* [net-next 05/18] net/mlx5: DR, Expose an internal API to issue RDMA operations
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Inserting or deleting a rule is done by RDMA read/write operation to SW
ICM device memory. This file provides the support for executing these
operations. It includes allocating the needed resources and providing an
API for writing steering entries to the memory.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_send.c | 976 ++++++++++++++++++
1 file changed, 976 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
new file mode 100644
index 000000000000..ef0dea44f3b3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c
@@ -0,0 +1,976 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define QUEUE_SIZE 128
+#define SIGNAL_PER_DIV_QUEUE 16
+#define TH_NUMS_TO_DRAIN 2
+
+enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 };
+
+struct dr_data_seg {
+ u64 addr;
+ u32 length;
+ u32 lkey;
+ unsigned int send_flags;
+};
+
+struct postsend_info {
+ struct dr_data_seg write;
+ struct dr_data_seg read;
+ u64 remote_addr;
+ u32 rkey;
+};
+
+struct dr_qp_rtr_attr {
+ struct mlx5dr_cmd_gid_attr dgid_attr;
+ enum ib_mtu mtu;
+ u32 qp_num;
+ u16 port_num;
+ u8 min_rnr_timer;
+ u8 sgid_index;
+ u16 udp_src_port;
+};
+
+struct dr_qp_rts_attr {
+ u8 timeout;
+ u8 retry_cnt;
+ u8 rnr_retry;
+};
+
+struct dr_qp_init_attr {
+ u32 cqn;
+ u32 pdn;
+ u32 max_send_wr;
+ struct mlx5_uars_page *uar;
+};
+
+static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64)
+{
+ unsigned int idx;
+ u8 opcode;
+
+ opcode = get_cqe_opcode(cqe64);
+ if (opcode == MLX5_CQE_REQ_ERR) {
+ idx = be16_to_cpu(cqe64->wqe_counter) &
+ (dr_cq->qp->sq.wqe_cnt - 1);
+ dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+ } else if (opcode == MLX5_CQE_RESP_ERR) {
+ ++dr_cq->qp->sq.cc;
+ } else {
+ idx = be16_to_cpu(cqe64->wqe_counter) &
+ (dr_cq->qp->sq.wqe_cnt - 1);
+ dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+
+ return CQ_OK;
+ }
+
+ return CQ_POLL_ERR;
+}
+
+static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq)
+{
+ struct mlx5_cqe64 *cqe64;
+ int err;
+
+ cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq);
+ if (!cqe64)
+ return CQ_EMPTY;
+
+ mlx5_cqwq_pop(&dr_cq->wq);
+ err = dr_parse_cqe(dr_cq, cqe64);
+ mlx5_cqwq_update_db_record(&dr_cq->wq);
+
+ return err;
+}
+
+static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
+{
+ int npolled;
+ int err = 0;
+
+ for (npolled = 0; npolled < ne; ++npolled) {
+ err = dr_cq_poll_one(dr_cq);
+ if (err != CQ_OK)
+ break;
+ }
+
+ return err == CQ_POLL_ERR ? err : npolled;
+}
+
+static void dr_qp_event(struct mlx5_core_qp *mqp, int event)
+{
+ pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn);
+}
+
+static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
+ struct dr_qp_init_attr *attr)
+{
+ u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
+ struct mlx5_wq_param wqp;
+ struct mlx5dr_qp *dr_qp;
+ int inlen;
+ void *qpc;
+ void *in;
+ int err;
+
+ dr_qp = kzalloc(sizeof(*dr_qp), GFP_KERNEL);
+ if (!dr_qp)
+ return NULL;
+
+ wqp.buf_numa_node = mdev->priv.numa_node;
+ wqp.db_numa_node = mdev->priv.numa_node;
+
+ dr_qp->rq.pc = 0;
+ dr_qp->rq.cc = 0;
+ dr_qp->rq.wqe_cnt = 4;
+ dr_qp->sq.pc = 0;
+ dr_qp->sq.cc = 0;
+ dr_qp->sq.wqe_cnt = roundup_pow_of_two(attr->max_send_wr);
+
+ MLX5_SET(qpc, temp_qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+ MLX5_SET(qpc, temp_qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+ MLX5_SET(qpc, temp_qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+ err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq,
+ &dr_qp->wq_ctrl);
+ if (err) {
+ mlx5_core_info(mdev, "Can't create QP WQ\n");
+ goto err_wq;
+ }
+
+ dr_qp->sq.wqe_head = kcalloc(dr_qp->sq.wqe_cnt,
+ sizeof(dr_qp->sq.wqe_head[0]),
+ GFP_KERNEL);
+
+ if (!dr_qp->sq.wqe_head) {
+ mlx5_core_warn(mdev, "Can't allocate wqe head\n");
+ goto err_wqe_head;
+ }
+
+ inlen = MLX5_ST_SZ_BYTES(create_qp_in) +
+ MLX5_FLD_SZ_BYTES(create_qp_in, pas[0]) *
+ dr_qp->wq_ctrl.buf.npages;
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_in;
+ }
+
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+ MLX5_SET(qpc, qpc, pd, attr->pdn);
+ MLX5_SET(qpc, qpc, uar_page, attr->uar->index);
+ MLX5_SET(qpc, qpc, log_page_size,
+ dr_qp->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET(qpc, qpc, fre, 1);
+ MLX5_SET(qpc, qpc, rlky, 1);
+ MLX5_SET(qpc, qpc, cqn_snd, attr->cqn);
+ MLX5_SET(qpc, qpc, cqn_rcv, attr->cqn);
+ MLX5_SET(qpc, qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+ MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+ MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
+ MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+ MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma);
+ if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
+ MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
+ mlx5_fill_page_frag_array(&dr_qp->wq_ctrl.buf,
+ (__be64 *)MLX5_ADDR_OF(create_qp_in,
+ in, pas));
+
+ err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen);
+ kfree(in);
+
+ if (err) {
+ mlx5_core_warn(mdev, " Can't create QP\n");
+ goto err_in;
+ }
+ dr_qp->mqp.event = dr_qp_event;
+ dr_qp->uar = attr->uar;
+
+ return dr_qp;
+
+err_in:
+ kfree(dr_qp->sq.wqe_head);
+err_wqe_head:
+ mlx5_wq_destroy(&dr_qp->wq_ctrl);
+err_wq:
+ kfree(dr_qp);
+ return NULL;
+}
+
+static void dr_destroy_qp(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp)
+{
+ mlx5_core_destroy_qp(mdev, &dr_qp->mqp);
+ kfree(dr_qp->sq.wqe_head);
+ mlx5_wq_destroy(&dr_qp->wq_ctrl);
+ kfree(dr_qp);
+}
+
+static void dr_cmd_notify_hw(struct mlx5dr_qp *dr_qp, void *ctrl)
+{
+ dma_wmb();
+ *dr_qp->wq.sq.db = cpu_to_be32(dr_qp->sq.pc & 0xfffff);
+
+ /* After wmb() the hw aware of new work */
+ wmb();
+
+ mlx5_write64(ctrl, dr_qp->uar->map + MLX5_BF_OFFSET);
+}
+
+static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
+ u32 rkey, struct dr_data_seg *data_seg,
+ u32 opcode, int nreq)
+{
+ struct mlx5_wqe_raddr_seg *wq_raddr;
+ struct mlx5_wqe_ctrl_seg *wq_ctrl;
+ struct mlx5_wqe_data_seg *wq_dseg;
+ unsigned int size;
+ unsigned int idx;
+
+ size = sizeof(*wq_ctrl) / 16 + sizeof(*wq_dseg) / 16 +
+ sizeof(*wq_raddr) / 16;
+
+ idx = dr_qp->sq.pc & (dr_qp->sq.wqe_cnt - 1);
+
+ wq_ctrl = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
+ wq_ctrl->imm = 0;
+ wq_ctrl->fm_ce_se = (data_seg->send_flags) ?
+ MLX5_WQE_CTRL_CQ_UPDATE : 0;
+ wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) |
+ opcode);
+ wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8);
+ wq_raddr = (void *)(wq_ctrl + 1);
+ wq_raddr->raddr = cpu_to_be64(remote_addr);
+ wq_raddr->rkey = cpu_to_be32(rkey);
+ wq_raddr->reserved = 0;
+
+ wq_dseg = (void *)(wq_raddr + 1);
+ wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+ wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+ wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+ dr_qp->sq.wqe_head[idx] = dr_qp->sq.pc++;
+
+ if (nreq)
+ dr_cmd_notify_hw(dr_qp, wq_ctrl);
+}
+
+static void dr_post_send(struct mlx5dr_qp *dr_qp, struct postsend_info *send_info)
+{
+ dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+ &send_info->write, MLX5_OPCODE_RDMA_WRITE, 0);
+ dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+ &send_info->read, MLX5_OPCODE_RDMA_READ, 1);
+}
+
+/**
+ * mlx5dr_send_fill_and_append_ste_send_info: Add data to be sent
+ * with send_list parameters:
+ *
+ * @ste: The data that attached to this specific ste
+ * @size: of data to write
+ * @offset: of the data from start of the hw_ste entry
+ * @data: data
+ * @ste_info: ste to be sent with send_list
+ * @send_list: to append into it
+ * @copy_data: if true indicates that the data should be kept because
+ * it's not backuped any where (like in re-hash).
+ * if false, it lets the data to be updated after
+ * it was added to the list.
+ */
+void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size,
+ u16 offset, u8 *data,
+ struct mlx5dr_ste_send_info *ste_info,
+ struct list_head *send_list,
+ bool copy_data)
+{
+ ste_info->size = size;
+ ste_info->ste = ste;
+ ste_info->offset = offset;
+
+ if (copy_data) {
+ memcpy(ste_info->data_cont, data, size);
+ ste_info->data = ste_info->data_cont;
+ } else {
+ ste_info->data = data;
+ }
+
+ list_add_tail(&ste_info->send_list, send_list);
+}
+
+/* The function tries to consume one wc each time, unless the queue is full, in
+ * that case, which means that the hw is behind the sw in a full queue len
+ * the function will drain the cq till it empty.
+ */
+static int dr_handle_pending_wc(struct mlx5dr_domain *dmn,
+ struct mlx5dr_send_ring *send_ring)
+{
+ bool is_drain = false;
+ int ne;
+
+ if (send_ring->pending_wqe < send_ring->signal_th)
+ return 0;
+
+ /* Queue is full start drain it */
+ if (send_ring->pending_wqe >=
+ dmn->send_ring->signal_th * TH_NUMS_TO_DRAIN)
+ is_drain = true;
+
+ do {
+ ne = dr_poll_cq(send_ring->cq, 1);
+ if (ne < 0)
+ return ne;
+ else if (ne == 1)
+ send_ring->pending_wqe -= send_ring->signal_th;
+ } while (is_drain && send_ring->pending_wqe);
+
+ return 0;
+}
+
+static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring,
+ struct postsend_info *send_info)
+{
+ send_ring->pending_wqe++;
+
+ if (send_ring->pending_wqe % send_ring->signal_th == 0)
+ send_info->write.send_flags |= IB_SEND_SIGNALED;
+
+ send_ring->pending_wqe++;
+ send_info->read.length = send_info->write.length;
+ /* Read into the same write area */
+ send_info->read.addr = (uintptr_t)send_info->write.addr;
+ send_info->read.lkey = send_ring->mr->mkey.key;
+
+ if (send_ring->pending_wqe % send_ring->signal_th == 0)
+ send_info->read.send_flags = IB_SEND_SIGNALED;
+ else
+ send_info->read.send_flags = 0;
+}
+
+static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
+ struct postsend_info *send_info)
+{
+ struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+ u32 buff_offset;
+ int ret;
+
+ ret = dr_handle_pending_wc(dmn, send_ring);
+ if (ret)
+ return ret;
+
+ if (send_info->write.length > dmn->info.max_inline_size) {
+ buff_offset = (send_ring->tx_head &
+ (dmn->send_ring->signal_th - 1)) *
+ send_ring->max_post_send_size;
+ /* Copy to ring mr */
+ memcpy(send_ring->buf + buff_offset,
+ (void *)(uintptr_t)send_info->write.addr,
+ send_info->write.length);
+ send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset;
+ send_info->write.lkey = send_ring->mr->mkey.key;
+ }
+
+ send_ring->tx_head++;
+ dr_fill_data_segs(send_ring, send_info);
+ dr_post_send(send_ring->qp, send_info);
+
+ return 0;
+}
+
+static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 **data,
+ u32 *byte_size,
+ int *iterations,
+ int *num_stes)
+{
+ int alloc_size;
+
+ if (htbl->chunk->byte_size > dmn->send_ring->max_post_send_size) {
+ *iterations = htbl->chunk->byte_size /
+ dmn->send_ring->max_post_send_size;
+ *byte_size = dmn->send_ring->max_post_send_size;
+ alloc_size = *byte_size;
+ *num_stes = *byte_size / DR_STE_SIZE;
+ } else {
+ *iterations = 1;
+ *num_stes = htbl->chunk->num_of_entries;
+ alloc_size = *num_stes * DR_STE_SIZE;
+ }
+
+ *data = kzalloc(alloc_size, GFP_KERNEL);
+ if (!*data)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * mlx5dr_send_postsend_ste: write size bytes into offset from the hw cm.
+ *
+ * @dmn: Domain
+ * @ste: The ste struct that contains the data (at
+ * least part of it)
+ * @data: The real data to send size data
+ * @size: for writing.
+ * @offset: The offset from the icm mapped data to
+ * start write to this for write only part of the
+ * buffer.
+ *
+ * Return: 0 on success.
+ */
+int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste,
+ u8 *data, u16 size, u16 offset)
+{
+ struct postsend_info send_info = {};
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr = mlx5dr_ste_get_mr_addr(ste) + offset;
+ send_info.rkey = ste->htbl->chunk->rkey;
+
+ return dr_postsend_icm_data(dmn, &send_info);
+}
+
+int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *formatted_ste, u8 *mask)
+{
+ u32 byte_size = htbl->chunk->byte_size;
+ int num_stes_per_iter;
+ int iterations;
+ u8 *data;
+ int ret;
+ int i;
+ int j;
+
+ ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+ &iterations, &num_stes_per_iter);
+ if (ret)
+ return ret;
+
+ /* Send the data iteration times */
+ for (i = 0; i < iterations; i++) {
+ u32 ste_index = i * (byte_size / DR_STE_SIZE);
+ struct postsend_info send_info = {};
+
+ /* Copy all ste's on the data buffer
+ * need to add the bit_mask
+ */
+ for (j = 0; j < num_stes_per_iter; j++) {
+ u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste;
+ u32 ste_off = j * DR_STE_SIZE;
+
+ if (mlx5dr_ste_is_not_valid_entry(hw_ste)) {
+ memcpy(data + ste_off,
+ formatted_ste, DR_STE_SIZE);
+ } else {
+ /* Copy data */
+ memcpy(data + ste_off,
+ htbl->ste_arr[ste_index + j].hw_ste,
+ DR_STE_SIZE_REDUCED);
+ /* Copy bit_mask */
+ memcpy(data + ste_off + DR_STE_SIZE_REDUCED,
+ mask, DR_STE_SIZE_MASK);
+ }
+ }
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr =
+ mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+ send_info.rkey = htbl->chunk->rkey;
+
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ goto out_free;
+ }
+
+out_free:
+ kfree(data);
+ return ret;
+}
+
+/* Initialize htble with default STEs */
+int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *ste_init_data,
+ bool update_hw_ste)
+{
+ u32 byte_size = htbl->chunk->byte_size;
+ int iterations;
+ int num_stes;
+ u8 *data;
+ int ret;
+ int i;
+
+ ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+ &iterations, &num_stes);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < num_stes; i++) {
+ u8 *copy_dst;
+
+ /* Copy the same ste on the data buffer */
+ copy_dst = data + i * DR_STE_SIZE;
+ memcpy(copy_dst, ste_init_data, DR_STE_SIZE);
+
+ if (update_hw_ste) {
+ /* Copy the reduced ste to hash table ste_arr */
+ copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
+ memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED);
+ }
+ }
+
+ /* Send the data iteration times */
+ for (i = 0; i < iterations; i++) {
+ u8 ste_index = i * (byte_size / DR_STE_SIZE);
+ struct postsend_info send_info = {};
+
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr =
+ mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+ send_info.rkey = htbl->chunk->rkey;
+
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ goto out_free;
+ }
+
+out_free:
+ kfree(data);
+ return ret;
+}
+
+int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action *action)
+{
+ struct postsend_info send_info = {};
+ int ret;
+
+ send_info.write.addr = (uintptr_t)action->rewrite.data;
+ send_info.write.length = action->rewrite.chunk->byte_size;
+ send_info.write.lkey = 0;
+ send_info.remote_addr = action->rewrite.chunk->mr_addr;
+ send_info.rkey = action->rewrite.chunk->rkey;
+
+ mutex_lock(&dmn->mutex);
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ mutex_unlock(&dmn->mutex);
+
+ return ret;
+}
+
+static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ int port)
+{
+ u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
+
+ MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, port);
+ MLX5_SET(qpc, qpc, pm_state, MLX5_QPC_PM_STATE_MIGRATED);
+ MLX5_SET(qpc, qpc, rre, 1);
+ MLX5_SET(qpc, qpc, rwe, 1);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ struct dr_qp_rts_attr *attr)
+{
+ u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc);
+
+ MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+ MLX5_SET(qpc, qpc, log_ack_req_freq, 0);
+ MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
+ MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
+ struct mlx5dr_qp *dr_qp,
+ struct dr_qp_rtr_attr *attr)
+{
+ u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
+ void *qpc;
+
+ qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc);
+
+ MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+ MLX5_SET(qpc, qpc, mtu, attr->mtu);
+ MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1);
+ MLX5_SET(qpc, qpc, remote_qpn, attr->qp_num);
+ memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rmac_47_32),
+ attr->dgid_attr.mac, sizeof(attr->dgid_attr.mac));
+ memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rgid_rip),
+ attr->dgid_attr.gid, sizeof(attr->dgid_attr.gid));
+ MLX5_SET(qpc, qpc, primary_address_path.src_addr_index,
+ attr->sgid_index);
+
+ if (attr->dgid_attr.roce_ver == MLX5_ROCE_VERSION_2)
+ MLX5_SET(qpc, qpc, primary_address_path.udp_sport,
+ attr->udp_src_port);
+
+ MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num);
+ MLX5_SET(qpc, qpc, min_rnr_nak, 1);
+
+ return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc,
+ &dr_qp->mqp);
+}
+
+static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_qp *dr_qp = dmn->send_ring->qp;
+ struct dr_qp_rts_attr rts_attr = {};
+ struct dr_qp_rtr_attr rtr_attr = {};
+ enum ib_mtu mtu = IB_MTU_1024;
+ u16 gid_index = 0;
+ int port = 1;
+ int ret;
+
+ /* Init */
+ ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port);
+ if (ret)
+ return ret;
+
+ /* RTR */
+ ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr);
+ if (ret)
+ return ret;
+
+ rtr_attr.mtu = mtu;
+ rtr_attr.qp_num = dr_qp->mqp.qpn;
+ rtr_attr.min_rnr_timer = 12;
+ rtr_attr.port_num = port;
+ rtr_attr.sgid_index = gid_index;
+ rtr_attr.udp_src_port = dmn->info.caps.roce_min_src_udp;
+
+ ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr);
+ if (ret)
+ return ret;
+
+ /* RTS */
+ rts_attr.timeout = 14;
+ rts_attr.retry_cnt = 7;
+ rts_attr.rnr_retry = 7;
+
+ ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static void dr_cq_event(struct mlx5_core_cq *mcq,
+ enum mlx5_event event)
+{
+ pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
+}
+
+static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
+ struct mlx5_uars_page *uar,
+ size_t ncqe)
+{
+ u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {};
+ u32 out[MLX5_ST_SZ_DW(create_cq_out)];
+ struct mlx5_wq_param wqp;
+ struct mlx5_cqe64 *cqe;
+ struct mlx5dr_cq *cq;
+ int inlen, err, eqn;
+ unsigned int irqn;
+ void *cqc, *in;
+ __be64 *pas;
+ u32 i;
+
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq)
+ return NULL;
+
+ ncqe = roundup_pow_of_two(ncqe);
+ MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(ncqe));
+
+ wqp.buf_numa_node = mdev->priv.numa_node;
+ wqp.db_numa_node = mdev->priv.numa_node;
+
+ err = mlx5_cqwq_create(mdev, &wqp, temp_cqc, &cq->wq,
+ &cq->wq_ctrl);
+ if (err)
+ goto out;
+
+ for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
+ cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
+ cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK;
+ }
+
+ inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+ sizeof(u64) * cq->wq_ctrl.buf.npages;
+ in = kvzalloc(inlen, GFP_KERNEL);
+ if (!in)
+ goto err_cqwq;
+
+ err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
+ if (err) {
+ kvfree(in);
+ goto err_cqwq;
+ }
+
+ cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+ MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe));
+ MLX5_SET(cqc, cqc, c_eqn, eqn);
+ MLX5_SET(cqc, cqc, uar_page, uar->index);
+ MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
+ MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
+
+ pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
+ mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
+
+ cq->mcq.event = dr_cq_event;
+
+ err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
+ kvfree(in);
+
+ if (err)
+ goto err_cqwq;
+
+ cq->mcq.cqe_sz = 64;
+ cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
+ cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
+ *cq->mcq.set_ci_db = 0;
+ *cq->mcq.arm_db = 0;
+ cq->mcq.vector = 0;
+ cq->mcq.irqn = irqn;
+ cq->mcq.uar = uar;
+
+ return cq;
+
+err_cqwq:
+ mlx5_wq_destroy(&cq->wq_ctrl);
+out:
+ kfree(cq);
+ return NULL;
+}
+
+static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq)
+{
+ mlx5_core_destroy_cq(mdev, &cq->mcq);
+ mlx5_wq_destroy(&cq->wq_ctrl);
+ kfree(cq);
+}
+
+static int
+dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey)
+{
+ u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
+ void *mkc;
+
+ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+ MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA);
+ MLX5_SET(mkc, mkc, a, 1);
+ MLX5_SET(mkc, mkc, rw, 1);
+ MLX5_SET(mkc, mkc, rr, 1);
+ MLX5_SET(mkc, mkc, lw, 1);
+ MLX5_SET(mkc, mkc, lr, 1);
+
+ MLX5_SET(mkc, mkc, pd, pdn);
+ MLX5_SET(mkc, mkc, length64, 1);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+
+ return mlx5_core_create_mkey(mdev, mkey, in, sizeof(in));
+}
+
+static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
+ u32 pdn, void *buf, size_t size)
+{
+ struct mlx5dr_mr *mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ struct device *dma_device;
+ dma_addr_t dma_addr;
+ int err;
+
+ if (!mr)
+ return NULL;
+
+ dma_device = &mdev->pdev->dev;
+ dma_addr = dma_map_single(dma_device, buf, size,
+ DMA_BIDIRECTIONAL);
+ err = dma_mapping_error(dma_device, dma_addr);
+ if (err) {
+ mlx5_core_warn(mdev, "Can't dma buf\n");
+ kfree(mr);
+ return NULL;
+ }
+
+ err = dr_create_mkey(mdev, pdn, &mr->mkey);
+ if (err) {
+ mlx5_core_warn(mdev, "Can't create mkey\n");
+ dma_unmap_single(dma_device, dma_addr, size,
+ DMA_BIDIRECTIONAL);
+ kfree(mr);
+ return NULL;
+ }
+
+ mr->dma_addr = dma_addr;
+ mr->size = size;
+ mr->addr = buf;
+
+ return mr;
+}
+
+static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr)
+{
+ mlx5_core_destroy_mkey(mdev, &mr->mkey);
+ dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size,
+ DMA_BIDIRECTIONAL);
+ kfree(mr);
+}
+
+int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
+{
+ struct dr_qp_init_attr init_attr = {};
+ int cq_size;
+ int size;
+ int ret;
+
+ dmn->send_ring = kzalloc(sizeof(*dmn->send_ring), GFP_KERNEL);
+ if (!dmn->send_ring)
+ return -ENOMEM;
+
+ cq_size = QUEUE_SIZE + 1;
+ dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size);
+ if (!dmn->send_ring->cq) {
+ ret = -ENOMEM;
+ goto free_send_ring;
+ }
+
+ init_attr.cqn = dmn->send_ring->cq->mcq.cqn;
+ init_attr.pdn = dmn->pdn;
+ init_attr.uar = dmn->uar;
+ init_attr.max_send_wr = QUEUE_SIZE;
+
+ dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr);
+ if (!dmn->send_ring->qp) {
+ ret = -ENOMEM;
+ goto clean_cq;
+ }
+
+ dmn->send_ring->cq->qp = dmn->send_ring->qp;
+
+ dmn->info.max_send_wr = QUEUE_SIZE;
+ dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
+ DR_STE_SIZE);
+
+ dmn->send_ring->signal_th = dmn->info.max_send_wr /
+ SIGNAL_PER_DIV_QUEUE;
+
+ /* Prepare qp to be used */
+ ret = dr_prepare_qp_to_rts(dmn);
+ if (ret)
+ goto clean_qp;
+
+ dmn->send_ring->max_post_send_size =
+ mlx5dr_icm_pool_chunk_size_to_byte(DR_CHUNK_SIZE_1K,
+ DR_ICM_TYPE_STE);
+
+ /* Allocating the max size as a buffer for writing */
+ size = dmn->send_ring->signal_th * dmn->send_ring->max_post_send_size;
+ dmn->send_ring->buf = kzalloc(size, GFP_KERNEL);
+ if (!dmn->send_ring->buf) {
+ ret = -ENOMEM;
+ goto clean_qp;
+ }
+
+ memset(dmn->send_ring->buf, 0, size);
+ dmn->send_ring->buf_size = size;
+
+ dmn->send_ring->mr = dr_reg_mr(dmn->mdev,
+ dmn->pdn, dmn->send_ring->buf, size);
+ if (!dmn->send_ring->mr) {
+ ret = -ENOMEM;
+ goto free_mem;
+ }
+
+ dmn->send_ring->sync_mr = dr_reg_mr(dmn->mdev,
+ dmn->pdn, dmn->send_ring->sync_buff,
+ MIN_READ_SYNC);
+ if (!dmn->send_ring->sync_mr) {
+ ret = -ENOMEM;
+ goto clean_mr;
+ }
+
+ return 0;
+
+clean_mr:
+ dr_dereg_mr(dmn->mdev, dmn->send_ring->mr);
+free_mem:
+ kfree(dmn->send_ring->buf);
+clean_qp:
+ dr_destroy_qp(dmn->mdev, dmn->send_ring->qp);
+clean_cq:
+ dr_destroy_cq(dmn->mdev, dmn->send_ring->cq);
+free_send_ring:
+ kfree(dmn->send_ring);
+
+ return ret;
+}
+
+void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
+ struct mlx5dr_send_ring *send_ring)
+{
+ dr_destroy_qp(dmn->mdev, send_ring->qp);
+ dr_destroy_cq(dmn->mdev, send_ring->cq);
+ dr_dereg_mr(dmn->mdev, send_ring->sync_mr);
+ dr_dereg_mr(dmn->mdev, send_ring->mr);
+ kfree(send_ring->buf);
+ kfree(send_ring);
+}
+
+int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+ struct postsend_info send_info = {};
+ u8 data[DR_STE_SIZE];
+ int num_of_sends_req;
+ int ret;
+ int i;
+
+ /* Sending this amount of requests makes sure we will get drain */
+ num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
+
+ /* Send fake requests forcing the last to be signaled */
+ send_info.write.addr = (uintptr_t)data;
+ send_info.write.length = DR_STE_SIZE;
+ send_info.write.lkey = 0;
+ /* Using the sync_mr in order to write/read */
+ send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
+ send_info.rkey = send_ring->sync_mr->mkey.key;
+
+ for (i = 0; i < num_of_sends_req; i++) {
+ ret = dr_postsend_icm_data(dmn, &send_info);
+ if (ret)
+ return ret;
+ }
+
+ ret = dr_handle_pending_wc(dmn, send_ring);
+
+ return ret;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 13/18] net/mlx5: DR, Expose APIs for direct rule managing
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Expose APIs for direct rule managing to increase insertion rate by
bypassing the firmware.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/mlx5dr.h | 212 ++++++++++++++++++
1 file changed, 212 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
new file mode 100644
index 000000000000..adda9cbfba45
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h
@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019, Mellanox Technologies */
+
+#ifndef _MLX5DR_H_
+#define _MLX5DR_H_
+
+struct mlx5dr_domain;
+struct mlx5dr_table;
+struct mlx5dr_matcher;
+struct mlx5dr_rule;
+struct mlx5dr_action;
+
+enum mlx5dr_domain_type {
+ MLX5DR_DOMAIN_TYPE_NIC_RX,
+ MLX5DR_DOMAIN_TYPE_NIC_TX,
+ MLX5DR_DOMAIN_TYPE_FDB,
+};
+
+enum mlx5dr_domain_sync_flags {
+ MLX5DR_DOMAIN_SYNC_FLAGS_SW = 1 << 0,
+ MLX5DR_DOMAIN_SYNC_FLAGS_HW = 1 << 1,
+};
+
+enum mlx5dr_action_reformat_type {
+ DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2,
+ DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2,
+ DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2,
+ DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3,
+};
+
+struct mlx5dr_match_parameters {
+ size_t match_sz;
+ u64 *match_buf; /* Device spec format */
+};
+
+#ifdef CONFIG_MLX5_SW_STEERING
+
+struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
+
+int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
+
+int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
+
+void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain *peer_dmn);
+
+struct mlx5dr_table *
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level);
+
+int mlx5dr_table_destroy(struct mlx5dr_table *table);
+
+u32 mlx5dr_table_get_id(struct mlx5dr_table *table);
+
+struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *table,
+ u16 priority,
+ u8 match_criteria_enable,
+ struct mlx5dr_match_parameters *mask);
+
+int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher);
+
+struct mlx5dr_rule *
+mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *value,
+ size_t num_actions,
+ struct mlx5dr_action *actions[]);
+
+int mlx5dr_rule_destroy(struct mlx5dr_rule *rule);
+
+int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+ struct mlx5dr_action *action);
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_table(struct mlx5dr_table *table);
+
+struct mlx5dr_action *
+mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
+ struct mlx5_core_dev *mdev);
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
+ u32 vport, u8 vhca_id_valid,
+ u16 vhca_id);
+
+struct mlx5dr_action *mlx5dr_action_create_drop(void);
+
+struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value);
+
+struct mlx5dr_action *
+mlx5dr_action_create_flow_counter(u32 counter_id);
+
+struct mlx5dr_action *
+mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
+ enum mlx5dr_action_reformat_type reformat_type,
+ size_t data_sz,
+ void *data);
+
+struct mlx5dr_action *
+mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain,
+ u32 flags,
+ size_t actions_sz,
+ __be64 actions[]);
+
+struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void);
+
+struct mlx5dr_action *
+mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, __be32 vlan_hdr);
+
+int mlx5dr_action_destroy(struct mlx5dr_action *action);
+
+static inline bool
+mlx5dr_is_supported(struct mlx5_core_dev *dev)
+{
+ return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner);
+}
+
+#else /* CONFIG_MLX5_SW_STEERING */
+
+static inline struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) { return NULL; }
+
+static inline int
+mlx5dr_domain_destroy(struct mlx5dr_domain *domain) { return 0; }
+
+static inline int
+mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags) { return 0; }
+
+static inline void
+mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain *peer_dmn) { }
+
+static inline struct mlx5dr_table *
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level) { return NULL; }
+
+static inline int
+mlx5dr_table_destroy(struct mlx5dr_table *table) { return 0; }
+
+static inline u32
+mlx5dr_table_get_id(struct mlx5dr_table *table) { return 0; }
+
+static inline struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *table,
+ u16 priority,
+ u8 match_criteria_enable,
+ struct mlx5dr_match_parameters *mask) { return NULL; }
+
+static inline int
+mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) { return 0; }
+
+static inline struct mlx5dr_rule *
+mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *value,
+ size_t num_actions,
+ struct mlx5dr_action *actions[]) { return NULL; }
+
+static inline int
+mlx5dr_rule_destroy(struct mlx5dr_rule *rule) { return 0; }
+
+static inline int
+mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+ struct mlx5dr_action *action) { return 0; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_dest_table(struct mlx5dr_table *table) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
+ struct mlx5_core_dev *mdev) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
+ u32 vport, u8 vhca_id_valid,
+ u16 vhca_id) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_drop(void) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_tag(u32 tag_value) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_flow_counter(u32 counter_id) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
+ enum mlx5dr_action_reformat_type reformat_type,
+ size_t data_sz,
+ void *data) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain,
+ u32 flags,
+ size_t actions_sz,
+ __be64 actions[]) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_pop_vlan(void) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain,
+ __be32 vlan_hdr) { return NULL; }
+
+static inline int
+mlx5dr_action_destroy(struct mlx5dr_action *action) { return 0; }
+
+static inline bool
+mlx5dr_is_supported(struct mlx5_core_dev *dev) { return false; }
+
+#endif /* CONFIG_MLX5_SW_STEERING */
+
+#endif /* _MLX5DR_H_ */
--
2.21.0
^ permalink raw reply related
* [net-next 06/18] net/mlx5: DR, Add Steering entry (STE) utilities
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Steering Entry (STE) object is the basic building block of the steering
map. There are several types of STEs. Each rule can be constructed of
multiple STEs. Each STE dictates which fields of the packet's header are
being matched as well as the information about the next step in map (hit
and miss pointers). The hardware gets a packet and tries to match it
against the STEs, going to either the hit pointer or the miss pointer.
This file handles the STE operations.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_crc32.c | 98 +
.../mellanox/mlx5/core/steering/dr_ste.c | 2308 +++++++++++++++++
2 files changed, 2406 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
new file mode 100644
index 000000000000..9e2eccbb1eb8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved.
+ * Slicing-by-16 contributed by Bulat Ziganshin
+ *
+ * This software is provided 'as-is', without any express or implied warranty.
