diff options
Diffstat (limited to 'net/sunrpc/xprtrdma')
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma.c | 11 | ||||
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 19 | ||||
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_sendto.c | 82 | ||||
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_transport.c | 49 | ||||
| -rw-r--r-- | net/sunrpc/xprtrdma/transport.c | 25 |
5 files changed, 115 insertions, 71 deletions
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index d718b8fa9525..09af4fab1a45 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -43,6 +43,7 @@ #include <linux/slab.h> #include <linux/fs.h> #include <linux/sysctl.h> +#include <linux/workqueue.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/sched.h> #include <linux/sunrpc/svc_rdma.h> @@ -74,6 +75,8 @@ atomic_t rdma_stat_sq_prod; struct kmem_cache *svc_rdma_map_cachep; struct kmem_cache *svc_rdma_ctxt_cachep; +struct workqueue_struct *svc_rdma_wq; + /* * This function implements reading and resetting an atomic_t stat * variable through read/write to a proc file. Any write to the file @@ -231,7 +234,7 @@ static ctl_table svcrdma_root_table[] = { void svc_rdma_cleanup(void) { dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); - flush_scheduled_work(); + destroy_workqueue(svc_rdma_wq); if (svcrdma_table_header) { unregister_sysctl_table(svcrdma_table_header); svcrdma_table_header = NULL; @@ -249,6 +252,11 @@ int svc_rdma_init(void) dprintk("\tsq_depth : %d\n", svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT); dprintk("\tmax_inline : %d\n", svcrdma_max_req_size); + + svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0); + if (!svc_rdma_wq) + return -ENOMEM; + if (!svcrdma_table_header) svcrdma_table_header = register_sysctl_table(svcrdma_root_table); @@ -283,6 +291,7 @@ int svc_rdma_init(void) kmem_cache_destroy(svc_rdma_map_cachep); err0: unregister_sysctl_table(svcrdma_table_header); + destroy_workqueue(svc_rdma_wq); return -ENOMEM; } MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>"); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 0194de814933..df67211c4baf 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -263,9 +263,9 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt, frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT; for (page_no = 0; page_no < frmr->page_list_len; page_no++) { frmr->page_list->page_list[page_no] = - ib_dma_map_single(xprt->sc_cm_id->device, - page_address(rqstp->rq_arg.pages[page_no]), - PAGE_SIZE, DMA_FROM_DEVICE); + ib_dma_map_page(xprt->sc_cm_id->device, + rqstp->rq_arg.pages[page_no], 0, + PAGE_SIZE, DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, frmr->page_list->page_list[page_no])) goto fatal_err; @@ -309,17 +309,21 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt, int count) { int i; + unsigned long off; ctxt->count = count; ctxt->direction = DMA_FROM_DEVICE; for (i = 0; i < count; i++) { ctxt->sge[i].length = 0; /* in case map fails */ if (!frmr) { + BUG_ON(0 == virt_to_page(vec[i].iov_base)); + off = (unsigned long)vec[i].iov_base & ~PAGE_MASK; ctxt->sge[i].addr = - ib_dma_map_single(xprt->sc_cm_id->device, - vec[i].iov_base, - vec[i].iov_len, - DMA_FROM_DEVICE); + ib_dma_map_page(xprt->sc_cm_id->device, + virt_to_page(vec[i].iov_base), + off, + vec[i].iov_len, + DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[i].addr)) return -EINVAL; @@ -491,6 +495,7 @@ next_sge: printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n", err); set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags); + svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 0); goto out; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index b15e1ebb2bfa..249a835b703f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -70,8 +70,8 @@ * on extra page for the RPCRMDA header. */ static int fast_reg_xdr(struct svcxprt_rdma *xprt, - struct xdr_buf *xdr, - struct svc_rdma_req_map *vec) + struct xdr_buf *xdr, + struct svc_rdma_req_map *vec) { int sge_no; u32 sge_bytes; @@ -96,21 +96,25 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, vec->count = 2; sge_no++; - /* Build the FRMR */ + /* Map the XDR head */ frmr->kva = frva; frmr->direction = DMA_TO_DEVICE; frmr->access_flags = 0; frmr->map_len = PAGE_SIZE; frmr->page_list_len = 1; + page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK; frmr->page_list->page_list[page_no] = - ib_dma_map_single(xprt->sc_cm_id->device, - (void *)xdr->head[0].iov_base, - PAGE_SIZE, DMA_TO_DEVICE); + ib_dma_map_page(xprt->sc_cm_id->device, + virt_to_page(xdr->head[0].iov_base), + page_off, + PAGE_SIZE - page_off, + DMA_TO_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, frmr->page_list->page_list[page_no])) goto fatal_err; atomic_inc(&xprt->sc_dma_used); + /* Map the XDR page list */ page_off = xdr->page_base; page_bytes = xdr->page_len + page_off; if (!page_bytes) @@ -128,9 +132,9 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, page_bytes -= sge_bytes; frmr->page_list->page_list[page_no] = - ib_dma_map_single(xprt->sc_cm_id->device, - page_address(page), - PAGE_SIZE, DMA_TO_DEVICE); + ib_dma_map_page(xprt->sc_cm_id->device, + page, page_off, + sge_bytes, DMA_TO_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, frmr->page_list->page_list[page_no])) goto fatal_err; @@ -166,8 +170,10 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt, vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off; frmr->page_list->page_list[page_no] = - ib_dma_map_single(xprt->sc_cm_id->device, va, PAGE_SIZE, - DMA_TO_DEVICE); + ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va), + page_off, + PAGE_SIZE, + DMA_TO_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, frmr->page_list->page_list[page_no])) goto fatal_err; @@ -245,6 +251,35 @@ static int map_xdr(struct svcxprt_rdma *xprt, return 0; } +static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt, + struct xdr_buf *xdr, + u32 xdr_off, size_t len, int dir) +{ + struct page *page; + dma_addr_t dma_addr; + if (xdr_off < xdr->head[0].iov_len) { + /* This offset is in the head */ + xdr_off += (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK; + page = virt_to_page(xdr->head[0].iov_base); + } else { + xdr_off -= xdr->head[0].iov_len; + if (xdr_off < xdr->page_len) { + /* This offset is in the page list */ + page = xdr->pages[xdr_off >> PAGE_SHIFT]; + xdr_off &= ~PAGE_MASK; + } else { + /* This offset is in the tail */ + xdr_off -= xdr->page_len; + xdr_off += (unsigned long) + xdr->tail[0].iov_base & ~PAGE_MASK; + page = virt_to_page(xdr->tail[0].iov_base); + } + } + dma_addr = ib_dma_map_page(xprt->sc_cm_id->device, page, xdr_off, + min_t(size_t, PAGE_SIZE, len), dir); + return dma_addr; +} + /* Assumptions: * - We are using FRMR * - or - @@ -293,10 +328,9 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge[sge_no].length = sge_bytes; if (!vec->frmr) { sge[sge_no].addr = - ib_dma_map_single(xprt->sc_cm_id->device, - (void *) - vec->sge[xdr_sge_no].iov_base + sge_off, - sge_bytes, DMA_TO_DEVICE); + dma_map_xdr(xprt, &rqstp->rq_res, xdr_off, + sge_bytes, DMA_TO_DEVICE); + xdr_off += sge_bytes; if (ib_dma_mapping_error(xprt->sc_cm_id->device, sge[sge_no].addr)) goto err; @@ -333,6 +367,8 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, goto err; return 0; err: + svc_rdma_unmap_dma(ctxt); + svc_rdma_put_frmr(xprt, vec->frmr); svc_rdma_put_context(ctxt, 0); /* Fatal error, close transport */ return -EIO; @@ -494,7 +530,8 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt, * In all three cases, this function prepares the RPCRDMA header in * sge[0], the 'type' parameter indicates the type to place in the * RPCRDMA header, and the 'byte_count' field indicates how much of - * the XDR to include in this RDMA_SEND. + * the XDR to include in this RDMA_SEND. NB: The offset of the payload + * to send is zero in the XDR. */ static int send_reply(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, @@ -536,23 +573,24 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[0].lkey = rdma->sc_dma_lkey; ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp); ctxt->sge[0].addr = - ib_dma_map_single(rdma->sc_cm_id->device, page_address(page), - ctxt->sge[0].length, DMA_TO_DEVICE); + ib_dma_map_page(rdma->sc_cm_id->device, page, 0, + ctxt->sge[0].length, DMA_TO_DEVICE); if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) goto err; atomic_inc(&rdma->sc_dma_used); ctxt->direction = DMA_TO_DEVICE; - /* Determine how many of our SGE are to be transmitted */ + /* Map the payload indicated by 'byte_count' */ for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) { + int xdr_off = 0; sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count); byte_count -= sge_bytes; if (!vec->frmr) { ctxt->sge[sge_no].addr = - ib_dma_map_single(rdma->sc_cm_id->device, - vec->sge[sge_no].iov_base, - sge_bytes, DMA_TO_DEVICE); + dma_map_xdr(rdma, &rqstp->rq_res, xdr_off, + sge_bytes, DMA_TO_DEVICE); + xdr_off += sge_bytes; if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[sge_no].addr)) goto err; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index edea15a54e51..9df1eadc912a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -45,6 +45,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/workqueue.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> #include <linux/sunrpc/svc_rdma.h> @@ -52,6 +53,7 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, + struct net *net, struct sockaddr *sa, int salen, int flags); static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); @@ -89,6 +91,9 @@ struct svc_xprt_class svc_rdma_class = { /* WR context cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_ctxt_cachep; +/* Workqueue created in svc_rdma.c */ +extern struct workqueue_struct *svc_rdma_wq; + struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) { struct svc_rdma_op_ctxt *ctxt; @@ -120,7 +125,7 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) */ if (ctxt->sge[i].lkey == xprt->sc_dma_lkey) { atomic_dec(&xprt->sc_dma_used); - ib_dma_unmap_single(xprt->sc_cm_id->device, + ib_dma_unmap_page(xprt->sc_cm_id->device, ctxt->sge[i].addr, ctxt->sge[i].length, ctxt->direction); @@ -502,8 +507,8 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) BUG_ON(sge_no >= xprt->sc_max_sge); page = svc_rdma_get_page(); ctxt->pages[sge_no] = page; - pa = ib_dma_map_single(xprt->sc_cm_id->device, - page_address(page), PAGE_SIZE, + pa = ib_dma_map_page(xprt->sc_cm_id->device, + page, 0, PAGE_SIZE, DMA_FROM_DEVICE); if (ib_dma_mapping_error(xprt->sc_cm_id->device, pa)) goto err_put_ctxt; @@ -511,9 +516,9 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) ctxt->sge[sge_no].addr = pa; ctxt->sge[sge_no].length = PAGE_SIZE; ctxt->sge[sge_no].lkey = xprt->sc_dma_lkey; + ctxt->count = sge_no + 1; buflen += PAGE_SIZE; } - ctxt->count = sge_no; recv_wr.next = NULL; recv_wr.sg_list = &ctxt->sge[0]; recv_wr.num_sge = ctxt->count; @@ -529,6 +534,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) return ret; err_put_ctxt: + svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); return -ENOMEM; } @@ -670,6 +676,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id, * Create a listening RDMA service endpoint. */ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, + struct net *net, struct sockaddr *sa, int salen, int flags) { @@ -798,8 +805,8 @@ static void frmr_unmap_dma(struct svcxprt_rdma *xprt, if (ib_dma_mapping_error(frmr->mr->device, addr)) continue; atomic_dec(&xprt->sc_dma_used); - ib_dma_unmap_single(frmr->mr->device, addr, PAGE_SIZE, - frmr->direction); + ib_dma_unmap_page(frmr->mr->device, addr, PAGE_SIZE, + frmr->direction); } } @@ -1184,7 +1191,7 @@ static void svc_rdma_free(struct svc_xprt *xprt) struct svcxprt_rdma *rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); INIT_WORK(&rdma->sc_work, __svc_rdma_free); - schedule_work(&rdma->sc_work); + queue_work(svc_rdma_wq, &rdma->sc_work); } static int svc_rdma_has_wspace(struct svc_xprt *xprt) @@ -1274,7 +1281,7 @@ int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr) atomic_read(&xprt->sc_sq_count) < xprt->sc_sq_depth); if (test_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags)) - return 0; + return -ENOTCONN; continue; } /* Take a transport ref for each WR posted */ @@ -1306,7 +1313,6 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, enum rpcrdma_errcode err) { struct ib_send_wr err_wr; - struct ib_sge sge; struct page *p; struct svc_rdma_op_ctxt *ctxt; u32 *va; @@ -1319,26 +1325,27 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, /* XDR encode error */ length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va); + ctxt = svc_rdma_get_context(xprt); + ctxt->direction = DMA_FROM_DEVICE; + ctxt->count = 1; + ctxt->pages[0] = p; + /* Prepare SGE for local address */ - sge.addr = ib_dma_map_single(xprt->sc_cm_id->device, - page_address(p), PAGE_SIZE, DMA_FROM_DEVICE); - if (ib_dma_mapping_error(xprt->sc_cm_id->device, sge.addr)) { + ctxt->sge[0].addr = ib_dma_map_page(xprt->sc_cm_id->device, + p, 0, length, DMA_FROM_DEVICE); + if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) { put_page(p); return; } atomic_inc(&xprt->sc_dma_used); - sge.lkey = xprt->sc_dma_lkey; - sge.length = length; - - ctxt = svc_rdma_get_context(xprt); - ctxt->count = 1; - ctxt->pages[0] = p; + ctxt->sge[0].lkey = xprt->sc_dma_lkey; + ctxt->sge[0].length = length; /* Prepare SEND WR */ memset(&err_wr, 0, sizeof err_wr); ctxt->wr_op = IB_WR_SEND; err_wr.wr_id = (unsigned long)ctxt; - err_wr.sg_list = &sge; + err_wr.sg_list = ctxt->sge; err_wr.num_sge = 1; err_wr.opcode = IB_WR_SEND; err_wr.send_flags = IB_SEND_SIGNALED; @@ -1348,9 +1355,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, if (ret) { dprintk("svcrdma: Error %d posting send for protocol error\n", ret); - ib_dma_unmap_single(xprt->sc_cm_id->device, - sge.addr, PAGE_SIZE, - DMA_FROM_DEVICE); + svc_rdma_unmap_dma(ctxt); svc_rdma_put_context(ctxt, 1); } } diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index a85e866a77f7..0867070bb5ca 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -237,8 +237,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) dprintk("RPC: %s: called\n", __func__); - cancel_delayed_work(&r_xprt->rdma_connect); - flush_scheduled_work(); + cancel_delayed_work_sync(&r_xprt->rdma_connect); xprt_clear_connected(xprt); @@ -251,9 +250,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) xprt_rdma_free_addresses(xprt); - kfree(xprt->slot); - xprt->slot = NULL; - kfree(xprt); + xprt_free(xprt); dprintk("RPC: %s: returning\n", __func__); @@ -285,23 +282,14 @@ xprt_setup_rdma(struct xprt_create *args) return ERR_PTR(-EBADF); } - xprt = kzalloc(sizeof(struct rpcrdma_xprt), GFP_KERNEL); + xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt), + xprt_rdma_slot_table_entries); if (xprt == NULL) { dprintk("RPC: %s: couldn't allocate rpcrdma_xprt\n", __func__); return ERR_PTR(-ENOMEM); } - xprt->max_reqs = xprt_rdma_slot_table_entries; - xprt->slot = kcalloc(xprt->max_reqs, - sizeof(struct rpc_rqst), GFP_KERNEL); - if (xprt->slot == NULL) { - dprintk("RPC: %s: couldn't allocate %d slots\n", - __func__, xprt->max_reqs); - kfree(xprt); - return ERR_PTR(-ENOMEM); - } - /* 60 second timeout, no retries */ xprt->timeout = &xprt_rdma_default_timeout; xprt->bind_timeout = (60U * HZ); @@ -410,8 +398,7 @@ out3: out2: rpcrdma_ia_close(&new_xprt->rx_ia); out1: - kfree(xprt->slot); - kfree(xprt); + xprt_free(xprt); return ERR_PTR(rc); } @@ -460,7 +447,7 @@ xprt_rdma_connect(struct rpc_task *task) } else { schedule_delayed_work(&r_xprt->rdma_connect, 0); if (!RPC_IS_ASYNC(task)) - flush_scheduled_work(); + flush_delayed_work(&r_xprt->rdma_connect); } } |