summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/core/cma.c9
-rw-r--r--drivers/infiniband/hw/amso1100/c2_ae.c1
-rw-r--r--drivers/infiniband/hw/cxgb3/iwch_cm.c6
-rw-r--r--drivers/infiniband/hw/cxgb4/cm.c6
-rw-r--r--drivers/infiniband/hw/ipath/ipath_init_chip.c10
-rw-r--r--drivers/infiniband/hw/mlx4/cm.c4
-rw-r--r--drivers/infiniband/hw/mlx4/cq.c34
-rw-r--r--drivers/infiniband/hw/mlx4/main.c27
-rw-r--r--drivers/infiniband/hw/mlx4/mlx4_ib.h1
-rw-r--r--drivers/infiniband/hw/mlx4/user.h12
-rw-r--r--drivers/infiniband/ulp/srp/ib_srp.c314
-rw-r--r--drivers/infiniband/ulp/srp/ib_srp.h11
12 files changed, 262 insertions, 173 deletions
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index a7568c34a1a..d789eea3216 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -345,17 +345,17 @@ static int find_gid_port(struct ib_device *device, union ib_gid *gid, u8 port_nu
err = ib_query_port(device, port_num, &props);
if (err)
- return 1;
+ return err;
for (i = 0; i < props.gid_tbl_len; ++i) {
err = ib_query_gid(device, port_num, i, &tmp);
if (err)
- return 1;
+ return err;
if (!memcmp(&tmp, gid, sizeof tmp))
return 0;
}
- return -EAGAIN;
+ return -EADDRNOTAVAIL;
}
static int cma_acquire_dev(struct rdma_id_private *id_priv)
@@ -388,8 +388,7 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv)
if (!ret) {
id_priv->id.port_num = port;
goto out;
- } else if (ret == 1)
- break;
+ }
}
}
}
diff --git a/drivers/infiniband/hw/amso1100/c2_ae.c b/drivers/infiniband/hw/amso1100/c2_ae.c
index 32d34e88d5c..706cf97cbe8 100644
--- a/drivers/infiniband/hw/amso1100/c2_ae.c
+++ b/drivers/infiniband/hw/amso1100/c2_ae.c
@@ -311,6 +311,7 @@ void c2_ae_event(struct c2_dev *c2dev, u32 mq_index)
if (cq->ibcq.event_handler)
cq->ibcq.event_handler(&ib_event,
cq->ibcq.cq_context);
+ break;
}
default:
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index aaf88ef9409..3e094cd6a0e 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -128,9 +128,8 @@ static void stop_ep_timer(struct iwch_ep *ep)
{
PDBG("%s ep %p\n", __func__, ep);
if (!timer_pending(&ep->timer)) {
- printk(KERN_ERR "%s timer stopped when its not running! ep %p state %u\n",
+ WARN(1, "%s timer stopped when its not running! ep %p state %u\n",
__func__, ep, ep->com.state);
- WARN_ON(1);
return;
}
del_timer_sync(&ep->timer);
@@ -1756,9 +1755,8 @@ static void ep_timeout(unsigned long arg)
__state_set(&ep->com, ABORTING);
break;
default:
- printk(KERN_ERR "%s unexpected state ep %p state %u\n",
+ WARN(1, "%s unexpected state ep %p state %u\n",
__func__, ep, ep->com.state);
- WARN_ON(1);
abort = 0;
}
spin_unlock_irqrestore(&ep->com.lock, flags);
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 6cfd4d8fd0b..5de86968379 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -151,9 +151,8 @@ static void stop_ep_timer(struct c4iw_ep *ep)
{
PDBG("%s ep %p\n", __func__, ep);
if (!timer_pending(&ep->timer)) {
- printk(KERN_ERR "%s timer stopped when its not running! "
+ WARN(1, "%s timer stopped when its not running! "
"ep %p state %u\n", __func__, ep, ep->com.state);
- WARN_ON(1);
return;
}
del_timer_sync(&ep->timer);
@@ -2551,9 +2550,8 @@ static void process_timeout(struct c4iw_ep *ep)
__state_set(&ep->com, ABORTING);
break;
default:
- printk(KERN_ERR "%s unexpected state ep %p tid %u state %u\n",
+ WARN(1, "%s unexpected state ep %p tid %u state %u\n",
__func__, ep, ep->hwtid, ep->com.state);
- WARN_ON(1);
abort = 0;
}
mutex_unlock(&ep->com.mutex);
diff --git a/drivers/infiniband/hw/ipath/ipath_init_chip.c b/drivers/infiniband/hw/ipath/ipath_init_chip.c
index 49b09c697c7..be2a60e142b 100644
--- a/drivers/infiniband/hw/ipath/ipath_init_chip.c
+++ b/drivers/infiniband/hw/ipath/ipath_init_chip.c
@@ -719,16 +719,6 @@ int ipath_init_chip(struct ipath_devdata *dd, int reinit)
goto done;
/*
- * we ignore most issues after reporting them, but have to specially
- * handle hardware-disabled chips.
