From 22ef683b48182f4d6125a2fb2725eb8a141514ff Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:44 -0700 Subject: [PATCH 01/15] ice: Rework flex descriptor programming The driver can support two flex descriptor profiles, ICE_RXDID_FLEX_NIC and ICE_RXDID_FLEX_NIC_2. This patch reworks the current flex programming logic to add support for the latter profile. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_common.c | 102 ++++++++++++++---- .../net/ethernet/intel/ice/ice_lan_tx_rx.h | 24 +++-- 2 files changed, 92 insertions(+), 34 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 661beea6af79..53cbfd942d03 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -7,16 +7,16 @@ #define ICE_PF_RESET_WAIT_COUNT 200 -#define ICE_NIC_FLX_ENTRY(hw, mdid, idx) \ - wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(ICE_RXDID_FLEX_NIC), \ +#define ICE_PROG_FLEX_ENTRY(hw, rxdid, mdid, idx) \ + wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(rxdid), \ ((ICE_RX_OPC_MDID << \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \ (((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M)) -#define ICE_NIC_FLX_FLG_ENTRY(hw, flg_0, flg_1, flg_2, flg_3, idx) \ - wr32((hw), GLFLXP_RXDID_FLAGS(ICE_RXDID_FLEX_NIC, idx), \ +#define ICE_PROG_FLG_ENTRY(hw, rxdid, flg_0, flg_1, flg_2, flg_3, idx) \ + wr32((hw), GLFLXP_RXDID_FLAGS(rxdid, idx), \ (((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \ GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \ (((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \ @@ -290,30 +290,85 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, } /** - * ice_init_flex_parser - initialize rx flex parser + * ice_init_flex_flags * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID * - * Function to initialize flex descriptors + * Function to initialize Rx flex flags */ -static void ice_init_flex_parser(struct ice_hw *hw) +static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id) { u8 idx = 0; - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_LOW, 0); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_HIGH, 1); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_LOWER, 2); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_HIGH, 3); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_FRG, ICE_RXFLG_UDP_GRE, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_FIN, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_SYN, ICE_RXFLG_RST, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, - ICE_RXFLG_EVLAN_x8100, ICE_RXFLG_EVLAN_x9100, - idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_VLAN_x8100, ICE_RXFLG_TNL_VLAN, - ICE_RXFLG_TNL_MAC, ICE_RXFLG_TNL0, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + /* Flex-flag fields (0-2) are programmed with FLG64 bits with layout: + * flexiflags0[5:0] - TCP flags, is_packet_fragmented, is_packet_UDP_GRE + * flexiflags1[3:0] - Not used for flag programming + * flexiflags2[7:0] - Tunnel and VLAN types + * 2 invalid fields in last index + */ + switch (prof_id) { + /* Rx flex flags are currently programmed for the NIC profiles only. + * Different flag bit programming configurations can be added per + * profile as needed. + */ + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_FRG, + ICE_RXFLG_UDP_GRE, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_FIN, idx++); + /* flex flag 1 is not used for flexi-flag programming, skipping + * these four FLG64 bits. + */ + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_SYN, ICE_RXFLG_RST, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_EVLAN_x8100, + ICE_RXFLG_EVLAN_x9100, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_VLAN_x8100, + ICE_RXFLG_TNL_VLAN, ICE_RXFLG_TNL_MAC, + ICE_RXFLG_TNL0, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Flag programming for profile ID %d not supported\n", + prof_id); + } +} + +/** + * ice_init_flex_flds + * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID + * + * Function to initialize flex descriptors + */ +static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id) +{ + enum ice_flex_rx_mdid mdid; + + switch (prof_id) { + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_LOW, 0); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_HIGH, 1); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_FLOW_ID_LOWER, 2); + + mdid = (prof_id == ICE_RXDID_FLEX_NIC_2) ? + ICE_RX_MDID_SRC_VSI : ICE_RX_MDID_FLOW_ID_HIGH; + + ICE_PROG_FLEX_ENTRY(hw, prof_id, mdid, 3); + + ice_init_flex_flags(hw, prof_id); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Field init for profile ID %d not supported\n", + prof_id); + } } /** @@ -494,7 +549,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_flex_parser(hw); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 068dbc740b76..94504023d86e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -188,23 +188,25 @@ struct ice_32b_rx_flex_desc_nic { * with a specific metadata (profile 7 reserved for HW) */ enum ice_rxdid { - ICE_RXDID_START = 0, - ICE_RXDID_LEGACY_0 = ICE_RXDID_START, - ICE_RXDID_LEGACY_1, - ICE_RXDID_FLX_START, - ICE_RXDID_FLEX_NIC = ICE_RXDID_FLX_START, - ICE_RXDID_FLX_LAST = 63, - ICE_RXDID_LAST = ICE_RXDID_FLX_LAST + ICE_RXDID_LEGACY_0 = 0, + ICE_RXDID_LEGACY_1 = 1, + ICE_RXDID_FLEX_NIC = 2, + ICE_RXDID_FLEX_NIC_2 = 6, + ICE_RXDID_HW = 7, + ICE_RXDID_LAST = 63, }; /* Receive Flex Descriptor Rx opcode values */ #define ICE_RX_OPC_MDID 0x01 /* Receive Descriptor MDID values */ -#define ICE_RX_MDID_FLOW_ID_LOWER 5 -#define ICE_RX_MDID_FLOW_ID_HIGH 6 -#define ICE_RX_MDID_HASH_LOW 56 -#define ICE_RX_MDID_HASH_HIGH 57 +enum ice_flex_rx_mdid { + ICE_RX_MDID_FLOW_ID_LOWER = 5, + ICE_RX_MDID_FLOW_ID_HIGH, + ICE_RX_MDID_SRC_VSI = 19, + ICE_RX_MDID_HASH_LOW = 56, + ICE_RX_MDID_HASH_HIGH, +}; /* Rx Flag64 packet flag bits */ enum ice_rx_flg64_bits { From b36c598c999c628130f6743dc2362585360de65c Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:45 -0700 Subject: [PATCH 02/15] ice: Updates to Tx scheduler code 1) The maximum device nodes is a global value and shared by the whole device. Add element AQ command would fail if there is no space to add new nodes so the check for max nodes isn't required. So remove ice_sched_get_num_nodes_per_layer and ice_sched_val_max_nodes. 2) In ice_sched_add_elems, set default node's CIR/EIR bandwidth weight. 3) Fix default scheduler topology buffer size as the firmware expects a 4KB buffer at all times, and will error out if one of any other size is provided. 4) In the latest spec, max children per node per layer is replaced by max sibling group size. Now it provides the max children of the below layer node, not the current layer node. 5) Fix some newline/whitespace issues for consistency. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_adminq_cmd.h | 5 +- drivers/net/ethernet/intel/ice/ice_common.c | 7 + drivers/net/ethernet/intel/ice/ice_sched.c | 161 ++++++------------ drivers/net/ethernet/intel/ice/ice_type.h | 2 + 4 files changed, 61 insertions(+), 114 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index a0614f472658..9a33fb95c0ea 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -771,9 +771,8 @@ struct ice_aqc_layer_props { u8 chunk_size; __le16 max_device_nodes; __le16 max_pf_nodes; - u8 rsvd0[2]; - __le16 max_shared_rate_lmtr; - __le16 max_children; + u8 rsvd0[4]; + __le16 max_sibl_grp_sz; __le16 max_cir_rl_profiles; __le16 max_eir_rl_profiles; __le16 max_srl_profiles; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 53cbfd942d03..b315655eab27 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -527,6 +527,13 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; + /* need a valid SW entry point to build a Tx tree */ + if (!hw->sw_entry_point_layer) { + ice_debug(hw, ICE_DBG_SCHED, "invalid sw entry point\n"); + status = ICE_ERR_CFG; + goto err_unroll_sched; + } + status = ice_init_fltr_mgmt_struct(hw); if (status) goto err_unroll_sched; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index eeae199469b6..9b7b50554952 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -17,7 +17,6 @@ ice_sched_add_root_node(struct ice_port_info *pi, { struct ice_sched_node *root; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -28,8 +27,8 @@ ice_sched_add_root_node(struct ice_port_info *pi, if (!root) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[0].max_children); - root->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + /* coverity[suspicious_sizeof] */ + root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], sizeof(*root), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); @@ -100,7 +99,6 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_sched_node *parent; struct ice_sched_node *node; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -120,9 +118,10 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[layer].max_children); - if (max_children) { - node->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + if (hw->max_children[layer]) { + /* coverity[suspicious_sizeof] */ + node->children = devm_kcalloc(ice_hw_to_dev(hw), + hw->max_children[layer], sizeof(*node), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); @@ -192,14 +191,17 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; + buf->hdr.parent_teid = parent->info.node_teid; buf->hdr.num_elems = cpu_to_le16(num_nodes); for (i = 0; i < num_nodes; i++) buf->teid[i] = cpu_to_le32(node_teids[i]); + status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size, &num_groups_removed, NULL); if (status || num_groups_removed != 1) ice_debug(hw, ICE_DBG_SCHED, "remove elements failed\n"); + devm_kfree(ice_hw_to_dev(hw), buf); return status; } @@ -592,13 +594,16 @@ static void ice_sched_clear_port(struct ice_port_info *pi) */ void ice_sched_cleanup_all(struct ice_hw *hw) { - if (!hw || !hw->port_info) + if (!hw) return; - if (hw->layer_info) + if (hw->layer_info) { devm_kfree(ice_hw_to_dev(hw), hw->layer_info); + hw->layer_info = NULL; + } - ice_sched_clear_port(hw->port_info); + if (hw->port_info) + ice_sched_clear_port(hw->port_info); hw->num_tx_sched_layers = 0; hw->num_tx_sched_phys_layers = 0; @@ -671,9 +676,13 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, ICE_AQC_ELEM_VALID_EIR; buf->generic[i].data.generic = 0; buf->generic[i].data.cir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); buf->generic[i].data.eir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); } status = ice_aq_add_sched_elems(hw, 1, buf, buf_size, @@ -697,7 +706,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, teid = le32_to_cpu(buf->generic[i].node_teid); new_node = ice_sched_find_node_by_teid(parent, teid); - if (!new_node) { ice_debug(hw, ICE_DBG_SCHED, "Node is missing for teid =%d\n", teid); @@ -710,7 +718,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, /* add it to previous node sibling pointer */ /* Note: siblings are not linked across branches */ prev = ice_sched_get_first_node(hw, tc_node, layer); - if (prev && prev != new_node) { while (prev->sibling) prev = prev->sibling; @@ -760,8 +767,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, return ICE_ERR_PARAM; /* max children per node per layer */ - max_child_nodes = - le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children); + max_child_nodes = hw->max_children[parent->tx_sched_layer]; /* current number of children + required nodes exceed max children ? */ if ((parent->num_children + num_nodes) > max_child_nodes) { @@ -850,78 +856,6 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) return hw->sw_entry_point_layer; } -/** - * ice_sched_get_num_nodes_per_layer - Get the total number of nodes per layer - * @pi: pointer to the port info struct - * @layer: layer number - * - * This function calculates the number of nodes present in the scheduler tree - * including all the branches for a given layer - */ -static u16 -ice_sched_get_num_nodes_per_layer(struct ice_port_info *pi, u8 layer) -{ - struct ice_hw *hw; - u16 num_nodes = 0; - u8 i; - - if (!pi) - return num_nodes; - - hw = pi->hw; - - /* Calculate the number of nodes for all TCs */ - for (i = 0; i < pi->root->num_children; i++) { - struct ice_sched_node *tc_node, *node; - - tc_node = pi->root->children[i]; - - /* Get the first node */ - node = ice_sched_get_first_node(hw, tc_node, layer); - if (!node) - continue; - - /* count the siblings */ - while (node) { - num_nodes++; - node = node->sibling; - } - } - - return num_nodes; -} - -/** - * ice_sched_val_max_nodes - check max number of nodes reached or not - * @pi: port information structure - * @new_num_nodes_per_layer: pointer to the new number of nodes array - * - * This function checks whether the scheduler tree layers have enough space to - * add new nodes - */ -static enum ice_status -ice_sched_validate_for_max_nodes(struct ice_port_info *pi, - u16 *new_num_nodes_per_layer) -{ - struct ice_hw *hw = pi->hw; - u8 i, qg_layer; - u16 num_nodes; - - qg_layer = ice_sched_get_qgrp_layer(hw); - - /* walk through all the layers from SW entry point to qgroup layer */ - for (i = hw->sw_entry_point_layer; i <= qg_layer; i++) { - num_nodes = ice_sched_get_num_nodes_per_layer(pi, i); - if (num_nodes + new_num_nodes_per_layer[i] > - le16_to_cpu(hw->layer_info[i].max_pf_nodes)) { - ice_debug(hw, ICE_DBG_SCHED, - "max nodes reached for layer = %d\n", i); - return ICE_ERR_CFG; - } - } - return 0; -} - /** * ice_rm_dflt_leaf_node - remove the default leaf node in the tree * @pi: port information structure @@ -1003,14 +937,12 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) hw = pi->hw; /* Query the Default Topology from FW */ - buf = devm_kcalloc(ice_hw_to_dev(hw), ICE_TXSCHED_MAX_BRANCHES, - sizeof(*buf), GFP_KERNEL); + buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; /* Query default scheduling tree topology */ - status = ice_aq_get_dflt_topo(hw, pi->lport, buf, - sizeof(*buf) * ICE_TXSCHED_MAX_BRANCHES, + status = ice_aq_get_dflt_topo(hw, pi->lport, buf, ICE_AQ_MAX_BUF_LEN, &num_branches, NULL); if (status) goto err_init_port; @@ -1097,6 +1029,8 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) { struct ice_aqc_query_txsched_res_resp *buf; enum ice_status status = 0; + __le16 max_sibl; + u8 i; if (hw->layer_info) return status; @@ -1115,7 +1049,20 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) hw->flattened_layers = buf->sched_props.flattening_bitmap; hw->max_cgds = buf->sched_props.max_pf_cgds; - hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, + /* max sibling group size of current layer refers to the max children + * of the below layer node. + * layer 1 node max children will be layer 2 max sibling group size + * layer 2 node max children will be layer 3 max sibling group size + * and so on. This array will be populated from root (index 0) to + * qgroup layer 7. Leaf node has no children. + */ + for (i = 0; i < hw->num_tx_sched_layers; i++) { + max_sibl = buf->layer_props[i].max_sibl_grp_sz; + hw->max_children[i] = le16_to_cpu(max_sibl); + } + + hw->layer_info = (struct ice_aqc_layer_props *) + devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, (hw->num_tx_sched_layers * sizeof(*hw->layer_info)), GFP_KERNEL); @@ -1202,7 +1149,7 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); - max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children); + max_children = pi->hw->max_children[qgrp_layer]; list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id); if (!list_elem) @@ -1278,10 +1225,8 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) /* calculate num nodes from q group to VSI layer */ for (i = qgl; i > vsil; i--) { - u16 max_children = le16_to_cpu(hw->layer_info[i].max_children); - /* round to the next integer if there is a remainder */ - num = DIV_ROUND_UP(num, max_children); + num = DIV_ROUND_UP(num, hw->max_children[i]); /* need at least one node */ num_nodes[i] = num ? num : 1; @@ -1311,16 +1256,13 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u16 num_added = 0; u8 i, qgl, vsil; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id); for (i = vsil + 1; i <= qgl; i++) { if (!parent) return ICE_ERR_CFG; + status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, @@ -1398,8 +1340,8 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *node; - u16 max_child; - u8 i, vsil; + u8 vsil; + int i; vsil = ice_sched_get_vsi_layer(hw); for (i = vsil; i >= hw->sw_entry_point_layer; i--) @@ -1412,12 +1354,10 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /* If intermediate nodes are reached max children * then add a new one. */ - node = ice_sched_get_first_node(hw, tc_node, i); - max_child = le16_to_cpu(hw->layer_info[i].max_children); - + node = ice_sched_get_first_node(hw, tc_node, (u8)i); /* scan all the siblings */ while (node) { - if (node->num_children < max_child) + if (node->num_children < hw->max_children[i]) break; node = node->sibling; } @@ -1451,10 +1391,6 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, if (!pi) return ICE_ERR_PARAM; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - vsil = ice_sched_get_vsi_layer(pi->hw); for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) { status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, @@ -1479,6 +1415,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, if (i == vsil) parent->vsi_id = vsi_id; } + return 0; } @@ -1633,9 +1570,11 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc); if (status) return status; + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); if (!vsi_node) return ICE_ERR_CFG; + vsi->vsi_node[tc] = vsi_node; vsi_node->in_use = true; } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 97c366e0ca59..df953f5f219b 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -204,6 +204,7 @@ enum ice_agg_type { }; #define ICE_SCHED_DFLT_RL_PROF_ID 0 +#define ICE_SCHED_DFLT_BW_WT 1 /* vsi type list entry to locate corresponding vsi/ag nodes */ struct ice_sched_vsi_info { @@ -286,6 +287,7 @@ struct ice_hw { u8 flattened_layers; u8 max_cgds; u8 sw_entry_point_layer; + u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; u8 evb_veb; /* true for VEB, false for VEPA */ struct ice_bus_info bus; From ff2b13213a6a0baca105bc3bc724225f0adde1f8 Mon Sep 17 00:00:00 2001 From: Dan Nowlin Date: Thu, 9 Aug 2018 06:29:46 -0700 Subject: [PATCH 03/15] ice: Update request resource command to latest specification Align Request Resource Ownership AQ command (0x0008) to the latest specification. This includes: - Correcting the resource IDs for the Global Cfg and Change locks. - new enum ICE_CHANGE_LOCK_RES_ID - new enum ICE_GLOBAL_CFG_LOCK_RES_ID - Altering the flow for Global Config Lock to allow only the first PF to download the package. Signed-off-by: Dan Nowlin Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_common.c | 75 ++++++++++++++++----- drivers/net/ethernet/intel/ice/ice_common.h | 2 +- drivers/net/ethernet/intel/ice/ice_nvm.c | 2 +- drivers/net/ethernet/intel/ice/ice_type.h | 9 ++- 4 files changed, 67 insertions(+), 21 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index b315655eab27..2a1e13576ce2 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -967,7 +967,22 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) * @timeout: the maximum time in ms that the driver may hold the resource * @cd: pointer to command details structure or NULL * - * requests common resource using the admin queue commands (0x0008) + * Requests common resource using the admin queue commands (0x0008). + * When attempting to acquire the Global Config Lock, the driver can + * learn of three states: + * 1) ICE_SUCCESS - acquired lock, and can perform download package + * 2) ICE_ERR_AQ_ERROR - did not get lock, driver should fail to load + * 3) ICE_ERR_AQ_NO_WORK - did not get lock, but another driver has + * successfully downloaded the package; the driver does + * not have to download the package and can continue + * loading + * + * Note that if the caller is in an acquire lock, perform action, release lock + * phase of operation, it is possible that the FW may detect a timeout and issue + * a CORER. In this case, the driver will receive a CORER interrupt and will + * have to determine its cause. The calling thread that is handling this flow + * will likely get an error propagated back to it indicating the Download + * Package, Update Package or the Release Resource AQ commands timed out. */ static enum ice_status ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, @@ -985,13 +1000,43 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, cmd_resp->res_id = cpu_to_le16(res); cmd_resp->access_type = cpu_to_le16(access); cmd_resp->res_number = cpu_to_le32(sdp_number); + cmd_resp->timeout = cpu_to_le32(*timeout); + *timeout = 0; status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + /* The completion specifies the maximum time in ms that the driver * may hold the resource in the Timeout field. - * If the resource is held by someone else, the command completes with - * busy return value and the timeout field indicates the maximum time - * the current owner of the resource has to free it. + */ + + /* Global config lock response utilizes an additional status field. + * + * If the Global config lock resource is held by some other driver, the + * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field + * and the timeout field indicates the maximum time the current owner + * of the resource has to free it. + */ + if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) { + if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return 0; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_IN_PROG) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return ICE_ERR_AQ_ERROR; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_DONE) { + return ICE_ERR_AQ_NO_WORK; + } + + /* invalid FW response, force a timeout immediately */ + *timeout = 0; + return ICE_ERR_AQ_ERROR; + } + + /* If the resource is held by some other driver, the command completes + * with a busy return value and the timeout field indicates the maximum + * time the current owner of the resource has to free it. */ if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY) *timeout = le32_to_cpu(cmd_resp->timeout); @@ -1030,30 +1075,28 @@ ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number, * @hw: pointer to the HW structure * @res: resource id * @access: access type (read or write) + * @timeout: timeout in milliseconds * * This function will attempt to acquire the ownership of a resource. */ enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access) + enum ice_aq_res_access_type access, u32 timeout) { #define ICE_RES_POLLING_DELAY_MS 10 u32 delay = ICE_RES_POLLING_DELAY_MS; + u32 time_left = timeout; enum ice_status status; - u32 time_left = 0; - u32 timeout; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - /* An admin queue return code of ICE_AQ_RC_EEXIST means that another - * driver has previously acquired the resource and performed any - * necessary updates; in this case the caller does not obtain the - * resource and has no further work to do. + /* A return code of ICE_ERR_AQ_NO_WORK means that another driver has + * previously acquired the resource and performed any necessary updates; + * in this case the caller does not obtain the resource and has no + * further work to do. */ - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { - status = ICE_ERR_AQ_NO_WORK; + if (status == ICE_ERR_AQ_NO_WORK) goto ice_acquire_res_exit; - } if (status) ice_debug(hw, ICE_DBG_RES, @@ -1066,11 +1109,9 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, timeout = (timeout > delay) ? timeout - delay : 0; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { + if (status == ICE_ERR_AQ_NO_WORK) /* lock free, but no work to do */ - status = ICE_ERR_AQ_NO_WORK; break; - } if (!status) /* lock acquired */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 9a5519130af1..6455b6952ec8 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -23,7 +23,7 @@ enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up); enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access); + enum ice_aq_res_access_type access, u32 timeout); void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res); enum ice_status ice_init_nvm(struct ice_hw *hw); enum ice_status diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 295a8cd87fc1..3274c543283c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -137,7 +137,7 @@ ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access) if (hw->nvm.blank_nvm_mode) return 0; - return ice_acquire_res(hw, ICE_NVM_RES_ID, access); + return ice_acquire_res(hw, ICE_NVM_RES_ID, access, ICE_NVM_TIMEOUT); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index df953f5f219b..e1a0d0e5d074 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -34,10 +34,15 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) enum ice_aq_res_ids { ICE_NVM_RES_ID = 1, ICE_SPD_RES_ID, - ICE_GLOBAL_CFG_LOCK_RES_ID, - ICE_CHANGE_LOCK_RES_ID + ICE_CHANGE_LOCK_RES_ID, + ICE_GLOBAL_CFG_LOCK_RES_ID }; +/* FW update timeout definitions are in milliseconds */ +#define ICE_NVM_TIMEOUT 180000 +#define ICE_CHANGE_LOCK_TIMEOUT 1000 +#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 3000 + enum ice_aq_res_access_type { ICE_RES_READ = 1, ICE_RES_WRITE From fd2a981777d911b2e94cdec50779c85c58a0dec9 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:47 -0700 Subject: [PATCH 04/15] ice: Prevent control queue operations during reset Once reset is issued, the driver loses all control queue interfaces. Exercising control queue operations during reset is incorrect and may result in long timeouts. This patch introduces a new field 'reset_ongoing' in the hw structure. This is set to 1 by the core driver when it receives a reset interrupt. ice_sq_send_cmd checks reset_ongoing before actually issuing the control queue operation. If a reset is in progress, it returns a soft error code (ICE_ERR_RESET_PENDING) to the caller. The caller may or may not have to take any action based on this return. Once the driver knows that the reset is done, it has to set reset_ongoing back to 0. This will allow control queue operations to be posted to the hardware again. This "bail out" logic was specifically added to ice_sq_send_cmd (which is pretty low level function) so that we have one solution in one place that applies to all types of control queues. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_controlq.c | 3 ++ drivers/net/ethernet/intel/ice/ice_main.c | 34 ++++++++++++++++--- drivers/net/ethernet/intel/ice/ice_status.h | 1 + drivers/net/ethernet/intel/ice/ice_type.h | 1 + 4 files changed, 34 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 62be72fdc8f3..1fe026a65d75 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -806,6 +806,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, u16 retval = 0; u32 val = 0; + /* if reset is in progress return a soft error */ + if (hw->reset_ongoing) + return ICE_ERR_RESET_ONGOING; mutex_lock(&cq->sq_lock); cq->sq_last_status = ICE_AQ_RC_OK; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f1e80eed2fd6..014a2f3ea76c 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -535,10 +535,13 @@ static void ice_reset_subtask(struct ice_pf *pf) ice_prepare_for_reset(pf); /* make sure we are ready to rebuild */ - if (ice_check_reset(&pf->hw)) + if (ice_check_reset(&pf->hw)) { set_bit(__ICE_RESET_FAILED, pf->state); - else + } else { + /* done with reset. start rebuild */ + pf->hw.reset_ongoing = false; ice_rebuild(pf); + } clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); goto unlock; } @@ -1754,7 +1757,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) * We also make note of which reset happened so that peer * devices/drivers can be informed. */ - if (!test_bit(__ICE_RESET_RECOVERY_PENDING, pf->state)) { + if (!test_and_set_bit(__ICE_RESET_RECOVERY_PENDING, + pf->state)) { if (reset == ICE_RESET_CORER) set_bit(__ICE_CORER_RECV, pf->state); else if (reset == ICE_RESET_GLOBR) @@ -1762,7 +1766,20 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) else set_bit(__ICE_EMPR_RECV, pf->state); - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* There are couple of different bits at play here. + * hw->reset_ongoing indicates whether the hardware is + * in reset. This is set to true when a reset interrupt + * is received and set back to false after the driver + * has determined that the hardware is out of reset. + * + * __ICE_RESET_RECOVERY_PENDING in pf->state indicates + * that a post reset rebuild is required before the + * driver is operational again. This is set above. + * + * As this is the start of the reset/rebuild cycle, set + * both to indicate that. + */ + hw->reset_ongoing = true; } } @@ -4185,7 +4202,14 @@ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) } status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, NULL); - if (status) { + /* if the disable queue command was exercised during an active reset + * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as + * the reset operation disables queues at the hardware level anyway. + */ + if (status == ICE_ERR_RESET_ONGOING) { + dev_dbg(&pf->pdev->dev, + "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status) { dev_err(&pf->pdev->dev, "Failed to disable LAN Tx queues, error: %d\n", status); diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h index 9a95c4ffd7d7..d2dae913d81e 100644 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ b/drivers/net/ethernet/intel/ice/ice_status.h @@ -20,6 +20,7 @@ enum ice_status { ICE_ERR_ALREADY_EXISTS = -14, ICE_ERR_DOES_NOT_EXIST = -15, ICE_ERR_MAX_LIMIT = -17, + ICE_ERR_RESET_ONGOING = -18, ICE_ERR_BUF_TOO_SHORT = -52, ICE_ERR_NVM_BLANK_MODE = -53, ICE_ERR_AQ_ERROR = -100, diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index e1a0d0e5d074..adfe131bd3f3 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -295,6 +295,7 @@ struct ice_hw { u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; u8 evb_veb; /* true for VEB, false for VEPA */ + u8 reset_ongoing; /* true if hw is in reset, false otherwise */ struct ice_bus_info bus; struct ice_nvm_info nvm; struct ice_hw_dev_caps dev_caps; /* device capabilities */ From 74118f7af092a4edc194573a8749f3843d280d3f Mon Sep 17 00:00:00 2001 From: Zhenning Xiao Date: Thu, 9 Aug 2018 06:29:48 -0700 Subject: [PATCH 05/15] ice: Code optimization for ice_fill_sw_rule() Use the buffer in the s_rule structure directly instead of using a local array eth_hdr[DUMMY_ETH_HDR_LEN] Signed-off-by: Zhenning Xiao Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_switch.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 6b7ec2ae5ad6..d8b18cabc3a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -464,8 +464,9 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc) { u16 vlan_id = ICE_MAX_VLAN_ID + 1; - u8 eth_hdr[DUMMY_ETH_HDR_LEN]; void *daddr = NULL; + u16 eth_hdr_sz; + u8 *eth_hdr; u32 act = 0; __be16 *off; @@ -477,8 +478,11 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, return; } + eth_hdr_sz = sizeof(dummy_eth_header); + eth_hdr = s_rule->pdata.lkup_tx_rx.hdr; + /* initialize the ether header with a dummy header */ - memcpy(eth_hdr, dummy_eth_header, sizeof(dummy_eth_header)); + memcpy(eth_hdr, dummy_eth_header, eth_hdr_sz); ice_fill_sw_info(hw, f_info); switch (f_info->fltr_act) { @@ -536,7 +540,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, daddr = f_info->l_data.ethertype_mac.mac_addr; /* fall-through */ case ICE_SW_LKUP_ETHERTYPE: - off = (__be16 *)ð_hdr[ICE_ETH_ETHTYPE_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); *off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype); break; case ICE_SW_LKUP_MAC_VLAN: @@ -563,18 +567,16 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); if (daddr) - ether_addr_copy(ð_hdr[ICE_ETH_DA_OFFSET], daddr); + ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr); if (!(vlan_id > ICE_MAX_VLAN_ID)) { - off = (__be16 *)ð_hdr[ICE_ETH_VLAN_TCI_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET); *off = cpu_to_be16(vlan_id); } /* Create the switch rule with the final dummy Ethernet header */ if (opc != ice_aqc_opc_update_sw_rules) - s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(sizeof(eth_hdr)); - - memcpy(s_rule->pdata.lkup_tx_rx.hdr, eth_hdr, sizeof(eth_hdr)); + s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(eth_hdr_sz); } /** From 80d144c9ac82fd07436c02c830b2af03c471db8a Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:49 -0700 Subject: [PATCH 06/15] ice: Refactor switch rule management structures and functions This patch is an adaptation of the work originally done by Grishma Kotecha that in summary refactors the switch filtering logic in the driver. More specifically, - Update the recipe structure to also store list of rules - Update the existing code for recipes like MAC, VLAN, ethtype etc to use list head that is attached to switch recipe structure - Add a common function to search for a rule entry and add a new rule entry. Update the code to use this new function. - Refactor the rem_handle_vsi_list function to simplify the logic CC: Shannon Nelson Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_adminq_cmd.h | 2 + drivers/net/ethernet/intel/ice/ice_common.c | 34 +- drivers/net/ethernet/intel/ice/ice_switch.c | 963 ++++++++---------- drivers/net/ethernet/intel/ice/ice_switch.h | 35 +- drivers/net/ethernet/intel/ice/ice_type.h | 13 +- 5 files changed, 497 insertions(+), 550 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 9a33fb95c0ea..87b304db9cad 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -443,6 +443,8 @@ struct ice_aqc_vsi_props { u8 reserved[24]; }; +#define ICE_MAX_NUM_RECIPES 64 + /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ struct ice_aqc_sw_rules { diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2a1e13576ce2..4c6b1038dc5f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -388,20 +388,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) INIT_LIST_HEAD(&sw->vsi_list_map_head); - mutex_init(&sw->mac_list_lock); - INIT_LIST_HEAD(&sw->mac_list_head); - - mutex_init(&sw->vlan_list_lock); - INIT_LIST_HEAD(&sw->vlan_list_head); - - mutex_init(&sw->eth_m_list_lock); - INIT_LIST_HEAD(&sw->eth_m_list_head); - - mutex_init(&sw->promisc_list_lock); - INIT_LIST_HEAD(&sw->promisc_list_head); - - mutex_init(&sw->mac_vlan_list_lock); - INIT_LIST_HEAD(&sw->mac_vlan_list_head); + ice_init_def_sw_recp(hw); return 0; } @@ -415,19 +402,28 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) struct ice_switch_info *sw = hw->switch_info; struct ice_vsi_list_map_info *v_pos_map; struct ice_vsi_list_map_info *v_tmp_map; + struct ice_sw_recipe *recps; + u8 i; list_for_each_entry_safe(v_pos_map, v_tmp_map, &sw->vsi_list_map_head, list_entry) { list_del(&v_pos_map->list_entry); devm_kfree(ice_hw_to_dev(hw), v_pos_map); } + recps = hw->switch_info->recp_list; + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; - mutex_destroy(&sw->mac_list_lock); - mutex_destroy(&sw->vlan_list_lock); - mutex_destroy(&sw->eth_m_list_lock); - mutex_destroy(&sw->promisc_list_lock); - mutex_destroy(&sw->mac_vlan_list_lock); + recps[i].root_rid = i; + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } + devm_kfree(ice_hw_to_dev(hw), sw->recp_list); devm_kfree(ice_hw_to_dev(hw), sw); } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index d8b18cabc3a8..2693bebef977 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -85,6 +85,35 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); } +/** + * ice_init_def_sw_recp - initialize the recipe book keeping tables + * @hw: pointer to the hw struct + * + * Allocate memory for the entire recipe table and initialize the structures/ + * entries corresponding to basic recipes. + */ +enum ice_status +ice_init_def_sw_recp(struct ice_hw *hw) +{ + struct ice_sw_recipe *recps; + u8 i; + + recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES, + sizeof(struct ice_sw_recipe), GFP_KERNEL); + if (!recps) + return ICE_ERR_NO_MEMORY; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + recps[i].root_rid = i; + INIT_LIST_HEAD(&recps[i].filt_rules); + mutex_init(&recps[i].filt_rule_lock); + } + + hw->switch_info->recp_list = recps; + + return 0; +} + /** * ice_aq_get_sw_cfg - get switch configuration * @hw: pointer to the hardware structure @@ -818,10 +847,10 @@ static enum ice_status ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { - struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *fm_entry; struct ice_aqc_sw_rules_elem *s_rule; enum ice_sw_lkup_type l_type; + struct ice_sw_recipe *recp; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -862,31 +891,9 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, * calls remove filter AQ command */ l_type = fm_entry->fltr_info.lkup_type; - if (l_type == ICE_SW_LKUP_MAC) { - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); - } else if (l_type == ICE_SW_LKUP_VLAN) { - mutex_lock(&sw->vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->vlan_list_head); - mutex_unlock(&sw->vlan_list_lock); - } else if (l_type == ICE_SW_LKUP_ETHERTYPE || - l_type == ICE_SW_LKUP_ETHERTYPE_MAC) { - mutex_lock(&sw->eth_m_list_lock); - list_add(&fm_entry->list_entry, &sw->eth_m_list_head); - mutex_unlock(&sw->eth_m_list_lock); - } else if (l_type == ICE_SW_LKUP_PROMISC || - l_type == ICE_SW_LKUP_PROMISC_VLAN) { - mutex_lock(&sw->promisc_list_lock); - list_add(&fm_entry->list_entry, &sw->promisc_list_head); - mutex_unlock(&sw->promisc_list_lock); - } else if (fm_entry->fltr_info.lkup_type == ICE_SW_LKUP_MAC_VLAN) { - mutex_lock(&sw->mac_vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_vlan_list_head); - mutex_unlock(&sw->mac_vlan_list_lock); - } else { - status = ICE_ERR_NOT_IMPL; - } + recp = &hw->switch_info->recp_list[l_type]; + list_add(&fm_entry->list_entry, &recp->filt_rules); + ice_create_pkt_fwd_rule_exit: devm_kfree(ice_hw_to_dev(hw), s_rule); return status; @@ -895,19 +902,15 @@ ice_create_pkt_fwd_rule_exit: /** * ice_update_pkt_fwd_rule * @hw: pointer to the hardware structure - * @rule_id: rule of previously created switch rule to update - * @vsi_list_id: VSI list id to be updated with - * @f_info: ice_fltr_info to pull other information for switch rule + * @f_info: filter information for switch rule * * Call AQ command to update a previously created switch rule with a * VSI list id */ static enum ice_status -ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, - struct ice_fltr_info f_info) +ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) { struct ice_aqc_sw_rules_elem *s_rule; - struct ice_fltr_info tmp_fltr; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -915,14 +918,9 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, if (!s_rule) return ICE_ERR_NO_MEMORY; - tmp_fltr = f_info; - tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; - tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules); - ice_fill_sw_rule(hw, &tmp_fltr, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(rule_id); + s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(f_info->fltr_rule_id); /* Update switch rule with new rule set to forward VSI list */ status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, @@ -933,7 +931,7 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, } /** - * ice_handle_vsi_list_mgmt + * ice_add_update_vsi_list * @hw: pointer to the hardware structure * @m_entry: pointer to current filter management list entry * @cur_fltr: filter information from the book keeping entry @@ -954,10 +952,10 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, * using the update switch rule command */ static enum ice_status -ice_handle_vsi_list_mgmt(struct ice_hw *hw, - struct ice_fltr_mgmt_list_entry *m_entry, - struct ice_fltr_info *cur_fltr, - struct ice_fltr_info *new_fltr) +ice_add_update_vsi_list(struct ice_hw *hw, + struct ice_fltr_mgmt_list_entry *m_entry, + struct ice_fltr_info *cur_fltr, + struct ice_fltr_info *new_fltr) { enum ice_status status = 0; u16 vsi_list_id = 0; @@ -977,8 +975,8 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, * a part of a VSI list. So, create a VSI list with the old and * new VSIs. */ + struct ice_fltr_info tmp_fltr; u16 vsi_id_arr[2]; - u16 fltr_rule; /* A rule already exists with the new VSI being added */ if (cur_fltr->fwd_id.vsi_id == new_fltr->fwd_id.vsi_id) @@ -992,12 +990,14 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, if (status) return status; - fltr_rule = cur_fltr->fltr_rule_id; + tmp_fltr = *new_fltr; + tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; /* Update the previous switch rule of "MAC forward to VSI" to * "MAC fwd to VSI list" */ - status = ice_update_pkt_fwd_rule(hw, fltr_rule, vsi_list_id, - *new_fltr); + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); if (status) return status; @@ -1042,54 +1042,245 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, } /** - * ice_find_mac_entry + * ice_find_rule_entry - Search a rule entry * @hw: pointer to the hardware structure - * @mac_addr: MAC address to search for + * @recp_id: lookup type for which the specified rule needs to be searched + * @f_info: rule information * - * Helper function to search for a MAC entry using a given MAC address - * Returns pointer to the entry if found. + * Helper function to search for a given rule entry + * Returns pointer to entry storing the rule if found */ static struct ice_fltr_mgmt_list_entry * -ice_find_mac_entry(struct ice_hw *hw, u8 *mac_addr) +ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) { - struct ice_fltr_mgmt_list_entry *m_list_itr, *mac_ret = NULL; + struct ice_fltr_mgmt_list_entry *list_itr, *ret = NULL; struct ice_switch_info *sw = hw->switch_info; + struct list_head *list_head; - mutex_lock(&sw->mac_list_lock); - list_for_each_entry(m_list_itr, &sw->mac_list_head, list_entry) { - u8 *buf = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; - - if (ether_addr_equal(buf, mac_addr)) { - mac_ret = m_list_itr; + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data, + sizeof(f_info->l_data)) && + f_info->flag == list_itr->fltr_info.flag) { + ret = list_itr; break; } } - mutex_unlock(&sw->mac_list_lock); - return mac_ret; + return ret; } /** - * ice_add_shared_mac - Add one MAC shared filter rule + * ice_add_rule_internal - add rule for a given lookup type * @hw: pointer to the hardware structure + * @recp_id: lookup type (recipe id) for which rule has to be added * @f_entry: structure containing MAC forwarding information * - * Adds or updates the book keeping list for the MAC addresses + * Adds or updates the rule lists for a given recipe */ static enum ice_status -ice_add_shared_mac(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) +ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) { + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *m_entry; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; + + mutex_lock(rule_lock); new_fltr = &f_entry->fltr_info; + if (new_fltr->flag & ICE_FLTR_RX) + new_fltr->src = hw->port_info->lport; + else if (new_fltr->flag & ICE_FLTR_TX) + new_fltr->src = f_entry->fltr_info.fwd_id.vsi_id; - m_entry = ice_find_mac_entry(hw, &new_fltr->l_data.mac.mac_addr[0]); - if (!m_entry) + m_entry = ice_find_rule_entry(hw, recp_id, new_fltr); + if (!m_entry) { + mutex_unlock(rule_lock); return ice_create_pkt_fwd_rule(hw, f_entry); + } cur_fltr = &m_entry->fltr_info; + status = ice_add_update_vsi_list(hw, m_entry, cur_fltr, new_fltr); + mutex_unlock(rule_lock); - return ice_handle_vsi_list_mgmt(hw, m_entry, cur_fltr, new_fltr); + return status; +} + +/** + * ice_remove_vsi_list_rule + * @hw: pointer to the hardware structure + * @vsi_list_id: VSI list id generated as part of allocate resource + * @lkup_type: switch rule filter lookup type + * + * The VSI list should be emptied before this function is called to remove the + * VSI list. + */ +static enum ice_status +ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, + enum ice_sw_lkup_type lkup_type) +{ + struct ice_aqc_sw_rules_elem *s_rule; + enum ice_status status; + u16 s_rule_size; + + s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); + s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); + s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); + + /* Free the vsi_list resource that we allocated. It is assumed that the + * list is empty at this point. + */ + status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, + ice_aqc_opc_free_res); + + devm_kfree(ice_hw_to_dev(hw), s_rule); + return status; +} + +/** + * ice_rem_update_vsi_list + * @hw: pointer to the hardware structure + * @vsi_id: ID of the VSI to remove + * @fm_list: filter management entry for which the VSI list management needs to + * be done + */ +static enum ice_status +ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_id, + struct ice_fltr_mgmt_list_entry *fm_list) +{ + enum ice_sw_lkup_type lkup_type; + enum ice_status status = 0; + u16 vsi_list_id; + + if (fm_list->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST || + fm_list->vsi_count == 0) + return ICE_ERR_PARAM; + + /* A rule with the VSI being removed does not exist */ + if (!test_bit(vsi_id, fm_list->vsi_list_info->vsi_map)) + return ICE_ERR_DOES_NOT_EXIST; + + lkup_type = fm_list->fltr_info.lkup_type; + vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id; + + status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + fm_list->vsi_count--; + clear_bit(vsi_id, fm_list->vsi_list_info->vsi_map); + + if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) || + (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) { + struct ice_vsi_list_map_info *vsi_list_info = + fm_list->vsi_list_info; + u16 rem_vsi_id; + + rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (rem_vsi_id == ICE_MAX_VSI) + return ICE_ERR_OUT_OF_RANGE; + + status = ice_update_vsi_list_rule(hw, &rem_vsi_id, 1, + vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + /* Remove the VSI list since it is no longer used */ + status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); + if (status) + return status; + + /* Change the list entry action from VSI_LIST to VSI */ + fm_list->fltr_info.fltr_act = ICE_FWD_TO_VSI; + fm_list->fltr_info.fwd_id.vsi_id = rem_vsi_id; + + list_del(&vsi_list_info->list_entry); + devm_kfree(ice_hw_to_dev(hw), vsi_list_info); + fm_list->vsi_list_info = NULL; + } + + return status; +} + +/** + * ice_remove_rule_internal - Remove a filter rule of a given type + * @hw: pointer to the hardware structure + * @recp_id: recipe id for which the rule needs to removed + * @f_entry: rule entry containing filter information + */ +static enum ice_status +ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_elem; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; + bool remove_rule = false; + u16 vsi_id; + + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; + mutex_lock(rule_lock); + list_elem = ice_find_rule_entry(hw, recp_id, &f_entry->fltr_info); + if (!list_elem) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } + + if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) { + remove_rule = true; + } else { + vsi_id = f_entry->fltr_info.fwd_id.vsi_id; + status = ice_rem_update_vsi_list(hw, vsi_id, list_elem); + if (status) + goto exit; + /* if vsi count goes to zero after updating the vsi list */ + if (list_elem->vsi_count == 0) + remove_rule = true; + } + + if (remove_rule) { + /* Remove the lookup rule */ + struct ice_aqc_sw_rules_elem *s_rule; + + s_rule = devm_kzalloc(ice_hw_to_dev(hw), + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, + GFP_KERNEL); + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto exit; + } + + ice_fill_sw_rule(hw, &list_elem->fltr_info, s_rule, + ice_aqc_opc_remove_sw_rules); + + status = ice_aq_sw_rules(hw, s_rule, + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, + ice_aqc_opc_remove_sw_rules, NULL); + if (status) + goto exit; + + /* Remove a book keeping from the list */ + devm_kfree(ice_hw_to_dev(hw), s_rule); + + list_del(&list_elem->list_entry); + devm_kfree(ice_hw_to_dev(hw), list_elem); + } +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1108,7 +1299,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_aqc_sw_rules_elem *s_rule, *r_iter; struct ice_fltr_list_entry *m_list_itr; + struct list_head *rule_head; u16 elem_sent, total_elem_left; + struct ice_switch_info *sw; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; u16 num_unicast = 0; u16 s_rule_size; @@ -1116,48 +1310,62 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) if (!m_list || !hw) return ICE_ERR_PARAM; + s_rule = NULL; + sw = hw->switch_info; + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry(m_list_itr, m_list, list_entry) { u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; - if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC) - return ICE_ERR_PARAM; - if (is_zero_ether_addr(add)) + m_list_itr->fltr_info.flag = ICE_FLTR_TX; + if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || + is_zero_ether_addr(add)) return ICE_ERR_PARAM; if (is_unicast_ether_addr(add) && !hw->ucast_shared) { /* Don't overwrite the unicast address */ - if (ice_find_mac_entry(hw, add)) + mutex_lock(rule_lock); + if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC, + &m_list_itr->fltr_info)) { + mutex_unlock(rule_lock); return ICE_ERR_ALREADY_EXISTS; + } + mutex_unlock(rule_lock); num_unicast++; } else if (is_multicast_ether_addr(add) || (is_unicast_ether_addr(add) && hw->ucast_shared)) { - status = ice_add_shared_mac(hw, m_list_itr); - if (status) { - m_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - m_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + m_list_itr->status = + ice_add_rule_internal(hw, ICE_SW_LKUP_MAC, + m_list_itr); + if (m_list_itr->status) + return m_list_itr->status; } } + mutex_lock(rule_lock); /* Exit if no suitable entries were found for adding bulk switch rule */ - if (!num_unicast) - return 0; + if (!num_unicast) { + status = 0; + goto ice_add_mac_exit; + } + + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; /* Allocate switch rule buffer for the bulk update for unicast */ s_rule_size = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto ice_add_mac_exit; + } r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - if (is_unicast_ether_addr(addr)) { - ice_fill_sw_rule(hw, &m_list_itr->fltr_info, - r_iter, ice_aqc_opc_add_sw_rules); + if (is_unicast_ether_addr(mac_addr)) { + ice_fill_sw_rule(hw, &m_list_itr->fltr_info, r_iter, + ice_aqc_opc_add_sw_rules); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } @@ -1185,11 +1393,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; - struct ice_switch_info *sw = hw->switch_info; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; struct ice_fltr_mgmt_list_entry *fm_entry; - if (is_unicast_ether_addr(addr)) { + if (is_unicast_ether_addr(mac_addr)) { f_info->fltr_rule_id = le16_to_cpu(r_iter->pdata.lkup_tx_rx.index); f_info->fltr_act = ICE_FWD_TO_VSI; @@ -1205,45 +1412,20 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) /* The book keeping entries will get removed when * base driver calls remove filter AQ command */ - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); + list_add(&fm_entry->list_entry, rule_head); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } } ice_add_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); + mutex_unlock(rule_lock); + if (s_rule) + devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } -/** - * ice_find_vlan_entry - * @hw: pointer to the hardware structure - * @vlan_id: VLAN id to search for - * - * Helper function to search for a VLAN entry using a given VLAN id - * Returns pointer to the entry if found. - */ -static struct ice_fltr_mgmt_list_entry * -ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) -{ - struct ice_fltr_mgmt_list_entry *vlan_list_itr, *vlan_ret = NULL; - struct ice_switch_info *sw = hw->switch_info; - - mutex_lock(&sw->vlan_list_lock); - list_for_each_entry(vlan_list_itr, &sw->vlan_list_head, list_entry) - if (vlan_list_itr->fltr_info.l_data.vlan.vlan_id == vlan_id) { - vlan_ret = vlan_list_itr; - break; - } - - mutex_unlock(&sw->vlan_list_lock); - return vlan_ret; -} - /** * ice_add_vlan_internal - Add one VLAN based filter rule * @hw: pointer to the hardware structure @@ -1252,20 +1434,22 @@ ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) static enum ice_status ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *v_list_itr; - u16 vlan_id; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; new_fltr = &f_entry->fltr_info; /* VLAN id should only be 12 bits */ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID) return ICE_ERR_PARAM; - vlan_id = new_fltr->l_data.vlan.vlan_id; - v_list_itr = ice_find_vlan_entry(hw, vlan_id); + rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; + mutex_lock(rule_lock); + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { u16 vsi_id = ICE_VSI_INVAL_ID; - enum ice_status status; u16 vsi_list_id = 0; if (new_fltr->fltr_act == ICE_FWD_TO_VSI) { @@ -1279,26 +1463,33 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) &vsi_list_id, lkup_type); if (status) - return status; + goto exit; new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; new_fltr->fwd_id.vsi_list_id = vsi_list_id; } status = ice_create_pkt_fwd_rule(hw, f_entry); if (!status && vsi_id != ICE_VSI_INVAL_ID) { - v_list_itr = ice_find_vlan_entry(hw, vlan_id); - if (!v_list_itr) - return ICE_ERR_DOES_NOT_EXIST; + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, + new_fltr); + if (!v_list_itr) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } v_list_itr->vsi_list_info = ice_create_vsi_list_map(hw, &vsi_id, 1, vsi_list_id); } - return status; + goto exit; } cur_fltr = &v_list_itr->fltr_info; - return ice_handle_vsi_list_mgmt(hw, v_list_itr, cur_fltr, new_fltr); + status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr, new_fltr); + +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1315,326 +1506,25 @@ ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) return ICE_ERR_PARAM; list_for_each_entry(v_list_itr, v_list, list_entry) { - enum ice_status status; - if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN) return ICE_ERR_PARAM; - - status = ice_add_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + v_list_itr->fltr_info.flag = ICE_FLTR_TX; + v_list_itr->status = ice_add_vlan_internal(hw, v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } return 0; } /** - * ice_remove_vsi_list_rule - * @hw: pointer to the hardware structure - * @vsi_list_id: VSI list id generated as part of allocate resource - * @lkup_type: switch rule filter lookup type - */ -static enum ice_status -ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, - enum ice_sw_lkup_type lkup_type) -{ - struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; - u16 s_rule_size; - - s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); - s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); - s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); - /* FW expects number of VSIs in vsi_list resource to be 0 for clear - * command. Since memory is zero'ed out during initialization, it's not - * necessary to explicitly initialize the variable to 0. - */ - - status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (!status) - /* Free the vsi_list resource that we allocated */ - status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, - ice_aqc_opc_free_res); - - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_handle_rem_vsi_list_mgmt - * @hw: pointer to the hardware structure - * @vsi_id: ID of the VSI to remove - * @fm_list_itr: filter management entry for which the VSI list management - * needs to be done - */ -static enum ice_status -ice_handle_rem_vsi_list_mgmt(struct ice_hw *hw, u16 vsi_id, - struct ice_fltr_mgmt_list_entry *fm_list_itr) -{ - struct ice_switch_info *sw = hw->switch_info; - enum ice_status status = 0; - enum ice_sw_lkup_type lkup_type; - bool is_last_elem = true; - bool conv_list = false; - bool del_list = false; - u16 vsi_list_id; - - lkup_type = fm_list_itr->fltr_info.lkup_type; - vsi_list_id = fm_list_itr->fltr_info.fwd_id.vsi_list_id; - - if (fm_list_itr->vsi_count > 1) { - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, - true, - ice_aqc_opc_update_sw_rules, - lkup_type); - if (status) - return status; - fm_list_itr->vsi_count--; - is_last_elem = false; - clear_bit(vsi_id, fm_list_itr->vsi_list_info->vsi_map); - } - - /* For non-VLAN rules that forward packets to a VSI list, convert them - * to forwarding packets to a VSI if there is only one VSI left in the - * list. Unused lists are then removed. - * VLAN rules need to use VSI lists even with only one VSI. - */ - if (fm_list_itr->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST) { - if (lkup_type == ICE_SW_LKUP_VLAN) { - del_list = is_last_elem; - } else if (fm_list_itr->vsi_count == 1) { - conv_list = true; - del_list = true; - } - } - - if (del_list) { - /* Remove the VSI list since it is no longer used */ - struct ice_vsi_list_map_info *vsi_list_info = - fm_list_itr->vsi_list_info; - - status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); - if (status) - return status; - - if (conv_list) { - u16 rem_vsi_id; - - rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, - ICE_MAX_VSI); - - /* Error out when the expected last element is not in - * the VSI list map - */ - if (rem_vsi_id == ICE_MAX_VSI) - return ICE_ERR_OUT_OF_RANGE; - - /* Change the list entry action from VSI_LIST to VSI */ - fm_list_itr->fltr_info.fltr_act = ICE_FWD_TO_VSI; - fm_list_itr->fltr_info.fwd_id.vsi_id = rem_vsi_id; - } - - list_del(&vsi_list_info->list_entry); - devm_kfree(ice_hw_to_dev(hw), vsi_list_info); - fm_list_itr->vsi_list_info = NULL; - } - - if (conv_list) { - /* Convert the rule's forward action to forwarding packets to - * a VSI - */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = - cpu_to_le16(fm_list_itr->fltr_info.fltr_rule_id); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, - ice_aqc_opc_update_sw_rules, NULL); - devm_kfree(ice_hw_to_dev(hw), s_rule); - if (status) - return status; - } - - if (is_last_elem) { - /* Remove the lookup rule */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_remove_sw_rules); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (status) - return status; - - /* Remove a book keeping entry from the MAC address list */ - mutex_lock(&sw->mac_list_lock); - list_del(&fm_list_itr->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), fm_list_itr); - devm_kfree(ice_hw_to_dev(hw), s_rule); - } - return status; -} - -/** - * ice_remove_mac_entry - * @hw: pointer to the hardware structure - * @f_entry: structure containing MAC forwarding information - */ -static enum ice_status -ice_remove_mac_entry(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) -{ - struct ice_fltr_mgmt_list_entry *m_entry; - u16 vsi_id; - u8 *add; - - add = &f_entry->fltr_info.l_data.mac.mac_addr[0]; - - m_entry = ice_find_mac_entry(hw, add); - if (!m_entry) - return ICE_ERR_PARAM; - - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, m_entry); -} - -/** - * ice_remove_mac - remove a MAC address based filter rule - * @hw: pointer to the hardware structure - * @m_list: list of MAC addresses and forwarding information - * - * This function removes either a MAC filter rule or a specific VSI from a - * VSI list for a multicast MAC address. - * - * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by - * ice_add_mac. Caller should be aware that this call will only work if all - * the entries passed into m_list were added previously. It will not attempt to - * do a partial remove of entries that were found. - */ -enum ice_status -ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) -{ - struct ice_aqc_sw_rules_elem *s_rule, *r_iter; - u8 s_rule_size = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; - struct ice_switch_info *sw = hw->switch_info; - struct ice_fltr_mgmt_list_entry *m_entry; - struct ice_fltr_list_entry *m_list_itr; - u16 elem_sent, total_elem_left; - enum ice_status status = 0; - u16 num_unicast = 0; - - if (!m_list) - return ICE_ERR_PARAM; - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr) && !hw->ucast_shared) - num_unicast++; - else if (is_multicast_ether_addr(addr) || - (is_unicast_ether_addr(addr) && hw->ucast_shared)) - ice_remove_mac_entry(hw, m_list_itr); - } - - /* Exit if no unicast addresses found. Multicast switch rules - * were added individually - */ - if (!num_unicast) - return 0; - - /* Allocate switch rule buffer for the bulk update for unicast */ - s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - r_iter = s_rule; - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) { - status = ICE_ERR_DOES_NOT_EXIST; - goto ice_remove_mac_exit; - } - - ice_fill_sw_rule(hw, &m_entry->fltr_info, - r_iter, ice_aqc_opc_remove_sw_rules); - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - } - - /* Call AQ bulk switch rule update for all unicast addresses */ - r_iter = s_rule; - /* Call AQ switch rule in AQ_MAX chunk */ - for (total_elem_left = num_unicast; total_elem_left > 0; - total_elem_left -= elem_sent) { - struct ice_aqc_sw_rules_elem *entry = r_iter; - - elem_sent = min(total_elem_left, - (u16)(ICE_AQ_MAX_BUF_LEN / s_rule_size)); - status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size, - elem_sent, ice_aqc_opc_remove_sw_rules, - NULL); - if (status) - break; - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) - return ICE_ERR_OUT_OF_RANGE; - mutex_lock(&sw->mac_list_lock); - list_del(&m_entry->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), m_entry); - } - } - -ice_remove_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_cfg_dflt_vsi - add filter rule to set/unset given VSI as default - * VSI for the switch (represented by swid) + * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure * @vsi_id: number of VSI to set as default * @set: true to add the above mentioned switch rule, false to remove it * @direction: ICE_FLTR_RX or ICE_FLTR_TX + * + * add filter rule to set/unset given VSI as default VSI for the switch + * (represented by swid) */ enum ice_status ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) @@ -1706,26 +1596,38 @@ out: } /** - * ice_remove_vlan_internal - Remove one VLAN based filter rule + * ice_remove_mac - remove a MAC address based filter rule * @hw: pointer to the hardware structure - * @f_entry: filter entry containing one VLAN information + * @m_list: list of MAC addresses and forwarding information + * + * This function removes either a MAC filter rule or a specific VSI from a + * VSI list for a multicast MAC address. + * + * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by + * ice_add_mac. Caller should be aware that this call will only work if all + * the entries passed into m_list were added previously. It will not attempt to + * do a partial remove of entries that were found. */ -static enum ice_status -ice_remove_vlan_internal(struct ice_hw *hw, - struct ice_fltr_list_entry *f_entry) +enum ice_status +ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_fltr_info *new_fltr; - struct ice_fltr_mgmt_list_entry *v_list_elem; - u16 vsi_id; + struct ice_fltr_list_entry *list_itr; - new_fltr = &f_entry->fltr_info; - - v_list_elem = ice_find_vlan_entry(hw, new_fltr->l_data.vlan.vlan_id); - if (!v_list_elem) + if (!m_list) return ICE_ERR_PARAM; - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, v_list_elem); + list_for_each_entry(list_itr, m_list, list_entry) { + enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_MAC) + return ICE_ERR_PARAM; + list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_MAC, + list_itr); + if (list_itr->status) + return list_itr->status; + } + return 0; } /** @@ -1737,20 +1639,78 @@ enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { struct ice_fltr_list_entry *v_list_itr; - enum ice_status status = 0; if (!v_list || !hw) return ICE_ERR_PARAM; list_for_each_entry(v_list_itr, v_list, list_entry) { - status = ice_remove_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_VLAN) + return ICE_ERR_PARAM; + v_list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_VLAN, + v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } - return status; + return 0; +} + +/** + * ice_vsi_uses_fltr - Determine if given VSI uses specified filter + * @fm_entry: filter entry to inspect + * @vsi_id: ID of VSI to compare with filter info + */ +static bool +ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_id) +{ + return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && + fm_entry->fltr_info.fwd_id.vsi_id == vsi_id) || + (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))); +} + +/** + * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list + * @hw: pointer to the hardware structure + * @vsi_id: ID of VSI to remove filters from + * @vsi_list_head: pointer to the list to add entry to + * @fi: pointer to fltr_info of filter entry to copy & add + * + * Helper function, used when creating a list of filters to remove from + * a specific VSI. The entry added to vsi_list_head is a COPY of the + * original filter entry, with the exception of fltr_info.fltr_act and + * fltr_info.fwd_id fields. These are set such that later logic can + * extract which VSI to remove the fltr from, and pass on that information. + */ +static enum ice_status +ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, + struct list_head *vsi_list_head, + struct ice_fltr_info *fi) +{ + struct ice_fltr_list_entry *tmp; + + /* this memory is freed up in the caller function + * once filters for this VSI are removed + */ + tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + tmp->fltr_info = *fi; + + /* Overwrite these fields to indicate which VSI to remove filter from, + * so find and remove logic can extract the information from the + * list entries. Note that original entries will still have proper + * values. + */ + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.fwd_id.vsi_id = vsi_id; + + list_add(&tmp->list_entry, vsi_list_head); + + return 0; } /** @@ -1759,6 +1719,12 @@ ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) * @vsi_id: ID of VSI to remove filters from * @lkup_list_head: pointer to the list that has certain lookup type filters * @vsi_list_head: pointer to the list pertaining to VSI with vsi_id + * + * Locates all filters in lkup_list_head that are used by the given VSI, + * and adds COPIES of those entries to vsi_list_head (intended to be used + * to remove the listed filters). + * Note that this means all entries in vsi_list_head must be explicitly + * deallocated by the caller when done with list. */ static enum ice_status ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, @@ -1766,46 +1732,25 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, struct list_head *vsi_list_head) { struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; /* check to make sure VSI id is valid and within boundary */ - if (vsi_id >= - (sizeof(fm_entry->vsi_list_info->vsi_map) * BITS_PER_BYTE - 1)) + if (vsi_id >= ICE_MAX_VSI) return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { struct ice_fltr_info *fi; fi = &fm_entry->fltr_info; - if ((fi->fltr_act == ICE_FWD_TO_VSI && - fi->fwd_id.vsi_id == vsi_id) || - (fi->fltr_act == ICE_FWD_TO_VSI_LIST && - (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))) { - struct ice_fltr_list_entry *tmp; + if (!ice_vsi_uses_fltr(fm_entry, vsi_id)) + continue; - /* this memory is freed up in the caller function - * ice_remove_vsi_lkup_fltr() once filters for - * this VSI are removed - */ - tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), - GFP_KERNEL); - if (!tmp) - return ICE_ERR_NO_MEMORY; - - memcpy(&tmp->fltr_info, fi, sizeof(*fi)); - - /* Expected below fields to be set to ICE_FWD_TO_VSI and - * the particular VSI id since we are only removing this - * one VSI - */ - if (fi->fltr_act == ICE_FWD_TO_VSI_LIST) { - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi_id; - } - - list_add(&tmp->list_entry, vsi_list_head); - } + status = ice_add_entry_to_vsi_fltr_list(hw, vsi_id, + vsi_list_head, fi); + if (status) + return status; } - return 0; + return status; } /** @@ -1821,46 +1766,40 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_list_entry *fm_entry; struct list_head remove_list_head; + struct list_head *rule_head; struct ice_fltr_list_entry *tmp; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status; INIT_LIST_HEAD(&remove_list_head); + rule_lock = &sw->recp_list[lkup].filt_rule_lock; + rule_head = &sw->recp_list[lkup].filt_rules; + mutex_lock(rule_lock); + status = ice_add_to_vsi_fltr_list(hw, vsi_id, rule_head, + &remove_list_head); + mutex_unlock(rule_lock); + if (status) + return; + switch (lkup) { case ICE_SW_LKUP_MAC: - mutex_lock(&sw->mac_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->mac_list_head, - &remove_list_head); - mutex_unlock(&sw->mac_list_lock); - if (!status) { - ice_remove_mac(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_mac(hw, &remove_list_head); break; case ICE_SW_LKUP_VLAN: - mutex_lock(&sw->vlan_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->vlan_list_head, - &remove_list_head); - mutex_unlock(&sw->vlan_list_lock); - if (!status) { - ice_remove_vlan(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_vlan(hw, &remove_list_head); break; case ICE_SW_LKUP_MAC_VLAN: case ICE_SW_LKUP_ETHERTYPE: case ICE_SW_LKUP_ETHERTYPE_MAC: case ICE_SW_LKUP_PROMISC: - case ICE_SW_LKUP_PROMISC_VLAN: case ICE_SW_LKUP_DFLT: - ice_debug(hw, ICE_DBG_SW, - "Remove filters for this lookup type hasn't been implemented yet\n"); + case ICE_SW_LKUP_PROMISC_VLAN: + case ICE_SW_LKUP_LAST: + default: + ice_debug(hw, ICE_DBG_SW, "Unsupported lookup type %d\n", lkup); break; } - return; -free_fltr_list: list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) { list_del(&fm_entry->list_entry); devm_kfree(ice_hw_to_dev(hw), fm_entry); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 9b8ec128ee31..09a3b6d6541a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -39,6 +39,7 @@ enum ice_sw_lkup_type { ICE_SW_LKUP_DFLT = 5, ICE_SW_LKUP_ETHERTYPE_MAC = 8, ICE_SW_LKUP_PROMISC_VLAN = 9, + ICE_SW_LKUP_LAST }; struct ice_fltr_info { @@ -98,6 +99,31 @@ struct ice_fltr_info { u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ }; +struct ice_sw_recipe { + struct list_head l_entry; + + /* To protect modification of filt_rule list + * defined below + */ + struct mutex filt_rule_lock; + + /* List of type ice_fltr_mgmt_list_entry */ + struct list_head filt_rules; + + /* linked list of type recipe_list_entry */ + struct list_head rg_list; + /* linked list of type ice_sw_fv_list_entry*/ + struct list_head fv_list; + struct ice_aqc_recipe_data_elem *r_buf; + u8 recp_count; + u8 root_rid; + u8 num_profs; + u8 *prof_ids; + + /* recipe bitmap: what all recipes makes this recipe */ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); +}; + /* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list id */ struct ice_vsi_list_map_info { struct list_head list_entry; @@ -105,15 +131,9 @@ struct ice_vsi_list_map_info { u16 vsi_list_id; }; -enum ice_sw_fltr_status { - ICE_FLTR_STATUS_NEW = 0, - ICE_FLTR_STATUS_FW_SUCCESS, - ICE_FLTR_STATUS_FW_FAIL, -}; - struct ice_fltr_list_entry { struct list_head list_entry; - enum ice_sw_fltr_status status; + enum ice_status status; struct ice_fltr_info fltr_info; }; @@ -157,5 +177,6 @@ enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); enum ice_status ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction); +enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index adfe131bd3f3..473d82fdb570 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -253,19 +253,8 @@ struct ice_port_info { }; struct ice_switch_info { - /* Switch VSI lists to MAC/VLAN translation */ - struct mutex mac_list_lock; /* protect MAC list */ - struct list_head mac_list_head; - struct mutex vlan_list_lock; /* protect VLAN list */ - struct list_head vlan_list_head; - struct mutex eth_m_list_lock; /* protect ethtype list */ - struct list_head eth_m_list_head; - struct mutex promisc_list_lock; /* protect promisc mode list */ - struct list_head promisc_list_head; - struct mutex mac_vlan_list_lock; /* protect MAC-VLAN list */ - struct list_head mac_vlan_list_head; - struct list_head vsi_list_map_head; + struct ice_sw_recipe *recp_list; }; /* Port hardware description */ From 0f9d5027a7496c451737f0f549be083688a40549 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:50 -0700 Subject: [PATCH 07/15] ice: Refactor VSI allocation, deletion and rebuild flow This patch refactors aspects of the VSI allocation, deletion and rebuild flow. Some of the more noteworthy changes are described below. 