summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-03-25 03:53:42 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2016-03-25 03:53:42 -0300
commit03dd4cb26d967f9588437b0fc9cc0e8353322bb7 (patch)
treefa581f6dc1c0596391690d1f67eceef3af8246dc /drivers/infiniband/hw
parentd4e493caf788ef44982e131ff9c786546904d934 (diff)
Linux-libre 4.5-gnu
Diffstat (limited to 'drivers/infiniband/hw')
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_cq.c4
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_mem.c102
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_provider.c146
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_provider.h15
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_qp.c82
-rw-r--r--drivers/infiniband/hw/cxgb4/cm.c16
-rw-r--r--drivers/infiniband/hw/cxgb4/cq.c3
-rw-r--r--drivers/infiniband/hw/cxgb4/device.c57
-rw-r--r--drivers/infiniband/hw/cxgb4/iw_cxgb4.h13
-rw-r--r--drivers/infiniband/hw/cxgb4/mem.c251
-rw-r--r--drivers/infiniband/hw/cxgb4/provider.c3
-rw-r--r--drivers/infiniband/hw/cxgb4/qp.c5
-rw-r--r--drivers/infiniband/hw/cxgb4/t4.h7
-rw-r--r--drivers/infiniband/hw/cxgb4/user.h2
-rw-r--r--drivers/infiniband/hw/mlx4/ah.c3
-rw-r--r--drivers/infiniband/hw/mlx4/cq.c3
-rw-r--r--drivers/infiniband/hw/mlx4/mad.c80
-rw-r--r--drivers/infiniband/hw/mlx4/main.c102
-rw-r--r--drivers/infiniband/hw/mlx4/mlx4_ib.h10
-rw-r--r--drivers/infiniband/hw/mlx4/mr.c22
-rw-r--r--drivers/infiniband/hw/mlx4/qp.c325
-rw-r--r--drivers/infiniband/hw/mlx4/srq.c3
-rw-r--r--drivers/infiniband/hw/mlx5/ah.c32
-rw-r--r--drivers/infiniband/hw/mlx5/cq.c31
-rw-r--r--drivers/infiniband/hw/mlx5/main.c912
-rw-r--r--drivers/infiniband/hw/mlx5/mlx5_ib.h160
-rw-r--r--drivers/infiniband/hw/mlx5/odp.c29
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c1026
-rw-r--r--drivers/infiniband/hw/mlx5/srq.c54
-rw-r--r--drivers/infiniband/hw/mlx5/user.h63
-rw-r--r--drivers/infiniband/hw/mthca/mthca_cq.c3
-rw-r--r--drivers/infiniband/hw/mthca/mthca_provider.c84
-rw-r--r--drivers/infiniband/hw/mthca/mthca_qp.c2
-rw-r--r--drivers/infiniband/hw/nes/nes_cm.c17
-rw-r--r--drivers/infiniband/hw/nes/nes_cm.h2
-rw-r--r--drivers/infiniband/hw/nes/nes_utils.c2
-rw-r--r--drivers/infiniband/hw/nes/nes_verbs.c216
-rw-r--r--drivers/infiniband/hw/nes/nes_verbs.h4
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma.h3
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_ah.c7
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_main.c7
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_stats.c16
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_stats.h2
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_verbs.c188
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_verbs.h3
-rw-r--r--drivers/infiniband/hw/qib/qib_fs.c12
-rw-r--r--drivers/infiniband/hw/qib/qib_mr.c51
-rw-r--r--drivers/infiniband/hw/qib/qib_verbs.c12
-rw-r--r--drivers/infiniband/hw/qib/qib_verbs.h4
-rw-r--r--drivers/infiniband/hw/usnic/usnic_debugfs.c5
-rw-r--r--drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c4
-rw-r--r--drivers/infiniband/hw/usnic/usnic_ib_verbs.c24
-rw-r--r--drivers/infiniband/hw/usnic/usnic_ib_verbs.h2
-rw-r--r--drivers/infiniband/hw/usnic/usnic_vnic.c54
54 files changed, 2700 insertions, 1585 deletions
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cq.c b/drivers/infiniband/hw/cxgb3/iwch_cq.c
index cfe404925..97fbfd2c2 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cq.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cq.c
@@ -115,10 +115,6 @@ static int iwch_poll_cq_one(struct iwch_dev *rhp, struct iwch_cq *chp,
case T3_SEND_WITH_SE_INV:
wc->opcode = IB_WC_SEND;
break;
- case T3_BIND_MW:
- wc->opcode = IB_WC_BIND_MW;
- break;
-
case T3_LOCAL_INV:
wc->opcode = IB_WC_LOCAL_INV;
break;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_mem.c b/drivers/infiniband/hw/cxgb3/iwch_mem.c
index 5c36ee280..1d04c872c 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_mem.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_mem.c
@@ -75,37 +75,6 @@ int iwch_register_mem(struct iwch_dev *rhp, struct iwch_pd *php,
return ret;
}
-int iwch_reregister_mem(struct iwch_dev *rhp, struct iwch_pd *php,
- struct iwch_mr *mhp,
- int shift,
- int npages)
-{
- u32 stag;
- int ret;
-
- /* We could support this... */
- if (npages > mhp->attr.pbl_size)
- return -ENOMEM;
-
- stag = mhp->attr.stag;
- if (cxio_reregister_phys_mem(&rhp->rdev,
- &stag, mhp->attr.pdid,
- mhp->attr.perms,
- mhp->attr.zbva,
- mhp->attr.va_fbo,
- mhp->attr.len,
- shift - 12,
- mhp->attr.pbl_size, mhp->attr.pbl_addr))
- return -ENOMEM;
-
- ret = iwch_finish_mem_reg(mhp, stag);
- if (ret)
- cxio_dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
- mhp->attr.pbl_addr);
-
- return ret;
-}
-
int iwch_alloc_pbl(struct iwch_mr *mhp, int npages)
{
mhp->attr.pbl_addr = cxio_hal_pblpool_alloc(&mhp->rhp->rdev,
@@ -130,74 +99,3 @@ int iwch_write_pbl(struct iwch_mr *mhp, __be64 *pages, int npages, int offset)
return cxio_write_pbl(&mhp->rhp->rdev, pages,
mhp->attr.pbl_addr + (offset << 3), npages);
}
-
-int build_phys_page_list(struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- u64 *iova_start,
- u64 *total_size,
- int *npages,
- int *shift,
- __be64 **page_list)
-{
- u64 mask;
- int i, j, n;
-
- mask = 0;
- *total_size = 0;
- for (i = 0; i < num_phys_buf; ++i) {
- if (i != 0 && buffer_list[i].addr & ~PAGE_MASK)
- return -EINVAL;
- if (i != 0 && i != num_phys_buf - 1 &&
- (buffer_list[i].size & ~PAGE_MASK))
- return -EINVAL;
- *total_size += buffer_list[i].size;
- if (i > 0)
- mask |= buffer_list[i].addr;
- else
- mask |= buffer_list[i].addr & PAGE_MASK;
- if (i != num_phys_buf - 1)
- mask |= buffer_list[i].addr + buffer_list[i].size;
- else
- mask |= (buffer_list[i].addr + buffer_list[i].size +
- PAGE_SIZE - 1) & PAGE_MASK;
- }
-
- if (*total_size > 0xFFFFFFFFULL)
- return -ENOMEM;
-
- /* Find largest page shift we can use to cover buffers */
- for (*shift = PAGE_SHIFT; *shift < 27; ++(*shift))
- if ((1ULL << *shift) & mask)
- break;
-
- buffer_list[0].size += buffer_list[0].addr & ((1ULL << *shift) - 1);
- buffer_list[0].addr &= ~0ull << *shift;
-
- *npages = 0;
- for (i = 0; i < num_phys_buf; ++i)
- *npages += (buffer_list[i].size +
- (1ULL << *shift) - 1) >> *shift;
-
- if (!*npages)
- return -EINVAL;
-
- *page_list = kmalloc(sizeof(u64) * *npages, GFP_KERNEL);
- if (!*page_list)
- return -ENOMEM;
-
- n = 0;
- for (i = 0; i < num_phys_buf; ++i)
- for (j = 0;
- j < (buffer_list[i].size + (1ULL << *shift) - 1) >> *shift;
- ++j)
- (*page_list)[n++] = cpu_to_be64(buffer_list[i].addr +
- ((u64) j << *shift));
-
- PDBG("%s va 0x%llx mask 0x%llx shift %d len %lld pbl_size %d\n",
- __func__, (unsigned long long) *iova_start,
- (unsigned long long) mask, *shift, (unsigned long long) *total_size,
- *npages);
-
- return 0;
-
-}
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index c34725ca0..2734820d2 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -458,9 +458,6 @@ static int iwch_dereg_mr(struct ib_mr *ib_mr)
u32 mmid;
PDBG("%s ib_mr %p\n", __func__, ib_mr);
- /* There can be no memory windows */
- if (atomic_read(&ib_mr->usecnt))
- return -EINVAL;
mhp = to_iwch_mr(ib_mr);
kfree(mhp->pages);
@@ -479,24 +476,25 @@ static int iwch_dereg_mr(struct ib_mr *ib_mr)
return 0;
}
-static struct ib_mr *iwch_register_phys_mem(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- int acc,
- u64 *iova_start)
+static struct ib_mr *iwch_get_dma_mr(struct ib_pd *pd, int acc)
{
- __be64 *page_list;
- int shift;
- u64 total_size;
- int npages;
- struct iwch_dev *rhp;
- struct iwch_pd *php;
+ const u64 total_size = 0xffffffff;
+ const u64 mask = (total_size + PAGE_SIZE - 1) & PAGE_MASK;
+ struct iwch_pd *php = to_iwch_pd(pd);
+ struct iwch_dev *rhp = php->rhp;
struct iwch_mr *mhp;
- int ret;
+ __be64 *page_list;
+ int shift = 26, npages, ret, i;
PDBG("%s ib_pd %p\n", __func__, pd);
- php = to_iwch_pd(pd);
- rhp = php->rhp;
+
+ /*
+ * T3 only supports 32 bits of size.
+ */
+ if (sizeof(phys_addr_t) > 4) {
+ pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n");
+ return ERR_PTR(-ENOTSUPP);
+ }
mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
if (!mhp)
@@ -504,22 +502,23 @@ static struct ib_mr *iwch_register_phys_mem(struct ib_pd *pd,
mhp->rhp = rhp;
- /* First check that we have enough alignment */
- if ((*iova_start & ~PAGE_MASK) != (buffer_list[0].addr & ~PAGE_MASK)) {
+ npages = (total_size + (1ULL << shift) - 1) >> shift;
+ if (!npages) {
ret = -EINVAL;
goto err;
}
- if (num_phys_buf > 1 &&
- ((buffer_list[0].addr + buffer_list[0].size) & ~PAGE_MASK)) {
- ret = -EINVAL;
+ page_list = kmalloc_array(npages, sizeof(u64), GFP_KERNEL);
+ if (!page_list) {
+ ret = -ENOMEM;
goto err;
}
- ret = build_phys_page_list(buffer_list, num_phys_buf, iova_start,
- &total_size, &npages, &shift, &page_list);
- if (ret)
- goto err;
+ for (i = 0; i < npages; i++)
+ page_list[i] = cpu_to_be64((u64)i << shift);
+
+ PDBG("%s mask 0x%llx shift %d len %lld pbl_size %d\n",
+ __func__, mask, shift, total_size, npages);
ret = iwch_alloc_pbl(mhp, npages);
if (ret) {
@@ -536,7 +535,7 @@ static struct ib_mr *iwch_register_phys_mem(struct ib_pd *pd,
mhp->attr.zbva = 0;
mhp->attr.perms = iwch_ib_to_tpt_access(acc);
- mhp->attr.va_fbo = *iova_start;
+ mhp->attr.va_fbo = 0;
mhp->attr.page_size = shift - 12;
mhp->attr.len = (u32) total_size;
@@ -553,76 +552,8 @@ err_pbl:
err:
kfree(mhp);
return ERR_PTR(ret);
-
-}
-
-static int iwch_reregister_phys_mem(struct ib_mr *mr,
- int mr_rereg_mask,
- struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- int acc, u64 * iova_start)
-{
-
- struct iwch_mr mh, *mhp;
- struct iwch_pd *php;
- struct iwch_dev *rhp;
- __be64 *page_list = NULL;
- int shift = 0;
- u64 total_size;
- int npages = 0;
- int ret;
-
- PDBG("%s ib_mr %p ib_pd %p\n", __func__, mr, pd);
-
- /* There can be no memory windows */
- if (atomic_read(&mr->usecnt))
- return -EINVAL;
-
- mhp = to_iwch_mr(mr);
- rhp = mhp->rhp;
- php = to_iwch_pd(mr->pd);
-
- /* make sure we are on the same adapter */
- if (rhp != php->rhp)
- return -EINVAL;
-
- memcpy(&mh, mhp, sizeof *mhp);
-
- if (mr_rereg_mask & IB_MR_REREG_PD)
- php = to_iwch_pd(pd);
- if (mr_rereg_mask & IB_MR_REREG_ACCESS)
- mh.attr.perms = iwch_ib_to_tpt_access(acc);
- if (mr_rereg_mask & IB_MR_REREG_TRANS) {
- ret = build_phys_page_list(buffer_list, num_phys_buf,
- iova_start,
- &total_size, &npages,
- &shift, &page_list);
- if (ret)
- return ret;
- }
-
- ret = iwch_reregister_mem(rhp, php, &mh, shift, npages);
- kfree(page_list);
- if (ret) {
- return ret;
- }
- if (mr_rereg_mask & IB_MR_REREG_PD)
- mhp->attr.pdid = php->pdid;
- if (mr_rereg_mask & IB_MR_REREG_ACCESS)
- mhp->attr.perms = iwch_ib_to_tpt_access(acc);
- if (mr_rereg_mask & IB_MR_REREG_TRANS) {
- mhp->attr.zbva = 0;
- mhp->attr.va_fbo = *iova_start;
- mhp->attr.page_size = shift - 12;
- mhp->attr.len = (u32) total_size;
- mhp->attr.pbl_size = npages;
- }
-
- return 0;
}
-
static struct ib_mr *iwch_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt, int acc, struct ib_udata *udata)
{
@@ -726,28 +657,6 @@ err:
return ERR_PTR(err);
}
-static struct ib_mr *iwch_get_dma_mr(struct ib_pd *pd, int acc)
-{
- struct ib_phys_buf bl;
- u64 kva;
- struct ib_mr *ibmr;
-
- PDBG("%s ib_pd %p\n", __func__, pd);
-
- /*
- * T3 only supports 32 bits of size.
- */
- if (sizeof(phys_addr_t) > 4) {
- pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n");
- return ERR_PTR(-ENOTSUPP);
- }
- bl.size = 0xffffffff;
- bl.addr = 0;
- kva = 0;
- ibmr = iwch_register_phys_mem(pd, &bl, 1, acc, &kva);
- return ibmr;
-}
-
static struct ib_mw *iwch_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
struct iwch_dev *rhp;
@@ -1452,12 +1361,9 @@ int iwch_register_device(struct iwch_dev *dev)
dev->ibdev.resize_cq = iwch_resize_cq;
dev->ibdev.poll_cq = iwch_poll_cq;
dev->ibdev.get_dma_mr = iwch_get_dma_mr;
- dev->ibdev.reg_phys_mr = iwch_register_phys_mem;
- dev->ibdev.rereg_phys_mr = iwch_reregister_phys_mem;
dev->ibdev.reg_user_mr = iwch_reg_user_mr;
dev->ibdev.dereg_mr = iwch_dereg_mr;
dev->ibdev.alloc_mw = iwch_alloc_mw;
- dev->ibdev.bind_mw = iwch_bind_mw;
dev->ibdev.dealloc_mw = iwch_dealloc_mw;
dev->ibdev.alloc_mr = iwch_alloc_mr;
dev->ibdev.map_mr_sg = iwch_map_mr_sg;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.h b/drivers/infiniband/hw/cxgb3/iwch_provider.h
index 2ac85b86a..252c464a0 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.h
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.h
@@ -330,9 +330,6 @@ int iwch_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr);
int iwch_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
struct ib_recv_wr **bad_wr);
-int iwch_bind_mw(struct ib_qp *qp,
- struct ib_mw *mw,
- struct ib_mw_bind *mw_bind);
int iwch_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
int iwch_post_terminate(struct iwch_qp *qhp, struct respQ_msg_t *rsp_msg);
int iwch_post_zb_read(struct iwch_ep *ep);
@@ -341,21 +338,9 @@ void iwch_unregister_device(struct iwch_dev *dev);
void stop_read_rep_timer(struct iwch_qp *qhp);
int iwch_register_mem(struct iwch_dev *rhp, struct iwch_pd *php,
struct iwch_mr *mhp, int shift);
-int iwch_reregister_mem(struct iwch_dev *rhp, struct iwch_pd *php,
- struct iwch_mr *mhp,
- int shift,
- int npages);
int iwch_alloc_pbl(struct iwch_mr *mhp, int npages);
void iwch_free_pbl(struct iwch_mr *mhp);
int iwch_write_pbl(struct iwch_mr *mhp, __be64 *pages, int npages, int offset);
-int build_phys_page_list(struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- u64 *iova_start,
- u64 *total_size,
- int *npages,
- int *shift,
- __be64 **page_list);
-
#define IWCH_NODE_DESC "cxgb3 Chelsio Communications"
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index d0548fc63..d939980a7 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -526,88 +526,6 @@ out:
return err;
}
-int iwch_bind_mw(struct ib_qp *qp,
- struct ib_mw *mw,
- struct ib_mw_bind *mw_bind)
-{
- struct iwch_dev *rhp;
- struct iwch_mw *mhp;
- struct iwch_qp *qhp;
- union t3_wr *wqe;
- u32 pbl_addr;
- u8 page_size;
- u32 num_wrs;
- unsigned long flag;
- struct ib_sge sgl;
- int err=0;
- enum t3_wr_flags t3_wr_flags;
- u32 idx;
- struct t3_swsq *sqp;
-
- qhp = to_iwch_qp(qp);
- mhp = to_iwch_mw(mw);
- rhp = qhp->rhp;
-
- spin_lock_irqsave(&qhp->lock, flag);
- if (qhp->attr.state > IWCH_QP_STATE_RTS) {
- spin_unlock_irqrestore(&qhp->lock, flag);
- return -EINVAL;
- }
- num_wrs = Q_FREECNT(qhp->wq.sq_rptr, qhp->wq.sq_wptr,
- qhp->wq.sq_size_log2);
- if (num_wrs == 0) {
- spin_unlock_irqrestore(&qhp->lock, flag);
- return -ENOMEM;
- }
- idx = Q_PTR2IDX(qhp->wq.wptr, qhp->wq.size_log2);
- PDBG("%s: idx 0x%0x, mw 0x%p, mw_bind 0x%p\n", __func__, idx,
- mw, mw_bind);
- wqe = (union t3_wr *) (qhp->wq.queue + idx);
-
- t3_wr_flags = 0;
- if (mw_bind->send_flags & IB_SEND_SIGNALED)
- t3_wr_flags = T3_COMPLETION_FLAG;
-
- sgl.addr = mw_bind->bind_info.addr;
- sgl.lkey = mw_bind->bind_info.mr->lkey;
- sgl.length = mw_bind->bind_info.length;
- wqe->bind.reserved = 0;
- wqe->bind.type = TPT_VATO;
-
- /* TBD: check perms */
- wqe->bind.perms = iwch_ib_to_tpt_bind_access(
- mw_bind->bind_info.mw_access_flags);
- wqe->bind.mr_stag = cpu_to_be32(mw_bind->bind_info.mr->lkey);
- wqe->bind.mw_stag = cpu_to_be32(mw->rkey);
- wqe->bind.mw_len = cpu_to_be32(mw_bind->bind_info.length);
- wqe->bind.mw_va = cpu_to_be64(mw_bind->bind_info.addr);
- err = iwch_sgl2pbl_map(rhp, &sgl, 1, &pbl_addr, &page_size);
- if (err) {
- spin_unlock_irqrestore(&qhp->lock, flag);
- return err;
- }
- wqe->send.wrid.id0.hi = qhp->wq.sq_wptr;
- sqp = qhp->wq.sq + Q_PTR2IDX(qhp->wq.sq_wptr, qhp->wq.sq_size_log2);
- sqp->wr_id = mw_bind->wr_id;
- sqp->opcode = T3_BIND_MW;
- sqp->sq_wptr = qhp->wq.sq_wptr;
- sqp->complete = 0;
- sqp->signaled = (mw_bind->send_flags & IB_SEND_SIGNALED);
- wqe->bind.mr_pbl_addr = cpu_to_be32(pbl_addr);
- wqe->bind.mr_pagesz = page_size;
- build_fw_riwrh((void *)wqe, T3_WR_BIND, t3_wr_flags,
- Q_GENBIT(qhp->wq.wptr, qhp->wq.size_log2), 0,
- sizeof(struct t3_bind_mw_wr) >> 3, T3_SOPEOP);
- ++(qhp->wq.wptr);
- ++(qhp->wq.sq_wptr);
- spin_unlock_irqrestore(&qhp->lock, flag);
-
- if (cxio_wq_db_enabled(&qhp->wq))
- ring_doorbell(qhp->wq.doorbell, qhp->wq.qpid);
-
- return err;
-}
-
static inline void build_term_codes(struct respQ_msg_t *rsp_msg,
u8 *layer_type, u8 *ecode)
{
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index c9cffced0..cd2ff5f95 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -449,7 +449,7 @@ static void act_open_req_arp_failure(void *handle, struct sk_buff *skb)
{
struct c4iw_ep *ep = handle;
- printk(KERN_ERR MOD "ARP failure duing connect\n");
+ printk(KERN_ERR MOD "ARP failure during connect\n");
kfree_skb(skb);
connect_reply_upcall(ep, -EHOSTUNREACH);
state_set(&ep->com, DEAD);
@@ -3271,6 +3271,12 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
&ep->com.mapped_local_addr;
+ if (ipv6_addr_type(&sin6->sin6_addr) != IPV6_ADDR_ANY) {
+ err = cxgb4_clip_get(ep->com.dev->rdev.lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr, 1);
+ if (err)
+ return err;
+ }
c4iw_init_wr_wait(&ep->com.wr_wait);
err = cxgb4_create_server6(ep->com.dev->rdev.lldi.ports[0],
ep->stid, &sin6->sin6_addr,
@@ -3282,13 +3288,13 @@ static int create_server6(struct c4iw_dev *dev, struct c4iw_listen_ep *ep)
0, 0, __func__);
else if (err > 0)
err = net_xmit_errno(err);
- if (err)
+ if (err) {
+ cxgb4_clip_release(ep->com.dev->rdev.lldi.ports[0],
+ (const u32 *)&sin6->sin6_addr.s6_addr, 1);
pr_err("cxgb4_create_server6/filter failed err %d stid %d laddr %pI6 lport %d\n",
err, ep->stid,
sin6->sin6_addr.s6_addr, ntohs(sin6->sin6_port));
- else
- cxgb4_clip_get(ep->com.dev->rdev.lldi.ports[0],
- (const u32 *)&sin6->sin6_addr.s6_addr, 1);
+ }
return err;
}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index de9cd6901..cf21df4a8 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -744,9 +744,6 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
case FW_RI_SEND_WITH_SE:
wc->opcode = IB_WC_SEND;
break;
- case FW_RI_BIND_MW:
- wc->opcode = IB_WC_BIND_MW;
- break;
case FW_RI_LOCAL_INV:
wc->opcode = IB_WC_LOCAL_INV;
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 58fce1742..8024ea441 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -315,14 +315,12 @@ static int qp_release(struct inode *inode, struct file *file)
static int qp_open(struct inode *inode, struct file *file)
{
struct c4iw_debugfs_data *qpd;
- int ret = 0;
int count = 1;
qpd = kmalloc(sizeof *qpd, GFP_KERNEL);
- if (!qpd) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!qpd)
+ return -ENOMEM;
+
qpd->devp = inode->i_private;
qpd->pos = 0;
@@ -333,8 +331,8 @@ static int qp_open(struct inode *inode, struct file *file)
qpd->bufsize = count * 128;
qpd->buf = vmalloc(qpd->bufsize);
if (!qpd->buf) {
- ret = -ENOMEM;
- goto err1;
+ kfree(qpd);
+ return -ENOMEM;
}
spin_lock_irq(&qpd->devp->lock);
@@ -343,11 +341,7 @@ static int qp_open(struct inode *inode, struct file *file)
qpd->buf[qpd->pos++] = 0;
file->private_data = qpd;
- goto out;
-err1:
- kfree(qpd);
-out:
- return ret;
+ return 0;
}
static const struct file_operations qp_debugfs_fops = {
@@ -781,8 +775,7 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
pr_err(MOD "%s: unsupported udb/ucq densities %u/%u\n",
pci_name(rdev->lldi.pdev), rdev->lldi.udb_density,
rdev->lldi.ucq_density);
- err = -EINVAL;
- goto err1;
+ return -EINVAL;
}
if (rdev->lldi.vr->qp.start != rdev->lldi.vr->cq.start ||
rdev->lldi.vr->qp.size != rdev->lldi.vr->cq.size) {
@@ -791,8 +784,7 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
pci_name(rdev->lldi.pdev), rdev->lldi.vr->qp.start,
rdev->lldi.vr->qp.size, rdev->lldi.vr->cq.size,
rdev->lldi.vr->cq.size);
- err = -EINVAL;
- goto err1;
+ return -EINVAL;
}
rdev->qpmask = rdev->lldi.udb_density - 1;
@@ -816,10 +808,8 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
rdev->lldi.db_reg, rdev->lldi.gts_reg,
rdev->qpmask, rdev->cqmask);
- if (c4iw_num_stags(rdev) == 0) {
- err = -EINVAL;
- goto err1;
- }
+ if (c4iw_num_stags(rdev) == 0)
+ return -EINVAL;
rdev->stats.pd.total = T4_MAX_NUM_PD;
rdev->stats.stag.total = rdev->lldi.vr->stag.size;
@@ -831,29 +821,31 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
err = c4iw_init_resource(rdev, c4iw_num_stags(rdev), T4_MAX_NUM_PD);
if (err) {
printk(KERN_ERR MOD "error %d initializing resources\n", err);
- goto err1;
+ return err;
}
err = c4iw_pblpool_create(rdev);
if (err) {
printk(KERN_ERR MOD "error %d initializing pbl pool\n", err);
- goto err2;
+ goto destroy_resource;
}
err = c4iw_rqtpool_create(rdev);
if (err) {
printk(KERN_ERR MOD "error %d initializing rqt pool\n", err);
- goto err3;
+ goto destroy_pblpool;
}
err = c4iw_ocqp_pool_create(rdev);
if (err) {
printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
- goto err4;
+ goto destroy_rqtpool;
}
rdev->status_page = (struct t4_dev_status_page *)
__get_free_page(GFP_KERNEL);
- if (!rdev->status_page) {
- pr_err(MOD "error allocating status page\n");
- goto err4;
- }
+ if (!rdev->status_page)
+ goto destroy_ocqp_pool;
+ rdev->status_page->qp_start = rdev->lldi.vr->qp.start;
+ rdev->status_page->qp_size = rdev->lldi.vr->qp.size;
+ rdev->status_page->cq_start = rdev->lldi.vr->cq.start;
+ rdev->status_page->cq_size = rdev->lldi.vr->cq.size;
if (c4iw_wr_log) {
rdev->wr_log = kzalloc((1 << c4iw_wr_log_size_order) *
@@ -869,13 +861,14 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
rdev->status_page->db_off = 0;
return 0;
-err4:
+destroy_ocqp_pool:
+ c4iw_ocqp_pool_destroy(rdev);
+destroy_rqtpool:
c4iw_rqtpool_destroy(rdev);
-err3:
+destroy_pblpool:
c4iw_pblpool_destroy(rdev);
-err2:
+destroy_resource:
c4iw_destroy_resource(&rdev->resource);
-err1:
return err;
}
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 00e55faa0..fb2de75a0 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -947,8 +947,6 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr);
int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
struct ib_recv_wr **bad_wr);
-int c4iw_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
- struct ib_mw_bind *mw_bind);
int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param);
int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog);
int c4iw_destroy_listen(struct iw_cm_id *cm_id);
@@ -968,17 +966,6 @@ struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start,
u64 length, u64 virt, int acc,
struct ib_udata *udata);
struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc);
-struct ib_mr *c4iw_register_phys_mem(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- int acc,
- u64 *iova_start);
-int c4iw_reregister_phys_mem(struct ib_mr *mr,
- int mr_rereg_mask,
- struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- int acc, u64 *iova_start);
int c4iw_dereg_mr(struct ib_mr *ib_mr);
int c4iw_destroy_cq(struct ib_cq *ib_cq);
struct ib_cq *c4iw_create_cq(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index e1629ab58..7849890c4 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -392,32 +392,6 @@ static int register_mem(struct c4iw_dev *rhp, struct c4iw_pd *php,
return ret;
}
-static int reregister_mem(struct c4iw_dev *rhp, struct c4iw_pd *php,
- struct c4iw_mr *mhp, int shift, int npages)
-{
- u32 stag;
- int ret;
-
- if (npages > mhp->attr.pbl_size)
- return -ENOMEM;
-
- stag = mhp->attr.stag;
- ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, mhp->attr.pdid,
- FW_RI_STAG_NSMR, mhp->attr.perms,
- mhp->attr.mw_bind_enable, mhp->attr.zbva,
- mhp->attr.va_fbo, mhp->attr.len, shift - 12,
- mhp->attr.pbl_size, mhp->attr.pbl_addr);
- if (ret)
- return ret;
-
- ret = finish_mem_reg(mhp, stag);
- if (ret)
- dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
- mhp->attr.pbl_addr);
-
- return ret;
-}
-
static int alloc_pbl(struct c4iw_mr *mhp, int npages)
{
mhp->attr.pbl_addr = c4iw_pblpool_alloc(&mhp->rhp->rdev,
@@ -431,228 +405,6 @@ static int alloc_pbl(struct c4iw_mr *mhp, int npages)
return 0;
}
-static int build_phys_page_list(struct ib_phys_buf *buffer_list,
- int num_phys_buf, u64 *iova_start,
- u64 *total_size, int *npages,
- int *shift, __be64 **page_list)
-{
- u64 mask;
- int i, j, n;
-
- mask = 0;
- *total_size = 0;
- for (i = 0; i < num_phys_buf; ++i) {
- if (i != 0 && buffer_list[i].addr & ~PAGE_MASK)
- return -EINVAL;
- if (i != 0 && i != num_phys_buf - 1 &&
- (buffer_list[i].size & ~PAGE_MASK))
- return -EINVAL;
- *total_size += buffer_list[i].size;
- if (i > 0)
- mask |= buffer_list[i].addr;
- else
- mask |= buffer_list[i].addr & PAGE_MASK;
- if (i != num_phys_buf - 1)
- mask |= buffer_list[i].addr + buffer_list[i].size;
- else
- mask |= (buffer_list[i].addr + buffer_list[i].size +
- PAGE_SIZE - 1) & PAGE_MASK;
- }
-
- if (*total_size > 0xFFFFFFFFULL)
- return -ENOMEM;
-
- /* Find largest page shift we can use to cover buffers */
- for (*shift = PAGE_SHIFT; *shift < 27; ++(*shift))
- if ((1ULL << *shift) & mask)
- break;
-
- buffer_list[0].size += buffer_list[0].addr & ((1ULL << *shift) - 1);
- buffer_list[0].addr &= ~0ull << *shift;
-
- *npages = 0;
- for (i = 0; i < num_phys_buf; ++i)
- *npages += (buffer_list[i].size +
- (1ULL << *shift) - 1) >> *shift;
-
- if (!*npages)
- return -EINVAL;
-
- *page_list = kmalloc(sizeof(u64) * *npages, GFP_KERNEL);
- if (!*page_list)
- return -ENOMEM;
-
- n = 0;
- for (i = 0; i < num_phys_buf; ++i)
- for (j = 0;
- j < (buffer_list[i].size + (1ULL << *shift) - 1) >> *shift;
- ++j)
- (*page_list)[n++] = cpu_to_be64(buffer_list[i].addr +
- ((u64) j << *shift));
-
- PDBG("%s va 0x%llx mask 0x%llx shift %d len %lld pbl_size %d\n",
- __func__, (unsigned long long)*iova_start,
- (unsigned long long)mask, *shift, (unsigned long long)*total_size,
- *npages);
-
- return 0;
-
-}
-
-int c4iw_reregister_phys_mem(struct ib_mr *mr, int mr_rereg_mask,
- struct ib_pd *pd, struct ib_phys_buf *buffer_list,
- int num_phys_buf, int acc, u64 *iova_start)
-{
-
- struct c4iw_mr mh, *mhp;
- struct c4iw_pd *php;
- struct c4iw_dev *rhp;
- __be64 *page_list = NULL;
- int shift = 0;
- u64 total_size;
- int npages;
- int ret;
-
- PDBG("%s ib_mr %p ib_pd %p\n", __func__, mr, pd);
-
- /* There can be no memory windows */
- if (atomic_read(&mr->usecnt))
- return -EINVAL;
-
- mhp = to_c4iw_mr(mr);
- rhp = mhp->rhp;
- php = to_c4iw_pd(mr->pd);
