Add Enhanced Connection Established (ECE)
cover Add Enhanced Connection Established (ECE)
From: Leon Romanovsky <[email protected]>
Enhanced Connection Established or ECE is new negotiation scheme introduced in IBTA v1.4 to exchange extra information about nodes capabilities and later negotiate them at the connection establishment phase.
The RDMA-CM messages (REQ, REP, SIDR_REQ and SIDR_REP) were extended to carry two fields, one new and another gained new functionality:
* VendorID is a new field that indicates that common subset of vendor option bits are supported as indicated by that VendorID.
* AttributeModifier already exists, but overloaded to indicate which vendor options are supported by this VendorID.
This is kernel part of such functionality which is responsible to get data from librdmacm and properly create and handle RDMA-CM messages.
Thanks
Leon Romanovsky (9):
RDMA/cm: Add Enhanced Connection Establishment (ECE) bits
RDMA: Promote field_avail() macro to be general code RDMA/cm: Delete not implemented CM peer to peer communication RDMA/uapi: Add ECE definitions to UCMA
RDMA/ucma: Extend ucma_connect to receive ECE parameters RDMA/ucma: Deliver ECE parameters through UCMA events RDMA/cm: Send and receive ECE parameter over the wire RDMA/cma: Connect ECE to rdma_accept
RDMA/cma: Provide ECE reject reason
drivers/infiniband/core/cm.c | 48 ++++++++++++++++++------ drivers/infiniband/core/cma.c | 54 ++++++++++++++++++++++++--- drivers/infiniband/core/cma_priv.h | 1 + drivers/infiniband/core/ucma.c | 40 ++++++++++++++++---- drivers/infiniband/hw/efa/efa_verbs.c | 3 -- drivers/infiniband/hw/mlx4/main.c | 7 +--- drivers/infiniband/hw/mlx5/main.c | 41 ++++++++++---------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 18 ++++----- include/linux/kernel.h | 18 +++++++++ include/rdma/ib_cm.h | 11 +++++- include/rdma/ibta_vol1_c12.h | 6 +++ include/rdma/rdma_cm.h | 28 ++++++++++++-- include/uapi/rdma/rdma_user_cm.h | 15 +++++++- 13 files changed, 219 insertions(+), 71 deletions(-)
--
2.24.1
PATCH 1/9 RDMA/cm: Add Enhanced Connection Establishment (ECE) bits
From: Leon Romanovsky <[email protected]>
Extend REQ (request for communications), REP (reply to request for communication), rejected reason and SIDR_REP (service ID resolution response) structures with hardware vendor ID bits according to approved IBA Comment #9434.
--- include/rdma/ibta_vol1_c12.h | 6 ++++++ 1 file changed, 6 insertions(+)
include/rdma/ibta_vol1_c12.h +6 -0
@@ -38,6 +38,7 @@/* Table 106 REQ Message Contents */ #define CM_REQ_LOCAL_COMM_ID CM_FIELD32_LOC(struct cm_req_msg, 0, 32) +#define CM_REQ_VENDOR_ID CM_FIELD32_LOC(struct cm_req_msg, 5, 24)#define CM_REQ_SERVICE_ID CM_FIELD64_LOC(struct cm_req_msg, 8)#define CM_REQ_LOCAL_CA_GUID CM_FIELD64_LOC(struct cm_req_msg, 16)#define CM_REQ_LOCAL_Q_KEY CM_FIELD32_LOC(struct cm_req_msg, 28, 32)
@@ -119,8 +120,11 @@ CM_STRUCT(struct cm_rej_msg, 84 * 8 + 1184);#define CM_REP_REMOTE_COMM_ID CM_FIELD32_LOC(struct cm_rep_msg, 4, 32)#define CM_REP_LOCAL_Q_KEY CM_FIELD32_LOC(struct cm_rep_msg, 8, 32)#define CM_REP_LOCAL_QPN CM_FIELD32_LOC(struct cm_rep_msg, 12, 24) +#define CM_REP_VENDOR_ID_H CM_FIELD8_LOC(struct cm_rep_msg, 15, 8)#define CM_REP_LOCAL_EE_CONTEXT_NUMBER CM_FIELD32_LOC(struct cm_rep_msg, 16, 24) +#define CM_REP_VENDOR_ID_M CM_FIELD8_LOC(struct cm_rep_msg, 19, 8)#define CM_REP_STARTING_PSN CM_FIELD32_LOC(struct cm_rep_msg, 20, 24) +#define CM_REP_VENDOR_ID_L CM_FIELD8_LOC(struct cm_rep_msg, 23, 8)#define CM_REP_RESPONDER_RESOURCES CM_FIELD8_LOC(struct cm_rep_msg, 24, 8)#define CM_REP_INITIATOR_DEPTH CM_FIELD8_LOC(struct cm_rep_msg, 25, 8)#define CM_REP_TARGET_ACK_DELAY CM_FIELD8_LOC(struct cm_rep_msg, 26, 5)
@@ -201,7 +205,9 @@ CM_STRUCT(struct cm_sidr_req_msg, 16 * 8 + 1728);#define CM_SIDR_REP_STATUS CM_FIELD8_LOC(struct cm_sidr_rep_msg, 4, 8)#define CM_SIDR_REP_ADDITIONAL_INFORMATION_LENGTH \ CM_FIELD8_LOC(struct cm_sidr_rep_msg, 5, 8) +#define CM_SIDR_REP_VENDOR_ID_H CM_FIELD16_LOC(struct cm_sidr_rep_msg, 6, 16)#define CM_SIDR_REP_QPN CM_FIELD32_LOC(struct cm_sidr_rep_msg, 8, 24) +#define CM_SIDR_REP_VENDOR_ID_L CM_FIELD8_LOC(struct cm_sidr_rep_msg, 11, 8)#define CM_SIDR_REP_SERVICEID CM_FIELD64_LOC(struct cm_sidr_rep_msg, 12)#define CM_SIDR_REP_Q_KEY CM_FIELD32_LOC(struct cm_sidr_rep_msg, 20, 32)#define CM_SIDR_REP_ADDITIONAL_INFORMATION \
--
2.24.1
PATCH 2/9 RDMA: Promote field_avail() macro to be general code
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
Main usage of such macro is to check user <-> kernel communication in order to ensure that user supplied enough space to read/write tested field.