1) On reset, all switch filters applied in the hardware are lost. In the rebuild flow, only MAC and broadcast filters are being restored. Instead, use a new function ice_replay_all_fltr to restore all the filters that were previously added. To do this, remove calls to ice_remove_vsi_fltr to prevent cleaning out the internal bookkeeping structures that ice_replay_all_fltr uses to replay filters. 2) Introduce a new state bit __ICE_PREPARED_FOR_RESET to distinguish the PF that requested the reset (and consequently prepared for it) from the rest of the PFs. These other PFs will prepare for reset only when they receive an interrupt from the firmware. 3) Use new functions ice_add_vsi and ice_free_vsi to create and destroy VSIs respectively. These functions accept a handle to uniquely identify a VSI. This same handle is required to rebuild the VSI post reset. To prevent confusion, the existing ice_vsi_add was renamed to ice_vsi_init. 4) Enhance ice_vsi_setup for the upcoming SR-IOV changes and expose a new wrapper function ice_pf_vsi_setup to create PF VSIs. Rework the error handling path in ice_setup_pf_sw. 5) Introduce a new function ice_vsi_release_all to release all PF VSIs. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 2 + .../net/ethernet/intel/ice/ice_adminq_cmd.h | 1 + drivers/net/ethernet/intel/ice/ice_common.c | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 371 +++++++++++------- drivers/net/ethernet/intel/ice/ice_switch.c | 357 +++++++++++++++-- drivers/net/ethernet/intel/ice/ice_switch.h | 14 +- drivers/net/ethernet/intel/ice/ice_type.h | 8 +- 7 files changed, 582 insertions(+), 173 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 868f4a1d0f72..e17030db0bee 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -62,6 +62,7 @@ extern const char ice_drv_ver[]; #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff +#define ICE_INVAL_VFID 256 #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -122,6 +123,7 @@ struct ice_sw { enum ice_state { __ICE_DOWN, __ICE_NEEDS_RESTART, + __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 87b304db9cad..55e8275ce2ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1253,6 +1253,7 @@ struct ice_aq_desc { struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; struct ice_aqc_add_get_update_free_vsi vsi_cmd; + struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; struct ice_aqc_get_link_status get_link_status; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 4c6b1038dc5f..b2bb42def038 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -711,6 +711,8 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) ice_debug(hw, ICE_DBG_INIT, "GlobalR requested\n"); val = GLGEN_RTRIG_GLOBR_M; break; + default: + return ICE_ERR_PARAM; } val |= rd32(hw, GLGEN_RTRIG); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 014a2f3ea76c..1ef63bf98cd8 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -32,6 +32,7 @@ static const struct net_device_ops ice_netdev_ops; static void ice_pf_dis_all_vsi(struct ice_pf *pf); static void ice_rebuild(struct ice_pf *pf); static int ice_vsi_release(struct ice_vsi *vsi); +static void ice_vsi_release_all(struct ice_pf *pf); static void ice_update_vsi_stats(struct ice_vsi *vsi); static void ice_update_pf_stats(struct ice_pf *pf); @@ -456,23 +457,13 @@ static void ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - u32 v; - - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - ice_remove_vsi_fltr(hw, pf->vsi[v]->vsi_num); - - dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); /* disable the VSIs and their queues that are not already DOWN */ - /* pf_dis_all_vsi modifies netdev structures -rtnl_lock needed */ ice_pf_dis_all_vsi(pf); - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - pf->vsi[v]->vsi_num = 0; - ice_shutdown_all_ctrlq(hw); + + set_bit(__ICE_PREPARED_FOR_RESET, pf->state); } /** @@ -490,26 +481,32 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) WARN_ON(in_interrupt()); /* PFR is a bit of a special case because it doesn't result in an OICR - * interrupt. So for PFR, we prepare for reset, issue the reset and - * rebuild sequentially. + * interrupt. Set pending bit here which otherwise gets set in the + * OICR handler. */ - if (reset_type == ICE_RESET_PFR) { + if (reset_type == ICE_RESET_PFR) set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - ice_prepare_for_reset(pf); - } + + ice_prepare_for_reset(pf); /* trigger the reset */ if (ice_reset(hw, reset_type)) { dev_err(dev, "reset %d failed\n", reset_type); set_bit(__ICE_RESET_FAILED, pf->state); clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); return; } + /* PFR is a bit of a special case because it doesn't result in an OICR + * interrupt. So for PFR, rebuild after the reset and clear the reset- + * associated state bits. + */ if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; ice_rebuild(pf); clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); } } @@ -519,20 +516,23 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) */ static void ice_reset_subtask(struct ice_pf *pf) { - enum ice_reset_req reset_type; - - rtnl_lock(); + enum ice_reset_req reset_type = ICE_RESET_INVAL; /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an - * OICR interrupt. The OICR handler (ice_misc_intr) determines what - * type of reset happened and sets __ICE_RESET_RECOVERY_PENDING bit in - * pf->state. So if reset/recovery is pending (as indicated by this bit) - * we do a rebuild and return. + * OICR interrupt. The OICR handler (ice_misc_intr) determines what type + * of reset is pending and sets bits in pf->state indicating the reset + * type and __ICE_RESET_RECOVERY_PENDING. So, if the latter bit is set + * prepare for pending reset if not already (for PF software-initiated + * global resets the software should already be prepared for it as + * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated + * by firmware or software on other PFs, that bit is not set so prepare + * for the reset now), poll for reset done, rebuild and return. */ if (ice_is_reset_recovery_pending(pf->state)) { clear_bit(__ICE_GLOBR_RECV, pf->state); clear_bit(__ICE_CORER_RECV, pf->state); - ice_prepare_for_reset(pf); + if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) + ice_prepare_for_reset(pf); /* make sure we are ready to rebuild */ if (ice_check_reset(&pf->hw)) { @@ -541,29 +541,32 @@ static void ice_reset_subtask(struct ice_pf *pf) /* done with reset. start rebuild */ pf->hw.reset_ongoing = false; ice_rebuild(pf); + /* clear bit to resume normal operations, but + * ICE_NEEDS_RESTART bit is set incase rebuild failed + */ + clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); } - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - goto unlock; + + return; } /* No pending resets to finish processing. Check for new resets */ + if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) + reset_type = ICE_RESET_PFR; + if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) + reset_type = ICE_RESET_CORER; if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state)) reset_type = ICE_RESET_GLOBR; - else if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) - reset_type = ICE_RESET_CORER; - else if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) - reset_type = ICE_RESET_PFR; - else - goto unlock; + /* If no valid reset type requested just return */ + if (reset_type == ICE_RESET_INVAL) + return; - /* reset if not already down or resetting */ + /* reset if not already down or busy */ if (!test_bit(__ICE_DOWN, pf->state) && !test_bit(__ICE_CFG_BUSY, pf->state)) { ice_do_reset(pf, reset_type); } - -unlock: - rtnl_unlock(); } /** @@ -970,7 +973,8 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) static void ice_service_task_schedule(struct ice_pf *pf) { if (!test_bit(__ICE_DOWN, pf->state) && - !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state)) + !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) && + !test_bit(__ICE_NEEDS_RESTART, pf->state)) queue_work(ice_wq, &pf->serv_task); } @@ -1013,9 +1017,10 @@ static void ice_service_task(struct work_struct *work) /* process reset requests first */ ice_reset_subtask(pf); - /* bail if a reset/recovery cycle is pending */ + /* bail if a reset/recovery cycle is pending or rebuild failed */ if (ice_is_reset_recovery_pending(pf->state) || - test_bit(__ICE_SUSPENDED, pf->state)) { + test_bit(__ICE_SUSPENDED, pf->state) || + test_bit(__ICE_NEEDS_RESTART, pf->state)) { ice_service_task_complete(pf); return; } @@ -1160,7 +1165,7 @@ static void ice_vsi_delete(struct ice_vsi *vsi) memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); - status = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); + status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL); if (status) dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", vsi->vsi_num); @@ -1423,13 +1428,13 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) } /** - * ice_vsi_add - Create a new VSI or fetch preallocated VSI + * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured * * This initializes a VSI context depending on the VSI type to be added and * passes it down to the add_vsi aq command to create a new VSI. */ -static int ice_vsi_add(struct ice_vsi *vsi) +static int ice_vsi_init(struct ice_vsi *vsi) { struct ice_vsi_ctx ctxt = { 0 }; struct ice_pf *pf = vsi->back; @@ -1456,13 +1461,17 @@ static int ice_vsi_add(struct ice_vsi *vsi) ctxt.info.sw_id = vsi->port_info->sw_id; ice_vsi_setup_q_map(vsi, &ctxt); - ret = ice_aq_add_vsi(hw, &ctxt, NULL); + ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL); if (ret) { - dev_err(&vsi->back->pdev->dev, - "Add VSI AQ call failed, err %d\n", ret); + dev_err(&pf->pdev->dev, + "Add VSI failed, err %d\n", ret); return -EIO; } + + /* keep context for update VSI operations */ vsi->info = ctxt.info; + + /* record VSI number returned */ vsi->vsi_num = ctxt.vsi_num; return ret; @@ -2652,14 +2661,12 @@ ice_vsi_cfg_rss_exit: } /** - * ice_vsi_reinit_setup - return resource and reallocate resource for a VSI - * @vsi: pointer to the ice_vsi - * - * This reallocates the VSIs queue resources + * ice_vsi_rebuild - Rebuild VSI after reset + * @vsi: vsi to be rebuild * * Returns 0 on success and negative value on failure */ -static int ice_vsi_reinit_setup(struct ice_vsi *vsi) +static int ice_vsi_rebuild(struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; int ret, i; @@ -2675,7 +2682,7 @@ static int ice_vsi_reinit_setup(struct ice_vsi *vsi) ice_vsi_set_num_qs(vsi); /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_add(vsi); + ret = ice_vsi_init(vsi); if (ret < 0) goto err_vsi; @@ -2685,19 +2692,7 @@ static int ice_vsi_reinit_setup(struct ice_vsi *vsi) switch (vsi->type) { case ICE_VSI_PF: - if (!vsi->netdev) { - ret = ice_cfg_netdev(vsi); - if (ret) - goto err_rings; - - ret = register_netdev(vsi->netdev); - if (ret) - goto err_rings; - - netif_carrier_off(vsi->netdev); - netif_tx_stop_all_queues(vsi->netdev); - } - + /* fall through */ ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto err_rings; @@ -2749,21 +2744,23 @@ err_vsi: /** * ice_vsi_setup - Set up a VSI by a given type * @pf: board private structure - * @type: VSI type * @pi: pointer to the port_info instance + * @type: VSI type + * @vf_id: defines VF id to which this VSI connects. This field is meant to be + * used only for ICE_VSI_VF VSI type. For other VSI types, should + * fill-in ICE_INVAL_VFID as input. * * This allocates the sw VSI structure and its queue resources. * - * Returns pointer to the successfully allocated and configure VSI sw struct on - * success, otherwise returns NULL on failure. + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. */ static struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type, - struct ice_port_info *pi) +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 __always_unused vf_id) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = &pf->pdev->dev; - struct ice_vsi_ctx ctxt = { 0 }; struct ice_vsi *vsi; int ret, i; @@ -2786,12 +2783,10 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type, ice_vsi_set_rss_params(vsi); /* create the VSI */ - ret = ice_vsi_add(vsi); + ret = ice_vsi_init(vsi); if (ret) goto err_vsi; - ctxt.vsi_num = vsi->vsi_num; - switch (vsi->type) { case ICE_VSI_PF: ret = ice_cfg_netdev(vsi); @@ -2860,10 +2855,7 @@ err_register_netdev: vsi->netdev = NULL; } err_cfg_netdev: - ret = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); - if (ret) - dev_err(&vsi->back->pdev->dev, - "Free VSI AQ call failed, err %d\n", ret); + ice_vsi_delete(vsi); err_vsi: ice_vsi_put_qs(vsi); err_get_qs: @@ -2874,6 +2866,20 @@ err_get_qs: return NULL; } +/** + * ice_pf_vsi_setup - Set up a PF VSI + * @pf: board private structure + * @pi: pointer to the port_info instance + * + * Returns pointer to the successfully allocated VSI sw struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi * +ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID); +} + /** * ice_vsi_add_vlan - Add vsi membership for given vlan * @vsi: the vsi being configured @@ -3021,50 +3027,48 @@ static int ice_setup_pf_sw(struct ice_pf *pf) struct ice_vsi *vsi; int status = 0; - if (!ice_is_reset_recovery_pending(pf->state)) { - vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info); - if (!vsi) { - status = -ENOMEM; - goto error_exit; - } - } else { - vsi = pf->vsi[0]; - status = ice_vsi_reinit_setup(vsi); - if (status < 0) - return -EIO; + if (ice_is_reset_recovery_pending(pf->state)) + return -EBUSY; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + status = -ENOMEM; + goto unroll_vsi_setup; } - /* tmp_add_list contains a list of MAC addresses for which MAC - * filters need to be programmed. Add the VSI's unicast MAC to - * this list + /* To add a MAC filter, first add the MAC to a list and then + * pass the list to ice_add_mac. */ + + /* Add a unicast MAC filter so the VSI can get its packets */ status = ice_add_mac_to_list(vsi, &tmp_add_list, vsi->port_info->mac.perm_addr); if (status) - goto error_exit; + goto unroll_vsi_setup; /* VSI needs to receive broadcast traffic, so add the broadcast - * MAC address to the list. + * MAC address to the list as well. */ eth_broadcast_addr(broadcast); status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); if (status) - goto error_exit; + goto free_mac_list; /* program MAC filters for entries in tmp_add_list */ status = ice_add_mac(&pf->hw, &tmp_add_list); if (status) { dev_err(&pf->pdev->dev, "Could not add MAC filters\n"); status = -ENOMEM; - goto error_exit; + goto free_mac_list; } ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); return status; -error_exit: +free_mac_list: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); +unroll_vsi_setup: if (vsi) { ice_vsi_free_q_vectors(vsi); if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) @@ -3453,24 +3457,13 @@ err_exit_unroll: static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - int i = 0; - int err; if (!pf) return; set_bit(__ICE_DOWN, pf->state); - for (i = 0; i < pf->num_alloc_vsi; i++) { - if (!pf->vsi[i]) - continue; - - err = ice_vsi_release(pf->vsi[i]); - if (err) - dev_dbg(&pf->pdev->dev, "Failed to release VSI index %d (err %d)\n", - i, err); - } - + ice_vsi_release_all(pf); ice_free_irq_msix_misc(pf); ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); @@ -3517,7 +3510,7 @@ static int __init ice_module_init(void) pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver); pr_info("%s\n", ice_copyright); - ice_wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; @@ -5104,8 +5097,14 @@ static int ice_vsi_release(struct ice_vsi *vsi) if (!vsi->back) return -ENODEV; pf = vsi->back; - - if (vsi->netdev) { + /* do not unregister and free netdevs while driver is in the reset + * recovery pending state. Since reset/rebuild happens through PF + * service task workqueue, its not a good idea to unregister netdev + * that is associated to the PF that is running the work queue items + * currently. This is done to avoid check_flush_dependency() warning + * on this wq + */ + if (vsi->netdev && !ice_is_reset_recovery_pending(pf->state)) { unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; @@ -5131,11 +5130,39 @@ static int ice_vsi_release(struct ice_vsi *vsi) pf->q_left_tx += vsi->alloc_txq; pf->q_left_rx += vsi->alloc_rxq; - ice_vsi_clear(vsi); + /* retain SW VSI data structure since it is needed to unregister and + * free VSI netdev when PF is not in reset recovery pending state,\ + * for ex: during rmmod. + */ + if (!ice_is_reset_recovery_pending(pf->state)) + ice_vsi_clear(vsi); return 0; } +/** + * ice_vsi_release_all - Delete all VSIs + * @pf: PF from which all VSIs are being removed + */ +static void ice_vsi_release_all(struct ice_pf *pf) +{ + int err, i; + + if (!pf->vsi) + return; + + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (!pf->vsi[i]) + continue; + + err = ice_vsi_release(pf->vsi[i]); + if (err) + dev_dbg(&pf->pdev->dev, + "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", + i, err, pf->vsi[i]->vsi_num); + } +} + /** * ice_dis_vsi - pause a VSI * @vsi: the VSI being paused @@ -5148,27 +5175,31 @@ static void ice_dis_vsi(struct ice_vsi *vsi) set_bit(__ICE_NEEDS_RESTART, vsi->state); if (vsi->netdev && netif_running(vsi->netdev) && - vsi->type == ICE_VSI_PF) + vsi->type == ICE_VSI_PF) { + rtnl_lock(); vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - - ice_vsi_close(vsi); + rtnl_unlock(); + } else { + ice_vsi_close(vsi); + } } /** * ice_ena_vsi - resume a VSI * @vsi: the VSI being resume */ -static void ice_ena_vsi(struct ice_vsi *vsi) +static int ice_ena_vsi(struct ice_vsi *vsi) { - if (!test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) - return; + int err = 0; - if (vsi->netdev && netif_running(vsi->netdev)) - vsi->netdev->netdev_ops->ndo_open(vsi->netdev); - else if (ice_vsi_open(vsi)) - /* this clears the DOWN bit */ - dev_dbg(&vsi->back->pdev->dev, "Failed open VSI 0x%04X on switch 0x%04X\n", - vsi->vsi_num, vsi->vsw->sw_id); + if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) + if (vsi->netdev && netif_running(vsi->netdev)) { + rtnl_lock(); + err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev); + rtnl_unlock(); + } + + return err; } /** @@ -5188,13 +5219,47 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf) * ice_pf_ena_all_vsi - Resume all VSIs on a PF * @pf: the PF */ -static void ice_pf_ena_all_vsi(struct ice_pf *pf) +static int ice_pf_ena_all_vsi(struct ice_pf *pf) { int v; ice_for_each_vsi(pf, v) if (pf->vsi[v]) - ice_ena_vsi(pf->vsi[v]); + if (ice_ena_vsi(pf->vsi[v])) + return -EIO; + + return 0; +} + +/** + * ice_vsi_rebuild_all - rebuild all VSIs in pf + * @pf: the PF + */ +static int ice_vsi_rebuild_all(struct ice_pf *pf) +{ + int i; + + /* loop through pf->vsi array and reinit the VSI if found */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + int err; + + if (!pf->vsi[i]) + continue; + + err = ice_vsi_rebuild(pf->vsi[i]); + if (err) { + dev_err(&pf->pdev->dev, + "VSI at index %d rebuild failed\n", + pf->vsi[i]->idx); + return err; + } + + dev_info(&pf->pdev->dev, + "VSI at index %d rebuilt. vsi_num = 0x%x\n", + pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + } + + return 0; } /** @@ -5216,13 +5281,13 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_init_all_ctrlq(hw); if (ret) { dev_err(dev, "control queues init failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ret = ice_clear_pf_cfg(hw); if (ret) { dev_err(dev, "clear PF configuration failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ice_clear_pxe_mode(hw); @@ -5230,14 +5295,24 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_get_caps(hw); if (ret) { dev_err(dev, "ice_get_caps failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } - /* basic nic switch setup */ - err = ice_setup_pf_sw(pf); + err = ice_sched_init_port(hw->port_info); + if (err) + goto err_sched_init_port; + + err = ice_vsi_rebuild_all(pf); if (err) { - dev_err(dev, "ice_setup_pf_sw failed\n"); - goto fail_reset; + dev_err(dev, "ice_vsi_rebuild_all failed\n"); + goto err_vsi_rebuild; + } + + ret = ice_replay_all_fltr(&pf->hw); + if (ret) { + dev_err(&pf->pdev->dev, + "error replaying switch filter rules\n"); + goto err_vsi_rebuild; } /* start misc vector */ @@ -5245,20 +5320,35 @@ static void ice_rebuild(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "misc vector setup failed: %d\n", err); - goto fail_reset; + goto err_vsi_rebuild; } } /* restart the VSIs that were rebuilt and running before the reset */ - ice_pf_ena_all_vsi(pf); + err = ice_pf_ena_all_vsi(pf); + if (err) { + dev_err(&pf->pdev->dev, "error enabling VSIs\n"); + /* no need to disable VSIs in tear down path in ice_rebuild() + * since its already taken care in ice_vsi_open() + */ + goto err_vsi_rebuild; + } + /* if we get here, reset flow is successful */ + clear_bit(__ICE_RESET_FAILED, pf->state); return; -fail_reset: +err_vsi_rebuild: + ice_vsi_release_all(pf); +err_sched_init_port: + ice_sched_cleanup_all(hw); +err_init_ctrlq: ice_shutdown_all_ctrlq(hw); set_bit(__ICE_RESET_FAILED, pf->state); clear_recovery: - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* set this bit in PF state to control service task scheduling */ + set_bit(__ICE_NEEDS_RESTART, pf->state); + dev_err(dev, "Rebuild failed, unload and reload driver\n"); } /** @@ -5431,6 +5521,11 @@ static int ice_open(struct net_device *netdev) struct ice_vsi *vsi = np->vsi; int err; + if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) { + netdev_err(netdev, "driver needs to be unloaded and reloaded\n"); + return -EIO; + } + netif_carrier_off(netdev); err = ice_vsi_open(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 2693bebef977..ac66c96a123d 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -169,17 +169,17 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp *buf, * * Add a VSI context to the hardware (0x0210) */ -enum ice_status +static enum ice_status ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *res; struct ice_aqc_add_get_update_free_vsi *cmd; - enum ice_status status; struct ice_aq_desc desc; + enum ice_status status; cmd = &desc.params.vsi_cmd; - res = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + res = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi); @@ -203,6 +203,42 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, return status; } +/** + * ice_aq_free_vsi + * @hw: pointer to the hw struct + * @vsi_ctx: pointer to a VSI context struct + * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources + * @cd: pointer to command details structure or NULL + * + * Free VSI context info from hardware (0x0213) + */ +static enum ice_status +ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_update_free_vsi_resp *resp; + struct ice_aqc_add_get_update_free_vsi *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.vsi_cmd; + resp = &desc.params.add_update_free_vsi_res; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); + + cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + if (keep_vsi_alloc) + cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) { + vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); + vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); + } + + return status; +} + /** * ice_aq_update_vsi * @hw: pointer to the hw struct @@ -221,7 +257,7 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, enum ice_status status; cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + resp = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi); @@ -241,38 +277,202 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** - * ice_aq_free_vsi + * ice_update_fltr_vsi_map - update given filter VSI map + * @list_head: list for which filters needs to be updated + * @list_lock: filter lock which needs to be updated + * @old_vsi_num: old VSI HW id + * @new_vsi_num: new VSI HW id + * + * update the VSI map for a given filter list + */ +static void +ice_update_fltr_vsi_map(struct list_head *list_head, + struct mutex *list_lock, u16 old_vsi_num, + u16 new_vsi_num) +{ + struct ice_fltr_mgmt_list_entry *itr; + + mutex_lock(list_lock); + if (list_empty(list_head)) + goto exit_update_map; + + list_for_each_entry(itr, list_head, list_entry) { + if (itr->vsi_list_info && + test_bit(old_vsi_num, itr->vsi_list_info->vsi_map)) { + clear_bit(old_vsi_num, itr->vsi_list_info->vsi_map); + set_bit(new_vsi_num, itr->vsi_list_info->vsi_map); + } else if (itr->fltr_info.fltr_act == ICE_FWD_TO_VSI && + itr->fltr_info.fwd_id.vsi_id == old_vsi_num) { + itr->fltr_info.fwd_id.vsi_id = new_vsi_num; + itr->fltr_info.src = new_vsi_num; + } + } +exit_update_map: + mutex_unlock(list_lock); +} + +/** + * ice_update_all_fltr_vsi_map - update all filters VSI map + * @hw: pointer to the hardware structure + * @old_vsi_num: old VSI HW id + * @new_vsi_num: new VSI HW id + * + * update all filters VSI map + */ +static void +ice_update_all_fltr_vsi_map(struct ice_hw *hw, u16 old_vsi_num, u16 new_vsi_num) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct list_head *head = &sw->recp_list[i].filt_rules; + struct mutex *lock; /* Lock to protect filter rule list */ + + lock = &sw->recp_list[i].filt_rule_lock; + ice_update_fltr_vsi_map(head, lock, old_vsi_num, + new_vsi_num); + } +} + +/** + * ice_is_vsi_valid - check whether the VSI is valid or not * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * check whether the VSI is valid or not + */ +static bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) +{ + return vsi_handle < ICE_MAX_VSI && hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_get_hw_vsi_num - return the hw VSI number + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the hw VSI number + * Caution: call this function only if VSI is valid (ice_is_vsi_valid) + */ +static u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) +{ + return hw->vsi_ctx[vsi_handle]->vsi_num; +} + +/** + * ice_get_vsi_ctx - return the VSI context entry for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the VSI context entry for a given VSI handle + */ +static struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + return (vsi_handle >= ICE_MAX_VSI) ? NULL : hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_save_vsi_ctx - save the VSI context for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * @vsi: VSI context pointer + * + * save the VSI context entry for a given VSI handle + */ +static void ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, + struct ice_vsi_ctx *vsi) +{ + hw->vsi_ctx[vsi_handle] = vsi; +} + +/** + * ice_clear_vsi_ctx - clear the VSI context entry + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * clear the VSI context entry + */ +static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + struct ice_vsi_ctx *vsi; + + vsi = ice_get_vsi_ctx(hw, vsi_handle); + if (vsi) { + devm_kfree(ice_hw_to_dev(hw), vsi); + hw->vsi_ctx[vsi_handle] = NULL; + } +} + +/** + * ice_add_vsi - add VSI context to the hardware and VSI handle list + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle provided by drivers + * @vsi_ctx: pointer to a VSI context struct + * @cd: pointer to command details structure or NULL + * + * Add a VSI context to the hardware also add it into the VSI handle list. + * If this function gets called after reset for existing VSIs then update + * with the new HW VSI number in the corresponding VSI handle list entry. + */ +enum ice_status +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd) +{ + struct ice_vsi_ctx *tmp_vsi_ctx; + enum ice_status status; + + if (vsi_handle >= ICE_MAX_VSI) + return ICE_ERR_PARAM; + status = ice_aq_add_vsi(hw, vsi_ctx, cd); + if (status) + return status; + tmp_vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!tmp_vsi_ctx) { + /* Create a new vsi context */ + tmp_vsi_ctx = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*tmp_vsi_ctx), GFP_KERNEL); + if (!tmp_vsi_ctx) { + ice_aq_free_vsi(hw, vsi_ctx, false, cd); + return ICE_ERR_NO_MEMORY; + } + *tmp_vsi_ctx = *vsi_ctx; + ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx); + } else { + /* update with new HW VSI num */ + if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num) { + /* update all filter lists with new HW VSI num */ + ice_update_all_fltr_vsi_map(hw, tmp_vsi_ctx->vsi_num, + vsi_ctx->vsi_num); + tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num; + } + } + + return status; +} + +/** + * ice_free_vsi- free VSI context from hardware and VSI handle list + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle * @vsi_ctx: pointer to a VSI context struct * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources * @cd: pointer to command details structure or NULL * - * Get VSI context info from hardware (0x0213) + * Free VSI context info from hardware as well as from VSI handle list */ enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd) +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) { - struct ice_aqc_add_update_free_vsi_resp *resp; - struct ice_aqc_add_get_update_free_vsi *cmd; - struct ice_aq_desc desc; enum ice_status status; - cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); - - cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); - if (keep_vsi_alloc) - cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); - if (!status) { - vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); - vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); - } - + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); + status = ice_aq_free_vsi(hw, vsi_ctx, keep_vsi_alloc, cd); + if (!status) + ice_clear_vsi_ctx(hw, vsi_handle); return status; } @@ -1516,6 +1716,25 @@ ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) return 0; } +/** + * ice_rem_sw_rule_info + * @hw: pointer to the hardware structure + * @rule_head: pointer to the switch list structure that we want to delete + */ +static void +ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) +{ + if (!list_empty(rule_head)) { + struct ice_fltr_mgmt_list_entry *entry; + struct ice_fltr_mgmt_list_entry *tmp; + + list_for_each_entry_safe(entry, tmp, rule_head, list_entry) { + list_del(&entry->list_entry); + devm_kfree(ice_hw_to_dev(hw), entry); + } + } +} + /** * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure @@ -1822,3 +2041,89 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id) ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE_MAC); ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC_VLAN); } + +/** + * ice_replay_fltr - Replay all the filters stored by a specific list head + * @hw: pointer to the hardware structure + * @list_head: list for which filters needs to be replayed + * @recp_id: Recipe id for which rules need to be replayed + */ +static enum ice_status +ice_replay_fltr(struct ice_hw *hw, u8 recp_id, struct list_head *list_head) +{ + struct ice_fltr_mgmt_list_entry *itr; + struct list_head l_head; + enum ice_status status = 0; + + if (list_empty(list_head)) + return status; + + /* Move entries from the given list_head to a temporary l_head so that + * they can be replayed. Otherwise when trying to re-add the same + * filter, the function will return already exists + */ + list_replace_init(list_head, &l_head); + + /* Mark the given list_head empty by reinitializing it so filters + * could be added again by *handler + */ + list_for_each_entry(itr, &l_head, list_entry) { + struct ice_fltr_list_entry f_entry; + + f_entry.fltr_info = itr->fltr_info; + if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN) { + status = ice_add_rule_internal(hw, recp_id, &f_entry); + if (status) + goto end; + continue; + } + + /* Add a filter per vsi separately */ + while (1) { + u16 vsi; + + vsi = find_first_bit(itr->vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (vsi == ICE_MAX_VSI) + break; + + clear_bit(vsi, itr->vsi_list_info->vsi_map); + f_entry.fltr_info.fwd_id.vsi_id = vsi; + f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; + if (recp_id == ICE_SW_LKUP_VLAN) + status = ice_add_vlan_internal(hw, &f_entry); + else + status = ice_add_rule_internal(hw, recp_id, + &f_entry); + if (status) + goto end; + } + } +end: + /* Clear the filter management list */ + ice_rem_sw_rule_info(hw, &l_head); + return status; +} + +/** + * ice_replay_all_fltr - replay all filters stored in bookkeeping lists + * @hw: pointer to the hardware structure + * + * NOTE: This function does not clean up partially added filters on error. + * It is up to caller of the function to issue a reset or fail early. + */ +enum ice_status ice_replay_all_fltr(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + enum ice_status status = 0; + u8 i; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct list_head *head = &sw->recp_list[i].filt_rules; + + status = ice_replay_fltr(hw, i, head); + if (status) + return status; + } + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 09a3b6d6541a..11a481644dac 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -158,15 +158,14 @@ struct ice_fltr_mgmt_list_entry { /* VSI related commands */ enum ice_status -ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - struct ice_sq_cd *cd); -enum ice_status ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd); - +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd); +enum ice_status +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd); enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ @@ -177,6 +176,9 @@ enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); enum ice_status ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction); + +enum ice_status ice_replay_all_fltr(struct ice_hw *hw); + enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 473d82fdb570..8b7efa87ce56 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -149,9 +149,10 @@ struct ice_mac_info { /* Various RESET request, These are not tied with HW reset types */ enum ice_reset_req { - ICE_RESET_PFR = 0, - ICE_RESET_CORER = 1, - ICE_RESET_GLOBR = 2, + ICE_RESET_INVAL = 0, + ICE_RESET_PFR = 1, + ICE_RESET_CORER = 2, + ICE_RESET_GLOBR = 3, }; /* Bus parameters */ @@ -283,6 +284,7 @@ struct ice_hw { u8 sw_entry_point_layer; u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; + struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI]; u8 evb_veb; /* true for VEB, false for VEPA */ u8 reset_ongoing; /* true if hw is in reset, false otherwise */ struct ice_bus_info bus; From 48cb27f2fd18391056ea40cce5e33f1fd741679e Mon Sep 17 00:00:00 2001 From: Chinh Cao Date: Thu, 9 Aug 2018 06:29:51 -0700 Subject: [PATCH 08/15] ice: Implement handlers for ethtool PHY/link operations This patch implements handlers for ethtool get_link_ksettings and set_link_ksettings. Helper functions use by these handlers are also introduced in this patch. Signed-off-by: Chinh Cao Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_adminq_cmd.h | 8 +- drivers/net/ethernet/intel/ice/ice_common.c | 121 ++- drivers/net/ethernet/intel/ice/ice_common.h | 14 +- drivers/net/ethernet/intel/ice/ice_ethtool.c | 803 +++++++++++++++++- 4 files changed, 892 insertions(+), 54 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 55e8275ce2ee..3dadb2b01b5c 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -920,9 +920,11 @@ struct ice_aqc_set_phy_cfg_data { u8 caps; #define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0) #define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1) -#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) -#define ICE_AQ_PHY_ENA_LINK BIT(3) -#define ICE_AQ_PHY_ENA_ATOMIC_LINK BIT(5) +#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) +#define ICE_AQ_PHY_ENA_LINK BIT(3) +#define ICE_AQ_PHY_ENA_AUTO_LINK_UPDT BIT(5) +#define ICE_AQ_PHY_ENA_LESM BIT(6) +#define ICE_AQ_PHY_ENA_AUTO_FEC BIT(7) u8 low_power_ctrl; __le16 eee_cap; /* Value from ice_aqc_get_phy_caps */ __le16 eeer_value; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index b2bb42def038..52c2bf4f108e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -125,7 +125,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, * * Returns the various PHY capabilities supported on the Port (0x0600) */ -static enum ice_status +enum ice_status ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *pcaps, struct ice_sq_cd *cd) @@ -1408,6 +1408,110 @@ void ice_clear_pxe_mode(struct ice_hw *hw) ice_aq_clear_pxe_mode(hw); } +/** + * ice_get_link_speed_based_on_phy_type - returns link speed + * @phy_type_low: lower part of phy_type + * + * This helper function will convert a phy_type_low to its corresponding link + * speed. + * Note: In the structure of phy_type_low, there should be one bit set, as + * this function will convert one phy type to its speed. + * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + */ +static u16 +ice_get_link_speed_based_on_phy_type(u64 phy_type_low) +{ + u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + + switch (phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + case ICE_PHY_TYPE_LOW_100M_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_100MB; + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + case ICE_PHY_TYPE_LOW_1000BASE_KX: + case ICE_PHY_TYPE_LOW_1G_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_1000MB; + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + case ICE_PHY_TYPE_LOW_2500BASE_X: + case ICE_PHY_TYPE_LOW_2500BASE_KX: + speed_phy_type_low = ICE_AQ_LINK_SPEED_2500MB; + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + speed_phy_type_low = ICE_AQ_LINK_SPEED_5GB; + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10GBASE_SR: + case ICE_PHY_TYPE_LOW_10GBASE_LR: + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_10GB; + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_25G_AUI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_25GB; + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB; + break; + default: + speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + + return speed_phy_type_low; +} + +/** + * ice_update_phy_type + * @phy_type_low: pointer to the lower part of phy_type + * @link_speeds_bitmap: targeted link speeds bitmap + * + * Note: For the link_speeds_bitmap structure, you can check it at + * [ice_aqc_get_link_status->link_speed]. Caller can pass in + * link_speeds_bitmap include multiple speeds. + * + * The value of phy_type_low will present a certain link speed. This helper + * function will turn on bits in the phy_type_low based on the value of + * link_speeds_bitmap input parameter. + */ +void ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap) +{ + u16 speed = ICE_AQ_LINK_SPEED_UNKNOWN; + u64 pt_low; + int index; + + /* We first check with low part of phy_type */ + for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) { + pt_low = BIT_ULL(index); + speed = ice_get_link_speed_based_on_phy_type(pt_low); + + if (link_speeds_bitmap & speed) + *phy_type_low |= BIT_ULL(index); + } +} + /** * ice_aq_set_phy_cfg * @hw: pointer to the hw struct @@ -1420,19 +1524,18 @@ void ice_clear_pxe_mode(struct ice_hw *hw) * mode as the PF may not have the privilege to set some of the PHY Config * parameters. This status will be indicated by the command response (0x0601). */ -static enum ice_status +enum ice_status ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd) { - struct ice_aqc_set_phy_cfg *cmd; struct ice_aq_desc desc; if (!cfg) return ICE_ERR_PARAM; - cmd = &desc.params.set_phy; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg); - cmd->lport_num = lport; + desc.params.set_phy.lport_num = lport; + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd); } @@ -1481,12 +1584,12 @@ out: * ice_set_fc * @pi: port information structure * @aq_failures: pointer to status code, specific to ice_set_fc routine - * @atomic_restart: enable automatic link update + * @ena_auto_link_update: enable automatic link update * * Set the requested flow control mode. */ enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { struct ice_aqc_set_phy_cfg_data cfg = { 0 }; struct ice_aqc_get_phy_caps_data *pcaps; @@ -1536,8 +1639,8 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) int retry_count, retry_max = 10; /* Auto restart link so settings take effect */ - if (atomic_restart) - cfg.caps |= ICE_AQ_PHY_ENA_ATOMIC_LINK; + if (ena_auto_link_update) + cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; /* Copy over all the old settings */ cfg.phy_type_low = pcaps->phy_type_low; cfg.low_power_ctrl = pcaps->low_power_ctrl; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 6455b6952ec8..409b9957f407 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -58,12 +58,24 @@ enum ice_status ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); + +enum ice_status +ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, + struct ice_aqc_get_phy_caps_data *caps, + struct ice_sq_cd *cd); +void +ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap); enum ice_status ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); enum ice_status ice_clear_pf_cfg(struct ice_hw *hw); enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart); +ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, + struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd); +enum ice_status +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, + bool ena_auto_link_update); + enum ice_status ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index c71a9b528d6d..db2c502ae932 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -332,58 +332,473 @@ ice_get_ethtool_stats(struct net_device *netdev, } } -static int -ice_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *ks) +/** + * ice_phy_type_to_ethtool - convert the phy_types to ethtool link modes + * @netdev: network interface device structure + * @ks: ethtool link ksettings struct to fill out + */ +static void ice_phy_type_to_ethtool(struct net_device *netdev, + struct ethtool_link_ksettings *ks) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; - bool link_up; + u64 phy_types_low; hw_link_info = &vsi->port_info->phy.link_info; - link_up = hw_link_info->link_info & ICE_AQ_LINK_UP; + phy_types_low = vsi->port_info->phy.phy_type_low; - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 10000baseT_Full); + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); - /* set speed and duplex */ - if (link_up) { - switch (hw_link_info->link_speed) { - case ICE_AQ_LINK_SPEED_100MB: - ks->base.speed = SPEED_100; - break; - case ICE_AQ_LINK_SPEED_2500MB: - ks->base.speed = SPEED_2500; - break; - case ICE_AQ_LINK_SPEED_5GB: - ks->base.speed = SPEED_5000; - break; - case ICE_AQ_LINK_SPEED_10GB: - ks->base.speed = SPEED_10000; - break; - case ICE_AQ_LINK_SPEED_25GB: - ks->base.speed = SPEED_25000; - break; - case ICE_AQ_LINK_SPEED_40GB: - ks->base.speed = SPEED_40000; - break; - default: - ks->base.speed = SPEED_UNKNOWN; - break; - } - - ks->base.duplex = DUPLEX_FULL; - } else { - ks->base.speed = SPEED_UNKNOWN; - ks->base.duplex = DUPLEX_UNKNOWN; + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_100M_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1G_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_SX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_LX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_X || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_DA || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_SR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_SR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_SR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseSR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_LR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseLR4_Full); } + /* Autoneg PHY types */ + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); + } +} + +#define TEST_SET_BITS_TIMEOUT 50 +#define TEST_SET_BITS_SLEEP_MAX 2000 +#define TEST_SET_BITS_SLEEP_MIN 1000 + +/** + * ice_get_settings_link_up - Get Link settings for when link is up + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + */ +static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks, + struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings cap_ksettings; + struct ice_link_status *link_info; + struct ice_vsi *vsi = np->vsi; + bool unrecog_phy_low = false; + + link_info = &vsi->port_info->phy.link_info; + + /* Initialize supported and advertised settings based on phy settings */ + switch (link_info->phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_100M_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1G_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_X: + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_SR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + break; + default: + unrecog_phy_low = true; + } + + if (unrecog_phy_low) { + /* if we got here and link is up something bad is afoot */ + netdev_info(netdev, "WARNING: Unrecognized PHY_Low (0x%llx).\n", + (u64)link_info->phy_type_low); + } + + /* Now that we've worked out everything that could be supported by the + * current PHY type, get what is supported by the NVM and intersect + * them to get what is truly supported + */ + memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings)); + ice_phy_type_to_ethtool(netdev, &cap_ksettings); + ethtool_intersect_link_masks(ks, &cap_ksettings); + + switch (link_info->link_speed) { + case ICE_AQ_LINK_SPEED_40GB: + ks->base.speed = SPEED_40000; + break; + case ICE_AQ_LINK_SPEED_25GB: + ks->base.speed = SPEED_25000; + break; + case ICE_AQ_LINK_SPEED_20GB: + ks->base.speed = SPEED_20000; + break; + case ICE_AQ_LINK_SPEED_10GB: + ks->base.speed = SPEED_10000; + break; + case ICE_AQ_LINK_SPEED_5GB: + ks->base.speed = SPEED_5000; + break; + case ICE_AQ_LINK_SPEED_2500MB: + ks->base.speed = SPEED_2500; + break; + case ICE_AQ_LINK_SPEED_1000MB: + ks->base.speed = SPEED_1000; + break; + case ICE_AQ_LINK_SPEED_100MB: + ks->base.speed = SPEED_100; + break; + default: + netdev_info(netdev, + "WARNING: Unrecognized link_speed (0x%x).