* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
-/* System headers. */
+/**
+ * @file
+ * mlx4 driver initialization.
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
#include <stddef.h>
+#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
-#include <stdint.h>
-#include <inttypes.h>
#include <string.h>
-#include <errno.h>
-#include <unistd.h>
-#include <assert.h>
-#include <rte_ether.h>
-#include <rte_ethdev.h>
-#include <rte_ethdev_pci.h>
+/* Verbs headers do not support -pedantic. */
+#ifdef PEDANTIC
+#pragma GCC diagnostic ignored "-Wpedantic"
+#endif
+#include <infiniband/verbs.h>
+#ifdef PEDANTIC
+#pragma GCC diagnostic error "-Wpedantic"
+#endif
+
+#include <rte_common.h>
#include <rte_dev.h>
-#include <rte_mbuf.h>
#include <rte_errno.h>
-#include <rte_mempool.h>
-#include <rte_malloc.h>
-#include <rte_memory.h>
-#include <rte_flow.h>
-#include <rte_kvargs.h>
+#include <rte_ethdev.h>
+#include <rte_ethdev_pci.h>
+#include <rte_ether.h>
#include <rte_interrupts.h>
-#include <rte_common.h>
-
-/* Generated configuration header. */
-#include "mlx4_autoconf.h"
+#include <rte_kvargs.h>
+#include <rte_malloc.h>
+#include <rte_mbuf.h>
-/* PMD headers. */
#include "mlx4.h"
#include "mlx4_flow.h"
#include "mlx4_rxtx.h"
NULL,
};
-/* Device configuration. */
-
-static int
-txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc,
- unsigned int socket, const struct rte_eth_txconf *conf);
-
-static void
-txq_cleanup(struct txq *txq);
-
-static int
-rxq_setup(struct rte_eth_dev *dev, struct rxq *rxq, uint16_t desc,
- unsigned int socket, const struct rte_eth_rxconf *conf,
- struct rte_mempool *mp);
-
-static void
-rxq_cleanup(struct rxq *rxq);
-
-static void
-priv_mac_addr_del(struct priv *priv);
-
/**
* DPDK callback for Ethernet device configuration.
*
- * Prepare the driver for a given number of TX and RX queues.
- *
* @param dev
* Pointer to Ethernet device structure.
*
mlx4_dev_configure(struct rte_eth_dev *dev)
{
struct priv *priv = dev->data->dev_private;
- unsigned int rxqs_n = dev->data->nb_rx_queues;
- unsigned int txqs_n = dev->data->nb_tx_queues;
-
- priv->rxqs = (void *)dev->data->rx_queues;
- priv->txqs = (void *)dev->data->tx_queues;
- if (txqs_n != priv->txqs_n) {
- INFO("%p: TX queues number update: %u -> %u",
- (void *)dev, priv->txqs_n, txqs_n);
- priv->txqs_n = txqs_n;
- }
- if (rxqs_n != priv->rxqs_n) {
- INFO("%p: Rx queues number update: %u -> %u",
- (void *)dev, priv->rxqs_n, rxqs_n);
- priv->rxqs_n = rxqs_n;
- }
- return 0;
-}
-
-/* TX queues handling. */
-
-/**
- * Allocate TX queue elements.
- *
- * @param txq
- * Pointer to TX queue structure.
- * @param elts_n
- * Number of elements to allocate.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-txq_alloc_elts(struct txq *txq, unsigned int elts_n)
-{
- unsigned int i;
- struct txq_elt (*elts)[elts_n] =
- rte_calloc_socket("TXQ", 1, sizeof(*elts), 0, txq->socket);
- int ret = 0;
-
- if (elts == NULL) {
- ERROR("%p: can't allocate packets array", (void *)txq);
- ret = ENOMEM;
- goto error;
- }
- for (i = 0; (i != elts_n); ++i) {
- struct txq_elt *elt = &(*elts)[i];
-
- elt->buf = NULL;
- }
- DEBUG("%p: allocated and configured %u WRs", (void *)txq, elts_n);
- txq->elts_n = elts_n;
- txq->elts = elts;
- txq->elts_head = 0;
- txq->elts_tail = 0;
- txq->elts_comp = 0;
- /*
- * Request send completion every MLX4_PMD_TX_PER_COMP_REQ packets or
- * at least 4 times per ring.
- */
- txq->elts_comp_cd_init =
- ((MLX4_PMD_TX_PER_COMP_REQ < (elts_n / 4)) ?
- MLX4_PMD_TX_PER_COMP_REQ : (elts_n / 4));
- txq->elts_comp_cd = txq->elts_comp_cd_init;
- assert(ret == 0);
- return 0;
-error:
- rte_free(elts);
- DEBUG("%p: failed, freed everything", (void *)txq);
- assert(ret > 0);
- rte_errno = ret;
- return -rte_errno;
-}
-
-/**
- * Free TX queue elements.
- *
- * @param txq
- * Pointer to TX queue structure.