+ * In no event will the author be held liable for any damages arising from the
+ * of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute it
+ * freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must not
+ * claim that you wrote the original software.
+ * 2. If you use this software in a product, an acknowledgment in the product
+ * documentation would be appreciated but is not required.
+ * 3. Altered source versions must be plainly marked as such, and must not be
+ * misrepresented as being the original software.
+ *
+ * Taken from http://create.stephan-brumme.com/crc32/ and adapted.
+ */
+
+#include "dr_types.h"
+
+#define DR_STE_CRC_POLY 0xEDB88320L
+
+static u32 dr_ste_crc_tab32[8][256];
+
+static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j)
+{
+ tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff];
+}
+
+void mlx5dr_crc32_init_table(void)
+{
+ u32 crc, i, j;
+
+ for (i = 0; i < 256; i++) {
+ crc = i;
+ for (j = 0; j < 8; j++) {
+ if (crc & 0x00000001L)
+ crc = (crc >> 1) ^ DR_STE_CRC_POLY;
+ else
+ crc = crc >> 1;
+ }
+ dr_ste_crc_tab32[0][i] = crc;
+ }
+
+ /* Init CRC lookup tables according to crc_slice_8 algorithm */
+ for (i = 0; i < 256; i++) {
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i);
+ dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i);
+ }
+}
+
+/* Compute CRC32 (Slicing-by-8 algorithm) */
+u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length)
+{
+ const u32 *curr = (const u32 *)input_data;
+ const u8 *curr_char;
+ u32 crc = 0, one, two;
+
+ if (!input_data)
+ return 0;
+
+ /* Process eight bytes at once (Slicing-by-8) */
+ while (length >= 8) {
+ one = *curr++ ^ crc;
+ two = *curr++;
+
+ crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff]
+ ^ dr_ste_crc_tab32[1][(two >> 16) & 0xff]
+ ^ dr_ste_crc_tab32[2][(two >> 8) & 0xff]
+ ^ dr_ste_crc_tab32[3][two & 0xff]
+ ^ dr_ste_crc_tab32[4][(one >> 24) & 0xff]
+ ^ dr_ste_crc_tab32[5][(one >> 16) & 0xff]
+ ^ dr_ste_crc_tab32[6][(one >> 8) & 0xff]
+ ^ dr_ste_crc_tab32[7][one & 0xff];
+
+ length -= 8;
+ }
+
+ curr_char = (const u8 *)curr;
+ /* Remaining 1 to 7 bytes (standard algorithm) */
+ while (length-- != 0)
+ crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff)
+ ^ *curr_char++];
+
+ return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) |
+ ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
new file mode 100644
index 000000000000..6b0af64536d8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -0,0 +1,2308 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/types.h>
+#include "dr_types.h"
+
+#define DR_STE_CRC_POLY 0xEDB88320L
+#define STE_IPV4 0x1
+#define STE_IPV6 0x2
+#define STE_TCP 0x1
+#define STE_UDP 0x2
+#define STE_SPI 0x3
+#define IP_VERSION_IPV4 0x4
+#define IP_VERSION_IPV6 0x6
+#define STE_SVLAN 0x1
+#define STE_CVLAN 0x2
+
+#define DR_STE_ENABLE_FLOW_TAG BIT(31)
+
+/* Set to STE a specific value using DR_STE_SET */
+#define DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, value) do { \
+ if ((spec)->s_fname) { \
+ MLX5_SET(ste_##lookup_type, tag, t_fname, value); \
+ (spec)->s_fname = 0; \
+ } \
+} while (0)
+
+/* Set to STE spec->s_fname to tag->t_fname */
+#define DR_STE_SET_TAG(lookup_type, tag, t_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, spec->s_fname)
+
+/* Set to STE -1 to bit_mask->bm_fname and set spec->s_fname as used */
+#define DR_STE_SET_MASK(lookup_type, bit_mask, bm_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, -1)
+
+/* Set to STE spec->s_fname to bit_mask->bm_fname and set spec->s_fname as used */
+#define DR_STE_SET_MASK_V(lookup_type, bit_mask, bm_fname, spec, s_fname) \
+ DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, (spec)->s_fname)
+
+#define DR_STE_SET_TCP_FLAGS(lookup_type, tag, spec) do { \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ns, !!((spec)->tcp_flags & (1 << 8))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_cwr, !!((spec)->tcp_flags & (1 << 7))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ece, !!((spec)->tcp_flags & (1 << 6))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_urg, !!((spec)->tcp_flags & (1 << 5))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_ack, !!((spec)->tcp_flags & (1 << 4))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_psh, !!((spec)->tcp_flags & (1 << 3))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_rst, !!((spec)->tcp_flags & (1 << 2))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_syn, !!((spec)->tcp_flags & (1 << 1))); \
+ MLX5_SET(ste_##lookup_type, tag, tcp_fin, !!((spec)->tcp_flags & (1 << 0))); \
+} while (0)
+
+#define DR_STE_SET_MPLS_MASK(lookup_type, mask, in_out, bit_mask) do { \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_label, mask, \
+ in_out##_first_mpls_label);\
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_s_bos, mask, \
+ in_out##_first_mpls_s_bos); \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_exp, mask, \
+ in_out##_first_mpls_exp); \
+ DR_STE_SET_MASK_V(lookup_type, mask, mpls0_ttl, mask, \
+ in_out##_first_mpls_ttl); \
+} while (0)
+
+#define DR_STE_SET_MPLS_TAG(lookup_type, mask, in_out, tag) do { \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_label, mask, \
+ in_out##_first_mpls_label);\
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_s_bos, mask, \
+ in_out##_first_mpls_s_bos); \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_exp, mask, \
+ in_out##_first_mpls_exp); \
+ DR_STE_SET_TAG(lookup_type, tag, mpls0_ttl, mask, \
+ in_out##_first_mpls_ttl); \
+} while (0)
+
+#define DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(_misc) (\
+ (_misc)->outer_first_mpls_over_gre_label || \
+ (_misc)->outer_first_mpls_over_gre_exp || \
+ (_misc)->outer_first_mpls_over_gre_s_bos || \
+ (_misc)->outer_first_mpls_over_gre_ttl)
+#define DR_STE_IS_OUTER_MPLS_OVER_UDP_SET(_misc) (\
+ (_misc)->outer_first_mpls_over_udp_label || \
+ (_misc)->outer_first_mpls_over_udp_exp || \
+ (_misc)->outer_first_mpls_over_udp_s_bos || \
+ (_misc)->outer_first_mpls_over_udp_ttl)
+
+#define DR_STE_CALC_LU_TYPE(lookup_type, rx, inner) \
+ ((inner) ? MLX5DR_STE_LU_TYPE_##lookup_type##_I : \
+ (rx) ? MLX5DR_STE_LU_TYPE_##lookup_type##_D : \
+ MLX5DR_STE_LU_TYPE_##lookup_type##_O)
+
+enum dr_ste_tunl_action {
+ DR_STE_TUNL_ACTION_NONE = 0,
+ DR_STE_TUNL_ACTION_ENABLE = 1,
+ DR_STE_TUNL_ACTION_DECAP = 2,
+ DR_STE_TUNL_ACTION_L3_DECAP = 3,
+ DR_STE_TUNL_ACTION_POP_VLAN = 4,
+};
+
+enum dr_ste_action_type {
+ DR_STE_ACTION_TYPE_PUSH_VLAN = 1,
+ DR_STE_ACTION_TYPE_ENCAP_L3 = 3,
+ DR_STE_ACTION_TYPE_ENCAP = 4,
+};
+
+struct dr_hw_ste_format {
+ u8 ctrl[DR_STE_SIZE_CTRL];
+ u8 tag[DR_STE_SIZE_TAG];
+ u8 mask[DR_STE_SIZE_MASK];
+};
+
+u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 masked[DR_STE_SIZE_TAG] = {};
+ u32 crc32, index;
+ u16 bit;
+ int i;
+
+ /* Don't calculate CRC if the result is predicted */
+ if (htbl->chunk->num_of_entries == 1 || htbl->byte_mask == 0)
+ return 0;
+
+ /* Mask tag using byte mask, bit per byte */
+ bit = 1 << (DR_STE_SIZE_TAG - 1);
+ for (i = 0; i < DR_STE_SIZE_TAG; i++) {
+ if (htbl->byte_mask & bit)
+ masked[i] = hw_ste->tag[i];
+
+ bit = bit >> 1;
+ }
+
+ crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG);
+ index = crc32 & (htbl->chunk->num_of_entries - 1);
+
+ return index;
+}
+
+static u16 dr_ste_conv_bit_to_byte_mask(u8 *bit_mask)
+{
+ u16 byte_mask = 0;
+ int i;
+
+ for (i = 0; i < DR_STE_SIZE_MASK; i++) {
+ byte_mask = byte_mask << 1;
+ if (bit_mask[i] == 0xff)
+ byte_mask |= 1;
+ }
+ return byte_mask;
+}
+
+void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+
+ memcpy(hw_ste->mask, bit_mask, DR_STE_SIZE_MASK);
+}
+
+void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer,
+ DR_STE_ENABLE_FLOW_TAG | flow_tag);
+}
+
+void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id)
+{
+ /* This can be used for both rx_steering_mult and for sx_transmit */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_15_0, ctr_id);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_23_16, ctr_id >> 16);
+}
+
+void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, go_back, 1);
+}
+
+void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_hdr,
+ bool go_back)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_type,
+ DR_STE_ACTION_TYPE_PUSH_VLAN);
+ MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, vlan_hdr);
+ /* Due to HW limitation we need to set this bit, otherwise reforamt +
+ * push vlan will not work.
+ */
+ if (go_back)
+ mlx5dr_ste_set_go_back_bit(hw_ste_p);
+}
+
+void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, int size, bool encap_l3)
+{
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_type,
+ encap_l3 ? DR_STE_ACTION_TYPE_ENCAP_L3 : DR_STE_ACTION_TYPE_ENCAP);
+ /* The hardware expects here size in words (2 byte) */
+ MLX5_SET(ste_sx_transmit, hw_ste_p, action_description, size / 2);
+ MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, reformat_id);
+}
+
+void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_DECAP);
+}
+
+void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_POP_VLAN);
+}
+
+void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan)
+{
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action,
+ DR_STE_TUNL_ACTION_L3_DECAP);
+ MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0);
+}
+
+void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type)
+{
+ MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type);
+}
+
+u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p)
+{
+ return MLX5_GET(ste_general, hw_ste_p, entry_type);
+}
+
+void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions,
+ u32 re_write_index)
+{
+ MLX5_SET(ste_modify_packet, hw_ste_p, number_of_re_write_actions,
+ num_of_actions);
+ MLX5_SET(ste_modify_packet, hw_ste_p, header_re_write_actions_pointer,
+ re_write_index);
+}
+
+void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi)
+{
+ MLX5_SET(ste_general, hw_ste_p, next_table_base_63_48, gvmi);
+}
+
+void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type,
+ u16 gvmi)
+{
+ MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type);
+ MLX5_SET(ste_general, hw_ste_p, entry_sub_type, lu_type);
+ MLX5_SET(ste_general, hw_ste_p, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE);
+
+ /* Set GVMI once, this is the same for RX/TX
+ * bits 63_48 of next table base / miss address encode the next GVMI
+ */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, gvmi, gvmi);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, next_table_base_63_48, gvmi);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi);
+}
+
+static void dr_ste_set_always_hit(struct dr_hw_ste_format *hw_ste)
+{
+ memset(&hw_ste->tag, 0, sizeof(hw_ste->tag));
+ memset(&hw_ste->mask, 0, sizeof(hw_ste->mask));
+}
+
+static void dr_ste_set_always_miss(struct dr_hw_ste_format *hw_ste)
+{
+ hw_ste->tag[0] = 0xdc;
+ hw_ste->mask[0] = 0;
+}
+
+u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste)
+{
+ u64 index =
+ (MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_31_6) |
+ MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_39_32) << 26);
+
+ return index << 6;
+}
+
+void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size)
+{
+ u64 index = (icm_addr >> 5) | ht_size;
+
+ MLX5_SET(ste_general, hw_ste, next_table_base_39_32_size, index >> 27);
+ MLX5_SET(ste_general, hw_ste, next_table_base_31_5_size, index);
+}
+
+u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return ste->htbl->chunk->icm_addr + DR_STE_SIZE * index;
+}
+
+u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return ste->htbl->chunk->mr_addr + DR_STE_SIZE * index;
+}
+
+struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste)
+{
+ u32 index = ste - ste->htbl->ste_arr;
+
+ return &ste->htbl->miss_list[index];
+}
+
+static void dr_ste_always_hit_htbl(struct mlx5dr_ste *ste,
+ struct mlx5dr_ste_htbl *next_htbl)
+{
+ struct mlx5dr_icm_chunk *chunk = next_htbl->chunk;
+ u8 *hw_ste = ste->hw_ste;
+
+ MLX5_SET(ste_general, hw_ste, byte_mask, next_htbl->byte_mask);
+ MLX5_SET(ste_general, hw_ste, next_lu_type, next_htbl->lu_type);
+ mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries);
+
+ dr_ste_set_always_hit((struct dr_hw_ste_format *)ste->hw_ste);
+}
+
+bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher,
+ u8 ste_location)
+{
+ return ste_location == nic_matcher->num_of_builders;
+}
+
+/* Replace relevant fields, except of:
+ * htbl - keep the origin htbl
+ * miss_list + list - already took the src from the list.
+ * icm_addr/mr_addr - depends on the hosting table.
+ *
+ * Before:
+ * | a | -> | b | -> | c | ->
+ *
+ * After:
+ * | a | -> | c | ->
+ * While the data that was in b copied to a.
+ */
+static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src)
+{
+ memcpy(dst->hw_ste, src->hw_ste, DR_STE_SIZE_REDUCED);
+ dst->next_htbl = src->next_htbl;
+ if (dst->next_htbl)
+ dst->next_htbl->pointing_ste = dst;
+
+ refcount_set(&dst->refcount, refcount_read(&src->refcount));
+
+ INIT_LIST_HEAD(&dst->rule_list);
+ list_splice_tail_init(&src->rule_list, &dst->rule_list);
+}
+
+/* Free ste which is the head and the only one in miss_list */
+static void
+dr_ste_remove_head_ste(struct mlx5dr_ste *ste,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste_send_info *ste_info_head,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+{
+ u8 tmp_data_ste[DR_STE_SIZE] = {};
+ struct mlx5dr_ste tmp_ste = {};
+ u64 miss_addr;
+
+ tmp_ste.hw_ste = tmp_data_ste;
+
+ /* Use temp ste because dr_ste_always_miss_addr
+ * touches bit_mask area which doesn't exist at ste->hw_ste.
+ */
+ memcpy(tmp_ste.hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED);
+ miss_addr = nic_matcher->e_anchor->chunk->icm_addr;
+ mlx5dr_ste_always_miss_addr(&tmp_ste, miss_addr);
+ memcpy(ste->hw_ste, tmp_ste.hw_ste, DR_STE_SIZE_REDUCED);
+
+ list_del_init(&ste->miss_list_node);
+
+ /* Write full STE size in order to have "always_miss" */
+ mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE,
+ 0, tmp_data_ste,
+ ste_info_head,
+ send_ste_list,
+ true /* Copy data */);
+
+ stats_tbl->ctrl.num_of_valid_entries--;
+}
+
+/* Free ste which is the head but NOT the only one in miss_list:
+ * |_ste_| --> |_next_ste_| -->|__| -->|__| -->/0
+ */
+static void
+dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste,
+ struct mlx5dr_ste_send_info *ste_info_head,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+
+{
+ struct mlx5dr_ste_htbl *next_miss_htbl;
+
+ next_miss_htbl = next_ste->htbl;
+
+ /* Remove from the miss_list the next_ste before copy */
+ list_del_init(&next_ste->miss_list_node);
+
+ /* All rule-members that use next_ste should know about that */
+ mlx5dr_rule_update_rule_member(next_ste, ste);
+
+ /* Move data from next into ste */
+ dr_ste_replace(ste, next_ste);
+
+ /* Del the htbl that contains the next_ste.
+ * The origin htbl stay with the same number of entries.
+ */
+ mlx5dr_htbl_put(next_miss_htbl);
+
+ mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE_REDUCED,
+ 0, ste->hw_ste,
+ ste_info_head,
+ send_ste_list,
+ true /* Copy data */);
+
+ stats_tbl->ctrl.num_of_collisions--;
+ stats_tbl->ctrl.num_of_valid_entries--;
+}
+
+/* Free ste that is located in the middle of the miss list:
+ * |__| -->|_prev_ste_|->|_ste_|-->|_next_ste_|
+ */
+static void dr_ste_remove_middle_ste(struct mlx5dr_ste *ste,
+ struct mlx5dr_ste_send_info *ste_info,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *stats_tbl)
+{
+ struct mlx5dr_ste *prev_ste;
+ u64 miss_addr;
+
+ prev_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->prev, struct mlx5dr_ste,
+ miss_list_node);
+ if (!prev_ste) {
+ WARN_ON(true);
+ return;
+ }
+
+ miss_addr = mlx5dr_ste_get_miss_addr(ste->hw_ste);
+ mlx5dr_ste_set_miss_addr(prev_ste->hw_ste, miss_addr);
+
+ mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_REDUCED, 0,
+ prev_ste->hw_ste, ste_info,
+ send_ste_list, true /* Copy data*/);
+
+ list_del_init(&ste->miss_list_node);
+
+ stats_tbl->ctrl.num_of_valid_entries--;
+ stats_tbl->ctrl.num_of_collisions--;
+}
+
+void mlx5dr_ste_free(struct mlx5dr_ste *ste,
+ struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ struct mlx5dr_ste_send_info *cur_ste_info, *tmp_ste_info;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_ste_send_info ste_info_head;
+ struct mlx5dr_ste *next_ste, *first_ste;
+ bool put_on_origin_table = true;
+ struct mlx5dr_ste_htbl *stats_tbl;
+ LIST_HEAD(send_ste_list);
+
+ first_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->next,
+ struct mlx5dr_ste, miss_list_node);
+ stats_tbl = first_ste->htbl;
+
+ /* Two options:
+ * 1. ste is head:
+ * a. head ste is the only ste in the miss list
+ * b. head ste is not the only ste in the miss-list
+ * 2. ste is not head
+ */
+ if (first_ste == ste) { /* Ste is the head */
+ struct mlx5dr_ste *last_ste;
+
+ last_ste = list_last_entry(mlx5dr_ste_get_miss_list(ste),
+ struct mlx5dr_ste, miss_list_node);
+ if (last_ste == first_ste)
+ next_ste = NULL;
+ else
+ next_ste = list_entry(ste->miss_list_node.next,
+ struct mlx5dr_ste, miss_list_node);
+
+ if (!next_ste) {
+ /* One and only entry in the list */
+ dr_ste_remove_head_ste(ste, nic_matcher,
+ &ste_info_head,
+ &send_ste_list,
+ stats_tbl);
+ } else {
+ /* First but not only entry in the list */
+ dr_ste_replace_head_ste(ste, next_ste, &ste_info_head,
+ &send_ste_list, stats_tbl);
+ put_on_origin_table = false;
+ }
+ } else { /* Ste in the middle of the list */
+ dr_ste_remove_middle_ste(ste, &ste_info_head, &send_ste_list, stats_tbl);
+ }
+
+ /* Update HW */
+ list_for_each_entry_safe(cur_ste_info, tmp_ste_info,
+ &send_ste_list, send_list) {
+ list_del(&cur_ste_info->send_list);
+ mlx5dr_send_postsend_ste(dmn, cur_ste_info->ste,
+ cur_ste_info->data, cur_ste_info->size,
+ cur_ste_info->offset);
+ }
+
+ if (put_on_origin_table)
+ mlx5dr_htbl_put(ste->htbl);
+}
+
+bool mlx5dr_ste_equal_tag(void *src, void *dst)
+{
+ struct dr_hw_ste_format *s_hw_ste = (struct dr_hw_ste_format *)src;
+ struct dr_hw_ste_format *d_hw_ste = (struct dr_hw_ste_format *)dst;
+
+ return !memcmp(s_hw_ste->tag, d_hw_ste->tag, DR_STE_SIZE_TAG);
+}
+
+void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste,
+ struct mlx5dr_ste_htbl *next_htbl)
+{
+ struct mlx5dr_icm_chunk *chunk = next_htbl->chunk;
+
+ mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries);
+}
+
+void mlx5dr_ste_set_miss_addr(u8 *hw_ste_p, u64 miss_addr)
+{
+ u64 index = miss_addr >> 6;
+
+ /* Miss address for TX and RX STEs located in the same offsets */
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32, index >> 26);
+ MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6, index);
+}
+
+void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr)
+{
+ u8 *hw_ste = ste->hw_ste;
+
+ MLX5_SET(ste_rx_steering_mult, hw_ste, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE);
+ mlx5dr_ste_set_miss_addr(hw_ste, miss_addr);
+ dr_ste_set_always_miss((struct dr_hw_ste_format *)ste->hw_ste);
+}
+
+/* The assumption here is that we don't update the ste->hw_ste if it is not
+ * used ste, so it will be all zero, checking the next_lu_type.
+ */
+bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)p_hw_ste;
+
+ if (MLX5_GET(ste_general, hw_ste, next_lu_type) ==
+ MLX5DR_STE_LU_TYPE_NOP)
+ return true;
+
+ return false;
+}
+
+bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste)
+{
+ return !refcount_read(&ste->refcount);
+}
+
+static u16 get_bits_per_mask(u16 byte_mask)
+{
+ u16 bits = 0;
+
+ while (byte_mask) {
+ byte_mask = byte_mask & (byte_mask - 1);
+ bits++;
+ }
+
+ return bits;
+}
+
+/* Init one ste as a pattern for ste data array */
+void mlx5dr_ste_set_formatted_ste(u16 gvmi,
+ struct mlx5dr_domain_rx_tx *nic_dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ u8 *formatted_ste,
+ struct mlx5dr_htbl_connect_info *connect_info)
+{
+ struct mlx5dr_ste ste = {};
+
+ mlx5dr_ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi);
+ ste.hw_ste = formatted_ste;
+
+ if (connect_info->type == CONNECT_HIT)
+ dr_ste_always_hit_htbl(&ste, connect_info->hit_next_htbl);
+ else
+ mlx5dr_ste_always_miss_addr(&ste, connect_info->miss_icm_addr);
+}
+
+int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain_rx_tx *nic_dmn,
+ struct mlx5dr_ste_htbl *htbl,
+ struct mlx5dr_htbl_connect_info *connect_info,
+ bool update_hw_ste)
+{
+ u8 formatted_ste[DR_STE_SIZE] = {};
+
+ mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi,
+ nic_dmn,
+ htbl,
+ formatted_ste,
+ connect_info);
+
+ return mlx5dr_send_postsend_formatted_htbl(dmn, htbl, formatted_ste, update_hw_ste);
+}
+
+int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste *ste,
+ u8 *cur_hw_ste,
+ enum mlx5dr_icm_chunk_size log_table_size)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)cur_hw_ste;
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *next_htbl;
+
+ if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) {
+ u32 bits_in_mask;
+ u8 next_lu_type;
+ u16 byte_mask;
+
+ next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type);
+ byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask);
+
+ /* Don't allocate table more than required,
+ * the size of the table defined via the byte_mask, so no need
+ * to allocate more than that.
+ */
+ bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE;
+ log_table_size = min(log_table_size, bits_in_mask);
+
+ next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ log_table_size,
+ next_lu_type,
+ byte_mask);
+ if (!next_htbl) {
+ mlx5dr_dbg(dmn, "Failed allocating table\n");
+ return -ENOMEM;
+ }
+
+ /* Write new table to HW */
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr;
+ if (mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, next_htbl,
+ &info, false)) {
+ mlx5dr_info(dmn, "Failed writing table to HW\n");
+ goto free_table;
+ }
+
+ mlx5dr_ste_set_hit_addr_by_next_htbl(cur_hw_ste, next_htbl);
+ ste->next_htbl = next_htbl;
+ next_htbl->pointing_ste = ste;
+ }
+
+ return 0;
+
+free_table:
+ mlx5dr_ste_htbl_free(next_htbl);
+ return -ENOENT;
+}
+
+static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl)
+{
+ struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl;
+ int num_of_entries;
+
+ htbl->ctrl.may_grow = true;
+
+ if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1)
+ htbl->ctrl.may_grow = false;
+
+ /* Threshold is 50%, one is added to table of size 1 */
+ num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size);
+ ctrl->increase_threshold = (num_of_entries + 1) / 2;
+}
+
+struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool,
+ enum mlx5dr_icm_chunk_size chunk_size,
+ u8 lu_type, u16 byte_mask)
+{
+ struct mlx5dr_icm_chunk *chunk;
+ struct mlx5dr_ste_htbl *htbl;
+ int i;
+
+ htbl = kzalloc(sizeof(*htbl), GFP_KERNEL);
+ if (!htbl)
+ return NULL;
+
+ chunk = mlx5dr_icm_alloc_chunk(pool, chunk_size);
+ if (!chunk)
+ goto out_free_htbl;
+
+ htbl->chunk = chunk;
+ htbl->lu_type = lu_type;
+ htbl->byte_mask = byte_mask;
+ htbl->ste_arr = chunk->ste_arr;
+ htbl->hw_ste_arr = chunk->hw_ste_arr;
+ htbl->miss_list = chunk->miss_list;
+ refcount_set(&htbl->refcount, 0);
+
+ for (i = 0; i < chunk->num_of_entries; i++) {
+ struct mlx5dr_ste *ste = &htbl->ste_arr[i];
+
+ ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
+ ste->htbl = htbl;
+ refcount_set(&ste->refcount, 0);
+ INIT_LIST_HEAD(&ste->miss_list_node);
+ INIT_LIST_HEAD(&htbl->miss_list[i]);
+ INIT_LIST_HEAD(&ste->rule_list);
+ }
+
+ htbl->chunk_size = chunk_size;
+ dr_ste_set_ctrl(htbl);
+ return htbl;
+
+out_free_htbl:
+ kfree(htbl);
+ return NULL;
+}
+
+int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl)
+{
+ if (refcount_read(&htbl->refcount))
+ return -EBUSY;
+
+ mlx5dr_icm_free_chunk(htbl->chunk);
+ kfree(htbl);
+ return 0;
+}
+
+int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn,
+ u8 match_criteria,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_match_param *value)
+{
+ if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) {
+ if (mask->misc.source_port && mask->misc.source_port != 0xffff) {
+ mlx5dr_dbg(dmn, "Partial mask source_port is not supported\n");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_match_param *value,
+ u8 *ste_arr)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_ste_build *sb;
+ int ret, i;
+
+ ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria,
+ &matcher->mask, value);
+ if (ret)
+ return ret;
+
+ sb = nic_matcher->ste_builder;
+ for (i = 0; i < nic_matcher->num_of_builders; i++) {
+ mlx5dr_ste_init(ste_arr,
+ sb->lu_type,
+ nic_dmn->ste_type,
+ dmn->info.caps.gvmi);
+
+ mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask);
+
+ ret = sb->ste_build_tag_func(value, sb, ste_arr);
+ if (ret)
+ return ret;
+
+ /* Connect the STEs */
+ if (i < (nic_matcher->num_of_builders - 1)) {
+ /* Need the next builder for these fields,
+ * not relevant for the last ste in the chain.
+ */
+ sb++;
+ MLX5_SET(ste_general, ste_arr, next_lu_type, sb->lu_type);
+ MLX5_SET(ste_general, ste_arr, byte_mask, sb->byte_mask);
+ }
+ ste_arr += DR_STE_SIZE;
+ }
+ return 0;
+}
+
+static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_15_0, mask, dmac_15_0);
+
+ if (mask->smac_47_16 || mask->smac_15_0) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_47_32,
+ mask->smac_47_16 >> 16);
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_31_0,
+ mask->smac_47_16 << 16 | mask->smac_15_0);
+ mask->smac_47_16 = 0;
+ mask->smac_15_0 = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK(eth_l2_src_dst, bit_mask, l3_type, mask, ip_version);
+
+ if (mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ } else if (mask->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1);
+ mask->svlan_tag = 0;
+ }
+
+ if (mask->cvlan_tag || mask->svlan_tag) {
+ pr_info("Invalid c/svlan mask configuration\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec)
+{
+ spec->gre_c_present = MLX5_GET(fte_match_set_misc, mask, gre_c_present);
+ spec->gre_k_present = MLX5_GET(fte_match_set_misc, mask, gre_k_present);
+ spec->gre_s_present = MLX5_GET(fte_match_set_misc, mask, gre_s_present);
+ spec->source_vhca_port = MLX5_GET(fte_match_set_misc, mask, source_vhca_port);
+ spec->source_sqn = MLX5_GET(fte_match_set_misc, mask, source_sqn);
+
+ spec->source_port = MLX5_GET(fte_match_set_misc, mask, source_port);
+
+ spec->outer_second_prio = MLX5_GET(fte_match_set_misc, mask, outer_second_prio);
+ spec->outer_second_cfi = MLX5_GET(fte_match_set_misc, mask, outer_second_cfi);
+ spec->outer_second_vid = MLX5_GET(fte_match_set_misc, mask, outer_second_vid);
+ spec->inner_second_prio = MLX5_GET(fte_match_set_misc, mask, inner_second_prio);
+ spec->inner_second_cfi = MLX5_GET(fte_match_set_misc, mask, inner_second_cfi);
+ spec->inner_second_vid = MLX5_GET(fte_match_set_misc, mask, inner_second_vid);
+
+ spec->outer_second_cvlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, outer_second_cvlan_tag);
+ spec->inner_second_cvlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, inner_second_cvlan_tag);
+ spec->outer_second_svlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, outer_second_svlan_tag);
+ spec->inner_second_svlan_tag =
+ MLX5_GET(fte_match_set_misc, mask, inner_second_svlan_tag);
+
+ spec->gre_protocol = MLX5_GET(fte_match_set_misc, mask, gre_protocol);
+
+ spec->gre_key_h = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi);
+ spec->gre_key_l = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo);
+
+ spec->vxlan_vni = MLX5_GET(fte_match_set_misc, mask, vxlan_vni);
+
+ spec->geneve_vni = MLX5_GET(fte_match_set_misc, mask, geneve_vni);
+ spec->geneve_oam = MLX5_GET(fte_match_set_misc, mask, geneve_oam);
+
+ spec->outer_ipv6_flow_label =
+ MLX5_GET(fte_match_set_misc, mask, outer_ipv6_flow_label);
+
+ spec->inner_ipv6_flow_label =
+ MLX5_GET(fte_match_set_misc, mask, inner_ipv6_flow_label);
+
+ spec->geneve_opt_len = MLX5_GET(fte_match_set_misc, mask, geneve_opt_len);
+ spec->geneve_protocol_type =
+ MLX5_GET(fte_match_set_misc, mask, geneve_protocol_type);
+
+ spec->bth_dst_qp = MLX5_GET(fte_match_set_misc, mask, bth_dst_qp);
+}
+
+static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec)
+{
+ u32 raw_ip[4];
+
+ spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16);
+
+ spec->smac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0);
+ spec->ethertype = MLX5_GET(fte_match_set_lyr_2_4, mask, ethertype);
+
+ spec->dmac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16);
+
+ spec->dmac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0);
+ spec->first_prio = MLX5_GET(fte_match_set_lyr_2_4, mask, first_prio);
+ spec->first_cfi = MLX5_GET(fte_match_set_lyr_2_4, mask, first_cfi);
+ spec->first_vid = MLX5_GET(fte_match_set_lyr_2_4, mask, first_vid);
+
+ spec->ip_protocol = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_protocol);
+ spec->ip_dscp = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_dscp);
+ spec->ip_ecn = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_ecn);
+ spec->cvlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, cvlan_tag);
+ spec->svlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, svlan_tag);
+ spec->frag = MLX5_GET(fte_match_set_lyr_2_4, mask, frag);
+ spec->ip_version = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_version);
+ spec->tcp_flags = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_flags);
+ spec->tcp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_sport);
+ spec->tcp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_dport);
+
+ spec->ttl_hoplimit = MLX5_GET(fte_match_set_lyr_2_4, mask, ttl_hoplimit);
+
+ spec->udp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_sport);
+ spec->udp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_dport);
+
+ memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+ src_ipv4_src_ipv6.ipv6_layout.ipv6),
+ sizeof(raw_ip));
+
+ spec->src_ip_127_96 = be32_to_cpu(raw_ip[0]);
+ spec->src_ip_95_64 = be32_to_cpu(raw_ip[1]);
+ spec->src_ip_63_32 = be32_to_cpu(raw_ip[2]);
+ spec->src_ip_31_0 = be32_to_cpu(raw_ip[3]);
+
+ memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask,
+ dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+ sizeof(raw_ip));
+
+ spec->dst_ip_127_96 = be32_to_cpu(raw_ip[0]);
+ spec->dst_ip_95_64 = be32_to_cpu(raw_ip[1]);
+ spec->dst_ip_63_32 = be32_to_cpu(raw_ip[2]);
+ spec->dst_ip_31_0 = be32_to_cpu(raw_ip[3]);
+}
+
+static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec)
+{
+ spec->outer_first_mpls_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_label);
+ spec->outer_first_mpls_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp);
+ spec->outer_first_mpls_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos);
+ spec->outer_first_mpls_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl);
+ spec->inner_first_mpls_label =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_label);
+ spec->inner_first_mpls_exp =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp);
+ spec->inner_first_mpls_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos);
+ spec->inner_first_mpls_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl);
+ spec->outer_first_mpls_over_gre_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label);
+ spec->outer_first_mpls_over_gre_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp);
+ spec->outer_first_mpls_over_gre_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos);
+ spec->outer_first_mpls_over_gre_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl);
+ spec->outer_first_mpls_over_udp_label =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label);
+ spec->outer_first_mpls_over_udp_exp =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp);
+ spec->outer_first_mpls_over_udp_s_bos =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos);
+ spec->outer_first_mpls_over_udp_ttl =
+ MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl);
+ spec->metadata_reg_c_7 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_7);
+ spec->metadata_reg_c_6 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_6);
+ spec->metadata_reg_c_5 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_5);
+ spec->metadata_reg_c_4 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_4);
+ spec->metadata_reg_c_3 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_3);
+ spec->metadata_reg_c_2 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_2);
+ spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1);
+ spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0);
+ spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a);
+ spec->metadata_reg_b = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_b);
+}
+
+static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec)
+{
+ spec->inner_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_seq_num);
+ spec->outer_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_seq_num);
+ spec->inner_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_ack_num);
+ spec->outer_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_ack_num);
+ spec->outer_vxlan_gpe_vni =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_vni);
+ spec->outer_vxlan_gpe_next_protocol =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol);
+ spec->outer_vxlan_gpe_flags =
+ MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_flags);
+ spec->icmpv4_header_data = MLX5_GET(fte_match_set_misc3, mask, icmp_header_data);
+ spec->icmpv6_header_data =
+ MLX5_GET(fte_match_set_misc3, mask, icmpv6_header_data);
+ spec->icmpv4_type = MLX5_GET(fte_match_set_misc3, mask, icmp_type);
+ spec->icmpv4_code = MLX5_GET(fte_match_set_misc3, mask, icmp_code);
+ spec->icmpv6_type = MLX5_GET(fte_match_set_misc3, mask, icmpv6_type);
+ spec->icmpv6_code = MLX5_GET(fte_match_set_misc3, mask, icmpv6_code);
+}
+
+void mlx5dr_ste_copy_param(u8 match_criteria,
+ struct mlx5dr_match_param *set_param,
+ struct mlx5dr_match_parameters *mask)
+{
+ u8 tail_param[MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4)] = {};
+ u8 *data = (u8 *)mask->match_buf;
+ size_t param_location;
+ void *buff;
+
+ if (match_criteria & DR_MATCHER_CRITERIA_OUTER) {
+ if (mask->match_sz < sizeof(struct mlx5dr_match_spec)) {
+ memcpy(tail_param, data, mask->match_sz);
+ buff = tail_param;
+ } else {
+ buff = mask->match_buf;
+ }
+ dr_ste_copy_mask_spec(buff, &set_param->outer);
+ }
+ param_location = sizeof(struct mlx5dr_match_spec);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc(buff, &set_param->misc);
+ }
+ param_location += sizeof(struct mlx5dr_match_misc);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_INNER) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_spec)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_spec(buff, &set_param->inner);
+ }
+ param_location += sizeof(struct mlx5dr_match_spec);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC2) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc2)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc2(buff, &set_param->misc2);
+ }
+
+ param_location += sizeof(struct mlx5dr_match_misc2);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC3) {
+ if (mask->match_sz < param_location +
+ sizeof(struct mlx5dr_match_misc3)) {
+ memcpy(tail_param, data + param_location,
+ mask->match_sz - param_location);
+ buff = tail_param;
+ } else {
+ buff = data + param_location;
+ }
+ dr_ste_copy_mask_misc3(buff, &set_param->misc3);
+ }
+}
+
+static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_15_0, spec, dmac_15_0);
+
+ if (spec->smac_47_16 || spec->smac_15_0) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, smac_47_32,
+ spec->smac_47_16 >> 16);
+ MLX5_SET(ste_eth_l2_src_dst, tag, smac_31_0,
+ spec->smac_47_16 << 16 | spec->smac_15_0);
+ spec->smac_47_16 = 0;
+ spec->smac_15_0 = 0;
+ }
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ pr_info("Unsupported ip_version value\n");
+ return -EINVAL;
+ }
+ }
+
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_src_dst, tag, first_priority, spec, first_prio);
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+ return 0;
+}
+
+int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_des_tag;
+
+ return 0;
+}
+
+static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_127_96, mask, dst_ip_127_96);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_95_64, mask, dst_ip_95_64);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_63_32, mask, dst_ip_63_32);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_31_0, mask, dst_ip_31_0);
+}
+
+static int dr_ste_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_63_32, spec, dst_ip_63_32);
+ DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_31_0, spec, dst_ip_31_0);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv6_dst_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_dst_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv6_src_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_127_96, mask, src_ip_127_96);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_95_64, mask, src_ip_95_64);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_63_32, mask, src_ip_63_32);
+ DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_31_0, mask, src_ip_31_0);
+}
+
+static int dr_ste_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_63_32, spec, src_ip_63_32);
+ DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_31_0, spec, src_ip_31_0);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv6_src_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_SRC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_src_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(struct mlx5dr_match_param *value,
+ bool inner,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_address, mask, dst_ip_31_0);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_address, mask, src_ip_31_0);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_port, mask, tcp_dport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ destination_port, mask, udp_dport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_port, mask, tcp_sport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ source_port, mask, udp_sport);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ protocol, mask, ip_protocol);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ dscp, mask, ip_dscp);
+ DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask,
+ ecn, mask, ip_ecn);
+
+ if (mask->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, bit_mask, mask);
+ mask->tcp_flags = 0;
+ }
+}
+
+static int dr_ste_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_address, spec, dst_ip_31_0);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_address, spec, src_ip_31_0);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, tcp_dport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, udp_dport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, tcp_sport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, udp_sport);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, protocol, spec, ip_protocol);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, dscp, spec, ip_dscp);
+ DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, ecn, spec, ip_ecn);
+
+ if (spec->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, tag, spec);
+ spec->tcp_flags = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_5_TUPLE, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_5_tuple_tag;
+}
+
+static void
+dr_ste_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, ip_fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, l3_ethertype, mask, ethertype);
+ DR_STE_SET_MASK(eth_l2_src, bit_mask, l3_type, mask, ip_version);
+
+ if (mask->svlan_tag || mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ mask->svlan_tag = 0;
+ }
+
+ if (inner) {
+ if (misc_mask->inner_second_cvlan_tag ||
+ misc_mask->inner_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1);
+ misc_mask->inner_second_cvlan_tag = 0;
+ misc_mask->inner_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_vlan_id, misc_mask, inner_second_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_cfi, misc_mask, inner_second_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_priority, misc_mask, inner_second_prio);
+ } else {
+ if (misc_mask->outer_second_cvlan_tag ||
+ misc_mask->outer_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1);
+ misc_mask->outer_second_cvlan_tag = 0;
+ misc_mask->outer_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_vlan_id, misc_mask, outer_second_vid);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_cfi, misc_mask, outer_second_cfi);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask,
+ second_priority, misc_mask, outer_second_prio);
+ }
+}
+
+static int dr_ste_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value,
+ bool inner, u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc_spec = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, first_priority, spec, first_prio);
+ DR_STE_SET_TAG(eth_l2_src, tag, ip_fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l2_src, tag, l3_ethertype, spec, ethertype);
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ pr_info("Unsupported ip_version value\n");
+ return -EINVAL;
+ }
+ }
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+
+ if (inner) {
+ if (misc_spec->inner_second_cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN);
+ misc_spec->inner_second_cvlan_tag = 0;
+ } else if (misc_spec->inner_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN);
+ misc_spec->inner_second_svlan_tag = 0;
+ }
+
+ DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, inner_second_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, inner_second_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, inner_second_prio);
+ } else {
+ if (misc_spec->outer_second_cvlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN);
+ misc_spec->outer_second_cvlan_tag = 0;
+ } else if (misc_spec->outer_second_svlan_tag) {
+ MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN);
+ misc_spec->outer_second_svlan_tag = 0;
+ }
+ DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, outer_second_vid);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, outer_second_cfi);
+ DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, outer_second_prio);
+ }
+
+ return 0;
+}
+
+static void dr_ste_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_47_16, mask, smac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_15_0, mask, smac_15_0);
+
+ dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask);
+}
+
+static int dr_ste_build_eth_l2_src_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_src, tag, smac_47_16, spec, smac_47_16);
+ DR_STE_SET_TAG(eth_l2_src, tag, smac_15_0, spec, smac_15_0);
+
+ return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+}
+
+void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_src_bit_mask(mask, inner, sb->bit_mask);
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_tag;
+}
+
+static void dr_ste_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_15_0, mask, dmac_15_0);
+
+ dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask);
+}
+
+static int dr_ste_build_eth_l2_dst_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_dst, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_dst, tag, dmac_15_0, spec, dmac_15_0);
+
+ return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p);
+}
+
+void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_dst_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_DST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_dst_tag;
+}
+
+static void dr_ste_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+ struct mlx5dr_match_misc *misc = &value->misc;
+
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_47_16, mask, dmac_47_16);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_15_0, mask, dmac_15_0);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_vlan_id, mask, first_vid);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_cfi, mask, first_cfi);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_priority, mask, first_prio);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, ip_fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, l3_ethertype, mask, ethertype);
+ DR_STE_SET_MASK(eth_l2_tnl, bit_mask, l3_type, mask, ip_version);
+
+ if (misc->vxlan_vni) {
+ MLX5_SET(ste_eth_l2_tnl, bit_mask,
+ l2_tunneling_network_id, (misc->vxlan_vni << 8));
+ misc->vxlan_vni = 0;
+ }
+
+ if (mask->svlan_tag || mask->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, bit_mask, first_vlan_qualifier, -1);
+ mask->cvlan_tag = 0;
+ mask->svlan_tag = 0;
+ }
+}
+
+static int dr_ste_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_47_16, spec, dmac_47_16);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_15_0, spec, dmac_15_0);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_vlan_id, spec, first_vid);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_cfi, spec, first_cfi);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, ip_fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, first_priority, spec, first_prio);
+ DR_STE_SET_TAG(eth_l2_tnl, tag, l3_ethertype, spec, ethertype);
+
+ if (misc->vxlan_vni) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l2_tunneling_network_id,
+ (misc->vxlan_vni << 8));
+ misc->vxlan_vni = 0;
+ }
+
+ if (spec->cvlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_CVLAN);
+ spec->cvlan_tag = 0;
+ } else if (spec->svlan_tag) {
+ MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_SVLAN);
+ spec->svlan_tag = 0;
+ }
+
+ if (spec->ip_version) {
+ if (spec->ip_version == IP_VERSION_IPV4) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV4);
+ spec->ip_version = 0;
+ } else if (spec->ip_version == IP_VERSION_IPV6) {
+ MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV6);
+ spec->ip_version = 0;
+ } else {
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask, bool inner, bool rx)
+{
+ dr_ste_build_eth_l2_tnl_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l2_tnl_tag;
+}
+
+static void dr_ste_build_eth_l3_ipv4_misc_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l3_ipv4_misc, bit_mask, time_to_live, mask, ttl_hoplimit);
+}
+
+static int dr_ste_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l3_ipv4_misc_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_MISC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_misc_tag;
+}
+
+static void dr_ste_build_ipv6_l3_l4_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer;
+
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, tcp_dport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, tcp_sport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, udp_dport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, udp_sport);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, protocol, mask, ip_protocol);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, fragmented, mask, frag);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, dscp, mask, ip_dscp);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, ecn, mask, ip_ecn);
+ DR_STE_SET_MASK_V(eth_l4, bit_mask, ipv6_hop_limit, mask, ttl_hoplimit);
+
+ if (mask->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l4, bit_mask, mask);
+ mask->tcp_flags = 0;
+ }
+}
+
+static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer;
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport);
+ DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport);
+ DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, udp_dport);
+ DR_STE_SET_TAG(eth_l4, tag, src_port, spec, udp_sport);
+ DR_STE_SET_TAG(eth_l4, tag, protocol, spec, ip_protocol);
+ DR_STE_SET_TAG(eth_l4, tag, fragmented, spec, frag);
+ DR_STE_SET_TAG(eth_l4, tag, dscp, spec, ip_dscp);
+ DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn);
+ DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit);
+
+ if (spec->tcp_flags) {
+ DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec);
+ spec->tcp_flags = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_ipv6_l3_l4_tag;
+}
+
+static int dr_ste_build_empty_always_hit_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ return 0;
+}
+
+void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx)
+{
+ sb->rx = rx;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_DONT_CARE;
+ sb->byte_mask = 0;
+ sb->ste_build_tag_func = &dr_ste_build_empty_always_hit_tag;
+}
+
+static void dr_ste_build_mpls_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc2_mask = &value->misc2;
+
+ if (inner)
+ DR_STE_SET_MPLS_MASK(mpls, misc2_mask, inner, bit_mask);
+ else
+ DR_STE_SET_MPLS_MASK(mpls, misc2_mask, outer, bit_mask);
+}
+
+static int dr_ste_build_mpls_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ if (sb->inner)
+ DR_STE_SET_MPLS_TAG(mpls, misc2_mask, inner, tag);
+ else
+ DR_STE_SET_MPLS_TAG(mpls, misc2_mask, outer, tag);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_mpls_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(MPLS_FIRST, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_mpls_tag;
+}
+
+static void dr_ste_build_gre_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_protocol, misc_mask, gre_protocol);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_k_present, misc_mask, gre_k_present);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_key_h, misc_mask, gre_key_h);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_key_l, misc_mask, gre_key_l);
+
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_c_present, misc_mask, gre_c_present);
+ DR_STE_SET_MASK_V(gre, bit_mask, gre_s_present, misc_mask, gre_s_present);
+}
+
+static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(gre, tag, gre_protocol, misc, gre_protocol);
+
+ DR_STE_SET_TAG(gre, tag, gre_k_present, misc, gre_k_present);
+ DR_STE_SET_TAG(gre, tag, gre_key_h, misc, gre_key_h);
+ DR_STE_SET_TAG(gre, tag, gre_key_l, misc, gre_key_l);
+
+ DR_STE_SET_TAG(gre, tag, gre_c_present, misc, gre_c_present);
+
+ DR_STE_SET_TAG(gre, tag, gre_s_present, misc, gre_s_present);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask, bool inner, bool rx)
+{
+ dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_GRE;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_gre_tag;
+}
+
+static void dr_ste_build_flex_parser_0_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) {
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_gre_label);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_gre_exp);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_gre_s_bos);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_gre_ttl);
+ } else {
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_udp_label);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_udp_exp);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_udp_s_bos);
+
+ DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_udp_ttl);
+ }
+}
+
+static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) {
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_gre_label);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_gre_exp);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_gre_s_bos);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_gre_ttl);
+ } else {
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label,
+ misc_2_mask, outer_first_mpls_over_udp_label);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp,
+ misc_2_mask, outer_first_mpls_over_udp_exp);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos,
+ misc_2_mask, outer_first_mpls_over_udp_s_bos);
+
+ DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl,
+ misc_2_mask, outer_first_mpls_over_udp_ttl);
+ }
+ return 0;
+}
+
+void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_0;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_0_tag;
+}
+
+#define ICMP_TYPE_OFFSET_FIRST_DW 24
+#define ICMP_CODE_OFFSET_FIRST_DW 16
+#define ICMP_HEADER_DATA_OFFSET_SECOND_DW 0
+
+static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3;
+ bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask);
+ u32 icmp_header_data_mask;
+ u32 icmp_type_mask;
+ u32 icmp_code_mask;
+ int dw0_location;
+ int dw1_location;
+
+ if (is_ipv4_mask) {
+ icmp_header_data_mask = misc_3_mask->icmpv4_header_data;
+ icmp_type_mask = misc_3_mask->icmpv4_type;
+ icmp_code_mask = misc_3_mask->icmpv4_code;
+ dw0_location = caps->flex_parser_id_icmp_dw0;
+ dw1_location = caps->flex_parser_id_icmp_dw1;
+ } else {
+ icmp_header_data_mask = misc_3_mask->icmpv6_header_data;
+ icmp_type_mask = misc_3_mask->icmpv6_type;
+ icmp_code_mask = misc_3_mask->icmpv6_code;
+ dw0_location = caps->flex_parser_id_icmpv6_dw0;
+ dw1_location = caps->flex_parser_id_icmpv6_dw1;
+ }
+
+ switch (dw0_location) {
+ case 4:
+ if (icmp_type_mask) {
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4,
+ (icmp_type_mask << ICMP_TYPE_OFFSET_FIRST_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_type = 0;
+ else
+ misc_3_mask->icmpv6_type = 0;
+ }
+ if (icmp_code_mask) {
+ u32 cur_val = MLX5_GET(ste_flex_parser_1, bit_mask,
+ flex_parser_4);
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4,
+ cur_val | (icmp_code_mask << ICMP_CODE_OFFSET_FIRST_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_code = 0;
+ else
+ misc_3_mask->icmpv6_code = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (dw1_location) {
+ case 5:
+ if (icmp_header_data_mask) {
+ MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_5,
+ (icmp_header_data_mask << ICMP_HEADER_DATA_OFFSET_SECOND_DW));
+ if (is_ipv4_mask)
+ misc_3_mask->icmpv4_header_data = 0;
+ else
+ misc_3_mask->icmpv6_header_data = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc_3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+ u32 icmp_header_data;
+ int dw0_location;
+ int dw1_location;
+ u32 icmp_type;
+ u32 icmp_code;
+ bool is_ipv4;
+
+ is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3);
+ if (is_ipv4) {
+ icmp_header_data = misc_3->icmpv4_header_data;
+ icmp_type = misc_3->icmpv4_type;
+ icmp_code = misc_3->icmpv4_code;
+ dw0_location = sb->caps->flex_parser_id_icmp_dw0;
+ dw1_location = sb->caps->flex_parser_id_icmp_dw1;
+ } else {
+ icmp_header_data = misc_3->icmpv6_header_data;
+ icmp_type = misc_3->icmpv6_type;
+ icmp_code = misc_3->icmpv6_code;
+ dw0_location = sb->caps->flex_parser_id_icmpv6_dw0;
+ dw1_location = sb->caps->flex_parser_id_icmpv6_dw1;
+ }
+
+ switch (dw0_location) {
+ case 4:
+ if (icmp_type) {
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_4,
+ (icmp_type << ICMP_TYPE_OFFSET_FIRST_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_type = 0;
+ else
+ misc_3->icmpv6_type = 0;
+ }
+
+ if (icmp_code) {
+ u32 cur_val = MLX5_GET(ste_flex_parser_1, tag,
+ flex_parser_4);
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_4,
+ cur_val | (icmp_code << ICMP_CODE_OFFSET_FIRST_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_code = 0;
+ else
+ misc_3->icmpv6_code = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ switch (dw1_location) {
+ case 5:
+ if (icmp_header_data) {
+ MLX5_SET(ste_flex_parser_1, tag, flex_parser_5,
+ (icmp_header_data << ICMP_HEADER_DATA_OFFSET_SECOND_DW));
+ if (is_ipv4)
+ misc_3->icmpv4_header_data = 0;
+ else
+ misc_3->icmpv6_header_data = 0;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_flex_parser_1_bit_mask(mask, caps, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->caps = caps;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_1;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_1_tag;
+
+ return 0;
+}
+
+static void dr_ste_build_general_purpose_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(general_purpose, bit_mask,
+ general_purpose_lookup_field, misc_2_mask,
+ metadata_reg_a);
+}
+
+static int dr_ste_build_general_purpose_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field,
+ misc_2_mask, metadata_reg_a);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_general_purpose_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_general_purpose_tag;
+}
+
+static void dr_ste_build_eth_l4_misc_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3;
+
+ if (inner) {
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask,
+ inner_tcp_seq_num);
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask,
+ inner_tcp_ack_num);
+ } else {
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask,
+ outer_tcp_seq_num);
+ DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask,
+ outer_tcp_ack_num);
+ }
+}
+
+static int dr_ste_build_eth_l4_misc_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+
+ if (sb->inner) {
+ DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, inner_tcp_seq_num);
+ DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, inner_tcp_ack_num);
+ } else {
+ DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, outer_tcp_seq_num);
+ DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, outer_tcp_ack_num);
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_eth_l4_misc_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4_MISC, rx, inner);
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag;
+}
+
+static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value,
+ bool inner, u8 *bit_mask)
+{
+ struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3;
+
+ if (misc_3_mask->outer_vxlan_gpe_flags ||
+ misc_3_mask->outer_vxlan_gpe_next_protocol) {
+ MLX5_SET(ste_flex_parser_tnl, bit_mask,
+ flex_parser_tunneling_header_63_32,
+ (misc_3_mask->outer_vxlan_gpe_flags << 24) |
+ (misc_3_mask->outer_vxlan_gpe_next_protocol));
+ misc_3_mask->outer_vxlan_gpe_flags = 0;
+ misc_3_mask->outer_vxlan_gpe_next_protocol = 0;
+ }
+
+ if (misc_3_mask->outer_vxlan_gpe_vni) {
+ MLX5_SET(ste_flex_parser_tnl, bit_mask,
+ flex_parser_tunneling_header_31_0,
+ misc_3_mask->outer_vxlan_gpe_vni << 8);
+ misc_3_mask->outer_vxlan_gpe_vni = 0;
+ }
+}
+
+static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc3 *misc3 = &value->misc3;
+ u8 *tag = hw_ste->tag;
+
+ if (misc3->outer_vxlan_gpe_flags ||
+ misc3->outer_vxlan_gpe_next_protocol) {
+ MLX5_SET(ste_flex_parser_tnl, tag,
+ flex_parser_tunneling_header_63_32,
+ (misc3->outer_vxlan_gpe_flags << 24) |
+ (misc3->outer_vxlan_gpe_next_protocol));
+ misc3->outer_vxlan_gpe_flags = 0;
+ misc3->outer_vxlan_gpe_next_protocol = 0;
+ }
+
+ if (misc3->outer_vxlan_gpe_vni) {
+ MLX5_SET(ste_flex_parser_tnl, tag,
+ flex_parser_tunneling_header_31_0,
+ misc3->outer_vxlan_gpe_vni << 8);
+ misc3->outer_vxlan_gpe_vni = 0;
+ }
+
+ return 0;
+}
+
+void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag;
+}
+
+static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_0_h,
+ misc_2_mask, metadata_reg_c_0);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_0_l,
+ misc_2_mask, metadata_reg_c_1);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_1_h,
+ misc_2_mask, metadata_reg_c_2);
+ DR_STE_SET_MASK_V(register_0, bit_mask, register_1_l,
+ misc_2_mask, metadata_reg_c_3);
+}
+
+static int dr_ste_build_register_0_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2 = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0);
+ DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1);
+ DR_STE_SET_TAG(register_0, tag, register_1_h, misc2, metadata_reg_c_2);
+ DR_STE_SET_TAG(register_0, tag, register_1_l, misc2, metadata_reg_c_3);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_register_0_bit_mask(mask, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_register_0_tag;
+}
+
+static void dr_ste_build_register_1_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2;
+
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_2_h,
+ misc_2_mask, metadata_reg_c_4);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_2_l,
+ misc_2_mask, metadata_reg_c_5);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_3_h,
+ misc_2_mask, metadata_reg_c_6);
+ DR_STE_SET_MASK_V(register_1, bit_mask, register_3_l,
+ misc_2_mask, metadata_reg_c_7);
+}
+
+static int dr_ste_build_register_1_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc2 *misc2 = &value->misc2;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4);
+ DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5);
+ DR_STE_SET_TAG(register_1, tag, register_3_h, misc2, metadata_reg_c_6);
+ DR_STE_SET_TAG(register_1, tag, register_3_l, misc2, metadata_reg_c_7);
+
+ return 0;
+}
+
+void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ bool inner, bool rx)
+{
+ dr_ste_build_register_1_bit_mask(mask, sb->bit_mask);
+
+ sb->rx = rx;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_register_1_tag;
+}
+
+static int dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value,
+ u8 *bit_mask)
+{
+ struct mlx5dr_match_misc *misc_mask = &value->misc;
+
+ if (misc_mask->source_port != 0xffff)
+ return -EINVAL;
+
+ DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_gvmi, misc_mask, source_port);
+ DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_qp, misc_mask, source_sqn);
+
+ return 0;
+}
+
+static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value,
+ struct mlx5dr_ste_build *sb,
+ u8 *hw_ste_p)
+{
+ struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+ struct mlx5dr_match_misc *misc = &value->misc;
+ struct mlx5dr_cmd_vport_cap *vport_cap;
+ u8 *tag = hw_ste->tag;
+
+ DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn);
+
+ vport_cap = mlx5dr_get_vport_cap(sb->caps, misc->source_port);
+ if (!vport_cap)
+ return -EINVAL;
+
+ if (vport_cap->vport_gvmi)
+ MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi);
+
+ misc->source_port = 0;
+
+ return 0;
+}
+
+int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_cmd_caps *caps,
+ bool inner, bool rx)
+{
+ int ret;
+
+ ret = dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask);
+ if (ret)
+ return ret;
+
+ sb->rx = rx;
+ sb->caps = caps;
+ sb->inner = inner;
+ sb->lu_type = MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP;
+ sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+ sb->ste_build_tag_func = &dr_ste_build_src_gvmi_qpn_tag;
+
+ return 0;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 07/18] net/mlx5: DR, Expose steering domain functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Domain is the frame for all of the dr (direct rule) objects.
There are different domain types which also affect the object under that
domain. Each domain can hold multiple tables which can hold multiple
matchers and so on, this means that all of the dr (direct rule) objects
exist under a specific domain. The domain object also holds the
resources needed for other objects such as memory management and
communication with the device.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_domain.c | 395 ++++++++++++++++++
1 file changed, 395 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
new file mode 100644
index 000000000000..3b9cf0bccf4d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/mlx5/eswitch.h>
+#include "dr_types.h"
+
+static int dr_domain_init_cache(struct mlx5dr_domain *dmn)
+{
+ /* Per vport cached FW FT for checksum recalculation, this
+ * recalculation is needed due to a HW bug.
+ */
+ dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports,
+ sizeof(dmn->cache.recalc_cs_ft[0]),
+ GFP_KERNEL);
+ if (!dmn->cache.recalc_cs_ft)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn)
+{
+ int i;
+
+ for (i = 0; i < dmn->info.caps.num_vports; i++) {
+ if (!dmn->cache.recalc_cs_ft[i])
+ continue;
+
+ mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]);
+ }
+
+ kfree(dmn->cache.recalc_cs_ft);
+}
+
+int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn,
+ u32 vport_num,
+ u64 *rx_icm_addr)
+{
+ struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
+
+ recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num];
+ if (!recalc_cs_ft) {
+ /* Table not in cache, need to allocate a new one */
+ recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num);
+ if (!recalc_cs_ft)
+ return -EINVAL;
+
+ dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft;
+ }
+
+ *rx_icm_addr = recalc_cs_ft->rx_icm_addr;
+
+ return 0;
+}
+
+static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
+{
+ int ret;
+
+ ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Couldn't allocate PD\n");
+ return ret;
+ }
+
+ dmn->uar = mlx5_get_uars_page(dmn->mdev);
+ if (!dmn->uar) {
+ mlx5dr_err(dmn, "Couldn't allocate UAR\n");
+ goto clean_pd;
+ }
+
+ dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE);
+ if (!dmn->ste_icm_pool) {
+ mlx5dr_err(dmn, "Couldn't get icm memory for %s\n",
+ dev_name(dmn->mdev->device));
+ goto clean_uar;
+ }
+
+ dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION);
+ if (!dmn->action_icm_pool) {
+ mlx5dr_err(dmn, "Couldn't get action icm memory for %s\n",
+ dev_name(dmn->mdev->device));
+ goto free_ste_icm_pool;
+ }
+
+ ret = mlx5dr_send_ring_alloc(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Couldn't create send-ring for %s\n",
+ dev_name(dmn->mdev->device));
+ goto free_action_icm_pool;
+ }
+
+ return 0;
+
+free_action_icm_pool:
+ mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+free_ste_icm_pool:
+ mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+clean_uar:
+ mlx5_put_uars_page(dmn->mdev, dmn->uar);
+clean_pd:
+ mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+
+ return ret;
+}
+
+static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn)
+{
+ mlx5dr_send_ring_free(dmn, dmn->send_ring);
+ mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+ mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+ mlx5_put_uars_page(dmn->mdev, dmn->uar);
+ mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+}
+
+static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
+ bool other_vport,
+ u16 vport_number)
+{
+ struct mlx5dr_cmd_vport_cap *vport_caps;
+ int ret;
+
+ vport_caps = &dmn->info.caps.vports_caps[vport_number];
+
+ ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev,
+ other_vport,
+ vport_number,
+ &vport_caps->icm_address_rx,
+ &vport_caps->icm_address_tx);
+ if (ret)
+ return ret;
+
+ ret = mlx5dr_cmd_query_gvmi(dmn->mdev,
+ other_vport,
+ vport_number,
+ &vport_caps->vport_gvmi);
+ if (ret)
+ return ret;
+
+ vport_caps->num = vport_number;
+ vport_caps->vhca_gvmi = dmn->info.caps.gvmi;
+
+ return 0;
+}
+
+static int dr_domain_query_vports(struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps;
+ struct mlx5dr_cmd_vport_cap *wire_vport;
+ int vport;
+ int ret;
+
+ /* Query vports (except wire vport) */
+ for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) {
+ ret = dr_domain_query_vport(dmn, !!vport, vport);
+ if (ret)
+ return ret;
+ }
+
+ /* Last vport is the wire port */
+ wire_vport = &dmn->info.caps.vports_caps[vport];
+ wire_vport->num = WIRE_PORT;
+ wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx;
+ wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx;
+ wire_vport->vport_gvmi = 0;
+ wire_vport->vhca_gvmi = dmn->info.caps.gvmi;
+
+ return 0;
+}
+
+static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
+ struct mlx5dr_domain *dmn)
+{
+ int ret;
+
+ if (!dmn->info.caps.eswitch_manager)
+ return -EOPNOTSUPP;
+
+ ret = mlx5dr_cmd_query_esw_caps(mdev, &dmn->info.caps.esw_caps);
+ if (ret)
+ return ret;
+
+ dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner;
+ dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx;
+ dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx;
+
+ dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports,
+ sizeof(dmn->info.caps.vports_caps[0]),
+ GFP_KERNEL);
+ if (!dmn->info.caps.vports_caps)
+ return -ENOMEM;
+
+ ret = dr_domain_query_vports(dmn);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed to query vports caps\n");
+ goto free_vports_caps;
+ }
+
+ dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1;
+
+ return 0;
+
+free_vports_caps:
+ kfree(dmn->info.caps.vports_caps);
+ dmn->info.caps.vports_caps = NULL;
+ return ret;
+}
+
+static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
+ struct mlx5dr_domain *dmn)
+{
+ struct mlx5dr_cmd_vport_cap *vport_cap;
+ int ret;
+
+ if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) {
+ mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n");
+ return -EOPNOTSUPP;
+ }
+
+ dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev);
+
+ ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps);
+ if (ret)
+ return ret;
+
+ ret = dr_domain_query_fdb_caps(mdev, dmn);
+ if (ret)
+ return ret;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ if (!dmn->info.caps.rx_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+ dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address;
+ dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address;
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ if (!dmn->info.caps.tx_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+ dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address;
+ dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address;
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ if (!dmn->info.caps.eswitch_manager)
+ return -ENOTSUPP;
+
+ if (!dmn->info.caps.fdb_sw_owner)
+ return -ENOTSUPP;
+
+ dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+ dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+ vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0);
+ if (!vport_cap) {
+ mlx5dr_dbg(dmn, "Failed to get esw manager vport\n");
+ return -ENOENT;
+ }
+
+ dmn->info.supp_sw_steering = true;
+ dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx;
+ dmn->info.rx.default_icm_addr = vport_cap->icm_address_rx;
+ dmn->info.rx.drop_icm_addr = dmn->info.caps.esw_rx_drop_address;
+ dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address;
+ break;
+ default:
+ mlx5dr_dbg(dmn, "Invalid domain\n");
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn)
+{
+ kfree(dmn->info.caps.vports_caps);
+}
+
+struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
+{
+ struct mlx5dr_domain *dmn;
+ int ret;
+
+ if (type > MLX5DR_DOMAIN_TYPE_FDB)
+ return NULL;
+
+ dmn = kzalloc(sizeof(*dmn), GFP_KERNEL);
+ if (!dmn)
+ return NULL;
+
+ dmn->mdev = mdev;
+ dmn->type = type;
+ refcount_set(&dmn->refcount, 1);
+ mutex_init(&dmn->mutex);
+
+ if (dr_domain_caps_init(mdev, dmn)) {
+ mlx5dr_dbg(dmn, "Failed init domain, no caps\n");
+ goto free_domain;
+ }
+
+ dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K;
+ dmn->info.max_log_sw_icm_sz = min_t(u32, DR_CHUNK_SIZE_1024K,
+ dmn->info.caps.log_icm_size);
+
+ if (!dmn->info.supp_sw_steering) {
+ mlx5dr_err(dmn, "SW steering not supported for %s\n",
+ dev_name(mdev->device));
+ goto uninit_caps;
+ }
+
+ /* Allocate resources */
+ ret = dr_domain_init_resources(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed init domain resources for %s\n",
+ dev_name(mdev->device));
+ goto uninit_caps;
+ }
+
+ ret = dr_domain_init_cache(dmn);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed initialize domain cache\n");
+ goto uninit_resourses;
+ }
+
+ /* Init CRC table for htbl CRC calculation */
+ mlx5dr_crc32_init_table();
+
+ return dmn;
+
+uninit_resourses:
+ dr_domain_uninit_resources(dmn);
+uninit_caps:
+ dr_domain_caps_uninit(dmn);
+free_domain:
+ kfree(dmn);
+ return NULL;
+}
+
+/* Assure synchronization of the device steering tables with updates made by SW
+ * insertion.
+ */
+int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
+{
+ int ret = 0;
+
+ if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
+ mutex_lock(&dmn->mutex);
+ ret = mlx5dr_send_ring_force_drain(dmn);
+ mutex_unlock(&dmn->mutex);
+ if (ret)
+ return ret;
+ }
+
+ if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
+ ret = mlx5dr_cmd_sync_steering(dmn->mdev);
+
+ return ret;
+}
+
+int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
+{
+ if (refcount_read(&dmn->refcount) > 1)
+ return -EBUSY;
+
+ /* make sure resources are not used by the hardware */
+ mlx5dr_cmd_sync_steering(dmn->mdev);
+ dr_domain_uninit_cache(dmn);
+ dr_domain_uninit_resources(dmn);
+ dr_domain_caps_uninit(dmn);
+ mutex_destroy(&dmn->mutex);
+ kfree(dmn);
+ return 0;
+}
+
+void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain *peer_dmn)
+{
+ mutex_lock(&dmn->mutex);
+
+ if (dmn->peer_dmn)
+ refcount_dec(&dmn->peer_dmn->refcount);
+
+ dmn->peer_dmn = peer_dmn;
+
+ if (dmn->peer_dmn)
+ refcount_inc(&dmn->peer_dmn->refcount);
+
+ mutex_unlock(&dmn->mutex);
+}
--
2.21.0
^ permalink raw reply related
* [net-next 08/18] net/mlx5: DR, Expose steering table functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Tables are objects which are used for storing matchers, each table
belongs to a domain and defined by the domain type. When a packet
reaches the table it is being processed by each of its matchers until a
successful match. Tables can hold multiple matchers ordered by matcher
priority. Each table has a level.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_table.c | 294 ++++++++++++++++++
1 file changed, 294 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
new file mode 100644
index 000000000000..e178d8d3dbc9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c
@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+ struct mlx5dr_action *action)
+{
+ struct mlx5dr_matcher *last_matcher = NULL;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *last_htbl;
+ int ret;
+
+ if (action && action->action_type != DR_ACTION_TYP_FT)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ if (!list_empty(&tbl->matcher_list))
+ last_matcher = list_last_entry(&tbl->matcher_list,
+ struct mlx5dr_matcher,
+ matcher_list);
+
+ if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX ||
+ tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+ if (last_matcher)
+ last_htbl = last_matcher->rx.e_anchor;
+ else
+ last_htbl = tbl->rx.s_anchor;
+
+ tbl->rx.default_icm_addr = action ?
+ action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr :
+ tbl->rx.nic_dmn->default_icm_addr;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = tbl->rx.default_icm_addr;
+
+ ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+ tbl->rx.nic_dmn,
+ last_htbl,
+ &info, true);
+ if (ret) {
+ mlx5dr_dbg(tbl->dmn, "Failed to set RX miss action, ret %d\n", ret);
+ goto out;
+ }
+ }
+
+ if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX ||
+ tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+ if (last_matcher)
+ last_htbl = last_matcher->tx.e_anchor;
+ else
+ last_htbl = tbl->tx.s_anchor;
+
+ tbl->tx.default_icm_addr = action ?
+ action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr :
+ tbl->tx.nic_dmn->default_icm_addr;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = tbl->tx.default_icm_addr;
+
+ ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+ tbl->tx.nic_dmn,
+ last_htbl, &info, true);
+ if (ret) {
+ mlx5dr_dbg(tbl->dmn, "Failed to set TX miss action, ret %d\n", ret);
+ goto out;
+ }
+ }
+
+ /* Release old action */
+ if (tbl->miss_action)
+ refcount_dec(&tbl->miss_action->refcount);
+
+ /* Set new miss action */
+ tbl->miss_action = action;
+ if (tbl->miss_action)
+ refcount_inc(&action->refcount);
+
+out:
+ mutex_unlock(&tbl->dmn->mutex);
+ return ret;
+}
+
+static void dr_table_uninit_nic(struct mlx5dr_table_rx_tx *nic_tbl)
+{
+ mlx5dr_htbl_put(nic_tbl->s_anchor);
+}
+
+static void dr_table_uninit_fdb(struct mlx5dr_table *tbl)
+{
+ dr_table_uninit_nic(&tbl->rx);
+ dr_table_uninit_nic(&tbl->tx);
+}
+
+static void dr_table_uninit(struct mlx5dr_table *tbl)
+{
+ mutex_lock(&tbl->dmn->mutex);
+
+ switch (tbl->dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ dr_table_uninit_nic(&tbl->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ dr_table_uninit_nic(&tbl->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ dr_table_uninit_fdb(tbl);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+
+ mutex_unlock(&tbl->dmn->mutex);
+}
+
+static int dr_table_init_nic(struct mlx5dr_domain *dmn,
+ struct mlx5dr_table_rx_tx *nic_tbl)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ int ret;
+
+ nic_tbl->default_icm_addr = nic_dmn->default_icm_addr;
+
+ nic_tbl->s_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ MLX5DR_STE_LU_TYPE_DONT_CARE,
+ 0);
+ if (!nic_tbl->s_anchor)
+ return -ENOMEM;
+
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_dmn->default_icm_addr;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ nic_tbl->s_anchor,
+ &info, true);
+ if (ret)
+ goto free_s_anchor;
+
+ mlx5dr_htbl_get(nic_tbl->s_anchor);
+
+ return 0;
+
+free_s_anchor:
+ mlx5dr_ste_htbl_free(nic_tbl->s_anchor);
+ return ret;
+}
+
+static int dr_table_init_fdb(struct mlx5dr_table *tbl)
+{
+ int ret;
+
+ ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+ if (ret)
+ return ret;
+
+ ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+ if (ret)
+ goto destroy_rx;
+
+ return 0;
+
+destroy_rx:
+ dr_table_uninit_nic(&tbl->rx);
+ return ret;
+}
+
+static int dr_table_init(struct mlx5dr_table *tbl)
+{
+ int ret = 0;
+
+ INIT_LIST_HEAD(&tbl->matcher_list);
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ switch (tbl->dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_RX;
+ tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+ ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_TX;
+ tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+ ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ tbl->table_type = MLX5_FLOW_TABLE_TYPE_FDB;
+ tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+ tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+ ret = dr_table_init_fdb(tbl);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+
+ mutex_unlock(&tbl->dmn->mutex);
+
+ return ret;
+}
+
+static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+ return mlx5dr_cmd_destroy_flow_table(tbl->dmn->mdev,
+ tbl->table_id,
+ tbl->table_type);
+}
+
+static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+ u64 icm_addr_rx = 0;
+ u64 icm_addr_tx = 0;
+ int ret;
+
+ if (tbl->rx.s_anchor)
+ icm_addr_rx = tbl->rx.s_anchor->chunk->icm_addr;
+
+ if (tbl->tx.s_anchor)
+ icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr;
+
+ ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev,
+ tbl->table_type,
+ icm_addr_rx,
+ icm_addr_tx,
+ tbl->dmn->info.caps.max_ft_level - 1,
+ true, false, NULL,
+ &tbl->table_id);
+
+ return ret;
+}
+
+struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level)
+{
+ struct mlx5dr_table *tbl;
+ int ret;
+
+ refcount_inc(&dmn->refcount);
+
+ tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+ if (!tbl)
+ goto dec_ref;
+
+ tbl->dmn = dmn;
+ tbl->level = level;
+ refcount_set(&tbl->refcount, 1);
+
+ ret = dr_table_init(tbl);
+ if (ret)
+ goto free_tbl;
+
+ ret = dr_table_create_sw_owned_tbl(tbl);
+ if (ret)
+ goto uninit_tbl;
+
+ return tbl;
+
+uninit_tbl:
+ dr_table_uninit(tbl);
+free_tbl:
+ kfree(tbl);
+dec_ref:
+ refcount_dec(&dmn->refcount);
+ return NULL;
+}
+
+int mlx5dr_table_destroy(struct mlx5dr_table *tbl)
+{
+ int ret;
+
+ if (refcount_read(&tbl->refcount) > 1)
+ return -EBUSY;
+
+ ret = dr_table_destroy_sw_owned_tbl(tbl);
+ if (ret)
+ return ret;
+
+ dr_table_uninit(tbl);
+
+ if (tbl->miss_action)
+ refcount_dec(&tbl->miss_action->refcount);
+
+ refcount_dec(&tbl->dmn->refcount);
+ kfree(tbl);
+
+ return ret;
+}
+
+u32 mlx5dr_table_get_id(struct mlx5dr_table *tbl)
+{
+ return tbl->table_id;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 17/18] net/mlx5: Add support to use SMFS in switchdev mode
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Maor Gottlieb,
Mark Bloch, Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Maor Gottlieb <maorg@mellanox.com>
In case that flow steering mode of the driver is SMFS (Software Managed
Flow Steering), then use the DR (SW steering) API to create the steering
objects.
In addition, add a call to the set peer namespace when switchdev gets
devcom pair event. It is required to support VF LAG in SMFS.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 1 +
.../mellanox/mlx5/core/eswitch_offloads.c | 61 ++++++++++++++++---
2 files changed, 55 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 4f70202db6af..6bd6f5895244 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -153,6 +153,7 @@ struct mlx5_eswitch_fdb {
} legacy;
struct offloads_fdb {
+ struct mlx5_flow_namespace *ns;
struct mlx5_flow_table *slow_fdb;
struct mlx5_flow_group *send_to_vport_grp;
struct mlx5_flow_group *peer_miss_grp;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bee67ff58137..afa623b15a38 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1068,6 +1068,13 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
err = -EOPNOTSUPP;
goto ns_err;
}
+ esw->fdb_table.offloads.ns = root_ns;
+ err = mlx5_flow_namespace_set_mode(root_ns,
+ esw->dev->priv.steering->mode);
+ if (err) {
+ esw_warn(dev, "Failed to set FDB namespace steering mode\n");
+ goto ns_err;
+ }
max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
MLX5_CAP_GEN(dev, max_flow_counter_15_0);
@@ -1207,6 +1214,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
esw_destroy_offloads_fast_fdb_tables(esw);
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
slow_fdb_err:
+ /* Holds true only as long as DMFS is the default */
+ mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS);
ns_err:
kvfree(flow_group_in);
return err;
@@ -1226,6 +1235,9 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
esw_destroy_offloads_fast_fdb_tables(esw);
+ /* Holds true only as long as DMFS is the default */
+ mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
+ MLX5_FLOW_STEERING_MODE_DMFS);
}
static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
@@ -1623,13 +1635,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
esw_del_fdb_peer_miss_rules(esw);
}
+static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
+ struct mlx5_eswitch *peer_esw,
+ bool pair)
+{
+ struct mlx5_flow_root_namespace *peer_ns;
+ struct mlx5_flow_root_namespace *ns;
+ int err;
+
+ peer_ns = peer_esw->dev->priv.steering->fdb_root_ns;
+ ns = esw->dev->priv.steering->fdb_root_ns;
+
+ if (pair) {
+ err = mlx5_flow_namespace_set_peer(ns, peer_ns);
+ if (err)
+ return err;
+
+ mlx5_flow_namespace_set_peer(peer_ns, ns);
+ if (err) {
+ mlx5_flow_namespace_set_peer(ns, NULL);
+ return err;
+ }
+ } else {
+ mlx5_flow_namespace_set_peer(ns, NULL);
+ mlx5_flow_namespace_set_peer(peer_ns, NULL);
+ }
+
+ return 0;
+}
+
static int mlx5_esw_offloads_devcom_event(int event,
void *my_data,
void *event_data)
{
struct mlx5_eswitch *esw = my_data;
- struct mlx5_eswitch *peer_esw = event_data;
struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+ struct mlx5_eswitch *peer_esw = event_data;
int err;
switch (event) {
@@ -1638,9 +1679,12 @@ static int mlx5_esw_offloads_devcom_event(int event,
mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
break;
- err = mlx5_esw_offloads_pair(esw, peer_esw);
+ err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true);
if (err)
goto err_out;
+ err = mlx5_esw_offloads_pair(esw, peer_esw);
+ if (err)
+ goto err_peer;
err = mlx5_esw_offloads_pair(peer_esw, esw);
if (err)
@@ -1656,6 +1700,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
mlx5_esw_offloads_unpair(peer_esw);
mlx5_esw_offloads_unpair(esw);
+ mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
break;
}
@@ -1663,7 +1708,8 @@ static int mlx5_esw_offloads_devcom_event(int event,
err_pair:
mlx5_esw_offloads_unpair(esw);
-
+err_peer:
+ mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
err_out:
mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
event, err);
@@ -2115,9 +2161,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
else
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
+ mlx5_rdma_enable_roce(esw->dev);
err = esw_offloads_steering_init(esw);
if (err)
- return err;
+ goto err_steering_init;
err = esw_set_passing_vport_metadata(esw, true);
if (err)
@@ -2132,8 +2179,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
esw_offloads_devcom_init(esw);
mutex_init(&esw->offloads.termtbl_mutex);
- mlx5_rdma_enable_roce(esw->dev);
-
return 0;
err_reps:
@@ -2141,6 +2186,8 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
esw_set_passing_vport_metadata(esw, false);
err_vport_metadata:
esw_offloads_steering_cleanup(esw);
+err_steering_init:
+ mlx5_rdma_disable_roce(esw->dev);
return err;
}
@@ -2165,12 +2212,12 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
void esw_offloads_disable(struct mlx5_eswitch *esw)
{
- mlx5_rdma_disable_roce(esw->dev);
esw_offloads_devcom_cleanup(esw);
esw_offloads_unload_all_reps(esw);
mlx5_eswitch_disable_pf_vf_vports(esw);
esw_set_passing_vport_metadata(esw, false);
esw_offloads_steering_cleanup(esw);
+ mlx5_rdma_disable_roce(esw->dev);
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
}
--
2.21.0
^ permalink raw reply related
* [net-next 09/18] net/mlx5: DR, Expose steering matcher functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Matcher defines which packets fields are matched when a packet arrives.
Matcher is a part of a table and can contain one or more rules. Where
rule defines specific values of the matcher's mask definition.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_matcher.c | 770 ++++++++++++++++++
1 file changed, 770 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
new file mode 100644
index 000000000000..01008cd66f75
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -0,0 +1,770 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+static bool dr_mask_is_smac_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->smac_47_16 || spec->smac_15_0);
+}
+
+static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dmac_47_16 || spec->dmac_15_0);
+}
+
+static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->src_ip_127_96 || spec->src_ip_95_64 ||
+ spec->src_ip_63_32 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dst_ip_127_96 || spec->dst_ip_95_64 ||
+ spec->dst_ip_63_32 || spec->dst_ip_31_0);
+}
+
+static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->ip_protocol || spec->frag || spec->tcp_flags ||
+ spec->ip_ecn || spec->ip_dscp);
+}
+
+static bool dr_mask_is_tcp_udp_base_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->tcp_sport || spec->tcp_dport ||
+ spec->udp_sport || spec->udp_dport);
+}
+
+static bool dr_mask_is_ipv4_set(struct mlx5dr_match_spec *spec)
+{
+ return (spec->dst_ip_31_0 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_ipv4_5_tuple_set(struct mlx5dr_match_spec *spec)
+{
+ return (dr_mask_is_l3_base_set(spec) ||
+ dr_mask_is_tcp_udp_base_set(spec) ||
+ dr_mask_is_ipv4_set(spec));
+}
+
+static bool dr_mask_is_eth_l2_tnl_set(struct mlx5dr_match_misc *misc)
+{
+ return misc->vxlan_vni;
+}
+
+static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec)
+{
+ return spec->ttl_hoplimit;
+}
+
+#define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \
+ (_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \
+ (_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \
+ (_spec).ethertype || (_spec).ip_version || \
+ (_misc)._inner_outer##_second_vid || \
+ (_misc)._inner_outer##_second_cfi || \
+ (_misc)._inner_outer##_second_prio || \
+ (_misc)._inner_outer##_second_cvlan_tag || \
+ (_misc)._inner_outer##_second_svlan_tag)
+
+#define DR_MASK_IS_ETH_L4_SET(_spec, _misc, _inner_outer) ( \
+ dr_mask_is_l3_base_set(&(_spec)) || \
+ dr_mask_is_tcp_udp_base_set(&(_spec)) || \
+ dr_mask_is_ttl_set(&(_spec)) || \
+ (_misc)._inner_outer##_ipv6_flow_label)
+
+#define DR_MASK_IS_ETH_L4_MISC_SET(_misc3, _inner_outer) ( \
+ (_misc3)._inner_outer##_tcp_seq_num || \
+ (_misc3)._inner_outer##_tcp_ack_num)
+
+#define DR_MASK_IS_FIRST_MPLS_SET(_misc2, _inner_outer) ( \
+ (_misc2)._inner_outer##_first_mpls_label || \
+ (_misc2)._inner_outer##_first_mpls_exp || \
+ (_misc2)._inner_outer##_first_mpls_s_bos || \
+ (_misc2)._inner_outer##_first_mpls_ttl)
+
+static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc)
+{
+ return (misc->gre_key_h || misc->gre_key_l ||
+ misc->gre_protocol || misc->gre_c_present ||
+ misc->gre_k_present || misc->gre_s_present);
+}
+
+#define DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET(_misc2, gre_udp) ( \
+ (_misc2).outer_first_mpls_over_##gre_udp##_label || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_exp || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \
+ (_misc2).outer_first_mpls_over_##gre_udp##_ttl)
+
+#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \
+ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \
+ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp))
+
+static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3)
+{
+ return (misc3->outer_vxlan_gpe_vni ||
+ misc3->outer_vxlan_gpe_next_protocol ||
+ misc3->outer_vxlan_gpe_flags);
+}
+
+static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
+{
+ return (misc3->icmpv6_type || misc3->icmpv6_code ||
+ misc3->icmpv6_header_data);
+}
+
+static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return misc2->metadata_reg_a;
+}
+
+static bool dr_mask_is_reg_c_0_3_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return (misc2->metadata_reg_c_0 || misc2->metadata_reg_c_1 ||
+ misc2->metadata_reg_c_2 || misc2->metadata_reg_c_3);
+}
+
+static bool dr_mask_is_reg_c_4_7_set(struct mlx5dr_match_misc2 *misc2)
+{
+ return (misc2->metadata_reg_c_4 || misc2->metadata_reg_c_5 ||
+ misc2->metadata_reg_c_6 || misc2->metadata_reg_c_7);
+}
+
+static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc)
+{
+ return (misc->source_sqn || misc->source_port);
+}
+
+static bool
+dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn)
+{
+ return dmn->info.caps.flex_protocols &
+ MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+}
+
+int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ bool ipv6)
+{
+ if (ipv6) {
+ nic_matcher->ste_builder = nic_matcher->ste_builder6;
+ nic_matcher->num_of_builders = nic_matcher->num_of_builders6;
+ } else {
+ nic_matcher->ste_builder = nic_matcher->ste_builder4;
+ nic_matcher->num_of_builders = nic_matcher->num_of_builders4;
+ }
+
+ if (!nic_matcher->num_of_builders) {
+ mlx5dr_dbg(matcher->tbl->dmn,
+ "Rule not supported on this matcher due to IP related fields\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ bool ipv6)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_match_param mask = {};
+ struct mlx5dr_match_misc3 *misc3;
+ struct mlx5dr_ste_build *sb;
+ u8 *num_of_builders;
+ bool inner, rx;
+ int idx = 0;
+ int ret, i;
+
+ if (ipv6) {
+ sb = nic_matcher->ste_builder6;
+ num_of_builders = &nic_matcher->num_of_builders6;
+ } else {
+ sb = nic_matcher->ste_builder4;
+ num_of_builders = &nic_matcher->num_of_builders4;
+ }
+
+ rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+
+ /* Create a temporary mask to track and clear used mask fields */
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER)
+ mask.outer = matcher->mask.outer;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC)
+ mask.misc = matcher->mask.misc;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_INNER)
+ mask.inner = matcher->mask.inner;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC2)
+ mask.misc2 = matcher->mask.misc2;
+
+ if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC3)
+ mask.misc3 = matcher->mask.misc3;
+
+ ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria,
+ &matcher->mask, NULL);
+ if (ret)
+ return ret;
+
+ /* Outer */
+ if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER |
+ DR_MATCHER_CRITERIA_MISC |
+ DR_MATCHER_CRITERIA_MISC2 |
+ DR_MATCHER_CRITERIA_MISC3)) {
+ inner = false;
+
+ if (dr_mask_is_wqe_metadata_set(&mask.misc2))
+ mlx5dr_ste_build_general_purpose(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_reg_c_0_3_set(&mask.misc2))
+ mlx5dr_ste_build_register_0(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_reg_c_4_7_set(&mask.misc2))
+ mlx5dr_ste_build_register_1(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) &&
+ (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) {
+ ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask,
+ &dmn->info.caps,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.outer) &&
+ dr_mask_is_dmac_set(&mask.outer)) {
+ ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.outer))
+ mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer))
+ mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+ if (ipv6) {
+ if (dr_mask_is_dst_addr_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_src_addr_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer))
+ mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
+ } else {
+ if (dr_mask_is_ipv4_5_tuple_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_ttl_set(&mask.outer))
+ mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+ inner, rx);
+ }
+
+ if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) &&
+ dr_matcher_supp_flex_parser_vxlan_gpe(dmn))
+ mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer))
+ mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer))
+ mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+ mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask,
+ inner, rx);
+
+ misc3 = &mask.misc3;
+ if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) &&
+ mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) ||
+ (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) &&
+ mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) {
+ ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++],
+ &mask, &dmn->info.caps,
+ inner, rx);
+ if (ret)
+ return ret;
+ }
+ if (dr_mask_is_gre_set(&mask.misc))
+ mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx);
+ }
+
+ /* Inner */
+ if (matcher->match_criteria & (DR_MATCHER_CRITERIA_INNER |
+ DR_MATCHER_CRITERIA_MISC |
+ DR_MATCHER_CRITERIA_MISC2 |
+ DR_MATCHER_CRITERIA_MISC3)) {
+ inner = true;
+
+ if (dr_mask_is_eth_l2_tnl_set(&mask.misc))
+ mlx5dr_ste_build_eth_l2_tnl(&sb[idx++], &mask, inner, rx);
+
+ if (dr_mask_is_smac_set(&mask.inner) &&
+ dr_mask_is_dmac_set(&mask.inner)) {
+ ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
+ &mask, inner, rx);
+ if (ret)
+ return ret;
+ }
+
+ if (dr_mask_is_smac_set(&mask.inner))
+ mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner))
+ mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+ if (ipv6) {
+ if (dr_mask_is_dst_addr_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_src_addr_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+ inner, rx);
+
+ if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner))
+ mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+ inner, rx);
+ } else {
+ if (dr_mask_is_ipv4_5_tuple_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+ inner, rx);
+
+ if (dr_mask_is_ttl_set(&mask.inner))
+ mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+ inner, rx);
+ }
+
+ if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, inner))
+ mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner))
+ mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+ if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+ mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx);
+ }
+ /* Empty matcher, takes all */
+ if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
+ mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx);
+
+ if (idx == 0) {
+ mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n");
+ return -EINVAL;
+ }
+
+ /* Check that all mask fields were consumed */
+ for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) {
+ if (((u8 *)&mask)[i] != 0) {
+ mlx5dr_info(dmn, "Mask contains unsupported parameters\n");
+ return -EOPNOTSUPP;
+ }
+ }
+
+ *num_of_builders = idx;
+
+ return 0;
+}
+
+static int dr_matcher_connect(struct mlx5dr_domain *dmn,
+ struct mlx5dr_matcher_rx_tx *curr_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+ struct mlx5dr_table_rx_tx *nic_tbl = curr_nic_matcher->nic_tbl;
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *prev_htbl;
+ int ret;
+
+ /* Connect end anchor hash table to next_htbl or to the default address */
+ if (next_nic_matcher) {
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = next_nic_matcher->s_htbl;
+ } else {
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_tbl->default_icm_addr;
+ }
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ curr_nic_matcher->e_anchor,
+ &info, info.type == CONNECT_HIT);
+ if (ret)
+ return ret;
+
+ /* Connect start hash table to end anchor */
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = curr_nic_matcher->e_anchor->chunk->icm_addr;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+ curr_nic_matcher->s_htbl,
+ &info, false);
+ if (ret)
+ return ret;
+
+ /* Connect previous hash table to matcher start hash table */
+ if (prev_nic_matcher)
+ prev_htbl = prev_nic_matcher->e_anchor;
+ else
+ prev_htbl = nic_tbl->s_anchor;
+
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = curr_nic_matcher->s_htbl;
+ ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_htbl,
+ &info, true);
+ if (ret)
+ return ret;
+
+ /* Update the pointing ste and next hash table */
+ curr_nic_matcher->s_htbl->pointing_ste = prev_htbl->ste_arr;
+ prev_htbl->ste_arr[0].next_htbl = curr_nic_matcher->s_htbl;
+
+ if (next_nic_matcher) {
+ next_nic_matcher->s_htbl->pointing_ste = curr_nic_matcher->e_anchor->ste_arr;
+ curr_nic_matcher->e_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+ }
+
+ return 0;
+}
+
+static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_matcher *next_matcher, *prev_matcher, *tmp_matcher;
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ bool first = true;
+ int ret;
+
+ next_matcher = NULL;
+ if (!list_empty(&tbl->matcher_list))
+ list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) {
+ if (tmp_matcher->prio >= matcher->prio) {
+ next_matcher = tmp_matcher;
+ break;
+ }
+ first = false;
+ }
+
+ prev_matcher = NULL;
+ if (next_matcher && !first)
+ prev_matcher = list_entry(next_matcher->matcher_list.prev,
+ struct mlx5dr_matcher,
+ matcher_list);
+ else if (!first)
+ prev_matcher = list_entry(tbl->matcher_list.prev,
+ struct mlx5dr_matcher,
+ matcher_list);
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ ret = dr_matcher_connect(dmn, &matcher->rx,
+ next_matcher ? &next_matcher->rx : NULL,
+ prev_matcher ? &prev_matcher->rx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ ret = dr_matcher_connect(dmn, &matcher->tx,
+ next_matcher ? &next_matcher->tx : NULL,
+ prev_matcher ? &prev_matcher->tx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (prev_matcher)
+ list_add(&matcher->matcher_list, &prev_matcher->matcher_list);
+ else if (next_matcher)
+ list_add_tail(&matcher->matcher_list,
+ &next_matcher->matcher_list);
+ else
+ list_add(&matcher->matcher_list, &tbl->matcher_list);
+
+ return 0;
+}
+
+static void dr_matcher_uninit_nic(struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ mlx5dr_htbl_put(nic_matcher->s_htbl);
+ mlx5dr_htbl_put(nic_matcher->e_anchor);
+}
+
+static void dr_matcher_uninit_fdb(struct mlx5dr_matcher *matcher)
+{
+ dr_matcher_uninit_nic(&matcher->rx);
+ dr_matcher_uninit_nic(&matcher->tx);
+}
+
+static void dr_matcher_uninit(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ dr_matcher_uninit_nic(&matcher->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ dr_matcher_uninit_nic(&matcher->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ dr_matcher_uninit_fdb(matcher);
+ break;
+ default:
+ WARN_ON(true);
+ break;
+ }
+}
+
+static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ int ret, ret_v4, ret_v6;
+
+ ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false);
+ ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true);
+
+ if (ret_v4 && ret_v6) {
+ mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n");
+ return -EINVAL;
+ }
+
+ if (!ret_v4)
+ nic_matcher->ste_builder = nic_matcher->ste_builder4;
+ else
+ nic_matcher->ste_builder = nic_matcher->ste_builder6;
+
+ nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ MLX5DR_STE_LU_TYPE_DONT_CARE,
+ 0);
+ if (!nic_matcher->e_anchor)
+ return -ENOMEM;
+
+ nic_matcher->s_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ nic_matcher->ste_builder[0].lu_type,
+ nic_matcher->ste_builder[0].byte_mask);
+ if (!nic_matcher->s_htbl) {
+ ret = -ENOMEM;
+ goto free_e_htbl;
+ }
+
+ /* make sure the tables exist while empty */
+ mlx5dr_htbl_get(nic_matcher->s_htbl);
+ mlx5dr_htbl_get(nic_matcher->e_anchor);
+
+ return 0;
+
+free_e_htbl:
+ mlx5dr_ste_htbl_free(nic_matcher->e_anchor);
+ return ret;
+}
+
+static int dr_matcher_init_fdb(struct mlx5dr_matcher *matcher)
+{
+ int ret;
+
+ ret = dr_matcher_init_nic(matcher, &matcher->rx);
+ if (ret)
+ return ret;
+
+ ret = dr_matcher_init_nic(matcher, &matcher->tx);
+ if (ret)
+ goto uninit_nic_rx;
+
+ return 0;
+
+uninit_nic_rx:
+ dr_matcher_uninit_nic(&matcher->rx);
+ return ret;
+}
+
+static int dr_matcher_init(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *mask)
+{
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ int ret;
+
+ if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) {
+ mlx5dr_info(dmn, "Invalid match criteria attribute\n");
+ return -EINVAL;
+ }
+
+ if (mask) {
+ if (mask->match_sz > sizeof(struct mlx5dr_match_param)) {
+ mlx5dr_info(dmn, "Invalid match size attribute\n");
+ return -EINVAL;
+ }
+ mlx5dr_ste_copy_param(matcher->match_criteria,
+ &matcher->mask, mask);
+ }
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ matcher->rx.nic_tbl = &tbl->rx;
+ ret = dr_matcher_init_nic(matcher, &matcher->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ matcher->tx.nic_tbl = &tbl->tx;
+ ret = dr_matcher_init_nic(matcher, &matcher->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ matcher->rx.nic_tbl = &tbl->rx;
+ matcher->tx.nic_tbl = &tbl->tx;
+ ret = dr_matcher_init_fdb(matcher);
+ break;
+ default:
+ WARN_ON(true);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+
+struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *tbl,
+ u16 priority,
+ u8 match_criteria_enable,
+ struct mlx5dr_match_parameters *mask)
+{
+ struct mlx5dr_matcher *matcher;
+ int ret;
+
+ refcount_inc(&tbl->refcount);
+
+ matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
+ if (!matcher)
+ goto dec_ref;
+
+ matcher->tbl = tbl;
+ matcher->prio = priority;
+ matcher->match_criteria = match_criteria_enable;
+ refcount_set(&matcher->refcount, 1);
+ INIT_LIST_HEAD(&matcher->matcher_list);
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ ret = dr_matcher_init(matcher, mask);
+ if (ret)
+ goto free_matcher;
+
+ ret = dr_matcher_add_to_tbl(matcher);
+ if (ret)
+ goto matcher_uninit;
+
+ mutex_unlock(&tbl->dmn->mutex);
+
+ return matcher;
+
+matcher_uninit:
+ dr_matcher_uninit(matcher);
+free_matcher:
+ mutex_unlock(&tbl->dmn->mutex);
+ kfree(matcher);
+dec_ref:
+ refcount_dec(&tbl->refcount);
+ return NULL;
+}
+
+static int dr_matcher_disconnect(struct mlx5dr_domain *dmn,
+ struct mlx5dr_table_rx_tx *nic_tbl,
+ struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+ struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_ste_htbl *prev_anchor;
+
+ if (prev_nic_matcher)
+ prev_anchor = prev_nic_matcher->e_anchor;
+ else
+ prev_anchor = nic_tbl->s_anchor;
+
+ /* Connect previous anchor hash table to next matcher or to the default address */
+ if (next_nic_matcher) {
+ info.type = CONNECT_HIT;
+ info.hit_next_htbl = next_nic_matcher->s_htbl;
+ next_nic_matcher->s_htbl->pointing_ste = prev_anchor->ste_arr;
+ prev_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+ } else {
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_tbl->default_icm_addr;
+ prev_anchor->ste_arr[0].next_htbl = NULL;
+ }
+
+ return mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_anchor,
+ &info, true);
+}
+
+static int dr_matcher_remove_from_tbl(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_matcher *prev_matcher, *next_matcher;
+ struct mlx5dr_table *tbl = matcher->tbl;
+ struct mlx5dr_domain *dmn = tbl->dmn;
+ int ret = 0;
+
+ if (list_is_last(&matcher->matcher_list, &tbl->matcher_list))
+ next_matcher = NULL;
+ else
+ next_matcher = list_next_entry(matcher, matcher_list);
+
+ if (matcher->matcher_list.prev == &tbl->matcher_list)
+ prev_matcher = NULL;
+ else
+ prev_matcher = list_prev_entry(matcher, matcher_list);
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ ret = dr_matcher_disconnect(dmn, &tbl->rx,
+ next_matcher ? &next_matcher->rx : NULL,
+ prev_matcher ? &prev_matcher->rx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+ dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ ret = dr_matcher_disconnect(dmn, &tbl->tx,
+ next_matcher ? &next_matcher->tx : NULL,
+ prev_matcher ? &prev_matcher->tx : NULL);
+ if (ret)
+ return ret;
+ }
+
+ list_del(&matcher->matcher_list);
+
+ return 0;
+}
+
+int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher)
+{
+ struct mlx5dr_table *tbl = matcher->tbl;
+
+ if (refcount_read(&matcher->refcount) > 1)
+ return -EBUSY;
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ dr_matcher_remove_from_tbl(matcher);
+ dr_matcher_uninit(matcher);
+ refcount_dec(&matcher->tbl->refcount);
+
+ mutex_unlock(&tbl->dmn->mutex);
+ kfree(matcher);
+
+ return 0;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 18/18] net/mlx5: Add devlink flow_steering_mode parameter
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Maor Gottlieb,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Maor Gottlieb <maorg@mellanox.com>
Add new parameter (flow_steering_mode) to control the flow steering
mode of the driver.
Two modes are supported:
1. DMFS - Device managed flow steering
2. SMFS - Software/Driver managed flow steering.
In the DMFS mode, the HW steering entities are created through the
FW. In the SMFS mode this entities are created though the driver
directly.
The driver will use the devlink steering mode only if the steering
domain supports it, for now SMFS will manages only the switchdev eswitch
steering domain.