\n", + link_info->link_speed); + break; + } + ks->base.duplex = DUPLEX_FULL; +} + +/** + * ice_get_settings_link_down - Get the Link settings when link is down + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + * + * Reports link settings that can be determined when link is down + */ +static void +ice_get_settings_link_down(struct ethtool_link_ksettings *ks, + struct net_device __always_unused *netdev) +{ + /* link is down and the driver needs to fall back on + * supported phy types to figure out what info to display + */ + ice_phy_type_to_ethtool(netdev, ks); + + /* With no link, speed and duplex are unknown */ + ks->base.speed = SPEED_UNKNOWN; + ks->base.duplex = DUPLEX_UNKNOWN; +} + +/** + * ice_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Reports speed/duplex settings based on media_type + */ +static int ice_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ks) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_link_status *hw_link_info; + struct ice_vsi *vsi = np->vsi; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); + hw_link_info = &vsi->port_info->phy.link_info; + + /* set speed and duplex */ + if (hw_link_info->link_info & ICE_AQ_LINK_UP) + ice_get_settings_link_up(ks, netdev); + else + ice_get_settings_link_down(ks, netdev); + /* set autoneg settings */ - ks->base.autoneg = ((hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ks->base.autoneg = (hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; /* set media type settings */ switch (vsi->port_info->phy.media_type) { @@ -441,6 +856,311 @@ ice_get_link_ksettings(struct net_device *netdev, return 0; } +/** + * ice_ksettings_find_adv_link_speed - Find advertising link speed + * @ks: ethtool ksettings + */ +static u16 +ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) +{ + u16 adv_link_speed = 0; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 100baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 5000baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_5GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseLR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_25GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseCR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseSR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseLR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseKR4_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_40GB; + + return adv_link_speed; +} + +/** + * ice_setup_autoneg + * @p: port info + * @ks: ethtool_link_ksettings + * @config: configuration that will be sent down to FW + * @autoneg_enabled: autonegotiation is enabled or not + * @autoneg_changed: will there a change in autonegotiation + * @netdev: network interface device structure + * + * Setup PHY autonegotiation feature + */ +static int +ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks, + struct ice_aqc_set_phy_cfg_data *config, + u8 autoneg_enabled, u8 *autoneg_changed, + struct net_device *netdev) +{ + int err = 0; + + *autoneg_changed = 0; + + /* Check autoneg */ + if (autoneg_enabled == AUTONEG_ENABLE) { + /* If autoneg was not already enabled */ + if (!(p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)) { + /* If autoneg is not supported, return error */ + if (!ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg not supported on this phy.\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } else { + /* If autoneg is currently enabled */ + if (p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) { + /* If autoneg is supported 10GBASE_T is the only phy + * that can disable it, so otherwise return error + */ + if (ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps &= ~ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } + + return err; +} + +/** + * ice_set_link_ksettings - Set Speed and Duplex + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Set speed/duplex per media_types advertised/forced + */ +static int ice_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ks) +{ + u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings safe_ks, copy_ks; + struct ice_aqc_get_phy_caps_data *abilities; + u16 adv_link_speed, curr_link_speed, idx; + struct ice_aqc_set_phy_cfg_data config; + struct ice_pf *pf = np->vsi->back; + struct ice_port_info *p; + u8 autoneg_changed = 0; + enum ice_status status; + u64 phy_type_low; + int err = 0; + bool linkup; + + p = np->vsi->port_info; + + if (!p) + return -EOPNOTSUPP; + + /* Check if this is lan vsi */ + for (idx = 0 ; idx < pf->num_alloc_vsi ; idx++) { + if (pf->vsi[idx]->type == ICE_VSI_PF) { + if (np->vsi != pf->vsi[idx]) + return -EOPNOTSUPP; + break; + } + } + + if (p->phy.media_type != ICE_MEDIA_BASET && + p->phy.media_type != ICE_MEDIA_FIBER && + p->phy.media_type != ICE_MEDIA_BACKPLANE && + p->phy.media_type != ICE_MEDIA_DA && + p->phy.link_info.link_info & ICE_AQ_LINK_UP) + return -EOPNOTSUPP; + + /* copy the ksettings to copy_ks to avoid modifying the original */ + memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings)); + + /* save autoneg out of ksettings */ + autoneg = copy_ks.base.autoneg; + + memset(&safe_ks, 0, sizeof(safe_ks)); + + /* Get link modes supported by hardware.*/ + ice_phy_type_to_ethtool(netdev, &safe_ks); + + /* and check against modes requested by user. + * Return an error if unsupported mode was set. + */ + if (!bitmap_subset(copy_ks.link_modes.advertising, + safe_ks.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; + + /* get our own copy of the bits to check against */ + memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings)); + safe_ks.base.cmd = copy_ks.base.cmd; + safe_ks.base.link_mode_masks_nwords = + copy_ks.base.link_mode_masks_nwords; + ice_get_link_ksettings(netdev, &safe_ks); + + /* set autoneg back to what it currently is */ + copy_ks.base.autoneg = safe_ks.base.autoneg; + /* we don't compare the speed */ + copy_ks.base.speed = safe_ks.base.speed; + + /* If copy_ks.base and safe_ks.base are not the same now, then they are + * trying to set something that we do not support. + */ + if (memcmp(©_ks.base, &safe_ks.base, + sizeof(struct ethtool_link_settings))) + return -EOPNOTSUPP; + + while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(TEST_SET_BITS_SLEEP_MIN, TEST_SET_BITS_SLEEP_MAX); + } + + abilities = devm_kzalloc(&pf->pdev->dev, sizeof(*abilities), + GFP_KERNEL); + if (!abilities) + return -ENOMEM; + + /* Get the current phy config */ + status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_SW_CFG, abilities, + NULL); + if (status) { + err = -EAGAIN; + goto done; + } + + /* Copy abilities to config in case autoneg is not set below */ + memset(&config, 0, sizeof(struct ice_aqc_set_phy_cfg_data)); + config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE; + if (abilities->caps & ICE_AQC_PHY_AN_MODE) + config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + + /* Check autoneg */ + err = ice_setup_autoneg(p, &safe_ks, &config, autoneg, &autoneg_changed, + netdev); + + if (err) + goto done; + + /* Call to get the current link speed */ + p->phy.get_link_info = true; + status = ice_get_link_status(p, &linkup); + if (status) { + err = -EAGAIN; + goto done; + } + + curr_link_speed = p->phy.link_info.link_speed; + adv_link_speed = ice_ksettings_find_adv_link_speed(ks); + + /* If speed didn't get set, set it to what it currently is. + * This is needed because if advertise is 0 (as it is when autoneg + * is disabled) then speed won't get set. + */ + if (!adv_link_speed) + adv_link_speed = curr_link_speed; + + /* Convert the advertise link speeds to their corresponded PHY_TYPE */ + ice_update_phy_type(&phy_type_low, adv_link_speed); + + if (!autoneg_changed && adv_link_speed == curr_link_speed) { + netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); + goto done; + } + + /* copy over the rest of the abilities */ + config.low_power_ctrl = abilities->low_power_ctrl; + config.eee_cap = abilities->eee_cap; + config.eeer_value = abilities->eeer_value; + config.link_fec_opt = abilities->link_fec_options; + + /* save the requested speeds */ + p->phy.link_info.req_speeds = adv_link_speed; + + /* set link and auto negotiation so changes take effect */ + config.caps |= ICE_AQ_PHY_ENA_LINK; + + if (phy_type_low) { + config.phy_type_low = cpu_to_le64(phy_type_low) & + abilities->phy_type_low; + } else { + err = -EAGAIN; + netdev_info(netdev, "Nothing changed. No PHY_TYPE is corresponded to advertised link speed.\n"); + goto done; + } + + /* If link is up put link down */ + if (p->phy.link_info.link_info & ICE_AQ_LINK_UP) { + /* Tell the OS link is going down, the link will go + * back up when fw says it is ready asynchronously + */ + ice_print_link_msg(np->vsi, false); + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + } + + /* make the aq call */ + status = ice_aq_set_phy_cfg(&pf->hw, lport, &config, NULL); + if (status) { + netdev_info(netdev, "Set phy config failed,\n"); + err = -EAGAIN; + } + +done: + devm_kfree(&pf->pdev->dev, abilities); + clear_bit(__ICE_CFG_BUSY, pf->state); + + return err; +} + /** * ice_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure @@ -933,6 +1653,7 @@ static int ice_set_rxfh(struct net_device *netdev, const u32 *indir, static const struct ethtool_ops ice_ethtool_ops = { .get_link_ksettings = ice_get_link_ksettings, + .set_link_ksettings = ice_set_link_ksettings, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, From f80eaa42107638684014f1f7c9d7bedda2b5e355 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:52 -0700 Subject: [PATCH 09/15] ice: Clean up register file This patch cleans up the existing register definitions. 1) Several instances of long defines names used in the BIT() macro were replaced to use the actual values they represent. As a result some defines for shifts (ending with _S) that were used only to create bitmasks were removed completely. 2) Apply more consistent tab spacing. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_hw_autogen.h | 417 ++++++++---------- 1 file changed, 188 insertions(+), 229 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 6076fc87df9d..067ca26a1d94 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -6,251 +6,210 @@ #ifndef _ICE_HW_AUTOGEN_H_ #define _ICE_HW_AUTOGEN_H_ -#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) -#define PF_FW_ARQBAH 0x00080180 -#define PF_FW_ARQBAL 0x00080080 -#define PF_FW_ARQH 0x00080380 -#define PF_FW_ARQH_ARQH_S 0 -#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, PF_FW_ARQH_ARQH_S) -#define PF_FW_ARQLEN 0x00080280 -#define PF_FW_ARQLEN_ARQLEN_S 0 -#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, PF_FW_ARQLEN_ARQLEN_S) -#define PF_FW_ARQLEN_ARQVFE_S 28 -#define PF_FW_ARQLEN_ARQVFE_M BIT(PF_FW_ARQLEN_ARQVFE_S) -#define PF_FW_ARQLEN_ARQOVFL_S 29 -#define PF_FW_ARQLEN_ARQOVFL_M BIT(PF_FW_ARQLEN_ARQOVFL_S) -#define PF_FW_ARQLEN_ARQCRIT_S 30 -#define PF_FW_ARQLEN_ARQCRIT_M BIT(PF_FW_ARQLEN_ARQCRIT_S) -#define PF_FW_ARQLEN_ARQENABLE_S 31 -#define PF_FW_ARQLEN_ARQENABLE_M BIT(PF_FW_ARQLEN_ARQENABLE_S) -#define PF_FW_ARQT 0x00080480 -#define PF_FW_ATQBAH 0x00080100 -#define PF_FW_ATQBAL 0x00080000 -#define PF_FW_ATQH 0x00080300 -#define PF_FW_ATQH_ATQH_S 0 -#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, PF_FW_ATQH_ATQH_S) -#define PF_FW_ATQLEN 0x00080200 -#define PF_FW_ATQLEN_ATQLEN_S 0 -#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, PF_FW_ATQLEN_ATQLEN_S) -#define PF_FW_ATQLEN_ATQVFE_S 28 -#define PF_FW_ATQLEN_ATQVFE_M BIT(PF_FW_ATQLEN_ATQVFE_S) -#define PF_FW_ATQLEN_ATQOVFL_S 29 -#define PF_FW_ATQLEN_ATQOVFL_M BIT(PF_FW_ATQLEN_ATQOVFL_S) -#define PF_FW_ATQLEN_ATQCRIT_S 30 -#define PF_FW_ATQLEN_ATQCRIT_M BIT(PF_FW_ATQLEN_ATQCRIT_S) -#define PF_FW_ATQLEN_ATQENABLE_S 31 -#define PF_FW_ATQLEN_ATQENABLE_M BIT(PF_FW_ATQLEN_ATQENABLE_S) -#define PF_FW_ATQT 0x00080400 - +#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) +#define PF_FW_ARQBAH 0x00080180 +#define PF_FW_ARQBAL 0x00080080 +#define PF_FW_ARQH 0x00080380 +#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN 0x00080280 +#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN_ARQVFE_M BIT(28) +#define PF_FW_ARQLEN_ARQOVFL_M BIT(29) +#define PF_FW_ARQLEN_ARQCRIT_M BIT(30) +#define PF_FW_ARQLEN_ARQENABLE_M BIT(31) +#define PF_FW_ARQT 0x00080480 +#define PF_FW_ATQBAH 0x00080100 +#define PF_FW_ATQBAL 0x00080000 +#define PF_FW_ATQH 0x00080300 +#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN 0x00080200 +#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN_ATQVFE_M BIT(28) +#define PF_FW_ATQLEN_ATQOVFL_M BIT(29) +#define PF_FW_ATQLEN_ATQCRIT_M BIT(30) +#define PF_FW_ATQLEN_ATQENABLE_M BIT(31) +#define PF_FW_ATQT 0x00080400 #define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S 8 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, 8) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S 16 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, 16) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S 24 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, 24) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_1(_i) (0x0045c900 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_2(_i) (0x0045ca00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_3(_i) (0x0045cb00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S) - -#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) -#define QRXFLXP_CNTXT_RXDID_IDX_S 0 -#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, QRXFLXP_CNTXT_RXDID_IDX_S) -#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 -#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, QRXFLXP_CNTXT_RXDID_PRIO_S) -#define QRXFLXP_CNTXT_TS_S 11 -#define QRXFLXP_CNTXT_TS_M BIT(QRXFLXP_CNTXT_TS_S) -#define GLGEN_RSTAT 0x000B8188 -#define GLGEN_RSTAT_DEVSTATE_S 0 -#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, GLGEN_RSTAT_DEVSTATE_S) -#define GLGEN_RSTCTL 0x000B8180 -#define GLGEN_RSTCTL_GRSTDEL_S 0 -#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) -#define GLGEN_RSTAT_RESET_TYPE_S 2 -#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, GLGEN_RSTAT_RESET_TYPE_S) -#define GLGEN_RTRIG 0x000B8190 -#define GLGEN_RTRIG_CORER_S 0 -#define GLGEN_RTRIG_CORER_M BIT(GLGEN_RTRIG_CORER_S) -#define GLGEN_RTRIG_GLOBR_S 1 -#define GLGEN_RTRIG_GLOBR_M BIT(GLGEN_RTRIG_GLOBR_S) -#define GLGEN_STAT 0x000B612C -#define PFGEN_CTRL 0x00091000 -#define PFGEN_CTRL_PFSWR_S 0 -#define PFGEN_CTRL_PFSWR_M BIT(PFGEN_CTRL_PFSWR_S) -#define PFGEN_STATE 0x00088000 -#define PRTGEN_STATUS 0x000B8100 -#define PFHMC_ERRORDATA 0x00520500 -#define PFHMC_ERRORINFO 0x00520400 -#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) -#define GLINT_DYN_CTL_INTENA_S 0 -#define GLINT_DYN_CTL_INTENA_M BIT(GLINT_DYN_CTL_INTENA_S) -#define GLINT_DYN_CTL_CLEARPBA_S 1 -#define GLINT_DYN_CTL_CLEARPBA_M BIT(GLINT_DYN_CTL_CLEARPBA_S) -#define GLINT_DYN_CTL_SWINT_TRIG_S 2 -#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(GLINT_DYN_CTL_SWINT_TRIG_S) -#define GLINT_DYN_CTL_ITR_INDX_S 3 -#define GLINT_DYN_CTL_SW_ITR_INDX_S 25 -#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S) -#define GLINT_DYN_CTL_INTENA_MSK_S 31 -#define GLINT_DYN_CTL_INTENA_MSK_M BIT(GLINT_DYN_CTL_INTENA_MSK_S) -#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) -#define PFINT_FW_CTL 0x0016C800 -#define PFINT_FW_CTL_MSIX_INDX_S 0 -#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_FW_CTL_MSIX_INDX_S) -#define PFINT_FW_CTL_ITR_INDX_S 11 -#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, PFINT_FW_CTL_ITR_INDX_S) -#define PFINT_FW_CTL_CAUSE_ENA_S 30 -#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S) -#define PFINT_OICR 0x0016CA00 -#define PFINT_OICR_ECC_ERR_S 16 -#define PFINT_OICR_ECC_ERR_M BIT(PFINT_OICR_ECC_ERR_S) -#define PFINT_OICR_MAL_DETECT_S 19 -#define PFINT_OICR_MAL_DETECT_M BIT(PFINT_OICR_MAL_DETECT_S) -#define PFINT_OICR_GRST_S 20 -#define PFINT_OICR_GRST_M BIT(PFINT_OICR_GRST_S) -#define PFINT_OICR_PCI_EXCEPTION_S 21 -#define PFINT_OICR_PCI_EXCEPTION_M BIT(PFINT_OICR_PCI_EXCEPTION_S) -#define PFINT_OICR_HMC_ERR_S 26 -#define PFINT_OICR_HMC_ERR_M BIT(PFINT_OICR_HMC_ERR_S) -#define PFINT_OICR_PE_CRITERR_S 28 -#define PFINT_OICR_PE_CRITERR_M BIT(PFINT_OICR_PE_CRITERR_S) -#define PFINT_OICR_CTL 0x0016CA80 -#define PFINT_OICR_CTL_MSIX_INDX_S 0 -#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_OICR_CTL_MSIX_INDX_S) -#define PFINT_OICR_CTL_ITR_INDX_S 11 -#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, PFINT_OICR_CTL_ITR_INDX_S) -#define PFINT_OICR_CTL_CAUSE_ENA_S 30 -#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(PFINT_OICR_CTL_CAUSE_ENA_S) -#define PFINT_OICR_ENA 0x0016C900 -#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) -#define QINT_RQCTL_MSIX_INDX_S 0 -#define QINT_RQCTL_ITR_INDX_S 11 -#define QINT_RQCTL_CAUSE_ENA_S 30 -#define QINT_RQCTL_CAUSE_ENA_M BIT(QINT_RQCTL_CAUSE_ENA_S) -#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) -#define QINT_TQCTL_MSIX_INDX_S 0 -#define QINT_TQCTL_ITR_INDX_S 11 -#define QINT_TQCTL_CAUSE_ENA_S 30 -#define QINT_TQCTL_CAUSE_ENA_M BIT(QINT_TQCTL_CAUSE_ENA_S) -#define GLLAN_RCTL_0 0x002941F8 -#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) -#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) -#define QRX_CTRL_MAX_INDEX 2047 -#define QRX_CTRL_QENA_REQ_S 0 -#define QRX_CTRL_QENA_REQ_M BIT(QRX_CTRL_QENA_REQ_S) -#define QRX_CTRL_QENA_STAT_S 2 -#define QRX_CTRL_QENA_STAT_M BIT(QRX_CTRL_QENA_STAT_S) -#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) -#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) -#define GLNVM_FLA 0x000B6108 -#define GLNVM_FLA_LOCKED_S 6 -#define GLNVM_FLA_LOCKED_M BIT(GLNVM_FLA_LOCKED_S) -#define GLNVM_GENS 0x000B6100 -#define GLNVM_GENS_SR_SIZE_S 5 -#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, GLNVM_GENS_SR_SIZE_S) -#define GLNVM_ULD 0x000B6008 -#define GLNVM_ULD_CORER_DONE_S 3 -#define GLNVM_ULD_CORER_DONE_M BIT(GLNVM_ULD_CORER_DONE_S) -#define GLNVM_ULD_GLOBR_DONE_S 4 -#define GLNVM_ULD_GLOBR_DONE_M BIT(GLNVM_ULD_GLOBR_DONE_S) -#define PF_FUNC_RID 0x0009E880 -#define PF_FUNC_RID_FUNC_NUM_S 0 -#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, PF_FUNC_RID_FUNC_NUM_S) -#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) -#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) -#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) -#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) -#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) -#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) -#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) -#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) -#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) -#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) -#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) -#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) -#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) -#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) -#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) -#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) -#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) -#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) -#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) -#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) -#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) -#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) -#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) -#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) -#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) -#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) -#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) -#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) -#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) -#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) -#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) -#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) -#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) -#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) -#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) -#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) -#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) -#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) -#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) -#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) -#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) -#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) -#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) -#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) -#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) -#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) -#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) -#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) -#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) -#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) -#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) -#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) -#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) -#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) -#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) -#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) -#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) -#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) -#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) -#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) -#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) -#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) -#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) -#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) -#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) -#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) -#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) -#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) -#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) -#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) -#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) -#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) -#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) -#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) -#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) -#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) -#define VSIQF_HKEY_MAX_INDEX 12 +#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, 30) +#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) +#define QRXFLXP_CNTXT_RXDID_IDX_S 0 +#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, 0) +#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 +#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, 8) +#define GLGEN_RSTAT 0x000B8188 +#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0) +#define GLGEN_RSTCTL 0x000B8180 +#define GLGEN_RSTCTL_GRSTDEL_S 0 +#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) +#define GLGEN_RSTAT_RESET_TYPE_S 2 +#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, 2) +#define GLGEN_RTRIG 0x000B8190 +#define GLGEN_RTRIG_CORER_M BIT(0) +#define GLGEN_RTRIG_GLOBR_M BIT(1) +#define GLGEN_STAT 0x000B612C +#define PFGEN_CTRL 0x00091000 +#define PFGEN_CTRL_PFSWR_M BIT(0) +#define PFGEN_STATE 0x00088000 +#define PRTGEN_STATUS 0x000B8100 +#define PFHMC_ERRORDATA 0x00520500 +#define PFHMC_ERRORINFO 0x00520400 +#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) +#define GLINT_DYN_CTL_INTENA_M BIT(0) +#define GLINT_DYN_CTL_CLEARPBA_M BIT(1) +#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(2) +#define GLINT_DYN_CTL_ITR_INDX_S 3 +#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) +#define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) +#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) +#define