From patchwork Wed Feb 13 06:55:32 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040963 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0R4Xw8z9s5c for ; Wed, 13 Feb 2019 17:56:23 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387519AbfBMG4S (ORCPT ); Wed, 13 Feb 2019 01:56:18 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52783 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726100AbfBMG4S (ORCPT ); Wed, 13 Feb 2019 01:56:18 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:14 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7ir021070; Wed, 13 Feb 2019 08:56:11 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen , Or Gerlitz , Daniel Jurgens Subject: [PATCH mlx5-next 01/15] net/mlx5: Use void pointer as the type in address_of macro Date: Tue, 12 Feb 2019 22:55:32 -0800 Message-Id: <20190213065546.3013-2-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang Better to use void * and avoid unnecessary casts. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0845a227a7b2..46223efa1877 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -67,7 +67,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld)) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ From patchwork Wed Feb 13 06:55:33 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040965 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0X06sxz9s5c for ; Wed, 13 Feb 2019 17:56:28 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387543AbfBMG4Z (ORCPT ); Wed, 13 Feb 2019 01:56:25 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52796 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728095AbfBMG4W (ORCPT ); Wed, 13 Feb 2019 01:56:22 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:18 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7is021070; Wed, 13 Feb 2019 08:56:15 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen , Or Gerlitz Subject: [PATCH mlx5-next 02/15] net/mlx5: Use consistent vport num argument type Date: Tue, 12 Feb 2019 22:55:33 -0800 Message-Id: <20190213065546.3013-3-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang Use u16 for vport number, which matches how hardware refers to this argument throughout commands. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 32 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/vport.c | 8 ++--- include/linux/mlx5/vport.h | 8 ++--- 3 files changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a44ea7b85614..d7382892e81c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -52,7 +52,7 @@ enum { struct vport_addr { struct l2addr_node node; u8 action; - u32 vport; + u16 vport; struct mlx5_flow_handle *flow_rule; bool mpfs; /* UC MAC was added to MPFs */ /* A flag indicating that mac was added due to mc promiscuous vport */ @@ -115,7 +115,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, +static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, u16 vlan, u8 qos, u8 set_flags) { u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0}; @@ -152,7 +152,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, /* E-Switch FDB */ static struct mlx5_flow_handle * -__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, +__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule, u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN]) { int match_header = (is_zero_ether_addr(mac_c) ? 0 : @@ -215,7 +215,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, } static struct mlx5_flow_handle * -esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) +esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport) { u8 mac_c[ETH_ALEN]; @@ -224,7 +224,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -237,7 +237,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -377,7 +377,7 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err; /* Skip mlx5_mpfs_add_mac for PFs, @@ -409,7 +409,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err = 0; /* Skip mlx5_mpfs_del_mac for PFs, @@ -438,7 +438,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, struct esw_mc_addr *esw_mc) { u8 *mac = vaddr->node.addr; - u32 vport_idx = 0; + u16 vport_idx = 0; for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) { struct mlx5_vport *vport = &esw->vports[vport_idx]; @@ -485,7 +485,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -525,7 +525,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -564,7 +564,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Apply vport UC/MC list to HW l2 table and FDB table */ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { struct mlx5_vport *vport = &esw->vports[vport_num]; bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; @@ -599,7 +599,7 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, /* Sync vport UC/MC list from vport context */ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { struct mlx5_vport *vport = &esw->vports[vport_num]; bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; @@ -686,7 +686,7 @@ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw, /* Sync vport UC/MC list from vport context * Must be called after esw_update_vport_addr_list */ -static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_vport *vport = &esw->vports[vport_num]; struct l2addr_node *node; @@ -721,7 +721,7 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) } /* Apply vport rx mode to HW FDB table */ -static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, +static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num, bool promisc, bool mc_promisc) { struct esw_mc_addr *allmulti_addr = &esw->mc_promisc; @@ -764,7 +764,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, } /* Sync vport rx mode from vport context */ -static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num) { struct mlx5_vport *vport = &esw->vports[vport_num]; int promisc_all = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 9b150ce9d315..9a928eb48522 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -255,7 +255,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int *list_size) @@ -373,7 +373,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list); int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, u16 vlans[], int *size) { @@ -526,7 +526,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, - u32 vport, u64 node_guid) + u16 vport, u64 node_guid) { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); void *nic_vport_context; @@ -827,7 +827,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid); int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, - u32 vport, + u16 vport, int *promisc_uc, int *promisc_mc, int *promisc_all) diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 9c694808c212..1654b911cdb2 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -60,7 +60,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, - u32 vport, u64 node_guid); + u16 vport, u64 node_guid); int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, u16 *qkey_viol_cntr); int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport, @@ -78,7 +78,7 @@ int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev, int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, u64 *node_guid); int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int *list_size); @@ -87,7 +87,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, u8 addr_list[][ETH_ALEN], int list_size); int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, - u32 vport, + u16 vport, int *promisc_uc, int *promisc_mc, int *promisc_all); @@ -96,7 +96,7 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, int promisc_mc, int promisc_all); int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, u16 vlans[], int *size); int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, From patchwork Wed Feb 13 06:55:34 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040967 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0f4MzQz9s5c for ; Wed, 13 Feb 2019 17:56:34 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387570AbfBMG4c (ORCPT ); Wed, 13 Feb 2019 01:56:32 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52816 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387544AbfBMG41 (ORCPT ); Wed, 13 Feb 2019 01:56:27 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:21 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7it021070; Wed, 13 Feb 2019 08:56:18 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Mark Bloch Subject: [PATCH mlx5-next 03/15] IB/mlx5: Use unified register/load function for uplink and VF vports Date: Tue, 12 Feb 2019 22:55:34 -0800 Message-Id: <20190213065546.3013-4-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang IB driver maintains different registration and load function calls for uplink and VF vports. This is not necessary as they only differ with each other on their profiles. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/ib_rep.c | 73 +++++++---------------------- drivers/infiniband/hw/mlx5/ib_rep.h | 10 ++-- drivers/infiniband/hw/mlx5/main.c | 26 +++++----- 3 files changed, 37 insertions(+), 72 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 46a9ddc8ca56..3fb22967c098 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -6,7 +6,7 @@ #include "ib_rep.h" #include "srq.h" -static const struct mlx5_ib_profile rep_profile = { +static const struct mlx5_ib_profile vf_rep_profile = { STAGE_CREATE(MLX5_IB_STAGE_INIT, mlx5_ib_stage_init_init, mlx5_ib_stage_init_cleanup), @@ -45,31 +45,18 @@ static const struct mlx5_ib_profile rep_profile = { NULL), }; -static int -mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) -{ - struct mlx5_ib_dev *ibdev; - - ibdev = mlx5_ib_rep_to_dev(rep); - if (!__mlx5_ib_add(ibdev, ibdev->profile)) - return -EINVAL; - return 0; -} - -static void -mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep) -{ - struct mlx5_ib_dev *ibdev; - - ibdev = mlx5_ib_rep_to_dev(rep); - __mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX); -} - static int mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { +#define FDB_UPLINK_VPORT 0xffff + const struct mlx5_ib_profile *profile; struct mlx5_ib_dev *ibdev; + if (rep->vport == FDB_UPLINK_VPORT) + profile = &uplink_rep_profile; + else + profile = &vf_rep_profile; + ibdev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*ibdev)); if (!ibdev) return -ENOMEM; @@ -78,7 +65,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) ibdev->mdev = dev; ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports), MLX5_CAP_GEN(dev, num_vhca_ports)); - if (!__mlx5_ib_add(ibdev, &rep_profile)) + if (!