- */
- if (ret == 2) {
- /* unique error, known to ipath_init_one */
- ret = -EPERM;
- goto done;
- }
-
- /*
* We could bump this to allow for full rcvegrcnt + rcvtidcnt,
* but then it no longer nicely fits power of two, and since
* we now use routines that backend onto __get_free_pages, the
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index 80079e5a2e3..dbc99d41605 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -268,15 +268,15 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
struct mlx4_ib_sriov *sriov = &to_mdev(ibdev)->sriov;
unsigned long flags;
- spin_lock_irqsave(&sriov->going_down_lock, flags);
spin_lock(&sriov->id_map_lock);
+ spin_lock_irqsave(&sriov->going_down_lock, flags);
/*make sure that there is no schedule inside the scheduled work.*/
if (!sriov->is_going_down) {
id->scheduled_delete = 1;
schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
}
- spin_unlock(&sriov->id_map_lock);
spin_unlock_irqrestore(&sriov->going_down_lock, flags);
+ spin_unlock(&sriov->id_map_lock);
}
int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id,
diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index c9eb6a6815c..ae67df35dd4 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -66,7 +66,7 @@ static void mlx4_ib_cq_event(struct mlx4_cq *cq, enum mlx4_event type)
static void *get_cqe_from_buf(struct mlx4_ib_cq_buf *buf, int n)
{
- return mlx4_buf_offset(&buf->buf, n * sizeof (struct mlx4_cqe));
+ return mlx4_buf_offset(&buf->buf, n * buf->entry_size);
}
static void *get_cqe(struct mlx4_ib_cq *cq, int n)
@@ -77,8 +77,9 @@ static void *get_cqe(struct mlx4_ib_cq *cq, int n)
static void *get_sw_cqe(struct mlx4_ib_cq *cq, int n)
{
struct mlx4_cqe *cqe = get_cqe(cq, n & cq->ibcq.cqe);
+ struct mlx4_cqe *tcqe = ((cq->buf.entry_size == 64) ? (cqe + 1) : cqe);
- return (!!(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK) ^
+ return (!!(tcqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK) ^
!!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
}
@@ -99,12 +100,13 @@ static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *
{
int err;
- err = mlx4_buf_alloc(dev->dev, nent * sizeof(struct mlx4_cqe),
+ err = mlx4_buf_alloc(dev->dev, nent * dev->dev->caps.cqe_size,
PAGE_SIZE * 2, &buf->buf);
if (err)
goto out;
+ buf->entry_size = dev->dev->caps.cqe_size;
err = mlx4_mtt_init(dev->dev, buf->buf.npages, buf->buf.page_shift,
&buf->mtt);
if (err)
@@ -120,8 +122,7 @@ err_mtt:
mlx4_mtt_cleanup(dev->dev, &buf->mtt);
err_buf:
- mlx4_buf_free(dev->dev, nent * sizeof(struct mlx4_cqe),
- &buf->buf);
+ mlx4_buf_free(dev->dev, nent * buf->entry_size, &buf->buf);
out:
return err;
@@ -129,7 +130,7 @@ out:
static void mlx4_ib_free_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *buf, int cqe)
{
- mlx4_buf_free(dev->dev, (cqe + 1) * sizeof(struct mlx4_cqe), &buf->buf);
+ mlx4_buf_free(dev->dev, (cqe + 1) * buf->entry_size, &buf->buf);
}
static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *context,
@@ -137,8 +138,9 @@ static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *cont
u64 buf_addr, int cqe)
{
int err;
+ int cqe_size = dev->dev->caps.cqe_size;
- *umem = ib_umem_get(context, buf_addr, cqe * sizeof (struct mlx4_cqe),
+ *umem = ib_umem_get(context, buf_addr, cqe * cqe_size,
IB_ACCESS_LOCAL_WRITE, 1);
if (IS_ERR(*umem))
return PTR_ERR(*umem);
@@ -331,16 +333,23 @@ static void mlx4_ib_cq_resize_copy_cqes(struct mlx4_ib_cq *cq)
{
struct mlx4_cqe *cqe, *new_cqe;
int i;
+ int cqe_size = cq->buf.entry_size;
+ int cqe_inc = cqe_size == 64 ? 1 : 0;
i = cq->mcq.cons_index;
cqe = get_cqe(cq, i & cq->ibcq.cqe);
+ cqe += cqe_inc;
+
while ((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) != MLX4_CQE_OPCODE_RESIZE) {
new_cqe = get_cqe_from_buf(&cq->resize_buf->buf,
(i + 1) & cq->resize_buf->cqe);
- memcpy(new_cqe, get_cqe(cq, i & cq->ibcq.cqe), sizeof(struct mlx4_cqe));
+ memcpy(new_cqe, get_cqe(cq, i & cq->ibcq.cqe), cqe_size);
+ new_cqe += cqe_inc;
+
