aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/core
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/infiniband/core')
-rw-r--r--drivers/infiniband/core/Makefile4
-rw-r--r--drivers/infiniband/core/cma.c4
-rw-r--r--drivers/infiniband/core/iwcm.c4
-rw-r--r--drivers/infiniband/core/iwpm_util.c1
-rw-r--r--drivers/infiniband/core/mr_pool.c86
-rw-r--r--drivers/infiniband/core/netlink.c5
-rw-r--r--drivers/infiniband/core/rw.c727
-rw-r--r--drivers/infiniband/core/sa_query.c4
-rw-r--r--drivers/infiniband/core/uverbs_cmd.c11
-rw-r--r--drivers/infiniband/core/verbs.c172
10 files changed, 946 insertions, 72 deletions
diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index f818538a7f4e..26987d9d7e1c 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -8,9 +8,9 @@ obj-$(CONFIG_INFINIBAND_USER_MAD) += ib_umad.o
obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o ib_ucm.o \
$(user_access-y)
-ib_core-y := packer.o ud_header.o verbs.o cq.o sysfs.o \
+ib_core-y := packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
device.o fmr_pool.o cache.o netlink.o \
- roce_gid_mgmt.o
+ roce_gid_mgmt.o mr_pool.o
ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 93ab0ae97208..f0c91ba3178a 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -800,6 +800,7 @@ int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
if (id->device != pd->device)
return -EINVAL;
+ qp_init_attr->port_num = id->port_num;
qp = ib_create_qp(pd, qp_init_attr);
if (IS_ERR(qp))
return PTR_ERR(qp);
@@ -4294,7 +4295,8 @@ static int __init cma_init(void)
if (ret)
goto err;
- if (ibnl_add_client(RDMA_NL_RDMA_CM, RDMA_NL_RDMA_CM_NUM_OPS, cma_cb_table))
+ if (ibnl_add_client(RDMA_NL_RDMA_CM, ARRAY_SIZE(cma_cb_table),
+ cma_cb_table))
pr_warn("RDMA CMA: failed to add netlink callback\n");
cma_configfs_init();
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index e28a160cdab0..f0572049d291 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -459,7 +459,7 @@ static void iw_cm_check_wildcard(struct sockaddr_storage *pm_addr,
if (pm_addr->ss_family == AF_INET) {
struct sockaddr_in *pm4_addr = (struct sockaddr_in *)pm_addr;
- if (pm4_addr->sin_addr.s_addr == INADDR_ANY) {
+ if (pm4_addr->sin_addr.s_addr == htonl(INADDR_ANY)) {
struct sockaddr_in *cm4_addr =
(struct sockaddr_in *)cm_addr;
struct sockaddr_in *cm4_outaddr =
@@ -1175,7 +1175,7 @@ static int __init iw_cm_init(void)
if (ret)
pr_err("iw_cm: couldn't init iwpm\n");
- ret = ibnl_add_client(RDMA_NL_IWCM, RDMA_NL_IWPM_NUM_OPS,
+ ret = ibnl_add_client(RDMA_NL_IWCM, ARRAY_SIZE(iwcm_nl_cb_table),
iwcm_nl_cb_table);
if (ret)
pr_err("iw_cm: couldn't register netlink callbacks\n");
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 9b2bf2fb2b00..b65e06c560d7 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -634,6 +634,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
if (!(ibnl_put_msg(skb, &nlh, 0, 0, nl_client,
RDMA_NL_IWPM_MAPINFO, NLM_F_MULTI))) {
pr_warn("%s Unable to put NLMSG_DONE\n", __func__);
+ dev_kfree_skb(skb);
return -ENOMEM;
}
nlh->nlmsg_type = NLMSG_DONE;
diff --git a/drivers/infiniband/core/mr_pool.c b/drivers/infiniband/core/mr_pool.c
new file mode 100644
index 000000000000..49d478b2ea94
--- /dev/null
+++ b/drivers/infiniband/core/mr_pool.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <rdma/ib_verbs.h>
+#include <rdma/mr_pool.h>
+
+struct ib_mr *ib_mr_pool_get(struct ib_qp *qp, struct list_head *list)
+{
+ struct ib_mr *mr;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qp->mr_lock, flags);
+ mr = list_first_entry_or_null(list, struct ib_mr, qp_entry);
+ if (mr) {
+ list_del(&mr->qp_entry);
+ qp->mrs_used++;
+ }
+ spin_unlock_irqrestore(&qp->mr_lock, flags);
+
+ return mr;
+}
+EXPORT_SYMBOL(ib_mr_pool_get);
+
+void ib_mr_pool_put(struct ib_qp *qp, struct list_head *list, struct ib_mr *mr)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&qp->mr_lock, flags);
+ list_add(&mr->qp_entry, list);
+ qp->mrs_used--;
+ spin_unlock_irqrestore(&qp->mr_lock, flags);
+}
+EXPORT_SYMBOL(ib_mr_pool_put);
+
+int ib_mr_pool_init(struct ib_qp *qp, struct list_head *list, int nr,
+ enum ib_mr_type type, u32 max_num_sg)
+{
+ struct ib_mr *mr;
+ unsigned long flags;
+ int ret, i;
+
+ for (i = 0; i < nr; i++) {
+ mr = ib_alloc_mr(qp->pd, type, max_num_sg);
+ if (IS_ERR(mr)) {
+ ret = PTR_ERR(mr);
+ goto out;
+ }
+
+ spin_lock_irqsave(&qp->mr_lock, flags);
