From ea77388b02270b0af8dc57f668f311235ea068f0 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 31 Jul 2019 14:40:13 +0300 Subject: [PATCH 01/23] net/mlx5: Fix mlx5_ifc_query_lag_out_bits Remove the "reserved_at_40" field to match the device specification. Fixes: 84df61ebc69b ("net/mlx5: Add HW interfaces used by LAG") Signed-off-by: Mark Zhang Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 30d15e80bcc7..1f9d4a8e6227 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9592,8 +9592,6 @@ struct mlx5_ifc_query_lag_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x40]; - struct mlx5_ifc_lagc_bits ctx; }; From 7084ed30ae2aba4efb4d3ef72c0e7042644e7637 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Wed, 31 Jul 2019 14:40:14 +0300 Subject: [PATCH 02/23] IB/mlx5: Support MLX5_CMD_OP_QUERY_LAG as a DEVX general command The "MLX5_CMD_OP_QUERY_LAG" is one of the DEVX general commands, add it. Fixes: 8aa8c95ce4cc ("IB/mlx5: Add support for DEVX general command") Signed-off-by: Mark Zhang Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index ec4370f99381..48968b4d561d 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -922,6 +922,7 @@ static bool devx_is_general_cmd(void *in, struct mlx5_ib_dev *dev) case MLX5_CMD_OP_QUERY_CONG_STATUS: case MLX5_CMD_OP_QUERY_CONG_PARAMS: case MLX5_CMD_OP_QUERY_CONG_STATISTICS: + case MLX5_CMD_OP_QUERY_LAG: return true; default: return false; From 694a296024d4cd5e637fa679c4c7e4c63a7c24f3 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 2 Aug 2019 16:13:16 +0100 Subject: [PATCH 03/23] net/mlx5: remove self-assignment on esw->dev There is a self assignment of esw->dev to itself, clean this up by removing it. Also make dev a const pointer. Addresses-Coverity: ("Self assignment") Fixes: 6cedde451399 ("net/mlx5: E-Switch, Verify support QoS element type") Signed-off-by: Colin Ian King Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d4465dd18c11..81e03e493a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1413,7 +1413,7 @@ out: static bool element_type_supported(struct mlx5_eswitch *esw, int type) { - struct mlx5_core_dev *dev = esw->dev = esw->dev; + const struct mlx5_core_dev *dev = esw->dev; switch (type) { case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: From 94f3e14e00fd43024b1c4d8e0c1e442db9b4d964 Mon Sep 17 00:00:00 2001 From: Chuhong Yuan Date: Tue, 6 Aug 2019 09:59:50 +0800 Subject: [PATCH 04/23] mlx5: Use refcount_t for refcount Reference counters are preferred to use refcount_t instead of atomic_t. This is because the implementation of refcount_t can prevent overflows and detect possible use-after-free. So convert atomic_t ref counters to refcount_t. Signed-off-by: Chuhong Yuan Acked-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/srq_cmd.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 6 +++--- include/linux/mlx5/driver.h | 3 ++- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/srq_cmd.c b/drivers/infiniband/hw/mlx5/srq_cmd.c index b0d0687c7a68..8fc3630a9d4c 100644 --- a/drivers/infiniband/hw/mlx5/srq_cmd.c +++ b/drivers/infiniband/hw/mlx5/srq_cmd.c @@ -86,7 +86,7 @@ struct mlx5_core_srq *mlx5_cmd_get_srq(struct mlx5_ib_dev *dev, u32 srqn) xa_lock(&table->array); srq = xa_load(&table->array, srqn); if (srq) - atomic_inc(&srq->common.refcount); + refcount_inc(&srq->common.refcount); xa_unlock(&table->array); return srq; @@ -592,7 +592,7 @@ int mlx5_cmd_create_srq(struct mlx5_ib_dev *dev, struct mlx5_core_srq *srq, if (err) return err; - atomic_set(&srq->common.refcount, 1); + refcount_set(&srq->common.refcount, 1); init_completion(&srq->common.free); err = xa_err(xa_store_irq(&table->array, srq->srqn, srq, GFP_KERNEL)); @@ -675,7 +675,7 @@ static int srq_event_notifier(struct notifier_block *nb, xa_lock(&table->array); srq = xa_load(&table->array, srqn); if (srq) - atomic_inc(&srq->common.refcount); + refcount_inc(&srq->common.refcount); xa_unlock(&table->array); if (!srq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index b8ba74de9555..7b44d1e49604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -53,7 +53,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) common = radix_tree_lookup(&table->tree, rsn); if (common) - atomic_inc(&common->refcount); + refcount_inc(&common->refcount); spin_unlock_irqrestore(&table->lock, flags); @@ -62,7 +62,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common) { - if (atomic_dec_and_test(&common->refcount)) + if (refcount_dec_and_test(&common->refcount)) complete(&common->free); } @@ -209,7 +209,7 @@ static int create_resource_common(struct mlx5_core_dev *dev, if (err) return err; - atomic_set(&qp->common.refcount, 1); + refcount_set(&qp->common.refcount, 1); init_completion(&qp->common.free); qp->pid = current->pid; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 267b2bc0ca4a..0acd28f2e62c 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -47,6 +47,7 @@ #include #include #include +#include #include #include @@ -398,7 +399,7 @@ enum mlx5_res_type { struct mlx5_core_rsc_common { enum mlx5_res_type res; - atomic_t refcount; + refcount_t refcount; struct completion free; }; From 647d58a989b3b0b788c721a08394aec825e3438c Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Aug 2019 11:43:55 +0300 Subject: [PATCH 05/23] net/mlx5: Use debug message instead of warn As QP may be created by DEVX, it may be valid to not find the rsn in mlx5 core tree, change the level to be debug. Signed-off-by: Yishai Hadas Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/qp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 7b44d1e49604..c3aea4cc2fff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -162,7 +162,7 @@ static int rsc_event_notifier(struct notifier_block *nb, common = mlx5_get_rsc(table, rsn); if (!common) { - mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n", rsn); + mlx5_core_dbg(dev, "Async event for unknown resource 0x%x\n", rsn); return NOTIFY_OK; } From b1635ee6120cbeb3de6ab270432b2a2b839c9c56 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Aug 2019 11:43:56 +0300 Subject: [PATCH 06/23] net/mlx5: Add XRQ legacy commands opcodes Add XRQ legacy commands opcodes, will be used via the DEVX interface. Signed-off-by: Yishai Hadas Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 4 ++++ include/linux/mlx5/mlx5_ifc.h | 2 ++ 2 files changed, 6 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..53d09620e215 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -446,6 +446,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_CREATE_UMEM: case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: + case MLX5_CMD_OP_MODIFY_XRQ: + case MLX5_CMD_OP_RELEASE_XRQ_ERROR: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -EIO; @@ -637,6 +639,8 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(DESTROY_UCTX); MLX5_COMMAND_STR_CASE(CREATE_UMEM); MLX5_COMMAND_STR_CASE(DESTROY_UMEM); + MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR); + MLX5_COMMAND_STR_CASE(MODIFY_XRQ); default: return "unknown command opcode"; } } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1f9d4a8e6227..ab6ae723aae6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -172,6 +172,8 @@ enum { MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725, MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726, MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, + MLX5_CMD_OP_RELEASE_XRQ_ERROR = 0x729, + MLX5_CMD_OP_MODIFY_XRQ = 0x72a, MLX5_CMD_OP_QUERY_ESW_FUNCTIONS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, From eed6f7dc28d35bbed74115fc246b9a29af0918de Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 15 Aug 2019 19:46:08 +0000 Subject: [PATCH 07/23] net/mlx5: Add missing include file to lib/crypto.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add missing include file to avoid compiler warnings: drivers/net/ethernet/mellanox/mlx5/core//lib/crypto.c:6:5: warning: no previous prototype for ‘mlx5_create_encryption_key’ 6 | int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, | ^~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/net/ethernet/mellanox/mlx5/core//lib/crypto.c:60:6: warning: no previous prototype for ‘mlx5_destroy_encryption_key’ 60 | void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, ... Fixes: 45d3b55dc665 ("net/mlx5: Add crypto library to support create/destroy encryption key") Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c index ea9ee88491e5..22bc45c831d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c @@ -2,6 +2,7 @@ // Copyright (c) 2019 Mellanox Technologies. #include "mlx5_core.h" +#include "lib/mlx5.h" int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, void *key, u32 sz_bytes, From 866ff8f22380a49d665ed72521704844bba6de08 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Thu, 15 Aug 2019 19:46:09 +0000 Subject: [PATCH 08/23] net/mlx5: Improve functions documentation Fix documentation of mlx5_eq_enable/disable to cleanup compiler warnings. drivers/net/ethernet/mellanox/mlx5/core//eq.c:334: warning: Function parameter or member 'dev' not described in 'mlx5_eq_enable' warning: Function parameter or member 'eq' not described in 'mlx5_eq_enable' warning: Function parameter or member 'nb' not described in 'mlx5_eq_enable' drivers/net/ethernet/mellanox/mlx5/core//eq.c:355: warning: Function parameter or member 'dev' not described in 'mlx5_eq_disable' warning: Function parameter or member 'eq' not described in 'mlx5_eq_disable' warning: Function parameter or member 'nb' not described in 'mlx5_eq_disable' Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 22 ++++++++++++-------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 2df9aaa421c6..a0e78ab64618 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -324,10 +324,13 @@ err_buf: /** * mlx5_eq_enable - Enable EQ for receiving EQEs - * @dev - Device which owns the eq - * @eq - EQ to enable - * @nb - notifier call block - * mlx5_eq_enable - must be called after EQ is created in device. + * @dev : Device which owns the eq + * @eq : EQ to enable + * @nb : Notifier call block + * + * Must be called after EQ is created in device. + * + * @return: 0 if no error */ int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) @@ -344,11 +347,12 @@ int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, EXPORT_SYMBOL(mlx5_eq_enable); /** - * mlx5_eq_disable - Enable EQ for receiving EQEs - * @dev - Device which owns the eq - * @eq - EQ to disable - * @nb - notifier call block - * mlx5_eq_disable - must be called before EQ is destroyed. + * mlx5_eq_disable - Disable EQ for receiving EQEs + * @dev : Device which owns the eq + * @eq : EQ to disable + * @nb : Notifier call block + * + * Must be called before EQ is destroyed. */ void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) From 30b10e89f2ae2c7b7b32548e04f57ab7eb030dfb Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 15 Aug 2019 19:46:11 +0000 Subject: [PATCH 09/23] net/mlx5: Add support for VNIC_ENV internal rq counter Add mlx5 interface support for reading internal rq out of buffer counter as part of QUERY_VNIC_ENV command. The command is used by the driver to query vnic diagnostic statistics from FW. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ab6ae723aae6..c788f895b350 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1116,7 +1116,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cache_line_128byte[0x1]; u8 reserved_at_165[0x4]; u8 rts2rts_qp_counters_set_id[0x1]; - u8 reserved_at_16a[0x5]; + u8 reserved_at_16a[0x2]; + u8 vnic_env_int_rq_oob[0x1]; + u8 reserved_at_16d[0x2]; u8 qcam_reg[0x1]; u8 gid_table_size[0x10]; @@ -2772,7 +2774,11 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xec0]; + u8 reserved_at_140[0xa0]; + + u8 internal_rq_out_of_buffer[0x20]; + + u8 reserved_at_200[0xe00]; }; struct mlx5_ifc_traffic_counter_bits { From caa1854735449d7afac6781679621fb9142fe810 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 15 Aug 2019 19:46:14 +0000 Subject: [PATCH 10/23] net/mlx5: Expose IP-in-IP capability bit Expose Fw indication that it supports Stateless Offloads for IP over IP tunneled packets. The following offloads are supported for the inner packets: RSS, RX & TX Checksum Offloads, LSO and Flow Steering. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c788f895b350..2837fe4d8901 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -808,7 +808,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 swp_csum[0x1]; u8 swp_lso[0x1]; u8 cqe_checksum_full[0x1]; - u8 reserved_at_24[0xc]; + u8 reserved_at_24[0x5]; + u8 tunnel_stateless_ip_over_ip[0x1]; + u8 reserved_at_2a[0x6]; u8 max_vxlan_udp_ports[0x8]; u8 reserved_at_38[0x6]; u8 max_geneve_opt_len[0x1]; From 1eba383f4e36637ba859cb82b40e198c415db802 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 15 Aug 2019 19:46:16 +0000 Subject: [PATCH 11/23] net/mlx5: Add lag_tx_port_affinity capability bit Add the lag_tx_port_affinity HCA capability bit that indicates that setting port affinity of TISes is supported. Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2837fe4d8901..1e55cf73e88c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1249,7 +1249,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_263[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_at_270[0xb]; + u8 reserved_at_270[0x8]; + u8 lag_tx_port_affinity[0x1]; + u8 reserved_at_279[0x2]; u8 lag_master[0x1]; u8 num_lag_ports[0x4]; From f66ad830b11406cdff84e7d8656a0a9e34b0b606 Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 19 Aug 2019 14:36:24 +0300 Subject: [PATCH 12/23] net/mlx5: Add per-namespace flow table default miss action support Currently all the namespaces under the same steering domain share the same default table miss action, however in some situations (e.g., RDMA RX) different actions are required. This patch adds a per-namespace default table miss action instead of using the miss action of the steering domain. Signed-off-by: Mark Zhang Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- .../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 4 +- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 73 +++++++++++-------- .../net/ethernet/mellanox/mlx5/core/fs_core.h | 3 +- 3 files changed, 47 insertions(+), 33 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index b84a225bbe86..1e3381604b3d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -182,7 +182,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, } else { MLX5_SET(create_flow_table_in, in, flow_table_context.table_miss_action, - ns->def_miss_action); + ft->def_miss_action); } break; @@ -262,7 +262,7 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, } else { MLX5_SET(modify_flow_table_in, in, flow_table_context.table_miss_action, - ns->def_miss_action); + ft->def_miss_action); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3e99799bdb40..fb3cfdfbafbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -60,7 +60,8 @@ ADD_PRIO(num_prios_val, 0, num_levels_val, {},\ __VA_ARGS__)\ -#define ADD_NS(...) {.type = FS_TYPE_NAMESPACE,\ +#define ADD_NS(def_miss_act, ...) {.type = FS_TYPE_NAMESPACE, \ + .def_miss_action = def_miss_act,\ .children = (struct init_tree_node[]) {__VA_ARGS__},\ .ar_size = INIT_TREE_NODE_ARRAY_SIZE(__VA_ARGS__) \ } @@ -131,33 +132,41 @@ static struct init_tree_node { int num_leaf_prios; int prio; int num_levels; + enum mlx5_flow_table_miss_action def_miss_action; } root_fs = { .type = FS_TYPE_NAMESPACE, .ar_size = 7, - .children = (struct init_tree_node[]) { - ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, - BY_PASS_PRIO_NUM_LEVELS))), - ADD_PRIO(0, LAG_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(LAG_NUM_PRIOS, - LAG_PRIO_NUM_LEVELS))), - ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, OFFLOADS_MAX_FT))), - ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(ETHTOOL_NUM_PRIOS, - ETHTOOL_PRIO_NUM_LEVELS))), - ADD_PRIO(0, KERNEL_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, KERNEL_NIC_TC_NUM_LEVELS), - ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, - KERNEL_NIC_PRIO_NUM_LEVELS))), - ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, LEFTOVERS_NUM_LEVELS))), - ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, ANCHOR_NUM_LEVELS))), + .children = (struct init_tree_node[]){ + ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + ADD_PRIO(0, LAG_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(LAG_NUM_PRIOS, + LAG_PRIO_NUM_LEVELS))), + ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, + OFFLOADS_MAX_FT))), + ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(ETHTOOL_NUM_PRIOS, + ETHTOOL_PRIO_NUM_LEVELS))), + ADD_PRIO(0, KERNEL_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, + KERNEL_NIC_TC_NUM_LEVELS), + ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, + KERNEL_NIC_PRIO_NUM_LEVELS))), + ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, + LEFTOVERS_NUM_LEVELS))), + ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, + ANCHOR_NUM_LEVELS))), } }; @@ -167,7 +176,8 @@ static struct init_tree_node egress_root_fs = { .children = (struct init_tree_node[]) { ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0, FS_CHAINING_CAPS_EGRESS, - ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, BY_PASS_PRIO_NUM_LEVELS))), } }; @@ -1014,6 +1024,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); + ft->def_miss_action = ns->def_miss_action; err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft); if (err) goto free_ft; @@ -2155,7 +2166,8 @@ static struct mlx5_flow_namespace *fs_init_namespace(struct mlx5_flow_namespace return ns; } -static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) +static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio, + int def_miss_act) { struct mlx5_flow_namespace *ns; @@ -2164,6 +2176,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); + ns->def_miss_action = def_miss_act; tree_init_node(&ns->node, NULL, del_sw_ns); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -2230,7 +2243,7 @@ static int init_root_tree_recursive(struct mlx5_flow_steering *steering, base = &fs_prio->node; } else