2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-26 22:24:09 +08:00
linux-next/drivers/infiniband/sw/rxe/rxe_loc.h

287 lines
7.9 KiB
C
Raw Normal View History

Soft RoCE driver Soft RoCE (RXE) - The software RoCE driver ib_rxe implements the RDMA transport and registers to the RDMA core device as a kernel verbs provider. It also implements the packet IO layer. On the other hand ib_rxe registers to the Linux netdev stack as a udp encapsulating protocol, in that case RDMA, for sending and receiving packets over any Ethernet device. This yields a RDMA transport over the UDP/Ethernet network layer forming a RoCEv2 compatible device. The configuration procedure of the Soft RoCE drivers requires binding to any existing Ethernet network device. This is done with /sys interface. A userspace Soft RoCE library (librxe) provides user applications the ability to run with Soft RoCE devices. The use of rxe verbs ins user space requires the inclusion of librxe as a device specifics plug-in to libibverbs. librxe is packaged separately. Architecture: +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ +---------------------------------------------------------------+ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Soft RoCE resources: [1[ https://github.com/SoftRoCE/librxe-dev librxe - source code in Github [2] https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home - Soft RoCE Wiki page [3] https://github.com/SoftRoCE/librxe-dev - Soft RoCE userspace library Signed-off-by: Kamal Heib <kamalh@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Reviewed-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-06-16 21:45:23 +08:00
/*
* Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved.
* Copyright (c) 2015 System Fabric Works, Inc. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef RXE_LOC_H
#define RXE_LOC_H
/* rxe_av.c */
int rxe_av_chk_attr(struct rxe_dev *rxe, struct ib_ah_attr *attr);
int rxe_av_from_attr(struct rxe_dev *rxe, u8 port_num,
struct rxe_av *av, struct ib_ah_attr *attr);
int rxe_av_to_attr(struct rxe_dev *rxe, struct rxe_av *av,
struct ib_ah_attr *attr);
int rxe_av_fill_ip_info(struct rxe_dev *rxe,
struct rxe_av *av,
struct ib_ah_attr *attr,
struct ib_gid_attr *sgid_attr,
union ib_gid *sgid);
struct rxe_av *rxe_get_av(struct rxe_pkt_info *pkt);
/* rxe_cq.c */
int rxe_cq_chk_attr(struct rxe_dev *rxe, struct rxe_cq *cq,
int cqe, int comp_vector, struct ib_udata *udata);
int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
int comp_vector, struct ib_ucontext *context,
struct ib_udata *udata);
int rxe_cq_resize_queue(struct rxe_cq *cq, int new_cqe, struct ib_udata *udata);
int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited);
void rxe_cq_cleanup(void *arg);
/* rxe_mcast.c */
int rxe_mcast_get_grp(struct rxe_dev *rxe, union ib_gid *mgid,
struct rxe_mc_grp **grp_p);
int rxe_mcast_add_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
struct rxe_mc_grp *grp);
int rxe_mcast_drop_grp_elem(struct rxe_dev *rxe, struct rxe_qp *qp,
union ib_gid *mgid);
void rxe_drop_all_mcast_groups(struct rxe_qp *qp);
void rxe_mc_cleanup(void *arg);
/* rxe_mmap.c */
struct rxe_mmap_info {
struct list_head pending_mmaps;
struct ib_ucontext *context;
struct kref ref;
void *obj;
struct mminfo info;
};
void rxe_mmap_release(struct kref *ref);
struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *dev,
u32 size,
struct ib_ucontext *context,
void *obj);
int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
/* rxe_mr.c */
enum copy_direction {
to_mem_obj,
from_mem_obj,
};
int rxe_mem_init_dma(struct rxe_dev *rxe, struct rxe_pd *pd,
int access, struct rxe_mem *mem);
int rxe_mem_init_user(struct rxe_dev *rxe, struct rxe_pd *pd, u64 start,
u64 length, u64 iova, int access, struct ib_udata *udata,
struct rxe_mem *mr);
int rxe_mem_init_fast(struct rxe_dev *rxe, struct rxe_pd *pd,
int max_pages, struct rxe_mem *mem);
int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr,
int length, enum copy_direction dir, u32 *crcp);
int copy_data(struct rxe_dev *rxe, struct rxe_pd *pd, int access,
struct rxe_dma_info *dma, void *addr, int length,
enum copy_direction dir, u32 *crcp);
void *iova_to_vaddr(struct rxe_mem *mem, u64 iova, int length);
enum lookup_type {
lookup_local,
lookup_remote,
};
struct rxe_mem *lookup_mem(struct rxe_pd *pd, int access, u32 key,
enum lookup_type type);
int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length);
int rxe_mem_map_pages(struct rxe_dev *rxe, struct rxe_mem *mem,
u64 *page, int num_pages, u64 iova);
void rxe_mem_cleanup(void *arg);
int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
/* rxe_qp.c */
int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init);
int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd,
struct ib_qp_init_attr *init, struct ib_udata *udata,
struct ib_pd *ibpd);
int rxe_qp_to_init(struct rxe_qp *qp, struct ib_qp_init_attr *init);
int rxe_qp_chk_attr(struct rxe_dev *rxe, struct rxe_qp *qp,
struct ib_qp_attr *attr, int mask);
int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr,
int mask, struct ib_udata *udata);
int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask);
void rxe_qp_error(struct rxe_qp *qp);
void rxe_qp_destroy(struct rxe_qp *qp);
void rxe_qp_cleanup(void *arg);
static inline int qp_num(struct rxe_qp *qp)
{
return qp->ibqp.qp_num;
}
static inline enum ib_qp_type qp_type(struct rxe_qp *qp)
{
return qp->ibqp.qp_type;
}
static inline enum ib_qp_state qp_state(struct rxe_qp *qp)
{
return qp->attr.qp_state;
}
static inline int qp_mtu(struct rxe_qp *qp)
{
if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC)
return qp->attr.path_mtu;
else
return RXE_PORT_MAX_MTU;
}
static inline int rcv_wqe_size(int max_sge)
{
return sizeof(struct rxe_recv_wqe) +
max_sge * sizeof(struct ib_sge);
}
void free_rd_atomic_resource(struct rxe_qp *qp, struct resp_res *res);
static inline void rxe_advance_resp_resource(struct rxe_qp *qp)
{
qp->resp.res_head++;
if (unlikely(qp->resp.res_head == qp->attr.max_dest_rd_atomic))
Soft RoCE driver Soft RoCE (RXE) - The software RoCE driver ib_rxe implements the RDMA transport and registers to the RDMA core device as a kernel verbs provider. It also implements the packet IO layer. On the other hand ib_rxe registers to the Linux netdev stack as a udp encapsulating protocol, in that case RDMA, for sending and receiving packets over any Ethernet device. This yields a RDMA transport over the UDP/Ethernet network layer forming a RoCEv2 compatible device. The configuration procedure of the Soft RoCE drivers requires binding to any existing Ethernet network device. This is done with /sys interface. A userspace Soft RoCE library (librxe) provides user applications the ability to run with Soft RoCE devices. The use of rxe verbs ins user space requires the inclusion of librxe as a device specifics plug-in to libibverbs. librxe is packaged separately. Architecture: +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ +---------------------------------------------------------------+ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +-----------------------------------------------------------+ | Application | +-----------------------------------------------------------+ +-----------------------------------+ | libibverbs | User +-----------------------------------+ +----------------+ +----------------+ | librxe | | HW RoCE lib | +----------------+ +----------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +--------------+ +------------+ | Sockets | | RDMA ULP | +--------------+ +------------+ +--------------+ +---------------------+ | TCP/IP | | ib_core | +--------------+ +---------------------+ +------------+ +----------------+ Kernel | ib_rxe | | HW RoCE driver | +------------+ +----------------+ +------------------------------------+ | NIC driver | +------------------------------------+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Soft RoCE resources: [1[ https://github.com/SoftRoCE/librxe-dev librxe - source code in Github [2] https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home - Soft RoCE Wiki page [3] https://github.com/SoftRoCE/librxe-dev - Soft RoCE userspace library Signed-off-by: Kamal Heib <kamalh@mellanox.com> Signed-off-by: Amir Vadai <amirv@mellanox.com> Signed-off-by: Moni Shoua <monis@mellanox.com> Reviewed-by: Haggai Eran <haggaie@mellanox.com> Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-06-16 21:45:23 +08:00
qp->resp.res_head = 0;
}
void retransmit_timer(unsigned long data);
void rnr_nak_timer(unsigned long data);
void dump_qp(struct rxe_qp *qp);
/* rxe_srq.c */
#define IB_SRQ_INIT_MASK (~IB_SRQ_LIMIT)
int rxe_srq_chk_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
struct ib_srq_attr *attr, enum ib_srq_attr_mask mask);
int rxe_srq_from_init(struct rxe_dev *rxe, struct rxe_srq *srq,
struct ib_srq_init_attr *init,
struct ib_ucontext *context, struct ib_udata *udata);
int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
struct ib_srq_attr *attr, enum ib_srq_attr_mask mask,
struct ib_udata *udata);
extern struct ib_dma_mapping_ops rxe_dma_mapping_ops;
void rxe_release(struct kref *kref);
int rxe_completer(void *arg);
int rxe_requester(void *arg);
int rxe_responder(void *arg);
u32 rxe_icrc_hdr(struct rxe_pkt_info *pkt, struct sk_buff *skb);
void rxe_resp_queue_pkt(struct rxe_dev *rxe,
struct rxe_qp *qp, struct sk_buff *skb);
void rxe_comp_queue_pkt(struct rxe_dev *rxe,
struct rxe_qp *qp, struct sk_buff *skb);
static inline unsigned wr_opcode_mask(int opcode, struct rxe_qp *qp)
{
return rxe_wr_opcode_info[opcode].mask[qp->ibqp.qp_type];
}
static inline int rxe_xmit_packet(struct rxe_dev *rxe, struct rxe_qp *qp,
struct rxe_pkt_info *pkt, struct sk_buff *skb)
{
int err;
int is_request = pkt->mask & RXE_REQ_MASK;
if ((is_request && (qp->req.state != QP_STATE_READY)) ||
(!is_request && (qp->resp.state != QP_STATE_READY))) {
pr_info("Packet dropped. QP is not in ready state\n");
goto drop;
}
if (pkt->mask & RXE_LOOPBACK_MASK) {
memcpy(SKB_TO_PKT(skb), pkt, sizeof(*pkt));
err = rxe->ifc_ops->loopback(skb);
} else {
err = rxe->ifc_ops->send(rxe, pkt, skb);
}
if (err) {
rxe->xmit_errors++;
return err;
}
atomic_inc(&qp->skb_out);
if ((qp_type(qp) != IB_QPT_RC) &&
(pkt->mask & RXE_END_MASK)) {
pkt->wqe->state = wqe_state_done;
rxe_run_task(&qp->comp.task, 1);
}
goto done;
drop:
kfree_skb(skb);
err = 0;
done:
return err;
}
#endif /* RXE_LOC_H */