+ list_add_tail(&mr->qp_entry, list);
+ spin_unlock_irqrestore(&qp->mr_lock, flags);
+ }
+
+ return 0;
+out:
+ ib_mr_pool_destroy(qp, list);
+ return ret;
+}
+EXPORT_SYMBOL(ib_mr_pool_init);
+
+void ib_mr_pool_destroy(struct ib_qp *qp, struct list_head *list)
+{
+ struct ib_mr *mr;
+ unsigned long flags;
+
+ spin_lock_irqsave(&qp->mr_lock, flags);
+ while (!list_empty(list)) {
+ mr = list_first_entry(list, struct ib_mr, qp_entry);
+ list_del(&mr->qp_entry);
+
+ spin_unlock_irqrestore(&qp->mr_lock, flags);
+ ib_dereg_mr(mr);
+ spin_lock_irqsave(&qp->mr_lock, flags);
+ }
+ spin_unlock_irqrestore(&qp->mr_lock, flags);
+}
+EXPORT_SYMBOL(ib_mr_pool_destroy);
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index d47df9356779..9b8c20c8209b 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -151,12 +151,11 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct ibnl_client *client;
int type = nlh->nlmsg_type;
int index = RDMA_NL_GET_CLIENT(type);
- int op = RDMA_NL_GET_OP(type);
+ unsigned int op = RDMA_NL_GET_OP(type);
list_for_each_entry(client, &client_list, list) {
if (client->index == index) {
- if (op < 0 || op >= client->nops ||
- !client->cb_table[op].dump)
+ if (op >= client->nops || !client->cb_table[op].dump)
return -EINVAL;
/*
diff --git a/drivers/infiniband/core/rw.c b/drivers/infiniband/core/rw.c
new file mode 100644
index 000000000000..1eb9b1294a63
--- /dev/null
+++ b/drivers/infiniband/core/rw.c
@@ -0,0 +1,727 @@
+/*
+ * Copyright (c) 2016 HGST, a Western Digital Company.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <rdma/mr_pool.h>
+#include <rdma/rw.h>
+
+enum {
+ RDMA_RW_SINGLE_WR,
+ RDMA_RW_MULTI_WR,
+ RDMA_RW_MR,
+ RDMA_RW_SIG_MR,
+};
+
+static bool rdma_rw_force_mr;
+module_param_named(force_mr, rdma_rw_force_mr, bool, 0);
+MODULE_PARM_DESC(force_mr, "Force usage of MRs for RDMA READ/WRITE operations");
+
+/*
+ * Check if the device might use memory registration. This is currently only
+ * true for iWarp devices. In the future we can hopefully fine tune this based
+ * on HCA driver input.
+ */
+static inline bool rdma_rw_can_use_mr(struct ib_device *dev, u8 port_num)
+{
+ if (rdma_protocol_iwarp(dev, port_num))
+ return true;
+ if (unlikely(rdma_rw_force_mr))
+ return true;
+ return false;
+}
+
+/*
+ * Check if the device will use memory registration for this RW operation.
+ * We currently always use memory registrations for iWarp RDMA READs, and
+ * have a debug option to force usage of MRs.
+ *
+ * XXX: In the future we can hopefully fine tune this based on HCA driver
+ * input.
+ */
+static inline bool rdma_rw_io_needs_mr(struct ib_device *dev, u8 port_num,
+ enum dma_data_direction dir, int dma_nents)
+{
+ if (rdma_protocol_iwarp(dev, port_num) && dir == DMA_FROM_DEVICE)
+ return true;
+ if (unlikely(rdma_rw_force_mr))
+ return true;
+ return false;
+}
+
+static inline u32 rdma_rw_max_sge(struct ib_device *dev,
+ enum dma_data_direction dir)
+{
+ return dir == DMA_TO_DEVICE ?
+ dev->attrs.max_sge : dev->attrs.max_sge_rd;
+}
+
+static inline u32 rdma_rw_fr_page_list_len(struct ib_device *dev)
+{
+ /* arbitrary limit to avoid allocating gigantic resources */
+ return min_t(u32, dev->attrs.max_fast_reg_page_list_len, 256);
+}
+
+static int rdma_rw_init_one_mr(struct ib_qp *qp, u8 port_num,
+ struct rdma_rw_reg_ctx *reg, struct scatterlist *sg,
+ u32 sg_cnt, u32 offset)
+{
+ u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
+ u32 nents = min(sg_cnt, pages_per_mr);
+ int count = 0, ret;
+
+ reg->mr = ib_mr_pool_get(qp, &qp->rdma_mrs);
+ if (!reg->mr)
+ return -EAGAIN;
+
+ if (reg->mr->need_inval) {
+ reg->inv_wr.opcode = IB_WR_LOCAL_INV;
+ reg->inv_wr.ex.invalidate_rkey = reg->mr->lkey;
+ reg->inv_wr.next = &reg->reg_wr.wr;
+ count++;
+ } else {
+ reg->inv_wr.next = NULL;
+ }
+
+ ret = ib_map_mr_sg(reg->mr, sg, nents, &offset, PAGE_SIZE);
+ if (ret < nents) {
+ ib_mr_pool_put(qp, &qp->rdma_mrs, reg->mr);
+ return -EINVAL;
+ }
+
+ reg->reg_wr.wr.opcode = IB_WR_REG_MR;
+ reg->reg_wr.mr = reg->mr;
+ reg->reg_wr.access = IB_ACCESS_LOCAL_WRITE;
+ if (rdma_protocol_iwarp(qp->device, port_num))
+ reg->reg_wr.access |= IB_ACCESS_REMOTE_WRITE;
+ count++;
+
+ reg->sge.addr = reg->mr->iova;
+ reg->sge.length = reg->mr->length;
+ return count;
+}
+
+static int rdma_rw_init_mr_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ u8 port_num, struct scatterlist *sg, u32 sg_cnt, u32 offset,
