@@ -64,7 +64,8 @@ man_MANS = man/ibv_asyncwatch.1 man/ibv_devices.1 man/ibv_devinfo.1 \
man/ibv_req_notify_cq.3 man/ibv_resize_cq.3 man/ibv_rate_to_mbps.3 \
man/ibv_create_qp_ex.3 man/ibv_create_srq_ex.3 man/ibv_open_xrcd.3 \
man/ibv_get_srq_num.3 man/ibv_open_qp.3 \
- man/ibv_query_device_ex.3 man/ibv_poll_cq_ex.3
+ man/ibv_query_device_ex.3 man/ibv_poll_cq_ex.3 \
+ man/ibv_create_cq_ex.3
DEBIAN = debian/changelog debian/compat debian/control debian/copyright \
debian/ibverbs-utils.install debian/libibverbs1.install \
@@ -144,6 +144,15 @@ int ibv_cmd_create_cq(struct ibv_context *context, int cqe,
int comp_vector, struct ibv_cq *cq,
struct ibv_create_cq *cmd, size_t cmd_size,
struct ibv_create_cq_resp *resp, size_t resp_size);
+int ibv_cmd_create_cq_ex(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *cq_attr,
+ struct ibv_cq *cq,
+ struct ibv_create_cq_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_cq_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size);
int ibv_cmd_poll_cq(struct ibv_cq *cq, int ne, struct ibv_wc *wc);
int ibv_cmd_req_notify_cq(struct ibv_cq *cq, int solicited_only);
#define IBV_CMD_RESIZE_CQ_HAS_RESP_PARAMS
@@ -110,9 +110,11 @@ enum {
enum {
IB_USER_VERBS_CMD_QUERY_DEVICE_EX = IB_USER_VERBS_CMD_EXTENDED_MASK |
IB_USER_VERBS_CMD_QUERY_DEVICE,
+ IB_USER_VERBS_CMD_CREATE_CQ_EX = IB_USER_VERBS_CMD_EXTENDED_MASK |
+ IB_USER_VERBS_CMD_CREATE_CQ,
IB_USER_VERBS_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_EXTENDED_MASK +
IB_USER_VERBS_CMD_THRESHOLD,
- IB_USER_VERBS_CMD_DESTROY_FLOW
+ IB_USER_VERBS_CMD_DESTROY_FLOW,
};
/*
@@ -400,6 +402,23 @@ struct ibv_create_cq_resp {
__u32 cqe;
};
+struct ibv_create_cq_ex {
+ struct ex_hdr hdr;
+ __u64 user_handle;
+ __u32 cqe;
+ __u32 comp_vector;
+ __s32 comp_channel;
+ __u32 comp_mask;
+ __u32 flags;
+ __u32 reserved;
+};
+
+struct ibv_create_cq_resp_ex {
+ struct ibv_create_cq_resp base;
+ __u32 comp_mask;
+ __u32 response_length;
+};
+
struct ibv_kern_wc {
__u64 wr_id;
__u32 status;
@@ -1033,7 +1052,8 @@ enum {
IB_USER_VERBS_CMD_OPEN_QP_V2 = -1,
IB_USER_VERBS_CMD_CREATE_FLOW_V2 = -1,
IB_USER_VERBS_CMD_DESTROY_FLOW_V2 = -1,
- IB_USER_VERBS_CMD_QUERY_DEVICE_EX_V2 = -1
+ IB_USER_VERBS_CMD_QUERY_DEVICE_EX_V2 = -1,
+ IB_USER_VERBS_CMD_CREATE_CQ_EX_V2 = -1,
};
struct ibv_modify_srq_v3 {
@@ -1193,6 +1193,42 @@ struct ibv_context {
void *abi_compat;
};
+enum ibv_create_cq_attr {
+ IBV_CREATE_CQ_ATTR_FLAGS = 1 << 0,
+ IBV_CREATE_CQ_ATTR_RESERVED = 1 << 1
+};
+
+enum ibv_create_cq_attr_flags {
+ IBV_CREATE_CQ_ATTR_COMPLETION_TIMESTAMP = 1 << 0,
+};
+
+struct ibv_create_cq_attr_ex {
+ /* Minimum number of entries required for CQ */
+ int cqe;
+ /* Consumer-supplied context returned for completion events */
+ void *cq_context;
+ /* Completion channel where completion events will be queued.
