qedr: Add support for PD,PKEY and CQ verbs
Add support for protection domain and completion queue verbs.
Signed-off-by: Rajesh Borundia <rajesh.borundia@cavium.com>
Signed-off-by: Ram Amrani <Ram.Amrani@cavium.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index b9dcade..b525c6c 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -49,6 +49,17 @@
#include "verbs.h"
#include <rdma/qedr-abi.h>
+#define DB_ADDR_SHIFT(addr) ((addr) << DB_PWM_ADDR_OFFSET_SHIFT)
+
+int qedr_query_pkey(struct ib_device *ibdev, u8 port, u16 index, u16 *pkey)
+{
+ if (index > QEDR_ROCE_PKEY_TABLE_LEN)
+ return -EINVAL;
+
+ *pkey = QEDR_ROCE_PKEY_DEFAULT;
+ return 0;
+}
+
int qedr_query_gid(struct ib_device *ibdev, u8 port, int index,
union ib_gid *sgid)
{
@@ -454,3 +465,531 @@ int qedr_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
DP_DEBUG(dev, QEDR_MSG_INIT, "qedr_mmap return code: %d\n", rc);
return rc;
}
+
+struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
+ struct ib_ucontext *context, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qedr_ucontext *uctx = NULL;
+ struct qedr_alloc_pd_uresp uresp;
+ struct qedr_pd *pd;
+ u16 pd_id;
+ int rc;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Function called from: %s\n",
+ (udata && context) ? "User Lib" : "Kernel");
+
+ if (!dev->rdma_ctx) {
+ DP_ERR(dev, "invlaid RDMA context\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+ if (!pd)
+ return ERR_PTR(-ENOMEM);
+
+ dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+
+ uresp.pd_id = pd_id;
+ pd->pd_id = pd_id;
+
+ if (udata && context) {
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id);
+ uctx = get_qedr_ucontext(context);
+ uctx->pd = pd;
+ pd->uctx = uctx;
+ }
+
+ return &pd->ibpd;
+}
+
+int qedr_dealloc_pd(struct ib_pd *ibpd)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibpd->device);
+ struct qedr_pd *pd = get_qedr_pd(ibpd);
+
+ if (!pd)
+ pr_err("Invalid PD received in dealloc_pd\n");
+
+ DP_DEBUG(dev, QEDR_MSG_INIT, "Deallocating PD %d\n", pd->pd_id);
+ dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd->pd_id);
+
+ kfree(pd);
+
+ return 0;
+}
+
+static void qedr_free_pbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info, struct qedr_pbl *pbl)
+{
+ struct pci_dev *pdev = dev->pdev;
+ int i;
+
+ for (i = 0; i < pbl_info->num_pbls; i++) {
+ if (!pbl[i].va)
+ continue;
+ dma_free_coherent(&pdev->dev, pbl_info->pbl_size,
+ pbl[i].va, pbl[i].pa);
+ }
+
+ kfree(pbl);
+}
+
+#define MIN_FW_PBL_PAGE_SIZE (4 * 1024)
+#define MAX_FW_PBL_PAGE_SIZE (64 * 1024)
+
+#define NUM_PBES_ON_PAGE(_page_size) (_page_size / sizeof(u64))
+#define MAX_PBES_ON_PAGE NUM_PBES_ON_PAGE(MAX_FW_PBL_PAGE_SIZE)
+#define MAX_PBES_TWO_LAYER (MAX_PBES_ON_PAGE * MAX_PBES_ON_PAGE)
+
+static struct qedr_pbl *qedr_alloc_pbl_tbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info,
+ gfp_t flags)
+{
+ struct pci_dev *pdev = dev->pdev;
+ struct qedr_pbl *pbl_table;
+ dma_addr_t *pbl_main_tbl;
+ dma_addr_t pa;
+ void *va;
+ int i;
+
+ pbl_table = kcalloc(pbl_info->num_pbls, sizeof(*pbl_table), flags);
+ if (!pbl_table)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < pbl_info->num_pbls; i++) {
+ va = dma_alloc_coherent(&pdev->dev, pbl_info->pbl_size,