+ u64 remote_addr, u32 rkey, enum dma_data_direction dir)
+{
+ u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
+ int i, j, ret = 0, count = 0;
+
+ ctx->nr_ops = (sg_cnt + pages_per_mr - 1) / pages_per_mr;
+ ctx->reg = kcalloc(ctx->nr_ops, sizeof(*ctx->reg), GFP_KERNEL);
+ if (!ctx->reg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < ctx->nr_ops; i++) {
+ struct rdma_rw_reg_ctx *prev = i ? &ctx->reg[i - 1] : NULL;
+ struct rdma_rw_reg_ctx *reg = &ctx->reg[i];
+ u32 nents = min(sg_cnt, pages_per_mr);
+
+ ret = rdma_rw_init_one_mr(qp, port_num, reg, sg, sg_cnt,
+ offset);
+ if (ret < 0)
+ goto out_free;
+ count += ret;
+
+ if (prev) {
+ if (reg->mr->need_inval)
+ prev->wr.wr.next = &reg->inv_wr;
+ else
+ prev->wr.wr.next = &reg->reg_wr.wr;
+ }
+
+ reg->reg_wr.wr.next = &reg->wr.wr;
+
+ reg->wr.wr.sg_list = &reg->sge;
+ reg->wr.wr.num_sge = 1;
+ reg->wr.remote_addr = remote_addr;
+ reg->wr.rkey = rkey;
+ if (dir == DMA_TO_DEVICE) {
+ reg->wr.wr.opcode = IB_WR_RDMA_WRITE;
+ } else if (!rdma_cap_read_inv(qp->device, port_num)) {
+ reg->wr.wr.opcode = IB_WR_RDMA_READ;
+ } else {
+ reg->wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV;
+ reg->wr.wr.ex.invalidate_rkey = reg->mr->lkey;
+ }
+ count++;
+
+ remote_addr += reg->sge.length;
+ sg_cnt -= nents;
+ for (j = 0; j < nents; j++)
+ sg = sg_next(sg);
+ offset = 0;
+ }
+
+ ctx->type = RDMA_RW_MR;
+ return count;
+
+out_free:
+ while (--i >= 0)
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->reg[i].mr);
+ kfree(ctx->reg);
+out:
+ return ret;
+}
+
+static int rdma_rw_init_map_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ struct scatterlist *sg, u32 sg_cnt, u32 offset,
+ u64 remote_addr, u32 rkey, enum dma_data_direction dir)
+{
+ struct ib_device *dev = qp->pd->device;
+ u32 max_sge = rdma_rw_max_sge(dev, dir);
+ struct ib_sge *sge;
+ u32 total_len = 0, i, j;
+
+ ctx->nr_ops = DIV_ROUND_UP(sg_cnt, max_sge);
+
+ ctx->map.sges = sge = kcalloc(sg_cnt, sizeof(*sge), GFP_KERNEL);
+ if (!ctx->map.sges)
+ goto out;
+
+ ctx->map.wrs = kcalloc(ctx->nr_ops, sizeof(*ctx->map.wrs), GFP_KERNEL);
+ if (!ctx->map.wrs)
+ goto out_free_sges;
+
+ for (i = 0; i < ctx->nr_ops; i++) {
+ struct ib_rdma_wr *rdma_wr = &ctx->map.wrs[i];
+ u32 nr_sge = min(sg_cnt, max_sge);
+
+ if (dir == DMA_TO_DEVICE)
+ rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
+ else
+ rdma_wr->wr.opcode = IB_WR_RDMA_READ;
+ rdma_wr->remote_addr = remote_addr + total_len;
+ rdma_wr->rkey = rkey;
+ rdma_wr->wr.sg_list = sge;
+
+ for (j = 0; j < nr_sge; j++, sg = sg_next(sg)) {
+ rdma_wr->wr.num_sge++;
+
+ sge->addr = ib_sg_dma_address(dev, sg) + offset;
+ sge->length = ib_sg_dma_len(dev, sg) - offset;
+ sge->lkey = qp->pd->local_dma_lkey;
+
+ total_len += sge->length;
+ sge++;
+ sg_cnt--;
+ offset = 0;
+ }
+
+ if (i + 1 < ctx->nr_ops)
+ rdma_wr->wr.next = &ctx->map.wrs[i + 1].wr;
+ }
+
+ ctx->type = RDMA_RW_MULTI_WR;
+ return ctx->nr_ops;
+
+out_free_sges:
+ kfree(ctx->map.sges);
+out:
+ return -ENOMEM;
+}
+
+static int rdma_rw_init_single_wr(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ struct scatterlist *sg, u32 offset, u64 remote_addr, u32 rkey,
+ enum dma_data_direction dir)
+{
+ struct ib_device *dev = qp->pd->device;
+ struct ib_rdma_wr *rdma_wr = &ctx->single.wr;
+
+ ctx->nr_ops = 1;
+
+ ctx->single.sge.lkey = qp->pd->local_dma_lkey;
+ ctx->single.sge.addr = ib_sg_dma_address(dev, sg) + offset;
+ ctx->single.sge.length = ib_sg_dma_len(dev, sg) - offset;
+
+ memset(rdma_wr, 0, sizeof(*rdma_wr));
+ if (dir == DMA_TO_DEVICE)
+ rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
+ else
+ rdma_wr->wr.opcode = IB_WR_RDMA_READ;
+ rdma_wr->wr.sg_list = &ctx->single.sge;
+ rdma_wr->wr.num_sge = 1;
+ rdma_wr->remote_addr = remote_addr;
+ rdma_wr->rkey = rkey;
+
+ ctx->type = RDMA_RW_SINGLE_WR;
+ return 1;
+}
+
+/**
+ * rdma_rw_ctx_init - initialize a RDMA READ/WRITE context
+ * @ctx: context to initialize
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @sg: scatterlist to READ/WRITE from/to
+ * @sg_cnt: number of entries in @sg
+ * @sg_offset: current byte offset into @sg
+ * @remote_addr:remote address to read/write (relative to @rkey)
+ * @rkey: remote key to operate on
+ * @dir: %DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
+ *
+ * Returns the number of WQEs that will be needed on the workqueue if
+ * successful, or a negative error code.
