diff options
34 files changed, 1168 insertions, 173 deletions
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 69f3d6dcd9fd..473d72c36d61 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -74,6 +74,7 @@ Contents: mpls-sysctl mptcp-sysctl multiqueue + multi-pf-netdev napi net_cachelines/index netconsole diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst new file mode 100644 index 000000000000..be8e4bcadf11 --- /dev/null +++ b/Documentation/networking/multi-pf-netdev.rst @@ -0,0 +1,174 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. include:: <isonum.txt> + +=============== +Multi-PF Netdev +=============== + +Contents +======== + +- `Background`_ +- `Overview`_ +- `mlx5 implementation`_ +- `Channels distribution`_ +- `Observability`_ +- `Steering`_ +- `Mutually exclusive features`_ + +Background +========== + +The Multi-PF NIC technology enables several CPUs within a multi-socket server to connect directly to +the network, each through its own dedicated PCIe interface. Through either a connection harness that +splits the PCIe lanes between two cards or by bifurcating a PCIe slot for a single card. This +results in eliminating the network traffic traversing over the internal bus between the sockets, +significantly reducing overhead and latency, in addition to reducing CPU utilization and increasing +network throughput. + +Overview +======== + +The feature adds support for combining multiple PFs of the same port in a Multi-PF environment under +one netdev instance. It is implemented in the netdev layer. Lower-layer instances like pci func, +sysfs entry, and devlink are kept separate. +Passing traffic through different devices belonging to different NUMA sockets saves cross-NUMA +traffic and allows apps running on the same netdev from different NUMAs to still feel a sense of +proximity to the device and achieve improved performance. + +mlx5 implementation +=================== + +Multi-PF or Socket-direct in mlx5 is achieved by grouping PFs together which belong to the same +NIC and has the socket-direct property enabled, once all PFs are probed, we create a single netdev +to represent all of them, symmetrically, we destroy the netdev whenever any of the PFs is removed. + +The netdev network channels are distributed between all devices, a proper configuration would utilize +the correct close NUMA node when working on a certain app/CPU. + +We pick one PF to be a primary (leader), and it fills a special role. The other devices +(secondaries) are disconnected from the network at the chip level (set to silent mode). In silent +mode, no south <-> north traffic flowing directly through a secondary PF. It needs the assistance of +the leader PF (east <-> west traffic) to function. All Rx/Tx traffic is steered through the primary +to/from the secondaries. + +Currently, we limit the support to PFs only, and up to two PFs (sockets). + +Channels distribution +===================== + +We distribute the channels between the different PFs to achieve local NUMA node performance +on multiple NUMA nodes. + +Each combined channel works against one specific PF, creating all its datapath queues against it. We +distribute channels to PFs in a round-robin policy. + +:: + + Example for 2 PFs and 5 channels: + +--------+--------+ + | ch idx | PF idx | + +--------+--------+ + | 0 | 0 | + | 1 | 1 | + | 2 | 0 | + | 3 | 1 | + | 4 | 0 | + +--------+--------+ + + +The reason we prefer round-robin is, it is less influenced by changes in the number of channels. The +mapping between a channel index and a PF is fixed, no matter how many channels the user configures. +As the channel stats are persistent across channel's closure, changing the mapping every single time +would turn the accumulative stats less representing of the channel's history. + +This is achieved by using the correct core device instance (mdev) in each channel, instead of them +all using the same instance under "priv->mdev". + +Observability +============= +The relation between PF, irq, napi, and queue can be observed via netlink spec: + +$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}' +[{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'}, + {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'}, + {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'}, + {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'}, + {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'}, + {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}] + +$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}' +[{'id': 543, 'ifindex': 13, 'irq': 42}, + {'id': 542, 'ifindex': 13, 'irq': 41}, + {'id': 541, 'ifindex': 13, 'irq': 40}, + {'id': 540, 'ifindex': 13, 'irq': 39}, + {'id': 539, 'ifindex': 13, 'irq': 36}] + +Here you can clearly observe our channels distribution policy: + +$ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 +/proc/irq/36/mlx5_comp1@pci:0000:08:00.0 +/proc/irq/39/mlx5_comp1@pci:0000:09:00.0 +/proc/irq/40/mlx5_comp2@pci:0000:08:00.0 +/proc/irq/41/mlx5_comp2@pci:0000:09:00.0 +/proc/irq/42/mlx5_comp3@pci:0000:08:00.0 + +Steering +======== +Secondary PFs are set to "silent" mode, meaning they are disconnected from the network. + +In Rx, the steering tables belong to the primary PF only, and it is its role to distribute incoming +traffic to other PFs, via cross-vhca steering capabilities. Still maintain a single default RSS table, +that is capable of pointing to the receive queues of a different PF. + +In Tx, the primary PF creates a new Tx flow table, which is aliased by the secondaries, so they can +go out to the network through it. + +In addition, we set default XPS configuration that, based on the CPU, selects an SQ belonging to the +PF on the same node as the CPU. + +XPS default config example: + +NUMA node(s): 2 +NUMA node0 CPU(s): 0-11 +NUMA node1 CPU(s): 12-23 + +PF0 on node0, PF1 on node1. + +- /sys/class/net/eth2/queues/tx-0/xps_cpus:000001 +- /sys/class/net/eth2/queues/tx-1/xps_cpus:001000 +- /sys/class/net/eth2/queues/tx-2/xps_cpus:000002 +- /sys/class/net/eth2/queues/tx-3/xps_cpus:002000 +- /sys/class/net/eth2/queues/tx-4/xps_cpus:000004 +- /sys/class/net/eth2/queues/tx-5/xps_cpus:004000 +- /sys/class/net/eth2/queues/tx-6/xps_cpus:000008 +- /sys/class/net/eth2/queues/tx-7/xps_cpus:008000 +- /sys/class/net/eth2/queues/tx-8/xps_cpus:000010 +- /sys/class/net/eth2/queues/tx-9/xps_cpus:010000 +- /sys/class/net/eth2/queues/tx-10/xps_cpus:000020 +- /sys/class/net/eth2/queues/tx-11/xps_cpus:020000 +- /sys/class/net/eth2/queues/tx-12/xps_cpus:000040 +- /sys/class/net/eth2/queues/tx-13/xps_cpus:040000 +- /sys/class/net/eth2/queues/tx-14/xps_cpus:000080 +- /sys/class/net/eth2/queues/tx-15/xps_cpus:080000 +- /sys/class/net/eth2/queues/tx-16/xps_cpus:000100 +- /sys/class/net/eth2/queues/tx-17/xps_cpus:100000 +- /sys/class/net/eth2/queues/tx-18/xps_cpus:000200 +- /sys/class/net/eth2/queues/tx-19/xps_cpus:200000 +- /sys/class/net/eth2/queues/tx-20/xps_cpus:000400 +- /sys/class/net/eth2/queues/tx-21/xps_cpus:400000 +- /sys/class/net/eth2/queues/tx-22/xps_cpus:000800 +- /sys/class/net/eth2/queues/tx-23/xps_cpus:800000 + +Mutually exclusive features +=========================== + +The nature of Multi-PF, where different channels work with different PFs, conflicts with +stateful features where the state is maintained in one of the PFs. +For example, in the TLS device-offload feature, special context objects are created per connection +and maintained in the PF. Transitioning between different RQs/SQs would break the feature. Hence, +we disable this combination for now. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index c44870b175f9..76dc5a9b9648 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -29,7 +29,7 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en/rqt.o en/tir.o en/rss.o en/rx_res.o \ en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/pool.o \ en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o en/devlink.o en/ptp.o \ en/qos.o en/htb.o en/trap.o en/fs_tt_redirect.o en/selq.o \ - lib/crypto.o + lib/crypto.o lib/sd.