+ &pa, flags);
+ if (!va)
+ goto err;
+
+ memset(va, 0, pbl_info->pbl_size);
+ pbl_table[i].va = va;
+ pbl_table[i].pa = pa;
+ }
+
+ /* Two-Layer PBLs, if we have more than one pbl we need to initialize
+ * the first one with physical pointers to all of the rest
+ */
+ pbl_main_tbl = (dma_addr_t *)pbl_table[0].va;
+ for (i = 0; i < pbl_info->num_pbls - 1; i++)
+ pbl_main_tbl[i] = pbl_table[i + 1].pa;
+
+ return pbl_table;
+
+err:
+ for (i--; i >= 0; i--)
+ dma_free_coherent(&pdev->dev, pbl_info->pbl_size,
+ pbl_table[i].va, pbl_table[i].pa);
+
+ qedr_free_pbl(dev, pbl_info, pbl_table);
+
+ return ERR_PTR(-ENOMEM);
+}
+
+static int qedr_prepare_pbl_tbl(struct qedr_dev *dev,
+ struct qedr_pbl_info *pbl_info,
+ u32 num_pbes, int two_layer_capable)
+{
+ u32 pbl_capacity;
+ u32 pbl_size;
+ u32 num_pbls;
+
+ if ((num_pbes > MAX_PBES_ON_PAGE) && two_layer_capable) {
+ if (num_pbes > MAX_PBES_TWO_LAYER) {
+ DP_ERR(dev, "prepare pbl table: too many pages %d\n",
+ num_pbes);
+ return -EINVAL;
+ }
+
+ /* calculate required pbl page size */
+ pbl_size = MIN_FW_PBL_PAGE_SIZE;
+ pbl_capacity = NUM_PBES_ON_PAGE(pbl_size) *
+ NUM_PBES_ON_PAGE(pbl_size);
+
+ while (pbl_capacity < num_pbes) {
+ pbl_size *= 2;
+ pbl_capacity = pbl_size / sizeof(u64);
+ pbl_capacity = pbl_capacity * pbl_capacity;
+ }
+
+ num_pbls = DIV_ROUND_UP(num_pbes, NUM_PBES_ON_PAGE(pbl_size));
+ num_pbls++; /* One for the layer0 ( points to the pbls) */
+ pbl_info->two_layered = true;
+ } else {
+ /* One layered PBL */
+ num_pbls = 1;
+ pbl_size = max_t(u32, MIN_FW_PBL_PAGE_SIZE,
+ roundup_pow_of_two((num_pbes * sizeof(u64))));
+ pbl_info->two_layered = false;
+ }
+
+ pbl_info->num_pbls = num_pbls;
+ pbl_info->pbl_size = pbl_size;
+ pbl_info->num_pbes = num_pbes;
+
+ DP_DEBUG(dev, QEDR_MSG_MR,
+ "prepare pbl table: num_pbes=%d, num_pbls=%d, pbl_size=%d\n",
+ pbl_info->num_pbes, pbl_info->num_pbls, pbl_info->pbl_size);
+
+ return 0;
+}
+
+static void qedr_populate_pbls(struct qedr_dev *dev, struct ib_umem *umem,
+ struct qedr_pbl *pbl,
+ struct qedr_pbl_info *pbl_info)
+{
+ int shift, pg_cnt, pages, pbe_cnt, total_num_pbes = 0;
+ struct qedr_pbl *pbl_tbl;
+ struct scatterlist *sg;
+ struct regpair *pbe;
+ int entry;
+ u32 addr;
+
+ if (!pbl_info->num_pbes)
+ return;
+
+ /* If we have a two layered pbl, the first pbl points to the rest
+ * of the pbls and the first entry lays on the second pbl in the table
+ */
+ if (pbl_info->two_layered)
+ pbl_tbl = &pbl[1];
+ else
+ pbl_tbl = pbl;
+
+ pbe = (struct regpair *)pbl_tbl->va;
+ if (!pbe) {
+ DP_ERR(dev, "cannot populate PBL due to a NULL PBE\n");
+ return;
+ }
+
+ pbe_cnt = 0;
+
+ shift = ilog2(umem->page_size);
+
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+ pages = sg_dma_len(sg) >> shift;
+ for (pg_cnt = 0; pg_cnt < pages; pg_cnt++) {
+ /* store the page address in pbe */
+ pbe->lo = cpu_to_le32(sg_dma_address(sg) +
+ umem->page_size * pg_cnt);
+ addr = upper_32_bits(sg_dma_address(sg) +
+ umem->page_size * pg_cnt);
+ pbe->hi = cpu_to_le32(addr);
+ pbe_cnt++;
+ total_num_pbes++;
+ pbe++;
+
+ if (total_num_pbes == pbl_info->num_pbes)
+ return;
+
+ /* If the given pbl is full storing the pbes,
+ * move to next pbl.