__mlx5_ib_add(ibdev, profile)) return -EINVAL; rep->rep_if[REP_IB].priv = ibdev; @@ -105,15 +92,14 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep) return mlx5_ib_rep_to_dev(rep); } -static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev) +void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) { - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vports = MLX5_TOTAL_VPORTS(mdev); + struct mlx5_eswitch_rep_if rep_if = {}; int vport; - for (vport = 1; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep_if rep_if = {}; - + for (vport = 0; vport < total_vports; vport++) { rep_if.load = mlx5_ib_vport_rep_load; rep_if.unload = mlx5_ib_vport_rep_unload; rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; @@ -121,39 +107,16 @@ static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev) } } -static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev) +void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) { - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); + struct mlx5_eswitch *esw = mdev->priv.eswitch; + int total_vports = MLX5_TOTAL_VPORTS(mdev); int vport; - for (vport = 1; vport < total_vfs; vport++) + for (vport = total_vports - 1; vport >= 0; vport--) mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB); } -void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) -{ - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - struct mlx5_eswitch_rep_if rep_if = {}; - - rep_if.load = mlx5_ib_nic_rep_load; - rep_if.unload = mlx5_ib_nic_rep_unload; - rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; - rep_if.priv = dev; - - mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB); - - mlx5_ib_rep_register_vf_vports(dev); -} - -void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) -{ - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - - mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */ - mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/ -} - u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) { return mlx5_eswitch_mode(esw); diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h index 2ba73636a2fb..798d41e61fb4 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.h +++ b/drivers/infiniband/hw/mlx5/ib_rep.h @@ -10,14 +10,16 @@ #include "mlx5_ib.h" #ifdef CONFIG_MLX5_ESWITCH +extern const struct mlx5_ib_profile uplink_rep_profile; + u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, int vport_index); struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw); struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, int vport_index); -void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev); -void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev); +void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev); +void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev); int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq); struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, @@ -48,8 +50,8 @@ struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, return NULL; } -static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {} -static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {} +static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {} +static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {} static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq) { diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 94fe253d4956..87ce62e44898 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -6386,7 +6386,7 @@ static const struct mlx5_ib_profile pf_profile = { mlx5_ib_stage_delay_drop_cleanup), }; -static const struct mlx5_ib_profile nic_rep_profile = { +const struct mlx5_ib_profile uplink_rep_profile = { STAGE_CREATE(MLX5_IB_STAGE_INIT, mlx5_ib_stage_init_init, mlx5_ib_stage_init_cleanup), @@ -6479,6 +6479,12 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) printk_once(KERN_INFO "%s", mlx5_version); + if (MLX5_ESWITCH_MANAGER(mdev) && + mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { + mlx5_ib_register_vport_reps(mdev); + return mdev; + } + port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); @@ -6493,14 +6499,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); - if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { - dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); - dev->profile = &nic_rep_profile; - mlx5_ib_register_vport_reps(dev); - return dev; - } - return __mlx5_ib_add(dev, &pf_profile); } @@ -6509,6 +6507,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_dev *dev; + if (MLX5_ESWITCH_MANAGER(mdev) && context == mdev) { + mlx5_ib_unregister_vport_reps(mdev); + return; + } + if (mlx5_core_is_mp_slave(mdev)) { mpi = context; mutex_lock(&mlx5_ib_multiport_mutex); @@ -6520,10 +6523,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) } dev = context; - if (dev->profile == &nic_rep_profile) - mlx5_ib_unregister_vport_reps(dev); - else - __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); + __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); ib_dealloc_device((struct ib_device *)dev); } From patchwork Wed Feb 13 06:55:35 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040966 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0c1vPpz9s5c for ; Wed, 13 Feb 2019 17:56:32 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387561AbfBMG4a (ORCPT ); Wed, 13 Feb 2019 01:56:30 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52819 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387545AbfBMG43 (ORCPT ); Wed, 13 Feb 2019 01:56:29 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:24 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7iu021070; Wed, 13 Feb 2019 08:56:21 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen Subject: [PATCH mlx5-next 04/15] net/mlx5: Introduce Mellanox SmartNIC and modify page management logic Date: Tue, 12 Feb 2019 22:55:35 -0800 Message-Id: <20190213065546.3013-5-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang Mellanox's SmartNIC combines embedded CPU(e.g, ARM) processing power with advanced network offloads to accelerate a multitude of security, networking and storage applications. With the introduction of the SmartNIC, there is a new PCI function called Embedded CPU Physical Function(ECPF). And it's possible for a PF to get its ICM pages from the ECPF PCI function. Driver shall identify if it is running on such a function by reading a bit in the initialization segment. When firmware asks for pages, it would issue a page request event specifying how many pages it requests and for which function. That driver responds with a manage_pages command providing the requested pages along with an indication for which function it is providing these pages. The encoding before this patch was as follows: function_id == 0: pages are requested for the function receiving the EQE. function_id != 0: pages are requested for VF identified by the function_id value A new one bit field in the EQE identifies that pages are requested for the ECPF. The notion of page_supplier can be introduced here and to support that, manage pages and query pages were modified so firmware can distinguish the following cases: 1. Function provides pages for itself 2. PF provides pages for its VF 3. ECPF provides pages to itself 4. ECPF provides pages for another function This distinction is possible through the introduction of the bit "embedded_cpu_function" in query_pages, manage_pages and page request EQE. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/Makefile | 2 +- .../net/ethernet/mellanox/mlx5/core/ecpf.c | 9 ++++ .../net/ethernet/mellanox/mlx5/core/ecpf.h | 25 +++++++++ .../net/ethernet/mellanox/mlx5/core/main.c | 2 + .../ethernet/mellanox/mlx5/core/mlx5_core.h | 2 +- .../ethernet/mellanox/mlx5/core/pagealloc.c | 54 +++++++++++++------ .../net/ethernet/mellanox/mlx5/core/sriov.c | 2 +- include/linux/mlx5/device.h | 2 +- include/linux/mlx5/driver.h | 9 +++- include/linux/mlx5/mlx5_ifc.h | 12 +++-- 10 files changed, 94 insertions(+), 25 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/ecpf.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/ecpf.h diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 0257731e6d42..07965350b903 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o # # Core extra # -mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o +mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o ecpf.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c new file mode 100644 index 000000000000..28b8c5c5c8c7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "ecpf.h" + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) +{ + return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h new file mode 100644 index 000000000000..8b684f0ab48f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_ECPF_H__ +#define __MLX5_ECPF_H__ + +#include +#include "mlx5_core.h" + +#ifdef CONFIG_MLX5_ESWITCH + +enum { + MLX5_ECPU_BIT_NUM = 23, +}; + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); + +#else /* CONFIG_MLX5_ESWITCH */ + +static inline bool +mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; } + +#endif /* CONFIG_MLX5_ESWITCH */ + +#endif /* __MLX5_ECPF_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e38aa206ab6d..bf810fd91454 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -65,6 +65,7 @@ #include "lib/vxlan.h" #include "lib/devcom.h" #include "diag/fw_tracer.h" +#include "ecpf.h" MODULE_AUTHOR("Eli Cohen "); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -901,6 +902,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, struct pci_dev *pdev = dev->pdev; int err; + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c68dcea5985b..b127044293b1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -121,7 +121,7 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 modify_bitmask); int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 element_id); -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages); u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index a83b517b0714..41025387ff2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -48,6 +48,7 @@ enum { struct mlx5_pages_req { struct mlx5_core_dev *dev; u16 func_id; + u8 ec_function; s32 npages; struct work_struct work; }; @@ -143,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, MLX5_SET(query_pages_in, in, op_mod, boot ? MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES : MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES); + MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev)); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -253,7 +255,8 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id) return err; } -static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) +static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id, + bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -262,6 +265,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES); MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -270,7 +274,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) } static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, - int notify_fail) + int notify_fail, bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); @@ -305,6 +309,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); if (err) { @@ -316,8 +321,11 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, dev->priv.fw_pages += npages; if (func_id) dev->priv.vfs_pages += npages; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages += npages; - mlx5_core_dbg(dev, "err %d\n", err); + mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", + npages, ec_function, func_id, err); kvfree(in); return 0; @@ -328,7 +336,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, out_free: kvfree(in); if (notify_fail) - page_notify_fail(dev, func_id); + page_notify_fail(dev, func_id, ec_function); return err; } @@ -364,7 +372,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, } static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, - int *nclaimed) + int *nclaimed, bool ec_function) { int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -385,6 +393,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen); @@ -410,6 +419,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, dev->priv.fw_pages -= num_claimed; if (func_id) dev->priv.vfs_pages -= num_claimed; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages -= num_claimed; out_free: kvfree(out); @@ -423,9 +434,10 @@ static void pages_work_handler(struct work_struct *work) int err = 0; if (req->npages < 0) - err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL); + err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL, + req->ec_function); else if (req->npages > 0) - err = give_pages(dev, req->func_id, req->npages, 1); + err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function); if (err) mlx5_core_warn(dev, "%s fail %d\n", @@ -434,6 +446,10 @@ static void pages_work_handler(struct work_struct *work) kfree(req); } +enum { + EC_FUNCTION_MASK = 0x8000, +}; + static int req_pages_handler(struct notifier_block *nb, unsigned long type, void *data) { @@ -441,6 +457,7 @@ static int req_pages_handler(struct notifier_block *nb, struct mlx5_core_dev *dev; struct mlx5_priv *priv; struct mlx5_eqe *eqe; + bool ec_function; u16 func_id; s32 npages; @@ -450,6 +467,7 @@ static int req_pages_handler(struct notifier_block *nb, func_id = be16_to_cpu(eqe->data.req_pages.func_id); npages = be32_to_cpu(eqe->data.req_pages.num_pages); + ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK; mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n", func_id, npages); req = kzalloc(sizeof(*req), GFP_ATOMIC); @@ -461,6 +479,7 @@ static int req_pages_handler(struct notifier_block *nb, req->dev = dev; req->func_id = func_id; req->npages = npages; + req->ec_function = ec_function; INIT_WORK(&req->work, pages_work_handler); queue_work(dev->priv.pg_wq, &req->work); return NOTIFY_OK; @@ -479,7 +498,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot) mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n", npages, boot ? "boot" : "init", func_id); - return give_pages(dev, func_id, npages, 0); + return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev)); } enum { @@ -513,7 +532,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) fwp = rb_entry(p, struct fw_page, rb_node); err = reclaim_pages(dev, fwp->func_id, optimal_reclaimed_pages(), - &nclaimed); + &nclaimed, mlx5_core_is_ecpf(dev)); if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", @@ -535,6 +554,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.vfs_pages, "VFs FW pages counter is %d after reclaiming all pages\n", dev->priv.vfs_pages); + WARN(dev->priv.peer_pf_pages, + "Peer PF FW pages counter is %d after reclaiming all pages\n", + dev->priv.peer_pf_pages); return 0; } @@ -567,10 +589,10 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) flush_workqueue(dev->priv.pg_wq); } -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - int prev_vfs_pages = dev->priv.vfs_pages; + int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { @@ -578,16 +600,16 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) return 0; } - mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages, + mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages, dev->priv.name); - while (dev->priv.vfs_pages) { + while (*pages) { if (time_after(jiffies, end)) { - mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages); + mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages); return -ETIMEDOUT; } - if (dev->priv.vfs_pages < prev_vfs_pages) { + if (*pages < prev_pages) { end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - prev_vfs_pages = dev->priv.vfs_pages; + prev_pages = *pages; } msleep(50); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 6e178030d8fb..7b23fa8d2d60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) if (MLX5_ESWITCH_MANAGER(dev)) mlx5_eswitch_disable_sriov(dev->priv.eswitch); - if (mlx5_wait_for_vf_pages(dev)) + if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 46223efa1877..f2070350f60a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -591,7 +591,7 @@ struct mlx5_eqe_cmd { }; struct mlx5_eqe_page_req { - u8 rsvd0[2]; + __be16 ec_function; __be16 func_id; __be32 num_pages; __be32 rsvd1[5]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 039c9398614c..cce4e8293384 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -522,6 +522,7 @@ struct mlx5_priv { atomic_t reg_pages; struct list_head free_list; int vfs_pages; + int peer_pf_pages; struct mlx5_core_health health; @@ -652,6 +653,7 @@ struct mlx5_core_dev { u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; + u8 embedded_cpu; } caps; u64 sys_image_guid; phys_addr_t iseg_base; @@ -922,7 +924,7 @@ void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s32 npages); + s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); @@ -1076,6 +1078,11 @@ static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); } +static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) +{ + return dev->caps.embedded_cpu; +} + #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev)) #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c5c679390fbd..46799b4c8859 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4441,7 +4441,8 @@ struct mlx5_ifc_query_pages_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 num_pages[0x20]; @@ -4460,7 +4461,8 @@ struct mlx5_ifc_query_pages_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -5880,7 +5882,8 @@ struct mlx5_ifc_manage_pages_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 input_num_entries[0x20]; @@ -8749,7 +8752,8 @@ struct mlx5_ifc_initial_seg_bits { u8 initializing[0x1]; u8 reserved_at_fe1[0x4]; u8 nic_interface_supported[0x3]; - u8 reserved_at_fe8[0x18]; + u8 embedded_cpu[0x1]; + u8 reserved_at_fe9[0x17]; struct mlx5_ifc_health_buffer_bits health_buffer; From patchwork Wed Feb 13 06:55:36 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040968 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0h6GWmz9s5c for ; Wed, 13 Feb 2019 17:56:36 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387585AbfBMG4f (ORCPT ); Wed, 13 Feb 2019 01:56:35 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52842 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387562AbfBMG4b (ORCPT ); Wed, 13 Feb 2019 01:56:31 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:27 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7iv021070; Wed, 13 Feb 2019 08:56:25 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen Subject: [PATCH mlx5-next 05/15] net/mlx5: Update enable HCA dependency Date: Tue, 12 Feb 2019 22:55:36 -0800 Message-Id: <20190213065546.3013-6-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang With the introduction of ECPF, we require that the ECPF driver will aways call enable/disable HCA for that PF in the same way a PF does this for its VFs. The PF is still responsible for calling enable and disable HCA for its VFs. To distinguish between the ECPF executing enable/disable HCA for itself or for the PF, it sets the embedded CPU function bit in the input params struct of these commands. When the bit is cleared and function ID is zero, it refers to the peer PF. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/ecpf.c | 76 +++++++++++++++++++ .../net/ethernet/mellanox/mlx5/core/ecpf.h | 4 + .../net/ethernet/mellanox/mlx5/core/main.c | 14 ++++ include/linux/mlx5/mlx5_ifc.h | 6 +- 4 files changed, 98 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 28b8c5c5c8c7..1bcf8b8f9713 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -7,3 +7,79 @@ bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1; } + +static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; + + MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); + MLX5_SET(enable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); +} + +static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; + + MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); + MLX5_SET(disable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_peer_pf_init(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_enable_hca(dev); + if (err) + mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n", + err); + + return err; +} + +static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_disable_hca(dev); + if (err) { + mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n", + err); + return; + } + + err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n", + err); +} + +int mlx5_ec_init(struct mlx5_core_dev *dev) +{ + int err = 0; + + if (!mlx5_core_is_ecpf(dev)) + return 0; + + /* ECPF shall enable HCA for peer PF in the same way a PF + * does this for its VFs. + */ + err = mlx5_peer_pf_init(dev); + if (err) + return err; + + return 0; +} + +void mlx5_ec_cleanup(struct mlx5_core_dev *dev) +{ + if (!mlx5_core_is_ecpf(dev)) + return; + + mlx5_peer_pf_cleanup(dev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h index 8b684f0ab48f..d3d7a00a02ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -14,11 +14,15 @@ enum { }; bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); +int mlx5_ec_init(struct mlx5_core_dev *dev); +void mlx5_ec_cleanup(struct mlx5_core_dev *dev); #else /* CONFIG_MLX5_ESWITCH */ static inline bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; } +static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {} #endif /* CONFIG_MLX5_ESWITCH */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index bf810fd91454..772dc460cfe6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -615,6 +615,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); MLX5_SET(enable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); } @@ -625,6 +627,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); MLX5_SET(disable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -1074,6 +1078,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_sriov; } + err = mlx5_ec_init(dev); + if (err) { + dev_err(&pdev->dev, "Failed to init embedded CPU\n"); + goto err_ec; + } + if (mlx5_device_registered(dev)) { mlx5_attach_device(dev); } else { @@ -1091,6 +1101,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, return 