+ * May be NULL if completion events will not be used.
+ */
+ struct ibv_comp_channel *channel;
+ /* Completion vector used to signal completion events.
+ * Must be >= 0 and < context->num_comp_vectors.
+ */
+ int comp_vector;
+ /* The wc_flags that should be returned in ibv_poll_cq_ex.
+ * Or'ed bit of enum ibv_wc_flags_ex.
+ */
+ uint64_t wc_flags;
+ /* compatibility mask (extended verb). Or'd flags of
+ * enum ibv_create_cq_attr
+ */
+ uint32_t comp_mask;
+ /* create cq attr flags - one or more flags from
+ * enum ibv_create_cq_attr_flags
+ */
+ uint32_t flags;
+};
+
enum verbs_context_mask {
VERBS_CONTEXT_XRCD = 1 << 0,
VERBS_CONTEXT_SRQ = 1 << 1,
@@ -1209,6 +1245,9 @@ struct ibv_poll_cq_ex_attr {
struct verbs_context {
/* "grows up" - new fields go here */
+ struct ibv_cq *(*create_cq_ex)(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *);
+ void *priv;
int (*poll_cq_ex)(struct ibv_cq *ibcq,
struct ibv_wc_ex *wc,
struct ibv_poll_cq_ex_attr *attr);
@@ -1449,6 +1488,30 @@ struct ibv_cq *ibv_create_cq(struct ibv_context *context, int cqe,
int comp_vector);
/**
+ * ibv_create_cq_ex - Create a completion queue
+ * @context - Context CQ will be attached to
+ * @cq_attr - Attributes to create the CQ with
+ */
+static inline
+struct ibv_cq *ibv_create_cq_ex(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *cq_attr)
+{
+ struct verbs_context *vctx = verbs_get_ctx_op(context, create_cq_ex);
+
+ if (!vctx) {
+ errno = ENOSYS;
+ return NULL;
+ }
+
+ if (cq_attr->comp_mask & ~(IBV_CREATE_CQ_ATTR_RESERVED - 1)) {
+ errno = EINVAL;
+ return NULL;
+ }
+
+ return vctx->create_cq_ex(context, cq_attr);
+}
+
+/**
* ibv_resize_cq - Modifies the capacity of the CQ.
* @cq: The CQ to resize.
* @cqe: The minimum size of the CQ.
new file mode 100644
@@ -0,0 +1,71 @@
+.\" -*- nroff -*-
+.\"
+.TH IBV_CREATE_CQ_EX 3 2006-10-31 libibverbs "Libibverbs Programmer's Manual"
+.SH "NAME"
+ibv_create_cq_ex \- create a completion queue (CQ)
+.SH "SYNOPSIS"
+.nf
+.B #include <infiniband/verbs.h>
+.sp
+.BI "struct ibv_cq *ibv_create_cq_ex(struct ibv_context " "*context" ",
+.BI " struct ibv_create_cq_attr_ex " "*cq_attr" );
+.fi
+.SH "DESCRIPTION"
+.B ibv_create_cq_ex()
+creates a completion queue (CQ) for RDMA device context
+.I context\fR.
+The argument
+.I cq_attr
+is a pointer to struct ibv_create_cq_attr_ex as defined in <infiniband/verbs.h>.