+ */
+int rdma_rw_ctx_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+ struct scatterlist *sg, u32 sg_cnt, u32 sg_offset,
+ u64 remote_addr, u32 rkey, enum dma_data_direction dir)
+{
+ struct ib_device *dev = qp->pd->device;
+ int ret;
+
+ ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
+ if (!ret)
+ return -ENOMEM;
+ sg_cnt = ret;
+
+ /*
+ * Skip to the S/G entry that sg_offset falls into:
+ */
+ for (;;) {
+ u32 len = ib_sg_dma_len(dev, sg);
+
+ if (sg_offset < len)
+ break;
+
+ sg = sg_next(sg);
+ sg_offset -= len;
+ sg_cnt--;
+ }
+
+ ret = -EIO;
+ if (WARN_ON_ONCE(sg_cnt == 0))
+ goto out_unmap_sg;
+
+ if (rdma_rw_io_needs_mr(qp->device, port_num, dir, sg_cnt)) {
+ ret = rdma_rw_init_mr_wrs(ctx, qp, port_num, sg, sg_cnt,
+ sg_offset, remote_addr, rkey, dir);
+ } else if (sg_cnt > 1) {
+ ret = rdma_rw_init_map_wrs(ctx, qp, sg, sg_cnt, sg_offset,
+ remote_addr, rkey, dir);
+ } else {
+ ret = rdma_rw_init_single_wr(ctx, qp, sg, sg_offset,
+ remote_addr, rkey, dir);
+ }
+
+ if (ret < 0)
+ goto out_unmap_sg;
+ return ret;
+
+out_unmap_sg:
+ ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
+ return ret;
+}
+EXPORT_SYMBOL(rdma_rw_ctx_init);
+
+/**
+ * rdma_rw_ctx_signature init - initialize a RW context with signature offload
+ * @ctx: context to initialize
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @sg: scatterlist to READ/WRITE from/to
+ * @sg_cnt: number of entries in @sg
+ * @prot_sg: scatterlist to READ/WRITE protection information from/to
+ * @prot_sg_cnt: number of entries in @prot_sg
+ * @sig_attrs: signature offloading algorithms
+ * @remote_addr:remote address to read/write (relative to @rkey)
+ * @rkey: remote key to operate on
+ * @dir: %DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
+ *
+ * Returns the number of WQEs that will be needed on the workqueue if
+ * successful, or a negative error code.
+ */
+int rdma_rw_ctx_signature_init(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ u8 port_num, struct scatterlist *sg, u32 sg_cnt,
+ struct scatterlist *prot_sg, u32 prot_sg_cnt,
+ struct ib_sig_attrs *sig_attrs,
+ u64 remote_addr, u32 rkey, enum dma_data_direction dir)
+{
+ struct ib_device *dev = qp->pd->device;
+ u32 pages_per_mr = rdma_rw_fr_page_list_len(qp->pd->device);
+ struct ib_rdma_wr *rdma_wr;
+ struct ib_send_wr *prev_wr = NULL;
+ int count = 0, ret;
+
+ if (sg_cnt > pages_per_mr || prot_sg_cnt > pages_per_mr) {
+ pr_err("SG count too large\n");
+ return -EINVAL;
+ }
+
+ ret = ib_dma_map_sg(dev, sg, sg_cnt, dir);
+ if (!ret)
+ return -ENOMEM;
+ sg_cnt = ret;
+
+ ret = ib_dma_map_sg(dev, prot_sg, prot_sg_cnt, dir);
+ if (!ret) {
+ ret = -ENOMEM;
+ goto out_unmap_sg;
+ }
+ prot_sg_cnt = ret;
+
+ ctx->type = RDMA_RW_SIG_MR;
+ ctx->nr_ops = 1;
+ ctx->sig = kcalloc(1, sizeof(*ctx->sig), GFP_KERNEL);
+ if (!ctx->sig) {
+ ret = -ENOMEM;
+ goto out_unmap_prot_sg;
+ }
+
+ ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->data, sg, sg_cnt, 0);
+ if (ret < 0)
+ goto out_free_ctx;
+ count += ret;
+ prev_wr = &ctx->sig->data.reg_wr.wr;
+
+ if (prot_sg_cnt) {
+ ret = rdma_rw_init_one_mr(qp, port_num, &ctx->sig->prot,
+ prot_sg, prot_sg_cnt, 0);
+ if (ret < 0)
+ goto out_destroy_data_mr;
+ count += ret;
+
+ if (ctx->sig->prot.inv_wr.next)
+ prev_wr->next = &ctx->sig->prot.inv_wr;
+ else
+ prev_wr->next = &ctx->sig->prot.reg_wr.wr;
+ prev_wr = &ctx->sig->prot.reg_wr.wr;
+ } else {
+ ctx->sig->prot.mr = NULL;
+ }
+
+ ctx->sig->sig_mr = ib_mr_pool_get(qp, &qp->sig_mrs);
+ if (!ctx->sig->sig_mr) {
+ ret = -EAGAIN;
+ goto out_destroy_prot_mr;
+ }
+
+ if (ctx->sig->sig_mr->need_inval) {
+ memset(&ctx->sig->sig_inv_wr, 0, sizeof(ctx->sig->sig_inv_wr));
+
+ ctx->sig->sig_inv_wr.opcode = IB_WR_LOCAL_INV;
+ ctx->sig->sig_inv_wr.ex.invalidate_rkey = ctx->sig->sig_mr->rkey;
+
+ prev_wr->next = &ctx->sig->sig_inv_wr;
+ prev_wr = &ctx->sig->sig_inv_wr;
+ }
+
+ ctx->sig->sig_wr.wr.opcode = IB_WR_REG_SIG_MR;
+ ctx->sig->sig_wr.wr.wr_cqe = NULL;
+ ctx->sig->sig_wr.wr.sg_list = &ctx->sig->data.sge;
+ ctx->sig->sig_wr.wr.num_sge = 1;
+ ctx->sig->sig_wr.access_flags = IB_ACCESS_LOCAL_WRITE;
+ ctx->sig->sig_wr.sig_attrs = sig_attrs;
+ ctx->sig->sig_wr.sig_mr = ctx->sig->sig_mr;
+ if (prot_sg_cnt)
+ ctx->sig->sig_wr.prot = &ctx->sig->prot.sge;
+ prev_wr->next = &ctx->sig->sig_wr.wr;
+ prev_wr = &ctx->sig->sig_wr.wr;
+ count++;
+
+ ctx->sig->sig_sge.addr = 0;
+ ctx->sig->sig_sge.length = ctx->sig->data.sge.length;
+ if (sig_attrs->wire.sig_type != IB_SIG_TYPE_NONE)
+ ctx->sig->sig_sge.length += ctx->sig->prot.sge.length;
+
+ rdma_wr = &ctx->sig->data.wr;
+ rdma_wr->wr.sg_list = &ctx->sig->sig_sge;
+ rdma_wr->wr.num_sge = 1;
+ rdma_wr->remote_addr = remote_addr;
+ rdma_wr->rkey = rkey;
+ if (dir == DMA_TO_DEVICE)
+ rdma_wr->wr.opcode = IB_WR_RDMA_WRITE;
+ else
+ rdma_wr->wr.opcode = IB_WR_RDMA_READ;
+ prev_wr->next = &rdma_wr->wr;
+ prev_wr = &rdma_wr->wr;
+ count++;
+
+ return count;
+
+out_destroy_prot_mr:
+ if (prot_sg_cnt)
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->prot.mr);
+out_destroy_data_mr:
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->data.mr);
+out_free_ctx:
+ kfree(ctx->sig);
+out_unmap_prot_sg:
+ ib_dma_unmap_sg(dev, prot_sg, prot_sg_cnt, dir);
+out_unmap_sg:
+ ib_dma_unmap_sg(dev, sg, sg_cnt, dir);
+ return ret;
+}
+EXPORT_SYMBOL(rdma_rw_ctx_signature_init);
+
+/*
+ * Now that we are going to post the WRs we can update the lkey and need_inval
+ * state on the MRs. If we were doing this at init time, we would get double
+ * or missing invalidations if a context was initialized but not actually
+ * posted.
