_SET(ste_flex_parser_tnl, bit_mask, + flex_parser_tunneling_header_63_32, + (misc_3_mask->outer_vxlan_gpe_flags << 24) | + (misc_3_mask->outer_vxlan_gpe_next_protocol)); + misc_3_mask->outer_vxlan_gpe_flags = 0; + misc_3_mask->outer_vxlan_gpe_next_protocol = 0; + } + + if (misc_3_mask->outer_vxlan_gpe_vni) { + MLX5_SET(ste_flex_parser_tnl, bit_mask, + flex_parser_tunneling_header_31_0, + misc_3_mask->outer_vxlan_gpe_vni << 8); + misc_3_mask->outer_vxlan_gpe_vni = 0; + } +} + +static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + u8 *tag = hw_ste->tag; + + if (misc3->outer_vxlan_gpe_flags || + misc3->outer_vxlan_gpe_next_protocol) { + MLX5_SET(ste_flex_parser_tnl, tag, + flex_parser_tunneling_header_63_32, + (misc3->outer_vxlan_gpe_flags << 24) | + (misc3->outer_vxlan_gpe_next_protocol)); + misc3->outer_vxlan_gpe_flags = 0; + misc3->outer_vxlan_gpe_next_protocol = 0; + } + + if (misc3->outer_vxlan_gpe_vni) { + MLX5_SET(ste_flex_parser_tnl, tag, + flex_parser_tunneling_header_31_0, + misc3->outer_vxlan_gpe_vni << 8); + misc3->outer_vxlan_gpe_vni = 0; + } + + return 0; +} + +void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag; +} + +static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(register_0, bit_mask, register_0_h, + misc_2_mask, metadata_reg_c_0); + DR_STE_SET_MASK_V(register_0, bit_mask, register_0_l, + misc_2_mask, metadata_reg_c_1); + DR_STE_SET_MASK_V(register_0, bit_mask, register_1_h, + misc_2_mask, metadata_reg_c_2); + DR_STE_SET_MASK_V(register_0, bit_mask, register_1_l, + misc_2_mask, metadata_reg_c_3); +} + +static int dr_ste_build_register_0_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0); + DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1); + DR_STE_SET_TAG(register_0, tag, register_1_h, misc2, metadata_reg_c_2); + DR_STE_SET_TAG(register_0, tag, register_1_l, misc2, metadata_reg_c_3); + + return 0; +} + +void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_register_0_bit_mask(mask, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_register_0_tag; +} + +static void dr_ste_build_register_1_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(register_1, bit_mask, register_2_h, + misc_2_mask, metadata_reg_c_4); + DR_STE_SET_MASK_V(register_1, bit_mask, register_2_l, + misc_2_mask, metadata_reg_c_5); + DR_STE_SET_MASK_V(register_1, bit_mask, register_3_h, + misc_2_mask, metadata_reg_c_6); + DR_STE_SET_MASK_V(register_1, bit_mask, register_3_l, + misc_2_mask, metadata_reg_c_7); +} + +static int dr_ste_build_register_1_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4); + DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5); + DR_STE_SET_TAG(register_1, tag, register_3_h, misc2, metadata_reg_c_6); + DR_STE_SET_TAG(register_1, tag, register_3_l, misc2, metadata_reg_c_7); + + return 0; +} + +void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_register_1_bit_mask(mask, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_register_1_tag; +} + +static int dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + if (misc_mask->source_port != 0xffff) + return -EINVAL; + + DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_gvmi, misc_mask, source_port); + DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_qp, misc_mask, source_sqn); + + return 0; +} + +static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + struct mlx5dr_cmd_vport_cap *vport_cap; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); + + vport_cap = mlx5dr_get_vport_cap(sb->caps, misc->source_port); + if (!vport_cap) + return -EINVAL; + + if (vport_cap->vport_gvmi) + MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi); + + misc->source_port = 0; + + return 0; +} + +int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->caps = caps; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_src_gvmi_qpn_tag; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c new file mode 100644 index 000000000000..e178d8d3dbc9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action) +{ + struct mlx5dr_matcher *last_matcher = NULL; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *last_htbl; + int ret; + + if (action && action->action_type != DR_ACTION_TYP_FT) + return -EOPNOTSUPP; + + mutex_lock(&tbl->dmn->mutex); + + if (!list_empty(&tbl->matcher_list)) + last_matcher = list_last_entry(&tbl->matcher_list, + struct mlx5dr_matcher, + matcher_list); + + if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX || + tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) { + if (last_matcher) + last_htbl = last_matcher->rx.e_anchor; + else + last_htbl = tbl->rx.s_anchor; + + tbl->rx.default_icm_addr = action ? + action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr : + tbl->rx.nic_dmn->default_icm_addr; + + info.type = CONNECT_MISS; + info.miss_icm_addr = tbl->rx.default_icm_addr; + + ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn, + tbl->rx.nic_dmn, + last_htbl, + &info, true); + if (ret) { + mlx5dr_dbg(tbl->dmn, "Failed to set RX miss action, ret %d\n", ret); + goto out; + } + } + + if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX || + tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) { + if (last_matcher) + last_htbl = last_matcher->tx.e_anchor; + else + last_htbl = tbl->tx.s_anchor; + + tbl->tx.default_icm_addr = action ? + action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr : + tbl->tx.nic_dmn->default_icm_addr; + + info.type = CONNECT_MISS; + info.miss_icm_addr = tbl->tx.default_icm_addr; + + ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn, + tbl->tx.nic_dmn, + last_htbl, &info, true); + if (ret) { + mlx5dr_dbg(tbl->dmn, "Failed to set TX miss action, ret %d\n", ret); + goto out; + } + } + + /* Release old action */ + if (tbl->miss_action) + refcount_dec(&tbl->miss_action->refcount); + + /* Set new miss action */ + tbl->miss_action = action; + if (tbl->miss_action) + refcount_inc(&action->refcount); + +out: + mutex_unlock(&tbl->dmn->mutex); + return ret; +} + +static void dr_table_uninit_nic(struct mlx5dr_table_rx_tx *nic_tbl) +{ + mlx5dr_htbl_put(nic_tbl->s_anchor); +} + +static void dr_table_uninit_fdb(struct mlx5dr_table *tbl) +{ + dr_table_uninit_nic(&tbl->rx); + dr_table_uninit_nic(&tbl->tx); +} + +static void dr_table_uninit(struct mlx5dr_table *tbl) +{ + mutex_lock(&tbl->dmn->mutex); + + switch (tbl->dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_table_uninit_nic(&tbl->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_table_uninit_nic(&tbl->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_table_uninit_fdb(tbl); + break; + default: + WARN_ON(true); + break; + } + + mutex_unlock(&tbl->dmn->mutex); +} + +static int dr_table_init_nic(struct mlx5dr_domain *dmn, + struct mlx5dr_table_rx_tx *nic_tbl) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + int ret; + + nic_tbl->default_icm_addr = nic_dmn->default_icm_addr; + + nic_tbl->s_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!nic_tbl->s_anchor) + return -ENOMEM; + + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_dmn->default_icm_addr; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + nic_tbl->s_anchor, + &info, true); + if (ret) + goto free_s_anchor; + + mlx5dr_htbl_get(nic_tbl->s_anchor); + + return 0; + +free_s_anchor: + mlx5dr_ste_htbl_free(nic_tbl->s_anchor); + return ret; +} + +static int dr_table_init_fdb(struct mlx5dr_table *tbl) +{ + int ret; + + ret = dr_table_init_nic(tbl->dmn, &tbl->rx); + if (ret) + return ret; + + ret = dr_table_init_nic(tbl->dmn, &tbl->tx); + if (ret) + goto destroy_rx; + + return 0; + +destroy_rx: + dr_table_uninit_nic(&tbl->rx); + return ret; +} + +static int dr_table_init(struct mlx5dr_table *tbl) +{ + int ret = 0; + + INIT_LIST_HEAD(&tbl->matcher_list); + + mutex_lock(&tbl->dmn->mutex); + + switch (tbl->dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_RX; + tbl->rx.nic_dmn = &tbl->dmn->info.rx; + ret = dr_table_init_nic(tbl->dmn, &tbl->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_TX; + tbl->tx.nic_dmn = &tbl->dmn->info.tx; + ret = dr_table_init_nic(tbl->dmn, &tbl->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_FDB; + tbl->rx.nic_dmn = &tbl->dmn->info.rx; + tbl->tx.nic_dmn = &tbl->dmn->info.tx; + ret = dr_table_init_fdb(tbl); + break; + default: + WARN_ON(true); + break; + } + + mutex_unlock(&tbl->dmn->mutex); + + return ret; +} + +static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl) +{ + return mlx5dr_cmd_destroy_flow_table(tbl->dmn->mdev, + tbl->table_id, + tbl->table_type); +} + +static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl) +{ + u64 icm_addr_rx = 0; + u64 icm_addr_tx = 0; + int ret; + + if (tbl->rx.s_anchor) + icm_addr_rx = tbl->rx.s_anchor->chunk->icm_addr; + + if (tbl->tx.s_anchor) + icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr; + + ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev, + tbl->table_type, + icm_addr_rx, + icm_addr_tx, + tbl->dmn->info.caps.max_ft_level - 1, + true, false, NULL, + &tbl->table_id); + + return ret; +} + +struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level) +{ + struct mlx5dr_table *tbl; + int ret; + + refcount_inc(&dmn->refcount); + + tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); + if (!tbl) + goto dec_ref; + + tbl->dmn = dmn; + tbl->level = level; + refcount_set(&tbl->refcount, 1); + + ret = dr_table_init(tbl); + if (ret) + goto free_tbl; + + ret = dr_table_create_sw_owned_tbl(tbl); + if (ret) + goto uninit_tbl; + + return tbl; + +uninit_tbl: + dr_table_uninit(tbl); +free_tbl: + kfree(tbl); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +int mlx5dr_table_destroy(struct mlx5dr_table *tbl) +{ + int ret; + + if (refcount_read(&tbl->refcount) > 1) + return -EBUSY; + + ret = dr_table_destroy_sw_owned_tbl(tbl); + if (ret) + return ret; + + dr_table_uninit(tbl); + + if (tbl->miss_action) + refcount_dec(&tbl->miss_action->refcount); + + refcount_dec(&tbl->dmn->refcount); + kfree(tbl); + + return ret; +} + +u32 mlx5dr_table_get_id(struct mlx5dr_table *tbl) +{ + return tbl->table_id; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h new file mode 100644 index 000000000000..a37ee6359be2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -0,0 +1,1060 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef _DR_TYPES_ +#define _DR_TYPES_ + +#include <linux/mlx5/driver.h> +#include <linux/refcount.h> +#include "fs_core.h" +#include "wq.h" +#include "lib/mlx5.h" +#include "mlx5_ifc_dr.h" +#include "mlx5dr.h" + +#define DR_RULE_MAX_STES 17 +#define DR_ACTION_MAX_STES 5 +#define WIRE_PORT 0xFFFF +#define DR_STE_SVLAN 0x1 +#define DR_STE_CVLAN 0x2 + +#define mlx5dr_err(dmn, arg...) mlx5_core_err((dmn)->mdev, ##arg) +#define mlx5dr_info(dmn, arg...) mlx5_core_info((dmn)->mdev, ##arg) +#define mlx5dr_dbg(dmn, arg...) mlx5_core_dbg((dmn)->mdev, ##arg) + +enum mlx5dr_icm_chunk_size { + DR_CHUNK_SIZE_1, + DR_CHUNK_SIZE_MIN = DR_CHUNK_SIZE_1, /* keep updated when changing */ + DR_CHUNK_SIZE_2, + DR_CHUNK_SIZE_4, + DR_CHUNK_SIZE_8, + DR_CHUNK_SIZE_16, + DR_CHUNK_SIZE_32, + DR_CHUNK_SIZE_64, + DR_CHUNK_SIZE_128, + DR_CHUNK_SIZE_256, + DR_CHUNK_SIZE_512, + DR_CHUNK_SIZE_1K, + DR_CHUNK_SIZE_2K, + DR_CHUNK_SIZE_4K, + DR_CHUNK_SIZE_8K, + DR_CHUNK_SIZE_16K, + DR_CHUNK_SIZE_32K, + DR_CHUNK_SIZE_64K, + DR_CHUNK_SIZE_128K, + DR_CHUNK_SIZE_256K, + DR_CHUNK_SIZE_512K, + DR_CHUNK_SIZE_1024K, + DR_CHUNK_SIZE_2048K, + DR_CHUNK_SIZE_MAX, +}; + +enum mlx5dr_icm_type { + DR_ICM_TYPE_STE, + DR_ICM_TYPE_MODIFY_ACTION, +}; + +static inline enum mlx5dr_icm_chunk_size +mlx5dr_icm_next_higher_chunk(enum mlx5dr_icm_chunk_size chunk) +{ + chunk += 2; + if (chunk < DR_CHUNK_SIZE_MAX) + return chunk; + + return DR_CHUNK_SIZE_MAX; +} + +enum { + DR_STE_SIZE = 64, + DR_STE_SIZE_CTRL = 32, + DR_STE_SIZE_TAG = 16, + DR_STE_SIZE_MASK = 16, +}; + +enum { + DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK, +}; + +enum { + DR_MODIFY_ACTION_SIZE = 8, +}; + +enum mlx5dr_matcher_criteria { + DR_MATCHER_CRITERIA_EMPTY = 0, + DR_MATCHER_CRITERIA_OUTER = 1 << 0, + DR_MATCHER_CRITERIA_MISC = 1 << 1, + DR_MATCHER_CRITERIA_INNER = 1 << 2, + DR_MATCHER_CRITERIA_MISC2 = 1 << 3, + DR_MATCHER_CRITERIA_MISC3 = 1 << 4, + DR_MATCHER_CRITERIA_MAX = 1 << 5, +}; + +enum mlx5dr_action_type { + DR_ACTION_TYP_TNL_L2_TO_L2, + DR_ACTION_TYP_L2_TO_TNL_L2, + DR_ACTION_TYP_TNL_L3_TO_L2, + DR_ACTION_TYP_L2_TO_TNL_L3, + DR_ACTION_TYP_DROP, + DR_ACTION_TYP_QP, + DR_ACTION_TYP_FT, + DR_ACTION_TYP_CTR, + DR_ACTION_TYP_TAG, + DR_ACTION_TYP_MODIFY_HDR, + DR_ACTION_TYP_VPORT, + DR_ACTION_TYP_POP_VLAN, + DR_ACTION_TYP_PUSH_VLAN, + DR_ACTION_TYP_MAX, +}; + +struct mlx5dr_icm_pool; +struct mlx5dr_icm_chunk; +struct mlx5dr_icm_bucket; +struct mlx5dr_ste_htbl; +struct mlx5dr_match_param; +struct mlx5dr_cmd_caps; +struct mlx5dr_matcher_rx_tx; + +struct mlx5dr_ste { + u8 *hw_ste; + /* refcount: indicates the num of rules that using this ste */ + refcount_t refcount; + + /* attached to the miss_list head at each htbl entry */ + struct list_head miss_list_node; + + /* each rule member that uses this ste attached here */ + struct list_head rule_list; + + /* this ste is member of htbl */ + struct mlx5dr_ste_htbl *htbl; + + struct mlx5dr_ste_htbl *next_htbl; + + /* this ste is part of a rule, located in ste's chain */ + u8 ste_chain_location; +}; + +struct mlx5dr_ste_htbl_ctrl { + /* total number of valid entries belonging to this hash table. This + * includes the non collision and collision entries + */ + unsigned int num_of_valid_entries; + + /* total number of collisions entries attached to this table */ + unsigned int num_of_collisions; + unsigned int increase_threshold; + u8 may_grow:1; +}; + +struct mlx5dr_ste_htbl { + u8 lu_type; + u16 byte_mask; + refcount_t refcount; + struct mlx5dr_icm_chunk *chunk; + struct mlx5dr_ste *ste_arr; + u8 *hw_ste_arr; + + struct list_head *miss_list; + + enum mlx5dr_icm_chunk_size chunk_size; + struct mlx5dr_ste *pointing_ste; + + struct mlx5dr_ste_htbl_ctrl ctrl; +}; + +struct mlx5dr_ste_send_info { + struct mlx5dr_ste *ste; + struct list_head send_list; + u16 size; + u16 offset; + u8 data_cont[DR_STE_SIZE]; + u8 *data; +}; + +void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size, + u16 offset, u8 *data, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_list, + bool copy_data); + +struct mlx5dr_ste_build { + u8 inner:1; + u8 rx:1; + struct mlx5dr_cmd_caps *caps; + u8 lu_type; + u16 byte_mask; + u8 bit_mask[DR_STE_SIZE_MASK]; + int (*ste_build_tag_func)(struct mlx5dr_match_param *spec, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p); +}; + +struct mlx5dr_ste_htbl * +mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + u8 lu_type, u16 byte_mask); + +int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl); + +static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl) +{ + if (refcount_dec_and_test(&htbl->refcount)) + mlx5dr_ste_htbl_free(htbl); +} + +static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl) +{ + refcount_inc(&htbl->refcount); +} + +/* STE utils */ +u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl); +void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type, u16 gvmi); +void mlx5dr_ste_always_hit_htbl(struct mlx5dr_ste *ste, + struct mlx5dr_ste_htbl *next_htbl); +void mlx5dr_ste_set_miss_addr(u8 *hw_ste, u64 miss_addr); +u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste); +void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi); +void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size); +void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr); +void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask); +bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste); +bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 ste_location); +void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag); +void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id); +void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, + int size, bool encap_l3); +void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p); +void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan); +void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p); +void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_tpid_pcp_dei_vid, + bool go_back); +void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type); +u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p); +void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, + u32 re_write_index); +void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p); +u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste); +u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste); +struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste); + +void mlx5dr_ste_free(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher); +static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + if (refcount_dec_and_test(&ste->refcount)) + mlx5dr_ste_free(ste, matcher, nic_matcher); +} + +/* initial as 0, increased only when ste appears in a new rule */ +static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste) +{ + refcount_inc(&ste->refcount); +} + +void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, + struct mlx5dr_ste_htbl *next_htbl); +bool mlx5dr_ste_equal_tag(void *src, void *dst); +int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *cur_hw_ste, + enum mlx5dr_icm_chunk_size log_table_size); + +/* STE build functions */ +int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, + u8 match_criteria, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value); +int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_match_param *value, + u8 *ste_arr); +int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx); + +/* Actions utils */ +int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_action *actions[], + u32 num_actions, + u8 *ste_arr, + u32 *new_hw_ste_arr_sz); + +struct mlx5dr_match_spec { + u32 smac_47_16; /* Source MAC address of incoming packet */ + /* Incoming packet Ethertype - this is the Ethertype + * following the last VLAN tag of the packet + */ + u32 ethertype:16; + u32 smac_15_0:16; /* Source MAC address of incoming packet */ + u32 dmac_47_16; /* Destination MAC address of incoming packet */ + /* VLAN ID of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_vid:12; + /* CFI bit of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_cfi:1; + /* Priority of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_prio:3; + u32 dmac_15_0:16; /* Destination MAC address of incoming packet */ + /* TCP flags. ;Bit 0: FIN;Bit 1: SYN;Bit 2: RST;Bit 3: PSH;Bit 4: ACK; + * Bit 5: URG;Bit 6: ECE;Bit 7: CWR;Bit 8: NS + */ + u32 tcp_flags:9; + u32 ip_version:4; /* IP version */ + u32 frag:1; /* Packet is an IP fragment */ + /* The first vlan in the packet is s-vlan (0x8a88). + * cvlan_tag and svlan_tag cannot be set together + */ + u32 svlan_tag:1; + /* The first vlan in the packet is c-vlan (0x8100). + * cvlan_tag and svlan_tag cannot be set together + */ + u32 cvlan_tag:1; + /* Explicit Congestion Notification derived from + * Traffic Class/TOS field of IPv6/v4 + */ + u32 ip_ecn:2; + /* Differentiated Services Code Point derived from + * Traffic Class/TOS field of IPv6/v4 + */ + u32 ip_dscp:6; + u32 ip_protocol:8; /* IP protocol */ + /* TCP destination port. + * tcp and udp sport/dport are mutually exclusive + */ + u32 tcp_dport:16; + /* TCP source port.;tcp and udp sport/dport are mutually exclusive */ + u32 tcp_sport:16; + u32 ttl_hoplimit:8; + u32 reserved:24; + /* UDP destination port.;tcp and udp sport/dport are mutually exclusive */ + u32 udp_dport:16; + /* UDP source port.;tcp and udp sport/dport are mutually exclusive */ + u32 udp_sport:16; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_127_96; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_95_64; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_63_32; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_31_0; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_127_96; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_95_64; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_63_32; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_31_0; +}; + +struct mlx5dr_match_misc { + u32 source_sqn:24; /* Source SQN */ + u32 source_vhca_port:4; + /* used with GRE, sequence number exist when gre_s_present == 1 */ + u32 gre_s_present:1; + /* used with GRE, key exist when gre_k_present == 1 */ + u32 gre_k_present:1; + u32 reserved_auto1:1; + /* used with GRE, checksum exist when gre_c_present == 1 */ + u32 gre_c_present:1; + /* Source port.;0xffff determines wire port */ + u32 source_port:16; + u32 reserved_auto2:16; + /* VLAN ID of first VLAN tag the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_vid:12; + /* CFI bit of first VLAN tag in the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_cfi:1; + /* Priority of second VLAN tag in the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_prio:3; + /* VLAN ID of first VLAN tag the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_vid:12; + /* CFI bit of first VLAN tag in the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_cfi:1; + /* Priority of second VLAN tag in the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_prio:3; + u32 gre_protocol:16; /* GRE Protocol (outer) */ + u32 reserved_auto3:12; + /* The second vlan in the inner header of the packet is s-vlan (0x8a88). + * inner_second_cvlan_tag and inner_second_svlan_tag cannot be set together + */ + u32 inner_second_svlan_tag:1; + /* The second vlan in the outer header of the packet is s-vlan (0x8a88). + * outer_second_cvlan_tag and outer_second_svlan_tag cannot be set together + */ + u32 outer_second_svlan_tag:1; + /* The second vlan in the inner header of the packet is c-vlan (0x8100). + * inner_second_cvlan_tag and inner_second_svlan_tag cannot be set together + */ + u32 inner_second_cvlan_tag:1; + /* The second vlan in the outer header of the packet is c-vlan (0x8100). + * outer_second_cvlan_tag and outer_second_svlan_tag cannot be set together + */ + u32 outer_second_cvlan_tag:1; + u32 gre_key_l:8; /* GRE Key [7:0] (outer) */ + u32 gre_key_h:24; /* GRE Key[31:8] (outer) */ + u32 reserved_auto4:8; + u32 vxlan_vni:24; /* VXLAN VNI (outer) */ + u32 geneve_oam:1; /* GENEVE OAM field (outer) */ + u32 reserved_auto5:7; + u32 geneve_vni:24; /* GENEVE VNI field (outer) */ + u32 outer_ipv6_flow_label:20; /* Flow label of incoming IPv6 packet (outer) */ + u32 reserved_auto6:12; + u32 inner_ipv6_flow_label:20; /* Flow label of incoming IPv6 packet (inner) */ + u32 reserved_auto7:12; + u32 geneve_protocol_type:16; /* GENEVE protocol type (outer) */ + u32 geneve_opt_len:6; /* GENEVE OptLen (outer) */ + u32 reserved_auto8:10; + u32 bth_dst_qp:24; /* Destination QP in BTH header */ + u32 reserved_auto9:8; + u8 reserved_auto10[20]; +}; + +struct mlx5dr_match_misc2 { + u32 outer_first_mpls_ttl:8; /* First MPLS TTL (outer) */ + u32 outer_first_mpls_s_bos:1; /* First MPLS S_BOS (outer) */ + u32 outer_first_mpls_exp:3; /* First MPLS EXP (outer) */ + u32 outer_first_mpls_label:20; /* First MPLS LABEL (outer) */ + u32 inner_first_mpls_ttl:8; /* First MPLS TTL (inner) */ + u32 inner_first_mpls_s_bos:1; /* First MPLS S_BOS (inner) */ + u32 inner_first_mpls_exp:3; /* First MPLS EXP (inner) */ + u32 inner_first_mpls_label:20; /* First MPLS LABEL (inner) */ + u32 outer_first_mpls_over_gre_ttl:8; /* last MPLS TTL (outer) */ + u32 outer_first_mpls_over_gre_s_bos:1; /* last MPLS S_BOS (outer) */ + u32 outer_first_mpls_over_gre_exp:3; /* last MPLS EXP (outer) */ + u32 outer_first_mpls_over_gre_label:20; /* last MPLS LABEL (outer) */ + u32 outer_first_mpls_over_udp_ttl:8; /* last MPLS TTL (outer) */ + u32 outer_first_mpls_over_udp_s_bos:1; /* last MPLS S_BOS (outer) */ + u32 outer_first_mpls_over_udp_exp:3; /* last MPLS EXP (outer) */ + u32 outer_first_mpls_over_udp_label:20; /* last MPLS LABEL (outer) */ + u32 metadata_reg_c_7; /* metadata_reg_c_7 */ + u32 metadata_reg_c_6; /* metadata_reg_c_6 */ + u32 metadata_reg_c_5; /* metadata_reg_c_5 */ + u32 metadata_reg_c_4; /* metadata_reg_c_4 */ + u32 metadata_reg_c_3; /* metadata_reg_c_3 */ + u32 metadata_reg_c_2; /* metadata_reg_c_2 */ + u32 metadata_reg_c_1; /* metadata_reg_c_1 */ + u32 metadata_reg_c_0; /* metadata_reg_c_0 */ + u32 metadata_reg_a; /* metadata_reg_a */ + u32 metadata_reg_b; /* metadata_reg_b */ + u8 reserved_auto2[8]; +}; + +struct mlx5dr_match_misc3 { + u32 inner_tcp_seq_num; + u32 outer_tcp_seq_num; + u32 inner_tcp_ack_num; + u32 outer_tcp_ack_num; + u32 outer_vxlan_gpe_vni:24; + u32 reserved_auto1:8; + u32 reserved_auto2:16; + u32 outer_vxlan_gpe_flags:8; + u32 outer_vxlan_gpe_next_protocol:8; + u32 icmpv4_header_data; + u32 icmpv6_header_data; + u32 icmpv6_code:8; + u32 icmpv6_type:8; + u32 icmpv4_code:8; + u32 icmpv4_type:8; + u8 reserved_auto3[0x1c]; +}; + +struct mlx5dr_match_param { + struct mlx5dr_match_spec outer; + struct mlx5dr_match_misc misc; + struct mlx5dr_match_spec inner; + struct mlx5dr_match_misc2 misc2; + struct mlx5dr_match_misc3 misc3; +}; + +#define DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ + (_misc3)->icmpv4_code || \ + (_misc3)->icmpv4_header_data) + +struct mlx5dr_esw_caps { + u64 drop_icm_address_rx; + u64 drop_icm_address_tx; + u64 uplink_icm_address_rx; + u64 uplink_icm_address_tx; + bool sw_owner; +}; + +struct mlx5dr_cmd_vport_cap { + u16 vport_gvmi; + u16 vhca_gvmi; + u64 icm_address_rx; + u64 icm_address_tx; + u32 num; +}; + +struct mlx5dr_cmd_caps { + u16 gvmi; + u64 nic_rx_drop_address; + u64 nic_tx_drop_address; + u64 nic_tx_allow_address; + u64 esw_rx_drop_address; + u64 esw_tx_drop_address; + u32 log_icm_size; + u64 hdr_modify_icm_addr; + u32 flex_protocols; + u8 flex_parser_id_icmp_dw0; + u8 flex_parser_id_icmp_dw1; + u8 flex_parser_id_icmpv6_dw0; + u8 flex_parser_id_icmpv6_dw1; + u8 max_ft_level; + u16 roce_min_src_udp; + u8 num_esw_ports; + bool eswitch_manager; + bool rx_sw_owner; + bool tx_sw_owner; + bool fdb_sw_owner; + u32 num_vports; + struct mlx5dr_esw_caps esw_caps; + struct mlx5dr_cmd_vport_cap *vports_caps; + bool prio_tag_required; +}; + +struct mlx5dr_domain_rx_tx { + u64 drop_icm_addr; + u64 default_icm_addr; + enum mlx5dr_ste_entry_type ste_type; +}; + +struct mlx5dr_domain_info { + bool supp_sw_steering; + u32 max_inline_size; + u32 max_send_wr; + u32 max_log_sw_icm_sz; + u32 max_log_action_icm_sz; + struct mlx5dr_domain_rx_tx rx; + struct mlx5dr_domain_rx_tx tx; + struct mlx5dr_cmd_caps caps; +}; + +struct mlx5dr_domain_cache { + struct mlx5dr_fw_recalc_cs_ft **recalc_cs_ft; +}; + +struct mlx5dr_domain { + struct mlx5dr_domain *peer_dmn; + struct mlx5_core_dev *mdev; + u32 pdn; + struct mlx5_uars_page *uar; + enum mlx5dr_domain_type type; + refcount_t refcount; + struct mutex mutex; /* protect domain */ + struct mlx5dr_icm_pool *ste_icm_pool; + struct mlx5dr_icm_pool *action_icm_pool; + struct mlx5dr_send_ring *send_ring; + struct mlx5dr_domain_info info; + struct mlx5dr_domain_cache cache; +}; + +struct mlx5dr_table_rx_tx { + struct mlx5dr_ste_htbl *s_anchor; + struct mlx5dr_domain_rx_tx *nic_dmn; + u64 default_icm_addr; +}; + +struct mlx5dr_table { + struct mlx5dr_domain *dmn; + struct mlx5dr_table_rx_tx rx; + struct mlx5dr_table_rx_tx tx; + u32 level; + u32 table_type; + u32 table_id; + struct list_head matcher_list; + struct mlx5dr_action *miss_action; + refcount_t refcount; +}; + +struct mlx5dr_matcher_rx_tx { + struct mlx5dr_ste_htbl *s_htbl; + struct mlx5dr_ste_htbl *e_anchor; + struct mlx5dr_ste_build *ste_builder; + struct mlx5dr_ste_build ste_builder4[DR_RULE_MAX_STES]; + struct mlx5dr_ste_build ste_builder6[DR_RULE_MAX_STES]; + u8 num_of_builders; + u8 num_of_builders4; + u8 num_of_builders6; + u64 default_icm_addr; + struct mlx5dr_table_rx_tx *nic_tbl; +}; + +struct mlx5dr_matcher { + struct mlx5dr_table *tbl; + struct mlx5dr_matcher_rx_tx rx; + struct mlx5dr_matcher_rx_tx tx; + struct list_head matcher_list; + u16 prio; + struct mlx5dr_match_param mask; + u8 match_criteria; + refcount_t refcount; + struct mlx5dv_flow_matcher *dv_matcher; +}; + +struct mlx5dr_rule_member { + struct mlx5dr_ste *ste; + /* attached to mlx5dr_rule via this */ + struct list_head list; + /* attached to mlx5dr_ste via this */ + struct list_head use_ste_list; +}; + +struct mlx5dr_action { + enum mlx5dr_action_type action_type; + refcount_t refcount; + union { + struct { + struct mlx5dr_domain *dmn; + struct mlx5dr_icm_chunk *chunk; + u8 *data; + u32 data_size; + u16 num_of_actions; + u32 index; + u8 allow_rx:1; + u8 allow_tx:1; + u8 modify_ttl:1; + } rewrite; + struct { + struct mlx5dr_domain *dmn; + u32 reformat_id; + u32 reformat_size; + } reformat; + struct { + u8 is_fw_tbl:1; + union { + struct mlx5dr_table *tbl; + struct { + struct mlx5_flow_table *ft; + u64 rx_icm_addr; + u64 tx_icm_addr; + struct mlx5_core_dev *mdev; + } fw_tbl; + }; + } dest_tbl; + struct { + u32 ctr_id; + u32 offeset; + } ctr; + struct { + struct mlx5dr_domain *dmn; + struct mlx5dr_cmd_vport_cap *caps; + u32 num; + } vport; + struct { + u32 vlan_hdr; /* tpid_pcp_dei_vid */ + } push_vlan; + u32 flow_tag; + }; +}; + +enum mlx5dr_connect_type { + CONNECT_HIT = 1, + CONNECT_MISS = 2, +}; + +struct mlx5dr_htbl_connect_info { + enum mlx5dr_connect_type type; + union { + struct mlx5dr_ste_htbl *hit_next_htbl; + u64 miss_icm_addr; + }; +}; + +struct mlx5dr_rule_rx_tx { + struct list_head rule_members_list; + struct mlx5dr_matcher_rx_tx *nic_matcher; +}; + +struct mlx5dr_rule { + struct mlx5dr_matcher *matcher; + struct mlx5dr_rule_rx_tx rx; + struct mlx5dr_rule_rx_tx tx; + struct list_head rule_actions_list; +}; + +void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste, + struct mlx5dr_ste *ste); + +struct mlx5dr_icm_chunk { + struct mlx5dr_icm_bucket *bucket; + struct list_head chunk_list; + u32 rkey; + u32 num_of_entries; + u32 byte_size; + u64 icm_addr; + u64 mr_addr; + + /* Memory optimisation */ + struct mlx5dr_ste *ste_arr; + u8 *hw_ste_arr; + struct list_head *miss_list; +}; + +static inline int +mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; +} + +static inline int +mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; +} + +int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6); + +static inline u32 +mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size) +{ + return 1 << chunk_size; +} + +static inline int +mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size, + enum mlx5dr_icm_type icm_type) +{ + int num_of_entries; + int entry_size; + + if (icm_type == DR_ICM_TYPE_STE) + entry_size = DR_STE_SIZE; + else + entry_size = DR_MODIFY_ACTION_SIZE; + + num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + + return entry_size * num_of_entries; +} + +static inline struct mlx5dr_cmd_vport_cap * +mlx5dr_get_vport_cap(struct mlx5dr_cmd_caps *caps, u32 vport) +{ + if (!caps->vports_caps || + (vport >= caps->num_vports && vport != WIRE_PORT)) + return NULL; + + if (vport == WIRE_PORT) + vport = caps->num_vports; + + return &caps->vports_caps[vport]; +} + +struct mlx5dr_cmd_query_flow_table_details { + u8 status; + u8 level; + u64 sw_owner_icm_root_1; + u64 sw_owner_icm_root_0; +}; + +/* internal API functions */ +int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, + struct mlx5dr_cmd_caps *caps); +int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev, + bool other_vport, u16 vport_number, + u64 *icm_address_rx, + u64 *icm_address_tx); +int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, + bool other_vport, u16 vport_number, u16 *gvmi); +int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_esw_caps *caps); +int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev); +int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id, + u32 modify_header_id, + u32 vport_id); +int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id); +int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev, + u32 table_type, + u8 num_of_actions, + u64 *actions, + u32 *modify_header_id); +int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev, + u32 modify_header_id); +int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 *group_id); +int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id); +int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev, + u32 table_type, + u64 icm_addr_rx, + u64 icm_addr_tx, + u8 level, + bool sw_owner, + bool term_tbl, + u64 *fdb_rx_icm_addr, + u32 *table_id); +int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev, + u32 table_id, + u32 table_type); +int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, + u32 table_id, + struct mlx5dr_cmd_query_flow_table_details *output); +int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, + enum mlx5_reformat_ctx_type rt, + size_t reformat_size, + void *reformat_data, + u32 *reformat_id); +void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, + u32 reformat_id); + +struct mlx5dr_cmd_gid_attr { + u8 gid[16]; + u8 mac[6]; + u32 roce_ver; +}; + +struct mlx5dr_cmd_qp_create_attr { + u32 page_id; + u32 pdn; + u32 cqn; + u32 pm_state; + u32 service_type; + u32 buff_umem_id; + u32 db_umem_id; + u32 sq_wqe_cnt; + u32 rq_wqe_cnt; + u32 rq_wqe_shift; +}; + +int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num, + u16 index, struct mlx5dr_cmd_gid_attr *attr); + +struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, + enum mlx5dr_icm_type icm_type); +void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool); + +struct mlx5dr_icm_chunk * +mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size); +void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk); +bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste); +int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_htbl_connect_info *connect_info, + bool update_hw_ste); +void mlx5dr_ste_set_formatted_ste(u16 gvmi, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, + struct mlx5dr_htbl_connect_info *connect_info); +void mlx5dr_ste_copy_param(u8 match_criteria, + struct mlx5dr_match_param *set_param, + struct mlx5dr_match_parameters *mask); + +void mlx5dr_crc32_init_table(void); +u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length); + +struct mlx5dr_qp { + struct mlx5_core_dev *mdev; + struct mlx5_wq_qp wq; + struct mlx5_uars_page *uar; + struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_core_qp mqp; + struct { + unsigned int pc; + unsigned int cc; + unsigned int size; + unsigned int *wqe_head; + unsigned int wqe_cnt; + } sq; + struct { + unsigned int pc; + unsigned int cc; + unsigned int size; + unsigned int wqe_cnt; + } rq; + int max_inline_data; +}; + +struct mlx5dr_cq { + struct mlx5_core_dev *mdev; + struct mlx5_cqwq wq; + struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_core_cq mcq; + struct mlx5dr_qp *qp; +}; + +struct mlx5dr_mr { + struct mlx5_core_dev *mdev; + struct mlx5_core_mkey mkey; + dma_addr_t dma_addr; + void *addr; + size_t size; +}; + +#define MAX_SEND_CQE 64 +#define MIN_READ_SYNC 64 + +struct mlx5dr_send_ring { + struct mlx5dr_cq *cq; + struct mlx5dr_qp *qp; + struct mlx5dr_mr *mr; + /* How much wqes are waiting for completion */ + u32 pending_wqe; + /* Signal request per this trash hold value */ + u16 signal_th; + /* Each post_send_size less than max_post_send_size */ + u32 max_post_send_size; + /* manage the send queue */ + u32 tx_head; + void *buf; + u32 buf_size; + struct ib_wc wc[MAX_SEND_CQE]; + u8 sync_buff[MIN_READ_SYNC]; + struct mlx5dr_mr *sync_mr; +}; + +int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn); +void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring); +int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn); +int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, + struct mlx5dr_ste *ste, + u8 *data, + u16 size, + u16 offset); +int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, u8 *mask); +int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *ste_init_data, + bool update_hw_ste); +int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action); + +struct mlx5dr_fw_recalc_cs_ft { + u64 rx_icm_addr; + u32 table_id; + u32 group_id; + u32 modify_hdr_id; +}; + +struct mlx5dr_fw_recalc_cs_ft * +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num); +void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn, + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft); +int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u32 vport_num, + u64 *rx_icm_addr); +#endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c new file mode 100644 index 000000000000..3d587d0bdbbe --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies */ + +#include "mlx5_core.h" +#include "fs_core.h" +#include "fs_cmd.h" +#include "mlx5dr.h" +#include "fs_dr.h" + +static bool mlx5_dr_is_fw_table(u32 flags) +{ + if (flags & MLX5_FLOW_TABLE_TERMINATION) + return true; + + return false; +} + +static int mlx5_cmd_dr_update_root_ft(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 underlay_qpn, + bool disconnect) +{ + return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn, + disconnect); +} + +static int set_miss_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + struct mlx5dr_action *old_miss_action; + struct mlx5dr_action *action = NULL; + struct mlx5dr_table *next_tbl; + int err; + + next_tbl = next_ft ? next_ft->fs_dr_table.dr_table : NULL; + if (next_tbl) { + action = mlx5dr_action_create_dest_table(next_tbl); + if (!action) + return -EINVAL; + } + old_miss_action = ft->fs_dr_table.miss_action; + err = mlx5dr_table_set_miss_action(ft->fs_dr_table.dr_table, action); + if (err && action) { + err = mlx5dr_action_destroy(action); + if (err) { + action = NULL; + mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n", + err); + } + } + ft->fs_dr_table.miss_action = action; + if (old_miss_action) { + err = mlx5dr_action_destroy(old_miss_action); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n", + err); + } + + return err; +} + +static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + unsigned int log_size, + struct mlx5_flow_table *next_ft) +{ + struct mlx5dr_table *tbl; + int err; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, + log_size, + next_ft); + + tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, + ft->level); + if (!tbl) { + mlx5_core_err(ns->dev, "Failed creating dr flow_table\n"); + return -EINVAL; + } + + ft->fs_dr_table.dr_table = tbl; + ft->id = mlx5dr_table_get_id(tbl); + + if (next_ft) { + err = set_miss_action(ns, ft, next_ft); + if (err) { + mlx5dr_table_destroy(tbl); + ft->fs_dr_table.dr_table = NULL; + return err; + } + } + + return 0; +} + +static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + struct mlx5dr_action *action = ft->fs_dr_table.miss_action; + int err; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + + err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table); + if (err) { + mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", + err); + return err; + } + if (action) { + err = mlx5dr_action_destroy(action); + if (err) { + mlx5_core_err(ns->dev, "Failed to destroy action(%d)\n", + err); + return err; + } + } + + return err; +} + +static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + return set_miss_action(ns, ft, next_ft); +} + +static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 *in, + struct mlx5_flow_group *fg) +{ + struct mlx5dr_matcher *matcher; + u16 priority = MLX5_GET(create_flow_group_in, in, + start_flow_index); + u8 match_criteria_enable = MLX5_GET(create_flow_group_in, + in, + match_criteria_enable); + struct mlx5dr_match_parameters mask; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, + fg); + + mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, + in, match_criteria); + mask.match_sz = sizeof(fg->mask.match_criteria); + + matcher = mlx5dr_matcher_create(ft->fs_dr_table.dr_table, + priority, + match_criteria_enable, + &mask); + if (!matcher) { + mlx5_core_err(ns->dev, "Failed creating matcher\n"); + return -EINVAL; + } + + fg->fs_dr_matcher.dr_matcher = matcher; + return 0; +} + +static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg); + + return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher); +} + +static struct mlx5dr_action *create_vport_action(struct mlx5dr_domain *domain, + struct mlx5_flow_rule *dst) +{ + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + + return mlx5dr_action_create_dest_vport(domain, dest_attr->vport.num, + dest_attr->vport.flags & + MLX5_FLOW_DEST_VPORT_VHCA_ID, + dest_attr->vport.vhca_id); +} + +static struct mlx5dr_action *create_ft_action(struct mlx5_core_dev *dev, + struct mlx5_flow_rule *dst) +{ + struct mlx5_flow_table *dest_ft = dst->dest_attr.ft; + + if (mlx5_dr_is_fw_table(dest_ft->flags)) + return mlx5dr_create_action_dest_flow_fw_table(dest_ft, dev); + return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table); +} + +static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domain, + struct mlx5_fs_vlan *vlan) +{ + u16 n_ethtype = vlan->ethtype; + u8 prio = vlan->prio; + u16 vid = vlan->vid; + u32 vlan_hdr; + + vlan_hdr = (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid; + return mlx5dr_action_create_push_vlan(domain, htonl(vlan_hdr)); +} + +#define MLX5_FLOW_CONTEXT_ACTION_MAX 20 +static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte) +{ + struct mlx5dr_domain *domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *term_action = NULL; + struct mlx5dr_match_parameters params; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5dr_action **fs_dr_actions; + struct mlx5dr_action *tmp_action; + struct mlx5dr_action **actions; + bool delay_encap_set = false; + struct mlx5dr_rule *rule; + struct mlx5_flow_rule *dst; + int fs_dr_num_actions = 0; + int num_actions = 0; + size_t match_sz; + int err = 0; + int i; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte); + + actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions), + GFP_KERNEL); + if (!actions) + return -ENOMEM; + + fs_dr_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*fs_dr_actions), GFP_KERNEL); + if (!fs_dr_actions) { + kfree(actions); + return -ENOMEM; + } + + match_sz = sizeof(fte->val); + + /* The order of the actions are must to be keep, only the following + * order is supported by SW steering: + * TX: push vlan -> modify header -> encap + * RX: decap -> pop vlan -> modify header + */ + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + enum mlx5dr_action_reformat_type decap_type = + DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2; + + tmp_action = mlx5dr_action_create_packet_reformat(domain, + decap_type, 0, + NULL); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { + bool is_decap = fte->action.pkt_reformat->reformat_type == + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; + + if (is_decap) + actions[num_actions++] = + fte->action.pkt_reformat->action.dr_action; + else + delay_encap_set = true; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { + tmp_action = + mlx5dr_action_create_pop_vlan(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) { + tmp_action = + mlx5dr_action_create_pop_vlan(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + actions[num_actions++] = + fte->action.modify_hdr->action.dr_action; + + if (delay_encap_set) + actions[num_actions++] = + fte->action.pkt_reformat->action.dr_action; + + /* The order of the actions below is not important */ + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) { + tmp_action = mlx5dr_action_create_drop(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + } + + if (fte->flow_context.flow_tag) { + tmp_action = + mlx5dr_action_create_tag(fte->flow_context.flow_tag); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + list_for_each_entry(dst, &fte->node.children, node.list) { + enum mlx5_flow_destination_type type = dst->dest_attr.type; + u32 id; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -ENOSPC; + goto free_actions; + } + + switch (type) { + case MLX5_FLOW_DESTINATION_TYPE_COUNTER: + id = dst->dest_attr.counter_id; + + tmp_action = + mlx5dr_action_create_flow_counter(id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: + tmp_action = create_ft_action(dev, dst); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_VPORT: + tmp_action = create_vport_action(domain, dst); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + break; + default: + err = -EOPNOTSUPP; + goto free_actions; + } + } + } + + params.match_sz = match_sz; + params.match_buf = (u64 *)fte->val; + + if (term_action) + actions[num_actions++] = term_action; + + rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher, + ¶ms, + num_actions, + actions); + if (!rule) { + err = -EINVAL; + goto free_actions; + } + + kfree(actions); + fte->fs_dr_rule.dr_rule = rule; + fte->fs_dr_rule.num_actions = fs_dr_num_actions; + fte->fs_dr_rule.dr_actions = fs_dr_actions; + + return 0; + +free_actions: + for (i = 0; i < fs_dr_num_actions; i++) + if (!IS_ERR_OR_NULL(fs_dr_actions[i])) + mlx5dr_action_destroy(fs_dr_actions[i]); + + mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err); + kfree(actions); + kfree(fs_dr_actions); + return err; +} + +static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *action; + int dr_reformat; + + switch (reformat_type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2; + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + dr_reformat = DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2; + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3; + break; + default: + mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", + reformat_type); + return -EOPNOTSUPP; + } + + action = mlx5dr_action_create_packet_reformat(dr_domain, + dr_reformat, + size, + reformat_data); + if (!action) { + mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n"); + return -EINVAL; + } + + pkt_reformat->action.dr_action = action; + + return 0; +} + +static void mlx5_cmd_dr_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ + mlx5dr_action_destroy(pkt_reformat->action.dr_action); +} + +static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *action; + size_t actions_sz; + + actions_sz = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * + num_actions; + action = mlx5dr_action_create_modify_header(dr_domain, 0, + actions_sz, + modify_actions); + if (!action) { + mlx5_core_err(ns->dev, "Failed allocating modify-header action\n"); + return -EINVAL; + } + + modify_hdr->action.dr_action = action; + + return 0; +} + +static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ + mlx5dr_action_destroy(modify_hdr->action.dr_action); +} + +static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + int modify_mask, + struct fs_fte *fte) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct fs_fte *fte) +{ + struct mlx5_fs_dr_rule *rule = &fte->fs_dr_rule; + int err; + int i; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte); + + err = mlx5dr_rule_destroy(rule->dr_rule); + if (err) + return err; + + for (i = 0; i < rule->num_actions; i++) + if (!IS_ERR_OR_NULL(rule->dr_actions[i])) + mlx5dr_action_destroy(rule->dr_actions[i]); + + kfree(rule->dr_actions); + return 0; +} + +static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + struct mlx5dr_domain *peer_domain = NULL; + + if (peer_ns) + peer_domain = peer_ns->fs_dr_domain.dr_domain; + mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain, + peer_domain); + return 0; +} + +static int mlx5_cmd_dr_create_ns(struct mlx5_flow_root_namespace *ns) +{ + ns->fs_dr_domain.dr_domain = + mlx5dr_domain_create(ns->dev, + MLX5DR_DOMAIN_TYPE_FDB); + if (!ns->fs_dr_domain.dr_domain) { + mlx5_core_err(ns->dev, "Failed to create dr flow namespace\n"); + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain); +} + +bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) +{ + return mlx5dr_is_supported(dev); +} + +static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { + .create_flow_table = mlx5_cmd_dr_create_flow_table, + .destroy_flow_table = mlx5_cmd_dr_destroy_flow_table, + .modify_flow_table = mlx5_cmd_dr_modify_flow_table, + .create_flow_group = mlx5_cmd_dr_create_flow_group, + .destroy_flow_group = mlx5_cmd_dr_destroy_flow_group, + .create_fte = mlx5_cmd_dr_create_fte, + .update_fte = mlx5_cmd_dr_update_fte, + .delete_fte = mlx5_cmd_dr_delete_fte, + .update_root_ft = mlx5_cmd_dr_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_dr_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc, + .set_peer = mlx5_cmd_dr_set_peer, + .create_ns = mlx5_cmd_dr_create_ns, + .destroy_ns = mlx5_cmd_dr_destroy_ns, +}; + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) +{ + return &mlx5_flow_cmds_dr; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h new file mode 100644 index 000000000000..1fb185d6ac7f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2019 Mellanox Technologies + */ + +#ifndef _MLX5_FS_DR_ +#define _MLX5_FS_DR_ + +#include "mlx5dr.h" + +struct mlx5_flow_root_namespace; +struct fs_fte; + +struct mlx5_fs_dr_action { + struct mlx5dr_action *dr_action; +}; + +struct mlx5_fs_dr_ns { + struct mlx5_dr_ns *dr_ns; +}; + +struct mlx5_fs_dr_rule { + struct mlx5dr_rule *dr_rule; + /* Only actions created by fs_dr */ + struct mlx5dr_action **dr_actions; + int num_actions; +}; + +struct mlx5_fs_dr_domain { + struct mlx5dr_domain *dr_domain; +}; + +struct mlx5_fs_dr_matcher { + struct mlx5dr_matcher *dr_matcher; +}; + +struct mlx5_fs_dr_table { + struct mlx5dr_table *dr_table; + struct mlx5dr_action *miss_action; +}; + +#ifdef CONFIG_MLX5_SW_STEERING + +bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev); + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void); + +#else + +static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) +{ + return NULL; +} + +static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) +{ + return false; +} + +#endif /* CONFIG_MLX5_SW_STEERING */ +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h new file mode 100644 index 000000000000..596c927220d9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -0,0 +1,604 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef MLX5_IFC_DR_H +#define MLX5_IFC_DR_H + +enum { + MLX5DR_ACTION_MDFY_HW_FLD_L2_0 = 0, + MLX5DR_ACTION_MDFY_HW_FLD_L2_1 = 1, + MLX5DR_ACTION_MDFY_HW_FLD_L2_2 = 2, + MLX5DR_ACTION_MDFY_HW_FLD_L3_0 = 3, + MLX5DR_ACTION_MDFY_HW_FLD_L3_1 = 4, + MLX5DR_ACTION_MDFY_HW_FLD_L3_2 = 5, + MLX5DR_ACTION_MDFY_HW_FLD_L3_3 = 6, + MLX5DR_ACTION_MDFY_HW_FLD_L3_4 = 7, + MLX5DR_ACTION_MDFY_HW_FLD_L4_0 = 8, + MLX5DR_ACTION_MDFY_HW_FLD_L4_1 = 9, + MLX5DR_ACTION_MDFY_HW_FLD_MPLS = 10, + MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_0 = 11, + MLX5DR_ACTION_MDFY_HW_FLD_REG_0 = 12, + MLX5DR_ACTION_MDFY_HW_FLD_REG_1 = 13, + MLX5DR_ACTION_MDFY_HW_FLD_REG_2 = 14, + MLX5DR_ACTION_MDFY_HW_FLD_REG_3 = 15, + MLX5DR_ACTION_MDFY_HW_FLD_L4_2 = 16, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_0 = 17, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_1 = 18, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_2 = 19, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_3 = 20, + MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_1 = 21, + MLX5DR_ACTION_MDFY_HW_FLD_METADATA = 22, + MLX5DR_ACTION_MDFY_HW_FLD_RESERVED = 23, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_OP_SET = 0x2, + MLX5DR_ACTION_MDFY_HW_OP_ADD = 0x3, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE = 0x0, + MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4 = 0x1, + MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6 = 0x2, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE = 0x0, + MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP = 0x1, + MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP = 0x2, +}; + +enum { + MLX5DR_STE_LU_TYPE_NOP = 0x00, + MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP = 0x05, + MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I = 0x0a, + MLX5DR_STE_LU_TYPE_ETHL2_DST_O = 0x06, + MLX5DR_STE_LU_TYPE_ETHL2_DST_I = 0x07, + MLX5DR_STE_LU_TYPE_ETHL2_DST_D = 0x1b, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_O = 0x08, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_I = 0x09, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_D = 0x1c, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_O = 0x36, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_I = 0x37, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_D = 0x38, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_O = 0x0d, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_I = 0x0e, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_D = 0x1e, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_O = 0x0f, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_I = 0x10, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_D = 0x1f, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x11, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x12, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_D = 0x20, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_O = 0x29, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_I = 0x2a, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_D = 0x2b, + MLX5DR_STE_LU_TYPE_ETHL4_O = 0x13, + MLX5DR_STE_LU_TYPE_ETHL4_I = 0x14, + MLX5DR_STE_LU_TYPE_ETHL4_D = 0x21, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_O = 0x2c, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_I = 0x2d, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_D = 0x2e, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_O = 0x15, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_I = 0x24, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_D = 0x25, + MLX5DR_STE_LU_TYPE_GRE = 0x16, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_0 = 0x22, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_1 = 0x23, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x19, + MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE = 0x18, + MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0 = 0x2f, + MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1 = 0x30, + MLX5DR_STE_LU_TYPE_DONT_CARE = 0x0f, +}; + +enum mlx5dr_ste_entry_type { + MLX5DR_STE_TYPE_TX = 1, + MLX5DR_STE_TYPE_RX = 2, + MLX5DR_STE_TYPE_MODIFY_PKT = 6, +}; + +struct mlx5_ifc_ste_general_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_5c[0x2]; + u8 next_table_rank[0x2]; + + u8 reserved_at_60[0xa0]; + u8 tag_value[0x60]; + u8 bit_mask[0x60]; +}; + +struct mlx5_ifc_ste_sx_transmit_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_5c[0x2]; + u8 next_table_rank[0x2]; + + u8 sx_wire[0x1]; + u8 sx_func_lb[0x1]; + u8 sx_sniffer[0x1]; + u8 sx_wire_enable[0x1]; + u8 sx_func_lb_enable[0x1]; + u8 sx_sniffer_enable[0x1]; + u8 action_type[0x3]; + u8 reserved_at_69[0x1]; + u8 action_description[0x6]; + u8 gvmi[0x10]; + + u8 encap_pointer_vlan_data[0x20]; + + u8 loopback_syndome_en[0x8]; + u8 loopback_syndome[0x8]; + u8 counter_trigger[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x8]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 go_back[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_rx_steering_mult_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_[0x2]; + u8 next_table_rank[0x2]; + + u8 member_count[0x10]; + u8 gvmi[0x10]; + + u8 qp_list_pointer[0x20]; + + u8 reserved_at_a0[0x1]; + u8 tunneling_action[0x3]; + u8 action_description[0x4]; + u8 reserved_at_a8[0x8]; + u8 counter_trigger_15_0[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x08]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 fail_on_error[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_modify_packet_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_[0x2]; + u8 next_table_rank[0x2]; + + u8 number_of_re_write_actions[0x10]; + u8 gvmi[0x10]; + + u8 header_re_write_actions_pointer[0x20]; + + u8 reserved_at_a0[0x1]; + u8 tunneling_action[0x3]; + u8 action_description[0x4]; + u8 reserved_at_a8[0x8]; + u8 counter_trigger_15_0[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x08]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 fail_on_error[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_eth_l2_src_bits { + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 qp_type[0x2]; + u8 ethertype_filter[0x1]; + u8 reserved_at_43[0x1]; + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 reserved_at_48[0x4]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_52[0x2]; + u8 first_vlan_id[0xc]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 reserved_at_68[0x4]; + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_dst_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 qp_type[0x2]; + u8 ethertype_filter[0x1]; + u8 reserved_at_43[0x1]; + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 reserved_at_48[0x4]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_52[0x2]; + u8 first_vlan_id[0xc]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 reserved_at_68[0x4]; + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_src_dst_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 smac_47_32[0x10]; + + u8 smac_31_0[0x20]; + + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 l3_type[0x2]; + u8 reserved_at_66[0x6]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 first_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_5_tuple_bits { + u8 destination_address[0x20]; + + u8 source_address[0x20]; + + u8 source_port[0x10]; + u8 destination_port[0x10]; + + u8 fragmented[0x1]; + u8 first_fragment[0x1]; + u8 reserved_at_62[0x2]; + u8 reserved_at_64[0x1]; + u8 ecn[0x2]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 dscp[0x6]; + u8 reserved_at_76[0x2]; + u8 protocol[0x8]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv6_dst_bits { + u8 dst_ip_127_96[0x20]; + + u8 dst_ip_95_64[0x20]; + + u8 dst_ip_63_32[0x20]; + + u8 dst_ip_31_0[0x20]; +}; + +struct mlx5_ifc_ste_eth_l2_tnl_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 l2_tunneling_network_id[0x20]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 reserved_at_6c[0x3]; + u8 gre_key_flag[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 first_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv6_src_bits { + u8 src_ip_127_96[0x20]; + + u8 src_ip_95_64[0x20]; + + u8 src_ip_63_32[0x20]; + + u8 src_ip_31_0[0x20]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_misc_bits { + u8 version[0x4]; + u8 ihl[0x4]; + u8 reserved_at_8[0x8]; + u8 total_length[0x10]; + + u8 identification[0x10]; + u8 flags[0x3]; + u8 fragment_offset[0xd]; + + u8 time_to_live[0x8]; + u8 reserved_at_48[0x8]; + u8 checksum[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_eth_l4_bits { + u8 fragmented[0x1]; + u8 first_fragment[0x1]; + u8 reserved_at_2[0x6]; + u8 protocol[0x8]; + u8 dst_port[0x10]; + + u8 ipv6_version[0x4]; + u8 reserved_at_24[0x1]; + u8 ecn[0x2]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 src_port[0x10]; + + u8 ipv6_payload_length[0x10]; + u8 ipv6_hop_limit[0x8]; + u8 dscp[0x6]; + u8 reserved_at_5e[0x2]; + + u8 tcp_data_offset[0x4]; + u8 reserved_at_64[0x8]; + u8 flow_label[0x14]; +}; + +struct mlx5_ifc_ste_eth_l4_misc_bits { + u8 checksum[0x10]; + u8 length[0x10]; + + u8 seq_num[0x20]; + + u8 ack_num[0x20]; + + u8 urgent_pointer[0x10]; + u8 window_size[0x10]; +}; + +struct mlx5_ifc_ste_mpls_bits { + u8 mpls0_label[0x14]; + u8 mpls0_exp[0x3]; + u8 mpls0_s_bos[0x1]; + u8 mpls0_ttl[0x8]; + + u8 mpls1_label[0x20]; + + u8 mpls2_label[0x20]; + + u8 reserved_at_60[0x16]; + u8 mpls4_s_bit[0x1]; + u8 mpls4_qualifier[0x1]; + u8 mpls3_s_bit[0x1]; + u8 mpls3_qualifier[0x1]; + u8 mpls2_s_bit[0x1]; + u8 mpls2_qualifier[0x1]; + u8 mpls1_s_bit[0x1]; + u8 mpls1_qualifier[0x1]; + u8 mpls0_s_bit[0x1]; + u8 mpls0_qualifier[0x1]; +}; + +struct mlx5_ifc_ste_register_0_bits { + u8 register_0_h[0x20]; + + u8 register_0_l[0x20]; + + u8 register_1_h[0x20]; + + u8 register_1_l[0x20]; +}; + +struct mlx5_ifc_ste_register_1_bits { + u8 register_2_h[0x20]; + + u8 register_2_l[0x20]; + + u8 register_3_h[0x20]; + + u8 register_3_l[0x20]; +}; + +struct mlx5_ifc_ste_gre_bits { + u8 gre_c_present[0x1]; + u8 reserved_at_30[0x1]; + u8 gre_k_present[0x1]; + u8 gre_s_present[0x1]; + u8 strict_src_route[0x1]; + u8 recur[0x3]; + u8 flags[0x5]; + u8 version[0x3]; + u8 gre_protocol[0x10]; + + u8 checksum[0x10]; + u8 offset[0x10]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 seq_num[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_0_bits { + u8 parser_3_label[0x14]; + u8 parser_3_exp[0x3]; + u8 parser_3_s_bos[0x1]; + u8 parser_3_ttl[0x8]; + + u8 flex_parser_2[0x20]; + + u8 flex_parser_1[0x20]; + + u8 flex_parser_0[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_1_bits { + u8 flex_parser_7[0x20]; + + u8 flex_parser_6[0x20]; + + u8 flex_parser_5[0x20]; + + u8 flex_parser_4[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_tnl_bits { + u8 flex_parser_tunneling_header_63_32[0x20]; + + u8 flex_parser_tunneling_header_31_0[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_ste_general_purpose_bits { + u8 general_purpose_lookup_field[0x20]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_src_gvmi_qp_bits { + u8 loopback_syndrome[0x8]; + u8 reserved_at_8[0x8]; + u8 source_gvmi[0x10]; + + u8 reserved_at_20[0x5]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 source_is_requestor[0x1]; + u8 source_qp[0x18]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_l2_hdr_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 smac_47_32[0x10]; + + u8 smac_31_0[0x20]; + + u8 ethertype[0x10]; + u8 vlan_type[0x10]; + + u8 vlan[0x10]; + u8 reserved_at_90[0x10]; +}; + +/* Both HW set and HW add share the same HW format with different opcodes */ +struct mlx5_ifc_dr_action_hw_set_bits { + u8 opcode[0x8]; + u8 destination_field_code[0x8]; + u8 reserved_at_10[0x2]; + u8 destination_left_shifter[0x6]; + u8 reserved_at_18[0x3]; + u8 destination_length[0x5]; + + u8 inline_data[0x20]; +}; + +#endif /* MLX5_IFC_DR_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h new file mode 100644 index 000000000000..adda9cbfba45 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef _MLX5DR_H_ +#define _MLX5DR_H_ + +struct mlx5dr_domain; +struct mlx5dr_table; +struct mlx5dr_matcher; +struct mlx5dr_rule; +struct mlx5dr_action; + +enum mlx5dr_domain_type { + MLX5DR_DOMAIN_TYPE_NIC_RX, + MLX5DR_DOMAIN_TYPE_NIC_TX, + MLX5DR_DOMAIN_TYPE_FDB, +}; + +enum mlx5dr_domain_sync_flags { + MLX5DR_DOMAIN_SYNC_FLAGS_SW = 1 << 0, + MLX5DR_DOMAIN_SYNC_FLAGS_HW = 1 << 1, +}; + +enum mlx5dr_action_reformat_type { + DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2, + DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2, + DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2, + DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3, +}; + +struct mlx5dr_match_parameters { + size_t match_sz; + u64 *match_buf; /* Device spec format */ +}; + +#ifdef CONFIG_MLX5_SW_STEERING + +struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type); + +int mlx5dr_domain_destroy(struct mlx5dr_domain *domain); + +int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags); + +void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn); + +struct mlx5dr_table * +mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level); + +int mlx5dr_table_destroy(struct mlx5dr_table *table); + +u32 mlx5dr_table_get_id(struct mlx5dr_table *table); + +struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *table, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask); + +int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher); + +struct mlx5dr_rule * +mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]); + +int mlx5dr_rule_destroy(struct mlx5dr_rule *rule); + +int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action); + +struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *table); + +struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev); + +struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, + u32 vport, u8 vhca_id_valid, + u16 vhca_id); + +struct mlx5dr_action *mlx5dr_action_create_drop(void); + +struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value); + +struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id); + +struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data); + +struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain, + u32 flags, + size_t actions_sz, + __be64 actions[]); + +struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void); + +struct mlx5dr_action * +mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, __be32 vlan_hdr); + +int mlx5dr_action_destroy(struct mlx5dr_action *action); + +static inline bool +mlx5dr_is_supported(struct mlx5_core_dev *dev) +{ + return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner); +} + +#else /* CONFIG_MLX5_SW_STEERING */ + +static inline struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) { return NULL; } + +static inline int +mlx5dr_domain_destroy(struct mlx5dr_domain *domain) { return 0; } + +static inline int +mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags) { return 0; } + +static inline void +mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn) { } + +static inline struct mlx5dr_table * +mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level) { return NULL; } + +static inline int +mlx5dr_table_destroy(struct mlx5dr_table *table) { return 0; } + +static inline u32 +mlx5dr_table_get_id(struct mlx5dr_table *table) { return 0; } + +static inline struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *table, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask) { return NULL; } + +static inline int +mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) { return 0; } + +static inline struct mlx5dr_rule * +mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) { return NULL; } + +static inline int +mlx5dr_rule_destroy(struct mlx5dr_rule *rule) { return 0; } + +static inline int +mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action) { return 0; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *table) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, + u32 vport, u8 vhca_id_valid, + u16 vhca_id) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_drop(void) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_tag(u32 tag_value) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain, + u32 flags, + size_t actions_sz, + __be64 actions[]) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_pop_vlan(void) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, + __be32 vlan_hdr) { return NULL; } + +static inline int +mlx5dr_action_destroy(struct mlx5dr_action *action) { return 0; } + +static inline bool +mlx5dr_is_supported(struct mlx5_core_dev *dev) { return false; } + +#endif /* CONFIG_MLX5_SW_STEERING */ + +#endif /* _MLX5DR_H_ */ diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig new file mode 100644 index 000000000000..5ea570be8379 --- /dev/null +++ b/drivers/net/ethernet/pensando/Kconfig @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2019 Pensando Systems, Inc +# +# Pensando device configuration +# + +config NET_VENDOR_PENSANDO + bool "Pensando devices" + default y + help + If you have a network (Ethernet) card belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Pensando cards. If you say Y, you will be asked + for your specific card in the following questions. + +if NET_VENDOR_PENSANDO + +config IONIC + tristate "Pensando Ethernet IONIC Support" + depends on 64BIT && PCI + help + This enables the support for the Pensando family of Ethernet + adapters. More specific information on this driver can be + found in + <file:Documentation/networking/device_drivers/pensando/ionic.rst>. + + To compile this driver as a module, choose M here. The module + will be called ionic. + +endif # NET_VENDOR_PENSANDO diff --git a/drivers/net/ethernet/pensando/Makefile b/drivers/net/ethernet/pensando/Makefile new file mode 100644 index 000000000000..21ce7499c122 --- /dev/null +++ b/drivers/net/ethernet/pensando/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Pensando network device drivers. +# + +obj-$(CONFIG_IONIC) += ionic/ diff --git a/drivers/net/ethernet/pensando/ionic/Makefile b/drivers/net/ethernet/pensando/ionic/Makefile new file mode 100644 index 000000000000..29f304d75261 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2017 - 2019 Pensando Systems, Inc + +obj-$(CONFIG_IONIC) := ionic.o + +ionic-y := ionic_main.o ionic_bus_pci.o ionic_devlink.o ionic_dev.o \ + ionic_debugfs.o ionic_lif.o ionic_rx_filter.o ionic_ethtool.o \ + ionic_txrx.o ionic_stats.o diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h new file mode 100644 index 000000000000..7a7060677f15 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_H_ +#define _IONIC_H_ + +struct ionic_lif; + +#include "ionic_if.h" +#include "ionic_dev.h" +#include "ionic_devlink.h" + +#define IONIC_DRV_NAME "ionic" +#define IONIC_DRV_DESCRIPTION "Pensando Ethernet NIC Driver" +#define IONIC_DRV_VERSION "0.15.0-k" + +#define PCI_VENDOR_ID_PENSANDO 0x1dd8 + +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 + +#define IONIC_SUBDEV_ID_NAPLES_25 0x4000 +#define IONIC_SUBDEV_ID_NAPLES_100_4 0x4001 +#define IONIC_SUBDEV_ID_NAPLES_100_8 0x4002 + +#define DEVCMD_TIMEOUT 10 + +struct ionic { + struct pci_dev *pdev; + struct device *dev; + struct devlink_port dl_port; + struct ionic_dev idev; + struct mutex dev_cmd_lock; /* lock for dev_cmd operations */ + struct dentry *dentry; + struct ionic_dev_bar bars[IONIC_BARS_MAX]; + unsigned int num_bars; + struct ionic_identity ident; + struct list_head lifs; + struct ionic_lif *master_lif; + unsigned int nnqs_per_lif; + unsigned int neqs_per_lif; + unsigned int ntxqs_per_lif; + unsigned int nrxqs_per_lif; + DECLARE_BITMAP(lifbits, IONIC_LIFS_MAX); + unsigned int nintrs; + DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); + struct work_struct nb_work; + struct notifier_block nb; +}; + +struct ionic_admin_ctx { + struct completion work; + union ionic_adminq_cmd cmd; + union ionic_adminq_comp comp; +}; + +int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, + ionic_cq_done_cb done_cb, void *done_arg); + +int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); +int ionic_set_dma_mask(struct ionic *ionic); +int ionic_setup(struct ionic *ionic); + +int ionic_identify(struct ionic *ionic); +int ionic_init(struct ionic *ionic); +int ionic_reset(struct ionic *ionic); + +int ionic_port_identify(struct ionic *ionic); +int ionic_port_init(struct ionic *ionic); +int ionic_port_reset(struct ionic *ionic); + +#endif /* _IONIC_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus.h b/drivers/net/ethernet/pensando/ionic/ionic_bus.h new file mode 100644 index 000000000000..2f4d08c64910 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_BUS_H_ +#define _IONIC_BUS_H_ + +int ionic_bus_get_irq(struct ionic *ionic, unsigned int num); +const char *ionic_bus_info(struct ionic *ionic); +int ionic_bus_alloc_irq_vectors(struct ionic *ionic, unsigned int nintrs); +void ionic_bus_free_irq_vectors(struct ionic *ionic); +int ionic_bus_register_driver(void); +void ionic_bus_unregister_driver(void); +void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num); +void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page); + +#endif /* _IONIC_BUS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c new file mode 100644 index 000000000000..9a9ab8cb2cb3 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/pci.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +/* Supported devices */ +static const struct pci_device_id ionic_id_table[] = { + { PCI_VDEVICE(PENSANDO, PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF) }, + { PCI_VDEVICE(PENSANDO, PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF) }, + { 0, } /* end of table */ +}; +MODULE_DEVICE_TABLE(pci, ionic_id_table); + +int ionic_bus_get_irq(struct ionic *ionic, unsigned int num) +{ + return pci_irq_vector(ionic->pdev, num); +} + +const char *ionic_bus_info(struct ionic *ionic) +{ + return pci_name(ionic->pdev); +} + +int ionic_bus_alloc_irq_vectors(struct ionic *ionic, unsigned int nintrs) +{ + return pci_alloc_irq_vectors(ionic->pdev, nintrs, nintrs, + PCI_IRQ_MSIX); +} + +void ionic_bus_free_irq_vectors(struct ionic *ionic) +{ + pci_free_irq_vectors(ionic->pdev); +} + +static int ionic_map_bars(struct ionic *ionic) +{ + struct pci_dev *pdev = ionic->pdev; + struct device *dev = ionic->dev; + struct ionic_dev_bar *bars; + unsigned int i, j; + + bars = ionic->bars; + ionic->num_bars = 0; + + for (i = 0, j = 0; i < IONIC_BARS_MAX; i++) { + if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM)) + continue; + bars[j].len = pci_resource_len(pdev, i); + + /* only map the whole bar 0 */ + if (j > 0) { + bars[j].vaddr = NULL; + } else { + bars[j].vaddr = pci_iomap(pdev, i, bars[j].len); + if (!bars[j].vaddr) { + dev_err(dev, + "Cannot memory-map BAR %d, aborting\n", + i); + return -ENODEV; + } + } + + bars[j].bus_addr = pci_resource_start(pdev, i); + bars[j].res_index = i; + ionic->num_bars++; + j++; + } + + return 0; +} + +static void ionic_unmap_bars(struct ionic *ionic) +{ + struct ionic_dev_bar *bars = ionic->bars; + unsigned int i; + + for (i = 0; i < IONIC_BARS_MAX; i++) { + if (bars[i].vaddr) { + iounmap(bars[i].vaddr); + bars[i].bus_addr = 0; + bars[i].vaddr = NULL; + bars[i].len = 0; + } + } +} + +void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num) +{ + return pci_iomap_range(ionic->pdev, + ionic->bars[IONIC_PCI_BAR_DBELL].res_index, + (u64)page_num << PAGE_SHIFT, PAGE_SIZE); +} + +void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page) +{ + iounmap(page); +} + +static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct ionic *ionic; + int err; + + ionic = ionic_devlink_alloc(dev); + if (!ionic) + return -ENOMEM; + + ionic->pdev = pdev; + ionic->dev = dev; + pci_set_drvdata(pdev, ionic); + mutex_init(&ionic->dev_cmd_lock); + + /* Query system for DMA addressing limitation for the device. */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(IONIC_ADDR_LEN)); + if (err) { + dev_err(dev, "Unable to obtain 64-bit DMA for consistent allocations, aborting. err=%d\n", + err); + goto err_out_clear_drvdata; + } + + ionic_debugfs_add_dev(ionic); + + /* Setup PCI device */ + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(dev, "Cannot enable PCI device: %d, aborting\n", err); + goto err_out_debugfs_del_dev; + } + + err = pci_request_regions(pdev, IONIC_DRV_NAME); + if (err) { + dev_err(dev, "Cannot request PCI regions: %d, aborting\n", err); + goto err_out_pci_disable_device; + } + + pci_set_master(pdev); + + err = ionic_map_bars(ionic); + if (err) + goto err_out_pci_clear_master; + + /* Configure the device */ + err = ionic_setup(ionic); + if (err) { + dev_err(dev, "Cannot setup device: %d, aborting\n", err); + goto err_out_unmap_bars; + } + + err = ionic_identify(ionic); + if (err) { + dev_err(dev, "Cannot identify device: %d, aborting\n", err); + goto err_out_teardown; + } + + err = ionic_init(ionic); + if (err) { + dev_err(dev, "Cannot init device: %d, aborting\n", err); + goto err_out_teardown; + } + + /* Configure the ports */ + err = ionic_port_identify(ionic); + if (err) { + dev_err(dev, "Cannot identify port: %d, aborting\n", err); + goto err_out_reset; + } + + err = ionic_port_init(ionic); + if (err) { + dev_err(dev, "Cannot init port: %d, aborting\n", err); + goto err_out_reset; + } + + /* Configure LIFs */ + err = ionic_lif_identify(ionic, IONIC_LIF_TYPE_CLASSIC, + &ionic->ident.lif); + if (err) { + dev_err(dev, "Cannot identify LIFs: %d, aborting\n", err); + goto err_out_port_reset; + } + + err = ionic_lifs_size(ionic); + if (err) { + dev_err(dev, "Cannot size LIFs: %d, aborting\n", err); + goto err_out_port_reset; + } + + err = ionic_lifs_alloc(ionic); + if (err) { + dev_err(dev, "Cannot allocate LIFs: %d, aborting\n", err); + goto err_out_free_irqs; + } + + err = ionic_lifs_init(ionic); + if (err) { + dev_err(dev, "Cannot init LIFs: %d, aborting\n", err); + goto err_out_free_lifs; + } + + err = ionic_lifs_register(ionic); + if (err) { + dev_err(dev, "Cannot register LIFs: %d, aborting\n", err); + goto err_out_deinit_lifs; + } + + err = ionic_devlink_register(ionic); + if (err) { + dev_err(dev, "Cannot register devlink: %d\n", err); + goto err_out_deregister_lifs; + } + + return 0; + +err_out_deregister_lifs: + ionic_lifs_unregister(ionic); +err_out_deinit_lifs: + ionic_lifs_deinit(ionic); +err_out_free_lifs: + ionic_lifs_free(ionic); +err_out_free_irqs: + ionic_bus_free_irq_vectors(ionic); +err_out_port_reset: + ionic_port_reset(ionic); +err_out_reset: + ionic_reset(ionic); +err_out_teardown: + ionic_dev_teardown(ionic); +err_out_unmap_bars: + ionic_unmap_bars(ionic); + pci_release_regions(pdev); +err_out_pci_clear_master: + pci_clear_master(pdev); +err_out_pci_disable_device: + pci_disable_device(pdev); +err_out_debugfs_del_dev: + ionic_debugfs_del_dev(ionic); +err_out_clear_drvdata: + mutex_destroy(&ionic->dev_cmd_lock); + ionic_devlink_free(ionic); + + return err; +} + +static void ionic_remove(struct pci_dev *pdev) +{ + struct ionic *ionic = pci_get_drvdata(pdev); + + if (!ionic) + return; + + ionic_devlink_unregister(ionic); + ionic_lifs_unregister(ionic); + ionic_lifs_deinit(ionic); + ionic_lifs_free(ionic); + ionic_bus_free_irq_vectors(ionic); + ionic_port_reset(ionic); + ionic_reset(ionic); + ionic_dev_teardown(ionic); + ionic_unmap_bars(ionic); + pci_release_regions(pdev); + pci_clear_master(pdev); + pci_disable_device(pdev); + ionic_debugfs_del_dev(ionic); + mutex_destroy(&ionic->dev_cmd_lock); + ionic_devlink_free(ionic); +} + +static struct pci_driver ionic_driver = { + .name = IONIC_DRV_NAME, + .id_table = ionic_id_table, + .probe = ionic_probe, + .remove = ionic_remove, +}; + +int ionic_bus_register_driver(void) +{ + return pci_register_driver(&ionic_driver); +} + +void ionic_bus_unregister_driver(void) +{ + pci_unregister_driver(&ionic_driver); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c new file mode 100644 index 000000000000..7afc4a365b75 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/pci.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +#ifdef CONFIG_DEBUG_FS + +static struct dentry *ionic_dir; + +void ionic_debugfs_create(void) +{ + ionic_dir = debugfs_create_dir(IONIC_DRV_NAME, NULL); +} + +void ionic_debugfs_destroy(void) +{ + debugfs_remove_recursive(ionic_dir); +} + +void ionic_debugfs_add_dev(struct ionic *ionic) +{ + ionic->dentry = debugfs_create_dir(ionic_bus_info(ionic), ionic_dir); +} + +void ionic_debugfs_del_dev(struct ionic *ionic) +{ + debugfs_remove_recursive(ionic->dentry); + ionic->dentry = NULL; +} + +static int identity_show(struct seq_file *seq, void *v) +{ + struct ionic *ionic = seq->private; + struct ionic_identity *ident; + + ident = &ionic->ident; + + seq_printf(seq, "nlifs: %d\n", ident->dev.nlifs); + seq_printf(seq, "nintrs: %d\n", ident->dev.nintrs); + seq_printf(seq, "ndbpgs_per_lif: %d\n", ident->dev.ndbpgs_per_lif); + seq_printf(seq, "intr_coal_mult: %d\n", ident->dev.intr_coal_mult); + seq_printf(seq, "intr_coal_div: %d\n", ident->dev.intr_coal_div); + + seq_printf(seq, "max_ucast_filters: %d\n", ident->lif.eth.max_ucast_filters); + seq_printf(seq, "max_mcast_filters: %d\n", ident->lif.eth.max_mcast_filters); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(identity); + +void ionic_debugfs_add_ident(struct ionic *ionic) +{ + debugfs_create_file("identity", 0400, ionic->dentry, + ionic, &identity_fops) ? 0 : -EOPNOTSUPP; +} + +void ionic_debugfs_add_sizes(struct ionic *ionic) +{ + debugfs_create_u32("nlifs", 0400, ionic->dentry, + (u32 *)&ionic->ident.dev.nlifs); + debugfs_create_u32("nintrs", 0400, ionic->dentry, &ionic->nintrs); + + debugfs_create_u32("ntxqs_per_lif", 0400, ionic->dentry, + (u32 *)&ionic->ident.lif.eth.config.queue_count[IONIC_QTYPE_TXQ]); + debugfs_create_u32("nrxqs_per_lif", 0400, ionic->dentry, + (u32 *)&ionic->ident.lif.eth.config.queue_count[IONIC_QTYPE_RXQ]); +} + +static int q_tail_show(struct seq_file *seq, void *v) +{ + struct ionic_queue *q = seq->private; + + seq_printf(seq, "%d\n", q->tail->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(q_tail); + +static int q_head_show(struct seq_file *seq, void *v) +{ + struct ionic_queue *q = seq->private; + + seq_printf(seq, "%d\n", q->head->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(q_head); + +static int cq_tail_show(struct seq_file *seq, void *v) +{ + struct ionic_cq *cq = seq->private; + + seq_printf(seq, "%d\n", cq->tail->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(cq_tail); + +static const struct debugfs_reg32 intr_ctrl_regs[] = { + { .name = "coal_init", .offset = 0, }, + { .name = "mask", .offset = 4, }, + { .name = "credits", .offset = 8, }, + { .name = "mask_on_assert", .offset = 12, }, + { .name = "coal_timer", .offset = 16, }, +}; + +void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct dentry *q_dentry, *cq_dentry, *intr_dentry, *stats_dentry; + struct ionic_dev *idev = &lif->ionic->idev; + struct debugfs_regset32 *intr_ctrl_regset; + struct ionic_intr_info *intr = &qcq->intr; + struct debugfs_blob_wrapper *desc_blob; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + + qcq->dentry = debugfs_create_dir(q->name, lif->dentry); + + debugfs_create_x32("total_size", 0400, qcq->dentry, &qcq->total_size); + debugfs_create_x64("base_pa", 0400, qcq->dentry, &qcq->base_pa); + + q_dentry = debugfs_create_dir("q", qcq->dentry); + + debugfs_create_u32("index", 0400, q_dentry, &q->index); + debugfs_create_x64("base_pa", 0400, q_dentry, &q->base_pa); + if (qcq->flags & IONIC_QCQ_F_SG) { + debugfs_create_x64("sg_base_pa", 0400, q_dentry, + &q->sg_base_pa); + debugfs_create_u32("sg_desc_size", 0400, q_dentry, + &q->sg_desc_size); + } + debugfs_create_u32("num_descs", 0400, q_dentry, &q->num_descs); + debugfs_create_u32("desc_size", 0400, q_dentry, &q->desc_size); + debugfs_create_u32("pid", 0400, q_dentry, &q->pid); + debugfs_create_u32("qid", 0400, q_dentry, &q->hw_index); + debugfs_create_u32("qtype", 0400, q_dentry, &q->hw_type); + debugfs_create_u64("drop", 0400, q_dentry, &q->drop); + debugfs_create_u64("stop", 0400, q_dentry, &q->stop); + debugfs_create_u64("wake", 0400, q_dentry, &q->wake); + + debugfs_create_file("tail", 0400, q_dentry, q, &q_tail_fops); + debugfs_create_file("head", 0400, q_dentry, q, &q_head_fops); + + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = q->base; + desc_blob->size = (unsigned long)q->num_descs * q->desc_size; + debugfs_create_blob("desc_blob", 0400, q_dentry, desc_blob); + + if (qcq->flags & IONIC_QCQ_F_SG) { + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = q->sg_base; + desc_blob->size = (unsigned long)q->num_descs * q->sg_desc_size; + debugfs_create_blob("sg_desc_blob", 0400, q_dentry, + desc_blob); + } + + cq_dentry = debugfs_create_dir("cq", qcq->dentry); + + debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa); + debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs); + debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size); + debugfs_create_u8("done_color", 0400, cq_dentry, + (u8 *)&cq->done_color); + + debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops); + + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = cq->base; + desc_blob->size = (unsigned long)cq->num_descs * cq->desc_size; + debugfs_create_blob("desc_blob", 0400, cq_dentry, desc_blob); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + intr_dentry = debugfs_create_dir("intr", qcq->dentry); + + debugfs_create_u32("index", 0400, intr_dentry, + &intr->index); + debugfs_create_u32("vector", 0400, intr_dentry, + &intr->vector); + + intr_ctrl_regset = devm_kzalloc(dev, sizeof(*intr_ctrl_regset), + GFP_KERNEL); + if (!intr_ctrl_regset) + return; + intr_ctrl_regset->regs = intr_ctrl_regs; + intr_ctrl_regset->nregs = ARRAY_SIZE(intr_ctrl_regs); + intr_ctrl_regset->base = &idev->intr_ctrl[intr->index]; + + debugfs_create_regset32("intr_ctrl", 0400, intr_dentry, + intr_ctrl_regset); + } + + if (qcq->flags & IONIC_QCQ_F_NOTIFYQ) { + stats_dentry = debugfs_create_dir("notifyblock", qcq->dentry); + + debugfs_create_u64("eid", 0400, stats_dentry, + (u64 *)&lif->info->status.eid); + debugfs_create_u16("link_status", 0400, stats_dentry, + (u16 *)&lif->info->status.link_status); + debugfs_create_u32("link_speed", 0400, stats_dentry, + (u32 *)&lif->info->status.link_speed); + debugfs_create_u16("link_down_count", 0400, stats_dentry, + (u16 *)&lif->info->status.link_down_count); + } +} + +static int netdev_show(struct seq_file *seq, void *v) +{ + struct net_device *netdev = seq->private; + + seq_printf(seq, "%s\n", netdev->name); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(netdev); + +void ionic_debugfs_add_lif(struct ionic_lif *lif) +{ + lif->dentry = debugfs_create_dir(lif->name, lif->ionic->dentry); + debugfs_create_file("netdev", 0400, lif->dentry, + lif->netdev, &netdev_fops); +} + +void ionic_debugfs_del_lif(struct ionic_lif *lif) +{ + debugfs_remove_recursive(lif->dentry); + lif->dentry = NULL; +} + +void ionic_debugfs_del_qcq(struct ionic_qcq *qcq) +{ + debugfs_remove_recursive(qcq->dentry); + qcq->dentry = NULL; +} + +#endif diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h new file mode 100644 index 000000000000..c44ebde170b6 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEBUGFS_H_ +#define _IONIC_DEBUGFS_H_ + +#include <linux/debugfs.h> + +#ifdef CONFIG_DEBUG_FS + +void ionic_debugfs_create(void); +void ionic_debugfs_destroy(void); +void ionic_debugfs_add_dev(struct ionic *ionic); +void ionic_debugfs_del_dev(struct ionic *ionic); +void ionic_debugfs_add_ident(struct ionic *ionic); +void ionic_debugfs_add_sizes(struct ionic *ionic); +void ionic_debugfs_add_lif(struct ionic_lif *lif); +void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq); +void ionic_debugfs_del_lif(struct ionic_lif *lif); +void ionic_debugfs_del_qcq(struct ionic_qcq *qcq); +#else +static inline void ionic_debugfs_create(void) { } +static inline void ionic_debugfs_destroy(void) { } +static inline void ionic_debugfs_add_dev(struct ionic *ionic) { } +static inline void ionic_debugfs_del_dev(struct ionic *ionic) { } +static inline void ionic_debugfs_add_ident(struct ionic *ionic) { } +static inline void ionic_debugfs_add_sizes(struct ionic *ionic) { } +static inline void ionic_debugfs_add_lif(struct ionic_lif *lif) { } +static inline void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) { } +static inline void ionic_debugfs_del_lif(struct ionic_lif *lif) { } +static inline void ionic_debugfs_del_qcq(struct ionic_qcq *qcq) { } +#endif + +#endif /* _IONIC_DEBUGFS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c new file mode 100644 index 000000000000..d168a6435322 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/etherdevice.h> +#include "ionic.h" +#include "ionic_dev.h" +#include "ionic_lif.h" + +void ionic_init_devinfo(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + + idev->dev_info.asic_type = ioread8(&idev->dev_info_regs->asic_type); + idev->dev_info.asic_rev = ioread8(&idev->dev_info_regs->asic_rev); + + memcpy_fromio(idev->dev_info.fw_version, + idev->dev_info_regs->fw_version, + IONIC_DEVINFO_FWVERS_BUFLEN); + + memcpy_fromio(idev->dev_info.serial_num, + idev->dev_info_regs->serial_num, + IONIC_DEVINFO_SERIAL_BUFLEN); + + idev->dev_info.fw_version[IONIC_DEVINFO_FWVERS_BUFLEN] = 0; + idev->dev_info.serial_num[IONIC_DEVINFO_SERIAL_BUFLEN] = 0; + + dev_dbg(ionic->dev, "fw_version %s\n", idev->dev_info.fw_version); +} + +int ionic_dev_setup(struct ionic *ionic) +{ + struct ionic_dev_bar *bar = ionic->bars; + unsigned int num_bars = ionic->num_bars; + struct ionic_dev *idev = &ionic->idev; + struct device *dev = ionic->dev; + u32 sig; + + /* BAR0: dev_cmd and interrupts */ + if (num_bars < 1) { + dev_err(dev, "No bars found, aborting\n"); + return -EFAULT; + } + + if (bar->len < IONIC_BAR0_SIZE) { + dev_err(dev, "Resource bar size %lu too small, aborting\n", + bar->len); + return -EFAULT; + } + + idev->dev_info_regs = bar->vaddr + IONIC_BAR0_DEV_INFO_REGS_OFFSET; + idev->dev_cmd_regs = bar->vaddr + IONIC_BAR0_DEV_CMD_REGS_OFFSET; + idev->intr_status = bar->vaddr + IONIC_BAR0_INTR_STATUS_OFFSET; + idev->intr_ctrl = bar->vaddr + IONIC_BAR0_INTR_CTRL_OFFSET; + + sig = ioread32(&idev->dev_info_regs->signature); + if (sig != IONIC_DEV_INFO_SIGNATURE) { + dev_err(dev, "Incompatible firmware signature %x", sig); + return -EFAULT; + } + + ionic_init_devinfo(ionic); + + /* BAR1: doorbells */ + bar++; + if (num_bars < 2) { + dev_err(dev, "Doorbell bar missing, aborting\n"); + return -EFAULT; + } + + idev->db_pages = bar->vaddr; + idev->phy_db_pages = bar->bus_addr; + + return 0; +} + +void ionic_dev_teardown(struct ionic *ionic) +{ + /* place holder */ +} + +/* Devcmd Interface */ +u8 ionic_dev_cmd_status(struct ionic_dev *idev) +{ + return ioread8(&idev->dev_cmd_regs->comp.comp.status); +} + +bool ionic_dev_cmd_done(struct ionic_dev *idev) +{ + return ioread32(&idev->dev_cmd_regs->done) & IONIC_DEV_CMD_DONE; +} + +void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp) +{ + memcpy_fromio(comp, &idev->dev_cmd_regs->comp, sizeof(*comp)); +} + +void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd) +{ + memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd)); + iowrite32(0, &idev->dev_cmd_regs->done); + iowrite32(1, &idev->dev_cmd_regs->doorbell); +} + +/* Device commands */ +void ionic_dev_cmd_identify(struct ionic_dev *idev, u8 ver) +{ + union ionic_dev_cmd cmd = { + .identify.opcode = IONIC_CMD_IDENTIFY, + .identify.ver = ver, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_init(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .init.opcode = IONIC_CMD_INIT, + .init.type = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_reset(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .reset.opcode = IONIC_CMD_RESET, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +/* Port commands */ +void ionic_dev_cmd_port_identify(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_init.opcode = IONIC_CMD_PORT_IDENTIFY, + .port_init.index = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_init(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_init.opcode = IONIC_CMD_PORT_INIT, + .port_init.index = 0, + .port_init.info_pa = cpu_to_le64(idev->port_info_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_reset(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_reset.opcode = IONIC_CMD_PORT_RESET, + .port_reset.index = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_STATE, + .port_setattr.state = state, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_SPEED, + .port_setattr.speed = cpu_to_le32(speed), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_AUTONEG, + .port_setattr.an_enable = an_enable, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_FEC, + .port_setattr.fec_type = fec_type, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_PAUSE, + .port_setattr.pause_type = pause_type, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +/* LIF commands */ +void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver) +{ + union ionic_dev_cmd cmd = { + .lif_identify.opcode = IONIC_CMD_LIF_IDENTIFY, + .lif_identify.type = type, + .lif_identify.ver = ver, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index, + dma_addr_t info_pa) +{ + union ionic_dev_cmd cmd = { + .lif_init.opcode = IONIC_CMD_LIF_INIT, + .lif_init.index = cpu_to_le16(lif_index), + .lif_init.info_pa = cpu_to_le64(info_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_lif_reset(struct ionic_dev *idev, u16 lif_index) +{ + union ionic_dev_cmd cmd = { + .lif_init.opcode = IONIC_CMD_LIF_RESET, + .lif_init.index = cpu_to_le16(lif_index), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_adminq_init(struct ionic_dev *idev, struct ionic_qcq *qcq, + u16 lif_index, u16 intr_index) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + + union ionic_dev_cmd cmd = { + .q_init.opcode = IONIC_CMD_Q_INIT, + .q_init.lif_index = cpu_to_le16(lif_index), + .q_init.type = q->type, + .q_init.index = cpu_to_le32(q->index), + .q_init.flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_ENA), + .q_init.pid = cpu_to_le16(q->pid), + .q_init.intr_index = cpu_to_le16(intr_index), + .q_init.ring_size = ilog2(q->num_descs), + .q_init.ring_base = cpu_to_le64(q->base_pa), + .q_init.cq_ring_base = cpu_to_le64(cq->base_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +int ionic_db_page_num(struct ionic_lif *lif, int pid) +{ + return (lif->hw_index * lif->dbid_count) + pid; +} + +int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, + struct ionic_intr_info *intr, + unsigned int num_descs, size_t desc_size) +{ + struct ionic_cq_info *cur; + unsigned int ring_size; + unsigned int i; + + if (desc_size == 0 || !is_power_of_2(num_descs)) + return -EINVAL; + + ring_size = ilog2(num_descs); + if (ring_size < 2 || ring_size > 16) + return -EINVAL; + + cq->lif = lif; + cq->bound_intr = intr; + cq->num_descs = num_descs; + cq->desc_size = desc_size; + cq->tail = cq->info; + cq->done_color = 1; + + cur = cq->info; + + for (i = 0; i < num_descs; i++) { + if (i + 1 == num_descs) { + cur->next = cq->info; + cur->last = true; + } else { + cur->next = cur + 1; + } + cur->index = i; + cur++; + } + + return 0; +} + +void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa) +{ + struct ionic_cq_info *cur; + unsigned int i; + + cq->base = base; + cq->base_pa = base_pa; + + for (i = 0, cur = cq->info; i < cq->num_descs; i++, cur++) + cur->cq_desc = base + (i * cq->desc_size); +} + +void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q) +{ + cq->bound_q = q; +} + +unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, + ionic_cq_cb cb, ionic_cq_done_cb done_cb, + void *done_arg) +{ + unsigned int work_done = 0; + + if (work_to_do == 0) + return 0; + + while (cb(cq, cq->tail)) { + if (cq->tail->last) + cq->done_color = !cq->done_color; + cq->tail = cq->tail->next; + DEBUG_STATS_CQE_CNT(cq); + + if (++work_done >= work_to_do) + break; + } + + if (work_done && done_cb) + done_cb(done_arg); + + return work_done; +} + +int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, + struct ionic_queue *q, unsigned int index, const char *name, + unsigned int num_descs, size_t desc_size, + size_t sg_desc_size, unsigned int pid) +{ + struct ionic_desc_info *cur; + unsigned int ring_size; + unsigned int i; + + if (desc_size == 0 || !is_power_of_2(num_descs)) + return -EINVAL; + + ring_size = ilog2(num_descs); + if (ring_size < 2 || ring_size > 16) + return -EINVAL; + + q->lif = lif; + q->idev = idev; + q->index = index; + q->num_descs = num_descs; + q->desc_size = desc_size; + q->sg_desc_size = sg_desc_size; + q->tail = q->info; + q->head = q->tail; + q->pid = pid; + + snprintf(q->name, sizeof(q->name), "L%d-%s%u", lif->index, name, index); + + cur = q->info; + + for (i = 0; i < num_descs; i++) { + if (i + 1 == num_descs) + cur->next = q->info; + else + cur->next = cur + 1; + cur->index = i; + cur->left = num_descs - i; + cur++; + } + + return 0; +} + +void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) +{ + struct ionic_desc_info *cur; + unsigned int i; + + q->base = base; + q->base_pa = base_pa; + + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + cur->desc = base + (i * q->desc_size); +} + +void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) +{ + struct ionic_desc_info *cur; + unsigned int i; + + q->sg_base = base; + q->sg_base_pa = base_pa; + + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + cur->sg_desc = base + (i * q->sg_desc_size); +} + +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, + void *cb_arg) +{ + struct device *dev = q->lif->ionic->dev; + struct ionic_lif *lif = q->lif; + + q->head->cb = cb; + q->head->cb_arg = cb_arg; + q->head = q->head->next; + + dev_dbg(dev, "lif=%d qname=%s qid=%d qtype=%d p_index=%d ringdb=%d\n", + q->lif->index, q->name, q->hw_type, q->hw_index, + q->head->index, ring_doorbell); + + if (ring_doorbell) + ionic_dbell_ring(lif->kern_dbpage, q->hw_type, + q->dbval | q->head->index); +} + +static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) +{ + unsigned int mask, tail, head; + + mask = q->num_descs - 1; + tail = q->tail->index; + head = q->head->index; + + return ((pos - tail) & mask) < ((head - tail) & mask); +} + +void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, + unsigned int stop_index) +{ + struct ionic_desc_info *desc_info; + ionic_desc_cb cb; + void *cb_arg; + + /* check for empty queue */ + if (q->tail->index == q->head->index) + return; + + /* stop index must be for a descriptor that is not yet completed */ + if (unlikely(!ionic_q_is_posted(q, stop_index))) + dev_err(q->lif->ionic->dev, + "ionic stop is not posted %s stop %u tail %u head %u\n", + q->name, stop_index, q->tail->index, q->head->index); + + do { + desc_info = q->tail; + q->tail = desc_info->next; + + cb = desc_info->cb; + cb_arg = desc_info->cb_arg; + + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + + if (cb) + cb(q, desc_info, cq_info, cb_arg); + } while (desc_info->index != stop_index); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h new file mode 100644 index 000000000000..9610aeb7d5f4 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -0,0 +1,299 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEV_H_ +#define _IONIC_DEV_H_ + +#include <linux/mutex.h> +#include <linux/workqueue.h> + +#include "ionic_if.h" +#include "ionic_regs.h" + +#define IONIC_MIN_MTU ETH_MIN_MTU +#define IONIC_MAX_MTU 9194 +#define IONIC_MAX_TXRX_DESC 16384 +#define IONIC_MIN_TXRX_DESC 16 +#define IONIC_DEF_TXRX_DESC 4096 +#define IONIC_LIFS_MAX 1024 +#define IONIC_ITR_COAL_USEC_DEFAULT 64 + +#define IONIC_DEV_CMD_REG_VERSION 1 +#define IONIC_DEV_INFO_REG_COUNT 32 +#define IONIC_DEV_CMD_REG_COUNT 32 + +struct ionic_dev_bar { + void __iomem *vaddr; + phys_addr_t bus_addr; + unsigned long len; + int res_index; +}; + +/* Registers */ +static_assert(sizeof(struct ionic_intr) == 32); + +static_assert(sizeof(struct ionic_doorbell) == 8); +static_assert(sizeof(struct ionic_intr_status) == 8); +static_assert(sizeof(union ionic_dev_regs) == 4096); +static_assert(sizeof(union ionic_dev_info_regs) == 2048); +static_assert(sizeof(union ionic_dev_cmd_regs) == 2048); +static_assert(sizeof(struct ionic_lif_stats) == 1024); + +static_assert(sizeof(struct ionic_admin_cmd) == 64); +static_assert(sizeof(struct ionic_admin_comp) == 16); +static_assert(sizeof(struct ionic_nop_cmd) == 64); +static_assert(sizeof(struct ionic_nop_comp) == 16); + +/* Device commands */ +static_assert(sizeof(struct ionic_dev_identify_cmd) == 64); +static_assert(sizeof(struct ionic_dev_identify_comp) == 16); +static_assert(sizeof(struct ionic_dev_init_cmd) == 64); +static_assert(sizeof(struct ionic_dev_init_comp) == 16); +static_assert(sizeof(struct ionic_dev_reset_cmd) == 64); +static_assert(sizeof(struct ionic_dev_reset_comp) == 16); +static_assert(sizeof(struct ionic_dev_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_dev_getattr_comp) == 16); +static_assert(sizeof(struct ionic_dev_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_dev_setattr_comp) == 16); + +/* Port commands */ +static_assert(sizeof(struct ionic_port_identify_cmd) == 64); +static_assert(sizeof(struct ionic_port_identify_comp) == 16); +static_assert(sizeof(struct ionic_port_init_cmd) == 64); +static_assert(sizeof(struct ionic_port_init_comp) == 16); +static_assert(sizeof(struct ionic_port_reset_cmd) == 64); +static_assert(sizeof(struct ionic_port_reset_comp) == 16); +static_assert(sizeof(struct ionic_port_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_port_getattr_comp) == 16); +static_assert(sizeof(struct ionic_port_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_port_setattr_comp) == 16); + +/* LIF commands */ +static_assert(sizeof(struct ionic_lif_init_cmd) == 64); +static_assert(sizeof(struct ionic_lif_init_comp) == 16); +static_assert(sizeof(struct ionic_lif_reset_cmd) == 64); +static_assert(sizeof(ionic_lif_reset_comp) == 16); +static_assert(sizeof(struct ionic_lif_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_lif_getattr_comp) == 16); +static_assert(sizeof(struct ionic_lif_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_lif_setattr_comp) == 16); + +static_assert(sizeof(struct ionic_q_init_cmd) == 64); +static_assert(sizeof(struct ionic_q_init_comp) == 16); +static_assert(sizeof(struct ionic_q_control_cmd) == 64); +static_assert(sizeof(ionic_q_control_comp) == 16); + +static_assert(sizeof(struct ionic_rx_mode_set_cmd) == 64); +static_assert(sizeof(ionic_rx_mode_set_comp) == 16); +static_assert(sizeof(struct ionic_rx_filter_add_cmd) == 64); +static_assert(sizeof(struct ionic_rx_filter_add_comp) == 16); +static_assert(sizeof(struct ionic_rx_filter_del_cmd) == 64); +static_assert(sizeof(ionic_rx_filter_del_comp) == 16); + +/* RDMA commands */ +static_assert(sizeof(struct ionic_rdma_reset_cmd) == 64); +static_assert(sizeof(struct ionic_rdma_queue_cmd) == 64); + +/* Events */ +static_assert(sizeof(struct ionic_notifyq_cmd) == 4); +static_assert(sizeof(union ionic_notifyq_comp) == 64); +static_assert(sizeof(struct ionic_notifyq_event) == 64); +static_assert(sizeof(struct ionic_link_change_event) == 64); +static_assert(sizeof(struct ionic_reset_event) == 64); +static_assert(sizeof(struct ionic_heartbeat_event) == 64); +static_assert(sizeof(struct ionic_log_event) == 64); + +/* I/O */ +static_assert(sizeof(struct ionic_txq_desc) == 16); +static_assert(sizeof(struct ionic_txq_sg_desc) == 128); +static_assert(sizeof(struct ionic_txq_comp) == 16); + +static_assert(sizeof(struct ionic_rxq_desc) == 16); +static_assert(sizeof(struct ionic_rxq_sg_desc) == 128); +static_assert(sizeof(struct ionic_rxq_comp) == 16); + +struct ionic_devinfo { + u8 asic_type; + u8 asic_rev; + char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN + 1]; + char serial_num[IONIC_DEVINFO_SERIAL_BUFLEN + 1]; +}; + +struct ionic_dev { + union ionic_dev_info_regs __iomem *dev_info_regs; + union ionic_dev_cmd_regs __iomem *dev_cmd_regs; + + u64 __iomem *db_pages; + dma_addr_t phy_db_pages; + + struct ionic_intr __iomem *intr_ctrl; + u64 __iomem *intr_status; + + u32 port_info_sz; + struct ionic_port_info *port_info; + dma_addr_t port_info_pa; + + struct ionic_devinfo dev_info; +}; + +struct ionic_cq_info { + void *cq_desc; + struct ionic_cq_info *next; + unsigned int index; + bool last; +}; + +struct ionic_queue; +struct ionic_qcq; +struct ionic_desc_info; + +typedef void (*ionic_desc_cb)(struct ionic_queue *q, + struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg); + +struct ionic_desc_info { + void *desc; + void *sg_desc; + struct ionic_desc_info *next; + unsigned int index; + unsigned int left; + ionic_desc_cb cb; + void *cb_arg; +}; + +#define QUEUE_NAME_MAX_SZ 32 + +struct ionic_queue { + u64 dbell_count; + u64 drop; + u64 stop; + u64 wake; + struct ionic_lif *lif; + struct ionic_desc_info *info; + struct ionic_desc_info *tail; + struct ionic_desc_info *head; + struct ionic_dev *idev; + unsigned int index; + unsigned int type; + unsigned int hw_index; + unsigned int hw_type; + u64 dbval; + void *base; + void *sg_base; + dma_addr_t base_pa; + dma_addr_t sg_base_pa; + unsigned int num_descs; + unsigned int desc_size; + unsigned int sg_desc_size; + unsigned int pid; + char name[QUEUE_NAME_MAX_SZ]; +}; + +#define INTR_INDEX_NOT_ASSIGNED -1 +#define INTR_NAME_MAX_SZ 32 + +struct ionic_intr_info { + char name[INTR_NAME_MAX_SZ]; + unsigned int index; + unsigned int vector; + u64 rearm_count; + unsigned int cpu; + cpumask_t affinity_mask; +}; + +struct ionic_cq { + void *base; + dma_addr_t base_pa; + struct ionic_lif *lif; + struct ionic_cq_info *info; + struct ionic_cq_info *tail; + struct ionic_queue *bound_q; + struct ionic_intr_info *bound_intr; + bool done_color; + unsigned int num_descs; + u64 compl_count; + unsigned int desc_size; +}; + +struct ionic; + +static inline void ionic_intr_init(struct ionic_dev *idev, + struct ionic_intr_info *intr, + unsigned long index) +{ + ionic_intr_clean(idev->intr_ctrl, index); + intr->index = index; +} + +static inline unsigned int ionic_q_space_avail(struct ionic_queue *q) +{ + unsigned int avail = q->tail->index; + + if (q->head->index >= avail) + avail += q->head->left - 1; + else + avail -= q->head->index + 1; + + return avail; +} + +static inline bool ionic_q_has_space(struct ionic_queue *q, unsigned int want) +{ + return ionic_q_space_avail(q) >= want; +} + +void ionic_init_devinfo(struct ionic *ionic); +int ionic_dev_setup(struct ionic *ionic); +void ionic_dev_teardown(struct ionic *ionic); + +void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd); +u8 ionic_dev_cmd_status(struct ionic_dev *idev); +bool ionic_dev_cmd_done(struct ionic_dev *idev); +void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp); + +void ionic_dev_cmd_identify(struct ionic_dev *idev, u8 ver); +void ionic_dev_cmd_init(struct ionic_dev *idev); +void ionic_dev_cmd_reset(struct ionic_dev *idev); + +void ionic_dev_cmd_port_identify(struct ionic_dev *idev); +void ionic_dev_cmd_port_init(struct ionic_dev *idev); +void ionic_dev_cmd_port_reset(struct ionic_dev *idev); +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state); +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed); +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable); +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type); +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type); + +void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver); +void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index, + dma_addr_t addr); +void ionic_dev_cmd_lif_reset(struct ionic_dev *idev, u16 lif_index); +void ionic_dev_cmd_adminq_init(struct ionic_dev *idev, struct ionic_qcq *qcq, + u16 lif_index, u16 intr_index); + +int ionic_db_page_num(struct ionic_lif *lif, int pid); + +int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, + struct ionic_intr_info *intr, + unsigned int num_descs, size_t desc_size); +void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa); +void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q); +typedef bool (*ionic_cq_cb)(struct ionic_cq *cq, struct ionic_cq_info *cq_info); +typedef void (*ionic_cq_done_cb)(void *done_arg); +unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, + ionic_cq_cb cb, ionic_cq_done_cb done_cb, + void *done_arg); + +int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, + struct ionic_queue *q, unsigned int index, const char *name, + unsigned int num_descs, size_t desc_size, + size_t sg_desc_size, unsigned int pid); +void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); +void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, + void *cb_arg); +void ionic_q_rewind(struct ionic_queue *q, struct ionic_desc_info *start); +void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, + unsigned int stop_index); + +#endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c new file mode 100644 index 000000000000..af1647afa4e8 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_devlink.h" + +static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct ionic *ionic = devlink_priv(dl); + struct ionic_dev *idev = &ionic->idev; + char buf[16]; + int err = 0; + + err = devlink_info_driver_name_put(req, IONIC_DRV_NAME); + if (err) + goto info_out; + + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, + idev->dev_info.fw_version); + if (err) + goto info_out; + + snprintf(buf, sizeof(buf), "0x%x", idev->dev_info.asic_type); + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, + buf); + if (err) + goto info_out; + + snprintf(buf, sizeof(buf), "0x%x", idev->dev_info.asic_rev); + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_REV, + buf); + if (err) + goto info_out; + + err = devlink_info_serial_number_put(req, idev->dev_info.serial_num); + +info_out: + return err; +} + +static const struct devlink_ops ionic_dl_ops = { + .info_get = ionic_dl_info_get, +}; + +struct ionic *ionic_devlink_alloc(struct device *dev) +{ + struct devlink *dl; + + dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic)); + + return devlink_priv(dl); +} + +void ionic_devlink_free(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + + devlink_free(dl); +} + +int ionic_devlink_register(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + int err; + + err = devlink_register(dl, ionic->dev); + if (err) { + dev_warn(ionic->dev, "devlink_register failed: %d\n", err); + return err; + } + + devlink_port_attrs_set(&ionic->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, + 0, false, 0, NULL, 0); + err = devlink_port_register(dl, &ionic->dl_port, 0); + if (err) + dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); + else + devlink_port_type_eth_set(&ionic->dl_port, + ionic->master_lif->netdev); + + return err; +} + +void ionic_devlink_unregister(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + + devlink_port_unregister(&ionic->dl_port); + devlink_unregister(dl); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.h b/drivers/net/ethernet/pensando/ionic/ionic_devlink.h new file mode 100644 index 000000000000..0690172fc57a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEVLINK_H_ +#define _IONIC_DEVLINK_H_ + +#include <net/devlink.h> + +struct ionic *ionic_devlink_alloc(struct device *dev); +void ionic_devlink_free(struct ionic *ionic); +int ionic_devlink_register(struct ionic *ionic); +void ionic_devlink_unregister(struct ionic *ionic); + +#endif /* _IONIC_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c new file mode 100644 index 000000000000..7d10265f782a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -0,0 +1,779 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_ethtool.h" +#include "ionic_stats.h" + +static const char ionic_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define PRIV_F_SW_DBG_STATS BIT(0) + "sw-dbg-stats", +}; +#define PRIV_FLAGS_COUNT ARRAY_SIZE(ionic_priv_flags_strings) + +static void ionic_get_stats_strings(struct ionic_lif *lif, u8 *buf) +{ + u32 i; + + for (i = 0; i < ionic_num_stats_grps; i++) + ionic_stats_groups[i].get_strings(lif, &buf); +} + +static void ionic_get_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *buf) +{ + struct ionic_lif *lif; + u32 i; + + lif = netdev_priv(netdev); + + memset(buf, 0, stats->n_stats * sizeof(*buf)); + for (i = 0; i < ionic_num_stats_grps; i++) + ionic_stats_groups[i].get_values(lif, &buf); +} + +static int ionic_get_stats_count(struct ionic_lif *lif) +{ + int i, num_stats = 0; + + for (i = 0; i < ionic_num_stats_grps; i++) + num_stats += ionic_stats_groups[i].get_count(lif); + + return num_stats; +} + +static int ionic_get_sset_count(struct net_device *netdev, int sset) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int count = 0; + + switch (sset) { + case ETH_SS_STATS: + count = ionic_get_stats_count(lif); + break; + case ETH_SS_PRIV_FLAGS: + count = PRIV_FLAGS_COUNT; + break; + } + return count; +} + +static void ionic_get_strings(struct net_device *netdev, + u32 sset, u8 *buf) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + switch (sset) { + case ETH_SS_STATS: + ionic_get_stats_strings(lif, buf); + break; + case ETH_SS_PRIV_FLAGS: + memcpy(buf, ionic_priv_flags_strings, + PRIV_FLAGS_COUNT * ETH_GSTRING_LEN); + break; + } +} + +static void ionic_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + + strlcpy(drvinfo->driver, IONIC_DRV_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, IONIC_DRV_VERSION, sizeof(drvinfo->version)); + strlcpy(drvinfo->fw_version, ionic->idev.dev_info.fw_version, + sizeof(drvinfo->fw_version)); + strlcpy(drvinfo->bus_info, ionic_bus_info(ionic), + sizeof(drvinfo->bus_info)); +} + +static int ionic_get_regs_len(struct net_device *netdev) +{ + return (IONIC_DEV_INFO_REG_COUNT + IONIC_DEV_CMD_REG_COUNT) * sizeof(u32); +} + +static void ionic_get_regs(struct net_device *netdev, struct ethtool_regs *regs, + void *p) +{ + struct ionic_lif *lif = netdev_priv(netdev); + unsigned int size; + + regs->version = IONIC_DEV_CMD_REG_VERSION; + + size = IONIC_DEV_INFO_REG_COUNT * sizeof(u32); + memcpy_fromio(p, lif->ionic->idev.dev_info_regs->words, size); + + size = IONIC_DEV_CMD_REG_COUNT * sizeof(u32); + memcpy_fromio(p, lif->ionic->idev.dev_cmd_regs->words, size); +} + +static int ionic_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ks) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + int copper_seen = 0; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + + /* The port_info data is found in a DMA space that the NIC keeps + * up-to-date, so there's no need to request the data from the + * NIC, we already have it in our memory space. + */ + + switch (le16_to_cpu(idev->port_info->status.xcvr.pid)) { + /* Copper */ + case IONIC_XCVR_PID_QSFP_100G_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseCR4_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_QSFP_40GBASE_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_SFP_25GBASE_CR_S: + case IONIC_XCVR_PID_SFP_25GBASE_CR_L: + case IONIC_XCVR_PID_SFP_25GBASE_CR_N: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_SFP_10GBASE_AOC: + case IONIC_XCVR_PID_SFP_10GBASE_CU: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + copper_seen++; + break; + + /* Fibre */ + case IONIC_XCVR_PID_QSFP_100G_SR4: + case IONIC_XCVR_PID_QSFP_100G_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseSR4_Full); + break; + case IONIC_XCVR_PID_QSFP_100G_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseLR4_ER4_Full); + break; + case IONIC_XCVR_PID_QSFP_100G_ER4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseLR4_ER4_Full); + break; + case IONIC_XCVR_PID_QSFP_40GBASE_SR4: + case IONIC_XCVR_PID_QSFP_40GBASE_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + break; + case IONIC_XCVR_PID_QSFP_40GBASE_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + break; + case IONIC_XCVR_PID_SFP_25GBASE_SR: + case IONIC_XCVR_PID_SFP_25GBASE_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_SR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_LRM: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLRM_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_ER: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseER_Full); + break; + case IONIC_XCVR_PID_UNKNOWN: + /* This means there's no module plugged in */ + break; + default: + dev_info(lif->ionic->dev, "unknown xcvr type pid=%d / 0x%x\n", + idev->port_info->status.xcvr.pid, + idev->port_info->status.xcvr.pid); + break; + } + + bitmap_copy(ks->link_modes.advertising, ks->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + if (idev->port_info->config.fec_type == IONIC_PORT_FEC_TYPE_FC) + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_BASER); + else if (idev->port_info->config.fec_type == IONIC_PORT_FEC_TYPE_RS) + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(ks, supported, Pause); + + if (idev->port_info->status.xcvr.phy == IONIC_PHY_TYPE_COPPER || + copper_seen) + ks->base.port = PORT_DA; + else if (idev->port_info->status.xcvr.phy == IONIC_PHY_TYPE_FIBER) + ks->base.port = PORT_FIBRE; + else + ks->base.port = PORT_NONE; + + if (ks->base.port != PORT_NONE) { + ks->base.speed = le32_to_cpu(lif->info->status.link_speed); + + if (le16_to_cpu(lif->info->status.link_status)) + ks->base.duplex = DUPLEX_FULL; + else + ks->base.duplex = DUPLEX_UNKNOWN; + + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + + if (idev->port_info->config.an_enable) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); + ks->base.autoneg = AUTONEG_ENABLE; + } + } + + return 0; +} + +static int ionic_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ks) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + struct ionic_dev *idev; + u32 req_rs, req_fc; + u8 fec_type; + int err = 0; + + idev = &lif->ionic->idev; + fec_type = IONIC_PORT_FEC_TYPE_NONE; + + /* set autoneg */ + if (ks->base.autoneg != idev->port_info->config.an_enable) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_autoneg(idev, ks->base.autoneg); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + /* set speed */ + if (ks->base.speed != le32_to_cpu(idev->port_info->config.speed)) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_speed(idev, ks->base.speed); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + /* set FEC */ + req_rs = ethtool_link_ksettings_test_link_mode(ks, advertising, FEC_RS); + req_fc = ethtool_link_ksettings_test_link_mode(ks, advertising, FEC_BASER); + if (req_rs && req_fc) { + netdev_info(netdev, "Only select one FEC mode at a time\n"); + return -EINVAL; + } else if (req_fc) { + fec_type = IONIC_PORT_FEC_TYPE_FC; + } else if (req_rs) { + fec_type = IONIC_PORT_FEC_TYPE_RS; + } else if (!(req_rs | req_fc)) { + fec_type = IONIC_PORT_FEC_TYPE_NONE; + } + + if (fec_type != idev->port_info->config.fec_type) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_fec(idev, fec_type); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + return 0; +} + +static void ionic_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u8 pause_type; + + pause->autoneg = 0; + + pause_type = lif->ionic->idev.port_info->config.pause_type; + if (pause_type) { + pause->rx_pause = pause_type & IONIC_PAUSE_F_RX ? 1 : 0; + pause->tx_pause = pause_type & IONIC_PAUSE_F_TX ? 1 : 0; + } +} + +static int ionic_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + u32 requested_pause; + int err; + + if (pause->autoneg) + return -EOPNOTSUPP; + + /* change both at the same time */ + requested_pause = IONIC_PORT_PAUSE_TYPE_LINK; + if (pause->rx_pause) + requested_pause |= IONIC_PAUSE_F_RX; + if (pause->tx_pause) + requested_pause |= IONIC_PAUSE_F_TX; + + if (requested_pause == lif->ionic->idev.port_info->config.pause_type) + return 0; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_pause(&lif->ionic->idev, requested_pause); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + + return 0; +} + +static int ionic_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + /* Tx uses Rx interrupt */ + coalesce->tx_coalesce_usecs = lif->rx_coalesce_usecs; + coalesce->rx_coalesce_usecs = lif->rx_coalesce_usecs; + + return 0; +} + +static int ionic_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_identity *ident; + struct ionic_qcq *qcq; + unsigned int i; + u32 usecs; + u32 coal; + + if (coalesce->rx_max_coalesced_frames || + coalesce->rx_coalesce_usecs_irq || + coalesce->rx_max_coalesced_frames_irq || + coalesce->tx_max_coalesced_frames || + coalesce->tx_coalesce_usecs_irq || + coalesce->tx_max_coalesced_frames_irq || + coalesce->stats_block_coalesce_usecs || + coalesce->use_adaptive_rx_coalesce || + coalesce->use_adaptive_tx_coalesce || + coalesce->pkt_rate_low || + coalesce->rx_coalesce_usecs_low || + coalesce->rx_max_coalesced_frames_low || + coalesce->tx_coalesce_usecs_low || + coalesce->tx_max_coalesced_frames_low || + coalesce->pkt_rate_high || + coalesce->rx_coalesce_usecs_high || + coalesce->rx_max_coalesced_frames_high || + coalesce->tx_coalesce_usecs_high || + coalesce->tx_max_coalesced_frames_high || + coalesce->rate_sample_interval) + return -EINVAL; + + ident = &lif->ionic->ident; + if (ident->dev.intr_coal_div == 0) { + netdev_warn(netdev, "bad HW value in dev.intr_coal_div = %d\n", + ident->dev.intr_coal_div); + return -EIO; + } + + /* Tx uses Rx interrupt, so only change Rx */ + if (coalesce->tx_coalesce_usecs != lif->rx_coalesce_usecs) { + netdev_warn(netdev, "only the rx-usecs can be changed\n"); + return -EINVAL; + } + + coal = ionic_coal_usec_to_hw(lif->ionic, coalesce->rx_coalesce_usecs); + + if (coal > IONIC_INTR_CTRL_COAL_MAX) + return -ERANGE; + + /* If they asked for non-zero and it resolved to zero, bump it up */ + if (!coal && coalesce->rx_coalesce_usecs) + coal = 1; + + /* Convert it back to get device resolution */ + usecs = ionic_coal_hw_to_usec(lif->ionic, coal); + + if (usecs != lif->rx_coalesce_usecs) { + lif->rx_coalesce_usecs = usecs; + + if (test_bit(IONIC_LIF_UP, lif->state)) { + for (i = 0; i < lif->nxqs; i++) { + qcq = lif->rxqcqs[i].qcq; + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + qcq->intr.index, coal); + } + } + } + + return 0; +} + +static void ionic_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + ring->tx_max_pending = IONIC_MAX_TXRX_DESC; + ring->tx_pending = lif->ntxq_descs; + ring->rx_max_pending = IONIC_MAX_TXRX_DESC; + ring->rx_pending = lif->nrxq_descs; +} + +static int ionic_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ionic_lif *lif = netdev_priv(netdev); + bool running; + + if (ring->rx_mini_pending || ring->rx_jumbo_pending) { + netdev_info(netdev, "Changing jumbo or mini descriptors not supported\n"); + return -EINVAL; + } + + if (!is_power_of_2(ring->tx_pending) || + !is_power_of_2(ring->rx_pending)) { + netdev_info(netdev, "Descriptor count must be a power of 2\n"); + return -EINVAL; + } + + /* if nothing to do return success */ + if (ring->tx_pending == lif->ntxq_descs && + ring->rx_pending == lif->nrxq_descs) + return 0; + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = test_bit(IONIC_LIF_UP, lif->state); + if (running) + ionic_stop(netdev); + + lif->ntxq_descs = ring->tx_pending; + lif->nrxq_descs = ring->rx_pending; + + if (running) + ionic_open(netdev); + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return 0; +} + +static void ionic_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + /* report maximum channels */ + ch->max_combined = lif->ionic->ntxqs_per_lif; + + /* report current channels */ + ch->combined_count = lif->nxqs; +} + +static int ionic_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct ionic_lif *lif = netdev_priv(netdev); + bool running; + + if (!ch->combined_count || ch->other_count || + ch->rx_count || ch->tx_count) + return -EINVAL; + + if (ch->combined_count == lif->nxqs) + return 0; + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = test_bit(IONIC_LIF_UP, lif->state); + if (running) + ionic_stop(netdev); + + lif->nxqs = ch->combined_count; + + if (running) + ionic_open(netdev); + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return 0; +} + +static u32 ionic_get_priv_flags(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u32 priv_flags = 0; + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) + priv_flags |= PRIV_F_SW_DBG_STATS; + + return priv_flags; +} + +static int ionic_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u32 flags = lif->flags; + + clear_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state); + if (priv_flags & PRIV_F_SW_DBG_STATS) + set_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state); + + if (flags != lif->flags) + lif->flags = flags; + + return 0; +} + +static int ionic_get_rxnfc(struct net_device *netdev, + struct ethtool_rxnfc *info, u32 *rules) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err = 0; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = lif->nxqs; + break; + default: + netdev_err(netdev, "Command parameter %d is not supported\n", + info->cmd); + err = -EOPNOTSUPP; + } + + return err; +} + +static u32 ionic_get_rxfh_indir_size(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + return le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); +} + +static u32 ionic_get_rxfh_key_size(struct net_device *netdev) +{ + return IONIC_RSS_HASH_KEY_SIZE; +} + +static int ionic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct ionic_lif *lif = netdev_priv(netdev); + unsigned int i, tbl_sz; + + if (indir) { + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + indir[i] = lif->rss_ind_tbl[i]; + } + + if (key) + memcpy(key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int ionic_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + err = ionic_lif_rss_config(lif, lif->rss_types, key, indir); + if (err) + return err; + + return 0; +} + +static int ionic_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct ionic_lif *lif = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + lif->rx_copybreak = *(u32 *)data; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int ionic_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *tuna, void *data) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = lif->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int ionic_get_module_info(struct net_device *netdev, + struct ethtool_modinfo *modinfo) + +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_xcvr_status *xcvr; + + xcvr = &idev->port_info->status.xcvr; + + /* report the module data type and length */ + switch (xcvr->sprom[0]) { + case 0x03: /* SFP */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + break; + case 0x0D: /* QSFP */ + case 0x11: /* QSFP28 */ + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + break; + default: + netdev_info(netdev, "unknown xcvr type 0x%02x\n", + xcvr->sprom[0]); + break; + } + + return 0; +} + +static int ionic_get_module_eeprom(struct net_device *netdev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_xcvr_status *xcvr; + char tbuf[sizeof(xcvr->sprom)]; + int count = 10; + u32 len; + + /* The NIC keeps the module prom up-to-date in the DMA space + * so we can simply copy the module bytes into the data buffer. + */ + xcvr = &idev->port_info->status.xcvr; + len = min_t(u32, sizeof(xcvr->sprom), ee->len); + + do { + memcpy(data, xcvr->sprom, len); + memcpy(tbuf, xcvr->sprom, len); + + /* Let's make sure we got a consistent copy */ + if (!memcmp(data, tbuf, len)) + break; + + } while (--count); + + if (!count) + return -ETIMEDOUT; + + return 0; +} + +static int ionic_nway_reset(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + int err = 0; + + /* flap the link to force auto-negotiation */ + + mutex_lock(&ionic->dev_cmd_lock); + + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_DOWN); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + if (!err) { + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_UP); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +static const struct ethtool_ops ionic_ethtool_ops = { + .get_drvinfo = ionic_get_drvinfo, + .get_regs_len = ionic_get_regs_len, + .get_regs = ionic_get_regs, + .get_link = ethtool_op_get_link, + .get_link_ksettings = ionic_get_link_ksettings, + .get_coalesce = ionic_get_coalesce, + .set_coalesce = ionic_set_coalesce, + .get_ringparam = ionic_get_ringparam, + .set_ringparam = ionic_set_ringparam, + .get_channels = ionic_get_channels, + .set_channels = ionic_set_channels, + .get_strings = ionic_get_strings, + .get_ethtool_stats = ionic_get_stats, + .get_sset_count = ionic_get_sset_count, + .get_priv_flags = ionic_get_priv_flags, + .set_priv_flags = ionic_set_priv_flags, + .get_rxnfc = ionic_get_rxnfc, + .get_rxfh_indir_size = ionic_get_rxfh_indir_size, + .get_rxfh_key_size = ionic_get_rxfh_key_size, + .get_rxfh = ionic_get_rxfh, + .set_rxfh = ionic_set_rxfh, + .get_tunable = ionic_get_tunable, + .set_tunable = ionic_set_tunable, + .get_module_info = ionic_get_module_info, + .get_module_eeprom = ionic_get_module_eeprom, + .get_pauseparam = ionic_get_pauseparam, + .set_pauseparam = ionic_set_pauseparam, + .set_link_ksettings = ionic_set_link_ksettings, + .nway_reset = ionic_nway_reset, +}; + +void ionic_ethtool_set_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ionic_ethtool_ops; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h new file mode 100644 index 000000000000..38b91b1d70ae --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_ETHTOOL_H_ +#define _IONIC_ETHTOOL_H_ + +void ionic_ethtool_set_ops(struct net_device *netdev); + +#endif /* _IONIC_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h new file mode 100644 index 000000000000..5bfdda19f64d --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -0,0 +1,2482 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB OR BSD-2-Clause */ +/* Copyright (c) 2017-2019 Pensando Systems, Inc. All rights reserved. */ + +#ifndef _IONIC_IF_H_ +#define _IONIC_IF_H_ + +#pragma pack(push, 1) + +#define IONIC_DEV_INFO_SIGNATURE 0x44455649 /* 'DEVI' */ +#define IONIC_DEV_INFO_VERSION 1 +#define IONIC_IFNAMSIZ 16 + +/** + * Commands + */ +enum ionic_cmd_opcode { + IONIC_CMD_NOP = 0, + + /* Device commands */ + IONIC_CMD_IDENTIFY = 1, + IONIC_CMD_INIT = 2, + IONIC_CMD_RESET = 3, + IONIC_CMD_GETATTR = 4, + IONIC_CMD_SETATTR = 5, + + /* Port commands */ + IONIC_CMD_PORT_IDENTIFY = 10, + IONIC_CMD_PORT_INIT = 11, + IONIC_CMD_PORT_RESET = 12, + IONIC_CMD_PORT_GETATTR = 13, + IONIC_CMD_PORT_SETATTR = 14, + + /* LIF commands */ + IONIC_CMD_LIF_IDENTIFY = 20, + IONIC_CMD_LIF_INIT = 21, + IONIC_CMD_LIF_RESET = 22, + IONIC_CMD_LIF_GETATTR = 23, + IONIC_CMD_LIF_SETATTR = 24, + + IONIC_CMD_RX_MODE_SET = 30, + IONIC_CMD_RX_FILTER_ADD = 31, + IONIC_CMD_RX_FILTER_DEL = 32, + + /* Queue commands */ + IONIC_CMD_Q_INIT = 40, + IONIC_CMD_Q_CONTROL = 41, + + /* RDMA commands */ + IONIC_CMD_RDMA_RESET_LIF = 50, + IONIC_CMD_RDMA_CREATE_EQ = 51, + IONIC_CMD_RDMA_CREATE_CQ = 52, + IONIC_CMD_RDMA_CREATE_ADMINQ = 53, + + /* QoS commands */ + IONIC_CMD_QOS_CLASS_IDENTIFY = 240, + IONIC_CMD_QOS_CLASS_INIT = 241, + IONIC_CMD_QOS_CLASS_RESET = 242, + + /* Firmware commands */ + IONIC_CMD_FW_DOWNLOAD = 254, + IONIC_CMD_FW_CONTROL = 255, +}; + +/** + * Command Return codes + */ +enum ionic_status_code { + IONIC_RC_SUCCESS = 0, /* Success */ + IONIC_RC_EVERSION = 1, /* Incorrect version for request */ + IONIC_RC_EOPCODE = 2, /* Invalid cmd opcode */ + IONIC_RC_EIO = 3, /* I/O error */ + IONIC_RC_EPERM = 4, /* Permission denied */ + IONIC_RC_EQID = 5, /* Bad qid */ + IONIC_RC_EQTYPE = 6, /* Bad qtype */ + IONIC_RC_ENOENT = 7, /* No such element */ + IONIC_RC_EINTR = 8, /* operation interrupted */ + IONIC_RC_EAGAIN = 9, /* Try again */ + IONIC_RC_ENOMEM = 10, /* Out of memory */ + IONIC_RC_EFAULT = 11, /* Bad address */ + IONIC_RC_EBUSY = 12, /* Device or resource busy */ + IONIC_RC_EEXIST = 13, /* object already exists */ + IONIC_RC_EINVAL = 14, /* Invalid argument */ + IONIC_RC_ENOSPC = 15, /* No space left or alloc failure */ + IONIC_RC_ERANGE = 16, /* Parameter out of range */ + IONIC_RC_BAD_ADDR = 17, /* Descriptor contains a bad ptr */ + IONIC_RC_DEV_CMD = 18, /* Device cmd attempted on AdminQ */ + IONIC_RC_ENOSUPP = 19, /* Operation not supported */ + IONIC_RC_ERROR = 29, /* Generic error */ + + IONIC_RC_ERDMA = 30, /* Generic RDMA error */ +}; + +enum ionic_notifyq_opcode { + IONIC_EVENT_LINK_CHANGE = 1, + IONIC_EVENT_RESET = 2, + IONIC_EVENT_HEARTBEAT = 3, + IONIC_EVENT_LOG = 4, +}; + +/** + * struct cmd - General admin command format + * @opcode: Opcode for the command + * @lif_index: LIF index + * @cmd_data: Opcode-specific command bytes + */ +struct ionic_admin_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 cmd_data[60]; +}; + +/** + * struct admin_comp - General admin command completion format + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @cmd_data: Command-specific bytes. + * @color: Color bit. (Always 0 for commands issued to the + * Device Cmd Registers.) + */ +struct ionic_admin_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 cmd_data[11]; + u8 color; +#define IONIC_COMP_COLOR_MASK 0x80 +}; + +static inline u8 color_match(u8 color, u8 done_color) +{ + return (!!(color & IONIC_COMP_COLOR_MASK)) == done_color; +} + +/** + * struct nop_cmd - NOP command + * @opcode: opcode + */ +struct ionic_nop_cmd { + u8 opcode; + u8 rsvd[63]; +}; + +/** + * struct nop_comp - NOP command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_nop_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct dev_init_cmd - Device init command + * @opcode: opcode + * @type: device type + */ +struct ionic_dev_init_cmd { + u8 opcode; + u8 type; + u8 rsvd[62]; +}; + +/** + * struct init_comp - Device init command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_dev_init_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct dev_reset_cmd - Device reset command + * @opcode: opcode + */ +struct ionic_dev_reset_cmd { + u8 opcode; + u8 rsvd[63]; +}; + +/** + * struct reset_comp - Reset command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_dev_reset_comp { + u8 status; + u8 rsvd[15]; +}; + +#define IONIC_IDENTITY_VERSION_1 1 + +/** + * struct dev_identify_cmd - Driver/device identify command + * @opcode: opcode + * @ver: Highest version of identify supported by driver + */ +struct ionic_dev_identify_cmd { + u8 opcode; + u8 ver; + u8 rsvd[62]; +}; + +/** + * struct dev_identify_comp - Driver/device identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_dev_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +enum ionic_os_type { + IONIC_OS_TYPE_LINUX = 1, + IONIC_OS_TYPE_WIN = 2, + IONIC_OS_TYPE_DPDK = 3, + IONIC_OS_TYPE_FREEBSD = 4, + IONIC_OS_TYPE_IPXE = 5, + IONIC_OS_TYPE_ESXI = 6, +}; + +/** + * union drv_identity - driver identity information + * @os_type: OS type (see enum os_type) + * @os_dist: OS distribution, numeric format + * @os_dist_str: OS distribution, string format + * @kernel_ver: Kernel version, numeric format + * @kernel_ver_str: Kernel version, string format + * @driver_ver_str: Driver version, string format + */ +union ionic_drv_identity { + struct { + __le32 os_type; + __le32 os_dist; + char os_dist_str[128]; + __le32 kernel_ver; + char kernel_ver_str[32]; + char driver_ver_str[32]; + }; + __le32 words[512]; +}; + +/** + * union dev_identity - device identity information + * @version: Version of device identify + * @type: Identify type (0 for now) + * @nports: Number of ports provisioned + * @nlifs: Number of LIFs provisioned + * @nintrs: Number of interrupts provisioned + * @ndbpgs_per_lif: Number of doorbell pages per LIF + * @intr_coal_mult: Interrupt coalescing multiplication factor. + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @intr_coal_div: Interrupt coalescing division factor. + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * + */ +union ionic_dev_identity { + struct { + u8 version; + u8 type; + u8 rsvd[2]; + u8 nports; + u8 rsvd2[3]; + __le32 nlifs; + __le32 nintrs; + __le32 ndbpgs_per_lif; + __le32 intr_coal_mult; + __le32 intr_coal_div; + }; + __le32 words[512]; +}; + +enum ionic_lif_type { + IONIC_LIF_TYPE_CLASSIC = 0, + IONIC_LIF_TYPE_MACVLAN = 1, + IONIC_LIF_TYPE_NETQUEUE = 2, +}; + +/** + * struct lif_identify_cmd - lif identify command + * @opcode: opcode + * @type: lif type (enum lif_type) + * @ver: version of identify returned by device + */ +struct ionic_lif_identify_cmd { + u8 opcode; + u8 type; + u8 ver; + u8 rsvd[61]; +}; + +/** + * struct lif_identify_comp - lif identify command completion + * @status: status of the command (enum status_code) + * @ver: version of identify returned by device + */ +struct ionic_lif_identify_comp { + u8 status; + u8 ver; + u8 rsvd2[14]; +}; + +enum ionic_lif_capability { + IONIC_LIF_CAP_ETH = BIT(0), + IONIC_LIF_CAP_RDMA = BIT(1), +}; + +/** + * Logical Queue Types + */ +enum ionic_logical_qtype { + IONIC_QTYPE_ADMINQ = 0, + IONIC_QTYPE_NOTIFYQ = 1, + IONIC_QTYPE_RXQ = 2, + IONIC_QTYPE_TXQ = 3, + IONIC_QTYPE_EQ = 4, + IONIC_QTYPE_MAX = 16, +}; + +/** + * struct lif_logical_qtype - Descriptor of logical to hardware queue type. + * @qtype: Hardware Queue Type. + * @qid_count: Number of Queue IDs of the logical type. + * @qid_base: Minimum Queue ID of the logical type. + */ +struct ionic_lif_logical_qtype { + u8 qtype; + u8 rsvd[3]; + __le32 qid_count; + __le32 qid_base; +}; + +enum ionic_lif_state { + IONIC_LIF_DISABLE = 0, + IONIC_LIF_ENABLE = 1, + IONIC_LIF_HANG_RESET = 2, +}; + +/** + * LIF configuration + * @state: lif state (enum lif_state) + * @name: lif name + * @mtu: mtu + * @mac: station mac address + * @features: features (enum eth_hw_features) + * @queue_count: queue counts per queue-type + */ +union ionic_lif_config { + struct { + u8 state; + u8 rsvd[3]; + char name[IONIC_IFNAMSIZ]; + __le32 mtu; + u8 mac[6]; + u8 rsvd2[2]; + __le64 features; + __le32 queue_count[IONIC_QTYPE_MAX]; + }; + __le32 words[64]; +}; + +/** + * struct lif_identity - lif identity information (type-specific) + * + * @capabilities LIF capabilities + * + * Ethernet: + * @version: Ethernet identify structure version. + * @features: Ethernet features supported on this lif type. + * @max_ucast_filters: Number of perfect unicast addresses supported. + * @max_mcast_filters: Number of perfect multicast addresses supported. + * @min_frame_size: Minimum size of frames to be sent + * @max_frame_size: Maximim size of frames to be sent + * @config: LIF config struct with features, mtu, mac, q counts + * + * RDMA: + * @version: RDMA version of opcodes and queue descriptors. + * @qp_opcodes: Number of rdma queue pair opcodes supported. + * @admin_opcodes: Number of rdma admin opcodes supported. + * @npts_per_lif: Page table size per lif + * @nmrs_per_lif: Number of memory regions per lif + * @nahs_per_lif: Number of address handles per lif + * @max_stride: Max work request stride. + * @cl_stride: Cache line stride. + * @pte_stride: Page table entry stride. + * @rrq_stride: Remote RQ work request stride. + * @rsq_stride: Remote SQ work request stride. + * @dcqcn_profiles: Number of DCQCN profiles + * @aq_qtype: RDMA Admin Qtype. + * @sq_qtype: RDMA Send Qtype. + * @rq_qtype: RDMA Receive Qtype. + * @cq_qtype: RDMA Completion Qtype. + * @eq_qtype: RDMA Event Qtype. + */ +union ionic_lif_identity { + struct { + __le64 capabilities; + + struct { + u8 version; + u8 rsvd[3]; + __le32 max_ucast_filters; + __le32 max_mcast_filters; + __le16 rss_ind_tbl_sz; + __le32 min_frame_size; + __le32 max_frame_size; + u8 rsvd2[106]; + union ionic_lif_config config; + } eth; + + struct { + u8 version; + u8 qp_opcodes; + u8 admin_opcodes; + u8 rsvd; + __le32 npts_per_lif; + __le32 nmrs_per_lif; + __le32 nahs_per_lif; + u8 max_stride; + u8 cl_stride; + u8 pte_stride; + u8 rrq_stride; + u8 rsq_stride; + u8 dcqcn_profiles; + u8 rsvd_dimensions[10]; + struct ionic_lif_logical_qtype aq_qtype; + struct ionic_lif_logical_qtype sq_qtype; + struct ionic_lif_logical_qtype rq_qtype; + struct ionic_lif_logical_qtype cq_qtype; + struct ionic_lif_logical_qtype eq_qtype; + } rdma; + }; + __le32 words[512]; +}; + +/** + * struct lif_init_cmd - LIF init command + * @opcode: opcode + * @type: LIF type (enum lif_type) + * @index: LIF index + * @info_pa: destination address for lif info (struct lif_info) + */ +struct ionic_lif_init_cmd { + u8 opcode; + u8 type; + __le16 index; + __le32 rsvd; + __le64 info_pa; + u8 rsvd2[48]; +}; + +/** + * struct lif_init_comp - LIF init command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_lif_init_comp { + u8 status; + u8 rsvd; + __le16 hw_index; + u8 rsvd2[12]; +}; + +/** + * struct q_init_cmd - Queue init command + * @opcode: opcode + * @type: Logical queue type + * @ver: Queue version (defines opcode/descriptor scope) + * @lif_index: LIF index + * @index: (lif, qtype) relative admin queue index + * @intr_index: Interrupt control register index + * @pid: Process ID + * @flags: + * IRQ: Interrupt requested on completion + * ENA: Enable the queue. If ENA=0 the queue is initialized + * but remains disabled, to be later enabled with the + * Queue Enable command. If ENA=1, then queue is + * initialized and then enabled. + * SG: Enable Scatter-Gather on the queue. + * in number of descs. The actual ring size is + * (1 << ring_size). For example, to + * select a ring size of 64 descriptors write + * ring_size = 6. The minimum ring_size value is 2 + * for a ring size of 4 descriptors. The maximum + * ring_size value is 16 for a ring size of 64k + * descriptors. Values of ring_size <2 and >16 are + * reserved. + * EQ: Enable the Event Queue + * @cos: Class of service for this queue. + * @ring_size: Queue ring size, encoded as a log2(size) + * @ring_base: Queue ring base address + * @cq_ring_base: Completion queue ring base address + * @sg_ring_base: Scatter/Gather ring base address + * @eq_index: Event queue index + */ +struct ionic_q_init_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 type; + u8 ver; + u8 rsvd1[2]; + __le32 index; + __le16 pid; + __le16 intr_index; + __le16 flags; +#define IONIC_QINIT_F_IRQ 0x01 /* Request interrupt on completion */ +#define IONIC_QINIT_F_ENA 0x02 /* Enable the queue */ +#define IONIC_QINIT_F_SG 0x04 /* Enable scatter/gather on the queue */ +#define IONIC_QINIT_F_EQ 0x08 /* Enable event queue */ +#define IONIC_QINIT_F_DEBUG 0x80 /* Enable queue debugging */ + u8 cos; + u8 ring_size; + __le64 ring_base; + __le64 cq_ring_base; + __le64 sg_ring_base; + __le32 eq_index; + u8 rsvd2[16]; +}; + +/** + * struct q_init_comp - Queue init command completion + * @status: The status of the command (enum status_code) + * @ver: Queue version (defines opcode/descriptor scope) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @hw_index: Hardware Queue ID + * @hw_type: Hardware Queue type + * @color: Color + */ +struct ionic_q_init_comp { + u8 status; + u8 ver; + __le16 comp_index; + __le32 hw_index; + u8 hw_type; + u8 rsvd2[6]; + u8 color; +}; + +/* the device's internal addressing uses up to 52 bits */ +#define IONIC_ADDR_LEN 52 +#define IONIC_ADDR_MASK (BIT_ULL(IONIC_ADDR_LEN) - 1) + +enum ionic_txq_desc_opcode { + IONIC_TXQ_DESC_OPCODE_CSUM_NONE = 0, + IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL = 1, + IONIC_TXQ_DESC_OPCODE_CSUM_HW = 2, + IONIC_TXQ_DESC_OPCODE_TSO = 3, +}; + +/** + * struct txq_desc - Ethernet Tx queue descriptor format + * @opcode: Tx operation, see TXQ_DESC_OPCODE_*: + * + * IONIC_TXQ_DESC_OPCODE_CSUM_NONE: + * + * Non-offload send. No segmentation, + * fragmentation or checksum calc/insertion is + * performed by device; packet is prepared + * to send by software stack and requires + * no further manipulation from device. + * + * IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL: + * + * Offload 16-bit L4 checksum + * calculation/insertion. The device will + * calculate the L4 checksum value and + * insert the result in the packet's L4 + * header checksum field. The L4 checksum + * is calculated starting at @csum_start bytes + * into the packet to the end of the packet. + * The checksum insertion position is given + * in @csum_offset. This feature is only + * applicable to protocols such as TCP, UDP + * and ICMP where a standard (i.e. the + * 'IP-style' checksum) one's complement + * 16-bit checksum is used, using an IP + * pseudo-header to seed the calculation. + * Software will preload the L4 checksum + * field with the IP pseudo-header checksum. + * + * For tunnel encapsulation, @csum_start and + * @csum_offset refer to the inner L4 + * header. Supported tunnels encapsulations + * are: IPIP, GRE, and UDP. If the @encap + * is clear, no further processing by the + * device is required; software will + * calculate the outer header checksums. If + * the @encap is set, the device will + * offload the outer header checksums using + * LCO (local checksum offload) (see + * Documentation/networking/checksum- + * offloads.txt for more info). + * + * IONIC_TXQ_DESC_OPCODE_CSUM_HW: + * + * Offload 16-bit checksum computation to hardware. + * If @csum_l3 is set then the packet's L3 checksum is + * updated. Similarly, if @csum_l4 is set the the L4 + * checksum is updated. If @encap is set then encap header + * checksums are also updated. + * + * IONIC_TXQ_DESC_OPCODE_TSO: + * + * Device preforms TCP segmentation offload + * (TSO). @hdr_len is the number of bytes + * to the end of TCP header (the offset to + * the TCP payload). @mss is the desired + * MSS, the TCP payload length for each + * segment. The device will calculate/ + * insert IP (IPv4 only) and TCP checksums + * for each segment. In the first data + * buffer containing the header template, + * the driver will set IPv4 checksum to 0 + * and preload TCP checksum with the IP + * pseudo header calculated with IP length = 0. + * + * Supported tunnel encapsulations are IPIP, + * layer-3 GRE, and UDP. @hdr_len includes + * both outer and inner headers. The driver + * will set IPv4 checksum to zero and + * preload TCP checksum with IP pseudo + * header on the inner header. + * + * TCP ECN offload is supported. The device + * will set CWR flag in the first segment if + * CWR is set in the template header, and + * clear CWR in remaining segments. + * @flags: + * vlan: + * Insert an L2 VLAN header using @vlan_tci. + * encap: + * Calculate encap header checksum. + * csum_l3: + * Compute L3 header checksum. + * csum_l4: + * Compute L4 header checksum. + * tso_sot: + * TSO start + * tso_eot: + * TSO end + * @num_sg_elems: Number of scatter-gather elements in SG + * descriptor + * @addr: First data buffer's DMA address. + * (Subsequent data buffers are on txq_sg_desc). + * @len: First data buffer's length, in bytes + * @vlan_tci: VLAN tag to insert in the packet (if requested + * by @V-bit). Includes .1p and .1q tags + * @hdr_len: Length of packet headers, including + * encapsulating outer header, if applicable. + * Valid for opcodes TXQ_DESC_OPCODE_CALC_CSUM and + * TXQ_DESC_OPCODE_TSO. Should be set to zero for + * all other modes. For + * TXQ_DESC_OPCODE_CALC_CSUM, @hdr_len is length + * of headers up to inner-most L4 header. For + * TXQ_DESC_OPCODE_TSO, @hdr_len is up to + * inner-most L4 payload, so inclusive of + * inner-most L4 header. + * @mss: Desired MSS value for TSO. Only applicable for + * TXQ_DESC_OPCODE_TSO. + * @csum_start: Offset into inner-most L3 header of checksum + * @csum_offset: Offset into inner-most L4 header of checksum + */ + +#define IONIC_TXQ_DESC_OPCODE_MASK 0xf +#define IONIC_TXQ_DESC_OPCODE_SHIFT 4 +#define IONIC_TXQ_DESC_FLAGS_MASK 0xf +#define IONIC_TXQ_DESC_FLAGS_SHIFT 0 +#define IONIC_TXQ_DESC_NSGE_MASK 0xf +#define IONIC_TXQ_DESC_NSGE_SHIFT 8 +#define IONIC_TXQ_DESC_ADDR_MASK (BIT_ULL(IONIC_ADDR_LEN) - 1) +#define IONIC_TXQ_DESC_ADDR_SHIFT 12 + +/* common flags */ +#define IONIC_TXQ_DESC_FLAG_VLAN 0x1 +#define IONIC_TXQ_DESC_FLAG_ENCAP 0x2 + +/* flags for csum_hw opcode */ +#define IONIC_TXQ_DESC_FLAG_CSUM_L3 0x4 +#define IONIC_TXQ_DESC_FLAG_CSUM_L4 0x8 + +/* flags for tso opcode */ +#define IONIC_TXQ_DESC_FLAG_TSO_SOT 0x4 +#define IONIC_TXQ_DESC_FLAG_TSO_EOT 0x8 + +struct ionic_txq_desc { + __le64 cmd; + __le16 len; + union { + __le16 vlan_tci; + __le16 hword0; + }; + union { + __le16 csum_start; + __le16 hdr_len; + __le16 hword1; + }; + union { + __le16 csum_offset; + __le16 mss; + __le16 hword2; + }; +}; + +static inline u64 encode_txq_desc_cmd(u8 opcode, u8 flags, + u8 nsge, u64 addr) +{ + u64 cmd; + + cmd = (opcode & IONIC_TXQ_DESC_OPCODE_MASK) << IONIC_TXQ_DESC_OPCODE_SHIFT; + cmd |= (flags & IONIC_TXQ_DESC_FLAGS_MASK) << IONIC_TXQ_DESC_FLAGS_SHIFT; + cmd |= (nsge & IONIC_TXQ_DESC_NSGE_MASK) << IONIC_TXQ_DESC_NSGE_SHIFT; + cmd |= (addr & IONIC_TXQ_DESC_ADDR_MASK) << IONIC_TXQ_DESC_ADDR_SHIFT; + + return cmd; +}; + +static inline void decode_txq_desc_cmd(u64 cmd, u8 *opcode, u8 *flags, + u8 *nsge, u64 *addr) +{ + *opcode = (cmd >> IONIC_TXQ_DESC_OPCODE_SHIFT) & IONIC_TXQ_DESC_OPCODE_MASK; + *flags = (cmd >> IONIC_TXQ_DESC_FLAGS_SHIFT) & IONIC_TXQ_DESC_FLAGS_MASK; + *nsge = (cmd >> IONIC_TXQ_DESC_NSGE_SHIFT) & IONIC_TXQ_DESC_NSGE_MASK; + *addr = (cmd >> IONIC_TXQ_DESC_ADDR_SHIFT) & IONIC_TXQ_DESC_ADDR_MASK; +}; + +#define IONIC_TX_MAX_SG_ELEMS 8 +#define IONIC_RX_MAX_SG_ELEMS 8 + +/** + * struct txq_sg_desc - Transmit scatter-gather (SG) list + * @addr: DMA address of SG element data buffer + * @len: Length of SG element data buffer, in bytes + */ +struct ionic_txq_sg_desc { + struct ionic_txq_sg_elem { + __le64 addr; + __le16 len; + __le16 rsvd[3]; + } elems[IONIC_TX_MAX_SG_ELEMS]; +}; + +/** + * struct txq_comp - Ethernet transmit queue completion descriptor + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @color: Color bit. + */ +struct ionic_txq_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 rsvd2[11]; + u8 color; +}; + +enum ionic_rxq_desc_opcode { + IONIC_RXQ_DESC_OPCODE_SIMPLE = 0, + IONIC_RXQ_DESC_OPCODE_SG = 1, +}; + +/** + * struct rxq_desc - Ethernet Rx queue descriptor format + * @opcode: Rx operation, see RXQ_DESC_OPCODE_*: + * + * RXQ_DESC_OPCODE_SIMPLE: + * + * Receive full packet into data buffer + * starting at @addr. Results of + * receive, including actual bytes received, + * are recorded in Rx completion descriptor. + * + * @len: Data buffer's length, in bytes. + * @addr: Data buffer's DMA address + */ +struct ionic_rxq_desc { + u8 opcode; + u8 rsvd[5]; + __le16 len; + __le64 addr; +}; + +/** + * struct rxq_sg_desc - Receive scatter-gather (SG) list + * @addr: DMA address of SG element data buffer + * @len: Length of SG element data buffer, in bytes + */ +struct ionic_rxq_sg_desc { + struct ionic_rxq_sg_elem { + __le64 addr; + __le16 len; + __le16 rsvd[3]; + } elems[IONIC_RX_MAX_SG_ELEMS]; +}; + +/** + * struct rxq_comp - Ethernet receive queue completion descriptor + * @status: The status of the command (enum status_code) + * @num_sg_elems: Number of SG elements used by this descriptor + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @rss_hash: 32-bit RSS hash + * @csum: 16-bit sum of the packet's L2 payload. + * If the packet's L2 payload is odd length, an extra + * zero-value byte is included in the @csum calculation but + * not included in @len. + * @vlan_tci: VLAN tag stripped from the packet. Valid if @VLAN is + * set. Includes .1p and .1q tags. + * @len: Received packet length, in bytes. Excludes FCS. + * @csum_calc L2 payload checksum is computed or not + * @csum_tcp_ok: The TCP checksum calculated by the device + * matched the checksum in the receive packet's + * TCP header + * @csum_tcp_bad: The TCP checksum calculated by the device did + * not match the checksum in the receive packet's + * TCP header. + * @csum_udp_ok: The UDP checksum calculated by the device + * matched the checksum in the receive packet's + * UDP header + * @csum_udp_bad: The UDP checksum calculated by the device did + * not match the checksum in the receive packet's + * UDP header. + * @csum_ip_ok: The IPv4 checksum calculated by the device + * matched the checksum in the receive packet's + * first IPv4 header. If the receive packet + * contains both a tunnel IPv4 header and a + * transport IPv4 header, the device validates the + * checksum for the both IPv4 headers. + * @csum_ip_bad: The IPv4 checksum calculated by the device did + * not match the checksum in the receive packet's + * first IPv4 header. If the receive packet + * contains both a tunnel IPv4 header and a + * transport IPv4 header, the device validates the + * checksum for both IP headers. + * @VLAN: VLAN header was stripped and placed in @vlan_tci. + * @pkt_type: Packet type + * @color: Color bit. + */ +struct ionic_rxq_comp { + u8 status; + u8 num_sg_elems; + __le16 comp_index; + __le32 rss_hash; + __le16 csum; + __le16 vlan_tci; + __le16 len; + u8 csum_flags; +#define IONIC_RXQ_COMP_CSUM_F_TCP_OK 0x01 +#define IONIC_RXQ_COMP_CSUM_F_TCP_BAD 0x02 +#define IONIC_RXQ_COMP_CSUM_F_UDP_OK 0x04 +#define IONIC_RXQ_COMP_CSUM_F_UDP_BAD 0x08 +#define IONIC_RXQ_COMP_CSUM_F_IP_OK 0x10 +#define IONIC_RXQ_COMP_CSUM_F_IP_BAD 0x20 +#define IONIC_RXQ_COMP_CSUM_F_VLAN 0x40 +#define IONIC_RXQ_COMP_CSUM_F_CALC 0x80 + u8 pkt_type_color; +#define IONIC_RXQ_COMP_PKT_TYPE_MASK 0x0f +}; + +enum ionic_pkt_type { + IONIC_PKT_TYPE_NON_IP = 0x000, + IONIC_PKT_TYPE_IPV4 = 0x001, + IONIC_PKT_TYPE_IPV4_TCP = 0x003, + IONIC_PKT_TYPE_IPV4_UDP = 0x005, + IONIC_PKT_TYPE_IPV6 = 0x008, + IONIC_PKT_TYPE_IPV6_TCP = 0x018, + IONIC_PKT_TYPE_IPV6_UDP = 0x028, +}; + +enum ionic_eth_hw_features { + IONIC_ETH_HW_VLAN_TX_TAG = BIT(0), + IONIC_ETH_HW_VLAN_RX_STRIP = BIT(1), + IONIC_ETH_HW_VLAN_RX_FILTER = BIT(2), + IONIC_ETH_HW_RX_HASH = BIT(3), + IONIC_ETH_HW_RX_CSUM = BIT(4), + IONIC_ETH_HW_TX_SG = BIT(5), + IONIC_ETH_HW_RX_SG = BIT(6), + IONIC_ETH_HW_TX_CSUM = BIT(7), + IONIC_ETH_HW_TSO = BIT(8), + IONIC_ETH_HW_TSO_IPV6 = BIT(9), + IONIC_ETH_HW_TSO_ECN = BIT(10), + IONIC_ETH_HW_TSO_GRE = BIT(11), + IONIC_ETH_HW_TSO_GRE_CSUM = BIT(12), + IONIC_ETH_HW_TSO_IPXIP4 = BIT(13), + IONIC_ETH_HW_TSO_IPXIP6 = BIT(14), + IONIC_ETH_HW_TSO_UDP = BIT(15), + IONIC_ETH_HW_TSO_UDP_CSUM = BIT(16), +}; + +/** + * struct q_control_cmd - Queue control command + * @opcode: opcode + * @type: Queue type + * @lif_index: LIF index + * @index: Queue index + * @oper: Operation (enum q_control_oper) + */ +struct ionic_q_control_cmd { + u8 opcode; + u8 type; + __le16 lif_index; + __le32 index; + u8 oper; + u8 rsvd[55]; +}; + +typedef struct ionic_admin_comp ionic_q_control_comp; + +enum q_control_oper { + IONIC_Q_DISABLE = 0, + IONIC_Q_ENABLE = 1, + IONIC_Q_HANG_RESET = 2, +}; + +/** + * Physical connection type + */ +enum ionic_phy_type { + IONIC_PHY_TYPE_NONE = 0, + IONIC_PHY_TYPE_COPPER = 1, + IONIC_PHY_TYPE_FIBER = 2, +}; + +/** + * Transceiver status + */ +enum ionic_xcvr_state { + IONIC_XCVR_STATE_REMOVED = 0, + IONIC_XCVR_STATE_INSERTED = 1, + IONIC_XCVR_STATE_PENDING = 2, + IONIC_XCVR_STATE_SPROM_READ = 3, + IONIC_XCVR_STATE_SPROM_READ_ERR = 4, +}; + +/** + * Supported link modes + */ +enum ionic_xcvr_pid { + IONIC_XCVR_PID_UNKNOWN = 0, + + /* CU */ + IONIC_XCVR_PID_QSFP_100G_CR4 = 1, + IONIC_XCVR_PID_QSFP_40GBASE_CR4 = 2, + IONIC_XCVR_PID_SFP_25GBASE_CR_S = 3, + IONIC_XCVR_PID_SFP_25GBASE_CR_L = 4, + IONIC_XCVR_PID_SFP_25GBASE_CR_N = 5, + + /* Fiber */ + IONIC_XCVR_PID_QSFP_100G_AOC = 50, + IONIC_XCVR_PID_QSFP_100G_ACC = 51, + IONIC_XCVR_PID_QSFP_100G_SR4 = 52, + IONIC_XCVR_PID_QSFP_100G_LR4 = 53, + IONIC_XCVR_PID_QSFP_100G_ER4 = 54, + IONIC_XCVR_PID_QSFP_40GBASE_ER4 = 55, + IONIC_XCVR_PID_QSFP_40GBASE_SR4 = 56, + IONIC_XCVR_PID_QSFP_40GBASE_LR4 = 57, + IONIC_XCVR_PID_QSFP_40GBASE_AOC = 58, + IONIC_XCVR_PID_SFP_25GBASE_SR = 59, + IONIC_XCVR_PID_SFP_25GBASE_LR = 60, + IONIC_XCVR_PID_SFP_25GBASE_ER = 61, + IONIC_XCVR_PID_SFP_25GBASE_AOC = 62, + IONIC_XCVR_PID_SFP_10GBASE_SR = 63, + IONIC_XCVR_PID_SFP_10GBASE_LR = 64, + IONIC_XCVR_PID_SFP_10GBASE_LRM = 65, + IONIC_XCVR_PID_SFP_10GBASE_ER = 66, + IONIC_XCVR_PID_SFP_10GBASE_AOC = 67, + IONIC_XCVR_PID_SFP_10GBASE_CU = 68, + IONIC_XCVR_PID_QSFP_100G_CWDM4 = 69, + IONIC_XCVR_PID_QSFP_100G_PSM4 = 70, +}; + +/** + * Port types + */ +enum ionic_port_type { + IONIC_PORT_TYPE_NONE = 0, /* port type not configured */ + IONIC_PORT_TYPE_ETH = 1, /* port carries ethernet traffic (inband) */ + IONIC_PORT_TYPE_MGMT = 2, /* port carries mgmt traffic (out-of-band) */ +}; + +/** + * Port config state + */ +enum ionic_port_admin_state { + IONIC_PORT_ADMIN_STATE_NONE = 0, /* port admin state not configured */ + IONIC_PORT_ADMIN_STATE_DOWN = 1, /* port is admin disabled */ + IONIC_PORT_ADMIN_STATE_UP = 2, /* port is admin enabled */ +}; + +/** + * Port operational status + */ +enum ionic_port_oper_status { + IONIC_PORT_OPER_STATUS_NONE = 0, /* port is disabled */ + IONIC_PORT_OPER_STATUS_UP = 1, /* port is linked up */ + IONIC_PORT_OPER_STATUS_DOWN = 2, /* port link status is down */ +}; + +/** + * Ethernet Forward error correction (fec) modes + */ +enum ionic_port_fec_type { + IONIC_PORT_FEC_TYPE_NONE = 0, /* Disabled */ + IONIC_PORT_FEC_TYPE_FC = 1, /* FireCode */ + IONIC_PORT_FEC_TYPE_RS = 2, /* ReedSolomon */ +}; + +/** + * Ethernet pause (flow control) modes + */ +enum ionic_port_pause_type { + IONIC_PORT_PAUSE_TYPE_NONE = 0, /* Disable Pause */ + IONIC_PORT_PAUSE_TYPE_LINK = 1, /* Link level pause */ + IONIC_PORT_PAUSE_TYPE_PFC = 2, /* Priority-Flow control */ +}; + +/** + * Loopback modes + */ +enum ionic_port_loopback_mode { + IONIC_PORT_LOOPBACK_MODE_NONE = 0, /* Disable loopback */ + IONIC_PORT_LOOPBACK_MODE_MAC = 1, /* MAC loopback */ + IONIC_PORT_LOOPBACK_MODE_PHY = 2, /* PHY/Serdes loopback */ +}; + +/** + * Transceiver Status information + * @state: Transceiver status (enum xcvr_state) + * @phy: Physical connection type (enum phy_type) + * @pid: Transceiver link mode (enum pid) + * @sprom: Transceiver sprom contents + */ +struct ionic_xcvr_status { + u8 state; + u8 phy; + __le16 pid; + u8 sprom[256]; +}; + +/** + * Port configuration + * @speed: port speed (in Mbps) + * @mtu: mtu + * @state: port admin state (enum port_admin_state) + * @an_enable: autoneg enable + * @fec_type: fec type (enum port_fec_type) + * @pause_type: pause type (enum port_pause_type) + * @loopback_mode: loopback mode (enum port_loopback_mode) + */ +union ionic_port_config { + struct { +#define IONIC_SPEED_100G 100000 /* 100G in Mbps */ +#define IONIC_SPEED_50G 50000 /* 50G in Mbps */ +#define IONIC_SPEED_40G 40000 /* 40G in Mbps */ +#define IONIC_SPEED_25G 25000 /* 25G in Mbps */ +#define IONIC_SPEED_10G 10000 /* 10G in Mbps */ +#define IONIC_SPEED_1G 1000 /* 1G in Mbps */ + __le32 speed; + __le32 mtu; + u8 state; + u8 an_enable; + u8 fec_type; +#define IONIC_PAUSE_TYPE_MASK 0x0f +#define IONIC_PAUSE_FLAGS_MASK 0xf0 +#define IONIC_PAUSE_F_TX 0x10 +#define IONIC_PAUSE_F_RX 0x20 + u8 pause_type; + u8 loopback_mode; + }; + __le32 words[64]; +}; + +/** + * Port Status information + * @status: link status (enum port_oper_status) + * @id: port id + * @speed: link speed (in Mbps) + * @xcvr: tranceiver status + */ +struct ionic_port_status { + __le32 id; + __le32 speed; + u8 status; + u8 rsvd[51]; + struct ionic_xcvr_status xcvr; +}; + +/** + * struct port_identify_cmd - Port identify command + * @opcode: opcode + * @index: port index + * @ver: Highest version of identify supported by driver + */ +struct ionic_port_identify_cmd { + u8 opcode; + u8 index; + u8 ver; + u8 rsvd[61]; +}; + +/** + * struct port_identify_comp - Port identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_port_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +/** + * struct port_init_cmd - Port initialization command + * @opcode: opcode + * @index: port index + * @info_pa: destination address for port info (struct port_info) + */ +struct ionic_port_init_cmd { + u8 opcode; + u8 index; + u8 rsvd[6]; + __le64 info_pa; + u8 rsvd2[48]; +}; + +/** + * struct port_init_comp - Port initialization command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_port_init_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct port_reset_cmd - Port reset command + * @opcode: opcode + * @index: port index + */ +struct ionic_port_reset_cmd { + u8 opcode; + u8 index; + u8 rsvd[62]; +}; + +/** + * struct port_reset_comp - Port reset command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_port_reset_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * enum stats_ctl_cmd - List of commands for stats control + */ +enum ionic_stats_ctl_cmd { + IONIC_STATS_CTL_RESET = 0, +}; + + +/** + * enum ionic_port_attr - List of device attributes + */ +enum ionic_port_attr { + IONIC_PORT_ATTR_STATE = 0, + IONIC_PORT_ATTR_SPEED = 1, + IONIC_PORT_ATTR_MTU = 2, + IONIC_PORT_ATTR_AUTONEG = 3, + IONIC_PORT_ATTR_FEC = 4, + IONIC_PORT_ATTR_PAUSE = 5, + IONIC_PORT_ATTR_LOOPBACK = 6, + IONIC_PORT_ATTR_STATS_CTRL = 7, +}; + +/** + * struct port_setattr_cmd - Set port attributes on the NIC + * @opcode: Opcode + * @index: port index + * @attr: Attribute type (enum ionic_port_attr) + */ +struct ionic_port_setattr_cmd { + u8 opcode; + u8 index; + u8 attr; + u8 rsvd; + union { + u8 state; + __le32 speed; + __le32 mtu; + u8 an_enable; + u8 fec_type; + u8 pause_type; + u8 loopback_mode; + u8 stats_ctl; + u8 rsvd2[60]; + }; +}; + +/** + * struct port_setattr_comp - Port set attr command completion + * @status: The status of the command (enum status_code) + * @color: Color bit + */ +struct ionic_port_setattr_comp { + u8 status; + u8 rsvd[14]; + u8 color; +}; + +/** + * struct port_getattr_cmd - Get port attributes from the NIC + * @opcode: Opcode + * @index: port index + * @attr: Attribute type (enum ionic_port_attr) + */ +struct ionic_port_getattr_cmd { + u8 opcode; + u8 index; + u8 attr; + u8 rsvd[61]; +}; + +/** + * struct port_getattr_comp - Port get attr command completion + * @status: The status of the command (enum status_code) + * @color: Color bit + */ +struct ionic_port_getattr_comp { + u8 status; + u8 rsvd[3]; + union { + u8 state; + __le32 speed; + __le32 mtu; + u8 an_enable; + u8 fec_type; + u8 pause_type; + u8 loopback_mode; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct lif_status - Lif status register + * @eid: most recent NotifyQ event id + * @port_num: port the lif is connected to + * @link_status: port status (enum port_oper_status) + * @link_speed: speed of link in Mbps + * @link_down_count: number of times link status changes + */ +struct ionic_lif_status { + __le64 eid; + u8 port_num; + u8 rsvd; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: eg 10000 = 10Gbps */ + __le16 link_down_count; + u8 rsvd2[46]; +}; + +/** + * struct lif_reset_cmd - LIF reset command + * @opcode: opcode + * @index: LIF index + */ +struct ionic_lif_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 index; + __le32 rsvd2[15]; +}; + +typedef struct ionic_admin_comp ionic_lif_reset_comp; + +enum ionic_dev_state { + IONIC_DEV_DISABLE = 0, + IONIC_DEV_ENABLE = 1, + IONIC_DEV_HANG_RESET = 2, +}; + +/** + * enum dev_attr - List of device attributes + */ +enum ionic_dev_attr { + IONIC_DEV_ATTR_STATE = 0, + IONIC_DEV_ATTR_NAME = 1, + IONIC_DEV_ATTR_FEATURES = 2, +}; + +/** + * struct dev_setattr_cmd - Set Device attributes on the NIC + * @opcode: Opcode + * @attr: Attribute type (enum dev_attr) + * @state: Device state (enum dev_state) + * @name: The bus info, e.g. PCI slot-device-function, 0 terminated + * @features: Device features + */ +struct ionic_dev_setattr_cmd { + u8 opcode; + u8 attr; + __le16 rsvd; + union { + u8 state; + char name[IONIC_IFNAMSIZ]; + __le64 features; + u8 rsvd2[60]; + }; +}; + +/** + * struct dev_setattr_comp - Device set attr command completion + * @status: The status of the command (enum status_code) + * @features: Device features + * @color: Color bit + */ +struct ionic_dev_setattr_comp { + u8 status; + u8 rsvd[3]; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct dev_getattr_cmd - Get Device attributes from the NIC + * @opcode: opcode + * @attr: Attribute type (enum dev_attr) + */ +struct ionic_dev_getattr_cmd { + u8 opcode; + u8 attr; + u8 rsvd[62]; +}; + +/** + * struct dev_setattr_comp - Device set attr command completion + * @status: The status of the command (enum status_code) + * @features: Device features + * @color: Color bit + */ +struct ionic_dev_getattr_comp { + u8 status; + u8 rsvd[3]; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * RSS parameters + */ +#define IONIC_RSS_HASH_KEY_SIZE 40 + +enum ionic_rss_hash_types { + IONIC_RSS_TYPE_IPV4 = BIT(0), + IONIC_RSS_TYPE_IPV4_TCP = BIT(1), + IONIC_RSS_TYPE_IPV4_UDP = BIT(2), + IONIC_RSS_TYPE_IPV6 = BIT(3), + IONIC_RSS_TYPE_IPV6_TCP = BIT(4), + IONIC_RSS_TYPE_IPV6_UDP = BIT(5), +}; + +/** + * enum lif_attr - List of LIF attributes + */ +enum ionic_lif_attr { + IONIC_LIF_ATTR_STATE = 0, + IONIC_LIF_ATTR_NAME = 1, + IONIC_LIF_ATTR_MTU = 2, + IONIC_LIF_ATTR_MAC = 3, + IONIC_LIF_ATTR_FEATURES = 4, + IONIC_LIF_ATTR_RSS = 5, + IONIC_LIF_ATTR_STATS_CTRL = 6, +}; + +/** + * struct lif_setattr_cmd - Set LIF attributes on the NIC + * @opcode: Opcode + * @type: Attribute type (enum lif_attr) + * @index: LIF index + * @state: lif state (enum lif_state) + * @name: The netdev name string, 0 terminated + * @mtu: Mtu + * @mac: Station mac + * @features: Features (enum eth_hw_features) + * @rss: RSS properties + * @types: The hash types to enable (see rss_hash_types). + * @key: The hash secret key. + * @addr: Address for the indirection table shared memory. + * @stats_ctl: stats control commands (enum stats_ctl_cmd) + */ +struct ionic_lif_setattr_cmd { + u8 opcode; + u8 attr; + __le16 index; + union { + u8 state; + char name[IONIC_IFNAMSIZ]; + __le32 mtu; + u8 mac[6]; + __le64 features; + struct { + __le16 types; + u8 key[IONIC_RSS_HASH_KEY_SIZE]; + u8 rsvd[6]; + __le64 addr; + } rss; + u8 stats_ctl; + u8 rsvd[60]; + }; +}; + +/** + * struct lif_setattr_comp - LIF set attr command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @features: features (enum eth_hw_features) + * @color: Color bit + */ +struct ionic_lif_setattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct lif_getattr_cmd - Get LIF attributes from the NIC + * @opcode: Opcode + * @attr: Attribute type (enum lif_attr) + * @index: LIF index + */ +struct ionic_lif_getattr_cmd { + u8 opcode; + u8 attr; + __le16 index; + u8 rsvd[60]; +}; + +/** + * struct lif_getattr_comp - LIF get attr command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @state: lif state (enum lif_state) + * @name: The netdev name string, 0 terminated + * @mtu: Mtu + * @mac: Station mac + * @features: Features (enum eth_hw_features) + * @color: Color bit + */ +struct ionic_lif_getattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + u8 state; + __le32 mtu; + u8 mac[6]; + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +enum ionic_rx_mode { + IONIC_RX_MODE_F_UNICAST = BIT(0), + IONIC_RX_MODE_F_MULTICAST = BIT(1), + IONIC_RX_MODE_F_BROADCAST = BIT(2), + IONIC_RX_MODE_F_PROMISC = BIT(3), + IONIC_RX_MODE_F_ALLMULTI = BIT(4), +}; + +/** + * struct rx_mode_set_cmd - Set LIF's Rx mode command + * @opcode: opcode + * @lif_index: LIF index + * @rx_mode: Rx mode flags: + * IONIC_RX_MODE_F_UNICAST: Accept known unicast packets. + * IONIC_RX_MODE_F_MULTICAST: Accept known multicast packets. + * IONIC_RX_MODE_F_BROADCAST: Accept broadcast packets. + * IONIC_RX_MODE_F_PROMISC: Accept any packets. + * IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets. + */ +struct ionic_rx_mode_set_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le16 rx_mode; + __le16 rsvd2[29]; +}; + +typedef struct ionic_admin_comp ionic_rx_mode_set_comp; + +enum ionic_rx_filter_match_type { + IONIC_RX_FILTER_MATCH_VLAN = 0, + IONIC_RX_FILTER_MATCH_MAC, + IONIC_RX_FILTER_MATCH_MAC_VLAN, +}; + +/** + * struct rx_filter_add_cmd - Add LIF Rx filter command + * @opcode: opcode + * @qtype: Queue type + * @lif_index: LIF index + * @qid: Queue ID + * @match: Rx filter match type. (See IONIC_RX_FILTER_MATCH_xxx) + * @vlan: VLAN ID + * @addr: MAC address (network-byte order) + */ +struct ionic_rx_filter_add_cmd { + u8 opcode; + u8 qtype; + __le16 lif_index; + __le32 qid; + __le16 match; + union { + struct { + __le16 vlan; + } vlan; + struct { + u8 addr[6]; + } mac; + struct { + __le16 vlan; + u8 addr[6]; + } mac_vlan; + u8 rsvd[54]; + }; +}; + +/** + * struct rx_filter_add_comp - Add LIF Rx filter command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @filter_id: Filter ID + * @color: Color bit. + */ +struct ionic_rx_filter_add_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le32 filter_id; + u8 rsvd2[7]; + u8 color; +}; + +/** + * struct rx_filter_del_cmd - Delete LIF Rx filter command + * @opcode: opcode + * @lif_index: LIF index + * @filter_id: Filter ID + */ +struct ionic_rx_filter_del_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le32 filter_id; + u8 rsvd2[56]; +}; + +typedef struct ionic_admin_comp ionic_rx_filter_del_comp; + +/** + * struct qos_identify_cmd - QoS identify command + * @opcode: opcode + * @ver: Highest version of identify supported by driver + * + */ +struct ionic_qos_identify_cmd { + u8 opcode; + u8 ver; + u8 rsvd[62]; +}; + +/** + * struct qos_identify_comp - QoS identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_qos_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +#define IONIC_QOS_CLASS_MAX 7 +#define IONIC_QOS_CLASS_NAME_SZ 32 +#define IONIC_QOS_DSCP_MAX_VALUES 64 + +/** + * enum qos_class + */ +enum ionic_qos_class { + IONIC_QOS_CLASS_DEFAULT = 0, + IONIC_QOS_CLASS_USER_DEFINED_1 = 1, + IONIC_QOS_CLASS_USER_DEFINED_2 = 2, + IONIC_QOS_CLASS_USER_DEFINED_3 = 3, + IONIC_QOS_CLASS_USER_DEFINED_4 = 4, + IONIC_QOS_CLASS_USER_DEFINED_5 = 5, + IONIC_QOS_CLASS_USER_DEFINED_6 = 6, +}; + +/** + * enum qos_class_type - Traffic classification criteria + */ +enum ionic_qos_class_type { + IONIC_QOS_CLASS_TYPE_NONE = 0, + IONIC_QOS_CLASS_TYPE_PCP = 1, /* Dot1Q pcp */ + IONIC_QOS_CLASS_TYPE_DSCP = 2, /* IP dscp */ +}; + +/** + * enum qos_sched_type - Qos class scheduling type + */ +enum ionic_qos_sched_type { + IONIC_QOS_SCHED_TYPE_STRICT = 0, /* Strict priority */ + IONIC_QOS_SCHED_TYPE_DWRR = 1, /* Deficit weighted round-robin */ +}; + +/** + * union qos_config - Qos configuration structure + * @flags: Configuration flags + * IONIC_QOS_CONFIG_F_ENABLE enable + * IONIC_QOS_CONFIG_F_DROP drop/nodrop + * IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP enable dot1q pcp rewrite + * IONIC_QOS_CONFIG_F_RW_IP_DSCP enable ip dscp rewrite + * @sched_type: Qos class scheduling type (enum qos_sched_type) + * @class_type: Qos class type (enum qos_class_type) + * @pause_type: Qos pause type (enum qos_pause_type) + * @name: Qos class name + * @mtu: MTU of the class + * @pfc_dot1q_pcp: Pcp value for pause frames (valid iff F_NODROP) + * @dwrr_weight: Qos class scheduling weight + * @strict_rlmt: Rate limit for strict priority scheduling + * @rw_dot1q_pcp: Rewrite dot1q pcp to this value (valid iff F_RW_DOT1Q_PCP) + * @rw_ip_dscp: Rewrite ip dscp to this value (valid iff F_RW_IP_DSCP) + * @dot1q_pcp: Dot1q pcp value + * @ndscp: Number of valid dscp values in the ip_dscp field + * @ip_dscp: IP dscp values + */ +union ionic_qos_config { + struct { +#define IONIC_QOS_CONFIG_F_ENABLE BIT(0) +#define IONIC_QOS_CONFIG_F_DROP BIT(1) +#define IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP BIT(2) +#define IONIC_QOS_CONFIG_F_RW_IP_DSCP BIT(3) + u8 flags; + u8 sched_type; + u8 class_type; + u8 pause_type; + char name[IONIC_QOS_CLASS_NAME_SZ]; + __le32 mtu; + /* flow control */ + u8 pfc_cos; + /* scheduler */ + union { + u8 dwrr_weight; + __le64 strict_rlmt; + }; + /* marking */ + union { + u8 rw_dot1q_pcp; + u8 rw_ip_dscp; + }; + /* classification */ + union { + u8 dot1q_pcp; + struct { + u8 ndscp; + u8 ip_dscp[IONIC_QOS_DSCP_MAX_VALUES]; + }; + }; + }; + __le32 words[64]; +}; + +/** + * union qos_identity - QoS identity structure + * @version: Version of the identify structure + * @type: QoS system type + * @nclasses: Number of usable QoS classes + * @config: Current configuration of classes + */ +union ionic_qos_identity { + struct { + u8 version; + u8 type; + u8 rsvd[62]; + union ionic_qos_config config[IONIC_QOS_CLASS_MAX]; + }; + __le32 words[512]; +}; + +/** + * struct qos_init_cmd - QoS config init command + * @opcode: Opcode + * @group: Qos class id + * @info_pa: destination address for qos info + */ +struct ionic_qos_init_cmd { + u8 opcode; + u8 group; + u8 rsvd[6]; + __le64 info_pa; + u8 rsvd1[48]; +}; + +typedef struct ionic_admin_comp ionic_qos_init_comp; + +/** + * struct qos_reset_cmd - Qos config reset command + * @opcode: Opcode + */ +struct ionic_qos_reset_cmd { + u8 opcode; + u8 group; + u8 rsvd[62]; +}; + +typedef struct ionic_admin_comp ionic_qos_reset_comp; + +/** + * struct fw_download_cmd - Firmware download command + * @opcode: opcode + * @addr: dma address of the firmware buffer + * @offset: offset of the firmware buffer within the full image + * @length: number of valid bytes in the firmware buffer + */ +struct ionic_fw_download_cmd { + u8 opcode; + u8 rsvd[3]; + __le32 offset; + __le64 addr; + __le32 length; +}; + +typedef struct ionic_admin_comp ionic_fw_download_comp; + +enum ionic_fw_control_oper { + IONIC_FW_RESET = 0, /* Reset firmware */ + IONIC_FW_INSTALL = 1, /* Install firmware */ + IONIC_FW_ACTIVATE = 2, /* Activate firmware */ +}; + +/** + * struct fw_control_cmd - Firmware control command + * @opcode: opcode + * @oper: firmware control operation (enum fw_control_oper) + * @slot: slot to activate + */ +struct ionic_fw_control_cmd { + u8 opcode; + u8 rsvd[3]; + u8 oper; + u8 slot; + u8 rsvd1[58]; +}; + +/** + * struct fw_control_comp - Firmware control copletion + * @opcode: opcode + * @slot: slot where the firmware was installed + */ +struct ionic_fw_control_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 slot; + u8 rsvd1[10]; + u8 color; +}; + +/****************************************************************** + ******************* RDMA Commands ******************************** + ******************************************************************/ + +/** + * struct rdma_reset_cmd - Reset RDMA LIF cmd + * @opcode: opcode + * @lif_index: lif index + * + * There is no rdma specific dev command completion struct. Completion uses + * the common struct admin_comp. Only the status is indicated. Nonzero status + * means the LIF does not support rdma. + **/ +struct ionic_rdma_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 rsvd2[60]; +}; + +/** + * struct rdma_queue_cmd - Create RDMA Queue command + * @opcode: opcode, 52, 53 + * @lif_index lif index + * @qid_ver: (qid | (rdma version << 24)) + * @cid: intr, eq_id, or cq_id + * @dbid: doorbell page id + * @depth_log2: log base two of queue depth + * @stride_log2: log base two of queue stride + * @dma_addr: address of the queue memory + * @xxx_table_index: temporary, but should not need pgtbl for contig. queues. + * + * The same command struct is used to create an rdma event queue, completion + * queue, or rdma admin queue. The cid is an interrupt number for an event + * queue, an event queue id for a completion queue, or a completion queue id + * for an rdma admin queue. + * + * The queue created via a dev command must be contiguous in dma space. + * + * The dev commands are intended only to be used during driver initialization, + * to create queues supporting the rdma admin queue. Other queues, and other + * types of rdma resources like memory regions, will be created and registered + * via the rdma admin queue, and will support a more complete interface + * providing scatter gather lists for larger, scattered queue buffers and + * memory registration. + * + * There is no rdma specific dev command completion struct. Completion uses + * the common struct admin_comp. Only the status is indicated. + **/ +struct ionic_rdma_queue_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le32 qid_ver; + __le32 cid; + __le16 dbid; + u8 depth_log2; + u8 stride_log2; + __le64 dma_addr; + u8 rsvd2[36]; + __le32 xxx_table_index; +}; + +/****************************************************************** + ******************* Notify Events ******************************** + ******************************************************************/ + +/** + * struct notifyq_event + * @eid: event number + * @ecode: event code + * @data: unspecified data about the event + * + * This is the generic event report struct from which the other + * actual events will be formed. + */ +struct ionic_notifyq_event { + __le64 eid; + __le16 ecode; + u8 data[54]; +}; + +/** + * struct link_change_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_LINK_CHANGE + * @link_status: link up or down, with error bits (enum port_status) + * @link_speed: speed of the network link + * + * Sent when the network link state changes between UP and DOWN + */ +struct ionic_link_change_event { + __le64 eid; + __le16 ecode; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: e.g. 10000 = 10Gbps */ + u8 rsvd[48]; +}; + +/** + * struct reset_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_RESET + * @reset_code: reset type + * @state: 0=pending, 1=complete, 2=error + * + * Sent when the NIC or some subsystem is going to be or + * has been reset. + */ +struct ionic_reset_event { + __le64 eid; + __le16 ecode; + u8 reset_code; + u8 state; + u8 rsvd[52]; +}; + +/** + * struct heartbeat_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_HEARTBEAT + * + * Sent periodically by the NIC to indicate continued health + */ +struct ionic_heartbeat_event { + __le64 eid; + __le16 ecode; + u8 rsvd[54]; +}; + +/** + * struct log_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_LOG + * @data: log data + * + * Sent to notify the driver of an internal error. + */ +struct ionic_log_event { + __le64 eid; + __le16 ecode; + u8 data[54]; +}; + +/** + * struct port_stats + */ +struct ionic_port_stats { + __le64 frames_rx_ok; + __le64 frames_rx_all; + __le64 frames_rx_bad_fcs; + __le64 frames_rx_bad_all; + __le64 octets_rx_ok; + __le64 octets_rx_all; + __le64 frames_rx_unicast; + __le64 frames_rx_multicast; + __le64 frames_rx_broadcast; + __le64 frames_rx_pause; + __le64 frames_rx_bad_length; + __le64 frames_rx_undersized; + __le64 frames_rx_oversized; + __le64 frames_rx_fragments; + __le64 frames_rx_jabber; + __le64 frames_rx_pripause; + __le64 frames_rx_stomped_crc; + __le64 frames_rx_too_long; + __le64 frames_rx_vlan_good; + __le64 frames_rx_dropped; + __le64 frames_rx_less_than_64b; + __le64 frames_rx_64b; + __le64 frames_rx_65b_127b; + __le64 frames_rx_128b_255b; + __le64 frames_rx_256b_511b; + __le64 frames_rx_512b_1023b; + __le64 frames_rx_1024b_1518b; + __le64 frames_rx_1519b_2047b; + __le64 frames_rx_2048b_4095b; + __le64 frames_rx_4096b_8191b; + __le64 frames_rx_8192b_9215b; + __le64 frames_rx_other; + __le64 frames_tx_ok; + __le64 frames_tx_all; + __le64 frames_tx_bad; + __le64 octets_tx_ok; + __le64 octets_tx_total; + __le64 frames_tx_unicast; + __le64 frames_tx_multicast; + __le64 frames_tx_broadcast; + __le64 frames_tx_pause; + __le64 frames_tx_pripause; + __le64 frames_tx_vlan; + __le64 frames_tx_less_than_64b; + __le64 frames_tx_64b; + __le64 frames_tx_65b_127b; + __le64 frames_tx_128b_255b; + __le64 frames_tx_256b_511b; + __le64 frames_tx_512b_1023b; + __le64 frames_tx_1024b_1518b; + __le64 frames_tx_1519b_2047b; + __le64 frames_tx_2048b_4095b; + __le64 frames_tx_4096b_8191b; + __le64 frames_tx_8192b_9215b; + __le64 frames_tx_other; + __le64 frames_tx_pri_0; + __le64 frames_tx_pri_1; + __le64 frames_tx_pri_2; + __le64 frames_tx_pri_3; + __le64 frames_tx_pri_4; + __le64 frames_tx_pri_5; + __le64 frames_tx_pri_6; + __le64 frames_tx_pri_7; + __le64 frames_rx_pri_0; + __le64 frames_rx_pri_1; + __le64 frames_rx_pri_2; + __le64 frames_rx_pri_3; + __le64 frames_rx_pri_4; + __le64 frames_rx_pri_5; + __le64 frames_rx_pri_6; + __le64 frames_rx_pri_7; + __le64 tx_pripause_0_1us_count; + __le64 tx_pripause_1_1us_count; + __le64 tx_pripause_2_1us_count; + __le64 tx_pripause_3_1us_count; + __le64 tx_pripause_4_1us_count; + __le64 tx_pripause_5_1us_count; + __le64 tx_pripause_6_1us_count; + __le64 tx_pripause_7_1us_count; + __le64 rx_pripause_0_1us_count; + __le64 rx_pripause_1_1us_count; + __le64 rx_pripause_2_1us_count; + __le64 rx_pripause_3_1us_count; + __le64 rx_pripause_4_1us_count; + __le64 rx_pripause_5_1us_count; + __le64 rx_pripause_6_1us_count; + __le64 rx_pripause_7_1us_count; + __le64 rx_pause_1us_count; + __le64 frames_tx_truncated; +}; + +struct ionic_mgmt_port_stats { + __le64 frames_rx_ok; + __le64 frames_rx_all; + __le64 frames_rx_bad_fcs; + __le64 frames_rx_bad_all; + __le64 octets_rx_ok; + __le64 octets_rx_all; + __le64 frames_rx_unicast; + __le64 frames_rx_multicast; + __le64 frames_rx_broadcast; + __le64 frames_rx_pause; + __le64 frames_rx_bad_length0; + __le64 frames_rx_undersized1; + __le64 frames_rx_oversized2; + __le64 frames_rx_fragments3; + __le64 frames_rx_jabber4; + __le64 frames_rx_64b5; + __le64 frames_rx_65b_127b6; + __le64 frames_rx_128b_255b7; + __le64 frames_rx_256b_511b8; + __le64 frames_rx_512b_1023b9; + __le64 frames_rx_1024b_1518b0; + __le64 frames_rx_gt_1518b1; + __le64 frames_rx_fifo_full2; + __le64 frames_tx_ok3; + __le64 frames_tx_all4; + __le64 frames_tx_bad5; + __le64 octets_tx_ok6; + __le64 octets_tx_total7; + __le64 frames_tx_unicast8; + __le64 frames_tx_multicast9; + __le64 frames_tx_broadcast0; + __le64 frames_tx_pause1; +}; + +/** + * struct port_identity - port identity structure + * @version: identity structure version + * @type: type of port (enum port_type) + * @num_lanes: number of lanes for the port + * @autoneg: autoneg supported + * @min_frame_size: minimum frame size supported + * @max_frame_size: maximum frame size supported + * @fec_type: supported fec types + * @pause_type: supported pause types + * @loopback_mode: supported loopback mode + * @speeds: supported speeds + * @config: current port configuration + */ +union ionic_port_identity { + struct { + u8 version; + u8 type; + u8 num_lanes; + u8 autoneg; + __le32 min_frame_size; + __le32 max_frame_size; + u8 fec_type[4]; + u8 pause_type[2]; + u8 loopback_mode[2]; + __le32 speeds[16]; + u8 rsvd2[44]; + union ionic_port_config config; + }; + __le32 words[512]; +}; + +/** + * struct port_info - port info structure + * @port_status: port status + * @port_stats: port stats + */ +struct ionic_port_info { + union ionic_port_config config; + struct ionic_port_status status; + struct ionic_port_stats stats; +}; + +/** + * struct lif_stats + */ +struct ionic_lif_stats { + /* RX */ + __le64 rx_ucast_bytes; + __le64 rx_ucast_packets; + __le64 rx_mcast_bytes; + __le64 rx_mcast_packets; + __le64 rx_bcast_bytes; + __le64 rx_bcast_packets; + __le64 rsvd0; + __le64 rsvd1; + /* RX drops */ + __le64 rx_ucast_drop_bytes; + __le64 rx_ucast_drop_packets; + __le64 rx_mcast_drop_bytes; + __le64 rx_mcast_drop_packets; + __le64 rx_bcast_drop_bytes; + __le64 rx_bcast_drop_packets; + __le64 rx_dma_error; + __le64 rsvd2; + /* TX */ + __le64 tx_ucast_bytes; + __le64 tx_ucast_packets; + __le64 tx_mcast_bytes; + __le64 tx_mcast_packets; + __le64 tx_bcast_bytes; + __le64 tx_bcast_packets; + __le64 rsvd3; + __le64 rsvd4; + /* TX drops */ + __le64 tx_ucast_drop_bytes; + __le64 tx_ucast_drop_packets; + __le64 tx_mcast_drop_bytes; + __le64 tx_mcast_drop_packets; + __le64 tx_bcast_drop_bytes; + __le64 tx_bcast_drop_packets; + __le64 tx_dma_error; + __le64 rsvd5; + /* Rx Queue/Ring drops */ + __le64 rx_queue_disabled; + __le64 rx_queue_empty; + __le64 rx_queue_error; + __le64 rx_desc_fetch_error; + __le64 rx_desc_data_error; + __le64 rsvd6; + __le64 rsvd7; + __le64 rsvd8; + /* Tx Queue/Ring drops */ + __le64 tx_queue_disabled; + __le64 tx_queue_error; + __le64 tx_desc_fetch_error; + __le64 tx_desc_data_error; + __le64 rsvd9; + __le64 rsvd10; + __le64 rsvd11; + __le64 rsvd12; + + /* RDMA/ROCE TX */ + __le64 tx_rdma_ucast_bytes; + __le64 tx_rdma_ucast_packets; + __le64 tx_rdma_mcast_bytes; + __le64 tx_rdma_mcast_packets; + __le64 tx_rdma_cnp_packets; + __le64 rsvd13; + __le64 rsvd14; + __le64 rsvd15; + + /* RDMA/ROCE RX */ + __le64 rx_rdma_ucast_bytes; + __le64 rx_rdma_ucast_packets; + __le64 rx_rdma_mcast_bytes; + __le64 rx_rdma_mcast_packets; + __le64 rx_rdma_cnp_packets; + __le64 rx_rdma_ecn_packets; + __le64 rsvd16; + __le64 rsvd17; + + __le64 rsvd18; + __le64 rsvd19; + __le64 rsvd20; + __le64 rsvd21; + __le64 rsvd22; + __le64 rsvd23; + __le64 rsvd24; + __le64 rsvd25; + + __le64 rsvd26; + __le64 rsvd27; + __le64 rsvd28; + __le64 rsvd29; + __le64 rsvd30; + __le64 rsvd31; + __le64 rsvd32; + __le64 rsvd33; + + __le64 rsvd34; + __le64 rsvd35; + __le64 rsvd36; + __le64 rsvd37; + __le64 rsvd38; + __le64 rsvd39; + __le64 rsvd40; + __le64 rsvd41; + + __le64 rsvd42; + __le64 rsvd43; + __le64 rsvd44; + __le64 rsvd45; + __le64 rsvd46; + __le64 rsvd47; + __le64 rsvd48; + __le64 rsvd49; + + /* RDMA/ROCE REQ Error/Debugs (768 - 895) */ + __le64 rdma_req_rx_pkt_seq_err; + __le64 rdma_req_rx_rnr_retry_err; + __le64 rdma_req_rx_remote_access_err; + __le64 rdma_req_rx_remote_inv_req_err; + __le64 rdma_req_rx_remote_oper_err; + __le64 rdma_req_rx_implied_nak_seq_err; + __le64 rdma_req_rx_cqe_err; + __le64 rdma_req_rx_cqe_flush_err; + + __le64 rdma_req_rx_dup_responses; + __le64 rdma_req_rx_invalid_packets; + __le64 rdma_req_tx_local_access_err; + __le64 rdma_req_tx_local_oper_err; + __le64 rdma_req_tx_memory_mgmt_err; + __le64 rsvd52; + __le64 rsvd53; + __le64 rsvd54; + + /* RDMA/ROCE RESP Error/Debugs (896 - 1023) */ + __le64 rdma_resp_rx_dup_requests; + __le64 rdma_resp_rx_out_of_buffer; + __le64 rdma_resp_rx_out_of_seq_pkts; + __le64 rdma_resp_rx_cqe_err; + __le64 rdma_resp_rx_cqe_flush_err; + __le64 rdma_resp_rx_local_len_err; + __le64 rdma_resp_rx_inv_request_err; + __le64 rdma_resp_rx_local_qp_oper_err; + + __le64 rdma_resp_rx_out_of_atomic_resource; + __le64 rdma_resp_tx_pkt_seq_err; + __le64 rdma_resp_tx_remote_inv_req_err; + __le64 rdma_resp_tx_remote_access_err; + __le64 rdma_resp_tx_remote_oper_err; + __le64 rdma_resp_tx_rnr_retry_err; + __le64 rsvd57; + __le64 rsvd58; +}; + +/** + * struct lif_info - lif info structure + */ +struct ionic_lif_info { + union ionic_lif_config config; + struct ionic_lif_status status; + struct ionic_lif_stats stats; +}; + +union ionic_dev_cmd { + u32 words[16]; + struct ionic_admin_cmd cmd; + struct ionic_nop_cmd nop; + + struct ionic_dev_identify_cmd identify; + struct ionic_dev_init_cmd init; + struct ionic_dev_reset_cmd reset; + struct ionic_dev_getattr_cmd getattr; + struct ionic_dev_setattr_cmd setattr; + + struct ionic_port_identify_cmd port_identify; + struct ionic_port_init_cmd port_init; + struct ionic_port_reset_cmd port_reset; + struct ionic_port_getattr_cmd port_getattr; + struct ionic_port_setattr_cmd port_setattr; + + struct ionic_lif_identify_cmd lif_identify; + struct ionic_lif_init_cmd lif_init; + struct ionic_lif_reset_cmd lif_reset; + + struct ionic_qos_identify_cmd qos_identify; + struct ionic_qos_init_cmd qos_init; + struct ionic_qos_reset_cmd qos_reset; + + struct ionic_q_init_cmd q_init; +}; + +union ionic_dev_cmd_comp { + u32 words[4]; + u8 status; + struct ionic_admin_comp comp; + struct ionic_nop_comp nop; + + struct ionic_dev_identify_comp identify; + struct ionic_dev_init_comp init; + struct ionic_dev_reset_comp reset; + struct ionic_dev_getattr_comp getattr; + struct ionic_dev_setattr_comp setattr; + + struct ionic_port_identify_comp port_identify; + struct ionic_port_init_comp port_init; + struct ionic_port_reset_comp port_reset; + struct ionic_port_getattr_comp port_getattr; + struct ionic_port_setattr_comp port_setattr; + + struct ionic_lif_identify_comp lif_identify; + struct ionic_lif_init_comp lif_init; + ionic_lif_reset_comp lif_reset; + + struct ionic_qos_identify_comp qos_identify; + ionic_qos_init_comp qos_init; + ionic_qos_reset_comp qos_reset; + + struct ionic_q_init_comp q_init; +}; + +/** + * union dev_info - Device info register format (read-only) + * @signature: Signature value of 0x44455649 ('DEVI'). + * @version: Current version of info. + * @asic_type: Asic type. + * @asic_rev: Asic revision. + * @fw_status: Firmware status. + * @fw_heartbeat: Firmware heartbeat counter. + * @serial_num: Serial number. + * @fw_version: Firmware version. + */ +union ionic_dev_info_regs { +#define IONIC_DEVINFO_FWVERS_BUFLEN 32 +#define IONIC_DEVINFO_SERIAL_BUFLEN 32 + struct { + u32 signature; + u8 version; + u8 asic_type; + u8 asic_rev; + u8 fw_status; + u32 fw_heartbeat; + char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; + char serial_num[IONIC_DEVINFO_SERIAL_BUFLEN]; + }; + u32 words[512]; +}; + +/** + * union dev_cmd_regs - Device command register format (read-write) + * @doorbell: Device Cmd Doorbell, write-only. + * Write a 1 to signal device to process cmd, + * poll done for completion. + * @done: Done indicator, bit 0 == 1 when command is complete. + * @cmd: Opcode-specific command bytes + * @comp: Opcode-specific response bytes + * @data: Opcode-specific side-data + */ +union ionic_dev_cmd_regs { + struct { + u32 doorbell; + u32 done; + union ionic_dev_cmd cmd; + union ionic_dev_cmd_comp comp; + u8 rsvd[48]; + u32 data[478]; + }; + u32 words[512]; +}; + +/** + * union dev_regs - Device register format in for bar 0 page 0 + * @info: Device info registers + * @devcmd: Device command registers + */ +union ionic_dev_regs { + struct { + union ionic_dev_info_regs info; + union ionic_dev_cmd_regs devcmd; + }; + __le32 words[1024]; +}; + +union ionic_adminq_cmd { + struct ionic_admin_cmd cmd; + struct ionic_nop_cmd nop; + struct ionic_q_init_cmd q_init; + struct ionic_q_control_cmd q_control; + struct ionic_lif_setattr_cmd lif_setattr; + struct ionic_lif_getattr_cmd lif_getattr; + struct ionic_rx_mode_set_cmd rx_mode_set; + struct ionic_rx_filter_add_cmd rx_filter_add; + struct ionic_rx_filter_del_cmd rx_filter_del; + struct ionic_rdma_reset_cmd rdma_reset; + struct ionic_rdma_queue_cmd rdma_queue; + struct ionic_fw_download_cmd fw_download; + struct ionic_fw_control_cmd fw_control; +}; + +union ionic_adminq_comp { + struct ionic_admin_comp comp; + struct ionic_nop_comp nop; + struct ionic_q_init_comp q_init; + struct ionic_lif_setattr_comp lif_setattr; + struct ionic_lif_getattr_comp lif_getattr; + struct ionic_rx_filter_add_comp rx_filter_add; + struct ionic_fw_control_comp fw_control; +}; + +#define IONIC_BARS_MAX 6 +#define IONIC_PCI_BAR_DBELL 1 + +/* BAR0 */ +#define IONIC_BAR0_SIZE 0x8000 + +#define IONIC_BAR0_DEV_INFO_REGS_OFFSET 0x0000 +#define IONIC_BAR0_DEV_CMD_REGS_OFFSET 0x0800 +#define IONIC_BAR0_DEV_CMD_DATA_REGS_OFFSET 0x0c00 +#define IONIC_BAR0_INTR_STATUS_OFFSET 0x1000 +#define IONIC_BAR0_INTR_CTRL_OFFSET 0x2000 +#define IONIC_DEV_CMD_DONE 0x00000001 + +#define IONIC_ASIC_TYPE_CAPRI 0 + +/** + * struct doorbell - Doorbell register layout + * @p_index: Producer index + * @ring: Selects the specific ring of the queue to update. + * Type-specific meaning: + * ring=0: Default producer/consumer queue. + * ring=1: (CQ, EQ) Re-Arm queue. RDMA CQs + * send events to EQs when armed. EQs send + * interrupts when armed. + * @qid: The queue id selects the queue destination for the + * producer index and flags. + */ +struct ionic_doorbell { + __le16 p_index; + u8 ring; + u8 qid_lo; + __le16 qid_hi; + u16 rsvd2; +}; + +struct ionic_intr_status { + u32 status[2]; +}; + +struct ionic_notifyq_cmd { + __le32 data; /* Not used but needed for qcq structure */ +}; + +union ionic_notifyq_comp { + struct ionic_notifyq_event event; + struct ionic_link_change_event link_change; + struct ionic_reset_event reset; + struct ionic_heartbeat_event heartbeat; + struct ionic_log_event log; +}; + +/* Deprecate */ +struct ionic_identity { + union ionic_drv_identity drv; + union ionic_dev_identity dev; + union ionic_lif_identity lif; + union ionic_port_identity port; + union ionic_qos_identity qos; +}; + +#pragma pack(pop) + +#endif /* _IONIC_IF_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c new file mode 100644 index 000000000000..db7c82742828 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -0,0 +1,2274 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/cpumask.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_txrx.h" +#include "ionic_ethtool.h" +#include "ionic_debugfs.h" + +static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode); +static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr); +static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr); +static void ionic_link_status_check(struct ionic_lif *lif); + +static void ionic_lif_deferred_work(struct work_struct *work) +{ + struct ionic_lif *lif = container_of(work, struct ionic_lif, deferred.work); + struct ionic_deferred *def = &lif->deferred; + struct ionic_deferred_work *w = NULL; + + spin_lock_bh(&def->lock); + if (!list_empty(&def->list)) { + w = list_first_entry(&def->list, + struct ionic_deferred_work, list); + list_del(&w->list); + } + spin_unlock_bh(&def->lock); + + if (w) { + switch (w->type) { + case IONIC_DW_TYPE_RX_MODE: + ionic_lif_rx_mode(lif, w->rx_mode); + break; + case IONIC_DW_TYPE_RX_ADDR_ADD: + ionic_lif_addr_add(lif, w->addr); + break; + case IONIC_DW_TYPE_RX_ADDR_DEL: + ionic_lif_addr_del(lif, w->addr); + break; + case IONIC_DW_TYPE_LINK_STATUS: + ionic_link_status_check(lif); + break; + default: + break; + } + kfree(w); + schedule_work(&def->work); + } +} + +static void ionic_lif_deferred_enqueue(struct ionic_deferred *def, + struct ionic_deferred_work *work) +{ + spin_lock_bh(&def->lock); + list_add_tail(&work->list, &def->list); + spin_unlock_bh(&def->lock); + schedule_work(&def->work); +} + +static void ionic_link_status_check(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + u16 link_status; + bool link_up; + + link_status = le16_to_cpu(lif->info->status.link_status); + link_up = link_status == IONIC_PORT_OPER_STATUS_UP; + + /* filter out the no-change cases */ + if (link_up == netif_carrier_ok(netdev)) + goto link_out; + + if (link_up) { + netdev_info(netdev, "Link up - %d Gbps\n", + le32_to_cpu(lif->info->status.link_speed) / 1000); + + if (test_bit(IONIC_LIF_UP, lif->state)) { + netif_tx_wake_all_queues(lif->netdev); + netif_carrier_on(netdev); + } + } else { + netdev_info(netdev, "Link down\n"); + + /* carrier off first to avoid watchdog timeout */ + netif_carrier_off(netdev); + if (test_bit(IONIC_LIF_UP, lif->state)) + netif_tx_stop_all_queues(netdev); + } + +link_out: + clear_bit(IONIC_LIF_LINK_CHECK_REQUESTED, lif->state); +} + +static void ionic_link_status_check_request(struct ionic_lif *lif) +{ + struct ionic_deferred_work *work; + + /* we only need one request outstanding at a time */ + if (test_and_set_bit(IONIC_LIF_LINK_CHECK_REQUESTED, lif->state)) + return; + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + work->type = IONIC_DW_TYPE_LINK_STATUS; + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_link_status_check(lif); + } +} + +static irqreturn_t ionic_isr(int irq, void *data) +{ + struct napi_struct *napi = data; + + napi_schedule_irqoff(napi); + + return IRQ_HANDLED; +} + +static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct ionic_intr_info *intr = &qcq->intr; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + const char *name; + + if (lif->registered) + name = lif->netdev->name; + else + name = dev_name(dev); + + snprintf(intr->name, sizeof(intr->name), + "%s-%s-%s", IONIC_DRV_NAME, name, q->name); + + return devm_request_irq(dev, intr->vector, ionic_isr, + 0, intr->name, &qcq->napi); +} + +static int ionic_intr_alloc(struct ionic_lif *lif, struct ionic_intr_info *intr) +{ + struct ionic *ionic = lif->ionic; + int index; + + index = find_first_zero_bit(ionic->intrs, ionic->nintrs); + if (index == ionic->nintrs) { + netdev_warn(lif->netdev, "%s: no intr, index=%d nintrs=%d\n", + __func__, index, ionic->nintrs); + return -ENOSPC; + } + + set_bit(index, ionic->intrs); + ionic_intr_init(&ionic->idev, intr, index); + + return 0; +} + +static void ionic_intr_free(struct ionic_lif *lif, int index) +{ + if (index != INTR_INDEX_NOT_ASSIGNED && index < lif->ionic->nintrs) + clear_bit(index, lif->ionic->intrs); +} + +static int ionic_qcq_enable(struct ionic_qcq *qcq) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_lif *lif = q->lif; + struct ionic_dev *idev; + struct device *dev; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_control = { + .opcode = IONIC_CMD_Q_CONTROL, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .oper = IONIC_Q_ENABLE, + }, + }; + + idev = &lif->ionic->idev; + dev = lif->ionic->dev; + + dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", + ctx.cmd.q_control.index, ctx.cmd.q_control.type); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); + napi_enable(&qcq->napi); + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_CLEAR); + } + + return ionic_adminq_post_wait(lif, &ctx); +} + +static int ionic_qcq_disable(struct ionic_qcq *qcq) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_lif *lif = q->lif; + struct ionic_dev *idev; + struct device *dev; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_control = { + .opcode = IONIC_CMD_Q_CONTROL, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .oper = IONIC_Q_DISABLE, + }, + }; + + idev = &lif->ionic->idev; + dev = lif->ionic->dev; + + dev_dbg(dev, "q_disable.index %d q_disable.qtype %d\n", + ctx.cmd.q_control.index, ctx.cmd.q_control.type); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + synchronize_irq(qcq->intr.vector); + irq_set_affinity_hint(qcq->intr.vector, NULL); + napi_disable(&qcq->napi); + } + + return ionic_adminq_post_wait(lif, &ctx); +} + +static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct device *dev = lif->ionic->dev; + + if (!qcq) + return; + + ionic_debugfs_del_qcq(qcq); + + if (!(qcq->flags & IONIC_QCQ_F_INITED)) + return; + + if (qcq->flags & IONIC_QCQ_F_INTR) { + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + devm_free_irq(dev, qcq->intr.vector, &qcq->napi); + netif_napi_del(&qcq->napi); + } + + qcq->flags &= ~IONIC_QCQ_F_INITED; +} + +static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + + if (!qcq) + return; + + dma_free_coherent(dev, qcq->total_size, qcq->base, qcq->base_pa); + qcq->base = NULL; + qcq->base_pa = 0; + + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_free(lif, qcq->intr.index); + + devm_kfree(dev, qcq->cq.info); + qcq->cq.info = NULL; + devm_kfree(dev, qcq->q.info); + qcq->q.info = NULL; + devm_kfree(dev, qcq); +} + +static void ionic_qcqs_free(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + unsigned int i; + + if (lif->notifyqcq) { + ionic_qcq_free(lif, lif->notifyqcq); + lif->notifyqcq = NULL; + } + + if (lif->adminqcq) { + ionic_qcq_free(lif, lif->adminqcq); + lif->adminqcq = NULL; + } + + for (i = 0; i < lif->nxqs; i++) + if (lif->rxqcqs[i].stats) + devm_kfree(dev, lif->rxqcqs[i].stats); + + devm_kfree(dev, lif->rxqcqs); + lif->rxqcqs = NULL; + + for (i = 0; i < lif->nxqs; i++) + if (lif->txqcqs[i].stats) + devm_kfree(dev, lif->txqcqs[i].stats); + + devm_kfree(dev, lif->txqcqs); + lif->txqcqs = NULL; +} + +static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, + struct ionic_qcq *n_qcq) +{ + if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) { + ionic_intr_free(n_qcq->cq.lif, n_qcq->intr.index); + n_qcq->flags &= ~IONIC_QCQ_F_INTR; + } + + n_qcq->intr.vector = src_qcq->intr.vector; + n_qcq->intr.index = src_qcq->intr.index; +} + +static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, + unsigned int index, + const char *name, unsigned int flags, + unsigned int num_descs, unsigned int desc_size, + unsigned int cq_desc_size, + unsigned int sg_desc_size, + unsigned int pid, struct ionic_qcq **qcq) +{ + struct ionic_dev *idev = &lif->ionic->idev; + u32 q_size, cq_size, sg_size, total_size; + struct device *dev = lif->ionic->dev; + void *q_base, *cq_base, *sg_base; + dma_addr_t cq_base_pa = 0; + dma_addr_t sg_base_pa = 0; + dma_addr_t q_base_pa = 0; + struct ionic_qcq *new; + int err; + + *qcq = NULL; + + q_size = num_descs * desc_size; + cq_size = num_descs * cq_desc_size; + sg_size = num_descs * sg_desc_size; + + total_size = ALIGN(q_size, PAGE_SIZE) + ALIGN(cq_size, PAGE_SIZE); + /* Note: aligning q_size/cq_size is not enough due to cq_base + * address aligning as q_base could be not aligned to the page. + * Adding PAGE_SIZE. + */ + total_size += PAGE_SIZE; + if (flags & IONIC_QCQ_F_SG) { + total_size += ALIGN(sg_size, PAGE_SIZE); + total_size += PAGE_SIZE; + } + + new = devm_kzalloc(dev, sizeof(*new), GFP_KERNEL); + if (!new) { + netdev_err(lif->netdev, "Cannot allocate queue structure\n"); + err = -ENOMEM; + goto err_out; + } + + new->flags = flags; + + new->q.info = devm_kzalloc(dev, sizeof(*new->q.info) * num_descs, + GFP_KERNEL); + if (!new->q.info) { + netdev_err(lif->netdev, "Cannot allocate queue info\n"); + err = -ENOMEM; + goto err_out; + } + + new->q.type = type; + + err = ionic_q_init(lif, idev, &new->q, index, name, num_descs, + desc_size, sg_desc_size, pid); + if (err) { + netdev_err(lif->netdev, "Cannot initialize queue\n"); + goto err_out; + } + + if (flags & IONIC_QCQ_F_INTR) { + err = ionic_intr_alloc(lif, &new->intr); + if (err) { + netdev_warn(lif->netdev, "no intr for %s: %d\n", + name, err); + goto err_out; + } + + err = ionic_bus_get_irq(lif->ionic, new->intr.index); + if (err < 0) { + netdev_warn(lif->netdev, "no vector for %s: %d\n", + name, err); + goto err_out_free_intr; + } + new->intr.vector = err; + ionic_intr_mask_assert(idev->intr_ctrl, new->intr.index, + IONIC_INTR_MASK_SET); + + new->intr.cpu = new->intr.index % num_online_cpus(); + if (cpu_online(new->intr.cpu)) + cpumask_set_cpu(new->intr.cpu, + &new->intr.affinity_mask); + } else { + new->intr.index = INTR_INDEX_NOT_ASSIGNED; + } + + new->cq.info = devm_kzalloc(dev, sizeof(*new->cq.info) * num_descs, + GFP_KERNEL); + if (!new->cq.info) { + netdev_err(lif->netdev, "Cannot allocate completion queue info\n"); + err = -ENOMEM; + goto err_out_free_intr; + } + + err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size); + if (err) { + netdev_err(lif->netdev, "Cannot initialize completion queue\n"); + goto err_out_free_intr; + } + + new->base = dma_alloc_coherent(dev, total_size, &new->base_pa, + GFP_KERNEL); + if (!new->base) { + netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n"); + err = -ENOMEM; + goto err_out_free_intr; + } + + new->total_size = total_size; + + q_base = new->base; + q_base_pa = new->base_pa; + + cq_base = (void *)ALIGN((uintptr_t)q_base + q_size, PAGE_SIZE); + cq_base_pa = ALIGN(q_base_pa + q_size, PAGE_SIZE); + + if (flags & IONIC_QCQ_F_SG) { + sg_base = (void *)ALIGN((uintptr_t)cq_base + cq_size, + PAGE_SIZE); + sg_base_pa = ALIGN(cq_base_pa + cq_size, PAGE_SIZE); + ionic_q_sg_map(&new->q, sg_base, sg_base_pa); + } + + ionic_q_map(&new->q, q_base, q_base_pa); + ionic_cq_map(&new->cq, cq_base, cq_base_pa); + ionic_cq_bind(&new->cq, &new->q); + + *qcq = new; + + return 0; + +err_out_free_intr: + ionic_intr_free(lif, new->intr.index); +err_out: + dev_err(dev, "qcq alloc of %s%d failed %d\n", name, index, err); + return err; +} + +static int ionic_qcqs_alloc(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + unsigned int q_list_size; + unsigned int flags; + int err; + int i; + + flags = IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_ADMINQ, 0, "admin", flags, + IONIC_ADMINQ_LENGTH, + sizeof(struct ionic_admin_cmd), + sizeof(struct ionic_admin_comp), + 0, lif->kern_pid, &lif->adminqcq); + if (err) + return err; + + if (lif->ionic->nnqs_per_lif) { + flags = IONIC_QCQ_F_NOTIFYQ; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_NOTIFYQ, 0, "notifyq", + flags, IONIC_NOTIFYQ_LENGTH, + sizeof(struct ionic_notifyq_cmd), + sizeof(union ionic_notifyq_comp), + 0, lif->kern_pid, &lif->notifyqcq); + if (err) + goto err_out_free_adminqcq; + + /* Let the notifyq ride on the adminq interrupt */ + ionic_link_qcq_interrupts(lif->adminqcq, lif->notifyqcq); + } + + q_list_size = sizeof(*lif->txqcqs) * lif->nxqs; + err = -ENOMEM; + lif->txqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + if (!lif->txqcqs) + goto err_out_free_notifyqcq; + for (i = 0; i < lif->nxqs; i++) { + lif->txqcqs[i].stats = devm_kzalloc(dev, + sizeof(struct ionic_q_stats), + GFP_KERNEL); + if (!lif->txqcqs[i].stats) + goto err_out_free_tx_stats; + } + + lif->rxqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + if (!lif->rxqcqs) + goto err_out_free_tx_stats; + for (i = 0; i < lif->nxqs; i++) { + lif->rxqcqs[i].stats = devm_kzalloc(dev, + sizeof(struct ionic_q_stats), + GFP_KERNEL); + if (!lif->rxqcqs[i].stats) + goto err_out_free_rx_stats; + } + + return 0; + +err_out_free_rx_stats: + for (i = 0; i < lif->nxqs; i++) + if (lif->rxqcqs[i].stats) + devm_kfree(dev, lif->rxqcqs[i].stats); + devm_kfree(dev, lif->rxqcqs); + lif->rxqcqs = NULL; +err_out_free_tx_stats: + for (i = 0; i < lif->nxqs; i++) + if (lif->txqcqs[i].stats) + devm_kfree(dev, lif->txqcqs[i].stats); + devm_kfree(dev, lif->txqcqs); + lif->txqcqs = NULL; +err_out_free_notifyqcq: + if (lif->notifyqcq) { + ionic_qcq_free(lif, lif->notifyqcq); + lif->notifyqcq = NULL; + } +err_out_free_adminqcq: + ionic_qcq_free(lif, lif->adminqcq); + lif->adminqcq = NULL; + + return err; +} + +static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_SG), + .intr_index = cpu_to_le16(lif->rxqcqs[q->index].qcq->intr.index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + .cq_ring_base = cpu_to_le64(cq->base_pa), + .sg_ring_base = cpu_to_le64(q->sg_base_pa), + }, + }; + int err; + + dev_dbg(dev, "txq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "txq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "txq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "txq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ), + .intr_index = cpu_to_le16(cq->bound_intr->index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + .cq_ring_base = cpu_to_le64(cq->base_pa), + }, + }; + int err; + + dev_dbg(dev, "rxq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "rxq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "rxq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "rxq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + + netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi, + NAPI_POLL_WEIGHT); + + err = ionic_request_irq(lif, qcq); + if (err) { + netif_napi_del(&qcq->napi); + return err; + } + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static bool ionic_notifyq_service(struct ionic_cq *cq, + struct ionic_cq_info *cq_info) +{ + union ionic_notifyq_comp *comp = cq_info->cq_desc; + struct net_device *netdev; + struct ionic_queue *q; + struct ionic_lif *lif; + u64 eid; + + q = cq->bound_q; + lif = q->info[0].cb_arg; + netdev = lif->netdev; + eid = le64_to_cpu(comp->event.eid); + + /* Have we run out of new completions to process? */ + if (eid <= lif->last_eid) + return false; + + lif->last_eid = eid; + + dev_dbg(lif->ionic->dev, "notifyq event:\n"); + dynamic_hex_dump("event ", DUMP_PREFIX_OFFSET, 16, 1, + comp, sizeof(*comp), true); + + switch (le16_to_cpu(comp->event.ecode)) { + case IONIC_EVENT_LINK_CHANGE: + ionic_link_status_check_request(lif); + break; + case IONIC_EVENT_RESET: + netdev_info(netdev, "Notifyq IONIC_EVENT_RESET eid=%lld\n", + eid); + netdev_info(netdev, " reset_code=%d state=%d\n", + comp->reset.reset_code, + comp->reset.state); + break; + default: + netdev_warn(netdev, "Notifyq unknown event ecode=%d eid=%lld\n", + comp->event.ecode, eid); + break; + } + + return true; +} + +static int ionic_notifyq_clean(struct ionic_lif *lif, int budget) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_cq *cq = &lif->notifyqcq->cq; + u32 work_done; + + work_done = ionic_cq_service(cq, budget, ionic_notifyq_service, + NULL, NULL); + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, IONIC_INTR_CRED_RESET_COALESCE); + + return work_done; +} + +static bool ionic_adminq_service(struct ionic_cq *cq, + struct ionic_cq_info *cq_info) +{ + struct ionic_admin_comp *comp = cq_info->cq_desc; + + if (!color_match(comp->color, cq->done_color)) + return false; + + ionic_q_service(cq->bound_q, cq_info, le16_to_cpu(comp->comp_index)); + + return true; +} + +static int ionic_adminq_napi(struct napi_struct *napi, int budget) +{ + struct ionic_lif *lif = napi_to_cq(napi)->lif; + int n_work = 0; + int a_work = 0; + + if (likely(lif->notifyqcq && lif->notifyqcq->flags & IONIC_QCQ_F_INITED)) + n_work = ionic_notifyq_clean(lif, budget); + a_work = ionic_napi(napi, budget, ionic_adminq_service, NULL, NULL); + + return max(n_work, a_work); +} + +static void ionic_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *ns) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_lif_stats *ls; + + memset(ns, 0, sizeof(*ns)); + ls = &lif->info->stats; + + ns->rx_packets = le64_to_cpu(ls->rx_ucast_packets) + + le64_to_cpu(ls->rx_mcast_packets) + + le64_to_cpu(ls->rx_bcast_packets); + + ns->tx_packets = le64_to_cpu(ls->tx_ucast_packets) + + le64_to_cpu(ls->tx_mcast_packets) + + le64_to_cpu(ls->tx_bcast_packets); + + ns->rx_bytes = le64_to_cpu(ls->rx_ucast_bytes) + + le64_to_cpu(ls->rx_mcast_bytes) + + le64_to_cpu(ls->rx_bcast_bytes); + + ns->tx_bytes = le64_to_cpu(ls->tx_ucast_bytes) + + le64_to_cpu(ls->tx_mcast_bytes) + + le64_to_cpu(ls->tx_bcast_bytes); + + ns->rx_dropped = le64_to_cpu(ls->rx_ucast_drop_packets) + + le64_to_cpu(ls->rx_mcast_drop_packets) + + le64_to_cpu(ls->rx_bcast_drop_packets); + + ns->tx_dropped = le64_to_cpu(ls->tx_ucast_drop_packets) + + le64_to_cpu(ls->tx_mcast_drop_packets) + + le64_to_cpu(ls->tx_bcast_drop_packets); + + ns->multicast = le64_to_cpu(ls->rx_mcast_packets); + + ns->rx_over_errors = le64_to_cpu(ls->rx_queue_empty); + + ns->rx_missed_errors = le64_to_cpu(ls->rx_dma_error) + + le64_to_cpu(ls->rx_queue_disabled) + + le64_to_cpu(ls->rx_desc_fetch_error) + + le64_to_cpu(ls->rx_desc_data_error); + + ns->tx_aborted_errors = le64_to_cpu(ls->tx_dma_error) + + le64_to_cpu(ls->tx_queue_disabled) + + le64_to_cpu(ls->tx_desc_fetch_error) + + le64_to_cpu(ls->tx_desc_data_error); + + ns->rx_errors = ns->rx_over_errors + + ns->rx_missed_errors; + + ns->tx_errors = ns->tx_aborted_errors; +} + +static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_add = { + .opcode = IONIC_CMD_RX_FILTER_ADD, + .lif_index = cpu_to_le16(lif->index), + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }, + }; + struct ionic_rx_filter *f; + int err; + + /* don't bother if we already have it */ + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_by_addr(lif, addr); + spin_unlock_bh(&lif->rx_filters.lock); + if (f) + return 0; + + netdev_dbg(lif->netdev, "rx_filter add ADDR %pM (id %d)\n", addr, + ctx.comp.rx_filter_add.filter_id); + + memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx); +} + +static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + int err; + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_by_addr(lif, addr); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + spin_unlock_bh(&lif->rx_filters.lock); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", addr, + ctx.cmd.rx_filter_del.filter_id); + + return 0; +} + +static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add) +{ + struct ionic *ionic = lif->ionic; + struct ionic_deferred_work *work; + unsigned int nmfilters; + unsigned int nufilters; + + if (add) { + /* Do we have space for this filter? We test the counters + * here before checking the need for deferral so that we + * can return an overflow error to the stack. + */ + nmfilters = le32_to_cpu(ionic->ident.lif.eth.max_mcast_filters); + nufilters = le32_to_cpu(ionic->ident.lif.eth.max_ucast_filters); + + if ((is_multicast_ether_addr(addr) && lif->nmcast < nmfilters)) + lif->nmcast++; + else if (!is_multicast_ether_addr(addr) && + lif->nucast < nufilters) + lif->nucast++; + else + return -ENOSPC; + } else { + if (is_multicast_ether_addr(addr) && lif->nmcast) + lif->nmcast--; + else if (!is_multicast_ether_addr(addr) && lif->nucast) + lif->nucast--; + } + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "%s OOM\n", __func__); + return -ENOMEM; + } + work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD : + IONIC_DW_TYPE_RX_ADDR_DEL; + memcpy(work->addr, addr, ETH_ALEN); + netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n", + add ? "add" : "del", addr); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + netdev_dbg(lif->netdev, "rx_filter %s %pM\n", + add ? "add" : "del", addr); + if (add) + return ionic_lif_addr_add(lif, addr); + else + return ionic_lif_addr_del(lif, addr); + } + + return 0; +} + +static int ionic_addr_add(struct net_device *netdev, const u8 *addr) +{ + return ionic_lif_addr(netdev_priv(netdev), addr, true); +} + +static int ionic_addr_del(struct net_device *netdev, const u8 *addr) +{ + return ionic_lif_addr(netdev_priv(netdev), addr, false); +} + +static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_mode_set = { + .opcode = IONIC_CMD_RX_MODE_SET, + .lif_index = cpu_to_le16(lif->index), + .rx_mode = cpu_to_le16(rx_mode), + }, + }; + char buf[128]; + int err; + int i; +#define REMAIN(__x) (sizeof(buf) - (__x)) + + i = snprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:", + lif->rx_mode, rx_mode); + if (rx_mode & IONIC_RX_MODE_F_UNICAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST"); + if (rx_mode & IONIC_RX_MODE_F_MULTICAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST"); + if (rx_mode & IONIC_RX_MODE_F_BROADCAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST"); + if (rx_mode & IONIC_RX_MODE_F_PROMISC) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC"); + if (rx_mode & IONIC_RX_MODE_F_ALLMULTI) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI"); + netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n", + rx_mode, err); + else + lif->rx_mode = rx_mode; +} + +static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) +{ + struct ionic_deferred_work *work; + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "%s OOM\n", __func__); + return; + } + work->type = IONIC_DW_TYPE_RX_MODE; + work->rx_mode = rx_mode; + netdev_dbg(lif->netdev, "deferred: rx_mode\n"); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_lif_rx_mode(lif, rx_mode); + } +} + +static void ionic_set_rx_mode(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_identity *ident; + unsigned int nfilters; + unsigned int rx_mode; + + ident = &lif->ionic->ident; + + rx_mode = IONIC_RX_MODE_F_UNICAST; + rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; + rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; + rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; + rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; + + /* sync unicast addresses + * next check to see if we're in an overflow state + * if so, we track that we overflowed and enable NIC PROMISC + * else if the overflow is set and not needed + * we remove our overflow flag and check the netdev flags + * to see if we can disable NIC PROMISC + */ + __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(ident->lif.eth.max_ucast_filters); + if (netdev_uc_count(netdev) + 1 > nfilters) { + rx_mode |= IONIC_RX_MODE_F_PROMISC; + lif->uc_overflow = true; + } else if (lif->uc_overflow) { + lif->uc_overflow = false; + if (!(netdev->flags & IFF_PROMISC)) + rx_mode &= ~IONIC_RX_MODE_F_PROMISC; + } + + /* same for multicast */ + __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(ident->lif.eth.max_mcast_filters); + if (netdev_mc_count(netdev) > nfilters) { + rx_mode |= IONIC_RX_MODE_F_ALLMULTI; + lif->mc_overflow = true; + } else if (lif->mc_overflow) { + lif->mc_overflow = false; + if (!(netdev->flags & IFF_ALLMULTI)) + rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI; + } + + if (lif->rx_mode != rx_mode) + _ionic_lif_rx_mode(lif, rx_mode); +} + +static __le64 ionic_netdev_features_to_nic(netdev_features_t features) +{ + u64 wanted = 0; + + if (features & NETIF_F_HW_VLAN_CTAG_TX) + wanted |= IONIC_ETH_HW_VLAN_TX_TAG; + if (features & NETIF_F_HW_VLAN_CTAG_RX) + wanted |= IONIC_ETH_HW_VLAN_RX_STRIP; + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) + wanted |= IONIC_ETH_HW_VLAN_RX_FILTER; + if (features & NETIF_F_RXHASH) + wanted |= IONIC_ETH_HW_RX_HASH; + if (features & NETIF_F_RXCSUM) + wanted |= IONIC_ETH_HW_RX_CSUM; + if (features & NETIF_F_SG) + wanted |= IONIC_ETH_HW_TX_SG; + if (features & NETIF_F_HW_CSUM) + wanted |= IONIC_ETH_HW_TX_CSUM; + if (features & NETIF_F_TSO) + wanted |= IONIC_ETH_HW_TSO; + if (features & NETIF_F_TSO6) + wanted |= IONIC_ETH_HW_TSO_IPV6; + if (features & NETIF_F_TSO_ECN) + wanted |= IONIC_ETH_HW_TSO_ECN; + if (features & NETIF_F_GSO_GRE) + wanted |= IONIC_ETH_HW_TSO_GRE; + if (features & NETIF_F_GSO_GRE_CSUM) + wanted |= IONIC_ETH_HW_TSO_GRE_CSUM; + if (features & NETIF_F_GSO_IPXIP4) + wanted |= IONIC_ETH_HW_TSO_IPXIP4; + if (features & NETIF_F_GSO_IPXIP6) + wanted |= IONIC_ETH_HW_TSO_IPXIP6; + if (features & NETIF_F_GSO_UDP_TUNNEL) + wanted |= IONIC_ETH_HW_TSO_UDP; + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) + wanted |= IONIC_ETH_HW_TSO_UDP_CSUM; + + return cpu_to_le64(wanted); +} + +static int ionic_set_nic_features(struct ionic_lif *lif, + netdev_features_t features) +{ + struct device *dev = lif->ionic->dev; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_FEATURES, + }, + }; + u64 vlan_flags = IONIC_ETH_HW_VLAN_TX_TAG | + IONIC_ETH_HW_VLAN_RX_STRIP | + IONIC_ETH_HW_VLAN_RX_FILTER; + int err; + + ctx.cmd.lif_setattr.features = ionic_netdev_features_to_nic(features); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + lif->hw_features = le64_to_cpu(ctx.cmd.lif_setattr.features & + ctx.comp.lif_setattr.features); + + if ((vlan_flags & features) && + !(vlan_flags & le64_to_cpu(ctx.comp.lif_setattr.features))) + dev_info_once(lif->ionic->dev, "NIC is not supporting vlan offload, likely in SmartNIC mode\n"); + + if (lif->hw_features & IONIC_ETH_HW_VLAN_TX_TAG) + dev_dbg(dev, "feature ETH_HW_VLAN_TX_TAG\n"); + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_STRIP) + dev_dbg(dev, "feature ETH_HW_VLAN_RX_STRIP\n"); + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_FILTER) + dev_dbg(dev, "feature ETH_HW_VLAN_RX_FILTER\n"); + if (lif->hw_features & IONIC_ETH_HW_RX_HASH) + dev_dbg(dev, "feature ETH_HW_RX_HASH\n"); + if (lif->hw_features & IONIC_ETH_HW_TX_SG) + dev_dbg(dev, "feature ETH_HW_TX_SG\n"); + if (lif->hw_features & IONIC_ETH_HW_TX_CSUM) + dev_dbg(dev, "feature ETH_HW_TX_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_RX_CSUM) + dev_dbg(dev, "feature ETH_HW_RX_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO) + dev_dbg(dev, "feature ETH_HW_TSO\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPV6) + dev_dbg(dev, "feature ETH_HW_TSO_IPV6\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_ECN) + dev_dbg(dev, "feature ETH_HW_TSO_ECN\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE) + dev_dbg(dev, "feature ETH_HW_TSO_GRE\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE_CSUM) + dev_dbg(dev, "feature ETH_HW_TSO_GRE_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP4) + dev_dbg(dev, "feature ETH_HW_TSO_IPXIP4\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP6) + dev_dbg(dev, "feature ETH_HW_TSO_IPXIP6\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP) + dev_dbg(dev, "feature ETH_HW_TSO_UDP\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP_CSUM) + dev_dbg(dev, "feature ETH_HW_TSO_UDP_CSUM\n"); + + return 0; +} + +static int ionic_init_nic_features(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + netdev_features_t features; + int err; + + /* set up what we expect to support by default */ + features = NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXHASH | + NETIF_F_SG | + NETIF_F_HW_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_TSO_ECN; + + err = ionic_set_nic_features(lif, features); + if (err) + return err; + + /* tell the netdev what we actually can support */ + netdev->features |= NETIF_F_HIGHDMA; + + if (lif->hw_features & IONIC_ETH_HW_VLAN_TX_TAG) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_STRIP) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_FILTER) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (lif->hw_features & IONIC_ETH_HW_RX_HASH) + netdev->hw_features |= NETIF_F_RXHASH; + if (lif->hw_features & IONIC_ETH_HW_TX_SG) + netdev->hw_features |= NETIF_F_SG; + + if (lif->hw_features & IONIC_ETH_HW_TX_CSUM) + netdev->hw_enc_features |= NETIF_F_HW_CSUM; + if (lif->hw_features & IONIC_ETH_HW_RX_CSUM) + netdev->hw_enc_features |= NETIF_F_RXCSUM; + if (lif->hw_features & IONIC_ETH_HW_TSO) + netdev->hw_enc_features |= NETIF_F_TSO; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPV6) + netdev->hw_enc_features |= NETIF_F_TSO6; + if (lif->hw_features & IONIC_ETH_HW_TSO_ECN) + netdev->hw_enc_features |= NETIF_F_TSO_ECN; + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE) + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_GRE_CSUM; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP4) + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP6) + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP6; + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_features |= netdev->hw_enc_features; + netdev->features |= netdev->hw_features; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + return 0; +} + +static int ionic_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + netdev_dbg(netdev, "%s: lif->features=0x%08llx new_features=0x%08llx\n", + __func__, (u64)lif->netdev->features, (u64)features); + + err = ionic_set_nic_features(lif, features); + + return err; +} + +static int ionic_set_mac_address(struct net_device *netdev, void *sa) +{ + struct sockaddr *addr = sa; + u8 *mac; + int err; + + mac = (u8 *)addr->sa_data; + if (ether_addr_equal(netdev->dev_addr, mac)) + return 0; + + err = eth_prepare_mac_addr_change(netdev, addr); + if (err) + return err; + + if (!is_zero_ether_addr(netdev->dev_addr)) { + netdev_info(netdev, "deleting mac addr %pM\n", + netdev->dev_addr); + ionic_addr_del(netdev, netdev->dev_addr); + } + + eth_commit_mac_addr_change(netdev, addr); + netdev_info(netdev, "updating mac addr %pM\n", mac); + + return ionic_addr_add(netdev, mac); +} + +static int ionic_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MTU, + .mtu = cpu_to_le32(new_mtu), + }, + }; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev->mtu = new_mtu; + err = ionic_reset_queues(lif); + + return err; +} + +static void ionic_tx_timeout_work(struct work_struct *ws) +{ + struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + + netdev_info(lif->netdev, "Tx Timeout recovery\n"); + + rtnl_lock(); + ionic_reset_queues(lif); + rtnl_unlock(); +} + +static void ionic_tx_timeout(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + schedule_work(&lif->tx_timeout_work); +} + +static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, + u16 vid) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_add = { + .opcode = IONIC_CMD_RX_FILTER_ADD, + .lif_index = cpu_to_le16(lif->index), + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }, + }; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev_dbg(netdev, "rx_filter add VLAN %d (id %d)\n", vid, + ctx.comp.rx_filter_add.filter_id); + + return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx); +} + +static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, + u16 vid) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + + spin_lock_bh(&lif->rx_filters.lock); + + f = ionic_rx_filter_by_vlan(lif, vid); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", vid, + le32_to_cpu(ctx.cmd.rx_filter_del.filter_id)); + + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + spin_unlock_bh(&lif->rx_filters.lock); + + return ionic_adminq_post_wait(lif, &ctx); +} + +int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types, + const u8 *key, const u32 *indir) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .attr = IONIC_LIF_ATTR_RSS, + .rss.types = cpu_to_le16(types), + .rss.addr = cpu_to_le64(lif->rss_ind_tbl_pa), + }, + }; + unsigned int i, tbl_sz; + + lif->rss_types = types; + + if (key) + memcpy(lif->rss_hash_key, key, IONIC_RSS_HASH_KEY_SIZE); + + if (indir) { + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + lif->rss_ind_tbl[i] = indir[i]; + } + + memcpy(ctx.cmd.lif_setattr.rss.key, lif->rss_hash_key, + IONIC_RSS_HASH_KEY_SIZE); + + return ionic_adminq_post_wait(lif, &ctx); +} + +static int ionic_lif_rss_init(struct ionic_lif *lif) +{ + u8 rss_key[IONIC_RSS_HASH_KEY_SIZE]; + unsigned int tbl_sz; + unsigned int i; + + netdev_rss_key_fill(rss_key, IONIC_RSS_HASH_KEY_SIZE); + + lif->rss_types = IONIC_RSS_TYPE_IPV4 | + IONIC_RSS_TYPE_IPV4_TCP | + IONIC_RSS_TYPE_IPV4_UDP | + IONIC_RSS_TYPE_IPV6 | + IONIC_RSS_TYPE_IPV6_TCP | + IONIC_RSS_TYPE_IPV6_UDP; + + /* Fill indirection table with 'default' values */ + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + lif->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, lif->nxqs); + + return ionic_lif_rss_config(lif, lif->rss_types, rss_key, NULL); +} + +static int ionic_lif_rss_deinit(struct ionic_lif *lif) +{ + return ionic_lif_rss_config(lif, 0x0, NULL, NULL); +} + +static void ionic_txrx_disable(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_qcq_disable(lif->txqcqs[i].qcq); + ionic_qcq_disable(lif->rxqcqs[i].qcq); + } +} + +static void ionic_txrx_deinit(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_tx_flush(&lif->txqcqs[i].qcq->cq); + + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + ionic_rx_flush(&lif->rxqcqs[i].qcq->cq); + ionic_rx_empty(&lif->rxqcqs[i].qcq->q); + } +} + +static void ionic_txrx_free(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_qcq_free(lif, lif->txqcqs[i].qcq); + lif->txqcqs[i].qcq = NULL; + + ionic_qcq_free(lif, lif->rxqcqs[i].qcq); + lif->rxqcqs[i].qcq = NULL; + } +} + +static int ionic_txrx_alloc(struct ionic_lif *lif) +{ + unsigned int flags; + unsigned int i; + int err = 0; + u32 coal; + + flags = IONIC_QCQ_F_TX_STATS | IONIC_QCQ_F_SG; + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, + lif->ntxq_descs, + sizeof(struct ionic_txq_desc), + sizeof(struct ionic_txq_comp), + sizeof(struct ionic_txq_sg_desc), + lif->kern_pid, &lif->txqcqs[i].qcq); + if (err) + goto err_out; + + lif->txqcqs[i].qcq->stats = lif->txqcqs[i].stats; + } + + flags = IONIC_QCQ_F_RX_STATS | IONIC_QCQ_F_INTR; + coal = ionic_coal_usec_to_hw(lif->ionic, lif->rx_coalesce_usecs); + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, + lif->nrxq_descs, + sizeof(struct ionic_rxq_desc), + sizeof(struct ionic_rxq_comp), + 0, lif->kern_pid, &lif->rxqcqs[i].qcq); + if (err) + goto err_out; + + lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; + + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[i].qcq->intr.index, coal); + ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, + lif->txqcqs[i].qcq); + } + + return 0; + +err_out: + ionic_txrx_free(lif); + + return err; +} + +static int ionic_txrx_init(struct ionic_lif *lif) +{ + unsigned int i; + int err; + + for (i = 0; i < lif->nxqs; i++) { + err = ionic_lif_txq_init(lif, lif->txqcqs[i].qcq); + if (err) + goto err_out; + + err = ionic_lif_rxq_init(lif, lif->rxqcqs[i].qcq); + if (err) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + goto err_out; + } + } + + if (lif->netdev->features & NETIF_F_RXHASH) + ionic_lif_rss_init(lif); + + ionic_set_rx_mode(lif->netdev); + + return 0; + +err_out: + while (i--) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + } + + return err; +} + +static int ionic_txrx_enable(struct ionic_lif *lif) +{ + int i, err; + + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_enable(lif->txqcqs[i].qcq); + if (err) + goto err_out; + + ionic_rx_fill(&lif->rxqcqs[i].qcq->q); + err = ionic_qcq_enable(lif->rxqcqs[i].qcq); + if (err) { + ionic_qcq_disable(lif->txqcqs[i].qcq); + goto err_out; + } + } + + return 0; + +err_out: + while (i--) { + ionic_qcq_disable(lif->rxqcqs[i].qcq); + ionic_qcq_disable(lif->txqcqs[i].qcq); + } + + return err; +} + +int ionic_open(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + netif_carrier_off(netdev); + + err = ionic_txrx_alloc(lif); + if (err) + return err; + + err = ionic_txrx_init(lif); + if (err) + goto err_txrx_free; + + err = ionic_txrx_enable(lif); + if (err) + goto err_txrx_deinit; + + netif_set_real_num_tx_queues(netdev, lif->nxqs); + netif_set_real_num_rx_queues(netdev, lif->nxqs); + + set_bit(IONIC_LIF_UP, lif->state); + + ionic_link_status_check_request(lif); + if (netif_carrier_ok(netdev)) + netif_tx_wake_all_queues(netdev); + + return 0; + +err_txrx_deinit: + ionic_txrx_deinit(lif); +err_txrx_free: + ionic_txrx_free(lif); + return err; +} + +int ionic_stop(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err = 0; + + if (!test_bit(IONIC_LIF_UP, lif->state)) { + dev_dbg(lif->ionic->dev, "%s: %s state=DOWN\n", + __func__, lif->name); + return 0; + } + dev_dbg(lif->ionic->dev, "%s: %s state=UP\n", __func__, lif->name); + clear_bit(IONIC_LIF_UP, lif->state); + + /* carrier off before disabling queues to avoid watchdog timeout */ + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + + ionic_txrx_disable(lif); + ionic_txrx_deinit(lif); + ionic_txrx_free(lif); + + return err; +} + +static const struct net_device_ops ionic_netdev_ops = { + .ndo_open = ionic_open, + .ndo_stop = ionic_stop, + .ndo_start_xmit = ionic_start_xmit, + .ndo_get_stats64 = ionic_get_stats64, + .ndo_set_rx_mode = ionic_set_rx_mode, + .ndo_set_features = ionic_set_features, + .ndo_set_mac_address = ionic_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_tx_timeout = ionic_tx_timeout, + .ndo_change_mtu = ionic_change_mtu, + .ndo_vlan_rx_add_vid = ionic_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ionic_vlan_rx_kill_vid, +}; + +int ionic_reset_queues(struct ionic_lif *lif) +{ + bool running; + int err = 0; + + /* Put off the next watchdog timeout */ + netif_trans_update(lif->netdev); + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = netif_running(lif->netdev); + if (running) + err = ionic_stop(lif->netdev); + if (!err && running) + ionic_open(lif->netdev); + + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return err; +} + +static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index) +{ + struct device *dev = ionic->dev; + struct net_device *netdev; + struct ionic_lif *lif; + int tbl_sz; + u32 coal; + int err; + + netdev = alloc_etherdev_mqs(sizeof(*lif), + ionic->ntxqs_per_lif, ionic->ntxqs_per_lif); + if (!netdev) { + dev_err(dev, "Cannot allocate netdev, aborting\n"); + return ERR_PTR(-ENOMEM); + } + + SET_NETDEV_DEV(netdev, dev); + + lif = netdev_priv(netdev); + lif->netdev = netdev; + ionic->master_lif = lif; + netdev->netdev_ops = &ionic_netdev_ops; + ionic_ethtool_set_ops(netdev); + + netdev->watchdog_timeo = 2 * HZ; + netdev->min_mtu = IONIC_MIN_MTU; + netdev->max_mtu = IONIC_MAX_MTU; + + lif->neqs = ionic->neqs_per_lif; + lif->nxqs = ionic->ntxqs_per_lif; + + lif->ionic = ionic; + lif->index = index; + lif->ntxq_descs = IONIC_DEF_TXRX_DESC; + lif->nrxq_descs = IONIC_DEF_TXRX_DESC; + + /* Convert the default coalesce value to actual hw resolution */ + coal = ionic_coal_usec_to_hw(lif->ionic, IONIC_ITR_COAL_USEC_DEFAULT); + lif->rx_coalesce_usecs = ionic_coal_hw_to_usec(lif->ionic, coal); + + snprintf(lif->name, sizeof(lif->name), "lif%u", index); + + spin_lock_init(&lif->adminq_lock); + + spin_lock_init(&lif->deferred.lock); + INIT_LIST_HEAD(&lif->deferred.list); + INIT_WORK(&lif->deferred.work, ionic_lif_deferred_work); + + /* allocate lif info */ + lif->info_sz = ALIGN(sizeof(*lif->info), PAGE_SIZE); + lif->info = dma_alloc_coherent(dev, lif->info_sz, + &lif->info_pa, GFP_KERNEL); + if (!lif->info) { + dev_err(dev, "Failed to allocate lif info, aborting\n"); + err = -ENOMEM; + goto err_out_free_netdev; + } + + /* allocate queues */ + err = ionic_qcqs_alloc(lif); + if (err) + goto err_out_free_lif_info; + + /* allocate rss indirection table */ + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + lif->rss_ind_tbl_sz = sizeof(*lif->rss_ind_tbl) * tbl_sz; + lif->rss_ind_tbl = dma_alloc_coherent(dev, lif->rss_ind_tbl_sz, + &lif->rss_ind_tbl_pa, + GFP_KERNEL); + + if (!lif->rss_ind_tbl) { + dev_err(dev, "Failed to allocate rss indirection table, aborting\n"); + goto err_out_free_qcqs; + } + + list_add_tail(&lif->list, &ionic->lifs); + + return lif; + +err_out_free_qcqs: + ionic_qcqs_free(lif); +err_out_free_lif_info: + dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); + lif->info = NULL; + lif->info_pa = 0; +err_out_free_netdev: + free_netdev(lif->netdev); + lif = NULL; + + return ERR_PTR(err); +} + +int ionic_lifs_alloc(struct ionic *ionic) +{ + struct ionic_lif *lif; + + INIT_LIST_HEAD(&ionic->lifs); + + /* only build the first lif, others are for later features */ + set_bit(0, ionic->lifbits); + lif = ionic_lif_alloc(ionic, 0); + + return PTR_ERR_OR_ZERO(lif); +} + +static void ionic_lif_reset(struct ionic_lif *lif) +{ + struct ionic_dev *idev = &lif->ionic->idev; + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_lif_reset(idev, lif->index); + ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + mutex_unlock(&lif->ionic->dev_cmd_lock); +} + +static void ionic_lif_free(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + + /* free rss indirection table */ + dma_free_coherent(dev, lif->rss_ind_tbl_sz, lif->rss_ind_tbl, + lif->rss_ind_tbl_pa); + lif->rss_ind_tbl = NULL; + lif->rss_ind_tbl_pa = 0; + + /* free queues */ + ionic_qcqs_free(lif); + ionic_lif_reset(lif); + + /* free lif info */ + dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); + lif->info = NULL; + lif->info_pa = 0; + + /* unmap doorbell page */ + ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); + lif->kern_dbpage = NULL; + kfree(lif->dbid_inuse); + lif->dbid_inuse = NULL; + + /* free netdev & lif */ + ionic_debugfs_del_lif(lif); + list_del(&lif->list); + free_netdev(lif->netdev); +} + +void ionic_lifs_free(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + + ionic_lif_free(lif); + } +} + +static void ionic_lif_deinit(struct ionic_lif *lif) +{ + if (!test_bit(IONIC_LIF_INITED, lif->state)) + return; + + clear_bit(IONIC_LIF_INITED, lif->state); + + ionic_rx_filters_deinit(lif); + ionic_lif_rss_deinit(lif); + + napi_disable(&lif->adminqcq->napi); + ionic_lif_qcq_deinit(lif, lif->notifyqcq); + ionic_lif_qcq_deinit(lif, lif->adminqcq); + + ionic_lif_reset(lif); +} + +void ionic_lifs_deinit(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + ionic_lif_deinit(lif); + } +} + +static int ionic_lif_adminq_init(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + struct ionic_q_init_comp comp; + struct ionic_dev *idev; + struct ionic_qcq *qcq; + struct ionic_queue *q; + int err; + + idev = &lif->ionic->idev; + qcq = lif->adminqcq; + q = &qcq->q; + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_adminq_init(idev, qcq, lif->index, qcq->intr.index); + err = ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + ionic_dev_cmd_comp(idev, (union ionic_dev_cmd_comp *)&comp); + mutex_unlock(&lif->ionic->dev_cmd_lock); + if (err) { + netdev_err(lif->netdev, "adminq init failed %d\n", err); + return err; + } + + q->hw_type = comp.hw_type; + q->hw_index = le32_to_cpu(comp.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi, + NAPI_POLL_WEIGHT); + + err = ionic_request_irq(lif, qcq); + if (err) { + netdev_warn(lif->netdev, "adminq irq request failed %d\n", err); + netif_napi_del(&qcq->napi); + return err; + } + + napi_enable(&qcq->napi); + + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_CLEAR); + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_lif_notifyq_init(struct ionic_lif *lif) +{ + struct ionic_qcq *qcq = lif->notifyqcq; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + int err; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_ENA), + .intr_index = cpu_to_le16(lif->adminqcq->intr.index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + } + }; + + dev_dbg(dev, "notifyq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "notifyq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "notifyq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "notifyq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "notifyq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "notifyq->hw_index %d\n", q->hw_index); + + /* preset the callback info */ + q->info[0].cb_arg = lif; + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_station_set(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_getattr = { + .opcode = IONIC_CMD_LIF_GETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MAC, + }, + }; + struct sockaddr addr; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); + addr.sa_family = AF_INET; + err = eth_prepare_mac_addr_change(netdev, &addr); + if (err) + return err; + + if (!is_zero_ether_addr(netdev->dev_addr)) { + netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", + netdev->dev_addr); + ionic_lif_addr(lif, netdev->dev_addr, false); + } + + eth_commit_mac_addr_change(netdev, &addr); + netdev_dbg(lif->netdev, "adding station MAC addr %pM\n", + netdev->dev_addr); + ionic_lif_addr(lif, netdev->dev_addr, true); + + return 0; +} + +static int ionic_lif_init(struct ionic_lif *lif) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct device *dev = lif->ionic->dev; + struct ionic_lif_init_comp comp; + int dbpage_num; + int err; + + ionic_debugfs_add_lif(lif); + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_lif_init(idev, lif->index, lif->info_pa); + err = ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + ionic_dev_cmd_comp(idev, (union ionic_dev_cmd_comp *)&comp); + mutex_unlock(&lif->ionic->dev_cmd_lock); + if (err) + return err; + + lif->hw_index = le16_to_cpu(comp.hw_index); + + /* now that we have the hw_index we can figure out our doorbell page */ + lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); + if (!lif->dbid_count) { + dev_err(dev, "No doorbell pages, aborting\n"); + return -EINVAL; + } + + lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL); + if (!lif->dbid_inuse) { + dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n"); + return -ENOMEM; + } + + /* first doorbell id reserved for kernel (dbid aka pid == zero) */ + set_bit(0, lif->dbid_inuse); + lif->kern_pid = 0; + + dbpage_num = ionic_db_page_num(lif, lif->kern_pid); + lif->kern_dbpage = ionic_bus_map_dbpage(lif->ionic, dbpage_num); + if (!lif->kern_dbpage) { + dev_err(dev, "Cannot map dbpage, aborting\n"); + err = -ENOMEM; + goto err_out_free_dbid; + } + + err = ionic_lif_adminq_init(lif); + if (err) + goto err_out_adminq_deinit; + + if (lif->ionic->nnqs_per_lif) { + err = ionic_lif_notifyq_init(lif); + if (err) + goto err_out_notifyq_deinit; + } + + err = ionic_init_nic_features(lif); + if (err) + goto err_out_notifyq_deinit; + + err = ionic_rx_filters_init(lif); + if (err) + goto err_out_notifyq_deinit; + + err = ionic_station_set(lif); + if (err) + goto err_out_notifyq_deinit; + + lif->rx_copybreak = IONIC_RX_COPYBREAK_DEFAULT; + + set_bit(IONIC_LIF_INITED, lif->state); + + INIT_WORK(&lif->tx_timeout_work, ionic_tx_timeout_work); + + return 0; + +err_out_notifyq_deinit: + ionic_lif_qcq_deinit(lif, lif->notifyqcq); +err_out_adminq_deinit: + ionic_lif_qcq_deinit(lif, lif->adminqcq); + ionic_lif_reset(lif); + ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); + lif->kern_dbpage = NULL; +err_out_free_dbid: + kfree(lif->dbid_inuse); + lif->dbid_inuse = NULL; + + return err; +} + +int ionic_lifs_init(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + int err; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + err = ionic_lif_init(lif); + if (err) + return err; + } + + return 0; +} + +static void ionic_lif_notify_work(struct work_struct *ws) +{ +} + +static void ionic_lif_set_netdev_info(struct ionic_lif *lif) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_NAME, + }, + }; + + strlcpy(ctx.cmd.lif_setattr.name, lif->netdev->name, + sizeof(ctx.cmd.lif_setattr.name)); + + ionic_adminq_post_wait(lif, &ctx); +} + +static struct ionic_lif *ionic_netdev_lif(struct net_device *netdev) +{ + if (!netdev || netdev->netdev_ops->ndo_start_xmit != ionic_start_xmit) + return NULL; + + return netdev_priv(netdev); +} + +static int ionic_lif_notify(struct notifier_block *nb, + unsigned long event, void *info) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(info); + struct ionic *ionic = container_of(nb, struct ionic, nb); + struct ionic_lif *lif = ionic_netdev_lif(ndev); + + if (!lif || lif->ionic != ionic) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_CHANGENAME: + ionic_lif_set_netdev_info(lif); + break; + } + + return NOTIFY_DONE; +} + +int ionic_lifs_register(struct ionic *ionic) +{ + int err; + + INIT_WORK(&ionic->nb_work, ionic_lif_notify_work); + + ionic->nb.notifier_call = ionic_lif_notify; + + err = register_netdevice_notifier(&ionic->nb); + if (err) + ionic->nb.notifier_call = NULL; + + /* only register LIF0 for now */ + err = register_netdev(ionic->master_lif->netdev); + if (err) { + dev_err(ionic->dev, "Cannot register net device, aborting\n"); + return err; + } + + ionic_link_status_check_request(ionic->master_lif); + ionic->master_lif->registered = true; + + return 0; +} + +void ionic_lifs_unregister(struct ionic *ionic) +{ + if (ionic->nb.notifier_call) { + unregister_netdevice_notifier(&ionic->nb); + cancel_work_sync(&ionic->nb_work); + ionic->nb.notifier_call = NULL; + } + + /* There is only one lif ever registered in the + * current model, so don't bother searching the + * ionic->lif for candidates to unregister + */ + cancel_work_sync(&ionic->master_lif->deferred.work); + cancel_work_sync(&ionic->master_lif->tx_timeout_work); + if (ionic->master_lif->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(ionic->master_lif->netdev); +} + +int ionic_lif_identify(struct ionic *ionic, u8 lif_type, + union ionic_lif_identity *lid) +{ + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + sz = min(sizeof(*lid), sizeof(idev->dev_cmd_regs->data)); + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_lif_identify(idev, lif_type, IONIC_IDENTITY_VERSION_1); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + memcpy_fromio(lid, &idev->dev_cmd_regs->data, sz); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return (err); + + dev_dbg(ionic->dev, "capabilities 0x%llx\n", + le64_to_cpu(lid->capabilities)); + + dev_dbg(ionic->dev, "eth.max_ucast_filters %d\n", + le32_to_cpu(lid->eth.max_ucast_filters)); + dev_dbg(ionic->dev, "eth.max_mcast_filters %d\n", + le32_to_cpu(lid->eth.max_mcast_filters)); + dev_dbg(ionic->dev, "eth.features 0x%llx\n", + le64_to_cpu(lid->eth.config.features)); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_ADMINQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_ADMINQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_NOTIFYQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_NOTIFYQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_RXQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_RXQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_TXQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_TXQ])); + dev_dbg(ionic->dev, "eth.config.name %s\n", lid->eth.config.name); + dev_dbg(ionic->dev, "eth.config.mac %pM\n", lid->eth.config.mac); + dev_dbg(ionic->dev, "eth.config.mtu %d\n", + le32_to_cpu(lid->eth.config.mtu)); + + return 0; +} + +int ionic_lifs_size(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + unsigned int nintrs, dev_nintrs; + union ionic_lif_config *lc; + unsigned int ntxqs_per_lif; + unsigned int nrxqs_per_lif; + unsigned int neqs_per_lif; + unsigned int nnqs_per_lif; + unsigned int nxqs, neqs; + unsigned int min_intrs; + int err; + + lc = &ident->lif.eth.config; + dev_nintrs = le32_to_cpu(ident->dev.nintrs); + neqs_per_lif = le32_to_cpu(ident->lif.rdma.eq_qtype.qid_count); + nnqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_NOTIFYQ]); + ntxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_TXQ]); + nrxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_RXQ]); + + nxqs = min(ntxqs_per_lif, nrxqs_per_lif); + nxqs = min(nxqs, num_online_cpus()); + neqs = min(neqs_per_lif, num_online_cpus()); + +try_again: + /* interrupt usage: + * 1 for master lif adminq/notifyq + * 1 for each CPU for master lif TxRx queue pairs + * whatever's left is for RDMA queues + */ + nintrs = 1 + nxqs + neqs; + min_intrs = 2; /* adminq + 1 TxRx queue pair */ + + if (nintrs > dev_nintrs) + goto try_fewer; + + err = ionic_bus_alloc_irq_vectors(ionic, nintrs); + if (err < 0 && err != -ENOSPC) { + dev_err(ionic->dev, "Can't get intrs from OS: %d\n", err); + return err; + } + if (err == -ENOSPC) + goto try_fewer; + + if (err != nintrs) { + ionic_bus_free_irq_vectors(ionic); + goto try_fewer; + } + + ionic->nnqs_per_lif = nnqs_per_lif; + ionic->neqs_per_lif = neqs; + ionic->ntxqs_per_lif = nxqs; + ionic->nrxqs_per_lif = nxqs; + ionic->nintrs = nintrs; + + ionic_debugfs_add_sizes(ionic); + + return 0; + +try_fewer: + if (nnqs_per_lif > 1) { + nnqs_per_lif >>= 1; + goto try_again; + } + if (neqs > 1) { + neqs >>= 1; + goto try_again; + } + if (nxqs > 1) { + nxqs >>= 1; + goto try_again; + } + dev_err(ionic->dev, "Can't get minimum %d intrs from OS\n", min_intrs); + return -ENOSPC; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h new file mode 100644 index 000000000000..812190e729c2 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -0,0 +1,277 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_LIF_H_ +#define _IONIC_LIF_H_ + +#include <linux/pci.h> +#include "ionic_rx_filter.h" + +#define IONIC_ADMINQ_LENGTH 16 /* must be a power of two */ +#define IONIC_NOTIFYQ_LENGTH 64 /* must be a power of two */ + +#define IONIC_MAX_NUM_NAPI_CNTR (NAPI_POLL_WEIGHT + 1) +#define IONIC_MAX_NUM_SG_CNTR (IONIC_TX_MAX_SG_ELEMS + 1) +#define IONIC_RX_COPYBREAK_DEFAULT 256 + +struct ionic_tx_stats { + u64 dma_map_err; + u64 pkts; + u64 bytes; + u64 clean; + u64 linearize; + u64 no_csum; + u64 csum; + u64 crc32_csum; + u64 tso; + u64 frags; + u64 sg_cntr[IONIC_MAX_NUM_SG_CNTR]; +}; + +struct ionic_rx_stats { + u64 dma_map_err; + u64 alloc_err; + u64 pkts; + u64 bytes; + u64 csum_none; + u64 csum_complete; + u64 csum_error; + u64 buffers_posted; +}; + +#define IONIC_QCQ_F_INITED BIT(0) +#define IONIC_QCQ_F_SG BIT(1) +#define IONIC_QCQ_F_INTR BIT(2) +#define IONIC_QCQ_F_TX_STATS BIT(3) +#define IONIC_QCQ_F_RX_STATS BIT(4) +#define IONIC_QCQ_F_NOTIFYQ BIT(5) + +struct ionic_napi_stats { + u64 poll_count; + u64 work_done_cntr[IONIC_MAX_NUM_NAPI_CNTR]; +}; + +struct ionic_q_stats { + union { + struct ionic_tx_stats tx; + struct ionic_rx_stats rx; + }; +}; + +struct ionic_qcq { + void *base; + dma_addr_t base_pa; + unsigned int total_size; + struct ionic_queue q; + struct ionic_cq cq; + struct ionic_intr_info intr; + struct napi_struct napi; + struct ionic_napi_stats napi_stats; + struct ionic_q_stats *stats; + unsigned int flags; + struct dentry *dentry; +}; + +struct ionic_qcqst { + struct ionic_qcq *qcq; + struct ionic_q_stats *stats; +}; + +#define q_to_qcq(q) container_of(q, struct ionic_qcq, q) +#define q_to_tx_stats(q) (&q_to_qcq(q)->stats->tx) +#define q_to_rx_stats(q) (&q_to_qcq(q)->stats->rx) +#define napi_to_qcq(napi) container_of(napi, struct ionic_qcq, napi) +#define napi_to_cq(napi) (&napi_to_qcq(napi)->cq) + +enum ionic_deferred_work_type { + IONIC_DW_TYPE_RX_MODE, + IONIC_DW_TYPE_RX_ADDR_ADD, + IONIC_DW_TYPE_RX_ADDR_DEL, + IONIC_DW_TYPE_LINK_STATUS, + IONIC_DW_TYPE_LIF_RESET, +}; + +struct ionic_deferred_work { + struct list_head list; + enum ionic_deferred_work_type type; + union { + unsigned int rx_mode; + u8 addr[ETH_ALEN]; + }; +}; + +struct ionic_deferred { + spinlock_t lock; /* lock for deferred work list */ + struct list_head list; + struct work_struct work; +}; + +struct ionic_lif_sw_stats { + u64 tx_packets; + u64 tx_bytes; + u64 rx_packets; + u64 rx_bytes; + u64 tx_tso; + u64 tx_no_csum; + u64 tx_csum; + u64 rx_csum_none; + u64 rx_csum_complete; + u64 rx_csum_error; +}; + +enum ionic_lif_state_flags { + IONIC_LIF_INITED, + IONIC_LIF_SW_DEBUG_STATS, + IONIC_LIF_UP, + IONIC_LIF_LINK_CHECK_REQUESTED, + IONIC_LIF_QUEUE_RESET, + + /* leave this as last */ + IONIC_LIF_STATE_SIZE +}; + +#define IONIC_LIF_NAME_MAX_SZ 32 +struct ionic_lif { + char name[IONIC_LIF_NAME_MAX_SZ]; + struct list_head list; + struct net_device *netdev; + DECLARE_BITMAP(state, IONIC_LIF_STATE_SIZE); + struct ionic *ionic; + bool registered; + unsigned int index; + unsigned int hw_index; + unsigned int kern_pid; + u64 __iomem *kern_dbpage; + spinlock_t adminq_lock; /* lock for AdminQ operations */ + struct ionic_qcq *adminqcq; + struct ionic_qcq *notifyqcq; + struct ionic_qcqst *txqcqs; + struct ionic_qcqst *rxqcqs; + u64 last_eid; + unsigned int neqs; + unsigned int nxqs; + unsigned int ntxq_descs; + unsigned int nrxq_descs; + u32 rx_copybreak; + unsigned int rx_mode; + u64 hw_features; + bool mc_overflow; + unsigned int nmcast; + bool uc_overflow; + unsigned int nucast; + + struct ionic_lif_info *info; + dma_addr_t info_pa; + u32 info_sz; + + u16 rss_types; + u8 rss_hash_key[IONIC_RSS_HASH_KEY_SIZE]; + u8 *rss_ind_tbl; + dma_addr_t rss_ind_tbl_pa; + u32 rss_ind_tbl_sz; + + struct ionic_rx_filters rx_filters; + struct ionic_deferred deferred; + unsigned long *dbid_inuse; + unsigned int dbid_count; + struct dentry *dentry; + u32 rx_coalesce_usecs; + u32 flags; + struct work_struct tx_timeout_work; +}; + +#define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) +#define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) +#define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) +#define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) + +static inline int ionic_wait_for_bit(struct ionic_lif *lif, int bitname) +{ + unsigned long tlimit = jiffies + HZ; + + while (test_and_set_bit(bitname, lif->state) && + time_before(jiffies, tlimit)) + usleep_range(100, 200); + + return test_bit(bitname, lif->state); +} + +static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) +{ + u32 mult = le32_to_cpu(ionic->ident.dev.intr_coal_mult); + u32 div = le32_to_cpu(ionic->ident.dev.intr_coal_div); + + /* Div-by-zero should never be an issue, but check anyway */ + if (!div || !mult) + return 0; + + /* Round up in case usecs is close to the next hw unit */ + usecs += (div / mult) >> 1; + + /* Convert from usecs to device units */ + return (usecs * mult) / div; +} + +static inline u32 ionic_coal_hw_to_usec(struct ionic *ionic, u32 units) +{ + u32 mult = le32_to_cpu(ionic->ident.dev.intr_coal_mult); + u32 div = le32_to_cpu(ionic->ident.dev.intr_coal_div); + + /* Div-by-zero should never be an issue, but check anyway */ + if (!div || !mult) + return 0; + + /* Convert from device units to usec */ + return (units * div) / mult; +} + +int ionic_lifs_alloc(struct ionic *ionic); +void ionic_lifs_free(struct ionic *ionic); +void ionic_lifs_deinit(struct ionic *ionic); +int ionic_lifs_init(struct ionic *ionic); +int ionic_lifs_register(struct ionic *ionic); +void ionic_lifs_unregister(struct ionic *ionic); +int ionic_lif_identify(struct ionic *ionic, u8 lif_type, + union ionic_lif_identity *lif_ident); +int ionic_lifs_size(struct ionic *ionic); +int ionic_lif_rss_config(struct ionic_lif *lif, u16 types, + const u8 *key, const u32 *indir); + +int ionic_open(struct net_device *netdev); +int ionic_stop(struct net_device *netdev); +int ionic_reset_queues(struct ionic_lif *lif); + +static inline void debug_stats_txq_post(struct ionic_qcq *qcq, + struct ionic_txq_desc *desc, bool dbell) +{ + u8 num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) + & IONIC_TXQ_DESC_NSGE_MASK); + + qcq->q.dbell_count += dbell; + + if (num_sg_elems > (IONIC_MAX_NUM_SG_CNTR - 1)) + num_sg_elems = IONIC_MAX_NUM_SG_CNTR - 1; + + qcq->stats->tx.sg_cntr[num_sg_elems]++; +} + +static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, + unsigned int work_done) +{ + qcq->napi_stats.poll_count++; + + if (work_done > (IONIC_MAX_NUM_NAPI_CNTR - 1)) + work_done = IONIC_MAX_NUM_NAPI_CNTR - 1; + + qcq->napi_stats.work_done_cntr[work_done]++; +} + +#define DEBUG_STATS_CQE_CNT(cq) ((cq)->compl_count++) +#define DEBUG_STATS_RX_BUFF_CNT(qcq) ((qcq)->stats->rx.buffers_posted++) +#define DEBUG_STATS_INTR_REARM(intr) ((intr)->rearm_count++) +#define DEBUG_STATS_TXQ_POST(qcq, txdesc, dbell) \ + debug_stats_txq_post(qcq, txdesc, dbell) +#define DEBUG_STATS_NAPI_POLL(qcq, work_done) \ + debug_stats_napi_poll(qcq, work_done) + +#endif /* _IONIC_LIF_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c new file mode 100644 index 000000000000..5ec67f3f1853 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/version.h> +#include <linux/netdevice.h> +#include <linux/utsname.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +MODULE_DESCRIPTION(IONIC_DRV_DESCRIPTION); +MODULE_AUTHOR("Pensando Systems, Inc"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(IONIC_DRV_VERSION); + +static const char *ionic_error_to_str(enum ionic_status_code code) +{ + switch (code) { + case IONIC_RC_SUCCESS: + return "IONIC_RC_SUCCESS"; + case IONIC_RC_EVERSION: + return "IONIC_RC_EVERSION"; + case IONIC_RC_EOPCODE: + return "IONIC_RC_EOPCODE"; + case IONIC_RC_EIO: + return "IONIC_RC_EIO"; + case IONIC_RC_EPERM: + return "IONIC_RC_EPERM"; + case IONIC_RC_EQID: + return "IONIC_RC_EQID"; + case IONIC_RC_EQTYPE: + return "IONIC_RC_EQTYPE"; + case IONIC_RC_ENOENT: + return "IONIC_RC_ENOENT"; + case IONIC_RC_EINTR: + return "IONIC_RC_EINTR"; + case IONIC_RC_EAGAIN: + return "IONIC_RC_EAGAIN"; + case IONIC_RC_ENOMEM: + return "IONIC_RC_ENOMEM"; + case IONIC_RC_EFAULT: + return "IONIC_RC_EFAULT"; + case IONIC_RC_EBUSY: + return "IONIC_RC_EBUSY"; + case IONIC_RC_EEXIST: + return "IONIC_RC_EEXIST"; + case IONIC_RC_EINVAL: + return "IONIC_RC_EINVAL"; + case IONIC_RC_ENOSPC: + return "IONIC_RC_ENOSPC"; + case IONIC_RC_ERANGE: + return "IONIC_RC_ERANGE"; + case IONIC_RC_BAD_ADDR: + return "IONIC_RC_BAD_ADDR"; + case IONIC_RC_DEV_CMD: + return "IONIC_RC_DEV_CMD"; + case IONIC_RC_ERROR: + return "IONIC_RC_ERROR"; + case IONIC_RC_ERDMA: + return "IONIC_RC_ERDMA"; + default: + return "IONIC_RC_UNKNOWN"; + } +} + +static int ionic_error_to_errno(enum ionic_status_code code) +{ + switch (code) { + case IONIC_RC_SUCCESS: + return 0; + case IONIC_RC_EVERSION: + case IONIC_RC_EQTYPE: + case IONIC_RC_EQID: + case IONIC_RC_EINVAL: + return -EINVAL; + case IONIC_RC_EPERM: + return -EPERM; + case IONIC_RC_ENOENT: + return -ENOENT; + case IONIC_RC_EAGAIN: + return -EAGAIN; + case IONIC_RC_ENOMEM: + return -ENOMEM; + case IONIC_RC_EFAULT: + return -EFAULT; + case IONIC_RC_EBUSY: + return -EBUSY; + case IONIC_RC_EEXIST: + return -EEXIST; + case IONIC_RC_ENOSPC: + return -ENOSPC; + case IONIC_RC_ERANGE: + return -ERANGE; + case IONIC_RC_BAD_ADDR: + return -EFAULT; + case IONIC_RC_EOPCODE: + case IONIC_RC_EINTR: + case IONIC_RC_DEV_CMD: + case IONIC_RC_ERROR: + case IONIC_RC_ERDMA: + case IONIC_RC_EIO: + default: + return -EIO; + } +} + +static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) +{ + switch (opcode) { + case IONIC_CMD_NOP: + return "IONIC_CMD_NOP"; + case IONIC_CMD_INIT: + return "IONIC_CMD_INIT"; + case IONIC_CMD_RESET: + return "IONIC_CMD_RESET"; + case IONIC_CMD_IDENTIFY: + return "IONIC_CMD_IDENTIFY"; + case IONIC_CMD_GETATTR: + return "IONIC_CMD_GETATTR"; + case IONIC_CMD_SETATTR: + return "IONIC_CMD_SETATTR"; + case IONIC_CMD_PORT_IDENTIFY: + return "IONIC_CMD_PORT_IDENTIFY"; + case IONIC_CMD_PORT_INIT: + return "IONIC_CMD_PORT_INIT"; + case IONIC_CMD_PORT_RESET: + return "IONIC_CMD_PORT_RESET"; + case IONIC_CMD_PORT_GETATTR: + return "IONIC_CMD_PORT_GETATTR"; + case IONIC_CMD_PORT_SETATTR: + return "IONIC_CMD_PORT_SETATTR"; + case IONIC_CMD_LIF_INIT: + return "IONIC_CMD_LIF_INIT"; + case IONIC_CMD_LIF_RESET: + return "IONIC_CMD_LIF_RESET"; + case IONIC_CMD_LIF_IDENTIFY: + return "IONIC_CMD_LIF_IDENTIFY"; + case IONIC_CMD_LIF_SETATTR: + return "IONIC_CMD_LIF_SETATTR"; + case IONIC_CMD_LIF_GETATTR: + return "IONIC_CMD_LIF_GETATTR"; + case IONIC_CMD_RX_MODE_SET: + return "IONIC_CMD_RX_MODE_SET"; + case IONIC_CMD_RX_FILTER_ADD: + return "IONIC_CMD_RX_FILTER_ADD"; + case IONIC_CMD_RX_FILTER_DEL: + return "IONIC_CMD_RX_FILTER_DEL"; + case IONIC_CMD_Q_INIT: + return "IONIC_CMD_Q_INIT"; + case IONIC_CMD_Q_CONTROL: + return "IONIC_CMD_Q_CONTROL"; + case IONIC_CMD_RDMA_RESET_LIF: + return "IONIC_CMD_RDMA_RESET_LIF"; + case IONIC_CMD_RDMA_CREATE_EQ: + return "IONIC_CMD_RDMA_CREATE_EQ"; + case IONIC_CMD_RDMA_CREATE_CQ: + return "IONIC_CMD_RDMA_CREATE_CQ"; + case IONIC_CMD_RDMA_CREATE_ADMINQ: + return "IONIC_CMD_RDMA_CREATE_ADMINQ"; + case IONIC_CMD_FW_DOWNLOAD: + return "IONIC_CMD_FW_DOWNLOAD"; + case IONIC_CMD_FW_CONTROL: + return "IONIC_CMD_FW_CONTROL"; + default: + return "DEVCMD_UNKNOWN"; + } +} + +static void ionic_adminq_flush(struct ionic_lif *lif) +{ + struct ionic_queue *adminq = &lif->adminqcq->q; + + spin_lock(&lif->adminq_lock); + + while (adminq->tail != adminq->head) { + memset(adminq->tail->desc, 0, sizeof(union ionic_adminq_cmd)); + adminq->tail->cb = NULL; + adminq->tail->cb_arg = NULL; + adminq->tail = adminq->tail->next; + } + spin_unlock(&lif->adminq_lock); +} + +static int ionic_adminq_check_err(struct ionic_lif *lif, + struct ionic_admin_ctx *ctx, + bool timeout) +{ + struct net_device *netdev = lif->netdev; + const char *opcode_str; + const char *status_str; + int err = 0; + + if (ctx->comp.comp.status || timeout) { + opcode_str = ionic_opcode_to_str(ctx->cmd.cmd.opcode); + status_str = ionic_error_to_str(ctx->comp.comp.status); + err = timeout ? -ETIMEDOUT : + ionic_error_to_errno(ctx->comp.comp.status); + + netdev_err(netdev, "%s (%d) failed: %s (%d)\n", + opcode_str, ctx->cmd.cmd.opcode, + timeout ? "TIMEOUT" : status_str, err); + + if (timeout) + ionic_adminq_flush(lif); + } + + return err; +} + +static void ionic_adminq_cb(struct ionic_queue *q, + struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_admin_ctx *ctx = cb_arg; + struct ionic_admin_comp *comp; + struct device *dev; + + if (!ctx) + return; + + comp = cq_info->cq_desc; + dev = &q->lif->netdev->dev; + + memcpy(&ctx->comp, comp, sizeof(*comp)); + + dev_dbg(dev, "comp admin queue command:\n"); + dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx->comp, sizeof(ctx->comp), true); + + complete_all(&ctx->work); +} + +static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + struct ionic_queue *adminq = &lif->adminqcq->q; + int err = 0; + + WARN_ON(in_interrupt()); + + spin_lock(&lif->adminq_lock); + if (!ionic_q_has_space(adminq, 1)) { + err = -ENOSPC; + goto err_out; + } + + memcpy(adminq->head->desc, &ctx->cmd, sizeof(ctx->cmd)); + + dev_dbg(&lif->netdev->dev, "post admin queue command:\n"); + dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx->cmd, sizeof(ctx->cmd), true); + + ionic_q_post(adminq, true, ionic_adminq_cb, ctx); + +err_out: + spin_unlock(&lif->adminq_lock); + + return err; +} + +int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + struct net_device *netdev = lif->netdev; + unsigned long remaining; + const char *name; + int err; + + err = ionic_adminq_post(lif, ctx); + if (err) { + name = ionic_opcode_to_str(ctx->cmd.cmd.opcode); + netdev_err(netdev, "Posting of %s (%d) failed: %d\n", + name, ctx->cmd.cmd.opcode, err); + return err; + } + + remaining = wait_for_completion_timeout(&ctx->work, + HZ * (ulong)DEVCMD_TIMEOUT); + return ionic_adminq_check_err(lif, ctx, (remaining == 0)); +} + +int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, + ionic_cq_done_cb done_cb, void *done_arg) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *cq = &qcq->cq; + u32 work_done, flags = 0; + + work_done = ionic_cq_service(cq, budget, cb, done_cb, done_arg); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(cq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(cq->lif->ionic->idev.intr_ctrl, + cq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +{ + struct ionic_dev *idev = &ionic->idev; + unsigned long start_time; + unsigned long max_wait; + unsigned long duration; + int opcode; + int done; + int err; + + WARN_ON(in_interrupt()); + + /* Wait for dev cmd to complete, retrying if we get EAGAIN, + * but don't wait any longer than max_seconds. + */ + max_wait = jiffies + (max_seconds * HZ); +try_again: + start_time = jiffies; + do { + done = ionic_dev_cmd_done(idev); + if (done) + break; + msleep(20); + } while (!done && time_before(jiffies, max_wait)); + duration = jiffies - start_time; + + opcode = idev->dev_cmd_regs->cmd.cmd.opcode; + dev_dbg(ionic->dev, "DEVCMD %s (%d) done=%d took %ld secs (%ld jiffies)\n", + ionic_opcode_to_str(opcode), opcode, + done, duration / HZ, duration); + + if (!done && !time_before(jiffies, max_wait)) { + dev_warn(ionic->dev, "DEVCMD %s (%d) timeout after %ld secs\n", + ionic_opcode_to_str(opcode), opcode, max_seconds); + return -ETIMEDOUT; + } + + err = ionic_dev_cmd_status(&ionic->idev); + if (err) { + if (err == IONIC_RC_EAGAIN && !time_after(jiffies, max_wait)) { + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) retrying...\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(err), err); + + msleep(1000); + iowrite32(0, &idev->dev_cmd_regs->done); + iowrite32(1, &idev->dev_cmd_regs->doorbell); + goto try_again; + } + + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(err), err); + + return ionic_error_to_errno(err); + } + + return 0; +} + +int ionic_setup(struct ionic *ionic) +{ + int err; + + err = ionic_dev_setup(ionic); + if (err) + return err; + + return 0; +} + +int ionic_identify(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + memset(ident, 0, sizeof(*ident)); + + ident->drv.os_type = cpu_to_le32(IONIC_OS_TYPE_LINUX); + strncpy(ident->drv.driver_ver_str, IONIC_DRV_VERSION, + sizeof(ident->drv.driver_ver_str) - 1); + + mutex_lock(&ionic->dev_cmd_lock); + + sz = min(sizeof(ident->drv), sizeof(idev->dev_cmd_regs->data)); + memcpy_toio(&idev->dev_cmd_regs->data, &ident->drv, sz); + + ionic_dev_cmd_identify(idev, IONIC_IDENTITY_VERSION_1); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + if (!err) { + sz = min(sizeof(ident->dev), sizeof(idev->dev_cmd_regs->data)); + memcpy_fromio(&ident->dev, &idev->dev_cmd_regs->data, sz); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + if (err) + goto err_out_unmap; + + ionic_debugfs_add_ident(ionic); + + return 0; + +err_out_unmap: + return err; +} + +int ionic_init(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_init(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_reset(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_port_identify(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + + ionic_dev_cmd_port_identify(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + if (!err) { + sz = min(sizeof(ident->port), sizeof(idev->dev_cmd_regs->data)); + memcpy_fromio(&ident->port, &idev->dev_cmd_regs->data, sz); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_port_init(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + if (idev->port_info) + return 0; + + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); + idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz, + &idev->port_info_pa, + GFP_KERNEL); + if (!idev->port_info) { + dev_err(ionic->dev, "Failed to allocate port info, aborting\n"); + return -ENOMEM; + } + + sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data)); + + mutex_lock(&ionic->dev_cmd_lock); + + memcpy_toio(&idev->dev_cmd_regs->data, &ident->port.config, sz); + ionic_dev_cmd_port_init(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_UP); + (void)ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + mutex_unlock(&ionic->dev_cmd_lock); + if (err) { + dev_err(ionic->dev, "Failed to init port\n"); + dma_free_coherent(ionic->dev, idev->port_info_sz, + idev->port_info, idev->port_info_pa); + idev->port_info = NULL; + idev->port_info_pa = 0; + } + + return err; +} + +int ionic_port_reset(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + if (!idev->port_info) + return 0; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + dma_free_coherent(ionic->dev, idev->port_info_sz, + idev->port_info, idev->port_info_pa); + + idev->port_info = NULL; + idev->port_info_pa = 0; + + if (err) + dev_err(ionic->dev, "Failed to reset port\n"); + + return err; +} + +static int __init ionic_init_module(void) +{ + pr_info("%s %s, ver %s\n", + IONIC_DRV_NAME, IONIC_DRV_DESCRIPTION, IONIC_DRV_VERSION); + ionic_debugfs_create(); + return ionic_bus_register_driver(); +} + +static void __exit ionic_cleanup_module(void) +{ + ionic_bus_unregister_driver(); + ionic_debugfs_destroy(); + + pr_info("%s removed\n", IONIC_DRV_NAME); +} + +module_init(ionic_init_module); +module_exit(ionic_cleanup_module); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_regs.h b/drivers/net/ethernet/pensando/ionic/ionic_regs.h new file mode 100644 index 000000000000..03ee5a36472b --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_regs.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB OR BSD-2-Clause */ +/* Copyright (c) 2018-2019 Pensando Systems, Inc. All rights reserved. */ + +#ifndef IONIC_REGS_H +#define IONIC_REGS_H + +#include <linux/io.h> + +/** struct ionic_intr - interrupt control register set. + * @coal_init: coalesce timer initial value. + * @mask: interrupt mask value. + * @credits: interrupt credit count and return. + * @mask_assert: interrupt mask value on assert. + * @coal: coalesce timer time remaining. + */ +struct ionic_intr { + u32 coal_init; + u32 mask; + u32 credits; + u32 mask_assert; + u32 coal; + u32 rsvd[3]; +}; + +#define IONIC_INTR_CTRL_REGS_MAX 2048 +#define IONIC_INTR_CTRL_COAL_MAX 0x3F + +/** enum ionic_intr_mask_vals - valid values for mask and mask_assert. + * @IONIC_INTR_MASK_CLEAR: unmask interrupt. + * @IONIC_INTR_MASK_SET: mask interrupt. + */ +enum ionic_intr_mask_vals { + IONIC_INTR_MASK_CLEAR = 0, + IONIC_INTR_MASK_SET = 1, +}; + +/** enum ionic_intr_credits_bits - bitwise composition of credits values. + * @IONIC_INTR_CRED_COUNT: bit mask of credit count, no shift needed. + * @IONIC_INTR_CRED_COUNT_SIGNED: bit mask of credit count, including sign bit. + * @IONIC_INTR_CRED_UNMASK: unmask the interrupt. + * @IONIC_INTR_CRED_RESET_COALESCE: reset the coalesce timer. + * @IONIC_INTR_CRED_REARM: unmask the and reset the timer. + */ +enum ionic_intr_credits_bits { + IONIC_INTR_CRED_COUNT = 0x7fffu, + IONIC_INTR_CRED_COUNT_SIGNED = 0xffffu, + IONIC_INTR_CRED_UNMASK = 0x10000u, + IONIC_INTR_CRED_RESET_COALESCE = 0x20000u, + IONIC_INTR_CRED_REARM = (IONIC_INTR_CRED_UNMASK | + IONIC_INTR_CRED_RESET_COALESCE), +}; + +static inline void ionic_intr_coal_init(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 coal) +{ + iowrite32(coal, &intr_ctrl[intr_idx].coal_init); +} + +static inline void ionic_intr_mask(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 mask) +{ + iowrite32(mask, &intr_ctrl[intr_idx].mask); +} + +static inline void ionic_intr_credits(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 cred, u32 flags) +{ + if (WARN_ON_ONCE(cred > IONIC_INTR_CRED_COUNT)) { + cred = ioread32(&intr_ctrl[intr_idx].credits); + cred &= IONIC_INTR_CRED_COUNT_SIGNED; + } + + iowrite32(cred | flags, &intr_ctrl[intr_idx].credits); +} + +static inline void ionic_intr_clean(struct ionic_intr __iomem *intr_ctrl, + int intr_idx) +{ + u32 cred; + + cred = ioread32(&intr_ctrl[intr_idx].credits); + cred &= IONIC_INTR_CRED_COUNT_SIGNED; + cred |= IONIC_INTR_CRED_RESET_COALESCE; + iowrite32(cred, &intr_ctrl[intr_idx].credits); +} + +static inline void ionic_intr_mask_assert(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 mask) +{ + iowrite32(mask, &intr_ctrl[intr_idx].mask_assert); +} + +/** enum ionic_dbell_bits - bitwise composition of dbell values. + * + * @IONIC_DBELL_QID_MASK: unshifted mask of valid queue id bits. + * @IONIC_DBELL_QID_SHIFT: queue id shift amount in dbell value. + * @IONIC_DBELL_QID: macro to build QID component of dbell value. + * + * @IONIC_DBELL_RING_MASK: unshifted mask of valid ring bits. + * @IONIC_DBELL_RING_SHIFT: ring shift amount in dbell value. + * @IONIC_DBELL_RING: macro to build ring component of dbell value. + * + * @IONIC_DBELL_RING_0: ring zero dbell component value. + * @IONIC_DBELL_RING_1: ring one dbell component value. + * @IONIC_DBELL_RING_2: ring two dbell component value. + * @IONIC_DBELL_RING_3: ring three dbell component value. + * + * @IONIC_DBELL_INDEX_MASK: bit mask of valid index bits, no shift needed. + */ +enum ionic_dbell_bits { + IONIC_DBELL_QID_MASK = 0xffffff, + IONIC_DBELL_QID_SHIFT = 24, + +#define IONIC_DBELL_QID(n) \ + (((u64)(n) & IONIC_DBELL_QID_MASK) << IONIC_DBELL_QID_SHIFT) + + IONIC_DBELL_RING_MASK = 0x7, + IONIC_DBELL_RING_SHIFT = 16, + +#define IONIC_DBELL_RING(n) \ + (((u64)(n) & IONIC_DBELL_RING_MASK) << IONIC_DBELL_RING_SHIFT) + + IONIC_DBELL_RING_0 = 0, + IONIC_DBELL_RING_1 = IONIC_DBELL_RING(1), + IONIC_DBELL_RING_2 = IONIC_DBELL_RING(2), + IONIC_DBELL_RING_3 = IONIC_DBELL_RING(3), + + IONIC_DBELL_INDEX_MASK = 0xffff, +}; + +static inline void ionic_dbell_ring(u64 __iomem *db_page, int qtype, u64 val) +{ + writeq(val, &db_page[qtype]); +} + +#endif /* IONIC_REGS_H */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c new file mode 100644 index 000000000000..7a093f148ee5 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_rx_filter.h" + +void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f) +{ + struct device *dev = lif->ionic->dev; + + hlist_del(&f->by_id); + hlist_del(&f->by_hash); + devm_kfree(dev, f); +} + +int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .filter_id = cpu_to_le32(f->filter_id), + }, + }; + + return ionic_adminq_post_wait(lif, &ctx); +} + +int ionic_rx_filters_init(struct ionic_lif *lif) +{ + unsigned int i; + + spin_lock_init(&lif->rx_filters.lock); + + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + INIT_HLIST_HEAD(&lif->rx_filters.by_hash[i]); + INIT_HLIST_HEAD(&lif->rx_filters.by_id[i]); + } + + return 0; +} + +void ionic_rx_filters_deinit(struct ionic_lif *lif) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + struct hlist_node *tmp; + unsigned int i; + + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + head = &lif->rx_filters.by_id[i]; + hlist_for_each_entry_safe(f, tmp, head, by_id) + ionic_rx_filter_free(lif, f); + } +} + +int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, + u32 hash, struct ionic_admin_ctx *ctx) +{ + struct device *dev = lif->ionic->dev; + struct ionic_rx_filter_add_cmd *ac; + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + ac = &ctx->cmd.rx_filter_add; + + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + key = le16_to_cpu(ac->vlan.vlan); + break; + case IONIC_RX_FILTER_MATCH_MAC: + key = *(u32 *)ac->mac.addr; + break; + case IONIC_RX_FILTER_MATCH_MAC_VLAN: + key = le16_to_cpu(ac->mac_vlan.vlan); + break; + default: + return -EINVAL; + } + + f = devm_kzalloc(dev, sizeof(*f), GFP_KERNEL); + if (!f) + return -ENOMEM; + + f->flow_id = flow_id; + f->filter_id = le32_to_cpu(ctx->comp.rx_filter_add.filter_id); + f->rxq_index = rxq_index; + memcpy(&f->cmd, ac, sizeof(f->cmd)); + + INIT_HLIST_NODE(&f->by_hash); + INIT_HLIST_NODE(&f->by_id); + + spin_lock_bh(&lif->rx_filters.lock); + + key = hash_32(key, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + hlist_add_head(&f->by_hash, head); + + key = f->filter_id & IONIC_RX_FILTER_HLISTS_MASK; + head = &lif->rx_filters.by_id[key]; + hlist_add_head(&f->by_id, head); + + spin_unlock_bh(&lif->rx_filters.lock); + + return 0; +} + +struct ionic_rx_filter *ionic_rx_filter_by_vlan(struct ionic_lif *lif, u16 vid) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + key = hash_32(vid, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + + hlist_for_each_entry(f, head, by_hash) { + if (le16_to_cpu(f->cmd.match) != IONIC_RX_FILTER_MATCH_VLAN) + continue; + if (le16_to_cpu(f->cmd.vlan.vlan) == vid) + return f; + } + + return NULL; +} + +struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, + const u8 *addr) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + key = hash_32(*(u32 *)addr, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + + hlist_for_each_entry(f, head, by_hash) { + if (le16_to_cpu(f->cmd.match) != IONIC_RX_FILTER_MATCH_MAC) + continue; + if (memcmp(addr, f->cmd.mac.addr, ETH_ALEN) == 0) + return f; + } + + return NULL; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h new file mode 100644 index 000000000000..b6aec9c19918 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_RX_FILTER_H_ +#define _IONIC_RX_FILTER_H_ + +#define IONIC_RXQ_INDEX_ANY (0xFFFF) +struct ionic_rx_filter { + u32 flow_id; + u32 filter_id; + u16 rxq_index; + struct ionic_rx_filter_add_cmd cmd; + struct hlist_node by_hash; + struct hlist_node by_id; +}; + +#define IONIC_RX_FILTER_HASH_BITS 10 +#define IONIC_RX_FILTER_HLISTS BIT(IONIC_RX_FILTER_HASH_BITS) +#define IONIC_RX_FILTER_HLISTS_MASK (IONIC_RX_FILTER_HLISTS - 1) +struct ionic_rx_filters { + spinlock_t lock; /* filter list lock */ + struct hlist_head by_hash[IONIC_RX_FILTER_HLISTS]; /* by skb hash */ + struct hlist_head by_id[IONIC_RX_FILTER_HLISTS]; /* by filter_id */ +}; + +void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f); +int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f); +int ionic_rx_filters_init(struct ionic_lif *lif); +void ionic_rx_filters_deinit(struct ionic_lif *lif); +int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, + u32 hash, struct ionic_admin_ctx *ctx); +struct ionic_rx_filter *ionic_rx_filter_by_vlan(struct ionic_lif *lif, u16 vid); +struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, const u8 *addr); + +#endif /* _IONIC_RX_FILTER_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c new file mode 100644 index 000000000000..e2907884f843 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_stats.h" + +static const struct ionic_stat_desc ionic_lif_stats_desc[] = { + IONIC_LIF_STAT_DESC(tx_packets), + IONIC_LIF_STAT_DESC(tx_bytes), + IONIC_LIF_STAT_DESC(rx_packets), + IONIC_LIF_STAT_DESC(rx_bytes), + IONIC_LIF_STAT_DESC(tx_tso), + IONIC_LIF_STAT_DESC(tx_no_csum), + IONIC_LIF_STAT_DESC(tx_csum), + IONIC_LIF_STAT_DESC(rx_csum_none), + IONIC_LIF_STAT_DESC(rx_csum_complete), + IONIC_LIF_STAT_DESC(rx_csum_error), +}; + +static const struct ionic_stat_desc ionic_tx_stats_desc[] = { + IONIC_TX_STAT_DESC(pkts), + IONIC_TX_STAT_DESC(bytes), + IONIC_TX_STAT_DESC(clean), + IONIC_TX_STAT_DESC(dma_map_err), + IONIC_TX_STAT_DESC(linearize), + IONIC_TX_STAT_DESC(frags), +}; + +static const struct ionic_stat_desc ionic_rx_stats_desc[] = { + IONIC_RX_STAT_DESC(pkts), + IONIC_RX_STAT_DESC(bytes), + IONIC_RX_STAT_DESC(dma_map_err), + IONIC_RX_STAT_DESC(alloc_err), + IONIC_RX_STAT_DESC(csum_none), + IONIC_RX_STAT_DESC(csum_complete), + IONIC_RX_STAT_DESC(csum_error), +}; + +static const struct ionic_stat_desc ionic_txq_stats_desc[] = { + IONIC_TX_Q_STAT_DESC(stop), + IONIC_TX_Q_STAT_DESC(wake), + IONIC_TX_Q_STAT_DESC(drop), + IONIC_TX_Q_STAT_DESC(dbell_count), +}; + +static const struct ionic_stat_desc ionic_dbg_cq_stats_desc[] = { + IONIC_CQ_STAT_DESC(compl_count), +}; + +static const struct ionic_stat_desc ionic_dbg_intr_stats_desc[] = { + IONIC_INTR_STAT_DESC(rearm_count), +}; + +static const struct ionic_stat_desc ionic_dbg_napi_stats_desc[] = { + IONIC_NAPI_STAT_DESC(poll_count), +}; + +#define IONIC_NUM_LIF_STATS ARRAY_SIZE(ionic_lif_stats_desc) +#define IONIC_NUM_TX_STATS ARRAY_SIZE(ionic_tx_stats_desc) +#define IONIC_NUM_RX_STATS ARRAY_SIZE(ionic_rx_stats_desc) +#define IONIC_NUM_TX_Q_STATS ARRAY_SIZE(ionic_txq_stats_desc) +#define IONIC_NUM_DBG_CQ_STATS ARRAY_SIZE(ionic_dbg_cq_stats_desc) +#define IONIC_NUM_DBG_INTR_STATS ARRAY_SIZE(ionic_dbg_intr_stats_desc) +#define IONIC_NUM_DBG_NAPI_STATS ARRAY_SIZE(ionic_dbg_napi_stats_desc) + +#define MAX_Q(lif) ((lif)->netdev->real_num_tx_queues) + +static void ionic_get_lif_stats(struct ionic_lif *lif, + struct ionic_lif_sw_stats *stats) +{ + struct ionic_tx_stats *tstats; + struct ionic_rx_stats *rstats; + struct ionic_qcq *txqcq; + struct ionic_qcq *rxqcq; + int q_num; + + memset(stats, 0, sizeof(*stats)); + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + txqcq = lif_to_txqcq(lif, q_num); + if (txqcq && txqcq->stats) { + tstats = &txqcq->stats->tx; + stats->tx_packets += tstats->pkts; + stats->tx_bytes += tstats->bytes; + stats->tx_tso += tstats->tso; + stats->tx_no_csum += tstats->no_csum; + stats->tx_csum += tstats->csum; + } + + rxqcq = lif_to_rxqcq(lif, q_num); + if (rxqcq && rxqcq->stats) { + rstats = &rxqcq->stats->rx; + stats->rx_packets += rstats->pkts; + stats->rx_bytes += rstats->bytes; + stats->rx_csum_none += rstats->csum_none; + stats->rx_csum_complete += rstats->csum_complete; + stats->rx_csum_error += rstats->csum_error; + } + } +} + +static u64 ionic_sw_stats_get_count(struct ionic_lif *lif) +{ + u64 total = 0; + + /* lif stats */ + total += IONIC_NUM_LIF_STATS; + + /* tx stats */ + total += MAX_Q(lif) * IONIC_NUM_TX_STATS; + + /* rx stats */ + total += MAX_Q(lif) * IONIC_NUM_RX_STATS; + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + /* tx debug stats */ + total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + + IONIC_NUM_TX_Q_STATS + + IONIC_NUM_DBG_INTR_STATS + + IONIC_MAX_NUM_SG_CNTR); + + /* rx debug stats */ + total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + + IONIC_NUM_DBG_INTR_STATS + + IONIC_NUM_DBG_NAPI_STATS + + IONIC_MAX_NUM_NAPI_CNTR); + } + + return total; +} + +static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) +{ + int i, q_num; + + for (i = 0; i < IONIC_NUM_LIF_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, ionic_lif_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + for (i = 0; i < IONIC_NUM_TX_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, "tx_%d_%s", + q_num, ionic_tx_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_%s", + q_num, + ionic_txq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_cq_%s", + q_num, + ionic_dbg_cq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_intr_%s", + q_num, + ionic_dbg_intr_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_sg_cntr_%d", + q_num, i); + *buf += ETH_GSTRING_LEN; + } + } + } + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + for (i = 0; i < IONIC_NUM_RX_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rx_%d_%s", + q_num, ionic_rx_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_cq_%s", + q_num, + ionic_dbg_cq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_intr_%s", + q_num, + ionic_dbg_intr_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_napi_%s", + q_num, + ionic_dbg_napi_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_napi_work_done_%d", + q_num, i); + *buf += ETH_GSTRING_LEN; + } + } + } +} + +static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) +{ + struct ionic_lif_sw_stats lif_stats; + struct ionic_qcq *txqcq, *rxqcq; + int i, q_num; + + ionic_get_lif_stats(lif, &lif_stats); + + for (i = 0; i < IONIC_NUM_LIF_STATS; i++) { + **buf = IONIC_READ_STAT64(&lif_stats, &ionic_lif_stats_desc[i]); + (*buf)++; + } + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + txqcq = lif_to_txqcq(lif, q_num); + + for (i = 0; i < IONIC_NUM_TX_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->stats->tx, + &ionic_tx_stats_desc[i]); + (*buf)++; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->q, + &ionic_txq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->cq, + &ionic_dbg_cq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->intr, + &ionic_dbg_intr_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { + **buf = txqcq->stats->tx.sg_cntr[i]; + (*buf)++; + } + } + } + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + rxqcq = lif_to_rxqcq(lif, q_num); + + for (i = 0; i < IONIC_NUM_RX_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->stats->rx, + &ionic_rx_stats_desc[i]); + (*buf)++; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->cq, + &ionic_dbg_cq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->intr, + &ionic_dbg_intr_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->napi_stats, + &ionic_dbg_napi_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { + **buf = rxqcq->napi_stats.work_done_cntr[i]; + (*buf)++; + } + } + } +} + +const struct ionic_stats_group_intf ionic_stats_groups[] = { + /* SW Stats group */ + { + .get_strings = ionic_sw_stats_get_strings, + .get_values = ionic_sw_stats_get_values, + .get_count = ionic_sw_stats_get_count, + }, + /* Add more stat groups here */ +}; + +const int ionic_num_stats_grps = ARRAY_SIZE(ionic_stats_groups); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.h b/drivers/net/ethernet/pensando/ionic/ionic_stats.h new file mode 100644 index 000000000000..d2c1122a2c6e --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_STATS_H_ +#define _IONIC_STATS_H_ + +#define IONIC_STAT_TO_OFFSET(type, stat_name) (offsetof(type, stat_name)) + +#define IONIC_STAT_DESC(type, stat_name) { \ + .name = #stat_name, \ + .offset = IONIC_STAT_TO_OFFSET(type, stat_name) \ +} + +#define IONIC_LIF_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_lif_sw_stats, stat_name) + +#define IONIC_TX_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_tx_stats, stat_name) + +#define IONIC_RX_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_rx_stats, stat_name) + +#define IONIC_TX_Q_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_queue, stat_name) + +#define IONIC_CQ_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_cq, stat_name) + +#define IONIC_INTR_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_intr_info, stat_name) + +#define IONIC_NAPI_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_napi_stats, stat_name) + +/* Interface structure for a particalar stats group */ +struct ionic_stats_group_intf { + void (*get_strings)(struct ionic_lif *lif, u8 **buf); + void (*get_values)(struct ionic_lif *lif, u64 **buf); + u64 (*get_count)(struct ionic_lif *lif); +}; + +extern const struct ionic_stats_group_intf ionic_stats_groups[]; +extern const int ionic_num_stats_grps; + +#define IONIC_READ_STAT64(base_ptr, desc_ptr) \ + (*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset))) + +struct ionic_stat_desc { + char name[ETH_GSTRING_LEN]; + u64 offset; +}; + +#endif /* _IONIC_STATS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c new file mode 100644 index 000000000000..ab6663d94f42 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -0,0 +1,925 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_vlan.h> +#include <net/ip6_checksum.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_txrx.h" + +static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg); + +static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, + ionic_desc_cb cb_func, void *cb_arg) +{ + DEBUG_STATS_TXQ_POST(q_to_qcq(q), q->head->desc, ring_dbell); + + ionic_q_post(q, ring_dbell, cb_func, cb_arg); +} + +static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, + ionic_desc_cb cb_func, void *cb_arg) +{ + ionic_q_post(q, ring_dbell, cb_func, cb_arg); + + DEBUG_STATS_RX_BUFF_CNT(q_to_qcq(q)); +} + +static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) +{ + return netdev_get_tx_queue(q->lif->netdev, q->index); +} + +static void ionic_rx_recycle(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct sk_buff *skb) +{ + struct ionic_rxq_desc *old = desc_info->desc; + struct ionic_rxq_desc *new = q->head->desc; + + new->addr = old->addr; + new->len = old->len; + + ionic_rxq_post(q, true, ionic_rx_clean, skb); +} + +static bool ionic_rx_copybreak(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, struct sk_buff **skb) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_rxq_desc *desc = desc_info->desc; + struct net_device *netdev = q->lif->netdev; + struct device *dev = q->lif->ionic->dev; + struct sk_buff *new_skb; + u16 clen, dlen; + + clen = le16_to_cpu(comp->len); + dlen = le16_to_cpu(desc->len); + if (clen > q->lif->rx_copybreak) { + dma_unmap_single(dev, (dma_addr_t)le64_to_cpu(desc->addr), + dlen, DMA_FROM_DEVICE); + return false; + } + + new_skb = netdev_alloc_skb_ip_align(netdev, clen); + if (!new_skb) { + dma_unmap_single(dev, (dma_addr_t)le64_to_cpu(desc->addr), + dlen, DMA_FROM_DEVICE); + return false; + } + + dma_sync_single_for_cpu(dev, (dma_addr_t)le64_to_cpu(desc->addr), + clen, DMA_FROM_DEVICE); + + memcpy(new_skb->data, (*skb)->data, clen); + + ionic_rx_recycle(q, desc_info, *skb); + *skb = new_skb; + + return true; +} + +static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_qcq *qcq = q_to_qcq(q); + struct sk_buff *skb = cb_arg; + struct ionic_rx_stats *stats; + struct net_device *netdev; + + stats = q_to_rx_stats(q); + netdev = q->lif->netdev; + + if (comp->status) { + ionic_rx_recycle(q, desc_info, skb); + return; + } + + if (unlikely(test_bit(IONIC_LIF_QUEUE_RESET, q->lif->state))) { + /* no packet processing while resetting */ + ionic_rx_recycle(q, desc_info, skb); + return; + } + + stats->pkts++; + stats->bytes += le16_to_cpu(comp->len); + + ionic_rx_copybreak(q, desc_info, cq_info, &skb); + + skb_put(skb, le16_to_cpu(comp->len)); + skb->protocol = eth_type_trans(skb, netdev); + + skb_record_rx_queue(skb, q->index); + + if (netdev->features & NETIF_F_RXHASH) { + switch (comp->pkt_type_color & IONIC_RXQ_COMP_PKT_TYPE_MASK) { + case IONIC_PKT_TYPE_IPV4: + case IONIC_PKT_TYPE_IPV6: + skb_set_hash(skb, le32_to_cpu(comp->rss_hash), + PKT_HASH_TYPE_L3); + break; + case IONIC_PKT_TYPE_IPV4_TCP: + case IONIC_PKT_TYPE_IPV6_TCP: + case IONIC_PKT_TYPE_IPV4_UDP: + case IONIC_PKT_TYPE_IPV6_UDP: + skb_set_hash(skb, le32_to_cpu(comp->rss_hash), + PKT_HASH_TYPE_L4); + break; + } + } + + if (netdev->features & NETIF_F_RXCSUM) { + if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) { + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum = (__wsum)le16_to_cpu(comp->csum); + stats->csum_complete++; + } + } else { + stats->csum_none++; + } + + if ((comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_TCP_BAD) || + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_UDP_BAD) || + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_IP_BAD)) + stats->csum_error++; + + if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { + if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_VLAN) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + le16_to_cpu(comp->vlan_tci)); + } + + napi_gro_receive(&qcq->napi, skb); +} + +static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_queue *q = cq->bound_q; + struct ionic_desc_info *desc_info; + + if (!color_match(comp->pkt_type_color, cq->done_color)) + return false; + + /* check for empty queue */ + if (q->tail->index == q->head->index) + return false; + + desc_info = q->tail; + if (desc_info->index != le16_to_cpu(comp->comp_index)) + return false; + + q->tail = desc_info->next; + + /* clean the related q entry, only one per qc completion */ + ionic_rx_clean(q, desc_info, cq_info, desc_info->cb_arg); + + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + + return true; +} + +static u32 ionic_rx_walk_cq(struct ionic_cq *rxcq, u32 limit) +{ + u32 work_done = 0; + + while (ionic_rx_service(rxcq, rxcq->tail)) { + if (rxcq->tail->last) + rxcq->done_color = !rxcq->done_color; + rxcq->tail = rxcq->tail->next; + DEBUG_STATS_CQE_CNT(rxcq); + + if (++work_done >= limit) + break; + } + + return work_done; +} + +void ionic_rx_flush(struct ionic_cq *cq) +{ + struct ionic_dev *idev = &cq->lif->ionic->idev; + u32 work_done; + + work_done = ionic_rx_walk_cq(cq, cq->num_descs); + + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, IONIC_INTR_CRED_RESET_COALESCE); +} + +static struct sk_buff *ionic_rx_skb_alloc(struct ionic_queue *q, unsigned int len, + dma_addr_t *dma_addr) +{ + struct ionic_lif *lif = q->lif; + struct ionic_rx_stats *stats; + struct net_device *netdev; + struct sk_buff *skb; + struct device *dev; + + netdev = lif->netdev; + dev = lif->ionic->dev; + stats = q_to_rx_stats(q); + skb = netdev_alloc_skb_ip_align(netdev, len); + if (!skb) { + net_warn_ratelimited("%s: SKB alloc failed on %s!\n", + netdev->name, q->name); + stats->alloc_err++; + return NULL; + } + + *dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, *dma_addr)) { + dev_kfree_skb(skb); + net_warn_ratelimited("%s: DMA single map failed on %s!\n", + netdev->name, q->name); + stats->dma_map_err++; + return NULL; + } + + return skb; +} + +#define IONIC_RX_RING_DOORBELL_STRIDE ((1 << 2) - 1) + +void ionic_rx_fill(struct ionic_queue *q) +{ + struct net_device *netdev = q->lif->netdev; + struct ionic_rxq_desc *desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + bool ring_doorbell; + unsigned int len; + unsigned int i; + + len = netdev->mtu + ETH_HLEN; + + for (i = ionic_q_space_avail(q); i; i--) { + skb = ionic_rx_skb_alloc(q, len, &dma_addr); + if (!skb) + return; + + desc = q->head->desc; + desc->addr = cpu_to_le64(dma_addr); + desc->len = cpu_to_le16(len); + desc->opcode = IONIC_RXQ_DESC_OPCODE_SIMPLE; + + ring_doorbell = ((q->head->index + 1) & + IONIC_RX_RING_DOORBELL_STRIDE) == 0; + + ionic_rxq_post(q, ring_doorbell, ionic_rx_clean, skb); + } +} + +static void ionic_rx_fill_cb(void *arg) +{ + ionic_rx_fill(arg); +} + +void ionic_rx_empty(struct ionic_queue *q) +{ + struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *cur; + struct ionic_rxq_desc *desc; + + for (cur = q->tail; cur != q->head; cur = cur->next) { + desc = cur->desc; + dma_unmap_single(dev, le64_to_cpu(desc->addr), + le16_to_cpu(desc->len), DMA_FROM_DEVICE); + dev_kfree_skb(cur->cb_arg); + cur->cb_arg = NULL; + } +} + +int ionic_rx_napi(struct napi_struct *napi, int budget) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *rxcq = napi_to_cq(napi); + unsigned int qi = rxcq->bound_q->index; + struct ionic_dev *idev; + struct ionic_lif *lif; + struct ionic_cq *txcq; + u32 work_done = 0; + u32 flags = 0; + + lif = rxcq->bound_q->lif; + idev = &lif->ionic->idev; + txcq = &lif->txqcqs[qi].qcq->cq; + + ionic_tx_flush(txcq); + + work_done = ionic_rx_walk_cq(rxcq, budget); + + if (work_done) + ionic_rx_fill_cb(rxcq->bound_q); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(rxcq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + +static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t len) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + + dma_addr = dma_map_single(dev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + net_warn_ratelimited("%s: DMA single map failed on %s!\n", + q->lif->netdev->name, q->name); + stats->dma_map_err++; + return 0; + } + return dma_addr; +} + +static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, const skb_frag_t *frag, + size_t offset, size_t len) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + + dma_addr = skb_frag_dma_map(dev, frag, offset, len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + net_warn_ratelimited("%s: DMA frag map failed on %s!\n", + q->lif->netdev->name, q->name); + stats->dma_map_err++; + } + return dma_addr; +} + +static void ionic_tx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_txq_sg_desc *sg_desc = desc_info->sg_desc; + struct ionic_txq_sg_elem *elem = sg_desc->elems; + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = desc_info->desc; + struct device *dev = q->lif->ionic->dev; + u8 opcode, flags, nsge; + u16 queue_index; + unsigned int i; + u64 addr; + + decode_txq_desc_cmd(le64_to_cpu(desc->cmd), + &opcode, &flags, &nsge, &addr); + + /* use unmap_single only if either this is not TSO, + * or this is first descriptor of a TSO + */ + if (opcode != IONIC_TXQ_DESC_OPCODE_TSO || + flags & IONIC_TXQ_DESC_FLAG_TSO_SOT) + dma_unmap_single(dev, (dma_addr_t)addr, + le16_to_cpu(desc->len), DMA_TO_DEVICE); + else + dma_unmap_page(dev, (dma_addr_t)addr, + le16_to_cpu(desc->len), DMA_TO_DEVICE); + + for (i = 0; i < nsge; i++, elem++) + dma_unmap_page(dev, (dma_addr_t)le64_to_cpu(elem->addr), + le16_to_cpu(elem->len), DMA_TO_DEVICE); + + if (cb_arg) { + struct sk_buff *skb = cb_arg; + u32 len = skb->len; + + queue_index = skb_get_queue_mapping(skb); + if (unlikely(__netif_subqueue_stopped(q->lif->netdev, + queue_index))) { + netif_wake_subqueue(q->lif->netdev, queue_index); + q->wake++; + } + dev_kfree_skb_any(skb); + stats->clean++; + netdev_tx_completed_queue(q_to_ndq(q), 1, len); + } +} + +void ionic_tx_flush(struct ionic_cq *cq) +{ + struct ionic_txq_comp *comp = cq->tail->cq_desc; + struct ionic_dev *idev = &cq->lif->ionic->idev; + struct ionic_queue *q = cq->bound_q; + struct ionic_desc_info *desc_info; + unsigned int work_done = 0; + + /* walk the completed cq entries */ + while (work_done < cq->num_descs && + color_match(comp->color, cq->done_color)) { + + /* clean the related q entries, there could be + * several q entries completed for each cq completion + */ + do { + desc_info = q->tail; + q->tail = desc_info->next; + ionic_tx_clean(q, desc_info, cq->tail, + desc_info->cb_arg); + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + } while (desc_info->index != le16_to_cpu(comp->comp_index)); + + if (cq->tail->last) + cq->done_color = !cq->done_color; + + cq->tail = cq->tail->next; + comp = cq->tail->cq_desc; + DEBUG_STATS_CQE_CNT(cq); + + work_done++; + } + + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, 0); +} + +static int ionic_tx_tcp_inner_pseudo_csum(struct sk_buff *skb) +{ + int err; + + err = skb_cow_head(skb, 0); + if (err) + return err; + + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + inner_ip_hdr(skb)->check = 0; + inner_tcp_hdr(skb)->check = + ~csum_tcpudp_magic(inner_ip_hdr(skb)->saddr, + inner_ip_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) { + inner_tcp_hdr(skb)->check = + ~csum_ipv6_magic(&inner_ipv6_hdr(skb)->saddr, + &inner_ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } + + return 0; +} + +static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) +{ + int err; + + err = skb_cow_head(skb, 0); + if (err) + return err; + + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + ip_hdr(skb)->check = 0; + 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); + } + + return 0; +} + +static void ionic_tx_tso_post(struct ionic_queue *q, struct ionic_txq_desc *desc, + struct sk_buff *skb, + dma_addr_t addr, u8 nsge, u16 len, + unsigned int hdrlen, unsigned int mss, + bool outer_csum, + u16 vlan_tci, bool has_vlan, + bool start, bool done) +{ + u8 flags = 0; + u64 cmd; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= outer_csum ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + flags |= start ? IONIC_TXQ_DESC_FLAG_TSO_SOT : 0; + flags |= done ? IONIC_TXQ_DESC_FLAG_TSO_EOT : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_TSO, flags, nsge, addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(len); + desc->vlan_tci = cpu_to_le16(vlan_tci); + desc->hdr_len = cpu_to_le16(hdrlen); + desc->mss = cpu_to_le16(mss); + + if (done) { + skb_tx_timestamp(skb); + netdev_tx_sent_queue(q_to_ndq(q), skb->len); + ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb); + } else { + ionic_txq_post(q, false, ionic_tx_clean, NULL); + } +} + +static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, + struct ionic_txq_sg_elem **elem) +{ + struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + struct ionic_txq_desc *desc = q->head->desc; + + *elem = sg_desc->elems; + return desc; +} + +static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_desc_info *abort = q->head; + struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *rewind = abort; + struct ionic_txq_sg_elem *elem; + struct ionic_txq_desc *desc; + unsigned int frag_left = 0; + unsigned int offset = 0; + unsigned int len_left; + dma_addr_t desc_addr; + unsigned int hdrlen; + unsigned int nfrags; + unsigned int seglen; + u64 total_bytes = 0; + u64 total_pkts = 0; + unsigned int left; + unsigned int len; + unsigned int mss; + skb_frag_t *frag; + bool start, done; + bool outer_csum; + bool has_vlan; + u16 desc_len; + u8 desc_nsge; + u16 vlan_tci; + bool encap; + int err; + + mss = skb_shinfo(skb)->gso_size; + nfrags = skb_shinfo(skb)->nr_frags; + len_left = skb->len - skb_headlen(skb); + outer_csum = (skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM) || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + has_vlan = !!skb_vlan_tag_present(skb); + vlan_tci = skb_vlan_tag_get(skb); + encap = skb->encapsulation; + + /* Preload inner-most TCP csum field with IP pseudo hdr + * calculated with IP length set to zero. HW will later + * add in length to each TCP segment resulting from the TSO. + */ + + if (encap) + err = ionic_tx_tcp_inner_pseudo_csum(skb); + else + err = ionic_tx_tcp_pseudo_csum(skb); + if (err) + return err; + + if (encap) + hdrlen = skb_inner_transport_header(skb) - skb->data + + inner_tcp_hdrlen(skb); + else + hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb); + + seglen = hdrlen + mss; + left = skb_headlen(skb); + + desc = ionic_tx_tso_next(q, &elem); + start = true; + + /* Chop skb->data up into desc segments */ + + while (left > 0) { + len = min(seglen, left); + frag_left = seglen - len; + desc_addr = ionic_tx_map_single(q, skb->data + offset, len); + if (dma_mapping_error(dev, desc_addr)) + goto err_out_abort; + desc_len = len; + desc_nsge = 0; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, + desc_addr, desc_nsge, desc_len, + hdrlen, mss, + outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + seglen = mss; + } + + /* Chop skb frags into desc segments */ + + for (frag = skb_shinfo(skb)->frags; len_left; frag++) { + offset = 0; + left = skb_frag_size(frag); + len_left -= left; + nfrags--; + stats->frags++; + + while (left > 0) { + if (frag_left > 0) { + len = min(frag_left, left); + frag_left -= len; + elem->addr = + cpu_to_le64(ionic_tx_map_frag(q, frag, + offset, len)); + if (dma_mapping_error(dev, elem->addr)) + goto err_out_abort; + elem->len = cpu_to_le16(len); + elem++; + desc_nsge++; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, desc_addr, + desc_nsge, desc_len, + hdrlen, mss, outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + } else { + len = min(mss, left); + frag_left = mss - len; + desc_addr = ionic_tx_map_frag(q, frag, + offset, len); + if (dma_mapping_error(dev, desc_addr)) + goto err_out_abort; + desc_len = len; + desc_nsge = 0; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, desc_addr, + desc_nsge, desc_len, + hdrlen, mss, outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + } + } + } + + stats->pkts += total_pkts; + stats->bytes += total_bytes; + stats->tso++; + + return 0; + +err_out_abort: + while (rewind->desc != q->head->desc) { + ionic_tx_clean(q, rewind, NULL, NULL); + rewind = rewind->next; + } + q->head = abort; + + return -ENOMEM; +} + +static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = q->head->desc; + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + bool has_vlan; + u8 flags = 0; + bool encap; + u64 cmd; + + has_vlan = !!skb_vlan_tag_present(skb); + encap = skb->encapsulation; + + dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= encap ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL, + flags, skb_shinfo(skb)->nr_frags, dma_addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(skb_headlen(skb)); + desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb)); + desc->csum_start = cpu_to_le16(skb_checksum_start_offset(skb)); + desc->csum_offset = cpu_to_le16(skb->csum_offset); + + if (skb->csum_not_inet) + stats->crc32_csum++; + else + stats->csum++; + + return 0; +} + +static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = q->head->desc; + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + bool has_vlan; + u8 flags = 0; + bool encap; + u64 cmd; + + has_vlan = !!skb_vlan_tag_present(skb); + encap = skb->encapsulation; + + dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= encap ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_CSUM_NONE, + flags, skb_shinfo(skb)->nr_frags, dma_addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(skb_headlen(skb)); + desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb)); + + stats->no_csum++; + + return 0; +} + +static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + unsigned int len_left = skb->len - skb_headlen(skb); + struct ionic_txq_sg_elem *elem = sg_desc->elems; + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + skb_frag_t *frag; + u16 len; + + for (frag = skb_shinfo(skb)->frags; len_left; frag++, elem++) { + len = skb_frag_size(frag); + elem->len = cpu_to_le16(len); + dma_addr = ionic_tx_map_frag(q, frag, 0, len); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + elem->addr = cpu_to_le64(dma_addr); + len_left -= len; + stats->frags++; + } + + return 0; +} + +static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + int err; + + /* set up the initial descriptor */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + err = ionic_tx_calc_csum(q, skb); + else + err = ionic_tx_calc_no_csum(q, skb); + if (err) + return err; + + /* add frags */ + err = ionic_tx_skb_frags(q, skb); + if (err) + return err; + + skb_tx_timestamp(skb); + stats->pkts++; + stats->bytes += skb->len; + + netdev_tx_sent_queue(q_to_ndq(q), skb->len); + ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb); + + return 0; +} + +static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + int err; + + /* If TSO, need roundup(skb->len/mss) descs */ + if (skb_is_gso(skb)) + return (skb->len / skb_shinfo(skb)->gso_size) + 1; + + /* If non-TSO, just need 1 desc and nr_frags sg elems */ + if (skb_shinfo(skb)->nr_frags <= IONIC_TX_MAX_SG_ELEMS) + return 1; + + /* Too many frags, so linearize */ + err = skb_linearize(skb); + if (err) + return err; + + stats->linearize++; + + /* Need 1 desc and zero sg elems */ + return 1; +} + +static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs) +{ + int stopped = 0; + + if (unlikely(!ionic_q_has_space(q, ndescs))) { + netif_stop_subqueue(q->lif->netdev, q->index); + q->stop++; + stopped = 1; + + /* Might race with ionic_tx_clean, check again */ + smp_rmb(); + if (ionic_q_has_space(q, ndescs)) { + netif_wake_subqueue(q->lif->netdev, q->index); + stopped = 0; + } + } + + return stopped; +} + +netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + u16 queue_index = skb_get_queue_mapping(skb); + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_queue *q; + int ndescs; + int err; + + if (unlikely(!test_bit(IONIC_LIF_UP, lif->state))) { + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (unlikely(!lif_to_txqcq(lif, queue_index))) + queue_index = 0; + q = lif_to_txq(lif, queue_index); + + ndescs = ionic_tx_descs_needed(q, skb); + if (ndescs < 0) + goto err_out_drop; + + if (unlikely(ionic_maybe_stop_tx(q, ndescs))) + return NETDEV_TX_BUSY; + + if (skb_is_gso(skb)) + err = ionic_tx_tso(q, skb); + else + err = ionic_tx(q, skb); + + if (err) + goto err_out_drop; + + /* Stop the queue if there aren't descriptors for the next packet. + * Since our SG lists per descriptor take care of most of the possible + * fragmentation, we don't need to have many descriptors available. + */ + ionic_maybe_stop_tx(q, 4); + + return NETDEV_TX_OK; + +err_out_drop: + q->stop++; + q->drop++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h new file mode 100644 index 000000000000..53775c62c85a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_TXRX_H_ +#define _IONIC_TXRX_H_ + +void ionic_rx_flush(struct ionic_cq *cq); +void ionic_tx_flush(struct ionic_cq *cq); + +void ionic_rx_fill(struct ionic_queue *q); +void ionic_rx_empty(struct ionic_queue *q); +int ionic_rx_napi(struct napi_struct *napi, int budget); +netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev); + +#endif /* _IONIC_TXRX_H_ */ diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index cb2ea8facd8d..3ab24fdccd3b 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1345,7 +1345,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], info->key.u.ipv4.dst = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); - if (IN_MULTICAST(ntohl(info->key.u.ipv4.dst))) { + if (ipv4_is_multicast(info->key.u.ipv4.dst)) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_REMOTE], "Remote IPv4 address cannot be Multicast"); return -EINVAL; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 778d27d1fb15..ec23c166e67b 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -757,6 +757,7 @@ struct r8152 { u32 msg_enable; u32 tx_qlen; u32 coalesce; + u32 advertising; u32 rx_buf_sz; u32 rx_copybreak; u32 rx_pending; @@ -790,6 +791,13 @@ enum tx_csum_stat { TX_CSUM_NONE }; +#define RTL_ADVERTISED_10_HALF BIT(0) +#define RTL_ADVERTISED_10_FULL BIT(1) +#define RTL_ADVERTISED_100_HALF BIT(2) +#define RTL_ADVERTISED_100_FULL BIT(3) +#define RTL_ADVERTISED_1000_HALF BIT(4) +#define RTL_ADVERTISED_1000_FULL BIT(5) + /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast). * The RTL chips use a 64 element hash table based on the Ethernet CRC. */ @@ -3801,90 +3809,117 @@ static void rtl8153b_disable(struct r8152 *tp) r8153b_aldps_en(tp, true); } -static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) +static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex, + u32 advertising) { - u16 bmcr, anar, gbcr; enum spd_duplex speed_duplex; + u16 bmcr; int ret = 0; - anar = r8152_mdio_read(tp, MII_ADVERTISE); - anar &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL | - ADVERTISE_100HALF | ADVERTISE_100FULL); - if (tp->mii.supports_gmii) { - gbcr = r8152_mdio_read(tp, MII_CTRL1000); - gbcr &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF); - } else { - gbcr = 0; - } - if (autoneg == AUTONEG_DISABLE) { - if (speed == SPEED_10) { - bmcr = 0; - anar |= ADVERTISE_10HALF | ADVERTISE_10FULL; - speed_duplex = FORCE_10M_HALF; - } else if (speed == SPEED_100) { - bmcr = BMCR_SPEED100; - anar |= ADVERTISE_100HALF | ADVERTISE_100FULL; - speed_duplex = FORCE_100M_HALF; - } else if (speed == SPEED_1000 && tp->mii.supports_gmii) { - bmcr = BMCR_SPEED1000; - gbcr |= ADVERTISE_1000FULL | ADVERTISE_1000HALF; - speed_duplex = NWAY_1000M_FULL; - } else { - ret = -EINVAL; - goto out; - } + if (duplex != DUPLEX_HALF && duplex != DUPLEX_FULL) + return -EINVAL; - if (duplex == DUPLEX_FULL) { - bmcr |= BMCR_FULLDPLX; - if (speed != SPEED_1000) - speed_duplex++; - } - } else { - if (speed == SPEED_10) { + switch (speed) { + case SPEED_10: + bmcr = BMCR_SPEED10; if (duplex == DUPLEX_FULL) { - anar |= ADVERTISE_10HALF | ADVERTISE_10FULL; - speed_duplex = NWAY_10M_FULL; + bmcr |= BMCR_FULLDPLX; + speed_duplex = FORCE_10M_FULL; } else { - anar |= ADVERTISE_10HALF; - speed_duplex = NWAY_10M_HALF; + speed_duplex = FORCE_10M_HALF; } - } else if (speed == SPEED_100) { + break; + case SPEED_100: + bmcr = BMCR_SPEED100; if (duplex == DUPLEX_FULL) { - anar |= ADVERTISE_10HALF | ADVERTISE_10FULL; - anar |= ADVERTISE_100HALF | ADVERTISE_100FULL; - speed_duplex = NWAY_100M_FULL; + bmcr |= BMCR_FULLDPLX; + speed_duplex = FORCE_100M_FULL; } else { - anar |= ADVERTISE_10HALF; - anar |= ADVERTISE_100HALF; - speed_duplex = NWAY_100M_HALF; + speed_duplex = FORCE_100M_HALF; } - } else if (speed == SPEED_1000 && tp->mii.supports_gmii) { - if (duplex == DUPLEX_FULL) { - anar |= ADVERTISE_10HALF | ADVERTISE_10FULL; - anar |= ADVERTISE_100HALF | ADVERTISE_100FULL; - gbcr |= ADVERTISE_1000FULL | ADVERTISE_1000HALF; - } else { - anar |= ADVERTISE_10HALF; - anar |= ADVERTISE_100HALF; - gbcr |= ADVERTISE_1000HALF; + break; + case SPEED_1000: + if (tp->mii.supports_gmii) { + bmcr = BMCR_SPEED1000 | BMCR_FULLDPLX; + speed_duplex = NWAY_1000M_FULL; + break; } - speed_duplex = NWAY_1000M_FULL; - } else { + /* fall through */ + default: ret = -EINVAL; goto out; } + if (duplex == DUPLEX_FULL) + tp->mii.full_duplex = 1; + else + tp->mii.full_duplex = 0; + + tp->mii.force_media = 1; + } else { + u16 anar, tmp1; + u32 support; + + support = RTL_ADVERTISED_10_HALF | RTL_ADVERTISED_10_FULL | + RTL_ADVERTISED_100_HALF | RTL_ADVERTISED_100_FULL; + + if (tp->mii.supports_gmii) + support |= RTL_ADVERTISED_1000_FULL; + + if (!(advertising & support)) + return -EINVAL; + + anar = r8152_mdio_read(tp, MII_ADVERTISE); + tmp1 = anar & ~(ADVERTISE_10HALF | ADVERTISE_10FULL | + ADVERTISE_100HALF | ADVERTISE_100FULL); + if (advertising & RTL_ADVERTISED_10_HALF) { + tmp1 |= ADVERTISE_10HALF; + speed_duplex = NWAY_10M_HALF; + } + if (advertising & RTL_ADVERTISED_10_FULL) { + tmp1 |= ADVERTISE_10FULL; + speed_duplex = NWAY_10M_FULL; + } + + if (advertising & RTL_ADVERTISED_100_HALF) { + tmp1 |= ADVERTISE_100HALF; + speed_duplex = NWAY_100M_HALF; + } + if (advertising & RTL_ADVERTISED_100_FULL) { + tmp1 |= ADVERTISE_100FULL; + speed_duplex = NWAY_100M_FULL; + } + + if (anar != tmp1) { + r8152_mdio_write(tp, MII_ADVERTISE, tmp1); + tp->mii.advertising = tmp1; + } + + if (tp->mii.supports_gmii) { + u16 gbcr; + + gbcr = r8152_mdio_read(tp, MII_CTRL1000); + tmp1 = gbcr & ~(ADVERTISE_1000FULL | + ADVERTISE_1000HALF); + + if (advertising & RTL_ADVERTISED_1000_FULL) { + tmp1 |= ADVERTISE_1000FULL; + speed_duplex = NWAY_1000M_FULL; + } + + if (gbcr != tmp1) + r8152_mdio_write(tp, MII_CTRL1000, tmp1); + } + bmcr = BMCR_ANENABLE | BMCR_ANRESTART; + + tp->mii.force_media = 0; } if (test_and_clear_bit(PHY_RESET, &tp->flags)) bmcr |= BMCR_RESET; - if (tp->mii.supports_gmii) - r8152_mdio_write(tp, MII_CTRL1000, gbcr); - - r8152_mdio_write(tp, MII_ADVERTISE, anar); r8152_mdio_write(tp, MII_BMCR, bmcr); switch (tp->version) { @@ -4122,7 +4157,8 @@ static void rtl_hw_phy_work_func_t(struct work_struct *work) tp->rtl_ops.hw_phy_cfg(tp); - rtl8152_set_speed(tp, tp->autoneg, tp->speed, tp->duplex); + rtl8152_set_speed(tp, tp->autoneg, tp->speed, tp->duplex, + tp->advertising); mutex_unlock(&tp->control); @@ -4840,20 +4876,46 @@ static int rtl8152_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { struct r8152 *tp = netdev_priv(dev); + u32 advertising = 0; int ret; ret = usb_autopm_get_interface(tp->intf); if (ret < 0) goto out; + if (test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_10_HALF; + + if (test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_10_FULL; + + if (test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_100_HALF; + + if (test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_100_FULL; + + if (test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_1000_HALF; + + if (test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + cmd->link_modes.advertising)) + advertising |= RTL_ADVERTISED_1000_FULL; + mutex_lock(&tp->control); ret = rtl8152_set_speed(tp, cmd->base.autoneg, cmd->base.speed, - cmd->base.duplex); + cmd->base.duplex, advertising); if (!ret) { tp->autoneg = cmd->base.autoneg; tp->speed = cmd->base.speed; tp->duplex = cmd->base.duplex; + tp->advertising = advertising; } mutex_unlock(&tp->control); @@ -5568,7 +5630,13 @@ static int rtl8152_probe(struct usb_interface *intf, tp->mii.phy_id = R8152_PHY_ID; tp->autoneg = AUTONEG_ENABLE; - tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100; + tp->speed = SPEED_100; + tp->advertising = RTL_ADVERTISED_10_HALF | RTL_ADVERTISED_10_FULL | + RTL_ADVERTISED_100_HALF | RTL_ADVERTISED_100_FULL; + if (tp->mii.supports_gmii) { + tp->speed = SPEED_1000; + tp->advertising |= RTL_ADVERTISED_1000_FULL; + } tp->duplex = DUPLEX_FULL; tp->rx_copybreak = RTL8152_RXFG_HEADSZ; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index c2f056b5766d..8dd081051a79 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1162,6 +1162,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) +#define MLX5_CAP64_FLOWTABLE(mdev, cap) \ + MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap) + #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \ MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap) @@ -1225,6 +1228,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(e_switch_cap, \ mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap) +#define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \ + MLX5_GET64(flow_table_eswitch_cap, \ + (mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap) + #define MLX5_CAP_ESW_MAX(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 52a56d741f79..3e80f03a387f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -626,6 +626,11 @@ struct mlx5e_resources { struct mlx5_sq_bfreg bfreg; }; +enum mlx5_sw_icm_type { + MLX5_SW_ICM_TYPE_STEERING, + MLX5_SW_ICM_TYPE_HEADER_MODIFY, +}; + #define MLX5_MAX_RESERVED_GIDS 8 struct mlx5_rsvd_gids { @@ -657,11 +662,15 @@ struct mlx5_clock { struct mlx5_pps pps_info; }; +struct mlx5_dm; struct mlx5_fw_tracer; struct mlx5_vxlan; struct mlx5_geneve; struct mlx5_hv_vhca; +#define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity)) +#define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)) + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -695,6 +704,7 @@ struct mlx5_core_dev { atomic_t num_qps; u32 issi; struct mlx5e_resources mlx5e_res; + struct mlx5_dm *dm; struct mlx5_vxlan *vxlan; struct mlx5_geneve *geneve; struct { @@ -1078,6 +1088,10 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, size_t *offsets); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); +int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id); +int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t addr, u32 obj_id); #ifdef CONFIG_MLX5_CORE_IPOIB struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 38a70d16d8d5..98e667b176ef 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -60,7 +60,6 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, u16 vport_num); void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type); -u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, u16 vport_num, u32 sqn); @@ -74,7 +73,14 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev); bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw); u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw, u16 vport_num); +u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ + +static inline u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) +{ + return MLX5_ESWITCH_NONE; +} + static inline enum devlink_eswitch_encap_mode mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 97ec6be62ac4..724d276ea133 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -84,6 +84,8 @@ enum { FDB_SLOW_PATH, }; +struct mlx5_pkt_reformat; +struct mlx5_modify_hdr; struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; @@ -121,7 +123,7 @@ struct mlx5_flow_destination { struct { u16 num; u16 vhca_id; - u32 reformat_id; + struct mlx5_pkt_reformat *pkt_reformat; u8 flags; } vport; }; @@ -195,8 +197,8 @@ enum { struct mlx5_flow_act { u32 action; - u32 reformat_id; - u32 modify_id; + struct mlx5_modify_hdr *modify_hdr; + struct mlx5_pkt_reformat *pkt_reformat; uintptr_t esp_id; u32 flags; struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; @@ -205,8 +207,6 @@ struct mlx5_flow_act { #define MLX5_DECLARE_FLOW_ACT(name) \ struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\ - .reformat_id = 0, \ - .modify_id = 0, \ .flags = 0, } /* Single destination per rule. @@ -236,19 +236,18 @@ u32 mlx5_fc_id(struct mlx5_fc *counter); int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id); +struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 ns_type, u8 num_actions, + void *modify_actions); void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, - u32 modify_header_id); - -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id); + struct mlx5_modify_hdr *modify_hdr); + +struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id); + struct mlx5_pkt_reformat *reformat); #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66b60afd5e06..7d65c0578ac9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -282,6 +282,7 @@ enum { MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT = 0x940, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941, MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT = 0x942, + MLX5_CMD_OP_SYNC_STEERING = 0xb00, MLX5_CMD_OP_FPGA_CREATE_QP = 0x960, MLX5_CMD_OP_FPGA_MODIFY_QP = 0x961, MLX5_CMD_OP_FPGA_QUERY_QP = 0x962, @@ -485,7 +486,11 @@ union mlx5_ifc_gre_key_bits { }; struct mlx5_ifc_fte_match_set_misc_bits { - u8 reserved_at_0[0x8]; + u8 gre_c_present[0x1]; + u8 reserved_auto1[0x1]; + u8 gre_k_present[0x1]; + u8 gre_s_present[0x1]; + u8 source_vhca_port[0x4]; u8 source_sqn[0x18]; u8 source_eswitch_owner_vhca_id[0x10]; @@ -565,12 +570,38 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; - u8 reserved_at_1a0[0x60]; + u8 metadata_reg_b[0x20]; + + u8 reserved_at_1c0[0x40]; }; struct mlx5_ifc_fte_match_set_misc3_bits { - u8 reserved_at_0[0x120]; + u8 inner_tcp_seq_num[0x20]; + + u8 outer_tcp_seq_num[0x20]; + + u8 inner_tcp_ack_num[0x20]; + + u8 outer_tcp_ack_num[0x20]; + + u8 reserved_at_80[0x8]; + u8 outer_vxlan_gpe_vni[0x18]; + + u8 outer_vxlan_gpe_next_protocol[0x8]; + u8 outer_vxlan_gpe_flags[0x8]; + u8 reserved_at_b0[0x10]; + + u8 icmp_header_data[0x20]; + + u8 icmpv6_header_data[0x20]; + + u8 icmp_type[0x8]; + u8 icmp_code[0x8]; + u8 icmpv6_type[0x8]; + u8 icmpv6_code[0x8]; + u8 geneve_tlv_option_0_data[0x20]; + u8 reserved_at_140[0xc0]; }; @@ -666,7 +697,15 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x7200]; + u8 reserved_at_e00[0x1200]; + + u8 sw_steering_nic_rx_action_drop_icm_address[0x40]; + + u8 sw_steering_nic_tx_action_drop_icm_address[0x40]; + + u8 sw_steering_nic_tx_action_allow_icm_address[0x40]; + + u8 reserved_at_20c0[0x5f40]; }; enum { @@ -698,7 +737,17 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_at_800[0x7800]; + u8 reserved_at_800[0x1000]; + + u8 sw_steering_fdb_action_drop_icm_address_rx[0x40]; + + u8 sw_steering_fdb_action_drop_icm_address_tx[0x40]; + + u8 sw_steering_uplink_icm_address_rx[0x40]; + + u8 sw_steering_uplink_icm_address_tx[0x40]; + + u8 reserved_at_1900[0x6700]; }; enum { @@ -849,6 +898,25 @@ struct mlx5_ifc_roce_cap_bits { u8 reserved_at_100[0x700]; }; +struct mlx5_ifc_sync_steering_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0xc0]; +}; + +struct mlx5_ifc_sync_steering_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_device_mem_cap_bits { u8 memic[0x1]; u8 reserved_at_1[0x1f]; @@ -1042,6 +1110,12 @@ enum { }; enum { + MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, + MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, + MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, +}; + +enum { MLX5_UCTX_CAP_RAW_TX = 1UL << 0, MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, }; @@ -1414,7 +1488,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_6c0[0x4]; u8 flex_parser_id_geneve_tlv_option_0[0x4]; - u8 reserved_at_6c8[0x28]; + u8 flex_parser_id_icmp_dw1[0x4]; + u8 flex_parser_id_icmp_dw0[0x4]; + u8 flex_parser_id_icmpv6_dw1[0x4]; + u8 flex_parser_id_icmpv6_dw0[0x4]; + u8 flex_parser_id_outer_first_mpls_over_gre[0x4]; + u8 flex_parser_id_outer_first_mpls_over_udp_label[0x4]; + + u8 reserved_at_6e0[0x10]; u8 sf_base_id[0x10]; u8 reserved_at_700[0x80]; @@ -2652,6 +2733,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_debug_cap_bits debug_cap; struct mlx5_ifc_fpga_cap_bits fpga_cap; struct mlx5_ifc_tls_cap_bits tls_cap; + struct mlx5_ifc_device_mem_cap_bits device_mem_cap; u8 reserved_at_0[0x8000]; }; @@ -3255,7 +3337,11 @@ struct mlx5_ifc_esw_vport_context_bits { u8 cvlan_pcp[0x3]; u8 cvlan_id[0xc]; - u8 reserved_at_60[0x7a0]; + u8 reserved_at_60[0x720]; + + u8 sw_steering_vport_icm_address_rx[0x40]; + + u8 sw_steering_vport_icm_address_tx[0x40]; }; enum { @@ -4941,23 +5027,98 @@ struct mlx5_ifc_query_hca_cap_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x40]; + u8 other_function[0x1]; + u8 reserved_at_41[0xf]; + u8 function_id[0x10]; + + u8 reserved_at_60[0x20]; }; -struct mlx5_ifc_query_flow_table_out_bits { +struct mlx5_ifc_other_hca_cap_bits { + u8 roce[0x1]; + u8 reserved_0[0x27f]; +}; + +struct mlx5_ifc_query_other_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_at_8[0x18]; + u8 reserved_0[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x80]; + u8 reserved_1[0x40]; - u8 reserved_at_c0[0x8]; + struct mlx5_ifc_other_hca_cap_bits other_capability; +}; + +struct mlx5_ifc_query_other_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + + u8 reserved_3[0x20]; +}; + +struct mlx5_ifc_modify_other_hca_cap_out_bits { + u8 status[0x8]; + u8 reserved_0[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_1[0x40]; +}; + +struct mlx5_ifc_modify_other_hca_cap_in_bits { + u8 opcode[0x10]; + u8 reserved_0[0x10]; + + u8 reserved_1[0x10]; + u8 op_mod[0x10]; + + u8 reserved_2[0x10]; + u8 function_id[0x10]; + u8 field_select[0x20]; + + struct mlx5_ifc_other_hca_cap_bits other_capability; +}; + +struct mlx5_ifc_flow_table_context_bits { + u8 reformat_en[0x1]; + u8 decap_en[0x1]; + u8 sw_owner[0x1]; + u8 termination_table[0x1]; + u8 table_miss_action[0x4]; u8 level[0x8]; - u8 reserved_at_d0[0x8]; + u8 reserved_at_10[0x8]; u8 log_size[0x8]; - u8 reserved_at_e0[0x120]; + u8 reserved_at_20[0x8]; + u8 table_miss_id[0x18]; + + u8 reserved_at_40[0x8]; + u8 lag_master_next_table_id[0x18]; + + u8 reserved_at_60[0x60]; + + u8 sw_owner_icm_root_1[0x40]; + + u8 sw_owner_icm_root_0[0x40]; + +}; + +struct mlx5_ifc_query_flow_table_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x80]; + + struct mlx5_ifc_flow_table_context_bits flow_table_context; }; struct mlx5_ifc_query_flow_table_in_bits { @@ -5227,7 +5388,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; -enum { +enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, @@ -5323,7 +5484,16 @@ enum { MLX5_ACTION_IN_FIELD_OUT_DIPV4 = 0x16, MLX5_ACTION_IN_FIELD_OUT_FIRST_VID = 0x17, MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47, + MLX5_ACTION_IN_FIELD_METADATA_REG_A = 0x49, + MLX5_ACTION_IN_FIELD_METADATA_REG_B = 0x50, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0 = 0x51, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_1 = 0x52, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_2 = 0x53, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_3 = 0x54, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_4 = 0x55, + MLX5_ACTION_IN_FIELD_METADATA_REG_C_5 = 0x56, + MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, + MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -7371,35 +7541,26 @@ struct mlx5_ifc_create_mkey_in_bits { u8 klm_pas_mtt[0][0x20]; }; +enum { + MLX5_FLOW_TABLE_TYPE_NIC_RX = 0x0, + MLX5_FLOW_TABLE_TYPE_NIC_TX = 0x1, + MLX5_FLOW_TABLE_TYPE_ESW_EGRESS_ACL = 0x2, + MLX5_FLOW_TABLE_TYPE_ESW_INGRESS_ACL = 0x3, + MLX5_FLOW_TABLE_TYPE_FDB = 0X4, + MLX5_FLOW_TABLE_TYPE_SNIFFER_RX = 0X5, + MLX5_FLOW_TABLE_TYPE_SNIFFER_TX = 0X6, +}; + struct mlx5_ifc_create_flow_table_out_bits { u8 status[0x8]; - u8 reserved_at_8[0x18]; + u8 icm_address_63_40[0x18]; u8 syndrome[0x20]; - u8 reserved_at_40[0x8]; + u8 icm_address_39_32[0x8]; u8 table_id[0x18]; - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_flow_table_context_bits { - u8 reformat_en[0x1]; - u8 decap_en[0x1]; - u8 reserved_at_2[0x1]; - u8 termination_table[0x1]; - u8 table_miss_action[0x4]; - u8 level[0x8]; - u8 reserved_at_10[0x8]; - u8 log_size[0x8]; - - u8 reserved_at_20[0x8]; - u8 table_miss_id[0x18]; - - u8 reserved_at_40[0x8]; - u8 lag_master_next_table_id[0x18]; - - u8 reserved_at_60[0xe0]; + u8 icm_address_31_0[0x20]; }; struct mlx5_ifc_create_flow_table_in_bits { diff --git a/include/net/devlink.h b/include/net/devlink.h index 13523b0a0642..460bc629d1a4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -458,6 +458,13 @@ enum devlink_param_generic_id { /* Maker of the board */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE "board.manufacture" +/* Part number, identifier of asic design */ +#define DEVLINK_INFO_VERSION_GENERIC_ASIC_ID "asic.id" +/* Revision of asic design */ +#define DEVLINK_INFO_VERSION_GENERIC_ASIC_REV "asic.rev" + +/* Overall FW version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW "fw" /* Control processor FW version */ #define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT "fw.mgmt" /* Data path microcode controlling high-speed packet processing */ diff --git a/include/net/tls.h b/include/net/tls.h index ec3c3ed2c6c3..c664e6dba0d1 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -275,16 +275,6 @@ struct tls_context { struct proto *sk_proto; void (*sk_destruct)(struct sock *sk); - void (*sk_proto_close)(struct sock *sk, long timeout); - - int (*setsockopt)(struct sock *sk, int level, - int optname, char __user *optval, - unsigned int optlen); - int (*getsockopt)(struct sock *sk, int level, - int optname, char __user *optval, - int __user *optlen); - int (*hash)(struct sock *sk); - void (*unhash)(struct sock *sk); union tls_crypto_context crypto_send; union tls_crypto_context crypto_recv; @@ -376,13 +366,9 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); -void tls_device_free_resources_tx(struct sock *sk); -void tls_device_init(void); -void tls_device_cleanup(void); int tls_tx_records(struct sock *sk, int flags); struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, @@ -659,7 +645,6 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); void tls_register_device(struct tls_device *device); void tls_unregister_device(struct tls_device *device); -int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); @@ -672,9 +657,40 @@ int tls_sw_fallback_init(struct sock *sk, struct tls_offload_context_tx *offload_ctx, struct tls_crypto_info *crypto_info); +#ifdef CONFIG_TLS_DEVICE +void tls_device_init(void); +void tls_device_cleanup(void); +int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); +void tls_device_free_resources_tx(struct sock *sk); int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); - void tls_device_offload_cleanup_rx(struct sock *sk); void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); +int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); +#else +static inline void tls_device_init(void) {} +static inline void tls_device_cleanup(void) {} +static inline int +tls_set_device_offload(struct sock *sk, struct tls_context *ctx) +{ + return -EOPNOTSUPP; +} + +static inline void tls_device_free_resources_tx(struct sock *sk) {} + +static inline int +tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) +{ + return -EOPNOTSUPP; +} + +static inline void tls_device_offload_cleanup_rx(struct sock *sk) {} +static inline void +tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {} + +static inline int tls_device_decrypted(struct sock *sk, struct sk_buff *skb) +{ + return 0; +} +#endif #endif /* _TLS_OFFLOAD_H */ diff --git a/include/net/vxlan.h b/include/net/vxlan.h index dc1583a1fb8a..335283dbe9b3 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -391,7 +391,7 @@ static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) if (ipa->sa.sa_family == AF_INET6) return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr); else - return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); + return ipv4_is_multicast(ipa->sin.sin_addr.s_addr); } #else /* !IS_ENABLED(CONFIG_IPV6) */ @@ -403,7 +403,7 @@ static inline bool vxlan_addr_any(const union vxlan_addr *ipa) static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa) { - return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr)); + return ipv4_is_multicast(ipa->sin.sin_addr.s_addr); } #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 2977137c28eb..1a5bf3fa4578 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -559,7 +559,7 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, ret = -EDESTADDRREQ; break; } - if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) || + if (ipv4_is_multicast(sin->sin_addr.s_addr) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) { ret = -EINVAL; break; @@ -593,7 +593,7 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr, addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || - IN_MULTICAST(ntohl(addr4))) { + ipv4_is_multicast(addr4)) { ret = -EPROTOTYPE; break; } diff --git a/net/rds/bind.c b/net/rds/bind.c index 0f4398e7f2a7..6dbb763bc1fd 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -181,7 +181,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in) || sin->sin_addr.s_addr == htonl(INADDR_ANY) || sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || - IN_MULTICAST(ntohl(sin->sin_addr.s_addr))) + ipv4_is_multicast(sin->sin_addr.s_addr)) return -EINVAL; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr); binding_addr = &v6addr; @@ -206,7 +206,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || - IN_MULTICAST(ntohl(addr4))) + ipv4_is_multicast(addr4)) return -EINVAL; } /* The scope ID must be specified for link local address. */ diff --git a/net/rds/send.c b/net/rds/send.c index 9ce552abf9e9..82dcd8b84fe7 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1144,7 +1144,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) case AF_INET: if (usin->sin_addr.s_addr == htonl(INADDR_ANY) || usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || - IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) { + ipv4_is_multicast(usin->sin_addr.s_addr)) { ret = -EINVAL; goto out; } @@ -1175,7 +1175,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || - IN_MULTICAST(ntohl(addr4))) { + ipv4_is_multicast(addr4)) { ret = -EINVAL; goto out; } diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 810645b5c086..93b58fde99b7 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -299,7 +299,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q) { struct ethtool_link_ksettings ecmd; int speed = SPEED_10; - int port_rate = -1; + int port_rate; int err; err = __ethtool_get_link_ksettings(dev, &ecmd); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index e188139f0464..41c106e45f01 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -159,12 +159,8 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) spin_lock_irqsave(&ctx->lock, flags); info = ctx->retransmit_hint; - if (info && !before(acked_seq, info->end_seq)) { + if (info && !before(acked_seq, info->end_seq)) ctx->retransmit_hint = NULL; - list_del(&info->list); - destroy_record(info); - deleted_records++; - } list_for_each_entry_safe(info, temp, &ctx->records_list, list) { if (before(acked_seq, info->end_seq)) @@ -838,22 +834,18 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) struct net_device *netdev; char *iv, *rec_seq; struct sk_buff *skb; - int rc = -EINVAL; __be64 rcd_sn; + int rc; if (!ctx) - goto out; + return -EINVAL; - if (ctx->priv_ctx_tx) { - rc = -EEXIST; - goto out; - } + if (ctx->priv_ctx_tx) + return -EEXIST; start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); - if (!start_marker_record) { - rc = -ENOMEM; - goto out; - } + if (!start_marker_record) + return -ENOMEM; offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL); if (!offload_ctx) { @@ -939,17 +931,11 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) if (skb) TCP_SKB_CB(skb)->eor = 1; - /* We support starting offload on multiple sockets - * concurrently, so we only need a read lock here. - * This lock must precede get_netdev_for_sock to prevent races between - * NETDEV_DOWN and setsockopt. - */ - down_read(&device_offload_lock); netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); rc = -EINVAL; - goto release_lock; + goto disable_cad; } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { @@ -960,10 +946,15 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event + * + * device_offload_lock is taken in tls_devices's NETDEV_DOWN + * handler thus protecting from the device going down before + * ctx was added to tls_device_list. */ + down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; - goto release_netdev; + goto release_lock; } ctx->priv_ctx_tx = offload_ctx; @@ -971,9 +962,10 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) - goto release_netdev; + goto release_lock; tls_device_attach(ctx, sk, netdev); + up_read(&device_offload_lock); /* following this assignment tls_is_sk_tx_device_offloaded * will return true and the context might be accessed @@ -981,13 +973,14 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) */ smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb); dev_put(netdev); - up_read(&device_offload_lock); - goto out; -release_netdev: - dev_put(netdev); + return 0; + release_lock: up_read(&device_offload_lock); +release_netdev: + dev_put(netdev); +disable_cad: clean_acked_data_disable(inet_csk(sk)); crypto_free_aead(offload_ctx->aead_send); free_rec_seq: @@ -999,7 +992,6 @@ free_offload_ctx: ctx->priv_ctx_tx = NULL; free_marker_record: kfree(start_marker_record); -out: return rc; } @@ -1012,17 +1004,10 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) if (ctx->crypto_recv.info.version != TLS_1_2_VERSION) return -EOPNOTSUPP; - /* We support starting offload on multiple sockets - * concurrently, so we only need a read lock here. - * This lock must precede get_netdev_for_sock to prevent races between - * NETDEV_DOWN and setsockopt. - */ - down_read(&device_offload_lock); netdev = get_netdev_for_sock(sk); if (!netdev) { pr_err_ratelimited("%s: netdev not found\n", __func__); - rc = -EINVAL; - goto release_lock; + return -EINVAL; } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { @@ -1033,16 +1018,21 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) /* Avoid offloading if the device is down * We don't want to offload new flows after * the NETDEV_DOWN event + * + * device_offload_lock is taken in tls_devices's NETDEV_DOWN + * handler thus protecting from the device going down before + * ctx was added to tls_device_list. */ + down_read(&device_offload_lock); if (!(netdev->flags & IFF_UP)) { rc = -EINVAL; - goto release_netdev; + goto release_lock; } context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL); if (!context) { rc = -ENOMEM; - goto release_netdev; + goto release_lock; } context->resync_nh_reset = 1; @@ -1058,7 +1048,11 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto free_sw_resources; tls_device_attach(ctx, sk, netdev); - goto release_netdev; + up_read(&device_offload_lock); + + dev_put(netdev); + + return 0; free_sw_resources: up_read(&device_offload_lock); @@ -1066,10 +1060,10 @@ free_sw_resources: down_read(&device_offload_lock); release_ctx: ctx->priv_ctx_rx = NULL; -release_netdev: - dev_put(netdev); release_lock: up_read(&device_offload_lock); +release_netdev: + dev_put(netdev); return rc; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 277f7c209fed..ac88877dcade 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -286,19 +286,14 @@ static void tls_sk_proto_cleanup(struct sock *sk, kfree(ctx->tx.rec_seq); kfree(ctx->tx.iv); tls_sw_release_resources_tx(sk); -#ifdef CONFIG_TLS_DEVICE } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); -#endif } if (ctx->rx_conf == TLS_SW) tls_sw_release_resources_rx(sk); - -#ifdef CONFIG_TLS_DEVICE - if (ctx->rx_conf == TLS_HW) + else if (ctx->rx_conf == TLS_HW) tls_device_offload_cleanup_rx(sk); -#endif } static void tls_sk_proto_close(struct sock *sk, long timeout) @@ -331,7 +326,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) tls_sw_strparser_done(ctx); if (ctx->rx_conf == TLS_SW) tls_sw_free_ctx_rx(ctx); - ctx->sk_proto_close(sk, timeout); + ctx->sk_proto->close(sk, timeout); if (free_ctx) tls_ctx_free(sk, ctx); @@ -451,7 +446,8 @@ static int tls_getsockopt(struct sock *sk, int level, int optname, struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) - return ctx->getsockopt(sk, level, optname, optval, optlen); + return ctx->sk_proto->getsockopt(sk, level, + optname, optval, optlen); return do_tls_getsockopt(sk, optname, optval, optlen); } @@ -536,26 +532,18 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) { -#ifdef CONFIG_TLS_DEVICE rc = tls_set_device_offload(sk, ctx); conf = TLS_HW; if (rc) { -#else - { -#endif rc = tls_set_sw_offload(sk, ctx, 1); if (rc) goto err_crypto_info; conf = TLS_SW; } } else { -#ifdef CONFIG_TLS_DEVICE rc = tls_set_device_offload_rx(sk, ctx); conf = TLS_HW; if (rc) { -#else - { -#endif rc = tls_set_sw_offload(sk, ctx, 0); if (rc) goto err_crypto_info; @@ -609,7 +597,8 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) - return ctx->setsockopt(sk, level, optname, optval, optlen); + return ctx->sk_proto->setsockopt(sk, level, optname, optval, + optlen); return do_tls_setsockopt(sk, optname, optval, optlen); } @@ -624,10 +613,7 @@ static struct tls_context *create_ctx(struct sock *sk) return NULL; rcu_assign_pointer(icsk->icsk_ulp_data, ctx); - ctx->setsockopt = sk->sk_prot->setsockopt; - ctx->getsockopt = sk->sk_prot->getsockopt; - ctx->sk_proto_close = sk->sk_prot->close; - ctx->unhash = sk->sk_prot->unhash; + ctx->sk_proto = sk->sk_prot; return ctx; } @@ -683,9 +669,6 @@ static int tls_hw_prot(struct sock *sk) spin_unlock_bh(&device_spinlock); tls_build_proto(sk); - ctx->hash = sk->sk_prot->hash; - ctx->unhash = sk->sk_prot->unhash; - ctx->sk_proto_close = sk->sk_prot->close; ctx->sk_destruct = sk->sk_destruct; sk->sk_destruct = tls_hw_sk_destruct; ctx->rx_conf = TLS_HW_RECORD; @@ -717,7 +700,7 @@ static void tls_hw_unhash(struct sock *sk) } } spin_unlock_bh(&device_spinlock); - ctx->unhash(sk); + ctx->sk_proto->unhash(sk); } static int tls_hw_hash(struct sock *sk) @@ -726,7 +709,7 @@ static int tls_hw_hash(struct sock *sk) struct tls_device *dev; int err; - err = ctx->hash(sk); + err = ctx->sk_proto->hash(sk); spin_lock_bh(&device_spinlock); list_for_each_entry(dev, &device_list, dev_list) { if (dev->hash) { @@ -816,7 +799,6 @@ static int tls_init(struct sock *sk) ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; - ctx->sk_proto = sk->sk_prot; update_sk_prot(sk, ctx); out: write_unlock_bh(&sk->sk_callback_lock); @@ -828,12 +810,10 @@ static void tls_update(struct sock *sk, struct proto *p) struct tls_context *ctx; ctx = tls_get_ctx(sk); - if (likely(ctx)) { - ctx->sk_proto_close = p->close; + if (likely(ctx)) ctx->sk_proto = p; - } else { + else sk->sk_prot = p; - } } static int tls_get_info(const struct sock *sk, struct sk_buff *skb) @@ -927,9 +907,7 @@ static int __init tls_register(void) tls_sw_proto_ops = inet_stream_ops; tls_sw_proto_ops.splice_read = tls_sw_splice_read; -#ifdef CONFIG_TLS_DEVICE tls_device_init(); -#endif tcp_register_ulp(&tcp_tls_ulp_ops); return 0; @@ -938,9 +916,7 @@ static int __init tls_register(void) static void __exit tls_unregister(void) { tcp_unregister_ulp(&tcp_tls_ulp_ops); -#ifdef CONFIG_TLS_DEVICE tls_device_cleanup(); -#endif } module_init(tls_register); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 91d21b048a9b..c2b5e0d2ba1a 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1489,13 +1489,12 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, int pad, err = 0; if (!ctx->decrypted) { -#ifdef CONFIG_TLS_DEVICE if (tls_ctx->rx_conf == TLS_HW) { err = tls_device_decrypted(sk, skb); if (err < 0) return err; } -#endif + /* Still not decrypted after tls_device */ if (!ctx->decrypted) { err = decrypt_internal(sk, skb, dest, NULL, chunk, zc, @@ -2014,10 +2013,9 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) ret = -EINVAL; goto read_failure; } -#ifdef CONFIG_TLS_DEVICE + tls_device_rx_resync_new_rec(strp->sk, data_len + TLS_HEADER_SIZE, TCP_SKB_CB(skb)->seq + rxm->offset); -#endif return data_len + TLS_HEADER_SIZE; read_failure: diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 94cc0fa3e848..5bb70c692b1e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -307,8 +307,13 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, spin_unlock_bh(&vvs->rx_lock); - /* We send a credit update only when the space available seen - * by the transmitter is less than VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + /* To reduce the number of credit update messages, + * don't update credits as long as lots of space is available. + * Note: the limit chosen here is arbitrary. Setting the limit + * too high causes extra messages. Too low causes transmitter + * stalls. As stalls are in theory more expensive than extra + * messages, we set the limit to a high value. TODO: experiment + * with different values. */ if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { virtio_transport_send_credit_update(vsk, |