diff options
author | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:12:06 (GMT) |
---|---|---|
committer | Scott Wood <scottwood@freescale.com> | 2015-02-13 22:19:22 (GMT) |
commit | 6faa2909871d8937cb2f79a10e1b21ffe193fac1 (patch) | |
tree | f558a94f1553814cc122ab8d9e04c0ebad5262a5 /drivers/infiniband | |
parent | fcb2fb84301c673ee15ca04e7a2fc965712d49a0 (diff) | |
download | linux-fsl-qoriq-6faa2909871d8937cb2f79a10e1b21ffe193fac1.tar.xz |
Reset to 3.12.37
Diffstat (limited to 'drivers/infiniband')
-rw-r--r-- | drivers/infiniband/core/iwcm.c | 27 | ||||
-rw-r--r-- | drivers/infiniband/core/user_mad.c | 75 | ||||
-rw-r--r-- | drivers/infiniband/hw/cxgb3/iwch_cm.c | 1 | ||||
-rw-r--r-- | drivers/infiniband/hw/ehca/ehca_cq.c | 1 | ||||
-rw-r--r-- | drivers/infiniband/hw/ipath/ipath_diag.c | 68 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx5/cq.c | 13 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx5/srq.c | 14 | ||||
-rw-r--r-- | drivers/infiniband/hw/mlx5/user.h | 2 | ||||
-rw-r--r-- | drivers/infiniband/hw/mthca/mthca_provider.c | 1 | ||||
-rw-r--r-- | drivers/infiniband/hw/nes/nes_verbs.c | 2 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_debugfs.c | 3 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_file_ops.c | 3 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_init.c | 25 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_mad.c | 2 | ||||
-rw-r--r-- | drivers/infiniband/hw/qib/qib_qp.c | 8 | ||||
-rw-r--r-- | drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 4 | ||||
-rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.c | 510 | ||||
-rw-r--r-- | drivers/infiniband/ulp/isert/ib_isert.h | 9 | ||||
-rw-r--r-- | drivers/infiniband/ulp/srp/ib_srp.c | 44 | ||||
-rw-r--r-- | drivers/infiniband/ulp/srpt/ib_srpt.c | 24 |
20 files changed, 546 insertions, 290 deletions
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index c47c203..4293e89 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -46,6 +46,7 @@ #include <linux/completion.h> #include <linux/slab.h> #include <linux/module.h> +#include <linux/sysctl.h> #include <rdma/iw_cm.h> #include <rdma/ib_addr.h> @@ -65,6 +66,20 @@ struct iwcm_work { struct list_head free_list; }; +static unsigned int default_backlog = 256; + +static struct ctl_table_header *iwcm_ctl_table_hdr; +static struct ctl_table iwcm_ctl_table[] = { + { + .procname = "default_backlog", + .data = &default_backlog, + .maxlen = sizeof(default_backlog), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + /* * The following services provide a mechanism for pre-allocating iwcm_work * elements. The design pre-allocates them based on the cm_id type: @@ -419,6 +434,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog) cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); + if (!backlog) + backlog = default_backlog; + ret = alloc_work_entries(cm_id_priv, backlog); if (ret) return ret; @@ -1024,11 +1042,20 @@ static int __init iw_cm_init(void) if (!iwcm_wq) return -ENOMEM; + iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm", + iwcm_ctl_table); + if (!iwcm_ctl_table_hdr) { + pr_err("iw_cm: couldn't register sysctl paths\n"); + destroy_workqueue(iwcm_wq); + return -ENOMEM; + } + return 0; } static void __exit iw_cm_cleanup(void) { + unregister_net_sysctl_table(iwcm_ctl_table_hdr); destroy_workqueue(iwcm_wq); } diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c index f0d588f..1acb991 100644 --- a/drivers/infiniband/core/user_mad.c +++ b/drivers/infiniband/core/user_mad.c @@ -98,7 +98,7 @@ struct ib_umad_port { struct ib_umad_device { int start_port, end_port; - struct kref ref; + struct kobject kobj; struct ib_umad_port port[0]; }; @@ -134,14 +134,18 @@ static DECLARE_BITMAP(dev_map, IB_UMAD_MAX_PORTS); static void ib_umad_add_one(struct ib_device *device); static void ib_umad_remove_one(struct ib_device *device); -static void ib_umad_release_dev(struct kref *ref) +static void ib_umad_release_dev(struct kobject *kobj) { struct ib_umad_device *dev = - container_of(ref, struct ib_umad_device, ref); + container_of(kobj, struct ib_umad_device, kobj); kfree(dev); } +static struct kobj_type ib_umad_dev_ktype = { + .release = ib_umad_release_dev, +}; + static int hdr_size(struct ib_umad_file *file) { return file->use_pkey_index ? sizeof (struct ib_user_mad_hdr) : @@ -780,27 +784,19 @@ static int ib_umad_open(struct inode *inode, struct file *filp) { struct ib_umad_port *port; struct ib_umad_file *file; - int ret; + int ret = -ENXIO; port = container_of(inode->i_cdev, struct ib_umad_port, cdev); - if (port) - kref_get(&port->umad_dev->ref); - else - return -ENXIO; mutex_lock(&port->file_mutex); - if (!port->ib_dev) { - ret = -ENXIO; + if (!port->ib_dev) goto out; - } + ret = -ENOMEM; file = kzalloc(sizeof *file, GFP_KERNEL); - if (!file) { - kref_put(&port->umad_dev->ref, ib_umad_release_dev); - ret = -ENOMEM; + if (!file) goto out; - } mutex_init(&file->mutex); spin_lock_init(&file->send_lock); @@ -814,6 +810,13 @@ static int ib_umad_open(struct inode *inode, struct file *filp) list_add_tail(&file->port_list, &port->file_list); ret = nonseekable_open(inode, filp); + if (ret) { + list_del(&file->port_list); + kfree(file); + goto out; + } + + kobject_get(&port->umad_dev->kobj); out: mutex_unlock(&port->file_mutex); @@ -852,7 +855,7 @@ static int ib_umad_close(struct inode *inode, struct file *filp) mutex_unlock(&file->port->file_mutex); kfree(file); - kref_put(&dev->ref, ib_umad_release_dev); + kobject_put(&dev->kobj); return 0; } @@ -880,10 +883,6 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp) int ret; port = container_of(inode->i_cdev, struct ib_umad_port, sm_cdev); - if (port) - kref_get(&port->umad_dev->ref); - else - return -ENXIO; if (filp->f_flags & O_NONBLOCK) { if (down_trylock(&port->sm_sem)) { @@ -898,17 +897,27 @@ static int ib_umad_sm_open(struct inode *inode, struct file *filp) } ret = ib_modify_port(port->ib_dev, port->port_num, 0, &props); - if (ret) { - up(&port->sm_sem); - goto fail; - } + if (ret) + goto err_up_sem; filp->private_data = port; - return nonseekable_open(inode, filp); + ret = nonseekable_open(inode, filp); + if (ret) + goto err_clr_sm_cap; + + kobject_get(&port->umad_dev->kobj); + + return 0; + +err_clr_sm_cap: + swap(props.set_port_cap_mask, props.clr_port_cap_mask); + ib_modify_port(port->ib_dev, port->port_num, 0, &props); + +err_up_sem: + up(&port->sm_sem); fail: - kref_put(&port->umad_dev->ref, ib_umad_release_dev); return ret; } @@ -927,7 +936,7 @@ static int ib_umad_sm_close(struct inode *inode, struct file *filp) up(&port->sm_sem); - kref_put(&port->umad_dev->ref, ib_umad_release_dev); + kobject_put(&port->umad_dev->kobj); return ret; } @@ -995,6 +1004,7 @@ static int find_overflow_devnum(void) } static int ib_umad_init_port(struct ib_device *device, int port_num, + struct ib_umad_device *umad_dev, struct ib_umad_port *port) { int devnum; @@ -1027,6 +1037,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num, cdev_init(&port->cdev, &umad_fops); port->cdev.owner = THIS_MODULE; + port->cdev.kobj.parent = &umad_dev->kobj; kobject_set_name(&port->cdev.kobj, "umad%d", port->dev_num); if (cdev_add(&port->cdev, base, 1)) goto err_cdev; @@ -1045,6 +1056,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num, base += IB_UMAD_MAX_PORTS; cdev_init(&port->sm_cdev, &umad_sm_fops); port->sm_cdev.owner = THIS_MODULE; + port->sm_cdev.kobj.parent = &umad_dev->kobj; kobject_set_name(&port->sm_cdev.kobj, "issm%d", port->dev_num); if (cdev_add(&port->sm_cdev, base, 1)) goto err_sm_cdev; @@ -1138,7 +1150,7 @@ static void ib_umad_add_one(struct ib_device *device) if (!umad_dev) return; - kref_init(&umad_dev->ref); + kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype); umad_dev->start_port = s; umad_dev->end_port = e; @@ -1146,7 +1158,8 @@ static void ib_umad_add_one(struct ib_device *device) for (i = s; i <= e; ++i) { umad_dev->port[i - s].umad_dev = umad_dev; - if (ib_umad_init_port(device, i, &umad_dev->port[i - s])) + if (ib_umad_init_port(device, i, umad_dev, + &umad_dev->port[i - s])) goto err; } @@ -1158,7 +1171,7 @@ err: while (--i >= s) ib_umad_kill_port(&umad_dev->port[i - s]); - kref_put(&umad_dev->ref, ib_umad_release_dev); + kobject_put(&umad_dev->kobj); } static void ib_umad_remove_one(struct ib_device *device) @@ -1172,7 +1185,7 @@ static void ib_umad_remove_one(struct ib_device *device) for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i) ib_umad_kill_port(&umad_dev->port[i]); - kref_put(&umad_dev->ref, ib_umad_release_dev); + kobject_put(&umad_dev->kobj); } static char *umad_devnode(struct device *dev, umode_t *mode) diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index 095bb04..cb78b1e 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -418,6 +418,7 @@ static int send_abort(struct iwch_ep *ep, struct sk_buff *skb, gfp_t gfp) skb->priority = CPL_PRIORITY_DATA; set_arp_failure_handler(skb, abort_arp_failure); req = (struct cpl_abort_req *) skb_put(skb, sizeof(*req)); + memset(req, 0, sizeof(*req)); req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_HOST_ABORT_CON_REQ)); req->wr.wr_lo = htonl(V_WR_TID(ep->hwtid)); OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_ABORT_REQ, ep->hwtid)); diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c index 212150c..8cc8375 100644 --- a/drivers/infiniband/hw/ehca/ehca_cq.c +++ b/drivers/infiniband/hw/ehca/ehca_cq.c @@ -283,6 +283,7 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector, (my_cq->galpas.user.fw_handle & (PAGE_SIZE - 1)); if (ib_copy_to_udata(udata, &resp, sizeof(resp))) { ehca_err(device, "Copy to udata failed."); + cq = ERR_PTR(-EFAULT); goto create_cq_exit4; } } diff --git a/drivers/infiniband/hw/ipath/ipath_diag.c b/drivers/infiniband/hw/ipath/ipath_diag.c index 714293b..45802e9 100644 --- a/drivers/infiniband/hw/ipath/ipath_diag.c +++ b/drivers/infiniband/hw/ipath/ipath_diag.c @@ -326,7 +326,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp, size_t count, loff_t *off) { u32 __iomem *piobuf; - u32 plen, clen, pbufn; + u32 plen, pbufn, maxlen_reserve; struct ipath_diag_pkt odp; struct ipath_diag_xpkt dp; u32 *tmpbuf = NULL; @@ -335,42 +335,24 @@ static ssize_t ipath_diagpkt_write(struct file *fp, u64 val; u32 l_state, lt_state; /* LinkState, LinkTrainingState */ - if (count < sizeof(odp)) { - ret = -EINVAL; - goto bail; - } if (count == sizeof(dp)) { if (copy_from_user(&dp, data, sizeof(dp))) { ret = -EFAULT; goto bail; } - } else if (copy_from_user(&odp, data, sizeof(odp))) { - ret = -EFAULT; - goto bail; - } - - /* - * Due to padding/alignment issues (lessened with new struct) - * the old and new structs are the same length. We need to - * disambiguate them, which we can do because odp.len has never - * been less than the total of LRH+BTH+DETH so far, while - * dp.unit (same offset) unit is unlikely to get that high. - * Similarly, dp.data, the pointer to user at the same offset - * as odp.unit, is almost certainly at least one (512byte)page - * "above" NULL. The if-block below can be omitted if compatibility - * between a new driver and older diagnostic code is unimportant. - * compatibility the other direction (new diags, old driver) is - * handled in the diagnostic code, with a warning. - */ - if (dp.unit >= 20 && dp.data < 512) { - /* very probable version mismatch. Fix it up */ - memcpy(&odp, &dp, sizeof(odp)); - /* We got a legacy dp, copy elements to dp */ + } else if (count == sizeof(odp)) { + if (copy_from_user(&odp, data, sizeof(odp))) { + ret = -EFAULT; + goto bail; + } + dp.len = odp.len; dp.unit = odp.unit; dp.data = odp.data; - dp.len = odp.len; - dp.pbc_wd = 0; /* Indicate we need to compute PBC wd */ + dp.pbc_wd = 0; + } else { + ret = -EINVAL; + goto bail; } /* send count must be an exact number of dwords */ @@ -379,7 +361,7 @@ static ssize_t ipath_diagpkt_write(struct file *fp, goto bail; } - clen = dp.len >> 2; + plen = dp.len >> 2; dd = ipath_lookup(dp.unit); if (!dd || !(dd->ipath_flags & IPATH_PRESENT) || @@ -422,16 +404,22 @@ static ssize_t ipath_diagpkt_write(struct file *fp, goto bail; } - /* need total length before first word written */ - /* +1 word is for the qword padding */ - plen = sizeof(u32) + dp.len; - - if ((plen + 4) > dd->ipath_ibmaxlen) { + /* + * need total length before first word written, plus 2 Dwords. One Dword + * is for padding so we get the full user data when not aligned on + * a word boundary. The other Dword is to make sure we have room for the + * ICRC which gets tacked on later. + */ + maxlen_reserve = 2 * sizeof(u32); + if (dp.len > dd->ipath_ibmaxlen - maxlen_reserve) { ipath_dbg("Pkt len 0x%x > ibmaxlen %x\n", - plen - 4, dd->ipath_ibmaxlen); + dp.len, dd->ipath_ibmaxlen); ret = -EINVAL; - goto bail; /* before writing pbc */ + goto bail; } + + plen = sizeof(u32) + dp.len; + tmpbuf = vmalloc(plen); if (!tmpbuf) { dev_info(&dd->pcidev->dev, "Unable to allocate tmp buffer, " @@ -473,11 +461,11 @@ static ssize_t ipath_diagpkt_write(struct file *fp, */ if (dd->ipath_flags & IPATH_PIO_FLUSH_WC) { ipath_flush_wc(); - __iowrite32_copy(piobuf + 2, tmpbuf, clen - 1); + __iowrite32_copy(piobuf + 2, tmpbuf, plen - 1); ipath_flush_wc(); - __raw_writel(tmpbuf[clen - 1], piobuf + clen + 1); + __raw_writel(tmpbuf[plen - 1], piobuf + plen + 1); } else - __iowrite32_copy(piobuf + 2, tmpbuf, clen); + __iowrite32_copy(piobuf + 2, tmpbuf, plen); ipath_flush_wc(); diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 344ab03..706833a 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" @@ -518,14 +519,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata, 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; diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c index 0aa478b..47a1f0a 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, diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h index a886de3..84fea5d 100644 --- a/drivers/infiniband/hw/mlx5/user.h +++ b/drivers/infiniband/hw/mlx5/user.h @@ -84,6 +84,7 @@ 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 { @@ -99,6 +100,7 @@ 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 { diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 5b71d43..42dde06 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -695,6 +695,7 @@ static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries, if (context && ib_copy_to_udata(udata, &cq->cqn, sizeof (__u32))) { mthca_free_cq(to_mdev(ibdev), cq); + err = -EFAULT; goto err_free; } diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c index 5b53ca5..09999cd 100644 --- a/drivers/infiniband/hw/nes/nes_verbs.c +++ b/drivers/infiniband/hw/nes/nes_verbs.c @@ -1186,7 +1186,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd, nes_free_resource(nesadapter, nesadapter->allocated_qps, qp_num); kfree(nesqp->allocated_buffer); nes_debug(NES_DBG_QP, "ib_copy_from_udata() Failed \n"); - return NULL; + return ERR_PTR(-EFAULT); } if (req.user_wqe_buffers) { virt_wqs = 1; diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 799a0c3..6abd3ed 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -193,6 +193,7 @@ static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) struct qib_qp_iter *iter; loff_t n = *pos; + rcu_read_lock(); iter = qib_qp_iter_init(s->private); if (!iter) return NULL; @@ -224,7 +225,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) { - /* nothing for now */ + rcu_read_unlock(); } static int _qp_stats_seq_show(struct seq_file *s, void *iter_ptr) diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 275f247..2023cd6 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1578,7 +1578,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp) struct qib_ctxtdata *rcd = fd->rcd; struct qib_devdata *dd = rcd->dd; - if (dd->flags & QIB_HAS_SEND_DMA) + if (dd->flags & QIB_HAS_SEND_DMA) { fd->pq = qib_user_sdma_queue_create(&dd->pcidev->dev, dd->unit, @@ -1586,6 +1586,7 @@ static int do_qib_user_sdma_queue_create(struct file *fp) fd->subctxt); if (!fd->pq) return -ENOMEM; + } return 0; } diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c index 24e802f..76c3e17 100644 --- a/drivers/infiniband/hw/qib/qib_init.c +++ b/drivers/infiniband/hw/qib/qib_init.c @@ -1097,14 +1097,10 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) int ret; dd = (struct qib_devdata *) ib_alloc_device(sizeof(*dd) + extra); - if (!dd) { - dd = ERR_PTR(-ENOMEM); - goto bail; - } + if (!dd) + return ERR_PTR(-ENOMEM); -#ifdef CONFIG_DEBUG_FS - qib_dbg_ibdev_init(&dd->verbs_dev); -#endif + INIT_LIST_HEAD(&dd->list); idr_preload(GFP_KERNEL); spin_lock_irqsave(&qib_devs_lock, flags); @@ -1121,11 +1117,6 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) if (ret < 0) { qib_early_err(&pdev->dev, "Could not allocate unit ID: error %d\n", -ret); -#ifdef CONFIG_DEBUG_FS - qib_dbg_ibdev_exit(&dd->verbs_dev); -#endif - ib_dealloc_device(&dd->verbs_dev.ibdev); - dd = ERR_PTR(ret); goto bail; } @@ -1139,9 +1130,15 @@ struct qib_devdata *qib_alloc_devdata(struct pci_dev *pdev, size_t extra) qib_early_err(&pdev->dev, "Could not alloc cpulist info, cpu affinity might be wrong\n"); } - -bail: +#ifdef CONFIG_DEBUG_FS + qib_dbg_ibdev_init(&dd->verbs_dev); +#endif return dd; +bail: + if (!list_empty(&dd->list)) + list_del_init(&dd->list); + ib_dealloc_device(&dd->verbs_dev.ibdev); + return ERR_PTR(ret);; } /* diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c index ccb1191..1dd9fcb 100644 --- a/drivers/infiniband/hw/qib/qib_mad.c +++ b/drivers/infiniband/hw/qib/qib_mad.c @@ -1028,7 +1028,7 @@ static int set_pkeys(struct qib_devdata *dd, u8 port, u16 *pkeys) event.event = IB_EVENT_PKEY_CHANGE; event.device = &dd->verbs_dev.ibdev; - event.element.port_num = 1; + event.element.port_num = port; ib_dispatch_event(&event); } return 0; diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 3cca55b..2c018ba 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -1324,7 +1324,6 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) struct qib_qp *pqp = iter->qp; struct qib_qp *qp; - rcu_read_lock(); for (; n < dev->qp_table_size; n++) { if (pqp) qp = rcu_dereference(pqp->next); @@ -1332,18 +1331,11 @@ int qib_qp_iter_next(struct qib_qp_iter *iter) qp = rcu_dereference(dev->qp_table[n]); pqp = qp; if (qp) { - if (iter->qp) - atomic_dec(&iter->qp->refcount); - atomic_inc(&qp->refcount); - rcu_read_unlock(); iter->qp = qp; iter->n = n; return 0; } } - rcu_read_unlock(); - if (iter->qp) - atomic_dec(&iter->qp->refcount); return ret; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 3800ef5..cecb98a 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -783,7 +783,7 @@ void ipoib_mcast_restart_task(struct work_struct *work) ipoib_mcast_stop_thread(dev, 0); - local_irq_save_nort(flags); + local_irq_save(flags); netif_addr_lock(dev); spin_lock(&priv->lock); @@ -865,7 +865,7 @@ void ipoib_mcast_restart_task(struct work_struct *work) spin_unlock(&priv->lock); netif_addr_unlock(dev); - local_irq_restore_nort(flags); + local_irq_restore(flags); /* We have to cancel outside of the spinlock */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 09c7129..60a3ed9 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -27,6 +27,7 @@ #include <target/target_core_base.h> #include <target/target_core_fabric.h> #include <target/iscsi/iscsi_transport.h> +#include <linux/semaphore.h> #include "isert_proto.h" #include "ib_isert.h" @@ -39,6 +40,7 @@ static DEFINE_MUTEX(device_list_mutex); static LIST_HEAD(device_list); static struct workqueue_struct *isert_rx_wq; static struct workqueue_struct *isert_comp_wq; +static struct workqueue_struct *isert_release_wq; static void isert_unmap_cmd(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn); @@ -50,6 +52,11 @@ isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn static int isert_reg_rdma_frwr(struct iscsi_conn *conn, struct iscsi_cmd *cmd, struct isert_rdma_wr *wr); +static