+ */
+static void rdma_rw_update_lkey(struct rdma_rw_reg_ctx *reg, bool need_inval)
+{
+ reg->mr->need_inval = need_inval;
+ ib_update_fast_reg_key(reg->mr, ib_inc_rkey(reg->mr->lkey));
+ reg->reg_wr.key = reg->mr->lkey;
+ reg->sge.lkey = reg->mr->lkey;
+}
+
+/**
+ * rdma_rw_ctx_wrs - return chain of WRs for a RDMA READ or WRITE operation
+ * @ctx: context to operate on
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @cqe: completion queue entry for the last WR
+ * @chain_wr: WR to append to the posted chain
+ *
+ * Return the WR chain for the set of RDMA READ/WRITE operations described by
+ * @ctx, as well as any memory registration operations needed. If @chain_wr
+ * is non-NULL the WR it points to will be appended to the chain of WRs posted.
+ * If @chain_wr is not set @cqe must be set so that the caller gets a
+ * completion notification.
+ */
+struct ib_send_wr *rdma_rw_ctx_wrs(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ u8 port_num, struct ib_cqe *cqe, struct ib_send_wr *chain_wr)
+{
+ struct ib_send_wr *first_wr, *last_wr;
+ int i;
+
+ switch (ctx->type) {
+ case RDMA_RW_SIG_MR:
+ rdma_rw_update_lkey(&ctx->sig->data, true);
+ if (ctx->sig->prot.mr)
+ rdma_rw_update_lkey(&ctx->sig->prot, true);
+
+ ctx->sig->sig_mr->need_inval = true;
+ ib_update_fast_reg_key(ctx->sig->sig_mr,
+ ib_inc_rkey(ctx->sig->sig_mr->lkey));
+ ctx->sig->sig_sge.lkey = ctx->sig->sig_mr->lkey;
+
+ if (ctx->sig->data.inv_wr.next)
+ first_wr = &ctx->sig->data.inv_wr;
+ else
+ first_wr = &ctx->sig->data.reg_wr.wr;
+ last_wr = &ctx->sig->data.wr.wr;
+ break;
+ case RDMA_RW_MR:
+ for (i = 0; i < ctx->nr_ops; i++) {
+ rdma_rw_update_lkey(&ctx->reg[i],
+ ctx->reg[i].wr.wr.opcode !=
+ IB_WR_RDMA_READ_WITH_INV);
+ }
+
+ if (ctx->reg[0].inv_wr.next)
+ first_wr = &ctx->reg[0].inv_wr;
+ else
+ first_wr = &ctx->reg[0].reg_wr.wr;
+ last_wr = &ctx->reg[ctx->nr_ops - 1].wr.wr;
+ break;
+ case RDMA_RW_MULTI_WR:
+ first_wr = &ctx->map.wrs[0].wr;
+ last_wr = &ctx->map.wrs[ctx->nr_ops - 1].wr;
+ break;
+ case RDMA_RW_SINGLE_WR:
+ first_wr = &ctx->single.wr.wr;
+ last_wr = &ctx->single.wr.wr;
+ break;
+ default:
+ BUG();
+ }
+
+ if (chain_wr) {
+ last_wr->next = chain_wr;
+ } else {
+ last_wr->wr_cqe = cqe;
+ last_wr->send_flags |= IB_SEND_SIGNALED;
+ }
+
+ return first_wr;
+}
+EXPORT_SYMBOL(rdma_rw_ctx_wrs);
+
+/**
+ * rdma_rw_ctx_post - post a RDMA READ or RDMA WRITE operation
+ * @ctx: context to operate on
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @cqe: completion queue entry for the last WR
+ * @chain_wr: WR to append to the posted chain
+ *
+ * Post the set of RDMA READ/WRITE operations described by @ctx, as well as
+ * any memory registration operations needed. If @chain_wr is non-NULL the
+ * WR it points to will be appended to the chain of WRs posted. If @chain_wr
+ * is not set @cqe must be set so that the caller gets a completion
+ * notification.
