[MLX5_IB_WR_UMR] = MLX5_OPCODE_UMR,
};
-/* handle_post_send_edge - Check if we get to SQ edge. If yes, update to the
- * next nearby edge and get new address translation for current WQE position.
- * @sq - SQ buffer.
- * @seg: Current WQE position (16B aligned).
- * @wqe_sz: Total current WQE size [16B].
- * @cur_edge: Updated current edge.
- */
-static inline void handle_post_send_edge(struct mlx5_ib_wq *sq, void **seg,
- u32 wqe_sz, void **cur_edge)
-{
- u32 idx;
-
- if (likely(*seg != *cur_edge))
- return;
-
- idx = (sq->cur_post + (wqe_sz >> 2)) & (sq->wqe_cnt - 1);
- *cur_edge = get_sq_edge(sq, idx);
-
- *seg = mlx5_frag_buf_get_wqe(&sq->fbc, idx);
-}
-
-/* memcpy_send_wqe - copy data from src to WQE and update the relevant WQ's
- * pointers. At the end @seg is aligned to 16B regardless the copied size.
- * @sq - SQ buffer.
- * @cur_edge: Updated current edge.
- * @seg: Current WQE position (16B aligned).
- * @wqe_sz: Total current WQE size [16B].
- * @src: Pointer to copy from.
- * @n: Number of bytes to copy.
- */
-static inline void memcpy_send_wqe(struct mlx5_ib_wq *sq, void **cur_edge,
- void **seg, u32 *wqe_sz, const void *src,
- size_t n)
-{
- while (likely(n)) {
- size_t leftlen = *cur_edge - *seg;
- size_t copysz = min_t(size_t, leftlen, n);
- size_t stride;
-
- memcpy(*seg, src, copysz);
-
- n -= copysz;
- src += copysz;
- stride = !n ? ALIGN(copysz, 16) : copysz;
- *seg += stride;
- *wqe_sz += stride >> 4;
- handle_post_send_edge(sq, seg, *wqe_sz, cur_edge);
- }
-}
-
-static int mlx5_wq_overflow(struct mlx5_ib_wq *wq, int nreq,
- struct ib_cq *ib_cq)
+int mlx5r_wq_overflow(struct mlx5_ib_wq *wq, int nreq, struct ib_cq *ib_cq)
{
struct mlx5_ib_cq *cq;
unsigned int cur;
eseg->mss = cpu_to_be16(ud_wr->mss);
eseg->inline_hdr.sz = cpu_to_be16(left);
- /* memcpy_send_wqe should get a 16B align address. Hence, we
- * first copy up to the current edge and then, if needed,
- * continue to memcpy_send_wqe.
+ /* mlx5r_memcpy_send_wqe should get a 16B align address. Hence,
+ * we first copy up to the current edge and then, if needed,
+ * continue to mlx5r_memcpy_send_wqe.
*/
copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start,
left);
handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
left -= copysz;
pdata += copysz;
- memcpy_send_wqe(&qp->sq, cur_edge, seg, size, pdata,
- left);
+ mlx5r_memcpy_send_wqe(&qp->sq, cur_edge, seg, size,
+ pdata, left);
}
return;
handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
if (umr_inline) {
- memcpy_send_wqe(&qp->sq, cur_edge, seg, size, mr->descs,
- mr_list_size);
+ mlx5r_memcpy_send_wqe(&qp->sq, cur_edge, seg, size, mr->descs,
+ mr_list_size);
*size = ALIGN(*size, MLX5_SEND_WQE_BB >> 4);
} else {
set_reg_data_seg(*seg, mr, pd);
}
}
-static int __begin_wqe(struct mlx5_ib_qp *qp, void **seg,
- struct mlx5_wqe_ctrl_seg **ctrl,
- const struct ib_send_wr *wr, unsigned int *idx,
- int *size, void **cur_edge, int nreq,
- bool send_signaled, bool solicited)
+int mlx5r_begin_wqe(struct mlx5_ib_qp *qp, void **seg,
+ struct mlx5_wqe_ctrl_seg **ctrl, unsigned int *idx,
+ int *size, void **cur_edge, int nreq, __be32 general_id,
+ bool send_signaled, bool solicited)
{
- if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)))
+ if (unlikely(mlx5r_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)))
return -ENOMEM;
*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
*seg = mlx5_frag_buf_get_wqe(&qp->sq.fbc, *idx);
*ctrl = *seg;
*(uint32_t *)(*seg + 8) = 0;
- (*ctrl)->imm = send_ieth(wr);
+ (*ctrl)->general_id = general_id;
(*ctrl)->fm_ce_se = qp->sq_signal_bits |
- (send_signaled ? MLX5_WQE_CTRL_CQ_UPDATE : 0) |
- (solicited ? MLX5_WQE_CTRL_SOLICITED : 0);
+ (send_signaled ? MLX5_WQE_CTRL_CQ_UPDATE : 0) |
+ (solicited ? MLX5_WQE_CTRL_SOLICITED : 0);
*seg += sizeof(**ctrl);
*size = sizeof(**ctrl) / 16;
const struct ib_send_wr *wr, unsigned int *idx, int *size,
void **cur_edge, int nreq)
{
- return __begin_wqe(qp, seg, ctrl, wr, idx, size, cur_edge, nreq,
- wr->send_flags & IB_SEND_SIGNALED,
- wr->send_flags & IB_SEND_SOLICITED);
+ return mlx5r_begin_wqe(qp, seg, ctrl, idx, size, cur_edge, nreq,
+ send_ieth(wr), wr->send_flags & IB_SEND_SIGNALED,
+ wr->send_flags & IB_SEND_SOLICITED);
}
-static void finish_wqe(struct mlx5_ib_qp *qp,
- struct mlx5_wqe_ctrl_seg *ctrl,
- void *seg, u8 size, void *cur_edge,
- unsigned int idx, u64 wr_id, int nreq, u8 fence,
- u32 mlx5_opcode)
+void mlx5r_finish_wqe(struct mlx5_ib_qp *qp, struct mlx5_wqe_ctrl_seg *ctrl,
+ void *seg, u8 size, void *cur_edge, unsigned int idx,
+ u64 wr_id, int nreq, u8 fence, u32 mlx5_opcode)
{
u8 opmod = 0;
/*
* SET_PSV WQEs are not signaled and solicited on error.
*/
- err = __begin_wqe(qp, seg, ctrl, wr, idx, size, cur_edge, nreq,
- false, true);
+ err = mlx5r_begin_wqe(qp, seg, ctrl, idx, size, cur_edge, nreq,
+ send_ieth(wr), false, true);
if (unlikely(err)) {
mlx5_ib_warn(dev, "\n");
err = -ENOMEM;
mlx5_ib_warn(dev, "\n");
goto out;
}
- finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx, wr->wr_id, nreq,
- next_fence, MLX5_OPCODE_SET_PSV);
+ mlx5r_finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx, wr->wr_id,
+ nreq, next_fence, MLX5_OPCODE_SET_PSV);
out:
return err;
if (unlikely(err))
goto out;
- finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx, wr->wr_id,
- nreq, fence, MLX5_OPCODE_UMR);
+ mlx5r_finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx,
+ wr->wr_id, nreq, fence, MLX5_OPCODE_UMR);
err = begin_wqe(qp, seg, ctrl, wr, idx, size, cur_edge, nreq);
if (unlikely(err)) {
mlx5_ib_warn(dev, "\n");
goto out;
}
- finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx, wr->wr_id, nreq,
- fence, MLX5_OPCODE_UMR);
+ mlx5r_finish_wqe(qp, *ctrl, *seg, *size, *cur_edge, *idx, wr->wr_id,
+ nreq, fence, MLX5_OPCODE_UMR);
sig_attrs = mr->ibmr.sig_attrs;
err = handle_psv(dev, qp, wr, ctrl, seg, size, cur_edge, idx, nreq,
return err;
}
+void mlx5r_ring_db(struct mlx5_ib_qp *qp, unsigned int nreq,
+ struct mlx5_wqe_ctrl_seg *ctrl)
+{
+ struct mlx5_bf *bf = &qp->bf;
+
+ qp->sq.head += nreq;
+
+ /* Make sure that descriptors are written before
+ * updating doorbell record and ringing the doorbell
+ */
+ wmb();
+
+ qp->db.db[MLX5_SND_DBR] = cpu_to_be32(qp->sq.cur_post);
+
+ /* Make sure doorbell record is visible to the HCA before
+ * we hit doorbell.
+ */
+ wmb();
+
+ mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset);
+ /* Make sure doorbells don't leak out of SQ spinlock
+ * and reach the HCA out of order.
+ */
+ bf->offset ^= bf->buf_size;
+}
+
int mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
const struct ib_send_wr **bad_wr, bool drain)
{
struct mlx5_core_dev *mdev = dev->mdev;
struct mlx5_ib_qp *qp = to_mqp(ibqp);
struct mlx5_wqe_xrc_seg *xrc;
- struct mlx5_bf *bf;
void *cur_edge;
int size;
unsigned long flags;
if (qp->type == IB_QPT_GSI)
return mlx5_ib_gsi_post_send(ibqp, wr, bad_wr);
- bf = &qp->bf;
-
spin_lock_irqsave(&qp->sq.lock, flags);
for (nreq = 0; wr; nreq++, wr = wr->next) {
}
qp->next_fence = next_fence;
- finish_wqe(qp, ctrl, seg, size, cur_edge, idx, wr->wr_id, nreq,
- fence, mlx5_ib_opcode[wr->opcode]);
+ mlx5r_finish_wqe(qp, ctrl, seg, size, cur_edge, idx, wr->wr_id,
+ nreq, fence, mlx5_ib_opcode[wr->opcode]);
skip_psv:
if (0)
dump_wqe(qp, idx, size);
}
out:
- if (likely(nreq)) {
- qp->sq.head += nreq;
-
- /* Make sure that descriptors are written before
- * updating doorbell record and ringing the doorbell
- */
- wmb();
-
- qp->db.db[MLX5_SND_DBR] = cpu_to_be32(qp->sq.cur_post);
-
- /* Make sure doorbell record is visible to the HCA before
- * we hit doorbell.
- */
- wmb();
-
- mlx5_write64((__be32 *)ctrl, bf->bfreg->map + bf->offset);
- /* Make sure doorbells don't leak out of SQ spinlock
- * and reach the HCA out of order.
- */
- bf->offset ^= bf->buf_size;
- }
+ if (likely(nreq))
+ mlx5r_ring_db(qp, nreq, ctrl);
spin_unlock_irqrestore(&qp->sq.lock, flags);
ind = qp->rq.head & (qp->rq.wqe_cnt - 1);
for (nreq = 0; wr; nreq++, wr = wr->next) {
- if (mlx5_wq_overflow(&qp->rq, nreq, qp->ibqp.recv_cq)) {
+ if (mlx5r_wq_overflow(&qp->rq, nreq, qp->ibqp.recv_cq)) {
err = -ENOMEM;
*bad_wr = wr;
goto out;
return fragment_end + MLX5_SEND_WQE_BB;
}
+/* handle_post_send_edge - Check if we get to SQ edge. If yes, update to the
+ * next nearby edge and get new address translation for current WQE position.
+ * @sq: SQ buffer.
+ * @seg: Current WQE position (16B aligned).
+ * @wqe_sz: Total current WQE size [16B].
+ * @cur_edge: Updated current edge.
+ */
+static inline void handle_post_send_edge(struct mlx5_ib_wq *sq, void **seg,
+ u32 wqe_sz, void **cur_edge)
+{
+ u32 idx;
+
+ if (likely(*seg != *cur_edge))
+ return;
+
+ idx = (sq->cur_post + (wqe_sz >> 2)) & (sq->wqe_cnt - 1);
+ *cur_edge = get_sq_edge(sq, idx);
+
+ *seg = mlx5_frag_buf_get_wqe(&sq->fbc, idx);
+}
+
+/* mlx5r_memcpy_send_wqe - copy data from src to WQE and update the relevant
+ * WQ's pointers. At the end @seg is aligned to 16B regardless the copied size.
+ * @sq: SQ buffer.
+ * @cur_edge: Updated current edge.
+ * @seg: Current WQE position (16B aligned).
+ * @wqe_sz: Total current WQE size [16B].
+ * @src: Pointer to copy from.
+ * @n: Number of bytes to copy.
+ */
+static inline void mlx5r_memcpy_send_wqe(struct mlx5_ib_wq *sq, void **cur_edge,
+ void **seg, u32 *wqe_sz,
+ const void *src, size_t n)
+{
+ while (likely(n)) {
+ size_t leftlen = *cur_edge - *seg;
+ size_t copysz = min_t(size_t, leftlen, n);
+ size_t stride;
+
+ memcpy(*seg, src, copysz);
+
+ n -= copysz;
+ src += copysz;
+ stride = !n ? ALIGN(copysz, 16) : copysz;
+ *seg += stride;
+ *wqe_sz += stride >> 4;
+ handle_post_send_edge(sq, seg, *wqe_sz, cur_edge);
+ }
+}
+
+int mlx5r_wq_overflow(struct mlx5_ib_wq *wq, int nreq, struct ib_cq *ib_cq);
+int mlx5r_begin_wqe(struct mlx5_ib_qp *qp, void **seg,
+ struct mlx5_wqe_ctrl_seg **ctrl, unsigned int *idx,
+ int *size, void **cur_edge, int nreq, __be32 general_id,
+ bool send_signaled, bool solicited);
+void mlx5r_finish_wqe(struct mlx5_ib_qp *qp, struct mlx5_wqe_ctrl_seg *ctrl,
+ void *seg, u8 size, void *cur_edge, unsigned int idx,
+ u64 wr_id, int nreq, u8 fence, u32 mlx5_opcode);
+void mlx5r_ring_db(struct mlx5_ib_qp *qp, unsigned int nreq,
+ struct mlx5_wqe_ctrl_seg *ctrl);
int mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
const struct ib_send_wr **bad_wr, bool drain);
int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
projects / linux.git / commitdiff