-
- /* make sure we are on the same adapter */
- if (rhp != php->rhp)
- return -EINVAL;
-
- memcpy(&mh, mhp, sizeof *mhp);
-
- if (mr_rereg_mask & IB_MR_REREG_PD)
- php = to_c4iw_pd(pd);
- if (mr_rereg_mask & IB_MR_REREG_ACCESS) {
- mh.attr.perms = c4iw_ib_to_tpt_access(acc);
- mh.attr.mw_bind_enable = (acc & IB_ACCESS_MW_BIND) ==
- IB_ACCESS_MW_BIND;
- }
- if (mr_rereg_mask & IB_MR_REREG_TRANS) {
- ret = build_phys_page_list(buffer_list, num_phys_buf,
- iova_start,
- &total_size, &npages,
- &shift, &page_list);
- if (ret)
- return ret;
- }
-
- if (mr_exceeds_hw_limits(rhp, total_size)) {
- kfree(page_list);
- return -EINVAL;
- }
-
- ret = reregister_mem(rhp, php, &mh, shift, npages);
- kfree(page_list);
- if (ret)
- return ret;
- if (mr_rereg_mask & IB_MR_REREG_PD)
- mhp->attr.pdid = php->pdid;
- if (mr_rereg_mask & IB_MR_REREG_ACCESS)
- mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
- if (mr_rereg_mask & IB_MR_REREG_TRANS) {
- mhp->attr.zbva = 0;
- mhp->attr.va_fbo = *iova_start;
- mhp->attr.page_size = shift - 12;
- mhp->attr.len = (u32) total_size;
- mhp->attr.pbl_size = npages;
- }
-
- return 0;
-}
-
-struct ib_mr *c4iw_register_phys_mem(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf, int acc, u64 *iova_start)
-{
- __be64 *page_list;
- int shift;
- u64 total_size;
- int npages;
- struct c4iw_dev *rhp;
- struct c4iw_pd *php;
- struct c4iw_mr *mhp;
- int ret;
-
- PDBG("%s ib_pd %p\n", __func__, pd);
- php = to_c4iw_pd(pd);
- rhp = php->rhp;
-
- mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
- if (!mhp)
- return ERR_PTR(-ENOMEM);
-
- mhp->rhp = rhp;
-
- /* First check that we have enough alignment */
- if ((*iova_start & ~PAGE_MASK) != (buffer_list[0].addr & ~PAGE_MASK)) {
- ret = -EINVAL;
- goto err;
- }
-
- if (num_phys_buf > 1 &&
- ((buffer_list[0].addr + buffer_list[0].size) & ~PAGE_MASK)) {
- ret = -EINVAL;
- goto err;
- }
-
- ret = build_phys_page_list(buffer_list, num_phys_buf, iova_start,
- &total_size, &npages, &shift,
- &page_list);
- if (ret)
- goto err;
-
- if (mr_exceeds_hw_limits(rhp, total_size)) {
- kfree(page_list);
- ret = -EINVAL;
- goto err;
- }
-
- ret = alloc_pbl(mhp, npages);
- if (ret) {
- kfree(page_list);
- goto err;
- }
-
- ret = write_pbl(&mhp->rhp->rdev, page_list, mhp->attr.pbl_addr,
- npages);
- kfree(page_list);
- if (ret)
- goto err_pbl;
-
- mhp->attr.pdid = php->pdid;
- mhp->attr.zbva = 0;
-
- mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
- mhp->attr.va_fbo = *iova_start;
- mhp->attr.page_size = shift - 12;
-
- mhp->attr.len = (u32) total_size;
- mhp->attr.pbl_size = npages;
- ret = register_mem(rhp, php, mhp, shift);
- if (ret)
- goto err_pbl;
-
- return &mhp->ibmr;
-
-err_pbl:
- c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
- mhp->attr.pbl_size << 3);
-
-err:
- kfree(mhp);
- return ERR_PTR(ret);
-
-}
-
struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
{
struct c4iw_dev *rhp;
@@ -952,9 +704,6 @@ int c4iw_dereg_mr(struct ib_mr *ib_mr)
u32 mmid;
PDBG("%s ib_mr %p\n", __func__, ib_mr);
- /* There can be no memory windows */
- if (atomic_read(&ib_mr->usecnt))
- return -EINVAL;
mhp = to_c4iw_mr(ib_mr);
rhp = mhp->rhp;
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 0a7d99818..ec04272fb 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -549,12 +549,9 @@ int c4iw_register_device(struct c4iw_dev *dev)
dev->ibdev.resize_cq = c4iw_resize_cq;
dev->ibdev.poll_cq = c4iw_poll_cq;
dev->ibdev.get_dma_mr = c4iw_get_dma_mr;
- dev->ibdev.reg_phys_mr = c4iw_register_phys_mem;
- dev->ibdev.rereg_phys_mr = c4iw_reregister_phys_mem;
dev->ibdev.reg_user_mr = c4iw_reg_user_mr;
dev->ibdev.dereg_mr = c4iw_dereg_mr;
dev->ibdev.alloc_mw = c4iw_alloc_mw;
- dev->ibdev.bind_mw = c4iw_bind_mw;
dev->ibdev.dealloc_mw = c4iw_dealloc_mw;
dev->ibdev.alloc_mr = c4iw_alloc_mr;
dev->ibdev.map_mr_sg = c4iw_map_mr_sg;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index aa515afee..e99345eb8 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -933,11 +933,6 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
return err;
}
-int c4iw_bind_mw(struct ib_qp *qp, struct ib_mw *mw, struct ib_mw_bind *mw_bind)
-{
- return -ENOSYS;
-}
-
static inline void build_term_codes(struct t4_cqe *err_cqe, u8 *layer_type,
u8 *ecode)
{
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 1092a2d1f..6126bbe36 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -699,4 +699,11 @@ static inline void t4_set_cq_in_error(struct t4_cq *cq)
struct t4_dev_status_page {
u8 db_off;
+ u8 pad1;
+ u16 pad2;
+ u32 pad3;
+ u64 qp_start;
+ u64 qp_size;
+ u64 cq_start;
+ u64 cq_size;
};
diff --git a/drivers/infiniband/hw/cxgb4/user.h b/drivers/infiniband/hw/cxgb4/user.h
index cbd0ce170..295f422b9 100644
--- a/drivers/infiniband/hw/cxgb4/user.h
+++ b/drivers/infiniband/hw/cxgb4/user.h
@@ -32,7 +32,7 @@
#ifndef __C4IW_USER_H__
#define __C4IW_USER_H__
-#define C4IW_UVERBS_ABI_VERSION 2
+#define C4IW_UVERBS_ABI_VERSION 3
/*
* Make sure that all structs defined in this file remain laid out so
diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 86af71351..105246fba 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -92,7 +92,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
ah_attr->grh.sgid_index, &sgid, &gid_attr);
if (ret)
return ERR_PTR(ret);
- memset(ah->av.eth.s_mac, 0, ETH_ALEN);
+ eth_zero_addr(ah->av.eth.s_mac);
if (gid_attr.ndev) {
if (is_vlan_dev(gid_attr.ndev))
vlan_tag = vlan_dev_vlan_id(gid_attr.ndev);
@@ -104,6 +104,7 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
ah->av.eth.gid_index = mlx4_ib_gid_index_to_real_index(ibdev, ah_attr->port_num, ah_attr->grh.sgid_index);
ah->av.eth.vlan = cpu_to_be16(vlan_tag);
+ ah->av.eth.hop_limit = ah_attr->grh.hop_limit;
if (ah_attr->static_rate) {
ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
while (ah->av.eth.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET &&
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index b88fc8f5a..9f8b516eb 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -811,9 +811,6 @@ repoll:
wc->opcode = IB_WC_MASKED_FETCH_ADD;
wc->byte_len = 8;
break;
- case MLX4_OPCODE_BIND_MW:
- wc->opcode = IB_WC_BIND_MW;
- break;
case MLX4_OPCODE_LSO:
wc->opcode = IB_WC_LSO;
break;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 870e56b6b..d68f506c1 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -40,6 +40,7 @@
#include <linux/gfp.h>
#include <rdma/ib_pma.h>
+#include <linux/mlx4/driver.h>
#include "mlx4_ib.h"
enum {
@@ -606,8 +607,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
struct ib_mad *mad)
{
struct mlx4_ib_dev *dev = to_mdev(ibdev);
- int err;
- int slave;
+ int err, other_port;
+ int slave = -1;
u8 *slave_id;
int is_eth = 0;
@@ -625,7 +626,17 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n");
return -EINVAL;
}
- if (mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave)) {
+ err = mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave);
+ if (err && mlx4_is_mf_bonded(dev->dev)) {
+ other_port = (port == 1) ? 2 : 1;
+ err = mlx4_get_slave_from_roce_gid(dev->dev, other_port, grh->dgid.raw, &slave);
+ if (!err) {
+ port = other_port;
+ pr_debug("resolved slave %d from gid %pI6 wire port %d other %d\n",
+ slave, grh->dgid.raw, port, other_port);
+ }
+ }
+ if (err) {
mlx4_ib_warn(ibdev, "failed matching grh\n");
return -ENOENT;
}
@@ -806,17 +817,48 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}
-static void edit_counter(struct mlx4_counter *cnt,
- struct ib_pma_portcounters *pma_cnt)
+static void edit_counter(struct mlx4_counter *cnt, void *counters,
+ __be16 attr_id)
+{
+ switch (attr_id) {
+ case IB_PMA_PORT_COUNTERS:
+ {
+ struct ib_pma_portcounters *pma_cnt =
+ (struct ib_pma_portcounters *)counters;
+
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
+ (be64_to_cpu(cnt->tx_bytes) >> 2));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
+ (be64_to_cpu(cnt->rx_bytes) >> 2));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
+ be64_to_cpu(cnt->tx_frames));
+ ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
+ be64_to_cpu(cnt->rx_frames));
+ break;
+ }
+ case IB_PMA_PORT_COUNTERS_EXT:
+ {
+ struct ib_pma_portcounters_ext *pma_cnt_ext =
+ (struct ib_pma_portcounters_ext *)counters;
+
+ pma_cnt_ext->port_xmit_data =
+ cpu_to_be64(be64_to_cpu(cnt->tx_bytes) >> 2);
+ pma_cnt_ext->port_rcv_data =
+ cpu_to_be64(be64_to_cpu(cnt->rx_bytes) >> 2);
+ pma_cnt_ext->port_xmit_packets = cnt->tx_frames;
+ pma_cnt_ext->port_rcv_packets = cnt->rx_frames;
+ break;
+ }
+ }
+}
+
+static int iboe_process_mad_port_info(void *out_mad)
{
- ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data,
- (be64_to_cpu(cnt->tx_bytes) >> 2));
- ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data,
- (be64_to_cpu(cnt->rx_bytes) >> 2));
- ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets,
- be64_to_cpu(cnt->tx_frames));
- ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets,
- be64_to_cpu(cnt->rx_frames));
+ struct ib_class_port_info cpi = {};
+
+ cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH;
+ memcpy(out_mad, &cpi, sizeof(cpi));
+ return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
}
static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
@@ -831,6 +873,9 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT)
return -EINVAL;
+ if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)
+ return iboe_process_mad_port_info((void *)(out_mad->data + 40));
+
memset(&counter_stats, 0, sizeof(counter_stats));
mutex_lock(&dev->counters_table[port_num - 1].mutex);
list_for_each_entry(tmp_counter,
@@ -852,7 +897,8 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
switch (counter_stats.counter_mode & 0xf) {
case 0:
edit_counter(&counter_stats,
- (void *)(out_mad->data + 40));
+ (void *)(out_mad->data + 40),
+ in_mad->mad_hdr.attr_id);
err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY;
break;
default:
@@ -883,8 +929,10 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
*/
if (link == IB_LINK_LAYER_INFINIBAND) {
if (mlx4_is_slave(dev->dev) &&
- in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
- in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+ (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+ (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS ||
+ in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT ||
+ in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO)))
return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
in_grh, in_mad, out_mad);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 97d6878f9..1c7ab6cab 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -154,9 +154,9 @@ static struct net_device *mlx4_ib_get_netdev(struct ib_device *device, u8 port_n
return dev;
}
-static int mlx4_ib_update_gids(struct gid_entry *gids,
- struct mlx4_ib_dev *ibdev,
- u8 port_num)
+static int mlx4_ib_update_gids_v1(struct gid_entry *gids,
+ struct mlx4_ib_dev *ibdev,
+ u8 port_num)
{
struct mlx4_cmd_mailbox *mailbox;
int err;
@@ -187,6 +187,63 @@ static int mlx4_ib_update_gids(struct gid_entry *gids,
return err;
}
+static int mlx4_ib_update_gids_v1_v2(struct gid_entry *gids,
+ struct mlx4_ib_dev *ibdev,
+ u8 port_num)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ int err;
+ struct mlx4_dev *dev = ibdev->dev;
+ int i;
+ struct {
+ union ib_gid gid;
+ __be32 rsrvd1[2];
+ __be16 rsrvd2;
+ u8 type;
+ u8 version;
+ __be32 rsrvd3;
+ } *gid_tbl;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return -ENOMEM;
+
+ gid_tbl = mailbox->buf;
+ for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
+ memcpy(&gid_tbl[i].gid, &gids[i].gid, sizeof(union ib_gid));
+ if (gids[i].gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
+ gid_tbl[i].version = 2;
+ if (!ipv6_addr_v4mapped((struct in6_addr *)&gids[i].gid))
+ gid_tbl[i].type = 1;
+ else
+ memset(&gid_tbl[i].gid, 0, 12);
+ }
+ }
+
+ err = mlx4_cmd(dev, mailbox->dma,
+ MLX4_SET_PORT_ROCE_ADDR << 8 | port_num,
+ 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+ if (mlx4_is_bonded(dev))
+ err += mlx4_cmd(dev, mailbox->dma,
+ MLX4_SET_PORT_ROCE_ADDR << 8 | 2,
+ 1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+ MLX4_CMD_WRAPPED);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return err;
+}
+
+static int mlx4_ib_update_gids(struct gid_entry *gids,
+ struct mlx4_ib_dev *ibdev,
+ u8 port_num)
+{
+ if (ibdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
+ return mlx4_ib_update_gids_v1_v2(gids, ibdev, port_num);
+
+ return mlx4_ib_update_gids_v1(gids, ibdev, port_num);
+}
+
static int mlx4_ib_add_gid(struct ib_device *device,
u8 port_num,
unsigned int index,
@@ -215,7 +272,8 @@ static int mlx4_ib_add_gid(struct ib_device *device,
port_gid_table = &iboe->gids[port_num - 1];
spin_lock_bh(&iboe->lock);
for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i) {
- if (!memcmp(&port_gid_table->gids[i].gid, gid, sizeof(*gid))) {
+ if (!memcmp(&port_gid_table->gids[i].gid, gid, sizeof(*gid)) &&
+ (port_gid_table->gids[i].gid_type == attr->gid_type)) {
found = i;
break;
}
@@ -233,6 +291,7 @@ static int mlx4_ib_add_gid(struct ib_device *device,
} else {
*context = port_gid_table->gids[free].ctx;
memcpy(&port_gid_table->gids[free].gid, gid, sizeof(*gid));
+ port_gid_table->gids[free].gid_type = attr->gid_type;
port_gid_table->gids[free].ctx->real_index = free;
port_gid_table->gids[free].ctx->refcount = 1;
hw_update = 1;
@@ -248,8 +307,10 @@ static int mlx4_ib_add_gid(struct ib_device *device,
if (!gids) {
ret = -ENOMEM;
} else {
- for (i = 0; i < MLX4_MAX_PORT_GIDS; i++)
+ for (i = 0; i < MLX4_MAX_PORT_GIDS; i++) {
memcpy(&gids[i].gid, &port_gid_table->gids[i].gid, sizeof(union ib_gid));
+ gids[i].gid_type = port_gid_table->gids[i].gid_type;
+ }
}
}
spin_unlock_bh(&iboe->lock);
@@ -325,6 +386,7 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
int i;
int ret;
unsigned long flags;
+ struct ib_gid_attr attr;
if (port_num > MLX4_MAX_PORTS)
return -EINVAL;
@@ -335,10 +397,13 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
if (!rdma_cap_roce_gid_table(&ibdev->ib_dev, port_num))
return index;
- ret = ib_get_cached_gid(&ibdev->ib_dev, port_num, index, &gid, NULL);
+ ret = ib_get_cached_gid(&ibdev->ib_dev, port_num, index, &gid, &attr);
if (ret)
return ret;
+ if (attr.ndev)
+ dev_put(attr.ndev);
+
if (!memcmp(&gid, &zgid, sizeof(gid)))
return -EINVAL;
@@ -346,7 +411,8 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,
port_gid_table = &iboe->gids[port_num - 1];
for (i = 0; i < MLX4_MAX_PORT_GIDS; ++i)
- if (!memcmp(&port_gid_table->gids[i].gid, &gid, sizeof(gid))) {
+ if (!memcmp(&port_gid_table->gids[i].gid, &gid, sizeof(gid)) &&
+ attr.gid_type == port_gid_table->gids[i].gid_type) {
ctx = port_gid_table->gids[i].ctx;
break;
}
@@ -2119,6 +2185,7 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
struct ib_port_immutable *immutable)
{
struct ib_port_attr attr;
+ struct mlx4_ib_dev *mdev = to_mdev(ibdev);
int err;
err = mlx4_ib_query_port(ibdev, port_num, &attr);
@@ -2128,10 +2195,15 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
immutable->pkey_tbl_len = attr.pkey_tbl_len;
immutable->gid_tbl_len = attr.gid_tbl_len;
- if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND)
+ if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND) {
immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
- else
- immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+ } else {
+ if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE)
+ immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+ if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2)
+ immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE |
+ RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+ }
immutable->max_mad_size = IB_MGMT_MAD_SIZE;
@@ -2283,7 +2355,6 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) {
ibdev->ib_dev.alloc_mw = mlx4_ib_alloc_mw;
- ibdev->ib_dev.bind_mw = mlx4_ib_bind_mw;
ibdev->ib_dev.dealloc_mw = mlx4_ib_dealloc_mw;
ibdev->ib_dev.uverbs_cmd_mask |=
@@ -2423,7 +2494,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
if (mlx4_ib_init_sriov(ibdev))
goto err_mad;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) {
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE ||
+ dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) {
if (!iboe->nb.notifier_call) {
iboe->nb.notifier_call = mlx4_ib_netdev_event;
err = register_netdevice_notifier(&iboe->nb);
@@ -2432,6 +2504,12 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
goto err_notif;
}
}
+ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) {
+ err = mlx4_config_roce_v2_port(dev, ROCE_V2_UDP_DPORT);
+ if (err) {
+ goto err_notif;
+ }
+ }
}
for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 1caa11eda..52ce7b000 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -177,11 +177,18 @@ struct mlx4_ib_wq {
unsigned tail;
};
+enum {
+ MLX4_IB_QP_CREATE_ROCE_V2_GSI = IB_QP_CREATE_RESERVED_START
+};
+
enum mlx4_ib_qp_flags {
MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO,
MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP,
MLX4_IB_QP_CREATE_USE_GFP_NOIO = IB_QP_CREATE_USE_GFP_NOIO,
+
+ /* Mellanox specific flags start from IB_QP_CREATE_RESERVED_START */
+ MLX4_IB_ROCE_V2_GSI_QP = MLX4_IB_QP_CREATE_ROCE_V2_GSI,
MLX4_IB_SRIOV_TUNNEL_QP = 1 << 30,
MLX4_IB_SRIOV_SQP = 1 << 31,
};
@@ -478,6 +485,7 @@ struct gid_cache_context {
struct gid_entry {
union ib_gid gid;
+ enum ib_gid_type gid_type;
struct gid_cache_context *ctx;
};
@@ -704,8 +712,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
struct ib_udata *udata);
int mlx4_ib_dereg_mr(struct ib_mr *mr);
struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
-int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
- struct ib_mw_bind *mw_bind);
int mlx4_ib_dealloc_mw(struct ib_mw *mw);
struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
enum ib_mr_type mr_type,
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 4d1e1c632..242b94ec1 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -366,28 +366,6 @@ err_free:
return ERR_PTR(err);
}
-int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
- struct ib_mw_bind *mw_bind)
-{
- struct ib_bind_mw_wr wr;
- struct ib_send_wr *bad_wr;
- int ret;
-
- memset(&wr, 0, sizeof(wr));
- wr.wr.opcode = IB_WR_BIND_MW;
- wr.wr.wr_id = mw_bind->wr_id;
- wr.wr.send_flags = mw_bind->send_flags;
- wr.mw = mw;
- wr.bind_info = mw_bind->bind_info;
- wr.rkey = ib_inc_rkey(mw->rkey);
-
- ret = mlx4_ib_post_send(qp, &wr.wr, &bad_wr);
- if (!ret)
- mw->rkey = wr.rkey;
-
- return ret;
-}
-
int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
{
struct mlx4_ib_mw *mw = to_mmw(ibmw);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 13eaaf452..fd9753476 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -32,6 +32,8 @@
*/
#include <linux/log2.h>
+#include <linux/etherdevice.h>
+#include <net/ip.h>
#include <linux/slab.h>
#include <linux/netdevice.h>
#include <linux/vmalloc.h>
@@ -85,6 +87,7 @@ struct mlx4_ib_sqp {
u32 send_psn;
struct ib_ud_header ud_header;
u8 header_buf[MLX4_IB_UD_HEADER_SIZE];
+ struct ib_qp *roce_v2_gsi;
};
enum {
@@ -115,7 +118,6 @@ static const __be32 mlx4_ib_opcode[] = {
[IB_WR_REG_MR] = cpu_to_be32(MLX4_OPCODE_FMR),
[IB_WR_MASKED_ATOMIC_CMP_AND_SWP] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_CS),
[IB_WR_MASKED_ATOMIC_FETCH_AND_ADD] = cpu_to_be32(MLX4_OPCODE_MASKED_ATOMIC_FA),
- [IB_WR_BIND_MW] = cpu_to_be32(MLX4_OPCODE_BIND_MW),
};
static struct mlx4_ib_sqp *to_msqp(struct mlx4_ib_qp *mqp)
@@ -154,7 +156,10 @@ static int is_sqp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
}
}
}
- return proxy_sqp;
+ if (proxy_sqp)
+ return 1;
+
+ return !!(qp->flags & MLX4_IB_ROCE_V2_GSI_QP);
}
/* used for INIT/CLOSE port logic */
@@ -796,11 +801,13 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
if (err)
goto err_mtt;
- qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof(u64), gfp);
+ qp->sq.wrid = kmalloc_array(qp->sq.wqe_cnt, sizeof(u64),
+ gfp | __GFP_NOWARN);
if (!qp->sq.wrid)
qp->sq.wrid = __vmalloc(qp->sq.wqe_cnt * sizeof(u64),
gfp, PAGE_KERNEL);
- qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof(u64), gfp);
+ qp->rq.wrid = kmalloc_array(qp->rq.wqe_cnt, sizeof(u64),
+ gfp | __GFP_NOWARN);
if (!qp->rq.wrid)
qp->rq.wrid = __vmalloc(qp->rq.wqe_cnt * sizeof(u64),
gfp, PAGE_KERNEL);
@@ -1099,9 +1106,9 @@ static u32 get_sqp_num(struct mlx4_ib_dev *dev, struct ib_qp_init_attr *attr)
return dev->dev->caps.qp1_proxy[attr->port_num - 1];
}
-struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
- struct ib_qp_init_attr *init_attr,
- struct ib_udata *udata)
+static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
+ struct ib_qp_init_attr *init_attr,
+ struct ib_udata *udata)
{
struct mlx4_ib_qp *qp = NULL;
int err;
@@ -1120,6 +1127,7 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
MLX4_IB_SRIOV_TUNNEL_QP |
MLX4_IB_SRIOV_SQP |
MLX4_IB_QP_NETIF |
+ MLX4_IB_QP_CREATE_ROCE_V2_GSI |
MLX4_IB_QP_CREATE_USE_GFP_NOIO))
return ERR_PTR(-EINVAL);
@@ -1128,15 +1136,21 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
return ERR_PTR(-EINVAL);
}
- if (init_attr->create_flags &&
- ((udata && init_attr->create_flags & ~(sup_u_create_flags)) ||
- ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP |
- MLX4_IB_QP_CREATE_USE_GFP_NOIO |
- MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK)) &&
- init_attr->qp_type != IB_QPT_UD) ||
- ((init_attr->create_flags & MLX4_IB_SRIOV_SQP) &&
- init_attr->qp_type > IB_QPT_GSI)))
- return ERR_PTR(-EINVAL);
+ if (init_attr->create_flags) {
+ if (udata && init_attr->create_flags & ~(sup_u_create_flags))
+ return ERR_PTR(-EINVAL);
+
+ if ((init_attr->create_flags & ~(MLX4_IB_SRIOV_SQP |
+ MLX4_IB_QP_CREATE_USE_GFP_NOIO |
+ MLX4_IB_QP_CREATE_ROCE_V2_GSI |
+ MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK) &&
+ init_attr->qp_type != IB_QPT_UD) ||
+ (init_attr->create_flags & MLX4_IB_SRIOV_SQP &&
+ init_attr->qp_type > IB_QPT_GSI) ||
+ (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI &&
+ init_attr->qp_type != IB_QPT_GSI))
+ return ERR_PTR(-EINVAL);
+ }
switch (init_attr->qp_type) {
case IB_QPT_XRC_TGT:
@@ -1173,19 +1187,29 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
case IB_QPT_SMI:
case IB_QPT_GSI:
{
+ int sqpn;
+
/* Userspace is not allowed to create special QPs: */
if (udata)
return ERR_PTR(-EINVAL);
+ if (init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI) {
+ int res = mlx4_qp_reserve_range(to_mdev(pd->device)->dev, 1, 1, &sqpn, 0);
+
+ if (res)
+ return ERR_PTR(res);
+ } else {
+ sqpn = get_sqp_num(to_mdev(pd->device), init_attr);
+ }
err = create_qp_common(to_mdev(pd->device), pd, init_attr, udata,
- get_sqp_num(to_mdev(pd->device), init_attr),
+ sqpn,
&qp, gfp);
if (err)
return ERR_PTR(err);
qp->port = init_attr->port_num;
- qp->ibqp.qp_num = init_attr->qp_type == IB_QPT_SMI ? 0 : 1;
-
+ qp->ibqp.qp_num = init_attr->qp_type == IB_QPT_SMI ? 0 :
+ init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI ? sqpn : 1;
break;
}
default:
@@ -1196,7 +1220,41 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
return &qp->ibqp;
}
-int mlx4_ib_destroy_qp(struct ib_qp *qp)
+struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
+ struct ib_qp_init_attr *init_attr,
+ struct ib_udata *udata) {
+ struct ib_device *device = pd ? pd->device : init_attr->xrcd->device;
+ struct ib_qp *ibqp;
+ struct mlx4_ib_dev *dev = to_mdev(device);
+
+ ibqp = _mlx4_ib_create_qp(pd, init_attr, udata);
+
+ if (!IS_ERR(ibqp) &&
+ (init_attr->qp_type == IB_QPT_GSI) &&
+ !(init_attr->create_flags & MLX4_IB_QP_CREATE_ROCE_V2_GSI)) {
+ struct mlx4_ib_sqp *sqp = to_msqp((to_mqp(ibqp)));
+ int is_eth = rdma_cap_eth_ah(&dev->ib_dev, init_attr->port_num);
+
+ if (is_eth &&
+ dev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ROCE_V1_V2) {
+ init_attr->create_flags |= MLX4_IB_QP_CREATE_ROCE_V2_GSI;
+ sqp->roce_v2_gsi = ib_create_qp(pd, init_attr);
+
+ if (IS_ERR(sqp->roce_v2_gsi)) {
+ pr_err("Failed to create GSI QP for RoCEv2 (%ld)\n", PTR_ERR(sqp->roce_v2_gsi));
+ sqp->roce_v2_gsi = NULL;
+ } else {
+ sqp = to_msqp(to_mqp(sqp->roce_v2_gsi));
+ sqp->qp.flags |= MLX4_IB_ROCE_V2_GSI_QP;
+ }
+
+ init_attr->create_flags &= ~MLX4_IB_QP_CREATE_ROCE_V2_GSI;
+ }
+ }
+ return ibqp;
+}
+
+static int _mlx4_ib_destroy_qp(struct ib_qp *qp)
{
struct mlx4_ib_dev *dev = to_mdev(qp->device);
struct mlx4_ib_qp *mqp = to_mqp(qp);
@@ -1225,6 +1283,20 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp)
return 0;
}
+int mlx4_ib_destroy_qp(struct ib_qp *qp)
+{
+ struct mlx4_ib_qp *mqp = to_mqp(qp);
+
+ if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
+ struct mlx4_ib_sqp *sqp = to_msqp(mqp);
+
+ if (sqp->roce_v2_gsi)
+ ib_destroy_qp(sqp->roce_v2_gsi);
+ }
+
+ return _mlx4_ib_destroy_qp(qp);
+}
+
static int to_mlx4_st(struct mlx4_ib_dev *dev, enum mlx4_ib_qp_type type)
{
switch (type) {
@@ -1507,6 +1579,24 @@ static int create_qp_lb_counter(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
return 0;
}
+enum {
+ MLX4_QPC_ROCE_MODE_1 = 0,
+ MLX4_QPC_ROCE_MODE_2 = 2,
+ MLX4_QPC_ROCE_MODE_UNDEFINED = 0xff
+};
+
+static u8 gid_type_to_qpc(enum ib_gid_type gid_type)
+{
+ switch (gid_type) {
+ case IB_GID_TYPE_ROCE:
+ return MLX4_QPC_ROCE_MODE_1;
+ case IB_GID_TYPE_ROCE_UDP_ENCAP:
+ return MLX4_QPC_ROCE_MODE_2;
+ default:
+ return MLX4_QPC_ROCE_MODE_UNDEFINED;
+ }
+}
+
static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
const struct ib_qp_attr *attr, int attr_mask,
enum ib_qp_state cur_state, enum ib_qp_state new_state)
@@ -1591,9 +1681,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
}
if (qp->ibqp.uobject)
- context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index);
+ context->usr_page = cpu_to_be32(
+ mlx4_to_hw_uar_index(dev->dev,
+ to_mucontext(ibqp->uobject->context)->uar.index));
else
- context->usr_page = cpu_to_be32(dev->priv_uar.index);
+ context->usr_page = cpu_to_be32(
+ mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index));
if (attr_mask & IB_QP_DEST_QPN)
context->remote_qpn = cpu_to_be32(attr->dest_qp_num);
@@ -1633,6 +1726,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
mlx4_ib_steer_qp_reg(dev, qp, 1);
steer_qp = 1;
}
+
+ if (ibqp->qp_type == IB_QPT_GSI) {
+ enum ib_gid_type gid_type = qp->flags & MLX4_IB_ROCE_V2_GSI_QP ?
+ IB_GID_TYPE_ROCE_UDP_ENCAP : IB_GID_TYPE_ROCE;
+ u8 qpc_roce_mode = gid_type_to_qpc(gid_type);
+
+ context->rlkey_roce_mode |= (qpc_roce_mode << 6);
+ }
}
if (attr_mask & IB_QP_PKEY_INDEX) {
@@ -1650,9 +1751,10 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
u16 vlan = 0xffff;
u8 smac[ETH_ALEN];
int status = 0;
+ int is_eth = rdma_cap_eth_ah(&dev->ib_dev, port_num) &&
+ attr->ah_attr.ah_flags & IB_AH_GRH;
- if (rdma_cap_eth_ah(&dev->ib_dev, port_num) &&
- attr->ah_attr.ah_flags & IB_AH_GRH) {
+ if (is_eth) {
int index = attr->ah_attr.grh.sgid_index;
status = ib_get_cached_gid(ibqp->device, port_num,
@@ -1674,6 +1776,18 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
optpar |= (MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH |
MLX4_QP_OPTPAR_SCHED_QUEUE);
+
+ if (is_eth &&
+ (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR)) {
+ u8 qpc_roce_mode = gid_type_to_qpc(gid_attr.gid_type);
+
+ if (qpc_roce_mode == MLX4_QPC_ROCE_MODE_UNDEFINED) {
+ err = -EINVAL;
+ goto out;
+ }
+ context->rlkey_roce_mode |= (qpc_roce_mode << 6);
+ }
+
}
if (attr_mask & IB_QP_TIMEOUT) {
@@ -1845,7 +1959,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
sqd_event = 0;
if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
- context->rlkey |= (1 << 4);
+ context->rlkey_roce_mode |= (1 << 4);
/*
* Before passing a kernel QP to the HW, make sure that the
@@ -2022,8 +2136,8 @@ out:
return err;
}
-int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
- int attr_mask, struct ib_udata *udata)
+static int _mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+ int attr_mask, struct ib_udata *udata)
{
struct mlx4_ib_dev *dev = to_mdev(ibqp->device);
struct mlx4_ib_qp *qp = to_mqp(ibqp);
@@ -2126,6 +2240,27 @@ out:
return err;
}
+int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+ int attr_mask, struct ib_udata *udata)
+{
+ struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+ int ret;
+
+ ret = _mlx4_ib_modify_qp(ibqp, attr, attr_mask, udata);
+
+ if (mqp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
+ struct mlx4_ib_sqp *sqp = to_msqp(mqp);
+ int err = 0;
+
+ if (sqp->roce_v2_gsi)
+ err = ib_modify_qp(sqp->roce_v2_gsi, attr, attr_mask);
+ if (err)
+ pr_err("Failed to modify GSI QP for RoCEv2 (%d)\n",
+ err);
+ }
+ return ret;
+}
+
static int vf_get_qp0_qkey(struct mlx4_dev *dev, int qpn, u32 *qkey)
{
int i;
@@ -2168,7 +2303,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER)
send_size += sizeof (struct mlx4_ib_tunnel_header);
- ib_ud_header_init(send_size, 1, 0, 0, 0, 0, &sqp->ud_header);
+ ib_ud_header_init(send_size, 1, 0, 0, 0, 0, 0, 0, &sqp->ud_header);
if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_SMI_OWNER) {
sqp->ud_header.lrh.service_level =
@@ -2252,16 +2387,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp,
return 0;
}
-static void mlx4_u64_to_smac(u8 *dst_mac, u64 src_mac)
-{
- int i;
-
- for (i = ETH_ALEN; i; i--) {
- dst_mac[i - 1] = src_mac & 0xff;
- src_mac >>= 8;
- }
-}
-
+#define MLX4_ROCEV2_QP1_SPORT 0xC000
static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
void *wqe, unsigned *mlx_seg_len)
{
@@ -2281,6 +2407,8 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
bool is_eth;
bool is_vlan = false;
bool is_grh;
+ bool is_udp = false;
+ int ip_version = 0;
send_size = 0;
for (i = 0; i < wr->wr.num_sge; ++i)
@@ -2289,6 +2417,8 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET;
is_grh = mlx4_ib_ah_grh_present(ah);
if (is_eth) {
+ struct ib_gid_attr gid_attr;
+
if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
/* When multi-function is enabled, the ib_core gid
* indexes don't necessarily match the hw ones, so
@@ -2302,19 +2432,35 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
err = ib_get_cached_gid(ib_dev,
be32_to_cpu(ah->av.ib.port_pd) >> 24,
ah->av.ib.gid_index, &sgid,
- NULL);
- if (!err && !memcmp(&sgid, &zgid, sizeof(sgid)))
- err = -ENOENT;
- if (err)
+ &gid_attr);
+ if (!err) {
+ if (gid_attr.ndev)
+ dev_put(gid_attr.ndev);
+ if (!memcmp(&sgid, &zgid, sizeof(sgid)))
+ err = -ENOENT;
+ }
+ if (!err) {
+ is_udp = gid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP;
+ if (is_udp) {
+ if (ipv6_addr_v4mapped((struct in6_addr *)&sgid))
+ ip_version = 4;
+ else
+ ip_version = 6;
+ is_grh = false;
+ }
+ } else {
return err;
+ }
}
-
if (ah->av.eth.vlan != cpu_to_be16(0xffff)) {
vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
is_vlan = 1;
}
}
- ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
+ err = ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh,
+ ip_version, is_udp, 0, &sqp->ud_header);
+ if (err)
+ return err;
if (!is_eth) {
sqp->ud_header.lrh.service_level =
@@ -2323,7 +2469,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.ib.g_slid & 0x7f);
}
- if (is_grh) {
+ if (is_grh || (ip_version == 6)) {
sqp->ud_header.grh.traffic_class =
(be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff;
sqp->ud_header.grh.flow_label =
@@ -2352,6 +2498,25 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
ah->av.ib.dgid, 16);
}
+ if (ip_version == 4) {
+ sqp->ud_header.ip4.tos =
+ (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff;
+ sqp->ud_header.ip4.id = 0;
+ sqp->ud_header.ip4.frag_off = htons(IP_DF);
+ sqp->ud_header.ip4.ttl = ah->av.eth.hop_limit;
+
+ memcpy(&sqp->ud_header.ip4.saddr,
+ sgid.raw + 12, 4);
+ memcpy(&sqp->ud_header.ip4.daddr, ah->av.ib.dgid + 12, 4);
+ sqp->ud_header.ip4.check = ib_ud_ip4_csum(&sqp->ud_header);
+ }
+
+ if (is_udp) {
+ sqp->ud_header.udp.dport = htons(ROCE_V2_UDP_DPORT);
+ sqp->ud_header.udp.sport = htons(MLX4_ROCEV2_QP1_SPORT);
+ sqp->ud_header.udp.csum = 0;
+ }
+
mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
if (!is_eth) {
@@ -2380,34 +2545,27 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_ud_wr *wr,
if (is_eth) {
struct in6_addr in6;
-
+ u16 ether_type;
u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
+ ether_type = (!is_udp) ? MLX4_IB_IBOE_ETHERTYPE :
+ (ip_version == 4 ? ETH_P_IP : ETH_P_IPV6);
+
mlx->sched_prio = cpu_to_be16(pcp);
+ ether_addr_copy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac);
memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
- /* FIXME: cache smac value? */
memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
memcpy(&in6, sgid.raw, sizeof(in6));
- if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
- u64 mac = atomic64_read(&to_mdev(ib_dev)->iboe.mac[sqp->qp.port - 1]);
- u8 smac[ETH_ALEN];
-
- mlx4_u64_to_smac(smac, mac);
- memcpy(sqp->ud_header.eth.smac_h, smac, ETH_ALEN);
- } else {
- /* use the src mac of the tunnel */
- memcpy(sqp->ud_header.eth.smac_h, ah->av.eth.s_mac, ETH_ALEN);
- }
if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
if (!is_vlan) {
- sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE);
+ sqp->ud_header.eth.type = cpu_to_be16(ether_type);
} else {
- sqp->ud_header.vlan.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE);
+ sqp->ud_header.vlan.type = cpu_to_be16(ether_type);
sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp);
}
} else {
@@ -2528,25 +2686,6 @@ static void set_reg_seg(struct mlx4_wqe_fmr_seg *fseg,
fseg->reserved[1] = 0;
}
-static void set_bind_seg(struct mlx4_wqe_bind_seg *bseg,
- struct ib_bind_mw_wr *wr)
-{
- bseg->flags1 =
- convert_access(wr->bind_info.mw_access_flags) &
- cpu_to_be32(MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_READ |
- MLX4_WQE_FMR_AND_BIND_PERM_REMOTE_WRITE |
- MLX4_WQE_FMR_AND_BIND_PERM_ATOMIC);
- bseg->flags2 = 0;
- if (wr->mw->type == IB_MW_TYPE_2)
- bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_TYPE_2);
- if (wr->bind_info.mw_access_flags & IB_ZERO_BASED)
- bseg->flags2 |= cpu_to_be32(MLX4_WQE_BIND_ZERO_BASED);
- bseg->new_rkey = cpu_to_be32(wr->rkey);
- bseg->lkey = cpu_to_be32(wr->bind_info.mr->lkey);
- bseg->addr = cpu_to_be64(wr->bind_info.addr);
- bseg->length = cpu_to_be64(wr->bind_info.length);
-}
-
static void set_local_inv_seg(struct mlx4_wqe_local_inval_seg *iseg, u32 rkey)
{
memset(iseg, 0, sizeof(*iseg));
@@ -2766,6 +2905,29 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
int i;
struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
+ if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) {
+ struct mlx4_ib_sqp *sqp = to_msqp(qp);
+
+ if (sqp->roce_v2_gsi) {
+ struct mlx4_ib_ah *ah = to_mah(ud_wr(wr)->ah);
+ struct ib_gid_attr gid_attr;
+ union ib_gid gid;
+
+ if (!ib_get_cached_gid(ibqp->device,
+ be32_to_cpu(ah->av.ib.port_pd) >> 24,
+ ah->av.ib.gid_index, &gid,
+ &gid_attr)) {
+ if (gid_attr.ndev)
+ dev_put(gid_attr.ndev);
+ qp = (gid_attr.gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ?
+ to_mqp(sqp->roce_v2_gsi) : qp;
+ } else {
+ pr_err("Failed to get gid at index %d. RoCEv2 will not work properly\n",
+ ah->av.ib.gid_index);
+ }
+ }
+ }
+
spin_lock_irqsave(&qp->sq.lock, flags);
if (mdev->dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR) {
err = -EIO;
@@ -2867,13 +3029,6 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
size += sizeof(struct mlx4_wqe_fmr_seg) / 16;
break;
- case IB_WR_BIND_MW:
- ctrl->srcrb_flags |=
- cpu_to_be32(MLX4_WQE_CTRL_STRONG_ORDER);
- set_bind_seg(wqe, bind_mw_wr(wr));
- wqe += sizeof(struct mlx4_wqe_bind_seg);
- size += sizeof(struct mlx4_wqe_bind_seg) / 16;
- break;
default:
/* No extra segments required for sends */
break;
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index c394376eb..0597f3eef 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -171,7 +171,8 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
if (err)
goto err_mtt;
- srq->wrid = kmalloc(srq->msrq.max * sizeof (u64), GFP_KERNEL);
+ srq->wrid = kmalloc_array(srq->msrq.max, sizeof(u64),
+ GFP_KERNEL | __GFP_NOWARN);
if (!srq->wrid) {
srq->wrid = __vmalloc(srq->msrq.max * sizeof(u64),
GFP_KERNEL, PAGE_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 66080580e..745efa4cf 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -32,8 +32,10 @@
#include "mlx5_ib.h"
-struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
- struct mlx5_ib_ah *ah)
+static struct ib_ah *create_ib_ah(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_ah *ah,
+ struct ib_ah_attr *ah_attr,
+ enum rdma_link_layer ll)
{
if (ah_attr->ah_flags & IB_AH_GRH) {
memcpy(ah->av.rgid, &ah_attr->grh.dgid, 16);
@@ -44,9 +46,20 @@ struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
ah->av.tclass = ah_attr->grh.traffic_class;
}
- ah->av.rlid = cpu_to_be16(ah_attr->dlid);
- ah->av.fl_mlid = ah_attr->src_path_bits & 0x7f;
- ah->av.stat_rate_sl = (ah_attr->static_rate << 4) | (ah_attr->sl & 0xf);
+ ah->av.stat_rate_sl = (ah_attr->static_rate << 4);
+
+ if (ll == IB_LINK_LAYER_ETHERNET) {
+ memcpy(ah->av.rmac, ah_attr->dmac, sizeof(ah_attr->dmac));
+ ah->av.udp_sport =
+ mlx5_get_roce_udp_sport(dev,
+ ah_attr->port_num,
+ ah_attr->grh.sgid_index);
+ ah->av.stat_rate_sl |= (ah_attr->sl & 0x7) << 1;
+ } else {
+ ah->av.rlid = cpu_to_be16(ah_attr->dlid);
+ ah->av.fl_mlid = ah_attr->src_path_bits & 0x7f;
+ ah->av.stat_rate_sl |= (ah_attr->sl & 0xf);
+ }
return &ah->ibah;
}
@@ -54,12 +67,19 @@ struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
{
struct mlx5_ib_ah *ah;
+ struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ enum rdma_link_layer ll;
+
+ ll = pd->device->get_link_layer(pd->device, ah_attr->port_num);
+
+ if (ll == IB_LINK_LAYER_ETHERNET && !(ah_attr->ah_flags & IB_AH_GRH))
+ return ERR_PTR(-EINVAL);
ah = kzalloc(sizeof(*ah), GFP_ATOMIC);
if (!ah)
return ERR_PTR(-ENOMEM);
- return create_ib_ah(ah_attr, ah); /* never fails */
+ return create_ib_ah(dev, ah, ah_attr, ll); /* never fails */
}
int mlx5_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 92ddae101..fd1de31e0 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -154,9 +154,6 @@ static void handle_good_req(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
wc->opcode = IB_WC_MASKED_FETCH_ADD;
wc->byte_len = 8;
break;
- case MLX5_OPCODE_BIND_MW:
- wc->opcode = IB_WC_BIND_MW;
- break;
case MLX5_OPCODE_UMR:
wc->opcode = get_umr_comp(wq, idx);
break;
@@ -171,6 +168,7 @@ enum {
static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
struct mlx5_ib_qp *qp)
{
+ enum rdma_link_layer ll = rdma_port_get_link_layer(qp->ibqp.device, 1);
struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.device);
struct mlx5_ib_srq *srq;
struct mlx5_ib_wq *wq;
@@ -236,6 +234,22 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
} else {
wc->pkey_index = 0;
}
+
+ if (ll != IB_LINK_LAYER_ETHERNET)
+ return;
+
+ switch (wc->sl & 0x3) {
+ case MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH:
+ wc->network_hdr_type = RDMA_NETWORK_IB;
+ break;
+ case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV6:
+ wc->network_hdr_type = RDMA_NETWORK_IPV6;
+ break;
+ case MLX5_CQE_ROCE_L3_HEADER_TYPE_IPV4:
+ wc->network_hdr_type = RDMA_NETWORK_IPV4;
+ break;
+ }
+ wc->wc_flags |= IB_WC_WITH_NETWORK_HDR_TYPE;
}
static void dump_cqe(struct mlx5_ib_dev *dev, struct mlx5_err_cqe *cqe)
@@ -760,12 +774,12 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
int eqn;
int err;
- if (attr->flags)
- return ERR_PTR(-EINVAL);
-
if (entries < 0)
return ERR_PTR(-EINVAL);
+ if (check_cq_create_flags(attr->flags))
+ return ERR_PTR(-EOPNOTSUPP);
+
entries = roundup_pow_of_two(entries + 1);
if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))
return ERR_PTR(-EINVAL);
@@ -779,6 +793,7 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
spin_lock_init(&cq->lock);
cq->resize_buf = NULL;
cq->resize_umem = NULL;
+ cq->create_flags = attr->flags;
if (context) {
err = create_cq_user(dev, udata, context, cq, entries,
@@ -796,6 +811,10 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
cq->cqe_size = cqe_size;
cqb->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;
+
+ if (cq->create_flags & IB_CQ_FLAGS_IGNORE_OVERRUN)
+ cqb->ctx.cqe_sz_flags |= (1 << 1);
+
cqb->ctx.log_sz_usr_page = cpu_to_be32((ilog2(entries) << 24) | index);
err = mlx5_vector2eqn(dev->mdev, vector, &eqn, &irqn);
if (err)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c4e091528..03c418ccb 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -40,9 +40,14 @@
#include <linux/io-mapping.h>
#include <linux/sched.h>
#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
#include <linux/mlx5/vport.h>
#include <rdma/ib_smi.h>
#include <rdma/ib_umem.h>
+#include <linux/in.h>
+#include <linux/etherdevice.h>
+#include <linux/mlx5/fs.h>
#include "user.h"
#include "mlx5_ib.h"
@@ -63,12 +68,14 @@ static char mlx5_version[] =
DRIVER_NAME ": Mellanox Connect-IB Infiniband driver v"
DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
+enum {
+ MLX5_ATOMIC_SIZE_QP_8BYTES = 1 << 3,
+};
+
static enum rdma_link_layer
-mlx5_ib_port_link_layer(struct ib_device *device)
+mlx5_port_type_cap_to_rdma_ll(int port_type_cap)
{
- struct mlx5_ib_dev *dev = to_mdev(device);
-
- switch (MLX5_CAP_GEN(dev->mdev, port_type)) {
+ switch (port_type_cap) {
case MLX5_CAP_PORT_TYPE_IB:
return IB_LINK_LAYER_INFINIBAND;
case MLX5_CAP_PORT_TYPE_ETH:
@@ -78,6 +85,202 @@ mlx5_ib_port_link_layer(struct ib_device *device)
}
}
+static enum rdma_link_layer
+mlx5_ib_port_link_layer(struct ib_device *device, u8 port_num)
+{
+ struct mlx5_ib_dev *dev = to_mdev(device);
+ int port_type_cap = MLX5_CAP_GEN(dev->mdev, port_type);
+
+ return mlx5_port_type_cap_to_rdma_ll(port_type_cap);
+}
+
+static int mlx5_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+ struct mlx5_ib_dev *ibdev = container_of(this, struct mlx5_ib_dev,
+ roce.nb);
+
+ if ((event != NETDEV_UNREGISTER) && (event != NETDEV_REGISTER))
+ return NOTIFY_DONE;
+
+ write_lock(&ibdev->roce.netdev_lock);
+ if (ndev->dev.parent == &ibdev->mdev->pdev->dev)
+ ibdev->roce.netdev = (event == NETDEV_UNREGISTER) ? NULL : ndev;
+ write_unlock(&ibdev->roce.netdev_lock);
+
+ return NOTIFY_DONE;
+}
+
+static struct net_device *mlx5_ib_get_netdev(struct ib_device *device,
+ u8 port_num)
+{
+ struct mlx5_ib_dev *ibdev = to_mdev(device);
+ struct net_device *ndev;
+
+ /* Ensure ndev does not disappear before we invoke dev_hold()
+ */
+ read_lock(&ibdev->roce.netdev_lock);
+ ndev = ibdev->roce.netdev;
+ if (ndev)
+ dev_hold(ndev);
+ read_unlock(&ibdev->roce.netdev_lock);
+
+ return ndev;
+}
+
+static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
+ struct ib_port_attr *props)
+{
+ struct mlx5_ib_dev *dev = to_mdev(device);
+ struct net_device *ndev;
+ enum ib_mtu ndev_ib_mtu;
+ u16 qkey_viol_cntr;
+
+ memset(props, 0, sizeof(*props));
+
+ props->port_cap_flags |= IB_PORT_CM_SUP;
+ props->port_cap_flags |= IB_PORT_IP_BASED_GIDS;
+
+ props->gid_tbl_len = MLX5_CAP_ROCE(dev->mdev,
+ roce_address_table_size);
+ props->max_mtu = IB_MTU_4096;
+ props->max_msg_sz = 1 << MLX5_CAP_GEN(dev->mdev, log_max_msg);
+ props->pkey_tbl_len = 1;
+ props->state = IB_PORT_DOWN;
+ props->phys_state = 3;
+
+ mlx5_query_nic_vport_qkey_viol_cntr(dev->mdev, &qkey_viol_cntr);
+ props->qkey_viol_cntr = qkey_viol_cntr;
+
+ ndev = mlx5_ib_get_netdev(device, port_num);
+ if (!ndev)
+ return 0;
+
+ if (netif_running(ndev) && netif_carrier_ok(ndev)) {
+ props->state = IB_PORT_ACTIVE;
+ props->phys_state = 5;
+ }
+
+ ndev_ib_mtu = iboe_get_mtu(ndev->mtu);
+
+ dev_put(ndev);
+
+ props->active_mtu = min(props->max_mtu, ndev_ib_mtu);
+
+ props->active_width = IB_WIDTH_4X; /* TODO */
+ props->active_speed = IB_SPEED_QDR; /* TODO */
+
+ return 0;
+}
+
+static void ib_gid_to_mlx5_roce_addr(const union ib_gid *gid,
+ const struct ib_gid_attr *attr,
+ void *mlx5_addr)
+{
+#define MLX5_SET_RA(p, f, v) MLX5_SET(roce_addr_layout, p, f, v)
+ char *mlx5_addr_l3_addr = MLX5_ADDR_OF(roce_addr_layout, mlx5_addr,
+ source_l3_address);
+ void *mlx5_addr_mac = MLX5_ADDR_OF(roce_addr_layout, mlx5_addr,
+ source_mac_47_32);
+
+ if (!gid)
+ return;
+
+ ether_addr_copy(mlx5_addr_mac, attr->ndev->dev_addr);
+
+ if (is_vlan_dev(attr->ndev)) {
+ MLX5_SET_RA(mlx5_addr, vlan_valid, 1);
+ MLX5_SET_RA(mlx5_addr, vlan_id, vlan_dev_vlan_id(attr->ndev));
+ }
+
+ switch (attr->gid_type) {
+ case IB_GID_TYPE_IB:
+ MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_1);
+ break;
+ case IB_GID_TYPE_ROCE_UDP_ENCAP:
+ MLX5_SET_RA(mlx5_addr, roce_version, MLX5_ROCE_VERSION_2);
+ break;
+
+ default:
+ WARN_ON(true);
+ }
+
+ if (attr->gid_type != IB_GID_TYPE_IB) {
+ if (ipv6_addr_v4mapped((void *)gid))
+ MLX5_SET_RA(mlx5_addr, roce_l3_type,
+ MLX5_ROCE_L3_TYPE_IPV4);
+ else
+ MLX5_SET_RA(mlx5_addr, roce_l3_type,
+ MLX5_ROCE_L3_TYPE_IPV6);
+ }
+
+ if ((attr->gid_type == IB_GID_TYPE_IB) ||
+ !ipv6_addr_v4mapped((void *)gid))
+ memcpy(mlx5_addr_l3_addr, gid, sizeof(*gid));
+ else
+ memcpy(&mlx5_addr_l3_addr[12], &gid->raw[12], 4);
+}
+
+static int set_roce_addr(struct ib_device *device, u8 port_num,
+ unsigned int index,
+ const union ib_gid *gid,
+ const struct ib_gid_attr *attr)
+{
+ struct mlx5_ib_dev *dev = to_mdev(device);
+ u32 in[MLX5_ST_SZ_DW(set_roce_address_in)];
+ u32 out[MLX5_ST_SZ_DW(set_roce_address_out)];
+ void *in_addr = MLX5_ADDR_OF(set_roce_address_in, in, roce_address);
+ enum rdma_link_layer ll = mlx5_ib_port_link_layer(device, port_num);
+
+ if (ll != IB_LINK_LAYER_ETHERNET)
+ return -EINVAL;
+
+ memset(in, 0, sizeof(in));
+
+ ib_gid_to_mlx5_roce_addr(gid, attr, in_addr);
+
+ MLX5_SET(set_roce_address_in, in, roce_address_index, index);
+ MLX5_SET(set_roce_address_in, in, opcode, MLX5_CMD_OP_SET_ROCE_ADDRESS);
+
+ memset(out, 0, sizeof(out));
+ return mlx5_cmd_exec(dev->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_ib_add_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, const union ib_gid *gid,
+ const struct ib_gid_attr *attr,
+ __always_unused void **context)
+{
+ return set_roce_addr(device, port_num, index, gid, attr);
+}
+
+static int mlx5_ib_del_gid(struct ib_device *device, u8 port_num,
+ unsigned int index, __always_unused void **context)
+{
+ return set_roce_addr(device, port_num, index, NULL, NULL);
+}
+
+__be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
+ int index)
+{
+ struct ib_gid_attr attr;
+ union ib_gid gid;
+
+ if (ib_get_cached_gid(&dev->ib_dev, port_num, index, &gid, &attr))
+ return 0;
+
+ if (!attr.ndev)
+ return 0;
+
+ dev_put(attr.ndev);
+
+ if (attr.gid_type != IB_GID_TYPE_ROCE_UDP_ENCAP)
+ return 0;
+
+ return cpu_to_be16(MLX5_CAP_ROCE(dev->mdev, r_roce_min_src_udp_port));
+}
+
static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
{
return !dev->mdev->issi;
@@ -94,13 +297,35 @@ static int mlx5_get_vport_access_method(struct ib_device *ibdev)
if (mlx5_use_mad_ifc(to_mdev(ibdev)))
return MLX5_VPORT_ACCESS_METHOD_MAD;
- if (mlx5_ib_port_link_layer(ibdev) ==
+ if (mlx5_ib_port_link_layer(ibdev, 1) ==
IB_LINK_LAYER_ETHERNET)
return MLX5_VPORT_ACCESS_METHOD_NIC;
return MLX5_VPORT_ACCESS_METHOD_HCA;
}
+static void get_atomic_caps(struct mlx5_ib_dev *dev,
+ struct ib_device_attr *props)
+{
+ u8 tmp;
+ u8 atomic_operations = MLX5_CAP_ATOMIC(dev->mdev, atomic_operations);
+ u8 atomic_size_qp = MLX5_CAP_ATOMIC(dev->mdev, atomic_size_qp);
+ u8 atomic_req_8B_endianness_mode =
+ MLX5_CAP_ATOMIC(dev->mdev, atomic_req_8B_endianess_mode);
+
+ /* Check if HW supports 8 bytes standard atomic operations and capable
+ * of host endianness respond
+ */
+ tmp = MLX5_ATOMIC_OPS_CMP_SWAP | MLX5_ATOMIC_OPS_FETCH_ADD;
+ if (((atomic_operations & tmp) == tmp) &&
+ (atomic_size_qp & MLX5_ATOMIC_SIZE_QP_8BYTES) &&
+ (atomic_req_8B_endianness_mode)) {
+ props->atomic_cap = IB_ATOMIC_HCA;
+ } else {
+ props->atomic_cap = IB_ATOMIC_NONE;
+ }
+}
+
static int mlx5_query_system_image_guid(struct ib_device *ibdev,
__be64 *sys_image_guid)
{
@@ -116,13 +341,21 @@ static int mlx5_query_system_image_guid(struct ib_device *ibdev,
case MLX5_VPORT_ACCESS_METHOD_HCA:
err = mlx5_query_hca_vport_system_image_guid(mdev, &tmp);
- if (!err)
- *sys_image_guid = cpu_to_be64(tmp);
- return err;
+ break;
+
+ case MLX5_VPORT_ACCESS_METHOD_NIC:
+ err = mlx5_query_nic_vport_system_image_guid(mdev, &tmp);
+ break;
default:
return -EINVAL;
}
+
+ if (!err)
+ *sys_image_guid = cpu_to_be64(tmp);
+
+ return err;
+
}
static int mlx5_query_max_pkeys(struct ib_device *ibdev,
@@ -176,13 +409,20 @@ static int mlx5_query_node_guid(struct mlx5_ib_dev *dev,
case MLX5_VPORT_ACCESS_METHOD_HCA:
err = mlx5_query_hca_vport_node_guid(dev->mdev, &tmp);
- if (!err)
- *node_guid = cpu_to_be64(tmp);
- return err;
+ break;
+
+ case MLX5_VPORT_ACCESS_METHOD_NIC:
+ err = mlx5_query_nic_vport_node_guid(dev->mdev, &tmp);
+ break;
default:
return -EINVAL;
}
+
+ if (!err)
+ *node_guid = cpu_to_be64(tmp);
+
+ return err;
}
struct mlx5_reg_node_desc {
@@ -260,6 +500,10 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
if (MLX5_CAP_GEN(mdev, block_lb_mc))
props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+ if (MLX5_CAP_GEN(dev->mdev, eth_net_offloads) &&
+ (MLX5_CAP_ETH(dev->mdev, csum_cap)))
+ props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
+
props->vendor_part_id = mdev->pdev->device;
props->hw_ver = mdev->pdev->revision;
@@ -286,13 +530,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->max_res_rd_atom = props->max_qp_rd_atom * props->max_qp;
props->max_srq_sge = max_rq_sg - 1;
props->max_fast_reg_page_list_len = (unsigned int)-1;
- props->atomic_cap = IB_ATOMIC_NONE;
+ get_atomic_caps(dev, props);
props->masked_atomic_cap = IB_ATOMIC_NONE;
props->max_mcast_grp = 1 << MLX5_CAP_GEN(mdev, log_max_mcg);
props->max_mcast_qp_attach = MLX5_CAP_GEN(mdev, max_qp_mcg);
props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
props->max_mcast_grp;
props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */
+ props->hca_core_clock = MLX5_CAP_GEN(mdev, device_frequency_khz);
+ props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;
#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
if (MLX5_CAP_GEN(mdev, pg))
@@ -300,6 +546,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->odp_caps = dev->odp_caps;
#endif
+ if (MLX5_CAP_GEN(mdev, cd))
+ props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL;
+
return 0;
}
@@ -480,6 +729,9 @@ int mlx5_ib_query_port(struct ib_device *ibdev, u8 port,
case MLX5_VPORT_ACCESS_METHOD_HCA:
return mlx5_query_hca_port(ibdev, port, props);
+ case MLX5_VPORT_ACCESS_METHOD_NIC:
+ return mlx5_query_port_roce(ibdev, port, props);
+
default:
return -EINVAL;
}
@@ -580,8 +832,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
struct ib_udata *udata)
{
struct mlx5_ib_dev *dev = to_mdev(ibdev);
- struct mlx5_ib_alloc_ucontext_req_v2 req;
- struct mlx5_ib_alloc_ucontext_resp resp;
+ struct mlx5_ib_alloc_ucontext_req_v2 req = {};
+ struct mlx5_ib_alloc_ucontext_resp resp = {};
struct mlx5_ib_ucontext *context;
struct mlx5_uuar_info *uuari;
struct mlx5_uar *uars;
@@ -592,24 +844,28 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
int err;
int i;
size_t reqlen;
+ size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
+ max_cqe_version);
if (!dev->ib_active)
return ERR_PTR(-EAGAIN);
- memset(&req, 0, sizeof(req));
+ if (udata->inlen < sizeof(struct ib_uverbs_cmd_hdr))
+ return ERR_PTR(-EINVAL);
+
reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
ver = 0;
- else if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req_v2))
+ else if (reqlen >= min_req_v2)
ver = 2;
else
return ERR_PTR(-EINVAL);
- err = ib_copy_from_udata(&req, udata, reqlen);
+ err = ib_copy_from_udata(&req, udata, min(reqlen, sizeof(req)));
if (err)
return ERR_PTR(err);
- if (req.flags || req.reserved)
+ if (req.flags)
return ERR_PTR(-EINVAL);
if (req.total_num_uuars > MLX5_MAX_UUARS)
@@ -618,6 +874,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
if (req.total_num_uuars == 0)
return ERR_PTR(-EINVAL);
+ if (req.comp_mask || req.reserved0 || req.reserved1 || req.reserved2)
+ return ERR_PTR(-EOPNOTSUPP);
+
+ if (reqlen > sizeof(req) &&
+ !ib_is_udata_cleared(udata, sizeof(req),
+ reqlen - sizeof(req)))
+ return ERR_PTR(-EOPNOTSUPP);
+
req.total_num_uuars = ALIGN(req.total_num_uuars,
MLX5_NON_FP_BF_REGS_PER_PAGE);
if (req.num_low_latency_uuars > req.total_num_uuars - 1)
@@ -633,6 +897,11 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
resp.max_send_wqebb = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
resp.max_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz);
resp.max_srq_recv_wr = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
+ resp.cqe_version = min_t(__u8,
+ (__u8)MLX5_CAP_GEN(dev->mdev, cqe_version),
+ req.max_cqe_version);
+ resp.response_length = min(offsetof(typeof(resp), response_length) +
+ sizeof(resp.response_length), udata->outlen);
context = kzalloc(sizeof(*context), GFP_KERNEL);
if (!context)
@@ -678,22 +947,49 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
#endif
+ if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain)) {
+ err = mlx5_core_alloc_transport_domain(dev->mdev,
+ &context->tdn);
+ if (err)
+ goto out_uars;
+ }
+
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);
resp.tot_uuars = req.total_num_uuars;
resp.num_ports = MLX5_CAP_GEN(dev->mdev, num_ports);
- err = ib_copy_to_udata(udata, &resp,
- sizeof(resp) - sizeof(resp.reserved));
+
+ if (field_avail(typeof(resp), cqe_version, udata->outlen))
+ resp.response_length += sizeof(resp.cqe_version);
+
+ if (field_avail(typeof(resp), hca_core_clock_offset, udata->outlen)) {
+ resp.comp_mask |=
+ MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET;
+ resp.hca_core_clock_offset =
+ offsetof(struct mlx5_init_seg, internal_timer_h) %
+ PAGE_SIZE;
+ resp.response_length += sizeof(resp.hca_core_clock_offset) +
+ sizeof(resp.reserved2) +
+ sizeof(resp.reserved3);
+ }
+
+ err = ib_copy_to_udata(udata, &resp, resp.response_length);
if (err)
- goto out_uars;
+ goto out_td;
uuari->ver = ver;
uuari->num_low_latency_uuars = req.num_low_latency_uuars;
uuari->uars = uars;
uuari->num_uars = num_uars;
+ context->cqe_version = resp.cqe_version;
+
return &context->ibucontext;
+out_td:
+ if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
+ mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
+
out_uars:
for (i--; i >= 0; i--)
mlx5_cmd_free_uar(dev->mdev, uars[i].index);
@@ -718,6 +1014,9 @@ static int mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
struct mlx5_uuar_info *uuari = &context->uuari;
int i;
+ if (MLX5_CAP_GEN(dev->mdev, log_max_transport_domain))
+ mlx5_core_dealloc_transport_domain(dev->mdev, context->tdn);
+
for (i = 0; i < uuari->num_uars; i++) {
if (mlx5_cmd_free_uar(dev->mdev, uuari->uars[i].index))
mlx5_ib_warn(dev, "failed to free UAR 0x%x\n", uuari->uars[i].index);
@@ -787,6 +1086,30 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
case MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES:
return -ENOSYS;
+ case MLX5_IB_MMAP_CORE_CLOCK:
+ if (vma->vm_end - vma->vm_start != PAGE_SIZE)
+ return -EINVAL;
+
+ if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+ return -EPERM;
+
+ /* Don't expose to user-space information it shouldn't have */
+ if (PAGE_SIZE > 4096)
+ return -EOPNOTSUPP;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+ pfn = (dev->mdev->iseg_base +
+ offsetof(struct mlx5_init_seg, internal_timer_h)) >>
+ PAGE_SHIFT;
+ if (io_remap_pfn_range(vma, vma->vm_start, pfn,
+ PAGE_SIZE, vma->vm_page_prot))
+ return -EAGAIN;
+
+ mlx5_ib_dbg(dev, "mapped internal timer at 0x%lx, PA 0x%llx\n",
+ vma->vm_start,
+ (unsigned long long)pfn << PAGE_SHIFT);
+ break;
+
default:
return -EINVAL;
}
@@ -835,6 +1158,457 @@ static int mlx5_ib_dealloc_pd(struct ib_pd *pd)
return 0;
}
+static bool outer_header_zero(u32 *match_criteria)
+{
+ int size = MLX5_ST_SZ_BYTES(fte_match_param);
+ char *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_criteria,
+ outer_headers);
+
+ return outer_headers_c[0] == 0 && !memcmp(outer_headers_c,
+ outer_headers_c + 1,
+ size - 1);
+}
+
+static int parse_flow_attr(u32 *match_c, u32 *match_v,
+ union ib_flow_spec *ib_spec)
+{
+ void *outer_headers_c = MLX5_ADDR_OF(fte_match_param, match_c,
+ outer_headers);
+ void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
+ outer_headers);
+ switch (ib_spec->type) {
+ case IB_FLOW_SPEC_ETH:
+ if (ib_spec->size != sizeof(ib_spec->eth))
+ return -EINVAL;
+
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ dmac_47_16),
+ ib_spec->eth.mask.dst_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ dmac_47_16),
+ ib_spec->eth.val.dst_mac);
+
+ if (ib_spec->eth.mask.vlan_tag) {
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ vlan_tag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ vlan_tag, 1);
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ first_vid, ntohs(ib_spec->eth.mask.vlan_tag));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ first_vid, ntohs(ib_spec->eth.val.vlan_tag));
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ first_cfi,
+ ntohs(ib_spec->eth.mask.vlan_tag) >> 12);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ first_cfi,
+ ntohs(ib_spec->eth.val.vlan_tag) >> 12);
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ first_prio,
+ ntohs(ib_spec->eth.mask.vlan_tag) >> 13);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ first_prio,
+ ntohs(ib_spec->eth.val.vlan_tag) >> 13);
+ }
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ ethertype, ntohs(ib_spec->eth.mask.ether_type));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ ethertype, ntohs(ib_spec->eth.val.ether_type));
+ break;
+ case IB_FLOW_SPEC_IPV4:
+ if (ib_spec->size != sizeof(ib_spec->ipv4))
+ return -EINVAL;
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
+ ethertype, 0xffff);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+ ethertype, ETH_P_IP);
+
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4),
+ &ib_spec->ipv4.mask.src_ip,
+ sizeof(ib_spec->ipv4.mask.src_ip));
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ src_ipv4_src_ipv6.ipv4_layout.ipv4),
+ &ib_spec->ipv4.val.src_ip,
+ sizeof(ib_spec->ipv4.val.src_ip));
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+ &ib_spec->ipv4.mask.dst_ip,
+ sizeof(ib_spec->ipv4.mask.dst_ip));
+ memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+ &ib_spec->ipv4.val.dst_ip,
+ sizeof(ib_spec->ipv4.val.dst_ip));
+ break;
+ case IB_FLOW_SPEC_TCP:
+ if (ib_spec->size != sizeof(ib_spec->tcp_udp))
+ return -EINVAL;
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
+ 0xff);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
+ IPPROTO_TCP);
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_sport,
+ ntohs(ib_spec->tcp_udp.mask.src_port));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_sport,
+ ntohs(ib_spec->tcp_udp.val.src_port));
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_dport,
+ ntohs(ib_spec->tcp_udp.mask.dst_port));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_dport,
+ ntohs(ib_spec->tcp_udp.val.dst_port));
+ break;
+ case IB_FLOW_SPEC_UDP:
+ if (ib_spec->size != sizeof(ib_spec->tcp_udp))
+ return -EINVAL;
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
+ 0xff);
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
+ IPPROTO_UDP);
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_sport,
+ ntohs(ib_spec->tcp_udp.mask.src_port));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_sport,
+ ntohs(ib_spec->tcp_udp.val.src_port));
+
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_dport,
+ ntohs(ib_spec->tcp_udp.mask.dst_port));
+ MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_dport,
+ ntohs(ib_spec->tcp_udp.val.dst_port));
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/* If a flow could catch both multicast and unicast packets,
+ * it won't fall into the multicast flow steering table and this rule
+ * could steal other multicast packets.
+ */
+static bool flow_is_multicast_only(struct ib_flow_attr *ib_attr)
+{
+ struct ib_flow_spec_eth *eth_spec;
+
+ if (ib_attr->type != IB_FLOW_ATTR_NORMAL ||
+ ib_attr->size < sizeof(struct ib_flow_attr) +
+ sizeof(struct ib_flow_spec_eth) ||
+ ib_attr->num_of_specs < 1)
+ return false;
+
+ eth_spec = (struct ib_flow_spec_eth *)(ib_attr + 1);
+ if (eth_spec->type != IB_FLOW_SPEC_ETH ||
+ eth_spec->size != sizeof(*eth_spec))
+ return false;
+
+ return is_multicast_ether_addr(eth_spec->mask.dst_mac) &&
+ is_multicast_ether_addr(eth_spec->val.dst_mac);
+}
+
+static bool is_valid_attr(struct ib_flow_attr *flow_attr)
+{
+ union ib_flow_spec *ib_spec = (union ib_flow_spec *)(flow_attr + 1);
+ bool has_ipv4_spec = false;
+ bool eth_type_ipv4 = true;
+ unsigned int spec_index;
+
+ /* Validate that ethertype is correct */
+ for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
+ if (ib_spec->type == IB_FLOW_SPEC_ETH &&
+ ib_spec->eth.mask.ether_type) {
+ if (!((ib_spec->eth.mask.ether_type == htons(0xffff)) &&
+ ib_spec->eth.val.ether_type == htons(ETH_P_IP)))
+ eth_type_ipv4 = false;
+ } else if (ib_spec->type == IB_FLOW_SPEC_IPV4) {
+ has_ipv4_spec = true;
+ }
+ ib_spec = (void *)ib_spec + ib_spec->size;
+ }
+ return !has_ipv4_spec || eth_type_ipv4;
+}
+
+static void put_flow_table(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_flow_prio *prio, bool ft_added)
+{
+ prio->refcount -= !!ft_added;
+ if (!prio->refcount) {
+ mlx5_destroy_flow_table(prio->flow_table);
+ prio->flow_table = NULL;
+ }
+}
+
+static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
+{
+ struct mlx5_ib_dev *dev = to_mdev(flow_id->qp->device);
+ struct mlx5_ib_flow_handler *handler = container_of(flow_id,
+ struct mlx5_ib_flow_handler,
+ ibflow);
+ struct mlx5_ib_flow_handler *iter, *tmp;
+
+ mutex_lock(&dev->flow_db.lock);
+
+ list_for_each_entry_safe(iter, tmp, &handler->list, list) {
+ mlx5_del_flow_rule(iter->rule);
+ list_del(&iter->list);
+ kfree(iter);
+ }
+
+ mlx5_del_flow_rule(handler->rule);
+ put_flow_table(dev, &dev->flow_db.prios[handler->prio], true);
+ mutex_unlock(&dev->flow_db.lock);
+
+ kfree(handler);
+
+ return 0;
+}
+
+#define MLX5_FS_MAX_TYPES 10
+#define MLX5_FS_MAX_ENTRIES 32000UL
+static struct mlx5_ib_flow_prio *get_flow_table(struct mlx5_ib_dev *dev,
+ struct ib_flow_attr *flow_attr)
+{
+ struct mlx5_flow_namespace *ns = NULL;
+ struct mlx5_ib_flow_prio *prio;
+ struct mlx5_flow_table *ft;
+ int num_entries;
+ int num_groups;
+ int priority;
+ int err = 0;
+
+ if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
+ if (flow_is_multicast_only(flow_attr))
+ priority = MLX5_IB_FLOW_MCAST_PRIO;
+ else
+ priority = flow_attr->priority;
+ ns = mlx5_get_flow_namespace(dev->mdev,
+ MLX5_FLOW_NAMESPACE_BYPASS);
+ num_entries = MLX5_FS_MAX_ENTRIES;
+ num_groups = MLX5_FS_MAX_TYPES;
+ prio = &dev->flow_db.prios[priority];
+ } else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
+ flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
+ ns = mlx5_get_flow_namespace(dev->mdev,
+ MLX5_FLOW_NAMESPACE_LEFTOVERS);
+ build_leftovers_ft_param(&priority,
+ &num_entries,
+ &num_groups);
+ prio = &dev->flow_db.prios[MLX5_IB_FLOW_LEFTOVERS_PRIO];
+ }
+
+ if (!ns)
+ return ERR_PTR(-ENOTSUPP);
+
+ ft = prio->flow_table;
+ if (!ft) {
+ ft = mlx5_create_auto_grouped_flow_table(ns, priority,
+ num_entries,
+ num_groups);
+
+ if (!IS_ERR(ft)) {
+ prio->refcount = 0;
+ prio->flow_table = ft;
+ } else {
+ err = PTR_ERR(ft);
+ }
+ }
+
+ return err ? ERR_PTR(err) : prio;
+}
+
+static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_flow_prio *ft_prio,
+ struct ib_flow_attr *flow_attr,
+ struct mlx5_flow_destination *dst)
+{
+ struct mlx5_flow_table *ft = ft_prio->flow_table;
+ struct mlx5_ib_flow_handler *handler;
+ void *ib_flow = flow_attr + 1;
+ u8 match_criteria_enable = 0;
+ unsigned int spec_index;
+ u32 *match_c;
+ u32 *match_v;
+ int err = 0;
+
+ if (!is_valid_attr(flow_attr))
+ return ERR_PTR(-EINVAL);
+
+ match_c = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+ match_v = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+ handler = kzalloc(sizeof(*handler), GFP_KERNEL);
+ if (!handler || !match_c || !match_v) {
+ err = -ENOMEM;
+ goto free;
+ }
+
+ INIT_LIST_HEAD(&handler->list);
+
+ for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
+ err = parse_flow_attr(match_c, match_v, ib_flow);
+ if (err < 0)
+ goto free;
+
+ ib_flow += ((union ib_flow_spec *)ib_flow)->size;
+ }
+
+ /* Outer header support only */
+ match_criteria_enable = (!outer_header_zero(match_c)) << 0;
+ handler->rule = mlx5_add_flow_rule(ft, match_criteria_enable,
+ match_c, match_v,
+ MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
+ MLX5_FS_DEFAULT_FLOW_TAG,
+ dst);
+
+ if (IS_ERR(handler->rule)) {
+ err = PTR_ERR(handler->rule);
+ goto free;
+ }
+
+ handler->prio = ft_prio - dev->flow_db.prios;
+
+ ft_prio->flow_table = ft;
+free:
+ if (err)
+ kfree(handler);
+ kfree(match_c);
+ kfree(match_v);
+ return err ? ERR_PTR(err) : handler;
+}
+
+enum {
+ LEFTOVERS_MC,
+ LEFTOVERS_UC,
+};
+
+static struct mlx5_ib_flow_handler *create_leftovers_rule(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_flow_prio *ft_prio,
+ struct ib_flow_attr *flow_attr,
+ struct mlx5_flow_destination *dst)
+{
+ struct mlx5_ib_flow_handler *handler_ucast = NULL;
+ struct mlx5_ib_flow_handler *handler = NULL;
+
+ static struct {
+ struct ib_flow_attr flow_attr;
+ struct ib_flow_spec_eth eth_flow;
+ } leftovers_specs[] = {
+ [LEFTOVERS_MC] = {
+ .flow_attr = {
+ .num_of_specs = 1,
+ .size = sizeof(leftovers_specs[0])
+ },
+ .eth_flow = {
+ .type = IB_FLOW_SPEC_ETH,
+ .size = sizeof(struct ib_flow_spec_eth),
+ .mask = {.dst_mac = {0x1} },
+ .val = {.dst_mac = {0x1} }
+ }
+ },
+ [LEFTOVERS_UC] = {
+ .flow_attr = {
+ .num_of_specs = 1,
+ .size = sizeof(leftovers_specs[0])
+ },
+ .eth_flow = {
+ .type = IB_FLOW_SPEC_ETH,
+ .size = sizeof(struct ib_flow_spec_eth),
+ .mask = {.dst_mac = {0x1} },
+ .val = {.dst_mac = {} }
+ }
+ }
+ };
+
+ handler = create_flow_rule(dev, ft_prio,
+ &leftovers_specs[LEFTOVERS_MC].flow_attr,
+ dst);
+ if (!IS_ERR(handler) &&
+ flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT) {
+ handler_ucast = create_flow_rule(dev, ft_prio,
+ &leftovers_specs[LEFTOVERS_UC].flow_attr,
+ dst);
+ if (IS_ERR(handler_ucast)) {
+ kfree(handler);
+ handler = handler_ucast;
+ } else {
+ list_add(&handler_ucast->list, &handler->list);
+ }
+ }
+
+ return handler;
+}
+
+static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
+ struct ib_flow_attr *flow_attr,
+ int domain)
+{
+ struct mlx5_ib_dev *dev = to_mdev(qp->device);
+ struct mlx5_ib_flow_handler *handler = NULL;
+ struct mlx5_flow_destination *dst = NULL;
+ struct mlx5_ib_flow_prio *ft_prio;
+ int err;
+
+ if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
+ return ERR_PTR(-ENOSPC);
+
+ if (domain != IB_FLOW_DOMAIN_USER ||
+ flow_attr->port > MLX5_CAP_GEN(dev->mdev, num_ports) ||
+ flow_attr->flags)
+ return ERR_PTR(-EINVAL);
+
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_lock(&dev->flow_db.lock);
+
+ ft_prio = get_flow_table(dev, flow_attr);
+ if (IS_ERR(ft_prio)) {
+ err = PTR_ERR(ft_prio);
+ goto unlock;
+ }
+
+ dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
+ dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn;
+
+ if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
+ handler = create_flow_rule(dev, ft_prio, flow_attr,
+ dst);
+ } else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
+ flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
+ handler = create_leftovers_rule(dev, ft_prio, flow_attr,
+ dst);
+ } else {
+ err = -EINVAL;
+ goto destroy_ft;
+ }
+
+ if (IS_ERR(handler)) {
+ err = PTR_ERR(handler);
+ handler = NULL;
+ goto destroy_ft;
+ }
+
+ ft_prio->refcount++;
+ mutex_unlock(&dev->flow_db.lock);
+ kfree(dst);
+
+ return &handler->ibflow;
+
+destroy_ft:
+ put_flow_table(dev, ft_prio, false);
+unlock:
+ mutex_unlock(&dev->flow_db.lock);
+ kfree(dst);
+ kfree(handler);
+ return ERR_PTR(err);
+}
+
static int mlx5_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
{
struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
@@ -1304,6 +2078,32 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr)
mlx5_ib_dealloc_pd(devr->p0);
}
+static u32 get_core_cap_flags(struct ib_device *ibdev)
+{
+ struct mlx5_ib_dev *dev = to_mdev(ibdev);
+ enum rdma_link_layer ll = mlx5_ib_port_link_layer(ibdev, 1);
+ u8 l3_type_cap = MLX5_CAP_ROCE(dev->mdev, l3_type);
+ u8 roce_version_cap = MLX5_CAP_ROCE(dev->mdev, roce_version);
+ u32 ret = 0;
+
+ if (ll == IB_LINK_LAYER_INFINIBAND)
+ return RDMA_CORE_PORT_IBA_IB;
+
+ if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV4_CAP))
+ return 0;
+
+ if (!(l3_type_cap & MLX5_ROCE_L3_TYPE_IPV6_CAP))
+ return 0;
+
+ if (roce_version_cap & MLX5_ROCE_VERSION_1_CAP)
+ ret |= RDMA_CORE_PORT_IBA_ROCE;
+
+ if (roce_version_cap & MLX5_ROCE_VERSION_2_CAP)
+ ret |= RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP;
+
+ return ret;
+}
+
static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
struct ib_port_immutable *immutable)
{
@@ -1316,20 +2116,50 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
immutable->pkey_tbl_len = attr.pkey_tbl_len;
immutable->gid_tbl_len = attr.gid_tbl_len;
- immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+ immutable->core_cap_flags = get_core_cap_flags(ibdev);
immutable->max_mad_size = IB_MGMT_MAD_SIZE;
return 0;
}
+static int mlx5_enable_roce(struct mlx5_ib_dev *dev)
+{
+ int err;
+
+ dev->roce.nb.notifier_call = mlx5_netdev_event;
+ err = register_netdevice_notifier(&dev->roce.nb);
+ if (err)
+ return err;
+
+ err = mlx5_nic_vport_enable_roce(dev->mdev);
+ if (err)
+ goto err_unregister_netdevice_notifier;
+
+ return 0;
+
+err_unregister_netdevice_notifier:
+ unregister_netdevice_notifier(&dev->roce.nb);
+ return err;
+}
+
+static void mlx5_disable_roce(struct mlx5_ib_dev *dev)
+{
+ mlx5_nic_vport_disable_roce(dev->mdev);
+ unregister_netdevice_notifier(&dev->roce.nb);
+}
+
static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
{
struct mlx5_ib_dev *dev;
+ enum rdma_link_layer ll;
+ int port_type_cap;
int err;
int i;
- /* don't create IB instance over Eth ports, no RoCE yet! */
- if (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH)
+ port_type_cap = MLX5_CAP_GEN(mdev, port_type);
+ ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap);
+
+ if ((ll == IB_LINK_LAYER_ETHERNET) && !MLX5_CAP_GEN(mdev, roce))
return NULL;
printk_once(KERN_INFO "%s", mlx5_version);
@@ -1340,6 +2170,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
dev->mdev = mdev;
+ rwlock_init(&dev->roce.netdev_lock);
err = get_port_caps(dev);
if (err)
goto err_dealloc;
@@ -1385,11 +2216,18 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ) |
(1ull << IB_USER_VERBS_CMD_OPEN_QP);
dev->ib_dev.uverbs_ex_cmd_mask =
- (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE);
+ (1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) |
+ (1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ) |
+ (1ull << IB_USER_VERBS_EX_CMD_CREATE_QP);
dev->ib_dev.query_device = mlx5_ib_query_device;
dev->ib_dev.query_port = mlx5_ib_query_port;
+ dev->ib_dev.get_link_layer = mlx5_ib_port_link_layer;
+ if (ll == IB_LINK_LAYER_ETHERNET)
+ dev->ib_dev.get_netdev = mlx5_ib_get_netdev;
dev->ib_dev.query_gid = mlx5_ib_query_gid;
+ dev->ib_dev.add_gid = mlx5_ib_add_gid;
+ dev->ib_dev.del_gid = mlx5_ib_del_gid;
dev->ib_dev.query_pkey = mlx5_ib_query_pkey;
dev->ib_dev.modify_device = mlx5_ib_modify_device;
dev->ib_dev.modify_port = mlx5_ib_modify_port;
@@ -1439,15 +2277,30 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
(1ull << IB_USER_VERBS_CMD_CLOSE_XRCD);
}
+ if (mlx5_ib_port_link_layer(&dev->ib_dev, 1) ==
+ IB_LINK_LAYER_ETHERNET) {
+ dev->ib_dev.create_flow = mlx5_ib_create_flow;
+ dev->ib_dev.destroy_flow = mlx5_ib_destroy_flow;
+ dev->ib_dev.uverbs_ex_cmd_mask |=
+ (1ull << IB_USER_VERBS_EX_CMD_CREATE_FLOW) |
+ (1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
+ }
err = init_node_data(dev);
if (err)
goto err_dealloc;
+ mutex_init(&dev->flow_db.lock);
mutex_init(&dev->cap_mask_mutex);
+ if (ll == IB_LINK_LAYER_ETHERNET) {
+ err = mlx5_enable_roce(dev);
+ if (err)
+ goto err_dealloc;
+ }
+
err = create_dev_resources(&dev->devr);
if (err)
- goto err_dealloc;
+ goto err_disable_roce;
err = mlx5_ib_odp_init_one(dev);
if (err)
@@ -1484,6 +2337,10 @@ err_odp:
err_rsrc:
destroy_dev_resources(&dev->devr);
+err_disable_roce:
+ if (ll == IB_LINK_LAYER_ETHERNET)
+ mlx5_disable_roce(dev);
+
err_dealloc:
ib_dealloc_device((struct ib_device *)dev);
@@ -1493,11 +2350,14 @@ err_dealloc:
static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
{
struct mlx5_ib_dev *dev = context;
+ enum rdma_link_layer ll = mlx5_ib_port_link_layer(&dev->ib_dev, 1);
ib_unregister_device(&dev->ib_dev);
destroy_umrc_res(dev);
mlx5_ib_odp_remove_one(dev);
destroy_dev_resources(&dev->devr);
+ if (ll == IB_LINK_LAYER_ETHERNET)
+ mlx5_disable_roce(dev);
ib_dealloc_device(&dev->ib_dev);
}
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 633347260..d2b9737ba 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -42,6 +42,7 @@
#include <linux/mlx5/qp.h>
#include <linux/mlx5/srq.h>
#include <linux/types.h>
+#include <linux/mlx5/transobj.h>
#define mlx5_ib_dbg(dev, format, arg...) \
pr_debug("%s:%s:%d:(pid %d): " format, (dev)->ib_dev.name, __func__, \
@@ -55,6 +56,11 @@ pr_err("%s:%s:%d:(pid %d): " format, (dev)->ib_dev.name, __func__, \
pr_warn("%s:%s:%d:(pid %d): " format, (dev)->ib_dev.name, __func__, \
__LINE__, current->pid, ##arg)
+#define field_avail(type, fld, sz) (offsetof(type, fld) + \
+ sizeof(((type *)0)->fld) <= (sz))
+#define MLX5_IB_DEFAULT_UIDX 0xffffff
+#define MLX5_USER_ASSIGNED_UIDX_MASK __mlx5_mask(qpc, user_index)
+
enum {
MLX5_IB_MMAP_CMD_SHIFT = 8,
MLX5_IB_MMAP_CMD_MASK = 0xff,
@@ -62,7 +68,9 @@ enum {
enum mlx5_ib_mmap_cmd {
MLX5_IB_MMAP_REGULAR_PAGE = 0,
- MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES = 1, /* always last */
+ MLX5_IB_MMAP_GET_CONTIGUOUS_PAGES = 1,
+ /* 5 is chosen in order to be compatible with old versions of libmlx5 */
+ MLX5_IB_MMAP_CORE_CLOCK = 5,
};
enum {
@@ -85,6 +93,15 @@ enum mlx5_ib_mad_ifc_flags {
MLX5_MAD_IFC_NET_VIEW = 4,
};
+enum {
+ MLX5_CROSS_CHANNEL_UUAR = 0,
+};
+
+enum {
+ MLX5_CQE_VERSION_V0,
+ MLX5_CQE_VERSION_V1,
+};
+
struct mlx5_ib_ucontext {
struct ib_ucontext ibucontext;
struct list_head db_page_list;
@@ -93,6 +110,9 @@ struct mlx5_ib_ucontext {
*/
struct mutex db_page_mutex;
struct mlx5_uuar_info uuari;
+ u8 cqe_version;
+ /* Transport Domain number */
+ u32 tdn;
};
static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibucontext)
@@ -105,6 +125,36 @@ struct mlx5_ib_pd {
u32 pdn;
};
+#define MLX5_IB_FLOW_MCAST_PRIO (MLX5_BY_PASS_NUM_PRIOS - 1)
+#define MLX5_IB_FLOW_LAST_PRIO (MLX5_IB_FLOW_MCAST_PRIO - 1)
+#if (MLX5_IB_FLOW_LAST_PRIO <= 0)
+#error "Invalid number of bypass priorities"
+#endif
+#define MLX5_IB_FLOW_LEFTOVERS_PRIO (MLX5_IB_FLOW_MCAST_PRIO + 1)
+
+#define MLX5_IB_NUM_FLOW_FT (MLX5_IB_FLOW_LEFTOVERS_PRIO + 1)
+struct mlx5_ib_flow_prio {
+ struct mlx5_flow_table *flow_table;
+ unsigned int refcount;
+};
+
+struct mlx5_ib_flow_handler {
+ struct list_head list;
+ struct ib_flow ibflow;
+ unsigned int prio;
+ struct mlx5_flow_rule *rule;
+};
+
+struct mlx5_ib_flow_db {
+ struct mlx5_ib_flow_prio prios[MLX5_IB_NUM_FLOW_FT];
+ /* Protect flow steering bypass flow tables
+ * when add/del flow rules.