The field_avail() macro is used by several RDMA drivers and in next patches will be used for RDMA-CM code as well, so being general enough, let's promote the code to in kernel.h
--- drivers/infiniband/hw/efa/efa_verbs.c | 3 -- drivers/infiniband/hw/mlx4/main.c | 7 ++--- drivers/infiniband/hw/mlx5/main.c | 41 +++++++++++++-------------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 18 ++++++------ include/linux/kernel.h | 18 ++++++++++++ 5 files changed, 48 insertions(+), 39 deletions(-)
drivers/infiniband/hw/efa/efa_verbs.c +0 -3
@@ -144,9 +144,6 @@ static inline bool is_rdma_read_cap(struct efa_dev *dev)return dev->dev_attr.device_caps &EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK ; } -#define field_avail (x, fld, sz) (offsetof(typeof(x), fld) + \ - sizeof_field(typeof(x), fld) <= (sz)) -#define is_reserved_cleared (reserved) \ !memchr_inv(reserved, 0, sizeof(reserved))
drivers/infiniband/hw/mlx4/main.c +2 -5
@@ -434,9 +434,6 @@ int mlx4_ib_gid_index_to_real_index(struct mlx4_ib_dev *ibdev,return real_index; } -#define field_avail (type, fld, sz) (offsetof(type, fld) + \ - sizeof(((type *)0)->fld) <= (sz)) -static int mlx4_ib_query_device (struct ib_device *ibdev,struct ib_device_attr *props,struct ib_udata *uhw)
@@ -602,7 +599,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,sizeof (struct mlx4_wqe_data_seg ); } -if (field_avail (typeof (resp), rss_caps, uhw->outlen)) { +if (field_avail (resp, rss_caps, uhw->outlen)) {if (props->rss_caps.supported_qpts) { resp.rss_caps.rx_hash_function =MLX4_IB_RX_HASH_FUNC_TOEPLITZ ;
@@ -626,7 +623,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,sizeof (resp.rss_caps); } -if (field_avail (typeof (resp), tso_caps, uhw->outlen)) { +if (field_avail (resp, tso_caps, uhw->outlen)) { if (dev->dev->caps.max_gso_sz && ((mlx4_ib_port_link_layer(ibdev, 1) == IB_LINK_LAYER_ETHERNET) ||
drivers/infiniband/hw/mlx5/main.c +20 -21
141 lines not on this page · raw message
drivers/infiniband/hw/mlx5/mlx5_ib.h +8 -10
@@ -64,8 +64,6 @@dev_warn (&(_dev)->ib_dev.dev,"%s:%d:(pid %d): " format, __func__, \ __LINE__, current->pid, ##arg) -#define field_avail(type, fld, sz) (offsetof(type, fld) + \ - sizeof(((type *)0)->fld) <= (sz)) #define MLX5_IB_DEFAULT_UIDX 0xffffff #define MLX5_USER_ASSIGNED_UIDX_MASK __mlx5_mask(qpc, user_index)
@@ -1471,13 +1469,13 @@ static inline int get_qp_user_index(struct mlx5_ib_ucontext *ucontext, u32 *user_index) {u8 cqe_version = ucontext->cqe_version; +struct mlx5_ib_create_qp qp; - if (field_avail(struct mlx5_ib_create_qp, uidx, inlen) && - !cqe_version && (ucmd->uidx ==MLX5_IB_DEFAULT_UIDX )) +if (field_avail (qp, uidx, inlen) && !cqe_version && + (ucmd->uidx ==MLX5_IB_DEFAULT_UIDX ))return 0 ; - if (!!(field_avail(struct mlx5_ib_create_qp, uidx, inlen) != - !!cqe_version)) +if (field_avail (qp, uidx, inlen) != !!cqe_version)return -EINVAL ;return verify_assign_uidx (cqe_version, ucmd->uidx, user_index);
@@ -1489,13 +1487,13 @@ static inline int get_srq_user_index(struct mlx5_ib_ucontext *ucontext, u32 *user_index) {u8 cqe_version = ucontext->cqe_version; +struct mlx5_ib_create_srq srq; - if (field_avail(struct mlx5_ib_create_srq, uidx, inlen) && - !cqe_version && (ucmd->uidx ==MLX5_IB_DEFAULT_UIDX )) +if (field_avail (srq, uidx, inlen) && !cqe_version && + (ucmd->uidx ==MLX5_IB_DEFAULT_UIDX ))return 0 ; - if (!!(field_avail(struct mlx5_ib_create_srq, uidx, inlen) != - !!cqe_version)) +if (field_avail (srq, uidx, inlen) != !!cqe_version)return -EINVAL ;return verify_assign_uidx (cqe_version, ucmd->uidx, user_index);
include/linux/kernel.h +18 -0
@@ -79,6 +79,24 @@*/ #define round_down (x, y) ((x) & ~__round_mask(x, y)) +/** +* FIELD_SIZEOF - get the size of a struct's field +* @t: the target struct +* @f: the target struct's field +* Return: the size of @f in the struct definition without having a +* declared instance of @t. +*/ +#define FIELD_SIZEOF (t, f) (sizeof(((t*)0)->f)) + +/** +* field_avail - check if specific field exists in provided data +* @x: the source data, usually struct received from the user +* @fld: field name +* @sz: size of the data +*/ +#define field_avail (x, fld, sz) \ + (offsetof(typeof(x), fld) + FIELD_SIZEOF(typeof(x), fld) <= (sz)) +#define typeof_member (T , m) typeof(((T*)0)->m)#define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
--
2.24.1
Re: [PATCH rdma-next 2/9] RDMA: Promote field_avail() macro to be general code
include/linux/kernel.h line 89
Quoted 9 lines · Leon Romanovsky
include/linux/kernel.h +8
-0+/** +* FIELD_SIZEOF - get the size of a struct's field +* @t: the target struct +* @f: the target struct's field +* Return: the size of @f in the struct definition without having a +* declared instance of @t. +*/ +#define FIELD_SIZEOF (t, f) (sizeof(((t*)0)->f))
This is already sizeof_field
include/linux/kernel.h line 98
Quoted 8 lines
include/linux/kernel.h +8
-0+/** +* field_avail - check if specific field exists in provided data +* @x: the source data, usually struct received from the user +* @fld: field name +* @sz: size of the data +*/ +#define field_avail (x, fld, sz) \ + (offsetof(typeof(x), fld) + FIELD_SIZEOF(typeof(x), fld) <= (sz))
This is just offsetofend, I'm not sure there is such a reason to even have this field_avail macro really..
Jason
Re: [PATCH rdma-next 2/9] RDMA: Promote field_avail() macro to be general code
Quoted 12 lines · Jason Gunthorpe
include/linux/kernel.h line 89
Quoted 9 lines · Leon Romanovsky
include/linux/kernel.h +8
-0+/** +* FIELD_SIZEOF - get the size of a struct's field +* @t: the target struct +* @f: the target struct's field +* Return: the size of @f in the struct definition without having a +* declared instance of @t. +*/ +#define FIELD_SIZEOF (t, f) (sizeof(((t*)0)->f))This is already
sizeof_field
Ohh, thanks
Quoted 12 lines
include/linux/kernel.h line 98
Quoted 9 lines
include/linux/kernel.h +8
-0+/** +* field_avail - check if specific field exists in provided data +* @x: the source data, usually struct received from the user +* @fld: field name +* @sz: size of the data +*/ +#define field_avail (x, fld, sz) \ + (offsetof(typeof(x), fld) + FIELD_SIZEOF(typeof(x), fld) <= (sz))This is just offsetofend, I'm not sure there is such a reason to even have this
field_availmacro really..
Even better.
Thanks
Quoted 2 lines
Jason
PATCH 3/9 RDMA/cm: Delete not implemented CM peer to peer communication
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
Peer to peer support was never implemented, so delete it to make code less clutter.
--- drivers/infiniband/core/cm.c | 7 ------- include/rdma/ib_cm.h | 1 - 2 files changed, 8 deletions(-)
drivers/infiniband/core/cm.c +0 -7
@@ -261,7 +261,6 @@ struct cm_id_private {__be16 pkey;u8 private_data_len;u8 max_cm_retries; -u8 peer_to_peer;u8 responder_resources;u8 initiator_depth;u8 retry_count;
@@ -1380,10 +1379,6 @@ static void cm_format_req(struct cm_req_msg *req_msg,static int cm_validate_req_param (struct ib_cm_req_param *param) { -/* peer-to-peer not supported */ -if (param->peer_to_peer) -return -EINVAL ; -if (!param->primary_path)return -EINVAL ;
@@ -2436,8 +2431,6 @@ static int cm_rep_handler(struct cm_work *work)cm_ack_timeout (cm_id_priv->target_ack_delay, cm_id_priv->alt_av.timeout -1 ); -/* todo: handle peer_to_peer */ -ib_cancel_mad (cm_id_priv->av.port->mad_agent, cm_id_priv->msg); ret =atomic_inc_and_test (&cm_id_priv->work_count);if (!ret)
include/rdma/ib_cm.h +0 -1
@@ -360,7 +360,6 @@ struct ib_cm_req_param {u32 starting_psn;const void *private_data;u8 private_data_len; -u8 peer_to_peer;u8 responder_resources;u8 initiator_depth;u8 remote_cm_response_timeout;
--
2.24.1
PATCH 4/9 RDMA/uapi: Add ECE definitions to UCMA
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
ECE parameters are used to perform handshake between different CMID nodes in order to allow extra connection setup supported by those two nodes. The data is provided by rdma_connect() for the client and rdma_get_events() for the server.
--- include/uapi/rdma/rdma_user_cm.h | 7 +++++++ 1 file changed, 7 insertions(+)
include/uapi/rdma/rdma_user_cm.h +7 -0
@@ -206,10 +206,16 @@ struct rdma_ucm_ud_param {__u8 reserved[7 ]; }; +struct rdma_ucm_ece { +__u32 vendor_id; +__u32 attr_mod; +}; +struct rdma_ucm_connect {struct rdma_ucm_conn_param conn_param;__u32 id;__u32 reserved; +struct rdma_ucm_ece ece; };struct rdma_ucm_listen {
@@ -287,6 +293,7 @@ struct rdma_ucm_event_resp {struct rdma_ucm_ud_param ud; } param;__u32 reserved; +struct rdma_ucm_ece ece; };/* Option levels */
--
2.24.1
PATCH 5/9 RDMA/ucma: Extend ucma_connect to receive ECE parameters
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
Active side of CMID initiates connection through librdmacm's rdma_connect() and kernel's ucma_connect(). Extend UCMA interface to handle those new parameters.
--- drivers/infiniband/core/cma.c | 13 +++++++++++++ drivers/infiniband/core/cma_priv.h | 1 + drivers/infiniband/core/ucma.c | 14 +++++++++++--- include/rdma/rdma_cm.h | 11 +++++++++++ 4 files changed, 36 insertions(+), 3 deletions(-)
drivers/infiniband/core/cma.c +13 -0
@@ -4000,6 +4000,19 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) }EXPORT_SYMBOL (rdma_connect); +int rdma_connect_ece (struct rdma_cm_id *id,struct rdma_conn_param *conn_param, +struct rdma_ucm_ece *ece) +{ +struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + + id_priv->ece.vendor_id = ece->vendor_id; + id_priv->ece.attr_mod = ece->attr_mod; + +return rdma_connect (id, conn_param); +} +EXPORT_SYMBOL (rdma_connect_ece); +static int cma_accept_ib (struct rdma_id_private *id_priv,struct rdma_conn_param *conn_param) {
drivers/infiniband/core/cma_priv.h +1 -0
@@ -95,6 +95,7 @@ struct rdma_id_private {* Internal to RDMA/core, don't use in the drivers */ struct rdma_restrack_entry res; +struct rdma_ucm_ece ece; };#if IS_ENABLED (CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS )
drivers/infiniband/core/ucma.c +11 -3
@@ -1070,12 +1070,15 @@ static void ucma_copy_conn_param(struct rdma_cm_id *id,static ssize_t ucma_connect (struct ucma_file *file,const char __user *inbuf,int in_len,int out_len) { -struct rdma_ucm_connect cmd;struct rdma_conn_param conn_param; +struct rdma_ucm_ece ece = {}; +struct rdma_ucm_connect cmd;struct ucma_context *ctx; +size_t in_size;int ret; -if (copy_from_user (&cmd, inbuf,sizeof (cmd))) + in_size =min_t (size_t, in_len,sizeof (cmd)); +if (copy_from_user (&cmd, inbuf, in_size))return -EFAULT ;if (!cmd.conn_param.valid)
@@ -1086,8 +1089,13 @@ static ssize_t ucma_connect(struct ucma_file *file, const char __user *inbuf,return PTR_ERR (ctx);ucma_copy_conn_param (ctx->cm_id, &conn_param, &cmd.conn_param); +if (field_avail (cmd, ece, in_size)) { + ece.vendor_id = cmd.ece.vendor_id; + ece.attr_mod = cmd.ece.attr_mod; + } +mutex_lock (&ctx->mutex); - ret =rdma_connect (ctx->cm_id, &conn_param); + ret =rdma_connect_ece (ctx->cm_id, &conn_param, &ece);mutex_unlock (&ctx->mutex);ucma_put_ctx (ctx);return ret;
include/rdma/rdma_cm.h +11 -0
@@ -264,6 +264,17 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,*/ int rdma_connect (struct rdma_cm_id *id,struct rdma_conn_param *conn_param); +/** +* rdma_connect_ece - Initiate an active connection request with ECE data. +* @id: Connection identifier to connect. +* @conn_param: Connection information used for connected QPs. +* @ece: ECE parameters +* +* See rdma_connect() explanation. +*/ +int rdma_connect_ece (struct rdma_cm_id *id,struct rdma_conn_param *conn_param, +struct rdma_ucm_ece *ece); +/** * rdma_listen - This function is called by the passive side to * listen for incoming connection requests.
--
2.24.1
PATCH 6/9 RDMA/ucma: Deliver ECE parameters through UCMA events
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
Passive side of CMID connection receives ECE request through REQ message and needs to respond with relevant REP message which will be forwarded to active side.
The UCMA events interface is responsible for such communication with the user space (librdmacm). Extend it to provide ECE wire data.
--- drivers/infiniband/core/ucma.c | 6 +++++- include/rdma/rdma_cm.h | 1 + 2 files changed, 6 insertions(+), 1 deletion(-)
drivers/infiniband/core/ucma.c +5 -1
@@ -360,6 +360,9 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,ucma_copy_conn_event (&uevent->resp.param.conn, &event->param.conn); + uevent->resp.ece.vendor_id = event->ece.vendor_id; + uevent->resp.ece.attr_mod = event->ece.attr_mod; +if (event->event ==RDMA_CM_EVENT_CONNECT_REQUEST ) {if (!ctx->backlog) { ret = -ENOMEM ;
@@ -404,7 +407,8 @@ static ssize_t ucma_get_event(struct ucma_file *file, const char __user *inbuf,* Old 32 bit user space does not send the 4 byte padding in the * reserved field. We don't care, allow it to keep working. */ -if (out_len <sizeof (uevent->resp) -sizeof (uevent->resp.reserved)) +if (out_len <sizeof (uevent->resp) -sizeof (uevent->resp.reserved) - +sizeof (uevent->resp.ece))return -ENOSPC ;if (copy_from_user (&cmd, inbuf,sizeof (cmd)))
include/rdma/rdma_cm.h +1 -0
@@ -111,6 +111,7 @@ struct rdma_cm_event {struct rdma_conn_param conn;struct rdma_ud_param ud; } param; +struct rdma_ucm_ece ece; };struct rdma_cm_id ;
--
2.24.1
PATCH 7/9 RDMA/cm: Send and receive ECE parameter over the wire
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
ECE parameters are exchanged through REQ->REP/SIDR_REP messages, this patch adds the data to provide to other side of CMID communication channel.
--- drivers/infiniband/core/cm.c | 41 +++++++++++++++++++++++++++++----- drivers/infiniband/core/cma.c | 8 +++++++ drivers/infiniband/core/ucma.c | 1 - include/rdma/ib_cm.h | 9 +++++++- 4 files changed, 52 insertions(+), 7 deletions(-)
drivers/infiniband/core/cm.c +36 -5
@@ -66,6 +66,8 @@ static const char * const ibcm_rej_reason_strs[] = { [IB_CM_REJ_INVALID_CLASS_VERSION] = "invalid class version", [IB_CM_REJ_INVALID_FLOW_LABEL] = "invalid flow label", [IB_CM_REJ_INVALID_ALT_FLOW_LABEL] = "invalid alt flow label", + [IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED ] = + "vendor option is not supported", }; const char *__attribute_const__ ibcm_reject_msg(int reason)
@@ -276,6 +278,8 @@ struct cm_id_private {struct list_head work_list;atomic_t work_count; + +struct rdma_ucm_ece ece; };static void cm_work_handler (struct work_struct *work);
@@ -1235,6 +1239,13 @@ static void cm_format_mad_hdr(struct ib_mad_hdr *hdr, hdr->tid = tid; } +static void cm_format_mad_ece_hdr (struct ib_mad_hdr *hdr,__be16 attr_id, +__be64 tid,u32 attr_mod) +{ +cm_format_mad_hdr (hdr, attr_id, tid); + hdr->attr_mod =cpu_to_be32 (attr_mod); +} +static void cm_format_req (struct cm_req_msg *req_msg,struct cm_id_private *cm_id_priv,struct ib_cm_req_param *param)
@@ -1247,8 +1258,8 @@ static void cm_format_req(struct cm_req_msg *req_msg, pri_ext =opa_is_extended_lid (pri_path->opa.dlid, pri_path->opa.slid); -cm_format_mad_hdr (&req_msg->hdr,CM_REQ_ATTR_ID , -cm_form_tid (cm_id_priv)); +cm_format_mad_ece_hdr (&req_msg->hdr,CM_REQ_ATTR_ID , +cm_form_tid (cm_id_priv), param->ece.attr_mod);IBA_SET (CM_REQ_LOCAL_COMM_ID , req_msg,be32_to_cpu (cm_id_priv->id.local_id));
@@ -1371,6 +1382,7 @@ static void cm_format_req(struct cm_req_msg *req_msg,cm_ack_timeout (cm_id_priv->av.port->cm_dev->ack_delay, alt_path->packet_life_time)); } +IBA_SET (CM_REQ_VENDOR_ID , req_msg, param->ece.vendor_id);if (param->private_data && param->private_data_len) IBA_SET_MEM(CM_REQ_PRIVATE_DATA, req_msg, param->private_data,
@@ -1728,6 +1740,9 @@ static void cm_format_req_event(struct cm_work *work, param->rnr_retry_count =IBA_GET (CM_REQ_RNR_RETRY_COUNT , req_msg); param->srq =IBA_GET (CM_REQ_SRQ , req_msg); param->ppath_sgid_attr = cm_id_priv->av.ah_attr.grh.sgid_attr; + param->ece.vendor_id =IBA_GET (CM_REQ_VENDOR_ID , req_msg); + param->ece.attr_mod =be32_to_cpu (req_msg->hdr.attr_mod); + work->cm_event.private_data =IBA_GET_MEM_PTR (CM_REQ_PRIVATE_DATA , req_msg); }
@@ -2107,7 +2122,8 @@ static void cm_format_rep(struct cm_rep_msg *rep_msg,struct cm_id_private *cm_id_priv, struct ib_cm_rep_param *param) { - cm_format_mad_hdr(&rep_msg->hdr, CM_REP_ATTR_ID, cm_id_priv->tid); + cm_format_mad_ece_hdr(&rep_msg->hdr, CM_REP_ATTR_ID, cm_id_priv->tid, + param->ece.attr_mod);IBA_SET (CM_REP_LOCAL_COMM_ID , rep_msg,be32_to_cpu (cm_id_priv->id.local_id)); IBA_SET(CM_REP_REMOTE_COMM_ID, rep_msg,
@@ -2134,6 +2150,12 @@ static void cm_format_rep(struct cm_rep_msg *rep_msg,IBA_SET (CM_REP_LOCAL_EE_CONTEXT_NUMBER , rep_msg, param->qp_num); } +IBA_SET (CM_REP_VENDOR_ID_L , rep_msg, param->ece.vendor_id &0xFF ); +IBA_SET (CM_REP_VENDOR_ID_M , rep_msg, + (param->ece.vendor_id >>8 ) &0xFF ); +IBA_SET (CM_REP_VENDOR_ID_H , rep_msg, + (param->ece.vendor_id >>16 ) &0xFF ); +if (param->private_data && param->private_data_len)IBA_SET_MEM (CM_REP_PRIVATE_DATA , rep_msg, param->private_data, param->private_data_len);
@@ -2281,6 +2303,11 @@ static void cm_format_rep_event(struct cm_work *work, enum ib_qp_type qp_type) param->flow_control =IBA_GET (CM_REP_END_TO_END_FLOW_CONTROL , rep_msg); param->rnr_retry_count =IBA_GET (CM_REP_RNR_RETRY_COUNT , rep_msg); param->srq =IBA_GET (CM_REP_SRQ , rep_msg); + param->ece.vendor_id =IBA_GET (CM_REP_VENDOR_ID_H , rep_msg) <<16 ; + param->ece.vendor_id |=IBA_GET (CM_REP_VENDOR_ID_M , rep_msg) <<8 ; + param->ece.vendor_id |=IBA_GET (CM_REP_VENDOR_ID_L , rep_msg); + param->ece.attr_mod =be32_to_cpu (rep_msg->hdr.attr_mod); + work->cm_event.private_data =IBA_GET_MEM_PTR (CM_REP_PRIVATE_DATA , rep_msg); }
@@ -3565,8 +3592,8 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,struct cm_id_private *cm_id_priv, struct ib_cm_sidr_rep_param *param) { - cm_format_mad_hdr(&sidr_rep_msg->hdr, CM_SIDR_REP_ATTR_ID, - cm_id_priv->tid); + cm_format_mad_ece_hdr(&sidr_rep_msg->hdr, CM_SIDR_REP_ATTR_ID, + cm_id_priv->tid, param->ece.attr_mod);IBA_SET (CM_SIDR_REP_REQUESTID , sidr_rep_msg,be32_to_cpu (cm_id_priv->id.remote_id));IBA_SET (CM_SIDR_REP_STATUS , sidr_rep_msg, param->status);
@@ -3574,6 +3601,10 @@ static void cm_format_sidr_rep(struct cm_sidr_rep_msg *sidr_rep_msg,IBA_SET (CM_SIDR_REP_SERVICEID , sidr_rep_msg,be64_to_cpu (cm_id_priv->id.service_id));IBA_SET (CM_SIDR_REP_Q_KEY , sidr_rep_msg, param->qkey); +IBA_SET (CM_SIDR_REP_VENDOR_ID_L , sidr_rep_msg, + param->ece.vendor_id &0xFF ); +IBA_SET (CM_SIDR_REP_VENDOR_ID_H , sidr_rep_msg, + (param->ece.vendor_id >>8 ) &0xFF );if (param->info && param->info_length) IBA_SET_MEM(CM_SIDR_REP_ADDITIONAL_INFORMATION, sidr_rep_msg,
drivers/infiniband/core/cma.c +8 -0
@@ -1906,6 +1906,9 @@ static void cma_set_rep_event_data(struct rdma_cm_event *event, event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; + + event->ece.vendor_id = rep_data->ece.vendor_id; + event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv,
@@ -2124,6 +2127,9 @@ static void cma_set_req_event_data(struct rdma_cm_event *event, event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; + + event->ece.vendor_id = req_data->ece.vendor_id; + event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id,
@@ -3911,6 +3917,8 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, req.local_cm_response_timeout =CMA_CM_RESPONSE_TIMEOUT ; req.max_cm_retries =CMA_MAX_CM_RETRIES ; req.srq = id_priv->srq ?1 :0 ; + req.ece.vendor_id = id_priv->ece.vendor_id; + req.ece.attr_mod = id_priv->ece.attr_mod;trace_cm_send_req (id_priv); ret =ib_send_cm_req (id_priv->cm_id.ib, &req);
drivers/infiniband/core/ucma.c +0 -1
@@ -362,7 +362,6 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id, uevent->resp.ece.vendor_id = event->ece.vendor_id; uevent->resp.ece.attr_mod = event->ece.attr_mod; -if (event->event ==RDMA_CM_EVENT_CONNECT_REQUEST ) {if (!ctx->backlog) { ret = -ENOMEM ;
include/rdma/ib_cm.h +8 -1
@@ -11,6 +11,7 @@#include <rdma/ib_mad.h> #include <rdma/ib_sa.h> +#include <rdma/rdma_cm.h> /* ib_cm and ib_user_cm modules share /sys/class/infiniband_cm */ extern struct class cm_class;
@@ -115,6 +116,7 @@ struct ib_cm_req_event_param { unsigned int retry_count:3; unsigned int rnr_retry_count:3; unsigned int srq:1; +struct rdma_ucm_ece ece; };struct ib_cm_rep_event_param {
@@ -129,6 +131,7 @@ struct ib_cm_rep_event_param { unsigned int flow_control:1; unsigned int rnr_retry_count:3; unsigned int srq:1; +struct rdma_ucm_ece ece; };enum ib_cm_rej_reason {
@@ -164,7 +167,8 @@ enum ib_cm_rej_reason {IB_CM_REJ_DUPLICATE_LOCAL_COMM_ID =30 ,IB_CM_REJ_INVALID_CLASS_VERSION =31 ,IB_CM_REJ_INVALID_FLOW_LABEL =32 , -IB_CM_REJ_INVALID_ALT_FLOW_LABEL =33 +IB_CM_REJ_INVALID_ALT_FLOW_LABEL =33 , + IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED = 35, }; struct ib_cm_rej_event_param {
@@ -369,6 +373,7 @@ struct ib_cm_req_param {u8 rnr_retry_count;u8 max_cm_retries;u8 srq; +struct rdma_ucm_ece ece; };/**
@@ -392,6 +397,7 @@ struct ib_cm_rep_param {u8 flow_control;u8 rnr_retry_count;u8 srq; +struct rdma_ucm_ece ece; };/**
@@ -546,6 +552,7 @@ struct ib_cm_sidr_rep_param {u8 info_length;const void *private_data;u8 private_data_len; +struct rdma_ucm_ece ece; };/**
--
2.24.1
PATCH 8/9 RDMA/cma: Connect ECE to rdma_accept
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
The rdma_accept() is called by both passive and active sides of CMID connection to mark readiness to start data transfer. For passive side, this is called explicitly, for active side, it is called implicitly while receiving REP message.
Provide ECE data to rdma_accept function needed for passive side to send that REP message.
--- drivers/infiniband/core/cma.c | 19 +++++++++++++++++++ drivers/infiniband/core/ucma.c | 14 +++++++++++--- include/rdma/rdma_cm.h | 3 +++ include/uapi/rdma/rdma_user_cm.h | 1 + 4 files changed, 34 insertions(+), 3 deletions(-)
drivers/infiniband/core/cma.c +19 -0
@@ -4046,6 +4046,8 @@ static int cma_accept_ib(struct rdma_id_private *id_priv, rep.flow_control = conn_param->flow_control; rep.rnr_retry_count =min_t (u8,7 , conn_param->rnr_retry_count); rep.srq = id_priv->srq ?1 :0 ; + rep.ece.vendor_id = id_priv->ece.vendor_id; + rep.ece.attr_mod = id_priv->ece.attr_mod;trace_cm_send_rep (id_priv); ret =ib_send_cm_rep (id_priv->cm_id.ib, &rep);
@@ -4093,7 +4095,11 @@ static int cma_send_sidr_rep(struct rdma_id_private *id_priv,return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; + + rep.ece.vendor_id = id_priv->ece.vendor_id; + rep.ece.attr_mod = id_priv->ece.attr_mod; } + rep.private_data = private_data; rep.private_data_len = private_data_len;
@@ -4151,6 +4157,19 @@ int __rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, }EXPORT_SYMBOL (__rdma_accept); +int __rdma_accept_ece (struct rdma_cm_id *id,struct rdma_conn_param *conn_param, +const char *caller,struct rdma_ucm_ece *ece) +{ +struct rdma_id_private *id_priv = + container_of(id, struct rdma_id_private, id); + + id_priv->ece.vendor_id = ece->vendor_id; + id_priv->ece.attr_mod = ece->attr_mod; + +return __rdma_accept (id, conn_param, caller); +} +EXPORT_SYMBOL (__rdma_accept_ece); +int rdma_notify (struct rdma_cm_id *id,enum ib_event_type event) {struct rdma_id_private *id_priv;
drivers/infiniband/core/ucma.c +11 -3
@@ -1132,28 +1132,36 @@ static ssize_t ucma_accept(struct ucma_file *file, const char __user *inbuf, {struct rdma_ucm_accept cmd;struct rdma_conn_param conn_param; +struct rdma_ucm_ece ece = {};struct ucma_context *ctx; +size_t in_size;int ret; -if (copy_from_user (&cmd, inbuf,sizeof (cmd))) + in_size =min_t (size_t, in_len,sizeof (cmd)); +if (copy_from_user (&cmd, inbuf, in_size))return -EFAULT ; ctx =ucma_get_ctx_dev (file, cmd.id);if (IS_ERR (ctx))return PTR_ERR (ctx); +if (field_avail (cmd, ece, in_size)) { + ece.vendor_id = cmd.ece.vendor_id; + ece.attr_mod = cmd.ece.attr_mod; + } +if (cmd.conn_param.valid) {ucma_copy_conn_param (ctx->cm_id, &conn_param, &cmd.conn_param);mutex_lock (&file->mut);mutex_lock (&ctx->mutex); - ret =__rdma_accept (ctx->cm_id, &conn_param,NULL ); + ret =__rdma_accept_ece (ctx->cm_id, &conn_param,NULL , &ece);mutex_unlock (&ctx->mutex);if (!ret) ctx->uid = cmd.uid;mutex_unlock (&file->mut); }else {mutex_lock (&ctx->mutex); - ret =__rdma_accept (ctx->cm_id,NULL ,NULL ); + ret =__rdma_accept_ece (ctx->cm_id,NULL ,NULL , &ece);mutex_unlock (&ctx->mutex); }ucma_put_ctx (ctx);
include/rdma/rdma_cm.h +3 -0
@@ -288,6 +288,9 @@ int rdma_listen(struct rdma_cm_id *id, int backlog);int __rdma_accept (struct rdma_cm_id *id,struct rdma_conn_param *conn_param,const char *caller); +int __rdma_accept_ece (struct rdma_cm_id *id,struct rdma_conn_param *conn_param, +const char *caller,struct rdma_ucm_ece *ece); +/** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request.
include/uapi/rdma/rdma_user_cm.h +1 -0
@@ -228,6 +228,7 @@ struct rdma_ucm_accept {struct rdma_ucm_conn_param conn_param;__u32 id;__u32 reserved; +struct rdma_ucm_ece ece; };struct rdma_ucm_reject {
--
2.24.1
PATCH 9/9 RDMA/cma: Provide ECE reject reason
In reply to Leon RomanovskyFrom: Leon Romanovsky <[email protected]>
IBTA declares "vendor option not supported" reject reason in REJ messages if passive side doesn't want to accept proposed ECE options.
Due to the fact that ECE is managed by userspace, there is a need to let users to provide such rejected reason.
--- drivers/infiniband/core/cma.c | 14 ++++++++------ drivers/infiniband/core/ucma.c | 7 ++++++- include/rdma/ib_cm.h | 3 ++- include/rdma/rdma_cm.h | 13 ++++++++++--- include/uapi/rdma/rdma_user_cm.h | 7 ++++++- 5 files changed, 32 insertions(+), 12 deletions(-)
drivers/infiniband/core/cma.c +8 -6
@@ -4191,8 +4191,8 @@ int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) }EXPORT_SYMBOL (rdma_notify); -int rdma_reject (struct rdma_cm_id *id,const void *private_data, -u8 private_data_len) +int rdma_reject_ece (struct rdma_cm_id *id,const void *private_data, +u8 private_data_len,enum rdma_ucm_reject_reason reason) {struct rdma_id_private *id_priv;int ret;
@@ -4206,10 +4206,12 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data, ret =cma_send_sidr_rep (id_priv,IB_SIDR_REJECT ,0 , private_data, private_data_len); }else { +enum ib_cm_rej_reason r = + (reason) ?:IB_CM_REJ_CONSUMER_DEFINED ; +trace_cm_send_rej (id_priv); - ret =ib_send_cm_rej (id_priv->cm_id.ib, -IB_CM_REJ_CONSUMER_DEFINED ,NULL , -0 , private_data, private_data_len); + ret =ib_send_cm_rej (id_priv->cm_id.ib, r,NULL ,0 , + private_data, private_data_len); } }else if (rdma_cap_iw_cm (id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw,
@@ -4219,7 +4221,7 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,return ret; } -EXPORT_SYMBOL (rdma_reject); +EXPORT_SYMBOL (rdma_reject_ece);int rdma_disconnect (struct rdma_cm_id *id) {
drivers/infiniband/core/ucma.c +6 -1
@@ -1178,12 +1178,17 @@ static ssize_t ucma_reject(struct ucma_file *file, const char __user *inbuf,if (copy_from_user (&cmd, inbuf,sizeof (cmd)))return -EFAULT ; +if (cmd.reason && + cmd.reason !=RDMA_USER_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED ) +return -EINVAL ; + ctx =ucma_get_ctx_dev (file, cmd.id);if (IS_ERR (ctx))return PTR_ERR (ctx);mutex_lock (&ctx->mutex); - ret =rdma_reject (ctx->cm_id, cmd.private_data, cmd.private_data_len); + ret =rdma_reject_ece (ctx->cm_id, cmd.private_data, + cmd.private_data_len, cmd.reason);mutex_unlock (&ctx->mutex);ucma_put_ctx (ctx);return ret;
include/rdma/ib_cm.h +2 -1
@@ -168,7 +168,8 @@ enum ib_cm_rej_reason {IB_CM_REJ_INVALID_CLASS_VERSION =31 ,IB_CM_REJ_INVALID_FLOW_LABEL =32 ,IB_CM_REJ_INVALID_ALT_FLOW_LABEL =33 , - IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED = 35, +IB_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED = + RDMA_USER_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED, }; struct ib_cm_rej_event_param {
include/rdma/rdma_cm.h +10 -3
@@ -324,11 +324,18 @@ int __rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param,*/ int rdma_notify (struct rdma_cm_id *id,enum ib_event_type event); +/** -* rdma_reject - Called to reject a connection request or response. +* rdma_reject_ece - Called to reject a connection request or response. */ -int rdma_reject (struct rdma_cm_id *id,const void *private_data, -u8 private_data_len); +int rdma_reject_ece (struct rdma_cm_id *id,const void *private_data, +u8 private_data_len,enum rdma_ucm_reject_reason reason); + +static inline int rdma_reject (struct rdma_cm_id *id,const void *private_data, +u8 private_data_len) +{ +return rdma_reject_ece (id, private_data, private_data_len,0 ); +}/** * rdma_disconnect - This function disconnects the associated QP and
include/uapi/rdma/rdma_user_cm.h +6 -1
@@ -78,6 +78,10 @@ enum rdma_ucm_port_space { RDMA_PS_UDP = 0x0111, }; +enum rdma_ucm_reject_reason { +RDMA_USER_CM_REJ_VENDOR_OPTION_NOT_SUPPORTED =35 +}; +/* * command ABI structures. */
@@ -234,7 +238,8 @@ struct rdma_ucm_accept {struct rdma_ucm_reject {__u32 id;__u8 private_data_len; -__u8 reserved[3 ]; +__u8 reason;/* enum rdma_ucm_reject_reason */ +__u8 reserved[2 ];__u8 private_data[RDMA_MAX_PRIVATE_DATA ]; };
--
2.24.1