+.PP
+.nf
+struct ibv_create_cq_attr_ex {
+.in +8
+int cqe; /* Minimum number of entries required for CQ */
+void *cq_context; /* Consumer-supplied context returned for completion events */
+struct ibv_comp_channel *channel; /* Completion channel where completion events will be queued. May be NULL if completion events will not be used. */
+int comp_vector; /* Completion vector used to signal completion events. Must be >= 0 and < context->num_comp_vectors. */
+uint64_t wc_flags; /* The wc_flags that should be returned in ibv_poll_cq_ex. Or'ed bit of enum ibv_wc_flags_ex. */
+uint32_t comp_mask; /* compatibility mask (extended verb). Or'd flags of enum ibv_create_cq_attr */
+uint32_t flags; /* create cq attr flags - one or more flags from enum ibv_create_cq_attr_flags */
+.in -8
+};
+
+enum ibv_wc_flags_ex {
+ IBV_WC_EX_GRH = 1 << 0, /* Output only */
+ IBV_WC_EX_IMM = 1 << 1, /* Output only */
+ IBV_WC_EX_WITH_BYTE_LEN = 1 << 2, /* Require byte len in WC */
+ IBV_WC_EX_WITH_IMM = 1 << 3, /* Require immediate in WC */
+ IBV_WC_EX_WITH_QP_NUM = 1 << 4, /* Require QP number in WC */
+ IBV_WC_EX_WITH_SRC_QP = 1 << 5, /* Require source QP in WC */
+ IBV_WC_EX_WITH_PKEY_INDEX = 1 << 6, /* Require pkey index in WC */
+ IBV_WC_EX_WITH_SLID = 1 << 7, /* Require slid in WC */
+ IBV_WC_EX_WITH_SL = 1 << 8, /* Require sl in WC */
+ IBV_WC_EX_WITH_DLID_PATH_BITS = 1 << 9, /* Require dlid path bits in WC */
+ IBV_WC_EX_WITH_COMPLETION_TIMESTAMP = 1 << 10, /* Require completion timestamp in WC /*
+};
+
+
+enum ibv_create_cq_attr {
+ IBV_CREATE_CQ_ATTR_FLAGS = 1 << 0,
+};
+.SH "RETURN VALUE"
+.B ibv_create_cq_ex()
+returns a pointer to the CQ, or NULL if the request fails.
+.SH "NOTES"
+.B ibv_create_cq_ex()
+may create a CQ with size greater than or equal to the requested
+size. Check the cqe attribute in the returned CQ for the actual size.
+.PP
+CQ should be destroyed with ibv_destroy_cq.
+.PP
+.SH "SEE ALSO"
+.BR ibv_create_cq (3),
+.BR ibv_destroy_cq (3),
+.BR ibv_resize_cq (3),
+.BR ibv_req_notify_cq (3),
+.BR ibv_ack_cq_events (3),
+.BR ibv_create_qp (3)
+.SH "AUTHORS"
+.TP
+Matan Barak <matanb@mellanox.com>
@@ -393,6 +393,48 @@ int ibv_cmd_create_cq(struct ibv_context *context, int cqe,
return 0;
}
+int ibv_cmd_create_cq_ex(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *cq_attr,
+ struct ibv_cq *cq,
+ struct ibv_create_cq_ex *cmd,
+ size_t cmd_core_size,
+ size_t cmd_size,
+ struct ibv_create_cq_resp_ex *resp,
+ size_t resp_core_size,
+ size_t resp_size)
+{
+ int err;
+
+ memset(cmd, 0, cmd_core_size);
+ IBV_INIT_CMD_RESP_EX_V(cmd, cmd_core_size, cmd_size, CREATE_CQ_EX, resp,
+ resp_core_size, resp_size);
+
+ if (cq_attr->comp_mask & ~(IBV_CREATE_CQ_ATTR_RESERVED - 1))
+ return EINVAL;
+
+ cmd->user_handle = (uintptr_t)cq;
+ cmd->cqe = cq_attr->cqe;
+ cmd->comp_vector = cq_attr->comp_vector;
+ cmd->comp_channel = cq_attr->channel ? cq_attr->channel->fd : -1;
+ cmd->comp_mask = 0;
+
+ if (cmd_core_size >= offsetof(struct ibv_create_cq_ex, flags) +
+ sizeof(cmd->flags) && cq_attr->comp_mask & IBV_CREATE_CQ_ATTR_FLAGS)
+ cmd->flags = cq_attr->flags;
+
+ err = write(context->cmd_fd, cmd, cmd_size);
+ if (err != cmd_size)
+ return errno;
+
+ (void)VALGRIND_MAKE_MEM_DEFINED(resp, resp_size);
+
+ cq->handle = resp->base.cq_handle;
+ cq->cqe = resp->base.cqe;
+ cq->context = context;
+
+ return 0;
+}
+
int ibv_cmd_poll_cq(struct ibv_cq *ibcq, int ne, struct ibv_wc *wc)
{
struct ibv_poll_cq cmd;
@@ -122,6 +122,33 @@ uint64_t __ibv_get_device_guid(struct ibv_device *device)
