diff options
Diffstat (limited to 'net/sunrpc')
-rw-r--r-- | net/sunrpc/Kconfig | 28 | ||||
-rw-r--r-- | net/sunrpc/Makefile | 3 | ||||
-rw-r--r-- | net/sunrpc/auth_gss/gss_krb5_crypto.c | 8 | ||||
-rw-r--r-- | net/sunrpc/svc.c | 2 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/Makefile | 14 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/frwr_ops.c | 4 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/module.c | 46 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma.c | 8 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_marshal.c | 140 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 6 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_sendto.c | 16 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_transport.c | 119 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/transport.c | 13 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/verbs.c | 99 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/xprt_rdma.h | 11 |
15 files changed, 184 insertions, 333 deletions
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig index 9068e72aa73c..04ce2c0b660e 100644 --- a/net/sunrpc/Kconfig +++ b/net/sunrpc/Kconfig @@ -48,28 +48,16 @@ config SUNRPC_DEBUG If unsure, say Y. -config SUNRPC_XPRT_RDMA_CLIENT - tristate "RPC over RDMA Client Support" +config SUNRPC_XPRT_RDMA + tristate "RPC-over-RDMA transport" depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS default SUNRPC && INFINIBAND help - This option allows the NFS client to support an RDMA-enabled - transport. + This option allows the NFS client and server to use RDMA + transports (InfiniBand, iWARP, or RoCE). - To compile RPC client RDMA transport support as a module, - choose M here: the module will be called xprtrdma. + To compile this support as a module, choose M. The module + will be called rpcrdma.ko. - If unsure, say N. - -config SUNRPC_XPRT_RDMA_SERVER - tristate "RPC over RDMA Server Support" - depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS - default SUNRPC && INFINIBAND - help - This option allows the NFS server to support an RDMA-enabled - transport. - - To compile RPC server RDMA transport support as a module, - choose M here: the module will be called svcrdma. - - If unsure, say N. + If unsure, or you know there is no RDMA capability on your + hardware platform, say N. diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 15e6f6c23c5d..936ad0a15371 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -5,8 +5,7 @@ obj-$(CONFIG_SUNRPC) += sunrpc.o obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ - -obj-y += xprtrdma/ +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ auth.o auth_null.o auth_unix.o auth_generic.o \ diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index b5408e8a37f2..fee3c15a4b52 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -881,9 +881,7 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, &zeroconstant, 4); - + sg_init_one(sg, &zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kseq); if (err) goto out_err; @@ -951,9 +949,7 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx, struct crypto_blkcipher *cipher, if (err) goto out_err; - sg_init_table(sg, 1); - sg_set_buf(sg, zeroconstant, 4); - + sg_init_one(sg, zeroconstant, 4); err = crypto_hash_digest(&desc, sg, 4, Kcrypt); if (err) goto out_err; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 78974e4d9ad2..852ae606b02a 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1290,7 +1290,6 @@ err_bad: svc_putnl(resv, ntohl(rpc_stat)); goto sendit; } -EXPORT_SYMBOL_GPL(svc_process); /* * Process the RPC request. @@ -1338,6 +1337,7 @@ out_drop: svc_drop(rqstp); return 0; } +EXPORT_SYMBOL_GPL(svc_process); #if defined(CONFIG_SUNRPC_BACKCHANNEL) /* diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 579f72bbcf4b..48913de240bd 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,9 +1,7 @@ -obj-$(CONFIG_SUNRPC_XPRT_RDMA_CLIENT) += xprtrdma.o +obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o -xprtrdma-y := transport.o rpc_rdma.o verbs.o \ - fmr_ops.o frwr_ops.o physical_ops.o - -obj-$(CONFIG_SUNRPC_XPRT_RDMA_SERVER) += svcrdma.o - -svcrdma-y := svc_rdma.o svc_rdma_transport.o \ - svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o +rpcrdma-y := transport.o rpc_rdma.o verbs.o \ + fmr_ops.o frwr_ops.o physical_ops.o \ + svc_rdma.o svc_rdma_transport.o \ + svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ + module.o 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/module.c b/net/sunrpc/xprtrdma/module.c new file mode 100644 index 000000000000..560712bd9fa2 --- /dev/null +++ b/net/sunrpc/xprtrdma/module.c @@ -0,0 +1,46 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + */ + +/* rpcrdma.ko module initialization + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/sunrpc/svc_rdma.h> +#include "xprt_rdma.h" + +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) +# define RPCDBG_FACILITY RPCDBG_TRANS +#endif + +MODULE_AUTHOR("Open Grid Computing and Network Appliance, Inc."); +MODULE_DESCRIPTION("RPC/RDMA Transport"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("svcrdma"); +MODULE_ALIAS("xprtrdma"); + +static void __exit rpc_rdma_cleanup(void) +{ + xprt_rdma_cleanup(); + svc_rdma_cleanup(); +} + +static int __init rpc_rdma_init(void) +{ + int rc; + + rc = svc_rdma_init(); + if (rc) + goto out; + + rc = xprt_rdma_init(); + if (rc) + svc_rdma_cleanup(); + +out: + return rc; +} + +module_init(rpc_rdma_init); +module_exit(rpc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index c1b6270262c2..2cd252f023a5 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -38,8 +38,7 @@ * * Author: Tom Tucker <tom@opengridcomputing.com> */ -#include <linux/module.h> -#include <linux/init.h> + #include <linux/slab.h> #include <linux/fs.h> #include <linux/sysctl.h> @@ -295,8 +294,3 @@ int svc_rdma_init(void) destroy_workqueue(svc_rdma_wq); return -ENOMEM; } -MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>"); -MODULE_DESCRIPTION("SVC RDMA Transport"); -MODULE_LICENSE("Dual BSD/GPL"); -module_init(svc_rdma_init); -module_exit(svc_rdma_cleanup); diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c index b681855cf970..e2fca7617242 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c +++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c @@ -50,12 +50,12 @@ /* * Decodes a read chunk list. The expected format is as follows: * descrim : xdr_one - * position : u32 offset into XDR stream - * handle : u32 RKEY + * position : __be32 offset into XDR stream + * handle : __be32 RKEY * . . . * end-of-list: xdr_zero */ -static u32 *decode_read_list(u32 *va, u32 *vaend) +static __be32 *decode_read_list(__be32 *va, __be32 *vaend) { struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va; @@ -67,20 +67,20 @@ static u32 *decode_read_list(u32 *va, u32 *vaend) } ch++; } - return (u32 *)&ch->rc_position; + return &ch->rc_position; } /* * Decodes a write chunk list. The expected format is as follows: * descrim : xdr_one * nchunks : <count> - * handle : u32 RKEY ---+ - * length : u32 <len of segment> | + * handle : __be32 RKEY ---+ + * length : __be32 <len of segment> | * offset : remove va + <count> * . . . | * ---+ */ -static u32 *decode_write_list(u32 *va, u32 *vaend) +static __be32 *decode_write_list(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -90,14 +90,14 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) /* Check for not write-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -112,10 +112,10 @@ static u32 *decode_write_list(u32 *va, u32 *vaend) * rs_length is the 2nd 4B field in wc_target and taking its * address skips the list terminator */ - return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length; + return &ary->wc_array[nchunks].wc_target.rs_length; } -static u32 *decode_reply_array(u32 *va, u32 *vaend) +static __be32 *decode_reply_array(__be32 *va, __be32 *vaend) { unsigned long start, end; int nchunks; @@ -124,14 +124,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) /* Check for no reply-array */ if (ary->wc_discrim == xdr_zero) - return (u32 *)&ary->wc_nchunks; + return &ary->wc_nchunks; if ((unsigned long)ary + sizeof(struct rpcrdma_write_array) > (unsigned long)vaend) { dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend); return NULL; } - nchunks = ntohl(ary->wc_nchunks); + nchunks = be32_to_cpu(ary->wc_nchunks); start = (unsigned long)&ary->wc_array[0]; end = (unsigned long)vaend; @@ -142,15 +142,14 @@ static u32 *decode_reply_array(u32 *va, u32 *vaend) ary, nchunks, vaend); return NULL; } - return (u32 *)&ary->wc_array[nchunks]; + return (__be32 *)&ary->wc_array[nchunks]; } int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, struct svc_rqst *rqstp) { struct rpcrdma_msg *rmsgp = NULL; - u32 *va; - u32 *vaend; + __be32 *va, *vaend; u32 hdr_len; rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; @@ -162,22 +161,17 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return -EINVAL; } - /* Decode the header */ - rmsgp->rm_xid = ntohl(rmsgp->rm_xid); - rmsgp->rm_vers = ntohl(rmsgp->rm_vers); - rmsgp->rm_credit = ntohl(rmsgp->rm_credit); - rmsgp->rm_type = ntohl(rmsgp->rm_type); - - if (rmsgp->rm_vers != RPCRDMA_VERSION) + if (rmsgp->rm_vers != rpcrdma_version) return -ENOSYS; /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { + if (rmsgp->rm_type == rdma_msgp) { int hdrlen; + rmsgp->rm_body.rm_padded.rm_align = - ntohl(rmsgp->rm_body.rm_padded.rm_align); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_align); rmsgp->rm_body.rm_padded.rm_thresh = - ntohl(rmsgp->rm_body.rm_padded.rm_thresh); + be32_to_cpu(rmsgp->rm_body.rm_padded.rm_thresh); va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; rqstp->rq_arg.head[0].iov_base = va; @@ -192,7 +186,7 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, * chunk list and a reply chunk list. */ va = &rmsgp->rm_body.rm_chunks[0]; - vaend = (u32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); + vaend = (__be32 *)((unsigned long)rmsgp + rqstp->rq_arg.len); va = decode_read_list(va, vaend); if (!va) return -EINVAL; @@ -211,76 +205,20 @@ int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req, return hdr_len; } -int svc_rdma_xdr_decode_deferred_req(struct svc_rqst *rqstp) -{ - struct rpcrdma_msg *rmsgp = NULL; - struct rpcrdma_read_chunk *ch; - struct rpcrdma_write_array *ary; - u32 *va; - u32 hdrlen; - - dprintk("svcrdma: processing deferred RDMA header on rqstp=%p\n", - rqstp); - rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - - /* Pull in the extra for the padded case and bump our pointer */ - if (rmsgp->rm_type == RDMA_MSGP) { - va = &rmsgp->rm_body.rm_padded.rm_pempty[4]; - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (u32)((unsigned long)va - (unsigned long)rmsgp); - rqstp->rq_arg.head[0].iov_len -= hdrlen; - return hdrlen; - } - - /* - * Skip all chunks to find RPC msg. These were previously processed - */ - va = &rmsgp->rm_body.rm_chunks[0]; - - /* Skip read-list */ - for (ch = (struct rpcrdma_read_chunk *)va; - ch->rc_discrim != xdr_zero; ch++); - va = (u32 *)&ch->rc_position; - - /* Skip write-list */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - /* - * rs_length is the 2nd 4B field in wc_target and taking its - * address skips the list terminator - */ - va = (u32 *)&ary->wc_array[ary->wc_nchunks].wc_target.rs_length; - - /* Skip reply-array */ - ary = (struct rpcrdma_write_array *)va; - if (ary->wc_discrim == xdr_zero) - va = (u32 *)&ary->wc_nchunks; - else - va = (u32 *)&ary->wc_array[ary->wc_nchunks]; - - rqstp->rq_arg.head[0].iov_base = va; - hdrlen = (unsigned long)va - (unsigned long)rmsgp; - rqstp->rq_arg.head[0].iov_len -= hdrlen; - - return hdrlen; -} - int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, - enum rpcrdma_errcode err, u32 *va) + enum rpcrdma_errcode err, __be32 *va) { - u32 *startp = va; + __be32 *startp = va; - *va++ = htonl(rmsgp->rm_xid); - *va++ = htonl(rmsgp->rm_vers); - *va++ = htonl(xprt->sc_max_requests); - *va++ = htonl(RDMA_ERROR); - *va++ = htonl(err); + *va++ = rmsgp->rm_xid; + *va++ = rmsgp->rm_vers; + *va++ = cpu_to_be32(xprt->sc_max_requests); + *va++ = rdma_error; + *va++ = cpu_to_be32(err); if (err == ERR_VERS) { - *va++ = htonl(RPCRDMA_VERSION); - *va++ = htonl(RPCRDMA_VERSION); + *va++ = rpcrdma_version; + *va++ = rpcrdma_version; } return (int)((unsigned long)va - (unsigned long)startp); @@ -297,7 +235,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) &rmsgp->rm_body.rm_chunks[1]; if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]. + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]. wc_target.rs_length; else wr_ary = (struct rpcrdma_write_array *) @@ -306,7 +244,7 @@ int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *rmsgp) /* skip reply array */ if (wr_ary->wc_discrim) wr_ary = (struct rpcrdma_write_array *) - &wr_ary->wc_array[ntohl(wr_ary->wc_nchunks)]; + &wr_ary->wc_array[be32_to_cpu(wr_ary->wc_nchunks)]; else wr_ary = (struct rpcrdma_write_array *) &wr_ary->wc_nchunks; @@ -325,7 +263,7 @@ void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks) ary = (struct rpcrdma_write_array *) &rmsgp->rm_body.rm_chunks[1]; ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); /* write-list terminator */ ary->wc_array[chunks].wc_target.rs_handle = xdr_zero; @@ -338,7 +276,7 @@ void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary, int chunks) { ary->wc_discrim = xdr_one; - ary->wc_nchunks = htonl(chunks); + ary->wc_nchunks = cpu_to_be32(chunks); } void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, @@ -350,7 +288,7 @@ void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary, struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target; seg->rs_handle = rs_handle; seg->rs_offset = rs_offset; - seg->rs_length = htonl(write_len); + seg->rs_length = cpu_to_be32(write_len); } void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, @@ -358,10 +296,10 @@ void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rdma_resp, enum rpcrdma_proc rdma_type) { - rdma_resp->rm_xid = htonl(rdma_argp->rm_xid); - rdma_resp->rm_vers = htonl(rdma_argp->rm_vers); - rdma_resp->rm_credit = htonl(xprt->sc_max_requests); - rdma_resp->rm_type = htonl(rdma_type); + rdma_resp->rm_xid = rdma_argp->rm_xid; + rdma_resp->rm_vers = rdma_argp->rm_vers; + rdma_resp->rm_credit = cpu_to_be32(xprt->sc_max_requests); + rdma_resp->rm_type = cpu_to_be32(rdma_type); /* Encode <nul> chunks lists */ rdma_resp->rm_body.rm_chunks[0] = xdr_zero; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index f9f13a32ddb8..2e1348bde325 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -85,7 +85,7 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp, /* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */ rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base; - if (be32_to_cpu(rmsgp->rm_type) == RDMA_NOMSG) + if (rmsgp->rm_type == rdma_nomsg) rqstp->rq_arg.pages = &rqstp->rq_pages[0]; else rqstp->rq_arg.pages = &rqstp->rq_pages[1]; @@ -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_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 7de33d1af9b6..d25cd430f9ff 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -240,6 +240,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, u32 xdr_off; int chunk_off; int chunk_no; + int nchunks; struct rpcrdma_write_array *arg_ary; struct rpcrdma_write_array *res_ary; int ret; @@ -251,14 +252,15 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[1]; /* Write chunks start at the pagelist */ + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0; - xfer_len && chunk_no < arg_ary->wc_nchunks; + xfer_len && chunk_no < nchunks; chunk_no++) { struct rpcrdma_segment *arg_ch; u64 rs_offset; arg_ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, ntohl(arg_ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(arg_ch->rs_length)); /* Prepare the response chunk given the length actually * written */ @@ -270,7 +272,7 @@ static int send_write_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(arg_ch->rs_handle), + be32_to_cpu(arg_ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -318,13 +320,13 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, &rdma_resp->rm_body.rm_chunks[2]; /* xdr offset starts at RPC message */ - nchunks = ntohl(arg_ary->wc_nchunks); + nchunks = be32_to_cpu(arg_ary->wc_nchunks); for (xdr_off = 0, chunk_no = 0; xfer_len && chunk_no < nchunks; chunk_no++) { u64 rs_offset; ch = &arg_ary->wc_array[chunk_no].wc_target; - write_len = min(xfer_len, htonl(ch->rs_length)); + write_len = min(xfer_len, be32_to_cpu(ch->rs_length)); /* Prepare the reply chunk given the length actually * written */ @@ -335,7 +337,7 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, chunk_off = 0; while (write_len) { ret = send_write(xprt, rqstp, - ntohl(ch->rs_handle), + be32_to_cpu(ch->rs_handle), rs_offset + chunk_off, xdr_off, write_len, @@ -515,7 +517,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) inline_bytes = rqstp->rq_res.len; /* Create the RDMA response header */ - res_page = svc_rdma_get_page(); + res_page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); rdma_resp = page_address(res_page); reply_ary = svc_rdma_get_reply_array(rdma_argp); if (reply_ary) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index f609c1c2d38d..6b36279e4288 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = { .xcl_name = "rdma", .xcl_owner = THIS_MODULE, .xcl_ops = &svc_rdma_ops, - .xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA, + .xcl_max_payload = RPCRDMA_MAXPAYLOAD, .xcl_ident = XPRT_TRANSPORT_RDMA, }; @@ -99,12 +99,8 @@ struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; - while (1) { - ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, GFP_KERNEL); - if (ctxt) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, + GFP_KERNEL | __GFP_NOFAIL); ctxt->xprt = xprt; INIT_LIST_HEAD(&ctxt->dto_q); ctxt->count = 0; @@ -156,12 +152,8 @@ void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) struct svc_rdma_req_map *svc_rdma_get_req_map(void) { struct svc_rdma_req_map *map; - while (1) { - map = kmem_cache_alloc(svc_rdma_map_cachep, GFP_KERNEL); - if (map) - break; - schedule_timeout_uninterruptible(msecs_to_jiffies(500)); - } + map = kmem_cache_alloc(svc_rdma_map_cachep, + GFP_KERNEL | __GFP_NOFAIL); map->count = 0; return map; } @@ -175,8 +167,8 @@ 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 +183,9 @@ 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 +194,10 @@ 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 +396,8 @@ 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 */ @@ -490,18 +485,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, return cma_xprt; } -struct page *svc_rdma_get_page(void) -{ - struct page *page; - - while ((page = alloc_page(GFP_KERNEL)) == NULL) { - /* If we can't get memory, wait a bit and try again */ - printk(KERN_INFO "svcrdma: out of memory...retrying in 1s\n"); - schedule_timeout_uninterruptible(msecs_to_jiffies(1000)); - } - return page; -} - int svc_rdma_post_recv(struct svcxprt_rdma *xprt) { struct ib_recv_wr recv_wr, *bad_recv_wr; @@ -520,7 +503,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err_put_ctxt; } - page = svc_rdma_get_page(); + page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); ctxt->pages[sge_no] = page; pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, @@ -616,7 +599,8 @@ 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 +620,8 @@ 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 +654,8 @@ 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 +663,8 @@ 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 +835,11 @@ 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 +888,22 @@ 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 +973,26 @@ 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 */ @@ -1319,11 +1298,11 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, struct ib_send_wr err_wr; struct page *p; struct svc_rdma_op_ctxt *ctxt; - u32 *va; + __be32 *va; int length; int ret; - p = svc_rdma_get_page(); + p = alloc_page(GFP_KERNEL | __GFP_NOFAIL); va = page_address(p); /* XDR encode error */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 54f23b1be986..436da2caec95 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -48,7 +48,6 @@ */ #include <linux/module.h> -#include <linux/init.h> #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/sunrpc/addr.h> @@ -59,11 +58,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -MODULE_LICENSE("Dual BSD/GPL"); - -MODULE_DESCRIPTION("RPC/RDMA Transport for Linux kernel NFS"); -MODULE_AUTHOR("Network Appliance, Inc."); - /* * tunables */ @@ -711,7 +705,7 @@ static struct xprt_class xprt_rdma = { .setup = xprt_setup_rdma, }; -static void __exit xprt_rdma_cleanup(void) +void xprt_rdma_cleanup(void) { int rc; @@ -728,7 +722,7 @@ static void __exit xprt_rdma_cleanup(void) __func__, rc); } -static int __init xprt_rdma_init(void) +int xprt_rdma_init(void) { int rc; @@ -753,6 +747,3 @@ static int __init xprt_rdma_init(void) #endif return 0; } - -module_init(xprt_rdma_init); -module_exit(xprt_rdma_cleanup); 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", diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 78e0b8beaa36..58163b88738c 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -480,6 +480,11 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); */ int rpcrdma_marshal_req(struct rpc_rqst *); +/* RPC/RDMA module init - xprtrdma/transport.c + */ +int xprt_rdma_init(void); +void xprt_rdma_cleanup(void); + /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; /* WR context cache. Created in svc_rdma.c */ @@ -487,10 +492,4 @@ extern struct kmem_cache *svc_rdma_ctxt_cachep; /* Workqueue created in svc_rdma.c */ extern struct workqueue_struct *svc_rdma_wq; -#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD -#else -#define RPCSVC_MAXPAYLOAD_RDMA (RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT) -#endif - #endif /* _LINUX_SUNRPC_XPRT_RDMA_H */ |