+ */
+ if (pbe_cnt == (pbl_info->pbl_size / sizeof(u64))) {
+ pbl_tbl++;
+ pbe = (struct regpair *)pbl_tbl->va;
+ pbe_cnt = 0;
+ }
+ }
+ }
+}
+
+static int qedr_copy_cq_uresp(struct qedr_dev *dev,
+ struct qedr_cq *cq, struct ib_udata *udata)
+{
+ struct qedr_create_cq_uresp uresp;
+ int rc;
+
+ memset(&uresp, 0, sizeof(uresp));
+
+ uresp.db_offset = DB_ADDR_SHIFT(DQ_PWM_OFFSET_UCM_RDMA_CQ_CONS_32BIT);
+ uresp.icid = cq->icid;
+
+ rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
+ if (rc)
+ DP_ERR(dev, "copy error cqid=0x%x.\n", cq->icid);
+
+ return rc;
+}
+
+static void consume_cqe(struct qedr_cq *cq)
+{
+ if (cq->latest_cqe == cq->toggle_cqe)
+ cq->pbl_toggle ^= RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK;
+
+ cq->latest_cqe = qed_chain_consume(&cq->pbl);
+}
+
+static inline int qedr_align_cq_entries(int entries)
+{
+ u64 size, aligned_size;
+
+ /* We allocate an extra entry that we don't report to the FW. */
+ size = (entries + 1) * QEDR_CQE_SIZE;
+ aligned_size = ALIGN(size, PAGE_SIZE);
+
+ return aligned_size / QEDR_CQE_SIZE;
+}
+
+static inline int qedr_init_user_queue(struct ib_ucontext *ib_ctx,
+ struct qedr_dev *dev,
+ struct qedr_userq *q,
+ u64 buf_addr, size_t buf_len,
+ int access, int dmasync)
+{
+ int page_cnt;
+ int rc;
+
+ q->buf_addr = buf_addr;
+ q->buf_len = buf_len;
+ q->umem = ib_umem_get(ib_ctx, q->buf_addr, q->buf_len, access, dmasync);
+ if (IS_ERR(q->umem)) {
+ DP_ERR(dev, "create user queue: failed ib_umem_get, got %ld\n",
+ PTR_ERR(q->umem));
+ return PTR_ERR(q->umem);
+ }
+
+ page_cnt = ib_umem_page_count(q->umem);
+ rc = qedr_prepare_pbl_tbl(dev, &q->pbl_info, page_cnt, 0);
+ if (rc)
+ goto err0;
+
+ q->pbl_tbl = qedr_alloc_pbl_tbl(dev, &q->pbl_info, GFP_KERNEL);
+ if (IS_ERR_OR_NULL(q->pbl_tbl))
+ goto err0;
+
+ qedr_populate_pbls(dev, q->umem, q->pbl_tbl, &q->pbl_info);
+
+ return 0;
+
+err0:
+ ib_umem_release(q->umem);
+
+ return rc;
+}
+
+static inline void qedr_init_cq_params(struct qedr_cq *cq,
+ struct qedr_ucontext *ctx,
+ struct qedr_dev *dev, int vector,
+ int chain_entries, int page_cnt,
+ u64 pbl_ptr,
+ struct qed_rdma_create_cq_in_params
+ *params)
+{
+ memset(params, 0, sizeof(*params));
+ params->cq_handle_hi = upper_32_bits((uintptr_t)cq);
+ params->cq_handle_lo = lower_32_bits((uintptr_t)cq);
+ params->cnq_id = vector;
+ params->cq_size = chain_entries - 1;
+ params->dpi = (ctx) ? ctx->dpi : dev->dpi;
+ params->pbl_num_pages = page_cnt;
+ params->pbl_ptr = pbl_ptr;
+ params->pbl_two_level = 0;
+}
+
+static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags)
+{
+ /* Flush data before signalling doorbell */
+ wmb();
+ cq->db.data.agg_flags = flags;
+ cq->db.data.value = cpu_to_le32(cons);
+ writeq(cq->db.raw, cq->db_addr);
+
+ /* Make sure write would stick */
+ mmiowb();
+}
+
+int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
+{
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+ unsigned long sflags;
+
+ if (cq->cq_type == QEDR_CQ_TYPE_GSI)
+ return 0;
+
+ spin_lock_irqsave(&cq->cq_lock, sflags);
+
+ cq->arm_flags = 0;
+
+ if (flags & IB_CQ_SOLICITED)
+ cq->arm_flags |= DQ_UCM_ROCE_CQ_ARM_SE_CF_CMD;
+
+ if (flags & IB_CQ_NEXT_COMP)
+ cq->arm_flags |= DQ_UCM_ROCE_CQ_ARM_CF_CMD;
+
+ doorbell_cq(cq, cq->cq_cons - 1, cq->arm_flags);
+
+ spin_unlock_irqrestore(&cq->cq_lock, sflags);
+
+ return 0;
+}
+
+struct ib_cq *qedr_create_cq(struct ib_device *ibdev,
+ const struct ib_cq_init_attr *attr,
+ struct ib_ucontext *ib_ctx, struct ib_udata *udata)
+{
+ struct qedr_ucontext *ctx = get_qedr_ucontext(ib_ctx);
+ struct qed_rdma_destroy_cq_out_params destroy_oparams;
+ struct qed_rdma_destroy_cq_in_params destroy_iparams;
+ struct qedr_dev *dev = get_qedr_dev(ibdev);
+ struct qed_rdma_create_cq_in_params params;
+ struct qedr_create_cq_ureq ureq;
+ int vector = attr->comp_vector;
+ int entries = attr->cqe;
+ struct qedr_cq *cq;
+ int chain_entries;
+ int page_cnt;
+ u64 pbl_ptr;
+ u16 icid;
+ int rc;
+
+ DP_DEBUG(dev, QEDR_MSG_INIT,
+ "create_cq: called from %s. entries=%d, vector=%d\n",
+ udata ? "User Lib" : "Kernel", entries, vector);
+
+ if (entries > QEDR_MAX_CQES) {
+ DP_ERR(dev,
+ "create cq: the number of entries %d is too high. Must be equal or below %d.\n",
+ entries, QEDR_MAX_CQES);
+ return ERR_PTR(-EINVAL);
+ }
+
+ chain_entries = qedr_align_cq_entries(entries);
+ chain_entries = min_t(int, chain_entries, QEDR_MAX_CQES);
+
+ cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+ if (!cq)
+ return ERR_PTR(-ENOMEM);
+
+ if (udata) {
+ memset(&ureq, 0, sizeof(ureq));
+ if (ib_copy_from_udata(&ureq, udata, sizeof(ureq))) {
+ DP_ERR(dev,
+ "create cq: problem copying data from user space\n");
+ goto err0;
+ }
+
+ if (!ureq.len) {
+ DP_ERR(dev,
+ "create cq: cannot create a cq with 0 entries\n");
+ goto err0;
+ }
+
+ cq->cq_type = QEDR_CQ_TYPE_USER;
+
+ rc = qedr_init_user_queue(ib_ctx, dev, &cq->q, ureq.addr,
+ ureq.len, IB_ACCESS_LOCAL_WRITE, 1);
+ if (rc)
+ goto err0;
+
+ pbl_ptr = cq->q.pbl_tbl->pa;
+ page_cnt = cq->q.pbl_info.num_pbes;
+ } else {
+ cq->cq_type = QEDR_CQ_TYPE_KERNEL;
+
+ rc = dev->ops->common->chain_alloc(dev->cdev,
+ QED_CHAIN_USE_TO_CONSUME,
+ QED_CHAIN_MODE_PBL,
+ QED_CHAIN_CNT_TYPE_U32,
+ chain_entries,
+ sizeof(union rdma_cqe),
+ &cq->pbl);
+ if (rc)
+ goto err1;
+
+ page_cnt = qed_chain_get_page_cnt(&cq->pbl);
+ pbl_ptr = qed_chain_get_pbl_phys(&cq->pbl);
+ }
+
+ qedr_init_cq_params(cq, ctx, dev, vector, chain_entries, page_cnt,
+ pbl_ptr, ¶ms);
+
+ rc = dev->ops->rdma_create_cq(dev->rdma_ctx, ¶ms, &icid);
+ if (rc)
+ goto err2;
+
+ cq->icid = icid;
+ cq->sig = QEDR_CQ_MAGIC_NUMBER;
+ spin_lock_init(&cq->cq_lock);
+
+ if (ib_ctx) {
+ rc = qedr_copy_cq_uresp(dev, cq, udata);
+ if (rc)
+ goto err3;
+ } else {
+ /* Generate doorbell address. */
+ cq->db_addr = dev->db_addr +
+ DB_ADDR_SHIFT(DQ_PWM_OFFSET_UCM_RDMA_CQ_CONS_32BIT);
+ cq->db.data.icid = cq->icid;
+ cq->db.data.params = DB_AGG_CMD_SET <<
+ RDMA_PWM_VAL32_DATA_AGG_CMD_SHIFT;
+
+ /* point to the very last element, passing it we will toggle */
+ cq->toggle_cqe = qed_chain_get_last_elem(&cq->pbl);
+ cq->pbl_toggle = RDMA_CQE_REQUESTER_TOGGLE_BIT_MASK;
+ cq->latest_cqe = NULL;
+ consume_cqe(cq);
+ cq->cq_cons = qed_chain_get_cons_idx_u32(&cq->pbl);
+ }
+
+ DP_DEBUG(dev, QEDR_MSG_CQ,
+ "create cq: icid=0x%0x, addr=%p, size(entries)=0x%0x\n",
+ cq->icid, cq, params.cq_size);
+
+ return &cq->ibcq;
+
+err3:
+ destroy_iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &destroy_iparams,
+ &destroy_oparams);
+err2:
+ if (udata)
+ qedr_free_pbl(dev, &cq->q.pbl_info, cq->q.pbl_tbl);
+ else
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+err1:
+ if (udata)
+ ib_umem_release(cq->q.umem);
+err0:
+ kfree(cq);
+ return ERR_PTR(-EINVAL);
+}
+
+int qedr_resize_cq(struct ib_cq *ibcq, int new_cnt, struct ib_udata *udata)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+
+ DP_ERR(dev, "cq %p RESIZE NOT SUPPORTED\n", cq);
+
+ return 0;
+}
+
+int qedr_destroy_cq(struct ib_cq *ibcq)
+{
+ struct qedr_dev *dev = get_qedr_dev(ibcq->device);
+ struct qed_rdma_destroy_cq_out_params oparams;
+ struct qed_rdma_destroy_cq_in_params iparams;
+ struct qedr_cq *cq = get_qedr_cq(ibcq);
+
+ DP_DEBUG(dev, QEDR_MSG_CQ, "destroy cq: cq_id %d", cq->icid);
+
+ /* GSIs CQs are handled by driver, so they don't exist in the FW */
+ if (cq->cq_type != QEDR_CQ_TYPE_GSI) {
+ iparams.icid = cq->icid;
+ dev->ops->rdma_destroy_cq(dev->rdma_ctx, &iparams, &oparams);
+ dev->ops->common->chain_free(dev->cdev, &cq->pbl);
+ }
+
+ if (ibcq->uobject && ibcq->uobject->context) {
+ qedr_free_pbl(dev, &cq->q.pbl_info, cq->q.pbl_tbl);
+ ib_umem_release(cq->q.umem);
+ }
+
+ kfree(cq);
+
+ return 0;
+}