- */
-static void
-txq_free_elts(struct txq *txq)
-{
- unsigned int elts_n = txq->elts_n;
- unsigned int elts_head = txq->elts_head;
- unsigned int elts_tail = txq->elts_tail;
- struct txq_elt (*elts)[elts_n] = txq->elts;
-
- DEBUG("%p: freeing WRs", (void *)txq);
- txq->elts_n = 0;
- txq->elts_head = 0;
- txq->elts_tail = 0;
- txq->elts_comp = 0;
- txq->elts_comp_cd = 0;
- txq->elts_comp_cd_init = 0;
- txq->elts = NULL;
- if (elts == NULL)
- return;
- while (elts_tail != elts_head) {
- struct txq_elt *elt = &(*elts)[elts_tail];
-
- assert(elt->buf != NULL);
- rte_pktmbuf_free(elt->buf);
-#ifndef NDEBUG
- /* Poisoning. */
- memset(elt, 0x77, sizeof(*elt));
-#endif
- if (++elts_tail == elts_n)
- elts_tail = 0;
- }
- rte_free(elts);
-}
-
-/**
- * Clean up a TX queue.
- *
- * Destroy objects, free allocated memory and reset the structure for reuse.
- *
- * @param txq
- * Pointer to TX queue structure.
- */
-static void
-txq_cleanup(struct txq *txq)
-{
- size_t i;
-
- DEBUG("cleaning up %p", (void *)txq);
- txq_free_elts(txq);
- if (txq->qp != NULL)
- claim_zero(ibv_destroy_qp(txq->qp));
- if (txq->cq != NULL)
- claim_zero(ibv_destroy_cq(txq->cq));
- for (i = 0; (i != RTE_DIM(txq->mp2mr)); ++i) {
- if (txq->mp2mr[i].mp == NULL)
- break;
- assert(txq->mp2mr[i].mr != NULL);
- claim_zero(ibv_dereg_mr(txq->mp2mr[i].mr));
- }
- memset(txq, 0, sizeof(*txq));
-}
-
-struct mlx4_check_mempool_data {
- int ret;
- char *start;
- char *end;
-};
-
-/* Called by mlx4_check_mempool() when iterating the memory chunks. */
-static void mlx4_check_mempool_cb(struct rte_mempool *mp,
- void *opaque, struct rte_mempool_memhdr *memhdr,
- unsigned mem_idx)
-{
- struct mlx4_check_mempool_data *data = opaque;
-
- (void)mp;
- (void)mem_idx;
- /* It already failed, skip the next chunks. */
- if (data->ret != 0)
- return;
- /* It is the first chunk. */
- if (data->start == NULL && data->end == NULL) {
- data->start = memhdr->addr;
- data->end = data->start + memhdr->len;
- return;
- }
- if (data->end == memhdr->addr) {
- data->end += memhdr->len;
- return;
- }
- if (data->start == (char *)memhdr->addr + memhdr->len) {
- data->start -= memhdr->len;
- return;
- }
- /* Error, mempool is not virtually contigous. */
- data->ret = -1;
-}
-
-/**
- * Check if a mempool can be used: it must be virtually contiguous.
- *
- * @param[in] mp
- * Pointer to memory pool.
- * @param[out] start
- * Pointer to the start address of the mempool virtual memory area
- * @param[out] end
- * Pointer to the end address of the mempool virtual memory area
- *
- * @return
- * 0 on success (mempool is virtually contiguous), -1 on error.
- */
-static int mlx4_check_mempool(struct rte_mempool *mp, uintptr_t *start,
- uintptr_t *end)
-{
- struct mlx4_check_mempool_data data;
-
- memset(&data, 0, sizeof(data));
- rte_mempool_mem_iter(mp, mlx4_check_mempool_cb, &data);
- *start = (uintptr_t)data.start;
- *end = (uintptr_t)data.end;
- return data.ret;
-}
-
-/**
- * Register mempool as a memory region.
- *
- * @param pd
- * Pointer to protection domain.
- * @param mp
- * Pointer to memory pool.
- *
- * @return
- * Memory region pointer, NULL in case of error and rte_errno is set.
- */
-struct ibv_mr *
-mlx4_mp2mr(struct ibv_pd *pd, struct rte_mempool *mp)
-{
- const struct rte_memseg *ms = rte_eal_get_physmem_layout();
- uintptr_t start;
- uintptr_t end;
- unsigned int i;
- struct ibv_mr *mr;
-
- if (mlx4_check_mempool(mp, &start, &end) != 0) {
- rte_errno = EINVAL;
- ERROR("mempool %p: not virtually contiguous",
- (void *)mp);
- return NULL;
- }
- DEBUG("mempool %p area start=%p end=%p size=%zu",
- (void *)mp, (void *)start, (void *)end,
- (size_t)(end - start));
- /* Round start and end to page boundary if found in memory segments. */
- for (i = 0; (i < RTE_MAX_MEMSEG) && (ms[i].addr != NULL); ++i) {
- uintptr_t addr = (uintptr_t)ms[i].addr;
- size_t len = ms[i].len;
- unsigned int align = ms[i].hugepage_sz;
-
- if ((start > addr) && (start < addr + len))
- start = RTE_ALIGN_FLOOR(start, align);
- if ((end > addr) && (end < addr + len))
- end = RTE_ALIGN_CEIL(end, align);
- }
- DEBUG("mempool %p using start=%p end=%p size=%zu for MR",
- (void *)mp, (void *)start, (void *)end,
- (size_t)(end - start));
- mr = ibv_reg_mr(pd,
- (void *)start,
- end - start,
- IBV_ACCESS_LOCAL_WRITE);
- if (!mr)
- rte_errno = errno ? errno : EINVAL;
- return mr;
-}
-
-struct txq_mp2mr_mbuf_check_data {
- int ret;
-};
-
-/**
- * Callback function for rte_mempool_obj_iter() to check whether a given
- * mempool object looks like a mbuf.
