diff options
10 files changed, 381 insertions, 1 deletions
diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst index 43d72c8b713b..754c81436408 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst @@ -1341,3 +1341,35 @@ Device Counters - The number of times the device owned queue had not enough buffers allocated. - Error + + * - `pci_bw_inbound_high` + - The number of times the device crossed the high inbound pcie bandwidth + threshold. To be compared to pci_bw_inbound_low to check if the device + is in a congested state. + If pci_bw_inbound_high == pci_bw_inbound_low then the device is not congested. + If pci_bw_inbound_high > pci_bw_inbound_low then the device is congested. + - Tnformative + + * - `pci_bw_inbound_low` + - The number of times the device crossed the low inbound PCIe bandwidth + threshold. To be compared to pci_bw_inbound_high to check if the device + is in a congested state. + If pci_bw_inbound_high == pci_bw_inbound_low then the device is not congested. + If pci_bw_inbound_high > pci_bw_inbound_low then the device is congested. + - Informative + + * - `pci_bw_outbound_high` + - The number of times the device crossed the high outbound pcie bandwidth + threshold. To be compared to pci_bw_outbound_low to check if the device + is in a congested state. + If pci_bw_outbound_high == pci_bw_outbound_low then the device is not congested. + If pci_bw_outbound_high > pci_bw_outbound_low then the device is congested. + - Informative + + * - `pci_bw_outbound_low` + - The number of times the device crossed the low outbound PCIe bandwidth + threshold. To be compared to pci_bw_outbound_high to check if the device + is in a congested state. + If pci_bw_outbound_high == pci_bw_outbound_low then the device is not congested. + If pci_bw_outbound_high > pci_bw_outbound_low then the device is congested. + - Informative diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index d292e6a9e22c..650df18a9216 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \ en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \ - lib/crypto.o lib/sd.o + lib/crypto.o lib/sd.o en/pcie_cong_event.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 64e69e616b1f..b6340e9453c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -920,6 +920,8 @@ struct mlx5e_priv { struct notifier_block events_nb; struct notifier_block blocking_events_nb; + struct mlx5e_pcie_cong_event *cong_event; + struct udp_tunnel_nic_info nic_info; #ifdef CONFIG_MLX5_CORE_EN_DCB struct mlx5e_dcbx dcbx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c new file mode 100644 index 000000000000..0ed017569a19 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. + +#include "en.h" +#include "pcie_cong_event.h" + +#define MLX5E_CONG_HIGH_STATE 0x7 + +enum { + MLX5E_INBOUND_CONG = BIT(0), + MLX5E_OUTBOUND_CONG = BIT(1), +}; + +struct mlx5e_pcie_cong_thresh { + u16 inbound_high; + u16 inbound_low; + u16 outbound_high; + u16 outbound_low; +}; + +struct mlx5e_pcie_cong_stats { + u32 pci_bw_inbound_high; + u32 pci_bw_inbound_low; + u32 pci_bw_outbound_high; + u32 pci_bw_outbound_low; +}; + +struct mlx5e_pcie_cong_event { + u64 obj_id; + + struct mlx5e_priv *priv; + + /* For event notifier and workqueue. */ + struct work_struct work; + struct mlx5_nb nb; + + /* Stores last read state. */ + u8 state; + + /* For ethtool stats group. */ + struct mlx5e_pcie_cong_stats stats; +}; + +/* In units of 0.01 % */ +static const struct mlx5e_pcie_cong_thresh default_thresh_config = { + .inbound_high = 9000, + .inbound_low = 7500, + .outbound_high = 9000, + .outbound_low = 7500, +}; + +static const struct counter_desc mlx5e_pcie_cong_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats, + pci_bw_inbound_high) }, + { MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats, + pci_bw_inbound_low) }, + { MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats, + pci_bw_outbound_high) }, + { MLX5E_DECLARE_STAT(struct mlx5e_pcie_cong_stats, + pci_bw_outbound_low) }, +}; + +#define NUM_PCIE_CONG_COUNTERS ARRAY_SIZE(mlx5e_pcie_cong_stats_desc) + +static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(pcie_cong) +{ + return priv->cong_event ? NUM_PCIE_CONG_COUNTERS : 0; +} + +static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(pcie_cong) {} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(pcie_cong) +{ + if (!priv->cong_event) + return; + + for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++) + ethtool_puts(data, mlx5e_pcie_cong_stats_desc[i].format); +} + +static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(pcie_cong) +{ + if (!priv->cong_event) + return; + + for (int i = 0; i < NUM_PCIE_CONG_COUNTERS; i++) { + u32 ctr = MLX5E_READ_CTR32_CPU(&priv->cong_event->stats, + mlx5e_pcie_cong_stats_desc, + i); + + mlx5e_ethtool_put_stat(data, ctr); + } +} + +MLX5E_DEFINE_STATS_GRP(pcie_cong, 0); + +static int +mlx5_cmd_pcie_cong_event_set(struct mlx5_core_dev *dev, + const struct mlx5e_pcie_cong_thresh *config, + u64 *obj_id) +{ + u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + void *cong_obj; + void *hdr; + int err; + + hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr); + cong_obj = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, cong_obj); + + MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + + MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type, + MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT); + + MLX5_SET(pcie_cong_event_obj, cong_obj, inbound_event_en, 1); + MLX5_SET(pcie_cong_event_obj, cong_obj, outbound_event_en, 1); + + MLX5_SET(pcie_cong_event_obj, cong_obj, + inbound_cong_high_threshold, config->inbound_high); + MLX5_SET(pcie_cong_event_obj, cong_obj, + inbound_cong_low_threshold, config->inbound_low); + + MLX5_SET(pcie_cong_event_obj, cong_obj, + outbound_cong_high_threshold, config->outbound_high); + MLX5_SET(pcie_cong_event_obj, cong_obj, + outbound_cong_low_threshold, config->outbound_low); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + mlx5_core_dbg(dev, "PCIe congestion event (obj_id=%llu) created. Config: in: [%u, %u], out: [%u, %u]\n", + *obj_id, + config->inbound_high, config->inbound_low, + config->outbound_high, config->outbound_low); + + return 0; +} + +static int mlx5_cmd_pcie_cong_event_destroy(struct mlx5_core_dev *dev, + u64 obj_id) +{ + u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + void *hdr; + + hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr); + MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type, + MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT); + MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_id, obj_id); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_cmd_pcie_cong_event_query(struct mlx5_core_dev *dev, + u64 obj_id, + u32 *state) +{ + u32 in[MLX5_ST_SZ_DW(pcie_cong_event_cmd_in)] = {}; + u32 out[MLX5_ST_SZ_DW(pcie_cong_event_cmd_out)]; + void *obj; + void *hdr; + u8 cong; + int err; + + hdr = MLX5_ADDR_OF(pcie_cong_event_cmd_in, in, hdr); + + MLX5_SET(general_obj_in_cmd_hdr, hdr, opcode, + MLX5_CMD_OP_QUERY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_type, + MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT); + MLX5_SET(general_obj_in_cmd_hdr, hdr, obj_id, obj_id); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + obj = MLX5_ADDR_OF(pcie_cong_event_cmd_out, out, cong_obj); + + if (state) { + cong = MLX5_GET(pcie_cong_event_obj, obj, inbound_cong_state); + if (cong == MLX5E_CONG_HIGH_STATE) + *state |= MLX5E_INBOUND_CONG; + + cong = MLX5_GET(pcie_cong_event_obj, obj, outbound_cong_state); + if (cong == MLX5E_CONG_HIGH_STATE) + *state |= MLX5E_OUTBOUND_CONG; + } + + return 0; +} + +static void mlx5e_pcie_cong_event_work(struct work_struct *work) +{ + struct mlx5e_pcie_cong_event *cong_event; + struct mlx5_core_dev *dev; + struct mlx5e_priv *priv; + u32 new_cong_state = 0; + u32 changes; + int err; + + cong_event = container_of(work, struct mlx5e_pcie_cong_event, work); + priv = cong_event->priv; + dev = priv->mdev; + + err = mlx5_cmd_pcie_cong_event_query(dev, cong_event->obj_id, + &new_cong_state); + if (err) { + mlx5_core_warn(dev, "Error %d when querying PCIe cong event object (obj_id=%llu).\n", + err, cong_event->obj_id); + return; + } + + changes = cong_event->state ^ new_cong_state; + if (!changes) + return; + + cong_event->state = new_cong_state; + + if (changes & MLX5E_INBOUND_CONG) { + if (new_cong_state & MLX5E_INBOUND_CONG) + cong_event->stats.pci_bw_inbound_high++; + else + cong_event->stats.pci_bw_inbound_low++; + } + + if (changes & MLX5E_OUTBOUND_CONG) { + if (new_cong_state & MLX5E_OUTBOUND_CONG) + cong_event->stats.pci_bw_outbound_high++; + else + cong_event->stats.pci_bw_outbound_low++; + } +} + +static int mlx5e_pcie_cong_event_handler(struct notifier_block *nb, + unsigned long event, void *eqe) +{ + struct mlx5e_pcie_cong_event *cong_event; + + cong_event = mlx5_nb_cof(nb, struct mlx5e_pcie_cong_event, nb); + queue_work(cong_event->priv->wq, &cong_event->work); + + return NOTIFY_OK; +} + +int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv) +{ + struct mlx5e_pcie_cong_event *cong_event; + struct mlx5_core_dev *mdev = priv->mdev; + int err; + + if (!mlx5_pcie_cong_event_supported(mdev)) + return 0; + + cong_event = kvzalloc_node(sizeof(*cong_event), GFP_KERNEL, + mdev->priv.numa_node); + if (!cong_event) + return -ENOMEM; + + INIT_WORK(&cong_event->work, mlx5e_pcie_cong_event_work); + MLX5_NB_INIT(&cong_event->nb, mlx5e_pcie_cong_event_handler, + OBJECT_CHANGE); + + cong_event->priv = priv; + + err = mlx5_cmd_pcie_cong_event_set(mdev, &default_thresh_config, + &cong_event->obj_id); + if (err) { + mlx5_core_warn(mdev, "Error creating a PCIe congestion event object\n"); + goto err_free; + } + + err = mlx5_eq_notifier_register(mdev, &cong_event->nb); + if (err) { + mlx5_core_warn(mdev, "Error registering notifier for the PCIe congestion event\n"); + goto err_obj_destroy; + } + + priv->cong_event = cong_event; + + return 0; + +err_obj_destroy: + mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id); +err_free: + kvfree(cong_event); + + return err; +} + +void mlx5e_pcie_cong_event_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_pcie_cong_event *cong_event = priv->cong_event; + struct mlx5_core_dev *mdev = priv->mdev; + + if (!cong_event) + return; + + priv->cong_event = NULL; + + mlx5_eq_notifier_unregister(mdev, &cong_event->nb); + cancel_work_sync(&cong_event->work); + + if (mlx5_cmd_pcie_cong_event_destroy(mdev, cong_event->obj_id)) + mlx5_core_warn(mdev, "Error destroying PCIe congestion event (obj_id=%llu)\n", + cong_event->obj_id); + + kvfree(cong_event); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h new file mode 100644 index 000000000000..b1ea46bf648a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/pcie_cong_event.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */ + +#ifndef __MLX5_PCIE_CONG_EVENT_H__ +#define __MLX5_PCIE_CONG_EVENT_H__ + +int mlx5e_pcie_cong_event_init(struct mlx5e_priv *priv); +void mlx5e_pcie_cong_event_cleanup(struct mlx5e_priv *priv); + +#endif /* __MLX5_PCIE_CONG_EVENT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index fee323ade522..bd481f3384d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -76,6 +76,7 @@ #include "en/trap.h" #include "lib/devcom.h" #include "lib/sd.h" +#include "en/pcie_cong_event.h" static bool mlx5e_hw_gro_supported(struct mlx5_core_dev *mdev) { @@ -5989,6 +5990,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) if (mlx5e_monitor_counter_supported(priv)) mlx5e_monitor_counter_init(priv); + mlx5e_pcie_cong_event_init(priv); mlx5e_hv_vhca_stats_create(priv); if (netdev->reg_state != NETREG_REGISTERED) return; @@ -6028,6 +6030,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_nic_set_rx_mode(priv); + mlx5e_pcie_cong_event_cleanup(priv); mlx5e_hv_vhca_stats_destroy(priv); if (mlx5e_monitor_counter_supported(priv)) mlx5e_monitor_counter_cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 19664fa7f217..87536f158d07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -2612,6 +2612,7 @@ mlx5e_stats_grp_t mlx5e_nic_stats_grps[] = { #ifdef CONFIG_MLX5_MACSEC &MLX5E_STATS_GRP(macsec_hw), #endif + &MLX5E_STATS_GRP(pcie_cong), }; unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index def5dea1463d..72dbcc1928ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -535,5 +535,6 @@ extern MLX5E_DECLARE_STATS_GRP(ipsec_hw); extern MLX5E_DECLARE_STATS_GRP(ipsec_sw); extern MLX5E_DECLARE_STATS_GRP(ptp); extern MLX5E_DECLARE_STATS_GRP(macsec_hw); +extern MLX5E_DECLARE_STATS_GRP(pcie_cong); #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index dfb079e59d85..66dce17219a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -585,6 +585,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4]) async_event_mask |= (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE); + if (mlx5_pcie_cong_event_supported(dev)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_OBJECT_CHANGE); + mask[0] = async_event_mask; if (MLX5_CAP_GEN(dev, event_cap)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 2e02bdea8361..c518380c4ce7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -495,4 +495,17 @@ static inline int mlx5_max_eq_cap_get(const struct mlx5_core_dev *dev) return 1 << MLX5_CAP_GEN(dev, log_max_eq); } + +static inline bool mlx5_pcie_cong_event_supported(struct mlx5_core_dev *dev) +{ + u64 features = MLX5_CAP_GEN_2_64(dev, general_obj_types_127_64); + + if (!(features & MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT)) + return false; + + if (dev->sd) + return false; + + return true; +} #endif /* __MLX5_CORE_H__ */ |