int +isert_rdma_post_recvl(struct isert_conn *isert_conn); +static int +isert_rdma_accept(struct isert_conn *isert_conn); +struct rdma_cm_id *isert_setup_id(struct isert_np *isert_np); static void isert_qp_event_callback(struct ib_event *e, void *context) @@ -110,9 +117,12 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) attr.cap.max_recv_wr = ISERT_QP_MAX_RECV_DTOS; /* * FIXME: Use devattr.max_sge - 2 for max_send_sge as - * work-around for RDMA_READ.. + * work-around for RDMA_READs with ConnectX-2. + * + * Also, still make sure to have at least two SGEs for + * outgoing control PDU responses. */ - attr.cap.max_send_sge = device->dev_attr.max_sge - 2; + attr.cap.max_send_sge = max(2, device->dev_attr.max_sge - 2); isert_conn->max_sge = attr.cap.max_send_sge; attr.cap.max_recv_sge = 1; @@ -127,12 +137,18 @@ isert_conn_setup_qp(struct isert_conn *isert_conn, struct rdma_cm_id *cma_id) ret = rdma_create_qp(cma_id, isert_conn->conn_pd, &attr); if (ret) { pr_err("rdma_create_qp failed for cma_id %d\n", ret); - return ret; + goto err; } isert_conn->conn_qp = cma_id->qp; pr_debug("rdma_create_qp() returned success >>>>>>>>>>>>>>>>>>>>>>>>>.\n"); return 0; +err: + mutex_lock(&device_list_mutex); + device->cq_active_qps[min_index]--; + mutex_unlock(&device_list_mutex); + + return ret; } static void @@ -218,12 +234,16 @@ isert_create_device_ib_res(struct isert_device *device) struct isert_cq_desc *cq_desc; struct ib_device_attr *dev_attr; int ret = 0, i, j; + int max_rx_cqe, max_tx_cqe; dev_attr = &device->dev_attr; ret = isert_query_device(ib_dev, dev_attr); if (ret) return ret; + max_rx_cqe = min(ISER_MAX_RX_CQ_LEN, dev_attr->max_cqe); + max_tx_cqe = min(ISER_MAX_TX_CQ_LEN, dev_attr->max_cqe); + /* asign function handlers */ if (dev_attr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { device->use_frwr = 1; @@ -265,7 +285,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_rx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_RX_CQ_LEN, i); + max_rx_cqe, i); if (IS_ERR(device->dev_rx_cq[i])) { ret = PTR_ERR(device->dev_rx_cq[i]); device->dev_rx_cq[i] = NULL; @@ -277,7 +297,7 @@ isert_create_device_ib_res(struct isert_device *device) isert_cq_tx_callback, isert_cq_event_callback, (void *)&cq_desc[i], - ISER_MAX_TX_CQ_LEN, i); + max_tx_cqe, i); if (IS_ERR(device->dev_tx_cq[i])) { ret = PTR_ERR(device->dev_tx_cq[i]); device->dev_tx_cq[i] = NULL; @@ -426,11 +446,18 @@ isert_conn_create_frwr_pool(struct isert_conn *isert_conn) { struct fast_reg_descriptor *fr_desc; struct isert_device *device = isert_conn->conn_device; - int i, ret; + struct se_session *se_sess = isert_conn->conn->sess->se_sess; + struct se_node_acl *se_nacl = se_sess->se_node_acl; + int i, ret, tag_num; + /* + * Setup the number of FRMRs based upon the number of tags + * available to session in iscsi_target_locate_portal(). + */ + tag_num = max_t(u32, ISCSIT_MIN_TAGS, se_nacl->queue_depth); + tag_num = (tag_num * 2) + ISCSIT_EXTRA_TAGS; - INIT_LIST_HEAD(&isert_conn->conn_frwr_pool); isert_conn->conn_frwr_pool_size = 0; - for (i = 0; i < ISCSI_DEF_XMIT_CMDS_MAX; i++) { + for (i = 0; i < tag_num; i++) { fr_desc = kzalloc(sizeof(*fr_desc), GFP_KERNEL); if (!fr_desc) { pr_err("Failed to allocate fast_reg descriptor\n"); @@ -478,13 +505,21 @@ err: static int isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { - struct iscsi_np *np = cma_id->context; - struct isert_np *isert_np = np->np_context; + struct isert_np *isert_np = cma_id->context; + struct iscsi_np *np = isert_np->np; struct isert_conn *isert_conn; struct isert_device *device; struct ib_device *ib_dev = cma_id->device; int ret = 0; + spin_lock_bh(&np->np_thread_lock); + if (!np->enabled) { + spin_unlock_bh(&np->np_thread_lock); + pr_debug("iscsi_np is not enabled, reject connect request\n"); + return rdma_reject(cma_id, NULL, 0); + } + spin_unlock_bh(&np->np_thread_lock); + pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n", cma_id, cma_id->context); @@ -496,14 +531,14 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->state = ISER_CONN_INIT; INIT_LIST_HEAD(&isert_conn->conn_accept_node); init_completion(&isert_conn->conn_login_comp); + init_completion(&isert_conn->login_req_comp); init_completion(&isert_conn->conn_wait); init_completion(&isert_conn->conn_wait_comp_err); kref_init(&isert_conn->conn_kref); - kref_get(&isert_conn->conn_kref); mutex_init(&isert_conn->conn_mutex); spin_lock_init(&isert_conn->conn_lock); + INIT_LIST_HEAD(&isert_conn->conn_frwr_pool); - cma_id->context = isert_conn; isert_conn->conn_cm_id = cma_id; isert_conn->responder_resources = event->param.conn.responder_resources; isert_conn->initiator_depth = event->param.conn.initiator_depth; @@ -559,30 +594,27 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) isert_conn->conn_pd = device->dev_pd; isert_conn->conn_mr = device->dev_mr; - if (device->use_frwr) { - ret = isert_conn_create_frwr_pool(isert_conn); - if (ret) { - pr_err("Conn: %p failed to create frwr_pool\n", isert_conn); - goto out_frwr; - } - } - ret = isert_conn_setup_qp(isert_conn, cma_id); if (ret) goto out_conn_dev; + ret = isert_rdma_post_recvl(isert_conn); + if (ret) + goto out_conn_dev; + + ret = isert_rdma_accept(isert_conn); + if (ret) + goto out_conn_dev; + mutex_lock(&isert_np->np_accept_mutex); - list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node); + list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list); mutex_unlock(&isert_np->np_accept_mutex); - pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np); - wake_up(&isert_np->np_accept_wq); + pr_debug("isert_connect_request() up np_sem np: %p\n", np); + up(&isert_np->np_sem); return 0; out_conn_dev: - if (device->use_frwr) - isert_conn_free_frwr_pool(isert_conn); -out_frwr: isert_device_try_release(device); out_rsp_dma_map: ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma, @@ -594,6 +626,7 @@ out_login_buf: kfree(isert_conn->login_buf); out: kfree(isert_conn); + rdma_reject(cma_id, NULL, 0); return ret; } @@ -609,18 +642,20 @@ isert_connect_release(struct isert_conn *isert_conn) if (device && device->use_frwr) isert_conn_free_frwr_pool(isert_conn); + isert_free_rx_descriptors(isert_conn); + rdma_destroy_id(isert_conn->conn_cm_id); + if (isert_conn->conn_qp) { cq_index = ((struct isert_cq_desc *) isert_conn->conn_qp->recv_cq->cq_context)->cq_index; pr_debug("isert_connect_release: cq_index: %d\n", cq_index); + mutex_lock(&device_list_mutex); isert_conn->conn_device->cq_active_qps[cq_index]--; + mutex_unlock(&device_list_mutex); - rdma_destroy_qp(isert_conn->conn_cm_id); + ib_destroy_qp(isert_conn->conn_qp); } - isert_free_rx_descriptors(isert_conn); - rdma_destroy_id(isert_conn->conn_cm_id); - if (isert_conn->login_buf) { ib_dma_unmap_single(ib_dev, isert_conn->login_rsp_dma, ISER_RX_LOGIN_SIZE, DMA_TO_DEVICE); @@ -640,7 +675,19 @@ isert_connect_release(struct isert_conn *isert_conn) static void isert_connected_handler(struct rdma_cm_id *cma_id) { - return; + struct isert_conn *isert_conn = cma_id->qp->qp_context; + + pr_info("conn %p\n", isert_conn); + + if (!kref_get_unless_zero(&isert_conn->conn_kref)) { + pr_warn("conn %p connect_release is running\n", isert_conn); + return; + } + + mutex_lock(&isert_conn->conn_mutex); + if (isert_conn->state != ISER_CONN_FULL_FEATURE) + isert_conn->state = ISER_CONN_UP; + mutex_unlock(&isert_conn->conn_mutex); } static void @@ -661,49 +708,102 @@ isert_put_conn(struct isert_conn *isert_conn) kref_put(&isert_conn->conn_kref, isert_release_conn_kref); } +/** + * isert_conn_terminate() - Initiate connection termination + * @isert_conn: isert connection struct + * + * Notes: + * In case the connection state is FULL_FEATURE, move state + * to TEMINATING and start teardown sequence (rdma_disconnect). + * In case the connection state is UP, complete flush as well. + * + * This routine must be called with conn_mutex held. Thus it is + * safe to call multiple times. + */ static void -isert_disconnect_work(struct work_struct *work) +isert_conn_terminate(struct isert_conn *isert_conn) { - struct isert_conn *isert_conn = container_of(work, - struct isert_conn, conn_logout_work); + int err; - pr_debug("isert_disconnect_work(): >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>\n"); - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->state == ISER_CONN_UP) + switch (isert_conn->state) { + case ISER_CONN_TERMINATING: + break; + case ISER_CONN_UP: + /* + * No flush completions will occur as we didn't + * get to ISER_CONN_FULL_FEATURE yet, complete + * to allow teardown progress. + */ + complete(&isert_conn->conn_wait_comp_err); + case ISER_CONN_FULL_FEATURE: /* FALLTHRU */ + pr_info("Terminating conn %p state %d\n", + isert_conn, isert_conn->state); isert_conn->state = ISER_CONN_TERMINATING; - - if (isert_conn->post_recv_buf_count == 0 && - atomic_read(&isert_conn->post_send_buf_count) == 0) { - mutex_unlock(&isert_conn->conn_mutex); - goto wake_up; - } - if (!isert_conn->conn_cm_id) { - mutex_unlock(&isert_conn->conn_mutex); - isert_put_conn(isert_conn); - return; + err = rdma_disconnect(isert_conn->conn_cm_id); + if (err) + pr_warn("Failed rdma_disconnect isert_conn %p\n", + isert_conn); + break; + default: + pr_warn("conn %p teminating in state %d\n", + isert_conn, isert_conn->state); } - if (!isert_conn->logout_posted) { - pr_debug("Calling rdma_disconnect for !logout_posted from" - " isert_disconnect_work\n"); - rdma_disconnect(isert_conn->conn_cm_id); - mutex_unlock(&isert_conn->conn_mutex); - iscsit_cause_connection_reinstatement(isert_conn->conn, 0); - goto wake_up; +} + +static int +isert_np_cma_handler(struct isert_np *isert_np, + enum rdma_cm_event_type event) +{ + pr_debug("isert np %p, handling event %d\n", isert_np, event); + + switch (event) { + case RDMA_CM_EVENT_DEVICE_REMOVAL: + isert_np->np_cm_id = NULL; + break; + case RDMA_CM_EVENT_ADDR_CHANGE: + isert_np->np_cm_id = isert_setup_id(isert_np); + if (IS_ERR(isert_np->np_cm_id)) { + pr_err("isert np %p setup id failed: %ld\n", + isert_np, PTR_ERR(isert_np->np_cm_id)); + isert_np->np_cm_id = NULL; + } + break; + default: + pr_err("isert np %p Unexpected event %d\n", + isert_np, event); } + + return -1; +} + +static int +isert_disconnected_handler(struct rdma_cm_id *cma_id, + enum rdma_cm_event_type event) +{ + struct isert_np *isert_np = cma_id->context; + struct isert_conn *isert_conn; + + if (isert_np->np_cm_id == cma_id) + return isert_np_cma_handler(cma_id->context, event); + + isert_conn = cma_id->qp->qp_context; + + mutex_lock(&isert_conn->conn_mutex); + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); -wake_up: + pr_info("conn %p completing conn_wait\n", isert_conn); complete(&isert_conn->conn_wait); - isert_put_conn(isert_conn); + + return 0; } static void -isert_disconnected_handler(struct rdma_cm_id *cma_id) +isert_connect_error(struct rdma_cm_id *cma_id) { - struct isert_conn *isert_conn = (struct isert_conn *)cma_id->context; + struct isert_conn *isert_conn = cma_id->qp->qp_context; - INIT_WORK(&isert_conn->conn_logout_work, isert_disconnect_work); - schedule_work(&isert_conn->conn_logout_work); + isert_put_conn(isert_conn); } static int @@ -716,32 +816,30 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: - pr_debug("RDMA_CM_EVENT_CONNECT_REQUEST: >>>>>>>>>>>>>>>\n"); ret = isert_connect_request(cma_id, event); + if (ret) + pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", + event->event, ret); break; case RDMA_CM_EVENT_ESTABLISHED: - pr_debug("RDMA_CM_EVENT_ESTABLISHED >>>>>>>>>>>>>>\n"); isert_connected_handler(cma_id); break; - case RDMA_CM_EVENT_DISCONNECTED: - pr_debug("RDMA_CM_EVENT_DISCONNECTED: >>>>>>>>>>>>>>\n"); - isert_disconnected_handler(cma_id); - break; - case RDMA_CM_EVENT_DEVICE_REMOVAL: - case RDMA_CM_EVENT_ADDR_CHANGE: + case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */ + case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */ + case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */ + ret = isert_disconnected_handler(cma_id, event->event); break; + case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */ + case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */ case RDMA_CM_EVENT_CONNECT_ERROR: + isert_connect_error(cma_id); + break; default: - pr_err("Unknown RDMA CMA event: %d\n", event->event); + pr_err("Unhandled RDMA CMA event: %d\n", event->event); break; } - if (ret != 0) { - pr_err("isert_cma_handler failed RDMA_CM_EVENT: 0x%08x %d\n", - event->event, ret); - dump_stack(); - } - return ret; } @@ -930,6 +1028,15 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, } if (!login->login_failed) { if (login->login_complete) { + if (isert_conn->conn_device->use_frwr) { + ret = isert_conn_create_frwr_pool(isert_conn); + if (ret) { + pr_err("Conn: %p failed to create" + " frwr_pool\n", isert_conn); + return ret; + } + } + ret = isert_alloc_rx_descriptors(isert_conn); if (ret) return ret; @@ -938,7 +1045,10 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login, if (ret) return ret; - isert_conn->state = ISER_CONN_UP; + /* Now we are in FULL_FEATURE phase */ + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_FULL_FEATURE; + mutex_unlock(&isert_conn->conn_mutex); goto post_send; } @@ -955,18 +1065,17 @@ post_send: } static void -isert_rx_login_req(struct iser_rx_desc *rx_desc, int rx_buflen, - struct isert_conn *isert_conn) +isert_rx_login_req(struct isert_conn *isert_conn) { + struct iser_rx_desc *rx_desc = (void *)isert_conn->login_req_buf; + int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; int size; - if (!login) { - pr_err("conn->conn_login is NULL\n"); - dump_stack(); - return; - } + pr_info("conn %p\n", isert_conn); + + WARN_ON_ONCE(!login); if (login->first_request) { struct iscsi_login_req *login_req = @@ -1074,6 +1183,8 @@ sequence_cmd: if (!rc && dump_payload == false && unsol_data) iscsit_set_unsoliticed_dataout(cmd); + else if (dump_payload && imm_data) + target_put_sess_cmd(conn->sess->se_sess, &cmd->se_cmd); return 0; } @@ -1327,11 +1438,20 @@ isert_rx_completion(struct iser_rx_desc *desc, struct isert_conn *isert_conn, hdr->opcode, hdr->itt, hdr->flags, (int)(xfer_len - ISER_HEADERS_LEN)); - if ((char *)desc == isert_conn->login_req_buf) - isert_rx_login_req(desc, xfer_len - ISER_HEADERS_LEN, - isert_conn); - else + if ((char *)desc == isert_conn->login_req_buf) { + isert_conn->login_req_len = xfer_len - ISER_HEADERS_LEN; + if (isert_conn->conn) { + struct iscsi_login *login = isert_conn->conn->conn_login; + + if (login && !login->first_request) + isert_rx_login_req(isert_conn); + } + mutex_lock(&isert_conn->conn_mutex); + complete(&isert_conn->login_req_comp); + mutex_unlock(&isert_conn->conn_mutex); + } else { isert_rx_do_work(desc, isert_conn); + } ib_dma_sync_single_for_device(ib_dev, rx_dma, rx_buflen, DMA_FROM_DEVICE); @@ -1414,7 +1534,7 @@ isert_unreg_rdma_frwr(struct isert_cmd *isert_cmd, struct isert_conn *isert_conn } static void -isert_put_cmd(struct isert_cmd *isert_cmd) +isert_put_cmd(struct isert_cmd *isert_cmd, bool comp_err) { struct iscsi_cmd *cmd = isert_cmd->iscsi_cmd; struct isert_conn *isert_conn = isert_cmd->conn; @@ -1430,8 +1550,21 @@ isert_put_cmd(struct isert_cmd *isert_cmd) list_del_init(&cmd->i_conn_node); spin_unlock_bh(&conn->cmd_lock); - if (cmd->data_direction == DMA_TO_DEVICE) + if (cmd->data_direction == DMA_TO_DEVICE) { iscsit_stop_dataout_timer(cmd); + /* + * Check for special case during comp_err where + * WRITE_PENDING has been handed off from core, + * but requires an extra target_put_sess_cmd() + * before transport_generic_free_cmd() below. + */ + if (comp_err && + cmd->se_cmd.t_state == TRANSPORT_WRITE_PENDING) { + struct se_cmd *se_cmd = &cmd->se_cmd; + + target_put_sess_cmd(se_cmd->se_sess, se_cmd); + } + } device->unreg_rdma_mem(isert_cmd, isert_conn); transport_generic_free_cmd(&cmd->se_cmd, 0); @@ -1486,7 +1619,7 @@ isert_unmap_tx_desc(struct iser_tx_desc *tx_desc, struct ib_device *ib_dev) static void isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd, - struct ib_device *ib_dev) + struct ib_device *ib_dev, bool comp_err) { if (isert_cmd->pdu_buf_dma != 0) { pr_debug("Calling ib_dma_unmap_single for isert_cmd->pdu_buf_dma\n"); @@ -1496,7 +1629,7 @@ isert_completion_put(struct iser_tx_desc *tx_desc, struct isert_cmd *isert_cmd, } isert_unmap_tx_desc(tx_desc, ib_dev); - isert_put_cmd(isert_cmd); + isert_put_cmd(isert_cmd, comp_err); } static void @@ -1540,28 +1673,25 @@ isert_do_control_comp(struct work_struct *work) iscsit_tmr_post_handler(cmd, cmd->conn); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; case ISTATE_SEND_REJECT: pr_debug("Got isert_do_control_comp ISTATE_SEND_REJECT: >>>\n"); atomic_dec(&isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; case ISTATE_SEND_LOGOUTRSP: pr_debug("Calling iscsit_logout_post_handler >>>>>>>>>>>>>>\n"); - /* - * Call atomic_dec(&isert_conn->post_send_buf_count) - * from isert_wait_conn() - */ - isert_conn->logout_posted = true; + + atomic_dec(&isert_conn->post_send_buf_count); iscsit_logout_post_handler(cmd, cmd->conn); break; case ISTATE_SEND_TEXTRSP: atomic_dec(&isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev); + isert_completion_put(&isert_cmd->tx_desc, isert_cmd, ib_dev, false); break; default: pr_err("Unknown do_control_comp i_state %d\n", cmd->i_state); @@ -1592,7 +1722,7 @@ isert_response_completion(struct iser_tx_desc *tx_desc, atomic_sub(wr->send_wr_num + 1, &isert_conn->post_send_buf_count); cmd->i_state = ISTATE_SENT_STATUS; - isert_completion_put(tx_desc, isert_cmd, ib_dev); + isert_completion_put(tx_desc, isert_cmd, ib_dev, false); } static void @@ -1646,7 +1776,7 @@ isert_cq_tx_comp_err(struct iser_tx_desc *tx_desc, struct isert_conn *isert_conn if (!isert_cmd) isert_unmap_tx_desc(tx_desc, ib_dev); else - isert_completion_put(tx_desc, isert_cmd, ib_dev); + isert_completion_put(tx_desc, isert_cmd, ib_dev, true); } static void @@ -1666,9 +1796,11 @@ isert_cq_rx_comp_err(struct isert_conn *isert_conn) msleep(3000); mutex_lock(&isert_conn->conn_mutex); - isert_conn->state = ISER_CONN_DOWN; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); + iscsit_cause_connection_reinstatement(isert_conn->conn, 0); + complete(&isert_conn->conn_wait_comp_err); } @@ -1922,7 +2054,7 @@ isert_put_text_rsp(struct iscsi_cmd *cmd, struct iscsi_conn *conn) int rc; isert_create_send_desc(isert_conn, isert_cmd, &isert_cmd->tx_desc); - rc = iscsit_build_text_rsp(cmd, conn, hdr); + rc = iscsit_build_text_rsp(cmd, conn, hdr, ISCSI_INFINIBAND); if (rc < 0) return rc; @@ -2444,13 +2576,51 @@ isert_response_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state) return ret; } +struct rdma_cm_id * +isert_setup_id(struct isert_np *isert_np) +{ + struct iscsi_np *np = isert_np->np; + struct rdma_cm_id *id; + struct sockaddr *sa; + int ret; + + sa = (struct sockaddr *)&np->np_sockaddr; + pr_debug("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa); + + id = rdma_create_id(isert_cma_handler, isert_np, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(id)) { + pr_err("rdma_create_id() failed: %ld\n", PTR_ERR(id)); + ret = PTR_ERR(id); + goto out; + } + pr_debug("id %p context %p\n", id, id->context); + + ret = rdma_bind_addr(id, sa); + if (ret) { + pr_err("rdma_bind_addr() failed: %d\n", ret); + goto out_id; + } + + ret = rdma_listen(id, ISERT_RDMA_LISTEN_BACKLOG); + if (ret) { + pr_err("rdma_listen() failed: %d\n", ret); + goto out_id; + } + + return id; +out_id: + rdma_destroy_id(id); +out: + return ERR_PTR(ret); +} + static int isert_setup_np(struct iscsi_np *np, struct __kernel_sockaddr_storage *ksockaddr) { struct isert_np *isert_np; struct rdma_cm_id *isert_lid; - struct sockaddr *sa; int ret; isert_np = kzalloc(sizeof(struct isert_np), GFP_KERNEL); @@ -2458,13 +2628,12 @@ isert_setup_np(struct iscsi_np *np, pr_err("Unable to allocate struct isert_np\n"); return -ENOMEM; } - init_waitqueue_head(&isert_np->np_accept_wq); + sema_init(&isert_np->np_sem, 0); mutex_init(&isert_np->np_accept_mutex); INIT_LIST_HEAD(&isert_np->np_accept_list); init_completion(&isert_np->np_login_comp); + isert_np->np = np; - sa = (struct sockaddr *)ksockaddr; - pr_debug("ksockaddr: %p, sa: %p\n", ksockaddr, sa); /* * Setup the np->np_sockaddr from the passed sockaddr setup * in iscsi_target_configfs.c code.. @@ -2472,50 +2641,21 @@ isert_setup_np(struct iscsi_np *np, memcpy(&np->np_sockaddr, ksockaddr, sizeof(struct __kernel_sockaddr_storage)); - isert_lid = rdma_create_id(isert_cma_handler, np, RDMA_PS_TCP, - IB_QPT_RC); + isert_lid = isert_setup_id(isert_np); if (IS_ERR(isert_lid)) { - pr_err("rdma_create_id() for isert_listen_handler failed: %ld\n", - PTR_ERR(isert_lid)); ret = PTR_ERR(isert_lid); goto out; } - ret = rdma_bind_addr(isert_lid, sa); - if (ret) { - pr_err("rdma_bind_addr() for isert_lid failed: %d\n", ret); - goto out_lid; - } - - ret = rdma_listen(isert_lid, ISERT_RDMA_LISTEN_BACKLOG); - if (ret) { - pr_err("rdma_listen() for isert_lid failed: %d\n", ret); - goto out_lid; - } - isert_np->np_cm_id = isert_lid; np->np_context = isert_np; - pr_debug("Setup isert_lid->context: %p\n", isert_lid->context); return 0; -out_lid: - rdma_destroy_id(isert_lid); out: kfree(isert_np); - return ret; -} -static int -isert_check_accept_queue(struct isert_np *isert_np) -{ - int empty; - - mutex_lock(&isert_np->np_accept_mutex); - empty = list_empty(&isert_np->np_accept_list); - mutex_unlock(&isert_np->np_accept_mutex); - - return empty; + return ret; } static int @@ -2550,7 +2690,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) struct isert_conn *isert_conn = (struct isert_conn *)conn->context; int ret; - pr_debug("isert_get_login_rx before conn_login_comp conn: %p\n", conn); + pr_info("before login_req comp conn: %p\n", isert_conn); + ret = wait_for_completion_interruptible(&isert_conn->login_req_comp); + if (ret) { + pr_err("isert_conn %p interrupted before got login req\n", + isert_conn); + return ret; + } + INIT_COMPLETION(isert_conn->login_req_comp); + /* * For login requests after the first PDU, isert_rx_login_req() will * kick schedule_delayed_work(&conn->login_work) as the packet is @@ -2560,11 +2708,15 @@ isert_get_login_rx(struct iscsi_conn *conn, struct iscsi_login *login) if (!login->first_request) return 0; + isert_rx_login_req(isert_conn); + + pr_info("before conn_login_comp conn: %p\n", conn); ret = wait_for_completion_interruptible(&isert_conn->conn_login_comp); if (ret) return ret; - pr_debug("isert_get_login_rx processing login->req: %p\n", login->req); + pr_info("processing login->req: %p\n", login->req); + return 0; } @@ -2610,16 +2762,19 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn) int max_accept = 0, ret; accept_wait: - ret = wait_event_interruptible(isert_np->np_accept_wq, - !isert_check_accept_queue(isert_np) || - np->np_thread_state == ISCSI_NP_THREAD_RESET); + ret = down_interruptible(&isert_np->np_sem); if (max_accept > 5) return -ENODEV; spin_lock_bh(&np->np_thread_lock); - if (np->np_thread_state == ISCSI_NP_THREAD_RESET) { + if (np->np_thread_state >= ISCSI_NP_THREAD_RESET) { spin_unlock_bh(&np->np_thread_lock); - pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n"); + pr_debug("np_thread_state %d for isert_accept_np\n", + np->np_thread_state); + /** + * No point in stalling here when np_thread + * is in state RESET/SHUTDOWN/EXIT - bail + **/ return -ENODEV; } spin_unlock_bh(&np->np_thread_lock); @@ -2639,17 +2794,10 @@ accept_wait: isert_conn->conn = conn; max_accept = 0; - ret = isert_rdma_post_recvl(isert_conn); - if (ret) - return ret; - - ret = isert_rdma_accept(isert_conn); - if (ret) - return ret; - isert_set_conn_info(np, conn, isert_conn); - pr_debug("Processing isert_accept_np: isert_conn: %p\n", isert_conn); + pr_debug("Processing isert_conn: %p\n", isert_conn); + return 0; } @@ -2658,29 +2806,38 @@ isert_free_np(struct iscsi_np *np) { struct isert_np *isert_np = (struct isert_np *)np->np_context; - rdma_destroy_id(isert_np->np_cm_id); + if (isert_np->np_cm_id) + rdma_destroy_id(isert_np->np_cm_id); np->np_context = NULL; kfree(isert_np); } +static void isert_release_work(struct work_struct *work) +{ + struct isert_conn *isert_conn = container_of(work, + struct isert_conn, + release_work); + + pr_info("Starting release conn %p\n", isert_conn); + + wait_for_completion(&isert_conn->conn_wait); + + mutex_lock(&isert_conn->conn_mutex); + isert_conn->state = ISER_CONN_DOWN; + mutex_unlock(&isert_conn->conn_mutex); + + pr_info("Destroying conn %p\n", isert_conn); + isert_put_conn(isert_conn); +} + static void isert_wait_conn(struct iscsi_conn *conn) { struct isert_conn *isert_conn = conn->context; pr_debug("isert_wait_conn: Starting \n"); - /* - * Decrement post_send_buf_count for special case when called - * from isert_do_control_comp() -> iscsit_logout_post_handler() - */ - mutex_lock(&isert_conn->conn_mutex); - if (isert_conn->logout_posted) - atomic_dec(&isert_conn->post_send_buf_count); - if (isert_conn->conn_cm_id && isert_conn->state != ISER_CONN_DOWN) { - pr_debug("Calling rdma_disconnect from isert_wait_conn\n"); - rdma_disconnect(isert_conn->conn_cm_id); - } + mutex_lock(&isert_conn->conn_mutex); /* * Only wait for conn_wait_comp_err if the isert_conn made it * into full feature phase.. @@ -2689,13 +2846,13 @@ static void isert_wait_conn(struct iscsi_conn *conn) mutex_unlock(&isert_conn->conn_mutex); return; } - if (isert_conn->state == ISER_CONN_UP) - isert_conn->state = ISER_CONN_TERMINATING; + isert_conn_terminate(isert_conn); mutex_unlock(&isert_conn->conn_mutex); wait_for_completion(&isert_conn->conn_wait_comp_err); - wait_for_completion(&isert_conn->conn_wait); + INIT_WORK(&isert_conn->release_work, isert_release_work); + queue_work(isert_release_wq, &isert_conn->release_work); } static void isert_free_conn(struct iscsi_conn *conn) @@ -2741,10 +2898,21 @@ static int __init isert_init(void) goto destroy_rx_wq; } + isert_release_wq = alloc_workqueue("isert_release_wq", WQ_UNBOUND, + WQ_UNBOUND_MAX_ACTIVE); + if (!isert_release_wq) { + pr_err("Unable to allocate isert_release_wq\n"); + ret = -ENOMEM; + goto destroy_comp_wq; + } + iscsit_register_transport(&iser_target_transport); - pr_debug("iSER_TARGET[0] - Loaded iser_target_transport\n"); + pr_info("iSER_TARGET[0] - Loaded iser_target_transport\n"); + return 0; +destroy_comp_wq: + destroy_workqueue(isert_comp_wq); destroy_rx_wq: destroy_workqueue(isert_rx_wq); return ret; @@ -2752,6 +2920,8 @@ destroy_rx_wq: static void __exit isert_exit(void) { + flush_scheduled_work(); + destroy_workqueue(isert_release_wq); destroy_workqueue(isert_comp_wq); destroy_workqueue(isert_rx_wq); iscsit_unregister_transport(&iser_target_transport); diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h index 52f4bf0..1ea5279 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -23,6 +23,7 @@ enum iser_ib_op_code { enum iser_conn_state { ISER_CONN_INIT, ISER_CONN_UP, + ISER_CONN_FULL_FEATURE, ISER_CONN_TERMINATING, ISER_CONN_DOWN, }; @@ -90,7 +91,6 @@ struct isert_device; struct isert_conn { enum iser_conn_state state; - bool logout_posted; int post_recv_buf_count; atomic_t post_send_buf_count; u32 responder_resources; @@ -100,6 +100,7 @@ struct isert_conn { char *login_req_buf; char *login_rsp_buf; u64 login_req_dma; + int login_req_len; u64 login_rsp_dma; unsigned int conn_rx_desc_head; struct iser_rx_desc *conn_rx_descs; @@ -107,13 +108,13 @@ struct isert_conn { struct iscsi_conn *conn; struct list_head conn_accept_node; struct completion conn_login_comp; + struct completion login_req_comp; struct iser_tx_desc conn_login_tx_desc; struct rdma_cm_id *conn_cm_id; struct ib_pd *conn_pd; struct ib_mr *conn_mr; struct ib_qp *conn_qp; struct isert_device *conn_device; - struct work_struct conn_logout_work; struct mutex conn_mutex; struct completion conn_wait; struct completion conn_wait_comp_err; @@ -122,6 +123,7 @@ struct isert_conn { int conn_frwr_pool_size; /* lock to protect frwr_pool */ spinlock_t conn_lock; + struct work_struct release_work; }; #define ISERT_MAX_CQ 64 @@ -154,7 +156,8 @@ struct isert_device { }; struct isert_np { - wait_queue_head_t np_accept_wq; + struct iscsi_np *np; + struct semaphore np_sem; struct rdma_cm_id *np_cm_id; struct mutex np_accept_mutex; struct list_head np_accept_list; diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 17b58f4..15984e1 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -93,6 +93,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr); static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event); static struct scsi_transport_template *ib_srp_transport_template; +static struct workqueue_struct *srp_remove_wq; static struct ib_client srp_client = { .name = "srp", @@ -458,7 +459,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target) spin_unlock_irq(&target->lock); if (changed) - queue_work(system_long_wq, &target->remove_work); + queue_work(srp_remove_wq, &target->remove_work); return changed; } @@ -1412,6 +1413,12 @@ err_unmap: err_iu: srp_put_tx_iu(target, iu, SRP_IU_CMD); + /* + * Avoid that the loops that iterate over the request ring can + * encounter a dangling SCSI command pointer. + */ + req->scmnd = NULL; + spin_lock_irqsave(&target->lock, flags); list_add(&req->list, &target->free_reqs); @@ -2596,9 +2603,10 @@ static void srp_remove_one(struct ib_device *device) spin_unlock(&host->target_lock); /* - * Wait for target port removal tasks. + * Wait for tl_err and target port removal tasks. */ flush_workqueue(system_long_wq); + flush_workqueue(srp_remove_wq); kfree(host); } @@ -2643,16 +2651,22 @@ static int __init srp_init_module(void) indirect_sg_entries = cmd_sg_entries; } + srp_remove_wq = create_workqueue("srp_remove"); + if (IS_ERR(srp_remove_wq)) { + ret = PTR_ERR(srp_remove_wq); + goto out; + } + + ret = -ENOMEM; ib_srp_transport_template = srp_attach_transport(&ib_srp_transport_functions); if (!ib_srp_transport_template) - return -ENOMEM; + goto destroy_wq; ret = class_register(&srp_class); if (ret) { pr_err("couldn't register class infiniband_srp\n"); - srp_release_transport(ib_srp_transport_template); - return ret; + goto release_tr; } ib_sa_register_client(&srp_sa_client); @@ -2660,13 +2674,22 @@ static int __init srp_init_module(void) ret = ib_register_client(&srp_client); if (ret) { pr_err("couldn't register IB client\n"); - srp_release_transport(ib_srp_transport_template); - ib_sa_unregister_client(&srp_sa_client); - class_unregister(&srp_class); - return ret; + goto unreg_sa; } - return 0; +out: + return ret; + +unreg_sa: + ib_sa_unregister_client(&srp_sa_client); + class_unregister(&srp_class); + +release_tr: + srp_release_transport(ib_srp_transport_template); + +destroy_wq: + destroy_workqueue(srp_remove_wq); + goto out; } static void __exit srp_cleanup_module(void) @@ -2675,6 +2698,7 @@ static void __exit srp_cleanup_module(void) ib_sa_unregister_client(&srp_sa_client); class_unregister(&srp_class); srp_release_transport(ib_srp_transport_template); + destroy_workqueue(srp_remove_wq); } module_init(srp_init_module); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 6c923c7..1ed08cc 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -1078,6 +1078,7 @@ static void srpt_unmap_sg_to_ib_sge(struct srpt_rdma_ch *ch, static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, struct srpt_send_ioctx *ioctx) { + struct ib_device *dev = ch->sport->sdev->device; struct se_cmd *cmd; struct scatterlist *sg, *sg_orig; int sg_cnt; @@ -1124,7 +1125,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, db = ioctx->rbufs; tsize = cmd->data_length; - dma_len = sg_dma_len(&sg[0]); + dma_len = ib_sg_dma_len(dev, &sg[0]); riu = ioctx->rdma_ius; /* @@ -1155,7 +1156,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, ++j; if (j < count) { sg = sg_next(sg); - dma_len = sg_dma_len(sg); + dma_len = ib_sg_dma_len( + dev, sg); } } } else { @@ -1192,8 +1194,8 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, tsize = cmd->data_length; riu = ioctx->rdma_ius; sg = sg_orig; - dma_len = sg_dma_len(&sg[0]); - dma_addr = sg_dma_address(&sg[0]); + dma_len = ib_sg_dma_len(dev, &sg[0]); + dma_addr = ib_sg_dma_address(dev, &sg[0]); /* this second loop is really mapped sg_addres to rdma_iu->ib_sge */ for (i = 0, j = 0; @@ -1216,8 +1218,10 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch, ++j; if (j < count) { sg = sg_next(sg); - dma_len = sg_dma_len(sg); - dma_addr = sg_dma_address(sg); + dma_len = ib_sg_dma_len( + dev, sg); + dma_addr = ib_sg_dma_address( + dev, sg); } } } else { @@ -2097,6 +2101,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) if (!qp_init) goto out; +retry: ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch, ch->rq_size + srp_sq_size, 0); if (IS_ERR(ch->cq)) { @@ -2120,6 +2125,13 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch) ch->qp = ib_create_qp(sdev->pd, qp_init); if (IS_ERR(ch->qp)) { ret = PTR_ERR(ch->qp); + if (ret == -ENOMEM) { + srp_sq_size /= 2; + if (srp_sq_size >= MIN_SRPT_SQ_SIZE) { + ib_destroy_cq(ch->cq); + goto retry; + } + } printk(KERN_ERR "failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } |