diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 00:53:26 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-06-24 00:53:26 +0200 |
commit | f9d1b5a31ab02208e29631756630739175cdaa02 (patch) | |
tree | 65cc0f69edd1b7198f9c4428e56942d054de0562 /net | |
parent | Merge branch 'for-linus-clk' of git://ftp.arm.linux.org.uk/~rmk/linux-arm (diff) | |
parent | IB/mad: Add final OPA MAD processing (diff) | |
download | linux-f9d1b5a31ab02208e29631756630739175cdaa02.tar.xz linux-f9d1b5a31ab02208e29631756630739175cdaa02.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma updates from Doug Ledford:
- a large cleanup of how device capabilities are checked for various
features
- additional cleanups in the MAD processing
- update to the srp driver
- creation and use of centralized log message helpers
- add const to a number of args to calls and clean up call chain
- add support for extended cq create verb
- add support for timestamps on cq completion
- add support for processing OPA MAD packets
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (92 commits)
IB/mad: Add final OPA MAD processing
IB/mad: Add partial Intel OPA MAD support
IB/mad: Add partial Intel OPA MAD support
IB/core: Add OPA MAD core capability flag
IB/mad: Add support for additional MAD info to/from drivers
IB/mad: Convert allocations from kmem_cache to kzalloc
IB/core: Add ability for drivers to report an alternate MAD size.
IB/mad: Support alternate Base Versions when creating MADs
IB/mad: Create a generic helper for DR forwarding checks
IB/mad: Create a generic helper for DR SMP Recv processing
IB/mad: Create a generic helper for DR SMP Send processing
IB/mad: Split IB SMI handling from MAD Recv handler
IB/mad cleanup: Generalize processing of MAD data
IB/mad cleanup: Clean up function params -- find_mad_agent
IB/mlx4: Add support for CQ time-stamping
IB/mlx4: Add mmap call to map the hardware clock
IB/core: Pass hardware specific data in query_device
IB/core: Add timestamp_mask and hca_core_clock to query_device
IB/core: Extend ib_uverbs_create_cq
IB/core: Add CQ creation time-stamping flag
...
Diffstat (limited to 'net')
-rw-r--r-- | net/9p/trans_rdma.c | 4 | ||||
-rw-r--r-- | net/rds/af_rds.c | 9 | ||||
-rw-r--r-- | net/rds/ib.h | 1 | ||||
-rw-r--r-- | net/rds/ib_cm.c | 43 | ||||
-rw-r--r-- | net/rds/ib_recv.c | 4 | ||||
-rw-r--r-- | net/rds/ib_send.c | 55 | ||||
-rw-r--r-- | net/rds/iw_cm.c | 7 | ||||
-rw-r--r-- | net/rds/iw_send.c | 18 | ||||
-rw-r--r-- | net/rds/rdma_transport.c | 34 | ||||
-rw-r--r-- | net/rds/rds.h | 3 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/frwr_ops.c | 4 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 4 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_transport.c | 83 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/verbs.c | 99 |
14 files changed, 102 insertions, 266 deletions
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 3533d2a53ab6..37a78d20c0f6 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -648,6 +648,7 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) struct rdma_conn_param conn_param; struct ib_qp_init_attr qp_attr; struct ib_device_attr devattr; + struct ib_cq_init_attr cq_attr = {}; /* Parse the transport specific mount options */ err = parse_opts(args, &opts); @@ -705,9 +706,10 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args) goto error; /* Create the Completion Queue */ + cq_attr.cqe = opts.sq_depth + opts.rq_depth + 1; rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler, cq_event_handler, client, - opts.sq_depth + opts.rq_depth + 1, 0); + &cq_attr); if (IS_ERR(rdma->cq)) goto error; ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP); diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 10443377fb9d..11b623c2840c 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -40,15 +40,6 @@ #include "rds.h" -char *rds_str_array(char **array, size_t elements, size_t index) -{ - if ((index < elements) && array[index]) - return array[index]; - else - return "unknown"; -} -EXPORT_SYMBOL(rds_str_array); - /* this is just used for stats gathering :/ */ static DEFINE_SPINLOCK(rds_sock_lock); static unsigned long rds_sock_count; diff --git a/net/rds/ib.h b/net/rds/ib.h index c36d713229e0..333611d9e07d 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -339,7 +339,6 @@ u32 rds_ib_ring_completed(struct rds_ib_work_ring *ring, u32 wr_id, u32 oldest); extern wait_queue_head_t rds_ib_ring_empty_wait; /* ib_send.c */ -char *rds_ib_wc_status_str(enum ib_wc_status status); void rds_ib_xmit_complete(struct rds_connection *conn); int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, unsigned int hdr_off, unsigned int sg, unsigned int off); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 8a09ee7db3c1..0da2a45b33bd 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -39,36 +39,6 @@ #include "rds.h" #include "ib.h" -static char *rds_ib_event_type_strings[] = { -#define RDS_IB_EVENT_STRING(foo) \ - [IB_EVENT_##foo] = __stringify(IB_EVENT_##foo) - RDS_IB_EVENT_STRING(CQ_ERR), - RDS_IB_EVENT_STRING(QP_FATAL), - RDS_IB_EVENT_STRING(QP_REQ_ERR), - RDS_IB_EVENT_STRING(QP_ACCESS_ERR), - RDS_IB_EVENT_STRING(COMM_EST), - RDS_IB_EVENT_STRING(SQ_DRAINED), - RDS_IB_EVENT_STRING(PATH_MIG), - RDS_IB_EVENT_STRING(PATH_MIG_ERR), - RDS_IB_EVENT_STRING(DEVICE_FATAL), - RDS_IB_EVENT_STRING(PORT_ACTIVE), - RDS_IB_EVENT_STRING(PORT_ERR), - RDS_IB_EVENT_STRING(LID_CHANGE), - RDS_IB_EVENT_STRING(PKEY_CHANGE), - RDS_IB_EVENT_STRING(SM_CHANGE), - RDS_IB_EVENT_STRING(SRQ_ERR), - RDS_IB_EVENT_STRING(SRQ_LIMIT_REACHED), - RDS_IB_EVENT_STRING(QP_LAST_WQE_REACHED), - RDS_IB_EVENT_STRING(CLIENT_REREGISTER), -#undef RDS_IB_EVENT_STRING -}; - -static char *rds_ib_event_str(enum ib_event_type type) -{ - return rds_str_array(rds_ib_event_type_strings, - ARRAY_SIZE(rds_ib_event_type_strings), type); -}; - /* * Set the selected protocol version */ @@ -243,7 +213,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, static void rds_ib_cq_event_handler(struct ib_event *event, void *data) { rdsdebug("event %u (%s) data %p\n", - event->event, rds_ib_event_str(event->event), data); + event->event, ib_event_msg(event->event), data); } static void rds_ib_qp_event_handler(struct ib_event *event, void *data) @@ -252,7 +222,7 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) struct rds_ib_connection *ic = conn->c_transport_data; rdsdebug("conn %p ic %p event %u (%s)\n", conn, ic, event->event, - rds_ib_event_str(event->event)); + ib_event_msg(event->event)); switch (event->event) { case IB_EVENT_COMM_EST: @@ -261,7 +231,7 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) default: rdsdebug("Fatal QP Event %u (%s) " "- connection %pI4->%pI4, reconnecting\n", - event->event, rds_ib_event_str(event->event), + event->event, ib_event_msg(event->event), &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); break; @@ -277,6 +247,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) struct rds_ib_connection *ic = conn->c_transport_data; struct ib_device *dev = ic->i_cm_id->device; struct ib_qp_init_attr attr; + struct ib_cq_init_attr cq_attr = {}; struct rds_ib_device *rds_ibdev; int ret; @@ -300,9 +271,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn) ic->i_pd = rds_ibdev->pd; ic->i_mr = rds_ibdev->mr; + cq_attr.cqe = ic->i_send_ring.w_nr + 1; ic->i_send_cq = ib_create_cq(dev, rds_ib_send_cq_comp_handler, rds_ib_cq_event_handler, conn, - ic->i_send_ring.w_nr + 1, 0); + &cq_attr); if (IS_ERR(ic->i_send_cq)) { ret = PTR_ERR(ic->i_send_cq); ic->i_send_cq = NULL; @@ -310,9 +282,10 @@ static int rds_ib_setup_qp(struct rds_connection *conn) goto out; } + cq_attr.cqe = ic->i_recv_ring.w_nr; ic->i_recv_cq = ib_create_cq(dev, rds_ib_recv_cq_comp_handler, rds_ib_cq_event_handler, conn, - ic->i_recv_ring.w_nr, 0); + &cq_attr); if (IS_ERR(ic->i_recv_cq)) { ret = PTR_ERR(ic->i_recv_cq); ic->i_recv_cq = NULL; diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 1b981a4e42c2..cac5b4506ee3 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -956,7 +956,7 @@ static inline void rds_poll_cq(struct rds_ib_connection *ic, while (ib_poll_cq(ic->i_recv_cq, 1, &wc) > 0) { rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n", (unsigned long long)wc.wr_id, wc.status, - rds_ib_wc_status_str(wc.status), wc.byte_len, + ib_wc_status_msg(wc.status), wc.byte_len, be32_to_cpu(wc.ex.imm_data)); rds_ib_stats_inc(s_ib_rx_cq_event); @@ -978,7 +978,7 @@ static inline void rds_poll_cq(struct rds_ib_connection *ic, "status %u (%s), disconnecting and " "reconnecting\n", &conn->c_faddr, wc.status, - rds_ib_wc_status_str(wc.status)); + ib_wc_status_msg(wc.status)); } /* diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index bd3825d38abc..5d0a704fa039 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -39,40 +39,6 @@ #include "rds.h" #include "ib.h" -static char *rds_ib_wc_status_strings[] = { -#define RDS_IB_WC_STATUS_STR(foo) \ - [IB_WC_##foo] = __stringify(IB_WC_##foo) - RDS_IB_WC_STATUS_STR(SUCCESS), - RDS_IB_WC_STATUS_STR(LOC_LEN_ERR), - RDS_IB_WC_STATUS_STR(LOC_QP_OP_ERR), - RDS_IB_WC_STATUS_STR(LOC_EEC_OP_ERR), - RDS_IB_WC_STATUS_STR(LOC_PROT_ERR), - RDS_IB_WC_STATUS_STR(WR_FLUSH_ERR), - RDS_IB_WC_STATUS_STR(MW_BIND_ERR), - RDS_IB_WC_STATUS_STR(BAD_RESP_ERR), - RDS_IB_WC_STATUS_STR(LOC_ACCESS_ERR), - RDS_IB_WC_STATUS_STR(REM_INV_REQ_ERR), - RDS_IB_WC_STATUS_STR(REM_ACCESS_ERR), - RDS_IB_WC_STATUS_STR(REM_OP_ERR), - RDS_IB_WC_STATUS_STR(RETRY_EXC_ERR), - RDS_IB_WC_STATUS_STR(RNR_RETRY_EXC_ERR), - RDS_IB_WC_STATUS_STR(LOC_RDD_VIOL_ERR), - RDS_IB_WC_STATUS_STR(REM_INV_RD_REQ_ERR), - RDS_IB_WC_STATUS_STR(REM_ABORT_ERR), - RDS_IB_WC_STATUS_STR(INV_EECN_ERR), - RDS_IB_WC_STATUS_STR(INV_EEC_STATE_ERR), - RDS_IB_WC_STATUS_STR(FATAL_ERR), - RDS_IB_WC_STATUS_STR(RESP_TIMEOUT_ERR), - RDS_IB_WC_STATUS_STR(GENERAL_ERR), -#undef RDS_IB_WC_STATUS_STR -}; - -char *rds_ib_wc_status_str(enum ib_wc_status status) -{ - return rds_str_array(rds_ib_wc_status_strings, - ARRAY_SIZE(rds_ib_wc_status_strings), status); -} - /* * Convert IB-specific error message to RDS error message and call core * completion handler. @@ -293,7 +259,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) while (ib_poll_cq(cq, 1, &wc) > 0) { rdsdebug("wc wr_id 0x%llx status %u (%s) byte_len %u imm_data %u\n", (unsigned long long)wc.wr_id, wc.status, - rds_ib_wc_status_str(wc.status), wc.byte_len, + ib_wc_status_msg(wc.status), wc.byte_len, be32_to_cpu(wc.ex.imm_data)); rds_ib_stats_inc(s_ib_tx_cq_event); @@ -344,7 +310,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) rds_ib_conn_error(conn, "send completion on %pI4 had status " "%u (%s), disconnecting and reconnecting\n", &conn->c_faddr, wc.status, - rds_ib_wc_status_str(wc.status)); + ib_wc_status_msg(wc.status)); } } } @@ -605,6 +571,8 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, } rds_message_addref(rm); + rm->data.op_dmasg = 0; + rm->data.op_dmaoff = 0; ic->i_data_op = &rm->data; /* Finalize the header */ @@ -658,7 +626,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, send = &ic->i_sends[pos]; first = send; prev = NULL; - scat = &ic->i_data_op->op_sg[sg]; + scat = &ic->i_data_op->op_sg[rm->data.op_dmasg]; i = 0; do { unsigned int len = 0; @@ -680,17 +648,20 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, /* Set up the data, if present */ if (i < work_alloc && scat != &rm->data.op_sg[rm->data.op_count]) { - len = min(RDS_FRAG_SIZE, ib_sg_dma_len(dev, scat) - off); + len = min(RDS_FRAG_SIZE, + ib_sg_dma_len(dev, scat) - rm->data.op_dmaoff); send->s_wr.num_sge = 2; - send->s_sge[1].addr = ib_sg_dma_address(dev, scat) + off; + send->s_sge[1].addr = ib_sg_dma_address(dev, scat); + send->s_sge[1].addr += rm->data.op_dmaoff; send->s_sge[1].length = len; bytes_sent += len; - off += len; - if (off == ib_sg_dma_len(dev, scat)) { + rm->data.op_dmaoff += len; + if (rm->data.op_dmaoff == ib_sg_dma_len(dev, scat)) { scat++; - off = 0; + rm->data.op_dmasg++; + rm->data.op_dmaoff = 0; } } diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index a6c2bea9f8f9..8f486fa32079 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -179,6 +179,7 @@ static int rds_iw_init_qp_attrs(struct ib_qp_init_attr *attr, void *context) { struct ib_device *dev = rds_iwdev->dev; + struct ib_cq_init_attr cq_attr = {}; unsigned int send_size, recv_size; int ret; @@ -198,9 +199,10 @@ static int rds_iw_init_qp_attrs(struct ib_qp_init_attr *attr, attr->sq_sig_type = IB_SIGNAL_REQ_WR; attr->qp_type = IB_QPT_RC; + cq_attr.cqe = send_size; attr->send_cq = ib_create_cq(dev, send_cq_handler, rds_iw_cq_event_handler, - context, send_size, 0); + context, &cq_attr); if (IS_ERR(attr->send_cq)) { ret = PTR_ERR(attr->send_cq); attr->send_cq = NULL; @@ -208,9 +210,10 @@ static int rds_iw_init_qp_attrs(struct ib_qp_init_attr *attr, goto out; } + cq_attr.cqe = recv_size; attr->recv_cq = ib_create_cq(dev, recv_cq_handler, rds_iw_cq_event_handler, - context, recv_size, 0); + context, &cq_attr); if (IS_ERR(attr->recv_cq)) { ret = PTR_ERR(attr->recv_cq); attr->recv_cq = NULL; diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 13834780a308..334fe98c5084 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -581,6 +581,8 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, ic->i_unsignaled_wrs = rds_iw_sysctl_max_unsig_wrs; ic->i_unsignaled_bytes = rds_iw_sysctl_max_unsig_bytes; rds_message_addref(rm); + rm->data.op_dmasg = 0; + rm->data.op_dmaoff = 0; ic->i_rm = rm; /* Finalize the header */ @@ -622,7 +624,7 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, send = &ic->i_sends[pos]; first = send; prev = NULL; - scat = &rm->data.op_sg[sg]; + scat = &rm->data.op_sg[rm->data.op_dmasg]; sent = 0; i = 0; @@ -656,10 +658,11 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, send = &ic->i_sends[pos]; - len = min(RDS_FRAG_SIZE, ib_sg_dma_len(dev, scat) - off); + len = min(RDS_FRAG_SIZE, + ib_sg_dma_len(dev, scat) - rm->data.op_dmaoff); rds_iw_xmit_populate_wr(ic, send, pos, - ib_sg_dma_address(dev, scat) + off, len, - send_flags); + ib_sg_dma_address(dev, scat) + rm->data.op_dmaoff, len, + send_flags); /* * We want to delay signaling completions just enough to get @@ -687,10 +690,11 @@ int rds_iw_xmit(struct rds_connection *conn, struct rds_message *rm, &send->s_wr, send->s_wr.num_sge, send->s_wr.next); sent += len; - off += len; - if (off == ib_sg_dma_len(dev, scat)) { + rm->data.op_dmaoff += len; + if (rm->data.op_dmaoff == ib_sg_dma_len(dev, scat)) { scat++; - off = 0; + rm->data.op_dmaoff = 0; + rm->data.op_dmasg++; } add_header: diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 6cd9d1deafc3..208240836043 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -37,34 +37,6 @@ static struct rdma_cm_id *rds_rdma_listen_id; -static char *rds_cm_event_strings[] = { -#define RDS_CM_EVENT_STRING(foo) \ - [RDMA_CM_EVENT_##foo] = __stringify(RDMA_CM_EVENT_##foo) - RDS_CM_EVENT_STRING(ADDR_RESOLVED), - RDS_CM_EVENT_STRING(ADDR_ERROR), - RDS_CM_EVENT_STRING(ROUTE_RESOLVED), - RDS_CM_EVENT_STRING(ROUTE_ERROR), - RDS_CM_EVENT_STRING(CONNECT_REQUEST), - RDS_CM_EVENT_STRING(CONNECT_RESPONSE), - RDS_CM_EVENT_STRING(CONNECT_ERROR), - RDS_CM_EVENT_STRING(UNREACHABLE), - RDS_CM_EVENT_STRING(REJECTED), - RDS_CM_EVENT_STRING(ESTABLISHED), - RDS_CM_EVENT_STRING(DISCONNECTED), - RDS_CM_EVENT_STRING(DEVICE_REMOVAL), - RDS_CM_EVENT_STRING(MULTICAST_JOIN), - RDS_CM_EVENT_STRING(MULTICAST_ERROR), - RDS_CM_EVENT_STRING(ADDR_CHANGE), - RDS_CM_EVENT_STRING(TIMEWAIT_EXIT), -#undef RDS_CM_EVENT_STRING -}; - -static char *rds_cm_event_str(enum rdma_cm_event_type type) -{ - return rds_str_array(rds_cm_event_strings, - ARRAY_SIZE(rds_cm_event_strings), type); -}; - int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { @@ -74,7 +46,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, int ret = 0; rdsdebug("conn %p id %p handling event %u (%s)\n", conn, cm_id, - event->event, rds_cm_event_str(event->event)); + event->event, rdma_event_msg(event->event)); if (cm_id->device->node_type == RDMA_NODE_RNIC) trans = &rds_iw_transport; @@ -139,7 +111,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, default: /* things like device disconnect? */ printk(KERN_ERR "RDS: unknown event %u (%s)!\n", - event->event, rds_cm_event_str(event->event)); + event->event, rdma_event_msg(event->event)); break; } @@ -148,7 +120,7 @@ out: mutex_unlock(&conn->c_cm_lock); rdsdebug("id %p event %u (%s) handling ret %d\n", cm_id, event->event, - rds_cm_event_str(event->event), ret); + rdma_event_msg(event->event), ret); return ret; } diff --git a/net/rds/rds.h b/net/rds/rds.h index 0d41155a2258..cc549858ed0e 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -363,6 +363,8 @@ struct rds_message { unsigned int op_active:1; unsigned int op_nents; unsigned int op_count; + unsigned int op_dmasg; + unsigned int op_dmaoff; struct scatterlist *op_sg; } data; }; @@ -575,7 +577,6 @@ struct rds_statistics { }; /* af_rds.c */ -char *rds_str_array(char **array, size_t elements, size_t index); void rds_sock_addref(struct rds_sock *rs); void rds_sock_put(struct rds_sock *rs); void rds_wake_sk_sleep(struct rds_sock *rs); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index dff0481dbcf8..d234521320a4 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -128,8 +128,8 @@ frwr_sendcompletion(struct ib_wc *wc) /* WARNING: Only wr_id and status are reliable at this point */ r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; - dprintk("RPC: %s: frmr %p (stale), status %d\n", - __func__, r, wc->status); + dprintk("RPC: %s: frmr %p (stale), status %s (%d)\n", + __func__, r, ib_wc_status_msg(wc->status), wc->status); r->r.frmr.fr_state = FRMR_IS_STALE; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index f9f13a32ddb8..86b44164172b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -117,8 +117,8 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, static int rdma_read_max_sge(struct svcxprt_rdma *xprt, int sge_count) { - if (rdma_node_get_transport(xprt->sc_cm_id->device->node_type) == - RDMA_TRANSPORT_IWARP) + if (!rdma_cap_read_multi_sge(xprt->sc_cm_id->device, + xprt->sc_cm_id->port_num)) return 1; else return min_t(int, sge_count, xprt->sc_max_sge); diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f609c1c2d38d..f4cfa764d76f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -175,8 +175,8 @@ void svc_rdma_put_req_map(struct svc_rdma_req_map *map) static void cq_event_handler(struct ib_event *event, void *context) { struct svc_xprt *xprt = context; - dprintk("svcrdma: received CQ event id=%d, context=%p\n", - event->event, context); + dprintk("svcrdma: received CQ event %s (%d), context=%p\n", + ib_event_msg(event->event), event->event, context); set_bit(XPT_CLOSE, &xprt->xpt_flags); } @@ -191,8 +191,9 @@ static void qp_event_handler(struct ib_event *event, void *context) case IB_EVENT_COMM_EST: case IB_EVENT_SQ_DRAINED: case IB_EVENT_QP_LAST_WQE_REACHED: - dprintk("svcrdma: QP event %d received for QP=%p\n", - event->event, event->element.qp); + dprintk("svcrdma: QP event %s (%d) received for QP=%p\n", + ib_event_msg(event->event), event->event, + event->element.qp); break; /* These are considered fatal events */ case IB_EVENT_PATH_MIG_ERR: @@ -201,9 +202,10 @@ static void qp_event_handler(struct ib_event *event, void *context) case IB_EVENT_QP_ACCESS_ERR: case IB_EVENT_DEVICE_FATAL: default: - dprintk("svcrdma: QP ERROR event %d received for QP=%p, " + dprintk("svcrdma: QP ERROR event %s (%d) received for QP=%p, " "closing transport\n", - event->event, event->element.qp); + ib_event_msg(event->event), event->event, + event->element.qp); set_bit(XPT_CLOSE, &xprt->xpt_flags); break; } @@ -402,7 +404,8 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) for (i = 0; i < ret; i++) { wc = &wc_a[i]; if (wc->status != IB_WC_SUCCESS) { - dprintk("svcrdma: sq wc err status %d\n", + dprintk("svcrdma: sq wc err status %s (%d)\n", + ib_wc_status_msg(wc->status), wc->status); /* Close the transport */ @@ -616,7 +619,8 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: dprintk("svcrdma: Connect request on cma_id=%p, xprt = %p, " - "event=%d\n", cma_id, cma_id->context, event->event); + "event = %s (%d)\n", cma_id, cma_id->context, + rdma_event_msg(event->event), event->event); handle_connect_req(cma_id, event->param.conn.initiator_depth); break; @@ -636,7 +640,8 @@ static int rdma_listen_handler(struct rdma_cm_id *cma_id, default: dprintk("svcrdma: Unexpected event on listening endpoint %p, " - "event=%d\n", cma_id, event->event); + "event = %s (%d)\n", cma_id, + rdma_event_msg(event->event), event->event); break; } @@ -669,7 +674,8 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, break; case RDMA_CM_EVENT_DEVICE_REMOVAL: dprintk("svcrdma: Device removal cma_id=%p, xprt = %p, " - "event=%d\n", cma_id, xprt, event->event); + "event = %s (%d)\n", cma_id, xprt, + rdma_event_msg(event->event), event->event); if (xprt) { set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); @@ -677,7 +683,8 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, break; default: dprintk("svcrdma: Unexpected event on DTO endpoint %p, " - "event=%d\n", cma_id, event->event); + "event = %s (%d)\n", cma_id, + rdma_event_msg(event->event), event->event); break; } return 0; @@ -848,10 +855,11 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) struct svcxprt_rdma *listen_rdma; struct svcxprt_rdma *newxprt = NULL; struct rdma_conn_param conn_param; + struct ib_cq_init_attr cq_attr = {}; struct ib_qp_init_attr qp_attr; struct ib_device_attr devattr; int uninitialized_var(dma_mr_acc); - int need_dma_mr; + int need_dma_mr = 0; int ret; int i; @@ -900,22 +908,22 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dprintk("svcrdma: error creating PD for connect request\n"); goto errout; } + cq_attr.cqe = newxprt->sc_sq_depth; newxprt->sc_sq_cq = ib_create_cq(newxprt->sc_cm_id->device, sq_comp_handler, cq_event_handler, newxprt, - newxprt->sc_sq_depth, - 0); + &cq_attr); if (IS_ERR(newxprt->sc_sq_cq)) { dprintk("svcrdma: error creating SQ CQ for connect request\n"); goto errout; } + cq_attr.cqe = newxprt->sc_max_requests; newxprt->sc_rq_cq = ib_create_cq(newxprt->sc_cm_id->device, rq_comp_handler, cq_event_handler, newxprt, - newxprt->sc_max_requests, - 0); + &cq_attr); if (IS_ERR(newxprt->sc_rq_cq)) { dprintk("svcrdma: error creating RQ CQ for connect request\n"); goto errout; @@ -985,35 +993,26 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* * Determine if a DMA MR is required and if so, what privs are required */ - switch (rdma_node_get_transport(newxprt->sc_cm_id->device->node_type)) { - case RDMA_TRANSPORT_IWARP: - newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; - if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) { - need_dma_mr = 1; - dma_mr_acc = - (IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE); - } else if (!(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else - need_dma_mr = 0; - break; - case RDMA_TRANSPORT_IB: - if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else if (!(devattr.device_cap_flags & - IB_DEVICE_LOCAL_DMA_LKEY)) { - need_dma_mr = 1; - dma_mr_acc = IB_ACCESS_LOCAL_WRITE; - } else - need_dma_mr = 0; - break; - default: + if (!rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num) && + !rdma_ib_or_roce(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num)) goto errout; + + if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG) || + !(devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) { + need_dma_mr = 1; + dma_mr_acc = IB_ACCESS_LOCAL_WRITE; + if (rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num) && + !(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG)) + dma_mr_acc |= IB_ACCESS_REMOTE_WRITE; } + if (rdma_protocol_iwarp(newxprt->sc_cm_id->device, + newxprt->sc_cm_id->port_num)) + newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_READ_W_INV; + /* Create the DMA MR if needed, otherwise, use the DMA LKEY */ if (need_dma_mr) { /* Register all of physical memory */ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4870d272e006..52df265b472a 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -105,32 +105,6 @@ rpcrdma_run_tasklet(unsigned long data) static DECLARE_TASKLET(rpcrdma_tasklet_g, rpcrdma_run_tasklet, 0UL); -static const char * const async_event[] = { - "CQ error", - "QP fatal error", - "QP request error", - "QP access error", - "communication established", - "send queue drained", - "path migration successful", - "path mig error", - "device fatal error", - "port active", - "port error", - "LID change", - "P_key change", - "SM change", - "SRQ error", - "SRQ limit reached", - "last WQE reached", - "client reregister", - "GID change", -}; - -#define ASYNC_MSG(status) \ - ((status) < ARRAY_SIZE(async_event) ? \ - async_event[(status)] : "unknown async error") - static void rpcrdma_schedule_tasklet(struct list_head *sched_list) { @@ -148,7 +122,7 @@ rpcrdma_qp_async_error_upcall(struct ib_event *event, void *context) struct rpcrdma_ep *ep = context; pr_err("RPC: %s: %s on device %s ep %p\n", - __func__, ASYNC_MSG(event->event), + __func__, ib_event_msg(event->event), event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; @@ -163,7 +137,7 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context) struct rpcrdma_ep *ep = context; pr_err("RPC: %s: %s on device %s ep %p\n", - __func__, ASYNC_MSG(event->event), + __func__, ib_event_msg(event->event), event->device->name, context); if (ep->rep_connected == 1) { ep->rep_connected = -EIO; @@ -172,35 +146,6 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context) } } -static const char * const wc_status[] = { - "success", - "local length error", - "local QP operation error", - "local EE context operation error", - "local protection error", - "WR flushed", - "memory management operation error", - "bad response error", - "local access error", - "remote invalid request error", - "remote access error", - "remote operation error", - "transport retry counter exceeded", - "RNR retry counter exceeded", - "local RDD violation error", - "remove invalid RD request", - "operation aborted", - "invalid EE context number", - "invalid EE context state", - "fatal error", - "response timeout error", - "general error", -}; - -#define COMPLETION_MSG(status) \ - ((status) < ARRAY_SIZE(wc_status) ? \ - wc_status[(status)] : "unexpected completion error") - static void rpcrdma_sendcq_process_wc(struct ib_wc *wc) { @@ -209,7 +154,7 @@ rpcrdma_sendcq_process_wc(struct ib_wc *wc) if (wc->status != IB_WC_SUCCESS && wc->status != IB_WC_WR_FLUSH_ERR) pr_err("RPC: %s: SEND: %s\n", - __func__, COMPLETION_MSG(wc->status)); + __func__, ib_wc_status_msg(wc->status)); } else { struct rpcrdma_mw *r; @@ -302,7 +247,7 @@ out_schedule: out_fail: if (wc->status != IB_WC_WR_FLUSH_ERR) pr_err("RPC: %s: rep %p: %s\n", - __func__, rep, COMPLETION_MSG(wc->status)); + __func__, rep, ib_wc_status_msg(wc->status)); rep->rr_len = ~0U; goto out_schedule; } @@ -386,31 +331,6 @@ rpcrdma_flush_cqs(struct rpcrdma_ep *ep) rpcrdma_sendcq_process_wc(&wc); } -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -static const char * const conn[] = { - "address resolved", - "address error", - "route resolved", - "route error", - "connect request", - "connect response", - "connect error", - "unreachable", - "rejected", - "established", - "disconnected", - "device removal", - "multicast join", - "multicast error", - "address change", - "timewait exit", -}; - -#define CONNECTION_MSG(status) \ - ((status) < ARRAY_SIZE(conn) ? \ - conn[(status)] : "unrecognized connection error") -#endif - static int rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event) { @@ -476,7 +396,7 @@ connected: default: dprintk("RPC: %s: %pIS:%u (ep 0x%p): %s\n", __func__, sap, rpc_get_port(sap), ep, - CONNECTION_MSG(event->event)); + rdma_event_msg(event->event)); break; } @@ -724,6 +644,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, { struct ib_device_attr *devattr = &ia->ri_devattr; struct ib_cq *sendcq, *recvcq; + struct ib_cq_init_attr cq_attr = {}; int rc, err; /* check provider's send/recv wr limits */ @@ -771,9 +692,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, init_waitqueue_head(&ep->rep_connect_wait); INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); + cq_attr.cqe = ep->rep_attr.cap.max_send_wr + 1; sendcq = ib_create_cq(ia->ri_id->device, rpcrdma_sendcq_upcall, - rpcrdma_cq_async_error_upcall, ep, - ep->rep_attr.cap.max_send_wr + 1, 0); + rpcrdma_cq_async_error_upcall, ep, &cq_attr); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); dprintk("RPC: %s: failed to create send CQ: %i\n", @@ -788,9 +709,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, goto out2; } + cq_attr.cqe = ep->rep_attr.cap.max_recv_wr + 1; recvcq = ib_create_cq(ia->ri_id->device, rpcrdma_recvcq_upcall, - rpcrdma_cq_async_error_upcall, ep, - ep->rep_attr.cap.max_recv_wr + 1, 0); + rpcrdma_cq_async_error_upcall, ep, &cq_attr); if (IS_ERR(recvcq)) { rc = PTR_ERR(recvcq); dprintk("RPC: %s: failed to create recv CQ: %i\n", |