if (init_node->type == FS_TYPE_NAMESPACE) { fs_get_obj(fs_prio, fs_parent_node); - fs_ns = fs_create_namespace(fs_prio); + fs_ns = fs_create_namespace(fs_prio, init_node->def_miss_action); if (IS_ERR(fs_ns)) return PTR_ERR(fs_ns); base = &fs_ns->node; @@ -2500,7 +2513,7 @@ static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) if (!steering->rdma_rx_root_ns) return -ENOMEM; - steering->rdma_rx_root_ns->def_miss_action = + steering->rdma_rx_root_ns->ns.def_miss_action = MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN; /* Create single prio */ @@ -2543,7 +2556,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) } for (chain = 0; chain <= FDB_MAX_CHAIN; chain++) { - ns = fs_create_namespace(maj_prio); + ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); if (IS_ERR(ns)) { err = PTR_ERR(ns); goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c48c382f926f..69f809831959 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -145,6 +145,7 @@ struct mlx5_flow_table { struct list_head fwd_rules; u32 flags; struct rhltable fgs_hash; + enum mlx5_flow_table_miss_action def_miss_action; }; struct mlx5_ft_underlay_qp { @@ -191,6 +192,7 @@ struct fs_prio { struct mlx5_flow_namespace { /* parent == NULL => root ns */ struct fs_node node; + enum mlx5_flow_table_miss_action def_miss_action; }; struct mlx5_flow_group_mask { @@ -219,7 +221,6 @@ struct mlx5_flow_root_namespace { struct mutex chain_lock; struct list_head underlay_qpns; const struct mlx5_flow_cmds *cmds; - enum mlx5_flow_table_miss_action def_miss_action; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); From e6806e9a63a759e445383915bb9d2ec85a90aebf Mon Sep 17 00:00:00 2001 From: Mark Zhang Date: Mon, 19 Aug 2019 14:36:25 +0300 Subject: [PATCH 13/23] net/mlx5: Create bypass and loopback flow steering namespaces for RDMA RX Use different namespaces for bypass and switchdev loopback because they have different priorities and default table miss action requirement: 1. bypass: with multiple priorities support, and MLX5_FLOW_TABLE_MISS_ACTION_DEF as the default table miss action; 2. switchdev loopback: with single priority support, and MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN as the default table miss action. Signed-off-by: Mark Zhang Reviewed-by: Mark Bloch Signed-off-by: Leon Romanovsky --- .../net/ethernet/mellanox/mlx5/core/fs_core.c | 49 +++++++++++++++---- .../net/ethernet/mellanox/mlx5/core/rdma.c | 2 +- include/linux/mlx5/fs.h | 1 + 3 files changed, 41 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fb3cfdfbafbe..7bdec442f0ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -182,6 +182,26 @@ static struct init_tree_node egress_root_fs = { } }; +#define RDMA_RX_BYPASS_PRIO 0 +#define RDMA_RX_KERNEL_PRIO 1 +static struct init_tree_node rdma_rx_root_fs = { + .type = FS_TYPE_NAMESPACE, + .ar_size = 2, + .children = (struct init_tree_node[]) { + [RDMA_RX_BYPASS_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + [RDMA_RX_KERNEL_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, + ADD_MULTIPLE_PRIO(1, 1))), + } +}; + enum fs_i_lock_class { FS_LOCK_GRANDPARENT, FS_LOCK_PARENT, @@ -2067,16 +2087,18 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; - case MLX5_FLOW_NAMESPACE_RDMA_RX: - if (steering->rdma_rx_root_ns) - return &steering->rdma_rx_root_ns->ns; - return NULL; default: break; } if (type == MLX5_FLOW_NAMESPACE_EGRESS) { root_ns = steering->egress_root_ns; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_BYPASS_PRIO; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_KERNEL_PRIO; } else { /* Must be NIC RX */ root_ns = steering->root_ns; prio = type; @@ -2507,18 +2529,25 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { - struct fs_prio *prio; + int err; steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX); if (!steering->rdma_rx_root_ns) return -ENOMEM; - steering->rdma_rx_root_ns->ns.def_miss_action = - MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN; + err = init_root_tree(steering, &rdma_rx_root_fs, + &steering->rdma_rx_root_ns->ns.node); + if (err) + goto out_err; - /* Create single prio */ - prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1); - return PTR_ERR_OR_ZERO(prio); + set_prio_attrs(steering->rdma_rx_root_ns); + + return 0; + +out_err: + cleanup_root_ns(steering->rdma_rx_root_ns); + steering->rdma_rx_root_ns = NULL; + return err; } static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 17ce9dd56b13..18af6981e0be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -51,7 +51,7 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) return -ENOMEM; } - ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX); + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL); if (!ns) { mlx5_core_err(dev, "Failed to get RDMA RX namespace"); err = -EOPNOTSUPP; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 04a569568eac..5235b09a8ef3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -75,6 +75,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_SNIFFER_TX, MLX5_FLOW_NAMESPACE_EGRESS, MLX5_FLOW_NAMESPACE_RDMA_RX, + MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, }; enum { From bb487d29ce005416ed355dea213bbc39c03dabe7 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 23 Aug 2019 15:56:23 -0400 Subject: [PATCH 14/23] net/mlx5: fix a -Wstringop-truncation warning In file included from ./arch/powerpc/include/asm/paca.h:15, from ./arch/powerpc/include/asm/current.h:13, from ./include/linux/thread_info.h:21, from ./include/asm-generic/preempt.h:5, from ./arch/powerpc/include/generated/asm/preempt.h:1, from ./include/linux/preempt.h:78, from ./include/linux/spinlock.h:51, from ./include/linux/wait.h:9, from ./include/linux/completion.h:12, from ./include/linux/mlx5/driver.h:37, from drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h:6, from drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:33: In function 'strncpy', inlined from 'mlx5_fw_tracer_save_trace' at drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:549:2, inlined