User command examples:
- Set SMFS flow steering mode::
$ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
- Read device flow steering mode::
$ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
pci/0000:06:00.0:
name flow_steering_mode type driver-specific
values:
cmode runtime value smfs
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../device_drivers/mellanox/mlx5.rst | 33 ++++++
.../net/ethernet/mellanox/mlx5/core/devlink.c | 112 +++++++++++++++++-
2 files changed, 144 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/device_drivers/mellanox/mlx5.rst b/Documentation/networking/device_drivers/mellanox/mlx5.rst
index b30a63dbf4b7..d071c6b49e1f 100644
--- a/Documentation/networking/device_drivers/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/mellanox/mlx5.rst
@@ -11,6 +11,7 @@ Contents
- `Enabling the driver and kconfig options`_
- `Devlink info`_
+- `Devlink parameters`_
- `Devlink health reporters`_
- `mlx5 tracepoints`_
@@ -122,6 +123,38 @@ User command example::
stored:
fw.version 16.26.0100
+Devlink parameters
+==================
+
+flow_steering_mode: Device flow steering mode
+---------------------------------------------
+The flow steering mode parameter controls the flow steering mode of the driver.
+Two modes are supported:
+1. 'dmfs' - Device managed flow steering.
+2. 'smfs - Software/Driver managed flow steering.
+
+In DMFS mode, the HW steering entities are created and managed through the
+Firmware.
+In SMFS mode, the HW steering entities are created and managed though by
+the driver directly into Hardware without firmware intervention.
+
+SMFS mode is faster and provides better rule inserstion rate compared to default DMFS mode.
+
+User command examples:
+
+- Set SMFS flow steering mode::
+
+ $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
+
+- Read device flow steering mode::
+
+ $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
+ pci/0000:06:00.0:
+ name flow_steering_mode type driver-specific
+ values:
+ cmode runtime value smfs
+
+
Devlink health reporters
========================
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index a400f4430c28..7bf7b6fbc776 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -4,6 +4,7 @@
#include <devlink.h>
#include "mlx5_core.h"
+#include "fs_core.h"
#include "eswitch.h"
static int mlx5_devlink_flash_update(struct devlink *devlink,
@@ -107,12 +108,121 @@ void mlx5_devlink_free(struct devlink *devlink)
devlink_free(devlink);
}
+static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id,
+ union devlink_param_value val,
+ struct netlink_ext_ack *extack)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ char *value = val.vstr;
+ int err = 0;
+
+ if (!strcmp(value, "dmfs")) {
+ return 0;
+ } else if (!strcmp(value, "smfs")) {
+ u8 eswitch_mode;
+ bool smfs_cap;
+
+ eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch);
+ smfs_cap = mlx5_fs_dr_is_supported(dev);
+
+ if (!smfs_cap) {
+ err = -EOPNOTSUPP;
+ NL_SET_ERR_MSG_MOD(extack,
+ "Software managed steering is not supported by current device");
+ }
+
+ else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Software managed steering is not supported when eswitch offlaods enabled.");
+ err = -EOPNOTSUPP;
+ }
+ } else {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Bad parameter: supported values are [\"dmfs\", \"smfs\"]");
+ err = -EINVAL;
+ }
+
+ return err;
+}
+
+static int mlx5_devlink_fs_mode_set(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ enum mlx5_flow_steering_mode mode;
+
+ if (!strcmp(ctx->val.vstr, "smfs"))
+ mode = MLX5_FLOW_STEERING_MODE_SMFS;
+ else
+ mode = MLX5_FLOW_STEERING_MODE_DMFS;
+ dev->priv.steering->mode = mode;
+
+ return 0;
+}
+
+static int mlx5_devlink_fs_mode_get(struct devlink *devlink, u32 id,
+ struct devlink_param_gset_ctx *ctx)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+ if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS)
+ strcpy(ctx->val.vstr, "smfs");
+ else
+ strcpy(ctx->val.vstr, "dmfs");
+ return 0;
+}
+
+enum mlx5_devlink_param_id {
+ MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+ MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+};
+
+static const struct devlink_param mlx5_devlink_params[] = {
+ DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+ "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING,
+ BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+ mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set,
+ mlx5_devlink_fs_mode_validate),
+};
+
+static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
+{
+ struct mlx5_core_dev *dev = devlink_priv(devlink);
+ union devlink_param_value value;
+
+ if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS)
+ strcpy(value.vstr, "dmfs");
+ else
+ strcpy(value.vstr, "smfs");
+ devlink_param_driverinit_value_set(devlink,
+ MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+ value);
+}
+
int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
{
- return devlink_register(devlink, dev);
+ int err;
+
+ err = devlink_register(devlink, dev);
+ if (err)
+ return err;
+
+ err = devlink_params_register(devlink, mlx5_devlink_params,
+ ARRAY_SIZE(mlx5_devlink_params));
+ if (err)
+ goto params_reg_err;
+ mlx5_devlink_set_params_init_values(devlink);
+ devlink_params_publish(devlink);
+ return 0;
+
+params_reg_err:
+ devlink_unregister(devlink);
+ return err;
}
void mlx5_devlink_unregister(struct devlink *devlink)
{
+ devlink_params_unregister(devlink, mlx5_devlink_params,
+ ARRAY_SIZE(mlx5_devlink_params));
devlink_unregister(devlink);
}
--
2.21.0
^ permalink raw reply related
* [net-next 10/18] net/mlx5: DR, Expose steering action functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
On rule creation a set of actions can be provided, the actions describe
what to do with the packet in case of a match. It is possible to provide
a set of actions which will be done by order.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_action.c | 1588 +++++++++++++++++
1 file changed, 1588 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
new file mode 100644
index 000000000000..a02f87f85c17
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -0,0 +1,1588 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+enum dr_action_domain {
+ DR_ACTION_DOMAIN_NIC_INGRESS,
+ DR_ACTION_DOMAIN_NIC_EGRESS,
+ DR_ACTION_DOMAIN_FDB_INGRESS,
+ DR_ACTION_DOMAIN_FDB_EGRESS,
+ DR_ACTION_DOMAIN_MAX,
+};
+
+enum dr_action_valid_state {
+ DR_ACTION_STATE_ERR,
+ DR_ACTION_STATE_NO_ACTION,
+ DR_ACTION_STATE_REFORMAT,
+ DR_ACTION_STATE_MODIFY_HDR,
+ DR_ACTION_STATE_MODIFY_VLAN,
+ DR_ACTION_STATE_NON_TERM,
+ DR_ACTION_STATE_TERM,
+ DR_ACTION_STATE_MAX,
+};
+
+static const enum dr_action_valid_state
+next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] = {
+ [DR_ACTION_DOMAIN_NIC_INGRESS] = {
+ [DR_ACTION_STATE_NO_ACTION] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_REFORMAT] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_MODIFY_HDR] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR,
+ },
+ [DR_ACTION_STATE_MODIFY_VLAN] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ },
+ [DR_ACTION_STATE_NON_TERM] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_TERM] = {
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM,
+ },
+ },
+ [DR_ACTION_DOMAIN_NIC_EGRESS] = {
+ [DR_ACTION_STATE_NO_ACTION] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_REFORMAT] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT,
+ },
+ [DR_ACTION_STATE_MODIFY_HDR] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_MODIFY_VLAN] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ },
+ [DR_ACTION_STATE_NON_TERM] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ },
+ [DR_ACTION_STATE_TERM] = {
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM,
+ },
+ },
+ [DR_ACTION_DOMAIN_FDB_INGRESS] = {
+ [DR_ACTION_STATE_NO_ACTION] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_REFORMAT] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_MODIFY_HDR] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_MODIFY_VLAN] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ },
+ [DR_ACTION_STATE_NON_TERM] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_TERM] = {
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM,
+ },
+ },
+ [DR_ACTION_DOMAIN_FDB_EGRESS] = {
+ [DR_ACTION_STATE_NO_ACTION] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_REFORMAT] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_MODIFY_HDR] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_MODIFY_VLAN] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_NON_TERM] = {
+ [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM,
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM,
+ [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR,
+ [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT,
+ [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN,
+ [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM,
+ },
+ [DR_ACTION_STATE_TERM] = {
+ [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM,
+ },
+ },
+};
+
+struct dr_action_modify_field_conv {
+ u16 hw_field;
+ u8 start;
+ u8 end;
+ u8 l3_type;
+ u8 l4_type;
+};
+
+static const struct dr_action_modify_field_conv dr_action_conv_arr[] = {
+ [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 16, .end = 47,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 0, .end = 15,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 32, .end = 47,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 16, .end = 47,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 0, .end = 15,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 0, .end = 5,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 48, .end = 56,
+ .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15,
+ .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31,
+ .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15,
+ .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31,
+ .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 32, .end = 63,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 0, .end = 31,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 32, .end = 63,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 0, .end = 31,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 32, .end = 63,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 0, .end = 31,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63,
+ .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 0, .end = 31,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 32, .end = 63,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 32, .end = 63,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 0, .end = 31,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 32, .end = 63,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 0, .end = 31,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 32, .end = 63,
+ },
+ [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 0, .end = 31,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 32, .end = 63,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 0, .end = 31,
+ },
+ [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = {
+ .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 0, .end = 15,
+ },
+};
+
+#define MAX_VLANS 2
+struct dr_action_vlan_info {
+ int count;
+ u32 headers[MAX_VLANS];
+};
+
+struct dr_action_apply_attr {
+ u32 modify_index;
+ u16 modify_actions;
+ u32 decap_index;
+ u16 decap_actions;
+ u8 decap_with_vlan:1;
+ u64 final_icm_addr;
+ u32 flow_tag;
+ u32 ctr_id;
+ u16 gvmi;
+ u16 hit_gvmi;
+ u32 reformat_id;
+ u32 reformat_size;
+ struct dr_action_vlan_info vlans;
+};
+
+static int
+dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type,
+ enum mlx5dr_action_type *action_type)
+{
+ switch (reformat_type) {
+ case DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2:
+ *action_type = DR_ACTION_TYP_TNL_L2_TO_L2;
+ break;
+ case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2:
+ *action_type = DR_ACTION_TYP_L2_TO_TNL_L2;
+ break;
+ case DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2:
+ *action_type = DR_ACTION_TYP_TNL_L3_TO_L2;
+ break;
+ case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3:
+ *action_type = DR_ACTION_TYP_L2_TO_TNL_L3;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void dr_actions_init_next_ste(u8 **last_ste,
+ u32 *added_stes,
+ enum mlx5dr_ste_entry_type entry_type,
+ u16 gvmi)
+{
+ (*added_stes)++;
+ *last_ste += DR_STE_SIZE;
+ mlx5dr_ste_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, entry_type, gvmi);
+}
+
+static void dr_actions_apply_tx(struct mlx5dr_domain *dmn,
+ u8 *action_type_set,
+ u8 *last_ste,
+ struct dr_action_apply_attr *attr,
+ u32 *added_stes)
+{
+ bool encap = action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2] ||
+ action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3];
+
+ /* We want to make sure the modify header comes before L2
+ * encapsulation. The reason for that is that we support
+ * modify headers for outer headers only
+ */
+ if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) {
+ mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+ mlx5dr_ste_set_rewrite_actions(last_ste,
+ attr->modify_actions,
+ attr->modify_index);
+ }
+
+ if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) {
+ int i;
+
+ for (i = 0; i < attr->vlans.count; i++) {
+ if (i || action_type_set[DR_ACTION_TYP_MODIFY_HDR])
+ dr_actions_init_next_ste(&last_ste,
+ added_stes,
+ MLX5DR_STE_TYPE_TX,
+ attr->gvmi);
+
+ mlx5dr_ste_set_tx_push_vlan(last_ste,
+ attr->vlans.headers[i],
+ encap);
+ }
+ }
+
+ if (encap) {
+ /* Modify header and encapsulation require a different STEs.
+ * Since modify header STE format doesn't support encapsulation
+ * tunneling_action.
+ */
+ if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] ||
+ action_type_set[DR_ACTION_TYP_PUSH_VLAN])
+ dr_actions_init_next_ste(&last_ste,
+ added_stes,
+ MLX5DR_STE_TYPE_TX,
+ attr->gvmi);
+
+ mlx5dr_ste_set_tx_encap(last_ste,
+ attr->reformat_id,
+ attr->reformat_size,
+ action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]);
+ /* Whenever prio_tag_required enabled, we can be sure that the
+ * previous table (ACL) already push vlan to our packet,
+ * And due to HW limitation we need to set this bit, otherwise
+ * push vlan + reformat will not work.
+ */
+ if (MLX5_CAP_GEN(dmn->mdev, prio_tag_required))
+ mlx5dr_ste_set_go_back_bit(last_ste);
+ }
+
+ if (action_type_set[DR_ACTION_TYP_CTR])
+ mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id);
+}
+
+static void dr_actions_apply_rx(u8 *action_type_set,
+ u8 *last_ste,
+ struct dr_action_apply_attr *attr,
+ u32 *added_stes)
+{
+ if (action_type_set[DR_ACTION_TYP_CTR])
+ mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id);
+
+ if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) {
+ mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+ mlx5dr_ste_set_rx_decap_l3(last_ste, attr->decap_with_vlan);
+ mlx5dr_ste_set_rewrite_actions(last_ste,
+ attr->decap_actions,
+ attr->decap_index);
+ }
+
+ if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2])
+ mlx5dr_ste_set_rx_decap(last_ste);
+
+ if (action_type_set[DR_ACTION_TYP_POP_VLAN]) {
+ int i;
+
+ for (i = 0; i < attr->vlans.count; i++) {
+ if (i ||
+ action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2] ||
+ action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2])
+ dr_actions_init_next_ste(&last_ste,
+ added_stes,
+ MLX5DR_STE_TYPE_RX,
+ attr->gvmi);
+
+ mlx5dr_ste_set_rx_pop_vlan(last_ste);
+ }
+ }
+
+ if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) {
+ if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT)
+ dr_actions_init_next_ste(&last_ste,
+ added_stes,
+ MLX5DR_STE_TYPE_MODIFY_PKT,
+ attr->gvmi);
+ else
+ mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT);
+
+ mlx5dr_ste_set_rewrite_actions(last_ste,
+ attr->modify_actions,
+ attr->modify_index);
+ }
+
+ if (action_type_set[DR_ACTION_TYP_TAG]) {
+ if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT)
+ dr_actions_init_next_ste(&last_ste,
+ added_stes,
+ MLX5DR_STE_TYPE_RX,
+ attr->gvmi);
+
+ mlx5dr_ste_rx_set_flow_tag(last_ste, attr->flow_tag);
+ }
+}
+
+/* Apply the actions on the rule STE array starting from the last_ste.
+ * Actions might require more than one STE, new_num_stes will return
+ * the new size of the STEs array, rule with actions.
+ */
+static void dr_actions_apply(struct mlx5dr_domain *dmn,
+ enum mlx5dr_ste_entry_type ste_type,
+ u8 *action_type_set,
+ u8 *last_ste,
+ struct dr_action_apply_attr *attr,
+ u32 *new_num_stes)
+{
+ u32 added_stes = 0;
+
+ if (ste_type == MLX5DR_STE_TYPE_RX)
+ dr_actions_apply_rx(action_type_set, last_ste, attr, &added_stes);
+ else
+ dr_actions_apply_tx(dmn, action_type_set, last_ste, attr, &added_stes);
+
+ last_ste += added_stes * DR_STE_SIZE;
+ *new_num_stes += added_stes;
+
+ mlx5dr_ste_set_hit_gvmi(last_ste, attr->hit_gvmi);
+ mlx5dr_ste_set_hit_addr(last_ste, attr->final_icm_addr, 1);
+}
+
+static enum dr_action_domain
+dr_action_get_action_domain(enum mlx5dr_domain_type domain,
+ enum mlx5dr_ste_entry_type ste_type)
+{
+ switch (domain) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ return DR_ACTION_DOMAIN_NIC_INGRESS;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ return DR_ACTION_DOMAIN_NIC_EGRESS;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ if (ste_type == MLX5DR_STE_TYPE_RX)
+ return DR_ACTION_DOMAIN_FDB_INGRESS;
+ return DR_ACTION_DOMAIN_FDB_EGRESS;
+ default:
+ WARN_ON(true);
+ return DR_ACTION_DOMAIN_MAX;
+ }
+}
+
+static
+int dr_action_validate_and_get_next_state(enum dr_action_domain action_domain,
+ u32 action_type,
+ u32 *state)
+{
+ u32 cur_state = *state;
+
+ /* Check action state machine is valid */
+ *state = next_action_state[action_domain][cur_state][action_type];
+
+ if (*state == DR_ACTION_STATE_ERR)
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action *dest_action,
+ u64 *final_icm_addr)
+{
+ int ret;
+
+ switch (dest_action->action_type) {
+ case DR_ACTION_TYP_FT:
+ /* Allow destination flow table only if table is a terminating
+ * table, since there is an *assumption* that in such case FW
+ * will recalculate the CS.
+ */
+ if (dest_action->dest_tbl.is_fw_tbl) {
+ *final_icm_addr = dest_action->dest_tbl.fw_tbl.rx_icm_addr;
+ } else {
+ mlx5dr_dbg(dmn,
+ "Destination FT should be terminating when modify TTL is used\n");
+ return -EINVAL;
+ }
+ break;
+
+ case DR_ACTION_TYP_VPORT:
+ /* If destination is vport we will get the FW flow table
+ * that recalculates the CS and forwards to the vport.
+ */
+ ret = mlx5dr_domain_cache_get_recalc_cs_ft_addr(dest_action->vport.dmn,
+ dest_action->vport.num,
+ final_icm_addr);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed to get FW cs recalc flow table\n");
+ return ret;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+#define WITH_VLAN_NUM_HW_ACTIONS 6
+
+int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_action *actions[],
+ u32 num_actions,
+ u8 *ste_arr,
+ u32 *new_hw_ste_arr_sz)
+{
+ struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+ bool rx_rule = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ u8 action_type_set[DR_ACTION_TYP_MAX] = {};
+ struct mlx5dr_action *dest_action = NULL;
+ u32 state = DR_ACTION_STATE_NO_ACTION;
+ struct dr_action_apply_attr attr = {};
+ enum dr_action_domain action_domain;
+ bool recalc_cs_required = false;
+ u8 *last_ste;
+ int i, ret;
+
+ attr.gvmi = dmn->info.caps.gvmi;
+ attr.hit_gvmi = dmn->info.caps.gvmi;
+ attr.final_icm_addr = nic_dmn->default_icm_addr;
+ action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->ste_type);
+
+ for (i = 0; i < num_actions; i++) {
+ struct mlx5dr_action *action;
+ int max_actions_type = 1;
+ u32 action_type;
+
+ action = actions[i];
+ action_type = action->action_type;
+
+ switch (action_type) {
+ case DR_ACTION_TYP_DROP:
+ attr.final_icm_addr = nic_dmn->drop_icm_addr;
+ break;
+ case DR_ACTION_TYP_FT:
+ dest_action = action;
+ if (!action->dest_tbl.is_fw_tbl) {
+ if (action->dest_tbl.tbl->dmn != dmn) {
+ mlx5dr_dbg(dmn,
+ "Destination table belongs to a different domain\n");
+ goto out_invalid_arg;
+ }
+ if (action->dest_tbl.tbl->level <= matcher->tbl->level) {
+ mlx5dr_dbg(dmn,
+ "Destination table level should be higher than source table\n");
+ goto out_invalid_arg;
+ }
+ attr.final_icm_addr = rx_rule ?
+ action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr :
+ action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr;
+ } else {
+ struct mlx5dr_cmd_query_flow_table_details output;
+ int ret;
+
+ /* get the relevant addresses */
+ if (!action->dest_tbl.fw_tbl.rx_icm_addr) {
+ ret = mlx5dr_cmd_query_flow_table(action->dest_tbl.fw_tbl.mdev,
+ action->dest_tbl.fw_tbl.ft->type,
+ action->dest_tbl.fw_tbl.ft->id,
+ &output);
+ if (!ret) {
+ action->dest_tbl.fw_tbl.tx_icm_addr =
+ output.sw_owner_icm_root_1;
+ action->dest_tbl.fw_tbl.rx_icm_addr =
+ output.sw_owner_icm_root_0;
+ } else {
+ mlx5dr_dbg(dmn,
+ "Failed mlx5_cmd_query_flow_table ret: %d\n",
+ ret);
+ return ret;
+ }
+ }
+ attr.final_icm_addr = rx_rule ?
+ action->dest_tbl.fw_tbl.rx_icm_addr :
+ action->dest_tbl.fw_tbl.tx_icm_addr;
+ }
+ break;
+ case DR_ACTION_TYP_QP:
+ mlx5dr_info(dmn, "Domain doesn't support QP\n");
+ goto out_invalid_arg;
+ case DR_ACTION_TYP_CTR:
+ attr.ctr_id = action->ctr.ctr_id +
+ action->ctr.offeset;
+ break;
+ case DR_ACTION_TYP_TAG:
+ attr.flow_tag = action->flow_tag;
+ break;
+ case DR_ACTION_TYP_TNL_L2_TO_L2:
+ break;
+ case DR_ACTION_TYP_TNL_L3_TO_L2:
+ attr.decap_index = action->rewrite.index;
+ attr.decap_actions = action->rewrite.num_of_actions;
+ attr.decap_with_vlan =
+ attr.decap_actions == WITH_VLAN_NUM_HW_ACTIONS;
+ break;
+ case DR_ACTION_TYP_MODIFY_HDR:
+ attr.modify_index = action->rewrite.index;
+ attr.modify_actions = action->rewrite.num_of_actions;
+ recalc_cs_required = action->rewrite.modify_ttl;
+ break;
+ case DR_ACTION_TYP_L2_TO_TNL_L2:
+ case DR_ACTION_TYP_L2_TO_TNL_L3:
+ attr.reformat_size = action->reformat.reformat_size;
+ attr.reformat_id = action->reformat.reformat_id;
+ break;
+ case DR_ACTION_TYP_VPORT:
+ attr.hit_gvmi = action->vport.caps->vhca_gvmi;
+ dest_action = action;
+ if (rx_rule) {
+ /* Loopback on WIRE vport is not supported */
+ if (action->vport.num == WIRE_PORT)
+ goto out_invalid_arg;
+
+ attr.final_icm_addr = action->vport.caps->icm_address_rx;
+ } else {
+ attr.final_icm_addr = action->vport.caps->icm_address_tx;
+ }
+ break;
+ case DR_ACTION_TYP_POP_VLAN:
+ max_actions_type = MAX_VLANS;
+ attr.vlans.count++;
+ break;
+ case DR_ACTION_TYP_PUSH_VLAN:
+ max_actions_type = MAX_VLANS;
+ if (attr.vlans.count == MAX_VLANS)
+ return -EINVAL;
+
+ attr.vlans.headers[attr.vlans.count++] = action->push_vlan.vlan_hdr;
+ break;
+ default:
+ goto out_invalid_arg;
+ }
+
+ /* Check action duplication */
+ if (++action_type_set[action_type] > max_actions_type) {
+ mlx5dr_dbg(dmn, "Action type %d supports only max %d time(s)\n",
+ action_type, max_actions_type);
+ goto out_invalid_arg;
+ }
+
+ /* Check action state machine is valid */
+ if (dr_action_validate_and_get_next_state(action_domain,
+ action_type,
+ &state)) {
+ mlx5dr_dbg(dmn, "Invalid action sequence provided\n");
+ return -EOPNOTSUPP;
+ }
+ }
+
+ *new_hw_ste_arr_sz = nic_matcher->num_of_builders;
+ last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1);
+
+ /* Due to a HW bug, modifying TTL on RX flows will cause an incorrect
+ * checksum calculation. In this case we will use a FW table to
+ * recalculate.
+ */
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB &&
+ rx_rule && recalc_cs_required && dest_action) {
+ ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr);
+ if (ret) {
+ mlx5dr_dbg(dmn,
+ "Failed to handle checksum recalculation err %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ dr_actions_apply(dmn,
+ nic_dmn->ste_type,
+ action_type_set,
+ last_ste,
+ &attr,
+ new_hw_ste_arr_sz);
+
+ return 0;
+
+out_invalid_arg:
+ return -EINVAL;
+}
+
+#define CVLAN_ETHERTYPE 0x8100
+#define SVLAN_ETHERTYPE 0x88a8
+#define HDR_LEN_L2_ONLY 14
+#define HDR_LEN_L2_VLAN 18
+#define REWRITE_HW_ACTION_NUM 6
+
+static int dr_actions_l2_rewrite(struct mlx5dr_domain *dmn,
+ struct mlx5dr_action *action,
+ void *data, size_t data_sz)
+{
+ struct mlx5_ifc_l2_hdr_bits *l2_hdr = data;
+ u64 ops[REWRITE_HW_ACTION_NUM] = {};
+ u32 hdr_fld_4b;
+ u16 hdr_fld_2b;
+ u16 vlan_type;
+ bool vlan;
+ int i = 0;
+ int ret;
+
+ vlan = (data_sz != HDR_LEN_L2_ONLY);
+
+ /* dmac_47_16 */
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_length, 0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 16);
+ hdr_fld_4b = MLX5_GET(l2_hdr, l2_hdr, dmac_47_16);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ inline_data, hdr_fld_4b);
+ i++;
+
+ /* smac_47_16 */
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_length, 0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 16);
+ hdr_fld_4b = (MLX5_GET(l2_hdr, l2_hdr, smac_31_0) >> 16 |
+ MLX5_GET(l2_hdr, l2_hdr, smac_47_32) << 16);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ inline_data, hdr_fld_4b);
+ i++;
+
+ /* dmac_15_0 */
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_length, 16);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 0);
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, dmac_15_0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ inline_data, hdr_fld_2b);
+ i++;
+
+ /* ethertype + (optional) vlan */
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 32);
+ if (!vlan) {
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype);
+ MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_2b);
+ MLX5_SET(dr_action_hw_set, ops + i, destination_length, 16);
+ } else {
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype);
+ vlan_type = hdr_fld_2b == SVLAN_ETHERTYPE ? DR_STE_SVLAN : DR_STE_CVLAN;
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan);
+ hdr_fld_4b = (vlan_type << 16) | hdr_fld_2b;
+ MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_4b);
+ MLX5_SET(dr_action_hw_set, ops + i, destination_length, 18);
+ }
+ i++;
+
+ /* smac_15_0 */
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_length, 16);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 0);
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, smac_31_0);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ inline_data, hdr_fld_2b);
+ i++;
+
+ if (vlan) {
+ MLX5_SET(dr_action_hw_set, ops + i,
+ opcode, MLX5DR_ACTION_MDFY_HW_OP_SET);
+ hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan_type);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ inline_data, hdr_fld_2b);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_length, 16);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2);
+ MLX5_SET(dr_action_hw_set, ops + i,
+ destination_left_shifter, 0);
+ i++;
+ }
+
+ action->rewrite.data = (void *)ops;
+ action->rewrite.num_of_actions = i;
+ action->rewrite.chunk->byte_size = i * sizeof(*ops);
+
+ ret = mlx5dr_send_postsend_action(dmn, action);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Writing encapsulation action to ICM failed\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static struct mlx5dr_action *
+dr_action_create_generic(enum mlx5dr_action_type action_type)
+{
+ struct mlx5dr_action *action;
+
+ action = kzalloc(sizeof(*action), GFP_KERNEL);
+ if (!action)
+ return NULL;
+
+ action->action_type = action_type;
+ refcount_set(&action->refcount, 1);
+
+ return action;
+}
+
+struct mlx5dr_action *mlx5dr_action_create_drop(void)
+{
+ return dr_action_create_generic(DR_ACTION_TYP_DROP);
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_table(struct mlx5dr_table *tbl)
+{
+ struct mlx5dr_action *action;
+
+ refcount_inc(&tbl->refcount);
+
+ action = dr_action_create_generic(DR_ACTION_TYP_FT);
+ if (!action)
+ goto dec_ref;
+
+ action->dest_tbl.tbl = tbl;
+
+ return action;
+
+dec_ref:
+ refcount_dec(&tbl->refcount);
+ return NULL;
+}
+
+struct mlx5dr_action *
+mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
+ struct mlx5_core_dev *mdev)
+{
+ struct mlx5dr_action *action;
+
+ action = dr_action_create_generic(DR_ACTION_TYP_FT);
+ if (!action)
+ return NULL;
+
+ action->dest_tbl.is_fw_tbl = 1;
+ action->dest_tbl.fw_tbl.ft = ft;
+ action->dest_tbl.fw_tbl.mdev = mdev;
+
+ return action;
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_flow_counter(u32 counter_id)
+{
+ struct mlx5dr_action *action;
+
+ action = dr_action_create_generic(DR_ACTION_TYP_CTR);
+ if (!action)
+ return NULL;
+
+ action->ctr.ctr_id = counter_id;
+
+ return action;
+}
+
+struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value)
+{
+ struct mlx5dr_action *action;
+
+ action = dr_action_create_generic(DR_ACTION_TYP_TAG);
+ if (!action)
+ return NULL;
+
+ action->flow_tag = tag_value & 0xffffff;
+
+ return action;
+}
+
+static int
+dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type,
+ struct mlx5dr_domain *dmn,
+ size_t data_sz,
+ void *data)
+{
+ if ((!data && data_sz) || (data && !data_sz) || reformat_type >
+ DR_ACTION_TYP_L2_TO_TNL_L3) {
+ mlx5dr_dbg(dmn, "Invalid reformat parameter!\n");
+ goto out_err;
+ }
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB)
+ return 0;
+
+ if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ if (reformat_type != DR_ACTION_TYP_TNL_L2_TO_L2 &&
+ reformat_type != DR_ACTION_TYP_TNL_L3_TO_L2) {
+ mlx5dr_dbg(dmn, "Action reformat type not support on RX domain\n");
+ goto out_err;
+ }
+ } else if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ if (reformat_type != DR_ACTION_TYP_L2_TO_TNL_L2 &&
+ reformat_type != DR_ACTION_TYP_L2_TO_TNL_L3) {
+ mlx5dr_dbg(dmn, "Action reformat type not support on TX domain\n");
+ goto out_err;
+ }
+ }
+
+ return 0;
+
+out_err:
+ return -EINVAL;
+}
+
+#define ACTION_CACHE_LINE_SIZE 64
+
+static int
+dr_action_create_reformat_action(struct mlx5dr_domain *dmn,
+ size_t data_sz, void *data,
+ struct mlx5dr_action *action)
+{
+ u32 reformat_id;
+ int ret;
+
+ switch (action->action_type) {
+ case DR_ACTION_TYP_L2_TO_TNL_L2:
+ case DR_ACTION_TYP_L2_TO_TNL_L3:
+ {
+ enum mlx5dr_action_type rt;
+
+ if (action->action_type == DR_ACTION_TYP_L2_TO_TNL_L2)
+ rt = MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL;
+ else
+ rt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL;
+
+ ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, data_sz, data,
+ &reformat_id);
+ if (ret)
+ return ret;
+
+ action->reformat.reformat_id = reformat_id;
+ action->reformat.reformat_size = data_sz;
+ return 0;
+ }
+ case DR_ACTION_TYP_TNL_L2_TO_L2:
+ {
+ return 0;
+ }
+ case DR_ACTION_TYP_TNL_L3_TO_L2:
+ {
+ /* Only Ethernet frame is supported, with VLAN (18) or without (14) */
+ if (data_sz != HDR_LEN_L2_ONLY && data_sz != HDR_LEN_L2_VLAN)
+ return -EINVAL;
+
+ action->rewrite.chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool,
+ DR_CHUNK_SIZE_8);
+ if (!action->rewrite.chunk)
+ return -ENOMEM;
+
+ action->rewrite.index = (action->rewrite.chunk->icm_addr -
+ dmn->info.caps.hdr_modify_icm_addr) /
+ ACTION_CACHE_LINE_SIZE;
+
+ ret = dr_actions_l2_rewrite(dmn, action, data, data_sz);
+ if (ret) {
+ mlx5dr_icm_free_chunk(action->rewrite.chunk);
+ return ret;
+ }
+ return 0;
+ }
+ default:
+ mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type);
+ return -EINVAL;
+ }
+}
+
+struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void)
+{
+ return dr_action_create_generic(DR_ACTION_TYP_POP_VLAN);
+}
+
+struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn,
+ __be32 vlan_hdr)
+{
+ u32 vlan_hdr_h = ntohl(vlan_hdr);
+ u16 ethertype = vlan_hdr_h >> 16;
+ struct mlx5dr_action *action;
+
+ if (ethertype != SVLAN_ETHERTYPE && ethertype != CVLAN_ETHERTYPE) {
+ mlx5dr_dbg(dmn, "Invalid vlan ethertype\n");
+ return NULL;
+ }
+
+ action = dr_action_create_generic(DR_ACTION_TYP_PUSH_VLAN);
+ if (!action)
+ return NULL;
+
+ action->push_vlan.vlan_hdr = vlan_hdr_h;
+ return action;
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
+ enum mlx5dr_action_reformat_type reformat_type,
+ size_t data_sz,
+ void *data)
+{
+ enum mlx5dr_action_type action_type;
+ struct mlx5dr_action *action;
+ int ret;
+
+ refcount_inc(&dmn->refcount);
+
+ /* General checks */
+ ret = dr_action_reformat_to_action_type(reformat_type, &action_type);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Invalid reformat_type provided\n");
+ goto dec_ref;
+ }
+
+ ret = dr_action_verify_reformat_params(action_type, dmn, data_sz, data);
+ if (ret)
+ goto dec_ref;
+
+ action = dr_action_create_generic(action_type);
+ if (!action)
+ goto dec_ref;
+
+ action->reformat.dmn = dmn;
+
+ ret = dr_action_create_reformat_action(dmn,
+ data_sz,
+ data,
+ action);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed creating reformat action %d\n", ret);
+ goto free_action;
+ }
+
+ return action;
+
+free_action:
+ kfree(action);
+dec_ref:
+ refcount_dec(&dmn->refcount);
+ return NULL;
+}
+
+static const struct dr_action_modify_field_conv *
+dr_action_modify_get_hw_info(u16 sw_field)
+{
+ const struct dr_action_modify_field_conv *hw_action_info;
+
+ if (sw_field >= ARRAY_SIZE(dr_action_conv_arr))
+ goto not_found;
+
+ hw_action_info = &dr_action_conv_arr[sw_field];
+ if (!hw_action_info->end && !hw_action_info->start)
+ goto not_found;
+
+ return hw_action_info;
+
+not_found:
+ return NULL;
+}
+
+static int
+dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn,
+ __be64 *sw_action,
+ __be64 *hw_action,
+ const struct dr_action_modify_field_conv **ret_hw_info)
+{
+ const struct dr_action_modify_field_conv *hw_action_info;
+ u8 offset, length, max_length, action;
+ u16 sw_field;
+ u8 hw_opcode;
+ u32 data;
+
+ /* Get SW modify action data */
+ action = MLX5_GET(set_action_in, sw_action, action_type);
+ length = MLX5_GET(set_action_in, sw_action, length);
+ offset = MLX5_GET(set_action_in, sw_action, offset);
+ sw_field = MLX5_GET(set_action_in, sw_action, field);
+ data = MLX5_GET(set_action_in, sw_action, data);
+
+ /* Convert SW data to HW modify action format */
+ hw_action_info = dr_action_modify_get_hw_info(sw_field);
+ if (!hw_action_info) {
+ mlx5dr_dbg(dmn, "Modify action invalid field given\n");
+ return -EINVAL;
+ }
+
+ max_length = hw_action_info->end - hw_action_info->start + 1;
+
+ switch (action) {
+ case MLX5_ACTION_TYPE_SET:
+ hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_SET;
+ /* PRM defines that length zero specific length of 32bits */
+ if (!length)
+ length = 32;
+
+ if (length + offset > max_length) {
+ mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n");
+ return -EINVAL;
+ }
+ break;
+
+ case MLX5_ACTION_TYPE_ADD:
+ hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_ADD;
+ offset = 0;
+ length = max_length;
+ break;
+
+ default:
+ mlx5dr_info(dmn, "Unsupported action_type for modify action\n");
+ return -EOPNOTSUPP;
+ }
+
+ MLX5_SET(dr_action_hw_set, hw_action, opcode, hw_opcode);
+
+ MLX5_SET(dr_action_hw_set, hw_action, destination_field_code,
+ hw_action_info->hw_field);
+
+ MLX5_SET(dr_action_hw_set, hw_action, destination_left_shifter,
+ hw_action_info->start + offset);
+
+ MLX5_SET(dr_action_hw_set, hw_action, destination_length,
+ length == 32 ? 0 : length);
+
+ MLX5_SET(dr_action_hw_set, hw_action, inline_data, data);
+
+ *ret_hw_info = hw_action_info;
+
+ return 0;
+}
+
+static int
+dr_action_modify_check_field_limitation(struct mlx5dr_domain *dmn,
+ const __be64 *sw_action)
+{
+ u16 sw_field;
+ u8 action;
+
+ sw_field = MLX5_GET(set_action_in, sw_action, field);
+ action = MLX5_GET(set_action_in, sw_action, action_type);
+
+ /* Check if SW field is supported in current domain (RX/TX) */
+ if (action == MLX5_ACTION_TYPE_SET) {
+ if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_A) {
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n",
+ sw_field);
+ return -EINVAL;
+ }
+ }
+
+ if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_B) {
+ if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n",
+ sw_field);
+ return -EINVAL;
+ }
+ }
+ } else if (action == MLX5_ACTION_TYPE_ADD) {
+ if (sw_field != MLX5_ACTION_IN_FIELD_OUT_IP_TTL &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM &&
+ sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM) {
+ mlx5dr_dbg(dmn, "Unsupported field %d for add action\n", sw_field);
+ return -EINVAL;
+ }
+ } else {
+ mlx5dr_info(dmn, "Unsupported action %d modify action\n", action);
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
+static bool
+dr_action_modify_check_is_ttl_modify(const u64 *sw_action)
+{
+ u16 sw_field = MLX5_GET(set_action_in, sw_action, field);
+
+ return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL;
+}
+
+static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn,
+ u32 max_hw_actions,
+ u32 num_sw_actions,
+ __be64 sw_actions[],
+ __be64 hw_actions[],
+ u32 *num_hw_actions,
+ bool *modify_ttl)
+{
+ const struct dr_action_modify_field_conv *hw_action_info;
+ u16 hw_field = MLX5DR_ACTION_MDFY_HW_FLD_RESERVED;
+ u32 l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE;
+ u32 l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE;
+ int ret, i, hw_idx = 0;
+ __be64 *sw_action;
+ __be64 hw_action;
+
+ *modify_ttl = false;
+
+ for (i = 0; i < num_sw_actions; i++) {
+ sw_action = &sw_actions[i];
+
+ ret = dr_action_modify_check_field_limitation(dmn, sw_action);
+ if (ret)
+ return ret;
+
+ if (!(*modify_ttl))
+ *modify_ttl = dr_action_modify_check_is_ttl_modify(sw_action);
+
+ /* Convert SW action to HW action */
+ ret = dr_action_modify_sw_to_hw(dmn,
+ sw_action,
+ &hw_action,
+ &hw_action_info);
+ if (ret)
+ return ret;
+
+ /* Due to a HW limitation we cannot modify 2 different L3 types */
+ if (l3_type && hw_action_info->l3_type &&
+ hw_action_info->l3_type != l3_type) {
+ mlx5dr_dbg(dmn, "Action list can't support two different L3 types\n");
+ return -EINVAL;
+ }
+ if (hw_action_info->l3_type)
+ l3_type = hw_action_info->l3_type;
+
+ /* Due to a HW limitation we cannot modify two different L4 types */
+ if (l4_type && hw_action_info->l4_type &&
+ hw_action_info->l4_type != l4_type) {
+ mlx5dr_dbg(dmn, "Action list can't support two different L4 types\n");
+ return -EINVAL;
+ }
+ if (hw_action_info->l4_type)
+ l4_type = hw_action_info->l4_type;
+
+ /* HW reads and executes two actions at once this means we
+ * need to create a gap if two actions access the same field
+ */
+ if ((hw_idx % 2) && hw_field == hw_action_info->hw_field) {
+ /* Check if after gap insertion the total number of HW
+ * modify actions doesn't exceeds the limit
+ */
+ hw_idx++;
+ if ((num_sw_actions + hw_idx - i) >= max_hw_actions) {
+ mlx5dr_dbg(dmn, "Modify header action number exceeds HW limit\n");
+ return -EINVAL;
+ }
+ }
+ hw_field = hw_action_info->hw_field;
+
+ hw_actions[hw_idx] = hw_action;
+ hw_idx++;
+ }
+
+ *num_hw_actions = hw_idx;
+
+ return 0;
+}
+
+static int dr_action_create_modify_action(struct mlx5dr_domain *dmn,
+ size_t actions_sz,
+ __be64 actions[],
+ struct mlx5dr_action *action)
+{
+ struct mlx5dr_icm_chunk *chunk;
+ u32 max_hw_actions;
+ u32 num_hw_actions;
+ u32 num_sw_actions;
+ __be64 *hw_actions;
+ bool modify_ttl;
+ int ret;
+
+ num_sw_actions = actions_sz / DR_MODIFY_ACTION_SIZE;
+ max_hw_actions = mlx5dr_icm_pool_chunk_size_to_entries(DR_CHUNK_SIZE_16);
+
+ if (num_sw_actions > max_hw_actions) {
+ mlx5dr_dbg(dmn, "Max number of actions %d exceeds limit %d\n",
+ num_sw_actions, max_hw_actions);
+ return -EINVAL;
+ }
+
+ chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool, DR_CHUNK_SIZE_16);
+ if (!chunk)
+ return -ENOMEM;
+
+ hw_actions = kcalloc(1, max_hw_actions * DR_MODIFY_ACTION_SIZE, GFP_KERNEL);
+ if (!hw_actions) {
+ ret = -ENOMEM;
+ goto free_chunk;
+ }
+
+ ret = dr_actions_convert_modify_header(dmn,
+ max_hw_actions,
+ num_sw_actions,
+ actions,
+ hw_actions,
+ &num_hw_actions,
+ &modify_ttl);
+ if (ret)
+ goto free_hw_actions;
+
+ action->rewrite.chunk = chunk;
+ action->rewrite.modify_ttl = modify_ttl;
+ action->rewrite.data = (u8 *)hw_actions;
+ action->rewrite.num_of_actions = num_hw_actions;
+ action->rewrite.index = (chunk->icm_addr -
+ dmn->info.caps.hdr_modify_icm_addr) /
+ ACTION_CACHE_LINE_SIZE;
+
+ ret = mlx5dr_send_postsend_action(dmn, action);
+ if (ret)
+ goto free_hw_actions;
+
+ return 0;
+
+free_hw_actions:
+ kfree(hw_actions);
+free_chunk:
+ mlx5dr_icm_free_chunk(chunk);
+ return ret;
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_modify_header(struct mlx5dr_domain *dmn,
+ u32 flags,
+ size_t actions_sz,
+ __be64 actions[])
+{
+ struct mlx5dr_action *action;
+ int ret = 0;
+
+ refcount_inc(&dmn->refcount);
+
+ if (actions_sz % DR_MODIFY_ACTION_SIZE) {
+ mlx5dr_dbg(dmn, "Invalid modify actions size provided\n");
+ goto dec_ref;
+ }
+
+ action = dr_action_create_generic(DR_ACTION_TYP_MODIFY_HDR);
+ if (!action)
+ goto dec_ref;
+
+ action->rewrite.dmn = dmn;
+
+ ret = dr_action_create_modify_action(dmn,
+ actions_sz,
+ actions,
+ action);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed creating modify header action %d\n", ret);
+ goto free_action;
+ }
+
+ return action;
+
+free_action:
+ kfree(action);
+dec_ref:
+ refcount_dec(&dmn->refcount);
+ return NULL;
+}
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn,
+ u32 vport, u8 vhca_id_valid,
+ u16 vhca_id)
+{
+ struct mlx5dr_cmd_vport_cap *vport_cap;
+ struct mlx5dr_domain *vport_dmn;
+ struct mlx5dr_action *action;
+ u8 peer_vport;
+
+ peer_vport = vhca_id_valid && (vhca_id != dmn->info.caps.gvmi);
+ vport_dmn = peer_vport ? dmn->peer_dmn : dmn;
+ if (!vport_dmn) {
+ mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n");
+ return NULL;
+ }
+
+ if (vport_dmn->type != MLX5DR_DOMAIN_TYPE_FDB) {
+ mlx5dr_dbg(dmn, "Domain doesn't support vport actions\n");
+ return NULL;
+ }
+
+ vport_cap = mlx5dr_get_vport_cap(&vport_dmn->info.caps, vport);
+ if (!vport_cap) {
+ mlx5dr_dbg(dmn, "Failed to get vport %d caps\n", vport);
+ return NULL;
+ }
+
+ action = dr_action_create_generic(DR_ACTION_TYP_VPORT);
+ if (!action)
+ return NULL;
+
+ action->vport.dmn = vport_dmn;
+ action->vport.caps = vport_cap;
+
+ return action;
+}
+
+int mlx5dr_action_destroy(struct mlx5dr_action *action)
+{
+ if (refcount_read(&action->refcount) > 1)
+ return -EBUSY;
+
+ switch (action->action_type) {
+ case DR_ACTION_TYP_FT:
+ if (!action->dest_tbl.is_fw_tbl)
+ refcount_dec(&action->dest_tbl.tbl->refcount);
+ break;
+ case DR_ACTION_TYP_TNL_L2_TO_L2:
+ refcount_dec(&action->reformat.dmn->refcount);
+ break;
+ case DR_ACTION_TYP_TNL_L3_TO_L2:
+ mlx5dr_icm_free_chunk(action->rewrite.chunk);
+ refcount_dec(&action->reformat.dmn->refcount);
+ break;
+ case DR_ACTION_TYP_L2_TO_TNL_L2:
+ case DR_ACTION_TYP_L2_TO_TNL_L3:
+ mlx5dr_cmd_destroy_reformat_ctx((action->reformat.dmn)->mdev,
+ action->reformat.reformat_id);
+ refcount_dec(&action->reformat.dmn->refcount);
+ break;
+ case DR_ACTION_TYP_MODIFY_HDR:
+ mlx5dr_icm_free_chunk(action->rewrite.chunk);
+ refcount_dec(&action->rewrite.dmn->refcount);
+ break;
+ default:
+ break;
+ }
+
+ kfree(action);
+ return 0;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 11/18] net/mlx5: DR, Expose steering rule functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Rules are the actual objects that tie matchers, header values and
actions. Each rule belongs to a matcher, which can hold multiple rules
sharing the same mask. Each rule is a specific set of values and
actions.
When a packet reaches a matcher it is being matched against the
matcher`s rules. In case of a match over a rule its actions will be
executed. Each rule object contains a set of STEs, where each STE is a
definition of match values and actions defined by the rule.
This file handles the rule operations and processing.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_rule.c | 1243 +++++++++++++++++
1 file changed, 1243 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
new file mode 100644
index 000000000000..3bc3f66b8fa8
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -0,0 +1,1243 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define DR_RULE_MAX_STE_CHAIN (DR_RULE_MAX_STES + DR_ACTION_MAX_STES)
+
+struct mlx5dr_rule_action_member {
+ struct mlx5dr_action *action;
+ struct list_head list;
+};
+
+static int dr_rule_append_to_miss_list(struct mlx5dr_ste *new_last_ste,
+ struct list_head *miss_list,
+ struct list_head *send_list)
+{
+ struct mlx5dr_ste_send_info *ste_info_last;
+ struct mlx5dr_ste *last_ste;
+
+ /* The new entry will be inserted after the last */
+ last_ste = list_entry(miss_list->prev, struct mlx5dr_ste, miss_list_node);
+ WARN_ON(!last_ste);
+
+ ste_info_last = kzalloc(sizeof(*ste_info_last), GFP_KERNEL);
+ if (!ste_info_last)
+ return -ENOMEM;
+
+ mlx5dr_ste_set_miss_addr(last_ste->hw_ste,
+ mlx5dr_ste_get_icm_addr(new_last_ste));
+ list_add_tail(&new_last_ste->miss_list_node, miss_list);
+
+ mlx5dr_send_fill_and_append_ste_send_info(last_ste, DR_STE_SIZE_REDUCED,
+ 0, last_ste->hw_ste,
+ ste_info_last, send_list, true);
+
+ return 0;
+}
+
+static struct mlx5dr_ste *
+dr_rule_create_collision_htbl(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ u8 *hw_ste)
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_ste_htbl *new_htbl;
+ struct mlx5dr_ste *ste;
+
+ /* Create new table for miss entry */
+ new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ DR_CHUNK_SIZE_1,
+ MLX5DR_STE_LU_TYPE_DONT_CARE,
+ 0);
+ if (!new_htbl) {
+ mlx5dr_dbg(dmn, "Failed allocating collision table\n");
+ return NULL;
+ }
+
+ /* One and only entry, never grows */
+ ste = new_htbl->ste_arr;
+ mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr);
+ mlx5dr_htbl_get(new_htbl);
+
+ return ste;
+}
+
+static struct mlx5dr_ste *
+dr_rule_create_collision_entry(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ u8 *hw_ste,
+ struct mlx5dr_ste *orig_ste)
+{
+ struct mlx5dr_ste *ste;
+
+ ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste);
+ if (!ste) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed creating collision entry\n");
+ return NULL;
+ }
+
+ ste->ste_chain_location = orig_ste->ste_chain_location;
+
+ /* In collision entry, all members share the same miss_list_head */
+ ste->htbl->miss_list = mlx5dr_ste_get_miss_list(orig_ste);
+
+ /* Next table */
+ if (mlx5dr_ste_create_next_htbl(matcher, nic_matcher, ste, hw_ste,
+ DR_CHUNK_SIZE_1)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n");
+ goto free_tbl;
+ }
+
+ return ste;
+
+free_tbl:
+ mlx5dr_ste_free(ste, matcher, nic_matcher);
+ return NULL;
+}
+
+static int
+dr_rule_handle_one_ste_in_update_list(struct mlx5dr_ste_send_info *ste_info,
+ struct mlx5dr_domain *dmn)
+{
+ int ret;
+
+ list_del(&ste_info->send_list);
+ ret = mlx5dr_send_postsend_ste(dmn, ste_info->ste, ste_info->data,
+ ste_info->size, ste_info->offset);
+ if (ret)
+ goto out;
+ /* Copy data to ste, only reduced size, the last 16B (mask)
+ * is already written to the hw.
+ */
+ memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_REDUCED);
+
+out:
+ kfree(ste_info);
+ return ret;
+}
+
+static int dr_rule_send_update_list(struct list_head *send_ste_list,
+ struct mlx5dr_domain *dmn,
+ bool is_reverse)
+{
+ struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info;
+ int ret;
+
+ if (is_reverse) {
+ list_for_each_entry_safe_reverse(ste_info, tmp_ste_info,
+ send_ste_list, send_list) {
+ ret = dr_rule_handle_one_ste_in_update_list(ste_info,
+ dmn);
+ if (ret)
+ return ret;
+ }
+ } else {
+ list_for_each_entry_safe(ste_info, tmp_ste_info,
+ send_ste_list, send_list) {
+ ret = dr_rule_handle_one_ste_in_update_list(ste_info,
+ dmn);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static struct mlx5dr_ste *
+dr_rule_find_ste_in_miss_list(struct list_head *miss_list, u8 *hw_ste)
+{
+ struct mlx5dr_ste *ste;
+
+ if (list_empty(miss_list))
+ return NULL;
+
+ /* Check if hw_ste is present in the list */
+ list_for_each_entry(ste, miss_list, miss_list_node) {
+ if (mlx5dr_ste_equal_tag(ste->hw_ste, hw_ste))
+ return ste;
+ }
+
+ return NULL;
+}
+
+static struct mlx5dr_ste *
+dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct list_head *update_list,
+ struct mlx5dr_ste *col_ste,
+ u8 *hw_ste)
+{
+ struct mlx5dr_ste *new_ste;
+ int ret;
+
+ new_ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste);
+ if (!new_ste)
+ return NULL;
+
+ /* In collision entry, all members share the same miss_list_head */
+ new_ste->htbl->miss_list = mlx5dr_ste_get_miss_list(col_ste);
+
+ /* Update the previous from the list */
+ ret = dr_rule_append_to_miss_list(new_ste,
+ mlx5dr_ste_get_miss_list(col_ste),
+ update_list);
+ if (ret) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed update dup entry\n");
+ goto err_exit;
+ }
+
+ return new_ste;
+
+err_exit:
+ mlx5dr_ste_free(new_ste, matcher, nic_matcher);
+ return NULL;
+}
+
+static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste *cur_ste,
+ struct mlx5dr_ste *new_ste)
+{
+ new_ste->next_htbl = cur_ste->next_htbl;
+ new_ste->ste_chain_location = cur_ste->ste_chain_location;
+
+ if (!mlx5dr_ste_is_last_in_rule(nic_matcher, new_ste->ste_chain_location))
+ new_ste->next_htbl->pointing_ste = new_ste;
+
+ /* We need to copy the refcount since this ste
+ * may have been traversed several times
+ */
+ refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount));
+
+ /* Link old STEs rule_mem list to the new ste */
+ mlx5dr_rule_update_rule_member(cur_ste, new_ste);
+ INIT_LIST_HEAD(&new_ste->rule_list);
+ list_splice_tail_init(&cur_ste->rule_list, &new_ste->rule_list);
+}
+
+static struct mlx5dr_ste *
+dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste *cur_ste,
+ struct mlx5dr_ste_htbl *new_htbl,
+ struct list_head *update_list)
+{
+ struct mlx5dr_ste_send_info *ste_info;
+ bool use_update_list = false;
+ u8 hw_ste[DR_STE_SIZE] = {};
+ struct mlx5dr_ste *new_ste;
+ int new_idx;
+ u8 sb_idx;
+
+ /* Copy STE mask from the matcher */
+ sb_idx = cur_ste->ste_chain_location - 1;
+ mlx5dr_ste_set_bit_mask(hw_ste, nic_matcher->ste_builder[sb_idx].bit_mask);
+
+ /* Copy STE control and tag */
+ memcpy(hw_ste, cur_ste->hw_ste, DR_STE_SIZE_REDUCED);
+ mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr);
+
+ new_idx = mlx5dr_ste_calc_hash_index(hw_ste, new_htbl);
+ new_ste = &new_htbl->ste_arr[new_idx];
+
+ if (mlx5dr_ste_not_used_ste(new_ste)) {
+ mlx5dr_htbl_get(new_htbl);
+ list_add_tail(&new_ste->miss_list_node,
+ mlx5dr_ste_get_miss_list(new_ste));
+ } else {
+ new_ste = dr_rule_rehash_handle_collision(matcher,
+ nic_matcher,
+ update_list,
+ new_ste,
+ hw_ste);
+ if (!new_ste) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed adding collision entry, index: %d\n",
+ new_idx);
+ return NULL;
+ }
+ new_htbl->ctrl.num_of_collisions++;
+ use_update_list = true;
+ }
+
+ memcpy(new_ste->hw_ste, hw_ste, DR_STE_SIZE_REDUCED);
+
+ new_htbl->ctrl.num_of_valid_entries++;
+
+ if (use_update_list) {
+ ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL);
+ if (!ste_info)
+ goto err_exit;
+
+ mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0,
+ hw_ste, ste_info,
+ update_list, true);
+ }
+
+ dr_rule_rehash_copy_ste_ctrl(matcher, nic_matcher, cur_ste, new_ste);
+
+ return new_ste;
+
+err_exit:
+ mlx5dr_ste_free(new_ste, matcher, nic_matcher);
+ return NULL;
+}
+
+static int dr_rule_rehash_copy_miss_list(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct list_head *cur_miss_list,
+ struct mlx5dr_ste_htbl *new_htbl,
+ struct list_head *update_list)
+{
+ struct mlx5dr_ste *tmp_ste, *cur_ste, *new_ste;
+
+ if (list_empty(cur_miss_list))
+ return 0;
+
+ list_for_each_entry_safe(cur_ste, tmp_ste, cur_miss_list, miss_list_node) {
+ new_ste = dr_rule_rehash_copy_ste(matcher,
+ nic_matcher,
+ cur_ste,
+ new_htbl,
+ update_list);
+ if (!new_ste)
+ goto err_insert;
+
+ list_del(&cur_ste->miss_list_node);
+ mlx5dr_htbl_put(cur_ste->htbl);
+ }
+ return 0;
+
+err_insert:
+ mlx5dr_err(matcher->tbl->dmn, "Fatal error during resize\n");
+ WARN_ON(true);
+ return -EINVAL;
+}
+
+static int dr_rule_rehash_copy_htbl(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste_htbl *cur_htbl,
+ struct mlx5dr_ste_htbl *new_htbl,
+ struct list_head *update_list)
+{
+ struct mlx5dr_ste *cur_ste;
+ int cur_entries;
+ int err = 0;
+ int i;
+
+ cur_entries = mlx5dr_icm_pool_chunk_size_to_entries(cur_htbl->chunk_size);
+
+ if (cur_entries < 1) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Invalid number of entries\n");
+ return -EINVAL;
+ }
+
+ for (i = 0; i < cur_entries; i++) {
+ cur_ste = &cur_htbl->ste_arr[i];
+ if (mlx5dr_ste_not_used_ste(cur_ste)) /* Empty, nothing to copy */
+ continue;
+
+ err = dr_rule_rehash_copy_miss_list(matcher,
+ nic_matcher,
+ mlx5dr_ste_get_miss_list(cur_ste),
+ new_htbl,
+ update_list);
+ if (err)
+ goto clean_copy;
+ }
+
+clean_copy:
+ return err;
+}
+
+static struct mlx5dr_ste_htbl *
+dr_rule_rehash_htbl(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule,
+ struct mlx5dr_ste_htbl *cur_htbl,
+ u8 ste_location,
+ struct list_head *update_list,
+ enum mlx5dr_icm_chunk_size new_size)
+{
+ struct mlx5dr_ste_send_info *del_ste_info, *tmp_ste_info;
+ struct mlx5dr_matcher *matcher = rule->matcher;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_matcher_rx_tx *nic_matcher;
+ struct mlx5dr_ste_send_info *ste_info;
+ struct mlx5dr_htbl_connect_info info;
+ struct mlx5dr_domain_rx_tx *nic_dmn;
+ u8 formatted_ste[DR_STE_SIZE] = {};
+ LIST_HEAD(rehash_table_send_list);
+ struct mlx5dr_ste *ste_to_update;
+ struct mlx5dr_ste_htbl *new_htbl;
+ int err;
+
+ nic_matcher = nic_rule->nic_matcher;
+ nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+
+ ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL);
+ if (!ste_info)
+ return NULL;
+
+ new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+ new_size,
+ cur_htbl->lu_type,
+ cur_htbl->byte_mask);
+ if (!new_htbl) {
+ mlx5dr_err(dmn, "Failed to allocate new hash table\n");
+ goto free_ste_info;
+ }
+
+ /* Write new table to HW */
+ info.type = CONNECT_MISS;
+ info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr;
+ mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi,
+ nic_dmn,
+ new_htbl,
+ formatted_ste,
+ &info);
+
+ new_htbl->pointing_ste = cur_htbl->pointing_ste;
+ new_htbl->pointing_ste->next_htbl = new_htbl;
+ err = dr_rule_rehash_copy_htbl(matcher,
+ nic_matcher,
+ cur_htbl,
+ new_htbl,
+ &rehash_table_send_list);
+ if (err)
+ goto free_new_htbl;
+
+ if (mlx5dr_send_postsend_htbl(dmn, new_htbl, formatted_ste,
+ nic_matcher->ste_builder[ste_location - 1].bit_mask)) {
+ mlx5dr_err(dmn, "Failed writing table to HW\n");
+ goto free_new_htbl;
+ }
+
+ /* Writing to the hw is done in regular order of rehash_table_send_list,
+ * in order to have the origin data written before the miss address of
+ * collision entries, if exists.
+ */
+ if (dr_rule_send_update_list(&rehash_table_send_list, dmn, false)) {
+ mlx5dr_err(dmn, "Failed updating table to HW\n");
+ goto free_ste_list;
+ }
+
+ /* Connect previous hash table to current */
+ if (ste_location == 1) {
+ /* The previous table is an anchor, anchors size is always one STE */
+ struct mlx5dr_ste_htbl *prev_htbl = cur_htbl->pointing_ste->htbl;
+
+ /* On matcher s_anchor we keep an extra refcount */
+ mlx5dr_htbl_get(new_htbl);
+ mlx5dr_htbl_put(cur_htbl);
+
+ nic_matcher->s_htbl = new_htbl;
+
+ /* It is safe to operate dr_ste_set_hit_addr on the hw_ste here
+ * (48B len) which works only on first 32B
+ */
+ mlx5dr_ste_set_hit_addr(prev_htbl->ste_arr[0].hw_ste,
+ new_htbl->chunk->icm_addr,
+ new_htbl->chunk->num_of_entries);
+
+ ste_to_update = &prev_htbl->ste_arr[0];
+ } else {
+ mlx5dr_ste_set_hit_addr_by_next_htbl(cur_htbl->pointing_ste->hw_ste,
+ new_htbl);
+ ste_to_update = cur_htbl->pointing_ste;
+ }
+
+ mlx5dr_send_fill_and_append_ste_send_info(ste_to_update, DR_STE_SIZE_REDUCED,
+ 0, ste_to_update->hw_ste, ste_info,
+ update_list, false);
+
+ return new_htbl;
+
+free_ste_list:
+ /* Clean all ste_info's from the new table */
+ list_for_each_entry_safe(del_ste_info, tmp_ste_info,
+ &rehash_table_send_list, send_list) {
+ list_del(&del_ste_info->send_list);
+ kfree(del_ste_info);
+ }
+
+free_new_htbl:
+ mlx5dr_ste_htbl_free(new_htbl);
+free_ste_info:
+ kfree(ste_info);
+ mlx5dr_info(dmn, "Failed creating rehash table\n");
+ return NULL;
+}
+
+static struct mlx5dr_ste_htbl *dr_rule_rehash(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule,
+ struct mlx5dr_ste_htbl *cur_htbl,
+ u8 ste_location,
+ struct list_head *update_list)
+{
+ struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn;
+ enum mlx5dr_icm_chunk_size new_size;
+
+ new_size = mlx5dr_icm_next_higher_chunk(cur_htbl->chunk_size);
+ new_size = min_t(u32, new_size, dmn->info.max_log_sw_icm_sz);
+
+ if (new_size == cur_htbl->chunk_size)
+ return NULL; /* Skip rehash, we already at the max size */
+
+ return dr_rule_rehash_htbl(rule, nic_rule, cur_htbl, ste_location,
+ update_list, new_size);
+}
+
+static struct mlx5dr_ste *
+dr_rule_handle_collision(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste *ste,
+ u8 *hw_ste,
+ struct list_head *miss_list,
+ struct list_head *send_list)
+{
+ struct mlx5dr_ste_send_info *ste_info;
+ struct mlx5dr_ste *new_ste;
+
+ ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL);
+ if (!ste_info)
+ return NULL;
+
+ new_ste = dr_rule_create_collision_entry(matcher, nic_matcher, hw_ste, ste);
+ if (!new_ste)
+ goto free_send_info;
+
+ if (dr_rule_append_to_miss_list(new_ste, miss_list, send_list)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed to update prev miss_list\n");
+ goto err_exit;
+ }
+
+ mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0, hw_ste,
+ ste_info, send_list, false);
+
+ ste->htbl->ctrl.num_of_collisions++;
+ ste->htbl->ctrl.num_of_valid_entries++;
+
+ return new_ste;
+
+err_exit:
+ mlx5dr_ste_free(new_ste, matcher, nic_matcher);
+free_send_info:
+ kfree(ste_info);
+ return NULL;
+}
+
+static void dr_rule_remove_action_members(struct mlx5dr_rule *rule)
+{
+ struct mlx5dr_rule_action_member *action_mem;
+ struct mlx5dr_rule_action_member *tmp;
+
+ list_for_each_entry_safe(action_mem, tmp, &rule->rule_actions_list, list) {
+ list_del(&action_mem->list);
+ refcount_dec(&action_mem->action->refcount);
+ kvfree(action_mem);
+ }
+}
+
+static int dr_rule_add_action_members(struct mlx5dr_rule *rule,
+ size_t num_actions,
+ struct mlx5dr_action *actions[])
+{
+ struct mlx5dr_rule_action_member *action_mem;
+ int i;
+
+ for (i = 0; i < num_actions; i++) {
+ action_mem = kvzalloc(sizeof(*action_mem), GFP_KERNEL);
+ if (!action_mem)
+ goto free_action_members;
+
+ action_mem->action = actions[i];
+ INIT_LIST_HEAD(&action_mem->list);
+ list_add_tail(&action_mem->list, &rule->rule_actions_list);
+ refcount_inc(&action_mem->action->refcount);
+ }
+
+ return 0;
+
+free_action_members:
+ dr_rule_remove_action_members(rule);
+ return -ENOMEM;
+}
+
+/* While the pointer of ste is no longer valid, like while moving ste to be
+ * the first in the miss_list, and to be in the origin table,
+ * all rule-members that are attached to this ste should update their ste member
+ * to the new pointer
+ */
+void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste,
+ struct mlx5dr_ste *new_ste)
+{
+ struct mlx5dr_rule_member *rule_mem;
+
+ if (!list_empty(&ste->rule_list))
+ list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list)
+ rule_mem->ste = new_ste;
+}
+
+static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule)
+{
+ struct mlx5dr_rule_member *rule_mem;
+ struct mlx5dr_rule_member *tmp_mem;
+
+ if (list_empty(&nic_rule->rule_members_list))
+ return;
+ list_for_each_entry_safe(rule_mem, tmp_mem, &nic_rule->rule_members_list, list) {
+ list_del(&rule_mem->list);
+ list_del(&rule_mem->use_ste_list);
+ mlx5dr_ste_put(rule_mem->ste, rule->matcher, nic_rule->nic_matcher);
+ kvfree(rule_mem);
+ }
+}
+
+static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl,
+ struct mlx5dr_domain *dmn,
+ struct mlx5dr_domain_rx_tx *nic_dmn)
+{
+ struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl;
+
+ if (dmn->info.max_log_sw_icm_sz <= htbl->chunk_size)
+ return false;
+
+ if (!ctrl->may_grow)
+ return false;
+
+ if (ctrl->num_of_collisions >= ctrl->increase_threshold &&
+ (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold)
+ return true;
+
+ return false;
+}
+
+static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule,
+ struct mlx5dr_ste *ste)
+{
+ struct mlx5dr_rule_member *rule_mem;
+
+ rule_mem = kvzalloc(sizeof(*rule_mem), GFP_KERNEL);
+ if (!rule_mem)
+ return -ENOMEM;
+
+ rule_mem->ste = ste;
+ list_add_tail(&rule_mem->list, &nic_rule->rule_members_list);
+
+ list_add_tail(&rule_mem->use_ste_list, &ste->rule_list);
+
+ return 0;
+}
+
+static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste *last_ste,
+ u8 *hw_ste_arr,
+ u32 new_hw_ste_arr_sz)
+{
+ struct mlx5dr_matcher_rx_tx *nic_matcher = nic_rule->nic_matcher;
+ struct mlx5dr_ste_send_info *ste_info_arr[DR_ACTION_MAX_STES];
+ u8 num_of_builders = nic_matcher->num_of_builders;
+ struct mlx5dr_matcher *matcher = rule->matcher;
+ u8 *curr_hw_ste, *prev_hw_ste;
+ struct mlx5dr_ste *action_ste;
+ int i, k, ret;
+
+ /* Two cases:
+ * 1. num_of_builders is equal to new_hw_ste_arr_sz, the action in the ste
+ * 2. num_of_builders is less then new_hw_ste_arr_sz, new ste was added
+ * to support the action.
+ */
+ if (num_of_builders == new_hw_ste_arr_sz)
+ return 0;
+
+ for (i = num_of_builders, k = 0; i < new_hw_ste_arr_sz; i++, k++) {
+ curr_hw_ste = hw_ste_arr + i * DR_STE_SIZE;
+ prev_hw_ste = (i == 0) ? curr_hw_ste : hw_ste_arr + ((i - 1) * DR_STE_SIZE);
+ action_ste = dr_rule_create_collision_htbl(matcher,
+ nic_matcher,
+ curr_hw_ste);
+ if (!action_ste)
+ return -ENOMEM;
+
+ mlx5dr_ste_get(action_ste);
+
+ /* While free ste we go over the miss list, so add this ste to the list */
+ list_add_tail(&action_ste->miss_list_node,
+ mlx5dr_ste_get_miss_list(action_ste));
+
+ ste_info_arr[k] = kzalloc(sizeof(*ste_info_arr[k]),
+ GFP_KERNEL);
+ if (!ste_info_arr[k])
+ goto err_exit;
+
+ /* Point current ste to the new action */
+ mlx5dr_ste_set_hit_addr_by_next_htbl(prev_hw_ste, action_ste->htbl);
+ ret = dr_rule_add_member(nic_rule, action_ste);
+ if (ret) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed adding rule member\n");
+ goto free_ste_info;
+ }
+ mlx5dr_send_fill_and_append_ste_send_info(action_ste, DR_STE_SIZE, 0,
+ curr_hw_ste,
+ ste_info_arr[k],
+ send_ste_list, false);
+ }
+
+ return 0;
+
+free_ste_info:
+ kfree(ste_info_arr[k]);
+err_exit:
+ mlx5dr_ste_put(action_ste, matcher, nic_matcher);
+ return -ENOMEM;
+}
+
+static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_matcher_rx_tx *nic_matcher,
+ struct mlx5dr_ste_htbl *cur_htbl,
+ struct mlx5dr_ste *ste,
+ u8 ste_location,
+ u8 *hw_ste,
+ struct list_head *miss_list,
+ struct list_head *send_list)
+{
+ struct mlx5dr_ste_send_info *ste_info;
+
+ /* Take ref on table, only on first time this ste is used */
+ mlx5dr_htbl_get(cur_htbl);
+
+ /* new entry -> new branch */
+ list_add_tail(&ste->miss_list_node, miss_list);
+
+ mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr);
+
+ ste->ste_chain_location = ste_location;
+
+ ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL);
+ if (!ste_info)
+ goto clean_ste_setting;
+
+ if (mlx5dr_ste_create_next_htbl(matcher,
+ nic_matcher,
+ ste,
+ hw_ste,
+ DR_CHUNK_SIZE_1)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n");
+ goto clean_ste_info;
+ }
+
+ cur_htbl->ctrl.num_of_valid_entries++;
+
+ mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, 0, hw_ste,
+ ste_info, send_list, false);
+
+ return 0;
+
+clean_ste_info:
+ kfree(ste_info);
+clean_ste_setting:
+ list_del_init(&ste->miss_list_node);
+ mlx5dr_htbl_put(cur_htbl);
+
+ return -ENOMEM;
+}
+
+static struct mlx5dr_ste *
+dr_rule_handle_ste_branch(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule,
+ struct list_head *send_ste_list,
+ struct mlx5dr_ste_htbl *cur_htbl,
+ u8 *hw_ste,
+ u8 ste_location,
+ struct mlx5dr_ste_htbl **put_htbl)
+{
+ struct mlx5dr_matcher *matcher = rule->matcher;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_matcher_rx_tx *nic_matcher;
+ struct mlx5dr_domain_rx_tx *nic_dmn;
+ struct mlx5dr_ste_htbl *new_htbl;
+ struct mlx5dr_ste *matched_ste;
+ struct list_head *miss_list;
+ bool skip_rehash = false;
+ struct mlx5dr_ste *ste;
+ int index;
+
+ nic_matcher = nic_rule->nic_matcher;
+ nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+
+again:
+ index = mlx5dr_ste_calc_hash_index(hw_ste, cur_htbl);
+ miss_list = &cur_htbl->chunk->miss_list[index];
+ ste = &cur_htbl->ste_arr[index];
+
+ if (mlx5dr_ste_not_used_ste(ste)) {
+ if (dr_rule_handle_empty_entry(matcher, nic_matcher, cur_htbl,
+ ste, ste_location,
+ hw_ste, miss_list,
+ send_ste_list))
+ return NULL;
+ } else {
+ /* Hash table index in use, check if this ste is in the miss list */
+ matched_ste = dr_rule_find_ste_in_miss_list(miss_list, hw_ste);
+ if (matched_ste) {
+ /* If it is last STE in the chain, and has the same tag
+ * it means that all the previous stes are the same,
+ * if so, this rule is duplicated.
+ */
+ if (mlx5dr_ste_is_last_in_rule(nic_matcher,
+ matched_ste->ste_chain_location)) {
+ mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n");
+ return NULL;
+ }
+ return matched_ste;
+ }
+
+ if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) {
+ /* Hash table index in use, try to resize of the hash */
+ skip_rehash = true;
+
+ /* Hold the table till we update.
+ * Release in dr_rule_create_rule()
+ */
+ *put_htbl = cur_htbl;
+ mlx5dr_htbl_get(cur_htbl);
+
+ new_htbl = dr_rule_rehash(rule, nic_rule, cur_htbl,
+ ste_location, send_ste_list);
+ if (!new_htbl) {
+ mlx5dr_htbl_put(cur_htbl);
+ mlx5dr_info(dmn, "failed creating rehash table, htbl-log_size: %d\n",
+ cur_htbl->chunk_size);
+ } else {
+ cur_htbl = new_htbl;
+ }
+ goto again;
+ } else {
+ /* Hash table index in use, add another collision (miss) */
+ ste = dr_rule_handle_collision(matcher,
+ nic_matcher,
+ ste,
+ hw_ste,
+ miss_list,
+ send_ste_list);
+ if (!ste) {
+ mlx5dr_dbg(dmn, "failed adding collision entry, index: %d\n",
+ index);
+ return NULL;
+ }
+ }
+ }
+ return ste;
+}
+
+static bool dr_rule_cmp_value_to_mask(u8 *mask, u8 *value,
+ u32 s_idx, u32 e_idx)
+{
+ u32 i;
+
+ for (i = s_idx; i < e_idx; i++) {
+ if (value[i] & ~mask[i]) {
+ pr_info("Rule parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+ return true;
+}
+
+static bool dr_rule_verify(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *value,
+ struct mlx5dr_match_param *param)
+{
+ u8 match_criteria = matcher->match_criteria;
+ size_t value_size = value->match_sz;
+ u8 *mask_p = (u8 *)&matcher->mask;
+ u8 *param_p = (u8 *)param;
+ u32 s_idx, e_idx;
+
+ if (!value_size ||
+ (value_size > sizeof(struct mlx5dr_match_param) ||
+ (value_size % sizeof(u32)))) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule parameters length is incorrect\n");
+ return false;
+ }
+
+ mlx5dr_ste_copy_param(matcher->match_criteria, param, value);
+
+ if (match_criteria & DR_MATCHER_CRITERIA_OUTER) {
+ s_idx = offsetof(struct mlx5dr_match_param, outer);
+ e_idx = min(s_idx + sizeof(param->outer), value_size);
+
+ if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule outer parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC) {
+ s_idx = offsetof(struct mlx5dr_match_param, misc);
+ e_idx = min(s_idx + sizeof(param->misc), value_size);
+
+ if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule misc parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+
+ if (match_criteria & DR_MATCHER_CRITERIA_INNER) {
+ s_idx = offsetof(struct mlx5dr_match_param, inner);
+ e_idx = min(s_idx + sizeof(param->inner), value_size);
+
+ if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule inner parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC2) {
+ s_idx = offsetof(struct mlx5dr_match_param, misc2);
+ e_idx = min(s_idx + sizeof(param->misc2), value_size);
+
+ if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule misc2 parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+
+ if (match_criteria & DR_MATCHER_CRITERIA_MISC3) {
+ s_idx = offsetof(struct mlx5dr_match_param, misc3);
+ e_idx = min(s_idx + sizeof(param->misc3), value_size);
+
+ if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) {
+ mlx5dr_dbg(matcher->tbl->dmn, "Rule misc3 parameters contains a value not specified by mask\n");
+ return false;
+ }
+ }
+ return true;
+}
+
+static int dr_rule_destroy_rule_nic(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule)
+{
+ dr_rule_clean_rule_members(rule, nic_rule);
+ return 0;
+}
+
+static int dr_rule_destroy_rule_fdb(struct mlx5dr_rule *rule)
+{
+ dr_rule_destroy_rule_nic(rule, &rule->rx);
+ dr_rule_destroy_rule_nic(rule, &rule->tx);
+ return 0;
+}
+
+static int dr_rule_destroy_rule(struct mlx5dr_rule *rule)
+{
+ struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ dr_rule_destroy_rule_nic(rule, &rule->rx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ dr_rule_destroy_rule_nic(rule, &rule->tx);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ dr_rule_destroy_rule_fdb(rule);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ dr_rule_remove_action_members(rule);
+ kfree(rule);
+ return 0;
+}
+
+static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param)
+{
+ return (param->outer.ip_version == 6 ||
+ param->inner.ip_version == 6 ||
+ param->outer.ethertype == ETH_P_IPV6 ||
+ param->inner.ethertype == ETH_P_IPV6);
+}
+
+static bool dr_rule_skip(enum mlx5dr_domain_type domain,
+ enum mlx5dr_ste_entry_type ste_type,
+ struct mlx5dr_match_param *mask,
+ struct mlx5dr_match_param *value)
+{
+ if (domain != MLX5DR_DOMAIN_TYPE_FDB)
+ return false;
+
+ if (mask->misc.source_port) {
+ if (ste_type == MLX5DR_STE_TYPE_RX)
+ if (value->misc.source_port != WIRE_PORT)
+ return true;
+
+ if (ste_type == MLX5DR_STE_TYPE_TX)
+ if (value->misc.source_port == WIRE_PORT)
+ return true;
+ }
+
+ /* Metadata C can be used to describe the source vport */
+ if (mask->misc2.metadata_reg_c_0) {
+ if (ste_type == MLX5DR_STE_TYPE_RX)
+ if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) != WIRE_PORT)
+ return true;
+
+ if (ste_type == MLX5DR_STE_TYPE_TX)
+ if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) == WIRE_PORT)
+ return true;
+ }
+ return false;
+}
+
+static int
+dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
+ struct mlx5dr_rule_rx_tx *nic_rule,
+ struct mlx5dr_match_param *param,
+ size_t num_actions,
+ struct mlx5dr_action *actions[])
+{
+ struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info;
+ struct mlx5dr_matcher *matcher = rule->matcher;
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_matcher_rx_tx *nic_matcher;
+ struct mlx5dr_domain_rx_tx *nic_dmn;
+ struct mlx5dr_ste_htbl *htbl = NULL;
+ struct mlx5dr_ste_htbl *cur_htbl;
+ struct mlx5dr_ste *ste = NULL;
+ LIST_HEAD(send_ste_list);
+ u8 *hw_ste_arr = NULL;
+ u32 new_hw_ste_arr_sz;
+ int ret, i;
+
+ nic_matcher = nic_rule->nic_matcher;
+ nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+
+ INIT_LIST_HEAD(&nic_rule->rule_members_list);
+
+ if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param))
+ return 0;
+
+ ret = mlx5dr_matcher_select_builders(matcher,
+ nic_matcher,
+ dr_rule_is_ipv6(param));
+ if (ret)
+ goto out_err;
+
+ hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL);
+ if (!hw_ste_arr) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ /* Set the tag values inside the ste array */
+ ret = mlx5dr_ste_build_ste_arr(matcher, nic_matcher, param, hw_ste_arr);
+ if (ret)
+ goto free_hw_ste;
+
+ /* Set the actions values/addresses inside the ste array */
+ ret = mlx5dr_actions_build_ste_arr(matcher, nic_matcher, actions,
+ num_actions, hw_ste_arr,
+ &new_hw_ste_arr_sz);
+ if (ret)
+ goto free_hw_ste;
+
+ cur_htbl = nic_matcher->s_htbl;
+
+ /* Go over the array of STEs, and build dr_ste accordingly.
+ * The loop is over only the builders which are equal or less to the
+ * number of stes, in case we have actions that lives in other stes.
+ */
+ for (i = 0; i < nic_matcher->num_of_builders; i++) {
+ /* Calculate CRC and keep new ste entry */
+ u8 *cur_hw_ste_ent = hw_ste_arr + (i * DR_STE_SIZE);
+
+ ste = dr_rule_handle_ste_branch(rule,
+ nic_rule,
+ &send_ste_list,
+ cur_htbl,
+ cur_hw_ste_ent,
+ i + 1,
+ &htbl);
+ if (!ste) {
+ mlx5dr_err(dmn, "Failed creating next branch\n");
+ ret = -ENOENT;
+ goto free_rule;
+ }
+
+ cur_htbl = ste->next_htbl;
+
+ /* Keep all STEs in the rule struct */
+ ret = dr_rule_add_member(nic_rule, ste);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed adding rule member index %d\n", i);
+ goto free_ste;
+ }
+
+ mlx5dr_ste_get(ste);
+ }
+
+ /* Connect actions */
+ ret = dr_rule_handle_action_stes(rule, nic_rule, &send_ste_list,
+ ste, hw_ste_arr, new_hw_ste_arr_sz);
+ if (ret) {
+ mlx5dr_dbg(dmn, "Failed apply actions\n");
+ goto free_rule;
+ }
+ ret = dr_rule_send_update_list(&send_ste_list, dmn, true);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed sending ste!\n");
+ goto free_rule;
+ }
+
+ if (htbl)
+ mlx5dr_htbl_put(htbl);
+
+ return 0;
+
+free_ste:
+ mlx5dr_ste_put(ste, matcher, nic_matcher);
+free_rule:
+ dr_rule_clean_rule_members(rule, nic_rule);
+ /* Clean all ste_info's */
+ list_for_each_entry_safe(ste_info, tmp_ste_info, &send_ste_list, send_list) {
+ list_del(&ste_info->send_list);
+ kfree(ste_info);
+ }
+free_hw_ste:
+ kfree(hw_ste_arr);
+out_err:
+ return ret;
+}
+
+static int
+dr_rule_create_rule_fdb(struct mlx5dr_rule *rule,
+ struct mlx5dr_match_param *param,
+ size_t num_actions,
+ struct mlx5dr_action *actions[])
+{
+ struct mlx5dr_match_param copy_param = {};
+ int ret;
+
+ /* Copy match_param since they will be consumed during the first
+ * nic_rule insertion.
+ */
+ memcpy(©_param, param, sizeof(struct mlx5dr_match_param));
+
+ ret = dr_rule_create_rule_nic(rule, &rule->rx, param,
+ num_actions, actions);
+ if (ret)
+ return ret;
+
+ ret = dr_rule_create_rule_nic(rule, &rule->tx, ©_param,
+ num_actions, actions);
+ if (ret)
+ goto destroy_rule_nic_rx;
+
+ return 0;
+
+destroy_rule_nic_rx:
+ dr_rule_destroy_rule_nic(rule, &rule->rx);
+ return ret;
+}
+
+static struct mlx5dr_rule *
+dr_rule_create_rule(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *value,
+ size_t num_actions,
+ struct mlx5dr_action *actions[])
+{
+ struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+ struct mlx5dr_match_param param = {};
+ struct mlx5dr_rule *rule;
+ int ret;
+
+ if (!dr_rule_verify(matcher, value, ¶m))
+ return NULL;
+
+ rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+ if (!rule)
+ return NULL;
+
+ rule->matcher = matcher;
+ INIT_LIST_HEAD(&rule->rule_actions_list);
+
+ ret = dr_rule_add_action_members(rule, num_actions, actions);
+ if (ret)
+ goto free_rule;
+
+ switch (dmn->type) {
+ case MLX5DR_DOMAIN_TYPE_NIC_RX:
+ rule->rx.nic_matcher = &matcher->rx;
+ ret = dr_rule_create_rule_nic(rule, &rule->rx, ¶m,
+ num_actions, actions);
+ break;
+ case MLX5DR_DOMAIN_TYPE_NIC_TX:
+ rule->tx.nic_matcher = &matcher->tx;
+ ret = dr_rule_create_rule_nic(rule, &rule->tx, ¶m,
+ num_actions, actions);
+ break;
+ case MLX5DR_DOMAIN_TYPE_FDB:
+ rule->rx.nic_matcher = &matcher->rx;
+ rule->tx.nic_matcher = &matcher->tx;
+ ret = dr_rule_create_rule_fdb(rule, ¶m,
+ num_actions, actions);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ if (ret)
+ goto remove_action_members;
+
+ return rule;
+
+remove_action_members:
+ dr_rule_remove_action_members(rule);
+free_rule:
+ kfree(rule);
+ mlx5dr_info(dmn, "Failed creating rule\n");
+ return NULL;
+}
+
+struct mlx5dr_rule *mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
+ struct mlx5dr_match_parameters *value,
+ size_t num_actions,
+ struct mlx5dr_action *actions[])
+{
+ struct mlx5dr_rule *rule;
+
+ mutex_lock(&matcher->tbl->dmn->mutex);
+ refcount_inc(&matcher->refcount);
+
+ rule = dr_rule_create_rule(matcher, value, num_actions, actions);
+ if (!rule)
+ refcount_dec(&matcher->refcount);
+
+ mutex_unlock(&matcher->tbl->dmn->mutex);
+
+ return rule;
+}
+
+int mlx5dr_rule_destroy(struct mlx5dr_rule *rule)
+{
+ struct mlx5dr_matcher *matcher = rule->matcher;
+ struct mlx5dr_table *tbl = rule->matcher->tbl;
+ int ret;
+
+ mutex_lock(&tbl->dmn->mutex);
+
+ ret = dr_rule_destroy_rule(rule);
+
+ mutex_unlock(&tbl->dmn->mutex);
+
+ if (!ret)
+ refcount_dec(&matcher->refcount);
+ return ret;
+}
--
2.21.0
^ permalink raw reply related
* [net-next 14/18] net/mlx5: DR, Add CONFIG_MLX5_SW_STEERING for software steering support
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit,
Yevgeny Kliteynik, Mark Bloch, Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
Add new mlx5 Kconfig flag to allow selecting software steering
support and compile all the steering files only if the flag is
selected.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 7 +++++++
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 7 +++++++
drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile | 2 ++
3 files changed, 16 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 37fef8cd25e3..0d8dd885b7d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -154,3 +154,10 @@ config MLX5_EN_TLS
Build support for TLS cryptography-offload accelaration in the NIC.
Note: Support for hardware with this capability needs to be selected
for this option to become available.
+
+config MLX5_SW_STEERING
+ bool "Mellanox Technologies software-managed steering"
+ depends on MLX5_CORE_EN && MLX5_ESWITCH
+ default y
+ help
+ Build support for software-managed steering in the NIC.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index e9163875efd6..716558476eda 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -67,3 +67,10 @@ mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o \
en_accel/ktls.o en_accel/ktls_tx.o
+
+mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \
+ steering/dr_matcher.o steering/dr_rule.o \
+ steering/dr_icm_pool.o steering/dr_crc32.o \
+ steering/dr_ste.o steering/dr_send.o \
+ steering/dr_cmd.o steering/dr_fw.o \
+ steering/dr_action.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile
new file mode 100644
index 000000000000..c78512eed8d7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+subdir-ccflags-y += -I$(src)/..
--
2.21.0
^ permalink raw reply related
* [net-next 15/18] net/mlx5: Add direct rule fs_cmd implementation
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Maor Gottlieb,
Mark Bloch, Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Maor Gottlieb <maorg@mellanox.com>
Add support to create flow steering objects
via direct rule API (SW steering).
New layer is added - fs_dr, this layer translates the command that
fs_core sends to the FW into direct rule API. In case that direct
rule is not supported in some feature then -EOPNOTSUPP is
returned.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 2 +-
.../net/ethernet/mellanox/mlx5/core/fs_cmd.c | 28 +-
.../net/ethernet/mellanox/mlx5/core/fs_cmd.h | 7 +
.../net/ethernet/mellanox/mlx5/core/fs_core.c | 6 +
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 20 +-
.../mellanox/mlx5/core/steering/fs_dr.c | 600 ++++++++++++++++++
.../mellanox/mlx5/core/steering/fs_dr.h | 60 ++
7 files changed, 717 insertions(+), 6 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 716558476eda..5708fcc079ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -73,4 +73,4 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
steering/dr_icm_pool.o steering/dr_crc32.o \
steering/dr_ste.o steering/dr_send.o \
steering/dr_cmd.o steering/dr_fw.o \
- steering/dr_action.o
+ steering/dr_action.o steering/fs_dr.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 488f50dfb404..579c306caa7b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -135,6 +135,22 @@ static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace
{
}
+static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_root_namespace *peer_ns)
+{
+ return 0;
+}
+
+static int mlx5_cmd_stub_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+ return 0;
+}
+
+static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+ return 0;
+}
+
static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
struct mlx5_flow_table *ft, u32 underlay_qpn,
bool disconnect)
@@ -838,7 +854,10 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = {
.packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc,
.packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc,
.modify_header_alloc = mlx5_cmd_modify_header_alloc,
- .modify_header_dealloc = mlx5_cmd_modify_header_dealloc
+ .modify_header_dealloc = mlx5_cmd_modify_header_dealloc,
+ .set_peer = mlx5_cmd_stub_set_peer,
+ .create_ns = mlx5_cmd_stub_create_ns,
+ .destroy_ns = mlx5_cmd_stub_destroy_ns,
};
static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
@@ -854,10 +873,13 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
.packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc,
.packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc,
.modify_header_alloc = mlx5_cmd_stub_modify_header_alloc,
- .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc
+ .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc,
+ .set_peer = mlx5_cmd_stub_set_peer,
+ .create_ns = mlx5_cmd_stub_create_ns,
+ .destroy_ns = mlx5_cmd_stub_destroy_ns,
};
-static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
{
return &mlx5_flow_cmds;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 3268654d6748..d62de642eca9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -93,6 +93,12 @@ struct mlx5_flow_cmds {
void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns,
struct mlx5_modify_hdr *modify_hdr);
+
+ int (*set_peer)(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_root_namespace *peer_ns);
+
+ int (*create_ns)(struct mlx5_flow_root_namespace *ns);
+ int (*destroy_ns)(struct mlx5_flow_root_namespace *ns);
};
int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
@@ -108,5 +114,6 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
u32 *out);
const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type);
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 1d2333fd3080..c2d6e9f4cb90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2991,3 +2991,9 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
kfree(pkt_reformat);
}
EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
+
+int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_root_namespace *peer_ns)
+{
+ return ns->cmds->set_peer(ns, peer_ns);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index ea0f221685ab..a133ec5487ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -37,16 +37,23 @@
#include <linux/mlx5/fs.h>
#include <linux/rhashtable.h>
#include <linux/llist.h>
+#include <steering/fs_dr.h>
struct mlx5_modify_hdr {
enum mlx5_flow_namespace_type ns_type;
- u32 id;
+ union {
+ struct mlx5_fs_dr_action action;
+ u32 id;
+ };
};
struct mlx5_pkt_reformat {
enum mlx5_flow_namespace_type ns_type;
int reformat_type; /* from mlx5_ifc */
- u32 id;
+ union {
+ struct mlx5_fs_dr_action action;
+ u32 id;
+ };
};
/* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only,
@@ -139,6 +146,7 @@ struct mlx5_flow_handle {
/* Type of children is mlx5_flow_group */
struct mlx5_flow_table {
struct fs_node node;
+ struct mlx5_fs_dr_table fs_dr_table;
u32 id;
u16 vport;
unsigned int max_fte;
@@ -179,6 +187,7 @@ struct mlx5_ft_underlay_qp {
/* Type of children is mlx5_flow_rule */
struct fs_fte {
struct fs_node node;
+ struct mlx5_fs_dr_rule fs_dr_rule;
u32 val[MLX5_ST_SZ_DW_MATCH_PARAM];
u32 dests_size;
u32 index;
@@ -214,6 +223,7 @@ struct mlx5_flow_group_mask {
/* Type of children is fs_fte */
struct mlx5_flow_group {
struct fs_node node;
+ struct mlx5_fs_dr_matcher fs_dr_matcher;
struct mlx5_flow_group_mask mask;
u32 start_index;
u32 max_ftes;
@@ -225,6 +235,7 @@ struct mlx5_flow_group {
struct mlx5_flow_root_namespace {
struct mlx5_flow_namespace ns;
+ struct mlx5_fs_dr_domain fs_dr_domain;
enum fs_flow_table_type table_type;
struct mlx5_core_dev *dev;
struct mlx5_flow_table *root_ft;
@@ -242,6 +253,11 @@ void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
unsigned long interval);
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
+
+int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_root_namespace *peer_ns);
+
int mlx5_init_fs(struct mlx5_core_dev *dev);
void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
new file mode 100644
index 000000000000..3d587d0bdbbe
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include "mlx5_core.h"
+#include "fs_core.h"
+#include "fs_cmd.h"
+#include "mlx5dr.h"
+#include "fs_dr.h"
+
+static bool mlx5_dr_is_fw_table(u32 flags)
+{
+ if (flags & MLX5_FLOW_TABLE_TERMINATION)
+ return true;
+
+ return false;
+}
+
+static int mlx5_cmd_dr_update_root_ft(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ u32 underlay_qpn,
+ bool disconnect)
+{
+ return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn,
+ disconnect);
+}
+
+static int set_miss_action(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_table *next_ft)
+{
+ struct mlx5dr_action *old_miss_action;
+ struct mlx5dr_action *action = NULL;
+ struct mlx5dr_table *next_tbl;
+ int err;
+
+ next_tbl = next_ft ? next_ft->fs_dr_table.dr_table : NULL;
+ if (next_tbl) {
+ action = mlx5dr_action_create_dest_table(next_tbl);
+ if (!action)
+ return -EINVAL;
+ }
+ old_miss_action = ft->fs_dr_table.miss_action;
+ err = mlx5dr_table_set_miss_action(ft->fs_dr_table.dr_table, action);
+ if (err && action) {
+ err = mlx5dr_action_destroy(action);
+ if (err) {
+ action = NULL;
+ mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n",
+ err);
+ }
+ }
+ ft->fs_dr_table.miss_action = action;
+ if (old_miss_action) {
+ err = mlx5dr_action_destroy(old_miss_action);
+ if (err)
+ mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n",
+ err);
+ }
+
+ return err;
+}
+
+static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ unsigned int log_size,
+ struct mlx5_flow_table *next_ft)
+{
+ struct mlx5dr_table *tbl;
+ int err;
+
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
+ log_size,
+ next_ft);
+
+ tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
+ ft->level);
+ if (!tbl) {
+ mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
+ return -EINVAL;
+ }
+
+ ft->fs_dr_table.dr_table = tbl;
+ ft->id = mlx5dr_table_get_id(tbl);
+
+ if (next_ft) {
+ err = set_miss_action(ns, ft, next_ft);
+ if (err) {
+ mlx5dr_table_destroy(tbl);
+ ft->fs_dr_table.dr_table = NULL;
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft)
+{
+ struct mlx5dr_action *action = ft->fs_dr_table.miss_action;
+ int err;
+
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+
+ err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table);
+ if (err) {
+ mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n",
+ err);
+ return err;
+ }
+ if (action) {
+ err = mlx5dr_action_destroy(action);
+ if (err) {
+ mlx5_core_err(ns->dev, "Failed to destroy action(%d)\n",
+ err);
+ return err;
+ }
+ }
+
+ return err;
+}
+
+static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_table *next_ft)
+{
+ return set_miss_action(ns, ft, next_ft);
+}
+
+static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ u32 *in,
+ struct mlx5_flow_group *fg)
+{
+ struct mlx5dr_matcher *matcher;
+ u16 priority = MLX5_GET(create_flow_group_in, in,
+ start_flow_index);
+ u8 match_criteria_enable = MLX5_GET(create_flow_group_in,
+ in,
+ match_criteria_enable);
+ struct mlx5dr_match_parameters mask;
+
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in,
+ fg);
+
+ mask.match_buf = MLX5_ADDR_OF(create_flow_group_in,
+ in, match_criteria);
+ mask.match_sz = sizeof(fg->mask.match_criteria);
+
+ matcher = mlx5dr_matcher_create(ft->fs_dr_table.dr_table,
+ priority,
+ match_criteria_enable,
+ &mask);
+ if (!matcher) {
+ mlx5_core_err(ns->dev, "Failed creating matcher\n");
+ return -EINVAL;
+ }
+
+ fg->fs_dr_matcher.dr_matcher = matcher;
+ return 0;
+}
+
+static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_group *fg)
+{
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg);
+
+ return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher);
+}
+
+static struct mlx5dr_action *create_vport_action(struct mlx5dr_domain *domain,
+ struct mlx5_flow_rule *dst)
+{
+ struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+
+ return mlx5dr_action_create_dest_vport(domain, dest_attr->vport.num,
+ dest_attr->vport.flags &
+ MLX5_FLOW_DEST_VPORT_VHCA_ID,
+ dest_attr->vport.vhca_id);
+}
+
+static struct mlx5dr_action *create_ft_action(struct mlx5_core_dev *dev,
+ struct mlx5_flow_rule *dst)
+{
+ struct mlx5_flow_table *dest_ft = dst->dest_attr.ft;
+
+ if (mlx5_dr_is_fw_table(dest_ft->flags))
+ return mlx5dr_create_action_dest_flow_fw_table(dest_ft, dev);
+ return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table);
+}
+
+static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domain,
+ struct mlx5_fs_vlan *vlan)
+{
+ u16 n_ethtype = vlan->ethtype;
+ u8 prio = vlan->prio;
+ u16 vid = vlan->vid;
+ u32 vlan_hdr;
+
+ vlan_hdr = (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid;
+ return mlx5dr_action_create_push_vlan(domain, htonl(vlan_hdr));
+}
+
+#define MLX5_FLOW_CONTEXT_ACTION_MAX 20
+static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_group *group,
+ struct fs_fte *fte)
+{
+ struct mlx5dr_domain *domain = ns->fs_dr_domain.dr_domain;
+ struct mlx5dr_action *term_action = NULL;
+ struct mlx5dr_match_parameters params;
+ struct mlx5_core_dev *dev = ns->dev;
+ struct mlx5dr_action **fs_dr_actions;
+ struct mlx5dr_action *tmp_action;
+ struct mlx5dr_action **actions;
+ bool delay_encap_set = false;
+ struct mlx5dr_rule *rule;
+ struct mlx5_flow_rule *dst;
+ int fs_dr_num_actions = 0;
+ int num_actions = 0;
+ size_t match_sz;
+ int err = 0;
+ int i;
+
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
+
+ actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions),
+ GFP_KERNEL);
+ if (!actions)
+ return -ENOMEM;
+
+ fs_dr_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+ sizeof(*fs_dr_actions), GFP_KERNEL);
+ if (!fs_dr_actions) {
+ kfree(actions);
+ return -ENOMEM;
+ }
+
+ match_sz = sizeof(fte->val);
+
+ /* The order of the actions are must to be keep, only the following
+ * order is supported by SW steering:
+ * TX: push vlan -> modify header -> encap
+ * RX: decap -> pop vlan -> modify header
+ */
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+ tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+ tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+ enum mlx5dr_action_reformat_type decap_type =
+ DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2;
+
+ tmp_action = mlx5dr_action_create_packet_reformat(domain,
+ decap_type, 0,
+ NULL);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+ bool is_decap = fte->action.pkt_reformat->reformat_type ==
+ MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
+
+ if (is_decap)
+ actions[num_actions++] =
+ fte->action.pkt_reformat->action.dr_action;
+ else
+ delay_encap_set = true;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+ tmp_action =
+ mlx5dr_action_create_pop_vlan();
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
+ tmp_action =
+ mlx5dr_action_create_pop_vlan();
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+ actions[num_actions++] =
+ fte->action.modify_hdr->action.dr_action;
+
+ if (delay_encap_set)
+ actions[num_actions++] =
+ fte->action.pkt_reformat->action.dr_action;
+
+ /* The order of the actions below is not important */
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+ tmp_action = mlx5dr_action_create_drop();
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ term_action = tmp_action;
+ }
+
+ if (fte->flow_context.flow_tag) {
+ tmp_action =
+ mlx5dr_action_create_tag(fte->flow_context.flow_tag);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ }
+
+ if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+ list_for_each_entry(dst, &fte->node.children, node.list) {
+ enum mlx5_flow_destination_type type = dst->dest_attr.type;
+ u32 id;
+
+ if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+ err = -ENOSPC;
+ goto free_actions;
+ }
+
+ switch (type) {
+ case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
+ id = dst->dest_attr.counter_id;
+
+ tmp_action =
+ mlx5dr_action_create_flow_counter(id);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ actions[num_actions++] = tmp_action;
+ break;
+ case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+ tmp_action = create_ft_action(dev, dst);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ term_action = tmp_action;
+ break;
+ case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+ tmp_action = create_vport_action(domain, dst);
+ if (!tmp_action) {
+ err = -ENOMEM;
+ goto free_actions;
+ }
+ fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+ term_action = tmp_action;
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto free_actions;
+ }
+ }
+ }
+
+ params.match_sz = match_sz;
+ params.match_buf = (u64 *)fte->val;
+
+ if (term_action)
+ actions[num_actions++] = term_action;
+
+ rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher,
+ ¶ms,
+ num_actions,
+ actions);
+ if (!rule) {
+ err = -EINVAL;
+ goto free_actions;
+ }
+
+ kfree(actions);
+ fte->fs_dr_rule.dr_rule = rule;
+ fte->fs_dr_rule.num_actions = fs_dr_num_actions;
+ fte->fs_dr_rule.dr_actions = fs_dr_actions;
+
+ return 0;
+
+free_actions:
+ for (i = 0; i < fs_dr_num_actions; i++)
+ if (!IS_ERR_OR_NULL(fs_dr_actions[i]))
+ mlx5dr_action_destroy(fs_dr_actions[i]);
+
+ mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err);
+ kfree(actions);
+ kfree(fs_dr_actions);
+ return err;
+}
+
+static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+ int reformat_type,
+ size_t size,
+ void *reformat_data,
+ enum mlx5_flow_namespace_type namespace,
+ struct mlx5_pkt_reformat *pkt_reformat)
+{
+ struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain;
+ struct mlx5dr_action *action;
+ int dr_reformat;
+
+ switch (reformat_type) {
+ case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+ case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+ case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+ dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2;
+ break;
+ case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+ dr_reformat = DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2;
+ break;
+ case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+ dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3;
+ break;
+ default:
+ mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
+ reformat_type);
+ return -EOPNOTSUPP;
+ }
+
+ action = mlx5dr_action_create_packet_reformat(dr_domain,
+ dr_reformat,
+ size,
+ reformat_data);
+ if (!action) {
+ mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n");
+ return -EINVAL;
+ }
+
+ pkt_reformat->action.dr_action = action;
+
+ return 0;
+}
+
+static void mlx5_cmd_dr_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_pkt_reformat *pkt_reformat)
+{
+ mlx5dr_action_destroy(pkt_reformat->action.dr_action);
+}
+
+static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+ u8 namespace, u8 num_actions,
+ void *modify_actions,
+ struct mlx5_modify_hdr *modify_hdr)
+{
+ struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain;
+ struct mlx5dr_action *action;
+ size_t actions_sz;
+
+ actions_sz = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) *
+ num_actions;
+ action = mlx5dr_action_create_modify_header(dr_domain, 0,
+ actions_sz,
+ modify_actions);
+ if (!action) {
+ mlx5_core_err(ns->dev, "Failed allocating modify-header action\n");
+ return -EINVAL;
+ }
+
+ modify_hdr->action.dr_action = action;
+
+ return 0;
+}
+
+static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_modify_hdr *modify_hdr)
+{
+ mlx5dr_action_destroy(modify_hdr->action.dr_action);
+}
+
+static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct mlx5_flow_group *group,
+ int modify_mask,
+ struct fs_fte *fte)
+{
+ return -EOPNOTSUPP;
+}
+
+static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_table *ft,
+ struct fs_fte *fte)
+{
+ struct mlx5_fs_dr_rule *rule = &fte->fs_dr_rule;
+ int err;
+ int i;
+
+ if (mlx5_dr_is_fw_table(ft->flags))
+ return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte);
+
+ err = mlx5dr_rule_destroy(rule->dr_rule);
+ if (err)
+ return err;
+
+ for (i = 0; i < rule->num_actions; i++)
+ if (!IS_ERR_OR_NULL(rule->dr_actions[i]))
+ mlx5dr_action_destroy(rule->dr_actions[i]);
+
+ kfree(rule->dr_actions);
+ return 0;
+}
+
+static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns,
+ struct mlx5_flow_root_namespace *peer_ns)
+{
+ struct mlx5dr_domain *peer_domain = NULL;
+
+ if (peer_ns)
+ peer_domain = peer_ns->fs_dr_domain.dr_domain;
+ mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain,
+ peer_domain);
+ return 0;
+}
+
+static int mlx5_cmd_dr_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+ ns->fs_dr_domain.dr_domain =
+ mlx5dr_domain_create(ns->dev,
+ MLX5DR_DOMAIN_TYPE_FDB);
+ if (!ns->fs_dr_domain.dr_domain) {
+ mlx5_core_err(ns->dev, "Failed to create dr flow namespace\n");
+ return -EOPNOTSUPP;
+ }
+ return 0;
+}
+
+static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+ return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain);
+}
+
+bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
+{
+ return mlx5dr_is_supported(dev);
+}
+
+static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = {
+ .create_flow_table = mlx5_cmd_dr_create_flow_table,
+ .destroy_flow_table = mlx5_cmd_dr_destroy_flow_table,
+ .modify_flow_table = mlx5_cmd_dr_modify_flow_table,
+ .create_flow_group = mlx5_cmd_dr_create_flow_group,
+ .destroy_flow_group = mlx5_cmd_dr_destroy_flow_group,
+ .create_fte = mlx5_cmd_dr_create_fte,
+ .update_fte = mlx5_cmd_dr_update_fte,
+ .delete_fte = mlx5_cmd_dr_delete_fte,
+ .update_root_ft = mlx5_cmd_dr_update_root_ft,
+ .packet_reformat_alloc = mlx5_cmd_dr_packet_reformat_alloc,
+ .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc,
+ .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc,
+ .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc,
+ .set_peer = mlx5_cmd_dr_set_peer,
+ .create_ns = mlx5_cmd_dr_create_ns,
+ .destroy_ns = mlx5_cmd_dr_destroy_ns,
+};
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
+{
+ return &mlx5_flow_cmds_dr;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h
new file mode 100644
index 000000000000..1fb185d6ac7f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2019 Mellanox Technologies
+ */
+
+#ifndef _MLX5_FS_DR_
+#define _MLX5_FS_DR_
+
+#include "mlx5dr.h"
+
+struct mlx5_flow_root_namespace;
+struct fs_fte;
+
+struct mlx5_fs_dr_action {
+ struct mlx5dr_action *dr_action;
+};
+
+struct mlx5_fs_dr_ns {
+ struct mlx5_dr_ns *dr_ns;
+};
+
+struct mlx5_fs_dr_rule {
+ struct mlx5dr_rule *dr_rule;
+ /* Only actions created by fs_dr */
+ struct mlx5dr_action **dr_actions;
+ int num_actions;
+};
+
+struct mlx5_fs_dr_domain {
+ struct mlx5dr_domain *dr_domain;
+};
+
+struct mlx5_fs_dr_matcher {
+ struct mlx5dr_matcher *dr_matcher;
+};
+
+struct mlx5_fs_dr_table {
+ struct mlx5dr_table *dr_table;
+ struct mlx5dr_action *miss_action;
+};
+
+#ifdef CONFIG_MLX5_SW_STEERING
+
+bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev);
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void);
+
+#else
+
+static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
+{
+ return NULL;
+}
+
+static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
+{
+ return false;
+}
+
+#endif /* CONFIG_MLX5_SW_STEERING */
+#endif
--
2.21.0
^ permalink raw reply related
* [net-next 16/18] net/mlx5: Add API to set the namespace steering mode
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Maor Gottlieb,
Mark Bloch, Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Maor Gottlieb <maorg@mellanox.com>
Add API to set the flow steering root namesapce mode.
Setting new mode should be called before any steering operation
is executed on the namespace.
This API is going to be used by steering users such switchdev.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/fs_core.c | 49 +++++++++++++++++++
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 12 ++++-
2 files changed, 60 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index c2d6e9f4cb90..3bbb49354829 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2995,5 +2995,54 @@ EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
struct mlx5_flow_root_namespace *peer_ns)
{
+ if (peer_ns && ns->mode != peer_ns->mode) {
+ mlx5_core_err(ns->dev,
+ "Can't peer namespace of different steering mode\n");
+ return -EINVAL;
+ }
+
return ns->cmds->set_peer(ns, peer_ns);
}
+
+/* This function should be called only at init stage of the namespace.
+ * It is not safe to call this function while steering operations
+ * are executed in the namespace.
+ */
+int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
+ enum mlx5_flow_steering_mode mode)
+{
+ struct mlx5_flow_root_namespace *root;
+ const struct mlx5_flow_cmds *cmds;
+ int err;
+
+ root = find_root(&ns->node);
+ if (&root->ns != ns)
+ /* Can't set cmds to non root namespace */
+ return -EINVAL;
+
+ if (root->table_type != FS_FT_FDB)
+ return -EOPNOTSUPP;
+
+ if (root->mode == mode)
+ return 0;
+
+ if (mode == MLX5_FLOW_STEERING_MODE_SMFS)
+ cmds = mlx5_fs_cmd_get_dr_cmds();
+ else
+ cmds = mlx5_fs_cmd_get_fw_cmds();
+ if (!cmds)
+ return -EOPNOTSUPP;
+
+ err = cmds->create_ns(root);
+ if (err) {
+ mlx5_core_err(root->dev, "Failed to create flow namespace (%d)\n",
+ err);
+ return err;
+ }
+
+ root->cmds->destroy_ns(root);
+ root->cmds = cmds;
+ root->mode = mode;
+
+ return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index a133ec5487ae..00717eba2256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -98,9 +98,15 @@ enum fs_fte_status {
FS_FTE_STATUS_EXISTING = 1UL << 0,
};
+enum mlx5_flow_steering_mode {
+ MLX5_FLOW_STEERING_MODE_DMFS,
+ MLX5_FLOW_STEERING_MODE_SMFS
+};
+
struct mlx5_flow_steering {
struct mlx5_core_dev *dev;
- struct kmem_cache *fgs_cache;
+ enum mlx5_flow_steering_mode mode;
+ struct kmem_cache *fgs_cache;
struct kmem_cache *ftes_cache;
struct mlx5_flow_root_namespace *root_ns;
struct mlx5_flow_root_namespace *fdb_root_ns;
@@ -235,6 +241,7 @@ struct mlx5_flow_group {
struct mlx5_flow_root_namespace {
struct mlx5_flow_namespace ns;
+ enum mlx5_flow_steering_mode mode;
struct mlx5_fs_dr_domain fs_dr_domain;
enum fs_flow_table_type table_type;
struct mlx5_core_dev *dev;
@@ -258,6 +265,9 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
struct mlx5_flow_root_namespace *peer_ns);
+int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
+ enum mlx5_flow_steering_mode mode);
+
int mlx5_init_fs(struct mlx5_core_dev *dev);
void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
--
2.21.0
^ permalink raw reply related
* [net-next 12/18] net/mlx5: DR, Add required FW steering functionality
From: Saeed Mahameed @ 2019-09-02 7:23 UTC (permalink / raw)
To: David S. Miller
Cc: netdev@vger.kernel.org, Alex Vesker, Erez Shitrit, Mark Bloch,
Saeed Mahameed
In-Reply-To: <20190902072213.7683-1-saeedm@mellanox.com>
From: Alex Vesker <valex@mellanox.com>
SW steering is capable of doing many steering functionalities
but there are still some functionalities which are not exposed
to upper layers and therefore performed by the FW.
This is the support for recalculating checksum using a hairpin QP.
The recalculation is required after a modify TTL action which skips
the needed CS calculation in HW.
Signed-off-by: Alex Vesker <valex@mellanox.com>
Reviewed-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/steering/dr_fw.c | 93 +++++++++++++++++++
1 file changed, 93 insertions(+)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
new file mode 100644
index 000000000000..60ef6e6171e3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/types.h>
+#include "dr_types.h"
+
+struct mlx5dr_fw_recalc_cs_ft *
+mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num)
+{
+ struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
+ u32 table_id, group_id, modify_hdr_id;
+ u64 rx_icm_addr, modify_ttl_action;
+ int ret;
+
+ recalc_cs_ft = kzalloc(sizeof(*recalc_cs_ft), GFP_KERNEL);
+ if (!recalc_cs_ft)
+ return NULL;
+
+ ret = mlx5dr_cmd_create_flow_table(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB,
+ 0, 0, dmn->info.caps.max_ft_level - 1,
+ false, true, &rx_icm_addr, &table_id);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed creating TTL W/A FW flow table %d\n", ret);
+ goto free_ttl_tbl;
+ }
+
+ ret = mlx5dr_cmd_create_empty_flow_group(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ table_id, &group_id);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed creating TTL W/A FW flow group %d\n", ret);
+ goto destroy_flow_table;
+ }
+
+ /* Modify TTL action by adding zero to trigger CS recalculation */
+ modify_ttl_action = 0;
+ MLX5_SET(set_action_in, &modify_ttl_action, action_type, MLX5_ACTION_TYPE_ADD);
+ MLX5_SET(set_action_in, &modify_ttl_action, field, MLX5_ACTION_IN_FIELD_OUT_IP_TTL);
+
+ ret = mlx5dr_cmd_alloc_modify_header(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, 1,
+ &modify_ttl_action,
+ &modify_hdr_id);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed modify header TTL %d\n", ret);
+ goto destroy_flow_group;
+ }
+
+ ret = mlx5dr_cmd_set_fte_modify_and_vport(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ table_id, group_id, modify_hdr_id,
+ vport_num);
+ if (ret) {
+ mlx5dr_err(dmn, "Failed setting TTL W/A flow table entry %d\n", ret);
+ goto dealloc_modify_header;
+ }
+
+ recalc_cs_ft->modify_hdr_id = modify_hdr_id;
+ recalc_cs_ft->rx_icm_addr = rx_icm_addr;
+ recalc_cs_ft->table_id = table_id;
+ recalc_cs_ft->group_id = group_id;
+
+ return recalc_cs_ft;
+
+dealloc_modify_header:
+ mlx5dr_cmd_dealloc_modify_header(dmn->mdev, modify_hdr_id);
+destroy_flow_group:
+ mlx5dr_cmd_destroy_flow_group(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ table_id, group_id);
+destroy_flow_table:
+ mlx5dr_cmd_destroy_flow_table(dmn->mdev, table_id, MLX5_FLOW_TABLE_TYPE_FDB);
+free_ttl_tbl:
+ kfree(recalc_cs_ft);
+ return NULL;
+}
+
+void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn,
+ struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft)
+{
+ mlx5dr_cmd_del_flow_table_entry(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ recalc_cs_ft->table_id);
+ mlx5dr_cmd_dealloc_modify_header(dmn->mdev, recalc_cs_ft->modify_hdr_id);
+ mlx5dr_cmd_destroy_flow_group(dmn->mdev,
+ MLX5_FLOW_TABLE_TYPE_FDB,
+ recalc_cs_ft->table_id,
+ recalc_cs_ft->group_id);
+ mlx5dr_cmd_destroy_flow_table(dmn->mdev,
+ recalc_cs_ft->table_id,
+ MLX5_FLOW_TABLE_TYPE_FDB);
+
+ kfree(recalc_cs_ft);
+}
--
2.21.0
^ permalink raw reply related
* Re: [RFC PATCH v2 net-next 10/15] net: dsa: Pass ndo_setup_tc slave callback to drivers
From: Kurt Kanzenbach @ 2019-09-02 7:52 UTC (permalink / raw)
To: Vladimir Oltean
Cc: f.fainelli, vivien.didelot, andrew, davem, vinicius.gomes,
vedang.patel, richardcochran, weifeng.voon, jiri, m-karicheri2,
Jose.Abreu, ilias.apalodimas, jhs, xiyou.wangcong, netdev
In-Reply-To: <20190830004635.24863-11-olteanv@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3694 bytes --]
Hi,
On Fri, Aug 30, 2019 at 03:46:30AM +0300, Vladimir Oltean wrote:
> DSA currently handles shared block filters (for the classifier-action
> qdisc) in the core due to what I believe are simply pragmatic reasons -
> hiding the complexity from drivers and offerring a simple API for port
> mirroring.
>
> Extend the dsa_slave_setup_tc function by passing all other qdisc
> offloads to the driver layer, where the driver may choose what it
> implements and how. DSA is simply a pass-through in this case.
I'm having the same problem on how to pass the taprio schedule down to
the DSA driver. I didn't perform a pass-through to keep it in sync with
the already implemented offload. See my approach below.
>
> There is an open question related to the drivers potentially needing to
> do work in process context, but .ndo_setup_tc is called in atomic
> context. At the moment the drivers are left to handle this on their own.
> The risk is that once accepting the offload callback right away in the
> DSA core, then the driver would have no way to signal an error back. So
> right now the driver has to do as much error checking as possible in the
> atomic context and only defer (probably) the actual configuring of the
> offload.
>
> Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
> ---
> include/net/dsa.h | 3 +++
> net/dsa/slave.c | 12 ++++++++----
> 2 files changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/include/net/dsa.h b/include/net/dsa.h
> index 96acb14ec1a8..232b5d36815d 100644
> --- a/include/net/dsa.h
> +++ b/include/net/dsa.h
> @@ -154,6 +154,7 @@ struct dsa_mall_tc_entry {
> };
> };
>
> +struct tc_taprio_qopt_offload;
Is this needed? The rest looks good to me.
My approach:
diff --git a/include/net/dsa.h b/include/net/dsa.h
index ba6dfff98196..a60bd55f27f2 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -20,6 +20,7 @@
#include <linux/platform_data/dsa.h>
#include <net/devlink.h>
#include <net/switchdev.h>
+#include <net/pkt_sched.h>
struct tc_action;
struct phy_device;
@@ -539,6 +540,13 @@ struct dsa_switch_ops {
*/
netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port,
struct sk_buff *skb);
+
+ /*
+ * Scheduled traffic functionality
+ */
+ int (*port_set_schedule)(struct dsa_switch *ds, int port,
+ const struct tc_taprio_qopt_offload *taprio);
+ int (*port_del_schedule)(struct dsa_switch *ds, int port);
};
struct dsa_switch_driver {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 8157be7e162d..6290d55e6011 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -15,6 +15,7 @@
#include <linux/mdio.h>
#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
#include <net/tc_act/tc_mirred.h>
#include <linux/if_bridge.h>
#include <linux/netpoll.h>
@@ -953,12 +954,33 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
}
}
+static int dsa_slave_setup_tc_taprio(struct net_device *dev,
+ const struct tc_taprio_qopt_offload *taprio)
+{
+ struct dsa_port *dp = dsa_slave_to_port(dev);
+ struct dsa_switch *ds = dp->ds;
+
+ if (taprio->enable) {
+ if (!ds->ops->port_set_schedule)
+ return -EOPNOTSUPP;
+
+ return ds->ops->port_set_schedule(ds, dp->index, taprio);
+ }
+
+ if (!ds->ops->port_del_schedule)
+ return -EOPNOTSUPP;
+
+ return ds->ops->port_del_schedule(ds, dp->index);
+}
+
static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
switch (type) {
case TC_SETUP_BLOCK:
return dsa_slave_setup_tc_block(dev, type_data);
+ case TC_SETUP_QDISC_TAPRIO:
+ return dsa_slave_setup_tc_taprio(dev, type_data);
default:
return -EOPNOTSUPP;
}
Thanks,
Kurt
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply related
* Re: [PATCH] iwlwifi: mvm: Move static keyword to the front of declarations
From: Luca Coelho @ 2019-09-02 7:52 UTC (permalink / raw)
To: Krzysztof Wilczynski, Kalle Valo
Cc: Johannes Berg, Emmanuel Grumbach, Intel Linux Wireless,
David S. Miller, Sara Sharon, Shaul Triebitz, Liad Kaufman,
linux-wireless, netdev, linux-kernel
In-Reply-To: <20190831220108.10602-1-kw@linux.com>
On Sun, 2019-09-01 at 00:01 +0200, Krzysztof Wilczynski wrote:
> Move the static keyword to the front of declarations of
> he_if_types_ext_capa_sta and he_iftypes_ext_capa, and
> resolve the following compiler warnings that can be seen
> when building with warnings enabled (W=1):
>
> drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c:427:1: warning:
> ‘static’ is not at beginning of declaration [-Wold-style-declaration]
>
> drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c:434:1: warning:
> ‘static’ is not at beginning of declaration [-Wold-style-declaration]
>
> Signed-off-by: Krzysztof Wilczynski <kw@linux.com>
> ---
> Related: https://lore.kernel.org/r/20190827233017.GK9987@google.com
>
> drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
> index d6499763f0dd..937a843fed56 100644
> --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
> +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
> @@ -424,14 +424,14 @@ int iwl_mvm_init_fw_regd(struct iwl_mvm *mvm)
> return ret;
> }
>
> -const static u8 he_if_types_ext_capa_sta[] = {
> +static const u8 he_if_types_ext_capa_sta[] = {
> [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
> [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
> [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
> [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT,
> };
>
> -const static struct wiphy_iftype_ext_capab he_iftypes_ext_capa[] = {
> +static const struct wiphy_iftype_ext_capab he_iftypes_ext_capa[] = {
> {
> .iftype = NL80211_IFTYPE_STATION,
> .extended_capabilities = he_if_types_ext_capa_sta,
Thanks for your patch! Though we already have this change in our
internal tree (submitted by YueHaibing) and it will reach the mainline
soon.
--
Cheers,
Luca.
^ permalink raw reply
* [PATCH net-next 00/13] net: stmmac: Improvements for -next
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
Couple of improvements for -next tree. More info in commit logs. Some of them
includes fixes for features that are only in -next tree.
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
Jose Abreu (13):
net: stmmac: selftests: Return proper error code to userspace
net: stmmac: xgmac: Add RBU handling in DMA interrupt
net: stmmac: Do not return error code in TC Initialization
net: stmmac: Implement L3/L4 Filters using TC Flower
net: stmmac: selftests: Add selftest for L3/L4 Filters
net: stmmac: xgmac: Implement ARP Offload
net: stmmac: selftests: Implement the ARP Offload test
net: stmmac: Only consider RX error when HW Timestamping is not
enabled
net: stmmac: ethtool: Let user configure TX coalesce without RIWT
net: stmmac: xgmac: Correct RAVSEL field interpretation
net: stmmac: Correctly assing MAX MTU in XGMAC cores case
net: stmmac: xgmac: Enable RX Jumbo frame support
net: stmmac: selftests: Add Jumbo Frame tests
drivers/net/ethernet/stmicro/stmmac/common.h | 2 +
drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 33 +-
.../net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 205 +++++++++-
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 8 +-
drivers/net/ethernet/stmicro/stmmac/hwif.h | 19 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 12 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 21 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 18 +-
.../net/ethernet/stmicro/stmmac/stmmac_selftests.c | 451 ++++++++++++++++++++-
drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 247 ++++++++++-
10 files changed, 969 insertions(+), 47 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH net-next 11/13] net: stmmac: Correctly assing MAX MTU in XGMAC cores case
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
Maximum MTU for XGMAC cores is 16k thus the check for presence of XGMAC
shall be done first in order to assign correct value.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5271c6129f0e..c3baca9f587b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4542,10 +4542,10 @@ int stmmac_dvr_probe(struct device *device,
/* MTU range: 46 - hw-specific max */
ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
- if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
- ndev->max_mtu = JUMBO_LEN;
- else if (priv->plat->has_xgmac)
+ if (priv->plat->has_xgmac)
ndev->max_mtu = XGMAC_JUMBO_LEN;
+ else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
+ ndev->max_mtu = JUMBO_LEN;
else
ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN);
/* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 08/13] net: stmmac: Only consider RX error when HW Timestamping is not enabled
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
Only consider that we have an error when HW Timestamping is not enabled
as this can give false positives due to the fact the RX Timestamping in
XGMAC and GMAC cores comes from context descriptors.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c59c232aca64..5271c6129f0e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3511,9 +3511,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
&priv->xstats, rx_q->dma_erx + entry);
if (unlikely(status == discard_frame)) {
page_pool_recycle_direct(rx_q->page_pool, buf->page);
- priv->dev->stats.rx_errors++;
buf->page = NULL;
error = 1;
+ if (!priv->hwts_rx_en)
+ priv->dev->stats.rx_errors++;
}
if (unlikely(error && (status & rx_not_ls)))
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 10/13] net: stmmac: xgmac: Correct RAVSEL field interpretation
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
RAVSEL means that only RX side is available for AVB features. As we use
both TX and RX features we need to check if RAVSEL is selected and
disable AVB if only RX side is available.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index fd60bf5e0a72..53c4a40d8386 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -369,7 +369,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13;
dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12;
dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11;
- dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10;
+ dma_cap->av &= !(hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10;
dma_cap->arpoffsel = (hw_cap & XGMAC_HWFEAT_ARPOFFSEL) >> 9;
dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8;
dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7;
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 03/13] net: stmmac: Do not return error code in TC Initialization
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
As we can still use the remaining TC callbacks, e.g. CBS. We should not
fail in the initialization only because RX Parser is not available.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 6c305b6ecad0..8dbbbf181ada 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -243,8 +243,9 @@ static int tc_init(struct stmmac_priv *priv)
struct dma_features *dma_cap = &priv->dma_cap;
unsigned int count;
+ /* Fail silently as we can still use remaining features, e.g. CBS */
if (!dma_cap->frpsel)
- return -EINVAL;
+ return 0;
switch (dma_cap->frpbs) {
case 0x0:
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 09/13] net: stmmac: ethtool: Let user configure TX coalesce without RIWT
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
When RX Watchdog is disabled its currently not possible to configure TX
coalesce settings. Let user configure it anyway.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 21 +++++++++------------
1 file changed, 9 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 1c450105e5a6..1a768837ca72 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -746,8 +746,15 @@ static int stmmac_set_coalesce(struct net_device *dev,
(ec->tx_max_coalesced_frames_high) || (ec->rate_sample_interval))
return -EOPNOTSUPP;
- if (ec->rx_coalesce_usecs == 0)
- return -EINVAL;
+ if (priv->use_riwt && (ec->rx_coalesce_usecs > 0)) {
+ rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv);
+
+ if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT))
+ return -EINVAL;
+
+ priv->rx_riwt = rx_riwt;
+ stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
+ }
if ((ec->tx_coalesce_usecs == 0) &&
(ec->tx_max_coalesced_frames == 0))
@@ -757,20 +764,10 @@ static int stmmac_set_coalesce(struct net_device *dev,
(ec->tx_max_coalesced_frames > STMMAC_TX_MAX_FRAMES))
return -EINVAL;
- rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv);
-
- if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT))
- return -EINVAL;
- else if (!priv->use_riwt)
- return -EOPNOTSUPP;
-
/* Only copy relevant parameters, ignore all others. */
priv->tx_coal_frames = ec->tx_max_coalesced_frames;
priv->tx_coal_timer = ec->tx_coalesce_usecs;
priv->rx_coal_frames = ec->rx_max_coalesced_frames;
- priv->rx_riwt = rx_riwt;
- stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
-
return 0;
}
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 13/13] net: stmmac: selftests: Add Jumbo Frame tests
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
Add a test to validate the Jumbo Frame support in stmmac in single
channel and multichannel mode.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
.../net/ethernet/stmicro/stmmac/stmmac_selftests.c | 65 +++++++++++++++++++++-
1 file changed, 62 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index f531dbe038df..ff499b91ea9f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -43,9 +43,11 @@ struct stmmac_packet_attrs {
int dont_wait;
int timeout;
int size;
+ int max_size;
int remove_sa;
u8 id;
int sarc;
+ u16 queue_mapping;
};
static u8 stmmac_test_next_id;
@@ -73,12 +75,14 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
else
size += sizeof(struct udphdr);
- skb = netdev_alloc_skb(priv->dev, size);
+ if (attr->max_size && (attr->max_size > size))
+ size = attr->max_size;
+
+ skb = netdev_alloc_skb_ip_align(priv->dev, size);
if (!skb)
return NULL;
prefetchw(skb->data);
- skb_reserve(skb, NET_IP_ALIGN);
if (attr->vlan > 1)
ehdr = skb_push(skb, ETH_HLEN + 8);
@@ -147,6 +151,9 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
uhdr->source = htons(attr->sport);
uhdr->dest = htons(attr->dport);
uhdr->len = htons(sizeof(*shdr) + sizeof(*uhdr) + attr->size);
+ if (attr->max_size)
+ uhdr->len = htons(attr->max_size -
+ (sizeof(*ihdr) + sizeof(*ehdr)));
uhdr->check = 0;
}
@@ -162,6 +169,10 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
iplen += sizeof(*thdr);
else
iplen += sizeof(*uhdr);
+
+ if (attr->max_size)
+ iplen = attr->max_size - sizeof(*ehdr);
+
ihdr->tot_len = htons(iplen);
ihdr->frag_off = 0;
ihdr->saddr = htonl(attr->ip_src);
@@ -178,6 +189,8 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv,
if (attr->size)
skb_put(skb, attr->size);
+ if (attr->max_size && (attr->max_size > skb->len))
+ skb_put(skb, attr->max_size - skb->len);
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
@@ -324,7 +337,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv,
goto cleanup;
}
- skb_set_queue_mapping(skb, 0);
+ skb_set_queue_mapping(skb, attr->queue_mapping);
ret = dev_queue_xmit(skb);
if (ret)
goto cleanup;
@@ -1502,6 +1515,44 @@ static int stmmac_test_arpoffload(struct stmmac_priv *priv)
return ret;
}
+static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue)
+{
+ struct stmmac_packet_attrs attr = { };
+ int size = priv->dma_buf_sz;
+
+ /* Only XGMAC has SW support for multiple RX descs in same packet */
+ if (priv->plat->has_xgmac)
+ size = priv->dev->max_mtu;
+
+ attr.dst = priv->dev->dev_addr;
+ attr.max_size = size - ETH_FCS_LEN;
+ attr.queue_mapping = queue;
+
+ return __stmmac_test_loopback(priv, &attr);
+}
+
+static int stmmac_test_jumbo(struct stmmac_priv *priv)
+{
+ return __stmmac_test_jumbo(priv, 0);
+}
+
+static int stmmac_test_mjumbo(struct stmmac_priv *priv)
+{
+ u32 chan, tx_cnt = priv->plat->tx_queues_to_use;
+ int ret;
+
+ if (tx_cnt <= 1)
+ return -EOPNOTSUPP;
+
+ for (chan = 0; chan < tx_cnt; chan++) {
+ ret = __stmmac_test_jumbo(priv, chan);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
#define STMMAC_LOOPBACK_NONE 0
#define STMMAC_LOOPBACK_MAC 1
#define STMMAC_LOOPBACK_PHY 2
@@ -1615,6 +1666,14 @@ static const struct stmmac_test {
.name = "ARP Offload ",
.lb = STMMAC_LOOPBACK_PHY,
.fn = stmmac_test_arpoffload,
+ }, {
+ .name = "Jumbo Frame ",
+ .lb = STMMAC_LOOPBACK_PHY,
+ .fn = stmmac_test_jumbo,
+ }, {
+ .name = "Multichannel Jumbo ",
+ .lb = STMMAC_LOOPBACK_PHY,
+ .fn = stmmac_test_mjumbo,
},
};
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 01/13] net: stmmac: selftests: Return proper error code to userspace
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
We can do better than just return 1 to userspace. Lets return a proper
Linux error code.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
.../net/ethernet/stmicro/stmmac/stmmac_selftests.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index ecc8602c6799..d3234338a0ca 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -318,7 +318,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv,
attr->timeout = STMMAC_LB_TIMEOUT;
wait_for_completion_timeout(&tpriv->comp, attr->timeout);
- ret = !tpriv->ok;
+ ret = tpriv->ok ? 0 : -ETIMEDOUT;
cleanup:
if (!attr->dont_wait)
@@ -480,7 +480,7 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv)
/* Shall NOT receive packet */
ret = __stmmac_test_loopback(priv, &attr);
- ret = !ret;
+ ret = ret ? 0 : -EINVAL;
cleanup:
dev_mc_del(priv->dev, gd_addr);
@@ -512,7 +512,7 @@ static int stmmac_test_pfilt(struct stmmac_priv *priv)
/* Shall NOT receive packet */
ret = __stmmac_test_loopback(priv, &attr);
- ret = !ret;
+ ret = ret ? 0 : -EINVAL;
cleanup:
dev_uc_del(priv->dev, gd_addr);
@@ -562,7 +562,7 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv)
/* Shall NOT receive packet */
ret = __stmmac_test_loopback(priv, &attr);
- ret = !ret;
+ ret = ret ? 0 : -EINVAL;
cleanup:
dev_uc_del(priv->dev, uc_addr);
@@ -600,7 +600,7 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv)
/* Shall NOT receive packet */
ret = __stmmac_test_loopback(priv, &attr);
- ret = !ret;
+ ret = ret ? 0 : -EINVAL;
cleanup:
dev_mc_del(priv->dev, mc_addr);
@@ -699,7 +699,7 @@ static int stmmac_test_flowctrl(struct stmmac_priv *priv)
}
wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT);
- ret = !tpriv->ok;
+ ret = tpriv->ok ? 0 : -ETIMEDOUT;
cleanup:
dev_mc_del(priv->dev, paddr);
@@ -833,11 +833,11 @@ static int stmmac_test_vlanfilt(struct stmmac_priv *priv)
goto vlan_del;
wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT);
- ret = !tpriv->ok;
+ ret = tpriv->ok ? 0 : -ETIMEDOUT;
if (ret && !i) {
goto vlan_del;
} else if (!ret && i) {
- ret = -1;
+ ret = -EINVAL;
goto vlan_del;
} else {
ret = 0;
@@ -909,11 +909,11 @@ static int stmmac_test_dvlanfilt(struct stmmac_priv *priv)
goto vlan_del;
wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT);
- ret = !tpriv->ok;
+ ret = tpriv->ok ? 0 : -ETIMEDOUT;
if (ret && !i) {
goto vlan_del;
} else if (!ret && i) {
- ret = -1;
+ ret = -EINVAL;
goto vlan_del;
} else {
ret = 0;
@@ -998,7 +998,7 @@ static int stmmac_test_rxp(struct stmmac_priv *priv)
attr.src = addr;
ret = __stmmac_test_loopback(priv, &attr);
- ret = !ret; /* Shall NOT receive packet */
+ ret = ret ? 0 : -EINVAL; /* Shall NOT receive packet */
cls_u32.command = TC_CLSU32_DELETE_KNODE;
stmmac_tc_setup_cls_u32(priv, priv, &cls_u32);
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 02/13] net: stmmac: xgmac: Add RBU handling in DMA interrupt
From: Jose Abreu @ 2019-09-02 8:01 UTC (permalink / raw)
To: netdev
Cc: Joao Pinto, Jose Abreu, Giuseppe Cavallaro, Alexandre Torgue,
David S. Miller, Maxime Coquelin, linux-stm32, linux-arm-kernel,
linux-kernel
In-Reply-To: <cover.1567410970.git.joabreu@synopsys.com>
Add the handling of Receive Buffer Unavailable interrupt in the DMA
handler of XGMAC cores.
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
---
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Jose Abreu <joabreu@synopsys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: netdev@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 64956465c030..e77eb0ddf9b5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -322,6 +322,10 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
/* ABNORMAL interrupts */
if (unlikely(intr_status & XGMAC_AIS)) {
+ if (unlikely(intr_status & XGMAC_RBU)) {
+ x->rx_buf_unav_irq++;
+ ret |= handle_rx;
+ }
if (unlikely(intr_status & XGMAC_TPS)) {
x->tx_process_stopped_irq++;
ret |= tx_hard_error;
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox