IB/mlx5: Break up wqe handling into begin & finish routines

As a preliminary step for signature feature which will require posting
multiple (3) WQEs for a single WR, we break post_send routine WQE
indexing into begin and finish routines.

This patch does not change any functionality.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Sagi Grimberg 2014-02-23 14:19:08 +02:00 committed by Roland Dreier
parent e1e66cc264
commit 6e5eadace1
1 changed files with 63 additions and 38 deletions

View File

@ -2047,6 +2047,59 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
} }
} }
static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
struct mlx5_wqe_ctrl_seg **ctrl,
struct ib_send_wr *wr, int *idx,
int *size, int nreq)
{
int err = 0;
if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
err = -ENOMEM;
return err;
}
*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
*seg = mlx5_get_send_wqe(qp, *idx);
*ctrl = *seg;
*(uint32_t *)(*seg + 8) = 0;
(*ctrl)->imm = send_ieth(wr);
(*ctrl)->fm_ce_se = qp->sq_signal_bits |
(wr->send_flags & IB_SEND_SIGNALED ?
MLX5_WQE_CTRL_CQ_UPDATE : 0) |
(wr->send_flags & IB_SEND_SOLICITED ?
MLX5_WQE_CTRL_SOLICITED : 0);
*seg += sizeof(**ctrl);
*size = sizeof(**ctrl) / 16;
return err;
}
static void finish_wqe(struct mlx5_ib_qp *qp,
struct mlx5_wqe_ctrl_seg *ctrl,
u8 size, unsigned idx, u64 wr_id,
int nreq, u8 fence, u8 next_fence,
u32 mlx5_opcode)
{
u8 opmod = 0;
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->fm_ce_se |= fence;
qp->fm_cache = next_fence;
if (unlikely(qp->wq_sig))
ctrl->signature = wq_sig(ctrl);
qp->sq.wrid[idx] = wr_id;
qp->sq.w_list[idx].opcode = mlx5_opcode;
qp->sq.wqe_head[idx] = qp->sq.head + nreq;
qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
qp->sq.w_list[idx].next = qp->sq.cur_post;
}
int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct ib_send_wr **bad_wr) struct ib_send_wr **bad_wr)
{ {
@ -2060,7 +2113,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
int uninitialized_var(size); int uninitialized_var(size);
void *qend = qp->sq.qend; void *qend = qp->sq.qend;
unsigned long flags; unsigned long flags;
u32 mlx5_opcode;
unsigned idx; unsigned idx;
int err = 0; int err = 0;
int inl = 0; int inl = 0;
@ -2069,7 +2121,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
int nreq; int nreq;
int i; int i;
u8 next_fence = 0; u8 next_fence = 0;
u8 opmod = 0;
u8 fence; u8 fence;
spin_lock_irqsave(&qp->sq.lock, flags); spin_lock_irqsave(&qp->sq.lock, flags);
@ -2082,13 +2133,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
goto out; goto out;
} }
if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
mlx5_ib_warn(dev, "\n");
err = -ENOMEM;
*bad_wr = wr;
goto out;
}
fence = qp->fm_cache; fence = qp->fm_cache;
num_sge = wr->num_sge; num_sge = wr->num_sge;
if (unlikely(num_sge > qp->sq.max_gs)) { if (unlikely(num_sge > qp->sq.max_gs)) {
@ -2098,19 +2142,13 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
goto out; goto out;
} }
idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1); err = begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, nreq);
seg = mlx5_get_send_wqe(qp, idx); if (err) {
ctrl = seg; mlx5_ib_warn(dev, "\n");
*(uint32_t *)(seg + 8) = 0; err = -ENOMEM;
ctrl->imm = send_ieth(wr); *bad_wr = wr;
ctrl->fm_ce_se = qp->sq_signal_bits | goto out;
(wr->send_flags & IB_SEND_SIGNALED ? }
MLX5_WQE_CTRL_CQ_UPDATE : 0) |
(wr->send_flags & IB_SEND_SOLICITED ?
MLX5_WQE_CTRL_SOLICITED : 0);
seg += sizeof(*ctrl);
size = sizeof(*ctrl) / 16;
switch (ibqp->qp_type) { switch (ibqp->qp_type) {
case IB_QPT_XRC_INI: case IB_QPT_XRC_INI:
@ -2244,22 +2282,9 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
} }
} }
mlx5_opcode = mlx5_ib_opcode[wr->opcode]; finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8) | get_fence(fence, wr), next_fence,
mlx5_opcode | mlx5_ib_opcode[wr->opcode]);
((u32)opmod << 24));
ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
ctrl->fm_ce_se |= get_fence(fence, wr);
qp->fm_cache = next_fence;
if (unlikely(qp->wq_sig))
ctrl->signature = wq_sig(ctrl);
qp->sq.wrid[idx] = wr->wr_id;
qp->sq.w_list[idx].opcode = mlx5_opcode;
qp->sq.wqe_head[idx] = qp->sq.head + nreq;
qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
qp->sq.w_list[idx].next = qp->sq.cur_post;
if (0) if (0)
dump_wqe(qp, idx, size); dump_wqe(qp, idx, size);
} }