diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
79 files changed, 5553 insertions, 1427 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 5c613c6663da5..9f54ccbddea74 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -593,30 +593,25 @@ static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) -/* In IPv6 packets, besides subtracting the pseudo header checksum, - * we also compute/add the IP header checksum which - * is not added by the HW. +/* In IPv6 packets, hw_checksum lacks 6 bytes from IPv6 header: + * 4 first bytes : priority, version, flow_lbl + * and 2 additional bytes : nexthdr, hop_limit. */ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, struct ipv6hdr *ipv6h) { __u8 nexthdr = ipv6h->nexthdr; - __wsum csum_pseudo_hdr = 0; + __wsum temp; if (unlikely(nexthdr == IPPROTO_FRAGMENT || nexthdr == IPPROTO_HOPOPTS || nexthdr == IPPROTO_SCTP)) return -1; - hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr)); - csum_pseudo_hdr = csum_partial(&ipv6h->saddr, - sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, - (__force __wsum)htons(nexthdr)); - - skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr); - skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0)); + /* priority, version, flow_lbl */ + temp = csum_add(hw_checksum, *(__wsum *)ipv6h); + /* nexthdr and hop_limit */ + skb->csum = csum_add(temp, (__force __wsum)*(__be16 *)&ipv6h->nexthdr); return 0; } #endif @@ -775,8 +770,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud act = bpf_prog_run_xdp(xdp_prog, &xdp); + length = xdp.data_end - xdp.data; if (xdp.data != orig_data) { - length = xdp.data_end - xdp.data; frags[0].page_offset = xdp.data - xdp.data_hard_start; va = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 6b68537738480..0227786308af5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -694,7 +694,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, u16 rings_p_up = priv->num_tx_rings_p_up; if (netdev_get_num_tc(dev)) - return skb_tx_hash(dev, skb); + return fallback(dev, skb); return fallback(dev, skb) % rings_p_up; } diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index de6b3d4161488..46dcbfbe4c5eb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -165,6 +165,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [36] = "QinQ VST mode support", [37] = "sl to vl mapping table change event support", [38] = "user MAC support", + [39] = "Report driver version to FW support", }; int i; @@ -1038,6 +1039,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP; if (field32 & (1 << 7)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT; + if (field32 & (1 << 8)) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW; MLX4_GET(field32, outbox, QUERY_DEV_CAP_DIAG_RPRT_PER_PORT); if (field32 & (1 << 17)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT; @@ -1860,6 +1863,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) #define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 +#define INIT_HCA_DRIVER_VERSION_OFFSET 0x140 +#define INIT_HCA_DRIVER_VERSION_SZ 0x40 #define INIT_HCA_FS_PARAM_OFFSET 0x1d0 #define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) #define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) @@ -1950,6 +1955,13 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT) *(inbox + INIT_HCA_RECOVERABLE_ERROR_EVENT_OFFSET / 4) |= cpu_to_be32(1 << 31); + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW) { + u8 *dst = (u8 *)(inbox + INIT_HCA_DRIVER_VERSION_OFFSET / 4); + + strncpy(dst, DRV_NAME_FOR_FW, INIT_HCA_DRIVER_VERSION_SZ - 1); + mlx4_dbg(dev, "Reporting Driver Version to FW: %s\n", dst); + } + /* QPC/EEC/CQC/EQC/RDMARC attributes */ MLX4_PUT(inbox, param->qpc_base, INIT_HCA_QPC_BASE_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 685337d58276f..5342bd8a3d0bf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -43,12 +43,13 @@ #include "fw.h" /* - * We allocate in page size (default 4KB on many archs) chunks to avoid high - * order memory allocations in fragmented/high usage memory situation. + * We allocate in as big chunks as we can, up to a maximum of 256 KB + * per chunk. Note that the chunks are not necessarily in contiguous + * physical memory. */ enum { - MLX4_ICM_ALLOC_SIZE = PAGE_SIZE, - MLX4_TABLE_CHUNK_SIZE = PAGE_SIZE, + MLX4_ICM_ALLOC_SIZE = 1 << 18, + MLX4_TABLE_CHUNK_SIZE = 1 << 18, }; static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk) @@ -135,6 +136,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, struct mlx4_icm *icm; struct mlx4_icm_chunk *chunk = NULL; int cur_order; + gfp_t mask; int ret; /* We use sg_set_buf for coherent allocs, which assumes low memory */ @@ -178,13 +180,17 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, while (1 << cur_order > npages) --cur_order; + mask = gfp_mask; + if (cur_order) + mask &= ~__GFP_DIRECT_RECLAIM; + if (coherent) ret = mlx4_alloc_icm_coherent(&dev->persist->pdev->dev, &chunk->mem[chunk->npages], - cur_order, gfp_mask); + cur_order, mask); else ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages], - cur_order, gfp_mask, + cur_order, mask, dev->numa_node); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 60172a38c4a43..0a30d81aab3ba 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -73,7 +73,7 @@ MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); static int msi_x = 1; module_param(msi_x, int, 0444); -MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero"); +MODULE_PARM_DESC(msi_x, "0 - don't use MSI-X, 1 - use MSI-X, >1 - limit number of MSI-X irqs to msi_x"); #else /* CONFIG_PCI_MSI */ @@ -2815,6 +2815,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) dev->caps.num_eqs - dev->caps.reserved_eqs, MAX_MSIX); + if (msi_x > 1) + nreq = min_t(int, nreq, msi_x); + entries = kcalloc(nreq, sizeof(*entries), GFP_KERNEL); if (!entries) goto no_msi; @@ -4127,17 +4130,68 @@ static const struct pci_error_handlers mlx4_err_handler = { .resume = mlx4_pci_resume, }; +static int mlx4_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; + + mlx4_err(dev, "suspend was called\n"); + mutex_lock(&persist->interface_state_mutex); + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) + mlx4_unload_one(pdev); + mutex_unlock(&persist->interface_state_mutex); + + return 0; +} + +static int mlx4_resume(struct pci_dev *pdev) +{ + struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; + struct mlx4_priv *priv = mlx4_priv(dev); + int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0}; + int total_vfs; + int ret = 0; + + mlx4_err(dev, "resume was called\n"); + total_vfs = dev->persist->num_vfs; + memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs)); + + mutex_lock(&persist->interface_state_mutex); + if (!(persist->interface_state & MLX4_INTERFACE_STATE_UP)) { + ret = mlx4_load_one(pdev, priv->pci_dev_data, total_vfs, + nvfs, priv, 1); + if (!ret) { + ret = restore_current_port_types(dev, + dev->persist->curr_port_type, + dev->persist->curr_port_poss_type); + if (ret) + mlx4_err(dev, "resume: could not restore original port types (%d)\n", ret); + } + } + mutex_unlock(&persist->interface_state_mutex); + + return ret; +} + static struct pci_driver mlx4_driver = { .name = DRV_NAME, .id_table = mlx4_pci_table, .probe = mlx4_init_one, .shutdown = mlx4_shutdown, .remove = mlx4_remove_one, + .suspend = mlx4_suspend, + .resume = mlx4_resume, .err_handler = &mlx4_err_handler, }; static int __init mlx4_verify_params(void) { + if (msi_x < 0) { + pr_warn("mlx4_core: bad msi_x: %d\n", msi_x); + return -1; + } + if ((log_num_mac < 0) || (log_num_mac > 7)) { pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac); return -1; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index c68da1986e51d..cb9e923e83996 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -55,8 +55,8 @@ #include "fw_qos.h" #define DRV_NAME "mlx4_core" -#define PFX DRV_NAME ": " #define DRV_VERSION "4.0-0" +#define DRV_NAME_FOR_FW "Linux," DRV_NAME "," DRV_VERSION #define MLX4_FS_UDP_UC_EN (1 << 1) #define MLX4_FS_TCP_UC_EN (1 << 2) diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 3ef3406ff4cbc..10fcc22f45908 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -614,9 +614,9 @@ int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int index_at_dup_port = -1; for (i = MLX4_VLAN_REGULAR; i < MLX4_MAX_VLAN_NUM; i++) { - if ((vlan == (MLX4_VLAN_MASK & be32_to_cpu(table->entries[i])))) + if (vlan == (MLX4_VLAN_MASK & be32_to_cpu(table->entries[i]))) index_at_port = i; - if ((vlan == (MLX4_VLAN_MASK & be32_to_cpu(dup_table->entries[i])))) + if (vlan == (MLX4_VLAN_MASK & be32_to_cpu(dup_table->entries[i]))) index_at_dup_port = i; } /* check that same vlan is not in the tables at different indices */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index c032319f1cb90..2545296a0c087 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -30,6 +30,7 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m + select PAGE_POOL default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. @@ -85,3 +86,15 @@ config MLX5_EN_IPSEC Build support for IPsec 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_EN_TLS + bool "TLS cryptography-offload accelaration" + depends on MLX5_CORE_EN + depends on TLS_DEVICE + depends on TLS=y || MLX5_CORE=m + depends on MLX5_ACCEL + default n + ---help--- + 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. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index c805769d92a9e..9efbf193ad5a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -8,24 +8,26 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \ diag/fs_tracepoint.o -mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o +mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ - fpga/ipsec.o + fpga/ipsec.o fpga/tls.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \ - en_arfs.o en_fs_ethtool.o en_selftest.o + en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o -mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o +mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o +mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o + CFLAGS_tracepoint.o := -I$(src) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c new file mode 100644 index 0000000000000..77ac19f38cbe8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c @@ -0,0 +1,71 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/mlx5/device.h> + +#include "accel/tls.h" +#include "mlx5_core.h" +#include "fpga/tls.h" + +int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) +{ + return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info, + start_offload_tcp_sn, p_swid); +} + +void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) +{ + mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL); +} + +bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_is_tls_device(mdev); +} + +u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_tls_device_caps(mdev); +} + +int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_tls_init(mdev); +} + +void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) +{ + mlx5_fpga_tls_cleanup(mdev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h new file mode 100644 index 0000000000000..6f9c9f446ecc8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h @@ -0,0 +1,86 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5_ACCEL_TLS_H__ +#define __MLX5_ACCEL_TLS_H__ + +#include <linux/mlx5/driver.h> +#include <linux/tls.h> + +#ifdef CONFIG_MLX5_ACCEL + +enum { + MLX5_ACCEL_TLS_TX = BIT(0), + MLX5_ACCEL_TLS_RX = BIT(1), + MLX5_ACCEL_TLS_V12 = BIT(2), + MLX5_ACCEL_TLS_V13 = BIT(3), + MLX5_ACCEL_TLS_LRO = BIT(4), + MLX5_ACCEL_TLS_IPV6 = BIT(5), + MLX5_ACCEL_TLS_AES_GCM128 = BIT(30), + MLX5_ACCEL_TLS_AES_GCM256 = BIT(31), +}; + +struct mlx5_ifc_tls_flow_bits { + u8 src_port[0x10]; + u8 dst_port[0x10]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; + u8 ipv6[0x1]; + u8 direction_sx[0x1]; + u8 reserved_at_2[0x1e]; +}; + +int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid); +void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid); +bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev); +u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev); +int mlx5_accel_tls_init(struct mlx5_core_dev *mdev); +void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev); + +#else + +static inline int +mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) { return 0; } +static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { } +static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; } +static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; } +static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; } +static inline void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) { } + +#endif + +#endif /* __MLX5_ACCEL_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 21cd1703a8620..487388aed98f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -135,6 +135,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) return cmd->cmd_buf + (idx << cmd->log_stride); } +static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg) +{ + int size = msg->len; + int blen = size - min_t(int, sizeof(msg->first.data), size); + + return DIV_ROUND_UP(blen, MLX5_CMD_DATA_BLOCK_SIZE); +} + static u8 xor8_buf(void *buf, size_t offset, int len) { u8 *ptr = buf; @@ -174,10 +182,7 @@ static void calc_block_sig(struct mlx5_cmd_prot_block *block) static void calc_chain_sig(struct mlx5_cmd_msg *msg) { struct mlx5_cmd_mailbox *next = msg->next; - int size = msg->len; - int blen = size - min_t(int, sizeof(msg->first.data), size); - int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) - / MLX5_CMD_DATA_BLOCK_SIZE; + int n = mlx5_calc_cmd_blocks(msg); int i = 0; for (i = 0; i < n && next; i++) { @@ -220,12 +225,9 @@ static void free_cmd(struct mlx5_cmd_work_ent *ent) static int verify_signature(struct mlx5_cmd_work_ent *ent) { struct mlx5_cmd_mailbox *next = ent->out->next; + int n = mlx5_calc_cmd_blocks(ent->out); int err; u8 sig; - int size = ent->out->len; - int blen = size - min_t(int, sizeof(ent->out->first.data), size); - int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) - / MLX5_CMD_DATA_BLOCK_SIZE; int i = 0; sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay)); @@ -720,9 +722,11 @@ static void dump_command(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg = input ? ent->in : ent->out; u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode); struct mlx5_cmd_mailbox *next = msg->next; + int n = mlx5_calc_cmd_blocks(msg); int data_only; u32 offset = 0; int dump_len; + int i; data_only = !!(mlx5_core_debug_mask & (1 << MLX5_CMD_DATA)); @@ -749,7 +753,7 @@ static void dump_command(struct mlx5_core_dev *dev, offset += sizeof(*ent->lay); } - while (next && offset < msg->len) { + for (i = 0; i < n && next; i++) { if (data_only) { dump_len = min_t(int, MLX5_CMD_DATA_BLOCK_SIZE, msg->len - offset); dump_buf(next->buf, dump_len, 1, offset); @@ -1137,7 +1141,6 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *tmp, *head = NULL; struct mlx5_cmd_prot_block *block; struct mlx5_cmd_msg *msg; - int blen; int err; int n; int i; @@ -1146,8 +1149,8 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, if (!msg) return ERR_PTR(-ENOMEM); - blen = size - min_t(int, sizeof(msg->first.data), size); - n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) / MLX5_CMD_DATA_BLOCK_SIZE; + msg->len = size; + n = mlx5_calc_cmd_blocks(msg); for (i = 0; i < n; i++) { tmp = alloc_cmd_box(dev, flags); @@ -1165,7 +1168,6 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, head = tmp; } msg->next = head; - msg->len = size; return msg; err_alloc: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index d93ff567b40d9..b3820a34e773a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -235,7 +235,7 @@ const char *parse_fs_dst(struct trace_seq *p, switch (dst->type) { case MLX5_FLOW_DESTINATION_TYPE_VPORT: - trace_seq_printf(p, "vport=%u\n", dst->vport_num); + trace_seq_printf(p, "vport=%u\n", dst->vport.num); break; case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: trace_seq_printf(p, "ft=%p\n", dst->ft); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 30cad07be2b51..eb9eb7aa953ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -53,6 +53,11 @@ #include "mlx5_core.h" #include "en_stats.h" +struct page_pool; + +#define MLX5E_METADATA_ETHER_TYPE (0x8CE4) +#define MLX5E_METADATA_ETHER_LEN 8 + #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) @@ -60,6 +65,7 @@ #define MLX5E_HW2SW_MTU(params, hwmtu) ((hwmtu) - ((params)->hard_mtu)) #define MLX5E_SW2HW_MTU(params, swmtu) ((swmtu) + ((params)->hard_mtu)) +#define MLX5E_MAX_PRIORITY 8 #define MLX5E_MAX_DSCP 64 #define MLX5E_MAX_NUM_TC 8 @@ -95,18 +101,22 @@ (MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW + \ (MLX5_MPWRQ_LOG_WQE_SZ - MLX5E_ORDER2_MAX_PACKET_MTU)) +#define MLX5E_MIN_SKB_FRAG_SZ (MLX5_SKB_FRAG_SZ(MLX5_RX_HEADROOM)) +#define MLX5E_LOG_MAX_RX_WQE_BULK \ + (ilog2(PAGE_SIZE / roundup_pow_of_two(MLX5E_MIN_SKB_FRAG_SZ))) + #define MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE 0x6 #define MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE 0xa #define MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE 0xd -#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE 0x1 +#define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE (1 + MLX5E_LOG_MAX_RX_WQE_BULK) #define MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE 0xa #define MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE min_t(u8, 0xd, \ MLX5E_LOG_MAX_RQ_NUM_PACKETS_MPW) #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW 0x2 -#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (256) +#define MLX5E_RX_MAX_HEAD (256) #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) #define MLX5E_DEFAULT_LRO_TIMEOUT 32 @@ -177,11 +187,16 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; + struct mlx5_wqe_data_seg data[0]; }; -struct mlx5e_rx_wqe { +struct mlx5e_rx_wqe_ll { struct mlx5_wqe_srq_next_seg next; - struct mlx5_wqe_data_seg data; + struct mlx5_wqe_data_seg data[0]; +}; + +struct mlx5e_rx_wqe_cyc { + struct mlx5_wqe_data_seg data[0]; }; struct mlx5e_umr_wqe { @@ -239,6 +254,7 @@ struct mlx5e_params { bool vlan_strip_disable; bool scatter_fcs_en; bool rx_dim_enabled; + bool tx_dim_enabled; u32 lro_timeout; u32 pflags; struct bpf_prog *xdp_prog; @@ -269,6 +285,11 @@ struct mlx5e_dcbx { /* The only setting that cannot be read from FW */ u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; u8 cap; + + /* Buffer configuration */ + bool manual_buffer; + u32 cable_len; + u32 xoff; }; struct mlx5e_dcbx_dp { @@ -282,8 +303,6 @@ enum { MLX5E_RQ_STATE_AM, }; -#define MLX5E_TEST_BIT(state, nr) (state & BIT(nr)) - struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; @@ -303,7 +322,7 @@ struct mlx5e_cq { /* control */ struct mlx5_core_dev *mdev; - struct mlx5_frag_wq_ctrl wq_ctrl; + struct mlx5_wq_ctrl wq_ctrl; } ____cacheline_aligned_in_smp; struct mlx5e_tx_wqe_info { @@ -328,6 +347,8 @@ enum { MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_RECOVERING, MLX5E_SQ_STATE_IPSEC, + MLX5E_SQ_STATE_AM, + MLX5E_SQ_STATE_TLS, }; struct mlx5e_sq_wqe_info { @@ -340,11 +361,11 @@ struct mlx5e_txqsq { /* dirtied @completion */ u16 cc; u32 dma_fifo_cc; + struct net_dim dim; /* Adaptive Moderation */ /* dirtied @xmit */ u16 pc ____cacheline_aligned_in_smp; u32 dma_fifo_pc; - struct mlx5e_sq_stats stats; struct mlx5e_cq cq; @@ -357,11 +378,11 @@ struct mlx5e_txqsq { /* read only */ struct mlx5_wq_cyc wq; u32 dma_fifo_mask; + struct mlx5e_sq_stats *stats; void __iomem *uar_map; struct netdev_queue *txq; u32 sqn; u8 min_inline_mode; - u16 edge; struct device *pdev; __be32 mkey_be; unsigned long state; @@ -392,6 +413,7 @@ struct mlx5e_xdpsq { struct { struct mlx5e_dma_info *di; bool doorbell; + bool redirect_flush; } db; /* read only */ @@ -425,7 +447,6 @@ struct mlx5e_icosq { struct mlx5_wq_cyc wq; void __iomem *uar_map; u32 sqn; - u16 edge; unsigned long state; /* control path */ @@ -436,7 +457,7 @@ struct mlx5e_icosq { static inline bool mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n) { - return (((wq->sz_m1 & (cc - pc)) >= n) || (cc == pc)); + return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc); } struct mlx5e_dma_info { @@ -445,8 +466,9 @@ struct mlx5e_dma_info { }; struct mlx5e_wqe_frag_info { - struct mlx5e_dma_info di; + struct mlx5e_dma_info *di; u32 offset; + bool last_in_page; }; struct mlx5e_umr_dma_info { @@ -459,6 +481,8 @@ struct mlx5e_mpw_info { DECLARE_BITMAP(xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE); }; +#define MLX5E_MAX_RX_FRAGS 4 + /* a single cache unit is capable to serve one napi call (for non-striding rq) * or a MPWQE (for striding rq). */ @@ -476,6 +500,9 @@ typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*); typedef struct sk_buff * (*mlx5e_fp_skb_from_cqe_mpwrq)(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx); +typedef struct sk_buff * +(*mlx5e_fp_skb_from_cqe)(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq); typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16); @@ -483,19 +510,30 @@ enum mlx5e_rq_flag { MLX5E_RQ_FLAG_XDP_XMIT = BIT(0), }; +struct mlx5e_rq_frag_info { + int frag_size; + int frag_stride; +}; + +struct mlx5e_rq_frags_info { + struct mlx5e_rq_frag_info arr[MLX5E_MAX_RX_FRAGS]; + u8 num_frags; + u8 log_num_frags; + u8 wqe_bulk; +}; + struct mlx5e_rq { /* data path */ - struct mlx5_wq_ll wq; - union { struct { - struct mlx5e_wqe_frag_info *frag_info; - u32 frag_sz; /* max possible skb frag_sz */ - union { - bool page_reuse; - }; + struct mlx5_wq_cyc wq; + struct mlx5e_wqe_frag_info *frags; + struct mlx5e_dma_info *di; + struct mlx5e_rq_frags_info info; + mlx5e_fp_skb_from_cqe skb_from_cqe; } wqe; struct { + struct mlx5_wq_ll wq; struct mlx5e_umr_wqe umr_wqe; struct mlx5e_mpw_info *info; mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq; @@ -506,14 +544,13 @@ struct mlx5e_rq { }; struct { u16 headroom; - u8 page_order; u8 map_dir; /* dma map direction */ } buff; struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; - struct mlx5e_rq_stats stats; + struct mlx5e_rq_stats *stats; struct mlx5e_cq cq; struct mlx5e_page_cache page_cache; struct hwtstamp_config *tstamp; @@ -533,6 +570,7 @@ struct mlx5e_rq { unsigned int hw_mtu; struct mlx5e_xdpsq xdpsq; DECLARE_BITMAP(flags, 8); + struct page_pool *page_pool; /* control */ struct mlx5_wq_ctrl wq_ctrl; @@ -560,7 +598,7 @@ struct mlx5e_channel { /* data path - accessed per napi poll */ struct irq_desc *irq_desc; - struct mlx5e_ch_stats stats; + struct mlx5e_ch_stats *stats; /* control */ struct mlx5e_priv *priv; @@ -576,6 +614,12 @@ struct mlx5e_channels { struct mlx5e_params params; }; +struct mlx5e_channel_stats { + struct mlx5e_ch_stats ch; + struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; + struct mlx5e_rq_stats rq; +} ____cacheline_aligned_in_smp; + enum mlx5e_traffic_types { MLX5E_TT_IPV4_TCP, MLX5E_TT_IPV6_TCP, @@ -625,7 +669,6 @@ struct mlx5e_flow_table { struct mlx5e_tc_table { struct mlx5_flow_table *t; - struct rhashtable_params ht_params; struct rhashtable ht; DECLARE_HASHTABLE(mod_hdr_tbl, 8); @@ -778,6 +821,8 @@ struct mlx5e_priv { struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; + struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS]; + u8 max_opened_tc; struct hwtstamp_config tstamp; u16 q_counter; u16 drop_rq_q_counter; @@ -790,6 +835,9 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_IPSEC struct mlx5e_ipsec *ipsec; #endif +#ifdef CONFIG_MLX5_EN_TLS + struct mlx5e_tls *tls; +#endif }; struct mlx5e_profile { @@ -820,6 +868,8 @@ void mlx5e_build_ptys2ethtool_map(void); u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe *wqe, u16 pi); void mlx5e_completion_event(struct mlx5_core_cq *mcq); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); @@ -849,6 +899,12 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct sk_buff * mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx); +struct sk_buff * +mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); +struct sk_buff * +mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); void mlx5e_update_stats(struct mlx5e_priv *priv); @@ -919,8 +975,6 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels); -int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); - void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, @@ -935,10 +989,21 @@ static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); } +static inline void mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + *wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(*wqe, 0, sizeof(**wqe)); +} + static inline struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc) { - u16 pi = *pc & wq->sz_m1; + u16 pi = mlx5_wq_cyc_ctr2ix(wq, *pc); struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; @@ -1067,6 +1132,10 @@ void mlx5e_update_stats_work(struct work_struct *work); int mlx5e_bits_invert(unsigned long a, int size); +typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv); +int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, + change_hw_mtu_cb set_mtu_cb); + /* ethtool helpers */ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo); @@ -1092,9 +1161,6 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv, int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv, struct ethtool_flash *flash); -int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv); - /* mlx5e generic netdev management API */ struct net_device* mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile, @@ -1107,4 +1173,5 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, u16 max_channels, u16 mtu); u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); +void mlx5e_tx_dim_work(struct work_struct *work); #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile new file mode 100644 index 0000000000000..d8e17110f25d0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/Makefile @@ -0,0 +1 @@ +subdir-ccflags-y += -I$(src)/.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c new file mode 100644 index 0000000000000..24e3b564964ff --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -0,0 +1,237 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include "port.h" + +/* speed in units of 1Mb */ +static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = { + [MLX5E_1000BASE_CX_SGMII] = 1000, + [MLX5E_1000BASE_KX] = 1000, + [MLX5E_10GBASE_CX4] = 10000, + [MLX5E_10GBASE_KX4] = 10000, + [MLX5E_10GBASE_KR] = 10000, + [MLX5E_20GBASE_KR2] = 20000, + [MLX5E_40GBASE_CR4] = 40000, + [MLX5E_40GBASE_KR4] = 40000, + [MLX5E_56GBASE_R4] = 56000, + [MLX5E_10GBASE_CR] = 10000, + [MLX5E_10GBASE_SR] = 10000, + [MLX5E_10GBASE_ER] = 10000, + [MLX5E_40GBASE_SR4] = 40000, + [MLX5E_40GBASE_LR4] = 40000, + [MLX5E_50GBASE_SR2] = 50000, + [MLX5E_100GBASE_CR4] = 100000, + [MLX5E_100GBASE_SR4] = 100000, + [MLX5E_100GBASE_KR4] = 100000, + [MLX5E_100GBASE_LR4] = 100000, + [MLX5E_100BASE_TX] = 100, + [MLX5E_1000BASE_T] = 1000, + [MLX5E_10GBASE_T] = 10000, + [MLX5E_25GBASE_CR] = 25000, + [MLX5E_25GBASE_KR] = 25000, + [MLX5E_25GBASE_SR] = 25000, + [MLX5E_50GBASE_CR2] = 50000, + [MLX5E_50GBASE_KR2] = 50000, +}; + +u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) +{ + unsigned long temp = eth_proto_oper; + u32 speed = 0; + int i; + + i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER); + if (i < MLX5E_LINK_MODES_NUMBER) + speed = mlx5e_link_speed[i]; + + return speed; +} + +int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {}; + u32 eth_proto_oper; + int err; + + err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1); + if (err) + return err; + + eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + *speed = mlx5e_port_ptys2speed(eth_proto_oper); + if (!(*speed)) { + mlx5_core_warn(mdev, "cannot get port speed\n"); + err = -EINVAL; + } + + return err; +} + +int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) +{ + u32 max_speed = 0; + u32 proto_cap; + int err; + int i; + + err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN); + if (err) + return err; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) + if (proto_cap & MLX5E_PROT_MASK(i)) + max_speed = max(max_speed, mlx5e_link_speed[i]); + + *speed = max_speed; + return 0; +} + +u32 mlx5e_port_speed2linkmodes(u32 speed) +{ + u32 link_modes = 0; + int i; + + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { + if (mlx5e_link_speed[i] == speed) + link_modes |= MLX5E_PROT_MASK(i); + } + + return link_modes; +} + +int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out) +{ + int sz = MLX5_ST_SZ_BYTES(pbmc_reg); + void *in; + int err; + + in = kzalloc(sz, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(pbmc_reg, in, local_port, 1); + err = mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PBMC, 0, 0); + + kfree(in); + return err; +} + +int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in) +{ + int sz = MLX5_ST_SZ_BYTES(pbmc_reg); + void *out; + int err; + + out = kzalloc(sz, GFP_KERNEL); + if (!out) + return -ENOMEM; + + MLX5_SET(pbmc_reg, in, local_port, 1); + err = mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PBMC, 0, 1); + + kfree(out); + return err; +} + +/* buffer[i]: buffer that priority i mapped to */ +int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer) +{ + int sz = MLX5_ST_SZ_BYTES(pptb_reg); + u32 prio_x_buff; + void *out; + void *in; + int prio; + int err; + + in = kzalloc(sz, GFP_KERNEL); + out = kzalloc(sz, GFP_KERNEL); + if (!in || !out) { + err = -ENOMEM; + goto out; + } + + MLX5_SET(pptb_reg, in, local_port, 1); + err = mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPTB, 0, 0); + if (err) + goto out; + + prio_x_buff = MLX5_GET(pptb_reg, out, prio_x_buff); + for (prio = 0; prio < 8; prio++) { + buffer[prio] = (u8)(prio_x_buff >> (4 * prio)) & 0xF; + mlx5_core_dbg(mdev, "prio %d, buffer %d\n", prio, buffer[prio]); + } +out: + kfree(in); + kfree(out); + return err; +} + +int mlx5e_port_set_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer) +{ + int sz = MLX5_ST_SZ_BYTES(pptb_reg); + u32 prio_x_buff; + void *out; + void *in; + int prio; + int err; + + in = kzalloc(sz, GFP_KERNEL); + out = kzalloc(sz, GFP_KERNEL); + if (!in || !out) { + err = -ENOMEM; + goto out; + } + + /* First query the pptb register */ + MLX5_SET(pptb_reg, in, local_port, 1); + err = mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPTB, 0, 0); + if (err) + goto out; + + memcpy(in, out, sz); + MLX5_SET(pptb_reg, in, local_port, 1); + + /* Update the pm and prio_x_buff */ + MLX5_SET(pptb_reg, in, pm, 0xFF); + + prio_x_buff = 0; + for (prio = 0; prio < 8; prio++) + prio_x_buff |= (buffer[prio] << (4 * prio)); + MLX5_SET(pptb_reg, in, prio_x_buff, prio_x_buff); + + err = mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPTB, 0, 1); + +out: + kfree(in); + kfree(out); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h new file mode 100644 index 0000000000000..f8cbd8194179c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -0,0 +1,48 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5E_EN_PORT_H +#define __MLX5E_EN_PORT_H + +#include <linux/mlx5/driver.h> +#include "en.h" + +u32 mlx5e_port_ptys2speed(u32 eth_proto_oper); +int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); +int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); +u32 mlx5e_port_speed2linkmodes(u32 speed); + +int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); +int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); +int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); +int mlx5e_port_set_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer); +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c new file mode 100644 index 0000000000000..c047da8752daa --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -0,0 +1,327 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#include "port_buffer.h" + +int mlx5e_port_query_buffer(struct mlx5e_priv *priv, + struct mlx5e_port_buffer *port_buffer) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int sz = MLX5_ST_SZ_BYTES(pbmc_reg); + u32 total_used = 0; + void *buffer; + void *out; + int err; + int i; + + out = kzalloc(sz, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5e_port_query_pbmc(mdev, out); + if (err) + goto out; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]); + port_buffer->buffer[i].lossy = + MLX5_GET(bufferx_reg, buffer, lossy); + port_buffer->buffer[i].epsb = + MLX5_GET(bufferx_reg, buffer, epsb); + port_buffer->buffer[i].size = + MLX5_GET(bufferx_reg, buffer, size) << MLX5E_BUFFER_CELL_SHIFT; + port_buffer->buffer[i].xon = + MLX5_GET(bufferx_reg, buffer, xon_threshold) << MLX5E_BUFFER_CELL_SHIFT; + port_buffer->buffer[i].xoff = + MLX5_GET(bufferx_reg, buffer, xoff_threshold) << MLX5E_BUFFER_CELL_SHIFT; + total_used += port_buffer->buffer[i].size; + + mlx5e_dbg(HW, priv, "buffer %d: size=%d, xon=%d, xoff=%d, epsb=%d, lossy=%d\n", i, + port_buffer->buffer[i].size, + port_buffer->buffer[i].xon, + port_buffer->buffer[i].xoff, + port_buffer->buffer[i].epsb, + port_buffer->buffer[i].lossy); + } + + port_buffer->port_buffer_size = + MLX5_GET(pbmc_reg, out, port_buffer_size) << MLX5E_BUFFER_CELL_SHIFT; + port_buffer->spare_buffer_size = + port_buffer->port_buffer_size - total_used; + + mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n", + port_buffer->port_buffer_size, + port_buffer->spare_buffer_size); +out: + kfree(out); + return err; +} + +static int port_set_buffer(struct mlx5e_priv *priv, + struct mlx5e_port_buffer *port_buffer) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int sz = MLX5_ST_SZ_BYTES(pbmc_reg); + void *buffer; + void *in; + int err; + int i; + + in = kzalloc(sz, GFP_KERNEL); + if (!in) + return -ENOMEM; + + err = mlx5e_port_query_pbmc(mdev, in); + if (err) + goto out; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); + + MLX5_SET(bufferx_reg, buffer, size, + port_buffer->buffer[i].size >> MLX5E_BUFFER_CELL_SHIFT); + MLX5_SET(bufferx_reg, buffer, lossy, + port_buffer->buffer[i].lossy); + MLX5_SET(bufferx_reg, buffer, xoff_threshold, + port_buffer->buffer[i].xoff >> MLX5E_BUFFER_CELL_SHIFT); + MLX5_SET(bufferx_reg, buffer, xon_threshold, + port_buffer->buffer[i].xon >> MLX5E_BUFFER_CELL_SHIFT); + } + + err = mlx5e_port_set_pbmc(mdev, in); +out: + kfree(in); + return err; +} + +/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */ +static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu) +{ + u32 speed; + u32 xoff; + int err; + + err = mlx5e_port_linkspeed(priv->mdev, &speed); + if (err) + return 0; + + xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100; + + mlx5e_dbg(HW, priv, "%s: xoff=%d\n", __func__, xoff); + return xoff; +} + +static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer, + u32 xoff, unsigned int mtu) +{ + int i; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + if (port_buffer->buffer[i].lossy) { + port_buffer->buffer[i].xoff = 0; + port_buffer->buffer[i].xon = 0; + continue; + } + + if (port_buffer->buffer[i].size < + (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT))) + return -ENOMEM; + + port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff; + port_buffer->buffer[i].xon = port_buffer->buffer[i].xoff - mtu; + } + + return 0; +} + +/** + * update_buffer_lossy() + * mtu: device's MTU + * pfc_en: <input> current pfc configuration + * buffer: <input> current prio to buffer mapping + * xoff: <input> xoff value + * port_buffer: <output> port receive buffer configuration + * change: <output> + * + * Update buffer configuration based on pfc configuraiton and priority + * to buffer mapping. + * Buffer's lossy bit is changed to: + * lossless if there is at least one PFC enabled priority mapped to this buffer + * lossy if all priorities mapped to this buffer are PFC disabled + * + * Return: + * Return 0 if no error. + * Set change to true if buffer configuration is modified. + */ +static int update_buffer_lossy(unsigned int mtu, + u8 pfc_en, u8 *buffer, u32 xoff, + struct mlx5e_port_buffer *port_buffer, + bool *change) +{ + bool changed = false; + u8 lossy_count; + u8 prio_count; + u8 lossy; + int prio; + int err; + int i; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + prio_count = 0; + lossy_count = 0; + + for (prio = 0; prio < MLX5E_MAX_PRIORITY; prio++) { + if (buffer[prio] != i) + continue; + + prio_count++; + lossy_count += !(pfc_en & (1 << prio)); + } + + if (lossy_count == prio_count) + lossy = 1; + else /* lossy_count < prio_count */ + lossy = 0; + + if (lossy != port_buffer->buffer[i].lossy) { + port_buffer->buffer[i].lossy = lossy; + changed = true; + } + } + + if (changed) { + err = update_xoff_threshold(port_buffer, xoff, mtu); + if (err) + return err; + + *change = true; + } + + return 0; +} + +int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, + u32 change, unsigned int mtu, + struct ieee_pfc *pfc, + u32 *buffer_size, + u8 *prio2buffer) +{ + struct mlx5e_port_buffer port_buffer; + u32 xoff = calculate_xoff(priv, mtu); + bool update_prio2buffer = false; + u8 buffer[MLX5E_MAX_PRIORITY]; + bool update_buffer = false; + u32 total_used = 0; + u8 curr_pfc_en; + int err; + int i; + + mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change); + + err = mlx5e_port_query_buffer(priv, &port_buffer); + if (err) + return err; + + if (change & MLX5E_PORT_BUFFER_CABLE_LEN) { + update_buffer = true; + err = update_xoff_threshold(&port_buffer, xoff, mtu); + if (err) + return err; + } + + if (change & MLX5E_PORT_BUFFER_PFC) { + err = mlx5e_port_query_priority2buffer(priv->mdev, buffer); + if (err) + return err; + + err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff, + &port_buffer, &update_buffer); + if (err) + return err; + } + + if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) { + update_prio2buffer = true; + err = mlx5_query_port_pfc(priv->mdev, &curr_pfc_en, NULL); + if (err) + return err; + + err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff, + &port_buffer, &update_buffer); + if (err) + return err; + } + + if (change & MLX5E_PORT_BUFFER_SIZE) { + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]); + if (!port_buffer.buffer[i].lossy && !buffer_size[i]) { + mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n", + __func__, i); + return -EINVAL; + } + + port_buffer.buffer[i].size = buffer_size[i]; + total_used += buffer_size[i]; + } + + mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used); + + if (total_used > port_buffer.port_buffer_size) + return -EINVAL; + + update_buffer = true; + err = update_xoff_threshold(&port_buffer, xoff, mtu); + if (err) + return err; + } + + /* Need to update buffer configuration if xoff value is changed */ + if (!update_buffer && xoff != priv->dcbx.xoff) { + update_buffer = true; + err = update_xoff_threshold(&port_buffer, xoff, mtu); + if (err) + return err; + } + priv->dcbx.xoff = xoff; + + /* Apply the settings */ + if (update_buffer) { + err = port_set_buffer(priv, &port_buffer); + if (err) + return err; + } + + if (update_prio2buffer) + err = mlx5e_port_set_priority2buffer(priv->mdev, prio2buffer); + + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h new file mode 100644 index 0000000000000..34f55b81a0deb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.h @@ -0,0 +1,75 @@ +/* + * Copyright (c) 2018, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __MLX5_EN_PORT_BUFFER_H__ +#define __MLX5_EN_PORT_BUFFER_H__ + +#include "en.h" +#include "port.h" + +#define MLX5E_MAX_BUFFER 8 +#define MLX5E_BUFFER_CELL_SHIFT 7 +#define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */ + +#define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \ + MLX5_CAP_PCAM_REG(mdev, pbmc) && \ + MLX5_CAP_PCAM_REG(mdev, pptb)) + +enum { + MLX5E_PORT_BUFFER_CABLE_LEN = BIT(0), + MLX5E_PORT_BUFFER_PFC = BIT(1), + MLX5E_PORT_BUFFER_PRIO2BUFFER = BIT(2), + MLX5E_PORT_BUFFER_SIZE = BIT(3), +}; + +struct mlx5e_bufferx_reg { + u8 lossy; + u8 epsb; + u32 size; + u32 xoff; + u32 xon; +}; + +struct mlx5e_port_buffer { + u32 port_buffer_size; + u32 spare_buffer_size; + struct mlx5e_bufferx_reg buffer[MLX5E_MAX_BUFFER]; +}; + +int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv, + u32 change, unsigned int mtu, + struct ieee_pfc *pfc, + u32 *buffer_size, + u8 *prio2buffer); + +int mlx5e_port_query_buffer(struct mlx5e_priv *priv, + struct mlx5e_port_buffer *port_buffer); +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h new file mode 100644 index 0000000000000..f20074dbef32c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -0,0 +1,72 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5E_EN_ACCEL_H__ +#define __MLX5E_EN_ACCEL_H__ + +#ifdef CONFIG_MLX5_ACCEL + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include "en_accel/ipsec_rxtx.h" +#include "en_accel/tls_rxtx.h" +#include "en.h" + +static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb, + struct mlx5e_txqsq *sq, + struct net_device *dev, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ +#ifdef CONFIG_MLX5_EN_TLS + if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) { + skb = mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi); + if (unlikely(!skb)) + return NULL; + } +#endif + +#ifdef CONFIG_MLX5_EN_IPSEC + if (test_bit(MLX5E_SQ_STATE_IPSEC, &sq->state)) { + skb = mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb); + if (unlikely(!skb)) + return NULL; + } +#endif + + return skb; +} + +#endif /* CONFIG_MLX5_ACCEL */ + +#endif /* __MLX5E_EN_ACCEL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 1198fc1eba4c8..93bf10e6508c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -45,9 +45,6 @@ #define MLX5E_IPSEC_SADB_RX_BITS 10 #define MLX5E_IPSEC_ESN_SCOPE_MID 0x80000000L -#define MLX5E_METADATA_ETHER_TYPE (0x8CE4) -#define MLX5E_METADATA_ETHER_LEN 8 - struct mlx5e_priv; struct mlx5e_ipsec_sw_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c new file mode 100644 index 0000000000000..d167845271c33 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c @@ -0,0 +1,197 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/netdevice.h> +#include <net/ipv6.h> +#include "en_accel/tls.h" +#include "accel/tls.h" + +static void mlx5e_tls_set_ipv4_flow(void *flow, struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + MLX5_SET(tls_flow, flow, ipv6, 0); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &inet->inet_daddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv4_layout.ipv4), + &inet->inet_rcv_saddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4)); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void mlx5e_tls_set_ipv6_flow(void *flow, struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + MLX5_SET(tls_flow, flow, ipv6, 1); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &sk->sk_v6_daddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv6_layout.ipv6), + &np->saddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); +} +#endif + +static void mlx5e_tls_set_flow_tcp_ports(void *flow, struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_port), &inet->inet_sport, + MLX5_FLD_SZ_BYTES(tls_flow, src_port)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_port), &inet->inet_dport, + MLX5_FLD_SZ_BYTES(tls_flow, dst_port)); +} + +static int mlx5e_tls_set_flow(void *flow, struct sock *sk, u32 caps) +{ + switch (sk->sk_family) { + case AF_INET: + mlx5e_tls_set_ipv4_flow(flow, sk); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + if (!sk->sk_ipv6only && + ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) { + mlx5e_tls_set_ipv4_flow(flow, sk); + break; + } + if (!(caps & MLX5_ACCEL_TLS_IPV6)) + goto error_out; + + mlx5e_tls_set_ipv6_flow(flow, sk); + break; +#endif + default: + goto error_out; + } + + mlx5e_tls_set_flow_tcp_ports(flow, sk); + return 0; +error_out: + return -EINVAL; +} + +static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct mlx5_core_dev *mdev = priv->mdev; + u32 caps = mlx5_accel_tls_device_caps(mdev); + int ret = -ENOMEM; + void *flow; + + if (direction != TLS_OFFLOAD_CTX_DIR_TX) + return -EINVAL; + + flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL); + if (!flow) + return ret; + + ret = mlx5e_tls_set_flow(flow, sk, caps); + if (ret) + goto free_flow; + + if (direction == TLS_OFFLOAD_CTX_DIR_TX) { + struct mlx5e_tls_offload_context *tx_ctx = + mlx5e_get_tls_tx_context(tls_ctx); + u32 swid; + + ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info, + start_offload_tcp_sn, &swid); + if (ret < 0) + goto free_flow; + + tx_ctx->swid = htonl(swid); + tx_ctx->expected_seq = start_offload_tcp_sn; + } + + return 0; +free_flow: + kfree(flow); + return ret; +} + +static void mlx5e_tls_del(struct net_device *netdev, + struct tls_context *tls_ctx, + enum tls_offload_ctx_dir direction) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (direction == TLS_OFFLOAD_CTX_DIR_TX) { + u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid); + + mlx5_accel_tls_del_tx_flow(priv->mdev, swid); + } else { + netdev_err(netdev, "unsupported direction %d\n", direction); + } +} + +static const struct tlsdev_ops mlx5e_tls_ops = { + .tls_dev_add = mlx5e_tls_add, + .tls_dev_del = mlx5e_tls_del, +}; + +void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) +{ + struct net_device *netdev = priv->netdev; + + if (!mlx5_accel_is_tls_device(priv->mdev)) + return; + + netdev->features |= NETIF_F_HW_TLS_TX; + netdev->hw_features |= NETIF_F_HW_TLS_TX; + netdev->tlsdev_ops = &mlx5e_tls_ops; +} + +int mlx5e_tls_init(struct mlx5e_priv *priv) +{ + struct mlx5e_tls *tls = kzalloc(sizeof(*tls), GFP_KERNEL); + + if (!tls) + return -ENOMEM; + + priv->tls = tls; + return 0; +} + +void mlx5e_tls_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_tls *tls = priv->tls; + + if (!tls) + return; + + kfree(tls); + priv->tls = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h new file mode 100644 index 0000000000000..b6162178f6211 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -0,0 +1,87 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#ifndef __MLX5E_TLS_H__ +#define __MLX5E_TLS_H__ + +#ifdef CONFIG_MLX5_EN_TLS + +#include <net/tls.h> +#include "en.h" + +struct mlx5e_tls_sw_stats { + atomic64_t tx_tls_drop_metadata; + atomic64_t tx_tls_drop_resync_alloc; + atomic64_t tx_tls_drop_no_sync_data; + atomic64_t tx_tls_drop_bypass_required; +}; + +struct mlx5e_tls { + struct mlx5e_tls_sw_stats sw_stats; +}; + +struct mlx5e_tls_offload_context { + struct tls_offload_context base; + u32 expected_seq; + __be32 swid; +}; + +static inline struct mlx5e_tls_offload_context * +mlx5e_get_tls_tx_context(struct tls_context *tls_ctx) +{ + BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) > + TLS_OFFLOAD_CONTEXT_SIZE); + return container_of(tls_offload_ctx(tls_ctx), + struct mlx5e_tls_offload_context, + base); +} + +void mlx5e_tls_build_netdev(struct mlx5e_priv *priv); +int mlx5e_tls_init(struct mlx5e_priv *priv); +void mlx5e_tls_cleanup(struct mlx5e_priv *priv); + +int mlx5e_tls_get_count(struct mlx5e_priv *priv); +int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data); +int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data); + +#else + +static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { } +static inline int mlx5e_tls_init(struct mlx5e_priv *priv) { return 0; } +static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { } +static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; } +static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; } +static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; } + +#endif + +#endif /* __MLX5E_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c new file mode 100644 index 0000000000000..15aef71d19576 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -0,0 +1,278 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include "en_accel/tls.h" +#include "en_accel/tls_rxtx.h" + +#define SYNDROME_OFFLOAD_REQUIRED 32 +#define SYNDROME_SYNC 33 + +struct sync_info { + u64 rcd_sn; + s32 sync_len; + int nr_frags; + skb_frag_t frags[MAX_SKB_FRAGS]; +}; + +struct mlx5e_tls_metadata { + /* One byte of syndrome followed by 3 bytes of swid */ + __be32 syndrome_swid; + __be16 first_seq; + /* packet type ID field */ + __be16 ethertype; +} __packed; + +static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid) +{ + struct mlx5e_tls_metadata *pet; + struct ethhdr *eth; + + if (skb_cow_head(skb, sizeof(struct mlx5e_tls_metadata))) + return -ENOMEM; + + eth = (struct ethhdr *)skb_push(skb, sizeof(struct mlx5e_tls_metadata)); + skb->mac_header -= sizeof(struct mlx5e_tls_metadata); + pet = (struct mlx5e_tls_metadata *)(eth + 1); + + memmove(skb->data, skb->data + sizeof(struct mlx5e_tls_metadata), + 2 * ETH_ALEN); + + eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE); + pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid; + + return 0; +} + +static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context, + u32 tcp_seq, struct sync_info *info) +{ + int remaining, i = 0, ret = -EINVAL; + struct tls_record_info *record; + unsigned long flags; + s32 sync_size; + + spin_lock_irqsave(&context->base.lock, flags); + record = tls_get_record(&context->base, tcp_seq, &info->rcd_sn); + + if (unlikely(!record)) + goto out; + + sync_size = tcp_seq - tls_record_start_seq(record); + info->sync_len = sync_size; + if (unlikely(sync_size < 0)) { + if (tls_record_is_start_marker(record)) + goto done; + + goto out; + } + + remaining = sync_size; + while (remaining > 0) { + info->frags[i] = record->frags[i]; + __skb_frag_ref(&info->frags[i]); + remaining -= skb_frag_size(&info->frags[i]); + + if (remaining < 0) + skb_frag_size_add(&info->frags[i], remaining); + + i++; + } + info->nr_frags = i; +done: + ret = 0; +out: + spin_unlock_irqrestore(&context->base.lock, flags); + return ret; +} + +static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb, + struct sk_buff *nskb, u32 tcp_seq, + int headln, __be64 rcd_sn) +{ + struct mlx5e_tls_metadata *pet; + u8 syndrome = SYNDROME_SYNC; + struct iphdr *iph; + struct tcphdr *th; + int data_len, mss; + + nskb->dev = skb->dev; + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, skb_network_offset(skb)); + skb_set_transport_header(nskb, skb_transport_offset(skb)); + memcpy(nskb->data, skb->data, headln); + memcpy(nskb->data + headln, &rcd_sn, sizeof(rcd_sn)); + + iph = ip_hdr(nskb); + iph->tot_len = htons(nskb->len - skb_network_offset(nskb)); + th = tcp_hdr(nskb); + data_len = nskb->len - headln; + tcp_seq -= data_len; + th->seq = htonl(tcp_seq); + + mss = nskb->dev->mtu - (headln - skb_network_offset(nskb)); + skb_shinfo(nskb)->gso_size = 0; + if (data_len > mss) { + skb_shinfo(nskb)->gso_size = mss; + skb_shinfo(nskb)->gso_segs = DIV_ROUND_UP(data_len, mss); + } + skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; + + pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr)); + memcpy(pet, &syndrome, sizeof(syndrome)); + pet->first_seq = htons(tcp_seq); + + /* MLX5 devices don't care about the checksum partial start, offset + * and pseudo header + */ + nskb->ip_summed = CHECKSUM_PARTIAL; + + nskb->xmit_more = 1; + nskb->queue_mapping = skb->queue_mapping; +} + +static struct sk_buff * +mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context, + struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi, + struct mlx5e_tls *tls) +{ + u32 tcp_seq = ntohl(tcp_hdr(skb)->seq); + struct sync_info info; + struct sk_buff *nskb; + int linear_len = 0; + int headln; + int i; + + sq->stats->tls_ooo++; + + if (mlx5e_tls_get_sync_data(context, tcp_seq, &info)) { + /* We might get here if a retransmission reaches the driver + * after the relevant record is acked. + * It should be safe to drop the packet in this case + */ + atomic64_inc(&tls->sw_stats.tx_tls_drop_no_sync_data); + goto err_out; + } + + if (unlikely(info.sync_len < 0)) { + u32 payload; + + headln = skb_transport_offset(skb) + tcp_hdrlen(skb); + payload = skb->len - headln; + if (likely(payload <= -info.sync_len)) + /* SKB payload doesn't require offload + */ + return skb; + + atomic64_inc(&tls->sw_stats.tx_tls_drop_bypass_required); + goto err_out; + } + + if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) { + atomic64_inc(&tls->sw_stats.tx_tls_drop_metadata); + goto err_out; + } + + headln = skb_transport_offset(skb) + tcp_hdrlen(skb); + linear_len += headln + sizeof(info.rcd_sn); + nskb = alloc_skb(linear_len, GFP_ATOMIC); + if (unlikely(!nskb)) { + atomic64_inc(&tls->sw_stats.tx_tls_drop_resync_alloc); + goto err_out; + } + + context->expected_seq = tcp_seq + skb->len - headln; + skb_put(nskb, linear_len); + for (i = 0; i < info.nr_frags; i++) + skb_shinfo(nskb)->frags[i] = info.frags[i]; + + skb_shinfo(nskb)->nr_frags = info.nr_frags; + nskb->data_len = info.sync_len; + nskb->len += info.sync_len; + sq->stats->tls_resync_bytes += nskb->len; + mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln, + cpu_to_be64(info.rcd_sn)); + mlx5e_sq_xmit(sq, nskb, *wqe, *pi); + mlx5e_sq_fetch_wqe(sq, wqe, pi); + return skb; + +err_out: + dev_kfree_skb_any(skb); + return NULL; +} + +struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_tls_offload_context *context; + struct tls_context *tls_ctx; + u32 expected_seq; + int datalen; + u32 skb_seq; + + if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)) + goto out; + + datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb)); + if (!datalen) + goto out; + + tls_ctx = tls_get_ctx(skb->sk); + if (unlikely(tls_ctx->netdev != netdev)) + goto out; + + skb_seq = ntohl(tcp_hdr(skb)->seq); + context = mlx5e_get_tls_tx_context(tls_ctx); + expected_seq = context->expected_seq; + + if (unlikely(expected_seq != skb_seq)) { + skb = mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls); + goto out; + } + + if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) { + atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata); + dev_kfree_skb_any(skb); + skb = NULL; + goto out; + } + + context->expected_seq = skb_seq + datalen; +out: + return skb; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h new file mode 100644 index 0000000000000..405dfd302225c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h @@ -0,0 +1,50 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5E_TLS_RXTX_H__ +#define __MLX5E_TLS_RXTX_H__ + +#ifdef CONFIG_MLX5_EN_TLS + +#include <linux/skbuff.h> +#include "en.h" + +struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi); + +#endif /* CONFIG_MLX5_EN_TLS */ + +#endif /* __MLX5E_TLS_RXTX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c new file mode 100644 index 0000000000000..01468ec274466 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/ethtool.h> +#include <net/sock.h> + +#include "en.h" +#include "accel/tls.h" +#include "fpga/sdk.h" +#include "en_accel/tls.h" + +static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_metadata) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_resync_alloc) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_no_sync_data) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) }, +}; + +#define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \ + atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset)) + +#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) + +int mlx5e_tls_get_count(struct mlx5e_priv *priv) +{ + if (!priv->tls) + return 0; + + return NUM_TLS_SW_COUNTERS; +} + +int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) +{ + unsigned int i, idx = 0; + + if (!priv->tls) + return 0; + + for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + mlx5e_tls_sw_stats_desc[i].format); + + return NUM_TLS_SW_COUNTERS; +} + +int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) +{ + int i, idx = 0; + + if (!priv->tls) + return 0; + + for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + data[idx++] = + MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats, + mlx5e_tls_sw_stats_desc, i); + + return NUM_TLS_SW_COUNTERS; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 610d485c4b038..75e4308ba786a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -213,7 +213,7 @@ out: } #define MLX5E_ARFS_NUM_GROUPS 2 -#define MLX5E_ARFS_GROUP1_SIZE BIT(12) +#define MLX5E_ARFS_GROUP1_SIZE (BIT(16) - 1) #define MLX5E_ARFS_GROUP2_SIZE BIT(0) #define MLX5E_ARFS_TABLE_SIZE (MLX5E_ARFS_GROUP1_SIZE +\ MLX5E_ARFS_GROUP2_SIZE) @@ -565,7 +565,7 @@ static void arfs_modify_rule_rq(struct mlx5e_priv *priv, err = mlx5_modify_rule_destination(rule, &dst, NULL); if (err) netdev_warn(priv->netdev, - "Failed to modfiy aRFS rule destination to rq=%d\n", rxq); + "Failed to modify aRFS rule destination to rq=%d\n", rxq); } static void arfs_handle_work(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index c641d5656b2de..0a52f31fef377 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -32,8 +32,8 @@ #include <linux/device.h> #include <linux/netdevice.h> #include "en.h" - -#define MLX5E_MAX_PRIORITY 8 +#include "en/port.h" +#include "en/port_buffer.h" #define MLX5E_100MB (100000) #define MLX5E_1GB (1000000) @@ -41,6 +41,9 @@ #define MLX5E_CEE_STATE_UP 1 #define MLX5E_CEE_STATE_DOWN 0 +/* Max supported cable length is 1000 meters */ +#define MLX5E_MAX_CABLE_LENGTH 1000 + enum { MLX5E_VENDOR_TC_GROUP_NUM = 7, MLX5E_LOWEST_PRIO_GROUP = 0, @@ -338,6 +341,9 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev, pfc->indications[i] = PPORT_PER_PRIO_GET(pstats, i, rx_pause); } + if (MLX5_BUFFER_SUPPORTED(mdev)) + pfc->delay = priv->dcbx.cable_len; + return mlx5_query_port_pfc(mdev, &pfc->pfc_en, NULL); } @@ -346,16 +352,39 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + u32 old_cable_len = priv->dcbx.cable_len; + struct ieee_pfc pfc_new; + u32 changed = 0; u8 curr_pfc_en; - int ret; + int ret = 0; + /* pfc_en */ mlx5_query_port_pfc(mdev, &curr_pfc_en, NULL); + if (pfc->pfc_en != curr_pfc_en) { + ret = mlx5_set_port_pfc(mdev, pfc->pfc_en, pfc->pfc_en); + if (ret) + return ret; + mlx5_toggle_port_link(mdev); + changed |= MLX5E_PORT_BUFFER_PFC; + } - if (pfc->pfc_en == curr_pfc_en) - return 0; + if (pfc->delay && + pfc->delay < MLX5E_MAX_CABLE_LENGTH && + pfc->delay != priv->dcbx.cable_len) { + priv->dcbx.cable_len = pfc->delay; + changed |= MLX5E_PORT_BUFFER_CABLE_LEN; + } - ret = mlx5_set_port_pfc(mdev, pfc->pfc_en, pfc->pfc_en); - mlx5_toggle_port_link(mdev); + if (MLX5_BUFFER_SUPPORTED(mdev)) { + pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en; + if (priv->dcbx.manual_buffer) + ret = mlx5e_port_manual_buffer_config(priv, changed, + dev->mtu, &pfc_new, + NULL, NULL); + + if (ret && (changed & MLX5E_PORT_BUFFER_CABLE_LEN)) + priv->dcbx.cable_len = old_cable_len; + } if (!ret) { mlx5e_dbg(HW, priv, @@ -873,6 +902,90 @@ static void mlx5e_dcbnl_setpfcstate(struct net_device *netdev, u8 state) cee_cfg->pfc_enable = state; } +static int mlx5e_dcbnl_getbuffer(struct net_device *dev, + struct dcbnl_buffer *dcb_buffer) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_port_buffer port_buffer; + u8 buffer[MLX5E_MAX_PRIORITY]; + int i, err; + + if (!MLX5_BUFFER_SUPPORTED(mdev)) + return -EOPNOTSUPP; + + err = mlx5e_port_query_priority2buffer(mdev, buffer); + if (err) + return err; + + for (i = 0; i < MLX5E_MAX_PRIORITY; i++) + dcb_buffer->prio2buffer[i] = buffer[i]; + + err = mlx5e_port_query_buffer(priv, &port_buffer); + if (err) + return err; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) + dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size; + dcb_buffer->total_size = port_buffer.port_buffer_size; + + return 0; +} + +static int mlx5e_dcbnl_setbuffer(struct net_device *dev, + struct dcbnl_buffer *dcb_buffer) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_port_buffer port_buffer; + u8 old_prio2buffer[MLX5E_MAX_PRIORITY]; + u32 *buffer_size = NULL; + u8 *prio2buffer = NULL; + u32 changed = 0; + int i, err; + + if (!MLX5_BUFFER_SUPPORTED(mdev)) + return -EOPNOTSUPP; + + for (i = 0; i < DCBX_MAX_BUFFERS; i++) + mlx5_core_dbg(mdev, "buffer[%d]=%d\n", i, dcb_buffer->buffer_size[i]); + + for (i = 0; i < MLX5E_MAX_PRIORITY; i++) + mlx5_core_dbg(mdev, "priority %d buffer%d\n", i, dcb_buffer->prio2buffer[i]); + + err = mlx5e_port_query_priority2buffer(mdev, old_prio2buffer); + if (err) + return err; + + for (i = 0; i < MLX5E_MAX_PRIORITY; i++) { + if (dcb_buffer->prio2buffer[i] != old_prio2buffer[i]) { + changed |= MLX5E_PORT_BUFFER_PRIO2BUFFER; + prio2buffer = dcb_buffer->prio2buffer; + break; + } + } + + err = mlx5e_port_query_buffer(priv, &port_buffer); + if (err) + return err; + + for (i = 0; i < MLX5E_MAX_BUFFER; i++) { + if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) { + changed |= MLX5E_PORT_BUFFER_SIZE; + buffer_size = dcb_buffer->buffer_size; + break; + } + } + + if (!changed) + return 0; + + priv->dcbx.manual_buffer = true; + err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL, + buffer_size, prio2buffer); + return err; +} + const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_getets = mlx5e_dcbnl_ieee_getets, .ieee_setets = mlx5e_dcbnl_ieee_setets, @@ -884,6 +997,8 @@ const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_delapp = mlx5e_dcbnl_ieee_delapp, .getdcbx = mlx5e_dcbnl_getdcbx, .setdcbx = mlx5e_dcbnl_setdcbx, + .dcbnl_getbuffer = mlx5e_dcbnl_getbuffer, + .dcbnl_setbuffer = mlx5e_dcbnl_setbuffer, /* CEE interfaces */ .setall = mlx5e_dcbnl_setall, @@ -1091,5 +1206,8 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) if (priv->dcbx.mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) priv->dcbx.cap |= DCB_CAP_DCBX_HOST; + priv->dcbx.manual_buffer = false; + priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN; + mlx5e_ets_init(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c index 602851ab5b145..d67adf70a97bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c @@ -33,16 +33,30 @@ #include <linux/net_dim.h> #include "en.h" +static void +mlx5e_complete_dim_work(struct net_dim *dim, struct net_dim_cq_moder moder, + struct mlx5_core_dev *mdev, struct mlx5_core_cq *mcq) +{ + mlx5_core_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts); + dim->state = NET_DIM_START_MEASURE; +} + void mlx5e_rx_dim_work(struct work_struct *work) { - struct net_dim *dim = container_of(work, struct net_dim, - work); + struct net_dim *dim = container_of(work, struct net_dim, work); struct mlx5e_rq *rq = container_of(dim, struct mlx5e_rq, dim); - struct net_dim_cq_moder cur_profile = net_dim_get_profile(dim->mode, - dim->profile_ix); + struct net_dim_cq_moder cur_moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); - mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq, - cur_profile.usec, cur_profile.pkts); + mlx5e_complete_dim_work(dim, cur_moder, rq->mdev, &rq->cq.mcq); +} - dim->state = NET_DIM_START_MEASURE; +void mlx5e_tx_dim_work(struct work_struct *work) +{ + struct net_dim *dim = container_of(work, struct net_dim, work); + struct mlx5e_txqsq *sq = container_of(dim, struct mlx5e_txqsq, dim); + struct net_dim_cq_moder cur_moder = + net_dim_get_tx_moderation(dim->mode, dim->profile_ix); + + mlx5e_complete_dim_work(dim, cur_moder, sq->cq.mdev, &sq->cq.mcq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 37fd0245b6c12..fffe514ba855c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -31,6 +31,7 @@ */ #include "en.h" +#include "en/port.h" void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo) @@ -59,18 +60,16 @@ static void mlx5e_get_drvinfo(struct net_device *dev, struct ptys2ethtool_config { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertised); - u32 speed; }; static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER]; -#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, speed_, ...) \ +#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, ...) \ ({ \ struct ptys2ethtool_config *cfg; \ const unsigned int modes[] = { __VA_ARGS__ }; \ unsigned int i; \ cfg = &ptys2ethtool_table[reg_]; \ - cfg->speed = speed_; \ bitmap_zero(cfg->supported, \ __ETHTOOL_LINK_MODE_MASK_NBITS); \ bitmap_zero(cfg->advertised, \ @@ -83,55 +82,55 @@ static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER]; void mlx5e_build_ptys2ethtool_map(void) { - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, SPEED_1000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, SPEED_1000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, SPEED_20000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, SPEED_40000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, SPEED_40000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, SPEED_56000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, SPEED_40000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, SPEED_40000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, SPEED_50000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, SPEED_100000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, SPEED_100000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, SPEED_100000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, SPEED_100000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, SPEED_10000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, ETHTOOL_LINK_MODE_10000baseT_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, SPEED_25000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, SPEED_25000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, SPEED_25000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, SPEED_50000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT); - MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, SPEED_50000, + MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT); } @@ -389,14 +388,20 @@ static int mlx5e_set_channels(struct net_device *dev, int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { + struct net_dim_cq_moder *rx_moder, *tx_moder; + if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) return -EOPNOTSUPP; - coal->rx_coalesce_usecs = priv->channels.params.rx_cq_moderation.usec; - coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts; - coal->tx_coalesce_usecs = priv->channels.params.tx_cq_moderation.usec; - coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts; - coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled; + rx_moder = &priv->channels.params.rx_cq_moderation; + coal->rx_coalesce_usecs = rx_moder->usec; + coal->rx_max_coalesced_frames = rx_moder->pkts; + coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled; + + tx_moder = &priv->channels.params.tx_cq_moderation; + coal->tx_coalesce_usecs = tx_moder->usec; + coal->tx_max_coalesced_frames = tx_moder->pkts; + coal->use_adaptive_tx_coalesce = priv->channels.params.tx_dim_enabled; return 0; } @@ -438,6 +443,7 @@ mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesc int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { + struct net_dim_cq_moder *rx_moder, *tx_moder; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_channels new_channels = {}; int err = 0; @@ -463,11 +469,15 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); new_channels.params = priv->channels.params; - new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs; - new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames; - new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs; - new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames; - new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce; + rx_moder = &new_channels.params.rx_cq_moderation; + rx_moder->usec = coal->rx_coalesce_usecs; + rx_moder->pkts = coal->rx_max_coalesced_frames; + new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce; + + tx_moder = &new_channels.params.tx_cq_moderation; + tx_moder->usec = coal->tx_coalesce_usecs; + tx_moder->pkts = coal->tx_max_coalesced_frames; + new_channels.params.tx_dim_enabled = !!coal->use_adaptive_tx_coalesce; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -475,7 +485,9 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, } /* we are opened */ - reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled; + reset = (!!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled) || + (!!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled); + if (!reset) { mlx5e_set_priv_channels_coalesce(priv, coal); priv->channels.params = new_channels.params; @@ -604,43 +616,24 @@ static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings } } -int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) -{ - u32 max_speed = 0; - u32 proto_cap; - int err; - int i; - - err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN); - if (err) - return err; - - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) - if (proto_cap & MLX5E_PROT_MASK(i)) - max_speed = max(max_speed, ptys2ethtool_table[i].speed); - - *speed = max_speed; - return 0; -} - static void get_speed_duplex(struct net_device *netdev, u32 eth_proto_oper, struct ethtool_link_ksettings *link_ksettings) { - int i; u32 speed = SPEED_UNKNOWN; u8 duplex = DUPLEX_UNKNOWN; if (!netif_carrier_ok(netdev)) goto out; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (eth_proto_oper & MLX5E_PROT_MASK(i)) { - speed = ptys2ethtool_table[i].speed; - duplex = DUPLEX_FULL; - break; - } + speed = mlx5e_port_ptys2speed(eth_proto_oper); + if (!speed) { + speed = SPEED_UNKNOWN; + goto out; } + + duplex = DUPLEX_FULL; + out: link_ksettings->base.speed = speed; link_ksettings->base.duplex = duplex; @@ -798,18 +791,6 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) return ptys_modes; } -static u32 mlx5e_ethtool2ptys_speed_link(u32 speed) -{ - u32 i, speed_links = 0; - - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (ptys2ethtool_table[i].speed == speed) - speed_links |= MLX5E_PROT_MASK(i); - } - - return speed_links; -} - static int mlx5e_set_link_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *link_ksettings) { @@ -829,7 +810,7 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev, link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) : - mlx5e_ethtool2ptys_speed_link(speed); + mlx5e_port_speed2linkmodes(speed); err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN); if (err) { @@ -1534,6 +1515,9 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return -EOPNOTSUPP; if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params)) return -EINVAL; + } else if (priv->channels.params.lro_en) { + netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n"); + return -EINVAL; } new_channels.params = priv->channels.params; @@ -1608,6 +1592,10 @@ static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags) out: mutex_unlock(&priv->state_lock); + + /* Need to fix some features.. */ + netdev_update_features(netdev); + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index f64dda2bed316..76cc10e44080b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -277,7 +277,6 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv, } break; case MLX5E_VLAN_RULE_TYPE_MATCH_CTAG_VID: - mlx5e_vport_context_update_vlans(priv); if (priv->fs.vlan.active_cvlans_rule[vid]) { mlx5_del_flow_rules(priv->fs.vlan.active_cvlans_rule[vid]); priv->fs.vlan.active_cvlans_rule[vid] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b29c1d93f0584..89c96a0f708e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -35,18 +35,23 @@ #include <linux/mlx5/fs.h> #include <net/vxlan.h> #include <linux/bpf.h> +#include <net/page_pool.h> #include "eswitch.h" #include "en.h" #include "en_tc.h" #include "en_rep.h" #include "en_accel/ipsec.h" #include "en_accel/ipsec_rxtx.h" +#include "en_accel/tls.h" #include "accel/ipsec.h" +#include "accel/tls.h" #include "vxlan.h" +#include "en/port.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; struct mlx5_wq_param wq; + struct mlx5e_rq_frags_info frags_info; }; struct mlx5e_sq_param { @@ -89,7 +94,7 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) return true; } -static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params) +static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params) { if (!params->xdp_prog) { u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); @@ -103,19 +108,27 @@ static u32 mlx5e_mpwqe_get_linear_frag_sz(struct mlx5e_params *params) static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params) { - u32 linear_frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params); + u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params); return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz); } +static bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) +{ + u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params); + + return !params->lro_en && frag_sz <= PAGE_SIZE; +} + static bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { - u32 frag_sz = mlx5e_mpwqe_get_linear_frag_sz(params); + u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params); s8 signed_log_num_strides_param; u8 log_num_strides; - if (params->lro_en || frag_sz > PAGE_SIZE) + if (!mlx5e_rx_is_linear_skb(mdev, params)) return false; if (MLX5_CAP_GEN(mdev, ext_stride_num_range)) @@ -141,7 +154,7 @@ static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) - return order_base_2(mlx5e_mpwqe_get_linear_frag_sz(params)); + return order_base_2(mlx5e_rx_get_linear_frag_sz(params)); return MLX5E_MPWQE_STRIDE_SZ(mdev, MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); @@ -159,16 +172,15 @@ static u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, { u16 linear_rq_headroom = params->xdp_prog ? XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM; + bool is_linear_skb; linear_rq_headroom += NET_IP_ALIGN; - if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST) - return linear_rq_headroom; - - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) - return linear_rq_headroom; + is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ? + mlx5e_rx_is_linear_skb(mdev, params) : + mlx5e_rx_mpwqe_is_linear_skb(mdev, params); - return 0; + return is_linear_skb ? linear_rq_headroom : 0; } void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, @@ -178,14 +190,6 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, params->log_rq_mtu_frames = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; - switch (params->rq_wq_type) { - case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - break; - default: /* MLX5_WQ_TYPE_LINKED_LIST */ - /* Extra room needed for build_skb */ - params->lro_wqe_sz -= mlx5e_get_rq_headroom(mdev, params) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - } mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n", params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, @@ -209,7 +213,7 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params) params->rq_wq_type = mlx5e_striding_rq_possible(mdev, params) && MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ) ? MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ : - MLX5_WQ_TYPE_LINKED_LIST; + MLX5_WQ_TYPE_CYCLIC; } static void mlx5e_update_carrier(struct mlx5e_priv *priv) @@ -323,10 +327,30 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } +static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq) +{ + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + return mlx5_wq_ll_get_size(&rq->mpwqe.wq); + default: + return mlx5_wq_cyc_get_size(&rq->wqe.wq); + } +} + +static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq) +{ + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + return rq->mpwqe.wq.cur_sz; + default: + return rq->wqe.wq.cur_sz; + } +} + static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, struct mlx5e_channel *c) { - int wq_sz = mlx5_wq_ll_get_size(&rq->wq); + int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), GFP_KERNEL, cpu_to_node(c->cpu)); @@ -374,7 +398,7 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq *rq) { - u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->wq)); + u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq)); return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey); } @@ -384,31 +408,77 @@ static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT; } +static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) +{ + struct mlx5e_wqe_frag_info next_frag, *prev; + int i; + + next_frag.di = &rq->wqe.di[0]; + next_frag.offset = 0; + prev = NULL; + + for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) { + struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0]; + struct mlx5e_wqe_frag_info *frag = + &rq->wqe.frags[i << rq->wqe.info.log_num_frags]; + int f; + + for (f = 0; f < rq->wqe.info.num_frags; f++, frag++) { + if (next_frag.offset + frag_info[f].frag_stride > PAGE_SIZE) { + next_frag.di++; + next_frag.offset = 0; + if (prev) + prev->last_in_page = true; + } + *frag = next_frag; + + /* prepare next */ + next_frag.offset += frag_info[f].frag_stride; + prev = frag; + } + } + + if (prev) + prev->last_in_page = true; +} + +static int mlx5e_init_di_list(struct mlx5e_rq *rq, + struct mlx5e_params *params, + int wq_sz, int cpu) +{ + int len = wq_sz << rq->wqe.info.log_num_frags; + + rq->wqe.di = kvzalloc_node(len * sizeof(*rq->wqe.di), + GFP_KERNEL, cpu_to_node(cpu)); + if (!rq->wqe.di) + return -ENOMEM; + + mlx5e_init_frags_partition(rq); + + return 0; +} + +static void mlx5e_free_di_list(struct mlx5e_rq *rq) +{ + kvfree(rq->wqe.di); +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *rqp, struct mlx5e_rq *rq) { + struct page_pool_params pp_params = { 0 }; struct mlx5_core_dev *mdev = c->mdev; void *rqc = rqp->rqc; void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq); - u32 byte_count; - int npages; + u32 pool_size; int wq_sz; int err; int i; rqp->wq.db_numa_node = cpu_to_node(c->cpu); - err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq, - &rq->wq_ctrl); - if (err) - return err; - - rq->wq.db = &rq->wq.db[MLX5_RCV_DBR]; - - wq_sz = mlx5_wq_ll_get_size(&rq->wq); - rq->wq_type = params->rq_wq_type; rq->pdev = c->pdev; rq->netdev = c->netdev; @@ -418,6 +488,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->ix = c->ix; rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + rq->stats = &c->priv->channel_stats[c->ix].rq; rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; if (IS_ERR(rq->xdp_prog)) { @@ -432,9 +503,21 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params); + pool_size = 1 << params->log_rq_mtu_frames; switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, + &rq->wq_ctrl); + if (err) + return err; + + rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; + + wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); + + pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params); + rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; @@ -459,8 +542,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params); rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params)); - byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; - err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) goto err_rq_wq_destroy; @@ -468,16 +549,31 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5e_rq_alloc_mpwqe_info(rq, c); if (err) - goto err_destroy_umr_mkey; + goto err_free; break; - default: /* MLX5_WQ_TYPE_LINKED_LIST */ - rq->wqe.frag_info = - kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info), - GFP_KERNEL, cpu_to_node(c->cpu)); - if (!rq->wqe.frag_info) { + default: /* MLX5_WQ_TYPE_CYCLIC */ + err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, + &rq->wq_ctrl); + if (err) + return err; + + rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; + + wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq); + + rq->wqe.info = rqp->frags_info; + rq->wqe.frags = + kvzalloc_node((wq_sz << rq->wqe.info.log_num_frags) * + sizeof(*rq->wqe.frags), + GFP_KERNEL, cpu_to_node(c->cpu)); + if (!rq->wqe.frags) { err = -ENOMEM; - goto err_rq_wq_destroy; + goto err_free; } + + err = mlx5e_init_di_list(rq, params, wq_sz, c->cpu); + if (err) + goto err_free; rq->post_wqes = mlx5e_post_rx_wqes; rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; @@ -488,41 +584,71 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, #endif rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe; if (!rq->handle_rx_cqe) { - kfree(rq->wqe.frag_info); err = -EINVAL; netdev_err(c->netdev, "RX handler of RQ is not set, err %d\n", err); - goto err_rq_wq_destroy; + goto err_free; } - byte_count = params->lro_en ? - params->lro_wqe_sz : - MLX5E_SW2HW_MTU(params, params->sw_mtu); -#ifdef CONFIG_MLX5_EN_IPSEC - if (MLX5_IPSEC_DEV(mdev)) - byte_count += MLX5E_METADATA_ETHER_LEN; -#endif - rq->wqe.page_reuse = !params->xdp_prog && !params->lro_en; - - /* calc the required page order */ - rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->buff.headroom + byte_count); - npages = DIV_ROUND_UP(rq->wqe.frag_sz, PAGE_SIZE); - rq->buff.page_order = order_base_2(npages); - - byte_count |= MLX5_HW_START_PADDING; + rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(mdev, params) ? + mlx5e_skb_from_cqe_linear : + mlx5e_skb_from_cqe_nonlinear; rq->mkey_be = c->mkey_be; } - for (i = 0; i < wq_sz; i++) { - struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i); + /* Create a page_pool and register it with rxq */ + pp_params.order = 0; + pp_params.flags = 0; /* No-internal DMA mapping in page_pool */ + pp_params.pool_size = pool_size; + pp_params.nid = cpu_to_node(c->cpu); + pp_params.dev = c->pdev; + pp_params.dma_dir = rq->buff.map_dir; + + /* page_pool can be used even when there is no rq->xdp_prog, + * given page_pool does not handle DMA mapping there is no + * required state to clear. And page_pool gracefully handle + * elevated refcnt. + */ + rq->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rq->page_pool)) { + err = PTR_ERR(rq->page_pool); + rq->page_pool = NULL; + goto err_free; + } + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, + MEM_TYPE_PAGE_POOL, rq->page_pool); + if (err) + goto err_free; + for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + struct mlx5e_rx_wqe_ll *wqe = + mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i); + u32 byte_count = + rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i); - wqe->data.addr = cpu_to_be64(dma_offset + rq->buff.headroom); - } + wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom); + wqe->data[0].byte_count = cpu_to_be32(byte_count); + wqe->data[0].lkey = rq->mkey_be; + } else { + struct mlx5e_rx_wqe_cyc *wqe = + mlx5_wq_cyc_get_wqe(&rq->wqe.wq, i); + int f; + + for (f = 0; f < rq->wqe.info.num_frags; f++) { + u32 frag_size = rq->wqe.info.arr[f].frag_size | + MLX5_HW_START_PADDING; - wqe->data.byte_count = cpu_to_be32(byte_count); - wqe->data.lkey = rq->mkey_be; + wqe->data[f].byte_count = cpu_to_be32(frag_size); + wqe->data[f].lkey = rq->mkey_be; + } + /* check if num_frags is not a pow of two */ + if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) { + wqe->data[f].byte_count = 0; + wqe->data[f].lkey = cpu_to_be32(MLX5_INVALID_LKEY); + wqe->data[f].addr = 0; + } + } } INIT_WORK(&rq->dim.work, mlx5e_rx_dim_work); @@ -541,13 +667,23 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, return 0; -err_destroy_umr_mkey: - mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); +err_free: + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + kfree(rq->mpwqe.info); + mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); + break; + default: /* MLX5_WQ_TYPE_CYCLIC */ + kvfree(rq->wqe.frags); + mlx5e_free_di_list(rq); + } err_rq_wq_destroy: if (rq->xdp_prog) bpf_prog_put(rq->xdp_prog); xdp_rxq_info_unreg(&rq->xdp_rxq); + if (rq->page_pool) + page_pool_destroy(rq->page_pool); mlx5_wq_destroy(&rq->wq_ctrl); return err; @@ -561,14 +697,17 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) bpf_prog_put(rq->xdp_prog); xdp_rxq_info_unreg(&rq->xdp_rxq); + if (rq->page_pool) + page_pool_destroy(rq->page_pool); switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kfree(rq->mpwqe.info); mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); break; - default: /* MLX5_WQ_TYPE_LINKED_LIST */ - kfree(rq->wqe.frag_info); + default: /* MLX5_WQ_TYPE_CYCLIC */ + kvfree(rq->wqe.frags); + mlx5e_free_di_list(rq); } for (i = rq->page_cache.head; i != rq->page_cache.tail; @@ -608,8 +747,8 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq, MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); - mlx5_fill_page_array(&rq->wq_ctrl.buf, - (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); + mlx5_fill_page_frag_array(&rq->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); err = mlx5_core_create_rq(mdev, in, inlen, &rq->rqn); @@ -710,56 +849,58 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq) mlx5_core_destroy_rq(rq->mdev, rq->rqn); } -static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq) +static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) { - unsigned long exp_time = jiffies + msecs_to_jiffies(20000); + unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time); struct mlx5e_channel *c = rq->channel; - struct mlx5_wq_ll *wq = &rq->wq; - u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5_wq_ll_get_size(wq)); + u16 min_wqes = mlx5_min_rx_wqes(rq->wq_type, mlx5e_rqwq_get_size(rq)); - while (time_before(jiffies, exp_time)) { - if (wq->cur_sz >= min_wqes) + do { + if (mlx5e_rqwq_get_cur_sz(rq) >= min_wqes) return 0; msleep(20); - } + } while (time_before(jiffies, exp_time)); + + netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n", + c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes); - netdev_warn(c->netdev, "Failed to get min RX wqes on RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n", - rq->rqn, wq->cur_sz, min_wqes); return -ETIMEDOUT; } static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) { - struct mlx5_wq_ll *wq = &rq->wq; - struct mlx5e_rx_wqe *wqe; __be16 wqe_ix_be; u16 wqe_ix; - /* UMR WQE (if in progress) is always at wq->head */ - if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && - rq->mpwqe.umr_in_progress) - mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); - - while (!mlx5_wq_ll_is_empty(wq)) { - wqe_ix_be = *wq->tail_next; - wqe_ix = be16_to_cpu(wqe_ix_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix); - rq->dealloc_wqe(rq, wqe_ix); - mlx5_wq_ll_pop(&rq->wq, wqe_ix_be, - &wqe->next.next_wqe_index); - } + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + struct mlx5_wq_ll *wq = &rq->mpwqe.wq; - if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST && rq->wqe.page_reuse) { - /* Clean outstanding pages on handled WQEs that decided to do page-reuse, - * but yet to be re-posted. - */ - int wq_sz = mlx5_wq_ll_get_size(&rq->wq); + /* UMR WQE (if in progress) is always at wq->head */ + if (rq->mpwqe.umr_in_progress) + mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); + + while (!mlx5_wq_ll_is_empty(wq)) { + struct mlx5e_rx_wqe_ll *wqe; + + wqe_ix_be = *wq->tail_next; + wqe_ix = be16_to_cpu(wqe_ix_be); + wqe = mlx5_wq_ll_get_wqe(wq, wqe_ix); + rq->dealloc_wqe(rq, wqe_ix); + mlx5_wq_ll_pop(wq, wqe_ix_be, + &wqe->next.next_wqe_index); + } + } else { + struct mlx5_wq_cyc *wq = &rq->wqe.wq; - for (wqe_ix = 0; wqe_ix < wq_sz; wqe_ix++) + while (!mlx5_wq_cyc_is_empty(wq)) { + wqe_ix = mlx5_wq_cyc_get_tail(wq); rq->dealloc_wqe(rq, wqe_ix); + mlx5_wq_cyc_pop(wq); + } } + } static int mlx5e_open_rq(struct mlx5e_channel *c, @@ -782,7 +923,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, goto err_destroy_rq; if (params->rx_dim_enabled) - c->rq.state |= BIT(MLX5E_RQ_STATE_AM); + __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); return 0; @@ -797,13 +938,15 @@ err_free_rq: static void mlx5e_activate_rq(struct mlx5e_rq *rq) { struct mlx5e_icosq *sq = &rq->channel->icosq; - u16 pi = sq->pc & sq->wq.sz_m1; + struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_tx_wqe *nopwqe; + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; - nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); - mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl); + nopwqe = mlx5e_post_nop(wq, sq->sqn, &sq->pc); + mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl); } static void mlx5e_deactivate_rq(struct mlx5e_rq *rq) @@ -846,6 +989,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, { void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_wq_cyc *wq = &sq->wq; int err; sq->pdev = c->pdev; @@ -855,10 +999,10 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->min_inline_mode = params->tx_min_inline_mode; param->wq.db_numa_node = cpu_to_node(c->cpu); - err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); + err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); if (err) return err; - sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; + wq->db = &wq->db[MLX5_SND_DBR]; err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu)); if (err) @@ -901,23 +1045,22 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, { void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_wq_cyc *wq = &sq->wq; int err; sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; param->wq.db_numa_node = cpu_to_node(c->cpu); - err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); + err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); if (err) return err; - sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; + wq->db = &wq->db[MLX5_SND_DBR]; err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; - sq->edge = (sq->wq.sz_m1 + 1) - MLX5E_ICOSQ_MAX_WQEBBS; - return 0; err_sq_wq_destroy: @@ -962,10 +1105,12 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_txqsq *sq) + struct mlx5e_txqsq *sq, + int tc) { void *sqc_wq = MLX5_ADDR_OF(sqc, param->sqc, wq); struct mlx5_core_dev *mdev = c->mdev; + struct mlx5_wq_cyc *wq = &sq->wq; int err; sq->pdev = c->pdev; @@ -976,21 +1121,25 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->txq_ix = txq_ix; sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; + sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); + if (mlx5_accel_is_tls_device(c->priv->mdev)) + set_bit(MLX5E_SQ_STATE_TLS, &sq->state); param->wq.db_numa_node = cpu_to_node(c->cpu); - err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); + err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); if (err) return err; - sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; + wq->db = &wq->db[MLX5_SND_DBR]; err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; - sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS; + INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work); + sq->dim.mode = params->tx_cq_moderation.cq_period_mode; return 0; @@ -1051,7 +1200,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, csp->wq_ctrl->db.dma); - mlx5_fill_page_array(&csp->wq_ctrl->buf, (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); + mlx5_fill_page_frag_array(&csp->wq_ctrl->buf, + (__be64 *)MLX5_ADDR_OF(wq, wq, pas)); err = mlx5_core_create_sq(mdev, in, inlen, sqn); @@ -1130,13 +1280,14 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, struct mlx5e_sq_param *param, - struct mlx5e_txqsq *sq) + struct mlx5e_txqsq *sq, + int tc) { struct mlx5e_create_sq_param csp = {}; u32 tx_rate; int err; - err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq); + err = mlx5e_alloc_txqsq(c, txq_ix, params, param, sq, tc); if (err) return err; @@ -1153,6 +1304,9 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c, if (tx_rate) mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate); + if (params->tx_dim_enabled) + sq->state |= BIT(MLX5E_SQ_STATE_AM); + return 0; err_free_txqsq: @@ -1191,6 +1345,7 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { struct mlx5e_channel *c = sq->channel; + struct mlx5_wq_cyc *wq = &sq->wq; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); /* prevent netif_tx_wake_queue */ @@ -1199,12 +1354,13 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) netif_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ - if (mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1)) { + if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); struct mlx5e_tx_wqe *nop; - sq->db.wqe_info[(sq->pc & sq->wq.sz_m1)].skb = NULL; - nop = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); - mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nop->ctrl); + sq->db.wqe_info[pi].skb = NULL; + nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc); + mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl); } } @@ -1319,7 +1475,7 @@ static void mlx5e_sq_recover(struct work_struct *work) return; mlx5e_reset_txqsq_cc_pc(sq); - sq->stats.recover++; + sq->stats->recover++; recover->last_recover = jiffies; mlx5e_activate_txqsq(sq); } @@ -1488,7 +1644,7 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, static void mlx5e_free_cq(struct mlx5e_cq *cq) { - mlx5_cqwq_destroy(&cq->wq_ctrl); + mlx5_wq_destroy(&cq->wq_ctrl); } static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) @@ -1504,7 +1660,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) int err; inlen = MLX5_ST_SZ_BYTES(create_cq_in) + - sizeof(u64) * cq->wq_ctrl.frag_buf.npages; + sizeof(u64) * cq->wq_ctrl.buf.npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -1513,7 +1669,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) memcpy(cqc, param->cqc, sizeof(param->cqc)); - mlx5_fill_page_frag_array(&cq->wq_ctrl.frag_buf, + mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); @@ -1521,7 +1677,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) MLX5_SET(cqc, cqc, cq_period_mode, param->cq_period_mode); MLX5_SET(cqc, cqc, c_eqn, eqn); MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); - MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift - + 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); @@ -1614,14 +1770,14 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) { - int err; - int tc; + struct mlx5e_priv *priv = c->priv; + int err, tc, max_nch = priv->profile->max_nch(priv->mdev); for (tc = 0; tc < params->num_tc; tc++) { - int txq_ix = c->ix + tc * params->num_channels; + int txq_ix = c->ix + tc * max_nch; err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix, - params, &cparam->sq, &c->sq[tc]); + params, &cparam->sq, &c->sq[tc], tc); if (err) goto err_close_sqs; } @@ -1751,6 +1907,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); c->num_tc = params->num_tc; c->xdp = !!params->xdp_prog; + c->stats = &priv->channel_stats[ix].ch; mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); c->irq_desc = irq_to_desc(irq); @@ -1864,6 +2021,76 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) kfree(c); } +#define DEFAULT_FRAG_SIZE (2048) + +static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + struct mlx5e_rq_frags_info *info) +{ + u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu); + int frag_size_max = DEFAULT_FRAG_SIZE; + u32 buf_size = 0; + int i; + +#ifdef CONFIG_MLX5_EN_IPSEC + if (MLX5_IPSEC_DEV(mdev)) + byte_count += MLX5E_METADATA_ETHER_LEN; +#endif + + if (mlx5e_rx_is_linear_skb(mdev, params)) { + int frag_stride; + + frag_stride = mlx5e_rx_get_linear_frag_sz(params); + frag_stride = roundup_pow_of_two(frag_stride); + + info->arr[0].frag_size = byte_count; + info->arr[0].frag_stride = frag_stride; + info->num_frags = 1; + info->wqe_bulk = PAGE_SIZE / frag_stride; + goto out; + } + + if (byte_count > PAGE_SIZE + + (MLX5E_MAX_RX_FRAGS - 1) * frag_size_max) + frag_size_max = PAGE_SIZE; + + i = 0; + while (buf_size < byte_count) { + int frag_size = byte_count - buf_size; + + if (i < MLX5E_MAX_RX_FRAGS - 1) + frag_size = min(frag_size, frag_size_max); + + info->arr[i].frag_size = frag_size; + info->arr[i].frag_stride = roundup_pow_of_two(frag_size); + + buf_size += frag_size; + i++; + } + info->num_frags = i; + /* number of different wqes sharing a page */ + info->wqe_bulk = 1 + (info->num_frags % 2); + +out: + info->wqe_bulk = max_t(u8, info->wqe_bulk, 8); + info->log_num_frags = order_base_2(info->num_frags); +} + +static inline u8 mlx5e_get_rqwq_log_stride(u8 wq_type, int ndsegs) +{ + int sz = sizeof(struct mlx5_wqe_data_seg) * ndsegs; + + switch (wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + sz += sizeof(struct mlx5e_rx_wqe_ll); + break; + default: /* MLX5_WQ_TYPE_CYCLIC */ + sz += sizeof(struct mlx5e_rx_wqe_cyc); + } + + return order_base_2(sz); +} + static void mlx5e_build_rq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_rq_param *param) @@ -1871,6 +2098,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, struct mlx5_core_dev *mdev = priv->mdev; void *rqc = param->rqc; void *wq = MLX5_ADDR_OF(rqc, rqc, wq); + int ndsegs = 1; switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: @@ -1880,23 +2108,24 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, MLX5_SET(wq, wq, log_wqe_stride_size, mlx5e_mpwqe_get_log_stride_size(mdev, params) - MLX5_MPWQE_LOG_STRIDE_SZ_BASE); - MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ); MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params)); break; - default: /* MLX5_WQ_TYPE_LINKED_LIST */ - MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); + default: /* MLX5_WQ_TYPE_CYCLIC */ MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames); + mlx5e_build_rq_frags_info(mdev, params, ¶m->frags_info); + ndsegs = param->frags_info.num_frags; } + MLX5_SET(wq, wq, wq_type, params->rq_wq_type); MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN); - MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); + MLX5_SET(wq, wq, log_wq_stride, + mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.pdn); MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); - param->wq.linear = 1; } static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv, @@ -1906,8 +2135,9 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv, void *rqc = param->rqc; void *wq = MLX5_ADDR_OF(rqc, rqc, wq); - MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_LINKED_LIST); - MLX5_SET(wq, wq, log_wq_stride, ilog2(sizeof(struct mlx5e_rx_wqe))); + MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); + MLX5_SET(wq, wq, log_wq_stride, + mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1)); MLX5_SET(rqc, rqc, counter_set_id, priv->drop_rq_q_counter); param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); @@ -1958,7 +2188,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) + mlx5e_mpwqe_get_log_num_strides(mdev, params); break; - default: /* MLX5_WQ_TYPE_LINKED_LIST */ + default: /* MLX5_WQ_TYPE_CYCLIC */ log_cq_size = params->log_rq_mtu_frames; } @@ -2084,13 +2314,11 @@ static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs) int err = 0; int i; - for (i = 0; i < chs->num; i++) { - err = mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq); - if (err) - break; - } + for (i = 0; i < chs->num; i++) + err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, + err ? 0 : 20000); - return err; + return err ? -ETIMEDOUT : 0; } static void mlx5e_deactivate_channels(struct mlx5e_channels *chs) @@ -2580,15 +2808,21 @@ static void mlx5e_netdev_set_tcs(struct net_device *netdev) netdev_set_tc_queue(netdev, tc, nch, 0); } -static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv) +static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv) { - struct mlx5e_channel *c; - struct mlx5e_txqsq *sq; + int max_nch = priv->profile->max_nch(priv->mdev); int i, tc; - for (i = 0; i < priv->channels.num; i++) + for (i = 0; i < max_nch; i++) for (tc = 0; tc < priv->profile->max_tc; tc++) - priv->channel_tc2txq[i][tc] = i + tc * priv->channels.num; + priv->channel_tc2txq[i][tc] = i + tc * max_nch; +} + +static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) +{ + struct mlx5e_channel *c; + struct mlx5e_txqsq *sq; + int i, tc; for (i = 0; i < priv->channels.num; i++) { c = priv->channels.c[i]; @@ -2608,7 +2842,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) netif_set_real_num_tx_queues(netdev, num_txqs); netif_set_real_num_rx_queues(netdev, priv->channels.num); - mlx5e_build_channels_tx_maps(priv); + mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); @@ -2760,8 +2994,8 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev *mdev, param->wq.db_numa_node = param->wq.buf_numa_node; - err = mlx5_wq_ll_create(mdev, ¶m->wq, rqc_wq, &rq->wq, - &rq->wq_ctrl); + err = mlx5_wq_cyc_create(mdev, ¶m->wq, rqc_wq, &rq->wqe.wq, + &rq->wq_ctrl); if (err) return err; @@ -3085,6 +3319,8 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev, if (err) goto out; + priv->max_opened_tc = max_t(u8, priv->max_opened_tc, + new_channels.params.num_tc); mlx5e_switch_priv_channels(priv, &new_channels, NULL); out: mutex_unlock(&priv->state_lock); @@ -3093,22 +3329,23 @@ out: #ifdef CONFIG_MLX5_ESWITCH static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *cls_flower) + struct tc_cls_flower_offload *cls_flower, + int flags) { switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: - return mlx5e_configure_flower(priv, cls_flower); + return mlx5e_configure_flower(priv, cls_flower, flags); case TC_CLSFLOWER_DESTROY: - return mlx5e_delete_flower(priv, cls_flower); + return mlx5e_delete_flower(priv, cls_flower, flags); case TC_CLSFLOWER_STATS: - return mlx5e_stats_flower(priv, cls_flower); + return mlx5e_stats_flower(priv, cls_flower, flags); default: return -EOPNOTSUPP; } } -int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv) +static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) { struct mlx5e_priv *priv = cb_priv; @@ -3117,7 +3354,7 @@ int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_setup_tc_cls_flower(priv, type_data); + return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS); default: return -EOPNOTSUPP; } @@ -3174,6 +3411,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok); stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok); } else { + mlx5e_grp_sw_update_stats(priv); stats->rx_packets = sstats->rx_packets; stats->rx_bytes = sstats->rx_bytes; stats->tx_packets = sstats->tx_packets; @@ -3248,12 +3486,18 @@ static int set_feature_lro(struct net_device *netdev, bool enable) mutex_lock(&priv->state_lock); old_params = &priv->channels.params; + if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) { + netdev_warn(netdev, "can't set LRO with legacy RQ\n"); + err = -EINVAL; + goto out; + } + reset = test_bit(MLX5E_STATE_OPENED, &priv->state); new_channels.params = *old_params; new_channels.params.lro_en = enable; - if (old_params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) { + if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) { if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) == mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params)) reset = false; @@ -3417,22 +3661,31 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_features_t features) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_params *params; mutex_lock(&priv->state_lock); + params = &priv->channels.params; if (!bitmap_empty(priv->fs.vlan.active_svlans, VLAN_N_VID)) { /* HW strips the outer C-tag header, this is a problem * for S-tag traffic. */ features &= ~NETIF_F_HW_VLAN_CTAG_RX; - if (!priv->channels.params.vlan_strip_disable) + if (!params->vlan_strip_disable) netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n"); } + if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) { + features &= ~NETIF_F_LRO; + if (params->lro_en) + netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n"); + } + mutex_unlock(&priv->state_lock); return features; } -static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) +int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, + change_hw_mtu_cb set_mtu_cb) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels new_channels = {}; @@ -3450,7 +3703,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; - if (params->rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST) { + if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params); u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params); @@ -3459,7 +3712,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) if (!reset) { params->sw_mtu = new_mtu; - mlx5e_set_dev_port_mtu(priv); + set_mtu_cb(priv); netdev->mtu = params->sw_mtu; goto out; } @@ -3468,7 +3721,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) if (err) goto out; - mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_set_dev_port_mtu); + mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb); netdev->mtu = new_channels.params.sw_mtu; out: @@ -3476,6 +3729,11 @@ out: return err; } +static int mlx5e_change_nic_mtu(struct net_device *netdev, int new_mtu) +{ + return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu); +} + int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) { struct hwtstamp_config config; @@ -3770,7 +4028,7 @@ static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, return false; netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn); - sq->channel->stats.eq_rearm++; + sq->channel->stats->eq_rearm++; return true; } @@ -3970,7 +4228,7 @@ static const struct net_device_ops mlx5e_netdev_ops = { .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, .ndo_set_features = mlx5e_set_features, .ndo_fix_features = mlx5e_fix_features, - .ndo_change_mtu = mlx5e_change_mtu, + .ndo_change_mtu = mlx5e_change_nic_mtu, .ndo_do_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, @@ -4038,7 +4296,7 @@ static bool slow_pci_heuristic(struct mlx5_core_dev *mdev) u32 link_speed = 0; u32 pci_bw = 0; - mlx5e_get_max_linkspeed(mdev, &link_speed); + mlx5e_port_max_linkspeed(mdev, &link_speed); pci_bw = pcie_bandwidth_available(mdev->pdev, NULL, NULL, NULL); mlx5_core_dbg_once(mdev, "Max link speed = %d, PCI BW = %d\n", link_speed, pci_bw); @@ -4049,18 +4307,48 @@ static bool slow_pci_heuristic(struct mlx5_core_dev *mdev) link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw; } -void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) { - params->tx_cq_moderation.cq_period_mode = cq_period_mode; + struct net_dim_cq_moder moder; + + moder.cq_period_mode = cq_period_mode; + moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; + moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC; + if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) + moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE; - params->tx_cq_moderation.pkts = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; - params->tx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC; + return moder; +} + +static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode) +{ + struct net_dim_cq_moder moder; + moder.cq_period_mode = cq_period_mode; + moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; + moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC; if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) - params->tx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE; + moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; + + return moder; +} + +static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode) +{ + return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE : + NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE; +} + +void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +{ + if (params->tx_dim_enabled) { + u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); + + params->tx_cq_moderation = net_dim_get_def_tx_moderation(dim_period_mode); + } else { + params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode); + } MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER, params->tx_cq_moderation.cq_period_mode == @@ -4069,28 +4357,12 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) { - params->rx_cq_moderation.cq_period_mode = cq_period_mode; - - params->rx_cq_moderation.pkts = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; - params->rx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC; - - if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) - params->rx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; - if (params->rx_dim_enabled) { - switch (cq_period_mode) { - case MLX5_CQ_PERIOD_MODE_START_FROM_CQE: - params->rx_cq_moderation = - net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE); - break; - case MLX5_CQ_PERIOD_MODE_START_FROM_EQE: - default: - params->rx_cq_moderation = - net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE); - } + u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); + + params->rx_cq_moderation = net_dim_get_def_rx_moderation(dim_period_mode); + } else { + params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode); } MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER, @@ -4135,9 +4407,16 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def); /* RQ */ - if (mlx5e_striding_rq_possible(mdev, params)) - MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, - !slow_pci_heuristic(mdev)); + /* Prefer Striding RQ, unless any of the following holds: + * - Striding RQ configuration is not possible/supported. + * - Slow PCI heuristic. + * - Legacy RQ would use linear SKB while Striding RQ would use non-linear. + */ + if (!slow_pci_heuristic(mdev) && + mlx5e_striding_rq_possible(mdev, params) && + (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) || + !mlx5e_rx_is_linear_skb(mdev, params))) + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true); mlx5e_set_rq_type(mdev, params); mlx5e_init_rq_type_params(mdev, params); @@ -4154,6 +4433,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, MLX5_CQ_PERIOD_MODE_START_FROM_CQE : MLX5_CQ_PERIOD_MODE_START_FROM_EQE; params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); + params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode); mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); @@ -4179,6 +4459,7 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, priv->profile = profile; priv->ppriv = ppriv; priv->msglevel = MLX5E_MSG_LEVEL; + priv->max_opened_tc = 1; mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev), netdev->mtu); @@ -4243,7 +4524,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_RX; - if (!!MLX5_CAP_ETH(mdev, lro_cap)) + if (!!MLX5_CAP_ETH(mdev, lro_cap) && + mlx5e_check_fragmented_striding_rq_cap(mdev)) netdev->vlan_features |= NETIF_F_LRO; netdev->hw_features = netdev->vlan_features; @@ -4320,6 +4602,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) #endif mlx5e_ipsec_build_netdev(priv); + mlx5e_tls_build_netdev(priv); } static void mlx5e_create_q_counters(struct mlx5e_priv *priv) @@ -4361,12 +4644,17 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, err = mlx5e_ipsec_init(priv); if (err) mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); + err = mlx5e_tls_init(priv); + if (err) + mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); + mlx5e_build_tc2txq_maps(priv); mlx5e_vxlan_init(priv); } static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { + mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); mlx5e_vxlan_cleanup(priv); } @@ -4398,7 +4686,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) goto err_destroy_direct_tirs; } - err = mlx5e_tc_init(priv); + err = mlx5e_tc_nic_init(priv); if (err) goto err_destroy_flow_steering; @@ -4419,7 +4707,7 @@ err_destroy_indirect_rqts: static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) { - mlx5e_tc_cleanup(priv); + mlx5e_tc_nic_cleanup(priv); mlx5e_destroy_flow_steering(priv); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_indirect_tirs(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 876c3e4c61932..57987f6546e83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -66,18 +66,36 @@ static const struct counter_desc sw_rep_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_bytes) }, }; -#define NUM_VPORT_REP_COUNTERS ARRAY_SIZE(sw_rep_stats_desc) +struct vport_stats { + u64 vport_rx_packets; + u64 vport_tx_packets; + u64 vport_rx_bytes; + u64 vport_tx_bytes; +}; + +static const struct counter_desc vport_rep_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_packets) }, + { MLX5E_DECLARE_STAT(struct vport_stats, vport_rx_bytes) }, + { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_packets) }, + { MLX5E_DECLARE_STAT(struct vport_stats, vport_tx_bytes) }, +}; + +#define NUM_VPORT_REP_SW_COUNTERS ARRAY_SIZE(sw_rep_stats_desc) +#define NUM_VPORT_REP_HW_COUNTERS ARRAY_SIZE(vport_rep_stats_desc) static void mlx5e_rep_get_strings(struct net_device *dev, u32 stringset, uint8_t *data) { - int i; + int i, j; switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++) + for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++) strcpy(data + (i * ETH_GSTRING_LEN), sw_rep_stats_desc[i].format); + for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++) + strcpy(data + (i * ETH_GSTRING_LEN), + vport_rep_stats_desc[j].format); break; } } @@ -116,13 +134,13 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv) for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - rq_stats = &c->rq.stats; + rq_stats = c->rq.stats; s->rx_packets += rq_stats->packets; s->rx_bytes += rq_stats->bytes; for (j = 0; j < priv->channels.params.num_tc; j++) { - sq_stats = &c->sq[j].stats; + sq_stats = c->sq[j].stats; s->tx_packets += sq_stats->packets; s->tx_bytes += sq_stats->bytes; @@ -130,17 +148,11 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv) } } -static void mlx5e_rep_update_stats(struct mlx5e_priv *priv) -{ - mlx5e_rep_update_sw_counters(priv); - mlx5e_rep_update_hw_counters(priv); -} - static void mlx5e_rep_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct mlx5e_priv *priv = netdev_priv(dev); - int i; + int i, j; if (!data) return; @@ -148,18 +160,23 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev, mutex_lock(&priv->state_lock); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) mlx5e_rep_update_sw_counters(priv); + mlx5e_rep_update_hw_counters(priv); mutex_unlock(&priv->state_lock); - for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++) + for (i = 0; i < NUM_VPORT_REP_SW_COUNTERS; i++) data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.sw, sw_rep_stats_desc, i); + + for (j = 0; j < NUM_VPORT_REP_HW_COUNTERS; j++, i++) + data[i] = MLX5E_READ_CTR64_CPU(&priv->stats.vf_vport, + vport_rep_stats_desc, j); } static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return NUM_VPORT_REP_COUNTERS; + return NUM_VPORT_REP_SW_COUNTERS + NUM_VPORT_REP_HW_COUNTERS; default: return -EOPNOTSUPP; } @@ -681,8 +698,8 @@ static int mlx5e_rep_open(struct net_device *dev) goto unlock; if (!mlx5_modify_vport_admin_state(priv->mdev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, - rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP)) + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, + rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP)) netif_carrier_on(dev); unlock: @@ -699,8 +716,8 @@ static int mlx5e_rep_close(struct net_device *dev) mutex_lock(&priv->state_lock); mlx5_modify_vport_admin_state(priv->mdev, - MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, - rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN); + MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, + rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN); ret = mlx5e_close_locked(dev); mutex_unlock(&priv->state_lock); return ret; @@ -723,15 +740,31 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, static int mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *cls_flower) + struct tc_cls_flower_offload *cls_flower, int flags) { switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: - return mlx5e_configure_flower(priv, cls_flower); + return mlx5e_configure_flower(priv, cls_flower, flags); case TC_CLSFLOWER_DESTROY: - return mlx5e_delete_flower(priv, cls_flower); + return mlx5e_delete_flower(priv, cls_flower, flags); case TC_CLSFLOWER_STATS: - return mlx5e_stats_flower(priv, cls_flower); + return mlx5e_stats_flower(priv, cls_flower, flags); + default: + return -EOPNOTSUPP; + } +} + +static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct mlx5e_priv *priv = cb_priv; + + if (!tc_cls_can_offload_and_chain0(priv->netdev, type_data)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS); default: return -EOPNOTSUPP; } @@ -747,7 +780,7 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_rep_setup_tc_cls_flower(priv, type_data); + return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS); default: return -EOPNOTSUPP; } @@ -832,6 +865,8 @@ mlx5e_get_sw_stats64(const struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_sw_stats *sstats = &priv->stats.sw; + mlx5e_rep_update_sw_counters(priv); + stats->rx_packets = sstats->rx_packets; stats->rx_bytes = sstats->rx_bytes; stats->tx_packets = sstats->tx_packets; @@ -865,6 +900,11 @@ static const struct switchdev_ops mlx5e_rep_switchdev_ops = { .switchdev_port_attr_get = mlx5e_attr_get, }; +static int mlx5e_change_rep_mtu(struct net_device *netdev, int new_mtu) +{ + return mlx5e_change_mtu(netdev, new_mtu, NULL); +} + static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_open = mlx5e_rep_open, .ndo_stop = mlx5e_rep_close, @@ -874,6 +914,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, + .ndo_change_mtu = mlx5e_change_rep_mtu, }; static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev, @@ -886,7 +927,7 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev, params->hard_mtu = MLX5E_ETH_HARD_MTU; params->sw_mtu = mtu; params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE; - params->rq_wq_type = MLX5_WQ_TYPE_LINKED_LIST; + params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; params->log_rq_mtu_frames = MLX5E_REP_PARAMS_LOG_RQ_SIZE; params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); @@ -900,6 +941,10 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev, static void mlx5e_build_rep_netdev(struct net_device *netdev) { + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u16 max_mtu; + netdev->netdev_ops = &mlx5e_netdev_ops_rep; netdev->watchdog_timeo = 15 * HZ; @@ -912,6 +957,10 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_TC; eth_hw_addr_random(netdev); + + netdev->min_mtu = ETH_MIN_MTU; + mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu); } static void mlx5e_init_rep(struct mlx5_core_dev *mdev, @@ -965,14 +1014,8 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) } rpriv->vport_rx_rule = flow_rule; - err = mlx5e_tc_init(priv); - if (err) - goto err_del_flow_rule; - return 0; -err_del_flow_rule: - mlx5_del_flow_rules(rpriv->vport_rx_rule); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: @@ -984,7 +1027,6 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - mlx5e_tc_cleanup(priv); mlx5_del_flow_rules(rpriv->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_direct_rqts(priv); @@ -1014,7 +1056,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .cleanup_rx = mlx5e_cleanup_rep_rx, .init_tx = mlx5e_init_rep_tx, .cleanup_tx = mlx5e_cleanup_nic_tx, - .update_stats = mlx5e_rep_update_stats, + .update_stats = mlx5e_rep_update_hw_counters, .max_nch = mlx5e_get_rep_max_num_channels, .update_carrier = NULL, .rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep, @@ -1042,8 +1084,15 @@ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) if (err) goto err_remove_sqs; + /* init shared tc flow table */ + err = mlx5e_tc_esw_init(&rpriv->tc_ht); + if (err) + goto err_neigh_cleanup; + return 0; +err_neigh_cleanup: + mlx5e_rep_neigh_cleanup(rpriv); err_remove_sqs: mlx5e_remove_sqs_fwd_rules(priv); return err; @@ -1058,9 +1107,8 @@ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep) if (test_bit(MLX5E_STATE_OPENED, &priv->state)) mlx5e_remove_sqs_fwd_rules(priv); - /* clean (and re-init) existing uplink offloaded TC rules */ - mlx5e_tc_cleanup(priv); - mlx5e_tc_init(priv); + /* clean uplink offloaded TC rules, delete shared tc flow table */ + mlx5e_tc_esw_cleanup(&rpriv->tc_ht); mlx5e_rep_neigh_cleanup(rpriv); } @@ -1107,7 +1155,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH); upriv = netdev_priv(uplink_rpriv->netdev); - err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb, + err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev, upriv); if (err) goto err_neigh_cleanup; @@ -1122,7 +1170,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) return 0; err_egdev_cleanup: - tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb, + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev, upriv); err_neigh_cleanup: @@ -1151,7 +1199,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH); upriv = netdev_priv(uplink_rpriv->netdev); - tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb, + tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev, upriv); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index b9b481f2833a4..844d32d5c29f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -59,6 +59,7 @@ struct mlx5e_rep_priv { struct net_device *netdev; struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; + struct rhashtable tc_ht; /* valid for uplink rep */ }; static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1ff0b0e938041..d3a1dd20e41d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include <linux/bpf_trace.h> #include <net/busy_poll.h> #include <net/ip6_checksum.h> +#include <net/page_pool.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" @@ -53,7 +54,7 @@ static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc, void *data) { - u32 ci = cqcc & cq->wq.fbc.sz_m1; + u32 ci = mlx5_cqwq_ctr2ix(&cq->wq, cqcc); memcpy(data, mlx5_cqwq_get_wqe(&cq->wq, ci), sizeof(struct mlx5_cqe64)); } @@ -64,7 +65,7 @@ static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq, mlx5e_read_cqe_slot(cq, cqcc, &cq->title); cq->decmprs_left = be32_to_cpu(cq->title.byte_cnt); cq->decmprs_wqe_counter = be16_to_cpu(cq->title.wqe_counter); - rq->stats.cqe_compress_blks++; + rq->stats->cqe_compress_blks++; } static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc) @@ -75,10 +76,11 @@ static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc) static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n) { - struct mlx5_frag_buf_ctrl *fbc = &cq->wq.fbc; - u8 op_own = (cqcc >> fbc->log_sz) & 1; - u32 wq_sz = 1 << fbc->log_sz; - u32 ci = cqcc & fbc->sz_m1; + struct mlx5_cqwq *wq = &cq->wq; + + u8 op_own = mlx5_cqwq_get_ctr_wrap_cnt(wq, cqcc) & 1; + u32 ci = mlx5_cqwq_ctr2ix(wq, cqcc); + u32 wq_sz = mlx5_cqwq_get_size(wq); u32 ci_top = min_t(u32, wq_sz, ci + n); for (; ci < ci_top; ci++, n--) { @@ -111,7 +113,7 @@ static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq, mpwrq_get_cqe_consumed_strides(&cq->title); else cq->decmprs_wqe_counter = - (cq->decmprs_wqe_counter + 1) & rq->wq.sz_m1; + mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cq->decmprs_wqe_counter + 1); } static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq, @@ -144,7 +146,7 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, mlx5e_cqes_update_owner(cq, cq->wq.cc, cqcc - cq->wq.cc); cq->wq.cc = cqcc; cq->decmprs_left -= cqe_count; - rq->stats.cqe_compress_pkts += cqe_count; + rq->stats->cqe_compress_pkts += cqe_count; return cqe_count; } @@ -162,8 +164,6 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1; } -#define RQ_PAGE_SIZE(rq) ((1 << rq->buff.page_order) << PAGE_SHIFT) - static inline bool mlx5e_page_is_reserved(struct page *page) { return page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); @@ -174,14 +174,15 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, { struct mlx5e_page_cache *cache = &rq->page_cache; u32 tail_next = (cache->tail + 1) & (MLX5E_CACHE_SIZE - 1); + struct mlx5e_rq_stats *stats = rq->stats; if (tail_next == cache->head) { - rq->stats.cache_full++; + stats->cache_full++; return false; } if (unlikely(mlx5e_page_is_reserved(dma_info->page))) { - rq->stats.cache_waive++; + stats->cache_waive++; return false; } @@ -194,23 +195,24 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { struct mlx5e_page_cache *cache = &rq->page_cache; + struct mlx5e_rq_stats *stats = rq->stats; if (unlikely(cache->head == cache->tail)) { - rq->stats.cache_empty++; + stats->cache_empty++; return false; } if (page_ref_count(cache->page_cache[cache->head].page) != 1) { - rq->stats.cache_busy++; + stats->cache_busy++; return false; } *dma_info = cache->page_cache[cache->head]; cache->head = (cache->head + 1) & (MLX5E_CACHE_SIZE - 1); - rq->stats.cache_reuse++; + stats->cache_reuse++; dma_sync_single_for_device(rq->pdev, dma_info->addr, - RQ_PAGE_SIZE(rq), + PAGE_SIZE, DMA_FROM_DEVICE); return true; } @@ -221,12 +223,12 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, if (mlx5e_rx_cache_get(rq, dma_info)) return 0; - dma_info->page = dev_alloc_pages(rq->buff.page_order); + dma_info->page = page_pool_dev_alloc_pages(rq->page_pool); if (unlikely(!dma_info->page)) return -ENOMEM; dma_info->addr = dma_map_page(rq->pdev, dma_info->page, 0, - RQ_PAGE_SIZE(rq), rq->buff.map_dir); + PAGE_SIZE, rq->buff.map_dir); if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) { put_page(dma_info->page); dma_info->page = NULL; @@ -236,73 +238,124 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, return 0; } +static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir); +} + void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, bool recycle) { - if (likely(recycle) && mlx5e_rx_cache_put(rq, dma_info)) - return; + if (likely(recycle)) { + if (mlx5e_rx_cache_put(rq, dma_info)) + return; - dma_unmap_page(rq->pdev, dma_info->addr, RQ_PAGE_SIZE(rq), - rq->buff.map_dir); - put_page(dma_info->page); + mlx5e_page_dma_unmap(rq, dma_info); + page_pool_recycle_direct(rq->page_pool, dma_info->page); + } else { + mlx5e_page_dma_unmap(rq, dma_info); + put_page(dma_info->page); + } } -static inline bool mlx5e_page_reuse(struct mlx5e_rq *rq, - struct mlx5e_wqe_frag_info *wi) +static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, + struct mlx5e_wqe_frag_info *frag) { - return rq->wqe.page_reuse && wi->di.page && - (wi->offset + rq->wqe.frag_sz <= RQ_PAGE_SIZE(rq)) && - !mlx5e_page_is_reserved(wi->di.page); + int err = 0; + + if (!frag->offset) + /* On first frag (offset == 0), replenish page (dma_info actually). + * Other frags that point to the same dma_info (with a different + * offset) should just use the new one without replenishing again + * by themselves. + */ + err = mlx5e_page_alloc_mapped(rq, frag->di); + + return err; } -static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) +static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq, + struct mlx5e_wqe_frag_info *frag) { - struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix]; + if (frag->last_in_page) + mlx5e_page_release(rq, frag->di, true); +} - /* check if page exists, hence can be reused */ - if (!wi->di.page) { - if (unlikely(mlx5e_page_alloc_mapped(rq, &wi->di))) - return -ENOMEM; - wi->offset = 0; +static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix) +{ + return &rq->wqe.frags[ix << rq->wqe.info.log_num_frags]; +} + +static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe, + u16 ix) +{ + struct mlx5e_wqe_frag_info *frag = get_frag(rq, ix); + int err; + int i; + + for (i = 0; i < rq->wqe.info.num_frags; i++, frag++) { + err = mlx5e_get_rx_frag(rq, frag); + if (unlikely(err)) + goto free_frags; + + wqe->data[i].addr = cpu_to_be64(frag->di->addr + + frag->offset + rq->buff.headroom); } - wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset + rq->buff.headroom); return 0; + +free_frags: + while (--i >= 0) + mlx5e_put_rx_frag(rq, --frag); + + return err; } static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi) { - mlx5e_page_release(rq, &wi->di, true); - wi->di.page = NULL; + int i; + + for (i = 0; i < rq->wqe.info.num_frags; i++, wi++) + mlx5e_put_rx_frag(rq, wi); } -static inline void mlx5e_free_rx_wqe_reuse(struct mlx5e_rq *rq, - struct mlx5e_wqe_frag_info *wi) +void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) { - if (mlx5e_page_reuse(rq, wi)) { - rq->stats.page_reuse++; - return; - } + struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix); mlx5e_free_rx_wqe(rq, wi); } -void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) +static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) { - struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix]; + struct mlx5_wq_cyc *wq = &rq->wqe.wq; + int err; + int i; - if (wi->di.page) - mlx5e_free_rx_wqe(rq, wi); + for (i = 0; i < wqe_bulk; i++) { + struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i); + + err = mlx5e_alloc_rx_wqe(rq, wqe, ix + i); + if (unlikely(err)) + goto free_wqes; + } + + return 0; + +free_wqes: + while (--i >= 0) + mlx5e_dealloc_rx_wqe(rq, ix + i); + + return err; } -static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq, - struct sk_buff *skb, - struct mlx5e_dma_info *di, - u32 frag_offset, u32 len) +static inline void +mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, + struct mlx5e_dma_info *di, u32 frag_offset, u32 len, + unsigned int truesize) { - unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz)); - dma_sync_single_for_cpu(rq->pdev, di->addr + frag_offset, len, DMA_FROM_DEVICE); @@ -312,29 +365,33 @@ static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq, } static inline void +mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, + struct mlx5e_dma_info *dma_info, + int offset_from, int offset_to, u32 headlen) +{ + const void *from = page_address(dma_info->page) + offset_from; + /* Aligning len to sizeof(long) optimizes memcpy performance */ + unsigned int len = ALIGN(headlen, sizeof(long)); + + dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len, + DMA_FROM_DEVICE); + skb_copy_to_linear_data_offset(skb, offset_to, from, len); +} + +static inline void mlx5e_copy_skb_header_mpwqe(struct device *pdev, struct sk_buff *skb, struct mlx5e_dma_info *dma_info, u32 offset, u32 headlen) { u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset); - unsigned int len; - /* Aligning len to sizeof(long) optimizes memcpy performance */ - len = ALIGN(headlen_pg, sizeof(long)); - dma_sync_single_for_cpu(pdev, dma_info->addr + offset, len, - DMA_FROM_DEVICE); - skb_copy_to_linear_data(skb, page_address(dma_info->page) + offset, len); + mlx5e_copy_skb_header(pdev, skb, dma_info, offset, 0, headlen_pg); if (unlikely(offset + headlen > PAGE_SIZE)) { dma_info++; - headlen_pg = len; - len = ALIGN(headlen - headlen_pg, sizeof(long)); - dma_sync_single_for_cpu(pdev, dma_info->addr, len, - DMA_FROM_DEVICE); - skb_copy_to_linear_data_offset(skb, headlen_pg, - page_address(dma_info->page), - len); + mlx5e_copy_skb_header(pdev, skb, dma_info, 0, headlen_pg, + headlen - headlen_pg); } } @@ -352,8 +409,8 @@ void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) { - struct mlx5_wq_ll *wq = &rq->wq; - struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); + struct mlx5_wq_ll *wq = &rq->mpwqe.wq; + struct mlx5e_rx_wqe_ll *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); rq->mpwqe.umr_in_progress = false; @@ -370,6 +427,22 @@ static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq) return sq->pc >> MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; } +static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq, + struct mlx5_wq_cyc *wq, + u16 pi, u16 frag_pi) +{ + struct mlx5e_sq_wqe_info *edge_wi, *wi = &sq->db.ico_wqe[pi]; + u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi; + + edge_wi = wi + nnops; + + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->opcode = MLX5_OPCODE_NOP; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } +} + static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; @@ -378,14 +451,16 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_umr_wqe *umr_wqe; u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1); + u16 pi, frag_pi; int err; - u16 pi; int i; - /* fill sq edge with nops to avoid wqe wrap around */ - while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { - sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; - mlx5e_post_nop(wq, sq->sqn, &sq->pc); + pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc); + + if (unlikely(frag_pi + MLX5E_UMR_WQEBBS > mlx5_wq_cyc_get_frag_size(wq))) { + mlx5e_fill_icosq_frag_edge(sq, wq, pi, frag_pi); + pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); } umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi); @@ -421,7 +496,7 @@ err_unmap: dma_info--; mlx5e_page_release(rq, dma_info, true); } - rq->stats.buff_alloc_err++; + rq->stats->buff_alloc_err++; return err; } @@ -435,31 +510,34 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) { - struct mlx5_wq_ll *wq = &rq->wq; + struct mlx5_wq_cyc *wq = &rq->wqe.wq; + u8 wqe_bulk; int err; - if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return false; - if (mlx5_wq_ll_is_full(wq)) + wqe_bulk = rq->wqe.info.wqe_bulk; + + if (mlx5_wq_cyc_missing(wq) < wqe_bulk) return false; do { - struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); + u16 head = mlx5_wq_cyc_get_head(wq); - err = mlx5e_alloc_rx_wqe(rq, wqe, wq->head); + err = mlx5e_alloc_rx_wqes(rq, head, wqe_bulk); if (unlikely(err)) { - rq->stats.buff_alloc_err++; + rq->stats->buff_alloc_err++; break; } - mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); - } while (!mlx5_wq_ll_is_full(wq)); + mlx5_wq_cyc_push_n(wq, wqe_bulk); + } while (mlx5_wq_cyc_missing(wq) >= wqe_bulk); /* ensure wqes are visible to device before updating doorbell record */ dma_wmb(); - mlx5_wq_ll_update_db_record(wq); + mlx5_wq_cyc_update_db_record(wq); return !!err; } @@ -470,7 +548,7 @@ static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq, struct mlx5_cqe64 *cqe) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1; + u16 ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter)); struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci]; mlx5_cqwq_pop(&cq->wq); @@ -496,7 +574,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); struct mlx5_cqe64 *cqe; - if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return; cqe = mlx5_cqwq_get_cqe(&cq->wq); @@ -511,9 +589,9 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) { - struct mlx5_wq_ll *wq = &rq->wq; + struct mlx5_wq_ll *wq = &rq->mpwqe.wq; - if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return false; mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq); @@ -660,6 +738,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, struct sk_buff *skb, bool lro) { + struct mlx5e_rq_stats *stats = rq->stats; int network_depth = 0; if (unlikely(!(netdev->features & NETIF_F_RXCSUM))) @@ -667,7 +746,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (lro) { skb->ip_summed = CHECKSUM_UNNECESSARY; - rq->stats.csum_unnecessary++; + stats->csum_unnecessary++; return; } @@ -685,7 +764,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (unlikely(netdev->features & NETIF_F_RXFCS)) skb->csum = csum_add(skb->csum, (__force __wsum)mlx5e_get_fcs(skb)); - rq->stats.csum_complete++; + stats->csum_complete++; return; } @@ -695,15 +774,15 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, if (cqe_is_tunneled(cqe)) { skb->csum_level = 1; skb->encapsulation = 1; - rq->stats.csum_unnecessary_inner++; + stats->csum_unnecessary_inner++; return; } - rq->stats.csum_unnecessary++; + stats->csum_unnecessary++; return; } csum_none: skb->ip_summed = CHECKSUM_NONE; - rq->stats.csum_none++; + stats->csum_none++; } static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, @@ -711,20 +790,20 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, struct sk_buff *skb) { + u8 lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; + struct mlx5e_rq_stats *stats = rq->stats; struct net_device *netdev = rq->netdev; - int lro_num_seg; skb->mac_len = ETH_HLEN; - lro_num_seg = be32_to_cpu(cqe->srqn) >> 24; if (lro_num_seg > 1) { mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt); skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg); /* Subtract one since we already counted this as one * "regular" packet in mlx5e_complete_rx_cqe() */ - rq->stats.packets += lro_num_seg - 1; - rq->stats.lro_packets++; - rq->stats.lro_bytes += cqe_bcnt; + stats->packets += lro_num_seg - 1; + stats->lro_packets++; + stats->lro_bytes += cqe_bcnt; } if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) @@ -739,7 +818,7 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, if (cqe_has_vlan(cqe)) { __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), be16_to_cpu(cqe->vlan_info)); - rq->stats.removed_vlan_packets++; + stats->removed_vlan_packets++; } skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK; @@ -753,8 +832,10 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - rq->stats.packets++; - rq->stats.bytes += cqe_bcnt; + struct mlx5e_rq_stats *stats = rq->stats; + + stats->packets++; + stats->bytes += cqe_bcnt; mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb); } @@ -762,7 +843,7 @@ static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_tx_wqe *wqe; - u16 pi = (sq->pc - 1) & wq->sz_m1; /* last pi */ + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */ wqe = mlx5_wq_cyc_get_wqe(wq, pi); @@ -775,7 +856,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, { struct mlx5e_xdpsq *sq = &rq->xdpsq; struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = sq->pc & wq->sz_m1; + u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; @@ -786,10 +867,12 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, dma_addr_t dma_addr = di->addr + data_offset; unsigned int dma_len = xdp->data_end - xdp->data; + struct mlx5e_rq_stats *stats = rq->stats; + prefetchw(wqe); if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) { - rq->stats.xdp_drop++; + stats->xdp_drop++; return false; } @@ -799,7 +882,7 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, mlx5e_xmit_xdp_doorbell(sq); sq->db.doorbell = false; } - rq->stats.xdp_tx_full++; + stats->xdp_tx_full++; return false; } @@ -833,18 +916,19 @@ static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, sq->db.doorbell = true; - rq->stats.xdp_tx++; + stats->xdp_tx++; return true; } /* returns true if packet was consumed by xdp */ -static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, - struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len) +static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq, + struct mlx5e_dma_info *di, + void *va, u16 *rx_headroom, u32 *len) { - const struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); struct xdp_buff xdp; u32 act; + int err; if (!prog) return false; @@ -865,12 +949,21 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp))) trace_xdp_exception(rq->netdev, prog, act); return true; + case XDP_REDIRECT: + /* When XDP enabled then page-refcnt==1 here */ + err = xdp_do_redirect(rq->netdev, &xdp, prog); + if (!err) { + __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); + rq->xdpsq.db.redirect_flush = true; + mlx5e_page_dma_unmap(rq, di); + } + return true; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: trace_xdp_exception(rq->netdev, prog, act); case XDP_DROP: - rq->stats.xdp_drop++; + rq->stats->xdp_drop++; return true; } } @@ -883,7 +976,7 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, struct sk_buff *skb = build_skb(va, frag_size); if (unlikely(!skb)) { - rq->stats.buff_alloc_err++; + rq->stats->buff_alloc_err++; return NULL; } @@ -893,11 +986,11 @@ struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va, return skb; } -static inline -struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, - struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) +struct sk_buff * +mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { - struct mlx5e_dma_info *di = &wi->di; + struct mlx5e_dma_info *di = wi->di; u16 rx_headroom = rq->buff.headroom; struct sk_buff *skb; void *va, *data; @@ -910,11 +1003,11 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, dma_sync_single_range_for_cpu(rq->pdev, di->addr, wi->offset, frag_size, DMA_FROM_DEVICE); + prefetchw(va); /* xdp_frame data area */ prefetch(data); - wi->offset += frag_size; if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) { - rq->stats.wqe_err++; + rq->stats->wqe_err++; return NULL; } @@ -934,41 +1027,87 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return skb; } +struct sk_buff * +mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) +{ + struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0]; + struct mlx5e_wqe_frag_info *head_wi = wi; + u16 headlen = min_t(u32, MLX5E_RX_MAX_HEAD, cqe_bcnt); + u16 frag_headlen = headlen; + u16 byte_cnt = cqe_bcnt - headlen; + struct sk_buff *skb; + + if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) { + rq->stats->wqe_err++; + return NULL; + } + + /* XDP is not supported in this configuration, as incoming packets + * might spread among multiple pages. + */ + skb = napi_alloc_skb(rq->cq.napi, + ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long))); + if (unlikely(!skb)) { + rq->stats->buff_alloc_err++; + return NULL; + } + + prefetchw(skb->data); + + while (byte_cnt) { + u16 frag_consumed_bytes = + min_t(u16, frag_info->frag_size - frag_headlen, byte_cnt); + + mlx5e_add_skb_frag(rq, skb, wi->di, wi->offset + frag_headlen, + frag_consumed_bytes, frag_info->frag_stride); + byte_cnt -= frag_consumed_bytes; + frag_headlen = 0; + frag_info++; + wi++; + } + + /* copy header */ + mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, + 0, headlen); + /* skb linear part was allocated with headlen and aligned to long */ + skb->tail += headlen; + skb->len += headlen; + + return skb; +} + void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { + struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; - struct mlx5e_rx_wqe *wqe; - __be16 wqe_counter_be; struct sk_buff *skb; - u16 wqe_counter; u32 cqe_bcnt; + u16 ci; - wqe_counter_be = cqe->wqe_counter; - wqe_counter = be16_to_cpu(wqe_counter_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); - wi = &rq->wqe.frag_info[wqe_counter]; - cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter)); + wi = get_frag(rq, ci); + cqe_bcnt = be32_to_cpu(cqe->byte_cnt); - skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt); + skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (!skb) { /* probably for XDP */ if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - wi->di.page = NULL; - /* do not return page to cache, it will be returned on XDP_TX completion */ - goto wq_ll_pop; + /* do not return page to cache, + * it will be returned on XDP_TX completion. + */ + goto wq_cyc_pop; } - /* probably an XDP_DROP, save the page-reuse checks */ - mlx5e_free_rx_wqe(rq, wi); - goto wq_ll_pop; + goto free_wqe; } mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); napi_gro_receive(rq->cq.napi, skb); - mlx5e_free_rx_wqe_reuse(rq, wi); -wq_ll_pop: - mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, - &wqe->next.next_wqe_index); +free_wqe: + mlx5e_free_rx_wqe(rq, wi); +wq_cyc_pop: + mlx5_wq_cyc_pop(wq); } #ifdef CONFIG_MLX5_ESWITCH @@ -978,29 +1117,26 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; - struct mlx5e_rx_wqe *wqe; struct sk_buff *skb; - __be16 wqe_counter_be; - u16 wqe_counter; u32 cqe_bcnt; + u16 ci; - wqe_counter_be = cqe->wqe_counter; - wqe_counter = be16_to_cpu(wqe_counter_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); - wi = &rq->wqe.frag_info[wqe_counter]; - cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter)); + wi = get_frag(rq, ci); + cqe_bcnt = be32_to_cpu(cqe->byte_cnt); - skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt); + skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (!skb) { + /* probably for XDP */ if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { - wi->di.page = NULL; - /* do not return page to cache, it will be returned on XDP_TX completion */ - goto wq_ll_pop; + /* do not return page to cache, + * it will be returned on XDP_TX completion. + */ + goto wq_cyc_pop; } - /* probably an XDP_DROP, save the page-reuse checks */ - mlx5e_free_rx_wqe(rq, wi); - goto wq_ll_pop; + goto free_wqe; } mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); @@ -1010,10 +1146,10 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); - mlx5e_free_rx_wqe_reuse(rq, wi); -wq_ll_pop: - mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, - &wqe->next.next_wqe_index); +free_wqe: + mlx5e_free_rx_wqe(rq, wi); +wq_cyc_pop: + mlx5_wq_cyc_pop(wq); } #endif @@ -1021,7 +1157,7 @@ struct sk_buff * mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx) { - u16 headlen = min_t(u16, MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, cqe_bcnt); + u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt); struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx]; u32 frag_offset = head_offset + headlen; u32 byte_cnt = cqe_bcnt - headlen; @@ -1029,9 +1165,9 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w struct sk_buff *skb; skb = napi_alloc_skb(rq->cq.napi, - ALIGN(MLX5_MPWRQ_SMALL_PACKET_THRESHOLD, sizeof(long))); + ALIGN(MLX5E_RX_MAX_HEAD, sizeof(long))); if (unlikely(!skb)) { - rq->stats.buff_alloc_err++; + rq->stats->buff_alloc_err++; return NULL; } @@ -1045,9 +1181,11 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w while (byte_cnt) { u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - frag_offset, byte_cnt); + unsigned int truesize = + ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); - mlx5e_add_skb_frag_mpwqe(rq, skb, di, frag_offset, - pg_consumed_bytes); + mlx5e_add_skb_frag(rq, skb, di, frag_offset, + pg_consumed_bytes, truesize); byte_cnt -= pg_consumed_bytes; frag_offset = 0; di++; @@ -1110,19 +1248,20 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz; u32 head_offset = wqe_offset & (PAGE_SIZE - 1); u32 page_idx = wqe_offset >> PAGE_SHIFT; - struct mlx5e_rx_wqe *wqe; + struct mlx5e_rx_wqe_ll *wqe; + struct mlx5_wq_ll *wq; struct sk_buff *skb; u16 cqe_bcnt; wi->consumed_strides += cstrides; if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) { - rq->stats.wqe_err++; + rq->stats->wqe_err++; goto mpwrq_cqe_out; } if (unlikely(mpwrq_is_filler_cqe(cqe))) { - rq->stats.mpwqe_filler++; + rq->stats->mpwqe_filler++; goto mpwrq_cqe_out; } @@ -1140,9 +1279,10 @@ mpwrq_cqe_out: if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) return; - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_id); + wq = &rq->mpwqe.wq; + wqe = mlx5_wq_ll_get_wqe(wq, wqe_id); mlx5e_free_rx_mpwqe(rq, wi); - mlx5_wq_ll_pop(&rq->wq, cqe->wqe_id, &wqe->next.next_wqe_index); + mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); } int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) @@ -1152,7 +1292,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5_cqe64 *cqe; int work_done = 0; - if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; if (cq->decmprs_left) @@ -1182,6 +1322,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) xdpsq->db.doorbell = false; } + if (xdpsq->db.redirect_flush) { + xdp_do_flush_map(); + xdpsq->db.redirect_flush = false; + } + mlx5_cqwq_update_db_record(&cq->wq); /* ensure cq space is freed before enabling more cqes */ @@ -1200,7 +1345,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) sq = container_of(cq, struct mlx5e_xdpsq, cq); - if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; cqe = mlx5_cqwq_get_cqe(&cq->wq); @@ -1229,7 +1374,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) last_wqe = (sqcc == wqe_counter); - ci = sqcc & sq->wq.sz_m1; + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); di = &sq->db.di[ci]; sqcc++; @@ -1254,7 +1399,7 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) u16 ci; while (sq->cc != sq->pc) { - ci = sq->cc & sq->wq.sz_m1; + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc); di = &sq->db.di[ci]; sq->cc++; @@ -1272,6 +1417,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { + struct mlx5e_rq_stats *stats = rq->stats; struct hwtstamp_config *tstamp; struct net_device *netdev; struct mlx5e_priv *priv; @@ -1333,27 +1479,24 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, skb->dev = netdev; - rq->stats.csum_complete++; - rq->stats.packets++; - rq->stats.bytes += cqe_bcnt; + stats->csum_complete++; + stats->packets++; + stats->bytes += cqe_bcnt; } void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { + struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; - struct mlx5e_rx_wqe *wqe; - __be16 wqe_counter_be; struct sk_buff *skb; - u16 wqe_counter; u32 cqe_bcnt; + u16 ci; - wqe_counter_be = cqe->wqe_counter; - wqe_counter = be16_to_cpu(wqe_counter_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); - wi = &rq->wqe.frag_info[wqe_counter]; - cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter)); + wi = get_frag(rq, ci); + cqe_bcnt = be32_to_cpu(cqe->byte_cnt); - skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt); + skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (!skb) goto wq_free_wqe; @@ -1365,9 +1508,8 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); wq_free_wqe: - mlx5e_free_rx_wqe_reuse(rq, wi); - mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, - &wqe->next.next_wqe_index); + mlx5e_free_rx_wqe(rq, wi); + mlx5_wq_cyc_pop(wq); } #endif /* CONFIG_MLX5_CORE_IPOIB */ @@ -1376,38 +1518,34 @@ wq_free_wqe: void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { + struct mlx5_wq_cyc *wq = &rq->wqe.wq; struct mlx5e_wqe_frag_info *wi; - struct mlx5e_rx_wqe *wqe; - __be16 wqe_counter_be; struct sk_buff *skb; - u16 wqe_counter; u32 cqe_bcnt; + u16 ci; - wqe_counter_be = cqe->wqe_counter; - wqe_counter = be16_to_cpu(wqe_counter_be); - wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_counter); - wi = &rq->wqe.frag_info[wqe_counter]; - cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + ci = mlx5_wq_cyc_ctr2ix(wq, be16_to_cpu(cqe->wqe_counter)); + wi = get_frag(rq, ci); + cqe_bcnt = be32_to_cpu(cqe->byte_cnt); - skb = skb_from_cqe(rq, cqe, wi, cqe_bcnt); + skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (unlikely(!skb)) { /* a DROP, save the page-reuse checks */ mlx5e_free_rx_wqe(rq, wi); - goto wq_ll_pop; + goto wq_cyc_pop; } skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb); if (unlikely(!skb)) { mlx5e_free_rx_wqe(rq, wi); - goto wq_ll_pop; + goto wq_cyc_pop; } mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); napi_gro_receive(rq->cq.napi, skb); - mlx5e_free_rx_wqe_reuse(rq, wi); -wq_ll_pop: - mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, - &wqe->next.next_wqe_index); + mlx5e_free_rx_wqe(rq, wi); +wq_cyc_pop: + mlx5_wq_cyc_pop(wq); } #endif /* CONFIG_MLX5_EN_IPSEC */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 027f54ac1ca2c..4d316cc9b008a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -100,7 +100,7 @@ static int mlx5e_test_link_speed(struct mlx5e_priv *priv) #ifdef CONFIG_INET /* loopback test */ -#define MLX5E_TEST_PKT_SIZE (MLX5_MPWRQ_SMALL_PACKET_THRESHOLD - NET_IP_ALIGN) +#define MLX5E_TEST_PKT_SIZE (MLX5E_RX_MAX_HEAD - NET_IP_ALIGN) static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST"; #define MLX5E_TEST_MAGIC 0x5AEED15C001ULL diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index b08c94422907e..1646859974ce2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -32,6 +32,7 @@ #include "en.h" #include "en_accel/ipsec.h" +#include "en_accel/tls.h" static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) }, @@ -43,6 +44,12 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) }, + +#ifdef CONFIG_MLX5_EN_TLS + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) }, +#endif + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) }, @@ -57,11 +64,11 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) }, @@ -74,7 +81,6 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) }, }; #define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc) @@ -102,20 +108,19 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) return idx; } -static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) +void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) { struct mlx5e_sw_stats temp, *s = &temp; - struct mlx5e_rq_stats *rq_stats; - struct mlx5e_sq_stats *sq_stats; - struct mlx5e_ch_stats *ch_stats; - int i, j; + int i; memset(s, 0, sizeof(*s)); - for (i = 0; i < priv->channels.num; i++) { - struct mlx5e_channel *c = priv->channels.c[i]; - rq_stats = &c->rq.stats; - ch_stats = &c->stats; + for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) { + struct mlx5e_channel_stats *channel_stats = + &priv->channel_stats[i]; + struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; + struct mlx5e_ch_stats *ch_stats = &channel_stats->ch; + int j; s->rx_packets += rq_stats->packets; s->rx_bytes += rq_stats->bytes; @@ -142,8 +147,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_cache_waive += rq_stats->cache_waive; s->ch_eq_rearm += ch_stats->eq_rearm; - for (j = 0; j < priv->channels.params.num_tc; j++) { - sq_stats = &c->sq[j].stats; + for (j = 0; j < priv->max_opened_tc; j++) { + struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; s->tx_packets += sq_stats->packets; s->tx_bytes += sq_stats->bytes; @@ -161,12 +166,13 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_csum_partial_inner += sq_stats->csum_partial_inner; s->tx_csum_none += sq_stats->csum_none; s->tx_csum_partial += sq_stats->csum_partial; +#ifdef CONFIG_MLX5_EN_TLS + s->tx_tls_ooo += sq_stats->tls_ooo; + s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; +#endif } } - s->link_down_events_phy = MLX5_GET(ppcnt_reg, - priv->stats.pport.phy_counters, - counter_set.phys_layer_cntrs.link_down_events); memcpy(&priv->stats.sw, s, sizeof(*s)); } @@ -569,12 +575,13 @@ static const struct counter_desc pport_phy_statistical_stats_desc[] = { { "rx_corrected_bits_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits) }, }; -#define NUM_PPORT_PHY_COUNTERS ARRAY_SIZE(pport_phy_statistical_stats_desc) +#define NUM_PPORT_PHY_STATISTICAL_COUNTERS ARRAY_SIZE(pport_phy_statistical_stats_desc) static int mlx5e_grp_phy_get_num_stats(struct mlx5e_priv *priv) { + /* "1" for link_down_events special counter */ return MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group) ? - NUM_PPORT_PHY_COUNTERS : 0; + NUM_PPORT_PHY_STATISTICAL_COUNTERS + 1 : 1; } static int mlx5e_grp_phy_fill_strings(struct mlx5e_priv *priv, u8 *data, @@ -582,10 +589,14 @@ static int mlx5e_grp_phy_fill_strings(struct mlx5e_priv *priv, u8 *data, { int i; - if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group)) - for (i = 0; i < NUM_PPORT_PHY_COUNTERS; i++) - strcpy(data + (idx++) * ETH_GSTRING_LEN, - pport_phy_statistical_stats_desc[i].format); + strcpy(data + (idx++) * ETH_GSTRING_LEN, "link_down_events_phy"); + + if (!MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group)) + return idx; + + for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pport_phy_statistical_stats_desc[i].format); return idx; } @@ -593,11 +604,17 @@ static int mlx5e_grp_phy_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) { int i; - if (MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group)) - for (i = 0; i < NUM_PPORT_PHY_COUNTERS; i++) - data[idx++] = - MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters, - pport_phy_statistical_stats_desc, i); + /* link_down_events_phy has special handling since it is not stored in __be64 format */ + data[idx++] = MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters, + counter_set.phys_layer_cntrs.link_down_events); + + if (!MLX5_CAP_PCAM_FEATURE((priv)->mdev, ppcnt_statistical_group)) + return idx; + + for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++) + data[idx++] = + MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters, + pport_phy_statistical_stats_desc, i); return idx; } @@ -1065,6 +1082,22 @@ static void mlx5e_grp_ipsec_update_stats(struct mlx5e_priv *priv) mlx5e_ipsec_update_stats(priv); } +static int mlx5e_grp_tls_get_num_stats(struct mlx5e_priv *priv) +{ + return mlx5e_tls_get_count(priv); +} + +static int mlx5e_grp_tls_fill_strings(struct mlx5e_priv *priv, u8 *data, + int idx) +{ + return idx + mlx5e_tls_get_strings(priv, data + idx * ETH_GSTRING_LEN); +} + +static int mlx5e_grp_tls_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) +{ + return idx + mlx5e_tls_get_stats(priv, data + idx); +} + static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, @@ -1104,11 +1137,11 @@ static const struct counter_desc sq_stats_desc[] = { { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, nop) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) }, + { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) }, }; static const struct counter_desc ch_stats_desc[] = { @@ -1121,30 +1154,30 @@ static const struct counter_desc ch_stats_desc[] = { static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) { - return (NUM_RQ_STATS * priv->channels.num) + - (NUM_CH_STATS * priv->channels.num) + - (NUM_SQ_STATS * priv->channels.num * priv->channels.params.num_tc); + int max_nch = priv->profile->max_nch(priv->mdev); + + return (NUM_RQ_STATS * max_nch) + + (NUM_CH_STATS * max_nch) + + (NUM_SQ_STATS * max_nch * priv->max_opened_tc); } static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx) { + int max_nch = priv->profile->max_nch(priv->mdev); int i, j, tc; - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - return idx; - - for (i = 0; i < priv->channels.num; i++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_CH_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, ch_stats_desc[j].format, i); - for (i = 0; i < priv->channels.num; i++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_RQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i); - for (tc = 0; tc < priv->channels.params.num_tc; tc++) - for (i = 0; i < priv->channels.num; i++) + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_SQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, sq_stats_desc[j].format, @@ -1156,29 +1189,26 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) { - struct mlx5e_channels *channels = &priv->channels; + int max_nch = priv->profile->max_nch(priv->mdev); int i, j, tc; - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - return idx; - - for (i = 0; i < channels->num; i++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_CH_STATS; j++) data[idx++] = - MLX5E_READ_CTR64_CPU(&channels->c[i]->stats, + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch, ch_stats_desc, j); - for (i = 0; i < channels->num; i++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_RQ_STATS; j++) data[idx++] = - MLX5E_READ_CTR64_CPU(&channels->c[i]->rq.stats, + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq, rq_stats_desc, j); - for (tc = 0; tc < priv->channels.params.num_tc; tc++) - for (i = 0; i < channels->num; i++) + for (tc = 0; tc < priv->max_opened_tc; tc++) + for (i = 0; i < max_nch; i++) for (j = 0; j < NUM_SQ_STATS; j++) data[idx++] = - MLX5E_READ_CTR64_CPU(&channels->c[i]->sq[tc].stats, + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc], sq_stats_desc, j); return idx; @@ -1190,7 +1220,6 @@ const struct mlx5e_stats_grp mlx5e_stats_grps[] = { .get_num_stats = mlx5e_grp_sw_get_num_stats, .fill_strings = mlx5e_grp_sw_fill_strings, .fill_stats = mlx5e_grp_sw_fill_stats, - .update_stats_mask = MLX5E_NDO_UPDATE_STATS, .update_stats = mlx5e_grp_sw_update_stats, }, { @@ -1268,6 +1297,11 @@ const struct mlx5e_stats_grp mlx5e_stats_grps[] = { .update_stats = mlx5e_grp_ipsec_update_stats, }, { + .get_num_stats = mlx5e_grp_tls_get_num_stats, + .fill_strings = mlx5e_grp_tls_fill_strings, + .fill_stats = mlx5e_grp_tls_fill_stats, + }, + { .get_num_stats = mlx5e_grp_channels_get_num_stats, .fill_strings = mlx5e_grp_channels_fill_strings, .fill_stats = mlx5e_grp_channels_fill_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 53111a2df5871..643153bb36072 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -75,11 +75,11 @@ struct mlx5e_sw_stats { u64 tx_csum_partial; u64 tx_csum_partial_inner; u64 tx_queue_stopped; - u64 tx_queue_wake; u64 tx_queue_dropped; u64 tx_xmit_more; - u64 tx_cqe_err; u64 tx_recover; + u64 tx_queue_wake; + u64 tx_cqe_err; u64 rx_wqe_err; u64 rx_mpwqe_filler; u64 rx_buff_alloc_err; @@ -93,8 +93,10 @@ struct mlx5e_sw_stats { u64 rx_cache_waive; u64 ch_eq_rearm; - /* Special handling counters */ - u64 link_down_events_phy; +#ifdef CONFIG_MLX5_EN_TLS + u64 tx_tls_ooo; + u64 tx_tls_resync_bytes; +#endif }; struct mlx5e_qcounter_stats { @@ -194,13 +196,18 @@ struct mlx5e_sq_stats { u64 csum_partial_inner; u64 added_vlan_packets; u64 nop; +#ifdef CONFIG_MLX5_EN_TLS + u64 tls_ooo; + u64 tls_resync_bytes; +#endif /* less likely accessed in data path */ u64 csum_none; u64 stopped; - u64 wake; u64 dropped; - u64 cqe_err; u64 recover; + /* dirtied @completion */ + u64 wake ____cacheline_aligned_in_smp; + u64 cqe_err; }; struct mlx5e_ch_stats { @@ -233,4 +240,6 @@ struct mlx5e_stats_grp { extern const struct mlx5e_stats_grp mlx5e_stats_grps[]; extern const int mlx5e_num_stats_grps; +void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv); + #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index b94276db3ce93..0edf4751a8ba2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -52,28 +52,37 @@ #include "eswitch.h" #include "vxlan.h" #include "fs_core.h" +#include "en/port.h" struct mlx5_nic_flow_attr { u32 action; u32 flow_tag; u32 mod_hdr_id; u32 hairpin_tirn; + u8 match_level; struct mlx5_flow_table *hairpin_ft; }; +#define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1) + enum { - MLX5E_TC_FLOW_ESWITCH = BIT(0), - MLX5E_TC_FLOW_NIC = BIT(1), - MLX5E_TC_FLOW_OFFLOADED = BIT(2), - MLX5E_TC_FLOW_HAIRPIN = BIT(3), - MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(4), + MLX5E_TC_FLOW_INGRESS = MLX5E_TC_INGRESS, + MLX5E_TC_FLOW_EGRESS = MLX5E_TC_EGRESS, + MLX5E_TC_FLOW_ESWITCH = BIT(MLX5E_TC_FLOW_BASE), + MLX5E_TC_FLOW_NIC = BIT(MLX5E_TC_FLOW_BASE + 1), + MLX5E_TC_FLOW_OFFLOADED = BIT(MLX5E_TC_FLOW_BASE + 2), + MLX5E_TC_FLOW_HAIRPIN = BIT(MLX5E_TC_FLOW_BASE + 3), + MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4), }; +#define MLX5E_TC_MAX_SPLITS 1 + struct mlx5e_tc_flow { struct rhash_head node; + struct mlx5e_priv *priv; u64 cookie; u8 flags; - struct mlx5_flow_handle *rule; + struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1]; struct list_head encap; /* flows sharing the same encap ID */ struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ struct list_head hairpin; /* flows sharing the same hairpin */ @@ -97,7 +106,7 @@ enum { }; #define MLX5E_TC_TABLE_NUM_GROUPS 4 -#define MLX5E_TC_TABLE_MAX_GROUP_SIZE (1 << 16) +#define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(16) struct mlx5e_hairpin { struct mlx5_hairpin *pair; @@ -607,7 +616,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, params.q_counter = priv->q_counter; /* set hairpin pair per each 50Gbs share of the link */ - mlx5e_get_max_linkspeed(priv->mdev, &link_speed); + mlx5e_port_max_linkspeed(priv->mdev, &link_speed); link_speed = max_t(u32, link_speed, 50000); link_speed64 = link_speed; do_div(link_speed64, 50000); @@ -753,7 +762,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, table_created = true; } - parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + if (attr->match_level != MLX5_MATCH_NONE) + parse_attr->spec.match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + rule = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec, &flow_act, dest, dest_ix); @@ -785,11 +796,11 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, struct mlx5_nic_flow_attr *attr = flow->nic_attr; struct mlx5_fc *counter = NULL; - counter = mlx5_flow_rule_counter(flow->rule); - mlx5_del_flow_rules(flow->rule); + counter = mlx5_flow_rule_counter(flow->rule[0]); + mlx5_del_flow_rules(flow->rule[0]); mlx5_fc_destroy(priv->mdev, counter); - if (!mlx5e_tc_num_filters(priv) && (priv->fs.tc.t)) { + if (!mlx5e_tc_num_filters(priv) && priv->fs.tc.t) { mlx5_destroy_flow_table(priv->fs.tc.t); priv->fs.tc.t = NULL; } @@ -835,7 +846,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, } out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; - attr->out_rep = rpriv->rep; + attr->out_rep[attr->out_count] = rpriv->rep; + attr->out_mdev[attr->out_count++] = out_priv->mdev; } err = mlx5_eswitch_add_vlan_action(esw, attr); @@ -860,9 +872,18 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, rule = mlx5_eswitch_add_offloaded_rule(esw, &parse_attr->spec, attr); if (IS_ERR(rule)) goto err_add_rule; + + if (attr->mirror_count) { + flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, &parse_attr->spec, attr); + if (IS_ERR(flow->rule[1])) + goto err_fwd_rule; + } } return rule; +err_fwd_rule: + mlx5_eswitch_del_offloaded_rule(esw, rule, attr); + rule = flow->rule[1]; err_add_rule: if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); @@ -883,7 +904,9 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED; - mlx5_eswitch_del_offloaded_rule(esw, flow->rule, attr); + if (attr->mirror_count) + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[1], attr); + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); } mlx5_eswitch_del_vlan_action(esw, attr); @@ -919,13 +942,25 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, list_for_each_entry(flow, &e->flows, encap) { esw_attr = flow->esw_attr; esw_attr->encap_id = e->encap_id; - flow->rule = mlx5_eswitch_add_offloaded_rule(esw, &esw_attr->parse_attr->spec, esw_attr); - if (IS_ERR(flow->rule)) { - err = PTR_ERR(flow->rule); + flow->rule[0] = mlx5_eswitch_add_offloaded_rule(esw, &esw_attr->parse_attr->spec, esw_attr); + if (IS_ERR(flow->rule[0])) { + err = PTR_ERR(flow->rule[0]); mlx5_core_warn(priv->mdev, "Failed to update cached encapsulation flow, %d\n", err); continue; } + + if (esw_attr->mirror_count) { + flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, &esw_attr->parse_attr->spec, esw_attr); + if (IS_ERR(flow->rule[1])) { + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], esw_attr); + err = PTR_ERR(flow->rule[1]); + mlx5_core_warn(priv->mdev, "Failed to update cached mirror flow, %d\n", + err); + continue; + } + } + flow->flags |= MLX5E_TC_FLOW_OFFLOADED; } } @@ -938,8 +973,12 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, &e->flows, encap) { if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { + struct mlx5_esw_flow_attr *attr = flow->esw_attr; + flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED; - mlx5_eswitch_del_offloaded_rule(esw, flow->rule, flow->esw_attr); + if (attr->mirror_count) + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[1], attr); + mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr); } } @@ -974,7 +1013,7 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) continue; list_for_each_entry(flow, &e->flows, encap) { if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { - counter = mlx5_flow_rule_counter(flow->rule); + counter = mlx5_flow_rule_counter(flow->rule[0]); mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { neigh_used = true; @@ -982,6 +1021,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) } } } + if (neigh_used) + break; } if (neigh_used) { @@ -1190,7 +1231,7 @@ vxlan_match_offload_err: static int __parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, - u8 *min_inline) + u8 *match_level) { void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); @@ -1199,7 +1240,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, u16 addr_type = 0; u8 ip_proto = 0; - *min_inline = MLX5_INLINE_MODE_L2; + *match_level = MLX5_MATCH_NONE; if (f->dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | @@ -1249,58 +1290,6 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, inner_headers); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); - - struct flow_dissector_key_control *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->mask); - addr_type = key->addr_type; - - /* the HW doesn't support frag first/later */ - if (mask->flags & FLOW_DIS_FIRST_FRAG) - return -EOPNOTSUPP; - - if (mask->flags & FLOW_DIS_IS_FRAGMENT) { - MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, - key->flags & FLOW_DIS_IS_FRAGMENT); - - /* the HW doesn't need L3 inline to match on frag=no */ - if (key->flags & FLOW_DIS_IS_FRAGMENT) - *min_inline = MLX5_INLINE_MODE_IP; - } - } - - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - ip_proto = key->ip_proto; - - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, - ntohs(mask->n_proto)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, - ntohs(key->n_proto)); - - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, - mask->ip_proto); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, - key->ip_proto); - - if (mask->ip_proto) - *min_inline = MLX5_INLINE_MODE_IP; - } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_dissector_key_eth_addrs *key = skb_flow_dissector_target(f->dissector, @@ -1324,6 +1313,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, smac_47_16), key->src); + + if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst)) + *match_level = MLX5_MATCH_L2; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { @@ -1344,9 +1336,79 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); + + *match_level = MLX5_MATCH_L2; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, + ntohs(mask->n_proto)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, + ntohs(key->n_proto)); + + if (mask->n_proto) + *match_level = MLX5_MATCH_L2; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->key); + + struct flow_dissector_key_control *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->mask); + addr_type = key->addr_type; + + /* the HW doesn't support frag first/later */ + if (mask->flags & FLOW_DIS_FIRST_FRAG) + return -EOPNOTSUPP; + + if (mask->flags & FLOW_DIS_IS_FRAGMENT) { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, + key->flags & FLOW_DIS_IS_FRAGMENT); + + /* the HW doesn't need L3 inline to match on frag=no */ + if (!(key->flags & FLOW_DIS_IS_FRAGMENT)) + *match_level = MLX5_INLINE_MODE_L2; + /* *** L2 attributes parsing up to here *** */ + else + *match_level = MLX5_INLINE_MODE_IP; } } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + struct flow_dissector_key_basic *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + ip_proto = key->ip_proto; + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, + mask->ip_proto); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, + key->ip_proto); + + if (mask->ip_proto) + *match_level = MLX5_MATCH_L3; + } + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { struct flow_dissector_key_ipv4_addrs *key = skb_flow_dissector_target(f->dissector, @@ -1371,7 +1433,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, &key->dst, sizeof(key->dst)); if (mask->src || mask->dst) - *min_inline = MLX5_INLINE_MODE_IP; + *match_level = MLX5_MATCH_L3; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { @@ -1400,7 +1462,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY || ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY) - *min_inline = MLX5_INLINE_MODE_IP; + *match_level = MLX5_MATCH_L3; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) { @@ -1428,9 +1490,11 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EOPNOTSUPP; if (mask->tos || mask->ttl) - *min_inline = MLX5_INLINE_MODE_IP; + *match_level = MLX5_MATCH_L3; } + /* *** L3 attributes parsing up to here *** */ + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { struct flow_dissector_key_ports *key = skb_flow_dissector_target(f->dissector, @@ -1471,7 +1535,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } if (mask->src || mask->dst) - *min_inline = MLX5_INLINE_MODE_TCP_UDP; + *match_level = MLX5_MATCH_L4; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) { @@ -1490,7 +1554,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, ntohs(key->flags)); if (mask->flags) - *min_inline = MLX5_INLINE_MODE_TCP_UDP; + *match_level = MLX5_MATCH_L4; } return 0; @@ -1505,23 +1569,28 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; - u8 min_inline; + u8 match_level; int err; - err = __parse_cls_flower(priv, spec, f, &min_inline); + err = __parse_cls_flower(priv, spec, f, &match_level); if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; if (rep->vport != FDB_UPLINK_VPORT && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && - esw->offloads.inline_mode < min_inline)) { + esw->offloads.inline_mode < match_level)) { netdev_warn(priv->netdev, "Flow is not offloaded due to min inline setting, required %d actual %d\n", - min_inline, esw->offloads.inline_mode); + match_level, esw->offloads.inline_mode); return -EOPNOTSUPP; } } + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + flow->esw_attr->match_level = match_level; + else + flow->nic_attr->match_level = match_level; + return err; } @@ -1578,7 +1647,6 @@ struct mlx5_fields { static struct mlx5_fields fields[] = { OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0), - OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0), OFFLOAD(DMAC_15_0, 2, eth.h_dest[4], 0), OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0), OFFLOAD(SMAC_15_0, 2, eth.h_source[4], 0), @@ -1764,12 +1832,12 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, err = -EOPNOTSUPP; /* can't be all optimistic */ if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) { - printk(KERN_WARNING "mlx5: legacy pedit isn't offloaded\n"); + netdev_warn(priv->netdev, "legacy pedit isn't offloaded\n"); goto out_err; } if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) { - printk(KERN_WARNING "mlx5: pedit cmd %d isn't offloaded\n", cmd); + netdev_warn(priv->netdev, "pedit cmd %d isn't offloaded\n", cmd); goto out_err; } @@ -1793,8 +1861,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { cmd_masks = &masks[cmd]; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { - printk(KERN_WARNING "mlx5: attempt to offload an unsupported field (cmd %d)\n", - cmd); + netdev_warn(priv->netdev, "attempt to offload an unsupported field (cmd %d)\n", cmd); print_hex_dump(KERN_WARNING, "mask: ", DUMP_PREFIX_ADDRESS, 16, 1, cmd_masks, sizeof(zero_masks), true); err = -EOPNOTSUPP; @@ -1917,21 +1984,21 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, struct mlx5_nic_flow_attr *attr = flow->nic_attr; const struct tc_action *a; LIST_HEAD(actions); + u32 action = 0; int err; if (!tcf_exts_has_actions(exts)) return -EINVAL; attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; - attr->action = 0; tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { if (is_tcf_gact_shot(a)) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP; + action |= MLX5_FLOW_CONTEXT_ACTION_DROP; if (MLX5_CAP_FLOWTABLE(priv->mdev, flow_table_properties_nic_receive.flow_counter)) - attr->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; continue; } @@ -1941,13 +2008,13 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, if (err) return err; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; continue; } if (is_tcf_csum(a)) { - if (csum_offload_supported(priv, attr->action, + if (csum_offload_supported(priv, action, tcf_csum_update_flags(a))) continue; @@ -1961,8 +2028,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, same_hw_devs(priv, netdev_priv(peer_dev))) { parse_attr->mirred_ifindex = peer_dev->ifindex; flow->flags |= MLX5E_TC_FLOW_HAIRPIN; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; } else { netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", peer_dev->name); @@ -1981,13 +2048,14 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } attr->flow_tag = mark; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; continue; } return -EINVAL; } + attr->action = action; if (!actions_match_supported(priv, exts, parse_attr, flow)) return -EOPNOTSUPP; @@ -2044,6 +2112,20 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, return 0; } +static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, + struct net_device *peer_netdev) +{ + struct mlx5e_priv *peer_priv; + + peer_priv = netdev_priv(peer_netdev); + + return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) && + (priv->netdev->netdev_ops == peer_netdev->netdev_ops) && + same_hw_devs(priv, peer_priv) && + MLX5_VPORT_MANAGER(peer_priv->mdev) && + (peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS)); +} + static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct net_device **out_dev, @@ -2459,60 +2541,71 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, const struct tc_action *a; LIST_HEAD(actions); bool encap = false; - int err = 0; + u32 action = 0; if (!tcf_exts_has_actions(exts)) return -EINVAL; - memset(attr, 0, sizeof(*attr)); attr->in_rep = rpriv->rep; + attr->in_mdev = priv->mdev; tcf_exts_to_list(exts, &actions); list_for_each_entry(a, &actions, list) { if (is_tcf_gact_shot(a)) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; continue; } if (is_tcf_pedit(a)) { + int err; + err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB, parse_attr); if (err) return err; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + attr->mirror_count = attr->out_count; continue; } if (is_tcf_csum(a)) { - if (csum_offload_supported(priv, attr->action, + if (csum_offload_supported(priv, action, tcf_csum_update_flags(a))) continue; return -EOPNOTSUPP; } - if (is_tcf_mirred_egress_redirect(a)) { - struct net_device *out_dev; + if (is_tcf_mirred_egress_redirect(a) || is_tcf_mirred_egress_mirror(a)) { struct mlx5e_priv *out_priv; + struct net_device *out_dev; out_dev = tcf_mirred_dev(a); + if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { + pr_err("can't support more than %d output ports, can't offload forwarding\n", + attr->out_count); + return -EOPNOTSUPP; + } + if (switchdev_port_same_parent_id(priv->netdev, - out_dev)) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + out_dev) || + is_merged_eswitch_dev(priv, out_dev)) { + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; out_priv = netdev_priv(out_dev); rpriv = out_priv->ppriv; - attr->out_rep = rpriv->rep; + attr->out_rep[attr->out_count] = rpriv->rep; + attr->out_mdev[attr->out_count++] = out_priv->mdev; } else if (encap) { parse_attr->mirred_ifindex = out_dev->ifindex; parse_attr->tun_info = *info; attr->parse_attr = parse_attr; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP | + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; /* attr->out_rep is resolved when we handle encap */ } else { pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", @@ -2528,14 +2621,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, encap = true; else return -EOPNOTSUPP; + attr->mirror_count = attr->out_count; continue; } if (is_tcf_vlan(a)) { if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; } else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; + action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; attr->vlan_vid = tcf_vlan_push_vid(a); if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) { attr->vlan_prio = tcf_vlan_push_prio(a); @@ -2549,38 +2643,84 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } else { /* action is TCA_VLAN_ACT_MODIFY */ return -EOPNOTSUPP; } + attr->mirror_count = attr->out_count; continue; } if (is_tcf_tunnel_release(a)) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; + action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; continue; } return -EINVAL; } + attr->action = action; if (!actions_match_supported(priv, exts, parse_attr, flow)) return -EOPNOTSUPP; - return err; + if (attr->out_count > 1 && !mlx5_esw_has_fwd_fdb(priv->mdev)) { + netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n"); + return -EOPNOTSUPP; + } + + return 0; +} + +static void get_flags(int flags, u8 *flow_flags) +{ + u8 __flow_flags = 0; + + if (flags & MLX5E_TC_INGRESS) + __flow_flags |= MLX5E_TC_FLOW_INGRESS; + if (flags & MLX5E_TC_EGRESS) + __flow_flags |= MLX5E_TC_FLOW_EGRESS; + + *flow_flags = __flow_flags; +} + +static const struct rhashtable_params tc_ht_params = { + .head_offset = offsetof(struct mlx5e_tc_flow, node), + .key_offset = offsetof(struct mlx5e_tc_flow, cookie), + .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie), + .automatic_shrinking = true, +}; + +static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_rep_priv *uplink_rpriv; + + if (MLX5_VPORT_MANAGER(priv->mdev) && esw->mode == SRIOV_OFFLOADS) { + uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + return &uplink_rpriv->tc_ht; + } else + return &priv->fs.tc.ht; } int mlx5e_configure_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f) + struct tc_cls_flower_offload *f, int flags) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5e_tc_table *tc = &priv->fs.tc; + struct rhashtable *tc_ht = get_tc_ht(priv); struct mlx5e_tc_flow *flow; int attr_size, err = 0; u8 flow_flags = 0; + get_flags(flags, &flow_flags); + + flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + if (flow) { + netdev_warn_once(priv->netdev, "flow cookie %lx already exists, ignoring\n", f->cookie); + return 0; + } + if (esw && esw->mode == SRIOV_OFFLOADS) { - flow_flags = MLX5E_TC_FLOW_ESWITCH; + flow_flags |= MLX5E_TC_FLOW_ESWITCH; attr_size = sizeof(struct mlx5_esw_flow_attr); } else { - flow_flags = MLX5E_TC_FLOW_NIC; + flow_flags |= MLX5E_TC_FLOW_NIC; attr_size = sizeof(struct mlx5_nic_flow_attr); } @@ -2593,6 +2733,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, flow->cookie = f->cookie; flow->flags = flow_flags; + flow->priv = priv; err = parse_cls_flower(priv, flow, &parse_attr->spec, f); if (err < 0) @@ -2602,16 +2743,16 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow); if (err < 0) goto err_free; - flow->rule = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow); } else { err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow); if (err < 0) goto err_free; - flow->rule = mlx5e_tc_add_nic_flow(priv, parse_attr, flow); + flow->rule[0] = mlx5e_tc_add_nic_flow(priv, parse_attr, flow); } - if (IS_ERR(flow->rule)) { - err = PTR_ERR(flow->rule); + if (IS_ERR(flow->rule[0])) { + err = PTR_ERR(flow->rule[0]); if (err != -EAGAIN) goto err_free; } @@ -2623,8 +2764,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, !(flow->esw_attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP)) kvfree(parse_attr); - err = rhashtable_insert_fast(&tc->ht, &flow->node, - tc->ht_params); + err = rhashtable_insert_fast(tc_ht, &flow->node, tc_ht_params); if (err) { mlx5e_tc_del_flow(priv, flow); kfree(flow); @@ -2638,18 +2778,28 @@ err_free: return err; } +#define DIRECTION_MASK (MLX5E_TC_INGRESS | MLX5E_TC_EGRESS) +#define FLOW_DIRECTION_MASK (MLX5E_TC_FLOW_INGRESS | MLX5E_TC_FLOW_EGRESS) + +static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags) +{ + if ((flow->flags & FLOW_DIRECTION_MASK) == (flags & DIRECTION_MASK)) + return true; + + return false; +} + int mlx5e_delete_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f) + struct tc_cls_flower_offload *f, int flags) { + struct rhashtable *tc_ht = get_tc_ht(priv); struct mlx5e_tc_flow *flow; - struct mlx5e_tc_table *tc = &priv->fs.tc; - flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, - tc->ht_params); - if (!flow) + flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + if (!flow || !same_flow_direction(flow, flags)) return -EINVAL; - rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); + rhashtable_remove_fast(tc_ht, &flow->node, tc_ht_params); mlx5e_tc_del_flow(priv, flow); @@ -2659,24 +2809,23 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv, } int mlx5e_stats_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f) + struct tc_cls_flower_offload *f, int flags) { - struct mlx5e_tc_table *tc = &priv->fs.tc; + struct rhashtable *tc_ht = get_tc_ht(priv); struct mlx5e_tc_flow *flow; struct mlx5_fc *counter; u64 bytes; u64 packets; u64 lastuse; - flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, - tc->ht_params); - if (!flow) + flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + if (!flow || !same_flow_direction(flow, flags)) return -EINVAL; if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED)) return 0; - counter = mlx5_flow_rule_counter(flow->rule); + counter = mlx5_flow_rule_counter(flow->rule[0]); if (!counter) return 0; @@ -2687,41 +2836,50 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, return 0; } -static const struct rhashtable_params mlx5e_tc_flow_ht_params = { - .head_offset = offsetof(struct mlx5e_tc_flow, node), - .key_offset = offsetof(struct mlx5e_tc_flow, cookie), - .key_len = sizeof(((struct mlx5e_tc_flow *)0)->cookie), - .automatic_shrinking = true, -}; - -int mlx5e_tc_init(struct mlx5e_priv *priv) +int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; hash_init(tc->mod_hdr_tbl); hash_init(tc->hairpin_tbl); - tc->ht_params = mlx5e_tc_flow_ht_params; - return rhashtable_init(&tc->ht, &tc->ht_params); + return rhashtable_init(&tc->ht, &tc_ht_params); } static void _mlx5e_tc_del_flow(void *ptr, void *arg) { struct mlx5e_tc_flow *flow = ptr; - struct mlx5e_priv *priv = arg; + struct mlx5e_priv *priv = flow->priv; mlx5e_tc_del_flow(priv, flow); kfree(flow); } -void mlx5e_tc_cleanup(struct mlx5e_priv *priv) +void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = &priv->fs.tc; - rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, priv); + rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL); if (!IS_ERR_OR_NULL(tc->t)) { mlx5_destroy_flow_table(tc->t); tc->t = NULL; } } + +int mlx5e_tc_esw_init(struct rhashtable *tc_ht) +{ + return rhashtable_init(tc_ht, &tc_ht_params); +} + +void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) +{ + rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); +} + +int mlx5e_tc_num_filters(struct mlx5e_priv *priv) +{ + struct rhashtable *tc_ht = get_tc_ht(priv); + + return atomic_read(&tc_ht->nelems); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index c14c263a739bd..49436bf3b80a4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -38,16 +38,26 @@ #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff #ifdef CONFIG_MLX5_ESWITCH -int mlx5e_tc_init(struct mlx5e_priv *priv); -void mlx5e_tc_cleanup(struct mlx5e_priv *priv); + +enum { + MLX5E_TC_INGRESS = BIT(0), + MLX5E_TC_EGRESS = BIT(1), + MLX5E_TC_LAST_EXPORTED_BIT = 1, +}; + +int mlx5e_tc_nic_init(struct mlx5e_priv *priv); +void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv); + +int mlx5e_tc_esw_init(struct rhashtable *tc_ht); +void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht); int mlx5e_configure_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f); + struct tc_cls_flower_offload *f, int flags); int mlx5e_delete_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f); + struct tc_cls_flower_offload *f, int flags); int mlx5e_stats_flower(struct mlx5e_priv *priv, - struct tc_cls_flower_offload *f); + struct tc_cls_flower_offload *f, int flags); struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, @@ -58,14 +68,11 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, struct mlx5e_neigh_hash_entry; void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); -static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) -{ - return atomic_read(&priv->fs.tc.ht.nelems); -} +int mlx5e_tc_num_filters(struct mlx5e_priv *priv); #else /* CONFIG_MLX5_ESWITCH */ -static inline int mlx5e_tc_init(struct mlx5e_priv *priv) { return 0; } -static inline void mlx5e_tc_cleanup(struct mlx5e_priv *priv) {} +static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; } +static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {} static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5532aa3675c75..f29deb44bf3b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -35,12 +35,21 @@ #include <net/dsfield.h> #include "en.h" #include "ipoib/ipoib.h" -#include "en_accel/ipsec_rxtx.h" +#include "en_accel/en_accel.h" #include "lib/clock.h" #define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS + +#ifndef CONFIG_MLX5_EN_TLS #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) +#else +/* TLS offload requires MLX5E_SQ_STOP_ROOM to have + * enough room for a resync SKB, a normal SKB and a NOP + */ +#define MLX5E_SQ_STOP_ROOM (2 * MLX5_SEND_WQE_MAX_WQEBBS +\ + MLX5E_SQ_NOPS_ROOM) +#endif static inline void mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) @@ -179,28 +188,16 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, return min_t(u16, hlen, skb_headlen(skb)); } -static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data, - unsigned int *skb_len, - unsigned int len) -{ - *skb_len -= len; - *skb_data += len; -} - -static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs, - unsigned char **skb_data, - unsigned int *skb_len) +static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) { struct vlan_ethhdr *vhdr = (struct vlan_ethhdr *)start; int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - memcpy(vhdr, *skb_data, cpy1_sz); - mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy1_sz); + memcpy(vhdr, skb->data, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); - memcpy(&vhdr->h_vlan_encapsulated_proto, *skb_data, cpy2_sz); - mlx5e_tx_skb_pull_inline(skb_data, skb_len, cpy2_sz); + memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); } static inline void @@ -211,34 +208,31 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct if (skb->encapsulation) { eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM | MLX5_ETH_WQE_L4_INNER_CSUM; - sq->stats.csum_partial_inner++; + sq->stats->csum_partial_inner++; } else { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; - sq->stats.csum_partial++; + sq->stats->csum_partial++; } } else - sq->stats.csum_none++; + sq->stats->csum_none++; } static inline u16 -mlx5e_txwqe_build_eseg_gso(struct mlx5e_txqsq *sq, struct sk_buff *skb, - struct mlx5_wqe_eth_seg *eseg, unsigned int *num_bytes) +mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb) { + struct mlx5e_sq_stats *stats = sq->stats; u16 ihs; - eseg->mss = cpu_to_be16(skb_shinfo(skb)->gso_size); - if (skb->encapsulation) { ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb); - sq->stats.tso_inner_packets++; - sq->stats.tso_inner_bytes += skb->len - ihs; + stats->tso_inner_packets++; + stats->tso_inner_bytes += skb->len - ihs; } else { ihs = skb_transport_offset(skb) + tcp_hdrlen(skb); - sq->stats.tso_packets++; - sq->stats.tso_bytes += skb->len - ihs; + stats->tso_packets++; + stats->tso_bytes += skb->len - ihs; } - *num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; return ihs; } @@ -291,17 +285,34 @@ dma_unmap_wqe_err: return -ENOMEM; } +static inline void mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, + struct mlx5_wq_cyc *wq, + u16 pi, u16 frag_pi) +{ + struct mlx5e_tx_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi]; + u8 nnops = mlx5_wq_cyc_get_frag_size(wq) - frag_pi; + + edge_wi = wi + nnops; + + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->skb = NULL; + wi->num_wqebbs = 1; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } + sq->stats->nop += nnops; +} + static inline void mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, - u8 opcode, u16 ds_cnt, u32 num_bytes, u8 num_dma, + u8 opcode, u16 ds_cnt, u8 num_wqebbs, u32 num_bytes, u8 num_dma, struct mlx5e_tx_wqe_info *wi, struct mlx5_wqe_ctrl_seg *cseg) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi; wi->num_bytes = num_bytes; wi->num_dma = num_dma; - wi->num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); + wi->num_wqebbs = num_wqebbs; wi->skb = skb; cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | opcode); @@ -315,84 +326,108 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, sq->pc += wi->num_wqebbs; if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, MLX5E_SQ_STOP_ROOM))) { netif_tx_stop_queue(sq->txq); - sq->stats.stopped++; + sq->stats->stopped++; } if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); - - /* fill sq edge with nops to avoid wqe wrap around */ - while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { - sq->db.wqe_info[pi].skb = NULL; - mlx5e_post_nop(wq, sq->sqn, &sq->pc); - sq->stats.nop++; - } } -static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, - struct mlx5e_tx_wqe *wqe, u16 pi) -{ - struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; +#define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) - struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; - struct mlx5_wqe_eth_seg *eseg = &wqe->eth; +netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe *wqe, u16 pi) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + struct mlx5_wqe_ctrl_seg *cseg; + struct mlx5_wqe_eth_seg *eseg; + struct mlx5_wqe_data_seg *dseg; + struct mlx5e_tx_wqe_info *wi; - unsigned char *skb_data = skb->data; - unsigned int skb_len = skb->len; - u8 opcode = MLX5_OPCODE_SEND; - unsigned int num_bytes; + struct mlx5e_sq_stats *stats = sq->stats; + u16 ds_cnt, ds_cnt_inl = 0; + u16 headlen, ihs, frag_pi; + u8 num_wqebbs, opcode; + u32 num_bytes; int num_dma; - u16 headlen; - u16 ds_cnt; - u16 ihs; - - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + __be16 mss; + /* Calc ihs and ds cnt, no writes to wqe yet */ + ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; if (skb_is_gso(skb)) { - opcode = MLX5_OPCODE_LSO; - ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes); - sq->stats.packets += skb_shinfo(skb)->gso_segs; + opcode = MLX5_OPCODE_LSO; + mss = cpu_to_be16(skb_shinfo(skb)->gso_size); + ihs = mlx5e_tx_get_gso_ihs(sq, skb); + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; + stats->packets += skb_shinfo(skb)->gso_segs; } else { - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + opcode = MLX5_OPCODE_SEND; + mss = 0; + ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); - sq->stats.packets++; + stats->packets++; } - sq->stats.bytes += num_bytes; - sq->stats.xmit_more += skb->xmit_more; - ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; + stats->bytes += num_bytes; + stats->xmit_more += skb->xmit_more; + + headlen = skb->len - ihs - skb->data_len; + ds_cnt += !!headlen; + ds_cnt += skb_shinfo(skb)->nr_frags; + + if (ihs) { + ihs += !!skb_vlan_tag_present(skb) * VLAN_HLEN; + + ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS); + ds_cnt += ds_cnt_inl; + } + + num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); + frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc); + if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) { + mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi); + mlx5e_sq_fetch_wqe(sq, &wqe, &pi); + } + + /* fill wqe */ + wi = &sq->db.wqe_info[pi]; + cseg = &wqe->ctrl; + eseg = &wqe->eth; + dseg = wqe->data; + + mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + + eseg->mss = mss; + if (ihs) { + eseg->inline_hdr.sz = cpu_to_be16(ihs); if (skb_vlan_tag_present(skb)) { - mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs, &skb_data, &skb_len); - ihs += VLAN_HLEN; - sq->stats.added_vlan_packets++; + ihs -= VLAN_HLEN; + mlx5e_insert_vlan(eseg->inline_hdr.start, skb, ihs); + stats->added_vlan_packets++; } else { - memcpy(eseg->inline_hdr.start, skb_data, ihs); - mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); + memcpy(eseg->inline_hdr.start, skb->data, ihs); } - eseg->inline_hdr.sz = cpu_to_be16(ihs); - ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS); + dseg += ds_cnt_inl; } else if (skb_vlan_tag_present(skb)) { eseg->insert.type = cpu_to_be16(MLX5_ETH_WQE_INSERT_VLAN); if (skb->vlan_proto == cpu_to_be16(ETH_P_8021AD)) eseg->insert.type |= cpu_to_be16(MLX5_ETH_WQE_SVLAN); eseg->insert.vlan_tci = cpu_to_be16(skb_vlan_tag_get(skb)); - sq->stats.added_vlan_packets++; + stats->added_vlan_packets++; } - headlen = skb_len - skb->data_len; - num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, - (struct mlx5_wqe_data_seg *)cseg + ds_cnt); + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg); if (unlikely(num_dma < 0)) goto err_drop; - mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, - num_bytes, num_dma, wi, cseg); + mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes, + num_dma, wi, cseg); return NETDEV_TX_OK; err_drop: - sq->stats.dropped++; + stats->dropped++; dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -401,21 +436,19 @@ err_drop: netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)]; - struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = sq->pc & wq->sz_m1; - struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + struct mlx5e_tx_wqe *wqe; + struct mlx5e_txqsq *sq; + u16 pi; - memset(wqe, 0, sizeof(*wqe)); + sq = priv->txq2sq[skb_get_queue_mapping(skb)]; + mlx5e_sq_fetch_wqe(sq, &wqe, &pi); -#ifdef CONFIG_MLX5_EN_IPSEC - if (sq->state & BIT(MLX5E_SQ_STATE_IPSEC)) { - skb = mlx5e_ipsec_handle_tx_skb(dev, wqe, skb); - if (unlikely(!skb)) - return NETDEV_TX_OK; - } +#ifdef CONFIG_MLX5_ACCEL + /* might send skbs and update wqe and pi */ + skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi); + if (unlikely(!skb)) + return NETDEV_TX_OK; #endif - return mlx5e_sq_xmit(sq, skb, wqe, pi); } @@ -443,7 +476,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_txqsq, cq); - if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; cqe = mlx5_cqwq_get_cqe(&cq->wq); @@ -478,7 +511,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) queue_work(cq->channel->priv->wq, &sq->recover.recover_work); } - sq->stats.cqe_err++; + sq->stats->cqe_err++; } do { @@ -489,7 +522,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) last_wqe = (sqcc == wqe_counter); - ci = sqcc & sq->wq.sz_m1; + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc); wi = &sq->db.wqe_info[ci]; skb = wi->skb; @@ -538,7 +571,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) MLX5E_SQ_STOP_ROOM) && !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { netif_tx_wake_queue(sq->txq); - sq->stats.wake++; + sq->stats->wake++; } return (i == MLX5E_TX_CQ_POLL_BUDGET); @@ -552,7 +585,7 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) int i; while (sq->cc != sq->pc) { - ci = sq->cc & sq->wq.sz_m1; + ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc); wi = &sq->db.wqe_info[ci]; skb = wi->skb; @@ -574,18 +607,6 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq) } #ifdef CONFIG_MLX5_CORE_IPOIB - -struct mlx5_wqe_eth_pad { - u8 rsvd0[16]; -}; - -struct mlx5i_tx_wqe { - struct mlx5_wqe_ctrl_seg ctrl; - struct mlx5_wqe_datagram_seg datagram; - struct mlx5_wqe_eth_pad pad; - struct mlx5_wqe_eth_seg eth; -}; - static inline void mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey, struct mlx5_wqe_datagram_seg *dseg) @@ -598,67 +619,92 @@ mlx5i_txwqe_build_datagram(struct mlx5_av *av, u32 dqpn, u32 dqkey, netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey) { - struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = sq->pc & wq->sz_m1; - struct mlx5i_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; - - struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl; - struct mlx5_wqe_datagram_seg *datagram = &wqe->datagram; - struct mlx5_wqe_eth_seg *eseg = &wqe->eth; - - unsigned char *skb_data = skb->data; - unsigned int skb_len = skb->len; - u8 opcode = MLX5_OPCODE_SEND; - unsigned int num_bytes; - int num_dma; - u16 headlen; - u16 ds_cnt; - u16 ihs; - - memset(wqe, 0, sizeof(*wqe)); + struct mlx5_wq_cyc *wq = &sq->wq; + struct mlx5i_tx_wqe *wqe; - mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); + struct mlx5_wqe_datagram_seg *datagram; + struct mlx5_wqe_ctrl_seg *cseg; + struct mlx5_wqe_eth_seg *eseg; + struct mlx5_wqe_data_seg *dseg; + struct mlx5e_tx_wqe_info *wi; - mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + struct mlx5e_sq_stats *stats = sq->stats; + u16 headlen, ihs, pi, frag_pi; + u16 ds_cnt, ds_cnt_inl = 0; + u8 num_wqebbs, opcode; + u32 num_bytes; + int num_dma; + __be16 mss; + /* Calc ihs and ds cnt, no writes to wqe yet */ + ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; if (skb_is_gso(skb)) { - opcode = MLX5_OPCODE_LSO; - ihs = mlx5e_txwqe_build_eseg_gso(sq, skb, eseg, &num_bytes); - sq->stats.packets += skb_shinfo(skb)->gso_segs; + opcode = MLX5_OPCODE_LSO; + mss = cpu_to_be16(skb_shinfo(skb)->gso_size); + ihs = mlx5e_tx_get_gso_ihs(sq, skb); + num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; + stats->packets += skb_shinfo(skb)->gso_segs; } else { - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + opcode = MLX5_OPCODE_SEND; + mss = 0; + ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); - sq->stats.packets++; + stats->packets++; } - sq->stats.bytes += num_bytes; - sq->stats.xmit_more += skb->xmit_more; + stats->bytes += num_bytes; + stats->xmit_more += skb->xmit_more; + + headlen = skb->len - ihs - skb->data_len; + ds_cnt += !!headlen; + ds_cnt += skb_shinfo(skb)->nr_frags; + + if (ihs) { + ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS); + ds_cnt += ds_cnt_inl; + } + + num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); + frag_pi = mlx5_wq_cyc_ctr2fragix(wq, sq->pc); + if (unlikely(frag_pi + num_wqebbs > mlx5_wq_cyc_get_frag_size(wq))) { + pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + mlx5e_fill_sq_frag_edge(sq, wq, pi, frag_pi); + } + + mlx5i_sq_fetch_wqe(sq, &wqe, &pi); + + /* fill wqe */ + wi = &sq->db.wqe_info[pi]; + cseg = &wqe->ctrl; + datagram = &wqe->datagram; + eseg = &wqe->eth; + dseg = wqe->data; + + mlx5i_txwqe_build_datagram(av, dqpn, dqkey, datagram); + + mlx5e_txwqe_build_eseg_csum(sq, skb, eseg); + + eseg->mss = mss; - ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS; if (ihs) { - memcpy(eseg->inline_hdr.start, skb_data, ihs); - mlx5e_tx_skb_pull_inline(&skb_data, &skb_len, ihs); + memcpy(eseg->inline_hdr.start, skb->data, ihs); eseg->inline_hdr.sz = cpu_to_be16(ihs); - ds_cnt += DIV_ROUND_UP(ihs - sizeof(eseg->inline_hdr.start), MLX5_SEND_WQE_DS); + dseg += ds_cnt_inl; } - headlen = skb_len - skb->data_len; - num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, - (struct mlx5_wqe_data_seg *)cseg + ds_cnt); + num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb->data + ihs, headlen, dseg); if (unlikely(num_dma < 0)) goto err_drop; - mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, - num_bytes, num_dma, wi, cseg); + mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes, + num_dma, wi, cseg); return NETDEV_TX_OK; err_drop: - sq->stats.dropped++; + stats->dropped++; dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index f292bb346985b..1b17f682693b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -44,6 +44,32 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) return cpumask_test_cpu(current_cpu, aff); } +static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) +{ + struct mlx5e_sq_stats *stats = sq->stats; + struct net_dim_sample dim_sample; + + if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state))) + return; + + net_dim_sample(sq->cq.event_ctr, stats->packets, stats->bytes, + &dim_sample); + net_dim(&sq->dim, dim_sample); +} + +static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) +{ + struct mlx5e_rq_stats *stats = rq->stats; + struct net_dim_sample dim_sample; + + if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state))) + return; + + net_dim_sample(rq->cq.event_ctr, stats->packets, stats->bytes, + &dim_sample); + net_dim(&rq->dim, dim_sample); +} + int mlx5e_napi_poll(struct napi_struct *napi, int budget) { struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, @@ -75,18 +101,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (unlikely(!napi_complete_done(napi, work_done))) return work_done; - for (i = 0; i < c->num_tc; i++) + for (i = 0; i < c->num_tc; i++) { + mlx5e_handle_tx_dim(&c->sq[i]); mlx5e_cq_arm(&c->sq[i].cq); - - if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM)) { - struct net_dim_sample dim_sample; - net_dim_sample(c->rq.cq.event_ctr, - c->rq.stats.packets, - c->rq.stats.bytes, - &dim_sample); - net_dim(&c->rq.dim, dim_sample); } + mlx5e_handle_rx_dim(&c->rq); + mlx5e_cq_arm(&c->rq.cq); mlx5e_cq_arm(&c->icosq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1814f803bd2cb..406c23862f5f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -144,6 +144,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_GPIO_EVENT"; case MLX5_EVENT_TYPE_PORT_MODULE_EVENT: return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT"; + case MLX5_EVENT_TYPE_TEMP_WARN_EVENT: + return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT"; case MLX5_EVENT_TYPE_REMOTE_CONFIG: return "MLX5_EVENT_TYPE_REMOTE_CONFIG"; case MLX5_EVENT_TYPE_DB_BF_CONGESTION: @@ -162,6 +164,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE"; case MLX5_EVENT_TYPE_FPGA_ERROR: return "MLX5_EVENT_TYPE_FPGA_ERROR"; + case MLX5_EVENT_TYPE_FPGA_QP_ERROR: + return "MLX5_EVENT_TYPE_FPGA_QP_ERROR"; case MLX5_EVENT_TYPE_GENERAL_EVENT: return "MLX5_EVENT_TYPE_GENERAL_EVENT"; default: @@ -396,6 +400,20 @@ static void general_event_handler(struct mlx5_core_dev *dev, } } +static void mlx5_temp_warning_event(struct mlx5_core_dev *dev, + struct mlx5_eqe *eqe) +{ + u64 value_lsb; + u64 value_msb; + + value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb); + value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb); + + mlx5_core_warn(dev, + "High temperature on sensors with bit set %llx %llx", + value_msb, value_lsb); +} + /* caller must eventually call mlx5_cq_put on the returned cq */ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn) { @@ -547,9 +565,14 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_FPGA_ERROR: + case MLX5_EVENT_TYPE_FPGA_QP_ERROR: mlx5_fpga_event(dev, eqe->type, &eqe->data.raw); break; + case MLX5_EVENT_TYPE_TEMP_WARN_EVENT: + mlx5_temp_warning_event(dev, eqe); + break; + case MLX5_EVENT_TYPE_GENERAL_EVENT: general_event_handler(dev, eqe); break; @@ -822,10 +845,13 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) async_event_mask |= (1ull << MLX5_EVENT_TYPE_PPS_EVENT); if (MLX5_CAP_GEN(dev, fpga)) - async_event_mask |= (1ull << MLX5_EVENT_TYPE_FPGA_ERROR); + async_event_mask |= (1ull << MLX5_EVENT_TYPE_FPGA_ERROR) | + (1ull << MLX5_EVENT_TYPE_FPGA_QP_ERROR); if (MLX5_CAP_GEN_MAX(dev, dct)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_DCT_DRAINED); + if (MLX5_CAP_GEN(dev, temp_warn_event)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT); err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD, MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1352d13eedb3c..6cab1dd66d1b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -192,7 +192,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, } dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest.vport_num = vport; + dest.vport.num = vport; esw_debug(esw->dev, "\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n", @@ -200,7 +200,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, spec->match_criteria_enable = match_header; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = - mlx5_add_flow_rules(esw->fdb_table.fdb, spec, + mlx5_add_flow_rules(esw->fdb_table.legacy.fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { esw_warn(esw->dev, @@ -282,7 +282,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) esw_warn(dev, "Failed to create FDB Table err %d\n", err); goto out; } - esw->fdb_table.fdb = fdb; + esw->fdb_table.legacy.fdb = fdb; /* Addresses group : Full match unicast/multicast addresses */ MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, @@ -343,9 +343,9 @@ out: mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); esw->fdb_table.legacy.addr_grp = NULL; } - if (!IS_ERR_OR_NULL(esw->fdb_table.fdb)) { - mlx5_destroy_flow_table(esw->fdb_table.fdb); - esw->fdb_table.fdb = NULL; + if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.fdb)) { + mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb); + esw->fdb_table.legacy.fdb = NULL; } } @@ -355,15 +355,15 @@ out: static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw) { - if (!esw->fdb_table.fdb) + if (!esw->fdb_table.legacy.fdb) return; esw_debug(esw->dev, "Destroy FDB Table\n"); mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp); mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp); mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp); - mlx5_destroy_flow_table(esw->fdb_table.fdb); - esw->fdb_table.fdb = NULL; + mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb); + esw->fdb_table.legacy.fdb = NULL; esw->fdb_table.legacy.addr_grp = NULL; esw->fdb_table.legacy.allmulti_grp = NULL; esw->fdb_table.legacy.promisc_grp = NULL; @@ -396,7 +396,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) fdb_add: /* SRIOV is enabled: Forward UC MAC to vport */ - if (esw->fdb_table.fdb && esw->mode == SRIOV_LEGACY) + if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY) vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport); esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", @@ -486,7 +486,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) u8 *mac = vaddr->node.addr; u32 vport = vaddr->vport; - if (!esw->fdb_table.fdb) + if (!esw->fdb_table.legacy.fdb) return 0; esw_mc = l2addr_hash_find(hash, mac, struct esw_mc_addr); @@ -526,7 +526,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) u8 *mac = vaddr->node.addr; u32 vport = vaddr->vport; - if (!esw->fdb_table.fdb) + if (!esw->fdb_table.legacy.fdb) return 0; esw_mc = l2addr_hash_find(hash, mac, struct esw_mc_addr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 4cd773fa55e33..b174da2884c56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -55,6 +55,9 @@ #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ min_t(u32, max_t(u32, (rate) / (divider), MLX5_MIN_BW_SHARE), limit) +#define mlx5_esw_has_fwd_fdb(dev) \ + MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table) + struct vport_ingress { struct mlx5_flow_table *acl; struct mlx5_flow_group *allow_untagged_spoofchk_grp; @@ -117,16 +120,18 @@ struct mlx5_vport { }; struct mlx5_eswitch_fdb { - void *fdb; union { struct legacy_fdb { + struct mlx5_flow_table *fdb; struct mlx5_flow_group *addr_grp; struct mlx5_flow_group *allmulti_grp; struct mlx5_flow_group *promisc_grp; } legacy; struct offloads_fdb { - struct mlx5_flow_table *fdb; + struct mlx5_flow_table *fast_fdb; + struct mlx5_flow_table *fwd_fdb; + struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *miss_grp; struct mlx5_flow_handle *miss_rule_uni; @@ -214,6 +219,10 @@ struct mlx5_flow_handle * mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_esw_flow_attr *attr); +struct mlx5_flow_handle * +mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr); void mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule, @@ -227,9 +236,24 @@ enum { SET_VLAN_INSERT = BIT(1) }; +enum mlx5_flow_match_level { + MLX5_MATCH_NONE = MLX5_INLINE_MODE_NONE, + MLX5_MATCH_L2 = MLX5_INLINE_MODE_L2, + MLX5_MATCH_L3 = MLX5_INLINE_MODE_IP, + MLX5_MATCH_L4 = MLX5_INLINE_MODE_TCP_UDP, +}; + +/* current maximum for flow based vport multicasting */ +#define MLX5_MAX_FLOW_FWD_VPORTS 2 + struct mlx5_esw_flow_attr { struct mlx5_eswitch_rep *in_rep; - struct mlx5_eswitch_rep *out_rep; + struct mlx5_eswitch_rep *out_rep[MLX5_MAX_FLOW_FWD_VPORTS]; + struct mlx5_core_dev *out_mdev[MLX5_MAX_FLOW_FWD_VPORTS]; + struct mlx5_core_dev *in_mdev; + + int mirror_count; + int out_count; int action; __be16 vlan_proto; @@ -238,6 +262,7 @@ struct mlx5_esw_flow_attr { bool vlan_handled; u32 encap_id; u32 mod_hdr_id; + u8 match_level; struct mlx5e_tc_flow_parse_attr *parse_attr; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 35e256eb2f6e4..cecd201f0b73a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -48,16 +48,22 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_esw_flow_attr *attr) { - struct mlx5_flow_destination dest[2] = {}; + struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; struct mlx5_flow_act flow_act = {0}; + struct mlx5_flow_table *ft = NULL; struct mlx5_fc *counter = NULL; struct mlx5_flow_handle *rule; + int j, i = 0; void *misc; - int i = 0; if (esw->mode != SRIOV_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); + if (attr->mirror_count) + ft = esw->fdb_table.offloads.fwd_fdb; + else + ft = esw->fdb_table.offloads.fast_fdb; + flow_act.action = attr->action; /* if per flow vlan pop/push is emulated, don't set that into the firmware */ if (!mlx5_eswitch_vlan_actions_supported(esw->dev)) @@ -70,9 +76,14 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { - dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest[i].vport_num = attr->out_rep->vport; - i++; + for (j = attr->mirror_count; j < attr->out_count; j++) { + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest[i].vport.num = attr->out_rep[j]->vport; + dest[i].vport.vhca_id = + MLX5_CAP_GEN(attr->out_mdev[j], vhca_id); + dest[i].vport.vhca_id_valid = !!MLX5_CAP_ESW(esw->dev, merged_eswitch); + i++; + } } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(esw->dev, true); @@ -88,11 +99,23 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + MLX5_SET(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id, + MLX5_CAP_GEN(attr->in_mdev, vhca_id)); + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + MLX5_SET_TO_ONES(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + + if (attr->match_level == MLX5_MATCH_NONE) + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + else + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | + MLX5_MATCH_MISC_PARAMETERS; - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS; if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; @@ -102,8 +125,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) flow_act.encap_id = attr->encap_id; - rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb, - spec, &flow_act, dest, i); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, i); if (IS_ERR(rule)) goto err_add_rule; else @@ -117,6 +139,57 @@ err_counter_alloc: return rule; } +struct mlx5_flow_handle * +mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr) +{ + struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {}; + struct mlx5_flow_act flow_act = {0}; + struct mlx5_flow_handle *rule; + void *misc; + int i; + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + for (i = 0; i < attr->mirror_count; i++) { + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest[i].vport.num = attr->out_rep[i]->vport; + dest[i].vport.vhca_id = + MLX5_CAP_GEN(attr->out_mdev[i], vhca_id); + dest[i].vport.vhca_id_valid = !!MLX5_CAP_ESW(esw->dev, merged_eswitch); + } + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest[i].ft = esw->fdb_table.offloads.fwd_fdb, + i++; + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport); + + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + MLX5_SET(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id, + MLX5_CAP_GEN(attr->in_mdev, vhca_id)); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + MLX5_SET_TO_ONES(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + + if (attr->match_level == MLX5_MATCH_NONE) + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + else + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | + MLX5_MATCH_MISC_PARAMETERS; + + rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fast_fdb, spec, &flow_act, dest, i); + + if (!IS_ERR(rule)) + esw->offloads.num_flows++; + + return rule; +} + void mlx5_eswitch_del_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_handle *rule, @@ -156,7 +229,7 @@ esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop) struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL; in_rep = attr->in_rep; - out_rep = attr->out_rep; + out_rep = attr->out_rep[0]; if (push) vport = in_rep; @@ -177,7 +250,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, goto out_notsupp; in_rep = attr->in_rep; - out_rep = attr->out_rep; + out_rep = attr->out_rep[0]; if (push && in_rep->vport == FDB_UPLINK_VPORT) goto out_notsupp; @@ -228,7 +301,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->out_rep->vport == FDB_UPLINK_VPORT) { + if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT) { vport->vlan_refcount++; attr->vlan_handled = true; } @@ -288,7 +361,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->out_rep->vport == FDB_UPLINK_VPORT) + if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT) vport->vlan_refcount--; return 0; @@ -343,10 +416,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest.vport_num = vport; + dest.vport.num = vport; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule)); @@ -387,10 +460,10 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dmac_c[0] = 0x01; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest.vport_num = 0; + dest.vport.num = 0; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); @@ -405,7 +478,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16); dmac_v[0] = 0x01; - flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); @@ -437,7 +510,7 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) if (!root_ns) { esw_warn(dev, "Failed to get FDB flow namespace\n"); err = -EOPNOTSUPP; - goto out; + goto out_namespace; } esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d)*groups(%d))\n", @@ -447,6 +520,9 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) esw_size = min_t(int, max_flow_counter * ESW_OFFLOADS_NUM_GROUPS, 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); + if (mlx5_esw_has_fwd_fdb(dev)) + esw_size >>= 1; + if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) flags |= MLX5_FLOW_TABLE_TUNNEL_EN; @@ -457,17 +533,37 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create Fast path FDB Table err %d\n", err); - goto out; + goto out_namespace; } - esw->fdb_table.fdb = fdb; + esw->fdb_table.offloads.fast_fdb = fdb; -out: + if (!mlx5_esw_has_fwd_fdb(dev)) + goto out_namespace; + + fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH, + esw_size, + ESW_OFFLOADS_NUM_GROUPS, 1, + flags); + if (IS_ERR(fdb)) { + err = PTR_ERR(fdb); + esw_warn(dev, "Failed to create fwd table err %d\n", err); + goto out_ft; + } + esw->fdb_table.offloads.fwd_fdb = fdb; + + return err; + +out_ft: + mlx5_destroy_flow_table(esw->fdb_table.offloads.fast_fdb); +out_namespace: return err; } static void esw_destroy_offloads_fast_fdb_table(struct mlx5_eswitch *esw) { - mlx5_destroy_flow_table(esw->fdb_table.fdb); + if (mlx5_esw_has_fwd_fdb(esw->dev)) + mlx5_destroy_flow_table(esw->fdb_table.offloads.fwd_fdb); + mlx5_destroy_flow_table(esw->fdb_table.offloads.fast_fdb); } #define MAX_PF_SQ 256 @@ -513,7 +609,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err); goto slow_fdb_err; } - esw->fdb_table.offloads.fdb = fdb; + esw->fdb_table.offloads.slow_fdb = fdb; /* create send-to-vport group */ memset(flow_group_in, 0, inlen); @@ -569,9 +665,9 @@ miss_rule_err: miss_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); send_vport_err: - mlx5_destroy_flow_table(esw->fdb_table.offloads.fdb); + mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); slow_fdb_err: - mlx5_destroy_flow_table(esw->fdb_table.fdb); + esw_destroy_offloads_fast_fdb_table(esw); fast_fdb_err: ns_err: kvfree(flow_group_in); @@ -580,7 +676,7 @@ ns_err: static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) { - if (!esw->fdb_table.fdb) + if (!esw->fdb_table.offloads.fast_fdb) return; esw_debug(esw->dev, "Destroy offloads FDB Tables\n"); @@ -589,7 +685,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); - mlx5_destroy_flow_table(esw->fdb_table.offloads.fdb); + mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); esw_destroy_offloads_fast_fdb_table(esw); } @@ -663,7 +759,7 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) esw->offloads.vport_rx_group = g; out: - kfree(flow_group_in); + kvfree(flow_group_in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h index d05233c9b4f6c..eb8b0fe0b4e14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h @@ -35,6 +35,13 @@ #include <linux/mlx5/driver.h> +enum mlx5_fpga_device_id { + MLX5_FPGA_DEVICE_UNKNOWN = 0, + MLX5_FPGA_DEVICE_KU040 = 1, + MLX5_FPGA_DEVICE_KU060 = 2, + MLX5_FPGA_DEVICE_KU060_2 = 3, +}; + enum mlx5_fpga_image { MLX5_FPGA_IMAGE_USER = 0, MLX5_FPGA_IMAGE_FACTORY, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index de7fe087d6fe9..4138a770ed571 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -181,6 +181,7 @@ int mlx5_fpga_conn_send(struct mlx5_fpga_conn *conn, if (!conn->qp.active) return -ENOTCONN; + buf->dma_dir = DMA_TO_DEVICE; err = mlx5_fpga_conn_map_buf(conn, buf); if (err) return err; @@ -255,8 +256,6 @@ static void mlx5_fpga_conn_rq_cqe(struct mlx5_fpga_conn *conn, ix = be16_to_cpu(cqe->wqe_counter) & (conn->qp.rq.size - 1); buf = conn->qp.rq.bufs[ix]; conn->qp.rq.bufs[ix] = NULL; - if (!status) - buf->sg[0].size = be32_to_cpu(cqe->byte_cnt); conn->qp.rq.cc++; if (unlikely(status && (status != MLX5_CQE_SYNDROME_WR_FLUSH_ERR))) @@ -274,6 +273,7 @@ static void mlx5_fpga_conn_rq_cqe(struct mlx5_fpga_conn *conn, return; } + buf->sg[0].size = be32_to_cpu(cqe->byte_cnt); mlx5_fpga_dbg(conn->fdev, "Message with %u bytes received successfully\n", buf->sg[0].size); conn->recv_cb(conn->cb_arg, buf); @@ -454,7 +454,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) } inlen = MLX5_ST_SZ_BYTES(create_cq_in) + - sizeof(u64) * conn->cq.wq_ctrl.frag_buf.npages; + sizeof(u64) * conn->cq.wq_ctrl.buf.npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) { err = -ENOMEM; @@ -469,12 +469,12 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size)); MLX5_SET(cqc, cqc, c_eqn, eqn); MLX5_SET(cqc, cqc, uar_page, fdev->conn_res.uar->index); - MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.frag_buf.page_shift - + MLX5_SET(cqc, cqc, log_page_size, conn->cq.wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, conn->cq.wq_ctrl.db.dma); pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); - mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.frag_buf, pas); + mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.buf, pas); err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen); kvfree(in); @@ -500,7 +500,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) goto out; err_cqwq: - mlx5_cqwq_destroy(&conn->cq.wq_ctrl); + mlx5_wq_destroy(&conn->cq.wq_ctrl); out: return err; } @@ -510,7 +510,7 @@ static void mlx5_fpga_conn_destroy_cq(struct mlx5_fpga_conn *conn) tasklet_disable(&conn->cq.tasklet); tasklet_kill(&conn->cq.tasklet); mlx5_core_destroy_cq(conn->fdev->mdev, &conn->cq.mcq); - mlx5_cqwq_destroy(&conn->cq.wq_ctrl); + mlx5_wq_destroy(&conn->cq.wq_ctrl); } static int mlx5_fpga_conn_create_wq(struct mlx5_fpga_conn *conn, void *qpc) @@ -591,8 +591,8 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn, if (MLX5_CAP_GEN(mdev, cqe_version) == 1) MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); - mlx5_fill_page_array(&conn->qp.wq_ctrl.buf, - (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas)); + mlx5_fill_page_frag_array(&conn->qp.wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(create_qp_in, in, pas)); err = mlx5_core_create_qp(mdev, &conn->qp.mqp, in, inlen); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h index 44bd9eccc711c..634ae10e287b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.h @@ -54,7 +54,7 @@ struct mlx5_fpga_conn { /* CQ */ struct { struct mlx5_cqwq wq; - struct mlx5_frag_wq_ctrl wq_ctrl; + struct mlx5_wq_ctrl wq_ctrl; struct mlx5_core_cq mcq; struct tasklet_struct tasklet; } cq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c index dc8970346521d..436a8136f26ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c @@ -50,6 +50,11 @@ static const char *const mlx5_fpga_error_strings[] = { "Temperature Critical", }; +static const char * const mlx5_fpga_qp_error_strings[] = { + "Null Syndrome", + "Retry Counter Expired", + "RNR Expired", +}; static struct mlx5_fpga_device *mlx5_fpga_device_alloc(void) { struct mlx5_fpga_device *fdev = NULL; @@ -75,6 +80,21 @@ static const char *mlx5_fpga_image_name(enum mlx5_fpga_image image) } } +static const char *mlx5_fpga_device_name(u32 device) +{ + switch (device) { + case MLX5_FPGA_DEVICE_KU040: + return "ku040"; + case MLX5_FPGA_DEVICE_KU060: + return "ku060"; + case MLX5_FPGA_DEVICE_KU060_2: + return "ku060_2"; + case MLX5_FPGA_DEVICE_UNKNOWN: + default: + return "unknown"; + } +} + static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev) { struct mlx5_fpga_query query; @@ -128,8 +148,9 @@ static int mlx5_fpga_device_brb(struct mlx5_fpga_device *fdev) int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) { struct mlx5_fpga_device *fdev = mdev->fpga; - unsigned long flags; unsigned int max_num_qps; + unsigned long flags; + u32 fpga_device_id; int err; if (!fdev) @@ -143,12 +164,23 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev) if (err) goto out; - mlx5_fpga_info(fdev, "device %u; %s image, version %u\n", - MLX5_CAP_FPGA(fdev->mdev, fpga_device), + fpga_device_id = MLX5_CAP_FPGA(fdev->mdev, fpga_device); + mlx5_fpga_info(fdev, "%s:%u; %s image, version %u; SBU %06x:%04x version %d\n", + mlx5_fpga_device_name(fpga_device_id), + fpga_device_id, mlx5_fpga_image_name(fdev->last_oper_image), - MLX5_CAP_FPGA(fdev->mdev, image_version)); + MLX5_CAP_FPGA(fdev->mdev, image_version), + MLX5_CAP_FPGA(fdev->mdev, ieee_vendor_id), + MLX5_CAP_FPGA(fdev->mdev, sandbox_product_id), + MLX5_CAP_FPGA(fdev->mdev, sandbox_product_version)); max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps); + if (!max_num_qps) { + mlx5_fpga_err(fdev, "FPGA reports 0 QPs in SHELL_CAPS\n"); + err = -ENOTSUPP; + goto out; + } + err = mlx5_core_reserve_gids(mdev, max_num_qps); if (err) goto out; @@ -244,23 +276,38 @@ static const char *mlx5_fpga_syndrome_to_string(u8 syndrome) return "Unknown"; } +static const char *mlx5_fpga_qp_syndrome_to_string(u8 syndrome) +{ + if (syndrome < ARRAY_SIZE(mlx5_fpga_qp_error_strings)) + return mlx5_fpga_qp_error_strings[syndrome]; + return "Unknown"; +} + void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data) { struct mlx5_fpga_device *fdev = mdev->fpga; const char *event_name; bool teardown = false; unsigned long flags; + u32 fpga_qpn; u8 syndrome; - if (event != MLX5_EVENT_TYPE_FPGA_ERROR) { + switch (event) { + case MLX5_EVENT_TYPE_FPGA_ERROR: + syndrome = MLX5_GET(fpga_error_event, data, syndrome); + event_name = mlx5_fpga_syndrome_to_string(syndrome); + break; + case MLX5_EVENT_TYPE_FPGA_QP_ERROR: + syndrome = MLX5_GET(fpga_qp_error_event, data, syndrome); + event_name = mlx5_fpga_qp_syndrome_to_string(syndrome); + fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn); + break; + default: mlx5_fpga_warn_ratelimited(fdev, "Unexpected event %u\n", event); return; } - syndrome = MLX5_GET(fpga_error_event, data, syndrome); - event_name = mlx5_fpga_syndrome_to_string(syndrome); - spin_lock_irqsave(&fdev->state_lock, flags); switch (fdev->state) { case MLX5_FPGA_STATUS_SUCCESS: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h index 82405ed847255..3e2355c8df3ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h @@ -53,6 +53,7 @@ struct mlx5_fpga_device { } conn_res; struct mlx5_fpga_ipsec *ipsec; + struct mlx5_fpga_tls *tls; }; #define mlx5_fpga_dbg(__adev, format, ...) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index fad8c2e3804e4..a0433b48e8331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -43,9 +43,6 @@ #include "fpga/sdk.h" #include "fpga/core.h" -#define SBU_QP_QUEUE_SIZE 8 -#define MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC (60 * 1000) - enum mlx5_fpga_ipsec_cmd_status { MLX5_FPGA_IPSEC_CMD_PENDING, MLX5_FPGA_IPSEC_CMD_SEND_FAIL, @@ -256,7 +253,7 @@ static int mlx5_fpga_ipsec_cmd_wait(void *ctx) { struct mlx5_fpga_ipsec_cmd_context *context = ctx; unsigned long timeout = - msecs_to_jiffies(MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC); + msecs_to_jiffies(MLX5_FPGA_CMD_TIMEOUT_MSEC); int res; res = wait_for_completion_timeout(&context->complete, timeout); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h index baa537e54a492..656f96be6e200 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h @@ -41,9 +41,17 @@ * DOC: Innova SDK * This header defines the in-kernel API for Innova FPGA client drivers. */ +#define SBU_QP_QUEUE_SIZE 8 +#define MLX5_FPGA_CMD_TIMEOUT_MSEC (60 * 1000) +/** + * enum mlx5_fpga_access_type - Enumerated the different methods possible for + * accessing the device memory address space + */ enum mlx5_fpga_access_type { + /** Use the slow CX-FPGA I2C bus */ MLX5_FPGA_ACCESS_TYPE_I2C = 0x0, + /** Use the fastest available method */ MLX5_FPGA_ACCESS_TYPE_DONTCARE = 0x0, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c new file mode 100644 index 0000000000000..c9736238604ab --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -0,0 +1,562 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/mlx5/device.h> +#include "fpga/tls.h" +#include "fpga/cmd.h" +#include "fpga/sdk.h" +#include "fpga/core.h" +#include "accel/tls.h" + +struct mlx5_fpga_tls_command_context; + +typedef void (*mlx5_fpga_tls_command_complete) + (struct mlx5_fpga_conn *conn, struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *ctx, + struct mlx5_fpga_dma_buf *resp); + +struct mlx5_fpga_tls_command_context { + struct list_head list; + /* There is no guarantee on the order between the TX completion + * and the command response. + * The TX completion is going to touch cmd->buf even in + * the case of successful transmission. + * So instead of requiring separate allocations for cmd + * and cmd->buf we've decided to use a reference counter + */ + refcount_t ref; + struct mlx5_fpga_dma_buf buf; + mlx5_fpga_tls_command_complete complete; +}; + +static void +mlx5_fpga_tls_put_command_ctx(struct mlx5_fpga_tls_command_context *ctx) +{ + if (refcount_dec_and_test(&ctx->ref)) + kfree(ctx); +} + +static void mlx5_fpga_tls_cmd_complete(struct mlx5_fpga_device *fdev, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_fpga_conn *conn = fdev->tls->conn; + struct mlx5_fpga_tls_command_context *ctx; + struct mlx5_fpga_tls *tls = fdev->tls; + unsigned long flags; + + spin_lock_irqsave(&tls->pending_cmds_lock, flags); + ctx = list_first_entry(&tls->pending_cmds, + struct mlx5_fpga_tls_command_context, list); + list_del(&ctx->list); + spin_unlock_irqrestore(&tls->pending_cmds_lock, flags); + ctx->complete(conn, fdev, ctx, resp); +} + +static void mlx5_fpga_cmd_send_complete(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_dma_buf *buf, + u8 status) +{ + struct mlx5_fpga_tls_command_context *ctx = + container_of(buf, struct mlx5_fpga_tls_command_context, buf); + + mlx5_fpga_tls_put_command_ctx(ctx); + + if (unlikely(status)) + mlx5_fpga_tls_cmd_complete(fdev, NULL); +} + +static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + mlx5_fpga_tls_command_complete complete) +{ + struct mlx5_fpga_tls *tls = fdev->tls; + unsigned long flags; + int ret; + + refcount_set(&cmd->ref, 2); + cmd->complete = complete; + cmd->buf.complete = mlx5_fpga_cmd_send_complete; + + spin_lock_irqsave(&tls->pending_cmds_lock, flags); + /* mlx5_fpga_sbu_conn_sendmsg is called under pending_cmds_lock + * to make sure commands are inserted to the tls->pending_cmds list + * and the command QP in the same order. + */ + ret = mlx5_fpga_sbu_conn_sendmsg(tls->conn, &cmd->buf); + if (likely(!ret)) + list_add_tail(&cmd->list, &tls->pending_cmds); + else + complete(tls->conn, fdev, cmd, NULL); + spin_unlock_irqrestore(&tls->pending_cmds_lock, flags); +} + +/* Start of context identifiers range (inclusive) */ +#define SWID_START 0 +/* End of context identifiers range (exclusive) */ +#define SWID_END BIT(24) + +static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock, + void *ptr) +{ + int ret; + + /* TLS metadata format is 1 byte for syndrome followed + * by 3 bytes of swid (software ID) + * swid must not exceed 3 bytes. + * See tls_rxtx.c:insert_pet() for details + */ + BUILD_BUG_ON((SWID_END - 1) & 0xFF000000); + + idr_preload(GFP_KERNEL); + spin_lock_irq(idr_spinlock); + ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC); + spin_unlock_irq(idr_spinlock); + idr_preload_end(); + + return ret; +} + +static void mlx5_fpga_tls_release_swid(struct idr *idr, + spinlock_t *idr_spinlock, u32 swid) +{ + unsigned long flags; + + spin_lock_irqsave(idr_spinlock, flags); + idr_remove(idr, swid); + spin_unlock_irqrestore(idr_spinlock, flags); +} + +struct mlx5_teardown_stream_context { + struct mlx5_fpga_tls_command_context cmd; + u32 swid; +}; + +static void +mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_teardown_stream_context *ctx = + container_of(cmd, struct mlx5_teardown_stream_context, cmd); + + if (resp) { + u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome); + + if (syndrome) + mlx5_fpga_err(fdev, + "Teardown stream failed with syndrome = %d", + syndrome); + else + mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr, + &fdev->tls->idr_spinlock, + ctx->swid); + } + mlx5_fpga_tls_put_command_ctx(cmd); +} + +static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd) +{ + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, src_port), flow, + MLX5_BYTE_OFF(tls_flow, ipv6)); + + MLX5_SET(tls_cmd, cmd, ipv6, MLX5_GET(tls_flow, flow, ipv6)); + MLX5_SET(tls_cmd, cmd, direction_sx, + MLX5_GET(tls_flow, flow, direction_sx)); +} + +static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, + void *flow, u32 swid, gfp_t flags) +{ + struct mlx5_teardown_stream_context *ctx; + struct mlx5_fpga_dma_buf *buf; + void *cmd; + + ctx = kzalloc(sizeof(*ctx) + MLX5_TLS_COMMAND_SIZE, flags); + if (!ctx) + return; + + buf = &ctx->cmd.buf; + cmd = (ctx + 1); + MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM); + MLX5_SET(tls_cmd, cmd, swid, swid); + + mlx5_fpga_tls_flow_to_cmd(flow, cmd); + kfree(flow); + + buf->sg[0].data = cmd; + buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; + + ctx->swid = swid; + mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd, + mlx5_fpga_tls_teardown_completion); +} + +void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags) +{ + struct mlx5_fpga_tls *tls = mdev->fpga->tls; + void *flow; + + rcu_read_lock(); + flow = idr_find(&tls->tx_idr, swid); + rcu_read_unlock(); + + if (!flow) { + mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n", + swid); + return; + } + + mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags); +} + +enum mlx5_fpga_setup_stream_status { + MLX5_FPGA_CMD_PENDING, + MLX5_FPGA_CMD_SEND_FAILED, + MLX5_FPGA_CMD_RESPONSE_RECEIVED, + MLX5_FPGA_CMD_ABANDONED, +}; + +struct mlx5_setup_stream_context { + struct mlx5_fpga_tls_command_context cmd; + atomic_t status; + u32 syndrome; + struct completion comp; +}; + +static void +mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_setup_stream_context *ctx = + container_of(cmd, struct mlx5_setup_stream_context, cmd); + int status = MLX5_FPGA_CMD_SEND_FAILED; + void *tls_cmd = ctx + 1; + + /* If we failed to send to command resp == NULL */ + if (resp) { + ctx->syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome); + status = MLX5_FPGA_CMD_RESPONSE_RECEIVED; + } + + status = atomic_xchg_release(&ctx->status, status); + if (likely(status != MLX5_FPGA_CMD_ABANDONED)) { + complete(&ctx->comp); + return; + } + + mlx5_fpga_err(fdev, "Command was abandoned, syndrome = %u\n", + ctx->syndrome); + + if (!ctx->syndrome) { + /* The process was killed while waiting for the context to be + * added, and the add completed successfully. + * We need to destroy the HW context, and we can't can't reuse + * the command context because we might not have received + * the tx completion yet. + */ + mlx5_fpga_tls_del_tx_flow(fdev->mdev, + MLX5_GET(tls_cmd, tls_cmd, swid), + GFP_ATOMIC); + } + + mlx5_fpga_tls_put_command_ctx(cmd); +} + +static int mlx5_fpga_tls_setup_stream_cmd(struct mlx5_core_dev *mdev, + struct mlx5_setup_stream_context *ctx) +{ + struct mlx5_fpga_dma_buf *buf; + void *cmd = ctx + 1; + int status, ret = 0; + + buf = &ctx->cmd.buf; + buf->sg[0].data = cmd; + buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; + MLX5_SET(tls_cmd, cmd, command_type, CMD_SETUP_STREAM); + + init_completion(&ctx->comp); + atomic_set(&ctx->status, MLX5_FPGA_CMD_PENDING); + ctx->syndrome = -1; + + mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd, + mlx5_fpga_tls_setup_completion); + wait_for_completion_killable(&ctx->comp); + + status = atomic_xchg_acquire(&ctx->status, MLX5_FPGA_CMD_ABANDONED); + if (unlikely(status == MLX5_FPGA_CMD_PENDING)) + /* ctx is going to be released in mlx5_fpga_tls_setup_completion */ + return -EINTR; + + if (unlikely(ctx->syndrome)) + ret = -ENOMEM; + + mlx5_fpga_tls_put_command_ctx(&ctx->cmd); + return ret; +} + +static void mlx5_fpga_tls_hw_qp_recv_cb(void *cb_arg, + struct mlx5_fpga_dma_buf *buf) +{ + struct mlx5_fpga_device *fdev = (struct mlx5_fpga_device *)cb_arg; + + mlx5_fpga_tls_cmd_complete(fdev, buf); +} + +bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev) +{ + if (!mdev->fpga || !MLX5_CAP_GEN(mdev, fpga)) + return false; + + if (MLX5_CAP_FPGA(mdev, ieee_vendor_id) != + MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX) + return false; + + if (MLX5_CAP_FPGA(mdev, sandbox_product_id) != + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS) + return false; + + if (MLX5_CAP_FPGA(mdev, sandbox_product_version) != 0) + return false; + + return true; +} + +static int mlx5_fpga_tls_get_caps(struct mlx5_fpga_device *fdev, + u32 *p_caps) +{ + int err, cap_size = MLX5_ST_SZ_BYTES(tls_extended_cap); + u32 caps = 0; + void *buf; + + buf = kzalloc(cap_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + err = mlx5_fpga_get_sbu_caps(fdev, cap_size, buf); + if (err) + goto out; + + if (MLX5_GET(tls_extended_cap, buf, tx)) + caps |= MLX5_ACCEL_TLS_TX; + if (MLX5_GET(tls_extended_cap, buf, rx)) + caps |= MLX5_ACCEL_TLS_RX; + if (MLX5_GET(tls_extended_cap, buf, tls_v12)) + caps |= MLX5_ACCEL_TLS_V12; + if (MLX5_GET(tls_extended_cap, buf, tls_v13)) + caps |= MLX5_ACCEL_TLS_V13; + if (MLX5_GET(tls_extended_cap, buf, lro)) + caps |= MLX5_ACCEL_TLS_LRO; + if (MLX5_GET(tls_extended_cap, buf, ipv6)) + caps |= MLX5_ACCEL_TLS_IPV6; + + if (MLX5_GET(tls_extended_cap, buf, aes_gcm_128)) + caps |= MLX5_ACCEL_TLS_AES_GCM128; + if (MLX5_GET(tls_extended_cap, buf, aes_gcm_256)) + caps |= MLX5_ACCEL_TLS_AES_GCM256; + + *p_caps = caps; + err = 0; +out: + kfree(buf); + return err; +} + +int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev) +{ + struct mlx5_fpga_device *fdev = mdev->fpga; + struct mlx5_fpga_conn_attr init_attr = {0}; + struct mlx5_fpga_conn *conn; + struct mlx5_fpga_tls *tls; + int err = 0; + + if (!mlx5_fpga_is_tls_device(mdev) || !fdev) + return 0; + + tls = kzalloc(sizeof(*tls), GFP_KERNEL); + if (!tls) + return -ENOMEM; + + err = mlx5_fpga_tls_get_caps(fdev, &tls->caps); + if (err) + goto error; + + if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 | + MLX5_ACCEL_TLS_AES_GCM128))) { + err = -ENOTSUPP; + goto error; + } + + init_attr.rx_size = SBU_QP_QUEUE_SIZE; + init_attr.tx_size = SBU_QP_QUEUE_SIZE; + init_attr.recv_cb = mlx5_fpga_tls_hw_qp_recv_cb; + init_attr.cb_arg = fdev; + conn = mlx5_fpga_sbu_conn_create(fdev, &init_attr); + if (IS_ERR(conn)) { + err = PTR_ERR(conn); + mlx5_fpga_err(fdev, "Error creating TLS command connection %d\n", + err); + goto error; + } + + tls->conn = conn; + spin_lock_init(&tls->pending_cmds_lock); + INIT_LIST_HEAD(&tls->pending_cmds); + + idr_init(&tls->tx_idr); + spin_lock_init(&tls->idr_spinlock); + fdev->tls = tls; + return 0; + +error: + kfree(tls); + return err; +} + +void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev) +{ + struct mlx5_fpga_device *fdev = mdev->fpga; + + if (!fdev || !fdev->tls) + return; + + mlx5_fpga_sbu_conn_destroy(fdev->tls->conn); + kfree(fdev->tls); + fdev->tls = NULL; +} + +static void mlx5_fpga_tls_set_aes_gcm128_ctx(void *cmd, + struct tls_crypto_info *info, + __be64 *rcd_sn) +{ + struct tls12_crypto_info_aes_gcm_128 *crypto_info = + (struct tls12_crypto_info_aes_gcm_128 *)info; + + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_rcd_sn), crypto_info->rec_seq, + TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); + + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_implicit_iv), + crypto_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key), + crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + /* in AES-GCM 128 we need to write the key twice */ + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key) + + TLS_CIPHER_AES_GCM_128_KEY_SIZE, + crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + MLX5_SET(tls_cmd, cmd, alg, MLX5_TLS_ALG_AES_GCM_128); +} + +static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps, + struct tls_crypto_info *crypto_info) +{ + __be64 rcd_sn; + + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: + if (!(caps & MLX5_ACCEL_TLS_AES_GCM128)) + return -EINVAL; + mlx5_fpga_tls_set_aes_gcm128_ctx(cmd, crypto_info, &rcd_sn); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, u32 swid, + u32 tcp_sn) +{ + u32 caps = mlx5_fpga_tls_device_caps(mdev); + struct mlx5_setup_stream_context *ctx; + int ret = -ENOMEM; + size_t cmd_size; + void *cmd; + + cmd_size = MLX5_TLS_COMMAND_SIZE + sizeof(*ctx); + ctx = kzalloc(cmd_size, GFP_KERNEL); + if (!ctx) + goto out; + + cmd = ctx + 1; + ret = mlx5_fpga_tls_set_key_material(cmd, caps, crypto_info); + if (ret) + goto free_ctx; + + mlx5_fpga_tls_flow_to_cmd(flow, cmd); + + MLX5_SET(tls_cmd, cmd, swid, swid); + MLX5_SET(tls_cmd, cmd, tcp_sn, tcp_sn); + + return mlx5_fpga_tls_setup_stream_cmd(mdev, ctx); + +free_ctx: + kfree(ctx); +out: + return ret; +} + +int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) +{ + struct mlx5_fpga_tls *tls = mdev->fpga->tls; + int ret = -ENOMEM; + u32 swid; + + ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow); + if (ret < 0) + return ret; + + swid = ret; + MLX5_SET(tls_flow, flow, direction_sx, 1); + + ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid, + start_offload_tcp_sn); + if (ret && ret != -EINTR) + goto free_swid; + + *p_swid = swid; + return 0; +free_swid: + mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid); + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h new file mode 100644 index 0000000000000..800a214e4e490 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h @@ -0,0 +1,68 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5_FPGA_TLS_H__ +#define __MLX5_FPGA_TLS_H__ + +#include <linux/mlx5/driver.h> + +#include <net/tls.h> +#include "fpga/core.h" + +struct mlx5_fpga_tls { + struct list_head pending_cmds; + spinlock_t pending_cmds_lock; /* Protects pending_cmds */ + u32 caps; + struct mlx5_fpga_conn *conn; + + struct idr tx_idr; + spinlock_t idr_spinlock; /* protects the IDR */ +}; + +int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid); + +void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags); + +bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev); +int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev); +void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev); + +static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev) +{ + return mdev->fpga->tls->caps; +} + +#endif /* __MLX5_FPGA_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index ef5afd7c93259..5a00deff54576 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -372,6 +372,15 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) { id = dst->dest_attr.ft->id; + } else if (dst->dest_attr.type == + MLX5_FLOW_DESTINATION_TYPE_VPORT) { + id = dst->dest_attr.vport.num; + MLX5_SET(dest_format_struct, in_dests, + destination_eswitch_owner_vhca_id_valid, + dst->dest_attr.vport.vhca_id_valid); + MLX5_SET(dest_format_struct, in_dests, + destination_eswitch_owner_vhca_id, + dst->dest_attr.vport.vhca_id); } else { id = dst->dest_attr.tir_num; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 56e275199256b..e1b609c61d593 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1373,6 +1373,8 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft, struct mlx5_core_dev *dev = get_dev(&ft->node); int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); void *match_criteria_addr; + u8 src_esw_owner_mask_on; + void *misc; int err; u32 *in; @@ -1385,6 +1387,14 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft, MLX5_SET(create_flow_group_in, in, start_flow_index, fg->start_index); MLX5_SET(create_flow_group_in, in, end_flow_index, fg->start_index + fg->max_ftes - 1); + + misc = MLX5_ADDR_OF(fte_match_param, fg->mask.match_criteria, + misc_parameters); + src_esw_owner_mask_on = !!MLX5_GET(fte_match_set_misc, misc, + source_eswitch_owner_vhca_id); + MLX5_SET(create_flow_group_in, in, + source_eswitch_owner_vhca_id_valid, src_esw_owner_mask_on); + match_criteria_addr = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); memcpy(match_criteria_addr, fg->mask.match_criteria, @@ -1405,7 +1415,7 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, { if (d1->type == d2->type) { if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT && - d1->vport_num == d2->vport_num) || + d1->vport.num == d2->vport.num) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -2484,7 +2494,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (!steering->fdb_root_ns) return -ENOMEM; - prio = fs_create_prio(&steering->fdb_root_ns->ns, 0, 1); + prio = fs_create_prio(&steering->fdb_root_ns->ns, 0, 2); if (IS_ERR(prio)) goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 6d9053bcbe95c..08eac92fc26cf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -33,6 +33,8 @@ #ifndef __MLX5E_IPOB_H__ #define __MLX5E_IPOB_H__ +#ifdef CONFIG_MLX5_CORE_IPOIB + #include <linux/mlx5/fs.h> #include "en.h" @@ -93,8 +95,32 @@ const struct mlx5e_profile *mlx5i_pkey_get_profile(void); /* Extract mlx5e_priv from IPoIB netdev */ #define mlx5i_epriv(netdev) ((void *)(((struct mlx5i_priv *)netdev_priv(netdev))->mlx5e_priv)) +struct mlx5_wqe_eth_pad { + u8 rsvd0[16]; +}; + +struct mlx5i_tx_wqe { + struct mlx5_wqe_ctrl_seg ctrl; + struct mlx5_wqe_datagram_seg datagram; + struct mlx5_wqe_eth_pad pad; + struct mlx5_wqe_eth_seg eth; + struct mlx5_wqe_data_seg data[0]; +}; + +static inline void mlx5i_sq_fetch_wqe(struct mlx5e_txqsq *sq, + struct mlx5i_tx_wqe **wqe, + u16 *pi) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + *wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(*wqe, 0, sizeof(**wqe)); +} + netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey); void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +#endif /* CONFIG_MLX5_CORE_IPOIB */ #endif /* __MLX5E_IPOB_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e2c465b0b3f88..615005e638195 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" +#include "accel/tls.h" #include "lib/clock.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -1190,6 +1191,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_ipsec_start; } + err = mlx5_accel_tls_init(dev); + if (err) { + dev_err(&pdev->dev, "TLS device start failed %d\n", err); + goto err_tls_start; + } + err = mlx5_init_fs(dev); if (err) { dev_err(&pdev->dev, "Failed to init flow steering\n"); @@ -1231,6 +1238,9 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: + mlx5_accel_tls_cleanup(dev); + +err_tls_start: mlx5_accel_ipsec_cleanup(dev); err_ipsec_start: @@ -1306,6 +1316,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); + mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index b9736f505bdfc..f4f02f775c938 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -123,8 +123,8 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key)); write_unlock_irqrestore(&table->lock, flags); if (!deleted_mkey) { - mlx5_core_warn(dev, "failed radix tree delete of mkey 0x%x\n", - mlx5_base_mkey(mkey->key)); + mlx5_core_dbg(dev, "failed radix tree delete of mkey 0x%x\n", + mlx5_base_mkey(mkey->key)); return -ENOENT; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 02d6c5b5d502a..4ca07bfb6b14f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -407,21 +407,21 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, case MLX5_CMD_OP_RST2INIT_QP: if (MBOX_ALLOC(mbox, rst2init_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_INIT2RTR_QP: if (MBOX_ALLOC(mbox, init2rtr_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_RTR2RTS_QP: if (MBOX_ALLOC(mbox, rtr2rts_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_RTS2RTS_QP: if (MBOX_ALLOC(mbox, rts2rts_qp)) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 177e076b8d17f..719cecb182c6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -511,7 +511,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, *system_image_guid = MLX5_GET64(query_nic_vport_context_out, out, nic_vport_context.system_image_guid); - kfree(out); + kvfree(out); return 0; } @@ -531,7 +531,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) *node_guid = MLX5_GET64(query_nic_vport_context_out, out, nic_vport_context.node_guid); - kfree(out); + kvfree(out); return 0; } @@ -587,7 +587,7 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, *qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out, nic_vport_context.qkey_violation_counter); - kfree(out); + kvfree(out); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index ea66448ba365c..b97bb72b4db45 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -36,7 +36,12 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) { - return (u32)wq->sz_m1 + 1; + return (u32)wq->fbc.sz_m1 + 1; +} + +u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) +{ + return (u32)wq->fbc.frag_sz_m1 + 1; } u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) @@ -46,12 +51,12 @@ u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) { - return (u32)wq->sz_m1 + 1; + return (u32)wq->fbc.sz_m1 + 1; } static u32 mlx5_wq_cyc_get_byte_size(struct mlx5_wq_cyc *wq) { - return mlx5_wq_cyc_get_size(wq) << wq->log_stride; + return mlx5_wq_cyc_get_size(wq) << wq->fbc.log_stride; } static u32 mlx5_wq_qp_get_byte_size(struct mlx5_wq_qp *wq) @@ -67,17 +72,20 @@ static u32 mlx5_cqwq_get_byte_size(struct mlx5_cqwq *wq) static u32 mlx5_wq_ll_get_byte_size(struct mlx5_wq_ll *wq) { - return mlx5_wq_ll_get_size(wq) << wq->log_stride; + return mlx5_wq_ll_get_size(wq) << wq->fbc.log_stride; } int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl) { + struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; int err; - wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride); - wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1; + mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride), + MLX5_GET(wq, wqc, log_wq_sz), + fbc); + wq->sz = wq->fbc.sz_m1 + 1; err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -85,14 +93,14 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } - err = mlx5_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq), - &wq_ctrl->buf, param->buf_numa_node); + err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_cyc_get_byte_size(wq), + &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - wq->buf = wq_ctrl->buf.frags->buf; + fbc->frag_buf = wq_ctrl->buf; wq->db = wq_ctrl->db.db; wq_ctrl->mdev = mdev; @@ -105,17 +113,35 @@ err_db_free: return err; } +static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf, + struct mlx5_wq_qp *qp) +{ + struct mlx5_frag_buf *rqb, *sqb; + + rqb = &qp->rq.fbc.frag_buf; + *rqb = *buf; + rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); + rqb->npages = 1 << get_order(rqb->size); + + sqb = &qp->sq.fbc.frag_buf; + *sqb = *buf; + sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); + sqb->npages = 1 << get_order(sqb->size); + sqb->frags += rqb->npages; /* first part is for the rq */ +} + int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { int err; - wq->rq.log_stride = MLX5_GET(qpc, qpc, log_rq_stride) + 4; - wq->rq.sz_m1 = (1 << MLX5_GET(qpc, qpc, log_rq_size)) - 1; - - wq->sq.log_stride = ilog2(MLX5_SEND_WQE_BB); - wq->sq.sz_m1 = (1 << MLX5_GET(qpc, qpc, log_sq_size)) - 1; + mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, + MLX5_GET(qpc, qpc, log_rq_size), + &wq->rq.fbc); + mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB), + MLX5_GET(qpc, qpc, log_sq_size), + &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -123,15 +149,15 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } - err = mlx5_buf_alloc_node(mdev, mlx5_wq_qp_get_byte_size(wq), - &wq_ctrl->buf, param->buf_numa_node); + err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_qp_get_byte_size(wq), + &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - wq->rq.buf = wq_ctrl->buf.frags->buf; - wq->sq.buf = wq->rq.buf + mlx5_wq_cyc_get_byte_size(&wq->rq); + mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq); + wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; @@ -147,7 +173,7 @@ err_db_free: int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, - struct mlx5_frag_wq_ctrl *wq_ctrl) + struct mlx5_wq_ctrl *wq_ctrl) { int err; @@ -160,7 +186,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, } err = mlx5_frag_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq), - &wq_ctrl->frag_buf, + &wq_ctrl->buf, param->buf_numa_node); if (err) { mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", @@ -168,7 +194,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - wq->fbc.frag_buf = wq_ctrl->frag_buf; + wq->fbc.frag_buf = wq_ctrl->buf; wq->db = wq_ctrl->db.db; wq_ctrl->mdev = mdev; @@ -185,12 +211,14 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl) { + struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; struct mlx5_wqe_srq_next_seg *next_seg; int err; int i; - wq->log_stride = MLX5_GET(wq, wqc, log_wq_stride); - wq->sz_m1 = (1 << MLX5_GET(wq, wqc, log_wq_sz)) - 1; + mlx5_fill_fbc(MLX5_GET(wq, wqc, log_wq_stride), + MLX5_GET(wq, wqc, log_wq_sz), + fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -198,17 +226,17 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } - err = mlx5_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq), - &wq_ctrl->buf, param->buf_numa_node); + err = mlx5_frag_buf_alloc_node(mdev, mlx5_wq_ll_get_byte_size(wq), + &wq_ctrl->buf, param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", err); goto err_db_free; } - wq->buf = wq_ctrl->buf.frags->buf; + wq->fbc.frag_buf = wq_ctrl->buf; wq->db = wq_ctrl->db.db; - for (i = 0; i < wq->sz_m1; i++) { + for (i = 0; i < fbc->sz_m1; i++) { next_seg = mlx5_wq_ll_get_wqe(wq, i); next_seg->next_wqe_index = cpu_to_be16(i + 1); } @@ -227,12 +255,7 @@ err_db_free: void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) { - mlx5_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); + mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db); } -void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl) -{ - mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->frag_buf); - mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index fca90b94596de..0b47126815b63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -38,7 +38,6 @@ #include <linux/mlx5/qp.h> struct mlx5_wq_param { - int linear; int buf_numa_node; int db_numa_node; }; @@ -49,17 +48,12 @@ struct mlx5_wq_ctrl { struct mlx5_db db; }; -struct mlx5_frag_wq_ctrl { - struct mlx5_core_dev *mdev; - struct mlx5_frag_buf frag_buf; - struct mlx5_db db; -}; - struct mlx5_wq_cyc { - void *buf; + struct mlx5_frag_buf_ctrl fbc; __be32 *db; - u16 sz_m1; - u8 log_stride; + u16 sz; + u16 wqe_ctr; + u16 cur_sz; }; struct mlx5_wq_qp { @@ -74,20 +68,19 @@ struct mlx5_cqwq { }; struct mlx5_wq_ll { - void *buf; + struct mlx5_frag_buf_ctrl fbc; __be32 *db; __be16 *tail_next; - u16 sz_m1; u16 head; u16 wqe_ctr; u16 cur_sz; - u8 log_stride; }; int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); +u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, @@ -95,7 +88,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, - struct mlx5_frag_wq_ctrl *wq_ctrl); + struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq); int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, @@ -104,16 +97,67 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); -void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl); + +static inline int mlx5_wq_cyc_is_full(struct mlx5_wq_cyc *wq) +{ + return wq->cur_sz == wq->sz; +} + +static inline int mlx5_wq_cyc_missing(struct mlx5_wq_cyc *wq) +{ + return wq->sz - wq->cur_sz; +} + +static inline int mlx5_wq_cyc_is_empty(struct mlx5_wq_cyc *wq) +{ + return !wq->cur_sz; +} + +static inline void mlx5_wq_cyc_push(struct mlx5_wq_cyc *wq) +{ + wq->wqe_ctr++; + wq->cur_sz++; +} + +static inline void mlx5_wq_cyc_push_n(struct mlx5_wq_cyc *wq, u8 n) +{ + wq->wqe_ctr += n; + wq->cur_sz += n; +} + +static inline void mlx5_wq_cyc_pop(struct mlx5_wq_cyc *wq) +{ + wq->cur_sz--; +} + +static inline void mlx5_wq_cyc_update_db_record(struct mlx5_wq_cyc *wq) +{ + *wq->db = cpu_to_be32(wq->wqe_ctr); +} static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr) { - return ctr & wq->sz_m1; + return ctr & wq->fbc.sz_m1; +} + +static inline u16 mlx5_wq_cyc_ctr2fragix(struct mlx5_wq_cyc *wq, u16 ctr) +{ + return ctr & wq->fbc.frag_sz_m1; +} + +static inline u16 mlx5_wq_cyc_get_head(struct mlx5_wq_cyc *wq) +{ + return mlx5_wq_cyc_ctr2ix(wq, wq->wqe_ctr); +} + +static inline u16 mlx5_wq_cyc_get_tail(struct mlx5_wq_cyc *wq) +{ + return mlx5_wq_cyc_ctr2ix(wq, wq->wqe_ctr - wq->cur_sz); } static inline void *mlx5_wq_cyc_get_wqe(struct mlx5_wq_cyc *wq, u16 ix) { - return wq->buf + (ix << wq->log_stride); + return mlx5_frag_buf_get_wqe(&wq->fbc, ix); } static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2) @@ -124,9 +168,14 @@ static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2) return !equal && !smaller; } +static inline u32 mlx5_cqwq_ctr2ix(struct mlx5_cqwq *wq, u32 ctr) +{ + return ctr & wq->fbc.sz_m1; +} + static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq) { - return wq->cc & wq->fbc.sz_m1; + return mlx5_cqwq_ctr2ix(wq, wq->cc); } static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix) @@ -134,9 +183,14 @@ static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix) return mlx5_frag_buf_get_wqe(&wq->fbc, ix); } +static inline u32 mlx5_cqwq_get_ctr_wrap_cnt(struct mlx5_cqwq *wq, u32 ctr) +{ + return ctr >> wq->fbc.log_sz; +} + static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq) { - return wq->cc >> wq->fbc.log_sz; + return mlx5_cqwq_get_ctr_wrap_cnt(wq, wq->cc); } static inline void mlx5_cqwq_pop(struct mlx5_cqwq *wq) @@ -167,7 +221,7 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq) static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq) { - return wq->cur_sz == wq->sz_m1; + return wq->cur_sz == wq->fbc.sz_m1; } static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq) @@ -177,7 +231,7 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq) static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix) { - return wq->buf + (ix << wq->log_stride); + return mlx5_frag_buf_get_wqe(&wq->fbc, ix); } static inline void mlx5_wq_ll_push(struct mlx5_wq_ll *wq, u16 head_next) diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 479511cf79bc1..2bc48054b685a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -58,7 +58,7 @@ static inline void mlxsw_cmd_mbox_zero(char *mbox) struct mlxsw_core; int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod, - u32 in_mod, bool out_mbox_direct, + u32 in_mod, bool out_mbox_direct, bool reset_ok, char *in_mbox, size_t in_mbox_size, char *out_mbox, size_t out_mbox_size); @@ -67,7 +67,7 @@ static inline int mlxsw_cmd_exec_in(struct mlxsw_core *mlxsw_core, u16 opcode, size_t in_mbox_size) { return mlxsw_cmd_exec(mlxsw_core, opcode, opcode_mod, in_mod, false, - in_mbox, in_mbox_size, NULL, 0); + false, in_mbox, in_mbox_size, NULL, 0); } static inline int mlxsw_cmd_exec_out(struct mlxsw_core *mlxsw_core, u16 opcode, @@ -76,7 +76,7 @@ static inline int mlxsw_cmd_exec_out(struct mlxsw_core *mlxsw_core, u16 opcode, char *out_mbox, size_t out_mbox_size) { return mlxsw_cmd_exec(mlxsw_core, opcode, opcode_mod, in_mod, - out_mbox_direct, NULL, 0, + out_mbox_direct, false, NULL, 0, out_mbox, out_mbox_size); } @@ -84,7 +84,7 @@ static inline int mlxsw_cmd_exec_none(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod, u32 in_mod) { return mlxsw_cmd_exec(mlxsw_core, opcode, opcode_mod, in_mod, false, - NULL, 0, NULL, 0); + false, NULL, 0, NULL, 0); } enum mlxsw_cmd_opcode { @@ -179,6 +179,8 @@ enum mlxsw_cmd_status { MLXSW_CMD_STATUS_BAD_INDEX = 0x0A, /* NVMEM checksum/CRC failed. */ MLXSW_CMD_STATUS_BAD_NVMEM = 0x0B, + /* Device is currently running reset */ + MLXSW_CMD_STATUS_RUNNING_RESET = 0x26, /* Bad management packet (silently discarded). */ MLXSW_CMD_STATUS_BAD_PKT = 0x30, }; @@ -208,6 +210,8 @@ static inline const char *mlxsw_cmd_status_str(u8 status) return "BAD_INDEX"; case MLXSW_CMD_STATUS_BAD_NVMEM: return "BAD_NVMEM"; + case MLXSW_CMD_STATUS_RUNNING_RESET: + return "RUNNING_RESET"; case MLXSW_CMD_STATUS_BAD_PKT: return "BAD_PKT"; default: @@ -424,10 +428,15 @@ MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_rdq_sz, 0x04, 24, 8); MLXSW_ITEM32(cmd_mbox, query_aq_cap, max_num_rdqs, 0x04, 0, 8); /* cmd_mbox_query_aq_cap_log_max_cq_sz - * Log (base 2) of max CQEs allowed on CQ. + * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv0 and CQEv1. */ MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cq_sz, 0x08, 24, 8); +/* cmd_mbox_query_aq_cap_log_max_cqv2_sz + * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv2. + */ +MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cqv2_sz, 0x08, 16, 8); + /* cmd_mbox_query_aq_cap_max_num_cqs * Maximum number of CQs. */ @@ -662,6 +671,12 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); +/* cmd_mbox_config_set_cqe_version + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1); + /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -841,6 +856,14 @@ MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_type, MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_properties, 0x60, 0, 8, 0x08, 0x00, false); +/* cmd_mbox_config_profile_cqe_version + * CQE version: + * 0: CQE version is 0 + * 1: CQE version is either 1 or 2 + * CQE ver 1 or 2 is configured by Completion Queue Context field cqe_ver. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, cqe_version, 0xB0, 0, 8); + /* ACCESS_REG - Access EMAD Supported Register * ---------------------------------- * OpMod == 0 (N/A), INMmod == 0 (N/A) @@ -850,10 +873,12 @@ MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_properties, */ static inline int mlxsw_cmd_access_reg(struct mlxsw_core *mlxsw_core, + bool reset_ok, char *in_mbox, char *out_mbox) { return mlxsw_cmd_exec(mlxsw_core, MLXSW_CMD_OPCODE_ACCESS_REG, - 0, 0, false, in_mbox, MLXSW_CMD_MBOX_SIZE, + 0, 0, false, reset_ok, + in_mbox, MLXSW_CMD_MBOX_SIZE, out_mbox, MLXSW_CMD_MBOX_SIZE); } @@ -1032,11 +1057,15 @@ static inline int mlxsw_cmd_sw2hw_cq(struct mlxsw_core *mlxsw_core, 0, cq_number, in_mbox, MLXSW_CMD_MBOX_SIZE); } -/* cmd_mbox_sw2hw_cq_cv +enum mlxsw_cmd_mbox_sw2hw_cq_cqe_ver { + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2, +}; + +/* cmd_mbox_sw2hw_cq_cqe_ver * CQE Version. - * 0 - CQE Version 0, 1 - CQE Version 1 */ -MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4); +MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cqe_ver, 0x00, 28, 4); /* cmd_mbox_sw2hw_cq_c_eqn * Event Queue this CQ reports completion events to. diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e13ac3b8dff75..f9c724752a326 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -770,27 +770,35 @@ static void mlxsw_core_driver_put(const char *kind) static int mlxsw_devlink_port_split(struct devlink *devlink, unsigned int port_index, - unsigned int count) + unsigned int count, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - if (port_index >= mlxsw_core->max_ports) + if (port_index >= mlxsw_core->max_ports) { + NL_SET_ERR_MSG_MOD(extack, "Port index exceeds maximum number of ports"); return -EINVAL; + } if (!mlxsw_core->driver->port_split) return -EOPNOTSUPP; - return mlxsw_core->driver->port_split(mlxsw_core, port_index, count); + return mlxsw_core->driver->port_split(mlxsw_core, port_index, count, + extack); } static int mlxsw_devlink_port_unsplit(struct devlink *devlink, - unsigned int port_index) + unsigned int port_index, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - if (port_index >= mlxsw_core->max_ports) + if (port_index >= mlxsw_core->max_ports) { + NL_SET_ERR_MSG_MOD(extack, "Port index exceeds maximum number of ports"); return -EINVAL; + } if (!mlxsw_core->driver->port_unsplit) return -EOPNOTSUPP; - return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index); + return mlxsw_core->driver->port_unsplit(mlxsw_core, port_index, + extack); } static int @@ -963,17 +971,16 @@ mlxsw_devlink_sb_occ_tc_port_bind_get(struct devlink_port *devlink_port, pool_type, p_cur, p_max); } -static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink) +static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - const struct mlxsw_bus *mlxsw_bus = mlxsw_core->bus; int err; - if (!mlxsw_bus->reset) + if (!(mlxsw_core->bus->features & MLXSW_BUS_F_RESET)) return -EOPNOTSUPP; mlxsw_core_bus_device_unregister(mlxsw_core, true); - mlxsw_bus->reset(mlxsw_core->bus_priv); err = mlxsw_core_bus_device_register(mlxsw_core->bus_info, mlxsw_core->bus, mlxsw_core->bus_priv, true, @@ -1480,6 +1487,7 @@ static int mlxsw_core_reg_access_cmd(struct mlxsw_core *mlxsw_core, { enum mlxsw_emad_op_tlv_status status; int err, n_retry; + bool reset_ok; char *in_mbox, *out_mbox, *tmp; dev_dbg(mlxsw_core->bus_info->dev, "Reg cmd access (reg_id=%x(%s),type=%s)\n", @@ -1501,9 +1509,16 @@ static int mlxsw_core_reg_access_cmd(struct mlxsw_core *mlxsw_core, tmp = in_mbox + MLXSW_EMAD_OP_TLV_LEN * sizeof(u32); mlxsw_emad_pack_reg_tlv(tmp, reg, payload); + /* There is a special treatment needed for MRSR (reset) register. + * The command interface will return error after the command + * is executed, so tell the lower layer to expect it + * and cope accordingly. + */ + reset_ok = reg->id == MLXSW_REG_MRSR_ID; + n_retry = 0; retry: - err = mlxsw_cmd_access_reg(mlxsw_core, in_mbox, out_mbox); + err = mlxsw_cmd_access_reg(mlxsw_core, reset_ok, in_mbox, out_mbox); if (!err) { err = mlxsw_emad_process_status(out_mbox, &status); if (err) { @@ -1714,15 +1729,16 @@ EXPORT_SYMBOL(mlxsw_core_port_fini); void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv, struct net_device *dev, - bool split, u32 split_group) + u32 port_number, bool split, + u32 split_port_subnumber) { struct mlxsw_core_port *mlxsw_core_port = &mlxsw_core->ports[local_port]; struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; mlxsw_core_port->port_driver_priv = port_driver_priv; - if (split) - devlink_port_split_set(devlink_port, split_group); + devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, + port_number, split, split_port_subnumber); devlink_port_type_eth_set(devlink_port, dev); } EXPORT_SYMBOL(mlxsw_core_port_eth_set); @@ -1762,6 +1778,17 @@ enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_port_type_get); +int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core, + u8 local_port, char *name, size_t len) +{ + struct mlxsw_core_port *mlxsw_core_port = + &mlxsw_core->ports[local_port]; + struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; + + return devlink_port_get_phys_port_name(devlink_port, name, len); +} +EXPORT_SYMBOL(mlxsw_core_port_get_phys_port_name); + static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core, const char *buf, size_t size) { @@ -1781,7 +1808,7 @@ static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core, } int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod, - u32 in_mod, bool out_mbox_direct, + u32 in_mod, bool out_mbox_direct, bool reset_ok, char *in_mbox, size_t in_mbox_size, char *out_mbox, size_t out_mbox_size) { @@ -1804,7 +1831,15 @@ int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod, in_mbox, in_mbox_size, out_mbox, out_mbox_size, &status); - if (err == -EIO && status != MLXSW_CMD_STATUS_OK) { + if (!err && out_mbox) { + dev_dbg(mlxsw_core->bus_info->dev, "Output mailbox:\n"); + mlxsw_core_buf_dump_dbg(mlxsw_core, out_mbox, out_mbox_size); + } + + if (reset_ok && err == -EIO && + status == MLXSW_CMD_STATUS_RUNNING_RESET) { + err = 0; + } else if (err == -EIO && status != MLXSW_CMD_STATUS_OK) { dev_err(mlxsw_core->bus_info->dev, "Cmd exec failed (opcode=%x(%s),opcode_mod=%x,in_mod=%x,status=%x(%s))\n", opcode, mlxsw_cmd_opcode_str(opcode), opcode_mod, in_mod, status, mlxsw_cmd_status_str(status)); @@ -1814,10 +1849,6 @@ int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod, in_mod); } - if (!err && out_mbox) { - dev_dbg(mlxsw_core->bus_info->dev, "Output mailbox:\n"); - mlxsw_core_buf_dump_dbg(mlxsw_core, out_mbox, out_mbox_size); - } return err; } EXPORT_SYMBOL(mlxsw_cmd_exec); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 092d39399f3ce..552cfa29c2f74 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -201,13 +201,16 @@ int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port); void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port); void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv, struct net_device *dev, - bool split, u32 split_group); + u32 port_number, bool split, + u32 split_port_subnumber); void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv); void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv); enum devlink_port_type mlxsw_core_port_type_get(struct mlxsw_core *mlxsw_core, u8 local_port); +int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core, + u8 local_port, char *name, size_t len); int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay); bool mlxsw_core_schedule_work(struct work_struct *work); @@ -271,8 +274,9 @@ struct mlxsw_driver { int (*port_type_set)(struct mlxsw_core *mlxsw_core, u8 local_port, enum devlink_port_type new_type); int (*port_split)(struct mlxsw_core *mlxsw_core, u8 local_port, - unsigned int count); - int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port); + unsigned int count, struct netlink_ext_ack *extack); + int (*port_unsplit)(struct mlxsw_core *mlxsw_core, u8 local_port, + struct netlink_ext_ack *extack); int (*sb_pool_get)(struct mlxsw_core *mlxsw_core, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info *pool_info); @@ -334,6 +338,7 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core, mlxsw_core_res_get(mlxsw_core, MLXSW_RES_ID_##short_res_id) #define MLXSW_BUS_F_TXRX BIT(0) +#define MLXSW_BUS_F_RESET BIT(1) struct mlxsw_bus { const char *kind; @@ -341,7 +346,6 @@ struct mlxsw_bus { const struct mlxsw_config_profile *profile, struct mlxsw_res *res); void (*fini)(void *bus_priv); - void (*reset)(void *bus_priv); bool (*skb_transmit_busy)(void *bus_priv, const struct mlxsw_tx_info *tx_info); int (*skb_transmit)(void *bus_priv, struct sk_buff *skb, diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 3a9381977d6d3..fc4557245ff42 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -117,6 +117,7 @@ struct mlxsw_pci_queue { struct { u32 comp_sdq_count; u32 comp_rdq_count; + enum mlxsw_pci_cqe_v v; } cq; struct { u32 ev_cmd_count; @@ -155,6 +156,8 @@ struct mlxsw_pci { } cmd; struct mlxsw_bus_info bus_info; const struct pci_device_id *id; + enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */ + u8 num_sdq_cqs; /* Number of CQs used for SDQs */ }; static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q) @@ -202,24 +205,6 @@ static bool mlxsw_pci_elem_hw_owned(struct mlxsw_pci_queue *q, bool owner_bit) return owner_bit != !!(q->consumer_counter & q->count); } -static char * -mlxsw_pci_queue_sw_elem_get(struct mlxsw_pci_queue *q, - u32 (*get_elem_owner_func)(const char *)) -{ - struct mlxsw_pci_queue_elem_info *elem_info; - char *elem; - bool owner_bit; - - elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - elem = elem_info->elem; - owner_bit = get_elem_owner_func(elem); - if (mlxsw_pci_elem_hw_owned(q, owner_bit)) - return NULL; - q->consumer_counter++; - rmb(); /* make sure we read owned bit before the rest of elem */ - return elem; -} - static struct mlxsw_pci_queue_type_group * mlxsw_pci_queue_type_group_get(struct mlxsw_pci *mlxsw_pci, enum mlxsw_pci_queue_type q_type) @@ -494,6 +479,17 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci, } } +static void mlxsw_pci_cq_pre_init(struct mlxsw_pci *mlxsw_pci, + struct mlxsw_pci_queue *q) +{ + q->u.cq.v = mlxsw_pci->max_cqe_ver; + + /* For SDQ it is pointless to use CQEv2, so use CQEv1 instead */ + if (q->u.cq.v == MLXSW_PCI_CQE_V2 && + q->num < mlxsw_pci->num_sdq_cqs) + q->u.cq.v = MLXSW_PCI_CQE_V1; +} + static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { @@ -505,10 +501,16 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, for (i = 0; i < q->count; i++) { char *elem = mlxsw_pci_queue_elem_get(q, i); - mlxsw_pci_cqe_owner_set(elem, 1); + mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1); } - mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */ + if (q->u.cq.v == MLXSW_PCI_CQE_V1) + mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1); + else if (q->u.cq.v == MLXSW_PCI_CQE_V2) + mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2); + mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM); mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count)); @@ -559,7 +561,7 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci, static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q, u16 consumer_counter_limit, - char *cqe) + enum mlxsw_pci_cqe_v cqe_v, char *cqe) { struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; @@ -579,10 +581,11 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); - if (mlxsw_pci_cqe_lag_get(cqe)) { + if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; - rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe); - rx_info.lag_port_index = mlxsw_pci_cqe_lag_port_index_get(cqe); + rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe); + rx_info.lag_port_index = + mlxsw_pci_cqe_lag_subport_get(cqe_v, cqe); } else { rx_info.is_lag = false; rx_info.u.sys_port = mlxsw_pci_cqe_system_port_get(cqe); @@ -591,7 +594,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe); byte_count = mlxsw_pci_cqe_byte_count_get(cqe); - if (mlxsw_pci_cqe_crc_get(cqe)) + if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) byte_count -= ETH_FCS_LEN; skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); @@ -608,7 +611,18 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q) { - return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_cqe_owner_get); + struct mlxsw_pci_queue_elem_info *elem_info; + char *elem; + bool owner_bit; + + elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); + elem = elem_info->elem; + owner_bit = mlxsw_pci_cqe_owner_get(q->u.cq.v, elem); + if (mlxsw_pci_elem_hw_owned(q, owner_bit)) + return NULL; + q->consumer_counter++; + rmb(); /* make sure we read owned bit before the rest of elem */ + return elem; } static void mlxsw_pci_cq_tasklet(unsigned long data) @@ -621,8 +635,8 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) { u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe); - u8 sendq = mlxsw_pci_cqe_sr_get(cqe); - u8 dqn = mlxsw_pci_cqe_dqn_get(cqe); + u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe); + u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe); if (sendq) { struct mlxsw_pci_queue *sdq; @@ -636,7 +650,7 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn); mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq, - wqe_counter, cqe); + wqe_counter, q->u.cq.v, cqe); q->u.cq.comp_rdq_count++; } if (++items == credits) @@ -648,6 +662,18 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) } } +static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q) +{ + return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT : + MLXSW_PCI_CQE01_COUNT; +} + +static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q) +{ + return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE : + MLXSW_PCI_CQE01_SIZE; +} + static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { @@ -696,7 +722,18 @@ static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe) static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q) { - return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_eqe_owner_get); + struct mlxsw_pci_queue_elem_info *elem_info; + char *elem; + bool owner_bit; + + elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); + elem = elem_info->elem; + owner_bit = mlxsw_pci_eqe_owner_get(elem); + if (mlxsw_pci_elem_hw_owned(q, owner_bit)) + return NULL; + q->consumer_counter++; + rmb(); /* make sure we read owned bit before the rest of elem */ + return elem; } static void mlxsw_pci_eq_tasklet(unsigned long data) @@ -749,11 +786,15 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) struct mlxsw_pci_queue_ops { const char *name; enum mlxsw_pci_queue_type type; + void (*pre_init)(struct mlxsw_pci *mlxsw_pci, + struct mlxsw_pci_queue *q); int (*init)(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q); void (*fini)(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q); void (*tasklet)(unsigned long data); + u16 (*elem_count_f)(const struct mlxsw_pci_queue *q); + u8 (*elem_size_f)(const struct mlxsw_pci_queue *q); u16 elem_count; u8 elem_size; }; @@ -776,11 +817,12 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = { static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = { .type = MLXSW_PCI_QUEUE_TYPE_CQ, + .pre_init = mlxsw_pci_cq_pre_init, .init = mlxsw_pci_cq_init, .fini = mlxsw_pci_cq_fini, .tasklet = mlxsw_pci_cq_tasklet, - .elem_count = MLXSW_PCI_CQE_COUNT, - .elem_size = MLXSW_PCI_CQE_SIZE + .elem_count_f = mlxsw_pci_cq_elem_count, + .elem_size_f = mlxsw_pci_cq_elem_size }; static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = { @@ -800,10 +842,15 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox, int i; int err; - spin_lock_init(&q->lock); q->num = q_num; - q->count = q_ops->elem_count; - q->elem_size = q_ops->elem_size; + if (q_ops->pre_init) + q_ops->pre_init(mlxsw_pci, q); + + spin_lock_init(&q->lock); + q->count = q_ops->elem_count_f ? q_ops->elem_count_f(q) : + q_ops->elem_count; + q->elem_size = q_ops->elem_size_f ? q_ops->elem_size_f(q) : + q_ops->elem_size; q->type = q_ops->type; q->pci = mlxsw_pci; @@ -832,7 +879,7 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox, elem_info = mlxsw_pci_queue_elem_info_get(q, i); elem_info->elem = - __mlxsw_pci_queue_elem_get(q, q_ops->elem_size, i); + __mlxsw_pci_queue_elem_get(q, q->elem_size, i); } mlxsw_cmd_mbox_zero(mbox); @@ -912,6 +959,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) u8 rdq_log2sz; u8 num_cqs; u8 cq_log2sz; + u8 cqv2_log2sz; u8 num_eqs; u8 eq_log2sz; int err; @@ -927,6 +975,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) rdq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_rdq_sz_get(mbox); num_cqs = mlxsw_cmd_mbox_query_aq_cap_max_num_cqs_get(mbox); cq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cq_sz_get(mbox); + cqv2_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cqv2_sz_get(mbox); num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox); eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox); @@ -938,12 +987,16 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) if ((1 << sdq_log2sz != MLXSW_PCI_WQE_COUNT) || (1 << rdq_log2sz != MLXSW_PCI_WQE_COUNT) || - (1 << cq_log2sz != MLXSW_PCI_CQE_COUNT) || + (1 << cq_log2sz != MLXSW_PCI_CQE01_COUNT) || + (mlxsw_pci->max_cqe_ver == MLXSW_PCI_CQE_V2 && + (1 << cqv2_log2sz != MLXSW_PCI_CQE2_COUNT)) || (1 << eq_log2sz != MLXSW_PCI_EQE_COUNT)) { dev_err(&pdev->dev, "Unsupported number of async queue descriptors\n"); return -EINVAL; } + mlxsw_pci->num_sdq_cqs = num_sdqs; + err = mlxsw_pci_queue_group_init(mlxsw_pci, mbox, &mlxsw_pci_eq_ops, num_eqs); if (err) { @@ -1184,6 +1237,11 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i, &profile->swid_config[i]); + if (mlxsw_pci->max_cqe_ver > MLXSW_PCI_CQE_V0) { + mlxsw_cmd_mbox_config_profile_set_cqe_version_set(mbox, 1); + mlxsw_cmd_mbox_config_profile_cqe_version_set(mbox, 1); + } + return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox); } @@ -1313,6 +1371,51 @@ static void mlxsw_pci_mbox_free(struct mlxsw_pci *mlxsw_pci, mbox->mapaddr); } +static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci, + const struct pci_device_id *id) +{ + unsigned long end; + char mrsr_pl[MLXSW_REG_MRSR_LEN]; + int err; + + mlxsw_reg_mrsr_pack(mrsr_pl); + err = mlxsw_reg_write(mlxsw_pci->core, MLXSW_REG(mrsr), mrsr_pl); + if (err) + return err; + if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) { + msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); + return 0; + } + + /* We must wait for the HW to become responsive once again. */ + msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS); + + end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); + do { + u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY); + + if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC) + break; + cond_resched(); + } while (time_before(jiffies, end)); + return 0; +} + +static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci) +{ + int err; + + err = pci_alloc_irq_vectors(mlxsw_pci->pdev, 1, 1, PCI_IRQ_MSIX); + if (err < 0) + dev_err(&mlxsw_pci->pdev->dev, "MSI-X init failed\n"); + return err; +} + +static void mlxsw_pci_free_irq_vectors(struct mlxsw_pci *mlxsw_pci) +{ + pci_free_irq_vectors(mlxsw_pci->pdev); +} + static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, const struct mlxsw_config_profile *profile, struct mlxsw_res *res) @@ -1340,6 +1443,16 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_out_mbox_alloc; + err = mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id); + if (err) + goto err_sw_reset; + + err = mlxsw_pci_alloc_irq_vectors(mlxsw_pci); + if (err < 0) { + dev_err(&pdev->dev, "MSI-X init failed\n"); + goto err_alloc_irq; + } + err = mlxsw_cmd_query_fw(mlxsw_core, mbox); if (err) goto err_query_fw; @@ -1378,6 +1491,21 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_query_resources; + if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V2) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V2)) + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V2; + else if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V1) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V1)) + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V1; + else if ((MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V0)) || + !MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0)) { + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V0; + } else { + dev_err(&pdev->dev, "Invalid supported CQE version combination reported\n"); + goto err_cqe_v_check; + } + err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile, res); if (err) goto err_config_profile; @@ -1400,6 +1528,7 @@ err_request_eq_irq: mlxsw_pci_aqs_fini(mlxsw_pci); err_aqs_init: err_config_profile: +err_cqe_v_check: err_query_resources: err_boardinfo: mlxsw_pci_fw_area_fini(mlxsw_pci); @@ -1407,6 +1536,9 @@ err_fw_area_init: err_doorbell_page_bar: err_iface_rev: err_query_fw: + mlxsw_pci_free_irq_vectors(mlxsw_pci); +err_alloc_irq: +err_sw_reset: mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); err_out_mbox_alloc: mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); @@ -1422,6 +1554,7 @@ static void mlxsw_pci_fini(void *bus_priv) free_irq(pci_irq_vector(mlxsw_pci->pdev, 0), mlxsw_pci); mlxsw_pci_aqs_fini(mlxsw_pci); mlxsw_pci_fw_area_fini(mlxsw_pci); + mlxsw_pci_free_irq_vectors(mlxsw_pci); mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.out_mbox); mlxsw_pci_mbox_free(mlxsw_pci, &mlxsw_pci->cmd.in_mbox); } @@ -1603,58 +1736,6 @@ static int mlxsw_pci_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod, return err; } -static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci, - const struct pci_device_id *id) -{ - unsigned long end; - - mlxsw_pci_write32(mlxsw_pci, SW_RESET, MLXSW_PCI_SW_RESET_RST_BIT); - if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) { - msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); - return 0; - } - - /* Reset needs to be written before we read control register, and - * we must wait for the HW to become responsive once again - */ - wmb(); - msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS); - - end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); - do { - u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY); - - if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC) - break; - cond_resched(); - } while (time_before(jiffies, end)); - return 0; -} - -static void mlxsw_pci_free_irq_vectors(struct mlxsw_pci *mlxsw_pci) -{ - pci_free_irq_vectors(mlxsw_pci->pdev); -} - -static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci) -{ - int err; - - err = pci_alloc_irq_vectors(mlxsw_pci->pdev, 1, 1, PCI_IRQ_MSIX); - if (err < 0) - dev_err(&mlxsw_pci->pdev->dev, "MSI-X init failed\n"); - return err; -} - -static void mlxsw_pci_reset(void *bus_priv) -{ - struct mlxsw_pci *mlxsw_pci = bus_priv; - - mlxsw_pci_free_irq_vectors(mlxsw_pci); - mlxsw_pci_sw_reset(mlxsw_pci, mlxsw_pci->id); - mlxsw_pci_alloc_irq_vectors(mlxsw_pci); -} - static const struct mlxsw_bus mlxsw_pci_bus = { .kind = "pci", .init = mlxsw_pci_init, @@ -1662,8 +1743,7 @@ static const struct mlxsw_bus mlxsw_pci_bus = { .skb_transmit_busy = mlxsw_pci_skb_transmit_busy, .skb_transmit = mlxsw_pci_skb_transmit, .cmd_exec = mlxsw_pci_cmd_exec, - .features = MLXSW_BUS_F_TXRX, - .reset = mlxsw_pci_reset, + .features = MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET, }; static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) @@ -1721,18 +1801,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mlxsw_pci->pdev = pdev; pci_set_drvdata(pdev, mlxsw_pci); - err = mlxsw_pci_sw_reset(mlxsw_pci, id); - if (err) { - dev_err(&pdev->dev, "Software reset failed\n"); - goto err_sw_reset; - } - - err = mlxsw_pci_alloc_irq_vectors(mlxsw_pci); - if (err < 0) { - dev_err(&pdev->dev, "MSI-X init failed\n"); - goto err_msix_init; - } - mlxsw_pci->bus_info.device_kind = driver_name; mlxsw_pci->bus_info.device_name = pci_name(mlxsw_pci->pdev); mlxsw_pci->bus_info.dev = &pdev->dev; @@ -1749,9 +1817,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; err_bus_device_register: - mlxsw_pci_free_irq_vectors(mlxsw_pci); -err_msix_init: -err_sw_reset: iounmap(mlxsw_pci->hw_addr); err_ioremap: err_pci_resource_len_check: @@ -1769,7 +1834,6 @@ static void mlxsw_pci_remove(struct pci_dev *pdev) struct mlxsw_pci *mlxsw_pci = pci_get_drvdata(pdev); mlxsw_core_bus_device_unregister(mlxsw_pci->core, false); - mlxsw_pci_free_irq_vectors(mlxsw_pci); iounmap(mlxsw_pci->hw_addr); pci_release_regions(mlxsw_pci->pdev); pci_disable_device(mlxsw_pci->pdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index fb082ad21b00e..963155f6a17a5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -82,10 +82,12 @@ #define MLXSW_PCI_AQ_PAGES 8 #define MLXSW_PCI_AQ_SIZE (MLXSW_PCI_PAGE_SIZE * MLXSW_PCI_AQ_PAGES) #define MLXSW_PCI_WQE_SIZE 32 /* 32 bytes per element */ -#define MLXSW_PCI_CQE_SIZE 16 /* 16 bytes per element */ +#define MLXSW_PCI_CQE01_SIZE 16 /* 16 bytes per element */ +#define MLXSW_PCI_CQE2_SIZE 32 /* 32 bytes per element */ #define MLXSW_PCI_EQE_SIZE 16 /* 16 bytes per element */ #define MLXSW_PCI_WQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE) -#define MLXSW_PCI_CQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE_SIZE) +#define MLXSW_PCI_CQE01_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE) +#define MLXSW_PCI_CQE2_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE2_SIZE) #define MLXSW_PCI_EQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_EQE_SIZE) #define MLXSW_PCI_EQE_UPDATE_COUNT 0x80 @@ -126,10 +128,48 @@ MLXSW_ITEM16_INDEXED(pci, wqe, byte_count, 0x02, 0, 14, 0x02, 0x00, false); */ MLXSW_ITEM64_INDEXED(pci, wqe, address, 0x08, 0, 64, 0x8, 0x0, false); +enum mlxsw_pci_cqe_v { + MLXSW_PCI_CQE_V0, + MLXSW_PCI_CQE_V1, + MLXSW_PCI_CQE_V2, +}; + +#define mlxsw_pci_cqe_item_helpers(name, v0, v1, v2) \ +static inline u32 mlxsw_pci_cqe_##name##_get(enum mlxsw_pci_cqe_v v, char *cqe) \ +{ \ + switch (v) { \ + default: \ + case MLXSW_PCI_CQE_V0: \ + return mlxsw_pci_cqe##v0##_##name##_get(cqe); \ + case MLXSW_PCI_CQE_V1: \ + return mlxsw_pci_cqe##v1##_##name##_get(cqe); \ + case MLXSW_PCI_CQE_V2: \ + return mlxsw_pci_cqe##v2##_##name##_get(cqe); \ + } \ +} \ +static inline void mlxsw_pci_cqe_##name##_set(enum mlxsw_pci_cqe_v v, \ + char *cqe, u32 val) \ +{ \ + switch (v) { \ + default: \ + case MLXSW_PCI_CQE_V0: \ + mlxsw_pci_cqe##v0##_##name##_set(cqe, val); \ + break; \ + case MLXSW_PCI_CQE_V1: \ + mlxsw_pci_cqe##v1##_##name##_set(cqe, val); \ + break; \ + case MLXSW_PCI_CQE_V2: \ + mlxsw_pci_cqe##v2##_##name##_set(cqe, val); \ + break; \ + } \ +} + /* pci_cqe_lag * Packet arrives from a port which is a LAG */ -MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1); +MLXSW_ITEM32(pci, cqe0, lag, 0x00, 23, 1); +MLXSW_ITEM32(pci, cqe12, lag, 0x00, 24, 1); +mlxsw_pci_cqe_item_helpers(lag, 0, 12, 12); /* pci_cqe_system_port/lag_id * When lag=0: System port on which the packet was received @@ -138,8 +178,12 @@ MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1); * bits [3:0] sub_port on which the packet was received */ MLXSW_ITEM32(pci, cqe, system_port, 0x00, 0, 16); -MLXSW_ITEM32(pci, cqe, lag_id, 0x00, 4, 12); -MLXSW_ITEM32(pci, cqe, lag_port_index, 0x00, 0, 4); +MLXSW_ITEM32(pci, cqe0, lag_id, 0x00, 4, 12); +MLXSW_ITEM32(pci, cqe12, lag_id, 0x00, 0, 16); +mlxsw_pci_cqe_item_helpers(lag_id, 0, 12, 12); +MLXSW_ITEM32(pci, cqe0, lag_subport, 0x00, 0, 4); +MLXSW_ITEM32(pci, cqe12, lag_subport, 0x00, 16, 8); +mlxsw_pci_cqe_item_helpers(lag_subport, 0, 12, 12); /* pci_cqe_wqe_counter * WQE count of the WQEs completed on the associated dqn @@ -162,28 +206,38 @@ MLXSW_ITEM32(pci, cqe, trap_id, 0x08, 0, 9); * Length include CRC. Indicates the length field includes * the packet's CRC. */ -MLXSW_ITEM32(pci, cqe, crc, 0x0C, 8, 1); +MLXSW_ITEM32(pci, cqe0, crc, 0x0C, 8, 1); +MLXSW_ITEM32(pci, cqe12, crc, 0x0C, 9, 1); +mlxsw_pci_cqe_item_helpers(crc, 0, 12, 12); /* pci_cqe_e * CQE with Error. */ -MLXSW_ITEM32(pci, cqe, e, 0x0C, 7, 1); +MLXSW_ITEM32(pci, cqe0, e, 0x0C, 7, 1); +MLXSW_ITEM32(pci, cqe12, e, 0x00, 27, 1); +mlxsw_pci_cqe_item_helpers(e, 0, 12, 12); /* pci_cqe_sr * 1 - Send Queue * 0 - Receive Queue */ -MLXSW_ITEM32(pci, cqe, sr, 0x0C, 6, 1); +MLXSW_ITEM32(pci, cqe0, sr, 0x0C, 6, 1); +MLXSW_ITEM32(pci, cqe12, sr, 0x00, 26, 1); +mlxsw_pci_cqe_item_helpers(sr, 0, 12, 12); /* pci_cqe_dqn * Descriptor Queue (DQ) Number. */ -MLXSW_ITEM32(pci, cqe, dqn, 0x0C, 1, 5); +MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5); +MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6); +mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12); /* pci_cqe_owner * Ownership bit. */ -MLXSW_ITEM32(pci, cqe, owner, 0x0C, 0, 1); +MLXSW_ITEM32(pci, cqe01, owner, 0x0C, 0, 1); +MLXSW_ITEM32(pci, cqe2, owner, 0x1C, 0, 1); +mlxsw_pci_cqe_item_helpers(owner, 01, 01, 2); /* pci_eqe_event_type * Event type. diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6218231e379ee..1877d9f8a11a2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -6833,6 +6833,12 @@ enum mlxsw_reg_mpat_span_type { */ MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH = 0x0, + /* Remote SPAN Ethernet VLAN. + * The packet is forwarded to the monitoring port on the monitoring + * VLAN. + */ + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH = 0x1, + /* Encapsulated Remote SPAN Ethernet L3 GRE. * The packet is encapsulated with GRE header. */ @@ -7028,6 +7034,30 @@ static inline void mlxsw_reg_mpar_pack(char *payload, u8 local_port, mlxsw_reg_mpar_pa_id_set(payload, pa_id); } +/* MRSR - Management Reset and Shutdown Register + * --------------------------------------------- + * MRSR register is used to reset or shutdown the switch or + * the entire system (when applicable). + */ +#define MLXSW_REG_MRSR_ID 0x9023 +#define MLXSW_REG_MRSR_LEN 0x08 + +MLXSW_REG_DEFINE(mrsr, MLXSW_REG_MRSR_ID, MLXSW_REG_MRSR_LEN); + +/* reg_mrsr_command + * Reset/shutdown command + * 0 - do nothing + * 1 - software reset + * Access: WO + */ +MLXSW_ITEM32(reg, mrsr, command, 0x00, 0, 4); + +static inline void mlxsw_reg_mrsr_pack(char *payload) +{ + MLXSW_REG_ZERO(mrsr, payload); + mlxsw_reg_mrsr_command_set(payload, 1); +} + /* MLCR - Management LED Control Register * -------------------------------------- * Controls the system LEDs. @@ -7892,6 +7922,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mcia), MLXSW_REG(mpat), MLXSW_REG(mpar), + MLXSW_REG(mrsr), MLXSW_REG(mlcr), MLXSW_REG(mpsc), MLXSW_REG(mcqi), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index 087aad52c1957..fd9299ccec721 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -43,6 +43,9 @@ enum mlxsw_res_id { MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE, MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE, MLXSW_RES_ID_MAX_TRAP_GROUPS, + MLXSW_RES_ID_CQE_V0, + MLXSW_RES_ID_CQE_V1, + MLXSW_RES_ID_CQE_V2, MLXSW_RES_ID_COUNTER_POOL_SIZE, MLXSW_RES_ID_MAX_SPAN, MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES, @@ -81,6 +84,9 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002, [MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003, [MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201, + [MLXSW_RES_ID_CQE_V0] = 0x2210, + [MLXSW_RES_ID_CQE_V1] = 0x2211, + [MLXSW_RES_ID_CQE_V2] = 0x2212, [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410, [MLXSW_RES_ID_MAX_SPAN] = 0x2420, [MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index adc6ab2cf4292..968b88af2ef5e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -441,29 +441,29 @@ static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); } -int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, - u8 state) +enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - enum mlxsw_reg_spms_state spms_state; - char *spms_pl; - int err; - switch (state) { case BR_STATE_FORWARDING: - spms_state = MLXSW_REG_SPMS_STATE_FORWARDING; - break; + return MLXSW_REG_SPMS_STATE_FORWARDING; case BR_STATE_LEARNING: - spms_state = MLXSW_REG_SPMS_STATE_LEARNING; - break; + return MLXSW_REG_SPMS_STATE_LEARNING; case BR_STATE_LISTENING: /* fall-through */ case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_BLOCKING: - spms_state = MLXSW_REG_SPMS_STATE_DISCARDING; - break; + return MLXSW_REG_SPMS_STATE_DISCARDING; default: BUG(); } +} + +int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, + u8 state) +{ + enum mlxsw_reg_spms_state spms_state = mlxsw_sp_stp_spms_state(state); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char *spms_pl; + int err; spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); if (!spms_pl) @@ -1238,21 +1238,10 @@ static int mlxsw_sp_port_get_phys_port_name(struct net_device *dev, char *name, size_t len) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - u8 module = mlxsw_sp_port->mapping.module; - u8 width = mlxsw_sp_port->mapping.width; - u8 lane = mlxsw_sp_port->mapping.lane; - int err; - - if (!mlxsw_sp_port->split) - err = snprintf(name, len, "p%d", module + 1); - else - err = snprintf(name, len, "p%ds%d", module + 1, - lane / width); - - if (err >= len) - return -EINVAL; - return 0; + return mlxsw_core_port_get_phys_port_name(mlxsw_sp_port->mlxsw_sp->core, + mlxsw_sp_port->local_port, + name, len); } static struct mlxsw_sp_port_mall_tc_entry * @@ -2927,8 +2916,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, } mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port, - mlxsw_sp_port, dev, mlxsw_sp_port->split, - module); + mlxsw_sp_port, dev, module + 1, + mlxsw_sp_port->split, lane / width); mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0); return 0; @@ -3103,7 +3092,8 @@ static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, - unsigned int count) + unsigned int count, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port *mlxsw_sp_port; @@ -3115,6 +3105,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, if (!mlxsw_sp_port) { dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", local_port); + NL_SET_ERR_MSG_MOD(extack, "Port number does not exist"); return -EINVAL; } @@ -3123,11 +3114,13 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, if (count != 2 && count != 4) { netdev_err(mlxsw_sp_port->dev, "Port can only be split into 2 or 4 ports\n"); + NL_SET_ERR_MSG_MOD(extack, "Port can only be split into 2 or 4 ports"); return -EINVAL; } if (cur_width != MLXSW_PORT_MODULE_MAX_WIDTH) { netdev_err(mlxsw_sp_port->dev, "Port cannot be split further\n"); + NL_SET_ERR_MSG_MOD(extack, "Port cannot be split further"); return -EINVAL; } @@ -3136,6 +3129,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, base_port = local_port; if (mlxsw_sp->ports[base_port + 1]) { netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); + NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); return -EINVAL; } } else { @@ -3143,6 +3137,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, if (mlxsw_sp->ports[base_port + 1] || mlxsw_sp->ports[base_port + 3]) { netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); + NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); return -EINVAL; } } @@ -3164,7 +3159,8 @@ err_port_split_create: return err; } -static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port) +static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, + struct netlink_ext_ack *extack) { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port *mlxsw_sp_port; @@ -3176,11 +3172,13 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port) if (!mlxsw_sp_port) { dev_err(mlxsw_sp->bus_info->dev, "Port number \"%d\" does not exist\n", local_port); + NL_SET_ERR_MSG_MOD(extack, "Port number does not exist"); return -EINVAL; } if (!mlxsw_sp_port->split) { - netdev_err(mlxsw_sp_port->dev, "Port wasn't split\n"); + netdev_err(mlxsw_sp_port->dev, "Port was not split\n"); + NL_SET_ERR_MSG_MOD(extack, "Port was not split"); return -EINVAL; } @@ -3666,6 +3664,15 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_lag_init; } + /* Initialize SPAN before router and switchdev, so that those components + * can call mlxsw_sp_span_respin(). + */ + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + err = mlxsw_sp_switchdev_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n"); @@ -3684,15 +3691,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_afa_init; } - err = mlxsw_sp_span_init(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); - goto err_span_init; - } - - /* Initialize router after SPAN is initialized, so that the FIB and - * neighbor event handlers can issue SPAN respin. - */ err = mlxsw_sp_router_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); @@ -3739,14 +3737,14 @@ err_acl_init: err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: - mlxsw_sp_span_fini(mlxsw_sp); -err_span_init: mlxsw_sp_afa_fini(mlxsw_sp); err_afa_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); err_counter_pool_init: mlxsw_sp_switchdev_fini(mlxsw_sp); err_switchdev_init: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: mlxsw_sp_lag_fini(mlxsw_sp); err_lag_init: mlxsw_sp_buffers_fini(mlxsw_sp); @@ -3768,10 +3766,10 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_acl_fini(mlxsw_sp); unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); - mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_lag_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); mlxsw_sp_traps_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 804d4d2c80318..4a519d8edec8f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -364,6 +364,7 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index, u32 maxrate); +enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 stp_state); int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, u8 state); int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1904c0323d390..77b2adb293415 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -442,7 +442,7 @@ struct mlxsw_sp_fib6_entry { struct mlxsw_sp_rt6 { struct list_head list; - struct rt6_info *rt; + struct fib6_info *rt; }; struct mlxsw_sp_lpm_tree { @@ -2770,9 +2770,9 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp, struct in6_addr *gw; int ifindex, weight; - ifindex = mlxsw_sp_rt6->rt->dst.dev->ifindex; - weight = mlxsw_sp_rt6->rt->rt6i_nh_weight; - gw = &mlxsw_sp_rt6->rt->rt6i_gateway; + ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex; + weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight; + gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw; if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex, weight)) return false; @@ -2838,7 +2838,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) struct net_device *dev; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - dev = mlxsw_sp_rt6->rt->dst.dev; + dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev; val ^= dev->ifindex; } @@ -3834,11 +3834,11 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, for (i = 0; i < nh_grp->count; i++) { struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; - if (nh->rif && nh->rif->dev == rt->dst.dev && + if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev && ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, - &rt->rt6i_gateway)) + &rt->fib6_nh.nh_gw)) return nh; continue; } @@ -3895,7 +3895,7 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) { list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, - list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; return; } @@ -3905,9 +3905,9 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6); if (nh && nh->offloaded) - mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; else - mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -3920,9 +3920,9 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, common); list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; - rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -4699,29 +4699,29 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); } -static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt) +static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) { /* Packets with link-local destination IP arriving to the router * are trapped to the CPU, so no need to program specific routes * for them. */ - if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LINKLOCAL) + if (ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) return true; /* Multicast routes aren't supported, so ignore them. Neighbour * Discovery packets are specifically trapped. */ - if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_MULTICAST) + if (ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_MULTICAST) return true; /* Cloned routes are irrelevant in the forwarding path. */ - if (rt->rt6i_flags & RTF_CACHE) + if (rt->fib6_flags & RTF_CACHE) return true; return false; } -static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt) +static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -4734,18 +4734,18 @@ static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt) * memory. */ mlxsw_sp_rt6->rt = rt; - rt6_hold(rt); + fib6_info_hold(rt); return mlxsw_sp_rt6; } #if IS_ENABLED(CONFIG_IPV6) -static void mlxsw_sp_rt6_release(struct rt6_info *rt) +static void mlxsw_sp_rt6_release(struct fib6_info *rt) { - rt6_release(rt); + fib6_info_release(rt); } #else -static void mlxsw_sp_rt6_release(struct rt6_info *rt) +static void mlxsw_sp_rt6_release(struct fib6_info *rt) { } #endif @@ -4756,13 +4756,13 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) kfree(mlxsw_sp_rt6); } -static bool mlxsw_sp_fib6_rt_can_mp(const struct rt6_info *rt) +static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt) { /* RTF_CACHE routes are ignored */ - return (rt->rt6i_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; + return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; } -static struct rt6_info * +static struct fib6_info * mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) { return list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, @@ -4771,7 +4771,7 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct rt6_info *nrt, bool replace) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; @@ -4779,21 +4779,21 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); /* RT6_TABLE_LOCAL and RT6_TABLE_MAIN share the same * virtual router. */ - if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id > nrt->fib6_table->tb6_id) continue; - if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (rt->rt6i_metric < nrt->rt6i_metric) + if (rt->fib6_metric < nrt->fib6_metric) continue; - if (rt->rt6i_metric == nrt->rt6i_metric && + if (rt->fib6_metric == nrt->fib6_metric && mlxsw_sp_fib6_rt_can_mp(rt)) return fib6_entry; - if (rt->rt6i_metric > nrt->rt6i_metric) + if (rt->fib6_metric > nrt->fib6_metric) break; } @@ -4802,7 +4802,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, static struct mlxsw_sp_rt6 * mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry, - const struct rt6_info *rt) + const struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -4815,21 +4815,21 @@ mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry, } static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt, + const struct fib6_info *rt, enum mlxsw_sp_ipip_type *ret) { - return rt->dst.dev && - mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->dst.dev, ret); + return rt->fib6_nh.nh_dev && + mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret); } static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, - const struct rt6_info *rt) + const struct fib6_info *rt) { const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; - struct net_device *dev = rt->dst.dev; + struct net_device *dev = rt->fib6_nh.nh_dev; struct mlxsw_sp_rif *rif; int err; @@ -4870,13 +4870,13 @@ static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, - const struct rt6_info *rt) + const struct fib6_info *rt) { - struct net_device *dev = rt->dst.dev; + struct net_device *dev = rt->fib6_nh.nh_dev; nh->nh_grp = nh_grp; - nh->nh_weight = rt->rt6i_nh_weight; - memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr)); + nh->nh_weight = rt->fib6_nh.nh_weight; + memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr)); mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -4897,9 +4897,9 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, } static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt) + const struct fib6_info *rt) { - return rt->rt6i_flags & RTF_GATEWAY || + return rt->fib6_flags & RTF_GATEWAY || mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL); } @@ -4928,7 +4928,7 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt); nh_grp->count = fib6_entry->nrt6; for (i = 0; i < nh_grp->count; i++) { - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; nh = &nh_grp->nexthops[i]; err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt); @@ -5040,7 +5040,7 @@ err_nexthop6_group_get: static int mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; int err; @@ -5068,7 +5068,7 @@ err_nexthop6_group_update: static void mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -5084,7 +5084,7 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, - const struct rt6_info *rt) + const struct fib6_info *rt) { /* Packets hitting RTF_REJECT routes need to be discarded by the * stack. We can rely on their destination device not having a @@ -5092,9 +5092,9 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, * local, which will cause them to be trapped with a lower * priority than packets that need to be locally received. */ - if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; - else if (rt->rt6i_flags & RTF_REJECT) + else if (rt->fib6_flags & RTF_REJECT) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; @@ -5118,7 +5118,7 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_entry *fib_entry; @@ -5168,25 +5168,25 @@ static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct rt6_info *nrt, bool replace) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); - if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id > nrt->fib6_table->tb6_id) continue; - if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (replace && rt->rt6i_metric == nrt->rt6i_metric) { + if (replace && rt->fib6_metric == nrt->fib6_metric) { if (mlxsw_sp_fib6_rt_can_mp(rt) == mlxsw_sp_fib6_rt_can_mp(nrt)) return fib6_entry; if (mlxsw_sp_fib6_rt_can_mp(nrt)) fallback = fallback ?: fib6_entry; } - if (rt->rt6i_metric > nrt->rt6i_metric) + if (rt->fib6_metric > nrt->fib6_metric) return fallback ?: fib6_entry; } @@ -5198,7 +5198,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, bool replace) { struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node; - struct rt6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); + struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); struct mlxsw_sp_fib6_entry *fib6_entry; fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace); @@ -5213,9 +5213,9 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, struct mlxsw_sp_fib6_entry *last; list_for_each_entry(last, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(last); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(last); - if (nrt->rt6i_table->tb6_id > rt->rt6i_table->tb6_id) + if (nrt->fib6_table->tb6_id > rt->fib6_table->tb6_id) break; fib6_entry = last; } @@ -5268,29 +5268,29 @@ mlxsw_sp_fib6_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt) + const struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; - vr = mlxsw_sp_vr_find(mlxsw_sp, rt->rt6i_table->tb6_id); + vr = mlxsw_sp_vr_find(mlxsw_sp, rt->fib6_table->tb6_id); if (!vr) return NULL; fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV6); - fib_node = mlxsw_sp_fib_node_lookup(fib, &rt->rt6i_dst.addr, - sizeof(rt->rt6i_dst.addr), - rt->rt6i_dst.plen); + fib_node = mlxsw_sp_fib_node_lookup(fib, &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), + rt->fib6_dst.plen); if (!fib_node) return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry); - if (rt->rt6i_table->tb6_id == iter_rt->rt6i_table->tb6_id && - rt->rt6i_metric == iter_rt->rt6i_metric && + if (rt->fib6_table->tb6_id == iter_rt->fib6_table->tb6_id && + rt->fib6_metric == iter_rt->fib6_metric && mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt)) return fib6_entry; } @@ -5316,7 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, - struct rt6_info *rt, bool replace) + struct fib6_info *rt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5325,16 +5325,16 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp->router->aborted) return 0; - if (rt->rt6i_src.plen) + if (rt->fib6_src.plen) return -EINVAL; if (mlxsw_sp_fib6_rt_should_ignore(rt)) return 0; - fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->rt6i_table->tb6_id, - &rt->rt6i_dst.addr, - sizeof(rt->rt6i_dst.addr), - rt->rt6i_dst.plen, + fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->fib6_table->tb6_id, + &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), + rt->fib6_dst.plen, MLXSW_SP_L3_PROTO_IPV6); if (IS_ERR(fib_node)) return PTR_ERR(fib_node); @@ -5373,7 +5373,7 @@ err_fib6_entry_nexthop_add: } static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5725,6 +5725,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; err = mlxsw_sp_router_fib6_add(mlxsw_sp, @@ -5831,12 +5832,13 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_APPEND: /* fall through */ case FIB_EVENT_ENTRY_ADD: /* fall through */ case FIB_EVENT_ENTRY_DEL: fen6_info = container_of(info, struct fib6_entry_notifier_info, info); fib_work->fen6_info = *fen6_info; - rt6_hold(fib_work->fen6_info.rt); + fib6_info_hold(fib_work->fen6_info.rt); break; } } @@ -5882,24 +5884,24 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, switch (info->family) { case AF_INET: if (!fib4_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case AF_INET6: if (!fib6_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case RTNL_FAMILY_IPMR: if (!ipmr_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case RTNL_FAMILY_IP6MR: if (!ip6mr_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; } if (err < 0) - NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported. Aborting offload"); + NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported"); return err; } @@ -5926,8 +5928,15 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, case FIB_EVENT_RULE_DEL: err = mlxsw_sp_router_fib_rule_event(event, info, router->mlxsw_sp); - if (!err) - return NOTIFY_DONE; + if (!err || info->extack) + return notifier_from_errno(err); + break; + case FIB_EVENT_ENTRY_ADD: + if (router->aborted) { + NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route"); + return notifier_from_errno(-EINVAL); + } + break; } fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 65a77708ff617..3d187d88cc7c5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -32,6 +32,7 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/if_bridge.h> #include <linux/list.h> #include <net/arp.h> #include <net/gre.h> @@ -39,8 +40,9 @@ #include <net/ip6_tunnel.h> #include "spectrum.h" -#include "spectrum_span.h" #include "spectrum_ipip.h" +#include "spectrum_span.h" +#include "spectrum_switchdev.h" int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) { @@ -135,14 +137,14 @@ struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = { static int mlxsw_sp_span_dmac(struct neigh_table *tbl, const void *pkey, - struct net_device *l3edev, + struct net_device *dev, unsigned char dmac[ETH_ALEN]) { - struct neighbour *neigh = neigh_lookup(tbl, pkey, l3edev); + struct neighbour *neigh = neigh_lookup(tbl, pkey, dev); int err = 0; if (!neigh) { - neigh = neigh_create(tbl, pkey, l3edev); + neigh = neigh_create(tbl, pkey, dev); if (IS_ERR(neigh)) return PTR_ERR(neigh); } @@ -167,8 +169,99 @@ mlxsw_sp_span_entry_unoffloadable(struct mlxsw_sp_span_parms *sparmsp) return 0; } +static struct net_device * +mlxsw_sp_span_entry_bridge_8021q(const struct net_device *br_dev, + unsigned char *dmac, + u16 *p_vid) +{ + struct bridge_vlan_info vinfo; + struct net_device *edev; + u16 vid = *p_vid; + + if (!vid && WARN_ON(br_vlan_get_pvid(br_dev, &vid))) + return NULL; + if (!vid || + br_vlan_get_info(br_dev, vid, &vinfo) || + !(vinfo.flags & BRIDGE_VLAN_INFO_BRENTRY)) + return NULL; + + edev = br_fdb_find_port(br_dev, dmac, vid); + if (!edev) + return NULL; + + if (br_vlan_get_info(edev, vid, &vinfo)) + return NULL; + if (vinfo.flags & BRIDGE_VLAN_INFO_UNTAGGED) + *p_vid = 0; + else + *p_vid = vid; + return edev; +} + +static struct net_device * +mlxsw_sp_span_entry_bridge_8021d(const struct net_device *br_dev, + unsigned char *dmac) +{ + return br_fdb_find_port(br_dev, dmac, 0); +} + +static struct net_device * +mlxsw_sp_span_entry_bridge(const struct net_device *br_dev, + unsigned char dmac[ETH_ALEN], + u16 *p_vid) +{ + struct mlxsw_sp_bridge_port *bridge_port; + enum mlxsw_reg_spms_state spms_state; + struct net_device *dev = NULL; + struct mlxsw_sp_port *port; + u8 stp_state; + + if (br_vlan_enabled(br_dev)) + dev = mlxsw_sp_span_entry_bridge_8021q(br_dev, dmac, p_vid); + else if (!*p_vid) + dev = mlxsw_sp_span_entry_bridge_8021d(br_dev, dmac); + if (!dev) + return NULL; + + port = mlxsw_sp_port_dev_lower_find(dev); + if (!port) + return NULL; + + bridge_port = mlxsw_sp_bridge_port_find(port->mlxsw_sp->bridge, dev); + if (!bridge_port) + return NULL; + + stp_state = mlxsw_sp_bridge_port_stp_state(bridge_port); + spms_state = mlxsw_sp_stp_spms_state(stp_state); + if (spms_state != MLXSW_REG_SPMS_STATE_FORWARDING) + return NULL; + + return dev; +} + +static struct net_device * +mlxsw_sp_span_entry_vlan(const struct net_device *vlan_dev, + u16 *p_vid) +{ + *p_vid = vlan_dev_vlan_id(vlan_dev); + return vlan_dev_real_dev(vlan_dev); +} + +static struct net_device * +mlxsw_sp_span_entry_lag(struct net_device *lag_dev) +{ + struct net_device *dev; + struct list_head *iter; + + netdev_for_each_lower_dev(lag_dev, dev, iter) + if ((dev->flags & IFF_UP) && mlxsw_sp_port_dev_check(dev)) + return dev; + + return NULL; +} + static __maybe_unused int -mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, +mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *edev, union mlxsw_sp_l3addr saddr, union mlxsw_sp_l3addr daddr, union mlxsw_sp_l3addr gw, @@ -177,21 +270,51 @@ mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, struct mlxsw_sp_span_parms *sparmsp) { unsigned char dmac[ETH_ALEN]; + u16 vid = 0; if (mlxsw_sp_l3addr_is_zero(gw)) gw = daddr; - if (!l3edev || !mlxsw_sp_port_dev_check(l3edev) || - mlxsw_sp_span_dmac(tbl, &gw, l3edev, dmac)) - return mlxsw_sp_span_entry_unoffloadable(sparmsp); + if (!edev || mlxsw_sp_span_dmac(tbl, &gw, edev, dmac)) + goto unoffloadable; - sparmsp->dest_port = netdev_priv(l3edev); + if (is_vlan_dev(edev)) + edev = mlxsw_sp_span_entry_vlan(edev, &vid); + + if (netif_is_bridge_master(edev)) { + edev = mlxsw_sp_span_entry_bridge(edev, dmac, &vid); + if (!edev) + goto unoffloadable; + } + + if (is_vlan_dev(edev)) { + if (vid || !(edev->flags & IFF_UP)) + goto unoffloadable; + edev = mlxsw_sp_span_entry_vlan(edev, &vid); + } + + if (netif_is_lag_master(edev)) { + if (!(edev->flags & IFF_UP)) + goto unoffloadable; + edev = mlxsw_sp_span_entry_lag(edev); + if (!edev) + goto unoffloadable; + } + + if (!mlxsw_sp_port_dev_check(edev)) + goto unoffloadable; + + sparmsp->dest_port = netdev_priv(edev); sparmsp->ttl = ttl; memcpy(sparmsp->dmac, dmac, ETH_ALEN); - memcpy(sparmsp->smac, l3edev->dev_addr, ETH_ALEN); + memcpy(sparmsp->smac, edev->dev_addr, ETH_ALEN); sparmsp->saddr = saddr; sparmsp->daddr = daddr; + sparmsp->vid = vid; return 0; + +unoffloadable: + return mlxsw_sp_span_entry_unoffloadable(sparmsp); } #if IS_ENABLED(CONFIG_NET_IPGRE) @@ -268,9 +391,10 @@ mlxsw_sp_span_entry_gretap4_configure(struct mlxsw_sp_span_entry *span_entry, /* Create a new port analayzer entry for local_port. */ mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, - sparms.dmac, false); + sparms.dmac, !!sparms.vid); mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(mpat_pl, sparms.ttl, sparms.smac, be32_to_cpu(sparms.saddr.addr4), @@ -368,9 +492,10 @@ mlxsw_sp_span_entry_gretap6_configure(struct mlxsw_sp_span_entry *span_entry, /* Create a new port analayzer entry for local_port. */ mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, - sparms.dmac, false); + sparms.dmac, !!sparms.vid); mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(mpat_pl, sparms.ttl, sparms.smac, sparms.saddr.addr6, sparms.daddr.addr6); @@ -394,6 +519,61 @@ struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = { }; #endif +static bool +mlxsw_sp_span_vlan_can_handle(const struct net_device *dev) +{ + return is_vlan_dev(dev) && + mlxsw_sp_port_dev_check(vlan_dev_real_dev(dev)); +} + +static int +mlxsw_sp_span_entry_vlan_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct net_device *real_dev; + u16 vid; + + if (!(to_dev->flags & IFF_UP)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + real_dev = mlxsw_sp_span_entry_vlan(to_dev, &vid); + sparmsp->dest_port = netdev_priv(real_dev); + sparmsp->vid = vid; + return 0; +} + +static int +mlxsw_sp_span_entry_vlan_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_vlan_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_vlan = { + .can_handle = mlxsw_sp_span_vlan_can_handle, + .parms = mlxsw_sp_span_entry_vlan_parms, + .configure = mlxsw_sp_span_entry_vlan_configure, + .deconfigure = mlxsw_sp_span_entry_vlan_deconfigure, +}; + static const struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { &mlxsw_sp_span_entry_ops_phys, @@ -403,6 +583,7 @@ struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { #if IS_ENABLED(CONFIG_IPV6_GRE) &mlxsw_sp_span_entry_ops_gretap6, #endif + &mlxsw_sp_span_entry_ops_vlan, }; static int @@ -766,7 +947,7 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms); if (!span_entry) - return -ENOENT; + return -ENOBUFS; netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", span_entry->id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index 4b87ec20e6581..14a6de904db17 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -63,6 +63,7 @@ struct mlxsw_sp_span_parms { unsigned char smac[ETH_ALEN]; union mlxsw_sp_l3addr daddr; union mlxsw_sp_l3addr saddr; + u16 vid; }; struct mlxsw_sp_span_entry_ops; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 4ed01182a82c2..e97652c40d13a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -49,7 +49,9 @@ #include <linux/netlink.h> #include <net/switchdev.h> +#include "spectrum_span.h" #include "spectrum_router.h" +#include "spectrum_switchdev.h" #include "spectrum.h" #include "core.h" #include "reg.h" @@ -239,7 +241,7 @@ __mlxsw_sp_bridge_port_find(const struct mlxsw_sp_bridge_device *bridge_device, return NULL; } -static struct mlxsw_sp_bridge_port * +struct mlxsw_sp_bridge_port * mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, struct net_device *brport_dev) { @@ -922,6 +924,9 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, break; } + if (switchdev_trans_ph_commit(trans)) + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); + return err; } @@ -1139,6 +1144,9 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_bridge_port *bridge_port; u16 vid; + if (netif_is_bridge_master(orig_dev)) + return -EOPNOTSUPP; + if (switchdev_trans_ph_prepare(trans)) return 0; @@ -1646,18 +1654,57 @@ mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port, } } +struct mlxsw_sp_span_respin_work { + struct work_struct work; + struct mlxsw_sp *mlxsw_sp; +}; + +static void mlxsw_sp_span_respin_work(struct work_struct *work) +{ + struct mlxsw_sp_span_respin_work *respin_work = + container_of(work, struct mlxsw_sp_span_respin_work, work); + + rtnl_lock(); + mlxsw_sp_span_respin(respin_work->mlxsw_sp); + rtnl_unlock(); + kfree(respin_work); +} + +static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_span_respin_work *respin_work; + + respin_work = kzalloc(sizeof(*respin_work), GFP_ATOMIC); + if (!respin_work) + return; + + INIT_WORK(&respin_work->work, mlxsw_sp_span_respin_work); + respin_work->mlxsw_sp = mlxsw_sp; + + mlxsw_core_schedule_work(&respin_work->work); +} + static int mlxsw_sp_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + const struct switchdev_obj_port_vlan *vlan; int err = 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, - SWITCHDEV_OBJ_PORT_VLAN(obj), - trans); + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans); + + if (switchdev_trans_ph_prepare(trans)) { + /* The event is emitted before the changes are actually + * applied to the bridge. Therefore schedule the respin + * call for later, so that the respin logic sees the + * updated bridge state. + */ + mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp); + } break; case SWITCHDEV_OBJ_ID_PORT_MDB: err = mlxsw_sp_port_mdb_add(mlxsw_sp_port, @@ -1697,6 +1744,9 @@ static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, struct mlxsw_sp_bridge_port *bridge_port; u16 vid; + if (netif_is_bridge_master(orig_dev)) + return -EOPNOTSUPP; + bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev); if (WARN_ON(!bridge_port)) return -EINVAL; @@ -1806,6 +1856,8 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev, break; } + mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp); + return err; } @@ -2222,6 +2274,8 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work) switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; err = mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, true); if (err) break; @@ -2231,10 +2285,20 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false); break; + case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_DEL_TO_BRIDGE: + /* These events are only used to potentially update an existing + * SPAN mirror. + */ + break; } + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); + out: rtnl_unlock(); kfree(switchdev_work->fdb_info.addr); @@ -2263,7 +2327,9 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ - case SWITCHDEV_FDB_DEL_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_DEL_TO_BRIDGE: memcpy(&switchdev_work->fdb_info, ptr, sizeof(switchdev_work->fdb_info)); switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); @@ -2295,6 +2361,12 @@ static struct notifier_block mlxsw_sp_switchdev_notifier = { .notifier_call = mlxsw_sp_switchdev_event, }; +u8 +mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port) +{ + return bridge_port->stp_state; +} + static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h new file mode 100644 index 0000000000000..bc44d5effc28b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 + * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/netdevice.h> + +struct mlxsw_sp_bridge; +struct mlxsw_sp_bridge_port; + +struct mlxsw_sp_bridge_port * +mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, + struct net_device *brport_dev); + +u8 mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index a655c5850aa6a..3922c1cfe5f5a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -417,13 +417,10 @@ static int mlxsw_sx_port_get_phys_port_name(struct net_device *dev, char *name, size_t len) { struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - int err; - - err = snprintf(name, len, "p%d", mlxsw_sx_port->mapping.module + 1); - if (err >= len) - return -EINVAL; - return 0; + return mlxsw_core_port_get_phys_port_name(mlxsw_sx_port->mlxsw_sx->core, + mlxsw_sx_port->local_port, + name, len); } static const struct net_device_ops mlxsw_sx_port_netdev_ops = { @@ -1149,7 +1146,7 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, } mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port, - mlxsw_sx_port, dev, false, 0); + mlxsw_sx_port, dev, module + 1, false, 0); mlxsw_sx->ports[local_port] = mlxsw_sx_port; return 0; |