+ */
+int rdma_rw_ctx_post(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+ struct ib_cqe *cqe, struct ib_send_wr *chain_wr)
+{
+ struct ib_send_wr *first_wr, *bad_wr;
+
+ first_wr = rdma_rw_ctx_wrs(ctx, qp, port_num, cqe, chain_wr);
+ return ib_post_send(qp, first_wr, &bad_wr);
+}
+EXPORT_SYMBOL(rdma_rw_ctx_post);
+
+/**
+ * rdma_rw_ctx_destroy - release all resources allocated by rdma_rw_ctx_init
+ * @ctx: context to release
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @sg: scatterlist that was used for the READ/WRITE
+ * @sg_cnt: number of entries in @sg
+ * @dir: %DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
+ */
+void rdma_rw_ctx_destroy(struct rdma_rw_ctx *ctx, struct ib_qp *qp, u8 port_num,
+ struct scatterlist *sg, u32 sg_cnt, enum dma_data_direction dir)
+{
+ int i;
+
+ switch (ctx->type) {
+ case RDMA_RW_MR:
+ for (i = 0; i < ctx->nr_ops; i++)
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->reg[i].mr);
+ kfree(ctx->reg);
+ break;
+ case RDMA_RW_MULTI_WR:
+ kfree(ctx->map.wrs);
+ kfree(ctx->map.sges);
+ break;
+ case RDMA_RW_SINGLE_WR:
+ break;
+ default:
+ BUG();
+ break;
+ }
+
+ ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+}
+EXPORT_SYMBOL(rdma_rw_ctx_destroy);
+
+/**
+ * rdma_rw_ctx_destroy_signature - release all resources allocated by
+ * rdma_rw_ctx_init_signature
+ * @ctx: context to release
+ * @qp: queue pair to operate on
+ * @port_num: port num to which the connection is bound
+ * @sg: scatterlist that was used for the READ/WRITE
+ * @sg_cnt: number of entries in @sg
+ * @prot_sg: scatterlist that was used for the READ/WRITE of the PI
+ * @prot_sg_cnt: number of entries in @prot_sg
+ * @dir: %DMA_TO_DEVICE for RDMA WRITE, %DMA_FROM_DEVICE for RDMA READ
+ */
+void rdma_rw_ctx_destroy_signature(struct rdma_rw_ctx *ctx, struct ib_qp *qp,
+ u8 port_num, struct scatterlist *sg, u32 sg_cnt,
+ struct scatterlist *prot_sg, u32 prot_sg_cnt,
+ enum dma_data_direction dir)
+{
+ if (WARN_ON_ONCE(ctx->type != RDMA_RW_SIG_MR))
+ return;
+
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->data.mr);
+ ib_dma_unmap_sg(qp->pd->device, sg, sg_cnt, dir);
+
+ if (ctx->sig->prot.mr) {
+ ib_mr_pool_put(qp, &qp->rdma_mrs, ctx->sig->prot.mr);
+ ib_dma_unmap_sg(qp->pd->device, prot_sg, prot_sg_cnt, dir);
+ }
+
+ ib_mr_pool_put(qp, &qp->sig_mrs, ctx->sig->sig_mr);
+ kfree(ctx->sig);
+}
+EXPORT_SYMBOL(rdma_rw_ctx_destroy_signature);
+
+void rdma_rw_init_qp(struct ib_device *dev, struct ib_qp_init_attr *attr)
+{
+ u32 factor;
+
+ WARN_ON_ONCE(attr->port_num == 0);
+
+ /*
+ * Each context needs at least one RDMA READ or WRITE WR.
+ *
+ * For some hardware we might need more, eventually we should ask the
+ * HCA driver for a multiplier here.
+ */
+ factor = 1;
+
+ /*
+ * If the devices needs MRs to perform RDMA READ or WRITE operations,
+ * we'll need two additional MRs for the registrations and the
+ * invalidation.
+ */
+ if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
+ factor += 6; /* (inv + reg) * (data + prot + sig) */
+ else if (rdma_rw_can_use_mr(dev, attr->port_num))
+ factor += 2; /* inv + reg */
+
+ attr->cap.max_send_wr += factor * attr->cap.max_rdma_ctxs;
+
+ /*
+ * But maybe we were just too high in the sky and the device doesn't
+ * even support all we need, and we'll have to live with what we get..
+ */
+ attr->cap.max_send_wr =
+ min_t(u32, attr->cap.max_send_wr, dev->attrs.max_qp_wr);
+}
+
+int rdma_rw_init_mrs(struct ib_qp *qp, struct ib_qp_init_attr *attr)
+{
+ struct ib_device *dev = qp->pd->device;
+ u32 nr_mrs = 0, nr_sig_mrs = 0;
+ int ret = 0;
+
+ if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN) {
+ nr_sig_mrs = attr->cap.max_rdma_ctxs;
+ nr_mrs = attr->cap.max_rdma_ctxs * 2;
+ } else if (rdma_rw_can_use_mr(dev, attr->port_num)) {
+ nr_mrs = attr->cap.max_rdma_ctxs;
+ }
+
+ if (nr_mrs) {
+ ret = ib_mr_pool_init(qp, &qp->rdma_mrs, nr_mrs,
+ IB_MR_TYPE_MEM_REG,
+ rdma_rw_fr_page_list_len(dev));
+ if (ret) {
+ pr_err("%s: failed to allocated %d MRs\n",
+ __func__, nr_mrs);
+ return ret;
+ }
+ }
+
+ if (nr_sig_mrs) {
+ ret = ib_mr_pool_init(qp, &qp->sig_mrs, nr_sig_mrs,
+ IB_MR_TYPE_SIGNATURE, 2);
+ if (ret) {
+ pr_err("%s: failed to allocated %d SIG MRs\n",
+ __func__, nr_mrs);
+ goto out_free_rdma_mrs;
+ }
+ }
+
+ return 0;
+
+out_free_rdma_mrs:
+ ib_mr_pool_destroy(qp, &qp->rdma_mrs);
+ return ret;
+}
+
+void rdma_rw_cleanup_mrs(struct ib_qp *qp)
+{
+ ib_mr_pool_destroy(qp, &qp->sig_mrs);
+ ib_mr_pool_destroy(qp, &qp->rdma_mrs);
+}
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 8a09c0fb268d..3ebd108bcc5f 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -536,7 +536,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
data = ibnl_put_msg(skb, &nlh, query->seq, 0, RDMA_NL_LS,
RDMA_NL_LS_OP_RESOLVE, NLM_F_REQUEST);
if (!data) {
- kfree_skb(skb);
+ nlmsg_free(skb);
return -EMSGSIZE;
}
@@ -1820,7 +1820,7 @@ static int __init ib_sa_init(void)
goto err3;
}
- if (ibnl_add_client(RDMA_NL_LS, RDMA_NL_LS_NUM_OPS,
+ if (ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ib_sa_cb_table),
ib_sa_cb_table)) {
pr_err("Failed to add netlink callback\n");
ret = -EINVAL;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 6fdc7ecdaca0..1a8babb8ee3c 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1833,7 +1833,8 @@ static int create_qp(struct ib_uverbs_file *file,
if (attr.create_flags & ~(IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK |
IB_QP_CREATE_CROSS_CHANNEL |
IB_QP_CREATE_MANAGED_SEND |
- IB_QP_CREATE_MANAGED_RECV)) {
+ IB_QP_CREATE_MANAGED_RECV |
+ IB_QP_CREATE_SCATTER_FCS)) {
ret = -EINVAL;
goto err_put;
}
@@ -3088,8 +3089,7 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
if (cmd.comp_mask)
return -EINVAL;
- if ((cmd.flow_attr.type == IB_FLOW_ATTR_SNIFFER &&
- !capable(CAP_NET_ADMIN)) || !capable(CAP_NET_RAW))
+ if (!capable(CAP_NET_RAW))
return -EPERM;
if (cmd.flow_attr.flags >= IB_FLOW_ATTR_FLAGS_RESERVED)
@@ -3655,6 +3655,11 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
resp.hca_core_clock = attr.hca_core_clock;
resp.response_length += sizeof(resp.hca_core_clock);
+ if (ucore->outlen < resp.response_length + sizeof(resp.device_cap_flags_ex))
+ goto end;
+
+ resp.device_cap_flags_ex = attr.device_cap_flags;
+ resp.response_length += sizeof(resp.device_cap_flags_ex);
end:
err = ib_copy_to_udata(ucore, &resp, resp.response_length);
return err;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index b65b3541e732..1d7d4cf442e3 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -48,6 +48,7 @@
#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>
#include <rdma/ib_addr.h>
+#include <rdma/rw.h>
#include "core_priv.h"
@@ -723,59 +724,89 @@ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd,
}
EXPORT_SYMBOL(ib_open_qp);
+static struct ib_qp *ib_create_xrc_qp(struct ib_qp *qp,
+ struct ib_qp_init_attr *qp_init_attr)
+{
+ struct ib_qp *real_qp = qp;
+
+ qp->event_handler = __ib_shared_qp_event_handler;
+ qp->qp_context = qp;
+ qp->pd = NULL;
+ qp->send_cq = qp->recv_cq = NULL;
+ qp->srq = NULL;
+ qp->xrcd = qp_init_attr->xrcd;
+ atomic_inc(&qp_init_attr->xrcd->usecnt);
+ INIT_LIST_HEAD(&qp->open_list);
+
+ qp = __ib_open_qp(real_qp, qp_init_attr->event_handler,
+ qp_init_attr->qp_context);
+ if (!IS_ERR(qp))
+ __ib_insert_xrcd_qp(qp_init_attr->xrcd, real_qp);
+ else
+ real_qp->device->destroy_qp(real_qp);
+ return qp;
+}
+
struct ib_qp *ib_create_qp(struct ib_pd *pd,
struct ib_qp_init_attr *qp_init_attr)
{
- struct ib_qp *qp, *real_qp;
- struct ib_device *device;
+ struct ib_device *device = pd ? pd->device : qp_init_attr->xrcd->device;
+ struct ib_qp *qp;
+ int ret;
+
+ /*
+ * If the callers is using the RDMA API calculate the resources
+ * needed for the RDMA READ/WRITE operations.
+ *
+ * Note that these callers need to pass in a port number.
+ */
+ if (qp_init_attr->cap.max_rdma_ctxs)
+ rdma_rw_init_qp(device, qp_init_attr);
- device = pd ? pd->device : qp_init_attr->xrcd->device;
qp = device->create_qp(pd, qp_init_attr, NULL);
+ if (IS_ERR(qp))
+ return qp;
+
+ qp->device = device;
+ qp->real_qp = qp;
+ qp->uobject = NULL;
+ qp->qp_type = qp_init_attr->qp_type;
+
+ atomic_set(&qp->usecnt, 0);
+ qp->mrs_used = 0;
+ spin_lock_init(&qp->mr_lock);
+ INIT_LIST_HEAD(&qp->rdma_mrs);
+ INIT_LIST_HEAD(&qp->sig_mrs);
+
+ if (qp_init_attr->qp_type == IB_QPT_XRC_TGT)
+ return ib_create_xrc_qp(qp, qp_init_attr);
+
+ qp->event_handler = qp_init_attr->event_handler;
+ qp->qp_context = qp_init_attr->qp_context;
+ if (qp_init_attr->qp_type == IB_QPT_XRC_INI) {
+ qp->recv_cq = NULL;
+ qp->srq = NULL;
+ } else {
+ qp->recv_cq = qp_init_attr->recv_cq;
+ atomic_inc(&qp_init_attr->recv_cq->usecnt);
+ qp->srq = qp_init_attr->srq;
+ if (qp->srq)
+ atomic_inc(&qp_init_attr->srq->usecnt);
+ }
- if (!IS_ERR(qp)) {
- qp->device = device;
- qp->real_qp = qp;
- qp->uobject = NULL;
- qp->qp_type = qp_init_attr->qp_type;
-
- atomic_set(&qp->usecnt, 0);
- if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) {
- qp->event_handler = __ib_shared_qp_event_handler;
- qp->qp_context = qp;
- qp->pd = NULL;
- qp->send_cq = qp->recv_cq = NULL;
- qp->srq = NULL;
- qp->xrcd = qp_init_attr->xrcd;
- atomic_inc(&qp_init_attr->xrcd->usecnt);
- INIT_LIST_HEAD(&qp->open_list);
-
- real_qp = qp;
- qp = __ib_open_qp(real_qp, qp_init_attr->event_handler,
- qp_init_attr->qp_context);
- if (!IS_ERR(qp))
- __ib_insert_xrcd_qp(qp_init_attr->xrcd, real_qp);
- else
- real_qp->device->destroy_qp(real_qp);
- } else {
- qp->event_handler = qp_init_attr->event_handler;
- qp->qp_context = qp_init_attr->qp_context;
- if (qp_init_attr->qp_type == IB_QPT_XRC_INI) {
- qp->recv_cq = NULL;
- qp->srq = NULL;
- } else {
- qp->recv_cq = qp_init_attr->recv_cq;
- atomic_inc(&qp_init_attr->recv_cq->usecnt);
- qp->srq = qp_init_attr->srq;
- if (qp->srq)
- atomic_inc(&qp_init_attr->srq->usecnt);
- }
+ qp->pd = pd;
+ qp->send_cq = qp_init_attr->send_cq;
+ qp->xrcd = NULL;
- qp->pd = pd;
- qp->send_cq = qp_init_attr->send_cq;
- qp->xrcd = NULL;
+ atomic_inc(&pd->usecnt);
+ atomic_inc(&qp_init_attr->send_cq->usecnt);
- atomic_inc(&pd->usecnt);
- atomic_inc(&qp_init_attr->send_cq->usecnt);
+ if (qp_init_attr->cap.max_rdma_ctxs) {
+ ret = rdma_rw_init_mrs(qp, qp_init_attr);
+ if (ret) {
+ pr_err("failed to init MR pool ret= %d\n", ret);
+ ib_destroy_qp(qp);
+ qp = ERR_PTR(ret);
}
}
@@ -1250,6 +1281,8 @@ int ib_destroy_qp(struct ib_qp *qp)
struct ib_srq *srq;
int ret;
+ WARN_ON_ONCE(qp->mrs_used > 0);
+
if (atomic_read(&qp->usecnt))
return -EBUSY;
@@ -1261,6 +1294,9 @@ int ib_destroy_qp(struct ib_qp *qp)
rcq = qp->recv_cq;
srq = qp->srq;
+ if (!qp->uobject)
+ rdma_rw_cleanup_mrs(qp);
+
ret = qp->device->destroy_qp(qp);
if (!ret) {
if (pd)
@@ -1343,6 +1379,7 @@ struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags)
mr->pd = pd;
mr->uobject = NULL;
atomic_inc(&pd->usecnt);
+ mr->need_inval = false;
}
return mr;
@@ -1389,6 +1426,7 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
mr->pd = pd;
mr->uobject = NULL;
atomic_inc(&pd->usecnt);
+ mr->need_inval = false;
}
return mr;
@@ -1597,6 +1635,7 @@ EXPORT_SYMBOL(ib_set_vf_guid);
* @mr: memory region
* @sg: dma mapped scatterlist
* @sg_nents: number of entries in sg
+ * @sg_offset: offset in bytes into sg
* @page_size: page vector desired page size
*
* Constraints:
@@ -1615,17 +1654,15 @@ EXPORT_SYMBOL(ib_set_vf_guid);
* After this completes successfully, the memory region
* is ready for registration.
*/
-int ib_map_mr_sg(struct ib_mr *mr,
- struct scatterlist *sg,
- int sg_nents,
- unsigned int page_size)
+int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
+ unsigned int *sg_offset, unsigned int page_size)
{
if (unlikely(!mr->device->map_mr_sg))
return -ENOSYS;
mr->page_size = page_size;
- return mr->device->map_mr_sg(mr, sg, sg_nents);
+ return mr->device->map_mr_sg(mr, sg, sg_nents, sg_offset);
}
EXPORT_SYMBOL(ib_map_mr_sg);
@@ -1635,6 +1672,10 @@ EXPORT_SYMBOL(ib_map_mr_sg);
* @mr: memory region
* @sgl: dma mapped scatterlist
* @sg_nents: number of entries in sg
+ * @sg_offset_p: IN: start offset in bytes into sg
+ * OUT: offset in bytes for element n of the sg of the first
+ * byte that has not been processed where n is the return
+ * value of this function.
* @set_page: driver page assignment function pointer
*
* Core service helper for drivers to convert the largest
@@ -1645,23 +1686,26 @@ EXPORT_SYMBOL(ib_map_mr_sg);
* Returns the number of sg elements that were assigned to
* a page vector.
*/
-int ib_sg_to_pages(struct ib_mr *mr,
- struct scatterlist *sgl,
- int sg_nents,
- int (*set_page)(struct ib_mr *, u64))
+int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
+ unsigned int *sg_offset_p, int (*set_page)(struct ib_mr *, u64))
{
struct scatterlist *sg;
u64 last_end_dma_addr = 0;
+ unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0;
unsigned int last_page_off = 0;
u64 page_mask = ~((u64)mr->page_size - 1);
int i, ret;
- mr->iova = sg_dma_address(&sgl[0]);
+ if (unlikely(sg_nents <= 0 || sg_offset > sg_dma_len(&sgl[0])))
+ return -EINVAL;
+
+ mr->iova = sg_dma_address(&sgl[0]) + sg_offset;
mr->length = 0;
for_each_sg(sgl, sg, sg_nents, i) {
- u64 dma_addr = sg_dma_address(sg);
- unsigned int dma_len = sg_dma_len(sg);
+ u64 dma_addr = sg_dma_address(sg) + sg_offset;
+ u64 prev_addr = dma_addr;
+ unsigned int dma_len = sg_dma_len(sg) - sg_offset;
u64 end_dma_addr = dma_addr + dma_len;
u64 page_addr = dma_addr & page_mask;
@@ -1685,8 +1729,14 @@ int ib_sg_to_pages(struct ib_mr *mr,
do {
ret = set_page(mr, page_addr);
- if (unlikely(ret < 0))
- return i ? : ret;
+ if (unlikely(ret < 0)) {
+ sg_offset = prev_addr - sg_dma_address(sg);
+ mr->length += prev_addr - dma_addr;
+ if (sg_offset_p)
+ *sg_offset_p = sg_offset;
+ return i || sg_offset ? i : ret;
+ }
+ prev_addr = page_addr;
next_page:
page_addr += mr->page_size;
} while (page_addr < end_dma_addr);
@@ -1694,8 +1744,12 @@ next_page:
mr->length += dma_len;
last_end_dma_addr = end_dma_addr;
last_page_off = end_dma_addr & ~page_mask;
+
+ sg_offset = 0;
}
+ if (sg_offset_p)
+ *sg_offset_p = 0;
return i;
}
EXPORT_SYMBOL(ib_sg_to_pages);
Powered by cgit, Gruvboxed by Blaster4385.