[GIT PULL] please pull infiniband.git
From: Roland Dreier
Date: Mon Jun 18 2007 - 11:49:36 EST
Linus, please pull from
master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git for-linus
This tree is also available from kernel.org mirrors at:
git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git for-linus
This will get a bunch of fixes to the new mlx4 driver. This pull is
bigger than I would have liked after -rc5, but Mellanox discovered a
problem that required a firmware change and also some driver help to
fix. Since this is a new driver for 2.6.22, which is for new hardware
that no one has in production yet, I think it's better to merge this
early even if it risks introducing a bug, rather than have a driver
in 2.6.22 that doesn't work at all with current adapter firmware.
Jack Morgenstein (1):
IB/mlx4: Handle buffer wraparound in __mlx4_ib_cq_clean()
Roland Dreier (6):
IB/mlx4: Fix handling of wq->tail for send completions
IB/mlx4: Fix warning in rounding up queue sizes
IB/mlx4: Handle new FW requirement for send request prefetching
IB/mlx4: Get rid of max_inline_data calculation
IB/mlx4: Handle FW command interface rev 3
IB/mlx4: Make sure inline data segments don't cross a 64 byte boundary
drivers/infiniband/hw/mlx4/cq.c | 19 ++--
drivers/infiniband/hw/mlx4/main.c | 16 ++-
drivers/infiniband/hw/mlx4/mlx4_ib.h | 5 +-
drivers/infiniband/hw/mlx4/qp.c | 196 ++++++++++++++++++++++------------
drivers/infiniband/hw/mlx4/user.h | 9 +-
drivers/net/mlx4/fw.c | 110 +++++++++++++-------
drivers/net/mlx4/fw.h | 10 +-
drivers/net/mlx4/main.c | 14 ++-
include/linux/mlx4/cmd.h | 1 +
include/linux/mlx4/device.h | 13 ++-
include/linux/mlx4/qp.h | 4 +
11 files changed, 259 insertions(+), 138 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index b2a290c..660b27a 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -354,8 +354,8 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
if (is_send) {
wq = &(*cur_qp)->sq;
wqe_ctr = be16_to_cpu(cqe->wqe_index);
- wq->tail += wqe_ctr - (u16) wq->tail;
- wc->wr_id = wq->wrid[wq->tail & (wq->max - 1)];
+ wq->tail += (u16) (wqe_ctr - (u16) wq->tail);
+ wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
++wq->tail;
} else if ((*cur_qp)->ibqp.srq) {
srq = to_msrq((*cur_qp)->ibqp.srq);
@@ -364,7 +364,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
mlx4_ib_free_srq_wqe(srq, wqe_ctr);
} else {
wq = &(*cur_qp)->rq;
- wc->wr_id = wq->wrid[wq->tail & (wq->max - 1)];
+ wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
++wq->tail;
}
@@ -478,7 +478,8 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
{
u32 prod_index;
int nfreed = 0;
- struct mlx4_cqe *cqe;
+ struct mlx4_cqe *cqe, *dest;
+ u8 owner_bit;
/*
* First we need to find the current producer index, so we
@@ -501,9 +502,13 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
if (srq && !(cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK))
mlx4_ib_free_srq_wqe(srq, be16_to_cpu(cqe->wqe_index));
++nfreed;
- } else if (nfreed)
- memcpy(get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe),
- cqe, sizeof *cqe);
+ } else if (nfreed) {
+ dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
+ owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
+ memcpy(dest, cqe, sizeof *cqe);
+ dest->owner_sr_opcode = owner_bit |
+ (dest->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK);
+ }
}
if (nfreed) {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 402f3a2..1095c82 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -125,7 +125,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
props->local_ca_ack_delay = dev->dev->caps.local_ca_ack_delay;
props->atomic_cap = dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_ATOMIC ?
IB_ATOMIC_HCA : IB_ATOMIC_NONE;
- props->max_pkeys = dev->dev->caps.pkey_table_len;
+ props->max_pkeys = dev->dev->caps.pkey_table_len[1];
props->max_mcast_grp = dev->dev->caps.num_mgms + dev->dev->caps.num_amgms;
props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm;
props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
@@ -168,9 +168,9 @@ static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
props->state = out_mad->data[32] & 0xf;
props->phys_state = out_mad->data[33] >> 4;
props->port_cap_flags = be32_to_cpup((__be32 *) (out_mad->data + 20));
- props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len;
+ props->gid_tbl_len = to_mdev(ibdev)->dev->caps.gid_table_len[port];
props->max_msg_sz = 0x80000000;
- props->pkey_tbl_len = to_mdev(ibdev)->dev->caps.pkey_table_len;
+ props->pkey_tbl_len = to_mdev(ibdev)->dev->caps.pkey_table_len[port];
props->bad_pkey_cntr = be16_to_cpup((__be16 *) (out_mad->data + 46));
props->qkey_viol_cntr = be16_to_cpup((__be16 *) (out_mad->data + 48));
props->active_width = out_mad->data[31] & 0xf;
@@ -280,8 +280,14 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
return PTR_ERR(mailbox);
memset(mailbox->buf, 0, 256);
- *(u8 *) mailbox->buf = !!reset_qkey_viols << 6;
- ((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
+
+ if (dev->dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+ *(u8 *) mailbox->buf = !!reset_qkey_viols << 6;
+ ((__be32 *) mailbox->buf)[2] = cpu_to_be32(cap_mask);
+ } else {
+ ((u8 *) mailbox->buf)[3] = !!reset_qkey_viols;
+ ((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask);
+ }
err = mlx4_cmd(dev->dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
MLX4_CMD_TIME_CLASS_B);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 93dac71..24ccadd 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -95,7 +95,8 @@ struct mlx4_ib_mr {
struct mlx4_ib_wq {
u64 *wrid;
spinlock_t lock;
- int max;
+ int wqe_cnt;
+ int max_post;
int max_gs;
int offset;
int wqe_shift;
@@ -113,6 +114,7 @@ struct mlx4_ib_qp {
u32 doorbell_qpn;
__be32 sq_signal_bits;
+ int sq_spare_wqes;
struct mlx4_ib_wq sq;
struct ib_umem *umem;
@@ -123,6 +125,7 @@ struct mlx4_ib_qp {
u8 alt_port;
u8 atomic_rd_en;
u8 resp_depth;
+ u8 sq_no_prefetch;
u8 state;
};
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 5c6d054..f8a1a08 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -109,6 +109,20 @@ static void *get_send_wqe(struct mlx4_ib_qp *qp, int n)
return get_wqe(qp, qp->sq.offset + (n << qp->sq.wqe_shift));
}
+/*
+ * Stamp a SQ WQE so that it is invalid if prefetched by marking the
+ * first four bytes of every 64 byte chunk with 0xffffffff, except for
+ * the very first chunk of the WQE.
+ */
+static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n)
+{
+ u32 *wqe = get_send_wqe(qp, n);
+ int i;
+
+ for (i = 16; i < 1 << (qp->sq.wqe_shift - 2); i += 16)
+ wqe[i] = 0xffffffff;
+}
+
static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type)
{
struct ib_event event;
@@ -178,6 +192,8 @@ static int send_wqe_overhead(enum ib_qp_type type)
case IB_QPT_GSI:
return sizeof (struct mlx4_wqe_ctrl_seg) +
ALIGN(MLX4_IB_UD_HEADER_SIZE +
+ DIV_ROUND_UP(MLX4_IB_UD_HEADER_SIZE,
+ MLX4_INLINE_ALIGN) *
sizeof (struct mlx4_wqe_inline_seg),
sizeof (struct mlx4_wqe_data_seg)) +
ALIGN(4 +
@@ -201,18 +217,18 @@ static int set_rq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
if (cap->max_recv_wr)
return -EINVAL;
- qp->rq.max = qp->rq.max_gs = 0;
+ qp->rq.wqe_cnt = qp->rq.max_gs = 0;
} else {
/* HW requires >= 1 RQ entry with >= 1 gather entry */
if (is_user && (!cap->max_recv_wr || !cap->max_recv_sge))
return -EINVAL;
- qp->rq.max = roundup_pow_of_two(max(1, cap->max_recv_wr));
- qp->rq.max_gs = roundup_pow_of_two(max(1, cap->max_recv_sge));
+ qp->rq.wqe_cnt = roundup_pow_of_two(max(1U, cap->max_recv_wr));
+ qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge));
qp->rq.wqe_shift = ilog2(qp->rq.max_gs * sizeof (struct mlx4_wqe_data_seg));
}
- cap->max_recv_wr = qp->rq.max;
+ cap->max_recv_wr = qp->rq.max_post = qp->rq.wqe_cnt;
cap->max_recv_sge = qp->rq.max_gs;
return 0;
@@ -236,8 +252,6 @@ static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
cap->max_send_sge + 2 > dev->dev->caps.max_sq_sg)
return -EINVAL;
- qp->sq.max = cap->max_send_wr ? roundup_pow_of_two(cap->max_send_wr) : 1;
-
qp->sq.wqe_shift = ilog2(roundup_pow_of_two(max(cap->max_send_sge *
sizeof (struct mlx4_wqe_data_seg),
cap->max_inline_data +
@@ -246,20 +260,27 @@ static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
qp->sq.max_gs = ((1 << qp->sq.wqe_shift) - send_wqe_overhead(type)) /
sizeof (struct mlx4_wqe_data_seg);
- qp->buf_size = (qp->rq.max << qp->rq.wqe_shift) +
- (qp->sq.max << qp->sq.wqe_shift);
+ /*
+ * We need to leave 2 KB + 1 WQE of headroom in the SQ to
+ * allow HW to prefetch.
+ */
+ qp->sq_spare_wqes = (2048 >> qp->sq.wqe_shift) + 1;
+ qp->sq.wqe_cnt = roundup_pow_of_two(cap->max_send_wr + qp->sq_spare_wqes);
+
+ qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
+ (qp->sq.wqe_cnt << qp->sq.wqe_shift);
if (qp->rq.wqe_shift > qp->sq.wqe_shift) {
qp->rq.offset = 0;
- qp->sq.offset = qp->rq.max << qp->rq.wqe_shift;
+ qp->sq.offset = qp->rq.wqe_cnt << qp->rq.wqe_shift;
} else {
- qp->rq.offset = qp->sq.max << qp->sq.wqe_shift;
+ qp->rq.offset = qp->sq.wqe_cnt << qp->sq.wqe_shift;
qp->sq.offset = 0;
}
- cap->max_send_wr = qp->sq.max;
- cap->max_send_sge = qp->sq.max_gs;
- cap->max_inline_data = (1 << qp->sq.wqe_shift) - send_wqe_overhead(type) -
- sizeof (struct mlx4_wqe_inline_seg);
+ cap->max_send_wr = qp->sq.max_post = qp->sq.wqe_cnt - qp->sq_spare_wqes;
+ cap->max_send_sge = qp->sq.max_gs;
+ /* We don't support inline sends for kernel QPs (yet) */
+ cap->max_inline_data = 0;
return 0;
}
@@ -267,11 +288,11 @@ static int set_kernel_sq_size(struct mlx4_ib_dev *dev, struct ib_qp_cap *cap,
static int set_user_sq_size(struct mlx4_ib_qp *qp,
struct mlx4_ib_create_qp *ucmd)
{
- qp->sq.max = 1 << ucmd->log_sq_bb_count;
+ qp->sq.wqe_cnt = 1 << ucmd->log_sq_bb_count;
qp->sq.wqe_shift = ucmd->log_sq_stride;
- qp->buf_size = (qp->rq.max << qp->rq.wqe_shift) +
- (qp->sq.max << qp->sq.wqe_shift);
+ qp->buf_size = (qp->rq.wqe_cnt << qp->rq.wqe_shift) +
+ (qp->sq.wqe_cnt << qp->sq.wqe_shift);
return 0;
}
@@ -307,6 +328,8 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
goto err;
}
+ qp->sq_no_prefetch = ucmd.sq_no_prefetch;
+
err = set_user_sq_size(qp, &ucmd);
if (err)
goto err;
@@ -334,6 +357,8 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
goto err_mtt;
}
} else {
+ qp->sq_no_prefetch = 0;
+
err = set_kernel_sq_size(dev, &init_attr->cap, init_attr->qp_type, qp);
if (err)
goto err;
@@ -360,16 +385,13 @@ 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.max * sizeof (u64), GFP_KERNEL);
- qp->rq.wrid = kmalloc(qp->rq.max * sizeof (u64), GFP_KERNEL);
+ qp->sq.wrid = kmalloc(qp->sq.wqe_cnt * sizeof (u64), GFP_KERNEL);
+ qp->rq.wrid = kmalloc(qp->rq.wqe_cnt * sizeof (u64), GFP_KERNEL);
if (!qp->sq.wrid || !qp->rq.wrid) {
err = -ENOMEM;
goto err_wrid;
}
-
- /* We don't support inline sends for kernel QPs (yet) */
- init_attr->cap.max_inline_data = 0;
}
err = mlx4_qp_alloc(dev->dev, sqpn, &qp->mqp);
@@ -583,24 +605,6 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp)
return 0;
}
-static void init_port(struct mlx4_ib_dev *dev, int port)
-{
- struct mlx4_init_port_param param;
- int err;
-
- memset(¶m, 0, sizeof param);
-
- param.port_width_cap = dev->dev->caps.port_width_cap;
- param.vl_cap = dev->dev->caps.vl_cap;
- param.mtu = ib_mtu_enum_to_int(dev->dev->caps.mtu_cap);
- param.max_gid = dev->dev->caps.gid_table_len;
- param.max_pkey = dev->dev->caps.pkey_table_len;
-
- err = mlx4_INIT_PORT(dev->dev, ¶m, port);
- if (err)
- printk(KERN_WARNING "INIT_PORT failed, return code %d.\n", err);
-}
-
static int to_mlx4_st(enum ib_qp_type type)
{
switch (type) {
@@ -674,9 +678,9 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
path->counter_index = 0xff;
if (ah->ah_flags & IB_AH_GRH) {
- if (ah->grh.sgid_index >= dev->dev->caps.gid_table_len) {
+ if (ah->grh.sgid_index >= dev->dev->caps.gid_table_len[port]) {
printk(KERN_ERR "sgid_index (%u) too large. max is %d\n",
- ah->grh.sgid_index, dev->dev->caps.gid_table_len - 1);
+ ah->grh.sgid_index, dev->dev->caps.gid_table_len[port] - 1);
return -1;
}
@@ -743,14 +747,17 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
context->mtu_msgmax = (attr->path_mtu << 5) | 31;
}
- if (qp->rq.max)
- context->rq_size_stride = ilog2(qp->rq.max) << 3;
+ if (qp->rq.wqe_cnt)
+ context->rq_size_stride = ilog2(qp->rq.wqe_cnt) << 3;
context->rq_size_stride |= qp->rq.wqe_shift - 4;
- if (qp->sq.max)
- context->sq_size_stride = ilog2(qp->sq.max) << 3;
+ if (qp->sq.wqe_cnt)
+ context->sq_size_stride = ilog2(qp->sq.wqe_cnt) << 3;
context->sq_size_stride |= qp->sq.wqe_shift - 4;
+ if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
+ context->sq_size_stride |= !!qp->sq_no_prefetch << 7;
+
if (qp->ibqp.uobject)
context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index);
else
@@ -789,13 +796,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
}
if (attr_mask & IB_QP_ALT_PATH) {
- if (attr->alt_pkey_index >= dev->dev->caps.pkey_table_len)
- return -EINVAL;
-
if (attr->alt_port_num == 0 ||
attr->alt_port_num > dev->dev->caps.num_ports)
return -EINVAL;
+ if (attr->alt_pkey_index >=
+ dev->dev->caps.pkey_table_len[attr->alt_port_num])
+ return -EINVAL;
+
if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
attr->alt_port_num))
return -EINVAL;
@@ -884,16 +892,19 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
/*
* Before passing a kernel QP to the HW, make sure that the
- * ownership bits of the send queue are set so that the
- * hardware doesn't start processing stale work requests.
+ * ownership bits of the send queue are set and the SQ
+ * headroom is stamped so that the hardware doesn't start
+ * processing stale work requests.
*/
if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
struct mlx4_wqe_ctrl_seg *ctrl;
int i;
- for (i = 0; i < qp->sq.max; ++i) {
+ for (i = 0; i < qp->sq.wqe_cnt; ++i) {
ctrl = get_send_wqe(qp, i);
ctrl->owner_opcode = cpu_to_be32(1 << 31);
+
+ stamp_send_wqe(qp, i);
}
}
@@ -923,7 +934,9 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
*/
if (is_qp0(dev, qp)) {
if (cur_state != IB_QPS_RTR && new_state == IB_QPS_RTR)
- init_port(dev, qp->port);
+ if (mlx4_INIT_PORT(dev->dev, qp->port))
+ printk(KERN_WARNING "INIT_PORT failed for port %d\n",
+ qp->port);
if (cur_state != IB_QPS_RESET && cur_state != IB_QPS_ERR &&
(new_state == IB_QPS_RESET || new_state == IB_QPS_ERR))
@@ -986,16 +999,17 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
goto out;
- if ((attr_mask & IB_QP_PKEY_INDEX) &&
- attr->pkey_index >= dev->dev->caps.pkey_table_len) {
- goto out;
- }
-
if ((attr_mask & IB_QP_PORT) &&
(attr->port_num == 0 || attr->port_num > dev->dev->caps.num_ports)) {
goto out;
}
+ if (attr_mask & IB_QP_PKEY_INDEX) {
+ int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+ if (attr->pkey_index >= dev->dev->caps.pkey_table_len[p])
+ goto out;
+ }
+
if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
attr->max_rd_atomic > dev->dev->caps.max_qp_init_rdma) {
goto out;
@@ -1037,6 +1051,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
u16 pkey;
int send_size;
int header_size;
+ int spc;
int i;
send_size = 0;
@@ -1112,10 +1127,43 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
printk("\n");
}
- inl->byte_count = cpu_to_be32(1 << 31 | header_size);
- memcpy(inl + 1, sqp->header_buf, header_size);
+ /*
+ * Inline data segments may not cross a 64 byte boundary. If
+ * our UD header is bigger than the space available up to the
+ * next 64 byte boundary in the WQE, use two inline data
+ * segments to hold the UD header.
+ */
+ spc = MLX4_INLINE_ALIGN -
+ ((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
+ if (header_size <= spc) {
+ inl->byte_count = cpu_to_be32(1 << 31 | header_size);
+ memcpy(inl + 1, sqp->header_buf, header_size);
+ i = 1;
+ } else {
+ inl->byte_count = cpu_to_be32(1 << 31 | spc);
+ memcpy(inl + 1, sqp->header_buf, spc);
- return ALIGN(sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
+ inl = (void *) (inl + 1) + spc;
+ memcpy(inl + 1, sqp->header_buf + spc, header_size - spc);
+ /*
+ * Need a barrier here to make sure all the data is
+ * visible before the byte_count field is set.
+ * Otherwise the HCA prefetcher could grab the 64-byte
+ * chunk with this inline segment and get a valid (!=
+ * 0xffffffff) byte count but stale data, and end up
+ * processing generating a packet with bad headers.
+ *
+ * The first inline segment's byte_count field doesn't
+ * need a barrier, because it comes after a
+ * control/MLX segment and therefore is at an offset
+ * of 16 mod 64.
+ */
+ wmb();
+ inl->byte_count = cpu_to_be32(1 << 31 | (header_size - spc));
+ i = 2;
+ }
+
+ return ALIGN(i * sizeof (struct mlx4_wqe_inline_seg) + header_size, 16);
}
static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq)
@@ -1124,7 +1172,7 @@ static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq
struct mlx4_ib_cq *cq;
cur = wq->head - wq->tail;
- if (likely(cur + nreq < wq->max))
+ if (likely(cur + nreq < wq->max_post))
return 0;
cq = to_mcq(ib_cq);
@@ -1132,7 +1180,7 @@ static int mlx4_wq_overflow(struct mlx4_ib_wq *wq, int nreq, struct ib_cq *ib_cq
cur = wq->head - wq->tail;
spin_unlock(&cq->lock);
- return cur + nreq >= wq->max;
+ return cur + nreq >= wq->max_post;
}
int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
@@ -1165,8 +1213,8 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
goto out;
}
- ctrl = wqe = get_send_wqe(qp, ind & (qp->sq.max - 1));
- qp->sq.wrid[ind & (qp->sq.max - 1)] = wr->wr_id;
+ ctrl = wqe = get_send_wqe(qp, ind & (qp->sq.wqe_cnt - 1));
+ qp->sq.wrid[ind & (qp->sq.wqe_cnt - 1)] = wr->wr_id;
ctrl->srcrb_flags =
(wr->send_flags & IB_SEND_SIGNALED ?
@@ -1301,7 +1349,16 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
}
ctrl->owner_opcode = mlx4_ib_opcode[wr->opcode] |
- (ind & qp->sq.max ? cpu_to_be32(1 << 31) : 0);
+ (ind & qp->sq.wqe_cnt ? cpu_to_be32(1 << 31) : 0);
+
+ /*
+ * We can improve latency by not stamping the last
+ * send queue WQE until after ringing the doorbell, so
+ * only stamp here if there are still more WQEs to post.
+ */
+ if (wr->next)
+ stamp_send_wqe(qp, (ind + qp->sq_spare_wqes) &
+ (qp->sq.wqe_cnt - 1));
++ind;
}
@@ -1324,6 +1381,9 @@ out:
* and reach the HCA out of order.
*/
mmiowb();
+
+ stamp_send_wqe(qp, (ind + qp->sq_spare_wqes - 1) &
+ (qp->sq.wqe_cnt - 1));
}
spin_unlock_irqrestore(&qp->rq.lock, flags);
@@ -1344,7 +1404,7 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
spin_lock_irqsave(&qp->rq.lock, flags);
- ind = qp->rq.head & (qp->rq.max - 1);
+ ind = qp->rq.head & (qp->rq.wqe_cnt - 1);
for (nreq = 0; wr; ++nreq, wr = wr->next) {
if (mlx4_wq_overflow(&qp->rq, nreq, qp->ibqp.send_cq)) {
@@ -1375,7 +1435,7 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
qp->rq.wrid[ind] = wr->wr_id;
- ind = (ind + 1) & (qp->rq.max - 1);
+ ind = (ind + 1) & (qp->rq.wqe_cnt - 1);
}
out:
diff --git a/drivers/infiniband/hw/mlx4/user.h b/drivers/infiniband/hw/mlx4/user.h
index 88c72d5..e2d11be 100644
--- a/drivers/infiniband/hw/mlx4/user.h
+++ b/drivers/infiniband/hw/mlx4/user.h
@@ -39,7 +39,7 @@
* Increment this value if any changes that break userspace ABI
* compatibility are made.
*/
-#define MLX4_IB_UVERBS_ABI_VERSION 2
+#define MLX4_IB_UVERBS_ABI_VERSION 3
/*
* Make sure that all structs defined in this file remain laid out so
@@ -87,9 +87,10 @@ struct mlx4_ib_create_srq_resp {
struct mlx4_ib_create_qp {
__u64 buf_addr;
__u64 db_addr;
- __u8 log_sq_bb_count;
- __u8 log_sq_stride;
- __u8 reserved[6];
+ __u8 log_sq_bb_count;
+ __u8 log_sq_stride;
+ __u8 sq_no_prefetch;
+ __u8 reserved[5];
};
#endif /* MLX4_IB_USER_H */
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index e7ca118..d2b0653 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -38,7 +38,9 @@
#include "icm.h"
enum {
- MLX4_COMMAND_INTERFACE_REV = 1
+ MLX4_COMMAND_INTERFACE_MIN_REV = 2,
+ MLX4_COMMAND_INTERFACE_MAX_REV = 3,
+ MLX4_COMMAND_INTERFACE_NEW_PORT_CMDS = 3,
};
extern void __buggy_use_of_MLX4_GET(void);
@@ -107,6 +109,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
u16 size;
u16 stat_rate;
int err;
+ int i;
#define QUERY_DEV_CAP_OUT_SIZE 0x100
#define QUERY_DEV_CAP_MAX_SRQ_SZ_OFFSET 0x10
@@ -176,7 +179,6 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
MLX4_CMD_TIME_CLASS_A);
-
if (err)
goto out;
@@ -216,18 +218,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev_cap->max_rdma_global = 1 << (field & 0x3f);
MLX4_GET(field, outbox, QUERY_DEV_CAP_ACK_DELAY_OFFSET);
dev_cap->local_ca_ack_delay = field & 0x1f;
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
- dev_cap->max_mtu = field >> 4;
- dev_cap->max_port_width = field & 0xf;
MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
- dev_cap->max_vl = field >> 4;
dev_cap->num_ports = field & 0xf;
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
- dev_cap->max_gids = 1 << (field & 0xf);
MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET);
dev_cap->stat_rate_support = stat_rate;
- MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
- dev_cap->max_pkeys = 1 << (field & 0xf);
MLX4_GET(dev_cap->flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET);
MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_UAR_OFFSET);
dev_cap->reserved_uars = field >> 4;
@@ -304,6 +298,42 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
MLX4_GET(dev_cap->max_icm_sz, outbox,
QUERY_DEV_CAP_MAX_ICM_SZ_OFFSET);
+ if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+ for (i = 1; i <= dev_cap->num_ports; ++i) {
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
+ dev_cap->max_vl[i] = field >> 4;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
+ dev_cap->max_mtu[i] = field >> 4;
+ dev_cap->max_port_width[i] = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
+ dev_cap->max_gids[i] = 1 << (field & 0xf);
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
+ dev_cap->max_pkeys[i] = 1 << (field & 0xf);
+ }
+ } else {
+#define QUERY_PORT_MTU_OFFSET 0x01
+#define QUERY_PORT_WIDTH_OFFSET 0x06
+#define QUERY_PORT_MAX_GID_PKEY_OFFSET 0x07
+#define QUERY_PORT_MAX_VL_OFFSET 0x0b
+
+ for (i = 1; i <= dev_cap->num_ports; ++i) {
+ err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
+ MLX4_CMD_TIME_CLASS_B);
+ if (err)
+ goto out;
+
+ MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
+ dev_cap->max_mtu[i] = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
+ dev_cap->max_port_width[i] = field & 0xf;
+ MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
+ dev_cap->max_gids[i] = 1 << (field >> 4);
+ dev_cap->max_pkeys[i] = 1 << (field & 0xf);
+ MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
+ dev_cap->max_vl[i] = field & 0xf;
+ }
+ }
+
if (dev_cap->bmme_flags & 1)
mlx4_dbg(dev, "Base MM extensions: yes "
"(flags %d, rsvd L_Key %08x)\n",
@@ -338,8 +368,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
mlx4_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n",
dev_cap->max_cq_sz, dev_cap->max_qp_sz, dev_cap->max_srq_sz);
mlx4_dbg(dev, "Local CA ACK delay: %d, max MTU: %d, port width cap: %d\n",
- dev_cap->local_ca_ack_delay, 128 << dev_cap->max_mtu,
- dev_cap->max_port_width);
+ dev_cap->local_ca_ack_delay, 128 << dev_cap->max_mtu[1],
+ dev_cap->max_port_width[1]);
mlx4_dbg(dev, "Max SQ desc size: %d, max SQ S/G: %d\n",
dev_cap->max_sq_desc_sz, dev_cap->max_sq_sg);
mlx4_dbg(dev, "Max RQ desc size: %d, max RQ S/G: %d\n",
@@ -491,7 +521,8 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
((fw_ver & 0x0000ffffull) << 16);
MLX4_GET(cmd_if_rev, outbox, QUERY_FW_CMD_IF_REV_OFFSET);
- if (cmd_if_rev != MLX4_COMMAND_INTERFACE_REV) {
+ if (cmd_if_rev < MLX4_COMMAND_INTERFACE_MIN_REV ||
+ cmd_if_rev > MLX4_COMMAND_INTERFACE_MAX_REV) {
mlx4_err(dev, "Installed FW has unsupported "
"command interface revision %d.\n",
cmd_if_rev);
@@ -499,12 +530,15 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
(int) (dev->caps.fw_ver >> 32),
(int) (dev->caps.fw_ver >> 16) & 0xffff,
(int) dev->caps.fw_ver & 0xffff);
- mlx4_err(dev, "This driver version supports only revision %d.\n",
- MLX4_COMMAND_INTERFACE_REV);
+ mlx4_err(dev, "This driver version supports only revisions %d to %d.\n",
+ MLX4_COMMAND_INTERFACE_MIN_REV, MLX4_COMMAND_INTERFACE_MAX_REV);
err = -ENODEV;
goto out;
}
+ if (cmd_if_rev < MLX4_COMMAND_INTERFACE_NEW_PORT_CMDS)
+ dev->flags |= MLX4_FLAG_OLD_PORT_CMDS;
+
MLX4_GET(lg, outbox, QUERY_FW_MAX_CMD_OFFSET);
cmd->max_cmds = 1 << lg;
@@ -708,13 +742,15 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
return err;
}
-int mlx4_INIT_PORT(struct mlx4_dev *dev, struct mlx4_init_port_param *param, int port)
+int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
{
struct mlx4_cmd_mailbox *mailbox;
u32 *inbox;
int err;
u32 flags;
+ u16 field;
+ if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
#define INIT_PORT_IN_SIZE 256
#define INIT_PORT_FLAGS_OFFSET 0x00
#define INIT_PORT_FLAG_SIG (1 << 18)
@@ -729,32 +765,32 @@ int mlx4_INIT_PORT(struct mlx4_dev *dev, struct mlx4_init_port_param *param, int
#define INIT_PORT_NODE_GUID_OFFSET 0x18
#define INIT_PORT_SI_GUID_OFFSET 0x20
- mailbox = mlx4_alloc_cmd_mailbox(dev);
- if (IS_ERR(mailbox))
- return PTR_ERR(mailbox);
- inbox = mailbox->buf;
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+ inbox = mailbox->buf;
- memset(inbox, 0, INIT_PORT_IN_SIZE);
+ memset(inbox, 0, INIT_PORT_IN_SIZE);
- flags = 0;
- flags |= param->set_guid0 ? INIT_PORT_FLAG_G0 : 0;
- flags |= param->set_node_guid ? INIT_PORT_FLAG_NG : 0;
- flags |= param->set_si_guid ? INIT_PORT_FLAG_SIG : 0;
- flags |= (param->vl_cap & 0xf) << INIT_PORT_VL_SHIFT;
- flags |= (param->port_width_cap & 0xf) << INIT_PORT_PORT_WIDTH_SHIFT;
- MLX4_PUT(inbox, flags, INIT_PORT_FLAGS_OFFSET);
+ flags = 0;
+ flags |= (dev->caps.vl_cap[port] & 0xf) << INIT_PORT_VL_SHIFT;
+ flags |= (dev->caps.port_width_cap[port] & 0xf) << INIT_PORT_PORT_WIDTH_SHIFT;
+ MLX4_PUT(inbox, flags, INIT_PORT_FLAGS_OFFSET);
- MLX4_PUT(inbox, param->mtu, INIT_PORT_MTU_OFFSET);
- MLX4_PUT(inbox, param->max_gid, INIT_PORT_MAX_GID_OFFSET);
- MLX4_PUT(inbox, param->max_pkey, INIT_PORT_MAX_PKEY_OFFSET);
- MLX4_PUT(inbox, param->guid0, INIT_PORT_GUID0_OFFSET);
- MLX4_PUT(inbox, param->node_guid, INIT_PORT_NODE_GUID_OFFSET);
- MLX4_PUT(inbox, param->si_guid, INIT_PORT_SI_GUID_OFFSET);
+ field = 128 << dev->caps.mtu_cap[port];
+ MLX4_PUT(inbox, field, INIT_PORT_MTU_OFFSET);
+ field = dev->caps.gid_table_len[port];
+ MLX4_PUT(inbox, field, INIT_PORT_MAX_GID_OFFSET);
+ field = dev->caps.pkey_table_len[port];
+ MLX4_PUT(inbox, field, INIT_PORT_MAX_PKEY_OFFSET);
- err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_INIT_PORT,
- MLX4_CMD_TIME_CLASS_A);
+ err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_INIT_PORT,
+ MLX4_CMD_TIME_CLASS_A);
- mlx4_free_cmd_mailbox(dev, mailbox);
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ } else
+ err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT,
+ MLX4_CMD_TIME_CLASS_A);
return err;
}
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index 2616fa5..296254a 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -59,13 +59,13 @@ struct mlx4_dev_cap {
int max_responder_per_qp;
int max_rdma_global;
int local_ca_ack_delay;
- int max_mtu;
- int max_port_width;
- int max_vl;
int num_ports;
- int max_gids;
+ int max_mtu[MLX4_MAX_PORTS + 1];
+ int max_port_width[MLX4_MAX_PORTS + 1];
+ int max_vl[MLX4_MAX_PORTS + 1];
+ int max_gids[MLX4_MAX_PORTS + 1];
+ int max_pkeys[MLX4_MAX_PORTS + 1];
u16 stat_rate_support;
- int max_pkeys;
u32 flags;
int reserved_uars;
int uar_size;
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index d417293..41eafeb 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -88,6 +88,7 @@ static struct mlx4_profile default_profile = {
static int __devinit mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
int err;
+ int i;
err = mlx4_QUERY_DEV_CAP(dev, dev_cap);
if (err) {
@@ -117,11 +118,15 @@ static int __devinit mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev
}
dev->caps.num_ports = dev_cap->num_ports;
+ for (i = 1; i <= dev->caps.num_ports; ++i) {
+ dev->caps.vl_cap[i] = dev_cap->max_vl[i];
+ dev->caps.mtu_cap[i] = dev_cap->max_mtu[i];
+ dev->caps.gid_table_len[i] = dev_cap->max_gids[i];
+ dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
+ dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
+ }
+
dev->caps.num_uars = dev_cap->uar_size / PAGE_SIZE;
- dev->caps.vl_cap = dev_cap->max_vl;
- dev->caps.mtu_cap = dev_cap->max_mtu;
- dev->caps.gid_table_len = dev_cap->max_gids;
- dev->caps.pkey_table_len = dev_cap->max_pkeys;
dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
dev->caps.bf_reg_size = dev_cap->bf_reg_size;
dev->caps.bf_regs_per_page = dev_cap->bf_regs_per_page;
@@ -148,7 +153,6 @@ static int __devinit mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev
dev->caps.reserved_mrws = dev_cap->reserved_mrws;
dev->caps.reserved_uars = dev_cap->reserved_uars;
dev->caps.reserved_pds = dev_cap->reserved_pds;
- dev->caps.port_width_cap = dev_cap->max_port_width;
dev->caps.mtt_entry_sz = MLX4_MTT_ENTRY_PER_SEG * dev_cap->mtt_entry_sz;
dev->caps.page_size_cap = ~(u32) (dev_cap->min_page_sz - 1);
dev->caps.flags = dev_cap->flags;
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 4fb552d..7d1eaa9 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -54,6 +54,7 @@ enum {
MLX4_CMD_INIT_PORT = 0x9,
MLX4_CMD_CLOSE_PORT = 0xa,
MLX4_CMD_QUERY_HCA = 0xb,
+ MLX4_CMD_QUERY_PORT = 0x43,
MLX4_CMD_SET_PORT = 0xc,
MLX4_CMD_ACCESS_DDR = 0x2e,
MLX4_CMD_MAP_ICM = 0xffa,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8c5f8fd..b372f59 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -41,6 +41,7 @@
enum {
MLX4_FLAG_MSI_X = 1 << 0,
+ MLX4_FLAG_OLD_PORT_CMDS = 1 << 1,
};
enum {
@@ -131,10 +132,10 @@ enum {
struct mlx4_caps {
u64 fw_ver;
int num_ports;
- int vl_cap;
- int mtu_cap;
- int gid_table_len;
- int pkey_table_len;
+ int vl_cap[MLX4_MAX_PORTS + 1];
+ int mtu_cap[MLX4_MAX_PORTS + 1];
+ int gid_table_len[MLX4_MAX_PORTS + 1];
+ int pkey_table_len[MLX4_MAX_PORTS + 1];
int local_ca_ack_delay;
int num_uars;
int bf_reg_size;
@@ -174,7 +175,7 @@ struct mlx4_caps {
u32 page_size_cap;
u32 flags;
u16 stat_rate_support;
- u8 port_width_cap;
+ u8 port_width_cap[MLX4_MAX_PORTS + 1];
};
struct mlx4_buf_list {
@@ -322,7 +323,7 @@ int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, struct mlx4_mtt *mtt,
void mlx4_srq_free(struct mlx4_dev *dev, struct mlx4_srq *srq);
int mlx4_srq_arm(struct mlx4_dev *dev, struct mlx4_srq *srq, int limit_watermark);
-int mlx4_INIT_PORT(struct mlx4_dev *dev, struct mlx4_init_port_param *param, int port);
+int mlx4_INIT_PORT(struct mlx4_dev *dev, int port);
int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 9eeb61a..10c57d2 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -269,6 +269,10 @@ struct mlx4_wqe_data_seg {
__be64 addr;
};
+enum {
+ MLX4_INLINE_ALIGN = 64,
+};
+
struct mlx4_wqe_inline_seg {
__be32 byte_count;
};
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/