0; err_reg_dev: + mlx5_ec_cleanup(dev); + +err_ec: mlx5_sriov_detach(dev); err_sriov: @@ -1165,6 +1178,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (mlx5_device_registered(dev)) mlx5_detach_device(dev); + mlx5_ec_cleanup(dev); mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 46799b4c8859..1b6d5a563a3a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6061,7 +6061,8 @@ struct mlx5_ifc_enable_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -6105,7 +6106,8 @@ struct mlx5_ifc_disable_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; From patchwork Wed Feb 13 06:55:37 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040970 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0t0CTYz9s5c for ; Wed, 13 Feb 2019 17:56:46 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387638AbfBMG4o (ORCPT ); Wed, 13 Feb 2019 01:56:44 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52871 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387592AbfBMG4h (ORCPT ); Wed, 13 Feb 2019 01:56:37 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:31 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7iw021070; Wed, 13 Feb 2019 08:56:28 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen , Or Gerlitz Subject: [PATCH mlx5-next 06/15] net/mlx5: Add query host params command Date: Tue, 12 Feb 2019 22:55:37 -0800 Message-Id: <20190213065546.3013-7-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang The QUERY_HOST_PARAMS command is used by an Embedded CPU Physical Function (ECPF) driver to identify and retrieve information about the PF on the host side. E.g, number of virtual functions and PCI BDF. The number of VFs can be changed on the fly, a function is added to query current number of VFs and will be used in downstream patches. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 + .../net/ethernet/mellanox/mlx5/core/ecpf.c | 27 ++++++++++++ .../net/ethernet/mellanox/mlx5/core/ecpf.h | 4 ++ include/linux/mlx5/mlx5_ifc.h | 41 +++++++++++++++++++ 4 files changed, 74 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index a25a8c6f938e..46d70eb2d2f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -316,6 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: case MLX5_CMD_OP_DEALLOC_MEMIC: case MLX5_CMD_OP_PAGE_FAULT_RESUME: + case MLX5_CMD_OP_QUERY_HOST_PARAMS: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -627,6 +628,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT); MLX5_COMMAND_STR_CASE(ALLOC_MEMIC); MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC); + MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS); default: return "unknown command opcode"; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 1bcf8b8f9713..4746f2d28fb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -83,3 +83,30 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) mlx5_peer_pf_cleanup(dev); } + +static int mlx5_query_host_params_context(struct mlx5_core_dev *dev, + u32 *out, int outlen) +{ + u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {}; + + MLX5_SET(query_host_params_in, in, opcode, + MLX5_CMD_OP_QUERY_HOST_PARAMS); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); +} + +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ + u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {}; + int err; + + err = mlx5_query_host_params_context(dev, out, sizeof(out)); + if (err) + return err; + + *num_vf = MLX5_GET(query_host_params_out, out, + host_params_context.host_num_of_vfs); + mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h index d3d7a00a02ac..346372df218f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -16,6 +16,7 @@ enum { bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); int mlx5_ec_init(struct mlx5_core_dev *dev); void mlx5_ec_cleanup(struct mlx5_core_dev *dev); +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf); #else /* CONFIG_MLX5_ESWITCH */ @@ -23,6 +24,9 @@ static inline bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; } static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {} +static inline int +mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_ESWITCH */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1b6d5a563a3a..565046830559 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -142,6 +142,7 @@ 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_QUERY_HOST_PARAMS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -9522,4 +9523,44 @@ struct mlx5_ifc_mtrc_ctrl_bits { u8 reserved_at_80[0x180]; }; +struct mlx5_ifc_host_params_context_bits { + u8 host_number[0x8]; + u8 reserved_at_8[0x8]; + u8 host_num_of_vfs[0x10]; + + u8 reserved_at_20[0x10]; + u8 host_pci_bus[0x10]; + + u8 reserved_at_40[0x10]; + u8 host_pci_device[0x10]; + + u8 reserved_at_60[0x10]; + u8 host_pci_function[0x10]; + + u8 reserved_at_80[0x180]; +}; + +struct mlx5_ifc_query_host_params_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_host_params_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_host_params_context_bits host_params_context; + + u8 reserved_at_280[0x180]; +}; + #endif /* MLX5_IFC_H */ From patchwork Wed Feb 13 06:55:38 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040969 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0l4Wnnz9s5c for ; Wed, 13 Feb 2019 17:56:39 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387607AbfBMG4i (ORCPT ); Wed, 13 Feb 2019 01:56:38 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52873 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387594AbfBMG4g (ORCPT ); Wed, 13 Feb 2019 01:56:36 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:34 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7ix021070; Wed, 13 Feb 2019 08:56:31 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Eli Cohen , Or Gerlitz Subject: [PATCH mlx5-next 07/15] net/mlx5: Add host params change event Date: Tue, 12 Feb 2019 22:55:38 -0800 Message-Id: <20190213065546.3013-8-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang In Embedded CPU (EC) configurations, the EC driver needs to know when the number of virtual functions change on the corresponding PF at the host side. This is required so the EC driver can create or destroy representor net devices that represent the VFs ports. Whenever a change in the number of VFs occurs, firmware will generate an event towards the EC which will trigger a work to complete the rest of the handling. The specifics of the handling will be introduced in a downstream patch. Signed-off-by: Bodong Wang Signed-off-by: Eli Cohen Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/events.c | 2 ++ include/linux/mlx5/device.h | 2 ++ include/linux/mlx5/driver.h | 5 +++++ 4 files changed, 12 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 7092457705a2..5c02f9291799 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -530,6 +530,9 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER); + if (mlx5_core_is_ecpf_esw_manager(dev)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE); + return async_event_mask; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index fbc42b7252a9..4f7f776d6332 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -103,6 +103,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_STALL_EVENT"; case MLX5_EVENT_TYPE_CMD: return "MLX5_EVENT_TYPE_CMD"; + case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE: + return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE"; case MLX5_EVENT_TYPE_PAGE_REQUEST: return "MLX5_EVENT_TYPE_PAGE_REQUEST"; case MLX5_EVENT_TYPE_PAGE_FAULT: diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f2070350f60a..f93a5598b942 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -342,6 +342,8 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, + MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe, + MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c, MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index cce4e8293384..151563a12fc2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1083,6 +1083,11 @@ static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) return dev->caps.embedded_cpu; } +static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev) +{ + return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager); +} + #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev)) #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ From patchwork Wed Feb 13 06:55:39 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040971 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr0w4WRgz9s5c for ; Wed, 13 Feb 2019 17:56:48 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387662AbfBMG4r (ORCPT ); Wed, 13 Feb 2019 01:56:47 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52887 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387594AbfBMG4l (ORCPT ); Wed, 13 Feb 2019 01:56:41 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:37 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j0021070; Wed, 13 Feb 2019 08:56:35 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Or Gerlitz Subject: [PATCH mlx5-next 08/15] net/mlx5: Provide an alternative VF upper bound for ECPF Date: Tue, 12 Feb 2019 22:55:39 -0800 Message-Id: <20190213065546.3013-9-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang ECPF doesn't support SR-IOV, but an ECPF E-Switch manager shall know the max VFs supported by its peer host PF in order to control those VF vports. The current driver implementation uses the total vfs quantity as provided by the pci sub-system for an upper bound of the VF vports the e-switch code needs to deal with. This obviously can't work as is on ECPF e-switch manager. For now, we use a hard coded value of 128 on such systems. Signed-off-by: Bodong Wang Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 151563a12fc2..46e0aa52a58a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1088,7 +1088,16 @@ static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev) return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager); } -#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev)) +#define MLX5_HOST_PF_MAX_VFS (127u) +static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_ecpf_esw_manager(dev)) + return MLX5_HOST_PF_MAX_VFS; + else + return pci_sriov_get_totalvfs(dev->pdev); +} + +#define MLX5_TOTAL_VPORTS(mdev) (1 + mlx5_core_max_vfs(mdev)) #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ From patchwork Wed Feb 13 06:55:40 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040972 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr106Xrvz9sDr for ; Wed, 13 Feb 2019 17:56:52 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387667AbfBMG4v (ORCPT ); Wed, 13 Feb 2019 01:56:51 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52903 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387642AbfBMG4s (ORCPT ); Wed, 13 Feb 2019 01:56:48 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:41 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j1021070; Wed, 13 Feb 2019 08:56:38 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Or Gerlitz Subject: [PATCH mlx5-next 09/15] net/mlx5: E-Switch, Normalize the name of uplink vport number Date: Tue, 12 Feb 2019 22:55:40 -0800 Message-Id: <20190213065546.3013-10-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang Driver used to name uplink vport as FDB_UPLINK_VPORT, it's hard to comply with the same naming convention along with the introduction of other vports. Use MLX5_VPORT as the prefix for such vports and relocate the uplink vport definition to public header file for the benefits of both net and IB drivers. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/ib_rep.c | 4 ++-- .../net/ethernet/mellanox/mlx5/core/en_rep.c | 22 +++++++++---------- .../net/ethernet/mellanox/mlx5/core/en_tc.c | 6 ++--- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 8 +++---- .../net/ethernet/mellanox/mlx5/core/eswitch.h | 2 -- .../mellanox/mlx5/core/eswitch_offloads.c | 14 ++++++------ include/linux/mlx5/vport.h | 4 ++++ 7 files changed, 30 insertions(+), 30 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 3fb22967c098..99cae9a10195 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -3,6 +3,7 @@ * Copyright (c) 2018 Mellanox Technologies. All rights reserved. */ +#include #include "ib_rep.h" #include "srq.h" @@ -48,11 +49,10 @@ static const struct mlx5_ib_profile vf_rep_profile = { static int mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { -#define FDB_UPLINK_VPORT 0xffff const struct mlx5_ib_profile *profile; struct mlx5_ib_dev *ibdev; - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) profile = &uplink_rep_profile; else profile = &vf_rep_profile; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 96cc0c6a4014..c78d21b2501e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -152,7 +152,7 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_uplink_rep_update_hw_counters(priv); else mlx5e_vf_rep_update_hw_counters(priv); @@ -1207,7 +1207,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) return false; rep = rpriv->rep; - return (rep->vport == FDB_UPLINK_VPORT); + return (rep->vport == MLX5_VPORT_UPLINK); } static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id) @@ -1343,7 +1343,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->sw_mtu = netdev->mtu; /* SQ */ - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; else params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE; @@ -1370,7 +1370,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) struct mlx5_eswitch_rep *rep = rpriv->rep; struct mlx5_core_dev *mdev = priv->mdev; - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev); netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep; /* we want a persistent mac for the uplink rep */ @@ -1402,7 +1402,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_TSO6; netdev->hw_features |= NETIF_F_RXCSUM; - if (rep->vport != FDB_UPLINK_VPORT) + if (rep->vport != MLX5_VPORT_UPLINK) netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= netdev->hw_features; @@ -1555,7 +1555,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { uplink_priv = &rpriv->uplink_priv; /* init shared tc flow table */ @@ -1591,7 +1591,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { /* clean indirect TC block notifications */ unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb); mlx5e_rep_indr_clean_block_privs(rpriv); @@ -1710,7 +1710,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rpriv->rep = rep; nch = mlx5e_get_max_num_channels(dev); - profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; + profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; netdev = mlx5e_create_netdev(dev, profile, nch, rpriv); if (!netdev) { pr_warn("Failed to create representor netdev for vport %d\n", @@ -1723,7 +1723,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rep->rep_if[REP_ETH].priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_create_mdev_resources(dev); if (err) goto err_destroy_netdev; @@ -1759,7 +1759,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) mlx5e_detach_netdev(netdev_priv(netdev)); err_destroy_mdev_resources: - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(dev); err_destroy_netdev: @@ -1779,7 +1779,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) unregister_netdev(netdev); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(priv->mdev); mlx5e_destroy_netdev(priv); kfree(ppriv); /* mlx5e_rep_priv */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index cae6c6d48984..1a73e661056a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1834,7 +1834,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; - if (rep->vport != FDB_UPLINK_VPORT && + if (rep->vport != MLX5_VPORT_UPLINK && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && esw->offloads.inline_mode < match_level)) { NL_SET_ERR_MSG_MOD(extack, @@ -2724,7 +2724,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags) static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; - bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT && + bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK && flow->flags & MLX5E_TC_FLOW_INGRESS; bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); @@ -2849,7 +2849,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f, * original flow and packets redirected from uplink use the * peer mdev. */ - if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT) + if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK) in_mdev = peer_priv->mdev; else in_mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d7382892e81c..0db56b4b7009 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -40,8 +40,6 @@ #include "eswitch.h" #include "fs_core.h" -#define UPLINK_VPORT 0xFFFF - enum { MLX5_ACTION_NONE = 0, MLX5_ACTION_ADD = 1, @@ -188,7 +186,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule, misc_parameters); mc_misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT); + MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK); MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port); } @@ -499,7 +497,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) return -ENOMEM; esw_mc->uplink_rule = /* Forward MC MAC to Uplink */ - esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT); + esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK); /* Add this multicast mac to all the mc promiscuous vports */ update_allmulti_vports(esw, vaddr, esw_mc); @@ -736,7 +734,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num, if (!allmulti_addr->uplink_rule) allmulti_addr->uplink_rule = esw_fdb_set_vport_allmulti_rule(esw, - UPLINK_VPORT); + MLX5_VPORT_UPLINK); allmulti_addr->refcnt++; } else if (vport->allmulti_rule) { mlx5_del_flow_rules(vport->allmulti_rule); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 9c89eea9b2c3..94da74b1e6ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -49,8 +49,6 @@ #define MLX5_MAX_MC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_mc_list)) -#define FDB_UPLINK_VPORT 0xffff - #define MLX5_MIN_BW_SHARE 1 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 53065b6ae593..b0b1267eab07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -359,15 +359,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, in_rep = attr->in_rep; out_rep = attr->dests[0].rep; - if (push && in_rep->vport == FDB_UPLINK_VPORT) + if (push && in_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; - if (pop && out_rep->vport == FDB_UPLINK_VPORT) + if (pop && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* vport has vlan push configured, can't offload VF --> wire rules w.o it */ if (!push && !pop && fwd) - if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT) + if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* protects against (1) setting rules with different vlans to push and @@ -409,7 +409,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) { + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { vport->vlan_refcount++; attr->vlan_handled = true; } @@ -469,7 +469,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) vport->vlan_refcount--; return 0; @@ -1227,7 +1227,7 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) ether_addr_copy(rep->hw_id, hw_id); } - offloads->vport_reps[0].vport = FDB_UPLINK_VPORT; + offloads->vport_reps[0].vport = MLX5_VPORT_UPLINK; return 0; } @@ -1811,7 +1811,7 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; - if (vport == FDB_UPLINK_VPORT) + if (vport == MLX5_VPORT_UPLINK) vport = UPLINK_REP_INDEX; rep = &offloads->vport_reps[vport]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 1654b911cdb2..2e2928eacd97 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -42,6 +42,10 @@ enum { MLX5_CAP_INLINE_MODE_NOT_REQUIRED, }; +enum { + MLX5_VPORT_UPLINK = 0xffff +}; + u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport, u8 state); From patchwork Wed Feb 13 06:55:41 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040973 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr136jQDz9sDr for ; Wed, 13 Feb 2019 17:56:55 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387674AbfBMG4w (ORCPT ); Wed, 13 Feb 2019 01:56:52 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52905 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387656AbfBMG4q (ORCPT ); Wed, 13 Feb 2019 01:56:46 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:44 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j2021070; Wed, 13 Feb 2019 08:56:41 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Or Gerlitz Subject: [PATCH mlx5-next 10/15] net/mlx5: Relocate vport macros to the vport header file Date: Tue, 12 Feb 2019 22:55:41 -0800 Message-Id: <20190213065546.3013-11-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang These are two macros in the driver general header which deal with the number of total vports and if a vport is vport manager. Such macros are vport entities, better to place them at the vport header file. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 1 + include/linux/mlx5/driver.h | 6 ------ include/linux/mlx5/vport.h | 7 +++++++ 4 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 5c02f9291799..bb6e5b5d9681 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #ifdef CONFIG_RFS_ACCEL diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 79f122b45def..b6a7bc8f667c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include #include +#include #include #include "mlx5_core.h" diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 46e0aa52a58a..c5454f985e1d 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1097,12 +1097,6 @@ static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) return pci_sriov_get_totalvfs(dev->pdev); } -#define MLX5_TOTAL_VPORTS(mdev) (1 + mlx5_core_max_vfs(mdev)) -#define MLX5_VPORT_MANAGER(mdev) \ - (MLX5_CAP_GEN(mdev, vport_group_manager) && \ - (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ - mlx5_core_is_pf(mdev)) - static inline int mlx5_get_gid_table_len(u16 param) { if (param > 4) { diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 2e2928eacd97..28f47e868fbc 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,6 +36,13 @@ #include #include +#define MLX5_TOTAL_VPORTS(mdev) (1 + mlx5_core_max_vfs(mdev)) + +#define MLX5_VPORT_MANAGER(mdev) \ + (MLX5_CAP_GEN(mdev, vport_group_manager) && \ + (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ + mlx5_core_is_pf(mdev)) + enum { MLX5_CAP_INLINE_MODE_L2, MLX5_CAP_INLINE_MODE_VPORT_CONTEXT, From patchwork Wed Feb 13 06:55:42 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040974 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr1456wyz9sLw for ; Wed, 13 Feb 2019 17:56:56 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387606AbfBMG4z (ORCPT ); Wed, 13 Feb 2019 01:56:55 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52921 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387644AbfBMG4w (ORCPT ); Wed, 13 Feb 2019 01:56:52 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:47 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j3021070; Wed, 13 Feb 2019 08:56:45 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Bodong Wang , Or Gerlitz Subject: [PATCH mlx5-next 11/15] net/mlx5: E-Switch, Avoid magic numbers when initializing offloads mode Date: Tue, 12 Feb 2019 22:55:42 -0800 Message-Id: <20190213065546.3013-12-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Bodong Wang When dealing with the offloads mode initialization, driver refers to the number of VFs and add magic number one (1) to take account of the uplink. This is not clear and will make the code less readable after adding other vports (e.g. host PF). As these are special vports compared to VF vports, add a helper macro to denote such special vports and eliminate the use of magic number. Moreover, when creating offloads flow table and groups, the driver reserves two more slots for UC and MC miss rules. Replace this magic number with a helper macro as well. This patch doesn't change any functionality. Signed-off-by: Bodong Wang Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 2 +- .../mellanox/mlx5/core/eswitch_offloads.c | 25 +++++++++++-------- include/linux/mlx5/vport.h | 4 ++- 3 files changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0db56b4b7009..49a9e3877d2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1638,7 +1638,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw, nvfs + 1); + err = esw_offloads_init(esw, nvfs + MLX5_SPECIAL_VPORTS); } if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b0b1267eab07..1496e82b5108 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -46,6 +46,11 @@ enum { FDB_SLOW_PATH }; +/* There are two match-all miss flows, one for unicast dst mac and + * one for multicast. + */ +#define MLX5_ESW_MISS_FLOWS (2) + #define fdb_prio_table(esw, chain, prio, level) \ (esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)] @@ -904,8 +909,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) esw->fdb_table.offloads.fdb_left[i] = ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0; - table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 + - esw->total_vports; + table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + + MLX5_ESW_MISS_FLOWS + esw->total_vports; /* create the slow path fdb with encap set, so further table instances * can be created at run time while VFs are probed if the FW allows that. @@ -999,7 +1004,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) dmac[0] = 0x01; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + MLX5_ESW_MISS_FLOWS); g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -1048,7 +1054,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_destroy_offloads_fast_fdb_tables(esw); } -static int esw_create_offloads_table(struct mlx5_eswitch *esw) +static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; @@ -1062,7 +1068,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -EOPNOTSUPP; } - ft_attr.max_fte = dev->priv.sriov.num_vfs + 2; + ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS; ft_offloads = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft_offloads)) { @@ -1082,16 +1088,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(offloads->ft_offloads); } -static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) +static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; - struct mlx5_priv *priv = &esw->dev->priv; u32 *flow_group_in; void *match_criteria, *misc; int err = 0; - int nvports = priv->sriov.num_vfs + 2; + nvports = nvports + MLX5_ESW_MISS_FLOWS; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; @@ -1407,11 +1412,11 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) return err; - err = esw_create_offloads_table(esw); + err = esw_create_offloads_table(esw, nvports); if (err) goto create_ft_err; - err = esw_create_vport_rx_group(esw); + err = esw_create_vport_rx_group(esw, nvports); if (err) goto create_fg_err; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 28f47e868fbc..3bc05449ac39 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,7 +36,9 @@ #include #include -#define MLX5_TOTAL_VPORTS(mdev) (1 + mlx5_core_max_vfs(mdev)) +#define MLX5_VPORT_PF_PLACEHOLDER (1u) +#define MLX5_SPECIAL_VPORTS (MLX5_VPORT_PF_PLACEHOLDER) +#define MLX5_TOTAL_VPORTS(mdev) (MLX5_SPECIAL_VPORTS + mlx5_core_max_vfs(mdev)) #define MLX5_VPORT_MANAGER(mdev) \ (MLX5_CAP_GEN(mdev, vport_group_manager) && \ From patchwork Wed Feb 13 06:55:43 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040976 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr1G69zgz9s5c for ; Wed, 13 Feb 2019 17:57:06 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387721AbfBMG5F (ORCPT ); Wed, 13 Feb 2019 01:57:05 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52941 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387686AbfBMG5B (ORCPT ); Wed, 13 Feb 2019 01:57:01 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:50 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j4021070; Wed, 13 Feb 2019 08:56:48 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Aya Levin , Eran Ben Elisha Subject: [PATCH mlx5-next 12/15] net/mlx5: Refactor queries to speed fields in Port Type and Speed register Date: Tue, 12 Feb 2019 22:55:43 -0800 Message-Id: <20190213065546.3013-13-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Aya Levin This patch fascicles queries to speed related fields in Port Type and Speed register (PTYS) into a single API. I addition, this patch refactors functions which serves only Ethernet driver: remove the protocol type as an input parameter, move code from 'core' directory into 'en' directory and add 'eth' prefix to the function's name. The patch also encapsulates functions that are not used outside the Ethernet driver removes redundant include files. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 6 +- .../net/ethernet/mellanox/mlx5/core/en/port.c | 75 +++++++++++-- .../net/ethernet/mellanox/mlx5/core/en/port.h | 12 ++ .../ethernet/mellanox/mlx5/core/en_ethtool.c | 23 ++-- .../net/ethernet/mellanox/mlx5/core/port.c | 106 ------------------ include/linux/mlx5/port.h | 11 -- 6 files changed, 91 insertions(+), 142 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 87ce62e44898..efd08b41126c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -393,6 +393,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, struct ib_port_attr *props) { struct mlx5_ib_dev *dev = to_mdev(device); + u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; struct mlx5_core_dev *mdev; struct net_device *ndev, *upper; enum ib_mtu ndev_ib_mtu; @@ -416,10 +417,11 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, /* Possible bad flows are checked before filling out props so in case * of an error it will still be zeroed out. */ - err = mlx5_query_port_eth_proto_oper(mdev, ð_prot_oper, - mdev_port_num); + err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, + mdev_port_num); if (err) goto out; + eth_prot_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); props->active_width = IB_WIDTH_4X; props->active_speed = IB_SPEED_QDR; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 4a37713023be..9a1c2b2f87d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -63,6 +63,67 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = { [MLX5E_50GBASE_KR2] = 50000, }; +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, + struct mlx5e_port_eth_proto *eproto) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + if (!eproto) + return -EINVAL; + + err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port); + if (err) + return err; + + eproto->cap = MLX5_GET(ptys_reg, out, eth_proto_capability); + eproto->admin = MLX5_GET(ptys_reg, out, eth_proto_admin); + eproto->oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + return 0; +} + +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + + *an_status = 0; + *an_disable_cap = 0; + *an_disable_admin = 0; + + if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1)) + return; + + *an_status = MLX5_GET(ptys_reg, out, an_status); + *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); + *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); +} + +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + u32 in[MLX5_ST_SZ_DW(ptys_reg)]; + u8 an_disable_admin; + u8 an_disable_cap; + u8 an_status; + + mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap, + &an_disable_admin); + if (!an_disable_cap && an_disable) + return -EPERM; + + memset(in, 0, sizeof(in)); + + MLX5_SET(ptys_reg, in, local_port, 1); + MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); + MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN); + MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PTYS, 0, 1); +} + u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) { unsigned long temp = eth_proto_oper; @@ -78,16 +139,14 @@ u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { - u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {}; - u32 eth_proto_oper; + struct mlx5e_port_eth_proto eproto; int err; - err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1); + err = mlx5_port_query_eth_proto(mdev, 1, &eproto); if (err) return err; - eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - *speed = mlx5e_port_ptys2speed(eth_proto_oper); + *speed = mlx5e_port_ptys2speed(eproto.oper); if (!(*speed)) err = -EINVAL; @@ -96,17 +155,17 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { + struct mlx5e_port_eth_proto eproto; u32 max_speed = 0; - u32 proto_cap; int err; int i; - err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN); + err = mlx5_port_query_eth_proto(mdev, 1, &eproto); if (err) return err; for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) - if (proto_cap & MLX5E_PROT_MASK(i)) + if (eproto.cap & MLX5E_PROT_MASK(i)) max_speed = max(max_speed, mlx5e_link_speed[i]); *speed = max_speed; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index cd2160b8c9bf..4bdab8be10af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -36,6 +36,18 @@ #include #include "en.h" +struct mlx5e_port_eth_proto { + u32 cap; + u32 admin; + u32 oper; +}; + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, + struct mlx5e_port_eth_proto *eproto); +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin); +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin); u32 mlx5e_port_ptys2speed(u32 eth_proto_oper); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index c9df08133718..c29e141d72fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -882,7 +882,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { struct mlx5_core_dev *mdev = priv->mdev; - u32 eth_proto_cap, eth_proto_admin; + struct mlx5e_port_eth_proto eproto; bool an_changes = false; u8 an_disable_admin; u8 an_disable_cap; @@ -898,14 +898,14 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) : mlx5e_port_speed2linkmodes(speed); - err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN); + err = mlx5_port_query_eth_proto(mdev, 1, &eproto); if (err) { - netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n", + netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); goto out; } - link_modes = link_modes & eth_proto_cap; + link_modes = link_modes & eproto.cap; if (!link_modes) { netdev_err(priv->netdev, "%s: Not supported link mode(s) requested", __func__); @@ -913,24 +913,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, goto out; } - err = mlx5_query_port_proto_admin(mdev, ð_proto_admin, MLX5_PTYS_EN); - if (err) { - netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n", - __func__, err); - goto out; - } - - mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status, - &an_disable_cap, &an_disable_admin); + mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap, + &an_disable_admin); an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE; an_changes = ((!an_disable && an_disable_admin) || (an_disable && !an_disable_admin)); - if (!an_changes && link_modes == eth_proto_admin) + if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes); mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 2b82f35f4c35..b81542820528 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -30,10 +30,7 @@ * SOFTWARE. */ -#include -#include #include -#include #include "mlx5_core.h" int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, @@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration) sizeof(out), MLX5_REG_MLCR, 0, 1); } -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); - else - *proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap); - -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); - else - *proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin); - int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, u8 *link_width_oper, u8 local_port) { @@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper); -int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev, - u32 *proto_oper, u8 local_port) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, - local_port); - if (err) - return err; - - *proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - - return 0; -} -EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper); - int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, u8 local_port) { @@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper); -int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - u32 in[MLX5_ST_SZ_DW(ptys_reg)]; - u8 an_disable_admin; - u8 an_disable_cap; - u8 an_status; - - mlx5_query_port_autoneg(dev, proto_mask, &an_status, - &an_disable_cap, &an_disable_admin); - if (!an_disable_cap && an_disable) - return -EPERM; - - memset(in, 0, sizeof(in)); - - MLX5_SET(ptys_reg, in, local_port, 1); - MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); - MLX5_SET(ptys_reg, in, proto_mask, proto_mask); - if (proto_mask == MLX5_PTYS_EN) - MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); - else - MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin); - - return mlx5_core_access_reg(dev, in, sizeof(in), out, - sizeof(out), MLX5_REG_PTYS, 0, 1); -} -EXPORT_SYMBOL_GPL(mlx5_set_port_ptys); - /* This function should be used after setting a port register only */ void mlx5_toggle_port_link(struct mlx5_core_dev *dev) { @@ -606,25 +519,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) } EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); -void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, - u8 *an_status, - u8 *an_disable_cap, u8 *an_disable_admin) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - - *an_status = 0; - *an_disable_cap = 0; - *an_disable_admin = 0; - - if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1)) - return; - - *an_status = MLX5_GET(ptys_reg, out, an_status); - *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); - *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); -} -EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg); - int mlx5_max_tc(struct mlx5_core_dev *mdev) { u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index bf4bc01ffb0c..5be7eefa6d75 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -110,27 +110,16 @@ enum mlx5e_connector_type { int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask); -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask); int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, u8 *link_width_oper, u8 local_port); int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, u8 local_port); -int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev, - u32 *proto_oper, u8 local_port); -int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin, int proto_mask); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration); -void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, - u8 *an_status, - u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); From patchwork Wed Feb 13 06:55:44 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040975 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr180zVLz9s5c for ; Wed, 13 Feb 2019 17:57:00 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387685AbfBMG47 (ORCPT ); Wed, 13 Feb 2019 01:56:59 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52940 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387644AbfBMG44 (ORCPT ); Wed, 13 Feb 2019 01:56:56 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:54 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j5021070; Wed, 13 Feb 2019 08:56:51 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Aya Levin , Eran Ben Elisha Subject: [PATCH mlx5-next 13/15] net/mlx5: Add new fields to Port Type and Speed register Date: Tue, 12 Feb 2019 22:55:44 -0800 Message-Id: <20190213065546.3013-14-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Aya Levin Register Port Type and Speed (PTYS) introduces three new fields extending the speed/protocols the can be reported and configured. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 565046830559..5decffe565fb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7826,21 +7826,23 @@ struct mlx5_ifc_ptys_reg_bits { u8 proto_mask[0x3]; u8 an_status[0x4]; - u8 reserved_at_24[0x3c]; + u8 reserved_at_24[0x1c]; + + u8 ext_eth_proto_capability[0x20]; u8 eth_proto_capability[0x20]; u8 ib_link_width_capability[0x10]; u8 ib_proto_capability[0x10]; - u8 reserved_at_a0[0x20]; + u8 ext_eth_proto_admin[0x20]; u8 eth_proto_admin[0x20]; u8 ib_link_width_admin[0x10]; u8 ib_proto_admin[0x10]; - u8 reserved_at_100[0x20]; + u8 ext_eth_proto_oper[0x20]; u8 eth_proto_oper[0x20]; @@ -8289,7 +8291,9 @@ struct mlx5_ifc_mpegc_reg_bits { struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x6d]; u8 rx_icrc_encapsulated_counter[0x1]; - u8 reserved_at_6e[0x8]; + u8 reserved_at_6e[0x4]; + u8 ptys_extended_ethernet[0x1]; + u8 reserved_at_73[0x3]; u8 pfcc_mask[0x1]; u8 reserved_at_77[0x3]; u8 per_lane_error_counters[0x1]; From patchwork Wed Feb 13 06:55:45 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040977 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr1H6lSlz9sDr for ; Wed, 13 Feb 2019 17:57:07 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387717AbfBMG5E (ORCPT ); Wed, 13 Feb 2019 01:57:04 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52951 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387644AbfBMG5C (ORCPT ); Wed, 13 Feb 2019 01:57:02 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:56:57 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j6021070; Wed, 13 Feb 2019 08:56:54 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Aya Levin , Eran Ben Elisha Subject: [PATCH mlx5-next 14/15] net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register Date: Tue, 12 Feb 2019 22:55:45 -0800 Message-Id: <20190213065546.3013-15-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Aya Levin This patch exposes new link modes (including 50Gbps per lane), and ext_* fields which describes the new link modes in Port Type and Speed register (PTYS). Access functions, translation functions (speed <-> HW bits) and link max speed function were modified. Signed-off-by: Aya Levin Reviewed-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 3 +- .../net/ethernet/mellanox/mlx5/core/en/port.c | 85 ++++++++++++++----- .../net/ethernet/mellanox/mlx5/core/en/port.h | 8 +- .../ethernet/mellanox/mlx5/core/en_ethtool.c | 9 +- include/linux/mlx5/port.h | 19 +++++ 5 files changed, 94 insertions(+), 30 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index efd08b41126c..3677c00fa3bb 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -421,7 +421,8 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, mdev_port_num); if (err) goto out; - eth_prot_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, false, + eth_proto_oper); props->active_width = IB_WIDTH_4X; props->active_speed = IB_SPEED_QDR; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 9a1c2b2f87d8..122927f3a600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -63,7 +63,31 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = { [MLX5E_50GBASE_KR2] = 50000, }; -int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, +static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { + [MLX5E_SGMII_100M] = 100, + [MLX5E_1000BASE_X_SGMII] = 1000, + [MLX5E_5GBASE_R] = 5000, + [MLX5E_10GBASE_XFI_XAUI_1] = 10000, + [MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000, + [MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000, + [MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000, + [MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000, + [MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000, + [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000, + [MLX5E_400GAUI_8] = 400000, +}; + +static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, + const u32 **arr, u32 *size) +{ + bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + + *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : + ARRAY_SIZE(mlx5e_link_speed); + *arr = ext ? mlx5e_ext_link_speed : mlx5e_link_speed; +} + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, struct mlx5e_port_eth_proto *eproto) { u32 out[MLX5_ST_SZ_DW(ptys_reg)]; @@ -72,13 +96,17 @@ int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, if (!eproto) return -EINVAL; + if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet)) + return -EOPNOTSUPP; + err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port); if (err) return err; - eproto->cap = MLX5_GET(ptys_reg, out, eth_proto_capability); - eproto->admin = MLX5_GET(ptys_reg, out, eth_proto_admin); - eproto->oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + eproto->cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_capability); + eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin); + eproto->oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); return 0; } @@ -100,7 +128,7 @@ void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, } int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin) + u32 proto_admin, bool ext) { u32 out[MLX5_ST_SZ_DW(ptys_reg)]; u32 in[MLX5_ST_SZ_DW(ptys_reg)]; @@ -118,38 +146,46 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, MLX5_SET(ptys_reg, in, local_port, 1); MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN); - MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); + if (ext) + MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin); + else + MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); return mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_PTYS, 0, 1); } -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) { unsigned long temp = eth_proto_oper; + const u32 *table; u32 speed = 0; + u32 max_size; int i; - i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER); - if (i < MLX5E_LINK_MODES_NUMBER) - speed = mlx5e_link_speed[i]; - + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + i = find_first_bit(&temp, max_size); + if (i < max_size) + speed = table[i]; return speed; } int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { struct mlx5e_port_eth_proto eproto; + bool ext; int err; - err = mlx5_port_query_eth_proto(mdev, 1, &eproto); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) - return err; + goto out; - *speed = mlx5e_port_ptys2speed(eproto.oper); + *speed = mlx5e_port_ptys2speed(mdev, eproto.oper); if (!(*speed)) err = -EINVAL; +out: return err; } @@ -157,31 +193,38 @@ int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { struct mlx5e_port_eth_proto eproto; u32 max_speed = 0; + const u32 *table; + u32 max_size; + bool ext; int err; int i; - err = mlx5_port_query_eth_proto(mdev, 1, &eproto); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) return err; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) if (eproto.cap & MLX5E_PROT_MASK(i)) - max_speed = max(max_speed, mlx5e_link_speed[i]); + max_speed = max(max_speed, table[i]); *speed = max_speed; return 0; } -u32 mlx5e_port_speed2linkmodes(u32 speed) +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed) { u32 link_modes = 0; + const u32 *table; + u32 max_size; int i; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (mlx5e_link_speed[i] == speed) + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) { + if (table[i] == speed) link_modes |= MLX5E_PROT_MASK(i); } - return link_modes; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index 4bdab8be10af..70f536ec51c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -42,16 +42,16 @@ struct mlx5e_port_eth_proto { u32 oper; }; -int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, struct mlx5e_port_eth_proto *eproto); void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin); -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper); + u32 proto_admin, bool ext); +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); -u32 mlx5e_port_speed2linkmodes(u32 speed); +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index c29e141d72fb..8343cf7d292c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -695,13 +695,14 @@ static void get_speed_duplex(struct net_device *netdev, u32 eth_proto_oper, struct ethtool_link_ksettings *link_ksettings) { + struct mlx5e_priv *priv = netdev_priv(netdev); u32 speed = SPEED_UNKNOWN; u8 duplex = DUPLEX_UNKNOWN; if (!netif_carrier_ok(netdev)) goto out; - speed = mlx5e_port_ptys2speed(eth_proto_oper); + speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper); if (!speed) { speed = SPEED_UNKNOWN; goto out; @@ -896,9 +897,9 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) : - mlx5e_port_speed2linkmodes(speed); + mlx5e_port_speed2linkmodes(mdev, speed); - err = mlx5_port_query_eth_proto(mdev, 1, &eproto); + err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto); if (err) { netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); @@ -923,7 +924,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, false); mlx5_toggle_port_link(mdev); out: diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 5be7eefa6d75..814fa194663b 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -92,6 +92,22 @@ enum mlx5e_link_mode { MLX5E_LINK_MODES_NUMBER, }; +enum mlx5e_ext_link_mode { + MLX5E_SGMII_100M = 0, + MLX5E_1000BASE_X_SGMII = 1, + MLX5E_5GBASE_R = 3, + MLX5E_10GBASE_XFI_XAUI_1 = 4, + MLX5E_40GBASE_XLAUI_4_XLPPI_4 = 5, + MLX5E_25GAUI_1_25GBASE_CR_KR = 6, + MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2 = 7, + MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8, + MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9, + MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10, + MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, + MLX5E_400GAUI_8 = 15, + MLX5E_EXT_LINK_MODES_NUMBER, +}; + enum mlx5e_connector_type { MLX5E_PORT_UNKNOWN = 0, MLX5E_PORT_NONE = 1, @@ -106,6 +122,9 @@ enum mlx5e_connector_type { }; #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ + (ext ? MLX5_GET(reg, out, ext_##field) : \ + MLX5_GET(reg, out, field)) int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, From patchwork Wed Feb 13 06:55:46 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Saeed Mahameed X-Patchwork-Id: 1040978 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming-netdev@ozlabs.org Delivered-To: patchwork-incoming-netdev@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=mellanox.com Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 43zr1L2xKsz9s5c for ; Wed, 13 Feb 2019 17:57:10 +1100 (AEDT) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2387724AbfBMG5I (ORCPT ); Wed, 13 Feb 2019 01:57:08 -0500 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:52976 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2387686AbfBMG5G (ORCPT ); Wed, 13 Feb 2019 01:57:06 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from saeedm@mellanox.com) with ESMTPS (AES256-SHA encrypted); 13 Feb 2019 08:57:00 +0200 Received: from sx1.mtl.com ([172.16.5.60]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id x1D6u7j7021070; Wed, 13 Feb 2019 08:56:58 +0200 From: Saeed Mahameed To: Saeed Mahameed , Leon Romanovsky Cc: netdev@vger.kernel.org, linux-rdma@vger.kernel.org, Aya Levin Subject: [PATCH mlx5-next 15/15] IB/mlx5: Add support for 50Gbps per lane link modes Date: Tue, 12 Feb 2019 22:55:46 -0800 Message-Id: <20190213065546.3013-16-saeedm@mellanox.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20190213065546.3013-1-saeedm@mellanox.com> References: <20190213065546.3013-1-saeedm@mellanox.com> MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org From: Aya Levin Driver now supports new link modes: 50Gbps per lane support for 50G/100G/200G. This patch reads the correct field (legacy vs. extended) based on a FW indication bit, and adds a translation function (link modes to IB width and speed) to the new link modes. Signed-off-by: Aya Levin Reviewed-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/main.c | 66 ++++++++++++++++++++++++++++--- 1 file changed, 61 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 3677c00fa3bb..581ae11e2fc9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -331,8 +331,8 @@ void mlx5_ib_put_native_port_mdev(struct mlx5_ib_dev *ibdev, u8 port_num) spin_unlock(&port->mp.mpi_lock); } -static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, - u8 *active_width) +static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width) { switch (eth_proto_oper) { case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII): @@ -389,6 +389,61 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, return 0; } +static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width) +{ + switch (eth_proto_oper) { + case MLX5E_PROT_MASK(MLX5E_SGMII_100M): + case MLX5E_PROT_MASK(MLX5E_1000BASE_X_SGMII): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_SDR; + break; + case MLX5E_PROT_MASK(MLX5E_5GBASE_R): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_DDR; + break; + case MLX5E_PROT_MASK(MLX5E_10GBASE_XFI_XAUI_1): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_QDR; + break; + case MLX5E_PROT_MASK(MLX5E_40GBASE_XLAUI_4_XLPPI_4): + *active_width = IB_WIDTH_4X; + *active_speed = IB_SPEED_QDR; + break; + case MLX5E_PROT_MASK(MLX5E_25GAUI_1_25GBASE_CR_KR): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_EDR; + break; + case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2): + case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_HDR; + break; + case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2): + *active_width = IB_WIDTH_2X; + *active_speed = IB_SPEED_HDR; + break; + case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4): + *active_width = IB_WIDTH_4X; + *active_speed = IB_SPEED_HDR; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width, bool ext) +{ + return ext ? + translate_eth_ext_proto_oper(eth_proto_oper, active_speed, + active_width) : + translate_eth_legacy_proto_oper(eth_proto_oper, active_speed, + active_width); +} + static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, struct ib_port_attr *props) { @@ -401,6 +456,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, u16 qkey_viol_cntr; u32 eth_prot_oper; u8 mdev_port_num; + bool ext; int err; mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num); @@ -421,14 +477,14 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, mdev_port_num); if (err) goto out; - eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, false, - eth_proto_oper); + ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet); + eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); props->active_width = IB_WIDTH_4X; props->active_speed = IB_SPEED_QDR; translate_eth_proto_oper(eth_prot_oper, &props->active_speed, - &props->active_width); + &props->active_width, ext); props->port_cap_flags |= IB_PORT_CM_SUP; props->ip_gids = true;