PFINT_FW_CTL 0x0016C800 +#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_FW_CTL_ITR_INDX_S 11 +#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_FW_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR 0x0016CA00 +#define PFINT_OICR_ECC_ERR_M BIT(16) +#define PFINT_OICR_MAL_DETECT_M BIT(19) +#define PFINT_OICR_GRST_M BIT(20) +#define PFINT_OICR_PCI_EXCEPTION_M BIT(21) +#define PFINT_OICR_HMC_ERR_M BIT(26) +#define PFINT_OICR_PE_CRITERR_M BIT(28) +#define PFINT_OICR_CTL 0x0016CA80 +#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_OICR_CTL_ITR_INDX_S 11 +#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR_ENA 0x0016C900 +#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) +#define QINT_RQCTL_MSIX_INDX_S 0 +#define QINT_RQCTL_ITR_INDX_S 11 +#define QINT_RQCTL_CAUSE_ENA_M BIT(30) +#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) +#define QINT_TQCTL_MSIX_INDX_S 0 +#define QINT_TQCTL_ITR_INDX_S 11 +#define QINT_TQCTL_CAUSE_ENA_M BIT(30) +#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) +#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) +#define QRX_CTRL_MAX_INDEX 2047 +#define QRX_CTRL_QENA_REQ_S 0 +#define QRX_CTRL_QENA_REQ_M BIT(0) +#define QRX_CTRL_QENA_STAT_S 2 +#define QRX_CTRL_QENA_STAT_M BIT(2) +#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) +#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) +#define GLNVM_FLA 0x000B6108 +#define GLNVM_FLA_LOCKED_M BIT(6) +#define GLNVM_GENS 0x000B6100 +#define GLNVM_GENS_SR_SIZE_S 5 +#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5) +#define GLNVM_ULD 0x000B6008 +#define GLNVM_ULD_CORER_DONE_M BIT(3) +#define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define PF_FUNC_RID 0x0009E880 +#define PF_FUNC_RID_FUNC_NUM_S 0 +#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) +#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) +#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) +#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) +#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) +#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) +#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) +#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) +#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) +#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) +#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) +#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) +#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) +#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) +#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) +#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) +#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) +#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) +#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) +#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) +#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) +#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) +#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) +#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) +#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) +#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) +#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) +#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) +#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) +#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) +#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) +#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) +#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) +#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) +#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) +#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) +#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) +#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) +#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) +#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) +#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) +#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) +#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) +#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) +#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) +#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) +#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) +#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) +#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) +#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) +#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) +#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) +#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) +#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) +#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) +#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) +#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) +#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) +#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) +#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) +#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) +#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) +#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) +#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) +#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) +#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) +#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) +#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) +#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) +#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) +#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) +#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) +#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) +#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) +#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) +#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) +#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) +#define VSIQF_HKEY_MAX_INDEX 12 #endif /* _ICE_HW_AUTOGEN_H_ */ From b3969fd727aa1f2ace4794f2a180f9769128027c Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Thu, 9 Aug 2018 06:29:53 -0700 Subject: [PATCH 10/15] ice: Add support for Tx hang, Tx timeout and malicious driver detection When a malicious operation is detected, the firmware triggers an interrupt, which is then picked up by the service task (specifically by ice_handle_mdd_event). A reset is scheduled if required. Tx hang detection works in a similar way, except the logic here monitors the VSI's Tx queues and tries to revive them if stalled. If the hang is not resolved, the kernel eventually calls ndo_tx_timeout, which is handled by ice_tx_timeout. Signed-off-by: Sudheer Mogilappagari Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 4 + .../net/ethernet/intel/ice/ice_hw_autogen.h | 39 +++ drivers/net/ethernet/intel/ice/ice_main.c | 286 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_txrx.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx.h | 1 + 5 files changed, 331 insertions(+) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index e17030db0bee..6f44a850c4b2 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -134,6 +134,7 @@ enum ice_state { __ICE_SUSPENDED, /* set on module remove path */ __ICE_RESET_FAILED, /* set by reset/rebuild */ __ICE_ADMINQ_EVENT_PENDING, + __ICE_MDD_EVENT_PENDING, __ICE_FLTR_OVERFLOW_PROMISC, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, @@ -272,6 +273,9 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded; /* has previous stats been loaded */ + u32 tx_timeout_count; + unsigned long tx_timeout_last_recovery; + u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; }; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 067ca26a1d94..88f11498804b 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -123,6 +123,45 @@ #define QRX_CTRL_QENA_STAT_M BIT(2) #define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) #define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) +#define QRX_TAIL_MAX_INDEX 2047 +#define QRX_TAIL_TAIL_S 0 +#define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0) +#define GL_MDET_RX 0x00294C00 +#define GL_MDET_RX_QNUM_S 0 +#define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_RX_VF_NUM_S 15 +#define GL_MDET_RX_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_RX_PF_NUM_S 23 +#define GL_MDET_RX_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_RX_MAL_TYPE_S 26 +#define GL_MDET_RX_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_RX_VALID_M BIT(31) +#define GL_MDET_TX_PQM 0x002D2E00 +#define GL_MDET_TX_PQM_PF_NUM_S 0 +#define GL_MDET_TX_PQM_PF_NUM_M ICE_M(0x7, 0) +#define GL_MDET_TX_PQM_VF_NUM_S 4 +#define GL_MDET_TX_PQM_VF_NUM_M ICE_M(0xFF, 4) +#define GL_MDET_TX_PQM_QNUM_S 12 +#define GL_MDET_TX_PQM_QNUM_M ICE_M(0x3FFF, 12) +#define GL_MDET_TX_PQM_MAL_TYPE_S 26 +#define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_PQM_VALID_M BIT(31) +#define GL_MDET_TX_TCLAN 0x000FC068 +#define GL_MDET_TX_TCLAN_QNUM_S 0 +#define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_TX_TCLAN_VF_NUM_S 15 +#define GL_MDET_TX_TCLAN_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_TX_TCLAN_PF_NUM_S 23 +#define GL_MDET_TX_TCLAN_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_TX_TCLAN_MAL_TYPE_S 26 +#define GL_MDET_TX_TCLAN_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_TCLAN_VALID_M BIT(31) +#define PF_MDET_RX 0x00294280 +#define PF_MDET_RX_VALID_M BIT(0) +#define PF_MDET_TX_PQM 0x002D2C80 +#define PF_MDET_TX_PQM_VALID_M BIT(0) +#define PF_MDET_TX_TCLAN 0x000FC000 +#define PF_MDET_TX_TCLAN_VALID_M BIT(0) #define GLNVM_FLA 0x000B6108 #define GLNVM_FLA_LOCKED_M BIT(6) #define GLNVM_GENS 0x000B6100 diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1ef63bf98cd8..fccecb6fa618 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -36,6 +36,81 @@ static void ice_vsi_release_all(struct ice_pf *pf); static void ice_update_vsi_stats(struct ice_vsi *vsi); static void ice_update_pf_stats(struct ice_pf *pf); +/** + * ice_get_tx_pending - returns number of Tx descriptors not processed + * @ring: the ring of descriptors + */ +static u32 ice_get_tx_pending(struct ice_ring *ring) +{ + u32 head, tail; + + head = ring->next_to_clean; + tail = readl(ring->tail); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + return 0; +} + +/** + * ice_check_for_hang_subtask - check for and recover hung queues + * @pf: pointer to PF struct + */ +static void ice_check_for_hang_subtask(struct ice_pf *pf) +{ + struct ice_vsi *vsi = NULL; + unsigned int i; + u32 v, v_idx; + int packets; + + ice_for_each_vsi(pf, v) + if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) { + vsi = pf->vsi[v]; + break; + } + + if (!vsi || test_bit(__ICE_DOWN, vsi->state)) + return; + + if (!(vsi->netdev && netif_carrier_ok(vsi->netdev))) + return; + + for (i = 0; i < vsi->num_txq; i++) { + struct ice_ring *tx_ring = vsi->tx_rings[i]; + + if (tx_ring && tx_ring->desc) { + int itr = ICE_ITR_NONE; + + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.pkts & INT_MAX; + if (tx_ring->tx_stats.prev_pkt == packets) { + /* Trigger sw interrupt to revive the queue */ + v_idx = tx_ring->q_vector->v_idx; + wr32(&vsi->back->hw, + GLINT_DYN_CTL(vsi->base_vector + v_idx), + (itr << GLINT_DYN_CTL_ITR_INDX_S) | + GLINT_DYN_CTL_SWINT_TRIG_M | + GLINT_DYN_CTL_INTENA_MSK_M); + continue; + } + + /* Memory barrier between read of packet count and call + * to ice_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt = + ice_get_tx_pending(tx_ring) ? packets : -1; + } + } +} + /** * ice_get_free_slot - get the next non-NULL location index in array * @array: array to search @@ -1003,6 +1078,114 @@ static void ice_service_timer(struct timer_list *t) ice_service_task_schedule(pf); } +/** + * ice_handle_mdd_event - handle malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from service task. OICR interrupt handler indicates MDD event + */ +static void ice_handle_mdd_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + bool mdd_detected = false; + u32 reg; + + if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state)) + return; + + /* find what triggered the MDD event */ + reg = rd32(hw, GL_MDET_TX_PQM); + if (reg & GL_MDET_TX_PQM_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> + GL_MDET_TX_PQM_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >> + GL_MDET_TX_PQM_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >> + GL_MDET_TX_PQM_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >> + GL_MDET_TX_PQM_QNUM_S); + + if (netif_msg_tx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_PQM, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_TX_TCLAN); + if (reg & GL_MDET_TX_TCLAN_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> + GL_MDET_TX_TCLAN_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >> + GL_MDET_TX_TCLAN_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >> + GL_MDET_TX_TCLAN_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> + GL_MDET_TX_TCLAN_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_RX); + if (reg & GL_MDET_RX_VALID_M) { + u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >> + GL_MDET_RX_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >> + GL_MDET_RX_VF_NUM_S; + u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >> + GL_MDET_RX_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_RX_QNUM_M) >> + GL_MDET_RX_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_RX, 0xffffffff); + mdd_detected = true; + } + + if (mdd_detected) { + bool pf_mdd_detected = false; + + reg = rd32(hw, PF_MDET_TX_PQM); + if (reg & PF_MDET_TX_PQM_VALID_M) { + wr32(hw, PF_MDET_TX_PQM, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_TX_TCLAN); + if (reg & PF_MDET_TX_TCLAN_VALID_M) { + wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_RX); + if (reg & PF_MDET_RX_VALID_M) { + wr32(hw, PF_MDET_RX, 0xFFFF); + dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + /* Queue belongs to the PF initiate a reset */ + if (pf_mdd_detected) { + set_bit(__ICE_NEEDS_RESTART, pf->state); + ice_service_task_schedule(pf); + } + } + + /* re-enable MDD interrupt cause */ + clear_bit(__ICE_MDD_EVENT_PENDING, pf->state); + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_MAL_DETECT_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -1025,7 +1208,9 @@ static void ice_service_task(struct work_struct *work) return; } + ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); + ice_handle_mdd_event(pf); ice_watchdog_subtask(pf); ice_clean_adminq_subtask(pf); @@ -1037,6 +1222,7 @@ static void ice_service_task(struct work_struct *work) * schedule the service task now. */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || + test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -1747,8 +1933,14 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); + if (oicr & PFINT_OICR_MAL_DETECT_M) { + ena_mask &= ~PFINT_OICR_MAL_DETECT_M; + set_bit(__ICE_MDD_EVENT_PENDING, pf->state); + } + if (oicr & PFINT_OICR_GRST_M) { u32 reset; + /* we have a reset warning */ ena_mask &= ~PFINT_OICR_GRST_M; reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >> @@ -5503,6 +5695,99 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) return 0; } +/** + * ice_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + */ +static void ice_tx_timeout(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_ring *tx_ring = NULL; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u32 head, val = 0, i; + int hung_queue = -1; + + pf->tx_timeout_count++; + + /* find the stopped queue the same way the stack does */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + unsigned long trans_start; + + q = netdev_get_tx_queue(netdev, i); + trans_start = q->trans_start; + if (netif_xmit_stopped(q) && + time_after(jiffies, + (trans_start + netdev->watchdog_timeo))) { + hung_queue = i; + break; + } + } + + if (i == netdev->num_tx_queues) { + netdev_info(netdev, "tx_timeout: no netdev hung queue found\n"); + } else { + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_txq; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (hung_queue == + vsi->tx_rings[i]->q_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + } + + /* Reset recovery level if enough time has elapsed after last timeout. + * Also ensure no new reset action happens before next timeout period. + */ + if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ * 20))) + pf->tx_timeout_recovery_level = 1; + else if (time_before(jiffies, (pf->tx_timeout_last_recovery + + netdev->watchdog_timeo))) + return; + + if (tx_ring) { + head = tx_ring->next_to_clean; + /* Read interrupt register */ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + val = rd32(&pf->hw, + GLINT_DYN_CTL(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + + netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + vsi->vsi_num, hung_queue, tx_ring->next_to_clean, + head, tx_ring->next_to_use, + readl(tx_ring->tail), val); + } + + pf->tx_timeout_last_recovery = jiffies; + netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n", + pf->tx_timeout_recovery_level, hung_queue); + + switch (pf->tx_timeout_recovery_level) { + case 1: + set_bit(__ICE_PFR_REQ, pf->state); + break; + case 2: + set_bit(__ICE_CORER_REQ, pf->state); + break; + case 3: + set_bit(__ICE_GLOBR_REQ, pf->state); + break; + default: + netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n"); + set_bit(__ICE_DOWN, pf->state); + set_bit(__ICE_NEEDS_RESTART, vsi->state); + break; + } + + ice_service_task_schedule(pf); + pf->tx_timeout_recovery_level++; +} + /** * ice_open - Called when a network interface becomes active * @netdev: network interface device structure @@ -5624,4 +5909,5 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_set_features = ice_set_features, .ndo_fdb_add = ice_fdb_add, .ndo_fdb_del = ice_fdb_del, + .ndo_tx_timeout = ice_tx_timeout, }; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 6481e3d86374..5dae968d853e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -251,6 +251,7 @@ int ice_setup_tx_ring(struct ice_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt = -1; return 0; err: diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 31bc998fe200..839fd9ff6043 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -71,6 +71,7 @@ struct ice_txq_stats { u64 restart_q; u64 tx_busy; u64 tx_linearize; + int prev_pkt; /* negative if no pending Tx descriptors */ }; struct ice_rxq_stats { From b1edc14a3fbfe0154a2aecb8bb9775c3012cb6e2 Mon Sep 17 00:00:00 2001 From: Md Fahad Iqbal Polash Date: Thu, 9 Aug 2018 06:29:54 -0700 Subject: [PATCH 11/15] ice: Implement ice_bridge_getlink and ice_bridge_setlink ice_bridge_getlink returns the current bridge mode using ndo_dflt_bridge_getlink and the mode parameter available in first_switch->bridge_mode. ice_bridge_setlink is invoked when the bridge mode needs to changed. The value to be changed to is available as a netlink message which is parsed in this function. If the mode has to be changed, switch_flags is set appropriately (set ALLOW_LB for VEB mode and clear it for VEPA mode) and ice_aq_update_vsi is called. Also change the unicast switch filter rules. Signed-off-by: Md Fahad Iqbal Polash Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_main.c | 140 +++++++++++++++++++- drivers/net/ethernet/intel/ice/ice_switch.c | 41 ++++++ drivers/net/ethernet/intel/ice/ice_switch.h | 1 + 3 files changed, 181 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index fccecb6fa618..cbeae1355593 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3599,7 +3599,11 @@ static int ice_probe(struct pci_dev *pdev, goto err_msix_misc_unroll; } - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + if (hw->evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; + pf->first_sw->pf = pf; /* record the sw_id available for later use */ @@ -5695,6 +5699,138 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) return 0; } +/** + * ice_bridge_getlink - Get the hardware bridge mode + * @skb: skb buff + * @pid: process id + * @seq: RTNL message seq + * @dev: the netdev being configured + * @filter_mask: filter mask passed in + * @nlflags: netlink flags passed in + * + * Return the bridge mode (VEB/VEPA) + */ +static int +ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, int nlflags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u16 bmode; + + bmode = pf->first_sw->bridge_mode; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bmode, 0, 0, nlflags, + filter_mask, NULL); +} + +/** + * ice_vsi_update_bridge_mode - Update VSI for switching bridge mode (VEB/VEPA) + * @vsi: Pointer to VSI structure + * @bmode: Hardware bridge mode (VEB/VEPA) + * + * Returns 0 on success, negative on failure + */ +static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_aqc_vsi_props *vsi_props; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + vsi_props = &vsi->info; + ctxt.info = vsi->info; + + if (bmode == BRIDGE_MODE_VEB) + /* change from VEPA to VEB mode */ + ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + else + /* change from VEB to VEPA mode */ + ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + ctxt.vsi_num = vsi->vsi_num; + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + status = ice_aq_update_vsi(hw, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", + bmode, status, hw->adminq.sq_last_status); + return -EIO; + } + /* Update sw flags for book keeping */ + vsi_props->sw_flags = ctxt.info.sw_flags; + + return 0; +} + +/** + * ice_bridge_setlink - Set the hardware bridge mode + * @dev: the netdev being configured + * @nlh: RTNL message + * @flags: bridge setlink flags + * + * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is + * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if + * not already set for all VSIs connected to this switch. And also update the + * unicast switch filter rules for the corresponding switch of the netdev. + */ +static int +ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 __always_unused flags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_pf *pf = np->vsi->back; + struct nlattr *attr, *br_spec; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + struct ice_sw *pf_sw; + int rem, v, err = 0; + + pf_sw = pf->first_sw; + /* find the attribute in the netlink message */ + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + + nla_for_each_nested(attr, br_spec, rem) { + __u16 mode; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + mode = nla_get_u16(attr); + if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) + return -EINVAL; + /* Continue if bridge mode is not being flipped */ + if (mode == pf_sw->bridge_mode) + continue; + /* Iterates through the PF VSI list and update the loopback + * mode of the VSI + */ + ice_for_each_vsi(pf, v) { + if (!pf->vsi[v]) + continue; + err = ice_vsi_update_bridge_mode(pf->vsi[v], mode); + if (err) + return err; + } + + hw->evb_veb = (mode == BRIDGE_MODE_VEB); + /* Update the unicast switch filter rules for the corresponding + * switch of the netdev + */ + status = ice_update_sw_rule_bridge_mode(hw); + if (status) { + netdev_err(dev, "update SW_RULE for bridge mode failed, = %d err %d aq_err %d\n", + mode, status, hw->adminq.sq_last_status); + /* revert hw->evb_veb */ + hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); + return -EIO; + } + + pf_sw->bridge_mode = mode; + } + + return 0; +} + /** * ice_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure @@ -5907,6 +6043,8 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, .ndo_set_features = ice_set_features, + .ndo_bridge_getlink = ice_bridge_getlink, + .ndo_bridge_setlink = ice_bridge_setlink, .ndo_fdb_add = ice_fdb_add, .ndo_fdb_del = ice_fdb_del, .ndo_tx_timeout = ice_tx_timeout, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index ac66c96a123d..65b4e1cca6be 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1130,6 +1130,47 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) return status; } +/** + * ice_update_sw_rule_bridge_mode + * @hw: pointer to the hw struct + * + * Updates unicast switch filter rules based on VEB/VEPA mode + */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; + struct list_head *rule_head; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; + + mutex_lock(rule_lock); + list_for_each_entry(fm_entry, rule_head, list_entry) { + struct ice_fltr_info *fi = &fm_entry->fltr_info; + u8 *addr = fi->l_data.mac.mac_addr; + + /* Update unicast Tx rules to reflect the selected + * VEB/VEPA mode + */ + if ((fi->flag & ICE_FLTR_TX) && is_unicast_ether_addr(addr) && + (fi->fltr_act == ICE_FWD_TO_VSI || + fi->fltr_act == ICE_FWD_TO_VSI_LIST || + fi->fltr_act == ICE_FWD_TO_Q || + fi->fltr_act == ICE_FWD_TO_QGRP)) { + status = ice_update_pkt_fwd_rule(hw, fi); + if (status) + break; + } + } + + mutex_unlock(rule_lock); + + return status; +} + /** * ice_add_update_vsi_list * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 11a481644dac..646389ca1238 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -169,6 +169,7 @@ ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id); From 8b97ceb1dc0f29d6af0cd85983041a9fbac8e14c Mon Sep 17 00:00:00 2001 From: Hieu Tran Date: Thu, 9 Aug 2018 06:29:55 -0700 Subject: [PATCH 12/15] ice: Enable firmware logging during device initialization. To enable FW logging, the "cq_en" and "uart_en" enable bits of the "fw_log" element in struct ice_hw need to set accordingly based on some user-provided parameters during driver loading. To select which FW log events to be emitted, the "cfg" elements of corresponding FW modules in the "evnts" array member of "fw_log" need to be configured. Signed-off-by: Hieu Tran Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- .../net/ethernet/intel/ice/ice_adminq_cmd.h | 83 ++++++++ drivers/net/ethernet/intel/ice/ice_common.c | 182 +++++++++++++++++- drivers/net/ethernet/intel/ice/ice_common.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 3 + drivers/net/ethernet/intel/ice/ice_type.h | 19 ++ 5 files changed, 286 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 3dadb2b01b5c..f8dfd675486c 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1206,6 +1206,84 @@ struct ice_aqc_dis_txq { struct ice_aqc_dis_txq_item qgrps[1]; }; +/* Configure Firmware Logging Command (indirect 0xFF09) + * Logging Information Read Response (indirect 0xFF10) + * Note: The 0xFF10 command has no input parameters. + */ +struct ice_aqc_fw_logging { + u8 log_ctrl; +#define ICE_AQC_FW_LOG_AQ_EN BIT(0) +#define ICE_AQC_FW_LOG_UART_EN BIT(1) + u8 rsvd0; + u8 log_ctrl_valid; /* Not used by 0xFF10 Response */ +#define ICE_AQC_FW_LOG_AQ_VALID BIT(0) +#define ICE_AQC_FW_LOG_UART_VALID BIT(1) + u8 rsvd1[5]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_fw_logging_mod { + ICE_AQC_FW_LOG_ID_GENERAL = 0, + ICE_AQC_FW_LOG_ID_CTRL, + ICE_AQC_FW_LOG_ID_LINK, + ICE_AQC_FW_LOG_ID_LINK_TOPO, + ICE_AQC_FW_LOG_ID_DNL, + ICE_AQC_FW_LOG_ID_I2C, + ICE_AQC_FW_LOG_ID_SDP, + ICE_AQC_FW_LOG_ID_MDIO, + ICE_AQC_FW_LOG_ID_ADMINQ, + ICE_AQC_FW_LOG_ID_HDMA, + ICE_AQC_FW_LOG_ID_LLDP, + ICE_AQC_FW_LOG_ID_DCBX, + ICE_AQC_FW_LOG_ID_DCB, + ICE_AQC_FW_LOG_ID_NETPROXY, + ICE_AQC_FW_LOG_ID_NVM, + ICE_AQC_FW_LOG_ID_AUTH, + ICE_AQC_FW_LOG_ID_VPD, + ICE_AQC_FW_LOG_ID_IOSF, + ICE_AQC_FW_LOG_ID_PARSER, + ICE_AQC_FW_LOG_ID_SW, + ICE_AQC_FW_LOG_ID_SCHEDULER, + ICE_AQC_FW_LOG_ID_TXQ, + ICE_AQC_FW_LOG_ID_RSVD, + ICE_AQC_FW_LOG_ID_POST, + ICE_AQC_FW_LOG_ID_WATCHDOG, + ICE_AQC_FW_LOG_ID_TASK_DISPATCH, + ICE_AQC_FW_LOG_ID_MNG, + ICE_AQC_FW_LOG_ID_MAX, +}; + +/* This is the buffer for both of the logging commands. + * The entry array size depends on the datalen parameter in the descriptor. + * There will be a total of datalen / 2 entries. + */ +struct ice_aqc_fw_logging_data { + __le16 entry[1]; +#define ICE_AQC_FW_LOG_ID_S 0 +#define ICE_AQC_FW_LOG_ID_M (0xFFF << ICE_AQC_FW_LOG_ID_S) + +#define ICE_AQC_FW_LOG_CONF_SUCCESS 0 /* Used by response */ +#define ICE_AQC_FW_LOG_CONF_BAD_INDX BIT(12) /* Used by response */ + +#define ICE_AQC_FW_LOG_EN_S 12 +#define ICE_AQC_FW_LOG_EN_M (0xF << ICE_AQC_FW_LOG_EN_S) +#define ICE_AQC_FW_LOG_INFO_EN BIT(12) /* Used by command */ +#define ICE_AQC_FW_LOG_INIT_EN BIT(13) /* Used by command */ +#define ICE_AQC_FW_LOG_FLOW_EN BIT(14) /* Used by command */ +#define ICE_AQC_FW_LOG_ERR_EN BIT(15) /* Used by command */ +}; + +/* Get/Clear FW Log (indirect 0xFF11) */ +struct ice_aqc_get_clear_fw_log { + u8 flags; +#define ICE_AQC_FW_LOG_CLEAR BIT(0) +#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL BIT(1) + u8 rsvd1[7]; + __le32 addr_high; + __le32 addr_low; +}; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -1256,6 +1334,8 @@ struct ice_aq_desc { struct ice_aqc_dis_txqs dis_txqs; struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; + struct ice_aqc_fw_logging fw_logging; + struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; struct ice_aqc_get_link_status get_link_status; @@ -1353,6 +1433,9 @@ enum ice_adminq_opc { /* TX queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + + /* debug commands */ + ice_aqc_opc_fw_logging = 0xFF09, }; #endif /* _ICE_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 52c2bf4f108e..0847dbf9d42f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -427,6 +427,176 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) devm_kfree(ice_hw_to_dev(hw), sw); } +#define ICE_FW_LOG_DESC_SIZE(n) (sizeof(struct ice_aqc_fw_logging_data) + \ + (((n) - 1) * sizeof(((struct ice_aqc_fw_logging_data *)0)->entry))) +#define ICE_FW_LOG_DESC_SIZE_MAX \ + ICE_FW_LOG_DESC_SIZE(ICE_AQC_FW_LOG_ID_MAX) + +/** + * ice_cfg_fw_log - configure FW logging + * @hw: pointer to the hw struct + * @enable: enable certain FW logging events if true, disable all if false + * + * This function enables/disables the FW logging via Rx CQ events and a UART + * port based on predetermined configurations. FW logging via the Rx CQ can be + * enabled/disabled for individual PF's. However, FW logging via the UART can + * only be enabled/disabled for all PFs on the same device. + * + * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in + * hw->fw_log need to be set accordingly, e.g. based on user-provided input, + * before initializing the device. + * + * When re/configuring FW logging, callers need to update the "cfg" elements of + * the hw->fw_log.evnts array with the desired logging event configurations for + * modules of interest. When disabling FW logging completely, the callers can + * just pass false in the "enable" parameter. On completion, the function will + * update the "cur" element of the hw->fw_log.evnts array with the resulting + * logging event configurations of the modules that are being re/configured. FW + * logging modules that are not part of a reconfiguration operation retain their + * previous states. + * + * Before resetting the device, it is recommended that the driver disables FW + * logging before shutting down the control queue. When disabling FW logging + * ("enable" = false), the latest configurations of FW logging events stored in + * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after + * a device reset. + * + * When enabling FW logging to emit log messages via the Rx CQ during the + * device's initialization phase, a mechanism alternative to interrupt handlers + * needs to be used to extract FW log messages from the Rx CQ periodically and + * to prevent the Rx CQ from being full and stalling other types of control + * messages from FW to SW. Interrupts are typically disabled during the device's + * initialization phase. + */ +static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) +{ + struct ice_aqc_fw_logging_data *data = NULL; + struct ice_aqc_fw_logging *cmd; + enum ice_status status = 0; + u16 i, chgs = 0, len = 0; + struct ice_aq_desc desc; + u8 actv_evnts = 0; + void *buf = NULL; + + if (!hw->fw_log.cq_en && !hw->fw_log.uart_en) + return 0; + + /* Disable FW logging only when the control queue is still responsive */ + if (!enable && + (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq))) + return 0; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging); + cmd = &desc.params.fw_logging; + + /* Indicate which controls are valid */ + if (hw->fw_log.cq_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID; + + if (hw->fw_log.uart_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID; + + if (enable) { + /* Fill in an array of entries with FW logging modules and + * logging events being reconfigured. + */ + for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { + u16 val; + + /* Keep track of enabled event types */ + actv_evnts |= hw->fw_log.evnts[i].cfg; + + if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur) + continue; + + if (!data) { + data = devm_kzalloc(ice_hw_to_dev(hw), + ICE_FW_LOG_DESC_SIZE_MAX, + GFP_KERNEL); + if (!data) + return ICE_ERR_NO_MEMORY; + } + + val = i << ICE_AQC_FW_LOG_ID_S; + val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S; + data->entry[chgs++] = cpu_to_le16(val); + } + + /* Only enable FW logging if at least one module is specified. + * If FW logging is currently enabled but all modules are not + * enabled to emit log messages, disable FW logging altogether. + */ + if (actv_evnts) { + /* Leave if there is effectively no change */ + if (!chgs) + goto out; + + if (hw->fw_log.cq_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN; + + if (hw->fw_log.uart_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN; + + buf = data; + len = ICE_FW_LOG_DESC_SIZE(chgs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } + } + + status = ice_aq_send_cmd(hw, &desc, buf, len, NULL); + if (!status) { + /* Update the current configuration to reflect events enabled. + * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW + * logging mode is enabled for the device. They do not reflect + * actual modules being enabled to emit log messages. So, their + * values remain unchanged even when all modules are disabled. + */ + u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX; + + hw->fw_log.actv_evnts = actv_evnts; + for (i = 0; i < cnt; i++) { + u16 v, m; + + if (!enable) { + /* When disabling all FW logging events as part + * of device's de-initialization, the original + * configurations are retained, and can be used + * to reconfigure FW logging later if the device + * is re-initialized. + */ + hw->fw_log.evnts[i].cur = 0; + continue; + } + + v = le16_to_cpu(data->entry[i]); + m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S; + hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg; + } + } + +out: + if (data) + devm_kfree(ice_hw_to_dev(hw), data); + + return status; +} + +/** + * ice_output_fw_log + * @hw: pointer to the hw struct + * @desc: pointer to the AQ message descriptor + * @buf: pointer to the buffer accompanying the AQ message + * + * Formats a FW Log message and outputs it via the standard driver logs. + */ +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) +{ + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg Start ]\n"); + ice_debug_array(hw, ICE_DBG_AQ_MSG, 16, 1, (u8 *)buf, + le16_to_cpu(desc->datalen)); + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg End ]\n"); +} + /** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure @@ -461,6 +631,11 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_cqinit; + /* Enable FW logging. Not fatal if this fails. */ + status = ice_cfg_fw_log(hw, true); + if (status) + ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n"); + status = ice_clear_pf_cfg(hw); if (status) goto err_unroll_cqinit; @@ -574,15 +749,18 @@ err_unroll_cqinit: */ void ice_deinit_hw(struct ice_hw *hw) { + ice_cleanup_fltr_mgmt_struct(hw); + ice_sched_cleanup_all(hw); - ice_shutdown_all_ctrlq(hw); if (hw->port_info) { devm_kfree(ice_hw_to_dev(hw), hw->port_info); hw->port_info = NULL; } - ice_cleanup_fltr_mgmt_struct(hw); + /* Attempt to disable FW logging before shutting down control queues */ + ice_cfg_fw_log(hw, false); + ice_shutdown_all_ctrlq(hw); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 409b9957f407..aac2d6cadaaf 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -95,4 +95,5 @@ enum ice_status ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index cbeae1355593..f04e124bca8c 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -984,6 +984,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) dev_err(&pf->pdev->dev, "Could not handle link event\n"); break; + case ice_aqc_opc_fw_logging: + ice_output_fw_log(hw, &event.desc, event.msg_buf); + break; default: dev_dbg(&pf->pdev->dev, "%s Receive Queue unknown event 0x%04x ignored\n", diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 8b7efa87ce56..e681804be4d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -258,6 +258,24 @@ struct ice_switch_info { struct ice_sw_recipe *recp_list; }; +/* FW logging configuration */ +struct ice_fw_log_evnt { + u8 cfg : 4; /* New event enables to configure */ + u8 cur : 4; /* Current/active event enables */ +}; + +struct ice_fw_log_cfg { + u8 cq_en : 1; /* FW logging is enabled via the control queue */ + u8 uart_en : 1; /* FW logging is enabled via UART for all PFs */ + u8 actv_evnts; /* Cumulation of currently enabled log events */ + +#define ICE_FW_LOG_EVNT_INFO (ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_INIT (ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_FLOW (ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_ERR (ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S) + struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX]; +}; + /* Port hardware description */ struct ice_hw { u8 __iomem *hw_addr; @@ -307,6 +325,7 @@ struct ice_hw { u8 fw_patch; /* firmware patch version */ u32 fw_build; /* firmware build number */ + struct ice_fw_log_cfg fw_log; /* minimum allowed value for different speeds */ #define ICE_ITR_GRAN_MIN_200 1 #define ICE_ITR_GRAN_MIN_100 1 From 4f74dcc1b86d75d8ec5506195d6d892666f2285b Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Thu, 9 Aug 2018 06:29:56 -0700 Subject: [PATCH 13/15] ice: Enable VSI Rx/Tx pruning only when VLAN 0 is active VLAN pruning is not valid when VLAN 0 is not active. If VLAN pruning is enabled and VLAN 0 is not active (8021q driver not loaded) then normal, non-VLAN, traffic will not pass. TX/RX VLAN pruning is enabled when the VLAN 0 is added to the active_vlan bitmap and it is disabled when VLAN 0 is removed from the active_vlan bitmap. So, only enable VLAN pruning when VLAN 0 is active. Setting RX VLAN pruning causes the switch to drop received VLAN packets when there are no matching VLAN ids in the associated VSI's switch filters. Setting TX pruning makes it so the switch will not send out any packets with VLAN tags that don't match the associated VSI's switch filters. With this patch, if the VF or PF tries to send a VLAN tagged packet with a VLAN tag that it does not have a pruning rule for it will trigger an MDD event. For example, if PF0 has VLAN10 and VLAN11 interfaces and scapy is used to send a packet with VLAN8 then the MDD is triggered. Also make ice_vsi_kill_vlan return a value which the caller can check before updating VLAN related data structures (counts, pruning bits, etc.). Signed-off-by: Brett Creeley Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_main.c | 94 ++++++++++++++++++++--- 1 file changed, 85 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f04e124bca8c..46d8e2275647 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -349,6 +349,63 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) test_bit(ICE_VSI_FLAG_VLAN_FLTR_CHANGED, vsi->flags); } +/** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct device *dev; + int status; + + if (!vsi) + return -EINVAL; + + dev = &vsi->back->pdev->dev; + ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) { + ctxt->info.sec_flags |= + ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } else { + ctxt->info.sec_flags &= + ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + ctxt->vsi_num = vsi->vsi_num; + status = ice_aq_update_vsi(&vsi->back->hw, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI %d failed, err = %d, aq_err = %d\n", + ena ? "Ena" : "Dis", vsi->vsi_num, status, + vsi->back->hw.adminq.sq_last_status); + goto err_out; + } + + vsi->info.sec_flags = ctxt->info.sec_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + devm_kfree(dev, ctxt); + return 0; + +err_out: + devm_kfree(dev, ctxt); + return -EIO; +} + /** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI @@ -3126,7 +3183,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret = 0; + int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -3137,6 +3194,13 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, if (vsi->info.pvid) return -EINVAL; + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) { + ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) + return ret; + } + /* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch @@ -3153,16 +3217,19 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN * @vsi: the VSI being configured * @vid: VLAN id to be removed + * + * Returns 0 on success and negative on failure */ -static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) +static int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) { struct ice_fltr_list_entry *list; struct ice_pf *pf = vsi->back; LIST_HEAD(tmp_add_list); + int status = 0; list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); if (!list) - return; + return -ENOMEM; list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; list->fltr_info.fwd_id.vsi_id = vsi->vsi_num; @@ -3174,11 +3241,14 @@ static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) INIT_LIST_HEAD(&list->list_entry); list_add(&list->list_entry, &tmp_add_list); - if (ice_remove_vlan(&pf->hw, &tmp_add_list)) + if (ice_remove_vlan(&pf->hw, &tmp_add_list)) { dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", vid, vsi->vsi_num); + status = -EIO; + } ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; } /** @@ -3194,19 +3264,25 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + int status; if (vsi->info.pvid) return -EINVAL; - /* return code is ignored as there is nothing a user - * can do about failure to remove and a log message was - * already printed from the other function + /* Make sure ice_vsi_kill_vlan is successful before updating VLAN + * information */ - ice_vsi_kill_vlan(vsi, vid); + status = ice_vsi_kill_vlan(vsi, vid); + if (status) + return status; clear_bit(vid, vsi->active_vlans); - return 0; + /* Disable VLAN pruning when VLAN 0 is removed */ + if (unlikely(!vid)) + status = ice_cfg_vlan_pruning(vsi, false); + + return status; } /** From 8d81fa55bac0c730d59e990db099ebecd82d7880 Mon Sep 17 00:00:00 2001 From: Akeem G Abodunrin Date: Thu, 9 Aug 2018 06:29:57 -0700 Subject: [PATCH 14/15] ice: Introduce SERVICE_DIS flag and service routine functions This patch introduces SERVICE_DIS flag to use for stopping service task. This flag will be checked before scheduling new tasks. Also add new functions ice_service_task_stop to stop service task. Signed-off-by: Akeem G Abodunrin Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 34 ++++++++++++++++++----- 2 files changed, 28 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 6f44a850c4b2..9cf233d085d8 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -138,6 +138,7 @@ enum ice_state { __ICE_FLTR_OVERFLOW_PROMISC, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, + __ICE_SERVICE_DIS, __ICE_STATE_NBITS /* must be last */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 46d8e2275647..b1c4dfbdeeb3 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1107,7 +1107,7 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) */ static void ice_service_task_schedule(struct ice_pf *pf) { - if (!test_bit(__ICE_DOWN, pf->state) && + if (!test_bit(__ICE_SERVICE_DIS, pf->state) && !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) && !test_bit(__ICE_NEEDS_RESTART, pf->state)) queue_work(ice_wq, &pf->serv_task); @@ -1126,6 +1126,22 @@ static void ice_service_task_complete(struct ice_pf *pf) clear_bit(__ICE_SERVICE_SCHED, pf->state); } +/** + * ice_service_task_stop - stop service task and cancel works + * @pf: board private structure + */ +static void ice_service_task_stop(struct ice_pf *pf) +{ + set_bit(__ICE_SERVICE_DIS, pf->state); + + if (pf->serv_tmr.function) + del_timer_sync(&pf->serv_tmr); + if (pf->serv_task.func) + cancel_work_sync(&pf->serv_task); + + clear_bit(__ICE_SERVICE_SCHED, pf->state); +} + /** * ice_service_timer - timer callback to schedule service task * @t: pointer to timer_list @@ -3389,10 +3405,7 @@ static void ice_determine_q_usage(struct ice_pf *pf) */ static void ice_deinit_pf(struct ice_pf *pf) { - if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); - if (pf->serv_task.func) - cancel_work_sync(&pf->serv_task); + ice_service_task_stop(pf); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->avail_q_mutex); } @@ -3599,6 +3612,8 @@ static int ice_probe(struct pci_dev *pdev, pf->pdev = pdev; pci_set_drvdata(pdev, pf); set_bit(__ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(__ICE_SERVICE_DIS, pf->state); hw = &pf->hw; hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; @@ -3656,6 +3671,9 @@ static int ice_probe(struct pci_dev *pdev, goto err_init_interrupt_unroll; } + /* Driver is mostly up */ + clear_bit(__ICE_DOWN, pf->state); + /* In case of MSIX we are going to setup the misc vector right here * to handle admin queue events etc. In case of legacy and MSI * the misc functionality and queue processing is combined in @@ -3695,8 +3713,7 @@ static int ice_probe(struct pci_dev *pdev, goto err_alloc_sw_unroll; } - /* Driver is mostly up */ - clear_bit(__ICE_DOWN, pf->state); + clear_bit(__ICE_SERVICE_DIS, pf->state); /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); @@ -3710,6 +3727,7 @@ static int ice_probe(struct pci_dev *pdev, return 0; err_alloc_sw_unroll: + set_bit(__ICE_SERVICE_DIS, pf->state); set_bit(__ICE_DOWN, pf->state); devm_kfree(&pf->pdev->dev, pf->first_sw); err_msix_misc_unroll: @@ -3737,6 +3755,7 @@ static void ice_remove(struct pci_dev *pdev) return; set_bit(__ICE_DOWN, pf->state); + ice_service_task_stop(pf); ice_vsi_release_all(pf); ice_free_irq_msix_misc(pf); @@ -5996,6 +6015,7 @@ static void ice_tx_timeout(struct net_device *netdev) netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n"); set_bit(__ICE_DOWN, pf->state); set_bit(__ICE_NEEDS_RESTART, vsi->state); + set_bit(__ICE_SERVICE_DIS, pf->state); break; } From 9ea47d81a7f17c6b77211ab75fbca2127719ad39 Mon Sep 17 00:00:00 2001 From: Anirudh Venkataramanan Date: Thu, 9 Aug 2018 06:29:58 -0700 Subject: [PATCH 15/15] ice: Fix and update driver version string Remove the "ice" prefix for the driver version string and bump version to 0.7.1-k. Signed-off-by: Anirudh Venkataramanan Tested-by: Tony Brelinski Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ice/ice_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b1c4dfbdeeb3..1b49a605d094 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7,7 +7,7 @@ #include "ice.h" -#define DRV_VERSION "ice-0.7.0-k" +#define DRV_VERSION "0.7.1-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY;