aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/mlx5
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/hw/mlx5')
-rw-r--r--drivers/infiniband/hw/mlx5/Kconfig2
-rw-r--r--drivers/infiniband/hw/mlx5/cq.c410
-rw-r--r--drivers/infiniband/hw/mlx5/doorbell.c4
-rw-r--r--drivers/infiniband/hw/mlx5/main.c72
-rw-r--r--drivers/infiniband/hw/mlx5/mem.c80
-rw-r--r--drivers/infiniband/hw/mlx5/mlx5_ib.h35
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c461
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c806
-rw-r--r--drivers/infiniband/hw/mlx5/srq.c26
-rw-r--r--drivers/infiniband/hw/mlx5/user.h12
10 files changed, 1553 insertions, 355 deletions
diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig
index 8e6aebfaf8a..10df386c634 100644
--- a/drivers/infiniband/hw/mlx5/Kconfig
+++ b/drivers/infiniband/hw/mlx5/Kconfig
@@ -1,6 +1,6 @@
config MLX5_INFINIBAND
tristate "Mellanox Connect-IB HCA support"
- depends on NETDEVICES && ETHERNET && PCI && X86
+ depends on NETDEVICES && ETHERNET && PCI
select NET_VENDOR_MELLANOX
select MLX5_CORE
---help---
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 344ab03948a..8ae4f896cb4 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -32,6 +32,7 @@
#include <linux/kref.h>
#include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
#include "mlx5_ib.h"
#include "user.h"
@@ -73,14 +74,24 @@ static void *get_cqe(struct mlx5_ib_cq *cq, int n)
return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz);
}
+static u8 sw_ownership_bit(int n, int nent)
+{
+ return (n & nent) ? 1 : 0;
+}
+
static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
{
void *cqe = get_cqe(cq, n & cq->ibcq.cqe);
struct mlx5_cqe64 *cqe64;
cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
- return ((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^
- !!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
+
+ if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
+ !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
+ return cqe;
+ } else {
+ return NULL;
+ }
}
static void *next_cqe_sw(struct mlx5_ib_cq *cq)
@@ -351,6 +362,43 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
qp->sq.last_poll = tail;
}
+static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
+{
+ mlx5_buf_free(&dev->mdev, &buf->buf);
+}
+
+static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
+ struct ib_sig_err *item)
+{
+ u16 syndrome = be16_to_cpu(cqe->syndrome);
+
+#define GUARD_ERR (1 << 13)
+#define APPTAG_ERR (1 << 12)
+#define REFTAG_ERR (1 << 11)
+
+ if (syndrome & GUARD_ERR) {
+ item->err_type = IB_SIG_BAD_GUARD;
+ item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
+ item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
+ } else
+ if (syndrome & REFTAG_ERR) {
+ item->err_type = IB_SIG_BAD_REFTAG;
+ item->expected = be32_to_cpu(cqe->expected_reftag);
+ item->actual = be32_to_cpu(cqe->actual_reftag);
+ } else
+ if (syndrome & APPTAG_ERR) {
+ item->err_type = IB_SIG_BAD_APPTAG;
+ item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
+ item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
+ } else {
+ pr_err("Got signature completion error with bad syndrome %04x\n",
+ syndrome);
+ }
+
+ item->sig_err_offset = be64_to_cpu(cqe->err_offset);
+ item->key = be32_to_cpu(cqe->mkey);
+}
+
static int mlx5_poll_one(struct mlx5_ib_cq *cq,
struct mlx5_ib_qp **cur_qp,
struct ib_wc *wc)
@@ -360,12 +408,16 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
struct mlx5_cqe64 *cqe64;
struct mlx5_core_qp *mqp;
struct mlx5_ib_wq *wq;
+ struct mlx5_sig_err_cqe *sig_err_cqe;
+ struct mlx5_core_mr *mmr;
+ struct mlx5_ib_mr *mr;
uint8_t opcode;
uint32_t qpn;
u16 wqe_ctr;
void *cqe;
int idx;
+repoll:
cqe = next_cqe_sw(cq);
if (!cqe)
return -EAGAIN;
@@ -379,7 +431,18 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
*/
rmb();
- /* TBD: resize CQ */
+ opcode = cqe64->op_own >> 4;
+ if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
+ if (likely(cq->resize_buf)) {
+ free_cq_buf(dev, &cq->buf);
+ cq->buf = *cq->resize_buf;
+ kfree(cq->resize_buf);
+ cq->resize_buf = NULL;
+ goto repoll;
+ } else {
+ mlx5_ib_warn(dev, "unexpected resize cqe\n");
+ }
+ }
qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
@@ -398,7 +461,6 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
}
wc->qp = &(*cur_qp)->ibqp;
- opcode = cqe64->op_own >> 4;
switch (opcode) {
case MLX5_CQE_REQ:
wq = &(*cur_qp)->sq;
@@ -449,6 +511,33 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
}
}
break;
+ case MLX5_CQE_SIG_ERR:
+ sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;
+
+ read_lock(&dev->mdev.priv.mr_table.lock);
+ mmr = __mlx5_mr_lookup(&dev->mdev,
+ mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
+ if (unlikely(!mmr)) {
+ read_unlock(&dev->mdev.priv.mr_table.lock);
+ mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
+ cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
+ return -EINVAL;
+ }
+
+ mr = to_mibmr(mmr);
+ get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
+ mr->sig->sig_err_exists = true;
+ mr->sig->sigerr_count++;
+
+ mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
+ cq->mcq.cqn, mr->sig->err_item.key,
+ mr->sig->err_item.err_type,
+ mr->sig->err_item.sig_err_offset,
+ mr->sig->err_item.expected,
+ mr->sig->err_item.actual);
+
+ read_unlock(&dev->mdev.priv.mr_table.lock);
+ goto repoll;
}
return 0;
@@ -503,29 +592,35 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf,
return err;
buf->cqe_size = cqe_size;
+ buf->nent = nent;
return 0;
}
-static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
-{
- mlx5_buf_free(&dev->mdev, &buf->buf);
-}
-
static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
struct ib_ucontext *context, struct mlx5_ib_cq *cq,
int entries, struct mlx5_create_cq_mbox_in **cqb,
int *cqe_size, int *index, int *inlen)
{
struct mlx5_ib_create_cq ucmd;
+ size_t ucmdlen;
int page_shift;
int npages;
int ncont;
int err;
- if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)))
+ ucmdlen =
+ (udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+ sizeof(ucmd)) ? (sizeof(ucmd) -
+ sizeof(ucmd.reserved)) : sizeof(ucmd);
+
+ if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
return -EFAULT;
+ if (ucmdlen == sizeof(ucmd) &&
+ ucmd.reserved != 0)
+ return -EINVAL;
+
if (ucmd.cqe_size != 64 && ucmd.cqe_size != 128)
return -EINVAL;
@@ -556,7 +651,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
goto err_db;
}
mlx5_ib_populate_pas(dev, cq->buf.umem, page_shift, (*cqb)->pas, 0);
- (*cqb)->ctx.log_pg_sz = page_shift - PAGE_SHIFT;
+ (*cqb)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
*index = to_mucontext(context)->uuari.uars[0].index;
@@ -576,16 +671,16 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context)
ib_umem_release(cq->buf.umem);
}
-static void init_cq_buf(struct mlx5_ib_cq *cq, int nent)
+static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf)
{
int i;
void *cqe;
struct mlx5_cqe64 *cqe64;
- for (i = 0; i < nent; i++) {
- cqe = get_cqe(cq, i);
- cqe64 = (cq->buf.cqe_size == 64) ? cqe : cqe + 64;
- cqe64->op_own = 0xf1;
+ for (i = 0; i < buf->nent; i++) {
+ cqe = get_cqe_from_buf(buf, i, buf->cqe_size);
+ cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
+ cqe64->op_own = MLX5_CQE_INVALID << 4;
}
}
@@ -610,7 +705,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
if (err)
goto err_db;
- init_cq_buf(cq, entries);
+ init_cq_buf(cq, &cq->buf);
*inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * cq->buf.buf.npages;
*cqb = mlx5_vzalloc(*inlen);
@@ -620,7 +715,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
}
mlx5_fill_page_array(&cq->buf.buf, (*cqb)->pas);
- (*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - PAGE_SHIFT;
+ (*cqb)->ctx.log_pg_sz = cq->buf.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
*index = dev->mdev.priv.uuari.uars[0].index;
return 0;
@@ -653,8 +748,11 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
int eqn;
int err;
+ if (entries < 0)
+ return ERR_PTR(-EINVAL);
+
entries = roundup_pow_of_two(entries + 1);
- if (entries < 1 || entries > dev->mdev.caps.max_cqes)
+ if (entries > dev->mdev.caps.max_cqes)
return ERR_PTR(-EINVAL);
cq = kzalloc(sizeof(*cq), GFP_KERNEL);
@@ -747,17 +845,9 @@ int mlx5_ib_destroy_cq(struct ib_cq *cq)
return 0;
}
-static int is_equal_rsn(struct mlx5_cqe64 *cqe64, struct mlx5_ib_srq *srq,
- u32 rsn)
+static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn)
{
- u32 lrsn;
-
- if (srq)
- lrsn = be32_to_cpu(cqe64->srqn) & 0xffffff;
- else
- lrsn = be32_to_cpu(cqe64->sop_drop_qpn) & 0xffffff;
-
- return rsn == lrsn;
+ return rsn == (ntohl(cqe64->sop_drop_qpn) & 0xffffff);
}
void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 rsn, struct mlx5_ib_srq *srq)
@@ -787,8 +877,8 @@ void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 rsn, struct mlx5_ib_srq *srq)
while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
- if (is_equal_rsn(cqe64, srq, rsn)) {
- if (srq)
+ if (is_equal_rsn(cqe64, rsn)) {
+ if (srq && (ntohl(cqe64->srqn) & 0xffffff))
mlx5_ib_free_srq_wqe(srq, be16_to_cpu(cqe64->wqe_counter));
++nfreed;
} else if (nfreed) {
@@ -823,12 +913,266 @@ void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
- return -ENOSYS;
+ struct mlx5_modify_cq_mbox_in *in;
+ struct mlx5_ib_dev *dev = to_mdev(cq->device);
+ struct mlx5_ib_cq *mcq = to_mcq(cq);
+ int err;
+ u32 fsel;
+
+ if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
+ return -ENOSYS;
+
+ in = kzalloc(sizeof(*in), GFP_KERNEL);
+ if (!in)
+ return -ENOMEM;
+
+ in->cqn = cpu_to_be32(mcq->mcq.cqn);
+ fsel = (MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT);
+ in->ctx.cq_period = cpu_to_be16(cq_period);
+ in->ctx.cq_max_count = cpu_to_be16(cq_count);
+ in->field_select = cpu_to_be32(fsel);
+ err = mlx5_core_modify_cq(&dev->mdev, &mcq->mcq, in, sizeof(*in));
+ kfree(in);
+
+ if (err)
+ mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn);
+
+ return err;
+}
+
+static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+ int entries, struct ib_udata *udata, int *npas,
+ int *page_shift, int *cqe_size)
+{
+ struct mlx5_ib_resize_cq ucmd;
+ struct ib_umem *umem;
+ int err;
+ int npages;
+ struct ib_ucontext *context = cq->buf.umem->context;
+
+ err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
+ if (err)
+ return err;
+
+ if (ucmd.reserved0 || ucmd.reserved1)
+ return -EINVAL;
+
+ umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size,
+ IB_ACCESS_LOCAL_WRITE, 1);
+ if (IS_ERR(umem)) {
+ err = PTR_ERR(umem);
+ return err;
+ }
+
+ mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift,
+ npas, NULL);
+
+ cq->resize_umem = umem;
+ *cqe_size = ucmd.cqe_size;
+
+ return 0;
+}
+
+static void un_resize_user(struct mlx5_ib_cq *cq)
+{
+ ib_umem_release(cq->resize_umem);
+}
+
+static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+ int entries, int cqe_size)
+{
+ int err;
+
+ cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL);
+ if (!cq->resize_buf)
+ return -ENOMEM;
+
+ err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size);
+ if (err)
+ goto ex;
+
+ init_cq_buf(cq, cq->resize_buf);
+
+ return 0;
+
+ex:
+ kfree(cq->resize_buf);
+ return err;
+}
+
+static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
+{
+ free_cq_buf(dev, cq->resize_buf);
+ cq->resize_buf = NULL;
+}
+
+static int copy_resize_cqes(struct mlx5_ib_cq *cq)
+{
+ struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
+ struct mlx5_cqe64 *scqe64;
+ struct mlx5_cqe64 *dcqe64;
+ void *start_cqe;
+ void *scqe;
+ void *dcqe;
+ int ssize;
+ int dsize;
+ int i;
+ u8 sw_own;
+
+ ssize = cq->buf.cqe_size;
+ dsize = cq->resize_buf->cqe_size;
+ if (ssize != dsize) {
+ mlx5_ib_warn(dev, "resize from different cqe size is not supported\n");
+ return -EINVAL;
+ }
+
+ i = cq->mcq.cons_index;
+ scqe = get_sw_cqe(cq, i);
+ scqe64 = ssize == 64 ? scqe : scqe + 64;
+ start_cqe = scqe;
+ if (!scqe) {
+ mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+ return -EINVAL;
+ }
+
+ while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
+ dcqe = get_cqe_from_buf(cq->resize_buf,
+ (i + 1) & (cq->resize_buf->nent),
+ dsize);
+ dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
+ sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent);
+ memcpy(dcqe, scqe, dsize);
+ dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own;
+
+ ++i;
+ scqe = get_sw_cqe(cq, i);
+ scqe64 = ssize == 64 ? scqe : scqe + 64;
+ if (!scqe) {
+ mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+ return -EINVAL;
+ }
+
+ if (scqe == start_cqe) {
+ pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n",
+ cq->mcq.cqn);
+ return -ENOMEM;
+ }
+ }
+ ++cq->mcq.cons_index;
+ return 0;
}
int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
{
- return -ENOSYS;
+ struct mlx5_ib_dev *dev = to_mdev(ibcq->device);
+ struct mlx5_ib_cq *cq = to_mcq(ibcq);
+ struct mlx5_modify_cq_mbox_in *in;
+ int err;
+ int npas;
+ int page_shift;
+ int inlen;
+ int uninitialized_var(cqe_size);
+ unsigned long flags;
+
+ if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
+ pr_info("Firmware does not support resize CQ\n");
+ return -ENOSYS;
+ }
+
+ if (entries < 1)
+ return -EINVAL;
+
+ entries = roundup_pow_of_two(entries + 1);
+ if (entries > dev->mdev.caps.max_cqes + 1)
+ return -EINVAL;
+
+ if (entries == ibcq->cqe + 1)
+ return 0;
+
+ mutex_lock(&cq->resize_mutex);
+ if (udata) {
+ err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
+ &cqe_size);
+ } else {
+ cqe_size = 64;
+ err = resize_kernel(dev, cq, entries, cqe_size);
+ if (!err) {
+ npas = cq->resize_buf->buf.npages;
+ page_shift = cq->resize_buf->buf.page_shift;
+ }
+ }
+
+ if (err)
+ goto ex;
+
+ inlen = sizeof(*in) + npas * sizeof(in->pas[0]);
+ in = mlx5_vzalloc(inlen);
+ if (!in) {
+ err = -ENOMEM;
+ goto ex_resize;
+ }
+
+ if (udata)
+ mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
+ in->pas, 0);
+ else
+ mlx5_fill_page_array(&cq->resize_buf->buf, in->pas);
+
+ in->field_select = cpu_to_be32(MLX5_MODIFY_CQ_MASK_LOG_SIZE |
+ MLX5_MODIFY_CQ_MASK_PG_OFFSET |
+ MLX5_MODIFY_CQ_MASK_PG_SIZE);
+ in->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
+ in->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;
+ in->ctx.page_offset = 0;
+ in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(entries) << 24);
+ in->hdr.opmod = cpu_to_be16(MLX5_CQ_OPMOD_RESIZE);
+ in->cqn = cpu_to_be32(cq->mcq.cqn);
+
+ err = mlx5_core_modify_cq(&dev->mdev, &cq->mcq, in, inlen);
+ if (err)
+ goto ex_alloc;
+
+ if (udata) {
+ cq->ibcq.cqe = entries - 1;
+ ib_umem_release(cq->buf.umem);
+ cq->buf.umem = cq->resize_umem;
+ cq->resize_umem = NULL;
+ } else {
+ struct mlx5_ib_cq_buf tbuf;
+ int resized = 0;
+
+ spin_lock_irqsave(&cq->lock, flags);
+ if (cq->resize_buf) {
+ err = copy_resize_cqes(cq);
+ if (!err) {
+ tbuf = cq->buf;
+ cq->buf = *cq->resize_buf;
+ kfree(cq->resize_buf);
+ cq->resize_buf = NULL;
+ resized = 1;
+ }
+ }
+ cq->ibcq.cqe = entries - 1;
+ spin_unlock_irqrestore(&cq->lock, flags);
+ if (resized)
+ free_cq_buf(dev, &tbuf);
+ }
+ mutex_unlock(&cq->resize_mutex);
+
+ mlx5_vfree(in);
+ return 0;
+
+ex_alloc:
+ mlx5_vfree(in);
+
+ex_resize:
+ if (udata)
+ un_resize_user(cq);
+ else
+ un_resize_kernel(dev, cq);
+ex:
+ mutex_unlock(&cq->resize_mutex);
+ return err;
}
int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq)
diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c
index 256a23344f2..ece028fc47d 100644
--- a/drivers/infiniband/hw/mlx5/doorbell.c
+++ b/drivers/infiniband/hw/mlx5/doorbell.c
@@ -47,7 +47,6 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
struct mlx5_db *db)
{
struct mlx5_ib_user_db_page *page;
- struct ib_umem_chunk *chunk;
int err = 0;
mutex_lock(&context->db_page_mutex);
@@ -75,8 +74,7 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
list_add(&page->list, &context->db_page_list);
found:
- chunk = list_entry(page->umem->chunk_list.next, struct ib_umem_chunk, list);
- db->dma = sg_dma_address(chunk->page_list) + (virt & ~PAGE_MASK);
+ db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK);
db->u.user_page = page;
++page->refcnt;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3f831de9a4d..364d4b6937f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -46,8 +46,8 @@
#include "mlx5_ib.h"
#define DRIVER_NAME "mlx5_ib"
-#define DRIVER_VERSION "1.0"
-#define DRIVER_RELDATE "June 2013"
+#define DRIVER_VERSION "2.2-1"
+#define DRIVER_RELDATE "Feb 2014"
MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver");
@@ -164,6 +164,7 @@ int mlx5_vector2eqn(struct mlx5_ib_dev *dev, int vector, int *eqn, int *irqn)
static int alloc_comp_eqs(struct mlx5_ib_dev *dev)
{
struct mlx5_eq_table *table = &dev->mdev.priv.eq_table;
+ char name[MLX5_MAX_EQ_NAME];
struct mlx5_eq *eq, *n;
int ncomp_vec;
int nent;
@@ -180,11 +181,10 @@ static int alloc_comp_eqs(struct mlx5_ib_dev *dev)
goto clean;
}
- snprintf(eq->name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i);
+ snprintf(name, MLX5_MAX_EQ_NAME, "mlx5_comp%d", i);
err = mlx5_create_map_eq(&dev->mdev, eq,
i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
- eq->name,
- &dev->mdev.priv.uuari.uars[0]);
+ name, &dev->mdev.priv.uuari.uars[0]);
if (err) {
kfree(eq);
goto clean;
@@ -261,8 +261,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT |
IB_DEVICE_PORT_ACTIVE_EVENT |
IB_DEVICE_SYS_IMAGE_GUID |
- IB_DEVICE_RC_RNR_NAK_GEN |
- IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+ IB_DEVICE_RC_RNR_NAK_GEN;
flags = dev->mdev.caps.flags;
if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR)
props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR;
@@ -274,6 +273,17 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
if (flags & MLX5_DEV_CAP_FLAG_XRC)
props->device_cap_flags |= IB_DEVICE_XRC;
props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
+ if (flags & MLX5_DEV_CAP_FLAG_SIG_HAND_OVER) {
+ props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
+ /* At this stage no support for signature handover */
+ props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
+ IB_PROT_T10DIF_TYPE_2 |
+ IB_PROT_T10DIF_TYPE_3;
+ props->sig_guard_cap = IB_GUARD_T10DIF_CRC |
+ IB_GUARD_T10DIF_CSUM;
+ }
+ if (flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)
+ props->device_cap_flags |= IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
props->vendor_id = be32_to_cpup((__be32 *)(out_mad->data + 36)) &
0xffffff;
@@ -301,9 +311,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->max_srq_sge = max_rq_sg - 1;
props->max_fast_reg_page_list_len = (unsigned int)-1;
props->local_ca_ack_delay = dev->mdev.caps.local_ca_ack_delay;
- props->atomic_cap = dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_ATOMIC ?
- IB_ATOMIC_HCA : IB_ATOMIC_NONE;
- props->masked_atomic_cap = IB_ATOMIC_HCA;
+ props->atomic_cap = IB_ATOMIC_NONE;
+ props->masked_atomic_cap = IB_ATOMIC_NONE;
props->max_pkeys = be16_to_cpup((__be16 *)(out_mad->data + 28));
props->max_mcast_grp = 1 << dev->mdev.caps.log_max_mcg;
props->max_mcast_qp_attach = dev->mdev.caps.max_qp_mcg;
@@ -537,34 +546,51 @@ 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 req;
+ 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;
+ int gross_uuars;
int num_uars;
+ int ver;
int uuarn;
int err;
int i;
+ int reqlen;
if (!dev->ib_active)
return ERR_PTR(-EAGAIN);
- err = ib_copy_from_udata(&req, udata, sizeof(req));
+ memset(&req, 0, sizeof(req));
+ 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))
+ ver = 2;
+ else
+ return ERR_PTR(-EINVAL);
+
+ err = ib_copy_from_udata(&req, udata, reqlen);
if (err)
return ERR_PTR(err);
+ if (req.flags || req.reserved)
+ return ERR_PTR(-EINVAL);
+
if (req.total_num_uuars > MLX5_MAX_UUARS)
return ERR_PTR(-ENOMEM);
if (req.total_num_uuars == 0)
return ERR_PTR(-EINVAL);
- req.total_num_uuars = ALIGN(req.total_num_uuars, MLX5_BF_REGS_PER_PAGE);
+ 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)
return ERR_PTR(-EINVAL);
- num_uars = req.total_num_uuars / MLX5_BF_REGS_PER_PAGE;
+ num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
+ gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
resp.qp_tab_size = 1 << dev->mdev.caps.log_max_qp;
resp.bf_reg_size = dev->mdev.caps.bf_reg_size;
resp.cache_line_size = L1_CACHE_BYTES;
@@ -586,7 +612,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
goto out_ctx;
}
- uuari->bitmap = kcalloc(BITS_TO_LONGS(req.total_num_uuars),
+ uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars),
sizeof(*uuari->bitmap),
GFP_KERNEL);
if (!uuari->bitmap) {
@@ -596,13 +622,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
/*
* clear all fast path uuars
*/
- for (i = 0; i < req.total_num_uuars; i++) {
+ for (i = 0; i < gross_uuars; i++) {
uuarn = i & 3;
if (uuarn == 2 || uuarn == 3)
set_bit(i, uuari->bitmap);
}
- uuari->count = kcalloc(req.total_num_uuars, sizeof(*uuari->count), GFP_KERNEL);
+ uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL);
if (!uuari->count) {
err = -ENOMEM;
goto out_bitmap;
@@ -624,6 +650,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
if (err)
goto out_uars;
+ uuari->ver = ver;
uuari->num_low_latency_uuars = req.num_low_latency_uuars;
uuari->uars = uars;
uuari->num_uars = num_uars;
@@ -746,7 +773,8 @@ static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
seg->start_addr = 0;
- err = mlx5_core_create_mkey(&dev->mdev, &mr, in, sizeof(*in));
+ err = mlx5_core_create_mkey(&dev->mdev, &mr, in, sizeof(*in),
+ NULL, NULL, NULL);
if (err) {
mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
goto err_in;
@@ -1006,6 +1034,11 @@ static void mlx5_ib_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
ibev.device = &ibdev->ib_dev;
ibev.element.port_num = port;
+ if (port < 1 || port > ibdev->num_ports) {
+ mlx5_ib_warn(ibdev, "warning: event on port %d\n", port);
+ return;
+ }
+
if (ibdev->ib_active)
ib_dispatch_event(&ibev);
}
@@ -1401,12 +1434,15 @@ static int init_one(struct pci_dev *pdev,
dev->ib_dev.get_dma_mr = mlx5_ib_get_dma_mr;
dev->ib_dev.reg_user_mr = mlx5_ib_reg_user_mr;
dev->ib_dev.dereg_mr = mlx5_ib_dereg_mr;
+ dev->ib_dev.destroy_mr = mlx5_ib_destroy_mr;
dev->ib_dev.attach_mcast = mlx5_ib_mcg_attach;
dev->ib_dev.detach_mcast = mlx5_ib_mcg_detach;
dev->ib_dev.process_mad = mlx5_ib_process_mad;
+ dev->ib_dev.create_mr = mlx5_ib_create_mr;
dev->ib_dev.alloc_fast_reg_mr = mlx5_ib_alloc_fast_reg_mr;
dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
dev->ib_dev.free_fast_reg_page_list = mlx5_ib_free_fast_reg_page_list;
+ dev->ib_dev.check_mr_status = mlx5_ib_check_mr_status;
if (mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC) {
dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 3a5322870b9..8499aec94db 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -44,16 +44,17 @@
void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
int *ncont, int *order)
{
- struct ib_umem_chunk *chunk;
unsigned long tmp;
unsigned long m;
- int i, j, k;
+ int i, k;
u64 base = 0;
int p = 0;
int skip;
int mask;
u64 len;
u64 pfn;
+ struct scatterlist *sg;
+ int entry;
addr = addr >> PAGE_SHIFT;
tmp = (unsigned long)addr;
@@ -61,32 +62,31 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
skip = 1 << m;
mask = skip - 1;
i = 0;
- list_for_each_entry(chunk, &umem->chunk_list, list)
- for (j = 0; j < chunk->nmap; j++) {
- len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
- pfn = sg_dma_address(&chunk->page_list[j]) >> PAGE_SHIFT;
- for (k = 0; k < len; k++) {
- if (!(i & mask)) {
- tmp = (unsigned long)pfn;
- m = min(m, find_first_bit(&tmp, sizeof(tmp)));
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+ len = sg_dma_len(sg) >> PAGE_SHIFT;
+ pfn = sg_dma_address(sg) >> PAGE_SHIFT;
+ for (k = 0; k < len; k++) {
+ if (!(i & mask)) {
+ tmp = (unsigned long)pfn;
+ m = min(m, find_first_bit(&tmp, sizeof(tmp)));
+ skip = 1 << m;
+ mask = skip - 1;
+ base = pfn;
+ p = 0;
+ } else {
+ if (base + p != pfn) {
+ tmp = (unsigned long)p;
+ m = find_first_bit(&tmp, sizeof(tmp));
skip = 1 << m;
mask = skip - 1;
base = pfn;
p = 0;
- } else {
- if (base + p != pfn) {
- tmp = (unsigned long)p;
- m = find_first_bit(&tmp, sizeof(tmp));
- skip = 1 << m;
- mask = skip - 1;
- base = pfn;
- p = 0;
- }
}
- p++;
- i++;
}
+ p++;
+ i++;
}
+ }
if (i) {
m = min_t(unsigned long, ilog2(roundup_pow_of_two(i)), m);
@@ -112,32 +112,32 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
{
int shift = page_shift - PAGE_SHIFT;
int mask = (1 << shift) - 1;
- struct ib_umem_chunk *chunk;
- int i, j, k;
+ int i, k;
u64 cur = 0;
u64 base;
int len;
+ struct scatterlist *sg;
+ int entry;
i = 0;
- list_for_each_entry(chunk, &umem->chunk_list, list)
- for (j = 0; j < chunk->nmap; j++) {
- len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
- base = sg_dma_address(&chunk->page_list[j]);
- for (k = 0; k < len; k++) {
- if (!(i & mask)) {
- cur = base + (k << PAGE_SHIFT);
- if (umr)
- cur |= 3;
+ for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+ len = sg_dma_len(sg) >> PAGE_SHIFT;
+ base = sg_dma_address(sg);
+ for (k = 0; k < len; k++) {
+ if (!(i & mask)) {
+ cur = base + (k << PAGE_SHIFT);
+ if (umr)
+ cur |= 3;
- pas[i >> shift] = cpu_to_be64(cur);
- mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
- i >> shift, be64_to_cpu(pas[i >> shift]));
- } else
- mlx5_ib_dbg(dev, "=====> 0x%llx\n",
- base + (k << PAGE_SHIFT));
- i++;
- }
+ pas[i >> shift] = cpu_to_be64(cur);
+ mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
+ i >> shift, be64_to_cpu(pas[i >> shift]));
+ } else
+ mlx5_ib_dbg(dev, "=====> 0x%llx\n",
+ base + (k << PAGE_SHIFT));
+ i++;
}
+ }
}
int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 836be915724..f2ccf1a5a29 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -189,12 +189,16 @@ struct mlx5_ib_qp {
int create_type;
u32 pa_lkey;
+
+ /* Store signature errors */
+ bool signature_en;
};
struct mlx5_ib_cq_buf {
struct mlx5_buf buf;
struct ib_umem *umem;
int cqe_size;
+ int nent;
};
enum mlx5_ib_qp_flags {
@@ -220,7 +224,7 @@ struct mlx5_ib_cq {
/* protect resize cq
*/
struct mutex resize_mutex;
- struct mlx5_ib_cq_resize *resize_buf;
+ struct mlx5_ib_cq_buf *resize_buf;
struct ib_umem *resize_umem;
int cqe_size;
};
@@ -260,8 +264,9 @@ struct mlx5_ib_mr {
__be64 *pas;
dma_addr_t dma;
int npages;
- struct completion done;
- enum ib_wc_status status;
+ struct mlx5_ib_dev *dev;
+ struct mlx5_create_mkey_mbox_out out;
+ struct mlx5_core_sig_ctx *sig;
};
struct mlx5_ib_fast_reg_page_list {
@@ -270,6 +275,17 @@ struct mlx5_ib_fast_reg_page_list {
dma_addr_t map;
};
+struct mlx5_ib_umr_context {
+ enum ib_wc_status status;
+ struct completion done;
+};
+
+static inline void mlx5_ib_init_umr_context(struct mlx5_ib_umr_context *context)
+{
+ context->status = -1;
+ init_completion(&context->done);
+}
+
struct umr_common {
struct ib_pd *pd;
struct ib_cq *cq;
@@ -323,6 +339,7 @@ struct mlx5_cache_ent {
struct mlx5_ib_dev *dev;
struct work_struct work;
struct delayed_work dwork;
+ int pending;
};
struct mlx5_mr_cache {
@@ -358,6 +375,8 @@ struct mlx5_ib_dev {
spinlock_t mr_lock;
struct mlx5_ib_resources devr;
struct mlx5_mr_cache cache;
+ struct timer_list delay_timer;
+ int fill_delay;
};
static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -390,6 +409,11 @@ static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp)
return container_of(mqp, struct mlx5_ib_qp, mqp);
}
+static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr)
+{
+ return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
static inline struct mlx5_ib_pd *to_mpd(struct ib_pd *ibpd)
{
return container_of(ibpd, struct mlx5_ib_pd, ibpd);
@@ -489,6 +513,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
u64 virt_addr, int access_flags,
struct ib_udata *udata);
int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr);
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+ struct ib_mr_init_attr *mr_init_attr);
struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len);
struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
@@ -524,6 +551,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift);
void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+ struct ib_mr_status *mr_status);
static inline void init_query_mad(struct ib_smp *mad)
{
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bd41df95b6f..afa873bd028 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -35,11 +35,16 @@
#include <linux/random.h>
#include <linux/debugfs.h>
#include <linux/export.h>
+#include <linux/delay.h>
#include <rdma/ib_umem.h>
#include "mlx5_ib.h"
enum {
- DEF_CACHE_SIZE = 10,
+ MAX_PENDING_REG_MR = 8,
+};
+
+enum {
+ MLX5_UMR_ALIGN = 2048
};
static __be64 *mr_align(__be64 *ptr, int align)
@@ -59,15 +64,67 @@ static int order2idx(struct mlx5_ib_dev *dev, int order)
return order - cache->ent[0].order;
}
+static void reg_mr_callback(int status, void *context)
+{
+ struct mlx5_ib_mr *mr = context;
+ struct mlx5_ib_dev *dev = mr->dev;
+ struct mlx5_mr_cache *cache = &dev->cache;
+ int c = order2idx(dev, mr->order);
+ struct mlx5_cache_ent *ent = &cache->ent[c];
+ u8 key;
+ unsigned long flags;
+ struct mlx5_mr_table *table = &dev->mdev.priv.mr_table;
+ int err;
+
+ spin_lock_irqsave(&ent->lock, flags);
+ ent->pending--;
+ spin_unlock_irqrestore(&ent->lock, flags);
+ if (status) {
+ mlx5_ib_warn(dev, "async reg mr failed. status %d\n", status);
+ kfree(mr);
+ dev->fill_delay = 1;
+ mod_timer(&dev->delay_timer, jiffies + HZ);
+ return;
+ }
+
+ if (mr->out.hdr.status) {
+ mlx5_ib_warn(dev, "failed - status %d, syndorme 0x%x\n",
+ mr->out.hdr.status,
+ be32_to_cpu(mr->out.hdr.syndrome));
+ kfree(mr);
+ dev->fill_delay = 1;
+ mod_timer(&dev->delay_timer, jiffies + HZ);
+ return;
+ }
+
+ spin_lock_irqsave(&dev->mdev.priv.mkey_lock, flags);
+ key = dev->mdev.priv.mkey_key++;
+ spin_unlock_irqrestore(&dev->mdev.priv.mkey_lock, flags);
+ mr->mmr.key = mlx5_idx_to_mkey(be32_to_cpu(mr->out.mkey) & 0xffffff) | key;
+
+ cache->last_add = jiffies;
+
+ spin_lock_irqsave(&ent->lock, flags);
+ list_add_tail(&mr->list, &ent->head);
+ ent->cur++;
+ ent->size++;
+ spin_unlock_irqrestore(&ent->lock, flags);
+
+ write_lock_irqsave(&table->lock, flags);
+ err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmr.key),
+ &mr->mmr);
+ if (err)
+ pr_err("Error inserting to mr tree. 0x%x\n", -err);
+ write_unlock_irqrestore(&table->lock, flags);
+}
+
static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
{
- struct device *ddev = dev->ib_dev.dma_device;
struct mlx5_mr_cache *cache = &dev->cache;
struct mlx5_cache_ent *ent = &cache->ent[c];
struct mlx5_create_mkey_mbox_in *in;
struct mlx5_ib_mr *mr;
int npages = 1 << ent->order;
- int size = sizeof(u64) * npages;
int err = 0;
int i;
@@ -76,87 +133,66 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
return -ENOMEM;
for (i = 0; i < num; i++) {
+ if (ent->pending >= MAX_PENDING_REG_MR) {
+ err = -EAGAIN;
+ break;
+ }
+
mr = kzalloc(sizeof(*mr), GFP_KERNEL);
if (!mr) {
err = -ENOMEM;
- goto out;
+ break;
}
mr->order = ent->order;
mr->umred = 1;
- mr->pas = kmalloc(size + 0x3f, GFP_KERNEL);
- if (!mr->pas) {
- kfree(mr);
- err = -ENOMEM;
- goto out;
- }
- mr->dma = dma_map_single(ddev, mr_align(mr->pas, 0x40), size,
- DMA_TO_DEVICE);
- if (dma_mapping_error(ddev, mr->dma)) {
- kfree(mr->pas);
- kfree(mr);
- err = -ENOMEM;
- goto out;
- }
-
+ mr->dev = dev;
in->seg.status = 1 << 6;
in->seg.xlt_oct_size = cpu_to_be32((npages + 1) / 2);
in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
in->seg.flags = MLX5_ACCESS_MODE_MTT | MLX5_PERM_UMR_EN;
in->seg.log2_page_size = 12;
+ spin_lock_irq(&ent->lock);
+ ent->pending++;
+ spin_unlock_irq(&ent->lock);
err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in,
- sizeof(*in));
+ sizeof(*in), reg_mr_callback,
+ mr, &mr->out);
if (err) {
mlx5_ib_warn(dev, "create mkey failed %d\n", err);
- dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE);
- kfree(mr->pas);
kfree(mr);
- goto out;
+ break;
}
- cache->last_add = jiffies;
-
- spin_lock(&ent->lock);
- list_add_tail(&mr->list, &ent->head);
- ent->cur++;
- ent->size++;
- spin_unlock(&ent->lock);
}
-out:
kfree(in);
return err;
}
static void remove_keys(struct mlx5_ib_dev *dev, int c, int num)
{
- struct device *ddev = dev->ib_dev.dma_device;
struct mlx5_mr_cache *cache = &dev->cache;
struct mlx5_cache_ent *ent = &cache->ent[c];
struct mlx5_ib_mr *mr;
- int size;
int err;
int i;
for (i = 0; i < num; i++) {
- spin_lock(&ent->lock);
+ spin_lock_irq(&ent->lock);
if (list_empty(&ent->head)) {
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
return;
}
mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list);
list_del(&mr->list);
ent->cur--;
ent->size--;
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
- if (err) {
+ if (err)
mlx5_ib_warn(dev, "failed destroy mkey\n");
- } else {
- size = ALIGN(sizeof(u64) * (1 << mr->order), 0x40);
- dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE);
- kfree(mr->pas);
+ else
kfree(mr);
- }
}
}
@@ -183,9 +219,13 @@ static ssize_t size_write(struct file *filp, const char __user *buf,
return -EINVAL;
if (var > ent->size) {
- err = add_keys(dev, c, var - ent->size);
- if (err)
- return err;
+ do {
+ err = add_keys(dev, c, var - ent->size);
+ if (err && err != -EAGAIN)
+ return err;
+
+ usleep_range(3000, 5000);
+ } while (err);
} else if (var < ent->size) {
remove_keys(dev, c, ent->size - var);
}
@@ -301,23 +341,37 @@ static void __cache_work_func(struct mlx5_cache_ent *ent)
struct mlx5_ib_dev *dev = ent->dev;
struct mlx5_mr_cache *cache = &dev->cache;
int i = order2idx(dev, ent->order);
+ int err;
if (cache->stopped)
return;
ent = &dev->cache.ent[i];
- if (ent->cur < 2 * ent->limit) {
- add_keys(dev, i, 1);
- if (ent->cur < 2 * ent->limit)
- queue_work(cache->wq, &ent->work);
+ if (ent->cur < 2 * ent->limit && !dev->fill_delay) {
+ err = add_keys(dev, i, 1);
+ if (ent->cur < 2 * ent->limit) {
+ if (err == -EAGAIN) {
+ mlx5_ib_dbg(dev, "returned eagain, order %d\n",
+ i + 2);
+ queue_delayed_work(cache->wq, &ent->dwork,
+ msecs_to_jiffies(3));
+ } else if (err) {
+ mlx5_ib_warn(dev, "command failed order %d, err %d\n",
+ i + 2, err);
+ queue_delayed_work(cache->wq, &ent->dwork,
+ msecs_to_jiffies(1000));
+ } else {
+ queue_work(cache->wq, &ent->work);
+ }
+ }
} else if (ent->cur > 2 * ent->limit) {
if (!someone_adding(cache) &&
- time_after(jiffies, cache->last_add + 60 * HZ)) {
+ time_after(jiffies, cache->last_add + 300 * HZ)) {
remove_keys(dev, i, 1);
if (ent->cur > ent->limit)
queue_work(cache->wq, &ent->work);
} else {
- queue_delayed_work(cache->wq, &ent->dwork, 60 * HZ);
+ queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ);
}
}
}
@@ -357,18 +411,18 @@ static struct mlx5_ib_mr *alloc_cached_mr(struct mlx5_ib_dev *dev, int order)
mlx5_ib_dbg(dev, "order %d, cache index %d\n", ent->order, i);
- spin_lock(&ent->lock);
+ spin_lock_irq(&ent->lock);
if (!list_empty(&ent->head)) {
mr = list_first_entry(&ent->head, struct mlx5_ib_mr,
list);
list_del(&mr->list);
ent->cur--;
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
if (ent->cur < ent->limit)
queue_work(cache->wq, &ent->work);
break;
}
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
queue_work(cache->wq, &ent->work);
@@ -395,12 +449,12 @@ static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
return;
}
ent = &cache->ent[c];
- spin_lock(&ent->lock);
+ spin_lock_irq(&ent->lock);
list_add_tail(&mr->list, &ent->head);
ent->cur++;
if (ent->cur > 2 * ent->limit)
shrink = 1;
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
if (shrink)
queue_work(cache->wq, &ent->work);
@@ -408,33 +462,28 @@ static void free_cached_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
static void clean_keys(struct mlx5_ib_dev *dev, int c)
{
- struct device *ddev = dev->ib_dev.dma_device;
struct mlx5_mr_cache *cache = &dev->cache;
struct mlx5_cache_ent *ent = &cache->ent[c];
struct mlx5_ib_mr *mr;
- int size;
int err;
+ cancel_delayed_work(&ent->dwork);
while (1) {
- spin_lock(&ent->lock);
+ spin_lock_irq(&ent->lock);
if (list_empty(&ent->head)) {
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
return;
}
mr = list_first_entry(&ent->head, struct mlx5_ib_mr, list);
list_del(&mr->list);
ent->cur--;
ent->size--;
- spin_unlock(&ent->lock);
+ spin_unlock_irq(&ent->lock);
err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
- if (err) {
+ if (err)
mlx5_ib_warn(dev, "failed destroy mkey\n");
- } else {
- size = ALIGN(sizeof(u64) * (1 << mr->order), 0x40);
- dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE);
- kfree(mr->pas);
+ else
kfree(mr);
- }
}
}
@@ -490,12 +539,18 @@ static void mlx5_mr_cache_debugfs_cleanup(struct mlx5_ib_dev *dev)
debugfs_remove_recursive(dev->cache.root);
}
+static void delay_time_func(unsigned long ctx)
+{
+ struct mlx5_ib_dev *dev = (struct mlx5_ib_dev *)ctx;
+
+ dev->fill_delay = 0;
+}
+
int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
{
struct mlx5_mr_cache *cache = &dev->cache;
struct mlx5_cache_ent *ent;
int limit;
- int size;
int err;
int i;
@@ -505,6 +560,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
return -ENOMEM;
}
+ setup_timer(&dev->delay_timer, delay_time_func, (unsigned long)dev);
for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) {
INIT_LIST_HEAD(&cache->ent[i].head);
spin_lock_init(&cache->ent[i].lock);
@@ -515,13 +571,11 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev)
ent->order = i + 2;
ent->dev = dev;
- if (dev->mdev.profile->mask & MLX5_PROF_MASK_MR_CACHE) {
- size = dev->mdev.profile->mr_cache[i].size;
+ if (dev->mdev.profile->mask & MLX5_PROF_MASK_MR_CACHE)
limit = dev->mdev.profile->mr_cache[i].limit;
- } else {
- size = DEF_CACHE_SIZE;
+ else
limit = 0;
- }
+
INIT_WORK(&ent->work, cache_work_func);
INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
ent->limit = limit;
@@ -540,13 +594,16 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev)
int i;
dev->cache.stopped = 1;
- destroy_workqueue(dev->cache.wq);
+ flush_workqueue(dev->cache.wq);
mlx5_mr_cache_debugfs_cleanup(dev);
for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++)
clean_keys(dev, i);
+ destroy_workqueue(dev->cache.wq);
+ del_timer_sync(&dev->delay_timer);
+
return 0;
}
@@ -575,7 +632,8 @@ struct ib_mr *mlx5_ib_get_dma_mr(struct ib_pd *pd, int acc)
seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
seg->start_addr = 0;
- err = mlx5_core_create_mkey(mdev, &mr->mmr, in, sizeof(*in));
+ err = mlx5_core_create_mkey(mdev, &mr->mmr, in, sizeof(*in), NULL, NULL,
+ NULL);
if (err)
goto err_in;
@@ -650,7 +708,7 @@ static void prep_umr_unreg_wqe(struct mlx5_ib_dev *dev,
void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context)
{
- struct mlx5_ib_mr *mr;
+ struct mlx5_ib_umr_context *context;
struct ib_wc wc;
int err;
@@ -663,9 +721,9 @@ void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context)
if (err == 0)
break;
- mr = (struct mlx5_ib_mr *)(unsigned long)wc.wr_id;
- mr->status = wc.status;
- complete(&mr->done);
+ context = (struct mlx5_ib_umr_context *) (unsigned long) wc.wr_id;
+ context->status = wc.status;
+ complete(&context->done);
}
ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
}
@@ -675,21 +733,24 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
int page_shift, int order, int access_flags)
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ struct device *ddev = dev->ib_dev.dma_device;
struct umr_common *umrc = &dev->umrc;
+ struct mlx5_ib_umr_context umr_context;
struct ib_send_wr wr, *bad;
struct mlx5_ib_mr *mr;
struct ib_sge sg;
- int err;
+ int size = sizeof(u64) * npages;
+ int err = 0;
int i;
- for (i = 0; i < 10; i++) {
+ for (i = 0; i < 1; i++) {
mr = alloc_cached_mr(dev, order);
if (mr)
break;
err = add_keys(dev, order2idx(dev, order), 1);
- if (err) {
- mlx5_ib_warn(dev, "add_keys failed\n");
+ if (err && err != -EAGAIN) {
+ mlx5_ib_warn(dev, "add_keys failed, err %d\n", err);
break;
}
}
@@ -697,38 +758,58 @@ static struct mlx5_ib_mr *reg_umr(struct ib_pd *pd, struct ib_umem *umem,
if (!mr)
return ERR_PTR(-EAGAIN);
- mlx5_ib_populate_pas(dev, umem, page_shift, mr_align(mr->pas, 0x40), 1);
+ mr->pas = kmalloc(size + MLX5_UMR_ALIGN - 1, GFP_KERNEL);
+ if (!mr->pas) {
+ err = -ENOMEM;
+ goto free_mr;
+ }
+
+ mlx5_ib_populate_pas(dev, umem, page_shift,
+ mr_align(mr->pas, MLX5_UMR_ALIGN), 1);
+
+ mr->dma = dma_map_single(ddev, mr_align(mr->pas, MLX5_UMR_ALIGN), size,
+ DMA_TO_DEVICE);
+ if (dma_mapping_error(ddev, mr->dma)) {
+ err = -ENOMEM;
+ goto free_pas;
+ }
memset(&wr, 0, sizeof(wr));
- wr.wr_id = (u64)(unsigned long)mr;
+ wr.wr_id = (u64)(unsigned long)&umr_context;
prep_umr_reg_wqe(pd, &wr, &sg, mr->dma, npages, mr->mmr.key, page_shift, virt_addr, len, access_flags);
- /* We serialize polls so one process does not kidnap another's
- * completion. This is not a problem since wr is completed in
- * around 1 usec
- */
+ mlx5_ib_init_umr_context(&umr_context);
down(&umrc->sem);
- init_completion(&mr->done);
err = ib_post_send(umrc->qp, &wr, &bad);
if (err) {
mlx5_ib_warn(dev, "post send failed, err %d\n", err);
- up(&umrc->sem);
- goto error;
+ goto unmap_dma;
+ } else {
+ wait_for_completion(&umr_context.done);
+ if (umr_context.status != IB_WC_SUCCESS) {
+ mlx5_ib_warn(dev, "reg umr failed\n");
+ err = -EFAULT;
+ }
}
- wait_for_completion(&mr->done);
+
+ mr->mmr.iova = virt_addr;
+ mr->mmr.size = len;
+ mr->mmr.pd = to_mpd(pd)->pdn;
+
+unmap_dma:
up(&umrc->sem);
+ dma_unmap_single(ddev, mr->dma, size, DMA_TO_DEVICE);
- if (mr->status != IB_WC_SUCCESS) {
- mlx5_ib_warn(dev, "reg umr failed\n");
- err = -EFAULT;
- goto error;
+free_pas:
+ kfree(mr->pas);
+
+free_mr:
+ if (err) {
+ free_cached_mr(dev, mr);
+ return ERR_PTR(err);
}
return mr;
-
-error:
- free_cached_mr(dev, mr);
- return ERR_PTR(err);
}
static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
@@ -763,8 +844,10 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, u64 virt_addr,
in->seg.xlt_oct_size = cpu_to_be32(get_octo_len(virt_addr, length, 1 << page_shift));
in->seg.log2_page_size = page_shift;
in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
- in->xlat_oct_act_size = cpu_to_be32(get_octo_len(virt_addr, length, 1 << page_shift));
- err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, inlen);
+ in->xlat_oct_act_size = cpu_to_be32(get_octo_len(virt_addr, length,
+ 1 << page_shift));
+ err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, inlen, NULL,
+ NULL, NULL);
if (err) {
mlx5_ib_warn(dev, "create mkey failed\n");
goto err_2;
@@ -855,24 +938,26 @@ error:
static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
{
struct umr_common *umrc = &dev->umrc;
+ struct mlx5_ib_umr_context umr_context;
struct ib_send_wr wr, *bad;
int err;
memset(&wr, 0, sizeof(wr));
- wr.wr_id = (u64)(unsigned long)mr;
+ wr.wr_id = (u64)(unsigned long)&umr_context;
prep_umr_unreg_wqe(dev, &wr, mr->mmr.key);
+ mlx5_ib_init_umr_context(&umr_context);
down(&umrc->sem);
- init_completion(&mr->done);
err = ib_post_send(umrc->qp, &wr, &bad);
if (err) {
up(&umrc->sem);
mlx5_ib_dbg(dev, "err %d\n", err);
goto error;
+ } else {
+ wait_for_completion(&umr_context.done);
+ up(&umrc->sem);
}
- wait_for_completion(&mr->done);
- up(&umrc->sem);
- if (mr->status != IB_WC_SUCCESS) {
+ if (umr_context.status != IB_WC_SUCCESS) {
mlx5_ib_warn(dev, "unreg umr failed\n");
err = -EFAULT;
goto error;
@@ -921,6 +1006,122 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
return 0;
}
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+ struct ib_mr_init_attr *mr_init_attr)
+{
+ struct mlx5_ib_dev *dev = to_mdev(pd->device);
+ struct mlx5_create_mkey_mbox_in *in;
+ struct mlx5_ib_mr *mr;
+ int access_mode, err;
+ int ndescs = roundup(mr_init_attr->max_reg_descriptors, 4);
+
+ mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+ if (!mr)
+ return ERR_PTR(-ENOMEM);
+
+ in = kzalloc(sizeof(*in), GFP_KERNEL);
+ if (!in) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ in->seg.status = 1 << 6; /* free */
+ in->seg.xlt_oct_size = cpu_to_be32(ndescs);
+ in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+ in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
+ access_mode = MLX5_ACCESS_MODE_MTT;
+
+ if (mr_init_attr->flags & IB_MR_SIGNATURE_EN) {
+ u32 psv_index[2];
+
+ in->seg.flags_pd = cpu_to_be32(be32_to_cpu(in->seg.flags_pd) |
+ MLX5_MKEY_BSF_EN);
+ in->seg.bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+ mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL);
+ if (!mr->sig) {
+ err = -ENOMEM;
+ goto err_free_in;
+ }
+
+ /* create mem & wire PSVs */
+ err = mlx5_core_create_psv(&dev->mdev, to_mpd(pd)->pdn,
+ 2, psv_index);
+ if (err)
+ goto err_free_sig;
+
+ access_mode = MLX5_ACCESS_MODE_KLM;
+ mr->sig->psv_memory.psv_idx = psv_index[0];
+ mr->sig->psv_wire.psv_idx = psv_index[1];
+
+ mr->sig->sig_status_checked = true;
+ mr->sig->sig_err_exists = false;
+ /* Next UMR, Arm SIGERR */
+ ++mr->sig->sigerr_count;
+ }
+
+ in->seg.flags = MLX5_PERM_UMR_EN | access_mode;
+ err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in),
+ NULL, NULL, NULL);
+ if (err)
+ goto err_destroy_psv;
+
+ mr->ibmr.lkey = mr->mmr.key;
+ mr->ibmr.rkey = mr->mmr.key;
+ mr->umem = NULL;
+ kfree(in);
+
+ return &mr->ibmr;
+
+err_destroy_psv:
+ if (mr->sig) {
+ if (mlx5_core_destroy_psv(&dev->mdev,
+ mr->sig->psv_memory.psv_idx))
+ mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+ mr->sig->psv_memory.psv_idx);
+ if (mlx5_core_destroy_psv(&dev->mdev,
+ mr->sig->psv_wire.psv_idx))
+ mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+ mr->sig->psv_wire.psv_idx);
+ }
+err_free_sig:
+ kfree(mr->sig);
+err_free_in:
+ kfree(in);
+err_free:
+ kfree(mr);
+ return ERR_PTR(err);
+}
+
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr)
+{
+ struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+ struct mlx5_ib_mr *mr = to_mmr(ibmr);
+ int err;
+
+ if (mr->sig) {
+ if (mlx5_core_destroy_psv(&dev->mdev,
+ mr->sig->psv_memory.psv_idx))
+ mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+ mr->sig->psv_memory.psv_idx);
+ if (mlx5_core_destroy_psv(&dev->mdev,
+ mr->sig->psv_wire.psv_idx))
+ mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+ mr->sig->psv_wire.psv_idx);
+ kfree(mr->sig);
+ }
+
+ err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
+ if (err) {
+ mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
+ mr->mmr.key, err);
+ return err;
+ }
+
+ kfree(mr);
+
+ return err;
+}
+
struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
int max_page_list_len)
{
@@ -948,7 +1149,8 @@ struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
* TBD not needed - issue 197292 */
in->seg.log2_page_size = PAGE_SHIFT;
- err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in));
+ err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in), NULL,
+ NULL, NULL);
kfree(in);
if (err)
goto err_free;
@@ -1005,3 +1207,44 @@ void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
kfree(mfrpl->ibfrpl.page_list);
kfree(mfrpl);
}
+
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+ struct ib_mr_status *mr_status)
+{
+ struct mlx5_ib_mr *mmr = to_mmr(ibmr);
+ int ret = 0;
+
+ if (check_mask & ~IB_MR_CHECK_SIG_STATUS) {
+ pr_err("Invalid status check mask\n");
+ ret = -EINVAL;
+ goto done;
+ }
+
+ mr_status->fail_status = 0;
+ if (check_mask & IB_MR_CHECK_SIG_STATUS) {
+ if (!mmr->sig) {
+ ret = -EINVAL;
+ pr_err("signature status check requested on a non-signature enabled MR\n");
+ goto done;
+ }
+
+ mmr->sig->sig_status_checked = true;
+ if (!mmr->sig->sig_err_exists)
+ goto done;
+
+ if (ibmr->lkey == mmr->sig->err_item.key)
+ memcpy(&mr_status->sig_err, &mmr->sig->err_item,
+ sizeof(mr_status->sig_err));
+ else {
+ mr_status->sig_err.err_type = IB_SIG_BAD_GUARD;
+ mr_status->sig_err.sig_err_offset = 0;
+ mr_status->sig_err.key = mmr->sig->err_item.key;
+ }
+
+ mmr->sig->sig_err_exists = false;
+ mr_status->fail_status |= IB_MR_CHECK_SIG_STATUS;
+ }
+
+done:
+ return ret;
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 045f8cdbd30..bbbcf389272 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -203,7 +203,7 @@ static int sq_overhead(enum ib_qp_type qp_type)
switch (qp_type) {
case IB_QPT_XRC_INI:
- size = sizeof(struct mlx5_wqe_xrc_seg);
+ size += sizeof(struct mlx5_wqe_xrc_seg);
/* fall through */
case IB_QPT_RC:
size += sizeof(struct mlx5_wqe_ctrl_seg) +
@@ -211,20 +211,25 @@ static int sq_overhead(enum ib_qp_type qp_type)
sizeof(struct mlx5_wqe_raddr_seg);
break;
+ case IB_QPT_XRC_TGT:
+ return 0;
+
case IB_QPT_UC:
- size = sizeof(struct mlx5_wqe_ctrl_seg) +
- sizeof(struct mlx5_wqe_raddr_seg);
+ 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);
break;
case IB_QPT_UD:
case IB_QPT_SMI:
case IB_QPT_GSI:
- size = sizeof(struct mlx5_wqe_ctrl_seg) +
+ size += sizeof(struct mlx5_wqe_ctrl_seg) +
sizeof(struct mlx5_wqe_datagram_seg);
break;
case MLX5_IB_QPT_REG_UMR:
- size = sizeof(struct mlx5_wqe_ctrl_seg) +
+ size += sizeof(struct mlx5_wqe_ctrl_seg) +
sizeof(struct mlx5_wqe_umr_ctrl_seg) +
sizeof(struct mlx5_mkey_seg);
break;
@@ -251,8 +256,11 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
}
size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
- return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
+ if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN &&
+ ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE)
+ return MLX5_SIG_WQE_SIZE;
+ else
+ return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
}
static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
@@ -270,7 +278,8 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
return wqe_size;
if (wqe_size > dev->mdev.caps.max_sq_desc_sz) {
- mlx5_ib_dbg(dev, "\n");
+ mlx5_ib_dbg(dev, "wqe_size(%d) > max_sq_desc_sz(%d)\n",
+ wqe_size, dev->mdev.caps.max_sq_desc_sz);
return -EINVAL;
}
@@ -278,11 +287,20 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
sizeof(struct mlx5_wqe_inline_seg);
attr->cap.max_inline_data = qp->max_inline_data;
+ if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
+ qp->signature_en = true;
+
wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
+ if (qp->sq.wqe_cnt > dev->mdev.caps.max_wqes) {
+ mlx5_ib_dbg(dev, "wqe count(%d) exceeds limits(%d)\n",
+ qp->sq.wqe_cnt, dev->mdev.caps.max_wqes);
+ return -ENOMEM;
+ }
qp->sq.wqe_shift = ilog2(MLX5_SEND_WQE_BB);
qp->sq.max_gs = attr->cap.max_send_sge;
- qp->sq.max_post = 1 << ilog2(wq_size / wqe_size);
+ qp->sq.max_post = wq_size / wqe_size;
+ attr->cap.max_send_wr = qp->sq.max_post;
return wq_size;
}
@@ -330,14 +348,57 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
return 1;
}
+static int first_med_uuar(void)
+{
+ return 1;
+}
+
+static int next_uuar(int n)
+{
+ n++;
+
+ while (((n % 4) & 2))
+ n++;
+
+ return n;
+}
+
+static int num_med_uuar(struct mlx5_uuar_info *uuari)
+{
+ int n;
+
+ n = uuari->num_uars * MLX5_NON_FP_BF_REGS_PER_PAGE -
+ uuari->num_low_latency_uuars - 1;
+
+ return n >= 0 ? n : 0;
+}
+
+static int max_uuari(struct mlx5_uuar_info *uuari)
+{
+ return uuari->num_uars * 4;
+}
+
+static int first_hi_uuar(struct mlx5_uuar_info *uuari)
+{
+ int med;
+ int i;
+ int t;
+
+ med = num_med_uuar(uuari);
+ for (t = 0, i = first_med_uuar();; i = next_uuar(i)) {
+ t++;
+ if (t == med)
+ return next_uuar(i);
+ }
+
+ return 0;
+}
+
static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
{
- int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
- int start_uuar;
int i;
- start_uuar = nuuars - uuari->num_low_latency_uuars;
- for (i = start_uuar; i < nuuars; i++) {
+ for (i = first_hi_uuar(uuari); i < max_uuari(uuari); i = next_uuar(i)) {
if (!test_bit(i, uuari->bitmap)) {
set_bit(i, uuari->bitmap);
uuari->count[i]++;
@@ -350,19 +411,10 @@ static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
static int alloc_med_class_uuar(struct mlx5_uuar_info *uuari)
{
- int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
- int minidx = 1;
- int uuarn;
- int end;
+ int minidx = first_med_uuar();
int i;
- end = nuuars - uuari->num_low_latency_uuars;
-
- for (i = 1; i < end; i++) {
- uuarn = i & 3;
- if (uuarn == 2 || uuarn == 3)
- continue;
-
+ for (i = first_med_uuar(); i < first_hi_uuar(uuari); i = next_uuar(i)) {
if (uuari->count[i] < uuari->count[minidx])
minidx = i;
}
@@ -384,11 +436,17 @@ static int alloc_uuar(struct mlx5_uuar_info *uuari,
break;
case MLX5_IB_LATENCY_CLASS_MEDIUM:
- uuarn = alloc_med_class_uuar(uuari);
+ if (uuari->ver < 2)
+ uuarn = -ENOMEM;
+ else
+ uuarn = alloc_med_class_uuar(uuari);
break;
case MLX5_IB_LATENCY_CLASS_HIGH:
- uuarn = alloc_high_class_uuar(uuari);
+ if (uuari->ver < 2)
+ uuarn = -ENOMEM;
+ else
+ uuarn = alloc_high_class_uuar(uuari);
break;
case MLX5_IB_LATENCY_CLASS_FAST_PATH:
@@ -479,12 +537,12 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
{
struct mlx5_ib_ucontext *context;
struct mlx5_ib_create_qp ucmd;
- int page_shift;
+ int page_shift = 0;
int uar_index;
int npages;
- u32 offset;
+ u32 offset = 0;
int uuarn;
- int ncont;
+ int ncont = 0;
int err;
err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
@@ -500,38 +558,53 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
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 high latency\n");
- uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+ mlx5_ib_dbg(dev, "reverting to medium latency\n");
+ uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
if (uuarn < 0) {
- mlx5_ib_dbg(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;
+ }
}
}
uar_index = uuarn_to_uar_index(&context->uuari, uuarn);
mlx5_ib_dbg(dev, "uuarn 0x%x, uar_index 0x%x\n", uuarn, uar_index);
+ qp->rq.offset = 0;
+ 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);
if (err)
goto err_uuar;
- 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);
- 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);
+ goto err_uuar;
+ }
+ } else {
+ qp->umem = NULL;
}
- 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;
+ 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);
}
- 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);
*inlen = sizeof(**in) + sizeof(*(*in)->pas) * ncont;
*in = mlx5_vzalloc(*inlen);
@@ -539,9 +612,10 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
err = -ENOMEM;
goto err_umem;
}
- mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
+ if (qp->umem)
+ mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
(*in)->ctx.log_pg_sz_remote_qpn =
- cpu_to_be32((page_shift - PAGE_SHIFT) << 24);
+ cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
(*in)->ctx.params2 = cpu_to_be32(offset << 6);
(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
@@ -570,7 +644,8 @@ err_free:
mlx5_vfree(*in);
err_umem:
- ib_umem_release(qp->umem);
+ if (qp->umem)
+ ib_umem_release(qp->umem);
err_uuar:
free_uuar(&context->uuari, uuarn);
@@ -583,7 +658,8 @@ static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp)
context = to_mucontext(pd->uobject->context);
mlx5_ib_db_unmap_user(context, &qp->db);
- ib_umem_release(qp->umem);
+ if (qp->umem)
+ ib_umem_release(qp->umem);
free_uuar(&context->uuari, qp->uuarn);
}
@@ -599,8 +675,8 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
int err;
uuari = &dev->mdev.priv.uuari;
- if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK)
- qp->flags |= MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK;
+ if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN | IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK))
+ return -EINVAL;
if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
lc = MLX5_IB_LATENCY_CLASS_FAST_PATH;
@@ -638,7 +714,8 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
goto err_buf;
}
(*in)->ctx.qp_counter_set_usr_page = cpu_to_be32(uar_index);
- (*in)->ctx.log_pg_sz_remote_qpn = cpu_to_be32((qp->buf.page_shift - PAGE_SHIFT) << 24);
+ (*in)->ctx.log_pg_sz_remote_qpn =
+ cpu_to_be32((qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
/* Set "fast registration enabled" for all kernel QPs */
(*in)->ctx.params1 |= cpu_to_be32(1 << 11);
(*in)->ctx.sq_crq_size |= cpu_to_be16(1 << 4);
@@ -734,6 +811,15 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
spin_lock_init(&qp->sq.lock);
spin_lock_init(&qp->rq.lock);
+ if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) {
+ if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_BLOCK_MCAST)) {
+ mlx5_ib_dbg(dev, "block multicast loopback isn't supported\n");
+ return -EINVAL;
+ } else {
+ qp->flags |= MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK;
+ }
+ }
+
if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
qp->sq_signal_bits = MLX5_WQE_CTRL_CQ_UPDATE;
@@ -805,6 +891,9 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
if (qp->wq_sig)
in->ctx.flags_pd |= cpu_to_be32(MLX5_QP_ENABLE_SIG);
+ if (qp->flags & MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK)
+ in->ctx.flags_pd |= cpu_to_be32(MLX5_QP_BLOCK_MCAST);
+
if (qp->scat_cqe && is_connected(init_attr->qp_type)) {
int rcqe_sz;
int scqe_sz;
@@ -1280,6 +1369,11 @@ static enum mlx5_qp_optpar opt_mask[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE][MLX5_Q
MLX5_QP_OPTPAR_Q_KEY,
[MLX5_QP_ST_MLX] = MLX5_QP_OPTPAR_PKEY_INDEX |
MLX5_QP_OPTPAR_Q_KEY,
+ [MLX5_QP_ST_XRC] = MLX5_QP_OPTPAR_ALT_ADDR_PATH |
+ MLX5_QP_OPTPAR_RRE |
+ MLX5_QP_OPTPAR_RAE |
+ MLX5_QP_OPTPAR_RWE |
+ MLX5_QP_OPTPAR_PKEY_INDEX,
},
},
[MLX5_QP_STATE_RTR] = {
@@ -1302,9 +1396,11 @@ static enum mlx5_qp_optpar opt_mask[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE][MLX5_Q
MLX5_QP_OPTPAR_RAE |
MLX5_QP_OPTPAR_RWE |
MLX5_QP_OPTPAR_RNR_TIMEOUT |
- MLX5_QP_OPTPAR_PM_STATE,
+ MLX5_QP_OPTPAR_PM_STATE |
+ MLX5_QP_OPTPAR_ALT_ADDR_PATH,
[MLX5_QP_ST_UC] = MLX5_QP_OPTPAR_RWE |
- MLX5_QP_OPTPAR_PM_STATE,
+ MLX5_QP_OPTPAR_PM_STATE |
+ MLX5_QP_OPTPAR_ALT_ADDR_PATH,
[MLX5_QP_ST_UD] = MLX5_QP_OPTPAR_Q_KEY |
MLX5_QP_OPTPAR_SRQN |
MLX5_QP_OPTPAR_CQN_RCV,
@@ -1314,6 +1410,11 @@ static enum mlx5_qp_optpar opt_mask[MLX5_QP_NUM_STATE][MLX5_QP_NUM_STATE][MLX5_Q
[MLX5_QP_STATE_RTS] = {
[MLX5_QP_ST_UD] = MLX5_QP_OPTPAR_Q_KEY,
[MLX5_QP_ST_MLX] = MLX5_QP_OPTPAR_Q_KEY,
+ [MLX5_QP_ST_UC] = MLX5_QP_OPTPAR_RWE,
+ [MLX5_QP_ST_RC] = MLX5_QP_OPTPAR_RNR_TIMEOUT |
+ MLX5_QP_OPTPAR_RWE |
+ MLX5_QP_OPTPAR_RAE |
+ MLX5_QP_OPTPAR_RRE,
},
},
};
@@ -1530,7 +1631,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
mlx5_cur = to_mlx5_state(cur_state);
mlx5_new = to_mlx5_state(new_state);
mlx5_st = to_mlx5_st(ibqp->qp_type);
- if (mlx5_cur < 0 || mlx5_new < 0 || mlx5_st < 0)
+ if (mlx5_st < 0)
goto out;
optpar = ib_mask_to_mlx5_opt(attr_mask);
@@ -1593,7 +1694,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
- !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+ !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+ IB_LINK_LAYER_UNSPECIFIED))
goto out;
if ((attr_mask & IB_QP_PORT) &&
@@ -1651,29 +1753,6 @@ static __always_inline void set_raddr_seg(struct mlx5_wqe_raddr_seg *rseg,
rseg->reserved = 0;
}
-static void set_atomic_seg(struct mlx5_wqe_atomic_seg *aseg, struct ib_send_wr *wr)
-{
- if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP) {
- aseg->swap_add = cpu_to_be64(wr->wr.atomic.swap);
- aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add);
- } else if (wr->opcode == IB_WR_MASKED_ATOMIC_FETCH_AND_ADD) {
- aseg->swap_add = cpu_to_be64(wr->wr.atomic.compare_add);
- aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add_mask);
- } else {
- aseg->swap_add = cpu_to_be64(wr->wr.atomic.compare_add);
- aseg->compare = 0;
- }
-}
-
-static void set_masked_atomic_seg(struct mlx5_wqe_masked_atomic_seg *aseg,
- struct ib_send_wr *wr)
-{
- aseg->swap_add = cpu_to_be64(wr->wr.atomic.swap);
- aseg->swap_add_mask = cpu_to_be64(wr->wr.atomic.swap_mask);
- aseg->compare = cpu_to_be64(wr->wr.atomic.compare_add);
- aseg->compare_mask = cpu_to_be64(wr->wr.atomic.compare_add_mask);
-}
-
static void set_datagram_seg(struct mlx5_wqe_datagram_seg *dseg,
struct ib_send_wr *wr)
{
@@ -1714,6 +1793,27 @@ static __be64 frwr_mkey_mask(void)
return cpu_to_be64(result);
}
+static __be64 sig_mkey_mask(void)
+{
+ u64 result;
+
+ result = MLX5_MKEY_MASK_LEN |
+ MLX5_MKEY_MASK_PAGE_SIZE |
+ MLX5_MKEY_MASK_START_ADDR |
+ MLX5_MKEY_MASK_EN_SIGERR |
+ MLX5_MKEY_MASK_EN_RINVAL |
+ MLX5_MKEY_MASK_KEY |
+ MLX5_MKEY_MASK_LR |
+ MLX5_MKEY_MASK_LW |
+ MLX5_MKEY_MASK_RR |
+ MLX5_MKEY_MASK_RW |
+ MLX5_MKEY_MASK_SMALL_FENCE |
+ MLX5_MKEY_MASK_FREE |
+ MLX5_MKEY_MASK_BSF_EN;
+
+ return cpu_to_be64(result);
+}
+
static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
struct ib_send_wr *wr, int li)
{
@@ -1747,6 +1847,7 @@ static void set_reg_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
MLX5_MKEY_MASK_PD |
MLX5_MKEY_MASK_LR |
MLX5_MKEY_MASK_LW |
+ MLX5_MKEY_MASK_KEY |
MLX5_MKEY_MASK_RR |
MLX5_MKEY_MASK_RW |
MLX5_MKEY_MASK_A |
@@ -1768,7 +1869,7 @@ static u8 get_umr_flags(int acc)
(acc & IB_ACCESS_REMOTE_WRITE ? MLX5_PERM_REMOTE_WRITE : 0) |
(acc & IB_ACCESS_REMOTE_READ ? MLX5_PERM_REMOTE_READ : 0) |
(acc & IB_ACCESS_LOCAL_WRITE ? MLX5_PERM_LOCAL_WRITE : 0) |
- MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN | MLX5_ACCESS_MODE_MTT;
+ MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN;
}
static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
@@ -1780,7 +1881,8 @@ static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
return;
}
- seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags);
+ seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags) |
+ MLX5_ACCESS_MODE_MTT;
*writ = seg->flags & (MLX5_PERM_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE);
seg->qpn_mkey7_0 = cpu_to_be32((wr->wr.fast_reg.rkey & 0xff) | 0xffffff00);
seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
@@ -1803,7 +1905,8 @@ static void set_reg_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *w
seg->start_addr = cpu_to_be64(wr->wr.fast_reg.iova_start);
seg->len = cpu_to_be64(wr->wr.fast_reg.length);
seg->log2_page_size = wr->wr.fast_reg.page_shift;
- seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+ seg->qpn_mkey7_0 = cpu_to_be32(0xffffff00 |
+ mlx5_mkey_variant(wr->wr.fast_reg.rkey));
}
static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
@@ -1895,6 +1998,342 @@ static int set_data_inl_seg(struct mlx5_ib_qp *qp, struct ib_send_wr *wr,
return 0;
}
+static u16 prot_field_size(enum ib_signature_type type)
+{
+ switch (type) {
+ case IB_SIG_TYPE_T10_DIF:
+ return MLX5_DIF_SIZE;
+ default:
+ return 0;
+ }
+}
+
+static u8 bs_selector(int block_size)
+{
+ switch (block_size) {
+ case 512: return 0x1;
+ case 520: return 0x2;
+ case 4096: return 0x3;
+ case 4160: return 0x4;
+ case 1073741824: return 0x5;
+ default: return 0;
+ }
+}
+
+static int format_selector(struct ib_sig_attrs *attr,
+ struct ib_sig_domain *domain,
+ int *selector)
+{
+
+#define FORMAT_DIF_NONE 0
+#define FORMAT_DIF_CRC_INC 8
+#define FORMAT_DIF_CRC_NO_INC 12
+#define FORMAT_DIF_CSUM_INC 13
+#define FORMAT_DIF_CSUM_NO_INC 14
+
+ switch (domain->sig.dif.type) {
+ case IB_T10DIF_NONE:
+ /* No DIF */
+ *selector = FORMAT_DIF_NONE;
+ break;
+ case IB_T10DIF_TYPE1: /* Fall through */
+ case IB_T10DIF_TYPE2:
+ switch (domain->sig.dif.bg_type) {
+ case IB_T10DIF_CRC:
+ *selector = FORMAT_DIF_CRC_INC;
+ break;
+ case IB_T10DIF_CSUM:
+ *selector = FORMAT_DIF_CSUM_INC;
+ break;
+ default:
+ return 1;
+ }
+ break;
+ case IB_T10DIF_TYPE3:
+ switch (domain->sig.dif.bg_type) {
+ case IB_T10DIF_CRC:
+ *selector = domain->sig.dif.type3_inc_reftag ?
+ FORMAT_DIF_CRC_INC :
+ FORMAT_DIF_CRC_NO_INC;
+ break;
+ case IB_T10DIF_CSUM:
+ *selector = domain->sig.dif.type3_inc_reftag ?
+ FORMAT_DIF_CSUM_INC :
+ FORMAT_DIF_CSUM_NO_INC;
+ break;
+ default:
+ return 1;
+ }
+ break;
+ default:
+ return 1;
+ }
+
+ return 0;
+}
+
+static int mlx5_set_bsf(struct ib_mr *sig_mr,
+ struct ib_sig_attrs *sig_attrs,
+ struct mlx5_bsf *bsf, u32 data_size)
+{
+ struct mlx5_core_sig_ctx *msig = to_mmr(sig_mr)->sig;
+ struct mlx5_bsf_basic *basic = &bsf->basic;
+ struct ib_sig_domain *mem = &sig_attrs->mem;
+ struct ib_sig_domain *wire = &sig_attrs->wire;
+ int ret, selector;
+
+ memset(bsf, 0, sizeof(*bsf));
+ switch (sig_attrs->mem.sig_type) {
+ case IB_SIG_TYPE_T10_DIF:
+ if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
+ return -EINVAL;
+
+ /* Input domain check byte mask */
+ basic->check_byte_mask = sig_attrs->check_mask;
+ if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
+ mem->sig.dif.type == wire->sig.dif.type) {
+ /* Same block structure */
+ basic->bsf_size_sbs = 1 << 4;
+ if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
+ basic->wire.copy_byte_mask |= 0xc0;
+ if (mem->sig.dif.app_tag == wire->sig.dif.app_tag)
+ basic->wire.copy_byte_mask |= 0x30;
+ if (mem->sig.dif.ref_tag == wire->sig.dif.ref_tag)
+ basic->wire.copy_byte_mask |= 0x0f;
+ } else
+ basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
+
+ basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
+ basic->raw_data_size = cpu_to_be32(data_size);
+
+ ret = format_selector(sig_attrs, mem, &selector);
+ if (ret)
+ return -EINVAL;
+ basic->m_bfs_psv = cpu_to_be32(selector << 24 |
+ msig->psv_memory.psv_idx);
+
+ ret = format_selector(sig_attrs, wire, &selector);
+ if (ret)
+ return -EINVAL;
+ basic->w_bfs_psv = cpu_to_be32(selector << 24 |
+ msig->psv_wire.psv_idx);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+ void **seg, int *size)
+{
+ struct ib_sig_attrs *sig_attrs = wr->wr.sig_handover.sig_attrs;
+ struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+ struct mlx5_bsf *bsf;
+ u32 data_len = wr->sg_list->length;
+ u32 data_key = wr->sg_list->lkey;
+ u64 data_va = wr->sg_list->addr;
+ int ret;
+ int wqe_size;
+
+ if (!wr->wr.sig_handover.prot ||
+ (data_key == wr->wr.sig_handover.prot->lkey &&
+ data_va == wr->wr.sig_handover.prot->addr &&
+ data_len == wr->wr.sig_handover.prot->length)) {
+ /**
+ * Source domain doesn't contain signature information
+ * or data and protection are interleaved in memory.
+ * So need construct:
+ * ------------------
+ * | data_klm |
+ * ------------------
+ * | BSF |
+ * ------------------
+ **/
+ struct mlx5_klm *data_klm = *seg;
+
+ data_klm->bcount = cpu_to_be32(data_len);
+ data_klm->key = cpu_to_be32(data_key);
+ data_klm->va = cpu_to_be64(data_va);
+ wqe_size = ALIGN(sizeof(*data_klm), 64);
+ } else {
+ /**
+ * Source domain contains signature information
+ * So need construct a strided block format:
+ * ---------------------------
+ * | stride_block_ctrl |
+ * ---------------------------
+ * | data_klm |
+ * ---------------------------
+ * | prot_klm |
+ * ---------------------------
+ * | BSF |
+ * ---------------------------
+ **/
+ struct mlx5_stride_block_ctrl_seg *sblock_ctrl;
+ struct mlx5_stride_block_entry *data_sentry;
+ struct mlx5_stride_block_entry *prot_sentry;
+ u32 prot_key = wr->wr.sig_handover.prot->lkey;
+ u64 prot_va = wr->wr.sig_handover.prot->addr;
+ u16 block_size = sig_attrs->mem.sig.dif.pi_interval;
+ int prot_size;
+
+ sblock_ctrl = *seg;
+ data_sentry = (void *)sblock_ctrl + sizeof(*sblock_ctrl);
+ prot_sentry = (void *)data_sentry + sizeof(*data_sentry);
+
+ prot_size = prot_field_size(sig_attrs->mem.sig_type);
+ if (!prot_size) {
+ pr_err("Bad block size given: %u\n", block_size);
+ return -EINVAL;
+ }
+ sblock_ctrl->bcount_per_cycle = cpu_to_be32(block_size +
+ prot_size);
+ sblock_ctrl->op = cpu_to_be32(MLX5_STRIDE_BLOCK_OP);
+ sblock_ctrl->repeat_count = cpu_to_be32(data_len / block_size);
+ sblock_ctrl->num_entries = cpu_to_be16(2);
+
+ data_sentry->bcount = cpu_to_be16(block_size);
+ data_sentry->key = cpu_to_be32(data_key);
+ data_sentry->va = cpu_to_be64(data_va);
+ data_sentry->stride = cpu_to_be16(block_size);
+
+ prot_sentry->bcount = cpu_to_be16(prot_size);
+ prot_sentry->key = cpu_to_be32(prot_key);
+ prot_sentry->va = cpu_to_be64(prot_va);
+ prot_sentry->stride = cpu_to_be16(prot_size);
+
+ wqe_size = ALIGN(sizeof(*sblock_ctrl) + sizeof(*data_sentry) +
+ sizeof(*prot_sentry), 64);
+ }
+
+ *seg += wqe_size;
+ *size += wqe_size / 16;
+ if (unlikely((*seg == qp->sq.qend)))
+ *seg = mlx5_get_send_wqe(qp, 0);
+
+ bsf = *seg;
+ ret = mlx5_set_bsf(sig_mr, sig_attrs, bsf, data_len);
+ if (ret)
+ return -EINVAL;
+
+ *seg += sizeof(*bsf);
+ *size += sizeof(*bsf) / 16;
+ if (unlikely((*seg == qp->sq.qend)))
+ *seg = mlx5_get_send_wqe(qp, 0);
+
+ return 0;
+}
+
+static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
+ struct ib_send_wr *wr, u32 nelements,
+ u32 length, u32 pdn)
+{
+ struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+ u32 sig_key = sig_mr->rkey;
+ u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;
+
+ memset(seg, 0, sizeof(*seg));
+
+ seg->flags = get_umr_flags(wr->wr.sig_handover.access_flags) |
+ MLX5_ACCESS_MODE_KLM;
+ seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
+ seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
+ MLX5_MKEY_BSF_EN | pdn);
+ seg->len = cpu_to_be64(length);
+ seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
+ seg->bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+}
+
+static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
+ struct ib_send_wr *wr, u32 nelements)
+{
+ memset(umr, 0, sizeof(*umr));
+
+ umr->flags = MLX5_FLAGS_INLINE | MLX5_FLAGS_CHECK_FREE;
+ umr->klm_octowords = get_klm_octo(nelements);
+ umr->bsf_octowords = cpu_to_be16(MLX5_MKEY_BSF_OCTO_SIZE);
+ umr->mkey_mask = sig_mkey_mask();
+}
+
+
+static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+ void **seg, int *size)
+{
+ struct mlx5_ib_mr *sig_mr = to_mmr(wr->wr.sig_handover.sig_mr);
+ u32 pdn = get_pd(qp)->pdn;
+ u32 klm_oct_size;
+ int region_len, ret;
+
+ if (unlikely(wr->num_sge != 1) ||
+ unlikely(wr->wr.sig_handover.access_flags &
+ IB_ACCESS_REMOTE_ATOMIC) ||
+ unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) ||
+ unlikely(!sig_mr->sig->sig_status_checked))
+ return -EINVAL;
+
+ /* length of the protected region, data + protection */
+ region_len = wr->sg_list->length;
+ if (wr->wr.sig_handover.prot &&
+ (wr->wr.sig_handover.prot->lkey != wr->sg_list->lkey ||
+ wr->wr.sig_handover.prot->addr != wr->sg_list->addr ||
+ wr->wr.sig_handover.prot->length != wr->sg_list->length))
+ region_len += wr->wr.sig_handover.prot->length;
+
+ /**
+ * KLM octoword size - if protection was provided
+ * then we use strided block format (3 octowords),
+ * else we use single KLM (1 octoword)
+ **/
+ klm_oct_size = wr->wr.sig_handover.prot ? 3 : 1;
+
+ set_sig_umr_segment(*seg, wr, klm_oct_size);
+ *seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
+ *size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
+ if (unlikely((*seg == qp->sq.qend)))
+ *seg = mlx5_get_send_wqe(qp, 0);
+
+ set_sig_mkey_segment(*seg, wr, klm_oct_size, region_len, pdn);
+ *seg += sizeof(struct mlx5_mkey_seg);
+ *size += sizeof(struct mlx5_mkey_seg) / 16;
+ if (unlikely((*seg == qp->sq.qend)))
+ *seg = mlx5_get_send_wqe(qp, 0);
+
+ ret = set_sig_data_segment(wr, qp, seg, size);
+ if (ret)
+ return ret;
+
+ sig_mr->sig->sig_status_checked = false;
+ return 0;
+}
+
+static int set_psv_wr(struct ib_sig_domain *domain,
+ u32 psv_idx, void **seg, int *size)
+{
+ struct mlx5_seg_set_psv *psv_seg = *seg;
+
+ memset(psv_seg, 0, sizeof(*psv_seg));
+ psv_seg->psv_num = cpu_to_be32(psv_idx);
+ switch (domain->sig_type) {
+ case IB_SIG_TYPE_T10_DIF:
+ psv_seg->transient_sig = cpu_to_be32(domain->sig.dif.bg << 16 |
+ domain->sig.dif.app_tag);
+ psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
+
+ *seg += sizeof(*psv_seg);
+ *size += sizeof(*psv_seg) / 16;
+ break;
+
+ default:
+ pr_err("Bad signature type given.\n");
+ return 1;
+ }
+
+ return 0;
+}
+
static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
struct mlx5_core_dev *mdev, struct mlx5_ib_pd *pd, struct mlx5_ib_qp *qp)
{
@@ -1916,6 +2355,10 @@ static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
if (unlikely((*seg == qp->sq.qend)))
*seg = mlx5_get_send_wqe(qp, 0);
if (!li) {
+ if (unlikely(wr->wr.fast_reg.page_list_len >
+ wr->wr.fast_reg.page_list->max_page_list_len))
+ return -ENOMEM;
+
set_frwr_pages(*seg, wr, mdev, pd, writ);
*seg += sizeof(struct mlx5_wqe_data_seg);
*size += (sizeof(struct mlx5_wqe_data_seg) / 16);
@@ -1978,6 +2421,59 @@ 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,
struct ib_send_wr **bad_wr)
{
@@ -1985,13 +2481,13 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
struct mlx5_core_dev *mdev = &dev->mdev;
struct mlx5_ib_qp *qp = to_mqp(ibqp);
+ struct mlx5_ib_mr *mr;
struct mlx5_wqe_data_seg *dpseg;
struct mlx5_wqe_xrc_seg *xrc;
struct mlx5_bf *bf = qp->bf;
int uninitialized_var(size);
void *qend = qp->sq.qend;
unsigned long flags;
- u32 mlx5_opcode;
unsigned idx;
int err = 0;
int inl = 0;
@@ -2000,7 +2496,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
int nreq;
int i;
u8 next_fence = 0;
- u8 opmod = 0;
u8 fence;
spin_lock_irqsave(&qp->sq.lock, flags);
@@ -2013,36 +2508,23 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
goto out;
}
- if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
+ fence = qp->fm_cache;
+ num_sge = wr->num_sge;
+ if (unlikely(num_sge > qp->sq.max_gs)) {
mlx5_ib_warn(dev, "\n");
err = -ENOMEM;
*bad_wr = wr;
goto out;
}
- fence = qp->fm_cache;
- num_sge = wr->num_sge;
- if (unlikely(num_sge > qp->sq.max_gs)) {
+ err = begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, nreq);
+ if (err) {
mlx5_ib_warn(dev, "\n");
err = -ENOMEM;
*bad_wr = wr;
goto out;
}
- 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;
-
switch (ibqp->qp_type) {
case IB_QPT_XRC_INI:
xrc = seg;
@@ -2063,28 +2545,11 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
case IB_WR_ATOMIC_CMP_AND_SWP:
case IB_WR_ATOMIC_FETCH_AND_ADD:
- set_raddr_seg(seg, wr->wr.atomic.remote_addr,
- wr->wr.atomic.rkey);
- seg += sizeof(struct mlx5_wqe_raddr_seg);
-
- set_atomic_seg(seg, wr);
- seg += sizeof(struct mlx5_wqe_atomic_seg);
-
- size += (sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_atomic_seg)) / 16;
- break;
-
case IB_WR_MASKED_ATOMIC_CMP_AND_SWP:
- set_raddr_seg(seg, wr->wr.atomic.remote_addr,
- wr->wr.atomic.rkey);
- seg += sizeof(struct mlx5_wqe_raddr_seg);
-
- set_masked_atomic_seg(seg, wr);
- seg += sizeof(struct mlx5_wqe_masked_atomic_seg);
-
- size += (sizeof(struct mlx5_wqe_raddr_seg) +
- sizeof(struct mlx5_wqe_masked_atomic_seg)) / 16;
- break;
+ mlx5_ib_warn(dev, "Atomic operations are not supported yet\n");
+ err = -ENOSYS;
+ *bad_wr = wr;
+ goto out;
case IB_WR_LOCAL_INV:
next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
@@ -2112,6 +2577,73 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
num_sge = 0;
break;
+ case IB_WR_REG_SIG_MR:
+ qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
+ mr = to_mmr(wr->wr.sig_handover.sig_mr);
+
+ ctrl->imm = cpu_to_be32(mr->ibmr.rkey);
+ err = set_sig_umr_wr(wr, qp, &seg, &size);
+ if (err) {
+ mlx5_ib_warn(dev, "\n");
+ *bad_wr = wr;
+ goto out;
+ }
+
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+ nreq, get_fence(fence, wr),
+ next_fence, MLX5_OPCODE_UMR);
+ /*
+ * SET_PSV WQEs are not signaled and solicited
+ * on error
+ */
+ wr->send_flags &= ~IB_SEND_SIGNALED;
+ wr->send_flags |= IB_SEND_SOLICITED;
+ err = begin_wqe(qp, &seg, &ctrl, wr,
+ &idx, &size, nreq);
+ if (err) {
+ mlx5_ib_warn(dev, "\n");
+ err = -ENOMEM;
+ *bad_wr = wr;
+ goto out;
+ }
+
+ err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->mem,
+ mr->sig->psv_memory.psv_idx, &seg,
+ &size);
+ if (err) {
+ mlx5_ib_warn(dev, "\n");
+ *bad_wr = wr;
+ goto out;
+ }
+
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+ nreq, get_fence(fence, wr),
+ next_fence, MLX5_OPCODE_SET_PSV);
+ err = begin_wqe(qp, &seg, &ctrl, wr,
+ &idx, &size, nreq);
+ if (err) {
+ mlx5_ib_warn(dev, "\n");
+ err = -ENOMEM;
+ *bad_wr = wr;
+ goto out;
+ }
+
+ next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+ err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->wire,
+ mr->sig->psv_wire.psv_idx, &seg,
+ &size);
+ if (err) {
+ mlx5_ib_warn(dev, "\n");
+ *bad_wr = wr;
+ goto out;
+ }
+
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+ nreq, get_fence(fence, wr),
+ next_fence, MLX5_OPCODE_SET_PSV);
+ num_sge = 0;
+ goto skip_psv;
+
default:
break;
}
@@ -2192,22 +2724,10 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
}
}
- mlx5_opcode = mlx5_ib_opcode[wr->opcode];
- 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 |= 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;
-
+ finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+ get_fence(fence, wr), next_fence,
+ mlx5_ib_opcode[wr->opcode]);
+skip_psv:
if (0)
dump_wqe(qp, idx, size);
}
@@ -2223,6 +2743,10 @@ out:
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();
+
if (bf->need_lock)
spin_lock(&bf->lock);
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 84d297afd6a..384af6dec5e 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -35,6 +35,7 @@
#include <linux/mlx5/srq.h>
#include <linux/slab.h>
#include <rdma/ib_umem.h>
+#include <rdma/ib_user_verbs.h>
#include "mlx5_ib.h"
#include "user.h"
@@ -78,16 +79,27 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
struct mlx5_ib_create_srq ucmd;
+ size_t ucmdlen;
int err;
int npages;
int page_shift;
int ncont;
u32 offset;
- if (ib_copy_from_udata(&ucmd, udata, sizeof(ucmd))) {
+ ucmdlen =
+ (udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
+ sizeof(ucmd)) ? (sizeof(ucmd) -
+ sizeof(ucmd.reserved)) : 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)
+ return -EINVAL;
+
srq->wq_sig = !!(ucmd.flags & MLX5_SRQ_FLAG_SIGNATURE);
srq->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr, buf_size,
@@ -123,7 +135,7 @@ static int create_srq_user(struct ib_pd *pd, struct mlx5_ib_srq *srq,
goto err_in;
}
- (*in)->ctx.log_pg_sz = page_shift - PAGE_SHIFT;
+ (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
(*in)->ctx.pgoff_cqn = cpu_to_be32(offset << 26);
return 0;
@@ -192,7 +204,7 @@ static int create_srq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_srq *srq,
}
srq->wq_sig = !!srq_signature;
- (*in)->ctx.log_pg_sz = page_shift - PAGE_SHIFT;
+ (*in)->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
return 0;
@@ -295,7 +307,7 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
mlx5_vfree(in);
if (err) {
mlx5_ib_dbg(dev, "create SRQ failed, err %d\n", err);
- goto err_srq;
+ goto err_usr_kern_srq;
}
mlx5_ib_dbg(dev, "create SRQ with srqn 0x%x\n", srq->msrq.srqn);
@@ -316,6 +328,8 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
err_core:
mlx5_core_destroy_srq(&dev->mdev, &srq->msrq);
+
+err_usr_kern_srq:
if (pd->uobject)
destroy_srq_user(pd, srq);
else
@@ -388,9 +402,7 @@ int mlx5_ib_destroy_srq(struct ib_srq *srq)
mlx5_ib_db_unmap_user(to_mucontext(srq->uobject->context), &msrq->db);
ib_umem_release(msrq->umem);
} else {
- kfree(msrq->wrid);
- mlx5_buf_free(&dev->mdev, &msrq->buf);
- mlx5_db_free(&dev->mdev, &msrq->db);
+ destroy_srq_kernel(dev, msrq);
}
kfree(srq);
diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h
index a886de3e593..d0ba264ac1e 100644
--- a/drivers/infiniband/hw/mlx5/user.h
+++ b/drivers/infiniband/hw/mlx5/user.h
@@ -62,6 +62,13 @@ struct mlx5_ib_alloc_ucontext_req {
__u32 num_low_latency_uuars;
};
+struct mlx5_ib_alloc_ucontext_req_v2 {
+ __u32 total_num_uuars;
+ __u32 num_low_latency_uuars;
+ __u32 flags;
+ __u32 reserved;
+};
+
struct mlx5_ib_alloc_ucontext_resp {
__u32 qp_tab_size;
__u32 bf_reg_size;
@@ -84,6 +91,7 @@ struct mlx5_ib_create_cq {
__u64 buf_addr;
__u64 db_addr;
__u32 cqe_size;
+ __u32 reserved; /* explicit padding (optional on i386) */
};
struct mlx5_ib_create_cq_resp {
@@ -93,12 +101,16 @@ struct mlx5_ib_create_cq_resp {
struct mlx5_ib_resize_cq {
__u64 buf_addr;
+ __u16 cqe_size;
+ __u16 reserved0;
+ __u32 reserved1;
};
struct mlx5_ib_create_srq {
__u64 buf_addr;
__u64 db_addr;
__u32 flags;
+ __u32 reserved; /* explicit padding (optional on i386) */
};
struct mlx5_ib_create_srq_resp {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 01:29:50 +0000