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 55c6ace0acd5..84db05fb9389 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -60,6 +60,7 @@ #include "lib/clock.h" #include "en/rx_res.h" #include "en/selq.h" +#include "lib/sd.h" extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; @@ -791,6 +792,8 @@ struct mlx5e_channel { struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; + int vec_ix; + int sd_ix; int cpu; /* Sync between icosq recovery and XSK enable/disable. */ struct mutex icosq_recovery_lock; @@ -914,7 +917,7 @@ struct mlx5e_priv { bool tx_ptp_opened; bool rx_ptp_opened; struct hwtstamp_config tstamp; - u16 q_counter; + u16 q_counter[MLX5_SD_MAX_GROUP_SZ]; u16 drop_rq_q_counter; struct notifier_block events_nb; struct notifier_block blocking_events_nb; @@ -1029,12 +1032,12 @@ struct mlx5e_xsk_param; struct mlx5e_rq_param; int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq); #define MLX5E_RQ_WQES_TIMEOUT 20000 /* msecs */ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); void mlx5e_close_rq(struct mlx5e_rq *rq); -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param); +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter); void mlx5e_destroy_rq(struct mlx5e_rq *rq); struct mlx5e_sq_param; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c index 48581ea3adcb..874a1016623c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.c @@ -23,20 +23,26 @@ bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix) return test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); } -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); *rqn = c->rq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn) +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id) { struct mlx5e_channel *c = mlx5e_channels_get(chs, ix); WARN_ON_ONCE(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)); *rqn = c->xskrq.rqn; + if (vhca_id) + *vhca_id = MLX5_CAP_GEN(c->mdev, vhca_id); } bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h index 637ca90daaa8..6715aa9383b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/channels.h @@ -10,8 +10,10 @@ struct mlx5e_channels; unsigned int mlx5e_channels_get_num(struct mlx5e_channels *chs); bool mlx5e_channels_is_xsk(struct mlx5e_channels *chs, unsigned int ix); -void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); -void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn); +void mlx5e_channels_get_regular_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); +void mlx5e_channels_get_xsk_rqn(struct mlx5e_channels *chs, unsigned int ix, u32 *rqn, + u32 *vhca_id); bool mlx5e_channels_get_ptp_rqn(struct mlx5e_channels *chs, u32 *rqn); #endif /* __MLX5_EN_CHANNELS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 40c8df111754..e2d8d2754be0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -20,10 +20,8 @@ #define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1 #define NUM_REQ_Q_COUNTERS_S1 MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1 -int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +static int mlx5e_monitor_counter_cap(struct mlx5_core_dev *mdev) { - struct mlx5_core_dev *mdev = priv->mdev; - if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters)) return false; if (MLX5_CAP_PCAM_REG(mdev, ppcnt) && @@ -36,24 +34,38 @@ int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) return true; } -static void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv) +int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (!mlx5e_monitor_counter_cap(pos)) + return false; + return true; +} + +static void mlx5e_monitor_counter_arm(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(arm_monitor_counter_in)] = {}; MLX5_SET(arm_monitor_counter_in, in, opcode, MLX5_CMD_OP_ARM_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, arm_monitor_counter, in); + mlx5_cmd_exec_in(mdev, arm_monitor_counter, in); } static void mlx5e_monitor_counters_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, monitor_counters_work); + struct mlx5_core_dev *pos; + int i; mutex_lock(&priv->state_lock); mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) + mlx5e_monitor_counter_arm(pos); } static int mlx5e_monitor_event_handler(struct notifier_block *nb, @@ -97,15 +109,13 @@ static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in) } /* check if mlx5e_monitor_counter_supported before calling this function*/ -static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) +static void mlx5e_set_monitor_counter(struct mlx5_core_dev *mdev, int q_counter) { - struct mlx5_core_dev *mdev = priv->mdev; int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters); int num_q_counters = MLX5_CAP_GEN(mdev, num_q_monitor_counters); int num_ppcnt_counters = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 : MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters); u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; - int q_counter = priv->q_counter; int cnt = 0; if (num_ppcnt_counters >= NUM_REQ_PPCNT_COUNTER_S1 && @@ -127,13 +137,17 @@ static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv) /* check if mlx5e_monitor_counter_supported before calling this function*/ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) { + struct mlx5_core_dev *pos; + int i; + INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work); MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler, MONITOR_COUNTER); - mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb); - - mlx5e_set_monitor_counter(priv); - mlx5e_monitor_counter_arm(priv); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_eq_notifier_register(pos, &priv->monitor_counters_nb); + mlx5e_set_monitor_counter(pos, priv->q_counter[i]); + mlx5e_monitor_counter_arm(pos); + } queue_work(priv->wq, &priv->update_stats_work); } @@ -141,11 +155,15 @@ void mlx5e_monitor_counter_init(struct mlx5e_priv *priv) void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(set_monitor_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(set_monitor_counter_in, in, opcode, MLX5_CMD_OP_SET_MONITOR_COUNTER); - mlx5_cmd_exec_in(priv->mdev, set_monitor_counter, in); - mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + mlx5_cmd_exec_in(pos, set_monitor_counter, in); + mlx5_eq_notifier_unregister(pos, &priv->monitor_counters_nb); + } cancel_work_sync(&priv->monitor_counters_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 5757f4f10c12..a3f31d9d527e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -688,7 +688,7 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e .napi = &c->napi, .ch_stats = c->stats, .node = cpu_to_node(c->cpu), - .ix = c->ix, + .ix = c->vec_ix, }; } @@ -959,7 +959,6 @@ static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *param int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1021,7 +1020,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs)); MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); @@ -1032,7 +1030,6 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, } void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param) { void *rqc = param->rqc; @@ -1041,7 +1038,6 @@ void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, log_wq_stride, mlx5e_get_rqwq_log_stride(MLX5_WQ_TYPE_CYCLIC, 1)); - MLX5_SET(rqc, rqc, counter_set_id, q_counter); param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); } @@ -1306,13 +1302,12 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam) { u8 icosq_log_wq_sz, async_icosq_log_wq_sz; int err; - err = mlx5e_build_rq_param(mdev, params, NULL, q_counter, &cparam->rq); + err = mlx5e_build_rq_param(mdev, params, NULL, &cparam->rq); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 6800949dafbc..9a781f18b57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -130,10 +130,8 @@ void mlx5e_build_create_cq_param(struct mlx5e_create_cq_param *ccp, struct mlx5e int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_drop_rq_param(struct mlx5_core_dev *mdev, - u16 q_counter, struct mlx5e_rq_param *param); void mlx5e_build_sq_param_common(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); @@ -149,7 +147,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev, struct mlx5e_sq_param *param); int mlx5e_build_channel_param(struct mlx5_core_dev *mdev, struct mlx5e_params *params, - u16 q_counter, struct mlx5e_channel_param *cparam); u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index a848a7fda66b..d0af7271da34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -646,7 +646,6 @@ static void mlx5e_ptp_build_sq_param(struct mlx5_core_dev *mdev, static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, struct net_device *netdev, - u16 q_counter, struct mlx5e_ptp_params *ptp_params) { struct mlx5e_rq_param *rq_params = &ptp_params->rq_param; @@ -655,7 +654,7 @@ static void mlx5e_ptp_build_rq_param(struct mlx5_core_dev *mdev, params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = netdev->max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, rq_params); + mlx5e_build_rq_param(mdev, params, NULL, rq_params); } static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, @@ -681,7 +680,7 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c, /* RQ */ if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { params->vlan_strip_disable = orig->vlan_strip_disable; - mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams); + mlx5e_ptp_build_rq_param(c->mdev, c->netdev, cparams); } } @@ -714,13 +713,16 @@ static int