+ * only single add/removal of flow steering rule could be done
+ * simultaneously.
+ */
+ struct mutex lock;
+};
+
/* Use macros here so that don't have to duplicate
* enum ib_send_flags and enum ib_qp_type for low-level driver
*/
@@ -171,35 +221,70 @@ struct mlx5_ib_pfault {
struct mlx5_pagefault mpfault;
};
+struct mlx5_ib_ubuffer {
+ struct ib_umem *umem;
+ int buf_size;
+ u64 buf_addr;
+};
+
+struct mlx5_ib_qp_base {
+ struct mlx5_ib_qp *container_mibqp;
+ struct mlx5_core_qp mqp;
+ struct mlx5_ib_ubuffer ubuffer;
+};
+
+struct mlx5_ib_qp_trans {
+ struct mlx5_ib_qp_base base;
+ u16 xrcdn;
+ u8 alt_port;
+ u8 atomic_rd_en;
+ u8 resp_depth;
+};
+
+struct mlx5_ib_rq {
+ struct mlx5_ib_qp_base base;
+ struct mlx5_ib_wq *rq;
+ struct mlx5_ib_ubuffer ubuffer;
+ struct mlx5_db *doorbell;
+ u32 tirn;
+ u8 state;
+};
+
+struct mlx5_ib_sq {
+ struct mlx5_ib_qp_base base;
+ struct mlx5_ib_wq *sq;
+ struct mlx5_ib_ubuffer ubuffer;
+ struct mlx5_db *doorbell;
+ u32 tisn;
+ u8 state;
+};
+
+struct mlx5_ib_raw_packet_qp {
+ struct mlx5_ib_sq sq;
+ struct mlx5_ib_rq rq;
+};
+
struct mlx5_ib_qp {
struct ib_qp ibqp;
- struct mlx5_core_qp mqp;
+ union {
+ struct mlx5_ib_qp_trans trans_qp;
+ struct mlx5_ib_raw_packet_qp raw_packet_qp;
+ };
struct mlx5_buf buf;
struct mlx5_db db;
struct mlx5_ib_wq rq;
- u32 doorbell_qpn;
u8 sq_signal_bits;
u8 fm_cache;
- int sq_max_wqes_per_wr;
- int sq_spare_wqes;
struct mlx5_ib_wq sq;
- struct ib_umem *umem;
- int buf_size;
-
/* serialize qp state modifications
*/
struct mutex mutex;
- u16 xrcdn;
u32 flags;
u8 port;
- u8 alt_port;
- u8 atomic_rd_en;
- u8 resp_depth;
u8 state;
- int mlx_type;
int wq_sig;
int scat_cqe;
int max_inline_data;
@@ -242,6 +327,9 @@ struct mlx5_ib_cq_buf {
enum mlx5_ib_qp_flags {
MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK = 1 << 0,
MLX5_IB_QP_SIGNATURE_HANDLING = 1 << 1,
+ MLX5_IB_QP_CROSS_CHANNEL = 1 << 2,
+ MLX5_IB_QP_MANAGED_SEND = 1 << 3,
+ MLX5_IB_QP_MANAGED_RECV = 1 << 4,
};
struct mlx5_umr_wr {
@@ -284,6 +372,7 @@ struct mlx5_ib_cq {
struct mlx5_ib_cq_buf *resize_buf;
struct ib_umem *resize_umem;
int cqe_size;
+ u32 create_flags;
};
struct mlx5_ib_srq {
@@ -407,9 +496,19 @@ struct mlx5_ib_resources {
struct ib_srq *s1;
};
+struct mlx5_roce {
+ /* Protect mlx5_ib_get_netdev from invoking dev_hold() with a NULL
+ * netdev pointer
+ */
+ rwlock_t netdev_lock;
+ struct net_device *netdev;
+ struct notifier_block nb;
+};
+
struct mlx5_ib_dev {
struct ib_device ib_dev;
struct mlx5_core_dev *mdev;
+ struct mlx5_roce roce;
MLX5_DECLARE_DOORBELL_LOCK(uar_lock);
int num_ports;
/* serialize update of capability mask
@@ -431,6 +530,7 @@ struct mlx5_ib_dev {
*/
struct srcu_struct mr_srcu;
#endif
+ struct mlx5_ib_flow_db flow_db;
};
static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -455,7 +555,7 @@ static inline struct mlx5_ib_cq *to_mcq(struct ib_cq *ibcq)
static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp)
{
- return container_of(mqp, struct mlx5_ib_qp, mqp);
+ return container_of(mqp, struct mlx5_ib_qp_base, mqp)->container_mibqp;
}
static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr)
@@ -507,8 +607,6 @@ void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index);
int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
const void *in_mad, void *response_mad);
-struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
- struct mlx5_ib_ah *ah);
struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
int mlx5_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr);
int mlx5_ib_destroy_ah(struct ib_ah *ah);
@@ -535,7 +633,8 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
struct ib_recv_wr **bad_wr);
void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n);
int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
- void *buffer, u32 length);
+ void *buffer, u32 length,
+ struct mlx5_ib_qp_base *base);
struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
const struct ib_cq_init_attr *attr,
struct ib_ucontext *context,
@@ -637,6 +736,9 @@ static inline void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp) {}
#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+__be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
+ int index);
+
static inline void init_query_mad(struct ib_smp *mad)
{
mad->base_version = 1;
@@ -662,4 +764,28 @@ static inline int is_qp1(enum ib_qp_type qp_type)
#define MLX5_MAX_UMR_SHIFT 16
#define MLX5_MAX_UMR_PAGES (1 << MLX5_MAX_UMR_SHIFT)
+static inline u32 check_cq_create_flags(u32 flags)
+{
+ /*
+ * It returns non-zero value for unsupported CQ
+ * create flags, otherwise it returns zero.
+ */
+ return (flags & ~(IB_CQ_FLAGS_IGNORE_OVERRUN |
+ IB_CQ_FLAGS_TIMESTAMP_COMPLETION));
+}
+
+static inline int verify_assign_uidx(u8 cqe_version, u32 cmd_uidx,
+ u32 *user_index)
+{
+ if (cqe_version) {
+ if ((cmd_uidx == MLX5_IB_DEFAULT_UIDX) ||
+ (cmd_uidx & ~MLX5_USER_ASSIGNED_UIDX_MASK))
+ return -EINVAL;
+ *user_index = cmd_uidx;
+ } else {
+ *user_index = MLX5_IB_DEFAULT_UIDX;
+ }
+
+ return 0;
+}
#endif /* MLX5_IB_H */
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index aa8391e75..b8d76361a 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -153,14 +153,16 @@ static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
struct mlx5_ib_pfault *pfault,
- int error) {
+ int error)
+{
struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
- int ret = mlx5_core_page_fault_resume(dev->mdev, qp->mqp.qpn,
+ u32 qpn = qp->trans_qp.base.mqp.qpn;
+ int ret = mlx5_core_page_fault_resume(dev->mdev,
+ qpn,
pfault->mpfault.flags,
error);
if (ret)
- pr_err("Failed to resolve the page fault on QP 0x%x\n",
- qp->mqp.qpn);
+ pr_err("Failed to resolve the page fault on QP 0x%x\n", qpn);
}
/*
@@ -391,6 +393,7 @@ static int mlx5_ib_mr_initiator_pfault_handler(
#if defined(DEBUG)
u32 ctrl_wqe_index, ctrl_qpn;
#endif
+ u32 qpn = qp->trans_qp.base.mqp.qpn;
ds = be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_DS_MASK;
if (ds * MLX5_WQE_DS_UNITS > wqe_length) {
@@ -401,7 +404,7 @@ static int mlx5_ib_mr_initiator_pfault_handler(
if (ds == 0) {
mlx5_ib_err(dev, "Got WQE with zero DS. wqe_index=%x, qpn=%x\n",
- wqe_index, qp->mqp.qpn);
+ wqe_index, qpn);
return -EFAULT;
}
@@ -411,16 +414,16 @@ static int mlx5_ib_mr_initiator_pfault_handler(
MLX5_WQE_CTRL_WQE_INDEX_SHIFT;
if (wqe_index != ctrl_wqe_index) {
mlx5_ib_err(dev, "Got WQE with invalid wqe_index. wqe_index=0x%x, qpn=0x%x ctrl->wqe_index=0x%x\n",
- wqe_index, qp->mqp.qpn,
+ wqe_index, qpn,
ctrl_wqe_index);
return -EFAULT;
}
ctrl_qpn = (be32_to_cpu(ctrl->qpn_ds) & MLX5_WQE_CTRL_QPN_MASK) >>
MLX5_WQE_CTRL_QPN_SHIFT;
- if (qp->mqp.qpn != ctrl_qpn) {
+ if (qpn != ctrl_qpn) {
mlx5_ib_err(dev, "Got WQE with incorrect QP number. wqe_index=0x%x, qpn=0x%x ctrl->qpn=0x%x\n",
- wqe_index, qp->mqp.qpn,
+ wqe_index, qpn,
ctrl_qpn);
return -EFAULT;
}
@@ -537,6 +540,7 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_qp *qp,
int resume_with_error = 0;
u16 wqe_index = pfault->mpfault.wqe.wqe_index;
int requestor = pfault->mpfault.flags & MLX5_PFAULT_REQUESTOR;
+ u32 qpn = qp->trans_qp.base.mqp.qpn;
buffer = (char *)__get_free_page(GFP_KERNEL);
if (!buffer) {
@@ -546,10 +550,10 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_qp *qp,
}
ret = mlx5_ib_read_user_wqe(qp, requestor, wqe_index, buffer,
- PAGE_SIZE);
+ PAGE_SIZE, &qp->trans_qp.base);
if (ret < 0) {
mlx5_ib_err(dev, "Failed reading a WQE following page fault, error=%x, wqe_index=%x, qpn=%x\n",
- -ret, wqe_index, qp->mqp.qpn);
+ -ret, wqe_index, qpn);
resume_with_error = 1;
goto resolve_page_fault;
}
@@ -586,7 +590,8 @@ static void mlx5_ib_mr_wqe_pfault_handler(struct mlx5_ib_qp *qp,
resolve_page_fault:
mlx5_ib_page_fault_resume(qp, pfault, resume_with_error);
mlx5_ib_dbg(dev, "PAGE FAULT completed. QP 0x%x resume_with_error=%d, flags: 0x%x\n",
- qp->mqp.qpn, resume_with_error, pfault->mpfault.flags);
+ qpn, resume_with_error,
+ pfault->mpfault.flags);
free_page((unsigned long)buffer);
}
@@ -753,7 +758,7 @@ void mlx5_ib_odp_create_qp(struct mlx5_ib_qp *qp)
qp->disable_page_faults = 1;
spin_lock_init(&qp->disable_page_faults_lock);
- qp->mqp.pfault_handler = mlx5_ib_pfault_handler;
+ qp->trans_qp.base.mqp.pfault_handler = mlx5_ib_pfault_handler;
for (i = 0; i < MLX5_IB_PAGEFAULT_CONTEXTS; ++i)
INIT_WORK(&qp->pagefaults[i].work, mlx5_ib_qp_pfault_action);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 307bdbca8..34cb8e87c 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -32,6 +32,8 @@
#include <linux/module.h>
#include <rdma/ib_umem.h>
+#include <rdma/ib_cache.h>
+#include <rdma/ib_user_verbs.h>
#include "mlx5_ib.h"
#include "user.h"
@@ -114,14 +116,15 @@ void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n)
* Return: the number of bytes copied, or an error code.
*/
int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
- void *buffer, u32 length)
+ void *buffer, u32 length,
+ struct mlx5_ib_qp_base *base)
{
struct ib_device *ibdev = qp->ibqp.device;
struct mlx5_ib_dev *dev = to_mdev(ibdev);
struct mlx5_ib_wq *wq = send ? &qp->sq : &qp->rq;
size_t offset;
size_t wq_end;
- struct ib_umem *umem = qp->umem;
+ struct ib_umem *umem = base->ubuffer.umem;
u32 first_copy_length;
int wqe_length;
int ret;
@@ -172,8 +175,10 @@ static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type)
struct ib_qp *ibqp = &to_mibqp(qp)->ibqp;
struct ib_event event;
- if (type == MLX5_EVENT_TYPE_PATH_MIG)
- to_mibqp(qp)->port = to_mibqp(qp)->alt_port;
+ if (type == MLX5_EVENT_TYPE_PATH_MIG) {
+ /* This event is only valid for trans_qps */
+ to_mibqp(qp)->port = to_mibqp(qp)->trans_qp.alt_port;
+ }
if (ibqp->event_handler) {
event.device = ibqp->device;
@@ -265,8 +270,10 @@ static int sq_overhead(enum ib_qp_type qp_type)
/* fall through */
case IB_QPT_RC:
size += sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_atomic_seg) +
- sizeof(struct mlx5_wqe_raddr_seg);
+ max(sizeof(struct mlx5_wqe_atomic_seg) +
+ sizeof(struct mlx5_wqe_raddr_seg),
+ sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+ sizeof(struct mlx5_mkey_seg));
break;
case IB_QPT_XRC_TGT:
@@ -274,9 +281,9 @@ static int sq_overhead(enum ib_qp_type qp_type)
case IB_QPT_UC:
size += sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_umr_ctrl_seg) +
- sizeof(struct mlx5_mkey_seg);
+ max(sizeof(struct mlx5_wqe_raddr_seg),
+ sizeof(struct mlx5_wqe_umr_ctrl_seg) +
+ sizeof(struct mlx5_mkey_seg));
break;
case IB_QPT_UD:
@@ -366,7 +373,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
static int set_user_buf_size(struct mlx5_ib_dev *dev,
struct mlx5_ib_qp *qp,
- struct mlx5_ib_create_qp *ucmd)
+ struct mlx5_ib_create_qp *ucmd,
+ struct mlx5_ib_qp_base *base,
+ struct ib_qp_init_attr *attr)
{
int desc_sz = 1 << qp->sq.wqe_shift;
@@ -391,8 +400,13 @@ static int set_user_buf_size(struct mlx5_ib_dev *dev,
return -EINVAL;
}
- qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
- (qp->sq.wqe_cnt << 6);
+ if (attr->qp_type == IB_QPT_RAW_PACKET) {
+ base->ubuffer.buf_size = qp->rq.wqe_cnt << qp->rq.wqe_shift;
+ qp->raw_packet_qp.sq.ubuffer.buf_size = qp->sq.wqe_cnt << 6;
+ } else {
+ base->ubuffer.buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
+ (qp->sq.wqe_cnt << 6);
+ }
return 0;
}
@@ -578,8 +592,8 @@ static int to_mlx5_st(enum ib_qp_type type)
case IB_QPT_SMI: return MLX5_QP_ST_QP0;
case IB_QPT_GSI: return MLX5_QP_ST_QP1;
case IB_QPT_RAW_IPV6: return MLX5_QP_ST_RAW_IPV6;
- case IB_QPT_RAW_ETHERTYPE: return MLX5_QP_ST_RAW_ETHERTYPE;
case IB_QPT_RAW_PACKET:
+ case IB_QPT_RAW_ETHERTYPE: return MLX5_QP_ST_RAW_ETHERTYPE;
case IB_QPT_MAX:
default: return -EINVAL;
}
@@ -590,13 +604,51 @@ static int uuarn_to_uar_index(struct mlx5_uuar_info *uuari, int uuarn)
return uuari->uars[uuarn / MLX5_BF_REGS_PER_PAGE].index;
}
+static int mlx5_ib_umem_get(struct mlx5_ib_dev *dev,
+ struct ib_pd *pd,
+ unsigned long addr, size_t size,
+ struct ib_umem **umem,
+ int *npages, int *page_shift, int *ncont,
+ u32 *offset)
+{
+ int err;
+
+ *umem = ib_umem_get(pd->uobject->context, addr, size, 0, 0);
+ if (IS_ERR(*umem)) {
+ mlx5_ib_dbg(dev, "umem_get failed\n");
+ return PTR_ERR(*umem);
+ }
+
+ mlx5_ib_cont_pages(*umem, addr, npages, page_shift, ncont, NULL);
+
+ err = mlx5_ib_get_buf_offset(addr, *page_shift, offset);
+ if (err) {
+ mlx5_ib_warn(dev, "bad offset\n");
+ goto err_umem;
+ }
+
+ mlx5_ib_dbg(dev, "addr 0x%lx, size %zu, npages %d, page_shift %d, ncont %d, offset %d\n",
+ addr, size, *npages, *page_shift, *ncont, *offset);
+
+ return 0;
+
+err_umem:
+ ib_umem_release(*umem);
+ *umem = NULL;
+
+ return err;
+}
+
static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
struct mlx5_ib_qp *qp, struct ib_udata *udata,
+ struct ib_qp_init_attr *attr,
struct mlx5_create_qp_mbox_in **in,
- struct mlx5_ib_create_qp_resp *resp, int *inlen)
+ struct mlx5_ib_create_qp_resp *resp, int *inlen,
+ struct mlx5_ib_qp_base *base)
{
struct mlx5_ib_ucontext *context;
struct mlx5_ib_create_qp ucmd;
+ struct mlx5_ib_ubuffer *ubuffer = &base->ubuffer;
int page_shift = 0;
int uar_index;
int npages;
@@ -615,18 +667,23 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
/*
* TBD: should come from the verbs when we have the API
*/
- uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH);
- if (uuarn < 0) {
- mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n");
- mlx5_ib_dbg(dev, "reverting to medium latency\n");
- uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
+ if (qp->flags & MLX5_IB_QP_CROSS_CHANNEL)
+ /* In CROSS_CHANNEL CQ and QP must use the same UAR */
+ uuarn = MLX5_CROSS_CHANNEL_UUAR;
+ else {
+ uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH);
if (uuarn < 0) {
- mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n");
- mlx5_ib_dbg(dev, "reverting to high latency\n");
- uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+ mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n");
+ mlx5_ib_dbg(dev, "reverting to medium latency\n");
+ uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
if (uuarn < 0) {
- mlx5_ib_warn(dev, "uuar allocation failed\n");
- return uuarn;
+ mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n");
+ mlx5_ib_dbg(dev, "reverting to high latency\n");
+ uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+ if (uuarn < 0) {
+ mlx5_ib_warn(dev, "uuar allocation failed\n");
+ return uuarn;
+ }
}
}
}
@@ -638,32 +695,20 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
- err = set_user_buf_size(dev, qp, &ucmd);
+ err = set_user_buf_size(dev, qp, &ucmd, base, attr);
if (err)
goto err_uuar;
- if (ucmd.buf_addr && qp->buf_size) {
- qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
- qp->buf_size, 0, 0);
- if (IS_ERR(qp->umem)) {
- mlx5_ib_dbg(dev, "umem_get failed\n");
- err = PTR_ERR(qp->umem);
+ if (ucmd.buf_addr && ubuffer->buf_size) {
+ ubuffer->buf_addr = ucmd.buf_addr;
+ err = mlx5_ib_umem_get(dev, pd, ubuffer->buf_addr,
+ ubuffer->buf_size,
+ &ubuffer->umem, &npages, &page_shift,
+ &ncont, &offset);
+ if (err)
goto err_uuar;
- }
} else {
- qp->umem = NULL;
- }
-
- if (qp->umem) {
- mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift,
- &ncont, NULL);
- err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset);
- if (err) {
- mlx5_ib_warn(dev, "bad offset\n");
- goto err_umem;
- }
- mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n",
- ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset);
+ ubuffer->umem = NULL;
}
*inlen = sizeof(**in) + sizeof(*(*in)->pas) * ncont;
@@ -672,8 +717,9 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
err = -ENOMEM;
goto err_umem;
}
- if (qp->umem)
- mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
+ if (ubuffer->umem)
+ mlx5_ib_populate_pas(dev, ubuffer->umem, page_shift,
+ (*in)->pas, 0);
(*in)->ctx.log_pg_sz_remote_qpn =
cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
(*in)->ctx.params2 = cpu_to_be32(offset << 6);
@@ -704,29 +750,31 @@ err_free:
kvfree(*in);
err_umem:
- if (qp->umem)
- ib_umem_release(qp->umem);
+ if (ubuffer->umem)
+ ib_umem_release(ubuffer->umem);
err_uuar:
free_uuar(&context->uuari, uuarn);
return err;
}
-static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp)
+static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp,
+ struct mlx5_ib_qp_base *base)
{
struct mlx5_ib_ucontext *context;
context = to_mucontext(pd->uobject->context);
mlx5_ib_db_unmap_user(context, &qp->db);
- if (qp->umem)
- ib_umem_release(qp->umem);
+ if (base->ubuffer.umem)
+ ib_umem_release(base->ubuffer.umem);
free_uuar(&context->uuari, qp->uuarn);
}
static int create_kernel_qp(struct mlx5_ib_dev *dev,
struct ib_qp_init_attr *init_attr,
struct mlx5_ib_qp *qp,
- struct mlx5_create_qp_mbox_in **in, int *inlen)
+ struct mlx5_create_qp_mbox_in **in, int *inlen,
+ struct mlx5_ib_qp_base *base)
{
enum mlx5_ib_latency_class lc = MLX5_IB_LATENCY_CLASS_LOW;
struct mlx5_uuar_info *uuari;
@@ -758,9 +806,9 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
qp->rq.offset = 0;
qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
- qp->buf_size = err + (qp->rq.wqe_cnt << qp->rq.wqe_shift);
+ base->ubuffer.buf_size = err + (qp->rq.wqe_cnt << qp->rq.wqe_shift);
- err = mlx5_buf_alloc(dev->mdev, qp->buf_size, &qp->buf);
+ err = mlx5_buf_alloc(dev->mdev, base->ubuffer.buf_size, &qp->buf);
if (err) {
mlx5_ib_dbg(dev, "err %d\n", err);
goto err_uuar;
@@ -853,19 +901,304 @@ static int is_connected(enum ib_qp_type qp_type)
return 0;
}
+static int create_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_sq *sq, u32 tdn)
+{
+ u32 in[MLX5_ST_SZ_DW(create_tis_in)];
+ void *tisc = MLX5_ADDR_OF(create_tis_in, in, ctx);
+
+ memset(in, 0, sizeof(in));
+
+ MLX5_SET(tisc, tisc, transport_domain, tdn);
+
+ return mlx5_core_create_tis(dev->mdev, in, sizeof(in), &sq->tisn);
+}
+
+static void destroy_raw_packet_qp_tis(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_sq *sq)
+{
+ mlx5_core_destroy_tis(dev->mdev, sq->tisn);
+}
+
+static int create_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_sq *sq, void *qpin,
+ struct ib_pd *pd)
+{
+ struct mlx5_ib_ubuffer *ubuffer = &sq->ubuffer;
+ __be64 *pas;
+ void *in;
+ void *sqc;
+ void *qpc = MLX5_ADDR_OF(create_qp_in, qpin, qpc);
+ void *wq;
+ int inlen;
+ int err;
+ int page_shift = 0;
+ int npages;
+ int ncont = 0;
+ u32 offset = 0;
+
+ err = mlx5_ib_umem_get(dev, pd, ubuffer->buf_addr, ubuffer->buf_size,
+ &sq->ubuffer.umem, &npages, &page_shift,
+ &ncont, &offset);
+ if (err)
+ return err;
+
+ inlen = MLX5_ST_SZ_BYTES(create_sq_in) + sizeof(u64) * ncont;
+ in = mlx5_vzalloc(inlen);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_umem;
+ }
+
+ sqc = MLX5_ADDR_OF(create_sq_in, in, ctx);
+ MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+ MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
+ MLX5_SET(sqc, sqc, user_index, MLX5_GET(qpc, qpc, user_index));
+ MLX5_SET(sqc, sqc, cqn, MLX5_GET(qpc, qpc, cqn_snd));
+ MLX5_SET(sqc, sqc, tis_lst_sz, 1);
+ MLX5_SET(sqc, sqc, tis_num_0, sq->tisn);
+
+ wq = MLX5_ADDR_OF(sqc, sqc, wq);
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
+ MLX5_SET(wq, wq, pd, MLX5_GET(qpc, qpc, pd));
+ MLX5_SET(wq, wq, uar_page, MLX5_GET(qpc, qpc, uar_page));
+ MLX5_SET64(wq, wq, dbr_addr, MLX5_GET64(qpc, qpc, dbr_addr));
+ MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
+ MLX5_SET(wq, wq, log_wq_sz, MLX5_GET(qpc, qpc, log_sq_size));
+ MLX5_SET(wq, wq, log_wq_pg_sz, page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+ MLX5_SET(wq, wq, page_offset, offset);
+
+ pas = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
+ mlx5_ib_populate_pas(dev, sq->ubuffer.umem, page_shift, pas, 0);
+
+ err = mlx5_core_create_sq_tracked(dev->mdev, in, inlen, &sq->base.mqp);
+
+ kvfree(in);
+
+ if (err)
+ goto err_umem;
+
+ return 0;
+
+err_umem:
+ ib_umem_release(sq->ubuffer.umem);
+ sq->ubuffer.umem = NULL;
+
+ return err;
+}
+
+static void destroy_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_sq *sq)
+{
+ mlx5_core_destroy_sq_tracked(dev->mdev, &sq->base.mqp);
+ ib_umem_release(sq->ubuffer.umem);
+}
+
+static int get_rq_pas_size(void *qpc)
+{
+ u32 log_page_size = MLX5_GET(qpc, qpc, log_page_size) + 12;
+ u32 log_rq_stride = MLX5_GET(qpc, qpc, log_rq_stride);
+ u32 log_rq_size = MLX5_GET(qpc, qpc, log_rq_size);
+ u32 page_offset = MLX5_GET(qpc, qpc, page_offset);
+ u32 po_quanta = 1 << (log_page_size - 6);
+ u32 rq_sz = 1 << (log_rq_size + 4 + log_rq_stride);
+ u32 page_size = 1 << log_page_size;
+ u32 rq_sz_po = rq_sz + (page_offset * po_quanta);
+ u32 rq_num_pas = (rq_sz_po + page_size - 1) / page_size;
+
+ return rq_num_pas * sizeof(u64);
+}
+
+static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq, void *qpin)
+{
+ __be64 *pas;
+ __be64 *qp_pas;
+ void *in;
+ void *rqc;
+ void *wq;
+ void *qpc = MLX5_ADDR_OF(create_qp_in, qpin, qpc);
+ int inlen;
+ int err;
+ u32 rq_pas_size = get_rq_pas_size(qpc);
+
+ inlen = MLX5_ST_SZ_BYTES(create_rq_in) + rq_pas_size;
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
+ MLX5_SET(rqc, rqc, vsd, 1);
+ MLX5_SET(rqc, rqc, mem_rq_type, MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE);
+ MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
+ MLX5_SET(rqc, rqc, flush_in_error_en, 1);
+ MLX5_SET(rqc, rqc, user_index, MLX5_GET(qpc, qpc, user_index));
+ MLX5_SET(rqc, rqc, cqn, MLX5_GET(qpc, qpc, cqn_rcv));
+
+ wq = MLX5_ADDR_OF(rqc, rqc, wq);
+ MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
+ MLX5_SET(wq, wq, end_padding_mode,
+ MLX5_GET(qpc, qpc, end_padding_mode));
+ MLX5_SET(wq, wq, page_offset, MLX5_GET(qpc, qpc, page_offset));
+ MLX5_SET(wq, wq, pd, MLX5_GET(qpc, qpc, pd));
+ MLX5_SET64(wq, wq, dbr_addr, MLX5_GET64(qpc, qpc, dbr_addr));
+ MLX5_SET(wq, wq, log_wq_stride, MLX5_GET(qpc, qpc, log_rq_stride) + 4);
+ MLX5_SET(wq, wq, log_wq_pg_sz, MLX5_GET(qpc, qpc, log_page_size));
+ MLX5_SET(wq, wq, log_wq_sz, MLX5_GET(qpc, qpc, log_rq_size));
+
+ pas = (__be64 *)MLX5_ADDR_OF(wq, wq, pas);
+ qp_pas = (__be64 *)MLX5_ADDR_OF(create_qp_in, qpin, pas);
+ memcpy(pas, qp_pas, rq_pas_size);
+
+ err = mlx5_core_create_rq_tracked(dev->mdev, in, inlen, &rq->base.mqp);
+
+ kvfree(in);
+
+ return err;
+}
+
+static void destroy_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq)
+{
+ mlx5_core_destroy_rq_tracked(dev->mdev, &rq->base.mqp);
+}
+
+static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq, u32 tdn)
+{
+ u32 *in;
+ void *tirc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(create_tir_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
+ MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
+ MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn);
+ MLX5_SET(tirc, tirc, transport_domain, tdn);
+
+ err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
+
+ kvfree(in);
+
+ return err;
+}
+
+static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq)
+{
+ mlx5_core_destroy_tir(dev->mdev, rq->tirn);
+}
+
+static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+ struct mlx5_create_qp_mbox_in *in,
+ struct ib_pd *pd)
+{
+ struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
+ struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
+ struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
+ struct ib_uobject *uobj = pd->uobject;
+ struct ib_ucontext *ucontext = uobj->context;
+ struct mlx5_ib_ucontext *mucontext = to_mucontext(ucontext);
+ int err;
+ u32 tdn = mucontext->tdn;
+
+ if (qp->sq.wqe_cnt) {
+ err = create_raw_packet_qp_tis(dev, sq, tdn);
+ if (err)
+ return err;
+
+ err = create_raw_packet_qp_sq(dev, sq, in, pd);
+ if (err)
+ goto err_destroy_tis;
+
+ sq->base.container_mibqp = qp;
+ }
+
+ if (qp->rq.wqe_cnt) {
+ err = create_raw_packet_qp_rq(dev, rq, in);
+ if (err)
+ goto err_destroy_sq;
+
+ rq->base.container_mibqp = qp;
+
+ err = create_raw_packet_qp_tir(dev, rq, tdn);
+ if (err)
+ goto err_destroy_rq;
+ }
+
+ qp->trans_qp.base.mqp.qpn = qp->sq.wqe_cnt ? sq->base.mqp.qpn :
+ rq->base.mqp.qpn;
+
+ return 0;
+
+err_destroy_rq:
+ destroy_raw_packet_qp_rq(dev, rq);
+err_destroy_sq:
+ if (!qp->sq.wqe_cnt)
+ return err;
+ destroy_raw_packet_qp_sq(dev, sq);
+err_destroy_tis:
+ destroy_raw_packet_qp_tis(dev, sq);
+
+ return err;
+}
+
+static void destroy_raw_packet_qp(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_qp *qp)
+{
+ struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
+ struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
+ struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
+
+ if (qp->rq.wqe_cnt) {
+ destroy_raw_packet_qp_tir(dev, rq);
+ destroy_raw_packet_qp_rq(dev, rq);
+ }
+
+ if (qp->sq.wqe_cnt) {
+ destroy_raw_packet_qp_sq(dev, sq);
+ destroy_raw_packet_qp_tis(dev, sq);
+ }
+}
+
+static void raw_packet_qp_copy_info(struct mlx5_ib_qp *qp,
+ struct mlx5_ib_raw_packet_qp *raw_packet_qp)
+{
+ struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
+ struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
+
+ sq->sq = &qp->sq;
+ rq->rq = &qp->rq;
+ sq->doorbell = &qp->db;
+ rq->doorbell = &qp->db;
+}
+
static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
struct ib_qp_init_attr *init_attr,
struct ib_udata *udata, struct mlx5_ib_qp *qp)
{
struct mlx5_ib_resources *devr = &dev->devr;
struct mlx5_core_dev *mdev = dev->mdev;
+ struct mlx5_ib_qp_base *base;
struct mlx5_ib_create_qp_resp resp;
struct mlx5_create_qp_mbox_in *in;
struct mlx5_ib_create_qp ucmd;
int inlen = sizeof(*in);
int err;
+ u32 uidx = MLX5_IB_DEFAULT_UIDX;
+ void *qpc;
+
+ base = init_attr->qp_type == IB_QPT_RAW_PACKET ?
+ &qp->raw_packet_qp.rq.base :
+ &qp->trans_qp.base;
- mlx5_ib_odp_create_qp(qp);
+ if (init_attr->qp_type != IB_QPT_RAW_PACKET)
+ mlx5_ib_odp_create_qp(qp);
mutex_init(&qp->mutex);
spin_lock_init(&qp->sq.lock);
@@ -880,6 +1213,21 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
}
}
+ if (init_attr->create_flags &
+ (IB_QP_CREATE_CROSS_CHANNEL |
+ IB_QP_CREATE_MANAGED_SEND |
+ IB_QP_CREATE_MANAGED_RECV)) {
+ if (!MLX5_CAP_GEN(mdev, cd)) {
+ mlx5_ib_dbg(dev, "cross-channel isn't supported\n");
+ return -EINVAL;
+ }
+ if (init_attr->create_flags & IB_QP_CREATE_CROSS_CHANNEL)
+ qp->flags |= MLX5_IB_QP_CROSS_CHANNEL;
+ if (init_attr->create_flags & IB_QP_CREATE_MANAGED_SEND)
+ qp->flags |= MLX5_IB_QP_MANAGED_SEND;
+ if (init_attr->create_flags & IB_QP_CREATE_MANAGED_RECV)
+ qp->flags |= MLX5_IB_QP_MANAGED_RECV;
+ }
if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE;
@@ -889,6 +1237,11 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
return -EFAULT;
}
+ err = get_qp_user_index(to_mucontext(pd->uobject->context),
+ &ucmd, udata->inlen, &uidx);
+ if (err)
+ return err;
+
qp->wq_sig = !!(ucmd.flags & MLX5_QP_FLAG_SIGNATURE);
qp->scat_cqe = !!(ucmd.flags & MLX5_QP_FLAG_SCATTER_CQE);
} else {
@@ -918,11 +1271,13 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
ucmd.sq_wqe_count, max_wqes);
return -EINVAL;
}
- err = create_user_qp(dev, pd, qp, udata, &in, &resp, &inlen);
+ err = create_user_qp(dev, pd, qp, udata, init_attr, &in,
+ &resp, &inlen, base);
if (err)
mlx5_ib_dbg(dev, "err %d\n", err);
} else {
- err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
+ err = create_kernel_qp(dev, init_attr, qp, &in, &inlen,
+ base);
if (err)
mlx5_ib_dbg(dev, "err %d\n", err);
}
@@ -954,6 +1309,13 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
if (qp->flags & MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK)
in->ctx.flags_pd |= cpu_to_be32(MLX5_QP_BLOCK_MCAST);
+ if (qp->flags & MLX5_IB_QP_CROSS_CHANNEL)
+ in->ctx.params2 |= cpu_to_be32(MLX5_QP_BIT_CC_MASTER);
+ if (qp->flags & MLX5_IB_QP_MANAGED_SEND)
+ in->ctx.params2 |= cpu_to_be32(MLX5_QP_BIT_CC_SLAVE_SEND);
+ if (qp->flags & MLX5_IB_QP_MANAGED_RECV)
+ in->ctx.params2 |= cpu_to_be32(MLX5_QP_BIT_CC_SLAVE_RECV);
+
if (qp->scat_cqe && is_connected(init_attr->qp_type)) {
int rcqe_sz;
int scqe_sz;
@@ -1018,26 +1380,35 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
in->ctx.db_rec_addr = cpu_to_be64(qp->db.dma);
- err = mlx5_core_create_qp(dev->mdev, &qp->mqp, in, inlen);
+ if (MLX5_CAP_GEN(mdev, cqe_version) == MLX5_CQE_VERSION_V1) {
+ qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ /* 0xffffff means we ask to work with cqe version 0 */
+ MLX5_SET(qpc, qpc, user_index, uidx);
+ }
+
+ if (init_attr->qp_type == IB_QPT_RAW_PACKET) {
+ qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr;
+ raw_packet_qp_copy_info(qp, &qp->raw_packet_qp);
+ err = create_raw_packet_qp(dev, qp, in, pd);
+ } else {
+ err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen);
+ }
+
if (err) {
mlx5_ib_dbg(dev, "create qp failed\n");
goto err_create;
}
kvfree(in);
- /* Hardware wants QPN written in big-endian order (after
- * shifting) for send doorbell. Precompute this value to save
- * a little bit when posting sends.
- */
- qp->doorbell_qpn = swab32(qp->mqp.qpn << 8);
- qp->mqp.event = mlx5_ib_qp_event;
+ base->container_mibqp = qp;
+ base->mqp.event = mlx5_ib_qp_event;
return 0;
err_create:
if (qp->create_type == MLX5_QP_USER)
- destroy_qp_user(pd, qp);
+ destroy_qp_user(pd, qp, base);
else if (qp->create_type == MLX5_QP_KERNEL)
destroy_qp_kernel(dev, qp);
@@ -1129,11 +1500,11 @@ static void get_cqs(struct mlx5_ib_qp *qp,
case IB_QPT_UD:
case IB_QPT_RAW_IPV6:
case IB_QPT_RAW_ETHERTYPE:
+ case IB_QPT_RAW_PACKET:
*send_cq = to_mcq(qp->ibqp.send_cq);
*recv_cq = to_mcq(qp->ibqp.recv_cq);
break;
- case IB_QPT_RAW_PACKET:
case IB_QPT_MAX:
default:
*send_cq = NULL;
@@ -1142,45 +1513,66 @@ static void get_cqs(struct mlx5_ib_qp *qp,
}
}
+static int modify_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+ u16 operation);
+
static void destroy_qp_common(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
{
struct mlx5_ib_cq *send_cq, *recv_cq;
+ struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
struct mlx5_modify_qp_mbox_in *in;
int err;
+ base = qp->ibqp.qp_type == IB_QPT_RAW_PACKET ?
+ &qp->raw_packet_qp.rq.base :
+ &qp->trans_qp.base;
+
in = kzalloc(sizeof(*in), GFP_KERNEL);
if (!in)
return;
if (qp->state != IB_QPS_RESET) {
- mlx5_ib_qp_disable_pagefaults(qp);
- if (mlx5_core_qp_modify(dev->mdev, to_mlx5_state(qp->state),
- MLX5_QP_STATE_RST, in, 0, &qp->mqp))
- mlx5_ib_warn(dev, "mlx5_ib: modify QP %06x to RESET failed\n",
- qp->mqp.qpn);
+ if (qp->ibqp.qp_type != IB_QPT_RAW_PACKET) {
+ mlx5_ib_qp_disable_pagefaults(qp);
+ err = mlx5_core_qp_modify(dev->mdev,
+ MLX5_CMD_OP_2RST_QP, in, 0,
+ &base->mqp);
+ } else {
+ err = modify_raw_packet_qp(dev, qp,
+ MLX5_CMD_OP_2RST_QP);
+ }
+ if (err)
+ mlx5_ib_warn(dev, "mlx5_ib: modify QP 0x%06x to RESET failed\n",
+ base->mqp.qpn);
}
get_cqs(qp, &send_cq, &recv_cq);
if (qp->create_type == MLX5_QP_KERNEL) {
mlx5_ib_lock_cqs(send_cq, recv_cq);
- __mlx5_ib_cq_clean(recv_cq, qp->mqp.qpn,
+ __mlx5_ib_cq_clean(recv_cq, base->mqp.qpn,
qp->ibqp.srq ? to_msrq(qp->ibqp.srq) : NULL);
if (send_cq != recv_cq)
- __mlx5_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
+ __mlx5_ib_cq_clean(send_cq, base->mqp.qpn,
+ NULL);
mlx5_ib_unlock_cqs(send_cq, recv_cq);
}
- err = mlx5_core_destroy_qp(dev->mdev, &qp->mqp);
- if (err)
- mlx5_ib_warn(dev, "failed to destroy QP 0x%x\n", qp->mqp.qpn);
- kfree(in);
+ if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+ destroy_raw_packet_qp(dev, qp);
+ } else {
+ err = mlx5_core_destroy_qp(dev->mdev, &base->mqp);
+ if (err)
+ mlx5_ib_warn(dev, "failed to destroy QP 0x%x\n",
+ base->mqp.qpn);
+ }
+ kfree(in);
if (qp->create_type == MLX5_QP_KERNEL)
destroy_qp_kernel(dev, qp);
else if (qp->create_type == MLX5_QP_USER)
- destroy_qp_user(&get_pd(qp)->ibpd, qp);
+ destroy_qp_user(&get_pd(qp)->ibpd, qp, base);
}
static const char *ib_qp_type_str(enum ib_qp_type type)
@@ -1225,6 +1617,16 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
if (pd) {
dev = to_mdev(pd->device);
+
+ if (init_attr->qp_type == IB_QPT_RAW_PACKET) {
+ if (!pd->uobject) {
+ mlx5_ib_dbg(dev, "Raw Packet QP is not supported for kernel consumers\n");
+ return ERR_PTR(-EINVAL);
+ } else if (!to_mucontext(pd->uobject->context)->cqe_version) {
+ mlx5_ib_dbg(dev, "Raw Packet QP is only supported for CQE version > 0\n");
+ return ERR_PTR(-EINVAL);
+ }
+ }
} else {
/* being cautious here */
if (init_attr->qp_type != IB_QPT_XRC_TGT &&
@@ -1250,6 +1652,7 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
}
/* fall through */
+ case IB_QPT_RAW_PACKET:
case IB_QPT_RC:
case IB_QPT_UC:
case IB_QPT_UD:
@@ -1272,19 +1675,19 @@ struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
else if (is_qp1(init_attr->qp_type))
qp->ibqp.qp_num = 1;
else
- qp->ibqp.qp_num = qp->mqp.qpn;
+ qp->ibqp.qp_num = qp->trans_qp.base.mqp.qpn;
mlx5_ib_dbg(dev, "ib qpnum 0x%x, mlx qpn 0x%x, rcqn 0x%x, scqn 0x%x\n",
- qp->ibqp.qp_num, qp->mqp.qpn, to_mcq(init_attr->recv_cq)->mcq.cqn,
+ qp->ibqp.qp_num, qp->trans_qp.base.mqp.qpn,
+ to_mcq(init_attr->recv_cq)->mcq.cqn,
to_mcq(init_attr->send_cq)->mcq.cqn);
- qp->xrcdn = xrcdn;
+ qp->trans_qp.xrcdn = xrcdn;
break;
case IB_QPT_RAW_IPV6:
case IB_QPT_RAW_ETHERTYPE:
- case IB_QPT_RAW_PACKET:
case IB_QPT_MAX:
default:
mlx5_ib_dbg(dev, "unsupported qp type %d\n",
@@ -1318,12 +1721,12 @@ static __be32 to_mlx5_access_flags(struct mlx5_ib_qp *qp, const struct ib_qp_att
if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
dest_rd_atomic = attr->max_dest_rd_atomic;
else
- dest_rd_atomic = qp->resp_depth;
+ dest_rd_atomic = qp->trans_qp.resp_depth;
if (attr_mask & IB_QP_ACCESS_FLAGS)
access_flags = attr->qp_access_flags;
else
- access_flags = qp->atomic_rd_en;
+ access_flags = qp->trans_qp.atomic_rd_en;
if (!dest_rd_atomic)
access_flags &= IB_ACCESS_REMOTE_WRITE;
@@ -1360,21 +1763,42 @@ static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
return rate + MLX5_STAT_RATE_OFFSET;
}
-static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
+static int modify_raw_packet_eth_prio(struct mlx5_core_dev *dev,
+ struct mlx5_ib_sq *sq, u8 sl)
+{
+ void *in;
+ void *tisc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_tis_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(modify_tis_in, in, bitmask.prio, 1);
+
+ tisc = MLX5_ADDR_OF(modify_tis_in, in, ctx);
+ MLX5_SET(tisc, tisc, prio, ((sl & 0x7) << 1));
+
+ err = mlx5_core_modify_tis(dev, sq->tisn, in, inlen);
+
+ kvfree(in);
+
+ return err;
+}
+
+static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+ const struct ib_ah_attr *ah,
struct mlx5_qp_path *path, u8 port, int attr_mask,
u32 path_flags, const struct ib_qp_attr *attr)
{
+ enum rdma_link_layer ll = rdma_port_get_link_layer(&dev->ib_dev, port);
int err;
- path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
- path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 : 0;
-
if (attr_mask & IB_QP_PKEY_INDEX)
path->pkey_index = attr->pkey_index;
- path->grh_mlid = ah->src_path_bits & 0x7f;
- path->rlid = cpu_to_be16(ah->dlid);
-
if (ah->ah_flags & IB_AH_GRH) {
if (ah->grh.sgid_index >=
dev->mdev->port_caps[port - 1].gid_table_len) {
@@ -1383,7 +1807,27 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
dev->mdev->port_caps[port - 1].gid_table_len);
return -EINVAL;
}
- path->grh_mlid |= 1 << 7;
+ }
+
+ if (ll == IB_LINK_LAYER_ETHERNET) {
+ if (!(ah->ah_flags & IB_AH_GRH))
+ return -EINVAL;
+ memcpy(path->rmac, ah->dmac, sizeof(ah->dmac));
+ path->udp_sport = mlx5_get_roce_udp_sport(dev, port,
+ ah->grh.sgid_index);
+ path->dci_cfi_prio_sl = (ah->sl & 0x7) << 4;
+ } else {
+ path->fl = (path_flags & MLX5_PATH_FLAG_FL) ? 0x80 : 0;
+ path->free_ar = (path_flags & MLX5_PATH_FLAG_FREE_AR) ? 0x80 :
+ 0;
+ path->rlid = cpu_to_be16(ah->dlid);
+ path->grh_mlid = ah->src_path_bits & 0x7f;
+ if (ah->ah_flags & IB_AH_GRH)
+ path->grh_mlid |= 1 << 7;
+ path->dci_cfi_prio_sl = ah->sl & 0xf;
+ }
+
+ if (ah->ah_flags & IB_AH_GRH) {
path->mgid_index = ah->grh.sgid_index;
path->hop_limit = ah->grh.hop_limit;
path->tclass_flowlabel =
@@ -1401,7 +1845,10 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, const struct ib_ah_attr *ah,
if (attr_mask & IB_QP_TIMEOUT)
path->ackto_lt = attr->timeout << 3;
- path->sl = ah->sl & 0xf;
+ if ((qp->ibqp.qp_type == IB_QPT_RAW_PACKET) && qp->sq.wqe_cnt)
+ return modify_raw_packet_eth_prio(dev->mdev,
+ &qp->raw_packet_qp.sq,
+ ah->sl & 0xf);
return 0;
}
@@ -1549,12 +1996,154 @@ static int ib_mask_to_mlx5_opt(int ib_mask)
return result;
}
+static int modify_raw_packet_qp_rq(struct mlx5_core_dev *dev,
+ struct mlx5_ib_rq *rq, int new_state)
+{
+ void *in;
+ void *rqc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_rq_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(modify_rq_in, in, rq_state, rq->state);
+
+ rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
+ MLX5_SET(rqc, rqc, state, new_state);
+
+ err = mlx5_core_modify_rq(dev, rq->base.mqp.qpn, in, inlen);
+ if (err)
+ goto out;
+
+ rq->state = new_state;
+
+out:
+ kvfree(in);
+ return err;
+}
+
+static int modify_raw_packet_qp_sq(struct mlx5_core_dev *dev,
+ struct mlx5_ib_sq *sq, int new_state)
+{
+ void *in;
+ void *sqc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(modify_sq_in);
+ in = mlx5_vzalloc(inlen);
+ if (!in)
+ return -ENOMEM;
+
+ MLX5_SET(modify_sq_in, in, sq_state, sq->state);
+
+ sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
+ MLX5_SET(sqc, sqc, state, new_state);
+
+ err = mlx5_core_modify_sq(dev, sq->base.mqp.qpn, in, inlen);
+ if (err)
+ goto out;
+
+ sq->state = new_state;
+
+out:
+ kvfree(in);
+ return err;
+}
+
+static int modify_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+ u16 operation)
+{
+ struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
+ struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
+ struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
+ int rq_state;
+ int sq_state;
+ int err;
+
+ switch (operation) {
+ case MLX5_CMD_OP_RST2INIT_QP:
+ rq_state = MLX5_RQC_STATE_RDY;
+ sq_state = MLX5_SQC_STATE_RDY;
+ break;
+ case MLX5_CMD_OP_2ERR_QP:
+ rq_state = MLX5_RQC_STATE_ERR;
+ sq_state = MLX5_SQC_STATE_ERR;
+ break;
+ case MLX5_CMD_OP_2RST_QP:
+ rq_state = MLX5_RQC_STATE_RST;
+ sq_state = MLX5_SQC_STATE_RST;
+ break;
+ case MLX5_CMD_OP_INIT2INIT_QP:
+ case MLX5_CMD_OP_INIT2RTR_QP:
+ case MLX5_CMD_OP_RTR2RTS_QP:
+ case MLX5_CMD_OP_RTS2RTS_QP:
+ /* Nothing to do here... */
+ return 0;
+ default:
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ if (qp->rq.wqe_cnt) {
+ err = modify_raw_packet_qp_rq(dev->mdev, rq, rq_state);
+ if (err)
+ return err;
+ }
+
+ if (qp->sq.wqe_cnt)
+ return modify_raw_packet_qp_sq(dev->mdev, sq, sq_state);
+
+ return 0;
+}
+
static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
const struct ib_qp_attr *attr, int attr_mask,
enum ib_qp_state cur_state, enum ib_qp_state new_state)
{
+ static const u16 optab[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE] = {
+ [MLX5_QP_STATE_RST] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ [MLX5_QP_STATE_INIT] = MLX5_CMD_OP_RST2INIT_QP,
+ },
+ [MLX5_QP_STATE_INIT] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ [MLX5_QP_STATE_INIT] = MLX5_CMD_OP_INIT2INIT_QP,
+ [MLX5_QP_STATE_RTR] = MLX5_CMD_OP_INIT2RTR_QP,
+ },
+ [MLX5_QP_STATE_RTR] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ [MLX5_QP_STATE_RTS] = MLX5_CMD_OP_RTR2RTS_QP,
+ },
+ [MLX5_QP_STATE_RTS] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ [MLX5_QP_STATE_RTS] = MLX5_CMD_OP_RTS2RTS_QP,
+ },
+ [MLX5_QP_STATE_SQD] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ },
+ [MLX5_QP_STATE_SQER] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ [MLX5_QP_STATE_RTS] = MLX5_CMD_OP_SQERR2RTS_QP,
+ },
+ [MLX5_QP_STATE_ERR] = {
+ [MLX5_QP_STATE_RST] = MLX5_CMD_OP_2RST_QP,
+ [MLX5_QP_STATE_ERR] = MLX5_CMD_OP_2ERR_QP,
+ }
+ };
+
struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
struct mlx5_ib_qp *qp = to_mqp(ibqp);
+ struct mlx5_ib_qp_base *base = &qp->trans_qp.base;
struct mlx5_ib_cq *send_cq, *recv_cq;
struct mlx5_qp_context *context;
struct mlx5_modify_qp_mbox_in *in;
@@ -1564,6 +2153,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
int sqd_event;
int mlx5_st;
int err;
+ u16 op;
in = kzalloc(sizeof(*in), GFP_KERNEL);
if (!in)
@@ -1623,7 +2213,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
context->pri_path.port = attr->port_num;
if (attr_mask & IB_QP_AV) {
- err = mlx5_set_path(dev, &attr->ah_attr, &context->pri_path,
+ err = mlx5_set_path(dev, qp, &attr->ah_attr, &context->pri_path,
attr_mask & IB_QP_PORT ? attr->port_num : qp->port,
attr_mask, 0, attr);
if (err)
@@ -1634,7 +2224,8 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
context->pri_path.ackto_lt |= attr->timeout << 3;
if (attr_mask & IB_QP_ALT_PATH) {
- err = mlx5_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
+ err = mlx5_set_path(dev, qp, &attr->alt_ah_attr,
+ &context->alt_path,
attr->alt_port_num, attr_mask, 0, attr);
if (err)
goto out;
@@ -1706,41 +2297,51 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
* again to RTS, and may cause the driver and the device to get out of
* sync. */
if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
- (new_state == IB_QPS_RESET || new_state == IB_QPS_ERR))
+ (new_state == IB_QPS_RESET || new_state == IB_QPS_ERR) &&
+ (qp->ibqp.qp_type != IB_QPT_RAW_PACKET))
mlx5_ib_qp_disable_pagefaults(qp);
+ if (mlx5_cur >= MLX5_QP_NUM_STATE || mlx5_new >= MLX5_QP_NUM_STATE ||
+ !optab[mlx5_cur][mlx5_new])
+ goto out;
+
+ op = optab[mlx5_cur][mlx5_new];
optpar = ib_mask_to_mlx5_opt(attr_mask);
optpar &= opt_mask[mlx5_cur][mlx5_new][mlx5_st];
in->optparam = cpu_to_be32(optpar);
- err = mlx5_core_qp_modify(dev->mdev, to_mlx5_state(cur_state),
- to_mlx5_state(new_state), in, sqd_event,
- &qp->mqp);
+
+ if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET)
+ err = modify_raw_packet_qp(dev, qp, op);
+ else
+ err = mlx5_core_qp_modify(dev->mdev, op, in, sqd_event,
+ &base->mqp);
if (err)
goto out;
- if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
+ if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT &&
+ (qp->ibqp.qp_type != IB_QPT_RAW_PACKET))
mlx5_ib_qp_enable_pagefaults(qp);
qp->state = new_state;
if (attr_mask & IB_QP_ACCESS_FLAGS)
- qp->atomic_rd_en = attr->qp_access_flags;
+ qp->trans_qp.atomic_rd_en = attr->qp_access_flags;
if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
- qp->resp_depth = attr->max_dest_rd_atomic;
+ qp->trans_qp.resp_depth = attr->max_dest_rd_atomic;
if (attr_mask & IB_QP_PORT)
qp->port = attr->port_num;
if (attr_mask & IB_QP_ALT_PATH)
- qp->alt_port = attr->alt_port_num;
+ qp->trans_qp.alt_port = attr->alt_port_num;
/*
* If we moved a kernel QP to RESET, clean up all old CQ
* entries and reinitialize the QP.
*/
if (new_state == IB_QPS_RESET && !ibqp->uobject) {
- mlx5_ib_cq_clean(recv_cq, qp->mqp.qpn,
+ mlx5_ib_cq_clean(recv_cq, base->mqp.qpn,
ibqp->srq ? to_msrq(ibqp->srq) : NULL);
if (send_cq != recv_cq)
- mlx5_ib_cq_clean(send_cq, qp->mqp.qpn, NULL);
+ mlx5_ib_cq_clean(send_cq, base->mqp.qpn, NULL);
qp->rq.head = 0;
qp->rq.tail = 0;
@@ -1765,15 +2366,21 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
enum ib_qp_state cur_state, new_state;
int err = -EINVAL;
int port;
+ enum rdma_link_layer ll = IB_LINK_LAYER_UNSPECIFIED;
mutex_lock(&qp->mutex);
cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
+ if (!(cur_state == new_state && cur_state == IB_QPS_RESET)) {
+ port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ ll = dev->ib_dev.get_link_layer(&dev->ib_dev, port);
+ }
+
if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
- IB_LINK_LAYER_UNSPECIFIED))
+ ll))
goto out;
if ((attr_mask & IB_QP_PORT) &&
@@ -2570,7 +3177,7 @@ static void finish_wqe(struct mlx5_ib_qp *qp,
ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8) |
mlx5_opcode | ((u32)opmod << 24));
- ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
+ ctrl->qpn_ds = cpu_to_be32(size | (qp->trans_qp.base.mqp.qpn << 8));
ctrl->fm_ce_se |= fence;
qp->fm_cache = next_fence;
if (unlikely(qp->wq_sig))
@@ -3003,7 +3610,7 @@ static void to_ib_ah_attr(struct mlx5_ib_dev *ibdev, struct ib_ah_attr *ib_ah_at
ib_ah_attr->port_num > MLX5_CAP_GEN(dev, num_ports))
return;
- ib_ah_attr->sl = path->sl & 0xf;
+ ib_ah_attr->sl = path->dci_cfi_prio_sl & 0xf;
ib_ah_attr->dlid = be16_to_cpu(path->rlid);
ib_ah_attr->src_path_bits = path->grh_mlid & 0x7f;
@@ -3021,39 +3628,153 @@ static void to_ib_ah_attr(struct mlx5_ib_dev *ibdev, struct ib_ah_attr *ib_ah_at
}
}
-int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr_mask,
- struct ib_qp_init_attr *qp_init_attr)
+static int query_raw_packet_qp_sq_state(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_sq *sq,
+ u8 *sq_state)
+{
+ void *out;
+ void *sqc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(query_sq_out);
+ out = mlx5_vzalloc(inlen);
+ if (!out)
+ return -ENOMEM;
+
+ err = mlx5_core_query_sq(dev->mdev, sq->base.mqp.qpn, out);
+ if (err)
+ goto out;
+
+ sqc = MLX5_ADDR_OF(query_sq_out, out, sq_context);
+ *sq_state = MLX5_GET(sqc, sqc, state);
+ sq->state = *sq_state;
+
+out:
+ kvfree(out);
+ return err;
+}
+
+static int query_raw_packet_qp_rq_state(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_rq *rq,
+ u8 *rq_state)
+{
+ void *out;
+ void *rqc;
+ int inlen;
+ int err;
+
+ inlen = MLX5_ST_SZ_BYTES(query_rq_out);
+ out = mlx5_vzalloc(inlen);
+ if (!out)
+ return -ENOMEM;
+
+ err = mlx5_core_query_rq(dev->mdev, rq->base.mqp.qpn, out);
+ if (err)
+ goto out;
+
+ rqc = MLX5_ADDR_OF(query_rq_out, out, rq_context);
+ *rq_state = MLX5_GET(rqc, rqc, state);
+ rq->state = *rq_state;
+
+out:
+ kvfree(out);
+ return err;
+}
+
+static int sqrq_state_to_qp_state(u8 sq_state, u8 rq_state,
+ struct mlx5_ib_qp *qp, u8 *qp_state)
+{
+ static const u8 sqrq_trans[MLX5_RQ_NUM_STATE][MLX5_SQ_NUM_STATE] = {
+ [MLX5_RQC_STATE_RST] = {
+ [MLX5_SQC_STATE_RST] = IB_QPS_RESET,
+ [MLX5_SQC_STATE_RDY] = MLX5_QP_STATE_BAD,
+ [MLX5_SQC_STATE_ERR] = MLX5_QP_STATE_BAD,
+ [MLX5_SQ_STATE_NA] = IB_QPS_RESET,
+ },
+ [MLX5_RQC_STATE_RDY] = {
+ [MLX5_SQC_STATE_RST] = MLX5_QP_STATE_BAD,
+ [MLX5_SQC_STATE_RDY] = MLX5_QP_STATE,
+ [MLX5_SQC_STATE_ERR] = IB_QPS_SQE,
+ [MLX5_SQ_STATE_NA] = MLX5_QP_STATE,
+ },
+ [MLX5_RQC_STATE_ERR] = {
+ [MLX5_SQC_STATE_RST] = MLX5_QP_STATE_BAD,
+ [MLX5_SQC_STATE_RDY] = MLX5_QP_STATE_BAD,
+ [MLX5_SQC_STATE_ERR] = IB_QPS_ERR,
+ [MLX5_SQ_STATE_NA] = IB_QPS_ERR,
+ },
+ [MLX5_RQ_STATE_NA] = {
+ [MLX5_SQC_STATE_RST] = IB_QPS_RESET,
+ [MLX5_SQC_STATE_RDY] = MLX5_QP_STATE,
+ [MLX5_SQC_STATE_ERR] = MLX5_QP_STATE,
+ [MLX5_SQ_STATE_NA] = MLX5_QP_STATE_BAD,
+ },
+ };
+
+ *qp_state = sqrq_trans[rq_state][sq_state];
+
+ if (*qp_state == MLX5_QP_STATE_BAD) {
+ WARN(1, "Buggy Raw Packet QP state, SQ 0x%x state: 0x%x, RQ 0x%x state: 0x%x",
+ qp->raw_packet_qp.sq.base.mqp.qpn, sq_state,
+ qp->raw_packet_qp.rq.base.mqp.qpn, rq_state);
+ return -EINVAL;
+ }
+
+ if (*qp_state == MLX5_QP_STATE)
+ *qp_state = qp->state;
+
+ return 0;
+}
+
+static int query_raw_packet_qp_state(struct mlx5_ib_dev *dev,
+ struct mlx5_ib_qp *qp,
+ u8 *raw_packet_qp_state)
+{
+ struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
+ struct mlx5_ib_sq *sq = &raw_packet_qp->sq;
+ struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
+ int err;
+ u8 sq_state = MLX5_SQ_STATE_NA;
+ u8 rq_state = MLX5_RQ_STATE_NA;
+
+ if (qp->sq.wqe_cnt) {
+ err = query_raw_packet_qp_sq_state(dev, sq, &sq_state);
+ if (err)
+ return err;
+ }
+
+ if (qp->rq.wqe_cnt) {
+ err = query_raw_packet_qp_rq_state(dev, rq, &rq_state);
+ if (err)
+ return err;
+ }
+
+ return sqrq_state_to_qp_state(sq_state, rq_state, qp,
+ raw_packet_qp_state);
+}
+
+static int query_qp_attr(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
+ struct ib_qp_attr *qp_attr)
{
- struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
- struct mlx5_ib_qp *qp = to_mqp(ibqp);
struct mlx5_query_qp_mbox_out *outb;
struct mlx5_qp_context *context;
int mlx5_state;
int err = 0;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
- /*
- * Wait for any outstanding page faults, in case the user frees memory
- * based upon this query's result.
- */
- flush_workqueue(mlx5_ib_page_fault_wq);
-#endif
-
- mutex_lock(&qp->mutex);
outb = kzalloc(sizeof(*outb), GFP_KERNEL);
- if (!outb) {
- err = -ENOMEM;
- goto out;
- }
+ if (!outb)
+ return -ENOMEM;
+
context = &outb->ctx;
- err = mlx5_core_qp_query(dev->mdev, &qp->mqp, outb, sizeof(*outb));
+ err = mlx5_core_qp_query(dev->mdev, &qp->trans_qp.base.mqp, outb,
+ sizeof(*outb));
if (err)
- goto out_free;
+ goto out;
mlx5_state = be32_to_cpu(context->flags) >> 28;
qp->state = to_ib_qp_state(mlx5_state);
- qp_attr->qp_state = qp->state;
qp_attr->path_mtu = context->mtu_msgmax >> 5;
qp_attr->path_mig_state =
to_ib_mig_state((be32_to_cpu(context->flags) >> 11) & 0x3);
@@ -3087,6 +3808,43 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
qp_attr->retry_cnt = (be32_to_cpu(context->params1) >> 16) & 0x7;
qp_attr->rnr_retry = (be32_to_cpu(context->params1) >> 13) & 0x7;
qp_attr->alt_timeout = context->alt_path.ackto_lt >> 3;
+
+out:
+ kfree(outb);
+ return err;
+}
+
+int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+ int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr)
+{
+ struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
+ struct mlx5_ib_qp *qp = to_mqp(ibqp);
+ int err = 0;
+ u8 raw_packet_qp_state;
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+ /*
+ * Wait for any outstanding page faults, in case the user frees memory
+ * based upon this query's result.
+ */
+ flush_workqueue(mlx5_ib_page_fault_wq);
+#endif
+
+ mutex_lock(&qp->mutex);
+
+ if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) {
+ err = query_raw_packet_qp_state(dev, qp, &raw_packet_qp_state);
+ if (err)
+ goto out;
+ qp->state = raw_packet_qp_state;
+ qp_attr->port_num = 1;
+ } else {
+ err = query_qp_attr(dev, qp, qp_attr);
+ if (err)
+ goto out;
+ }
+
+ qp_attr->qp_state = qp->state;
qp_attr->cur_qp_state = qp_attr->qp_state;
qp_attr->cap.max_recv_wr = qp->rq.wqe_cnt;
qp_attr->cap.max_recv_sge = qp->rq.max_gs;
@@ -3110,12 +3868,16 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
if (qp->flags & MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK)
qp_init_attr->create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK;
+ if (qp->flags & MLX5_IB_QP_CROSS_CHANNEL)
+ qp_init_attr->create_flags |= IB_QP_CREATE_CROSS_CHANNEL;
+ if (qp->flags & MLX5_IB_QP_MANAGED_SEND)
+ qp_init_attr->create_flags |= IB_QP_CREATE_MANAGED_SEND;
+ if (qp->flags & MLX5_IB_QP_MANAGED_RECV)
+ qp_init_attr->create_flags |= IB_QP_CREATE_MANAGED_RECV;
+
qp_init_attr->sq_sig_type = qp->sq_signal_bits & MLX5_WQE_CTRL_CQ_UPDATE ?
IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR;
-out_free:
- kfree(outb);
-
out:
mutex_unlock(&qp->mutex);
return err;
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index e008505e9..3b2ddd64a 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -75,31 +75,42 @@ static void mlx5_ib_srq_event(struct mlx5_core_srq *srq, enum mlx5_event type)
static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
struct mlx5_create_srq_mbox_in **in,
- struct ib_udata *udata, int buf_size, int *inlen)
+ struct ib_udata *udata, int buf_size, int *inlen,
+ int is_xrc)
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
- struct mlx5_ib_create_srq ucmd;
+ struct mlx5_ib_create_srq ucmd = {};
size_t ucmdlen;
+ void *xsrqc;
int err;
int npages;
int page_shift;
int ncont;
u32 offset;
+ u32 uidx = MLX5_IB_DEFAULT_UIDX;
- ucmdlen =
- (udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
- sizeof(ucmd)) ? (sizeof(ucmd) -
- sizeof(ucmd.reserved)) : sizeof(ucmd);
+ ucmdlen = min(udata->inlen, sizeof(ucmd));
if (ib_copy_from_udata(&ucmd, udata, ucmdlen)) {
mlx5_ib_dbg(dev, "failed copy udata\n");
return -EFAULT;
}
- if (ucmdlen == sizeof(ucmd) &&
- ucmd.reserved != 0)
+ if (ucmd.reserved0 || ucmd.reserved1)
return -EINVAL;
+ if (udata->inlen > sizeof(ucmd) &&
+ !ib_is_udata_cleared(udata, sizeof(ucmd),
+ udata->inlen - sizeof(ucmd)))
+ return -EINVAL;
+
+ if (is_xrc) {
+ err = get_srq_user_index(to_mucontext(pd->uobject->context),
+ &ucmd, udata->inlen, &uidx);
+ if (err)
+ return err;
+ }
+
srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size,
@@ -138,6 +149,13 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
(*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26);
+ if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) &&
+ is_xrc){
+ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in,
+ xrc_srq_context_entry);
+ MLX5_SET(xrc_srqc, xsrqc, user_index, uidx);
+ }
+
return 0;
err_in:
@@ -151,13 +169,14 @@ err_umem:
static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
struct mlx5_create_srq_mbox_in **in, int buf_size,
- int *inlen)
+ int *inlen, int is_xrc)
{
int err;
int i;
struct mlx5_wqe_srq_next_seg *next;
int page_shift;
int npages;
+ void *xsrqc;
err = mlx5_db_alloc(dev->mdev, &srq->db);
if (err) {
@@ -204,6 +223,14 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
(*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
+ if ((MLX5_CAP_GEN(dev->mdev, cqe_version) == MLX5_CQE_VERSION_V1) &&
+ is_xrc){
+ xsrqc = MLX5_ADDR_OF(create_xrc_srq_in, *in,
+ xrc_srq_context_entry);
+ /* 0xffffff means we ask to work with cqe version 0 */
+ MLX5_SET(xrc_srqc, xsrqc, user_index, MLX5_IB_DEFAULT_UIDX);
+ }
+
return 0;
err_in:
@@ -275,10 +302,14 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs,
srq->msrq.max_avail_gather);
+ is_xrc = (init_attr->srq_type == IB_SRQT_XRC);
+
if (pd->uobject)
- err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen);
+ err = create_srq_user(pd, srq, &in, udata, buf_size, &inlen,
+ is_xrc);
else
- err = create_srq_kernel(dev, srq, &in, buf_size, &inlen);
+ err = create_srq_kernel(dev, srq, &in, buf_size, &inlen,
+ is_xrc);
if (err) {
mlx5_ib_warn(dev, "create srq %s failed, err %d\n",
@@ -286,7 +317,6 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
goto err_srq;
}
- is_xrc = (init_attr->srq_type == IB_SRQT_XRC);
in->ctx.state_log_sz = ilog2(srq->msrq.max);
flgs = ((srq->msrq.wqe_shift - 4) | (is_xrc << 5) | (srq->wq_sig << 7)) << 24;
xrcdn = 0;
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index 76fb7b927..b94a55404 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -35,6 +35,8 @@
#include <linux/types.h>
+#include "mlx5_ib.h"
+
enum {
MLX5_QP_FLAG_SIGNATURE = 1 << 0,
MLX5_QP_FLAG_SCATTER_CQE = 1 << 1,
@@ -66,7 +68,15 @@ struct mlx5_ib_alloc_ucontext_req_v2 {
__u32 total_num_uuars;
__u32 num_low_latency_uuars;
__u32 flags;
- __u32 reserved;
+ __u32 comp_mask;
+ __u8 max_cqe_version;
+ __u8 reserved0;
+ __u16 reserved1;
+ __u32 reserved2;
+};
+
+enum mlx5_ib_alloc_ucontext_resp_mask {
+ MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET = 1UL << 0,
};
struct mlx5_ib_alloc_ucontext_resp {
@@ -80,7 +90,13 @@ struct mlx5_ib_alloc_ucontext_resp {
__u32 max_recv_wr;
__u32 max_srq_recv_wr;
__u16 num_ports;
- __u16 reserved;
+ __u16 reserved1;
+ __u32 comp_mask;
+ __u32 response_length;
+ __u8 cqe_version;
+ __u8 reserved2;
+ __u16 reserved3;
+ __u64 hca_core_clock_offset;
};
struct mlx5_ib_alloc_pd_resp {
@@ -110,7 +126,9 @@ struct mlx5_ib_create_srq {
__u64 buf_addr;
__u64 db_addr;
__u32 flags;
- __u32 reserved; /* explicit padding (optional on i386) */
+ __u32 reserved0; /* explicit padding (optional on i386) */
+ __u32 uidx;
+ __u32 reserved1;
};
struct mlx5_ib_create_srq_resp {
@@ -125,9 +143,48 @@ struct mlx5_ib_create_qp {
__u32 rq_wqe_count;
__u32 rq_wqe_shift;
__u32 flags;
+ __u32 uidx;
+ __u32 reserved0;
+ __u64 sq_buf_addr;
};
struct mlx5_ib_create_qp_resp {
__u32 uuar_index;
};
+
+static inline int get_qp_user_index(struct mlx5_ib_ucontext *ucontext,
+ struct mlx5_ib_create_qp *ucmd,
+ int inlen,
+ u32 *user_index)
+{
+ u8 cqe_version = ucontext->cqe_version;
+
+ if (field_avail(struct mlx5_ib_create_qp, uidx, inlen) &&
+ !cqe_version && (ucmd->uidx == MLX5_IB_DEFAULT_UIDX))
+ return 0;
+
+ if (!!(field_avail(struct mlx5_ib_create_qp, uidx, inlen) !=
+ !!cqe_version))
+ return -EINVAL;
+
+ return verify_assign_uidx(cqe_version, ucmd->uidx, user_index);
+}
+
+static inline int get_srq_user_index(struct mlx5_ib_ucontext *ucontext,
+ struct mlx5_ib_create_srq *ucmd,
+ int inlen,
+ u32 *user_index)
+{
+ u8 cqe_version = ucontext->cqe_version;
+
+ if (field_avail(struct mlx5_ib_create_srq, uidx, inlen) &&
+ !cqe_version && (ucmd->uidx == MLX5_IB_DEFAULT_UIDX))
+ return 0;
+
+ if (!!(field_avail(struct mlx5_ib_create_srq, uidx, inlen) !=
+ !!cqe_version))
+ return -EINVAL;
+
+ return verify_assign_uidx(cqe_version, ucmd->uidx, user_index);
+}
#endif /* MLX5_IB_USER_H */
diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index 40ba83338..a6531ffe2 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -608,9 +608,6 @@ static inline int mthca_poll_one(struct mthca_dev *dev,
entry->opcode = IB_WC_FETCH_ADD;
entry->byte_len = MTHCA_ATOMIC_BYTE_LEN;
break;
- case MTHCA_OPCODE_BIND_MW:
- entry->opcode = IB_WC_BIND_MW;
- break;
default:
entry->opcode = MTHCA_OPCODE_INVALID;
break;
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index dc2d48c59..9866c35cc 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -898,89 +898,6 @@ static struct ib_mr *mthca_get_dma_mr(struct ib_pd *pd, int acc)
return &mr->ibmr;
}
-static struct ib_mr *mthca_reg_phys_mr(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf,
- int acc,
- u64 *iova_start)
-{
- struct mthca_mr *mr;
- u64 *page_list;
- u64 total_size;
- unsigned long mask;
- int shift;
- int npages;
- int err;
- int i, j, n;
-
- mask = buffer_list[0].addr ^ *iova_start;
- total_size = 0;
- for (i = 0; i < num_phys_buf; ++i) {
- if (i != 0)
- mask |= buffer_list[i].addr;
- if (i != num_phys_buf - 1)
- mask |= buffer_list[i].addr + buffer_list[i].size;
-
- total_size += buffer_list[i].size;
- }
-
- if (mask & ~PAGE_MASK)
- return ERR_PTR(-EINVAL);
-
- shift = __ffs(mask | 1 << 31);
-
- buffer_list[0].size += buffer_list[0].addr & ((1ULL << shift) - 1);
- buffer_list[0].addr &= ~0ull << shift;
-
- mr = kmalloc(sizeof *mr, GFP_KERNEL);
- if (!mr)
- return ERR_PTR(-ENOMEM);
-
- npages = 0;
- for (i = 0; i < num_phys_buf; ++i)
- npages += (buffer_list[i].size + (1ULL << shift) - 1) >> shift;
-
- if (!npages)
- return &mr->ibmr;
-
- page_list = kmalloc(npages * sizeof *page_list, GFP_KERNEL);
- if (!page_list) {
- kfree(mr);
- return ERR_PTR(-ENOMEM);
- }
-
- n = 0;
- for (i = 0; i < num_phys_buf; ++i)
- for (j = 0;
- j < (buffer_list[i].size + (1ULL << shift) - 1) >> shift;
- ++j)
- page_list[n++] = buffer_list[i].addr + ((u64) j << shift);
-
- mthca_dbg(to_mdev(pd->device), "Registering memory at %llx (iova %llx) "
- "in PD %x; shift %d, npages %d.\n",
- (unsigned long long) buffer_list[0].addr,
- (unsigned long long) *iova_start,
- to_mpd(pd)->pd_num,
- shift, npages);
-
- err = mthca_mr_alloc_phys(to_mdev(pd->device),
- to_mpd(pd)->pd_num,
- page_list, shift, npages,
- *iova_start, total_size,
- convert_access(acc), mr);
-
- if (err) {
- kfree(page_list);
- kfree(mr);
- return ERR_PTR(err);
- }
-
- kfree(page_list);
- mr->umem = NULL;
-
- return &mr->ibmr;
-}
-
static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt, int acc, struct ib_udata *udata)
{
@@ -1346,7 +1263,6 @@ int mthca_register_device(struct mthca_dev *dev)
dev->ib_dev.destroy_cq = mthca_destroy_cq;
dev->ib_dev.poll_cq = mthca_poll_cq;
dev->ib_dev.get_dma_mr = mthca_get_dma_mr;
- dev->ib_dev.reg_phys_mr = mthca_reg_phys_mr;
dev->ib_dev.reg_user_mr = mthca_reg_user_mr;
dev->ib_dev.dereg_mr = mthca_dereg_mr;
dev->ib_dev.get_port_immutable = mthca_port_immutable;
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 35fe506e2..96e5fb91f 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1485,7 +1485,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp,
u16 pkey;
ib_ud_header_init(256, /* assume a MAD */ 1, 0, 0,
- mthca_ah_grh_present(to_mah(wr->ah)), 0,
+ mthca_ah_grh_present(to_mah(wr->ah)), 0, 0, 0,
&sqp->ud_header);
err = mthca_read_ah(dev, to_mah(wr->ah), &sqp->ud_header);
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 8a3ad170d..cb9f0f273 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -134,7 +134,7 @@ static void record_ird_ord(struct nes_cm_node *, u16, u16);
/* External CM API Interface */
/* instance of function pointers for client API */
/* set address of this instance to cm_core->cm_ops at cm_core alloc */
-static struct nes_cm_ops nes_cm_api = {
+static const struct nes_cm_ops nes_cm_api = {
mini_cm_accelerated,
mini_cm_listen,
mini_cm_del_listen,
@@ -3232,7 +3232,6 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
int passive_state;
struct nes_ib_device *nesibdev;
struct ib_mr *ibmr = NULL;
- struct ib_phys_buf ibphysbuf;
struct nes_pd *nespd;
u64 tagged_offset;
u8 mpa_frame_offset = 0;
@@ -3316,21 +3315,19 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
u64temp = (unsigned long)nesqp;
nesibdev = nesvnic->nesibdev;
nespd = nesqp->nespd;
- ibphysbuf.addr = nesqp->ietf_frame_pbase + mpa_frame_offset;
- ibphysbuf.size = buff_len;
tagged_offset = (u64)(unsigned long)*start_buff;
- ibmr = nesibdev->ibdev.reg_phys_mr((struct ib_pd *)nespd,
- &ibphysbuf, 1,
- IB_ACCESS_LOCAL_WRITE,
- &tagged_offset);
- if (!ibmr) {
+ ibmr = nes_reg_phys_mr(&nespd->ibpd,
+ nesqp->ietf_frame_pbase + mpa_frame_offset,
+ buff_len, IB_ACCESS_LOCAL_WRITE,
+ &tagged_offset);
+ if (IS_ERR(ibmr)) {
nes_debug(NES_DBG_CM, "Unable to register memory region"
"for lSMM for cm_node = %p \n",
cm_node);
pci_free_consistent(nesdev->pcidev,
nesqp->private_data_len + nesqp->ietf_frame_size,
nesqp->ietf_frame, nesqp->ietf_frame_pbase);
- return -ENOMEM;
+ return PTR_ERR(ibmr);
}
ibmr->pd = &nespd->ibpd;
diff --git a/drivers/infiniband/hw/nes/nes_cm.h b/drivers/infiniband/hw/nes/nes_cm.h
index 32a6420c2..147c2c884 100644
--- a/drivers/infiniband/hw/nes/nes_cm.h
+++ b/drivers/infiniband/hw/nes/nes_cm.h
@@ -423,7 +423,7 @@ struct nes_cm_core {
struct timer_list tcp_timer;
- struct nes_cm_ops *api;
+ const struct nes_cm_ops *api;
int (*post_event)(struct nes_cm_event *event);
atomic_t events_posted;
diff --git a/drivers/infiniband/hw/nes/nes_utils.c b/drivers/infiniband/hw/nes/nes_utils.c
index 2042c0f29..6d3a169c0 100644
--- a/drivers/infiniband/hw/nes/nes_utils.c
+++ b/drivers/infiniband/hw/nes/nes_utils.c
@@ -727,7 +727,7 @@ int nes_arp_table(struct nes_device *nesdev, u32 ip_addr, u8 *mac_addr, u32 acti
if (action == NES_ARP_DELETE) {
nes_debug(NES_DBG_NETDEV, "DELETE, arp_index=%d\n", arp_index);
nesadapter->arp_table[arp_index].ip_addr = 0;
- memset(nesadapter->arp_table[arp_index].mac_addr, 0x00, ETH_ALEN);
+ eth_zero_addr(nesadapter->arp_table[arp_index].mac_addr);
nes_free_resource(nesadapter, nesadapter->allocated_arps, arp_index);
return arp_index;
}
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 137880a19..8c4daf7f2 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -206,80 +206,6 @@ static int nes_dealloc_mw(struct ib_mw *ibmw)
}
-/**
- * nes_bind_mw
- */
-static int nes_bind_mw(struct ib_qp *ibqp, struct ib_mw *ibmw,
- struct ib_mw_bind *ibmw_bind)
-{
- u64 u64temp;
- struct nes_vnic *nesvnic = to_nesvnic(ibqp->device);
- struct nes_device *nesdev = nesvnic->nesdev;
- /* struct nes_mr *nesmr = to_nesmw(ibmw); */
- struct nes_qp *nesqp = to_nesqp(ibqp);
- struct nes_hw_qp_wqe *wqe;
- unsigned long flags = 0;
- u32 head;
- u32 wqe_misc = 0;
- u32 qsize;
-
- if (nesqp->ibqp_state > IB_QPS_RTS)
- return -EINVAL;
-
- spin_lock_irqsave(&nesqp->lock, flags);
-
- head = nesqp->hwqp.sq_head;
- qsize = nesqp->hwqp.sq_tail;
-
- /* Check for SQ overflow */
- if (((head + (2 * qsize) - nesqp->hwqp.sq_tail) % qsize) == (qsize - 1)) {
- spin_unlock_irqrestore(&nesqp->lock, flags);
- return -ENOMEM;
- }
-
- wqe = &nesqp->hwqp.sq_vbase[head];
- /* nes_debug(NES_DBG_MR, "processing sq wqe at %p, head = %u.\n", wqe, head); */
- nes_fill_init_qp_wqe(wqe, nesqp, head);
- u64temp = ibmw_bind->wr_id;
- set_wqe_64bit_value(wqe->wqe_words, NES_IWARP_SQ_WQE_COMP_SCRATCH_LOW_IDX, u64temp);
- wqe_misc = NES_IWARP_SQ_OP_BIND;
-
- wqe_misc |= NES_IWARP_SQ_WQE_LOCAL_FENCE;
-
- if (ibmw_bind->send_flags & IB_SEND_SIGNALED)
- wqe_misc |= NES_IWARP_SQ_WQE_SIGNALED_COMPL;
-
- if (ibmw_bind->bind_info.mw_access_flags & IB_ACCESS_REMOTE_WRITE)
- wqe_misc |= NES_CQP_STAG_RIGHTS_REMOTE_WRITE;
- if (ibmw_bind->bind_info.mw_access_flags & IB_ACCESS_REMOTE_READ)
- wqe_misc |= NES_CQP_STAG_RIGHTS_REMOTE_READ;
-
- set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_WQE_MISC_IDX, wqe_misc);
- set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_MR_IDX,
- ibmw_bind->bind_info.mr->lkey);
- set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_MW_IDX, ibmw->rkey);
- set_wqe_32bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_LENGTH_LOW_IDX,
- ibmw_bind->bind_info.length);
- wqe->wqe_words[NES_IWARP_SQ_BIND_WQE_LENGTH_HIGH_IDX] = 0;
- u64temp = (u64)ibmw_bind->bind_info.addr;
- set_wqe_64bit_value(wqe->wqe_words, NES_IWARP_SQ_BIND_WQE_VA_FBO_LOW_IDX, u64temp);
-
- head++;
- if (head >= qsize)
- head = 0;
-
- nesqp->hwqp.sq_head = head;
- barrier();
-
- nes_write32(nesdev->regs+NES_WQE_ALLOC,
- (1 << 24) | 0x00800000 | nesqp->hwqp.qp_id);
-
- spin_unlock_irqrestore(&nesqp->lock, flags);
-
- return 0;
-}
-
-
/*
* nes_alloc_fast_mr
*/
@@ -2074,9 +2000,8 @@ static int nes_reg_mr(struct nes_device *nesdev, struct nes_pd *nespd,
/**
* nes_reg_phys_mr
*/
-static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
- struct ib_phys_buf *buffer_list, int num_phys_buf, int acc,
- u64 * iova_start)
+struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd, u64 addr, u64 size,
+ int acc, u64 *iova_start)
{
u64 region_length;
struct nes_pd *nespd = to_nespd(ib_pd);
@@ -2088,13 +2013,10 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
struct nes_vpbl vpbl;
struct nes_root_vpbl root_vpbl;
u32 stag;
- u32 i;
unsigned long mask;
u32 stag_index = 0;
u32 next_stag_index = 0;
u32 driver_key = 0;
- u32 root_pbl_index = 0;
- u32 cur_pbl_index = 0;
int err = 0;
int ret = 0;
u16 pbl_count = 0;
@@ -2113,11 +2035,8 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
next_stag_index >>= 8;
next_stag_index %= nesadapter->max_mr;
- if (num_phys_buf > (1024*512)) {
- return ERR_PTR(-E2BIG);
- }
- if ((buffer_list[0].addr ^ *iova_start) & ~PAGE_MASK)
+ if ((addr ^ *iova_start) & ~PAGE_MASK)
return ERR_PTR(-EINVAL);
err = nes_alloc_resource(nesadapter, nesadapter->allocated_mrs, nesadapter->max_mr,
@@ -2132,84 +2051,33 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
return ERR_PTR(-ENOMEM);
}
- for (i = 0; i < num_phys_buf; i++) {
+ /* Allocate a 4K buffer for the PBL */
+ vpbl.pbl_vbase = pci_alloc_consistent(nesdev->pcidev, 4096,
+ &vpbl.pbl_pbase);
+ nes_debug(NES_DBG_MR, "Allocating leaf PBL, va = %p, pa = 0x%016lX\n",
+ vpbl.pbl_vbase, (unsigned long)vpbl.pbl_pbase);
+ if (!vpbl.pbl_vbase) {
+ nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
+ ibmr = ERR_PTR(-ENOMEM);
+ kfree(nesmr);
+ goto reg_phys_err;
+ }
- if ((i & 0x01FF) == 0) {
- if (root_pbl_index == 1) {
- /* Allocate the root PBL */
- root_vpbl.pbl_vbase = pci_alloc_consistent(nesdev->pcidev, 8192,
- &root_vpbl.pbl_pbase);
- nes_debug(NES_DBG_MR, "Allocating root PBL, va = %p, pa = 0x%08X\n",
- root_vpbl.pbl_vbase, (unsigned int)root_vpbl.pbl_pbase);
- if (!root_vpbl.pbl_vbase) {
- pci_free_consistent(nesdev->pcidev, 4096, vpbl.pbl_vbase,
- vpbl.pbl_pbase);
- nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
- kfree(nesmr);
- return ERR_PTR(-ENOMEM);
- }
- root_vpbl.leaf_vpbl = kzalloc(sizeof(*root_vpbl.leaf_vpbl)*1024, GFP_KERNEL);
- if (!root_vpbl.leaf_vpbl) {
- pci_free_consistent(nesdev->pcidev, 8192, root_vpbl.pbl_vbase,
- root_vpbl.pbl_pbase);
- pci_free_consistent(nesdev->pcidev, 4096, vpbl.pbl_vbase,
- vpbl.pbl_pbase);
- nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
- kfree(nesmr);
- return ERR_PTR(-ENOMEM);
- }
- root_vpbl.pbl_vbase[0].pa_low = cpu_to_le32((u32)vpbl.pbl_pbase);
- root_vpbl.pbl_vbase[0].pa_high =
- cpu_to_le32((u32)((((u64)vpbl.pbl_pbase) >> 32)));
- root_vpbl.leaf_vpbl[0] = vpbl;
- }
- /* Allocate a 4K buffer for the PBL */
- vpbl.pbl_vbase = pci_alloc_consistent(nesdev->pcidev, 4096,
- &vpbl.pbl_pbase);
- nes_debug(NES_DBG_MR, "Allocating leaf PBL, va = %p, pa = 0x%016lX\n",
- vpbl.pbl_vbase, (unsigned long)vpbl.pbl_pbase);
- if (!vpbl.pbl_vbase) {
- nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
- ibmr = ERR_PTR(-ENOMEM);
- kfree(nesmr);
- goto reg_phys_err;
- }
- /* Fill in the root table */
- if (1 <= root_pbl_index) {
- root_vpbl.pbl_vbase[root_pbl_index].pa_low =
- cpu_to_le32((u32)vpbl.pbl_pbase);
- root_vpbl.pbl_vbase[root_pbl_index].pa_high =
- cpu_to_le32((u32)((((u64)vpbl.pbl_pbase) >> 32)));
- root_vpbl.leaf_vpbl[root_pbl_index] = vpbl;
- }
- root_pbl_index++;
- cur_pbl_index = 0;
- }
- mask = !buffer_list[i].size;
- if (i != 0)
- mask |= buffer_list[i].addr;
- if (i != num_phys_buf - 1)
- mask |= buffer_list[i].addr + buffer_list[i].size;
-
- if (mask & ~PAGE_MASK) {
- nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
- nes_debug(NES_DBG_MR, "Invalid buffer addr or size\n");
- ibmr = ERR_PTR(-EINVAL);
- kfree(nesmr);
- goto reg_phys_err;
- }
+ mask = !size;
- region_length += buffer_list[i].size;
- if ((i != 0) && (single_page)) {
- if ((buffer_list[i-1].addr+PAGE_SIZE) != buffer_list[i].addr)
- single_page = 0;
- }
- vpbl.pbl_vbase[cur_pbl_index].pa_low = cpu_to_le32((u32)buffer_list[i].addr & PAGE_MASK);
- vpbl.pbl_vbase[cur_pbl_index++].pa_high =
- cpu_to_le32((u32)((((u64)buffer_list[i].addr) >> 32)));
+ if (mask & ~PAGE_MASK) {
+ nes_free_resource(nesadapter, nesadapter->allocated_mrs, stag_index);
+ nes_debug(NES_DBG_MR, "Invalid buffer addr or size\n");
+ ibmr = ERR_PTR(-EINVAL);
+ kfree(nesmr);
+ goto reg_phys_err;
}
+ region_length += size;
+ vpbl.pbl_vbase[0].pa_low = cpu_to_le32((u32)addr & PAGE_MASK);
+ vpbl.pbl_vbase[0].pa_high = cpu_to_le32((u32)((((u64)addr) >> 32)));
+
stag = stag_index << 8;
stag |= driver_key;
stag += (u32)stag_key;
@@ -2219,17 +2087,15 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
stag, (unsigned long)*iova_start, (unsigned long)region_length, stag_index);
/* Make the leaf PBL the root if only one PBL */
- if (root_pbl_index == 1) {
- root_vpbl.pbl_pbase = vpbl.pbl_pbase;
- }
+ root_vpbl.pbl_pbase = vpbl.pbl_pbase;
if (single_page) {
pbl_count = 0;
} else {
- pbl_count = root_pbl_index;
+ pbl_count = 1;
}
ret = nes_reg_mr(nesdev, nespd, stag, region_length, &root_vpbl,
- buffer_list[0].addr, pbl_count, (u16)cur_pbl_index, acc, iova_start,
+ addr, pbl_count, 1, acc, iova_start,
&nesmr->pbls_used, &nesmr->pbl_4k);
if (ret == 0) {
@@ -2242,21 +2108,9 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
ibmr = ERR_PTR(-ENOMEM);
}
- reg_phys_err:
- /* free the resources */
- if (root_pbl_index == 1) {
- /* single PBL case */
- pci_free_consistent(nesdev->pcidev, 4096, vpbl.pbl_vbase, vpbl.pbl_pbase);
- } else {
- for (i=0; i<root_pbl_index; i++) {
- pci_free_consistent(nesdev->pcidev, 4096, root_vpbl.leaf_vpbl[i].pbl_vbase,
- root_vpbl.leaf_vpbl[i].pbl_pbase);
- }
- kfree(root_vpbl.leaf_vpbl);
- pci_free_consistent(nesdev->pcidev, 8192, root_vpbl.pbl_vbase,
- root_vpbl.pbl_pbase);
- }
-
+reg_phys_err:
+ /* single PBL case */
+ pci_free_consistent(nesdev->pcidev, 4096, vpbl.pbl_vbase, vpbl.pbl_pbase);
return ibmr;
}
@@ -2266,17 +2120,13 @@ static struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
*/
static struct ib_mr *nes_get_dma_mr(struct ib_pd *pd, int acc)
{
- struct ib_phys_buf bl;
u64 kva = 0;
nes_debug(NES_DBG_MR, "\n");
- bl.size = (u64)0xffffffffffULL;
- bl.addr = 0;
- return nes_reg_phys_mr(pd, &bl, 1, acc, &kva);
+ return nes_reg_phys_mr(pd, 0, 0xffffffffffULL, acc, &kva);
}
-
/**
* nes_reg_user_mr
*/
@@ -3888,12 +3738,10 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
nesibdev->ibdev.destroy_cq = nes_destroy_cq;
nesibdev->ibdev.poll_cq = nes_poll_cq;
nesibdev->ibdev.get_dma_mr = nes_get_dma_mr;
- nesibdev->ibdev.reg_phys_mr = nes_reg_phys_mr;
nesibdev->ibdev.reg_user_mr = nes_reg_user_mr;
nesibdev->ibdev.dereg_mr = nes_dereg_mr;
nesibdev->ibdev.alloc_mw = nes_alloc_mw;
nesibdev->ibdev.dealloc_mw = nes_dealloc_mw;
- nesibdev->ibdev.bind_mw = nes_bind_mw;
nesibdev->ibdev.alloc_mr = nes_alloc_mr;
nesibdev->ibdev.map_mr_sg = nes_map_mr_sg;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.h b/drivers/infiniband/hw/nes/nes_verbs.h
index a204b677a..70290883d 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.h
+++ b/drivers/infiniband/hw/nes/nes_verbs.h
@@ -190,4 +190,8 @@ struct nes_qp {
u8 pau_state;
__u64 nesuqp_addr;
};
+
+struct ib_mr *nes_reg_phys_mr(struct ib_pd *ib_pd,
+ u64 addr, u64 size, int acc, u64 *iova_start);
+
#endif /* NES_VERBS_H */
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index 040bb8b5c..12503f15f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -323,9 +323,6 @@ struct ocrdma_cq {
*/
u32 max_hw_cqe;
bool phase_change;
- bool deferred_arm, deferred_sol;
- bool first_arm;
-
spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization
* to cq polling
*/
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 9820074be..3790771f2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -152,9 +152,10 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
if ((pd->uctx) &&
(!rdma_is_multicast_addr((struct in6_addr *)attr->grh.dgid.raw)) &&
(!rdma_link_local_addr((struct in6_addr *)attr->grh.dgid.raw))) {
- status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid,
- attr->dmac, &vlan_tag,
- sgid_attr.ndev->ifindex);
+ status = rdma_addr_find_l2_eth_by_grh(&sgid, &attr->grh.dgid,
+ attr->dmac, &vlan_tag,
+ &sgid_attr.ndev->ifindex,
+ NULL);
if (status) {
pr_err("%s(): Failed to resolve dmac from gid."