new_cqe->owner_sr_opcode = (cqe->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK) |
(((i + 1) & (cq->resize_buf->cqe + 1)) ? MLX4_CQE_OWNER_MASK : 0);
cqe = get_cqe(cq, ++i & cq->ibcq.cqe);
+ cqe += cqe_inc;
}
++cq->mcq.cons_index;
}
@@ -438,6 +447,7 @@ err_buf:
out:
mutex_unlock(&cq->resize_mutex);
+
return err;
}
@@ -586,6 +596,9 @@ repoll:
if (!cqe)
return -EAGAIN;
+ if (cq->buf.entry_size == 64)
+ cqe++;
+
++cq->mcq.cons_index;
/*
@@ -807,6 +820,7 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
int nfreed = 0;
struct mlx4_cqe *cqe, *dest;
u8 owner_bit;
+ int cqe_inc = cq->buf.entry_size == 64 ? 1 : 0;
/*
* First we need to find the current producer index, so we
@@ -825,12 +839,16 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
*/
while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
+ cqe += cqe_inc;
+
if ((be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK) == qpn) {
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) {
dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
+ dest += cqe_inc;
+
owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
memcpy(dest, cqe, sizeof *cqe);
dest->owner_sr_opcode = owner_bit |
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 718ec6b2bad..e7d81c0d1ac 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -563,15 +563,24 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
{
struct mlx4_ib_dev *dev = to_mdev(ibdev);
struct mlx4_ib_ucontext *context;
+ struct mlx4_ib_alloc_ucontext_resp_v3 resp_v3;
struct mlx4_ib_alloc_ucontext_resp resp;
int err;
if (!dev->ib_active)
return ERR_PTR(-EAGAIN);
- resp.qp_tab_size = dev->dev->caps.num_qps;
- resp.bf_reg_size = dev->dev->caps.bf_reg_size;
- resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+ if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION) {
+ resp_v3.qp_tab_size = dev->dev->caps.num_qps;
+ resp_v3.bf_reg_size = dev->dev->caps.bf_reg_size;
+ resp_v3.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+ } else {
+ resp.dev_caps = dev->dev->caps.userspace_caps;
+ resp.qp_tab_size = dev->dev->caps.num_qps;
+ resp.bf_reg_size = dev->dev->caps.bf_reg_size;
+ resp.bf_regs_per_page = dev->dev->caps.bf_regs_per_page;
+ resp.cqe_size = dev->dev->caps.cqe_size;
+ }
context = kmalloc(sizeof *context, GFP_KERNEL);
if (!context)
@@ -586,7 +595,11 @@ static struct ib_ucontext *mlx4_ib_alloc_ucontext(struct ib_device *ibdev,
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);
- err = ib_copy_to_udata(udata, &resp, sizeof resp);
+ if (ibdev->uverbs_abi_ver == MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION)
+ err = ib_copy_to_udata(udata, &resp_v3, sizeof(resp_v3));
+ else
+ err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+
if (err) {
mlx4_uar_free(to_mdev(ibdev)->dev, &context->uar);
kfree(context);
@@ -1342,7 +1355,11 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
ibdev->ib_dev.num_comp_vectors = dev->caps.num_comp_vectors;
ibdev->ib_dev.dma_device = &dev->pdev->dev;
- ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
+ if (dev->caps.userspace_caps)
+ ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_ABI_VERSION;
+ else
+ ibdev->ib_dev.uverbs_abi_ver = MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION;
+
ibdev->ib_dev.uverbs_cmd_mask =
(1ull << IB_USER_VERBS_CMD_GET_CONTEXT) |
(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) |
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index e04cbc9a54a..dcd845bc30f 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -90,6 +90,7 @@ struct mlx4_ib_xrcd {
struct mlx4_ib_cq_buf {
struct mlx4_buf buf;
struct mlx4_mtt mtt;
+ int entry_size;
};
struct mlx4_ib_cq_resize {
diff --git a/drivers/infiniband/hw/mlx4/user.h b/drivers/infiniband/hw/mlx4/user.h
index 13beedeeef9..07e6769ef43 100644
--- a/drivers/infiniband/hw/mlx4/user.h
+++ b/drivers/infiniband/hw/mlx4/user.h
@@ -40,7 +40,9 @@
* Increment this value if any changes that break userspace ABI
* compatibility are made.
*/
-#define MLX4_IB_UVERBS_ABI_VERSION 3
+
+#define MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION 3
+#define MLX4_IB_UVERBS_ABI_VERSION 4
/*
* Make sure that all structs defined in this file remain laid out so
@@ -50,10 +52,18 @@
* instead.
*/
+struct mlx4_ib_alloc_ucontext_resp_v3 {
+ __u32 qp_tab_size;
+ __u16 bf_reg_size;
+ __u16 bf_regs_per_page;
+};
+
struct mlx4_ib_alloc_ucontext_resp {
+ __u32 dev_caps;
__u32 qp_tab_size;
__u16 bf_reg_size;
__u16 bf_regs_per_page;
+ __u32 cqe_size;
};
struct mlx4_ib_alloc_pd_resp {
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 922d845f76b..d5088ce7829 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -222,27 +222,29 @@ static int srp_new_cm_id(struct srp_target_port *target)
static int srp_create_target_ib(struct srp_target_port *target)
{
struct ib_qp_init_attr *init_attr;
+ struct ib_cq *recv_cq, *send_cq;
+ struct ib_qp *qp;
int ret;
init_attr = kzalloc(sizeof *init_attr, GFP_KERNEL);
if (!init_attr)
return -ENOMEM;
- target->recv_cq = ib_create_cq(target->srp_host->srp_dev->dev,
- srp_recv_completion, NULL, target, SRP_RQ_SIZE, 0);
- if (IS_ERR(target->recv_cq)) {
- ret = PTR_ERR(target->recv_cq);
+ recv_cq = ib_create_cq(target->srp_host->srp_dev->dev,
+ srp_recv_completion, NULL, target, SRP_RQ_SIZE, 0);
+ if (IS_ERR(recv_cq)) {
+ ret = PTR_ERR(recv_cq);
goto err;
}
- target->send_cq = ib_create_cq(target->srp_host->srp_dev->dev,
- srp_send_completion, NULL, target, SRP_SQ_SIZE, 0);
- if (IS_ERR(target->send_cq)) {
- ret = PTR_ERR(target->send_cq);
+ send_cq = ib_create_cq(target->srp_host->srp_dev->dev,
+ srp_send_completion, NULL, target, SRP_SQ_SIZE, 0);
+ if (IS_ERR(send_cq)) {
+ ret = PTR_ERR(send_cq);
goto err_recv_cq;
}
- ib_req_notify_cq(target->recv_cq, IB_CQ_NEXT_COMP);
+ ib_req_notify_cq(recv_cq, IB_CQ_NEXT_COMP);
init_attr->event_handler = srp_qp_event;
init_attr->cap.max_send_wr = SRP_SQ_SIZE;
@@ -251,30 +253,41 @@ static int srp_create_target_ib(struct srp_target_port *target)
init_attr->cap.max_send_sge = 1;
init_attr->sq_sig_type = IB_SIGNAL_ALL_WR;
init_attr->qp_type = IB_QPT_RC;
- init_attr->send_cq = target->send_cq;
- init_attr->recv_cq = target->recv_cq;
+ init_attr->send_cq = send_cq;
+ init_attr->recv_cq = recv_cq;
- target->qp = ib_create_qp(target->srp_host->srp_dev->pd, init_attr);
- if (IS_ERR(target->qp)) {
- ret = PTR_ERR(target->qp);
+ qp = ib_create_qp(target->srp_host->srp_dev->pd, init_attr);
+ if (IS_ERR(qp)) {
+ ret = PTR_ERR(qp);
goto err_send_cq;
}
- ret = srp_init_qp(target, target->qp);
+ ret = srp_init_qp(target, qp);
if (ret)
goto err_qp;
+ if (target->qp)
+ ib_destroy_qp(target->qp);
+ if (target->recv_cq)
+ ib_destroy_cq(target->recv_cq);
+ if (target->send_cq)
+ ib_destroy_cq(target->send_cq);
+
+ target->qp = qp;
+ target->recv_cq = recv_cq;
+ target->send_cq = send_cq;
+
kfree(init_attr);
return 0;
err_qp:
- ib_destroy_qp(target->qp);
+ ib_destroy_qp(qp);
err_send_cq:
- ib_destroy_cq(target->send_cq);
+ ib_destroy_cq(send_cq);
err_recv_cq:
- ib_destroy_cq(target->recv_cq);
+ ib_destroy_cq(recv_cq);
err:
kfree(init_attr);
@@ -289,6 +302,9 @@ static void srp_free_target_ib(struct srp_target_port *target)
ib_destroy_cq(target->send_cq);
ib_destroy_cq(target->recv_cq);
+ target->qp = NULL;
+ target->send_cq = target->recv_cq = NULL;
+
for (i = 0; i < SRP_RQ_SIZE; ++i)
srp_free_iu(target->srp_host, target->rx_ring[i]);
for (i = 0; i < SRP_SQ_SIZE; ++i)
@@ -428,34 +444,50 @@ static int srp_send_req(struct srp_target_port *target)
return status;
}
-static void srp_disconnect_target(struct srp_target_port *target)
+static bool srp_queue_remove_work(struct srp_target_port *target)
{
- /* XXX should send SRP_I_LOGOUT request */
+ bool changed = false;
- init_completion(&target->done);
- if (ib_send_cm_dreq(target->cm_id, NULL, 0)) {
- shost_printk(KERN_DEBUG, target->scsi_host,
- PFX "Sending CM DREQ failed\n");
- return;
+ spin_lock_irq(&target->lock);
+ if (target->state != SRP_TARGET_REMOVED) {
+ target->state = SRP_TARGET_REMOVED;
+ changed = true;
}
- wait_for_completion(&target->done);
+ spin_unlock_irq(&target->lock);
+
+ if (changed)
+ queue_work(system_long_wq, &target->remove_work);
+
+ return changed;
}
-static bool srp_change_state(struct srp_target_port *target,
- enum srp_target_state old,
- enum srp_target_state new)
+static bool srp_change_conn_state(struct srp_target_port *target,
+ bool connected)
{
bool changed = false;
spin_lock_irq(&target->lock);
- if (target->state == old) {
- target->state = new;
+ if (target->connected != connected) {
+ target->connected = connected;
changed = true;
}
spin_unlock_irq(&target->lock);
+
return changed;
}
+static void srp_disconnect_target(struct srp_target_port *target)
+{
+ if (srp_change_conn_state(target, false)) {
+ /* XXX should send SRP_I_LOGOUT request */
+
+ if (ib_send_cm_dreq(target->cm_id, NULL, 0)) {
+ shost_printk(KERN_DEBUG, target->scsi_host,
+ PFX "Sending CM DREQ failed\n");
+ }
+ }
+}
+
static void srp_free_req_data(struct srp_target_port *target)
{
struct ib_device *ibdev = target->srp_host->srp_dev->dev;
@@ -489,32 +521,50 @@ static void srp_del_scsi_host_attr(struct Scsi_Host *shost)
device_remove_file(&shost->shost_dev, *attr);
}
-static void srp_remove_work(struct work_struct *work)
+static void srp_remove_target(struct srp_target_port *target)
{
- struct srp_target_port *target =
- container_of(work, struct srp_target_port, work);
-
- if (!srp_change_state(target, SRP_TARGET_DEAD, SRP_TARGET_REMOVED))
- return;
-
- spin_lock(&target->srp_host->target_lock);
- list_del(&target->list);
- spin_unlock(&target->srp_host->target_lock);
+ WARN_ON_ONCE(target->state != SRP_TARGET_REMOVED);
srp_del_scsi_host_attr(target->scsi_host);
srp_remove_host(target->scsi_host);
scsi_remove_host(target->scsi_host);
+ srp_disconnect_target(target);
ib_destroy_cm_id(target->cm_id);
srp_free_target_ib(target);
srp_free_req_data(target);
scsi_host_put(target->scsi_host);
}
+static void srp_remove_work(struct work_struct *work)
+{
+ struct srp_target_port *target =
+ container_of(work, struct srp_target_port, remove_work);
+
+ WARN_ON_ONCE(target->state != SRP_TARGET_REMOVED);
+
+ spin_lock(&target->srp_host->target_lock);
+ list_del(&target->list);
+ spin_unlock(&target->srp_host->target_lock);
+
+ srp_remove_target(target);
+}
+
+static void srp_rport_delete(struct srp_rport *rport)
+{
+ struct srp_target_port *target = rport->lld_data;
+
+ srp_queue_remove_work(target);
+}
+
static int srp_connect_target(struct srp_target_port *target)
{
int retries = 3;
int ret;
+ WARN_ON_ONCE(target->connected);
+
+ target->qp_in_error = false;
+
ret = srp_lookup_path(target);
if (ret)
return ret;
@@ -534,6 +584,7 @@ static int srp_connect_target(struct srp_target_port *target)
*/
switch (target->status) {
case 0:
+ srp_change_conn_state(target, true);
return 0;
case SRP_PORT_REDIRECT:
@@ -646,13 +697,14 @@ static void srp_reset_req(struct srp_target_port *target, struct srp_request *re
static int srp_reconnect_target(struct srp_target_port *target)
{
- struct ib_qp_attr qp_attr;
- struct ib_wc wc;
+ struct Scsi_Host *shost = target->scsi_host;
int i, ret;
- if (!srp_change_state(target, SRP_TARGET_LIVE, SRP_TARGET_CONNECTING))
+ if (target->state != SRP_TARGET_LIVE)
return -EAGAIN;
+ scsi_target_block(&shost->shost_gendev);
+
srp_disconnect_target(target);
/*
* Now get a new local CM ID so that we avoid confusing the
@@ -660,21 +712,11 @@ static int srp_reconnect_target(struct srp_target_port *target)
*/
ret = srp_new_cm_id(target);
if (ret)
- goto err;
+ goto unblock;
- qp_attr.qp_state = IB_QPS_RESET;
- ret = ib_modify_qp(target->qp, &qp_attr, IB_QP_STATE);
- if (ret)
- goto err;
-
- ret = srp_init_qp(target, target->qp);
+ ret = srp_create_target_ib(target);
if (ret)
- goto err;
-
- while (ib_poll_cq(target->recv_cq, 1, &wc) > 0)
- ; /* nothing */
- while (ib_poll_cq(target->send_cq, 1, &wc) > 0)
- ; /* nothing */
+ goto unblock;
for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
struct srp_request *req = &target->req_ring[i];
@@ -686,13 +728,16 @@ static int srp_reconnect_target(struct srp_target_port *target)
for (i = 0; i < SRP_SQ_SIZE; ++i)
list_add(&target->tx_ring[i]->list, &target->free_tx);
- target->qp_in_error = 0;
ret = srp_connect_target(target);
+
+unblock:
+ scsi_target_unblock(&shost->shost_gendev, ret == 0 ? SDEV_RUNNING :
+ SDEV_TRANSPORT_OFFLINE);
+
if (ret)
goto err;
- if (!srp_change_state(target, SRP_TARGET_CONNECTING, SRP_TARGET_LIVE))
- ret = -EAGAIN;
+ shost_printk(KERN_INFO, target->scsi_host, PFX "reconnect succeeded\n");
return ret;
@@ -705,17 +750,8 @@ err:
* However, we have to defer the real removal because we
* are in the context of the SCSI error handler now, which
* will deadlock if we call scsi_remove_host().
- *
- * Schedule our work inside the lock to avoid a race with
- * the flush_scheduled_work() in srp_remove_one().
*/
- spin_lock_irq(&target->lock);
- if (target->state == SRP_TARGET_CONNECTING) {
- target->state = SRP_TARGET_DEAD;
- INIT_WORK(&target->work, srp_remove_work);
- queue_work(ib_wq, &target->work);
- }
- spin_unlock_irq(&target->lock);
+ srp_queue_remove_work(target);
return ret;
}
@@ -1262,6 +1298,19 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
PFX "Recv failed with error code %d\n", res);
}
+static void srp_handle_qp_err(enum ib_wc_status wc_status,
+ enum ib_wc_opcode wc_opcode,
+ struct srp_target_port *target)
+{
+ if (target->connected && !target->qp_in_error) {
+ shost_printk(KERN_ERR, target->scsi_host,
+ PFX "failed %s status %d\n",
+ wc_opcode & IB_WC_RECV ? "receive" : "send",
+ wc_status);
+ }
+ target->qp_in_error = true;
+}
+
static void srp_recv_completion(struct ib_cq *cq, void *target_ptr)
{
struct srp_target_port *target = target_ptr;
@@ -1269,15 +1318,11 @@ static void srp_recv_completion(struct ib_cq *cq, void *target_ptr)
ib_req_notify_cq(cq, IB_CQ_NEXT_COMP);
while (ib_poll_cq(cq, 1, &wc) > 0) {
- if (wc.status) {
- shost_printk(KERN_ERR, target->scsi_host,
- PFX "failed receive status %d\n",
- wc.status);
- target->qp_in_error = 1;
- break;
+ if (likely(wc.status == IB_WC_SUCCESS)) {
+ srp_handle_recv(target, &wc);
+ } else {
+ srp_handle_qp_err(wc.status, wc.opcode, target);
}
-
- srp_handle_recv(target, &wc);
}
}
@@ -1288,16 +1333,12 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
struct srp_iu *iu;
while (ib_poll_cq(cq, 1, &wc) > 0) {
- if (wc.status) {
- shost_printk(KERN_ERR, target->scsi_host,
- PFX "failed send status %d\n",
- wc.status);
- target->qp_in_error = 1;
- break;
+ if (likely(wc.status == IB_WC_SUCCESS)) {
+ iu = (struct srp_iu *) (uintptr_t) wc.wr_id;
+ list_add(&iu->list, &target->free_tx);
+ } else {
+ srp_handle_qp_err(wc.status, wc.opcode, target);
}
-
- iu = (struct srp_iu *) (uintptr_t) wc.wr_id;
- list_add(&iu->list, &target->free_tx);
}
}
@@ -1311,16 +1352,6 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
unsigned long flags;
int len;
- if (target->state == SRP_TARGET_CONNECTING)
- goto err;
-
- if (target->state == SRP_TARGET_DEAD ||
- target->state == SRP_TARGET_REMOVED) {
- scmnd->result = DID_BAD_TARGET << 16;
- scmnd->scsi_done(scmnd);
- return 0;
- }
-
spin_lock_irqsave(&target->lock, flags);
iu = __srp_get_tx_iu(target, SRP_IU_CMD);
if (!iu)
@@ -1377,7 +1408,6 @@ err_iu:
err_unlock:
spin_unlock_irqrestore(&target->lock, flags);
-err:
return SCSI_MLQUEUE_HOST_BUSY;
}
@@ -1419,6 +1449,33 @@ err:
return -ENOMEM;
}
+static uint32_t srp_compute_rq_tmo(struct ib_qp_attr *qp_attr, int attr_mask)
+{
+ uint64_t T_tr_ns, max_compl_time_ms;
+ uint32_t rq_tmo_jiffies;
+
+ /*
+ * According to section 11.2.4.2 in the IBTA spec (Modify Queue Pair,
+ * table 91), both the QP timeout and the retry count have to be set
+ * for RC QP's during the RTR to RTS transition.
+ */
+ WARN_ON_ONCE((attr_mask & (IB_QP_TIMEOUT | IB_QP_RETRY_CNT)) !=
+ (IB_QP_TIMEOUT | IB_QP_RETRY_CNT));
+
+ /*
+ * Set target->rq_tmo_jiffies to one second more than the largest time
+ * it can take before an error completion is generated. See also
+ * C9-140..142 in the IBTA spec for more information about how to
+ * convert the QP Local ACK Timeout value to nanoseconds.
+ */
+ T_tr_ns = 4096 * (1ULL << qp_attr->timeout);
+ max_compl_time_ms = qp_attr->retry_cnt * 4 * T_tr_ns;
+ do_div(max_compl_time_ms, NSEC_PER_MSEC);
+ rq_tmo_jiffies = msecs_to_jiffies(max_compl_time_ms + 1000);
+
+ return rq_tmo_jiffies;
+}
+
static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
struct srp_login_rsp *lrsp,
struct srp_target_port *target)
@@ -1478,6 +1535,8 @@ static void srp_cm_rep_handler(struct ib_cm_id *cm_id,
if (ret)
goto error_free;
+ target->rq_tmo_jiffies = srp_compute_rq_tmo(qp_attr, attr_mask);
+
ret = ib_modify_qp(target->qp, qp_attr, attr_mask);
if (ret)
goto error_free;
@@ -1599,6 +1658,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
case IB_CM_DREQ_RECEIVED:
shost_printk(KERN_WARNING, target->scsi_host,
PFX "DREQ received - connection closed\n");
+ srp_change_conn_state(target, false);
if (ib_send_cm_drep(cm_id, NULL, 0))
shost_printk(KERN_ERR, target->scsi_host,
PFX "Sending CM DREP failed\n");
@@ -1608,7 +1668,6 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
shost_printk(KERN_ERR, target->scsi_host,
PFX "connection closed\n");
- comp = 1;
target->status = 0;
break;
@@ -1636,10 +1695,6 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target,
struct srp_iu *iu;
struct srp_tsk_mgmt *tsk_mgmt;
- if (target->state == SRP_TARGET_DEAD ||
- target->state == SRP_TARGET_REMOVED)
- return -1;
-
init_completion(&target->tsk_mgmt_done);
spin_lock_irq(&target->lock);
@@ -1729,6 +1784,21 @@ static int srp_reset_host(struct scsi_cmnd *scmnd)
return ret;
}
+static int srp_slave_configure(struct scsi_device *sdev)
+{
+ struct Scsi_Host *shost = sdev->host;
+ struct srp_target_port *target = host_to_target(shost);
+ struct request_queue *q = sdev->request_queue;
+ unsigned long timeout;
+
+ if (sdev->type == TYPE_DISK) {
+ timeout = max_t(unsigned, 30 * HZ, target->rq_tmo_jiffies);
+ blk_queue_rq_timeout(q, timeout);
+ }
+
+ return 0;
+}
+
static ssize_t show_id_ext(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -1861,6 +1931,7 @@ static struct scsi_host_template srp_template = {
.module = THIS_MODULE,
.name = "InfiniBand SRP initiator",
.proc_name = DRV_NAME,
+ .slave_configure = srp_slave_configure,
.info = srp_target_info,
.queuecommand = srp_queuecommand,
.eh_abort_handler = srp_abort,
@@ -1894,11 +1965,14 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
return PTR_ERR(rport);
}
+ rport->lld_data = target;
+
spin_lock(&host->target_lock);
list_add_tail(&target->list, &host->target_list);
spin_unlock(&host->target_lock);
target->state = SRP_TARGET_LIVE;
+ target->connected = false;
scsi_scan_target(&target->scsi_host->shost_gendev,
0, target->scsi_id, SCAN_WILD_CARD, 0);
@@ -2188,6 +2262,7 @@ static ssize_t srp_create_target(struct device *dev,
sizeof (struct srp_indirect_buf) +
target->cmd_sg_cnt * sizeof (struct srp_direct_buf);
+ INIT_WORK(&target->remove_work, srp_remove_work);
spin_lock_init(&target->lock);
INIT_LIST_HEAD(&target->free_tx);
INIT_LIST_HEAD(&target->free_reqs);
@@ -2232,7 +2307,6 @@ static ssize_t srp_create_target(struct device *dev,
if (ret)
goto err_free_ib;
- target->qp_in_error = 0;
ret = srp_connect_target(target);
if (ret) {
shost_printk(KERN_ERR, target->scsi_host,
@@ -2422,8 +2496,7 @@ static void srp_remove_one(struct ib_device *device)
{
struct srp_device *srp_dev;
struct srp_host *host, *tmp_host;
- LIST_HEAD(target_list);
- struct srp_target_port *target, *tmp_target;
+ struct srp_target_port *target;
srp_dev = ib_get_client_data(device, &srp_client);
@@ -2436,35 +2509,17 @@ static void srp_remove_one(struct ib_device *device)
wait_for_completion(&host->released);
/*
- * Mark all target ports as removed, so we stop queueing
- * commands and don't try to reconnect.
+ * Remove all target ports.
*/
spin_lock(&host->target_lock);
- list_for_each_entry(target, &host->target_list, list) {
- spin_lock_irq(&target->lock);
- target->state = SRP_TARGET_REMOVED;
- spin_unlock_irq(&target->lock);
- }
+ list_for_each_entry(target, &host->target_list, list)
+ srp_queue_remove_work(target);
spin_unlock(&host->target_lock);
/*
- * Wait for any reconnection tasks that may have
- * started before we marked our target ports as
- * removed, and any target port removal tasks.
+ * Wait for target port removal tasks.
*/
- flush_workqueue(ib_wq);
-
- list_for_each_entry_safe(target, tmp_target,
- &host->target_list, list) {
- srp_del_scsi_host_attr(target->scsi_host);
- srp_remove_host(target->scsi_host);
- scsi_remove_host(target->scsi_host);
- srp_disconnect_target(target);
- ib_destroy_cm_id(target->cm_id);
- srp_free_target_ib(target);
- srp_free_req_data(target);
- scsi_host_put(target->scsi_host);
- }
+ flush_workqueue(system_long_wq);
kfree(host);
}
@@ -2478,6 +2533,7 @@ static void srp_remove_one(struct ib_device *device)
}
static struct srp_function_template ib_srp_transport_functions = {
+ .rport_delete = srp_rport_delete,
};
static int __init srp_init_module(void)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.h b/drivers/infiniband/ulp/srp/ib_srp.h
index 020caf0c378..de2d0b3c0bf 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.h
+++ b/drivers/infiniband/ulp/srp/ib_srp.h
@@ -80,9 +80,7 @@ enum {
enum srp_target_state {
SRP_TARGET_LIVE,
- SRP_TARGET_CONNECTING,
- SRP_TARGET_DEAD,
- SRP_TARGET_REMOVED
+ SRP_TARGET_REMOVED,
};
enum srp_iu_type {
@@ -163,6 +161,9 @@ struct srp_target_port {
struct ib_sa_query *path_query;
int path_query_id;
+ u32 rq_tmo_jiffies;
+ bool connected;
+
struct ib_cm_id *cm_id;
int max_ti_iu_len;
@@ -173,12 +174,12 @@ struct srp_target_port {
struct srp_iu *rx_ring[SRP_RQ_SIZE];
struct srp_request req_ring[SRP_CMD_SQ_SIZE];
- struct work_struct work;
+ struct work_struct remove_work;
struct list_head list;
struct completion done;
int status;
- int qp_in_error;
+ bool qp_in_error;
struct completion tsk_mgmt_done;
u8 tsk_mgmt_status;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-24 22:08:49 +0000