from 'mlx5_tracer_print_trace' at drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c:574:2: ./include/linux/string.h:305:9: warning: '__builtin_strncpy' output may be truncated copying 256 bytes from a string of length 511 [-Wstringop-truncation] return __builtin_strncpy(p, q, size); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Fix it by using the new strscpy_pad() since the commit 458a3bf82df4 ("lib/string: Add strscpy_pad() function") which will always NUL-terminate the string, and avoid possibly leak data through the ring buffer where non-admin account might enable these events through perf. Fixes: fd1483fe1f9f ("net/mlx5: Add support for FW reporter dump") Signed-off-by: Qian Cai Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 8a4930c8bf62..2011eaf15cc5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -546,7 +546,7 @@ static void mlx5_fw_tracer_save_trace(struct mlx5_fw_tracer *tracer, trace_data->timestamp = timestamp; trace_data->lost = lost; trace_data->event_id = event_id; - strncpy(trace_data->msg, msg, TRACE_STR_MSG); + strscpy_pad(trace_data->msg, msg, TRACE_STR_MSG); tracer->st_arr.saved_traces_index = (tracer->st_arr.saved_traces_index + 1) & (SAVED_TRACES_NUM - 1); From 00679b631eddaa0aa0ceba719fcb1f60c65da5a3 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Mon, 19 Aug 2019 15:08:13 +0300 Subject: [PATCH 15/23] net/mlx5: Set ODP capabilities for DC transport to max In mlx5_core initialization, query max ODP capabilities for DC transport from FW and set as current capabilities. Signed-off-by: Michael Guralnik Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index fa0e991f1983..7f70ecb1db6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -495,6 +495,12 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev) ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); if (do_set) err = set_caps(dev, set_ctx, set_sz, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1e55cf73e88c..4e278114d8b3 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -948,7 +948,9 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits xrc_odp_caps; - u8 reserved_at_100[0x700]; + struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; + + u8 reserved_at_120[0x6E0]; }; struct mlx5_ifc_calc_op { From d5e1c0ef550e4fa4577e6567f829a460a7f4ab6e Mon Sep 17 00:00:00 2001 From: Erez Alfasi Date: Wed, 7 Aug 2019 17:56:02 +0300 Subject: [PATCH 16/23] net/mlx5e: ethtool, Fix a typo in WOL function names Fix a typo in 'mlx5e_refomrat_wol_mode_mlx5_to_linux' and 'mlx5e_refomrat_wol_mode_linux_to_mlx5' function names: "refomrat" -> "reformat". Fixes: 928cfe8745a6 ("net/mlx5e: Wake On LAN support") Signed-off-by: Erez Alfasi Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 7347d673f448..c5a9c20d7f00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1431,7 +1431,7 @@ static __u32 mlx5e_get_wol_supported(struct mlx5_core_dev *mdev) return ret; } -static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) +static __u32 mlx5e_reformat_wol_mode_mlx5_to_linux(u8 mode) { __u32 ret = 0; @@ -1459,7 +1459,7 @@ static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) return ret; } -static u8 mlx5e_refomrat_wol_mode_linux_to_mlx5(__u32 mode) +static u8 mlx5e_reformat_wol_mode_linux_to_mlx5(__u32 mode) { u8 ret = 0; @@ -1505,7 +1505,7 @@ static void mlx5e_get_wol(struct net_device *netdev, if (err) return; - wol->wolopts = mlx5e_refomrat_wol_mode_mlx5_to_linux(mlx5_wol_mode); + wol->wolopts = mlx5e_reformat_wol_mode_mlx5_to_linux(mlx5_wol_mode); } static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) @@ -1521,7 +1521,7 @@ static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) if (wol->wolopts & ~wol_supported) return -EINVAL; - mlx5_wol_mode = mlx5e_refomrat_wol_mode_linux_to_mlx5(wol->wolopts); + mlx5_wol_mode = mlx5e_reformat_wol_mode_linux_to_mlx5(wol->wolopts); return mlx5_set_port_wol(mdev, mlx5_wol_mode); } From 3c14562663c603bc523b6619a2b19a411e1cdc8e Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 24 Jun 2019 12:03:02 +0300 Subject: [PATCH 17/23] net/mlx5e: Expose new function for TIS destroy loop For better modularity and code sharing. Function internal change to be introduced in the next patches. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 +++++++++---- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 9 +++------ 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 446792799125..491c281416d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1107,6 +1107,7 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn); void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn); int mlx5e_create_tises(struct mlx5e_priv *priv); +void mlx5e_destroy_tises(struct mlx5e_priv *priv); int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8592b98d0e70..390e614ac46e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3179,6 +3179,14 @@ void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) mlx5_core_destroy_tis(mdev, tisn); } +void mlx5e_destroy_tises(struct mlx5e_priv *priv) +{ + int tc; + + for (tc = 0; tc < priv->profile->max_tc; tc++) + mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); +} + int mlx5e_create_tises(struct mlx5e_priv *priv) { int err; @@ -3208,10 +3216,7 @@ err_close_tises: static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { - int tc; - - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); } static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e7ac6233037d..1623cd32f303 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1621,7 +1621,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_rep_uplink_priv *uplink_priv; - int tc, err; + int err; err = mlx5e_create_tises(priv); if (err) { @@ -1657,18 +1657,15 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) tc_esw_cleanup: mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht); destroy_tises: - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); return err; } static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - int tc; - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { /* clean indirect TC block notifications */ From 45f171b1182b9c4ab6d854d6f7fd7dd771fed591 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Wed, 7 Aug 2019 17:46:15 +0300 Subject: [PATCH 18/23] net/mlx5e: Support LAG TX port affinity distribution When the VF LAG is in use, round-robin the TX affinity of channels among the different ports, if supported by the firmware. Create a set of TISes per port, while doing round-robin of the channels over the different sets. Let all SQs of a channel share the same set of TISes. If lag_tx_port_affinity HCA cap bit is supported, num_lag_ports > 1 and we aren't the LACP owner (PF in the regular use), assign the affinities, otherwise use tx_affinity == 0 in TIS context to let the FW assign the affinities itself. The TISes of the LACP owner are mapped only to the native physical port. For VFs, the starting port for round-robin is determined by its vhca_id, because a VF may have only one channel if attached to a single-core VM. Signed-off-by: Maxim Mikityanskiy Signed-off-by: Tariq Toukan Signed-off-by: Mark Bloch Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 11 +++- .../net/ethernet/mellanox/mlx5/core/en_main.c | 54 +++++++++++++------ .../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 4 +- .../mellanox/mlx5/core/ipoib/ipoib_vlan.c | 6 +-- 4 files changed, 53 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 491c281416d0..e03f973c962f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -163,6 +163,14 @@ enum mlx5e_rq_group { #define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g) }; +static inline u8 mlx5e_get_num_lag_ports(struct mlx5_core_dev *mdev) +{ + if (mlx5_lag_is_lacp_owner(mdev)) + return 1; + + return clamp_t(u8, MLX5_CAP_GEN(mdev, num_lag_ports), 1, MLX5_MAX_PORTS); +} + static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) { switch (wq_type) { @@ -705,6 +713,7 @@ struct mlx5e_channel { struct net_device *netdev; __be32 mkey_be; u8 num_tc; + u8 lag_port; /* XDP_REDIRECT */ struct mlx5e_xdpsq xdpsq; @@ -818,7 +827,7 @@ struct mlx5e_priv { struct mlx5e_rq drop_rq; struct mlx5e_channels channels; - u32 tisn[MLX5E_MAX_NUM_TC]; + u32 tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC]; struct mlx5e_rqt indir_rqt; struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 390e614ac46e..2786f5b8057d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1442,7 +1442,7 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, return err; csp.tis_lst_sz = 1; - csp.tisn = c->priv->tisn[0]; /* tc = 0 */ + csp.tisn = c->priv->tisn[c->lag_port][0]; /* tc = 0 */ csp.cqn = sq->cq.mcq.cqn; csp.wq_ctrl = &sq->wq_ctrl; csp.min_inline_mode = sq->min_inline_mode; @@ -1692,7 +1692,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, for (tc = 0; tc < params->num_tc; tc++) { int txq_ix = c->ix + tc * priv->max_nch; - err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix, + err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, params, &cparam->sq, &c->sq[tc], tc); if (err) goto err_close_sqs; @@ -1926,6 +1926,13 @@ static void mlx5e_close_queues(struct mlx5e_channel *c) mlx5e_close_cq(&c->icosq.cq); } +static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix) +{ + u16 port_aff_bias = mlx5_core_is_pf(mdev) ? 0 : MLX5_CAP_GEN(mdev, vhca_id); + + return (ix + port_aff_bias) % mlx5e_get_num_lag_ports(mdev); +} + static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, @@ -1960,6 +1967,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; c->irq_desc = irq_to_desc(irq); + c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); err = mlx5e_alloc_xps_cpumask(c, params); if (err) @@ -3181,35 +3189,49 @@ void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) void mlx5e_destroy_tises(struct mlx5e_priv *priv) { - int tc; + int tc, i; - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) + for (tc = 0; tc < priv->profile->max_tc; tc++) + mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); +} + +static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1; } int mlx5e_create_tises(struct mlx5e_priv *priv) { + int tc, i; int err; - int tc; - for (tc = 0; tc < priv->profile->max_tc; tc++) { - u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; - void *tisc; + for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) { + for (tc = 0; tc < priv->profile->max_tc; tc++) { + u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; + void *tisc; - tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); - MLX5_SET(tisc, tisc, prio, tc << 1); + MLX5_SET(tisc, tisc, prio, tc << 1); - err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[tc]); - if (err) - goto err_close_tises; + if (mlx5e_lag_should_assign_affinity(priv->mdev)) + MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1); + + err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]); + if (err) + goto err_close_tises; + } } return 0; err_close_tises: - for (tc--; tc >= 0; tc--) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + for (; i >= 0; i--) { + for (tc--; tc >= 0; tc--) + mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); + tc = priv->profile->max_tc; + } return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 1a2560e3bf7c..3ed8ab2d703d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -279,7 +279,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } - err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0]); + err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0][0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); goto err_destroy_underlay_qp; @@ -296,7 +296,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) { struct mlx5i_priv *ipriv = priv->ppriv; - mlx5e_destroy_tis(priv->mdev, priv->tisn[0]); + mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]); mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index c5a491e22e55..96e64187c089 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -210,7 +210,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) goto err_unint_underlay_qp; } - err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0]); + err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0][0]); if (err) { mlx5_core_warn(mdev, "create child tis failed, %d\n", err); goto err_remove_rx_uderlay_qp; @@ -228,7 +228,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) return 0; err_clear_state_opened_flag: - mlx5e_destroy_tis(mdev, epriv->tisn[0]); + mlx5e_destroy_tis(mdev, epriv->tisn[0][0]); err_remove_rx_uderlay_qp: mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); err_unint_underlay_qp: @@ -257,7 +257,7 @@ static int mlx5i_pkey_close(struct net_device *netdev) mlx5i_uninit_underlay_qp(priv); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); - mlx5e_destroy_tis(mdev, priv->tisn[0]); + mlx5e_destroy_tis(mdev, priv->tisn[0][0]); unlock: mutex_unlock(&priv->state_lock); return 0; From 0cfafd4b4ddff99d6c21e028704a13ec1a578b8b Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Sun, 4 Aug 2019 17:53:09 +0300 Subject: [PATCH 19/23] net/mlx5e: Add device out of buffer counter Added the following packets drop counter: Device out of buffer - counts packets which were dropped due to full device internal receive queue. This counter will be shown on ethtool as a new counter called dev_out_of_buffer. The counter is read from FW by command QUERY_VNIC_ENV. Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- .../ethernet/mellanox/mlx5/core/en_stats.c | 40 ++++++++++++------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 18e4c162256a..f1065e78086a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -369,17 +369,27 @@ static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv) } #define VNIC_ENV_OFF(c) MLX5_BYTE_OFF(query_vnic_env_out, c) -static const struct counter_desc vnic_env_stats_desc[] = { +static const struct counter_desc vnic_env_stats_steer_desc[] = { { "rx_steer_missed_packets", VNIC_ENV_OFF(vport_env.nic_receive_steering_discard) }, }; -#define NUM_VNIC_ENV_COUNTERS ARRAY_SIZE(vnic_env_stats_desc) +static const struct counter_desc vnic_env_stats_dev_oob_desc[] = { + { "dev_internal_queue_oob", + VNIC_ENV_OFF(vport_env.internal_rq_out_of_buffer) }, +}; + +#define NUM_VNIC_ENV_STEER_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, nic_receive_steering_discard) ? \ + ARRAY_SIZE(vnic_env_stats_steer_desc) : 0) +#define NUM_VNIC_ENV_DEV_OOB_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, vnic_env_int_rq_oob) ? \ + ARRAY_SIZE(vnic_env_stats_dev_oob_desc) : 0) static int mlx5e_grp_vnic_env_get_num_stats(struct mlx5e_priv *priv) { - return MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard) ? - NUM_VNIC_ENV_COUNTERS : 0; + return NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev) + + NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); } static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data, @@ -387,12 +397,13 @@ static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data, { int i; - if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard)) - return idx; - - for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++) + for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - vnic_env_stats_desc[i].format); + vnic_env_stats_steer_desc[i].format); + + for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + vnic_env_stats_dev_oob_desc[i].format); return idx; } @@ -401,12 +412,13 @@ static int mlx5e_grp_vnic_env_fill_stats(struct mlx5e_priv *priv, u64 *data, { int i; - if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard)) - return idx; - - for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++) + for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++) data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vnic.query_vnic_env_out, - vnic_env_stats_desc, i); + vnic_env_stats_steer_desc, i); + + for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++) + data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out, + vnic_env_stats_dev_oob_desc, i); return idx; } From a49e1f31ae155d64355d0cd0e0afa5b2bc8544cd Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Thu, 8 Aug 2019 16:16:28 +0300 Subject: [PATCH 20/23] net/mlx5e: Change function's position to a more fitting file Move function which indicates whether tunnel inner flow table is supported from en.h to en_fs.c. It fits better right after tunnel protocol rules definitions. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 ------ drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 6 ++++++ 3 files changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index e03f973c962f..8d76452cacdc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1065,12 +1065,6 @@ int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); void mlx5e_tx_disable_queue(struct netdev_queue *txq); -static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) -{ - return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); -} - static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) { return MLX5_CAP_ETH(mdev, swp) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index ca2161b42c7f..5acd982ff228 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -98,6 +98,8 @@ enum mlx5e_tunnel_types { MLX5E_NUM_TUNNEL_TT, }; +bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); + /* L3/L4 traffic type classifier */ struct mlx5e_ttc_table { struct mlx5e_flow_table ft; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 76cc10e44080..a8340e4fb0b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -749,6 +749,12 @@ static struct mlx5e_etype_proto ttc_tunnel_rules[] = { }, }; +bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) +{ + return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); +} + static u8 mlx5e_etype_to_ipv(u16 ethertype) { if (ethertype == ETH_P_IP) From a795d8db2a6d3c6f80e7002dd6357e6736dad1b6 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 29 Apr 2019 17:45:52 +0300 Subject: [PATCH 21/23] net/mlx5e: Support RSS for IP-in-IP and IPv6 tunneled packets Add support for inner header RSS on IP-in-IP and IPv6 tunneled packets. Add rules to the steering table regarding outer IP header, with IPv4/6->IP-in-IP. Tunneled packets with protocol numbers: 0x4 (IP-in-IP) and 0x29 (IPv6) are RSS-ed on the inner IP header. Separate FW dependencies between flow table inner IP capabilities and GRE offload support. Allowing this feature even if GRE offload is not supported. Tested with multi stream TCP traffic tunneled with IPnIP. Verified that: Without this patch, only a single RX ring was processing the traffic. With this patch, multiple RX rings were processing the traffic. Verified with and without GRE offload support. Signed-off-by: Aya Levin Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/en/fs.h | 4 ++ .../net/ethernet/mellanox/mlx5/core/en_fs.c | 46 ++++++++++++++++++- 2 files changed, 49 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 5acd982ff228..5aae3a7a5497 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -95,6 +95,10 @@ struct mlx5e_tirc_config { enum mlx5e_tunnel_types { MLX5E_TT_IPV4_GRE, MLX5E_TT_IPV6_GRE, + MLX5E_TT_IPV4_IPIP, + MLX5E_TT_IPV6_IPIP, + MLX5E_TT_IPV4_IPV6, + MLX5E_TT_IPV6_IPV6, MLX5E_NUM_TUNNEL_TT, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index a8340e4fb0b9..b99b17957543 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -747,11 +747,52 @@ static struct mlx5e_etype_proto ttc_tunnel_rules[] = { .etype = ETH_P_IPV6, .proto = IPPROTO_GRE, }, + [MLX5E_TT_IPV4_IPIP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPIP, + }, + [MLX5E_TT_IPV6_IPIP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPIP, + }, + [MLX5E_TT_IPV4_IPV6] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPV6, + }, + [MLX5E_TT_IPV6_IPV6] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPV6, + }, + }; +static bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type) +{ + switch (proto_type) { + case IPPROTO_GRE: + return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); + case IPPROTO_IPIP: + case IPPROTO_IPV6: + return MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip); + default: + return false; + } +} + +static bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) +{ + int tt; + + for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + if (mlx5e_tunnel_proto_supported(mdev, ttc_tunnel_rules[tt].proto)) + return true; + } + return false; +} + bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { - return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && + return (mlx5e_any_tunnel_proto_supported(mdev) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); } @@ -844,6 +885,9 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest.ft = params->inner_ttc->ft.t; for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + if (!mlx5e_tunnel_proto_supported(priv->mdev, + ttc_tunnel_rules[tt].proto)) + continue; rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest, ttc_tunnel_rules[tt].etype, ttc_tunnel_rules[tt].proto); From e3a53bc536fc279de2ace13b8d6d54b071afb722 Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Tue, 20 Aug 2019 03:36:29 +0300 Subject: [PATCH 22/23] net/mlx5e: Improve stateless offload capability check Use generic function for checking tunnel stateless offload capability instead of separate macros. Signed-off-by: Marina Varshaver Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++-- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index 5aae3a7a5497..68d593074f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -238,5 +238,8 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); +bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type); +bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev); + #endif /* __MLX5E_FLOW_STEER_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index b99b17957543..15b7f0f1427c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -766,7 +766,7 @@ static struct mlx5e_etype_proto ttc_tunnel_rules[] = { }; -static bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type) +bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type) { switch (proto_type) { case IPPROTO_GRE: @@ -779,7 +779,7 @@ static bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_ty } } -static bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) +bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) { int tt; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2786f5b8057d..327c90d936e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4879,7 +4879,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) || - MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + mlx5e_any_tunnel_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; netdev->hw_enc_features |= NETIF_F_TSO6; @@ -4894,7 +4894,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; } - if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) { netdev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM; netdev->hw_enc_features |= NETIF_F_GSO_GRE | From 25948b87dda284664edeb3b3dab689df0a7dc889 Mon Sep 17 00:00:00 2001 From: Marina Varshaver Date: Tue, 20 Aug 2019 04:59:11 +0300 Subject: [PATCH 23/23] net/mlx5e: Support TSO and TX checksum offloads for IP-in-IP tunnels Add TX offloads support for IP-in-IP tunneled packets by reporting the needed netdev features. Signed-off-by: Marina Varshaver Signed-off-by: Avihu Hagag Reviewed-by: Aya Levin Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 327c90d936e9..9ff28e2d72cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4243,6 +4243,8 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: + case IPPROTO_IPIP: + case IPPROTO_IPV6: return features; case IPPROTO_UDP: udph = udp_hdr(skb); @@ -4903,6 +4905,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) NETIF_F_GSO_GRE_CSUM; } + if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_IPIP)) { + netdev->hw_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + netdev->gso_partial_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + } + netdev->hw_features |= NETIF_F_GSO_PARTIAL; netdev->gso_partial_features |= NETIF_F_GSO_UDP_L4; netdev->hw_features |= NETIF_F_GSO_UDP_L4;