"status = %d\n", __func__, status);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 3afb40b85..f38743018 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -175,7 +175,6 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
dev->ibdev.req_notify_cq = ocrdma_arm_cq;
dev->ibdev.get_dma_mr = ocrdma_get_dma_mr;
- dev->ibdev.reg_phys_mr = ocrdma_reg_kernel_mr;
dev->ibdev.dereg_mr = ocrdma_dereg_mr;
dev->ibdev.reg_user_mr = ocrdma_reg_user_mr;
@@ -229,6 +228,11 @@ static int ocrdma_alloc_resources(struct ocrdma_dev *dev)
ocrdma_alloc_pd_pool(dev);
+ if (!ocrdma_alloc_stats_resources(dev)) {
+ pr_err("%s: stats resource allocation failed\n", __func__);
+ goto alloc_err;
+ }
+
spin_lock_init(&dev->av_tbl.lock);
spin_lock_init(&dev->flush_q_lock);
return 0;
@@ -239,6 +243,7 @@ alloc_err:
static void ocrdma_free_resources(struct ocrdma_dev *dev)
{
+ ocrdma_release_stats_resources(dev);
kfree(dev->stag_arr);
kfree(dev->qp_tbl);
kfree(dev->cq_tbl);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 86c303a62..255f77408 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -64,10 +64,11 @@ static int ocrdma_add_stat(char *start, char *pcur,
return cpy_len;
}
-static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev)
{
struct stats_mem *mem = &dev->stats_mem;
+ mutex_init(&dev->stats_lock);
/* Alloc mbox command mem*/
mem->size = max_t(u32, sizeof(struct ocrdma_rdma_stats_req),
sizeof(struct ocrdma_rdma_stats_resp));
@@ -91,13 +92,14 @@ static bool ocrdma_alloc_stats_mem(struct ocrdma_dev *dev)
return true;
}
-static void ocrdma_release_stats_mem(struct ocrdma_dev *dev)
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev)
{
struct stats_mem *mem = &dev->stats_mem;
if (mem->va)
dma_free_coherent(&dev->nic_info.pdev->dev, mem->size,
mem->va, mem->pa);
+ mem->va = NULL;
kfree(mem->debugfs_mem);
}
@@ -838,15 +840,9 @@ void ocrdma_add_port_stats(struct ocrdma_dev *dev)
&dev->reset_stats, &ocrdma_dbg_ops))
goto err;
- /* Now create dma_mem for stats mbx command */
- if (!ocrdma_alloc_stats_mem(dev))
- goto err;
-
- mutex_init(&dev->stats_lock);
return;
err:
- ocrdma_release_stats_mem(dev);
debugfs_remove_recursive(dev->dir);
dev->dir = NULL;
}
@@ -855,9 +851,7 @@ void ocrdma_rem_port_stats(struct ocrdma_dev *dev)
{
if (!dev->dir)
return;
- debugfs_remove(dev->dir);
- mutex_destroy(&dev->stats_lock);
- ocrdma_release_stats_mem(dev);
+ debugfs_remove_recursive(dev->dir);
}
void ocrdma_init_debugfs(void)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index c9e58d04c..bba1fec4f 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -65,6 +65,8 @@ enum OCRDMA_STATS_TYPE {
void ocrdma_rem_debugfs(void);
void ocrdma_init_debugfs(void);
+bool ocrdma_alloc_stats_resources(struct ocrdma_dev *dev);
+void ocrdma_release_stats_resources(struct ocrdma_dev *dev);
void ocrdma_rem_port_stats(struct ocrdma_dev *dev);
void ocrdma_add_port_stats(struct ocrdma_dev *dev);
int ocrdma_pma_counters(struct ocrdma_dev *dev,
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 76e96f97b..12420e4ec 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
IB_DEVICE_SYS_IMAGE_GUID |
IB_DEVICE_LOCAL_DMA_LKEY |
IB_DEVICE_MEM_MGT_EXTENSIONS;
- attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_srq_sge);
- attr->max_sge_rd = 0;
+ attr->max_sge = dev->attr.max_send_sge;
+ attr->max_sge_rd = attr->max_sge;
attr->max_cq = dev->attr.max_cq;
attr->max_cqe = dev->attr.max_cqe;
attr->max_mr = dev->attr.max_mr;
@@ -1094,7 +1094,6 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
spin_lock_init(&cq->comp_handler_lock);
INIT_LIST_HEAD(&cq->sq_head);
INIT_LIST_HEAD(&cq->rq_head);
- cq->first_arm = true;
if (ib_ctx) {
uctx = get_ocrdma_ucontext(ib_ctx);
@@ -2726,8 +2725,7 @@ static int ocrdma_update_ud_rcqe(struct ib_wc *ibwc, struct ocrdma_cqe *cqe)
OCRDMA_CQE_UD_STATUS_MASK) >> OCRDMA_CQE_UD_STATUS_SHIFT;
ibwc->src_qp = le32_to_cpu(cqe->flags_status_srcqpn) &
OCRDMA_CQE_SRCQP_MASK;
- ibwc->pkey_index = le32_to_cpu(cqe->ud.rxlen_pkey) &
- OCRDMA_CQE_PKEY_MASK;
+ ibwc->pkey_index = 0;
ibwc->wc_flags = IB_WC_GRH;
ibwc->byte_len = (le32_to_cpu(cqe->ud.rxlen_pkey) >>
OCRDMA_CQE_UD_XFER_LEN_SHIFT);
@@ -2911,12 +2909,9 @@ expand_cqe:
}
stop_cqe:
cq->getp = cur_getp;
- if (cq->deferred_arm || polled_hw_cqes) {
- ocrdma_ring_cq_db(dev, cq->id, cq->deferred_arm,
- cq->deferred_sol, polled_hw_cqes);
- cq->deferred_arm = false;
- cq->deferred_sol = false;
- }
+
+ if (polled_hw_cqes)
+ ocrdma_ring_cq_db(dev, cq->id, false, false, polled_hw_cqes);
return i;
}
@@ -3000,13 +2995,7 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags)
if (cq_flags & IB_CQ_SOLICITED)
sol_needed = true;
- if (cq->first_arm) {
- ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
- cq->first_arm = false;
- }
-
- cq->deferred_arm = true;
- cq->deferred_sol = sol_needed;
+ ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0);
spin_unlock_irqrestore(&cq->cq_lock, flags);
return 0;
@@ -3066,169 +3055,6 @@ pl_err:
return ERR_PTR(-ENOMEM);
}
-#define MAX_KERNEL_PBE_SIZE 65536
-static inline int count_kernel_pbes(struct ib_phys_buf *buf_list,
- int buf_cnt, u32 *pbe_size)
-{
- u64 total_size = 0;
- u64 buf_size = 0;
- int i;
- *pbe_size = roundup(buf_list[0].size, PAGE_SIZE);
- *pbe_size = roundup_pow_of_two(*pbe_size);
-
- /* find the smallest PBE size that we can have */
- for (i = 0; i < buf_cnt; i++) {
- /* first addr may not be page aligned, so ignore checking */
- if ((i != 0) && ((buf_list[i].addr & ~PAGE_MASK) ||
- (buf_list[i].size & ~PAGE_MASK))) {
- return 0;
- }
-
- /* if configured PBE size is greater then the chosen one,
- * reduce the PBE size.
- */
- buf_size = roundup(buf_list[i].size, PAGE_SIZE);
- /* pbe_size has to be even multiple of 4K 1,2,4,8...*/
- buf_size = roundup_pow_of_two(buf_size);
- if (*pbe_size > buf_size)
- *pbe_size = buf_size;
-
- total_size += buf_size;
- }
- *pbe_size = *pbe_size > MAX_KERNEL_PBE_SIZE ?
- (MAX_KERNEL_PBE_SIZE) : (*pbe_size);
-
- /* num_pbes = total_size / (*pbe_size); this is implemented below. */
-
- return total_size >> ilog2(*pbe_size);
-}
-
-static void build_kernel_pbes(struct ib_phys_buf *buf_list, int ib_buf_cnt,
- u32 pbe_size, struct ocrdma_pbl *pbl_tbl,
- struct ocrdma_hw_mr *hwmr)
-{
- int i;
- int idx;
- int pbes_per_buf = 0;
- u64 buf_addr = 0;
- int num_pbes;
- struct ocrdma_pbe *pbe;
- int total_num_pbes = 0;
-
- if (!hwmr->num_pbes)
- return;
-
- pbe = (struct ocrdma_pbe *)pbl_tbl->va;
- num_pbes = 0;
-
- /* go through the OS phy regions & fill hw pbe entries into pbls. */
- for (i = 0; i < ib_buf_cnt; i++) {
- buf_addr = buf_list[i].addr;
- pbes_per_buf =
- roundup_pow_of_two(roundup(buf_list[i].size, PAGE_SIZE)) /
- pbe_size;
- hwmr->len += buf_list[i].size;
- /* number of pbes can be more for one OS buf, when
- * buffers are of different sizes.
- * split the ib_buf to one or more pbes.
- */
- for (idx = 0; idx < pbes_per_buf; idx++) {
- /* we program always page aligned addresses,
- * first unaligned address is taken care by fbo.
- */
- if (i == 0) {
- /* for non zero fbo, assign the
- * start of the page.
- */
- pbe->pa_lo =
- cpu_to_le32((u32) (buf_addr & PAGE_MASK));
- pbe->pa_hi =
- cpu_to_le32((u32) upper_32_bits(buf_addr));
- } else {
- pbe->pa_lo =
- cpu_to_le32((u32) (buf_addr & 0xffffffff));
- pbe->pa_hi =
- cpu_to_le32((u32) upper_32_bits(buf_addr));
- }
- buf_addr += pbe_size;
- num_pbes += 1;
- total_num_pbes += 1;
- pbe++;
-
- if (total_num_pbes == hwmr->num_pbes)
- goto mr_tbl_done;
- /* if the pbl is full storing the pbes,
- * move to next pbl.
- */
- if (num_pbes == (hwmr->pbl_size/sizeof(u64))) {
- pbl_tbl++;
- pbe = (struct ocrdma_pbe *)pbl_tbl->va;
- num_pbes = 0;
- }
- }
- }
-mr_tbl_done:
- return;
-}
-
-struct ib_mr *ocrdma_reg_kernel_mr(struct ib_pd *ibpd,
- struct ib_phys_buf *buf_list,
- int buf_cnt, int acc, u64 *iova_start)
-{
- int status = -ENOMEM;
- struct ocrdma_mr *mr;
- struct ocrdma_pd *pd = get_ocrdma_pd(ibpd);
- struct ocrdma_dev *dev = get_ocrdma_dev(ibpd->device);
- u32 num_pbes;
- u32 pbe_size = 0;
-
- if ((acc & IB_ACCESS_REMOTE_WRITE) && !(acc & IB_ACCESS_LOCAL_WRITE))
- return ERR_PTR(-EINVAL);
-
- mr = kzalloc(sizeof(*mr), GFP_KERNEL);
- if (!mr)
- return ERR_PTR(status);
-
- num_pbes = count_kernel_pbes(buf_list, buf_cnt, &pbe_size);
- if (num_pbes == 0) {
- status = -EINVAL;
- goto pbl_err;
- }
- status = ocrdma_get_pbl_info(dev, mr, num_pbes);
- if (status)
- goto pbl_err;
-
- mr->hwmr.pbe_size = pbe_size;
- mr->hwmr.fbo = *iova_start - (buf_list[0].addr & PAGE_MASK);
- mr->hwmr.va = *iova_start;
- mr->hwmr.local_rd = 1;
- mr->hwmr.remote_wr = (acc & IB_ACCESS_REMOTE_WRITE) ? 1 : 0;
- mr->hwmr.remote_rd = (acc & IB_ACCESS_REMOTE_READ) ? 1 : 0;
- mr->hwmr.local_wr = (acc & IB_ACCESS_LOCAL_WRITE) ? 1 : 0;
- mr->hwmr.remote_atomic = (acc & IB_ACCESS_REMOTE_ATOMIC) ? 1 : 0;
- mr->hwmr.mw_bind = (acc & IB_ACCESS_MW_BIND) ? 1 : 0;
-
- status = ocrdma_build_pbl_tbl(dev, &mr->hwmr);
- if (status)
- goto pbl_err;
- build_kernel_pbes(buf_list, buf_cnt, pbe_size, mr->hwmr.pbl_table,
- &mr->hwmr);
- status = ocrdma_reg_mr(dev, &mr->hwmr, pd->id, acc);
- if (status)
- goto mbx_err;
-
- mr->ibmr.lkey = mr->hwmr.lkey;
- if (mr->hwmr.remote_wr || mr->hwmr.remote_rd)
- mr->ibmr.rkey = mr->hwmr.lkey;
- return &mr->ibmr;
-
-mbx_err:
- ocrdma_free_mr_pbl_tbl(dev, &mr->hwmr);
-pbl_err:
- kfree(mr);
- return ERR_PTR(status);
-}
-
static int ocrdma_set_page(struct ib_mr *ibmr, u64 addr)
{
struct ocrdma_mr *mr = get_ocrdma_mr(ibmr);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index a2f3b4dc2..8b517fd36 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -117,9 +117,6 @@ int ocrdma_post_srq_recv(struct ib_srq *, struct ib_recv_wr *,
int ocrdma_dereg_mr(struct ib_mr *);
struct ib_mr *ocrdma_get_dma_mr(struct ib_pd *, int acc);
-struct ib_mr *ocrdma_reg_kernel_mr(struct ib_pd *,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf, int acc, u64 *iova_start);
struct ib_mr *ocrdma_reg_user_mr(struct ib_pd *, u64 start, u64 length,
u64 virt, int acc, struct ib_udata *);
struct ib_mr *ocrdma_alloc_mr(struct ib_pd *pd,
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index 13ef22bd9..fcdf37913 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -89,14 +89,14 @@ static int create_file(const char *name, umode_t mode,
{
int error;
- mutex_lock(&d_inode(parent)->i_mutex);
+ inode_lock(d_inode(parent));
*dentry = lookup_one_len(name, parent, strlen(name));
if (!IS_ERR(*dentry))
error = qibfs_mknod(d_inode(parent), *dentry,
mode, fops, data);
else
error = PTR_ERR(*dentry);
- mutex_unlock(&d_inode(parent)->i_mutex);
+ inode_unlock(d_inode(parent));
return error;
}
@@ -481,7 +481,7 @@ static int remove_device_files(struct super_block *sb,
int ret, i;
root = dget(sb->s_root);
- mutex_lock(&d_inode(root)->i_mutex);
+ inode_lock(d_inode(root));
snprintf(unit, sizeof(unit), "%u", dd->unit);
dir = lookup_one_len(unit, root, strlen(unit));
@@ -491,7 +491,7 @@ static int remove_device_files(struct super_block *sb,
goto bail;
}
- mutex_lock(&d_inode(dir)->i_mutex);
+ inode_lock(d_inode(dir));
remove_file(dir, "counters");
remove_file(dir, "counter_names");
remove_file(dir, "portcounter_names");
@@ -506,13 +506,13 @@ static int remove_device_files(struct super_block *sb,
}
}
remove_file(dir, "flash");
- mutex_unlock(&d_inode(dir)->i_mutex);
+ inode_unlock(d_inode(dir));
ret = simple_rmdir(d_inode(root), dir);
d_delete(dir);
dput(dir);
bail:
- mutex_unlock(&d_inode(root)->i_mutex);
+ inode_unlock(d_inode(root));
dput(root);
return ret;
}
diff --git a/drivers/infiniband/hw/qib/qib_mr.c b/drivers/infiniband/hw/qib/qib_mr.c
index 294f5c706..5f53304e8 100644
--- a/drivers/infiniband/hw/qib/qib_mr.c
+++ b/drivers/infiniband/hw/qib/qib_mr.c
@@ -150,10 +150,7 @@ static struct qib_mr *alloc_mr(int count, struct ib_pd *pd)
rval = init_qib_mregion(&mr->mr, pd, count);
if (rval)
goto bail;
- /*
- * ib_reg_phys_mr() will initialize mr->ibmr except for
- * lkey and rkey.
- */
+
rval = qib_alloc_lkey(&mr->mr, 0);
if (rval)
goto bail_mregion;
@@ -171,52 +168,6 @@ bail:
}
/**
- * qib_reg_phys_mr - register a physical memory region
- * @pd: protection domain for this memory region
- * @buffer_list: pointer to the list of physical buffers to register
- * @num_phys_buf: the number of physical buffers to register
- * @iova_start: the starting address passed over IB which maps to this MR
- *
- * Returns the memory region on success, otherwise returns an errno.
- */
-struct ib_mr *qib_reg_phys_mr(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf, int acc, u64 *iova_start)
-{
- struct qib_mr *mr;
- int n, m, i;
- struct ib_mr *ret;
-
- mr = alloc_mr(num_phys_buf, pd);
- if (IS_ERR(mr)) {
- ret = (struct ib_mr *)mr;
- goto bail;
- }
-
- mr->mr.user_base = *iova_start;
- mr->mr.iova = *iova_start;
- mr->mr.access_flags = acc;
-
- m = 0;
- n = 0;
- for (i = 0; i < num_phys_buf; i++) {
- mr->mr.map[m]->segs[n].vaddr = (void *) buffer_list[i].addr;
- mr->mr.map[m]->segs[n].length = buffer_list[i].size;
- mr->mr.length += buffer_list[i].size;
- n++;
- if (n == QIB_SEGSZ) {
- m++;
- n = 0;
- }
- }
-
- ret = &mr->ibmr;
-
-bail:
- return ret;
-}
-
-/**
* qib_reg_user_mr - register a userspace memory region
* @pd: protection domain for this memory region
* @start: starting userspace address
diff --git a/drivers/infiniband/hw/qib/qib_verbs.c b/drivers/infiniband/hw/qib/qib_verbs.c
index de6cb6fcd..baf1e42b6 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.c
+++ b/drivers/infiniband/hw/qib/qib_verbs.c
@@ -346,6 +346,7 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
unsigned long flags;
struct qib_lkey_table *rkt;
struct qib_pd *pd;
+ int avoid_schedule = 0;
spin_lock_irqsave(&qp->s_lock, flags);
@@ -438,11 +439,15 @@ static int qib_post_one_send(struct qib_qp *qp, struct ib_send_wr *wr,
qp->ibqp.qp_type == IB_QPT_RC) {
if (wqe->length > 0x80000000U)
goto bail_inval_free;
+ if (wqe->length <= qp->pmtu)
+ avoid_schedule = 1;
} else if (wqe->length > (dd_from_ibdev(qp->ibqp.device)->pport +
- qp->port_num - 1)->ibmtu)
+ qp->port_num - 1)->ibmtu) {
goto bail_inval_free;
- else
+ } else {
atomic_inc(&to_iah(ud_wr(wr)->ah)->refcount);
+ avoid_schedule = 1;
+ }
wqe->ssn = qp->s_ssn++;
qp->s_head = next;
@@ -458,7 +463,7 @@ bail_inval_free:
bail_inval:
ret = -EINVAL;
bail:
- if (!ret && !wr->next &&
+ if (!ret && !wr->next && !avoid_schedule &&
!qib_sdma_empty(
dd_from_ibdev(qp->ibqp.device)->pport + qp->port_num - 1)) {
qib_schedule_send(qp);
@@ -2256,7 +2261,6 @@ int qib_register_ib_device(struct qib_devdata *dd)
ibdev->poll_cq = qib_poll_cq;
ibdev->req_notify_cq = qib_req_notify_cq;
ibdev->get_dma_mr = qib_get_dma_mr;
- ibdev->reg_phys_mr = qib_reg_phys_mr;
ibdev->reg_user_mr = qib_reg_user_mr;
ibdev->dereg_mr = qib_dereg_mr;
ibdev->alloc_mr = qib_alloc_mr;
diff --git a/drivers/infiniband/hw/qib/qib_verbs.h b/drivers/infiniband/hw/qib/qib_verbs.h
index bc803f33d..6c5e77753 100644
--- a/drivers/infiniband/hw/qib/qib_verbs.h
+++ b/drivers/infiniband/hw/qib/qib_verbs.h
@@ -1032,10 +1032,6 @@ int qib_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata);
struct ib_mr *qib_get_dma_mr(struct ib_pd *pd, int acc);
-struct ib_mr *qib_reg_phys_mr(struct ib_pd *pd,
- struct ib_phys_buf *buffer_list,
- int num_phys_buf, int acc, u64 *iova_start);
-
struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int mr_access_flags,
struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/usnic/usnic_debugfs.c b/drivers/infiniband/hw/usnic/usnic_debugfs.c
index 5e55b8bc6..92dc66cc2 100644
--- a/drivers/infiniband/hw/usnic/usnic_debugfs.c
+++ b/drivers/infiniband/hw/usnic/usnic_debugfs.c
@@ -157,8 +157,9 @@ void usnic_debugfs_flow_add(struct usnic_ib_qp_grp_flow *qp_flow)
qp_flow,
&flowinfo_ops);
if (IS_ERR_OR_NULL(qp_flow->dbgfs_dentry)) {
- usnic_err("Failed to create dbg fs entry for flow %u\n",
- qp_flow->flow->flow_id);
+ usnic_err("Failed to create dbg fs entry for flow %u with error %ld\n",
+ qp_flow->flow->flow_id,
+ PTR_ERR(qp_flow->dbgfs_dentry));
}
}
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
index fcea3a24d..5f44b66cc 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c
@@ -521,7 +521,7 @@ int usnic_ib_qp_grp_modify(struct usnic_ib_qp_grp *qp_grp,
if (!status) {
qp_grp->state = new_state;
- usnic_info("Transistioned %u from %s to %s",
+ usnic_info("Transitioned %u from %s to %s",
qp_grp->grp_id,
usnic_ib_qp_grp_state_to_string(old_state),
usnic_ib_qp_grp_state_to_string(new_state));
@@ -575,7 +575,7 @@ alloc_res_chunk_list(struct usnic_vnic *vnic,
return res_chunk_list;
out_free_res:
- for (i--; i > 0; i--)
+ for (i--; i >= 0; i--)
usnic_vnic_put_resources(res_chunk_list[i]);
kfree(res_chunk_list);
return ERR_PTR(err);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index f8e321168..6cdb4d23f 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -51,7 +51,7 @@
static void usnic_ib_fw_string_to_u64(char *fw_ver_str, u64 *fw_ver)
{
- *fw_ver = (u64) *fw_ver_str;
+ *fw_ver = *((u64 *)fw_ver_str);
}
static int usnic_ib_fill_create_qp_resp(struct usnic_ib_qp_grp *qp_grp,
@@ -571,20 +571,20 @@ int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
qp_grp = to_uqp_grp(ibqp);
- /* TODO: Future Support All States */
mutex_lock(&qp_grp->vf->pf->usdev_lock);
- if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_INIT) {
- status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_INIT, NULL);
- } else if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_RTR) {
- status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_RTR, NULL);
- } else if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_RTS) {
- status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_RTS, NULL);
+ if ((attr_mask & IB_QP_PORT) && attr->port_num != 1) {
+ /* usnic devices only have one port */
+ status = -EINVAL;
+ goto out_unlock;
+ }
+ if (attr_mask & IB_QP_STATE) {
+ status = usnic_ib_qp_grp_modify(qp_grp, attr->qp_state, NULL);
} else {
- usnic_err("Unexpected combination mask: %u state: %u\n",
- attr_mask & IB_QP_STATE, attr->qp_state);
+ usnic_err("Unhandled request, attr_mask=0x%x\n", attr_mask);
status = -EINVAL;
}
+out_unlock:
mutex_unlock(&qp_grp->vf->pf->usdev_lock);
return status;
}
@@ -625,8 +625,8 @@ struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
virt_addr, length);
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
- if (IS_ERR_OR_NULL(mr))
- return ERR_PTR(mr ? PTR_ERR(mr) : -ENOMEM);
+ if (!mr)
+ return ERR_PTR(-ENOMEM);
mr->umem = usnic_uiom_reg_get(to_upd(pd)->umem_pd, start, length,
access_flags, 0);
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
index 414eaa566..0d9d2e6a1 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.h
@@ -43,8 +43,6 @@ int usnic_ib_query_device(struct ib_device *ibdev,
struct ib_udata *uhw);
int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
struct ib_port_attr *props);
-enum rdma_protocol_type
-usnic_ib_query_protocol(struct ib_device *device, u8 port_num);
int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
int qp_attr_mask,
struct ib_qp_init_attr *qp_init_attr);
diff --git a/drivers/infiniband/hw/usnic/usnic_vnic.c b/drivers/infiniband/hw/usnic/usnic_vnic.c
index 66de93fb8..887510718 100644
--- a/drivers/infiniband/hw/usnic/usnic_vnic.c
+++ b/drivers/infiniband/hw/usnic/usnic_vnic.c
@@ -237,7 +237,7 @@ usnic_vnic_get_resources(struct usnic_vnic *vnic, enum usnic_vnic_res_type type,
struct usnic_vnic_res *res;
int i;
- if (usnic_vnic_res_free_cnt(vnic, type) < cnt || cnt < 1 || !owner)
+ if (usnic_vnic_res_free_cnt(vnic, type) < cnt || cnt < 0 || !owner)
return ERR_PTR(-EINVAL);
ret = kzalloc(sizeof(*ret), GFP_ATOMIC);
@@ -247,26 +247,28 @@ usnic_vnic_get_resources(struct usnic_vnic *vnic, enum usnic_vnic_res_type type,
return ERR_PTR(-ENOMEM);
}
- ret->res = kzalloc(sizeof(*(ret->res))*cnt, GFP_ATOMIC);
- if (!ret->res) {
- usnic_err("Failed to allocate resources for %s. Out of memory\n",
- usnic_vnic_pci_name(vnic));
- kfree(ret);
- return ERR_PTR(-ENOMEM);
- }
+ if (cnt > 0) {
+ ret->res = kcalloc(cnt, sizeof(*(ret->res)), GFP_ATOMIC);
+ if (!ret->res) {
+ usnic_err("Failed to allocate resources for %s. Out of memory\n",
+ usnic_vnic_pci_name(vnic));
+ kfree(ret);
+ return ERR_PTR(-ENOMEM);
+ }
- spin_lock(&vnic->res_lock);
- src = &vnic->chunks[type];
- for (i = 0; i < src->cnt && ret->cnt < cnt; i++) {
- res = src->res[i];
- if (!res->owner) {
- src->free_cnt--;
- res->owner = owner;
- ret->res[ret->cnt++] = res;
+ spin_lock(&vnic->res_lock);
+ src = &vnic->chunks[type];
+ for (i = 0; i < src->cnt && ret->cnt < cnt; i++) {
+ res = src->res[i];
+ if (!res->owner) {
+ src->free_cnt--;
+ res->owner = owner;
+ ret->res[ret->cnt++] = res;
+ }
}
- }
- spin_unlock(&vnic->res_lock);
+ spin_unlock(&vnic->res_lock);
+ }
ret->type = type;
ret->vnic = vnic;
WARN_ON(ret->cnt != cnt);
@@ -281,14 +283,16 @@ void usnic_vnic_put_resources(struct usnic_vnic_res_chunk *chunk)
int i;
struct usnic_vnic *vnic = chunk->vnic;
- spin_lock(&vnic->res_lock);
- while ((i = --chunk->cnt) >= 0) {
- res = chunk->res[i];
- chunk->res[i] = NULL;
- res->owner = NULL;
- vnic->chunks[res->type].free_cnt++;
+ if (chunk->cnt > 0) {
+ spin_lock(&vnic->res_lock);
+ while ((i = --chunk->cnt) >= 0) {
+ res = chunk->res[i];
+ chunk->res[i] = NULL;
+ res->owner = NULL;
+ vnic->chunks[res->type].free_cnt++;
+ }
+ spin_unlock(&vnic->res_lock);
}
- spin_unlock(&vnic->res_lock);
kfree(chunk->res);
kfree(chunk);