- *
- * @param[in] mp
- * The mempool pointer
- * @param[in] arg
- * Context data (struct txq_mp2mr_mbuf_check_data). Contains the
- * return value.
- * @param[in] obj
- * Object address.
- * @param index
- * Object index, unused.
- */
-static void
-txq_mp2mr_mbuf_check(struct rte_mempool *mp, void *arg, void *obj,
- uint32_t index __rte_unused)
-{
- struct txq_mp2mr_mbuf_check_data *data = arg;
- struct rte_mbuf *buf = obj;
-
- /*
- * Check whether mbuf structure fits element size and whether mempool
- * pointer is valid.
- */
- if (sizeof(*buf) > mp->elt_size || buf->pool != mp)
- data->ret = -1;
-}
-
-/**
- * Iterator function for rte_mempool_walk() to register existing mempools and
- * fill the MP to MR cache of a TX queue.
- *
- * @param[in] mp
- * Memory Pool to register.
- * @param *arg
- * Pointer to TX queue structure.
- */
-static void
-txq_mp2mr_iter(struct rte_mempool *mp, void *arg)
-{
- struct txq *txq = arg;
- struct txq_mp2mr_mbuf_check_data data = {
- .ret = 0,
- };
-
- /* Register mempool only if the first element looks like a mbuf. */
- if (rte_mempool_obj_iter(mp, txq_mp2mr_mbuf_check, &data) == 0 ||
- data.ret == -1)
- return;
- mlx4_txq_mp2mr(txq, mp);
-}
-
-/**
- * Configure a TX queue.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param txq
- * Pointer to TX queue structure.
- * @param desc
- * Number of descriptors to configure in queue.
- * @param socket
- * NUMA socket on which memory must be allocated.
- * @param[in] conf
- * Thresholds parameters.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-txq_setup(struct rte_eth_dev *dev, struct txq *txq, uint16_t desc,
- unsigned int socket, const struct rte_eth_txconf *conf)
-{
- struct priv *priv = dev->data->dev_private;
- struct txq tmpl = {
- .priv = priv,
- .socket = socket
- };
- union {
- struct ibv_qp_init_attr init;
- struct ibv_qp_attr mod;
- } attr;
- int ret;
-
- (void)conf; /* Thresholds configuration (ignored). */
- if (priv == NULL) {
- rte_errno = EINVAL;
- goto error;
- }
- if (desc == 0) {
- rte_errno = EINVAL;
- ERROR("%p: invalid number of Tx descriptors", (void *)dev);
- goto error;
- }
- /* MRs will be registered in mp2mr[] later. */
- tmpl.cq = ibv_create_cq(priv->ctx, desc, NULL, NULL, 0);
- if (tmpl.cq == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: CQ creation failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- DEBUG("priv->device_attr.max_qp_wr is %d",
- priv->device_attr.max_qp_wr);
- DEBUG("priv->device_attr.max_sge is %d",
- priv->device_attr.max_sge);
- attr.init = (struct ibv_qp_init_attr){
- /* CQ to be associated with the send queue. */
- .send_cq = tmpl.cq,
- /* CQ to be associated with the receive queue. */
- .recv_cq = tmpl.cq,
- .cap = {
- /* Max number of outstanding WRs. */
- .max_send_wr = ((priv->device_attr.max_qp_wr < desc) ?
- priv->device_attr.max_qp_wr :
- desc),
- /* Max number of scatter/gather elements in a WR. */
- .max_send_sge = 1,
- .max_inline_data = MLX4_PMD_MAX_INLINE,
- },
- .qp_type = IBV_QPT_RAW_PACKET,
- /*
- * Do *NOT* enable this, completions events are managed per
- * Tx burst.
- */
- .sq_sig_all = 0,
- };
- tmpl.qp = ibv_create_qp(priv->pd, &attr.init);
- if (tmpl.qp == NULL) {
- rte_errno = errno ? errno : EINVAL;
- ERROR("%p: QP creation failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- /* ibv_create_qp() updates this value. */
- tmpl.max_inline = attr.init.cap.max_inline_data;
- attr.mod = (struct ibv_qp_attr){
- /* Move the QP to this state. */
- .qp_state = IBV_QPS_INIT,
- /* Primary port number. */
- .port_num = priv->port
- };
- ret = ibv_modify_qp(tmpl.qp, &attr.mod, IBV_QP_STATE | IBV_QP_PORT);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: QP state to IBV_QPS_INIT failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- ret = txq_alloc_elts(&tmpl, desc);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: TXQ allocation failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- attr.mod = (struct ibv_qp_attr){
- .qp_state = IBV_QPS_RTR
- };
- ret = ibv_modify_qp(tmpl.qp, &attr.mod, IBV_QP_STATE);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: QP state to IBV_QPS_RTR failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- attr.mod.qp_state = IBV_QPS_RTS;
- ret = ibv_modify_qp(tmpl.qp, &attr.mod, IBV_QP_STATE);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: QP state to IBV_QPS_RTS failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- /* Clean up txq in case we're reinitializing it. */
- DEBUG("%p: cleaning-up old txq just in case", (void *)txq);
- txq_cleanup(txq);
- *txq = tmpl;
- DEBUG("%p: txq updated with %p", (void *)txq, (void *)&tmpl);
- /* Pre-register known mempools. */
- rte_mempool_walk(txq_mp2mr_iter, txq);
- return 0;
-error:
- ret = rte_errno;
- txq_cleanup(&tmpl);
- rte_errno = ret;
- assert(rte_errno > 0);
- return -rte_errno;
-}
-
-/**
- * DPDK callback to configure a TX queue.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param idx
- * TX queue index.
- * @param desc
- * Number of descriptors to configure in queue.
- * @param socket
- * NUMA socket on which memory must be allocated.
- * @param[in] conf
- * Thresholds parameters.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
- unsigned int socket, const struct rte_eth_txconf *conf)
-{
- struct priv *priv = dev->data->dev_private;
- struct txq *txq = (*priv->txqs)[idx];
- int ret;
-
- DEBUG("%p: configuring queue %u for %u descriptors",
- (void *)dev, idx, desc);
- if (idx >= priv->txqs_n) {
- rte_errno = EOVERFLOW;
- ERROR("%p: queue index out of range (%u >= %u)",
- (void *)dev, idx, priv->txqs_n);
- return -rte_errno;
- }
- if (txq != NULL) {
- DEBUG("%p: reusing already allocated queue index %u (%p)",
- (void *)dev, idx, (void *)txq);
- if (priv->started) {
- rte_errno = EEXIST;
- return -rte_errno;
- }
- (*priv->txqs)[idx] = NULL;
- txq_cleanup(txq);
- } else {
- txq = rte_calloc_socket("TXQ", 1, sizeof(*txq), 0, socket);
- if (txq == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: unable to allocate queue index %u",
- (void *)dev, idx);
- return -rte_errno;
- }
- }
- ret = txq_setup(dev, txq, desc, socket, conf);
- if (ret)
- rte_free(txq);
- else {
- txq->stats.idx = idx;
- DEBUG("%p: adding TX queue %p to list",
- (void *)dev, (void *)txq);
- (*priv->txqs)[idx] = txq;
- /* Update send callback. */
- dev->tx_pkt_burst = mlx4_tx_burst;
- }
- return ret;
-}
-
-/**
- * DPDK callback to release a TX queue.
- *
- * @param dpdk_txq
- * Generic TX queue pointer.
- */
-static void
-mlx4_tx_queue_release(void *dpdk_txq)
-{
- struct txq *txq = (struct txq *)dpdk_txq;
- struct priv *priv;
- unsigned int i;
-
- if (txq == NULL)
- return;
- priv = txq->priv;
- for (i = 0; (i != priv->txqs_n); ++i)
- if ((*priv->txqs)[i] == txq) {
- DEBUG("%p: removing TX queue %p from list",
- (void *)priv->dev, (void *)txq);
- (*priv->txqs)[i] = NULL;
- break;
- }
- txq_cleanup(txq);
- rte_free(txq);
-}
-
-/* RX queues handling. */
-
-/**
- * Allocate RX queue elements.
- *
- * @param rxq
- * Pointer to RX queue structure.
- * @param elts_n
- * Number of elements to allocate.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-rxq_alloc_elts(struct rxq *rxq, unsigned int elts_n)
-{
- unsigned int i;
- struct rxq_elt (*elts)[elts_n] =
- rte_calloc_socket("RXQ elements", 1, sizeof(*elts), 0,
- rxq->socket);
-
- if (elts == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: can't allocate packets array", (void *)rxq);
- goto error;
- }
- /* For each WR (packet). */
- for (i = 0; (i != elts_n); ++i) {
- struct rxq_elt *elt = &(*elts)[i];
- struct ibv_recv_wr *wr = &elt->wr;
- struct ibv_sge *sge = &(*elts)[i].sge;
- struct rte_mbuf *buf = rte_pktmbuf_alloc(rxq->mp);
-
- if (buf == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: empty mbuf pool", (void *)rxq);
- goto error;
- }
- elt->buf = buf;
- wr->next = &(*elts)[(i + 1)].wr;
- wr->sg_list = sge;
- wr->num_sge = 1;
- /* Headroom is reserved by rte_pktmbuf_alloc(). */
- assert(buf->data_off == RTE_PKTMBUF_HEADROOM);
- /* Buffer is supposed to be empty. */
- assert(rte_pktmbuf_data_len(buf) == 0);
- assert(rte_pktmbuf_pkt_len(buf) == 0);
- /* sge->addr must be able to store a pointer. */
- assert(sizeof(sge->addr) >= sizeof(uintptr_t));
- /* SGE keeps its headroom. */
- sge->addr = (uintptr_t)
- ((uint8_t *)buf->buf_addr + RTE_PKTMBUF_HEADROOM);
- sge->length = (buf->buf_len - RTE_PKTMBUF_HEADROOM);
- sge->lkey = rxq->mr->lkey;
- /* Redundant check for tailroom. */
- assert(sge->length == rte_pktmbuf_tailroom(buf));
- }
- /* The last WR pointer must be NULL. */
- (*elts)[(i - 1)].wr.next = NULL;
- DEBUG("%p: allocated and configured %u single-segment WRs",
- (void *)rxq, elts_n);
- rxq->elts_n = elts_n;
- rxq->elts_head = 0;
- rxq->elts = elts;
- return 0;
-error:
- if (elts != NULL) {
- for (i = 0; (i != RTE_DIM(*elts)); ++i)
- rte_pktmbuf_free_seg((*elts)[i].buf);
- rte_free(elts);
- }
- DEBUG("%p: failed, freed everything", (void *)rxq);
- assert(rte_errno > 0);
- return -rte_errno;
-}
-
-/**
- * Free RX queue elements.
- *
- * @param rxq
- * Pointer to RX queue structure.
- */
-static void
-rxq_free_elts(struct rxq *rxq)
-{
- unsigned int i;
- unsigned int elts_n = rxq->elts_n;
- struct rxq_elt (*elts)[elts_n] = rxq->elts;
-
- DEBUG("%p: freeing WRs", (void *)rxq);
- rxq->elts_n = 0;
- rxq->elts = NULL;
- if (elts == NULL)
- return;
- for (i = 0; (i != RTE_DIM(*elts)); ++i)
- rte_pktmbuf_free_seg((*elts)[i].buf);
- rte_free(elts);
-}
-
-/**
- * Unregister a MAC address.
- *
- * @param priv
- * Pointer to private structure.
- */
-static void
-priv_mac_addr_del(struct priv *priv)
-{
-#ifndef NDEBUG
- uint8_t (*mac)[ETHER_ADDR_LEN] = &priv->mac.addr_bytes;
-#endif
-
- if (!priv->mac_flow)
- return;
- DEBUG("%p: removing MAC address %02x:%02x:%02x:%02x:%02x:%02x",
- (void *)priv,
- (*mac)[0], (*mac)[1], (*mac)[2], (*mac)[3], (*mac)[4], (*mac)[5]);
- claim_zero(ibv_destroy_flow(priv->mac_flow));
- priv->mac_flow = NULL;
-}
-
-/**
- * Register a MAC address.
- *
- * The MAC address is registered in queue 0.
- *
- * @param priv
- * Pointer to private structure.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-priv_mac_addr_add(struct priv *priv)
-{
- uint8_t (*mac)[ETHER_ADDR_LEN] = &priv->mac.addr_bytes;
- struct rxq *rxq;
- struct ibv_flow *flow;
-
- /* If device isn't started, this is all we need to do. */
- if (!priv->started)
- return 0;
- if (priv->isolated)
- return 0;
- if (*priv->rxqs && (*priv->rxqs)[0])
- rxq = (*priv->rxqs)[0];
- else
- return 0;
-
- /* Allocate flow specification on the stack. */
- struct __attribute__((packed)) {
- struct ibv_flow_attr attr;
- struct ibv_flow_spec_eth spec;
- } data;
- struct ibv_flow_attr *attr = &data.attr;
- struct ibv_flow_spec_eth *spec = &data.spec;
-
- if (priv->mac_flow)
- priv_mac_addr_del(priv);
- /*
- * No padding must be inserted by the compiler between attr and spec.
- * This layout is expected by libibverbs.
- */
- assert(((uint8_t *)attr + sizeof(*attr)) == (uint8_t *)spec);
- *attr = (struct ibv_flow_attr){
- .type = IBV_FLOW_ATTR_NORMAL,
- .priority = 3,
- .num_of_specs = 1,
- .port = priv->port,
- .flags = 0
- };
- *spec = (struct ibv_flow_spec_eth){
- .type = IBV_FLOW_SPEC_ETH,
- .size = sizeof(*spec),
- .val = {
- .dst_mac = {
- (*mac)[0], (*mac)[1], (*mac)[2],
- (*mac)[3], (*mac)[4], (*mac)[5]
- },
- },
- .mask = {
- .dst_mac = "\xff\xff\xff\xff\xff\xff",
- }
- };
- DEBUG("%p: adding MAC address %02x:%02x:%02x:%02x:%02x:%02x",
- (void *)priv,
- (*mac)[0], (*mac)[1], (*mac)[2], (*mac)[3], (*mac)[4], (*mac)[5]);
- /* Create related flow. */
- flow = ibv_create_flow(rxq->qp, attr);
- if (flow == NULL) {
- rte_errno = errno ? errno : EINVAL;
- ERROR("%p: flow configuration failed, errno=%d: %s",
- (void *)rxq, rte_errno, strerror(errno));
- return -rte_errno;
- }
- assert(priv->mac_flow == NULL);
- priv->mac_flow = flow;
- return 0;
-}
-
-/**
- * Clean up a RX queue.
- *
- * Destroy objects, free allocated memory and reset the structure for reuse.
- *
- * @param rxq
- * Pointer to RX queue structure.
- */
-static void
-rxq_cleanup(struct rxq *rxq)
-{
- DEBUG("cleaning up %p", (void *)rxq);
- rxq_free_elts(rxq);
- if (rxq->qp != NULL)
- claim_zero(ibv_destroy_qp(rxq->qp));
- if (rxq->cq != NULL)
- claim_zero(ibv_destroy_cq(rxq->cq));
- if (rxq->channel != NULL)
- claim_zero(ibv_destroy_comp_channel(rxq->channel));
- if (rxq->mr != NULL)
- claim_zero(ibv_dereg_mr(rxq->mr));
- memset(rxq, 0, sizeof(*rxq));
-}
-
-/**
- * Allocate a Queue Pair.
- * Optionally setup inline receive if supported.
- *
- * @param priv
- * Pointer to private structure.
- * @param cq
- * Completion queue to associate with QP.
- * @param desc
- * Number of descriptors in QP (hint only).
- *
- * @return
- * QP pointer or NULL in case of error and rte_errno is set.
- */
-static struct ibv_qp *
-rxq_setup_qp(struct priv *priv, struct ibv_cq *cq, uint16_t desc)
-{
- struct ibv_qp *qp;
- struct ibv_qp_init_attr attr = {
- /* CQ to be associated with the send queue. */
- .send_cq = cq,
- /* CQ to be associated with the receive queue. */
- .recv_cq = cq,
- .cap = {
- /* Max number of outstanding WRs. */
- .max_recv_wr = ((priv->device_attr.max_qp_wr < desc) ?
- priv->device_attr.max_qp_wr :
- desc),
- /* Max number of scatter/gather elements in a WR. */
- .max_recv_sge = 1,
- },
- .qp_type = IBV_QPT_RAW_PACKET,
- };
-
- qp = ibv_create_qp(priv->pd, &attr);
- if (!qp)
- rte_errno = errno ? errno : EINVAL;
- return qp;
-}
-
-/**
- * Configure a RX queue.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param rxq
- * Pointer to RX queue structure.
- * @param desc
- * Number of descriptors to configure in queue.
- * @param socket
- * NUMA socket on which memory must be allocated.
- * @param[in] conf
- * Thresholds parameters.
- * @param mp
- * Memory pool for buffer allocations.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-rxq_setup(struct rte_eth_dev *dev, struct rxq *rxq, uint16_t desc,
- unsigned int socket, const struct rte_eth_rxconf *conf,
- struct rte_mempool *mp)
-{
- struct priv *priv = dev->data->dev_private;
- struct rxq tmpl = {
- .priv = priv,
- .mp = mp,
- .socket = socket
- };
- struct ibv_qp_attr mod;
- struct ibv_recv_wr *bad_wr;
- unsigned int mb_len;
int ret;
- (void)conf; /* Thresholds configuration (ignored). */
- mb_len = rte_pktmbuf_data_room_size(mp);
- if (desc == 0) {
- rte_errno = EINVAL;
- ERROR("%p: invalid number of Rx descriptors", (void *)dev);
- goto error;
- }
- /* Enable scattered packets support for this queue if necessary. */
- assert(mb_len >= RTE_PKTMBUF_HEADROOM);
- if (dev->data->dev_conf.rxmode.max_rx_pkt_len <=
- (mb_len - RTE_PKTMBUF_HEADROOM)) {
- ;
- } else if (dev->data->dev_conf.rxmode.enable_scatter) {
- WARN("%p: scattered mode has been requested but is"
- " not supported, this may lead to packet loss",
- (void *)dev);
- } else {
- WARN("%p: the requested maximum Rx packet size (%u) is"
- " larger than a single mbuf (%u) and scattered"
- " mode has not been requested",
- (void *)dev,
- dev->data->dev_conf.rxmode.max_rx_pkt_len,
- mb_len - RTE_PKTMBUF_HEADROOM);
- }
- /* Use the entire RX mempool as the memory region. */
- tmpl.mr = mlx4_mp2mr(priv->pd, mp);
- if (tmpl.mr == NULL) {
- rte_errno = EINVAL;
- ERROR("%p: MR creation failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- if (dev->data->dev_conf.intr_conf.rxq) {
- tmpl.channel = ibv_create_comp_channel(priv->ctx);
- if (tmpl.channel == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: Rx interrupt completion channel creation"
- " failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- if (mlx4_fd_set_non_blocking(tmpl.channel->fd) < 0) {
- ERROR("%p: unable to make Rx interrupt completion"
- " channel non-blocking: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- }
- tmpl.cq = ibv_create_cq(priv->ctx, desc, NULL, tmpl.channel, 0);
- if (tmpl.cq == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: CQ creation failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- DEBUG("priv->device_attr.max_qp_wr is %d",
- priv->device_attr.max_qp_wr);
- DEBUG("priv->device_attr.max_sge is %d",
- priv->device_attr.max_sge);
- tmpl.qp = rxq_setup_qp(priv, tmpl.cq, desc);
- if (tmpl.qp == NULL) {
- ERROR("%p: QP creation failure: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- mod = (struct ibv_qp_attr){
- /* Move the QP to this state. */
- .qp_state = IBV_QPS_INIT,
- /* Primary port number. */
- .port_num = priv->port
- };
- ret = ibv_modify_qp(tmpl.qp, &mod, IBV_QP_STATE | IBV_QP_PORT);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: QP state to IBV_QPS_INIT failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- ret = rxq_alloc_elts(&tmpl, desc);
- if (ret) {
- ERROR("%p: RXQ allocation failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- ret = ibv_post_recv(tmpl.qp, &(*tmpl.elts)[0].wr, &bad_wr);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: ibv_post_recv() failed for WR %p: %s",
- (void *)dev,
- (void *)bad_wr,
- strerror(rte_errno));
- goto error;
- }
- mod = (struct ibv_qp_attr){
- .qp_state = IBV_QPS_RTR
- };
- ret = ibv_modify_qp(tmpl.qp, &mod, IBV_QP_STATE);
- if (ret) {
- rte_errno = ret;
- ERROR("%p: QP state to IBV_QPS_RTR failed: %s",
- (void *)dev, strerror(rte_errno));
- goto error;
- }
- /* Save port ID. */
- tmpl.port_id = dev->data->port_id;
- DEBUG("%p: RTE port ID: %u", (void *)rxq, tmpl.port_id);
- /* Clean up rxq in case we're reinitializing it. */
- DEBUG("%p: cleaning-up old rxq just in case", (void *)rxq);
- rxq_cleanup(rxq);
- *rxq = tmpl;
- DEBUG("%p: rxq updated with %p", (void *)rxq, (void *)&tmpl);
- return 0;
-error:
- ret = rte_errno;
- rxq_cleanup(&tmpl);
- rte_errno = ret;
- assert(rte_errno > 0);
- return -rte_errno;
-}
-
-/**
- * DPDK callback to configure a RX queue.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param idx
- * RX queue index.
- * @param desc
- * Number of descriptors to configure in queue.
- * @param socket
- * NUMA socket on which memory must be allocated.
- * @param[in] conf
- * Thresholds parameters.
- * @param mp
- * Memory pool for buffer allocations.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx4_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
- unsigned int socket, const struct rte_eth_rxconf *conf,
- struct rte_mempool *mp)
-{
- struct priv *priv = dev->data->dev_private;
- struct rxq *rxq = (*priv->rxqs)[idx];
- int ret;
-
- DEBUG("%p: configuring queue %u for %u descriptors",
- (void *)dev, idx, desc);
- if (idx >= priv->rxqs_n) {
- rte_errno = EOVERFLOW;
- ERROR("%p: queue index out of range (%u >= %u)",
- (void *)dev, idx, priv->rxqs_n);
- return -rte_errno;
- }
- if (rxq != NULL) {
- DEBUG("%p: reusing already allocated queue index %u (%p)",
- (void *)dev, idx, (void *)rxq);
- if (priv->started) {
- rte_errno = EEXIST;
- return -rte_errno;
- }
- (*priv->rxqs)[idx] = NULL;
- if (idx == 0)
- priv_mac_addr_del(priv);
- rxq_cleanup(rxq);
- } else {
- rxq = rte_calloc_socket("RXQ", 1, sizeof(*rxq), 0, socket);
- if (rxq == NULL) {
- rte_errno = ENOMEM;
- ERROR("%p: unable to allocate queue index %u",
- (void *)dev, idx);
- return -rte_errno;
- }
- }
- ret = rxq_setup(dev, rxq, desc, socket, conf, mp);
+ /* Prepare internal flow rules. */
+ ret = mlx4_flow_sync(priv);
if (ret)
- rte_free(rxq);
- else {
- rxq->stats.idx = idx;
- DEBUG("%p: adding RX queue %p to list",
- (void *)dev, (void *)rxq);
- (*priv->rxqs)[idx] = rxq;
- /* Update receive callback. */
- dev->rx_pkt_burst = mlx4_rx_burst;
- }
+ ERROR("cannot set up internal flow rules: %s",
+ strerror(-ret));
return ret;
}
-/**
- * DPDK callback to release a RX queue.
- *
- * @param dpdk_rxq
- * Generic RX queue pointer.
- */
-static void
-mlx4_rx_queue_release(void *dpdk_rxq)
-{
- struct rxq *rxq = (struct rxq *)dpdk_rxq;
- struct priv *priv;
- unsigned int i;
-
- if (rxq == NULL)
- return;
- priv = rxq->priv;
- for (i = 0; (i != priv->rxqs_n); ++i)
- if ((*priv->rxqs)[i] == rxq) {
- DEBUG("%p: removing RX queue %p from list",
- (void *)priv->dev, (void *)rxq);
- (*priv->rxqs)[i] = NULL;
- if (i == 0)
- priv_mac_addr_del(priv);
- break;
- }
- rxq_cleanup(rxq);
- rte_free(rxq);
-}
-
/**
* DPDK callback to start the device.
*
return 0;
DEBUG("%p: attaching configured flows to all RX queues", (void *)dev);
priv->started = 1;
- ret = priv_mac_addr_add(priv);
- if (ret)
- goto err;
ret = mlx4_intr_install(priv);
if (ret) {
ERROR("%p: interrupt handler installation failed",
(void *)dev);
goto err;
}
- ret = mlx4_priv_flow_start(priv);
+ ret = mlx4_flow_start(priv);
if (ret) {
ERROR("%p: flow start failed: %s",
(void *)dev, strerror(ret));
return 0;
err:
/* Rollback. */
- priv_mac_addr_del(priv);
priv->started = 0;
return ret;
}
return;
DEBUG("%p: detaching flows from all RX queues", (void *)dev);
priv->started = 0;
- mlx4_priv_flow_stop(priv);
+ mlx4_flow_stop(priv);
mlx4_intr_uninstall(priv);
- priv_mac_addr_del(priv);
}
/**
mlx4_dev_close(struct rte_eth_dev *dev)
{
struct priv *priv = dev->data->dev_private;
- void *tmp;
unsigned int i;
if (priv == NULL)
DEBUG("%p: closing device \"%s\"",
(void *)dev,
((priv->ctx != NULL) ? priv->ctx->device->name : ""));
- priv_mac_addr_del(priv);
- /*
- * Prevent crashes when queues are still in use. This is unfortunately
- * still required for DPDK 1.3 because some programs (such as testpmd)
- * never release them before closing the device.
- */
+ mlx4_flow_clean(priv);
dev->rx_pkt_burst = mlx4_rx_burst_removed;
dev->tx_pkt_burst = mlx4_tx_burst_removed;
- if (priv->rxqs != NULL) {
- /* XXX race condition if mlx4_rx_burst() is still running. */
- usleep(1000);
- for (i = 0; (i != priv->rxqs_n); ++i) {
- tmp = (*priv->rxqs)[i];
- if (tmp == NULL)
- continue;
- (*priv->rxqs)[i] = NULL;
- rxq_cleanup(tmp);
- rte_free(tmp);
- }
- priv->rxqs_n = 0;
- priv->rxqs = NULL;
- }
- if (priv->txqs != NULL) {
- /* XXX race condition if mlx4_tx_burst() is still running. */
- usleep(1000);
- for (i = 0; (i != priv->txqs_n); ++i) {
- tmp = (*priv->txqs)[i];
- if (tmp == NULL)
- continue;
- (*priv->txqs)[i] = NULL;
- txq_cleanup(tmp);
- rte_free(tmp);
- }
- priv->txqs_n = 0;
- priv->txqs = NULL;
- }
+ for (i = 0; i != dev->data->nb_rx_queues; ++i)
+ mlx4_rx_queue_release(dev->data->rx_queues[i]);
+ for (i = 0; i != dev->data->nb_tx_queues; ++i)
+ mlx4_tx_queue_release(dev->data->tx_queues[i]);
if (priv->pd != NULL) {
assert(priv->ctx != NULL);
claim_zero(ibv_dealloc_pd(priv->pd));
memset(priv, 0, sizeof(*priv));
}
-const struct rte_flow_ops mlx4_flow_ops = {
- .validate = mlx4_flow_validate,
- .create = mlx4_flow_create,
- .destroy = mlx4_flow_destroy,
- .flush = mlx4_flow_flush,
- .query = NULL,
- .isolate = mlx4_flow_isolate,
-};
-
-/**
- * Manage filter operations.
- *
- * @param dev
- * Pointer to Ethernet device structure.
- * @param filter_type
- * Filter type.
- * @param filter_op
- * Operation to perform.
- * @param arg
- * Pointer to operation-specific structure.
- *
- * @return
- * 0 on success, negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx4_dev_filter_ctrl(struct rte_eth_dev *dev,
- enum rte_filter_type filter_type,
- enum rte_filter_op filter_op,
- void *arg)
-{
- switch (filter_type) {
- case RTE_ETH_FILTER_GENERIC:
- if (filter_op != RTE_ETH_FILTER_GET)
- break;
- *(const void **)arg = &mlx4_flow_ops;
- return 0;
- default:
- ERROR("%p: filter type (%d) not supported",
- (void *)dev, filter_type);
- break;
- }
- rte_errno = ENOTSUP;
- return -rte_errno;
-}
-
static const struct eth_dev_ops mlx4_dev_ops = {
.dev_configure = mlx4_dev_configure,
.dev_start = mlx4_dev_start,
.flow_ctrl_get = mlx4_flow_ctrl_get,
.flow_ctrl_set = mlx4_flow_ctrl_set,
.mtu_set = mlx4_mtu_set,
- .filter_ctrl = mlx4_dev_filter_ctrl,
+ .filter_ctrl = mlx4_filter_ctrl,
.rx_queue_intr_enable = mlx4_rx_intr_enable,
.rx_queue_intr_disable = mlx4_rx_intr_disable,
};
mac.addr_bytes[4], mac.addr_bytes[5]);
/* Register MAC address. */
priv->mac = mac;
- if (priv_mac_addr_add(priv))
- goto port_error;
#ifndef NDEBUG
{
char ifname[IF_NAMESIZE];