mlx5e_ptp_open_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param) { int node = dev_to_node(c->mdev->device); - int err; + int err, sd_ix; + u16 q_counter; err = mlx5e_init_ptp_rq(c, params, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_param, NULL, node, &c->rq); + sd_ix = mlx5_sd_ch_ix_get_dev_ix(c->mdev, MLX5E_PTP_CHANNEL_IX); + q_counter = c->priv->q_counter[sd_ix]; + return mlx5e_open_rq(params, rq_param, NULL, node, q_counter, &c->rq); } static int mlx5e_ptp_open_queues(struct mlx5e_ptp *c, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 34adf8c3f81a..e87e26f2c669 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -122,8 +122,8 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs, memset(¶m_sq, 0, sizeof(param_sq)); memset(¶m_cq, 0, sizeof(param_cq)); - mlx5e_build_sq_param(priv->mdev, params, ¶m_sq); - mlx5e_build_tx_cq_param(priv->mdev, params, ¶m_cq); + mlx5e_build_sq_param(c->mdev, params, ¶m_sq); + mlx5e_build_tx_cq_param(c->mdev, params, ¶m_cq); err = mlx5e_open_cq(c->mdev, params->tx_cq_moderation, ¶m_cq, &ccp, &sq->cq); if (err) goto err_free_sq; @@ -176,7 +176,7 @@ int mlx5e_activate_qos_sq(void *data, u16 node_qid, u32 hw_id) */ smp_wmb(); - qos_dbg(priv->mdev, "Activate QoS SQ qid %u\n", node_qid); + qos_dbg(sq->mdev, "Activate QoS SQ qid %u\n", node_qid); mlx5e_activate_txqsq(sq); return 0; @@ -190,7 +190,7 @@ void mlx5e_deactivate_qos_sq(struct mlx5e_priv *priv, u16 qid) if (!sq) /* Handle the case when the SQ failed to open. */ return; - qos_dbg(priv->mdev, "Deactivate QoS SQ qid %u\n", qid); + qos_dbg(sq->mdev, "Deactivate QoS SQ qid %u\n", qid); mlx5e_deactivate_txqsq(sq); priv->txq2sq[mlx5e_qid_from_qos(&priv->channels, qid)] = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 4358798d6ce1..25d751eba99b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -294,8 +294,8 @@ static void mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq, params = &priv->channels.params; rq_sz = mlx5e_rqwq_get_size(rq); - real_time = mlx5_is_real_time_rq(priv->mdev); - rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL)); + real_time = mlx5_is_real_time_rq(rq->mdev); + rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(rq->mdev, params, NULL)); mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 6b44ddce14e9..0ab9db319530 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -219,7 +219,6 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq, int tc) { bool stopped = netif_xmit_stopped(sq->txq); - struct mlx5e_priv *priv = sq->priv; u8 state; int err; @@ -227,7 +226,7 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + err = mlx5_core_query_sq_state(sq->mdev, sq->sqn, &state); if (!err) devlink_fmsg_u8_pair_put(fmsg, "HW state", state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c index 7b8ff7a71003..bcafb4bf9415 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c @@ -4,6 +4,33 @@ #include "rqt.h" #include <linux/mlx5/transobj.h> +static bool verify_num_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + unsigned int max_num_vhca_id = MLX5_CAP_GEN_2(mdev, max_rqt_vhca_id); + int i; + + /* Verify that all vhca_ids are in range [0, max_num_vhca_ids - 1] */ + for (i = 0; i < size; i++) + if (vhca_ids[i] >= max_num_vhca_id) + return false; + return true; +} + +static bool rqt_verify_vhca_ids(struct mlx5_core_dev *mdev, u32 *vhca_ids, + unsigned int size) +{ + if (!vhca_ids) + return true; + + if (!MLX5_CAP_GEN(mdev, cross_vhca_rqt)) + return false; + if (!verify_num_vhca_ids(mdev, vhca_ids, size)) + return false; + + return true; +} + void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels) { @@ -13,19 +40,38 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, indir->table[i] = i % num_channels; } +static void fill_rqn_list(void *rqtc, u32 *rqns, u32 *vhca_ids, unsigned int size) +{ + unsigned int i; + + if (vhca_ids) { + MLX5_SET(rqtc, rqtc, rq_vhca_id_format, 1); + for (i = 0; i < size; i++) { + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_num, rqns[i]); + MLX5_SET(rqtc, rqtc, rq_vhca[i].rq_vhca_id, vhca_ids[i]); + } + } else { + for (i = 0; i < size; i++) + MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + } +} static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u16 max_size, u32 *init_rqns, u16 init_size) + u16 max_size, u32 *init_rqns, u32 *init_vhca_ids, u16 init_size) { + int entry_sz; void *rqtc; int inlen; int err; u32 *in; - int i; + + if (!rqt_verify_vhca_ids(mdev, init_vhca_ids, init_size)) + return -EOPNOTSUPP; rqt->mdev = mdev; rqt->size = max_size; - inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + sizeof(u32) * init_size; + entry_sz = init_vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + entry_sz * init_size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -33,10 +79,9 @@ static int mlx5e_rqt_init(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context); MLX5_SET(rqtc, rqtc, rqt_max_size, rqt->size); - MLX5_SET(rqtc, rqtc, rqt_actual_size, init_size); - for (i = 0; i < init_size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], init_rqns[i]); + + fill_rqn_list(rqtc, init_rqns, init_vhca_ids, init_size); err = mlx5_core_create_rqt(rqt->mdev, in, inlen, &rqt->rqtn); @@ -49,7 +94,7 @@ int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, { u16 max_size = indir_enabled ? indir_table_size : 1; - return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, 1); + return mlx5e_rqt_init(rqt, mdev, max_size, &init_rqn, NULL, 1); } static int mlx5e_bits_invert(unsigned long a, int size) @@ -63,7 +108,8 @@ static int mlx5e_bits_invert(unsigned long a, int size) return inv; } -static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns, +static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, u32 *rss_vhca_ids, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { unsigned int i; @@ -82,30 +128,42 @@ static int mlx5e_calc_indir_rqns(u32 *rss_rqns, u32 *rqns, unsigned int num_rqns */ return -EINVAL; rss_rqns[i] = rqns[ix]; + if (vhca_ids) + rss_vhca_ids[i] = vhca_ids[ix]; } return 0; } int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; rss_rqns = kvmalloc_array(indir->actual_table_size, sizeof(*rss_rqns), GFP_KERNEL); if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, + err = mlx5e_rqt_init(rqt, mdev, indir->max_table_size, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } @@ -126,15 +184,20 @@ void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt) mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn); } -static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int size) +static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int size) { - unsigned int i; + int entry_sz; void *rqtc; int inlen; u32 *in; int err; - inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + sizeof(u32) * size; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, size)) + return -EINVAL; + + entry_sz = vhca_ids ? MLX5_ST_SZ_BYTES(rq_vhca) : MLX5_ST_SZ_BYTES(rq_num); + inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + entry_sz * size; in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; @@ -143,8 +206,8 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz MLX5_SET(modify_rqt_in, in, bitmask.rqn_list, 1); MLX5_SET(rqtc, rqtc, rqt_actual_size, size); - for (i = 0; i < size; i++) - MLX5_SET(rqtc, rqtc, rq_num[i], rqns[i]); + + fill_rqn_list(rqtc, rqns, vhca_ids, size); err = mlx5_core_modify_rqt(rqt->mdev, rqt->rqtn, in, inlen); @@ -152,17 +215,21 @@ static int mlx5e_rqt_redirect(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int siz return err; } -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn) +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id) { - return mlx5e_rqt_redirect(rqt, &rqn, 1); + return mlx5e_rqt_redirect(rqt, &rqn, vhca_id, 1); } -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir) { - u32 *rss_rqns; + u32 *rss_rqns, *rss_vhca_ids = NULL; int err; + if (!rqt_verify_vhca_ids(rqt->mdev, vhca_ids, num_rqns)) + return -EINVAL; + if (WARN_ON(rqt->size != indir->max_table_size)) return -EINVAL; @@ -170,13 +237,23 @@ int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_ if (!rss_rqns) return -ENOMEM; - err = mlx5e_calc_indir_rqns(rss_rqns, rqns, num_rqns, hfunc, indir); + if (vhca_ids) { + rss_vhca_ids = kvmalloc_array(indir->actual_table_size, sizeof(*rss_vhca_ids), + GFP_KERNEL); + if (!rss_vhca_ids) { + kvfree(rss_rqns); + return -ENOMEM; + } + } + + err = mlx5e_calc_indir_rqns(rss_rqns, rqns, rss_vhca_ids, vhca_ids, num_rqns, hfunc, indir); if (err) goto out; - err = mlx5e_rqt_redirect(rqt, rss_rqns, indir->actual_table_size); + err = mlx5e_rqt_redirect(rqt, rss_rqns, rss_vhca_ids, indir->actual_table_size); out: + kvfree(rss_vhca_ids); kvfree(rss_rqns); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h index 77fba3ebd18d..e0bc30308c77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h @@ -20,7 +20,7 @@ void mlx5e_rss_params_indir_init_uniform(struct mlx5e_rss_params_indir *indir, unsigned int num_channels); struct mlx5e_rqt { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 rqtn; u16 size; }; @@ -28,7 +28,7 @@ struct mlx5e_rqt { int mlx5e_rqt_init_direct(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, bool indir_enabled, u32 init_rqn, u32 indir_table_size); int mlx5e_rqt_init_indir(struct mlx5e_rqt *rqt, struct mlx5_core_dev *mdev, - u32 *rqns, unsigned int num_rqns, + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt); @@ -38,8 +38,9 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt) } u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels); -int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn); -int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, unsigned int num_rqns, +int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id); +int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids, + unsigned int num_rqns, u8 hfunc, struct mlx5e_rss_params_indir *indir); #endif /* __MLX5_EN_RQT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index c1545a2e8d6d..5f742f896600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -74,7 +74,7 @@ struct mlx5e_rss { struct mlx5e_tir *tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir *inner_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_rqt rqt; - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ u32 drop_rqn; bool inner_ft_support; bool enabled; @@ -473,21 +473,22 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, return 0; } -static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { int err; - err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, num_rqns, rss->hash.hfunc, &rss->indir); + err = mlx5e_rqt_redirect_indir(&rss->rqt, rqns, vhca_ids, num_rqns, rss->hash.hfunc, + &rss->indir); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), err); return err; } -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { rss->enabled = true; - mlx5e_rss_apply(rss, rqns, num_rqns); + mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); } void mlx5e_rss_disable(struct mlx5e_rss *rss) @@ -495,7 +496,7 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss) int err; rss->enabled = false; - err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn); + err = mlx5e_rqt_redirect_direct(&rss->rqt, rss->drop_rqn, NULL); if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to drop RQ %#x: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); @@ -568,7 +569,7 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc) int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns) + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns) { bool changed_indir = false; bool changed_hash = false; @@ -608,7 +609,7 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, } if (changed_indir && rss->enabled) { - err = mlx5e_rss_apply(rss, rqns, num_rqns); + err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns); if (err) { mlx5e_rss_copy(rss, old_rss); goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index d1d0bc350e92..d0df98963c8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -39,7 +39,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn); -void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); +void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); void mlx5e_rss_disable(struct mlx5e_rss *rss); int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, @@ -47,7 +47,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, - u32 *rqns, unsigned int num_rqns); + u32 *rqns, u32 *vhca_ids, unsigned int num_rqns); struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss); u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt); int mlx5e_rss_set_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index b23e224e3763..a86eade9a9e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -8,7 +8,7 @@ #define MLX5E_MAX_NUM_RSS 16 struct mlx5e_rx_res { - struct mlx5_core_dev *mdev; + struct mlx5_core_dev *mdev; /* primary */ enum mlx5e_rx_res_features features; unsigned int max_nch; u32 drop_rqn; @@ -19,6 +19,7 @@ struct mlx5e_rx_res { struct mlx5e_rss *rss[MLX5E_MAX_NUM_RSS]; bool rss_active; u32 *rss_rqns; + u32 *rss_vhca_ids; unsigned int rss_nch; struct { @@ -34,6 +35,13 @@ struct mlx5e_rx_res { /* API for rx_res_rss_* */ +static u32 *get_vhca_ids(struct mlx5e_rx_res *res, int offset) +{ + bool multi_vhca = res->features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; + + return multi_vhca ? res->rss_vhca_ids + offset : NULL; +} + void mlx5e_rx_res_rss_update_num_channels(struct mlx5e_rx_res *res, u32 nch) { int i; @@ -85,8 +93,11 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int i return PTR_ERR(rss); mlx5e_rss_set_indir_uniform(rss, init_nch); - if (res->rss_active) - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + if (res->rss_active) { + u32 *vhca_ids = get_vhca_ids(res, 0); + + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); + } res->rss[i] = rss; *rss_idx = i; @@ -153,10 +164,12 @@ static void mlx5e_rx_res_rss_enable(struct mlx5e_rx_res *res) for (i = 0; i < MLX5E_MAX_NUM_RSS; i++) { struct mlx5e_rss *rss = res->rss[i]; + u32 *vhca_ids; if (!rss) continue; - mlx5e_rss_enable(rss, res->rss_rqns, res->rss_nch); + vhca_ids = get_vhca_ids(res, 0); + mlx5e_rss_enable(rss, res->rss_rqns, vhca_ids, res->rss_nch); } } @@ -200,6 +213,7 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, const u32 *indir, const u8 *key, const u8 *hfunc) { + u32 *vhca_ids = get_vhca_ids(res, 0); struct mlx5e_rss *rss; if (rss_idx >= MLX5E_MAX_NUM_RSS) @@ -209,7 +223,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, if (!rss) return -ENOENT; - return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, res->rss_nch); + return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids, + res->rss_nch); } int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx, @@ -280,11 +295,13 @@ struct mlx5e_rss *mlx5e_rx_res_rss_get(struct mlx5e_rx_res *res, u32 rss_idx) static void mlx5e_rx_res_free(struct mlx5e_rx_res *res) { + kvfree(res->rss_vhca_ids); kvfree(res->rss_rqns); kvfree(res); } -static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch) +static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsigned int max_nch, + bool multi_vhca) { struct mlx5e_rx_res *rx_res; @@ -298,6 +315,15 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig return NULL; } + if (multi_vhca) { + rx_res->rss_vhca_ids = kvcalloc(max_nch, sizeof(*rx_res->rss_vhca_ids), GFP_KERNEL); + if (!rx_res->rss_vhca_ids) { + kvfree(rx_res->rss_rqns); + kvfree(rx_res); + return NULL; + } + } + return rx_res; } @@ -424,10 +450,11 @@ mlx5e_rx_res_create(struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features featu const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { + bool multi_vhca = features & MLX5E_RX_RES_FEATURE_MULTI_VHCA; struct mlx5e_rx_res *res; int err; - res = mlx5e_rx_res_alloc(mdev, max_nch); + res = mlx5e_rx_res_alloc(mdev, max_nch, multi_vhca); if (!res) return ERR_PTR(-ENOMEM); @@ -504,10 +531,11 @@ static void mlx5e_rx_res_channel_activate_direct(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix) { + u32 *vhca_id = get_vhca_ids(res, ix); u32 rqn = res->rss_rqns[ix]; int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, rqn, vhca_id); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -519,7 +547,7 @@ static void mlx5e_rx_res_channel_deactivate_direct(struct mlx5e_rx_res *res, { int err; - err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->channels[ix].direct_rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (channel %u): err = %d\n", mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), @@ -534,10 +562,12 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann nch = mlx5e_channels_get_num(chs); for (ix = 0; ix < chs->num; ix++) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (mlx5e_channels_is_xsk(chs, ix)) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); } res->rss_nch = chs->num; @@ -554,7 +584,7 @@ void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_chann if (!mlx5e_channels_get_ptp_rqn(chs, &rqn)) rqn = res->drop_rqn; - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -573,7 +603,7 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) mlx5e_rx_res_channel_deactivate_direct(res, ix); if (res->features & MLX5E_RX_RES_FEATURE_PTP) { - err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn); + err = mlx5e_rqt_redirect_direct(&res->ptp.rqt, res->drop_rqn, NULL); if (err) mlx5_core_warn(res->mdev, "Failed to redirect direct RQT %#x to drop RQ %#x (PTP): err = %d\n", mlx5e_rqt_get_rqtn(&res->ptp.rqt), @@ -584,10 +614,12 @@ void mlx5e_rx_res_channels_deactivate(struct mlx5e_rx_res *res) void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *chs, unsigned int ix, bool xsk) { + u32 *vhca_id = get_vhca_ids(res, ix); + if (xsk) - mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_xsk_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); else - mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix]); + mlx5e_channels_get_regular_rqn(chs, ix, &res->rss_rqns[ix], vhca_id); mlx5e_rx_res_rss_enable(res); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 82aaba8a82b3..7b1a9f0f1874 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -18,6 +18,7 @@ struct mlx5e_rss_params_hash; enum mlx5e_rx_res_features { MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0), MLX5E_RX_RES_FEATURE_PTP = BIT(1), + MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2), }; /* Setup */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index ac458a8d10e0..53ca16cb9c41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -63,10 +63,12 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) struct mlx5e_create_cq_param ccp = {}; struct dim_cq_moder trap_moder = {}; struct mlx5e_rq *rq = &t->rq; + u16 q_counter; int node; int err; node = dev_to_node(mdev->device); + q_counter = priv->q_counter[0]; ccp.netdev = priv->netdev; ccp.wq = priv->wq; @@ -79,7 +81,7 @@ static int mlx5e_open_trap_rq(struct mlx5e_priv *priv, struct mlx5e_trap *t) return err; mlx5e_init_trap_rq(t, &t->params, rq); - err = mlx5e_open_rq(&t->params, rq_param, NULL, node, rq); + err = mlx5e_open_rq(&t->params, rq_param, NULL, node, q_counter, rq); if (err) goto err_destroy_cq; @@ -116,15 +118,14 @@ static int mlx5e_create_trap_direct_rq_tir(struct mlx5_core_dev *mdev, struct ml } static void mlx5e_build_trap_params(struct mlx5_core_dev *mdev, - int max_mtu, u16 q_counter, - struct mlx5e_trap *t) + int max_mtu, struct mlx5e_trap *t) { struct mlx5e_params *params = &t->params; params->rq_wq_type = MLX5_WQ_TYPE_CYCLIC; mlx5e_init_rq_type_params(mdev, params); params->sw_mtu = max_mtu; - mlx5e_build_rq_param(mdev, params, NULL, q_counter, &t->rq_param); + mlx5e_build_rq_param(mdev, params, NULL, &t->rq_param); } static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) @@ -138,7 +139,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) if (!t) return ERR_PTR(-ENOMEM); - mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, priv->q_counter, t); + mlx5e_build_trap_params(priv->mdev, netdev->max_mtu, t); t->priv = priv; t->mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index ebada0c5af3c..db776e515b6a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -6,10 +6,10 @@ #include "setup.h" #include "en/params.h" -static int mlx5e_xsk_map_pool(struct mlx5e_priv *priv, +static int mlx5e_xsk_map_pool(struct mlx5_core_dev *mdev, struct xsk_buff_pool *pool) { - struct device *dev = mlx5_core_dma_dev(priv->mdev); + struct device *dev = mlx5_core_dma_dev(mdev); return xsk_pool_dma_map(pool, dev, DMA_ATTR_SKIP_CPU_SYNC); } @@ -89,7 +89,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, if (unlikely(!mlx5e_xsk_is_pool_sane(pool))) return -EINVAL; - err = mlx5e_xsk_map_pool(priv, pool); + err = mlx5e_xsk_map_pool(mlx5_sd_ch_ix_get_dev(priv->mdev, ix), pool); if (unlikely(err)) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 82e6abbc1734..06592b9f0424 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -49,10 +49,9 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params, static void mlx5e_build_xsk_cparam(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, - u16 q_counter, struct mlx5e_channel_param *cparam) { - mlx5e_build_rq_param(mdev, params, xsk, q_counter, &cparam->rq); + mlx5e_build_rq_param(mdev, params, xsk, &cparam->rq); mlx5e_build_xdpsq_param(mdev, params, xsk, &cparam->xdp_sq); } @@ -93,6 +92,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param struct mlx5e_rq_param *rq_params, struct xsk_buff_pool *pool, struct mlx5e_xsk_param *xsk) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; struct mlx5e_rq *xskrq = &c->xskrq; int err; @@ -100,7 +100,7 @@ static int mlx5e_open_xsk_rq(struct mlx5e_channel *c, struct mlx5e_params *param if (err) return err; - err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), xskrq); + err = mlx5e_open_rq(params, rq_params, xsk, cpu_to_node(c->cpu), q_counter, xskrq); if (err) return err; @@ -125,7 +125,7 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, if (!cparam) return -ENOMEM; - mlx5e_build_xsk_cparam(priv->mdev, params, xsk, priv->q_counter, cparam); + mlx5e_build_xsk_cparam(priv->mdev, params, xsk, cparam); err = mlx5e_open_cq(c->mdev, params->rx_cq_moderation, &cparam->rq.cqp, &ccp, &c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index 984fa04bd331..e3e57c849436 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -96,7 +96,7 @@ bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev) { u8 max_sq_wqebbs = mlx5e_get_max_sq_wqebbs(mdev); - if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx)) + if (is_kdump_kernel() || !MLX5_CAP_GEN(mdev, tls_rx) || mlx5_get_sd(mdev)) return false; /* Check the possibility to post the required ICOSQ WQEs. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index f11075e67658..adc6d8ea0960 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -11,6 +11,7 @@ #ifdef CONFIG_MLX5_EN_TLS #include "lib/crypto.h" +#include "lib/mlx5.h" struct mlx5_crypto_dek *mlx5_ktls_create_key(struct mlx5_crypto_dek_pool *dek_pool, struct tls_crypto_info *crypto_info); @@ -61,7 +62,8 @@ void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_ static inline bool mlx5e_is_ktls_tx(struct mlx5_core_dev *mdev) { - return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx); + return !is_kdump_kernel() && MLX5_CAP_GEN(mdev, tls_tx) && + !mlx5_get_sd(mdev); } bool mlx5e_is_ktls_rx(struct mlx5_core_dev *mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 9b597cb24598..65ccb33edafb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -267,7 +267,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, goto err_out; } - pdev = mlx5_core_dma_dev(sq->channel->priv->mdev); + pdev = mlx5_core_dma_dev(sq->channel->mdev); buf->dma_addr = dma_map_single(pdev, &buf->progress, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { @@ -425,14 +425,12 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, { struct mlx5e_ktls_rx_resync_buf *buf = wi->tls_get_params.buf; struct mlx5e_ktls_offload_context_rx *priv_rx; - struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; - resync = &priv_rx->resync; - dev = mlx5_core_dma_dev(resync->priv->mdev); + dev = mlx5_core_dma_dev(sq->channel->mdev); if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index be809556b2e1..91848eae4565 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -70,6 +70,7 @@ #include "qos.h" #include "en/trap.h" #include "lib/devcom.h" +#include "lib/sd.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift, enum mlx5e_mpwrq_umr_mode umr_mode) @@ -1024,7 +1025,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) mlx5_wq_destroy(&rq->wq_ctrl); } -int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) +int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter) { struct mlx5_core_dev *mdev = rq->mdev; u8 ts_format; @@ -1051,6 +1052,7 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param) MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); MLX5_SET(rqc, rqc, ts_format, ts_format); + MLX5_SET(rqc, rqc, counter_set_id, q_counter); MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, rq->wq_ctrl.db.dma); @@ -1274,7 +1276,7 @@ void mlx5e_free_rx_descs(struct mlx5e_rq *rq) } int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, - struct mlx5e_xsk_param *xsk, int node, + struct mlx5e_xsk_param *xsk, int node, u16 q_counter, struct mlx5e_rq *rq) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1287,7 +1289,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, if (err) return err; - err = mlx5e_create_rq(rq, param); + err = mlx5e_create_rq(rq, param, q_counter); if (err) goto err_free_rq; @@ -2335,13 +2337,14 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate) static int mlx5e_open_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_rq_param *rq_params) { + u16 q_counter = c->priv->q_counter[c->sd_ix]; int err; err = mlx5e_init_rxq_rq(c, params, rq_params->xdp_frag_size, &c->rq); if (err) return err; - return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), &c->rq); + return mlx5e_open_rq(params, rq_params, NULL, cpu_to_node(c->cpu), q_counter, &c->rq); } static int mlx5e_open_queues(struct mlx5e_channel *c, @@ -2528,14 +2531,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct xsk_buff_pool *xsk_pool, struct mlx5e_channel **cp) { - int cpu = mlx5_comp_vector_get_cpu(priv->mdev, ix); struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev; struct mlx5e_xsk_param xsk; struct mlx5e_channel *c; unsigned int irq; + int vec_ix; + int cpu; int err; - err = mlx5_comp_irqn_get(priv->mdev, ix, &irq); + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); + cpu = mlx5_comp_vector_get_cpu(mdev, vec_ix); + + err = mlx5_comp_irqn_get(mdev, vec_ix, &irq); if (err) return err; @@ -2548,18 +2557,20 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, return -ENOMEM; c->priv = priv; - c->mdev = priv->mdev; + c->mdev = mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->vec_ix = vec_ix; + c->sd_ix = mlx5_sd_ch_ix_get_dev_ix(mdev, ix); c->cpu = cpu; - c->pdev = mlx5_core_dma_dev(priv->mdev); + c->pdev = mlx5_core_dma_dev(mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); + c->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix]->ch; c->aff_mask = irq_get_effective_affinity_mask(irq); - c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); + c->lag_port = mlx5e_enumerate_lag_port(mdev, ix); netif_napi_add(netdev, &c->napi, mlx5e_napi_poll); netif_napi_set_irq(&c->napi, irq); @@ -2654,7 +2665,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, if (!chs->c || !cparam) goto err_free; - err = mlx5e_build_channel_param(priv->mdev, &chs->params, priv->q_counter, cparam); + err = mlx5e_build_channel_param(priv->mdev, &chs->params, cparam); if (err) goto err_free; @@ -2942,15 +2953,18 @@ static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_update_netdev_queues); static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = priv->mdev; - int num_comp_vectors, ix, irq; - - num_comp_vectors = mlx5_comp_vectors_max(mdev); + int ix; for (ix = 0; ix < params->num_channels; ix++) { + int num_comp_vectors, irq, vec_ix; + struct mlx5_core_dev *mdev; + + mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix); + num_comp_vectors = mlx5_comp_vectors_max(mdev); cpumask_clear(priv->scratchpad.cpumask); + vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix); - for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) { + for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) { int cpu = mlx5_comp_vector_get_cpu(mdev, irq); cpumask_set_cpu(cpu, priv->scratchpad.cpumask); @@ -3342,7 +3356,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, struct mlx5e_cq *cq = &drop_rq->cq; int err; - mlx5e_build_drop_rq_param(mdev, priv->drop_rq_q_counter, &rq_param); + mlx5e_build_drop_rq_param(mdev, &rq_param); err = mlx5e_alloc_drop_cq(priv, cq, &cq_param); if (err) @@ -3356,7 +3370,7 @@ int mlx5e_open_drop_rq(struct mlx5e_priv *priv, if (err) goto err_destroy_cq; - err = mlx5e_create_rq(drop_rq, &rq_param); + err = mlx5e_create_rq(drop_rq, &rq_param, priv->drop_rq_q_counter); if (err) goto err_free_rq; @@ -5271,13 +5285,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {}; struct mlx5_core_dev *mdev = priv->mdev; - int err; + struct mlx5_core_dev *pos; + int err, i; MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER); - err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); - if (!err) - priv->q_counter = - MLX5_GET(alloc_q_counter_out, out, counter_set_id); + + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5_cmd_exec_inout(pos, alloc_q_counter, in, out); + if (!err) + priv->q_counter[i] = + MLX5_GET(alloc_q_counter_out, out, counter_set_id); + } err = mlx5_cmd_exec_inout(mdev, alloc_q_counter, in, out); if (!err) @@ -5288,13 +5306,17 @@ void mlx5e_create_q_counters(struct mlx5e_priv *priv) void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) { u32 in[MLX5_ST_SZ_DW(dealloc_q_counter_in)] = {}; + struct mlx5_core_dev *pos; + int i; MLX5_SET(dealloc_q_counter_in, in, opcode, MLX5_CMD_OP_DEALLOC_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(dealloc_q_counter_in, in, counter_set_id, - priv->q_counter); - mlx5_cmd_exec_in(priv->mdev, dealloc_q_counter, in); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(dealloc_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + mlx5_cmd_exec_in(pos, dealloc_q_counter, in); + } } if (priv->drop_rq_q_counter) { @@ -5378,6 +5400,8 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) features = MLX5E_RX_RES_FEATURE_PTP; if (mlx5_tunnel_inner_ft_supported(mdev)) features |= MLX5E_RX_RES_FEATURE_INNER_FT; + if (mlx5_get_sd(priv->mdev)) + features |= MLX5E_RX_RES_FEATURE_MULTI_VHCA; priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch, priv->drop_rq.rqn, &priv->channels.params.packet_merge, @@ -5987,28 +6011,52 @@ void mlx5e_destroy_netdev(struct mlx5e_priv *priv) free_netdev(netdev); } -static int mlx5e_resume(struct auxiliary_device *adev) +static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = edev->mdev; - int err; + struct mlx5_core_dev *pos, *to; + int err, i; if (netif_device_present(netdev)) return 0; - err = mlx5e_create_mdev_resources(mdev, true); - if (err) - return err; + mlx5_sd_for_each_dev(i, mdev, pos) { + err = mlx5e_create_mdev_resources(pos, true); + if (err) + goto err_destroy_mdev_res; + } err = mlx5e_attach_netdev(priv); - if (err) { - mlx5e_destroy_mdev_resources(mdev); + if (err) + goto err_destroy_mdev_res; + + return 0; + +err_destroy_mdev_res: + to = pos; + mlx5_sd_for_each_dev_to(i, mdev, to, pos) + mlx5e_destroy_mdev_resources(pos); + return err; +} + +static int mlx5e_resume(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) return err; - } + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_resume(actual_adev); return 0; } @@ -6018,21 +6066,36 @@ static int _mlx5e_suspend(struct auxiliary_device *adev) struct mlx5e_priv *priv = mlx5e_dev->priv; struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_core_dev *pos; + int i; if (!netif_device_present(netdev)) { if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); return -ENODEV; } mlx5e_detach_netdev(priv); - mlx5e_destroy_mdev_resources(mdev); + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + return 0; } static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state) { - return _mlx5e_suspend(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err = 0; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + err = _mlx5e_suspend(actual_adev); + + mlx5_sd_cleanup(mdev); + return err; } static int _mlx5e_probe(struct auxiliary_device *adev) @@ -6078,9 +6141,9 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_destroy_netdev; } - err = mlx5e_resume(adev); + err = _mlx5e_resume(adev); if (err) { - mlx5_core_err(mdev, "mlx5e_resume failed, %d\n", err); + mlx5_core_err(mdev, "_mlx5e_resume failed, %d\n", err); goto err_profile_cleanup; } @@ -6111,15 +6174,29 @@ err_devlink_unregister: static int mlx5e_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id) { - return _mlx5e_probe(adev); + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + int err; + + err = mlx5_sd_init(mdev); + if (err) + return err; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + return _mlx5e_probe(actual_adev); + return 0; } -static void mlx5e_remove(struct auxiliary_device *adev) +static void _mlx5e_remove(struct auxiliary_device *adev) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); struct mlx5e_priv *priv = mlx5e_dev->priv; + struct mlx5_core_dev *mdev = edev->mdev; - mlx5_core_uplink_netdev_set(priv->mdev, NULL); + mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); _mlx5e_suspend(adev); @@ -6129,6 +6206,19 @@ static void mlx5e_remove(struct auxiliary_device *adev) mlx5e_destroy_devlink(mlx5e_dev); } +static void mlx5e_remove(struct auxiliary_device *adev) +{ + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); + struct mlx5_core_dev *mdev = edev->mdev; + struct auxiliary_device *actual_adev; + + actual_adev = mlx5_sd_get_adev(mdev, adev, edev->idx); + if (actual_adev) + _mlx5e_remove(actual_adev); + + mlx5_sd_cleanup(mdev); +} + static const struct auxiliary_device_id mlx5e_id_table[] = { { .name = MLX5_ADEV_NAME ".eth", }, {}, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 4b96ad657145..f3d0898bdbc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -561,11 +561,23 @@ static const struct counter_desc drop_rq_stats_desc[] = { #define NUM_Q_COUNTERS ARRAY_SIZE(q_stats_desc) #define NUM_DROP_RQ_COUNTERS ARRAY_SIZE(drop_rq_stats_desc) +static bool q_counter_any(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *pos; + int i; + + mlx5_sd_for_each_dev(i, priv->mdev, pos) + if (priv->q_counter[i++]) + return true; + + return false; +} + static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(qcnt) { int num_stats = 0; - if (priv->q_counter) + if (q_counter_any(priv)) num_stats += NUM_Q_COUNTERS; if (priv->drop_rq_q_counter) @@ -578,7 +590,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, q_stats_desc[i].format); @@ -593,7 +605,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(qcnt) { int i; - for (i = 0; i < NUM_Q_COUNTERS && priv->q_counter; i++) + for (i = 0; i < NUM_Q_COUNTERS && q_counter_any(priv); i++) data[idx++] = MLX5E_READ_CTR32_CPU(&priv->stats.qcnt, q_stats_desc, i); for (i = 0; i < NUM_DROP_RQ_COUNTERS && priv->drop_rq_q_counter; i++) @@ -607,18 +619,23 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(qcnt) struct mlx5e_qcounter_stats *qcnt = &priv->stats.qcnt; u32 out[MLX5_ST_SZ_DW(query_q_counter_out)] = {}; u32 in[MLX5_ST_SZ_DW(query_q_counter_in)] = {}; - int ret; + struct mlx5_core_dev *pos; + u32 rx_out_of_buffer = 0; + int ret, i; MLX5_SET(query_q_counter_in, in, opcode, MLX5_CMD_OP_QUERY_Q_COUNTER); - if (priv->q_counter) { - MLX5_SET(query_q_counter_in, in, counter_set_id, - priv->q_counter); - ret = mlx5_cmd_exec_inout(priv->mdev, query_q_counter, in, out); - if (!ret) - qcnt->rx_out_of_buffer = MLX5_GET(query_q_counter_out, - out, out_of_buffer); + mlx5_sd_for_each_dev(i, priv->mdev, pos) { + if (priv->q_counter[i]) { + MLX5_SET(query_q_counter_in, in, counter_set_id, + priv->q_counter[i]); + ret = mlx5_cmd_exec_inout(pos, query_q_counter, in, out); + if (!ret) + rx_out_of_buffer += MLX5_GET(query_q_counter_out, + out, out_of_buffer); + } } + qcnt->rx_out_of_buffer = rx_out_of_buffer; if (priv->drop_rq_q_counter) { MLX5_SET(query_q_counter_in, in, counter_set_id, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9fb2c057bd78..31ed26cac9bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -766,7 +766,7 @@ static int mlx5e_hairpin_create_indirect_rqt(struct mlx5e_hairpin *hp) return err; mlx5e_rss_params_indir_init_uniform(&indir, hp->num_channels); - err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, hp->num_channels, + err = mlx5e_rqt_init_indir(&hp->indir_rqt, mdev, hp->pair->rqn, NULL, hp->num_channels, mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc, &indir); @@ -1169,7 +1169,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz), MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); - params.q_counter = priv->q_counter; + params.q_counter = priv->q_counter[0]; err = devl_param_driverinit_value_get( devlink, MLX5_DEVLINK_PARAM_ID_HAIRPIN_NUM_QUEUES, &val); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index ec32b686f586..d58032dd0df7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -10,6 +10,7 @@ enum mlx5_devcom_component { MLX5_DEVCOM_ESW_OFFLOADS, MLX5_DEVCOM_MPV, MLX5_DEVCOM_HCA_PORTS, + MLX5_DEVCOM_SD_GROUP, MLX5_DEVCOM_NUM_COMPONENTS, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 2b5826a785c4..37d5f445598c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -54,4 +54,16 @@ static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *md { return mdev->mlx5e_res.uplink_netdev; } + +struct mlx5_sd; + +static inline struct mlx5_sd *mlx5_get_sd(struct mlx5_core_dev *dev) +{ + return dev->sd; +} + +static inline void mlx5_set_sd(struct mlx5_core_dev *dev, struct mlx5_sd *sd) +{ + dev->sd = sd; +} #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c new file mode 100644 index 000000000000..5b28084e8a03 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -0,0 +1,524 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "lib/sd.h" +#include "mlx5_core.h" +#include "lib/mlx5.h" +#include "fs_cmd.h" +#include <linux/mlx5/vport.h> +#include <linux/debugfs.h> + +#define sd_info(__dev, format, ...) \ + dev_info((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) +#define sd_warn(__dev, format, ...) \ + dev_warn((__dev)->device, "Socket-Direct: " format, ##__VA_ARGS__) + +struct mlx5_sd { + u32 group_id; + u8 host_buses; + struct mlx5_devcom_comp_dev *devcom; + struct dentry *dfs; + bool primary; + union { + struct { /* primary */ + struct mlx5_core_dev *secondaries[MLX5_SD_MAX_GROUP_SZ - 1]; + struct mlx5_flow_table *tx_ft; + }; + struct { /* secondary */ + struct mlx5_core_dev *primary_dev; + u32 alias_obj_id; + }; + }; +}; + +static int mlx5_sd_get_host_buses(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return 1; + + return sd->host_buses; +} + +static struct mlx5_core_dev *mlx5_sd_get_primary(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + if (!sd) + return dev; + + return sd->primary ? dev : sd->primary_dev; +} + +struct mlx5_core_dev * +mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx) +{ + struct mlx5_sd *sd; + + if (idx == 0) + return primary; + + if (idx >= mlx5_sd_get_host_buses(primary)) + return NULL; + + sd = mlx5_get_sd(primary); + return sd->secondaries[idx - 1]; +} + +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix % mlx5_sd_get_host_buses(dev); +} + +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix) +{ + return ch_ix / mlx5_sd_get_host_buses(dev); +} + +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix) +{ + int mdev_idx = mlx5_sd_ch_ix_get_dev_ix(primary, ch_ix); + + return mlx5_sd_primary_get_peer(primary, mdev_idx); +} + +static bool ft_create_alias_supported(struct mlx5_core_dev *dev) +{ + u64 obj_allowed = MLX5_CAP_GEN_2_64(dev, allowed_object_for_other_vhca_access); + u32 obj_supp = MLX5_CAP_GEN_2(dev, cross_vhca_object_to_object_supported); + + if (!(obj_supp & + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE)) + return false; + + if (!(obj_allowed & MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE)) + return false; + + return true; +} + +static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) +{ + /* Feature is currently implemented for PFs only */ + if (!mlx5_core_is_pf(dev)) + return false; + + /* Honor the SW implementation limit */ + if (host_buses > MLX5_SD_MAX_GROUP_SZ) + return false; + + /* Disconnect secondaries from the network */ + if (!MLX5_CAP_GEN(dev, eswitch_manager)) + return false; + if (!MLX5_CAP_GEN(dev, silent_mode)) + return false; + + /* RX steering from primary to secondaries */ + if (!MLX5_CAP_GEN(dev, cross_vhca_rqt)) + return false; + if (host_buses > MLX5_CAP_GEN_2(dev, max_rqt_vhca_id)) + return false; + + /* TX steering from secondaries to primary */ + if (!ft_create_alias_supported(dev)) + return false; + if (!MLX5_CAP_FLOWTABLE_NIC_TX(dev, reset_root_to_default)) + return false; + + return true; +} + +static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm, + u8 *host_buses, u8 *sd_group) +{ + u32 out[MLX5_ST_SZ_DW(mpir_reg)]; + int err; + + err = mlx5_query_mpir_reg(dev, out); + if (err) + return err; + + err = mlx5_query_nic_vport_sd_group(dev, sd_group); + if (err) + return err; + + *sdm = MLX5_GET(mpir_reg, out, sdm); + *host_buses = MLX5_GET(mpir_reg, out, host_buses); + + return 0; +} + +static u32 mlx5_sd_group_id(struct mlx5_core_dev *dev, u8 sd_group) +{ + return (u32)((MLX5_CAP_GEN(dev, native_port_num) << 8) | sd_group); +} + +static int sd_init(struct mlx5_core_dev *dev) +{ + u8 host_buses, sd_group; + struct mlx5_sd *sd; + u32 group_id; + bool sdm; + int err; + + if (!MLX5_CAP_MCAM_REG(dev, mpir)) + return 0; + + err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group); + if (err) + return err; + + if (!sdm) + return 0; + + if (!sd_group) + return 0; + + group_id = mlx5_sd_group_id(dev, sd_group); + + if (!mlx5_sd_is_supported(dev, host_buses)) { + sd_warn(dev, "can't support requested netdev combining for group id 0x%x), skipping\n", + group_id); + return 0; + } + + sd = kzalloc(sizeof(*sd), GFP_KERNEL); + if (!sd) + return -ENOMEM; + + sd->host_buses = host_buses; + sd->group_id = group_id; + + mlx5_set_sd(dev, sd); + + return 0; +} + +static void sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_set_sd(dev, NULL); + kfree(sd); +} + +static int sd_register(struct mlx5_core_dev *dev) +{ + struct mlx5_devcom_comp_dev *devcom, *pos; + struct mlx5_core_dev *peer, *primary; + struct mlx5_sd *sd, *primary_sd; + int err, i; + + sd = mlx5_get_sd(dev); + devcom = mlx5_devcom_register_component(dev->priv.devc, MLX5_DEVCOM_SD_GROUP, + sd->group_id, NULL, dev); + if (!devcom) + return -ENOMEM; + + sd->devcom = devcom; + + if (mlx5_devcom_comp_get_size(devcom) != sd->host_buses) + return 0; + + mlx5_devcom_comp_lock(devcom); + mlx5_devcom_comp_set_ready(devcom, true); + mlx5_devcom_comp_unlock(devcom); + + if (!mlx5_devcom_for_each_peer_begin(devcom)) { + err = -ENODEV; + goto err_devcom_unreg; + } + + primary = dev; + mlx5_devcom_for_each_peer_entry(devcom, peer, pos) + if (peer->pdev->bus->number < primary->pdev->bus->number) + primary = peer; + + primary_sd = mlx5_get_sd(primary); + primary_sd->primary = true; + i = 0; + /* loop the secondaries */ + mlx5_devcom_for_each_peer_entry(primary_sd->devcom, peer, pos) { + struct mlx5_sd *peer_sd = mlx5_get_sd(peer); + + primary_sd->secondaries[i++] = peer; + peer_sd->primary = false; + peer_sd->primary_dev = primary; + } + + mlx5_devcom_for_each_peer_end(devcom); + return 0; + +err_devcom_unreg: + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); + return err; +} + +static void sd_unregister(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + + mlx5_devcom_comp_lock(sd->devcom); + mlx5_devcom_comp_set_ready(sd->devcom, false); + mlx5_devcom_comp_unlock(sd->devcom); + mlx5_devcom_unregister_component(sd->devcom); +} + +static int sd_cmd_set_primary(struct mlx5_core_dev *primary, u8 *alias_key) +{ + struct mlx5_cmd_allow_other_vhca_access_attr allow_attr = {}; + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_namespace *nic_ns; + struct mlx5_flow_table *ft; + int err; + + nic_ns = mlx5_get_flow_namespace(primary, MLX5_FLOW_NAMESPACE_EGRESS); + if (!nic_ns) + return -EOPNOTSUPP; + + ft = mlx5_create_flow_table(nic_ns, &ft_attr); + if (IS_ERR(ft)) { + err = PTR_ERR(ft); + return err; + } + sd->tx_ft = ft; + memcpy(allow_attr.access_key, alias_key, ACCESS_KEY_LEN); + allow_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + allow_attr.obj_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + + err = mlx5_cmd_allow_other_vhca_access(primary, &allow_attr); + if (err) { + mlx5_core_err(primary, "Failed to allow other vhca access err=%d\n", + err); + mlx5_destroy_flow_table(ft); + return err; + } + + return 0; +} + +static void sd_cmd_unset_primary(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + + mlx5_destroy_flow_table(sd->tx_ft); +} + +static int sd_secondary_create_alias_ft(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + struct mlx5_flow_table *ft, + u32 *obj_id, u8 *alias_key) +{ + u32 aliased_object_id = (ft->type << FT_ID_FT_TYPE_OFFSET) | ft->id; + u16 vhca_id_to_be_accessed = MLX5_CAP_GEN(primary, vhca_id); + struct mlx5_cmd_alias_obj_create_attr alias_attr = {}; + int ret; + + memcpy(alias_attr.access_key, alias_key, ACCESS_KEY_LEN); + alias_attr.obj_id = aliased_object_id; + alias_attr.obj_type = MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS; + alias_attr.vhca_id = vhca_id_to_be_accessed; + ret = mlx5_cmd_alias_obj_create(secondary, &alias_attr, obj_id); + if (ret) { + mlx5_core_err(secondary, "Failed to create alias object err=%d\n", + ret); + return ret; + } + + return 0; +} + +static void sd_secondary_destroy_alias_ft(struct mlx5_core_dev *secondary) +{ + struct mlx5_sd *sd = mlx5_get_sd(secondary); + + mlx5_cmd_alias_obj_destroy(secondary, sd->alias_obj_id, + MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS); +} + +static int sd_cmd_set_secondary(struct mlx5_core_dev *secondary, + struct mlx5_core_dev *primary, + u8 *alias_key) +{ + struct mlx5_sd *primary_sd = mlx5_get_sd(primary); + struct mlx5_sd *sd = mlx5_get_sd(secondary); + int err; + + err = mlx5_fs_cmd_set_l2table_entry_silent(secondary, 1); + if (err) + return err; + + err = sd_secondary_create_alias_ft(secondary, primary, primary_sd->tx_ft, + &sd->alias_obj_id, alias_key); + if (err) + goto err_unset_silent; + + err = mlx5_fs_cmd_set_tx_flow_table_root(secondary, sd->alias_obj_id, false); + if (err) + goto err_destroy_alias_ft; + + return 0; + +err_destroy_alias_ft: + sd_secondary_destroy_alias_ft(secondary); +err_unset_silent: + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); + return err; +} + +static void sd_cmd_unset_secondary(struct mlx5_core_dev *secondary) +{ + mlx5_fs_cmd_set_tx_flow_table_root(secondary, 0, true); + sd_secondary_destroy_alias_ft(secondary); + mlx5_fs_cmd_set_l2table_entry_silent(secondary, 0); +} + +static void sd_print_group(struct mlx5_core_dev *primary) +{ + struct mlx5_sd *sd = mlx5_get_sd(primary); + struct mlx5_core_dev *pos; + int i; + + sd_info(primary, "group id %#x, primary %s, vhca %#x\n", + sd->group_id, pci_name(primary->pdev), + MLX5_CAP_GEN(primary, vhca_id)); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_info(primary, "group id %#x, secondary_%d %s, vhca %#x\n", + sd->group_id, i - 1, pci_name(pos->pdev), + MLX5_CAP_GEN(pos, vhca_id)); +} + +static ssize_t dev_read(struct file *filp, char __user *buf, size_t count, + loff_t *pos) +{ + struct mlx5_core_dev *dev; + char tbuf[32]; + int ret; + + dev = filp->private_data; + ret = snprintf(tbuf, sizeof(tbuf), "%s vhca %#x\n", pci_name(dev->pdev), + MLX5_CAP_GEN(dev, vhca_id)); + + return simple_read_from_buffer(buf, count, pos, tbuf, ret); +} + +static const struct file_operations dev_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = dev_read, +}; + +int mlx5_sd_init(struct mlx5_core_dev *dev) +{ + struct mlx5_core_dev *primary, *pos, *to; + struct mlx5_sd *sd = mlx5_get_sd(dev); + u8 alias_key[ACCESS_KEY_LEN]; + int err, i; + + err = sd_init(dev); + if (err) + return err; + + sd = mlx5_get_sd(dev); + if (!sd) + return 0; + + err = sd_register(dev); + if (err) + goto err_sd_cleanup; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return 0; + + primary = mlx5_sd_get_primary(dev); + + for (i = 0; i < ACCESS_KEY_LEN; i++) + alias_key[i] = get_random_u8(); + + err = sd_cmd_set_primary(primary, alias_key); + if (err) + goto err_sd_unregister; + + sd->dfs = debugfs_create_dir("multi-pf", mlx5_debugfs_get_dev_root(primary)); + debugfs_create_x32("group_id", 0400, sd->dfs, &sd->group_id); + debugfs_create_file("primary", 0400, sd->dfs, primary, &dev_fops); + + mlx5_sd_for_each_secondary(i, primary, pos) { + char name[32]; + + err = sd_cmd_set_secondary(pos, primary, alias_key); + if (err) + goto err_unset_secondaries; + + snprintf(name, sizeof(name), "secondary_%d", i - 1); + debugfs_create_file(name, 0400, sd->dfs, pos, &dev_fops); + + } + + sd_info(primary, "group id %#x, size %d, combined\n", + sd->group_id, mlx5_devcom_comp_get_size(sd->devcom)); + sd_print_group(primary); + + return 0; + +err_unset_secondaries: + to = pos; + mlx5_sd_for_each_secondary_to(i, primary, to, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); + debugfs_remove_recursive(sd->dfs); +err_sd_unregister: + sd_unregister(dev); +err_sd_cleanup: + sd_cleanup(dev); + return err; +} + +void mlx5_sd_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary, *pos; + int i; + + if (!sd) + return; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + goto out; + + primary = mlx5_sd_get_primary(dev); + mlx5_sd_for_each_secondary(i, primary, pos) + sd_cmd_unset_secondary(pos); + sd_cmd_unset_primary(primary); + debugfs_remove_recursive(sd->dfs); + + sd_info(primary, "group id %#x, uncombined\n", sd->group_id); +out: + sd_unregister(dev); + sd_cleanup(dev); +} + +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx) +{ + struct mlx5_sd *sd = mlx5_get_sd(dev); + struct mlx5_core_dev *primary; + + if (!sd) + return adev; + + if (!mlx5_devcom_comp_is_ready(sd->devcom)) + return NULL; + + primary = mlx5_sd_get_primary(dev); + if (dev == primary) + return adev; + + return &primary->priv.adev[idx]->adev; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h new file mode 100644 index 000000000000..137efaf9aabc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_LIB_SD_H__ +#define __MLX5_LIB_SD_H__ + +#define MLX5_SD_MAX_GROUP_SZ 2 + +struct mlx5_sd; + +struct mlx5_core_dev *mlx5_sd_primary_get_peer(struct mlx5_core_dev *primary, int idx); +int mlx5_sd_ch_ix_get_dev_ix(struct mlx5_core_dev *dev, int ch_ix); +int mlx5_sd_ch_ix_get_vec_ix(struct mlx5_core_dev *dev, int ch_ix); +struct mlx5_core_dev *mlx5_sd_ch_ix_get_dev(struct mlx5_core_dev *primary, int ch_ix); +struct auxiliary_device *mlx5_sd_get_adev(struct mlx5_core_dev *dev, + struct auxiliary_device *adev, + int idx); + +int mlx5_sd_init(struct mlx5_core_dev *dev); +void mlx5_sd_cleanup(struct mlx5_core_dev *dev); + +#define mlx5_sd_for_each_dev_from_to(i, primary, ix_from, to, pos) \ + for (i = ix_from; \ + (pos = mlx5_sd_primary_get_peer(primary, i)) && pos != (to); i++) + +#define mlx5_sd_for_each_dev(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, NULL, pos) + +#define mlx5_sd_for_each_dev_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 0, to, pos) + +#define mlx5_sd_for_each_secondary(i, primary, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, NULL, pos) + +#define mlx5_sd_for_each_secondary_to(i, primary, to, pos) \ + mlx5_sd_for_each_dev_from_to(i, primary, 1, to, pos) + +#endif /* __MLX5_LIB_SD_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 41f03b352401..bf9324a31ae9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -823,6 +823,7 @@ struct mlx5_core_dev { struct blocking_notifier_head macsec_nh; #endif u64 num_ipsec_offloads; + struct mlx5_sd *sd; }; struct mlx5_db { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3a8a9e57a51d..49f660563e49 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10253,7 +10253,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mcqi[0x1]; u8 mcqs[0x1]; - u8 regs_95_to_87[0x9]; + u8 regs_95_to_90[0x6]; + u8 mpir[0x1]; + u8 regs_88_to_87[0x2]; u8 mpegc[0x1]; u8 mtutc[0x1]; u8 regs_84_to_68[0x11]; |