}
default_symver(__ibv_get_device_guid, ibv_get_device_guid);
+struct ibv_cq *__lib_ibv_create_cq_ex(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *cq_attr)
+{
+ struct verbs_context *vctx = verbs_get_ctx(context);
+ struct ibv_cq *cq;
+
+ pthread_mutex_lock(&context->mutex);
+
+ cq = ((struct verbs_ex_private *)vctx->priv)->create_cq_ex(context, cq_attr);
+
+ if (cq) {
+ cq->context = context;
+ cq->channel = cq_attr->channel;
+ if (cq->channel)
+ ++cq->channel->refcnt;
+ cq->cq_context = cq_attr->cq_context;
+ cq->comp_events_completed = 0;
+ cq->async_events_completed = 0;
+ pthread_mutex_init(&cq->mutex, NULL);
+ pthread_cond_init(&cq->cond, NULL);
+ }
+
+ pthread_mutex_unlock(&context->mutex);
+
+ return cq;
+}
+
struct ibv_context *__ibv_open_device(struct ibv_device *device)
{
struct verbs_device *verbs_device = verbs_get_device(device);
@@ -148,6 +175,8 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
if (!context)
goto err;
} else {
+ struct verbs_ex_private *priv;
+
/* Library now allocates the context */
context_ex = calloc(1, sizeof(*context_ex) +
verbs_device->size_of_context);
@@ -156,6 +185,14 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
goto err;
}
+ priv = calloc(1, sizeof(*priv));
+ if (!priv) {
+ errno = ENOMEM;
+ free(context_ex);
+ goto err;
+ }
+
+ context_ex->priv = priv;
context_ex->context.abi_compat = __VERBS_ABI_IS_EXTENDED;
context_ex->sz = sizeof(*context_ex);
@@ -177,6 +214,11 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
*/
context_ex->ABI_placeholder1 = (void (*)(void)) context_ex->ibv_create_flow;
context_ex->ABI_placeholder2 = (void (*)(void)) context_ex->ibv_destroy_flow;
+
+ if (context_ex->create_cq_ex) {
+ priv->create_cq_ex = context_ex->create_cq_ex;
+ context_ex->create_cq_ex = __lib_ibv_create_cq_ex;
+ }
}
context->device = device;
@@ -186,6 +228,7 @@ struct ibv_context *__ibv_open_device(struct ibv_device *device)
return context;
verbs_err:
+ free(context_ex->priv);
free(context_ex);
err:
close(cmd_fd);
@@ -204,6 +247,7 @@ int __ibv_close_device(struct ibv_context *context)
if (context_ex) {
struct verbs_device *verbs_device = verbs_get_device(context->device);
verbs_device->uninit_context(verbs_device, context);
+ free(context_ex->priv);
free(context_ex);
} else {
context->device->ops.free_context(context);
@@ -81,6 +81,11 @@ extern HIDDEN int abi_ver;
HIDDEN int ibverbs_init(struct ibv_device ***list);
+struct verbs_ex_private {
+ struct ibv_cq *(*create_cq_ex)(struct ibv_context *context,
+ struct ibv_create_cq_attr_ex *);
+};
+
#define IBV_INIT_CMD(cmd, size, opcode) \
do { \
if (abi_ver > 2) \
@@ -47,6 +47,7 @@ IBVERBS_1.0 {
ibv_cmd_reg_mr;
ibv_cmd_dereg_mr;
ibv_cmd_create_cq;
+ ibv_cmd_create_cq_ex;
ibv_cmd_poll_cq;
ibv_cmd_req_notify_cq;
ibv_cmd_resize_cq;
Adding ibv_create_cq_ex. This extended verbs follows the extension verbs scheme and hence could be extendible in the future for more features. The new command supports creation flags with timestamp. Signed-off-by: Matan Barak <matanb@mellanox.com> --- Makefile.am | 3 +- include/infiniband/driver.h | 9 ++++++ include/infiniband/kern-abi.h | 24 +++++++++++++-- include/infiniband/verbs.h | 63 ++++++++++++++++++++++++++++++++++++++ man/ibv_create_cq_ex.3 | 71 +++++++++++++++++++++++++++++++++++++++++++ src/cmd.c | 42 +++++++++++++++++++++++++ src/device.c | 44 +++++++++++++++++++++++++++ src/ibverbs.h | 5 +++ src/libibverbs.map | 1 + 9 files changed, 259 insertions(+), 3 deletions(-) create mode 100644 man/ibv_create_cq_ex.3